diff options
34 files changed, 1413 insertions, 650 deletions
diff --git a/Documentation/driver-api/auxiliary_bus.rst b/Documentation/driver-api/auxiliary_bus.rst new file mode 100644 index 000000000000..2312506b0674 --- /dev/null +++ b/Documentation/driver-api/auxiliary_bus.rst @@ -0,0 +1,234 @@ +.. SPDX-License-Identifier: GPL-2.0-only + +============= +Auxiliary Bus +============= + +In some subsystems, the functionality of the core device (PCI/ACPI/other) is +too complex for a single device to be managed by a monolithic driver +(e.g. Sound Open Firmware), multiple devices might implement a common +intersection of functionality (e.g. NICs + RDMA), or a driver may want to +export an interface for another subsystem to drive (e.g. SIOV Physical Function +export Virtual Function management). A split of the functinoality into child- +devices representing sub-domains of functionality makes it possible to +compartmentalize, layer, and distribute domain-specific concerns via a Linux +device-driver model. + +An example for this kind of requirement is the audio subsystem where a single +IP is handling multiple entities such as HDMI, Soundwire, local devices such as +mics/speakers etc. The split for the core's functionality can be arbitrary or +be defined by the DSP firmware topology and include hooks for test/debug. This +allows for the audio core device to be minimal and focused on hardware-specific +control and communication. + +Each auxiliary_device represents a part of its parent functionality. The +generic behavior can be extended and specialized as needed by encapsulating an +auxiliary_device within other domain-specific structures and the use of .ops +callbacks. Devices on the auxiliary bus do not share any structures and the use +of a communication channel with the parent is domain-specific. + +Note that ops are intended as a way to augment instance behavior within a class +of auxiliary devices, it is not the mechanism for exporting common +infrastructure from the parent. Consider EXPORT_SYMBOL_NS() to convey +infrastructure from the parent module to the auxiliary module(s). + + +When Should the Auxiliary Bus Be Used +===================================== + +The auxiliary bus is to be used when a driver and one or more kernel modules, +who share a common header file with the driver, need a mechanism to connect and +provide access to a shared object allocated by the auxiliary_device's +registering driver. The registering driver for the auxiliary_device(s) and the +kernel module(s) registering auxiliary_drivers can be from the same subsystem, +or from multiple subsystems. + +The emphasis here is on a common generic interface that keeps subsystem +customization out of the bus infrastructure. + +One example is a PCI network device that is RDMA-capable and exports a child +device to be driven by an auxiliary_driver in the RDMA subsystem. The PCI +driver allocates and registers an auxiliary_device for each physical +function on the NIC. The RDMA driver registers an auxiliary_driver that claims +each of these auxiliary_devices. This conveys data/ops published by the parent +PCI device/driver to the RDMA auxiliary_driver. + +Another use case is for the PCI device to be split out into multiple sub +functions. For each sub function an auxiliary_device is created. A PCI sub +function driver binds to such devices that creates its own one or more class +devices. A PCI sub function auxiliary device is likely to be contained in a +struct with additional attributes such as user defined sub function number and +optional attributes such as resources and a link to the parent device. These +attributes could be used by systemd/udev; and hence should be initialized +before a driver binds to an auxiliary_device. + +A key requirement for utilizing the auxiliary bus is that there is no +dependency on a physical bus, device, register accesses or regmap support. +These individual devices split from the core cannot live on the platform bus as +they are not physical devices that are controlled by DT/ACPI. The same +argument applies for not using MFD in this scenario as MFD relies on individual +function devices being physical devices. + +Auxiliary Device +================ + +An auxiliary_device represents a part of its parent device's functionality. It +is given a name that, combined with the registering drivers KBUILD_MODNAME, +creates a match_name that is used for driver binding, and an id that combined +with the match_name provide a unique name to register with the bus subsystem. + +Registering an auxiliary_device is a two-step process. First call +auxiliary_device_init(), which checks several aspects of the auxiliary_device +struct and performs a device_initialize(). After this step completes, any +error state must have a call to auxiliary_device_uninit() in its resolution path. +The second step in registering an auxiliary_device is to perform a call to +auxiliary_device_add(), which sets the name of the device and add the device to +the bus. + +Unregistering an auxiliary_device is also a two-step process to mirror the +register process. First call auxiliary_device_delete(), then call +auxiliary_device_uninit(). + +.. code-block:: c + + struct auxiliary_device { + struct device dev; + const char *name; + u32 id; + }; + +If two auxiliary_devices both with a match_name "mod.foo" are registered onto +the bus, they must have unique id values (e.g. "x" and "y") so that the +registered devices names are "mod.foo.x" and "mod.foo.y". If match_name + id +are not unique, then the device_add fails and generates an error message. + +The auxiliary_device.dev.type.release or auxiliary_device.dev.release must be +populated with a non-NULL pointer to successfully register the auxiliary_device. + +The auxiliary_device.dev.parent must also be populated. + +Auxiliary Device Memory Model and Lifespan +------------------------------------------ + +The registering driver is the entity that allocates memory for the +auxiliary_device and register it on the auxiliary bus. It is important to note +that, as opposed to the platform bus, the registering driver is wholly +responsible for the management for the memory used for the driver object. + +A parent object, defined in the shared header file, contains the +auxiliary_device. It also contains a pointer to the shared object(s), which +also is defined in the shared header. Both the parent object and the shared +object(s) are allocated by the registering driver. This layout allows the +auxiliary_driver's registering module to perform a container_of() call to go +from the pointer to the auxiliary_device, that is passed during the call to the +auxiliary_driver's probe function, up to the parent object, and then have +access to the shared object(s). + +The memory for the auxiliary_device is freed only in its release() callback +flow as defined by its registering driver. + +The memory for the shared object(s) must have a lifespan equal to, or greater +than, the lifespan of the memory for the auxiliary_device. The auxiliary_driver +should only consider that this shared object is valid as long as the +auxiliary_device is still registered on the auxiliary bus. It is up to the +registering driver to manage (e.g. free or keep available) the memory for the +shared object beyond the life of the auxiliary_device. + +The registering driver must unregister all auxiliary devices before its own +driver.remove() is completed. + +Auxiliary Drivers +================= + +Auxiliary drivers follow the standard driver model convention, where +discovery/enumeration is handled by the core, and drivers +provide probe() and remove() methods. They support power management +and shutdown notifications using the standard conventions. + +.. code-block:: c + + struct auxiliary_driver { + int (*probe)(struct auxiliary_device *, + const struct auxiliary_device_id *id); + void (*remove)(struct auxiliary_device *); + void (*shutdown)(struct auxiliary_device *); + int (*suspend)(struct auxiliary_device *, pm_message_t); + int (*resume)(struct auxiliary_device *); + struct device_driver driver; + const struct auxiliary_device_id *id_table; + }; + +Auxiliary drivers register themselves with the bus by calling +auxiliary_driver_register(). The id_table contains the match_names of auxiliary +devices that a driver can bind with. + +Example Usage +============= + +Auxiliary devices are created and registered by a subsystem-level core device +that needs to break up its functionality into smaller fragments. One way to +extend the scope of an auxiliary_device is to encapsulate it within a domain- +pecific structure defined by the parent device. This structure contains the +auxiliary_device and any associated shared data/callbacks needed to establish +the connection with the parent. + +An example is: + +.. code-block:: c + + struct foo { + struct auxiliary_device auxdev; + void (*connect)(struct auxiliary_device *auxdev); + void (*disconnect)(struct auxiliary_device *auxdev); + void *data; + }; + +The parent device then registers the auxiliary_device by calling +auxiliary_device_init(), and then auxiliary_device_add(), with the pointer to +the auxdev member of the above structure. The parent provides a name for the +auxiliary_device that, combined with the parent's KBUILD_MODNAME, creates a +match_name that is be used for matching and binding with a driver. + +Whenever an auxiliary_driver is registered, based on the match_name, the +auxiliary_driver's probe() is invoked for the matching devices. The +auxiliary_driver can also be encapsulated inside custom drivers that make the +core device's functionality extensible by adding additional domain-specific ops +as follows: + +.. code-block:: c + + struct my_ops { + void (*send)(struct auxiliary_device *auxdev); + void (*receive)(struct auxiliary_device *auxdev); + }; + + + struct my_driver { + struct auxiliary_driver auxiliary_drv; + const struct my_ops ops; + }; + +An example of this type of usage is: + +.. code-block:: c + + const struct auxiliary_device_id my_auxiliary_id_table[] = { + { .name = "foo_mod.foo_dev" }, + { }, + }; + + const struct my_ops my_custom_ops = { + .send = my_tx, + .receive = my_rx, + }; + + const struct my_driver my_drv = { + .auxiliary_drv = { + .name = "myauxiliarydrv", + .id_table = my_auxiliary_id_table, + .probe = my_probe, + .remove = my_remove, + .shutdown = my_shutdown, + }, + .ops = my_custom_ops, + }; diff --git a/Documentation/driver-api/index.rst b/Documentation/driver-api/index.rst index f357f3eb400c..86759a74b7f1 100644 --- a/Documentation/driver-api/index.rst +++ b/Documentation/driver-api/index.rst @@ -72,6 +72,7 @@ available subsections can be seen below. thermal/index fpga/index acpi/index + auxiliary_bus backlight/lp855x-driver.rst connector console diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig index 8d7001712062..040be48ce046 100644 --- a/drivers/base/Kconfig +++ b/drivers/base/Kconfig @@ -1,6 +1,9 @@ # SPDX-License-Identifier: GPL-2.0 menu "Generic Driver Options" +config AUXILIARY_BUS + bool + config UEVENT_HELPER bool "Support for uevent helper" help diff --git a/drivers/base/Makefile b/drivers/base/Makefile index 41369fc7004f..5e7bf9669a81 100644 --- a/drivers/base/Makefile +++ b/drivers/base/Makefile @@ -7,6 +7,7 @@ obj-y := component.o core.o bus.o dd.o syscore.o \ attribute_container.o transport_class.o \ topology.o container.o property.o cacheinfo.o \ swnode.o +obj-$(CONFIG_AUXILIARY_BUS) += auxiliary.o obj-$(CONFIG_DEVTMPFS) += devtmpfs.o obj-y += power/ obj-$(CONFIG_ISA_BUS_API) += isa.o diff --git a/drivers/base/auxiliary.c b/drivers/base/auxiliary.c new file mode 100644 index 000000000000..f303daadf843 --- /dev/null +++ b/drivers/base/auxiliary.c @@ -0,0 +1,274 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2019-2020 Intel Corporation + * + * Please see Documentation/driver-api/auxiliary_bus.rst for more information. + */ + +#define pr_fmt(fmt) "%s:%s: " fmt, KBUILD_MODNAME, __func__ + +#include <linux/device.h> +#include <linux/init.h> +#include <linux/slab.h> +#include <linux/module.h> +#include <linux/pm_domain.h> +#include <linux/pm_runtime.h> +#include <linux/string.h> +#include <linux/auxiliary_bus.h> + +static const struct auxiliary_device_id *auxiliary_match_id(const struct auxiliary_device_id *id, + const struct auxiliary_device *auxdev) +{ + for (; id->name[0]; id++) { + const char *p = strrchr(dev_name(&auxdev->dev), '.'); + int match_size; + + if (!p) + continue; + match_size = p - dev_name(&auxdev->dev); + + /* use dev_name(&auxdev->dev) prefix before last '.' char to match to */ + if (strlen(id->name) == match_size && + !strncmp(dev_name(&auxdev->dev), id->name, match_size)) + return id; + } + return NULL; +} + +static int auxiliary_match(struct device *dev, struct device_driver *drv) +{ + struct auxiliary_device *auxdev = to_auxiliary_dev(dev); + struct auxiliary_driver *auxdrv = to_auxiliary_drv(drv); + + return !!auxiliary_match_id(auxdrv->id_table, auxdev); +} + +static int auxiliary_uevent(struct device *dev, struct kobj_uevent_env *env) +{ + const char *name, *p; + + name = dev_name(dev); + p = strrchr(name, '.'); + + return add_uevent_var(env, "MODALIAS=%s%.*s", AUXILIARY_MODULE_PREFIX, + (int)(p - name), name); +} + +static const struct dev_pm_ops auxiliary_dev_pm_ops = { + SET_RUNTIME_PM_OPS(pm_generic_runtime_suspend, pm_generic_runtime_resume, NULL) + SET_SYSTEM_SLEEP_PM_OPS(pm_generic_suspend, pm_generic_resume) +}; + +static int auxiliary_bus_probe(struct device *dev) +{ + struct auxiliary_driver *auxdrv = to_auxiliary_drv(dev->driver); + struct auxiliary_device *auxdev = to_auxiliary_dev(dev); + int ret; + + ret = dev_pm_domain_attach(dev, true); + if (ret) { + dev_warn(dev, "Failed to attach to PM Domain : %d\n", ret); + return ret; + } + + ret = auxdrv->probe(auxdev, auxiliary_match_id(auxdrv->id_table, auxdev)); + if (ret) + dev_pm_domain_detach(dev, true); + + return ret; +} + +static int auxiliary_bus_remove(struct device *dev) +{ + struct auxiliary_driver *auxdrv = to_auxiliary_drv(dev->driver); + struct auxiliary_device *auxdev = to_auxiliary_dev(dev); + + if (auxdrv->remove) + auxdrv->remove(auxdev); + dev_pm_domain_detach(dev, true); + + return 0; +} + +static void auxiliary_bus_shutdown(struct device *dev) +{ + struct auxiliary_driver *auxdrv = to_auxiliary_drv(dev->driver); + struct auxiliary_device *auxdev = to_auxiliary_dev(dev); + + if (auxdrv->shutdown) + auxdrv->shutdown(auxdev); +} + +static struct bus_type auxiliary_bus_type = { + .name = "auxiliary", + .probe = auxiliary_bus_probe, + .remove = auxiliary_bus_remove, + .shutdown = auxiliary_bus_shutdown, + .match = auxiliary_match, + .uevent = auxiliary_uevent, + .pm = &auxiliary_dev_pm_ops, +}; + +/** + * auxiliary_device_init - check auxiliary_device and initialize + * @auxdev: auxiliary device struct + * + * This is the first step in the two-step process to register an + * auxiliary_device. + * + * When this function returns an error code, then the device_initialize will + * *not* have been performed, and the caller will be responsible to free any + * memory allocated for the auxiliary_device in the error path directly. + * + * It returns 0 on success. On success, the device_initialize has been + * performed. After this point any error unwinding will need to include a call + * to auxiliary_device_uninit(). In this post-initialize error scenario, a call + * to the device's .release callback will be triggered, and all memory clean-up + * is expected to be handled there. + */ +int auxiliary_device_init(struct auxiliary_device *auxdev) +{ + struct device *dev = &auxdev->dev; + + if (!dev->parent) { + pr_err("auxiliary_device has a NULL dev->parent\n"); + return -EINVAL; + } + + if (!auxdev->name) { + pr_err("auxiliary_device has a NULL name\n"); + return -EINVAL; + } + + dev->bus = &auxiliary_bus_type; + device_initialize(&auxdev->dev); + return 0; +} +EXPORT_SYMBOL_GPL(auxiliary_device_init); + +/** + * __auxiliary_device_add - add an auxiliary bus device + * @auxdev: auxiliary bus device to add to the bus + * @modname: name of the parent device's driver module + * + * This is the second step in the two-step process to register an + * auxiliary_device. + * + * This function must be called after a successful call to + * auxiliary_device_init(), which will perform the device_initialize. This + * means that if this returns an error code, then a call to + * auxiliary_device_uninit() must be performed so that the .release callback + * will be triggered to free the memory associated with the auxiliary_device. + * + * The expectation is that users will call the "auxiliary_device_add" macro so + * that the caller's KBUILD_MODNAME is automatically inserted for the modname + * parameter. Only if a user requires a custom name would this version be + * called directly. + */ +int __auxiliary_device_add(struct auxiliary_device *auxdev, const char *modname) +{ + struct device *dev = &auxdev->dev; + int ret; + + if (!modname) { + dev_err(dev, "auxiliary device modname is NULL\n"); + return -EINVAL; + } + + ret = dev_set_name(dev, "%s.%s.%d", modname, auxdev->name, auxdev->id); + if (ret) { + dev_err(dev, "auxiliary device dev_set_name failed: %d\n", ret); + return ret; + } + + ret = device_add(dev); + if (ret) + dev_err(dev, "adding auxiliary device failed!: %d\n", ret); + + return ret; +} +EXPORT_SYMBOL_GPL(__auxiliary_device_add); + +/** + * auxiliary_find_device - auxiliary device iterator for locating a particular device. + * @start: Device to begin with + * @data: Data to pass to match function + * @match: Callback function to check device + * + * This function returns a reference to a device that is 'found' + * for later use, as determined by the @match callback. + * + * The callback should return 0 if the device doesn't match and non-zero + * if it does. If the callback returns non-zero, this function will + * return to the caller and not iterate over any more devices. + */ +struct auxiliary_device *auxiliary_find_device(struct device *start, + const void *data, + int (*match)(struct device *dev, const void *data)) +{ + struct device *dev; + + dev = bus_find_device(&auxiliary_bus_type, start, data, match); + if (!dev) + return NULL; + + return to_auxiliary_dev(dev); +} +EXPORT_SYMBOL_GPL(auxiliary_find_device); + +/** + * __auxiliary_driver_register - register a driver for auxiliary bus devices + * @auxdrv: auxiliary_driver structure + * @owner: owning module/driver + * @modname: KBUILD_MODNAME for parent driver + */ +int __auxiliary_driver_register(struct auxiliary_driver *auxdrv, + struct module *owner, const char *modname) +{ + if (WARN_ON(!auxdrv->probe) || WARN_ON(!auxdrv->id_table)) + return -EINVAL; + + if (auxdrv->name) + auxdrv->driver.name = kasprintf(GFP_KERNEL, "%s.%s", modname, + auxdrv->name); + else + auxdrv->driver.name = kasprintf(GFP_KERNEL, "%s", modname); + if (!auxdrv->driver.name) + return -ENOMEM; + + auxdrv->driver.owner = owner; + auxdrv->driver.bus = &auxiliary_bus_type; + auxdrv->driver.mod_name = modname; + + return driver_register(&auxdrv->driver); +} +EXPORT_SYMBOL_GPL(__auxiliary_driver_register); + +/** + * auxiliary_driver_unregister - unregister a driver + * @auxdrv: auxiliary_driver structure + */ +void auxiliary_driver_unregister(struct auxiliary_driver *auxdrv) +{ + driver_unregister(&auxdrv->driver); + kfree(auxdrv->driver.name); +} +EXPORT_SYMBOL_GPL(auxiliary_driver_unregister); + +static int __init auxiliary_bus_init(void) +{ + return bus_register(&auxiliary_bus_type); +} + +static void __exit auxiliary_bus_exit(void) +{ + bus_unregister(&auxiliary_bus_type); +} + +module_init(auxiliary_bus_init); +module_exit(auxiliary_bus_exit); + +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("Auxiliary Bus"); +MODULE_AUTHOR("David Ertman <david.m.ertman@intel.com>"); +MODULE_AUTHOR("Kiran Patil <kiran.patil@intel.com>"); diff --git a/drivers/infiniband/hw/mlx5/counters.c b/drivers/infiniband/hw/mlx5/counters.c index 70c8fd67ee2f..084652e2b15a 100644 --- a/drivers/infiniband/hw/mlx5/counters.c +++ b/drivers/infiniband/hw/mlx5/counters.c @@ -138,13 +138,6 @@ static int mlx5_ib_create_counters(struct ib_counters *counters, } -static bool is_mdev_switchdev_mode(const struct mlx5_core_dev *mdev) -{ - return MLX5_ESWITCH_MANAGER(mdev) && - mlx5_ib_eswitch_mode(mdev->priv.eswitch) == - MLX5_ESWITCH_OFFLOADS; -} - static const struct mlx5_ib_counters *get_counters(struct mlx5_ib_dev *dev, u8 port_num) { diff --git a/drivers/infiniband/hw/mlx5/ib_rep.c b/drivers/infiniband/hw/mlx5/ib_rep.c index 5c3d052ac30b..9164cc069ad4 100644 --- a/drivers/infiniband/hw/mlx5/ib_rep.c +++ b/drivers/infiniband/hw/mlx5/ib_rep.c @@ -13,7 +13,7 @@ mlx5_ib_set_vport_rep(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) struct mlx5_ib_dev *ibdev; int vport_index; - ibdev = mlx5_ib_get_uplink_ibdev(dev->priv.eswitch); + ibdev = mlx5_eswitch_uplink_get_proto_dev(dev->priv.eswitch, REP_IB); vport_index = rep->vport_index; ibdev->port[vport_index].rep = rep; @@ -33,6 +33,7 @@ mlx5_ib_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) const struct mlx5_ib_profile *profile; struct mlx5_ib_dev *ibdev; int vport_index; + int ret; if (rep->vport == MLX5_VPORT_UPLINK) profile = &raw_eth_profile; @@ -46,8 +47,8 @@ mlx5_ib_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) ibdev->port = kcalloc(num_ports, sizeof(*ibdev->port), GFP_KERNEL); if (!ibdev->port) { - ib_dealloc_device(&ibdev->ib_dev); - return -ENOMEM; + ret = -ENOMEM; + goto fail_port; } ibdev->is_rep = true; @@ -58,12 +59,24 @@ mlx5_ib_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) ibdev->mdev = dev; ibdev->num_ports = num_ports; - if (!__mlx5_ib_add(ibdev, profile)) - return -EINVAL; + ret = __mlx5_ib_add(ibdev, profile); + if (ret) + goto fail_add; rep->rep_data[REP_IB].priv = ibdev; return 0; + +fail_add: + kfree(ibdev->port); +fail_port: + ib_dealloc_device(&ibdev->ib_dev); + return ret; +} + +static void *mlx5_ib_rep_to_dev(struct mlx5_eswitch_rep *rep) +{ + return rep->rep_data[REP_IB].priv; } static void @@ -83,59 +96,18 @@ mlx5_ib_vport_rep_unload(struct mlx5_eswitch_rep *rep) __mlx5_ib_remove(dev, dev->profile, MLX5_IB_STAGE_MAX); } -static void *mlx5_ib_vport_get_proto_dev(struct mlx5_eswitch_rep *rep) -{ - return mlx5_ib_rep_to_dev(rep); -} - static const struct mlx5_eswitch_rep_ops rep_ops = { .load = mlx5_ib_vport_rep_load, .unload = mlx5_ib_vport_rep_unload, - .get_proto_dev = mlx5_ib_vport_get_proto_dev, + .get_proto_dev = mlx5_ib_rep_to_dev, }; -void mlx5_ib_register_vport_reps(struct mlx5_core_dev *mdev) -{ - struct mlx5_eswitch *esw = mdev->priv.eswitch; - - mlx5_eswitch_register_vport_reps(esw, &rep_ops, REP_IB); -} - -void mlx5_ib_unregister_vport_reps(struct mlx5_core_dev *mdev) -{ - struct mlx5_eswitch *esw = mdev->priv.eswitch; - - mlx5_eswitch_unregister_vport_reps(esw, REP_IB); -} - -u8 mlx5_ib_eswitch_mode(struct mlx5_eswitch *esw) -{ - return mlx5_eswitch_mode(esw); -} - -struct mlx5_ib_dev *mlx5_ib_get_rep_ibdev(struct mlx5_eswitch *esw, - u16 vport_num) -{ - return mlx5_eswitch_get_proto_dev(esw, vport_num, REP_IB); -} - struct net_device *mlx5_ib_get_rep_netdev(struct mlx5_eswitch *esw, u16 vport_num) { return mlx5_eswitch_get_proto_dev(esw, vport_num, REP_ETH); } -struct mlx5_ib_dev *mlx5_ib_get_uplink_ibdev(struct mlx5_eswitch *esw) -{ - return mlx5_eswitch_uplink_get_proto_dev(esw, REP_IB); -} - -struct mlx5_eswitch_rep *mlx5_ib_vport_rep(struct mlx5_eswitch *esw, - u16 vport_num) -{ - return mlx5_eswitch_vport_rep(esw, vport_num); -} - struct mlx5_flow_handle *create_flow_rule_vport_sq(struct mlx5_ib_dev *dev, struct mlx5_ib_sq *sq, u16 port) @@ -154,3 +126,49 @@ struct mlx5_flow_handle *create_flow_rule_vport_sq(struct mlx5_ib_dev *dev, return mlx5_eswitch_add_send_to_vport_rule(esw, rep->vport, sq->base.mqp.qpn); } + +static int mlx5r_rep_probe(struct auxiliary_device *adev, + const struct auxiliary_device_id *id) +{ + struct mlx5_adev *idev = container_of(adev, struct mlx5_adev, adev); + struct mlx5_core_dev *mdev = idev->mdev; + struct mlx5_eswitch *esw; + + esw = mdev->priv.eswitch; + mlx5_eswitch_register_vport_reps(esw, &rep_ops, REP_IB); + return 0; +} + +static void mlx5r_rep_remove(struct auxiliary_device *adev) +{ + struct mlx5_adev *idev = container_of(adev, struct mlx5_adev, adev); + struct mlx5_core_dev *mdev = idev->mdev; + struct mlx5_eswitch *esw; + + esw = mdev->priv.eswitch; + mlx5_eswitch_unregister_vport_reps(esw, REP_IB); +} + +static const struct auxiliary_device_id mlx5r_rep_id_table[] = { + { .name = MLX5_ADEV_NAME ".rdma-rep", }, + {}, +}; + +MODULE_DEVICE_TABLE(auxiliary, mlx5r_rep_id_table); + +static struct auxiliary_driver mlx5r_rep_driver = { + .name = "rep", + .probe = mlx5r_rep_probe, + .remove = mlx5r_rep_remove, + .id_table = mlx5r_rep_id_table, +}; + +int mlx5r_rep_init(void) +{ + return auxiliary_driver_register(&mlx5r_rep_driver); +} + +void mlx5r_rep_cleanup(void) +{ + auxiliary_driver_unregister(&mlx5r_rep_driver); +} diff --git a/drivers/infiniband/hw/mlx5/ib_rep.h b/drivers/infiniband/hw/mlx5/ib_rep.h index 5b30d3fa8f8d..ce1dcb105dbd 100644 --- a/drivers/infiniband/hw/mlx5/ib_rep.h +++ b/drivers/infiniband/hw/mlx5/ib_rep.h @@ -12,47 +12,16 @@ extern const struct mlx5_ib_profile raw_eth_profile; #ifdef CONFIG_MLX5_ESWITCH -u8 mlx5_ib_eswitch_mode(struct mlx5_eswitch *esw); -struct mlx5_ib_dev *mlx5_ib_get_rep_ibdev(struct mlx5_eswitch *esw, - u16 vport_num); -struct mlx5_ib_dev *mlx5_ib_get_uplink_ibdev(struct mlx5_eswitch *esw); -struct mlx5_eswitch_rep *mlx5_ib_vport_rep(struct mlx5_eswitch *esw, - u16 vport_num); -void mlx5_ib_register_vport_reps(struct mlx5_core_dev *mdev); -void mlx5_ib_unregister_vport_reps(struct mlx5_core_dev *mdev); +int mlx5r_rep_init(void); +void mlx5r_rep_cleanup(void); struct mlx5_flow_handle *create_flow_rule_vport_sq(struct mlx5_ib_dev *dev, struct mlx5_ib_sq *sq, u16 port); struct net_device *mlx5_ib_get_rep_netdev(struct mlx5_eswitch *esw, u16 vport_num); #else /* CONFIG_MLX5_ESWITCH */ -static inline u8 mlx5_ib_eswitch_mode(struct mlx5_eswitch *esw) -{ - return MLX5_ESWITCH_NONE; -} - -static inline -struct mlx5_ib_dev *mlx5_ib_get_rep_ibdev(struct mlx5_eswitch *esw, - u16 vport_num) -{ - return NULL; -} - -static inline -struct mlx5_ib_dev *mlx5_ib_get_uplink_ibdev(struct mlx5_eswitch *esw) -{ - return NULL; -} - -static inline -struct mlx5_eswitch_rep *mlx5_ib_vport_rep(struct mlx5_eswitch *esw, - u16 vport_num) -{ - return NULL; -} - -static inline void mlx5_ib_register_vport_reps(struct mlx5_core_dev *mdev) {} -static inline void mlx5_ib_unregister_vport_reps(struct mlx5_core_dev *mdev) {} +static inline int mlx5r_rep_init(void) { return 0; } +static inline void mlx5r_rep_cleanup(void) {} static inline struct mlx5_flow_handle *create_flow_rule_vport_sq(struct mlx5_ib_dev *dev, struct mlx5_ib_sq *sq, @@ -68,10 +37,4 @@ struct net_device *mlx5_ib_get_rep_netdev(struct mlx5_eswitch *esw, return NULL; } #endif - -static inline -struct mlx5_ib_dev *mlx5_ib_rep_to_dev(struct mlx5_eswitch_rep *rep) -{ - return rep->rep_data[REP_IB].priv; -} #endif /* __MLX5_IB_REP_H__ */ diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 246e3cbe0b2c..55545f1286e5 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -4593,8 +4593,8 @@ void __mlx5_ib_remove(struct mlx5_ib_dev *dev, ib_dealloc_device(&dev->ib_dev); } -void *__mlx5_ib_add(struct mlx5_ib_dev *dev, - const struct mlx5_ib_profile *profile) +int __mlx5_ib_add(struct mlx5_ib_dev *dev, + const struct mlx5_ib_profile *profile) { int err; int i; @@ -4610,13 +4610,16 @@ void *__mlx5_ib_add(struct mlx5_ib_dev *dev, } dev->ib_active = true; - - return dev; + return 0; err_out: - __mlx5_ib_remove(dev, profile, i); - - return NULL; + /* Clean up stages which were initialized */ + while (i) { + i--; + if (profile->stage[i].cleanup) + profile->stage[i].cleanup(dev); + } + return -ENOMEM; } static const struct mlx5_ib_profile pf_profile = { @@ -4739,8 +4742,11 @@ const struct mlx5_ib_profile raw_eth_profile = { NULL), }; -static void *mlx5_ib_add_slave_port(struct mlx5_core_dev *mdev) +static int mlx5r_mp_probe(struct auxiliary_device *adev, + const struct auxiliary_device_id *id) { + struct mlx5_adev *idev = container_of(adev, struct mlx5_adev, adev); + struct mlx5_core_dev *mdev = idev->mdev; struct mlx5_ib_multiport_info *mpi; struct mlx5_ib_dev *dev; bool bound = false; @@ -4748,15 +4754,14 @@ static void *mlx5_ib_add_slave_port(struct mlx5_core_dev *mdev) mpi = kzalloc(sizeof(*mpi), GFP_KERNEL); if (!mpi) - return NULL; + return -ENOMEM; mpi->mdev = mdev; - err = mlx5_query_nic_vport_system_image_guid(mdev, &mpi->sys_image_guid); if (err) { kfree(mpi); - return NULL; + return err; } mutex_lock(&mlx5_ib_multiport_mutex); @@ -4777,40 +4782,46 @@ static void *mlx5_ib_add_slave_port(struct mlx5_core_dev *mdev) } mutex_unlock(&mlx5_ib_multiport_mutex); - return mpi; + dev_set_drvdata(&adev->dev, mpi); + return 0; +} + +static void mlx5r_mp_remove(struct auxiliary_device *adev) +{ + struct mlx5_ib_multiport_info *mpi; + + mpi = dev_get_drvdata(&adev->dev); + mutex_lock(&mlx5_ib_multiport_mutex); + if (mpi->ibdev) + mlx5_ib_unbind_slave_port(mpi->ibdev, mpi); + list_del(&mpi->list); + mutex_unlock(&mlx5_ib_multiport_mutex); + kfree(mpi); } -static void *mlx5_ib_add(struct mlx5_core_dev *mdev) +static int mlx5r_probe(struct auxiliary_device *adev, + const struct auxiliary_device_id *id) { + struct mlx5_adev *idev = container_of(adev, struct mlx5_adev, adev); + struct mlx5_core_dev *mdev = idev->mdev; const struct mlx5_ib_profile *profile; + int port_type_cap, num_ports, ret; enum rdma_link_layer ll; struct mlx5_ib_dev *dev; - int port_type_cap; - int num_ports; - - if (MLX5_ESWITCH_MANAGER(mdev) && - mlx5_ib_eswitch_mode(mdev->priv.eswitch) == MLX5_ESWITCH_OFFLOADS) { - if (!mlx5_core_mp_enabled(mdev)) - mlx5_ib_register_vport_reps(mdev); - return mdev; - } port_type_cap = MLX5_CAP_GEN(mdev, port_type); ll = mlx5_port_type_cap_to_rdma_ll(port_type_cap); - if (mlx5_core_is_mp_slave(mdev) && ll == IB_LINK_LAYER_ETHERNET) - return mlx5_ib_add_slave_port(mdev); - num_ports = max(MLX5_CAP_GEN(mdev, num_ports), MLX5_CAP_GEN(mdev, num_vhca_ports)); dev = ib_alloc_device(mlx5_ib_dev, ib_dev); if (!dev) - return NULL; + return -ENOMEM; dev->port = kcalloc(num_ports, sizeof(*dev->port), GFP_KERNEL); if (!dev->port) { ib_dealloc_device(&dev->ib_dev); - return NULL; + return -ENOMEM; } dev->mdev = mdev; @@ -4821,38 +4832,50 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev) else profile = &pf_profile; - return __mlx5_ib_add(dev, profile); + ret = __mlx5_ib_add(dev, profile); + if (ret) { + kfree(dev->port); + ib_dealloc_device(&dev->ib_dev); + return ret; + } + + dev_set_drvdata(&adev->dev, dev); + return 0; } -static void mlx5_ib_remove(struct mlx5_core_dev *mdev, void *context) +static void mlx5r_remove(struct auxiliary_device *adev) { - struct mlx5_ib_multiport_info *mpi; struct mlx5_ib_dev *dev; - if (MLX5_ESWITCH_MANAGER(mdev) && context == mdev) { - mlx5_ib_unregister_vport_reps(mdev); - return; - } - - if (mlx5_core_is_mp_slave(mdev)) { - mpi = context; - mutex_lock(&mlx5_ib_multiport_mutex); - if (mpi->ibdev) - mlx5_ib_unbind_slave_port(mpi->ibdev, mpi); - list_del(&mpi->list); - mutex_unlock(&mlx5_ib_multiport_mutex); - kfree(mpi); - return; - } - - dev = context; + dev = dev_get_drvdata(&adev->dev); __mlx5_ib_remove(dev, dev->profile, MLX5_IB_STAGE_MAX); } -static struct mlx5_interface mlx5_ib_interface = { - .add = mlx5_ib_add, - .remove = mlx5_ib_remove, - .protocol = MLX5_INTERFACE_PROTOCOL_IB, +static const struct auxiliary_device_id mlx5r_mp_id_table[] = { + { .name = MLX5_ADEV_NAME ".multiport", }, + {}, +}; + +static const struct auxiliary_device_id mlx5r_id_table[] = { + { .name = MLX5_ADEV_NAME ".rdma", }, + {}, +}; + +MODULE_DEVICE_TABLE(auxiliary, mlx5r_mp_id_table); +MODULE_DEVICE_TABLE(auxiliary, mlx5r_id_table); + +static struct auxiliary_driver mlx5r_mp_driver = { + .name = "multiport", + .probe = mlx5r_mp_probe, + .remove = mlx5r_mp_remove, + .id_table = mlx5r_mp_id_table, +}; + +static struct auxiliary_driver mlx5r_driver = { + .name = "rdma", + .probe = mlx5r_probe, + .remove = mlx5r_remove, + .id_table = mlx5r_id_table, }; unsigned long mlx5_ib_get_xlt_emergency_page(void) @@ -4868,7 +4891,7 @@ void mlx5_ib_put_xlt_emergency_page(void) static int __init mlx5_ib_init(void) { - int err; + int ret; xlt_emergency_page = __get_free_page(GFP_KERNEL); if (!xlt_emergency_page) @@ -4883,15 +4906,33 @@ static int __init mlx5_ib_init(void) } mlx5_ib_odp_init(); + ret = mlx5r_rep_init(); + if (ret) + goto rep_err; + ret = auxiliary_driver_register(&mlx5r_mp_driver); + if (ret) + goto mp_err; + ret = auxiliary_driver_register(&mlx5r_driver); + if (ret) + goto drv_err; + return 0; - err = mlx5_register_interface(&mlx5_ib_interface); - - return err; +drv_err: + auxiliary_driver_unregister(&mlx5r_mp_driver); +mp_err: + mlx5r_rep_cleanup(); +rep_err: + destroy_workqueue(mlx5_ib_event_wq); + free_page((unsigned long)xlt_emergency_page); + return ret; } static void __exit mlx5_ib_cleanup(void) { - mlx5_unregister_interface(&mlx5_ib_interface); + auxiliary_driver_unregister(&mlx5r_driver); + auxiliary_driver_unregister(&mlx5r_mp_driver); + mlx5r_rep_cleanup(); + destroy_workqueue(mlx5_ib_event_wq); mutex_destroy(&xlt_emergency_page_mutex); free_page(xlt_emergency_page); diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index b1f2b34e5955..ea5243815cf6 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -1317,8 +1317,8 @@ extern const struct mmu_interval_notifier_ops mlx5_mn_ops; void __mlx5_ib_remove(struct mlx5_ib_dev *dev, const struct mlx5_ib_profile *profile, int stage); -void *__mlx5_ib_add(struct mlx5_ib_dev *dev, - const struct mlx5_ib_profile *profile); +int __mlx5_ib_add(struct mlx5_ib_dev *dev, + const struct mlx5_ib_profile *profile); int mlx5_ib_get_vf_config(struct ib_device *device, int vf, u8 port, struct ifla_vf_info *info); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig index 99f1ec3b2575..485478979b1a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig +++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig @@ -6,6 +6,7 @@ config MLX5_CORE tristate "Mellanox 5th generation network adapters (ConnectX series) core driver" depends on PCI + select AUXILIARY_BUS select NET_DEVLINK depends on VXLAN || !VXLAN depends on MLXFW || !MLXFW diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c index 1972ddd12704..b051417ede67 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c @@ -31,313 +31,484 @@ */ #include <linux/mlx5/driver.h> +#include <linux/mlx5/eswitch.h> +#include <linux/mlx5/mlx5_ifc_vdpa.h> #include "mlx5_core.h" -static LIST_HEAD(intf_list); -static LIST_HEAD(mlx5_dev_list); /* intf dev list mutex */ static DEFINE_MUTEX(mlx5_intf_mutex); +static DEFINE_IDA(mlx5_adev_ida); -struct mlx5_device_context { - struct list_head list; - struct mlx5_interface *intf; - void *context; - unsigned long state; -}; +static bool is_eth_rep_supported(struct mlx5_core_dev *dev) +{ + if (!IS_ENABLED(CONFIG_MLX5_ESWITCH)) + return false; -enum { - MLX5_INTERFACE_ADDED, - MLX5_INTERFACE_ATTACHED, -}; + if (!MLX5_ESWITCH_MANAGER(dev)) + return false; + if (!is_mdev_switchdev_mode(dev)) + return false; -void mlx5_add_device(struct mlx5_interface *intf, struct mlx5_priv *priv) + return true; +} + +static bool is_eth_supported(struct mlx5_core_dev *dev) { - struct mlx5_device_context *dev_ctx; - struct mlx5_core_dev *dev = container_of(priv, struct mlx5_core_dev, priv); + if (!IS_ENABLED(CONFIG_MLX5_CORE_EN)) + return false; - if (!mlx5_lag_intf_add(intf, priv)) - return; + if (is_eth_rep_supported(dev)) + return false; - dev_ctx = kzalloc(sizeof(*dev_ctx), GFP_KERNEL); - if (!dev_ctx) - return; + if (MLX5_CAP_GEN(dev, port_type) != MLX5_CAP_PORT_TYPE_ETH) + return false; - dev_ctx->intf = intf; + if (!MLX5_CAP_GEN(dev, eth_net_offloads)) { + mlx5_core_warn(dev, "Missing eth_net_offloads capability\n"); + return false; + } - dev_ctx->context = intf->add(dev); - if (dev_ctx->context) { - set_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state); - if (intf->attach) - set_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state); + if (!MLX5_CAP_GEN(dev, nic_flow_table)) { + mlx5_core_warn(dev, "Missing nic_flow_table capability\n"); + return false; + } - spin_lock_irq(&priv->ctx_lock); - list_add_tail(&dev_ctx->list, &priv->ctx_list); - spin_unlock_irq(&priv->ctx_lock); + if (!MLX5_CAP_ETH(dev, csum_cap)) { + mlx5_core_warn(dev, "Missing csum_cap capability\n"); + return false; } - if (!dev_ctx->context) - kfree(dev_ctx); + if (!MLX5_CAP_ETH(dev, max_lso_cap)) { + mlx5_core_warn(dev, "Missing max_lso_cap capability\n"); + return false; + } + + if (!MLX5_CAP_ETH(dev, vlan_cap)) { + mlx5_core_warn(dev, "Missing vlan_cap capability\n"); + return false; + } + + if (!MLX5_CAP_ETH(dev, rss_ind_tbl_cap)) { + mlx5_core_warn(dev, "Missing rss_ind_tbl_cap capability\n"); + return false; + } + + if (MLX5_CAP_FLOWTABLE(dev, + flow_table_properties_nic_receive.max_ft_level) < 3) { + mlx5_core_warn(dev, "max_ft_level < 3\n"); + return false; + } + + if (!MLX5_CAP_ETH(dev, self_lb_en_modifiable)) + mlx5_core_warn(dev, "Self loop back prevention is not supported\n"); + if (!MLX5_CAP_GEN(dev, cq_moderation)) + mlx5_core_warn(dev, "CQ moderation is not supported\n"); + + return true; } -static struct mlx5_device_context *mlx5_get_device(struct mlx5_interface *intf, - struct mlx5_priv *priv) +static bool is_vnet_supported(struct mlx5_core_dev *dev) { - struct mlx5_device_context *dev_ctx; + if (!IS_ENABLED(CONFIG_MLX5_VDPA_NET)) + return false; - list_for_each_entry(dev_ctx, &priv->ctx_list, list) - if (dev_ctx->intf == intf) - return dev_ctx; - return NULL; + if (mlx5_core_is_pf(dev)) + return false; + + if (!(MLX5_CAP_GEN_64(dev, general_obj_types) & + MLX5_GENERAL_OBJ_TYPES_CAP_VIRTIO_NET_Q)) + return false; + + if (!(MLX5_CAP_DEV_VDPA_EMULATION(dev, event_mode) & + MLX5_VIRTIO_Q_EVENT_MODE_QP_MODE)) + return false; + + if (!MLX5_CAP_DEV_VDPA_EMULATION(dev, eth_frame_offload_type)) + return false; + + return true; } -void mlx5_remove_device(struct mlx5_interface *intf, struct mlx5_priv *priv) +static bool is_ib_rep_supported(struct mlx5_core_dev *dev) { - struct mlx5_device_context *dev_ctx; - struct mlx5_core_dev *dev = container_of(priv, struct mlx5_core_dev, priv); + if (!IS_ENABLED(CONFIG_MLX5_INFINIBAND)) + return false; - dev_ctx = mlx5_get_device(intf, priv); - if (!dev_ctx) - return; + if (dev->priv.flags & MLX5_PRIV_FLAGS_DISABLE_IB_ADEV) + return false; - spin_lock_irq(&priv->ctx_lock); - list_del(&dev_ctx->list); - spin_unlock_irq(&priv->ctx_lock); + if (!is_eth_rep_supported(dev)) + return false; - if (test_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state)) - intf->remove(dev, dev_ctx->context); + if (!MLX5_ESWITCH_MANAGER(dev)) + return false; - kfree(dev_ctx); + if (!is_mdev_switchdev_mode(dev)) + return false; + + if (mlx5_core_mp_enabled(dev)) + return false; + + return true; } -static void mlx5_attach_interface(struct mlx5_interface *intf, struct mlx5_priv *priv) +static bool is_mp_supported(struct mlx5_core_dev *dev) { - struct mlx5_device_context *dev_ctx; - struct mlx5_core_dev *dev = container_of(priv, struct mlx5_core_dev, priv); - - dev_ctx = mlx5_get_device(intf, priv); - if (!dev_ctx) - return; - - if (intf->attach) { - if (test_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state)) - return; - if (intf->attach(dev, dev_ctx->context)) - return; - set_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state); - } else { - if (test_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state)) - return; - dev_ctx->context = intf->add(dev); - if (!dev_ctx->context) - return; - set_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state); - } + if (!IS_ENABLED(CONFIG_MLX5_INFINIBAND)) + return false; + + if (dev->priv.flags & MLX5_PRIV_FLAGS_DISABLE_IB_ADEV) + return false; + + if (is_ib_rep_supported(dev)) + return false; + + if (MLX5_CAP_GEN(dev, port_type) != MLX5_CAP_PORT_TYPE_ETH) + return false; + + if (!mlx5_core_is_mp_slave(dev)) + return false; + + return true; } -void mlx5_attach_device(struct mlx5_core_dev *dev) +static bool is_ib_supported(struct mlx5_core_dev *dev) { - struct mlx5_priv *priv = &dev->priv; - struct mlx5_interface *intf; + if (!IS_ENABLED(CONFIG_MLX5_INFINIBAND)) + return false; - mutex_lock(&mlx5_intf_mutex); - list_for_each_entry(intf, &intf_list, list) - mlx5_attach_interface(intf, priv); - mutex_unlock(&mlx5_intf_mutex); + if (dev->priv.flags & MLX5_PRIV_FLAGS_DISABLE_IB_ADEV) + return false; + + if (is_ib_rep_supported(dev)) + return false; + + if (is_mp_supported(dev)) + return false; + + return true; +} + +enum { + MLX5_INTERFACE_PROTOCOL_ETH_REP, + MLX5_INTERFACE_PROTOCOL_ETH, + + MLX5_INTERFACE_PROTOCOL_IB_REP, + MLX5_INTERFACE_PROTOCOL_MPIB, + MLX5_INTERFACE_PROTOCOL_IB, + + MLX5_INTERFACE_PROTOCOL_VNET, +}; + +static const struct mlx5_adev_device { + const char *suffix; + bool (*is_supported)(struct mlx5_core_dev *dev); +} mlx5_adev_devices[] = { + [MLX5_INTERFACE_PROTOCOL_VNET] = { .suffix = "vnet", + .is_supported = &is_vnet_supported }, + [MLX5_INTERFACE_PROTOCOL_IB] = { .suffix = "rdma", + .is_supported = &is_ib_supported }, + [MLX5_INTERFACE_PROTOCOL_ETH] = { .suffix = "eth", + .is_supported = &is_eth_supported }, + [MLX5_INTERFACE_PROTOCOL_ETH_REP] = { .suffix = "eth-rep", + .is_supported = &is_eth_rep_supported }, + [MLX5_INTERFACE_PROTOCOL_IB_REP] = { .suffix = "rdma-rep", + .is_supported = &is_ib_rep_supported }, + [MLX5_INTERFACE_PROTOCOL_MPIB] = { .suffix = "multiport", + .is_supported = &is_mp_supported }, +}; + +int mlx5_adev_idx_alloc(void) +{ + return ida_alloc(&mlx5_adev_ida, GFP_KERNEL); } -static void mlx5_detach_interface(struct mlx5_interface *intf, struct mlx5_priv *priv) +void mlx5_adev_idx_free(int idx) { - struct mlx5_device_context *dev_ctx; - struct mlx5_core_dev *dev = container_of(priv, struct mlx5_core_dev, priv); - - dev_ctx = mlx5_get_device(intf, priv); - if (!dev_ctx) - return; - - if (intf->detach) { - if (!test_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state)) - return; - intf->detach(dev, dev_ctx->context); - clear_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state); - } else { - if (!test_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state)) - return; - intf->remove(dev, dev_ctx->context); - clear_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state); - } + ida_free(&mlx5_adev_ida, idx); } -void mlx5_detach_device(struct mlx5_core_dev *dev) +int mlx5_adev_init(struct mlx5_core_dev *dev) { struct mlx5_priv *priv = &dev->priv; - struct mlx5_interface *intf; - mutex_lock(&mlx5_intf_mutex); - list_for_each_entry(intf, &intf_list, list) - mlx5_detach_interface(intf, priv); - mutex_unlock(&mlx5_intf_mutex); + priv->adev = kcalloc(ARRAY_SIZE(mlx5_adev_devices), + sizeof(struct mlx5_adev *), GFP_KERNEL); + if (!priv->adev) + return -ENOMEM; + + return 0; } -bool mlx5_device_registered(struct mlx5_core_dev *dev) +void mlx5_adev_cleanup(struct mlx5_core_dev *dev) { - struct mlx5_priv *priv; - bool found = false; + struct mlx5_priv *priv = &dev->priv; - mutex_lock(&mlx5_intf_mutex); - list_for_each_entry(priv, &mlx5_dev_list, dev_list) - if (priv == &dev->priv) - found = true; - mutex_unlock(&mlx5_intf_mutex); + kfree(priv->adev); +} + +static void adev_release(struct device *dev) +{ + struct mlx5_adev *mlx5_adev = + container_of(dev, struct mlx5_adev, adev.dev); + struct mlx5_priv *priv = &mlx5_adev->mdev->priv; + int idx = mlx5_adev->idx; - return found; + kfree(mlx5_adev); + priv->adev[idx] = NULL; } -void mlx5_register_device(struct mlx5_core_dev *dev) +static struct mlx5_adev *add_adev(struct mlx5_core_dev *dev, int idx) +{ + const char *suffix = mlx5_adev_devices[idx].suffix; + struct auxiliary_device *adev; + struct mlx5_adev *madev; + int ret; + + madev = kzalloc(sizeof(*madev), GFP_KERNEL); + if (!madev) + return ERR_PTR(-ENOMEM); + + adev = &madev->adev; + adev->id = dev->priv.adev_idx; + adev->name = suffix; + adev->dev.parent = dev->device; + adev->dev.release = adev_release; + madev->mdev = dev; + madev->idx = idx; + + ret = auxiliary_device_init(adev); + if (ret) { + kfree(madev); + return ERR_PTR(ret); + } + + ret = auxiliary_device_add(adev); + if (ret) { + auxiliary_device_uninit(adev); + return ERR_PTR(ret); + } + return madev; +} + +static void del_adev(struct auxiliary_device *adev) +{ + auxiliary_device_delete(adev); + auxiliary_device_uninit(adev); +} + +int mlx5_attach_device(struct mlx5_core_dev *dev) { struct mlx5_priv *priv = &dev->priv; - struct mlx5_interface *intf; + struct auxiliary_device *adev; + struct auxiliary_driver *adrv; + int ret = 0, i; mutex_lock(&mlx5_intf_mutex); - list_add_tail(&priv->dev_list, &mlx5_dev_list); - list_for_each_entry(intf, &intf_list, list) - mlx5_add_device(intf, priv); + for (i = 0; i < ARRAY_SIZE(mlx5_adev_devices); i++) { + if (!priv->adev[i]) { + bool is_supported = false; + + if (mlx5_adev_devices[i].is_supported) + is_supported = mlx5_adev_devices[i].is_supported(dev); + + if (!is_supported) + continue; + + priv->adev[i] = add_adev(dev, i); + if (IS_ERR(priv->adev[i])) { + ret = PTR_ERR(priv->adev[i]); + priv->adev[i] = NULL; + } + } else { + adev = &priv->adev[i]->adev; + adrv = to_auxiliary_drv(adev->dev.driver); + + if (adrv->resume) + ret = adrv->resume(adev); + } + if (ret) { + mlx5_core_warn(dev, "Device[%d] (%s) failed to load\n", + i, mlx5_adev_devices[i].suffix); + + break; + } + } mutex_unlock(&mlx5_intf_mutex); + return ret; } -void mlx5_unregister_device(struct mlx5_core_dev *dev) +void mlx5_detach_device(struct mlx5_core_dev *dev) { struct mlx5_priv *priv = &dev->priv; - struct mlx5_interface *intf; + struct auxiliary_device *adev; + struct auxiliary_driver *adrv; + pm_message_t pm = {}; + int i; mutex_lock(&mlx5_intf_mutex); - list_for_each_entry_reverse(intf, &intf_list, list) - mlx5_remove_device(intf, priv); - list_del(&priv->dev_list); + for (i = ARRAY_SIZE(mlx5_adev_devices) - 1; i >= 0; i--) { + if (!priv->adev[i]) + continue; + + adev = &priv->adev[i]->adev; + adrv = to_auxiliary_drv(adev->dev.driver); + + if (adrv->suspend) { + adrv->suspend(adev, pm); + continue; + } + + del_adev(&priv->adev[i]->adev); + priv->adev[i] = NULL; + } mutex_unlock(&mlx5_intf_mutex); } -int mlx5_register_interface(struct mlx5_interface *intf) +int mlx5_register_device(struct mlx5_core_dev *dev) { - struct mlx5_priv *priv; - - if (!intf->add || !intf->remove) - return -EINVAL; + int ret; mutex_lock(&mlx5_intf_mutex); - list_add_tail(&intf->list, &intf_list); - list_for_each_entry(priv, &mlx5_dev_list, dev_list) - mlx5_add_device(intf, priv); + dev->priv.flags &= ~MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV; + ret = mlx5_rescan_drivers_locked(dev); mutex_unlock(&mlx5_intf_mutex); + if (ret) + mlx5_unregister_device(dev); - return 0; + return ret; } -EXPORT_SYMBOL(mlx5_register_interface); -void mlx5_unregister_interface(struct mlx5_interface *intf) +void mlx5_unregister_device(struct mlx5_core_dev *dev) { - struct mlx5_priv *priv; - mutex_lock(&mlx5_intf_mutex); - list_for_each_entry(priv, &mlx5_dev_list, dev_list) - mlx5_remove_device(intf, priv); - list_del(&intf->list); + dev->priv.flags |= MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV; + mlx5_rescan_drivers_locked(dev); mutex_unlock(&mlx5_intf_mutex); } -EXPORT_SYMBOL(mlx5_unregister_interface); -/* Must be called with intf_mutex held */ -static bool mlx5_has_added_dev_by_protocol(struct mlx5_core_dev *mdev, int protocol) +static int add_drivers(struct mlx5_core_dev *dev) { - struct mlx5_device_context *dev_ctx; - struct mlx5_interface *intf; - bool found = false; - - list_for_each_entry(intf, &intf_list, list) { - if (intf->protocol == protocol) { - dev_ctx = mlx5_get_device(intf, &mdev->priv); - if (dev_ctx && test_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state)) - found = true; - break; + struct mlx5_priv *priv = &dev->priv; + int i, ret = 0; + + for (i = 0; i < ARRAY_SIZE(mlx5_adev_devices); i++) { + bool is_supported = false; + + if (priv->adev[i]) + continue; + + if (mlx5_adev_devices[i].is_supported) + is_supported = mlx5_adev_devices[i].is_supported(dev); + + if (!is_supported) + continue; + + priv->adev[i] = add_adev(dev, i); + if (IS_ERR(priv->adev[i])) { + mlx5_core_warn(dev, "Device[%d] (%s) failed to load\n", + i, mlx5_adev_devices[i].suffix); + /* We continue to rescan drivers and leave to the caller + * to make decision if to release everything or continue. + */ + ret = PTR_ERR(priv->adev[i]); + priv->adev[i] = NULL; } } - - return found; + return ret; } -void mlx5_reload_interface(struct mlx5_core_dev *mdev, int protocol) +static void delete_drivers(struct mlx5_core_dev *dev) { - mutex_lock(&mlx5_intf_mutex); - if (mlx5_has_added_dev_by_protocol(mdev, protocol)) { - mlx5_remove_dev_by_protocol(mdev, protocol); - mlx5_add_dev_by_protocol(mdev, protocol); + struct mlx5_priv *priv = &dev->priv; + bool delete_all; + int i; + + delete_all = priv->flags & MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV; + + for (i = ARRAY_SIZE(mlx5_adev_devices) - 1; i >= 0; i--) { + bool is_supported = false; + + if (!priv->adev[i]) + continue; + + if (mlx5_adev_devices[i].is_supported && !delete_all) + is_supported = mlx5_adev_devices[i].is_supported(dev); + + if (is_supported) + continue; + + del_adev(&priv->adev[i]->adev); + priv->adev[i] = NULL; } - mutex_unlock(&mlx5_intf_mutex); } -/* Must be called with intf_mutex held */ -void mlx5_add_dev_by_protocol(struct mlx5_core_dev *dev, int protocol) +/* This function is used after mlx5_core_dev is reconfigured. + */ +int mlx5_rescan_drivers_locked(struct mlx5_core_dev *dev) { - struct mlx5_interface *intf; + struct mlx5_priv *priv = &dev->priv; - list_for_each_entry(intf, &intf_list, list) - if (intf->protocol == protocol) { - mlx5_add_device(intf, &dev->priv); - break; - } -} + lockdep_assert_held(&mlx5_intf_mutex); -/* Must be called with intf_mutex held */ -void mlx5_remove_dev_by_protocol(struct mlx5_core_dev *dev, int protocol) -{ - struct mlx5_interface *intf; + delete_drivers(dev); + if (priv->flags & MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV) + return 0; - list_for_each_entry(intf, &intf_list, list) - if (intf->protocol == protocol) { - mlx5_remove_device(intf, &dev->priv); - break; - } + return add_drivers(dev); } -static u32 mlx5_gen_pci_id(struct mlx5_core_dev *dev) +static u32 mlx5_gen_pci_id(const struct mlx5_core_dev *dev) { return (u32)((pci_domain_nr(dev->pdev->bus) << 16) | (dev->pdev->bus->number << 8) | PCI_SLOT(dev->pdev->devfn)); } -/* Must be called with intf_mutex held */ +static int next_phys_dev(struct device *dev, const void *data) +{ + struct mlx5_adev *madev = container_of(dev, struct mlx5_adev, adev.dev); + struct mlx5_core_dev *mdev = madev->mdev; + const struct mlx5_core_dev *curr = data; + + if (!mlx5_core_is_pf(mdev)) + return 0; + + if (mdev == curr) + return 0; + + if (mlx5_gen_pci_id(mdev) != mlx5_gen_pci_id(curr)) + return 0; + + return 1; +} + +/* This function is called with two flows: + * 1. During initialization of mlx5_core_dev and we don't need to lock it. + * 2. During LAG configure stage and caller holds &mlx5_intf_mutex. + */ struct mlx5_core_dev *mlx5_get_next_phys_dev(struct mlx5_core_dev *dev) { - struct mlx5_core_dev *res = NULL; - struct mlx5_core_dev *tmp_dev; - struct mlx5_priv *priv; - u32 pci_id; + struct auxiliary_device *adev; + struct mlx5_adev *madev; if (!mlx5_core_is_pf(dev)) return NULL; - pci_id = mlx5_gen_pci_id(dev); - list_for_each_entry(priv, &mlx5_dev_list, dev_list) { - tmp_dev = container_of(priv, struct mlx5_core_dev, priv); - if (!mlx5_core_is_pf(tmp_dev)) - continue; - - if ((dev != tmp_dev) && (mlx5_gen_pci_id(tmp_dev) == pci_id)) { - res = tmp_dev; - break; - } - } + adev = auxiliary_find_device(NULL, dev, &next_phys_dev); + if (!adev) + return NULL; - return res; + madev = container_of(adev, struct mlx5_adev, adev); + put_device(&adev->dev); + return madev->mdev; } - void mlx5_dev_list_lock(void) { mutex_lock(&mlx5_intf_mutex); } - void mlx5_dev_list_unlock(void) { mutex_unlock(&mlx5_intf_mutex); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c index e2ed341648e4..3261d0dc1104 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c @@ -43,7 +43,7 @@ mlx5_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req, u32 running_fw, stored_fw; int err; - err = devlink_info_driver_name_put(req, DRIVER_NAME); + err = devlink_info_driver_name_put(req, KBUILD_MODNAME); if (err) return err; @@ -212,7 +212,7 @@ static int mlx5_devlink_fs_mode_validate(struct devlink *devlink, u32 id, u8 eswitch_mode; bool smfs_cap; - eswitch_mode = mlx5_eswitch_mode(dev->priv.eswitch); + eswitch_mode = mlx5_eswitch_mode(dev); smfs_cap = mlx5_fs_dr_is_supported(dev); if (!smfs_cap) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 42e61dc28ead..58a405f856eb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -41,9 +41,7 @@ void mlx5e_ethtool_get_drvinfo(struct mlx5e_priv *priv, { struct mlx5_core_dev *mdev = priv->mdev; - strlcpy(drvinfo->driver, DRIVER_NAME, sizeof(drvinfo->driver)); - strlcpy(drvinfo->version, DRIVER_VERSION, - sizeof(drvinfo->version)); + strlcpy(drvinfo->driver, KBUILD_MODNAME, sizeof(drvinfo->driver)); snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), "%d.%d.%04d (%.16s)", fw_rev_maj(mdev), fw_rev_min(mdev), fw_rev_sub(mdev), diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 427fc376fe1a..330201dfe9a4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -3112,7 +3112,7 @@ static void mlx5e_modify_admin_state(struct mlx5_core_dev *mdev, mlx5_set_port_admin_status(mdev, state); - if (!MLX5_ESWITCH_MANAGER(mdev) || mlx5_eswitch_mode(esw) == MLX5_ESWITCH_OFFLOADS) + if (mlx5_eswitch_mode(mdev) != MLX5_ESWITCH_LEGACY) return; if (state == MLX5_PORT_UP) @@ -4577,31 +4577,6 @@ const struct net_device_ops mlx5e_netdev_ops = { .ndo_get_devlink_port = mlx5e_get_devlink_port, }; -static int mlx5e_check_required_hca_cap(struct mlx5_core_dev *mdev) -{ - if (MLX5_CAP_GEN(mdev, port_type) != MLX5_CAP_PORT_TYPE_ETH) - return -EOPNOTSUPP; - if (!MLX5_CAP_GEN(mdev, eth_net_offloads) || - !MLX5_CAP_GEN(mdev, nic_flow_table) || - !MLX5_CAP_ETH(mdev, csum_cap) || - !MLX5_CAP_ETH(mdev, max_lso_cap) || - !MLX5_CAP_ETH(mdev, vlan_cap) || - !MLX5_CAP_ETH(mdev, rss_ind_tbl_cap) || - MLX5_CAP_FLOWTABLE(mdev, - flow_table_properties_nic_receive.max_ft_level) - < 3) { - mlx5_core_warn(mdev, - "Not creating net device, some required device capabilities are missing\n"); - return -EOPNOTSUPP; - } - if (!MLX5_CAP_ETH(mdev, self_lb_en_modifiable)) - mlx5_core_warn(mdev, "Self loop back prevention is not supported\n"); - if (!MLX5_CAP_GEN(mdev, cq_moderation)) - mlx5_core_warn(mdev, "CQ moderation is not supported\n"); - - return 0; -} - void mlx5e_build_default_indir_rqt(u32 *indirection_rqt, int len, int num_channels) { @@ -5421,13 +5396,12 @@ void mlx5e_destroy_netdev(struct mlx5e_priv *priv) free_netdev(netdev); } -/* mlx5e_attach and mlx5e_detach scope should be only creating/destroying - * hardware contexts and to connect it to the current netdev. - */ -static int mlx5e_attach(struct mlx5_core_dev *mdev, void *vpriv) +static int mlx5e_resume(struct auxiliary_device *adev) { - struct mlx5e_priv *priv = vpriv; + struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev); + struct mlx5e_priv *priv = dev_get_drvdata(&adev->dev); struct net_device *netdev = priv->netdev; + struct mlx5_core_dev *mdev = edev->mdev; int err; if (netif_device_present(netdev)) @@ -5446,109 +5420,111 @@ static int mlx5e_attach(struct mlx5_core_dev *mdev, void *vpriv) return 0; } -static void mlx5e_detach(struct mlx5_core_dev *mdev, void *vpriv) +static int mlx5e_suspend(struct auxiliary_device *adev, pm_message_t state) { - struct mlx5e_priv *priv = vpriv; + struct mlx5e_priv *priv = dev_get_drvdata(&adev->dev); struct net_device *netdev = priv->netdev; - -#ifdef CONFIG_MLX5_ESWITCH - if (MLX5_ESWITCH_MANAGER(mdev) && vpriv == mdev) - return; -#endif + struct mlx5_core_dev *mdev = priv->mdev; if (!netif_device_present(netdev)) - return; + return -ENODEV; mlx5e_detach_netdev(priv); mlx5e_destroy_mdev_resources(mdev); + return 0; } -static void *mlx5e_add(struct mlx5_core_dev *mdev) +static int mlx5e_probe(struct auxiliary_device *adev, + const struct auxiliary_device_id *id) { + struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev); + struct mlx5_core_dev *mdev = edev->mdev; struct net_device *netdev; + pm_message_t state = {}; void *priv; int err; int nch; - err = mlx5e_check_required_hca_cap(mdev); - if (err) - return NULL; - -#ifdef CONFIG_MLX5_ESWITCH - if (MLX5_ESWITCH_MANAGER(mdev) && - mlx5_eswitch_mode(mdev->priv.eswitch) == MLX5_ESWITCH_OFFLOADS) { - mlx5e_rep_register_vport_reps(mdev); - return mdev; - } -#endif - nch = mlx5e_get_max_num_channels(mdev); netdev = mlx5e_create_netdev(mdev, &mlx5e_nic_profile, nch, NULL); if (!netdev) { mlx5_core_err(mdev, "mlx5e_create_netdev failed\n"); - return NULL; + return -ENOMEM; } dev_net_set(netdev, mlx5_core_net(mdev)); priv = netdev_priv(netdev); + dev_set_drvdata(&adev->dev, priv); - err = mlx5e_attach(mdev, priv); + err = mlx5e_resume(adev); if (err) { - mlx5_core_err(mdev, "mlx5e_attach failed, %d\n", err); + mlx5_core_err(mdev, "mlx5e_resume failed, %d\n", err); goto err_destroy_netdev; } err = register_netdev(netdev); if (err) { mlx5_core_err(mdev, "register_netdev failed, %d\n", err); - goto err_detach; + goto err_resume; } mlx5e_devlink_port_type_eth_set(priv); mlx5e_dcbnl_init_app(priv); - return priv; + return 0; -err_detach: - mlx5e_detach(mdev, priv); +err_resume: + mlx5e_suspend(adev, state); err_destroy_netdev: mlx5e_destroy_netdev(priv); - return NULL; + return err; } -static void mlx5e_remove(struct mlx5_core_dev *mdev, void *vpriv) +static void mlx5e_remove(struct auxiliary_device *adev) { - struct mlx5e_priv *priv; + struct mlx5e_priv *priv = dev_get_drvdata(&adev->dev); + pm_message_t state = {}; -#ifdef CONFIG_MLX5_ESWITCH - if (MLX5_ESWITCH_MANAGER(mdev) && vpriv == mdev) { - mlx5e_rep_unregister_vport_reps(mdev); - return; - } -#endif - priv = vpriv; mlx5e_dcbnl_delete_app(priv); unregister_netdev(priv->netdev); - mlx5e_detach(mdev, vpriv); + mlx5e_suspend(adev, state); mlx5e_destroy_netdev(priv); } -static struct mlx5_interface mlx5e_interface = { - .add = mlx5e_add, - .remove = mlx5e_remove, - .attach = mlx5e_attach, - .detach = mlx5e_detach, - .protocol = MLX5_INTERFACE_PROTOCOL_ETH, +static const struct auxiliary_device_id mlx5e_id_table[] = { + { .name = MLX5_ADEV_NAME ".eth", }, + {}, }; -void mlx5e_init(void) +MODULE_DEVICE_TABLE(auxiliary, mlx5e_id_table); + +static struct auxiliary_driver mlx5e_driver = { + .name = "eth", + .probe = mlx5e_probe, + .remove = mlx5e_remove, + .suspend = mlx5e_suspend, + .resume = mlx5e_resume, + .id_table = mlx5e_id_table, +}; + +int mlx5e_init(void) { + int ret; + mlx5e_ipsec_build_inverse_table(); mlx5e_build_ptys2ethtool_map(); - mlx5_register_interface(&mlx5e_interface); + ret = mlx5e_rep_init(); + if (ret) + return ret; + + ret = auxiliary_driver_register(&mlx5e_driver); + if (ret) + mlx5e_rep_cleanup(); + return ret; } void mlx5e_cleanup(void) { - mlx5_unregister_interface(&mlx5e_interface); + auxiliary_driver_unregister(&mlx5e_driver); + mlx5e_rep_cleanup(); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 67247c33b9fd..989c70c1eda3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -64,7 +64,6 @@ static void mlx5e_rep_get_drvinfo(struct net_device *dev, strlcpy(drvinfo->driver, mlx5e_rep_driver_name, sizeof(drvinfo->driver)); - strlcpy(drvinfo->version, UTS_RELEASE, sizeof(drvinfo->version)); snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), "%d.%d.%04d (%.16s)", fw_rev_maj(mdev), fw_rev_min(mdev), @@ -1316,16 +1315,48 @@ static const struct mlx5_eswitch_rep_ops rep_ops = { .get_proto_dev = mlx5e_vport_rep_get_proto_dev }; -void mlx5e_rep_register_vport_reps(struct mlx5_core_dev *mdev) +static int mlx5e_rep_probe(struct auxiliary_device *adev, + const struct auxiliary_device_id *id) { - struct mlx5_eswitch *esw = mdev->priv.eswitch; + struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev); + struct mlx5_core_dev *mdev = edev->mdev; + struct mlx5_eswitch *esw; + esw = mdev->priv.eswitch; mlx5_eswitch_register_vport_reps(esw, &rep_ops, REP_ETH); + return 0; } -void mlx5e_rep_unregister_vport_reps(struct mlx5_core_dev *mdev) +static void mlx5e_rep_remove(struct auxiliary_device *adev) { - struct mlx5_eswitch *esw = mdev->priv.eswitch; + struct mlx5_adev *vdev = container_of(adev, struct mlx5_adev, adev); + struct mlx5_core_dev *mdev = vdev->mdev; + struct mlx5_eswitch *esw; + esw = mdev->priv.eswitch; mlx5_eswitch_unregister_vport_reps(esw, REP_ETH); } + +static const struct auxiliary_device_id mlx5e_rep_id_table[] = { + { .name = MLX5_ADEV_NAME ".eth-rep", }, + {}, +}; + +MODULE_DEVICE_TABLE(auxiliary, mlx5e_rep_id_table); + +static struct auxiliary_driver mlx5e_rep_driver = { + .name = "eth-rep", + .probe = mlx5e_rep_probe, + .remove = mlx5e_rep_remove, + .id_table = mlx5e_rep_id_table, +}; + +int mlx5e_rep_init(void) +{ + return auxiliary_driver_register(&mlx5e_rep_driver); +} + +void mlx5e_rep_cleanup(void) +{ + auxiliary_driver_unregister(&mlx5e_rep_driver); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h index 8932c387d46a..988195ab1c54 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h @@ -203,8 +203,8 @@ struct mlx5e_rep_sq { struct list_head list; }; -void mlx5e_rep_register_vport_reps(struct mlx5_core_dev *mdev); -void mlx5e_rep_unregister_vport_reps(struct mlx5_core_dev *mdev); +int mlx5e_rep_init(void); +void mlx5e_rep_cleanup(void); int mlx5e_rep_bond_init(struct mlx5e_rep_priv *rpriv); void mlx5e_rep_bond_cleanup(struct mlx5e_rep_priv *rpriv); int mlx5e_rep_bond_enslave(struct mlx5_eswitch *esw, struct net_device *netdev, @@ -232,6 +232,8 @@ static inline bool mlx5e_eswitch_rep(struct net_device *netdev) static inline bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv) { return false; } static inline int mlx5e_add_sqs_fwd_rules(struct mlx5e_priv *priv) { return 0; } static inline void mlx5e_remove_sqs_fwd_rules(struct mlx5e_priv *priv) {} +static inline int mlx5e_rep_init(void) { return 0; }; +static inline void mlx5e_rep_cleanup(void) {}; #endif static inline bool mlx5e_is_vport_rep(struct mlx5e_priv *priv) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index ce710f22b1ff..4cdf834fa74a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -271,8 +271,6 @@ mlx5e_tc_match_to_reg_set(struct mlx5_core_dev *mdev, return 0; } -#define esw_offloads_mode(esw) (mlx5_eswitch_mode(esw) == MLX5_ESWITCH_OFFLOADS) - static struct mlx5_tc_ct_priv * get_ct_priv(struct mlx5e_priv *priv) { @@ -280,7 +278,7 @@ get_ct_priv(struct mlx5e_priv *priv) struct mlx5_rep_uplink_priv *uplink_priv; struct mlx5e_rep_priv *uplink_rpriv; - if (esw_offloads_mode(esw)) { + if (is_mdev_switchdev_mode(priv->mdev)) { uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH); uplink_priv = &uplink_rpriv->uplink_priv; @@ -297,7 +295,7 @@ mlx5_tc_rule_insert(struct mlx5e_priv *priv, { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; - if (esw_offloads_mode(esw)) + if (is_mdev_switchdev_mode(priv->mdev)) return mlx5_eswitch_add_offloaded_rule(esw, spec, attr); return mlx5e_add_offloaded_nic_rule(priv, spec, attr); @@ -310,7 +308,7 @@ mlx5_tc_rule_delete(struct mlx5e_priv *priv, { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; - if (esw_offloads_mode(esw)) { + if (is_mdev_switchdev_mode(priv->mdev)) { mlx5_eswitch_del_offloaded_rule(esw, rule, attr); return; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 7f8c4a957f72..da901e364656 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1641,8 +1641,7 @@ int mlx5_eswitch_enable_locked(struct mlx5_eswitch *esw, int mode, int num_vfs) if (mode == MLX5_ESWITCH_LEGACY) { err = esw_legacy_enable(esw); } else { - mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_ETH); - mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB); + mlx5_rescan_drivers(esw->dev); err = esw_offloads_enable(esw); } @@ -1660,10 +1659,9 @@ int mlx5_eswitch_enable_locked(struct mlx5_eswitch *esw, int mode, int num_vfs) abort: esw->mode = MLX5_ESWITCH_NONE; - if (mode == MLX5_ESWITCH_OFFLOADS) { - mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB); - mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_ETH); - } + if (mode == MLX5_ESWITCH_OFFLOADS) + mlx5_rescan_drivers(esw->dev); + esw_destroy_tsar(esw); return err; } @@ -1724,10 +1722,9 @@ void mlx5_eswitch_disable_locked(struct mlx5_eswitch *esw, bool clear_vf) mlx5_lag_update(esw->dev); - if (old_mode == MLX5_ESWITCH_OFFLOADS) { - mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB); - mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_ETH); - } + if (old_mode == MLX5_ESWITCH_OFFLOADS) + mlx5_rescan_drivers(esw->dev); + esw_destroy_tsar(esw); if (clear_vf) @@ -2466,8 +2463,10 @@ free_out: return err; } -u8 mlx5_eswitch_mode(struct mlx5_eswitch *esw) +u8 mlx5_eswitch_mode(struct mlx5_core_dev *dev) { + struct mlx5_eswitch *esw = dev->priv.eswitch; + return ESW_ALLOWED(esw) ? esw->mode : MLX5_ESWITCH_NONE; } EXPORT_SYMBOL_GPL(mlx5_eswitch_mode); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c index cac8f085b16d..97d96fc38a65 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c @@ -39,7 +39,7 @@ static void mlx5i_get_drvinfo(struct net_device *dev, struct mlx5e_priv *priv = mlx5i_epriv(dev); mlx5e_ethtool_get_drvinfo(priv, drvinfo); - strlcpy(drvinfo->driver, DRIVER_NAME "[ib_ipoib]", + strlcpy(drvinfo->driver, KBUILD_MODNAME "[ib_ipoib]", sizeof(drvinfo->driver)); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c index 33081b24f10a..f3d45ef082cd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c @@ -243,24 +243,30 @@ static bool mlx5_lag_check_prereq(struct mlx5_lag *ldev) #endif } -static void mlx5_lag_add_ib_devices(struct mlx5_lag *ldev) +static void mlx5_lag_add_devices(struct mlx5_lag *ldev) { int i; - for (i = 0; i < MLX5_MAX_PORTS; i++) - if (ldev->pf[i].dev) - mlx5_add_dev_by_protocol(ldev->pf[i].dev, - MLX5_INTERFACE_PROTOCOL_IB); + for (i = 0; i < MLX5_MAX_PORTS; i++) { + if (!ldev->pf[i].dev) + continue; + + ldev->pf[i].dev->priv.flags &= ~MLX5_PRIV_FLAGS_DISABLE_IB_ADEV; + mlx5_rescan_drivers_locked(ldev->pf[i].dev); + } } -static void mlx5_lag_remove_ib_devices(struct mlx5_lag *ldev) +static void mlx5_lag_remove_devices(struct mlx5_lag *ldev) { int i; - for (i = 0; i < MLX5_MAX_PORTS; i++) - if (ldev->pf[i].dev) - mlx5_remove_dev_by_protocol(ldev->pf[i].dev, - MLX5_INTERFACE_PROTOCOL_IB); + for (i = 0; i < MLX5_MAX_PORTS; i++) { + if (!ldev->pf[i].dev) + continue; + + ldev->pf[i].dev->priv.flags |= MLX5_PRIV_FLAGS_DISABLE_IB_ADEV; + mlx5_rescan_drivers_locked(ldev->pf[i].dev); + } } static void mlx5_do_bond(struct mlx5_lag *ldev) @@ -290,20 +296,21 @@ static void mlx5_do_bond(struct mlx5_lag *ldev) #endif if (roce_lag) - mlx5_lag_remove_ib_devices(ldev); + mlx5_lag_remove_devices(ldev); err = mlx5_activate_lag(ldev, &tracker, roce_lag ? MLX5_LAG_FLAG_ROCE : MLX5_LAG_FLAG_SRIOV); if (err) { if (roce_lag) - mlx5_lag_add_ib_devices(ldev); + mlx5_lag_add_devices(ldev); return; } if (roce_lag) { - mlx5_add_dev_by_protocol(dev0, MLX5_INTERFACE_PROTOCOL_IB); + dev0->priv.flags &= ~MLX5_PRIV_FLAGS_DISABLE_IB_ADEV; + mlx5_rescan_drivers_locked(dev0); mlx5_nic_vport_enable_roce(dev1); } } else if (do_bond && __mlx5_lag_is_active(ldev)) { @@ -312,7 +319,8 @@ static void mlx5_do_bond(struct mlx5_lag *ldev) roce_lag = __mlx5_lag_is_roce(ldev); if (roce_lag) { - mlx5_remove_dev_by_protocol(dev0, MLX5_INTERFACE_PROTOCOL_IB); + dev0->priv.flags |= MLX5_PRIV_FLAGS_DISABLE_IB_ADEV; + mlx5_rescan_drivers_locked(dev0); mlx5_nic_vport_disable_roce(dev1); } @@ -321,7 +329,7 @@ static void mlx5_do_bond(struct mlx5_lag *ldev) return; if (roce_lag) - mlx5_lag_add_ib_devices(ldev); + mlx5_lag_add_devices(ldev); } } @@ -596,6 +604,8 @@ void mlx5_lag_add(struct mlx5_core_dev *dev, struct net_device *netdev) if (err) mlx5_core_err(dev, "Failed to init multipath lag err=%d\n", err); + + return; } /* Must be called with intf_mutex held */ @@ -739,24 +749,6 @@ unlock: } EXPORT_SYMBOL(mlx5_lag_get_slave_port); -bool mlx5_lag_intf_add(struct mlx5_interface *intf, struct mlx5_priv *priv) -{ - struct mlx5_core_dev *dev = container_of(priv, struct mlx5_core_dev, - priv); - struct mlx5_lag *ldev; - - if (intf->protocol != MLX5_INTERFACE_PROTOCOL_IB) - return true; - - ldev = mlx5_lag_dev_get(dev); - if (!ldev || !__mlx5_lag_is_roce(ldev) || - ldev->pf[MLX5_LAG_P1].dev == dev) - return true; - - /* If bonded, we do not add an IB device for PF1. */ - return false; -} - int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev, u64 *values, int num_counters, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index d86f06f14cd3..c08315b51fd3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -50,6 +50,7 @@ #ifdef CONFIG_RFS_ACCEL #include <linux/cpu_rmap.h> #endif +#include <linux/version.h> #include <net/devlink.h> #include "mlx5_core.h" #include "lib/eq.h" @@ -76,7 +77,6 @@ MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>"); MODULE_DESCRIPTION("Mellanox 5th generation network adapters (ConnectX series) core driver"); MODULE_LICENSE("Dual BSD/GPL"); -MODULE_VERSION(DRIVER_VERSION); unsigned int mlx5_core_debug_mask; module_param_named(debug_mask, mlx5_core_debug_mask, uint, 0644); @@ -227,13 +227,16 @@ static void mlx5_set_driver_version(struct mlx5_core_dev *dev) strncat(string, ",", remaining_size); remaining_size = max_t(int, 0, driver_ver_sz - strlen(string)); - strncat(string, DRIVER_NAME, remaining_size); + strncat(string, KBUILD_MODNAME, remaining_size); remaining_size = max_t(int, 0, driver_ver_sz - strlen(string)); strncat(string, ",", remaining_size); remaining_size = max_t(int, 0, driver_ver_sz - strlen(string)); - strncat(string, DRIVER_VERSION, remaining_size); + + snprintf(string + strlen(string), remaining_size, "%u.%u.%u", + (u8)((LINUX_VERSION_CODE >> 16) & 0xff), (u8)((LINUX_VERSION_CODE >> 8) & 0xff), + (u16)(LINUX_VERSION_CODE & 0xffff)); /*Send the command*/ MLX5_SET(set_driver_version_in, in, opcode, @@ -309,7 +312,7 @@ static int request_bar(struct pci_dev *pdev) return -ENODEV; } - err = pci_request_regions(pdev, DRIVER_NAME); + err = pci_request_regions(pdev, KBUILD_MODNAME); if (err) dev_err(&pdev->dev, "Couldn't get PCI resources, aborting\n"); @@ -1219,14 +1222,21 @@ int mlx5_load_one(struct mlx5_core_dev *dev, bool boot) err = mlx5_devlink_register(priv_to_devlink(dev), dev->device); if (err) goto err_devlink_reg; - mlx5_register_device(dev); + + err = mlx5_register_device(dev); } else { - mlx5_attach_device(dev); + err = mlx5_attach_device(dev); } + if (err) + goto err_register; + mutex_unlock(&dev->intf_state_mutex); return 0; +err_register: + if (boot) + mlx5_devlink_unregister(priv_to_devlink(dev)); err_devlink_reg: clear_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state); mlx5_unload(dev); @@ -1303,8 +1313,14 @@ static int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx) if (err) goto err_pagealloc_init; + err = mlx5_adev_init(dev); + if (err) + goto err_adev_init; + return 0; +err_adev_init: + mlx5_pagealloc_cleanup(dev); err_pagealloc_init: mlx5_health_cleanup(dev); err_health_init: @@ -1321,6 +1337,7 @@ static void mlx5_mdev_uninit(struct mlx5_core_dev *dev) { struct mlx5_priv *priv = &dev->priv; + mlx5_adev_cleanup(dev); mlx5_pagealloc_cleanup(dev); mlx5_health_cleanup(dev); debugfs_remove_recursive(dev->priv.dbg_root); @@ -1331,7 +1348,6 @@ static void mlx5_mdev_uninit(struct mlx5_core_dev *dev) mutex_destroy(&dev->intf_state_mutex); } -#define MLX5_IB_MOD "mlx5_ib" static int init_one(struct pci_dev *pdev, const struct pci_device_id *id) { struct mlx5_core_dev *dev; @@ -1351,6 +1367,10 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *id) dev->coredev_type = id->driver_data & MLX5_PCI_DEV_IS_VF ? MLX5_COREDEV_VF : MLX5_COREDEV_PF; + dev->priv.adev_idx = mlx5_adev_idx_alloc(); + if (dev->priv.adev_idx < 0) + return dev->priv.adev_idx; + err = mlx5_mdev_init(dev, prof_sel); if (err) goto mdev_init_err; @@ -1369,8 +1389,6 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *id) goto err_load_one; } - request_module_nowait(MLX5_IB_MOD); - err = mlx5_crdump_enable(dev); if (err) dev_err(&pdev->dev, "mlx5_crdump_enable failed with error code %d\n", err); @@ -1384,6 +1402,7 @@ err_load_one: pci_init_err: mlx5_mdev_uninit(dev); mdev_init_err: + mlx5_adev_idx_free(dev->priv.adev_idx); mlx5_devlink_free(devlink); return err; @@ -1400,6 +1419,7 @@ static void remove_one(struct pci_dev *pdev) mlx5_unload_one(dev, true); mlx5_pci_close(dev); mlx5_mdev_uninit(dev); + mlx5_adev_idx_free(dev->priv.adev_idx); mlx5_devlink_free(devlink); } @@ -1614,7 +1634,7 @@ void mlx5_recover_device(struct mlx5_core_dev *dev) } static struct pci_driver mlx5_core_driver = { - .name = DRIVER_NAME, + .name = KBUILD_MODNAME, .id_table = mlx5_core_pci_table, .probe = init_one, .remove = remove_one, @@ -1640,6 +1660,9 @@ static int __init init(void) { int err; + WARN_ONCE(strcmp(MLX5_ADEV_NAME, KBUILD_MODNAME), + "mlx5_core name not in sync with kernel module name"); + get_random_bytes(&sw_owner_id, sizeof(sw_owner_id)); mlx5_core_verify_params(); @@ -1651,7 +1674,11 @@ static int __init init(void) goto err_debug; #ifdef CONFIG_MLX5_CORE_EN - mlx5e_init(); + err = mlx5e_init(); + if (err) { + pci_unregister_driver(&mlx5_core_driver); + goto err_debug; + } #endif return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index 9d00efa9e6bc..0a0302ce7144 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -42,9 +42,6 @@ #include <linux/mlx5/fs.h> #include <linux/mlx5/driver.h> -#define DRIVER_NAME "mlx5_core" -#define DRIVER_VERSION "5.0-0" - extern uint mlx5_core_debug_mask; #define mlx5_core_dbg(__dev, format, ...) \ @@ -185,22 +182,20 @@ void mlx5_events_cleanup(struct mlx5_core_dev *dev); void mlx5_events_start(struct mlx5_core_dev *dev); void mlx5_events_stop(struct mlx5_core_dev *dev); -void mlx5_add_device(struct mlx5_interface *intf, struct mlx5_priv *priv); -void mlx5_remove_device(struct mlx5_interface *intf, struct mlx5_priv *priv); -void mlx5_attach_device(struct mlx5_core_dev *dev); +int mlx5_adev_idx_alloc(void); +void mlx5_adev_idx_free(int idx); +void mlx5_adev_cleanup(struct mlx5_core_dev *dev); +int mlx5_adev_init(struct mlx5_core_dev *dev); + +int mlx5_attach_device(struct mlx5_core_dev *dev); void mlx5_detach_device(struct mlx5_core_dev *dev); -bool mlx5_device_registered(struct mlx5_core_dev *dev); -void mlx5_register_device(struct mlx5_core_dev *dev); +int mlx5_register_device(struct mlx5_core_dev *dev); void mlx5_unregister_device(struct mlx5_core_dev *dev); -void mlx5_add_dev_by_protocol(struct mlx5_core_dev *dev, int protocol); -void mlx5_remove_dev_by_protocol(struct mlx5_core_dev *dev, int protocol); struct mlx5_core_dev *mlx5_get_next_phys_dev(struct mlx5_core_dev *dev); void mlx5_dev_list_lock(void); void mlx5_dev_list_unlock(void); int mlx5_dev_list_trylock(void); -bool mlx5_lag_intf_add(struct mlx5_interface *intf, struct mlx5_priv *priv); - int mlx5_query_mtpps(struct mlx5_core_dev *dev, u32 *mtpps, u32 mtpps_size); int mlx5_set_mtpps(struct mlx5_core_dev *mdev, u32 *mtpps, u32 mtpps_size); int mlx5_query_mtppse(struct mlx5_core_dev *mdev, u8 pin, u8 *arm, u8 *mode); @@ -219,7 +214,7 @@ int mlx5_firmware_flash(struct mlx5_core_dev *dev, const struct firmware *fw, int mlx5_fw_version_query(struct mlx5_core_dev *dev, u32 *running_ver, u32 *stored_ver); -void mlx5e_init(void); +int mlx5e_init(void); void mlx5e_cleanup(void); static inline bool mlx5_sriov_is_enabled(struct mlx5_core_dev *dev) @@ -239,7 +234,17 @@ static inline int mlx5_lag_is_lacp_owner(struct mlx5_core_dev *dev) MLX5_CAP_GEN(dev, lag_master); } -void mlx5_reload_interface(struct mlx5_core_dev *mdev, int protocol); +int mlx5_rescan_drivers_locked(struct mlx5_core_dev *dev); +static inline int mlx5_rescan_drivers(struct mlx5_core_dev *dev) +{ + int ret; + + mlx5_dev_list_lock(); + ret = mlx5_rescan_drivers_locked(dev); + mlx5_dev_list_unlock(); + return ret; +} + void mlx5_lag_update(struct mlx5_core_dev *dev); enum { diff --git a/drivers/vdpa/mlx5/Makefile b/drivers/vdpa/mlx5/Makefile index 89a5bededc9f..f717978c83bf 100644 --- a/drivers/vdpa/mlx5/Makefile +++ b/drivers/vdpa/mlx5/Makefile @@ -1,4 +1,4 @@ subdir-ccflags-y += -I$(srctree)/drivers/vdpa/mlx5/core obj-$(CONFIG_MLX5_VDPA_NET) += mlx5_vdpa.o -mlx5_vdpa-$(CONFIG_MLX5_VDPA_NET) += net/main.o net/mlx5_vnet.o core/resources.o core/mr.o +mlx5_vdpa-$(CONFIG_MLX5_VDPA_NET) += net/mlx5_vnet.o core/resources.o core/mr.o diff --git a/drivers/vdpa/mlx5/net/main.c b/drivers/vdpa/mlx5/net/main.c deleted file mode 100644 index 838cd98386ff..000000000000 --- a/drivers/vdpa/mlx5/net/main.c +++ /dev/null @@ -1,76 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB -/* Copyright (c) 2020 Mellanox Technologies Ltd. */ - -#include <linux/module.h> -#include <linux/mlx5/driver.h> -#include <linux/mlx5/device.h> -#include "mlx5_vdpa_ifc.h" -#include "mlx5_vnet.h" - -MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>"); -MODULE_DESCRIPTION("Mellanox VDPA driver"); -MODULE_LICENSE("Dual BSD/GPL"); - -static bool required_caps_supported(struct mlx5_core_dev *mdev) -{ - u8 event_mode; - u64 got; - - got = MLX5_CAP_GEN_64(mdev, general_obj_types); - - if (!(got & MLX5_GENERAL_OBJ_TYPES_CAP_VIRTIO_NET_Q)) - return false; - - event_mode = MLX5_CAP_DEV_VDPA_EMULATION(mdev, event_mode); - if (!(event_mode & MLX5_VIRTIO_Q_EVENT_MODE_QP_MODE)) - return false; - - if (!MLX5_CAP_DEV_VDPA_EMULATION(mdev, eth_frame_offload_type)) - return false; - - return true; -} - -static void *mlx5_vdpa_add(struct mlx5_core_dev *mdev) -{ - struct mlx5_vdpa_dev *vdev; - - if (mlx5_core_is_pf(mdev)) - return NULL; - - if (!required_caps_supported(mdev)) { - dev_info(mdev->device, "virtio net emulation not supported\n"); - return NULL; - } - vdev = mlx5_vdpa_add_dev(mdev); - if (IS_ERR(vdev)) - return NULL; - - return vdev; -} - -static void mlx5_vdpa_remove(struct mlx5_core_dev *mdev, void *context) -{ - struct mlx5_vdpa_dev *vdev = context; - - mlx5_vdpa_remove_dev(vdev); -} - -static struct mlx5_interface mlx5_vdpa_interface = { - .add = mlx5_vdpa_add, - .remove = mlx5_vdpa_remove, - .protocol = MLX5_INTERFACE_PROTOCOL_VDPA, -}; - -static int __init mlx5_vdpa_init(void) -{ - return mlx5_register_interface(&mlx5_vdpa_interface); -} - -static void __exit mlx5_vdpa_exit(void) -{ - mlx5_unregister_interface(&mlx5_vdpa_interface); -} - -module_init(mlx5_vdpa_init); -module_exit(mlx5_vdpa_exit); diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index 1fa6fcac8299..f1d54814db97 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -1,18 +1,28 @@ // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB /* Copyright (c) 2020 Mellanox Technologies Ltd. */ +#include <linux/module.h> #include <linux/vdpa.h> +#include <linux/vringh.h> +#include <uapi/linux/virtio_net.h> #include <uapi/linux/virtio_ids.h> #include <linux/virtio_config.h> +#include <linux/auxiliary_bus.h> +#include <linux/mlx5/cq.h> #include <linux/mlx5/qp.h> #include <linux/mlx5/device.h> +#include <linux/mlx5/driver.h> #include <linux/mlx5/vport.h> #include <linux/mlx5/fs.h> -#include <linux/mlx5/device.h> -#include "mlx5_vnet.h" -#include "mlx5_vdpa_ifc.h" +#include <linux/mlx5/mlx5_ifc_vdpa.h> #include "mlx5_vdpa.h" +MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>"); +MODULE_DESCRIPTION("Mellanox VDPA driver"); +MODULE_LICENSE("Dual BSD/GPL"); + +#define to_mlx5_vdpa_ndev(__mvdev) \ + container_of(__mvdev, struct mlx5_vdpa_net, mvdev) #define to_mvdev(__vdev) container_of((__vdev), struct mlx5_vdpa_dev, vdev) #define VALID_FEATURES_MASK \ @@ -159,6 +169,11 @@ static bool mlx5_vdpa_debug; mlx5_vdpa_info(mvdev, "%s\n", #_status); \ } while (0) +static inline u32 mlx5_vdpa_max_qps(int max_vqs) +{ + return max_vqs / 2; +} + static void print_status(struct mlx5_vdpa_dev *mvdev, u8 status, bool set) { if (status & ~VALID_STATUS_MASK) @@ -1928,8 +1943,11 @@ static void init_mvqs(struct mlx5_vdpa_net *ndev) } } -void *mlx5_vdpa_add_dev(struct mlx5_core_dev *mdev) +static int mlx5v_probe(struct auxiliary_device *adev, + const struct auxiliary_device_id *id) { + struct mlx5_adev *madev = container_of(adev, struct mlx5_adev, adev); + struct mlx5_core_dev *mdev = madev->mdev; struct virtio_net_config *config; struct mlx5_vdpa_dev *mvdev; struct mlx5_vdpa_net *ndev; @@ -1943,7 +1961,7 @@ void *mlx5_vdpa_add_dev(struct mlx5_core_dev *mdev) ndev = vdpa_alloc_device(struct mlx5_vdpa_net, mvdev.vdev, mdev->device, &mlx5_vdpa_ops, 2 * mlx5_vdpa_max_qps(max_vqs)); if (IS_ERR(ndev)) - return ndev; + return PTR_ERR(ndev); ndev->mvdev.max_vqs = max_vqs; mvdev = &ndev->mvdev; @@ -1972,7 +1990,8 @@ void *mlx5_vdpa_add_dev(struct mlx5_core_dev *mdev) if (err) goto err_reg; - return ndev; + dev_set_drvdata(&adev->dev, ndev); + return 0; err_reg: free_resources(ndev); @@ -1981,10 +2000,28 @@ err_res: err_mtu: mutex_destroy(&ndev->reslock); put_device(&mvdev->vdev.dev); - return ERR_PTR(err); + return err; } -void mlx5_vdpa_remove_dev(struct mlx5_vdpa_dev *mvdev) +static void mlx5v_remove(struct auxiliary_device *adev) { + struct mlx5_vdpa_dev *mvdev = dev_get_drvdata(&adev->dev); + vdpa_unregister_device(&mvdev->vdev); } + +static const struct auxiliary_device_id mlx5v_id_table[] = { + { .name = MLX5_ADEV_NAME ".vnet", }, + {}, +}; + +MODULE_DEVICE_TABLE(auxiliary, mlx5v_id_table); + +static struct auxiliary_driver mlx5v_driver = { + .name = "vnet", + .probe = mlx5v_probe, + .remove = mlx5v_remove, + .id_table = mlx5v_id_table, +}; + +module_auxiliary_driver(mlx5v_driver); diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.h b/drivers/vdpa/mlx5/net/mlx5_vnet.h deleted file mode 100644 index f2d6d68b020e..000000000000 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.h +++ /dev/null @@ -1,24 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ -/* Copyright (c) 2020 Mellanox Technologies Ltd. */ - -#ifndef __MLX5_VNET_H_ -#define __MLX5_VNET_H_ - -#include <linux/vdpa.h> -#include <linux/virtio_net.h> -#include <linux/vringh.h> -#include <linux/mlx5/driver.h> -#include <linux/mlx5/cq.h> -#include <linux/mlx5/qp.h> -#include "mlx5_vdpa.h" - -static inline u32 mlx5_vdpa_max_qps(int max_vqs) -{ - return max_vqs / 2; -} - -#define to_mlx5_vdpa_ndev(__mvdev) container_of(__mvdev, struct mlx5_vdpa_net, mvdev) -void *mlx5_vdpa_add_dev(struct mlx5_core_dev *mdev); -void mlx5_vdpa_remove_dev(struct mlx5_vdpa_dev *mvdev); - -#endif /* __MLX5_VNET_H_ */ diff --git a/include/linux/auxiliary_bus.h b/include/linux/auxiliary_bus.h new file mode 100644 index 000000000000..fc51d45f106b --- /dev/null +++ b/include/linux/auxiliary_bus.h @@ -0,0 +1,77 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2019-2020 Intel Corporation + * + * Please see Documentation/driver-api/auxiliary_bus.rst for more information. + */ + +#ifndef _AUXILIARY_BUS_H_ +#define _AUXILIARY_BUS_H_ + +#include <linux/device.h> +#include <linux/mod_devicetable.h> + +struct auxiliary_device { + struct device dev; + const char *name; + u32 id; +}; + +struct auxiliary_driver { + int (*probe)(struct auxiliary_device *auxdev, const struct auxiliary_device_id *id); + void (*remove)(struct auxiliary_device *auxdev); + void (*shutdown)(struct auxiliary_device *auxdev); + int (*suspend)(struct auxiliary_device *auxdev, pm_message_t state); + int (*resume)(struct auxiliary_device *auxdev); + const char *name; + struct device_driver driver; + const struct auxiliary_device_id *id_table; +}; + +static inline struct auxiliary_device *to_auxiliary_dev(struct device *dev) +{ + return container_of(dev, struct auxiliary_device, dev); +} + +static inline struct auxiliary_driver *to_auxiliary_drv(struct device_driver *drv) +{ + return container_of(drv, struct auxiliary_driver, driver); +} + +int auxiliary_device_init(struct auxiliary_device *auxdev); +int __auxiliary_device_add(struct auxiliary_device *auxdev, const char *modname); +#define auxiliary_device_add(auxdev) __auxiliary_device_add(auxdev, KBUILD_MODNAME) + +static inline void auxiliary_device_uninit(struct auxiliary_device *auxdev) +{ + put_device(&auxdev->dev); +} + +static inline void auxiliary_device_delete(struct auxiliary_device *auxdev) +{ + device_del(&auxdev->dev); +} + +int __auxiliary_driver_register(struct auxiliary_driver *auxdrv, struct module *owner, + const char *modname); +#define auxiliary_driver_register(auxdrv) \ + __auxiliary_driver_register(auxdrv, THIS_MODULE, KBUILD_MODNAME) + +void auxiliary_driver_unregister(struct auxiliary_driver *auxdrv); + +/** + * module_auxiliary_driver() - Helper macro for registering an auxiliary driver + * @__auxiliary_driver: auxiliary driver struct + * + * Helper macro for auxiliary drivers which do not do anything special in + * module init/exit. This eliminates a lot of boilerplate. Each module may only + * use this macro once, and calling it replaces module_init() and module_exit() + */ +#define module_auxiliary_driver(__auxiliary_driver) \ + module_driver(__auxiliary_driver, auxiliary_driver_register, auxiliary_driver_unregister) + +struct auxiliary_device *auxiliary_find_device(struct device *start, + const void *data, + int (*match)(struct device *dev, const void *data)); + +#endif /* _AUXILIARY_BUS_H_ */ diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index fff7173e2b82..f93bfe7473aa 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -48,6 +48,7 @@ #include <linux/idr.h> #include <linux/notifier.h> #include <linux/refcount.h> +#include <linux/auxiliary_bus.h> #include <linux/mlx5/device.h> #include <linux/mlx5/doorbell.h> @@ -56,6 +57,8 @@ #include <linux/ptp_clock_kernel.h> #include <net/devlink.h> +#define MLX5_ADEV_NAME "mlx5_core" + enum { MLX5_BOARD_ID_LEN = 64, }; @@ -534,6 +537,17 @@ struct mlx5_core_roce { struct mlx5_flow_handle *allow_rule; }; +enum { + MLX5_PRIV_FLAGS_DISABLE_IB_ADEV = 1 << 0, + MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV = 1 << 1, +}; + +struct mlx5_adev { + struct auxiliary_device adev; + struct mlx5_core_dev *mdev; + int idx; +}; + struct mlx5_priv { /* IRQ table valid only for real pci devices PF or VF */ struct mlx5_irq_table *irq_table; @@ -571,6 +585,8 @@ struct mlx5_priv { struct list_head dev_list; struct list_head ctx_list; spinlock_t ctx_lock; + struct mlx5_adev **adev; + int adev_idx; struct mlx5_events *events; struct mlx5_flow_steering *steering; @@ -578,6 +594,7 @@ struct mlx5_priv { struct mlx5_eswitch *eswitch; struct mlx5_core_sriov sriov; struct mlx5_lag *lag; + u32 flags; struct mlx5_devcom *devcom; struct mlx5_fw_reset *fw_reset; struct mlx5_core_roce roce; @@ -1055,23 +1072,6 @@ enum { MAX_MR_CACHE_ENTRIES }; -enum { - MLX5_INTERFACE_PROTOCOL_IB = 0, - MLX5_INTERFACE_PROTOCOL_ETH = 1, - MLX5_INTERFACE_PROTOCOL_VDPA = 2, -}; - -struct mlx5_interface { - void * (*add)(struct mlx5_core_dev *dev); - void (*remove)(struct mlx5_core_dev *dev, void *context); - int (*attach)(struct mlx5_core_dev *dev, void *context); - void (*detach)(struct mlx5_core_dev *dev, void *context); - int protocol; - struct list_head list; -}; - -int mlx5_register_interface(struct mlx5_interface *intf); -void mlx5_unregister_interface(struct mlx5_interface *intf); int mlx5_notifier_register(struct mlx5_core_dev *dev, struct notifier_block *nb); int mlx5_notifier_unregister(struct mlx5_core_dev *dev, struct notifier_block *nb); int mlx5_eq_notifier_register(struct mlx5_core_dev *dev, struct mlx5_nb *nb); diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h index b0ae8020f13e..29fd832950e0 100644 --- a/include/linux/mlx5/eswitch.h +++ b/include/linux/mlx5/eswitch.h @@ -96,10 +96,10 @@ static inline u32 mlx5_eswitch_get_vport_metadata_mask(void) u32 mlx5_eswitch_get_vport_metadata_for_match(struct mlx5_eswitch *esw, u16 vport_num); -u8 mlx5_eswitch_mode(struct mlx5_eswitch *esw); +u8 mlx5_eswitch_mode(struct mlx5_core_dev *dev); #else /* CONFIG_MLX5_ESWITCH */ -static inline u8 mlx5_eswitch_mode(struct mlx5_eswitch *esw) +static inline u8 mlx5_eswitch_mode(struct mlx5_core_dev *dev) { return MLX5_ESWITCH_NONE; } @@ -136,4 +136,8 @@ mlx5_eswitch_get_vport_metadata_mask(void) } #endif /* CONFIG_MLX5_ESWITCH */ +static inline bool is_mdev_switchdev_mode(struct mlx5_core_dev *dev) +{ + return mlx5_eswitch_mode(dev) == MLX5_ESWITCH_OFFLOADS; +} #endif diff --git a/drivers/vdpa/mlx5/core/mlx5_vdpa_ifc.h b/include/linux/mlx5/mlx5_ifc_vdpa.h index f6f57a29b38e..98b56b75c625 100644 --- a/drivers/vdpa/mlx5/core/mlx5_vdpa_ifc.h +++ b/include/linux/mlx5/mlx5_ifc_vdpa.h @@ -1,10 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ /* Copyright (c) 2020 Mellanox Technologies Ltd. */ -#ifndef __MLX5_VDPA_IFC_H_ -#define __MLX5_VDPA_IFC_H_ - -#include <linux/mlx5/mlx5_ifc.h> +#ifndef __MLX5_IFC_VDPA_H_ +#define __MLX5_IFC_VDPA_H_ enum { MLX5_VIRTIO_Q_EVENT_MODE_NO_MSIX_MODE = 0x0, @@ -165,4 +163,4 @@ struct mlx5_ifc_modify_virtio_net_q_out_bits { struct mlx5_ifc_general_obj_out_cmd_hdr_bits general_obj_out_cmd_hdr; }; -#endif /* __MLX5_VDPA_IFC_H_ */ +#endif /* __MLX5_IFC_VDPA_H_ */ diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 5b08a473cdba..c425290b21e2 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -838,4 +838,12 @@ struct mhi_device_id { kernel_ulong_t driver_data; }; +#define AUXILIARY_NAME_SIZE 32 +#define AUXILIARY_MODULE_PREFIX "auxiliary:" + +struct auxiliary_device_id { + char name[AUXILIARY_NAME_SIZE]; + kernel_ulong_t driver_data; +}; + #endif /* LINUX_MOD_DEVICETABLE_H */ diff --git a/scripts/mod/devicetable-offsets.c b/scripts/mod/devicetable-offsets.c index 27007c18e754..e377f52dbfa3 100644 --- a/scripts/mod/devicetable-offsets.c +++ b/scripts/mod/devicetable-offsets.c @@ -243,5 +243,8 @@ int main(void) DEVID(mhi_device_id); DEVID_FIELD(mhi_device_id, chan); + DEVID(auxiliary_device_id); + DEVID_FIELD(auxiliary_device_id, name); + return 0; } diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c index 2417dd1dee33..fb4827027536 100644 --- a/scripts/mod/file2alias.c +++ b/scripts/mod/file2alias.c @@ -1364,6 +1364,13 @@ static int do_mhi_entry(const char *filename, void *symval, char *alias) { DEF_FIELD_ADDR(symval, mhi_device_id, chan); sprintf(alias, MHI_DEVICE_MODALIAS_FMT, *chan); + return 1; +} + +static int do_auxiliary_entry(const char *filename, void *symval, char *alias) +{ + DEF_FIELD_ADDR(symval, auxiliary_device_id, name); + sprintf(alias, AUXILIARY_MODULE_PREFIX "%s", *name); return 1; } @@ -1442,6 +1449,7 @@ static const struct devtable devtable[] = { {"tee", SIZE_tee_client_device_id, do_tee_entry}, {"wmi", SIZE_wmi_device_id, do_wmi_entry}, {"mhi", SIZE_mhi_device_id, do_mhi_entry}, + {"auxiliary", SIZE_auxiliary_device_id, do_auxiliary_entry}, }; /* Create MODULE_ALIAS() statements. |