summaryrefslogtreecommitdiffstats
path: root/drivers/net/ethernet/mellanox/mlx5/core/sf
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/net/ethernet/mellanox/mlx5/core/sf')
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/sf/cmd.c49
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c380
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.h56
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/sf/dev/diag/dev_tracepoint.h58
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c104
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c571
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/sf/diag/sf_tracepoint.h173
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/sf/diag/vhca_tracepoint.h40
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c364
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/sf/mlx5_ifc_vhca_event.h82
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/sf/priv.h22
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h65
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.c191
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.h56
14 files changed, 2211 insertions, 0 deletions
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/cmd.c
new file mode 100644
index 000000000..a8d75c2f0
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/cmd.c
@@ -0,0 +1,49 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2020 Mellanox Technologies Ltd */
+
+#include <linux/mlx5/driver.h>
+#include "priv.h"
+
+int mlx5_cmd_alloc_sf(struct mlx5_core_dev *dev, u16 function_id)
+{
+ u32 out[MLX5_ST_SZ_DW(alloc_sf_out)] = {};
+ u32 in[MLX5_ST_SZ_DW(alloc_sf_in)] = {};
+
+ MLX5_SET(alloc_sf_in, in, opcode, MLX5_CMD_OP_ALLOC_SF);
+ MLX5_SET(alloc_sf_in, in, function_id, function_id);
+
+ return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+}
+
+int mlx5_cmd_dealloc_sf(struct mlx5_core_dev *dev, u16 function_id)
+{
+ u32 out[MLX5_ST_SZ_DW(dealloc_sf_out)] = {};
+ u32 in[MLX5_ST_SZ_DW(dealloc_sf_in)] = {};
+
+ MLX5_SET(dealloc_sf_in, in, opcode, MLX5_CMD_OP_DEALLOC_SF);
+ MLX5_SET(dealloc_sf_in, in, function_id, function_id);
+
+ return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+}
+
+int mlx5_cmd_sf_enable_hca(struct mlx5_core_dev *dev, u16 func_id)
+{
+ u32 out[MLX5_ST_SZ_DW(enable_hca_out)] = {};
+ u32 in[MLX5_ST_SZ_DW(enable_hca_in)] = {};
+
+ MLX5_SET(enable_hca_in, in, opcode, MLX5_CMD_OP_ENABLE_HCA);
+ MLX5_SET(enable_hca_in, in, function_id, func_id);
+ MLX5_SET(enable_hca_in, in, embedded_cpu_function, 0);
+ return mlx5_cmd_exec(dev, &in, sizeof(in), &out, sizeof(out));
+}
+
+int mlx5_cmd_sf_disable_hca(struct mlx5_core_dev *dev, u16 func_id)
+{
+ u32 out[MLX5_ST_SZ_DW(disable_hca_out)] = {};
+ u32 in[MLX5_ST_SZ_DW(disable_hca_in)] = {};
+
+ MLX5_SET(disable_hca_in, in, opcode, MLX5_CMD_OP_DISABLE_HCA);
+ MLX5_SET(disable_hca_in, in, function_id, func_id);
+ MLX5_SET(enable_hca_in, in, embedded_cpu_function, 0);
+ return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c
new file mode 100644
index 000000000..8e2abbab0
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c
@@ -0,0 +1,380 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2020 Mellanox Technologies Ltd */
+
+#include <linux/mlx5/driver.h>
+#include <linux/mlx5/device.h>
+#include "mlx5_core.h"
+#include "dev.h"
+#include "sf/vhca_event.h"
+#include "sf/sf.h"
+#include "sf/mlx5_ifc_vhca_event.h"
+#include "ecpf.h"
+#define CREATE_TRACE_POINTS
+#include "diag/dev_tracepoint.h"
+
+struct mlx5_sf_dev_table {
+ struct xarray devices;
+ unsigned int max_sfs;
+ phys_addr_t base_address;
+ u64 sf_bar_length;
+ struct notifier_block nb;
+ struct mutex table_lock; /* Serializes sf life cycle and vhca state change handler */
+ struct workqueue_struct *active_wq;
+ struct work_struct work;
+ u8 stop_active_wq:1;
+ struct mlx5_core_dev *dev;
+};
+
+static bool mlx5_sf_dev_supported(const struct mlx5_core_dev *dev)
+{
+ return MLX5_CAP_GEN(dev, sf) && mlx5_vhca_event_supported(dev);
+}
+
+bool mlx5_sf_dev_allocated(const struct mlx5_core_dev *dev)
+{
+ struct mlx5_sf_dev_table *table = dev->priv.sf_dev_table;
+
+ return table && !xa_empty(&table->devices);
+}
+
+static ssize_t sfnum_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ struct auxiliary_device *adev = container_of(dev, struct auxiliary_device, dev);
+ struct mlx5_sf_dev *sf_dev = container_of(adev, struct mlx5_sf_dev, adev);
+
+ return sysfs_emit(buf, "%u\n", sf_dev->sfnum);
+}
+static DEVICE_ATTR_RO(sfnum);
+
+static struct attribute *sf_device_attrs[] = {
+ &dev_attr_sfnum.attr,
+ NULL,
+};
+
+static const struct attribute_group sf_attr_group = {
+ .attrs = sf_device_attrs,
+};
+
+static const struct attribute_group *sf_attr_groups[2] = {
+ &sf_attr_group,
+ NULL
+};
+
+static void mlx5_sf_dev_release(struct device *device)
+{
+ struct auxiliary_device *adev = container_of(device, struct auxiliary_device, dev);
+ struct mlx5_sf_dev *sf_dev = container_of(adev, struct mlx5_sf_dev, adev);
+
+ mlx5_adev_idx_free(adev->id);
+ kfree(sf_dev);
+}
+
+static void mlx5_sf_dev_remove(struct mlx5_core_dev *dev, struct mlx5_sf_dev *sf_dev)
+{
+ int id;
+
+ id = sf_dev->adev.id;
+ trace_mlx5_sf_dev_del(dev, sf_dev, id);
+
+ auxiliary_device_delete(&sf_dev->adev);
+ auxiliary_device_uninit(&sf_dev->adev);
+}
+
+static void mlx5_sf_dev_add(struct mlx5_core_dev *dev, u16 sf_index, u16 fn_id, u32 sfnum)
+{
+ struct mlx5_sf_dev_table *table = dev->priv.sf_dev_table;
+ struct mlx5_sf_dev *sf_dev;
+ struct pci_dev *pdev;
+ int err;
+ int id;
+
+ id = mlx5_adev_idx_alloc();
+ if (id < 0) {
+ err = id;
+ goto add_err;
+ }
+
+ sf_dev = kzalloc(sizeof(*sf_dev), GFP_KERNEL);
+ if (!sf_dev) {
+ mlx5_adev_idx_free(id);
+ err = -ENOMEM;
+ goto add_err;
+ }
+ pdev = dev->pdev;
+ sf_dev->adev.id = id;
+ sf_dev->adev.name = MLX5_SF_DEV_ID_NAME;
+ sf_dev->adev.dev.release = mlx5_sf_dev_release;
+ sf_dev->adev.dev.parent = &pdev->dev;
+ sf_dev->adev.dev.groups = sf_attr_groups;
+ sf_dev->sfnum = sfnum;
+ sf_dev->parent_mdev = dev;
+ sf_dev->fn_id = fn_id;
+
+ if (!table->max_sfs) {
+ mlx5_adev_idx_free(id);
+ kfree(sf_dev);
+ err = -EOPNOTSUPP;
+ goto add_err;
+ }
+ sf_dev->bar_base_addr = table->base_address + (sf_index * table->sf_bar_length);
+
+ trace_mlx5_sf_dev_add(dev, sf_dev, id);
+
+ err = auxiliary_device_init(&sf_dev->adev);
+ if (err) {
+ mlx5_adev_idx_free(id);
+ kfree(sf_dev);
+ goto add_err;
+ }
+
+ err = auxiliary_device_add(&sf_dev->adev);
+ if (err) {
+ put_device(&sf_dev->adev.dev);
+ goto add_err;
+ }
+
+ err = xa_insert(&table->devices, sf_index, sf_dev, GFP_KERNEL);
+ if (err)
+ goto xa_err;
+ return;
+
+xa_err:
+ mlx5_sf_dev_remove(dev, sf_dev);
+add_err:
+ mlx5_core_err(dev, "SF DEV: fail device add for index=%d sfnum=%d err=%d\n",
+ sf_index, sfnum, err);
+}
+
+static void mlx5_sf_dev_del(struct mlx5_core_dev *dev, struct mlx5_sf_dev *sf_dev, u16 sf_index)
+{
+ struct mlx5_sf_dev_table *table = dev->priv.sf_dev_table;
+
+ xa_erase(&table->devices, sf_index);
+ mlx5_sf_dev_remove(dev, sf_dev);
+}
+
+static int
+mlx5_sf_dev_state_change_handler(struct notifier_block *nb, unsigned long event_code, void *data)
+{
+ struct mlx5_sf_dev_table *table = container_of(nb, struct mlx5_sf_dev_table, nb);
+ const struct mlx5_vhca_state_event *event = data;
+ struct mlx5_sf_dev *sf_dev;
+ u16 max_functions;
+ u16 sf_index;
+ u16 base_id;
+
+ max_functions = mlx5_sf_max_functions(table->dev);
+ if (!max_functions)
+ return 0;
+
+ base_id = MLX5_CAP_GEN(table->dev, sf_base_id);
+ if (event->function_id < base_id || event->function_id >= (base_id + max_functions))
+ return 0;
+
+ sf_index = event->function_id - base_id;
+ mutex_lock(&table->table_lock);
+ sf_dev = xa_load(&table->devices, sf_index);
+ switch (event->new_vhca_state) {
+ case MLX5_VHCA_STATE_INVALID:
+ case MLX5_VHCA_STATE_ALLOCATED:
+ if (sf_dev)
+ mlx5_sf_dev_del(table->dev, sf_dev, sf_index);
+ break;
+ case MLX5_VHCA_STATE_TEARDOWN_REQUEST:
+ if (sf_dev)
+ mlx5_sf_dev_del(table->dev, sf_dev, sf_index);
+ else
+ mlx5_core_err(table->dev,
+ "SF DEV: teardown state for invalid dev index=%d fn_id=0x%x\n",
+ sf_index, event->sw_function_id);
+ break;
+ case MLX5_VHCA_STATE_ACTIVE:
+ if (!sf_dev)
+ mlx5_sf_dev_add(table->dev, sf_index, event->function_id,
+ event->sw_function_id);
+ break;
+ default:
+ break;
+ }
+ mutex_unlock(&table->table_lock);
+ return 0;
+}
+
+static int mlx5_sf_dev_vhca_arm_all(struct mlx5_sf_dev_table *table)
+{
+ struct mlx5_core_dev *dev = table->dev;
+ u16 max_functions;
+ u16 function_id;
+ int err = 0;
+ int i;
+
+ max_functions = mlx5_sf_max_functions(dev);
+ function_id = MLX5_CAP_GEN(dev, sf_base_id);
+ /* Arm the vhca context as the vhca event notifier */
+ for (i = 0; i < max_functions; i++) {
+ err = mlx5_vhca_event_arm(dev, function_id);
+ if (err)
+ return err;
+
+ function_id++;
+ }
+ return 0;
+}
+
+static void mlx5_sf_dev_add_active_work(struct work_struct *work)
+{
+ struct mlx5_sf_dev_table *table = container_of(work, struct mlx5_sf_dev_table, work);
+ u32 out[MLX5_ST_SZ_DW(query_vhca_state_out)] = {};
+ struct mlx5_core_dev *dev = table->dev;
+ u16 max_functions;
+ u16 function_id;
+ u16 sw_func_id;
+ int err = 0;
+ u8 state;
+ int i;
+
+ max_functions = mlx5_sf_max_functions(dev);
+ function_id = MLX5_CAP_GEN(dev, sf_base_id);
+ for (i = 0; i < max_functions; i++, function_id++) {
+ if (table->stop_active_wq)
+ return;
+ err = mlx5_cmd_query_vhca_state(dev, function_id, out, sizeof(out));
+ if (err)
+ /* A failure of specific vhca doesn't mean others will
+ * fail as well.
+ */
+ continue;
+ state = MLX5_GET(query_vhca_state_out, out, vhca_state_context.vhca_state);
+ if (state != MLX5_VHCA_STATE_ACTIVE)
+ continue;
+
+ sw_func_id = MLX5_GET(query_vhca_state_out, out, vhca_state_context.sw_function_id);
+ mutex_lock(&table->table_lock);
+ /* Don't probe device which is already probe */
+ if (!xa_load(&table->devices, i))
+ mlx5_sf_dev_add(dev, i, function_id, sw_func_id);
+ /* There is a race where SF got inactive after the query
+ * above. e.g.: the query returns that the state of the
+ * SF is active, and after that the eswitch manager set it to
+ * inactive.
+ * This case cannot be managed in SW, since the probing of the
+ * SF is on one system, and the inactivation is on a different
+ * system.
+ * If the inactive is done after the SF perform init_hca(),
+ * the SF will fully probe and then removed. If it was
+ * done before init_hca(), the SF probe will fail.
+ */
+ mutex_unlock(&table->table_lock);
+ }
+}
+
+/* In case SFs are generated externally, probe active SFs */
+static int mlx5_sf_dev_queue_active_work(struct mlx5_sf_dev_table *table)
+{
+ if (MLX5_CAP_GEN(table->dev, eswitch_manager))
+ return 0; /* the table is local */
+
+ /* Use a workqueue to probe active SFs, which are in large
+ * quantity and may take up to minutes to probe.
+ */
+ table->active_wq = create_singlethread_workqueue("mlx5_active_sf");
+ if (!table->active_wq)
+ return -ENOMEM;
+ INIT_WORK(&table->work, &mlx5_sf_dev_add_active_work);
+ queue_work(table->active_wq, &table->work);
+ return 0;
+}
+
+static void mlx5_sf_dev_destroy_active_work(struct mlx5_sf_dev_table *table)
+{
+ if (table->active_wq) {
+ table->stop_active_wq = true;
+ destroy_workqueue(table->active_wq);
+ }
+}
+
+void mlx5_sf_dev_table_create(struct mlx5_core_dev *dev)
+{
+ struct mlx5_sf_dev_table *table;
+ unsigned int max_sfs;
+ int err;
+
+ if (!mlx5_sf_dev_supported(dev) || !mlx5_vhca_event_supported(dev))
+ return;
+
+ table = kzalloc(sizeof(*table), GFP_KERNEL);
+ if (!table) {
+ err = -ENOMEM;
+ goto table_err;
+ }
+
+ table->nb.notifier_call = mlx5_sf_dev_state_change_handler;
+ table->dev = dev;
+ if (MLX5_CAP_GEN(dev, max_num_sf))
+ max_sfs = MLX5_CAP_GEN(dev, max_num_sf);
+ else
+ max_sfs = 1 << MLX5_CAP_GEN(dev, log_max_sf);
+ table->sf_bar_length = 1 << (MLX5_CAP_GEN(dev, log_min_sf_size) + 12);
+ table->base_address = pci_resource_start(dev->pdev, 2);
+ table->max_sfs = max_sfs;
+ xa_init(&table->devices);
+ mutex_init(&table->table_lock);
+ dev->priv.sf_dev_table = table;
+
+ err = mlx5_vhca_event_notifier_register(dev, &table->nb);
+ if (err)
+ goto vhca_err;
+
+ err = mlx5_sf_dev_queue_active_work(table);
+ if (err)
+ goto add_active_err;
+
+ err = mlx5_sf_dev_vhca_arm_all(table);
+ if (err)
+ goto arm_err;
+ mlx5_core_dbg(dev, "SF DEV: max sf devices=%d\n", max_sfs);
+ return;
+
+arm_err:
+ mlx5_sf_dev_destroy_active_work(table);
+add_active_err:
+ mlx5_vhca_event_notifier_unregister(dev, &table->nb);
+vhca_err:
+ table->max_sfs = 0;
+ kfree(table);
+ dev->priv.sf_dev_table = NULL;
+table_err:
+ mlx5_core_err(dev, "SF DEV table create err = %d\n", err);
+}
+
+static void mlx5_sf_dev_destroy_all(struct mlx5_sf_dev_table *table)
+{
+ struct mlx5_sf_dev *sf_dev;
+ unsigned long index;
+
+ xa_for_each(&table->devices, index, sf_dev) {
+ xa_erase(&table->devices, index);
+ mlx5_sf_dev_remove(table->dev, sf_dev);
+ }
+}
+
+void mlx5_sf_dev_table_destroy(struct mlx5_core_dev *dev)
+{
+ struct mlx5_sf_dev_table *table = dev->priv.sf_dev_table;
+
+ if (!table)
+ return;
+
+ mlx5_sf_dev_destroy_active_work(table);
+ mlx5_vhca_event_notifier_unregister(dev, &table->nb);
+ mutex_destroy(&table->table_lock);
+
+ /* Now that event handler is not running, it is safe to destroy
+ * the sf device without race.
+ */
+ mlx5_sf_dev_destroy_all(table);
+
+ WARN_ON(!xa_empty(&table->devices));
+ kfree(table);
+ dev->priv.sf_dev_table = NULL;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.h
new file mode 100644
index 000000000..2a66a427e
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.h
@@ -0,0 +1,56 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2020 Mellanox Technologies Ltd */
+
+#ifndef __MLX5_SF_DEV_H__
+#define __MLX5_SF_DEV_H__
+
+#ifdef CONFIG_MLX5_SF
+
+#include <linux/auxiliary_bus.h>
+
+#define MLX5_SF_DEV_ID_NAME "sf"
+
+struct mlx5_sf_dev {
+ struct auxiliary_device adev;
+ struct mlx5_core_dev *parent_mdev;
+ struct mlx5_core_dev *mdev;
+ phys_addr_t bar_base_addr;
+ u32 sfnum;
+ u16 fn_id;
+};
+
+void mlx5_sf_dev_table_create(struct mlx5_core_dev *dev);
+void mlx5_sf_dev_table_destroy(struct mlx5_core_dev *dev);
+
+int mlx5_sf_driver_register(void);
+void mlx5_sf_driver_unregister(void);
+
+bool mlx5_sf_dev_allocated(const struct mlx5_core_dev *dev);
+
+#else
+
+static inline void mlx5_sf_dev_table_create(struct mlx5_core_dev *dev)
+{
+}
+
+static inline void mlx5_sf_dev_table_destroy(struct mlx5_core_dev *dev)
+{
+}
+
+static inline int mlx5_sf_driver_register(void)
+{
+ return 0;
+}
+
+static inline void mlx5_sf_driver_unregister(void)
+{
+}
+
+static inline bool mlx5_sf_dev_allocated(const struct mlx5_core_dev *dev)
+{
+ return false;
+}
+
+#endif
+
+#endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/diag/dev_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/diag/dev_tracepoint.h
new file mode 100644
index 000000000..7f7c9af5d
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/diag/dev_tracepoint.h
@@ -0,0 +1,58 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM mlx5
+
+#if !defined(_MLX5_SF_DEV_TP_) || defined(TRACE_HEADER_MULTI_READ)
+#define _MLX5_SF_DEV_TP_
+
+#include <linux/tracepoint.h>
+#include <linux/mlx5/driver.h>
+#include "../../dev/dev.h"
+
+DECLARE_EVENT_CLASS(mlx5_sf_dev_template,
+ TP_PROTO(const struct mlx5_core_dev *dev,
+ const struct mlx5_sf_dev *sfdev,
+ int aux_id),
+ TP_ARGS(dev, sfdev, aux_id),
+ TP_STRUCT__entry(__string(devname, dev_name(dev->device))
+ __field(const struct mlx5_sf_dev*, sfdev)
+ __field(int, aux_id)
+ __field(u16, hw_fn_id)
+ __field(u32, sfnum)
+ ),
+ TP_fast_assign(__assign_str(devname, dev_name(dev->device));
+ __entry->sfdev = sfdev;
+ __entry->aux_id = aux_id;
+ __entry->hw_fn_id = sfdev->fn_id;
+ __entry->sfnum = sfdev->sfnum;
+ ),
+ TP_printk("(%s) sfdev=%pK aux_id=%d hw_id=0x%x sfnum=%u\n",
+ __get_str(devname), __entry->sfdev,
+ __entry->aux_id, __entry->hw_fn_id,
+ __entry->sfnum)
+);
+
+DEFINE_EVENT(mlx5_sf_dev_template, mlx5_sf_dev_add,
+ TP_PROTO(const struct mlx5_core_dev *dev,
+ const struct mlx5_sf_dev *sfdev,
+ int aux_id),
+ TP_ARGS(dev, sfdev, aux_id)
+ );
+
+DEFINE_EVENT(mlx5_sf_dev_template, mlx5_sf_dev_del,
+ TP_PROTO(const struct mlx5_core_dev *dev,
+ const struct mlx5_sf_dev *sfdev,
+ int aux_id),
+ TP_ARGS(dev, sfdev, aux_id)
+ );
+
+#endif /* _MLX5_SF_DEV_TP_ */
+
+/* This part must be outside protection */
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH sf/dev/diag
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE dev_tracepoint
+#include <trace/define_trace.h>
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c
new file mode 100644
index 000000000..2424cdf9c
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c
@@ -0,0 +1,104 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2020 Mellanox Technologies Ltd */
+
+#include <linux/mlx5/driver.h>
+#include <linux/mlx5/device.h>
+#include "mlx5_core.h"
+#include "dev.h"
+#include "devlink.h"
+
+static int mlx5_sf_dev_probe(struct auxiliary_device *adev, const struct auxiliary_device_id *id)
+{
+ struct mlx5_sf_dev *sf_dev = container_of(adev, struct mlx5_sf_dev, adev);
+ struct mlx5_core_dev *mdev;
+ struct devlink *devlink;
+ int err;
+
+ devlink = mlx5_devlink_alloc(&adev->dev);
+ if (!devlink)
+ return -ENOMEM;
+
+ mdev = devlink_priv(devlink);
+ mdev->device = &adev->dev;
+ mdev->pdev = sf_dev->parent_mdev->pdev;
+ mdev->bar_addr = sf_dev->bar_base_addr;
+ mdev->iseg_base = sf_dev->bar_base_addr;
+ mdev->coredev_type = MLX5_COREDEV_SF;
+ mdev->priv.parent_mdev = sf_dev->parent_mdev;
+ mdev->priv.adev_idx = adev->id;
+ sf_dev->mdev = mdev;
+
+ err = mlx5_mdev_init(mdev, MLX5_DEFAULT_PROF);
+ if (err) {
+ mlx5_core_warn(mdev, "mlx5_mdev_init on err=%d\n", err);
+ goto mdev_err;
+ }
+
+ mdev->iseg = ioremap(mdev->iseg_base, sizeof(*mdev->iseg));
+ if (!mdev->iseg) {
+ mlx5_core_warn(mdev, "remap error\n");
+ err = -ENOMEM;
+ goto remap_err;
+ }
+
+ err = mlx5_init_one(mdev);
+ if (err) {
+ mlx5_core_warn(mdev, "mlx5_init_one err=%d\n", err);
+ goto init_one_err;
+ }
+ devlink_register(devlink);
+ return 0;
+
+init_one_err:
+ iounmap(mdev->iseg);
+remap_err:
+ mlx5_mdev_uninit(mdev);
+mdev_err:
+ mlx5_devlink_free(devlink);
+ return err;
+}
+
+static void mlx5_sf_dev_remove(struct auxiliary_device *adev)
+{
+ struct mlx5_sf_dev *sf_dev = container_of(adev, struct mlx5_sf_dev, adev);
+ struct devlink *devlink = priv_to_devlink(sf_dev->mdev);
+
+ mlx5_drain_health_wq(sf_dev->mdev);
+ devlink_unregister(devlink);
+ mlx5_uninit_one(sf_dev->mdev);
+ iounmap(sf_dev->mdev->iseg);
+ mlx5_mdev_uninit(sf_dev->mdev);
+ mlx5_devlink_free(devlink);
+}
+
+static void mlx5_sf_dev_shutdown(struct auxiliary_device *adev)
+{
+ struct mlx5_sf_dev *sf_dev = container_of(adev, struct mlx5_sf_dev, adev);
+
+ mlx5_unload_one(sf_dev->mdev, false);
+}
+
+static const struct auxiliary_device_id mlx5_sf_dev_id_table[] = {
+ { .name = MLX5_ADEV_NAME "." MLX5_SF_DEV_ID_NAME, },
+ { },
+};
+
+MODULE_DEVICE_TABLE(auxiliary, mlx5_sf_dev_id_table);
+
+static struct auxiliary_driver mlx5_sf_driver = {
+ .name = MLX5_SF_DEV_ID_NAME,
+ .probe = mlx5_sf_dev_probe,
+ .remove = mlx5_sf_dev_remove,
+ .shutdown = mlx5_sf_dev_shutdown,
+ .id_table = mlx5_sf_dev_id_table,
+};
+
+int mlx5_sf_driver_register(void)
+{
+ return auxiliary_driver_register(&mlx5_sf_driver);
+}
+
+void mlx5_sf_driver_unregister(void)
+{
+ auxiliary_driver_unregister(&mlx5_sf_driver);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
new file mode 100644
index 000000000..7d955a4d9
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
@@ -0,0 +1,571 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2020 Mellanox Technologies Ltd */
+
+#include <linux/mlx5/driver.h>
+#include "eswitch.h"
+#include "priv.h"
+#include "sf/dev/dev.h"
+#include "mlx5_ifc_vhca_event.h"
+#include "vhca_event.h"
+#include "ecpf.h"
+#define CREATE_TRACE_POINTS
+#include "diag/sf_tracepoint.h"
+
+struct mlx5_sf {
+ struct devlink_port dl_port;
+ unsigned int port_index;
+ u32 controller;
+ u16 id;
+ u16 hw_fn_id;
+ u16 hw_state;
+};
+
+struct mlx5_sf_table {
+ struct mlx5_core_dev *dev; /* To refer from notifier context. */
+ struct xarray port_indices; /* port index based lookup. */
+ refcount_t refcount;
+ struct completion disable_complete;
+ struct mutex sf_state_lock; /* Serializes sf state among user cmds & vhca event handler. */
+ struct notifier_block esw_nb;
+ struct notifier_block vhca_nb;
+ u8 ecpu: 1;
+};
+
+static struct mlx5_sf *
+mlx5_sf_lookup_by_index(struct mlx5_sf_table *table, unsigned int port_index)
+{
+ return xa_load(&table->port_indices, port_index);
+}
+
+static struct mlx5_sf *
+mlx5_sf_lookup_by_function_id(struct mlx5_sf_table *table, unsigned int fn_id)
+{
+ unsigned long index;
+ struct mlx5_sf *sf;
+
+ xa_for_each(&table->port_indices, index, sf) {
+ if (sf->hw_fn_id == fn_id)
+ return sf;
+ }
+ return NULL;
+}
+
+static int mlx5_sf_id_insert(struct mlx5_sf_table *table, struct mlx5_sf *sf)
+{
+ return xa_insert(&table->port_indices, sf->port_index, sf, GFP_KERNEL);
+}
+
+static void mlx5_sf_id_erase(struct mlx5_sf_table *table, struct mlx5_sf *sf)
+{
+ xa_erase(&table->port_indices, sf->port_index);
+}
+
+static struct mlx5_sf *
+mlx5_sf_alloc(struct mlx5_sf_table *table, struct mlx5_eswitch *esw,
+ u32 controller, u32 sfnum, struct netlink_ext_ack *extack)
+{
+ unsigned int dl_port_index;
+ struct mlx5_sf *sf;
+ u16 hw_fn_id;
+ int id_err;
+ int err;
+
+ if (!mlx5_esw_offloads_controller_valid(esw, controller)) {
+ NL_SET_ERR_MSG_MOD(extack, "Invalid controller number");
+ return ERR_PTR(-EINVAL);
+ }
+
+ id_err = mlx5_sf_hw_table_sf_alloc(table->dev, controller, sfnum);
+ if (id_err < 0) {
+ err = id_err;
+ goto id_err;
+ }
+
+ sf = kzalloc(sizeof(*sf), GFP_KERNEL);
+ if (!sf) {
+ err = -ENOMEM;
+ goto alloc_err;
+ }
+ sf->id = id_err;
+ hw_fn_id = mlx5_sf_sw_to_hw_id(table->dev, controller, sf->id);
+ dl_port_index = mlx5_esw_vport_to_devlink_port_index(table->dev, hw_fn_id);
+ sf->port_index = dl_port_index;
+ sf->hw_fn_id = hw_fn_id;
+ sf->hw_state = MLX5_VHCA_STATE_ALLOCATED;
+ sf->controller = controller;
+
+ err = mlx5_sf_id_insert(table, sf);
+ if (err)
+ goto insert_err;
+
+ return sf;
+
+insert_err:
+ kfree(sf);
+alloc_err:
+ mlx5_sf_hw_table_sf_free(table->dev, controller, id_err);
+id_err:
+ if (err == -EEXIST)
+ NL_SET_ERR_MSG_MOD(extack, "SF already exist. Choose different sfnum");
+ return ERR_PTR(err);
+}
+
+static void mlx5_sf_free(struct mlx5_sf_table *table, struct mlx5_sf *sf)
+{
+ mlx5_sf_id_erase(table, sf);
+ mlx5_sf_hw_table_sf_free(table->dev, sf->controller, sf->id);
+ trace_mlx5_sf_free(table->dev, sf->port_index, sf->controller, sf->hw_fn_id);
+ kfree(sf);
+}
+
+static struct mlx5_sf_table *mlx5_sf_table_try_get(struct mlx5_core_dev *dev)
+{
+ struct mlx5_sf_table *table = dev->priv.sf_table;
+
+ if (!table)
+ return NULL;
+
+ return refcount_inc_not_zero(&table->refcount) ? table : NULL;
+}
+
+static void mlx5_sf_table_put(struct mlx5_sf_table *table)
+{
+ if (refcount_dec_and_test(&table->refcount))
+ complete(&table->disable_complete);
+}
+
+static enum devlink_port_fn_state mlx5_sf_to_devlink_state(u8 hw_state)
+{
+ switch (hw_state) {
+ case MLX5_VHCA_STATE_ACTIVE:
+ case MLX5_VHCA_STATE_IN_USE:
+ return DEVLINK_PORT_FN_STATE_ACTIVE;
+ case MLX5_VHCA_STATE_INVALID:
+ case MLX5_VHCA_STATE_ALLOCATED:
+ case MLX5_VHCA_STATE_TEARDOWN_REQUEST:
+ default:
+ return DEVLINK_PORT_FN_STATE_INACTIVE;
+ }
+}
+
+static enum devlink_port_fn_opstate mlx5_sf_to_devlink_opstate(u8 hw_state)
+{
+ switch (hw_state) {
+ case MLX5_VHCA_STATE_IN_USE:
+ case MLX5_VHCA_STATE_TEARDOWN_REQUEST:
+ return DEVLINK_PORT_FN_OPSTATE_ATTACHED;
+ case MLX5_VHCA_STATE_INVALID:
+ case MLX5_VHCA_STATE_ALLOCATED:
+ case MLX5_VHCA_STATE_ACTIVE:
+ default:
+ return DEVLINK_PORT_FN_OPSTATE_DETACHED;
+ }
+}
+
+static bool mlx5_sf_is_active(const struct mlx5_sf *sf)
+{
+ return sf->hw_state == MLX5_VHCA_STATE_ACTIVE || sf->hw_state == MLX5_VHCA_STATE_IN_USE;
+}
+
+int mlx5_devlink_sf_port_fn_state_get(struct devlink_port *dl_port,
+ enum devlink_port_fn_state *state,
+ enum devlink_port_fn_opstate *opstate,
+ struct netlink_ext_ack *extack)
+{
+ struct mlx5_core_dev *dev = devlink_priv(dl_port->devlink);
+ struct mlx5_sf_table *table;
+ struct mlx5_sf *sf;
+ int err = 0;
+
+ table = mlx5_sf_table_try_get(dev);
+ if (!table)
+ return -EOPNOTSUPP;
+
+ sf = mlx5_sf_lookup_by_index(table, dl_port->index);
+ if (!sf) {
+ err = -EOPNOTSUPP;
+ goto sf_err;
+ }
+ mutex_lock(&table->sf_state_lock);
+ *state = mlx5_sf_to_devlink_state(sf->hw_state);
+ *opstate = mlx5_sf_to_devlink_opstate(sf->hw_state);
+ mutex_unlock(&table->sf_state_lock);
+sf_err:
+ mlx5_sf_table_put(table);
+ return err;
+}
+
+static int mlx5_sf_activate(struct mlx5_core_dev *dev, struct mlx5_sf *sf,
+ struct netlink_ext_ack *extack)
+{
+ int err;
+
+ if (mlx5_sf_is_active(sf))
+ return 0;
+ if (sf->hw_state != MLX5_VHCA_STATE_ALLOCATED) {
+ NL_SET_ERR_MSG_MOD(extack, "SF is inactivated but it is still attached");
+ return -EBUSY;
+ }
+
+ err = mlx5_cmd_sf_enable_hca(dev, sf->hw_fn_id);
+ if (err)
+ return err;
+
+ sf->hw_state = MLX5_VHCA_STATE_ACTIVE;
+ trace_mlx5_sf_activate(dev, sf->port_index, sf->controller, sf->hw_fn_id);
+ return 0;
+}
+
+static int mlx5_sf_deactivate(struct mlx5_core_dev *dev, struct mlx5_sf *sf)
+{
+ int err;
+
+ if (!mlx5_sf_is_active(sf))
+ return 0;
+
+ err = mlx5_cmd_sf_disable_hca(dev, sf->hw_fn_id);
+ if (err)
+ return err;
+
+ sf->hw_state = MLX5_VHCA_STATE_TEARDOWN_REQUEST;
+ trace_mlx5_sf_deactivate(dev, sf->port_index, sf->controller, sf->hw_fn_id);
+ return 0;
+}
+
+static int mlx5_sf_state_set(struct mlx5_core_dev *dev, struct mlx5_sf_table *table,
+ struct mlx5_sf *sf,
+ enum devlink_port_fn_state state,
+ struct netlink_ext_ack *extack)
+{
+ int err = 0;
+
+ mutex_lock(&table->sf_state_lock);
+ if (state == mlx5_sf_to_devlink_state(sf->hw_state))
+ goto out;
+ if (state == DEVLINK_PORT_FN_STATE_ACTIVE)
+ err = mlx5_sf_activate(dev, sf, extack);
+ else if (state == DEVLINK_PORT_FN_STATE_INACTIVE)
+ err = mlx5_sf_deactivate(dev, sf);
+ else
+ err = -EINVAL;
+out:
+ mutex_unlock(&table->sf_state_lock);
+ return err;
+}
+
+int mlx5_devlink_sf_port_fn_state_set(struct devlink_port *dl_port,
+ enum devlink_port_fn_state state,
+ struct netlink_ext_ack *extack)
+{
+ struct mlx5_core_dev *dev = devlink_priv(dl_port->devlink);
+ struct mlx5_sf_table *table;
+ struct mlx5_sf *sf;
+ int err;
+
+ table = mlx5_sf_table_try_get(dev);
+ if (!table) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Port state set is only supported in eswitch switchdev mode or SF ports are disabled.");
+ return -EOPNOTSUPP;
+ }
+ sf = mlx5_sf_lookup_by_index(table, dl_port->index);
+ if (!sf) {
+ err = -ENODEV;
+ goto out;
+ }
+
+ err = mlx5_sf_state_set(dev, table, sf, state, extack);
+out:
+ mlx5_sf_table_put(table);
+ return err;
+}
+
+static int mlx5_sf_add(struct mlx5_core_dev *dev, struct mlx5_sf_table *table,
+ const struct devlink_port_new_attrs *new_attr,
+ struct netlink_ext_ack *extack,
+ unsigned int *new_port_index)
+{
+ struct mlx5_eswitch *esw = dev->priv.eswitch;
+ struct mlx5_sf *sf;
+ int err;
+
+ sf = mlx5_sf_alloc(table, esw, new_attr->controller, new_attr->sfnum, extack);
+ if (IS_ERR(sf))
+ return PTR_ERR(sf);
+
+ err = mlx5_esw_offloads_sf_vport_enable(esw, &sf->dl_port, sf->hw_fn_id,
+ new_attr->controller, new_attr->sfnum);
+ if (err)
+ goto esw_err;
+ *new_port_index = sf->port_index;
+ trace_mlx5_sf_add(dev, sf->port_index, sf->controller, sf->hw_fn_id, new_attr->sfnum);
+ return 0;
+
+esw_err:
+ mlx5_sf_free(table, sf);
+ return err;
+}
+
+static int
+mlx5_sf_new_check_attr(struct mlx5_core_dev *dev, const struct devlink_port_new_attrs *new_attr,
+ struct netlink_ext_ack *extack)
+{
+ if (new_attr->flavour != DEVLINK_PORT_FLAVOUR_PCI_SF) {
+ NL_SET_ERR_MSG_MOD(extack, "Driver supports only SF port addition");
+ return -EOPNOTSUPP;
+ }
+ if (new_attr->port_index_valid) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Driver does not support user defined port index assignment");
+ return -EOPNOTSUPP;
+ }
+ if (!new_attr->sfnum_valid) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "User must provide unique sfnum. Driver does not support auto assignment");
+ return -EOPNOTSUPP;
+ }
+ if (new_attr->controller_valid && new_attr->controller &&
+ !mlx5_core_is_ecpf_esw_manager(dev)) {
+ NL_SET_ERR_MSG_MOD(extack, "External controller is unsupported");
+ return -EOPNOTSUPP;
+ }
+ if (new_attr->pfnum != mlx5_get_dev_index(dev)) {
+ NL_SET_ERR_MSG_MOD(extack, "Invalid pfnum supplied");
+ return -EOPNOTSUPP;
+ }
+ return 0;
+}
+
+int mlx5_devlink_sf_port_new(struct devlink *devlink,
+ const struct devlink_port_new_attrs *new_attr,
+ struct netlink_ext_ack *extack,
+ unsigned int *new_port_index)
+{
+ struct mlx5_core_dev *dev = devlink_priv(devlink);
+ struct mlx5_sf_table *table;
+ int err;
+
+ err = mlx5_sf_new_check_attr(dev, new_attr, extack);
+ if (err)
+ return err;
+
+ table = mlx5_sf_table_try_get(dev);
+ if (!table) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Port add is only supported in eswitch switchdev mode or SF ports are disabled.");
+ return -EOPNOTSUPP;
+ }
+ err = mlx5_sf_add(dev, table, new_attr, extack, new_port_index);
+ mlx5_sf_table_put(table);
+ return err;
+}
+
+static void mlx5_sf_dealloc(struct mlx5_sf_table *table, struct mlx5_sf *sf)
+{
+ if (sf->hw_state == MLX5_VHCA_STATE_ALLOCATED) {
+ mlx5_sf_free(table, sf);
+ } else if (mlx5_sf_is_active(sf)) {
+ /* Even if its active, it is treated as in_use because by the time,
+ * it is disabled here, it may getting used. So it is safe to
+ * always look for the event to ensure that it is recycled only after
+ * firmware gives confirmation that it is detached by the driver.
+ */
+ mlx5_cmd_sf_disable_hca(table->dev, sf->hw_fn_id);
+ mlx5_sf_hw_table_sf_deferred_free(table->dev, sf->controller, sf->id);
+ kfree(sf);
+ } else {
+ mlx5_sf_hw_table_sf_deferred_free(table->dev, sf->controller, sf->id);
+ kfree(sf);
+ }
+}
+
+int mlx5_devlink_sf_port_del(struct devlink *devlink, unsigned int port_index,
+ struct netlink_ext_ack *extack)
+{
+ struct mlx5_core_dev *dev = devlink_priv(devlink);
+ struct mlx5_eswitch *esw = dev->priv.eswitch;
+ struct mlx5_sf_table *table;
+ struct mlx5_sf *sf;
+ int err = 0;
+
+ table = mlx5_sf_table_try_get(dev);
+ if (!table) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Port del is only supported in eswitch switchdev mode or SF ports are disabled.");
+ return -EOPNOTSUPP;
+ }
+ sf = mlx5_sf_lookup_by_index(table, port_index);
+ if (!sf) {
+ err = -ENODEV;
+ goto sf_err;
+ }
+
+ mlx5_esw_offloads_sf_vport_disable(esw, sf->hw_fn_id);
+ mlx5_sf_id_erase(table, sf);
+
+ mutex_lock(&table->sf_state_lock);
+ mlx5_sf_dealloc(table, sf);
+ mutex_unlock(&table->sf_state_lock);
+sf_err:
+ mlx5_sf_table_put(table);
+ return err;
+}
+
+static bool mlx5_sf_state_update_check(const struct mlx5_sf *sf, u8 new_state)
+{
+ if (sf->hw_state == MLX5_VHCA_STATE_ACTIVE && new_state == MLX5_VHCA_STATE_IN_USE)
+ return true;
+
+ if (sf->hw_state == MLX5_VHCA_STATE_IN_USE && new_state == MLX5_VHCA_STATE_ACTIVE)
+ return true;
+
+ if (sf->hw_state == MLX5_VHCA_STATE_TEARDOWN_REQUEST &&
+ new_state == MLX5_VHCA_STATE_ALLOCATED)
+ return true;
+
+ return false;
+}
+
+static int mlx5_sf_vhca_event(struct notifier_block *nb, unsigned long opcode, void *data)
+{
+ struct mlx5_sf_table *table = container_of(nb, struct mlx5_sf_table, vhca_nb);
+ const struct mlx5_vhca_state_event *event = data;
+ bool update = false;
+ struct mlx5_sf *sf;
+
+ table = mlx5_sf_table_try_get(table->dev);
+ if (!table)
+ return 0;
+
+ mutex_lock(&table->sf_state_lock);
+ sf = mlx5_sf_lookup_by_function_id(table, event->function_id);
+ if (!sf)
+ goto sf_err;
+
+ /* When driver is attached or detached to a function, an event
+ * notifies such state change.
+ */
+ update = mlx5_sf_state_update_check(sf, event->new_vhca_state);
+ if (update)
+ sf->hw_state = event->new_vhca_state;
+ trace_mlx5_sf_update_state(table->dev, sf->port_index, sf->controller,
+ sf->hw_fn_id, sf->hw_state);
+sf_err:
+ mutex_unlock(&table->sf_state_lock);
+ mlx5_sf_table_put(table);
+ return 0;
+}
+
+static void mlx5_sf_table_enable(struct mlx5_sf_table *table)
+{
+ init_completion(&table->disable_complete);
+ refcount_set(&table->refcount, 1);
+}
+
+static void mlx5_sf_deactivate_all(struct mlx5_sf_table *table)
+{
+ struct mlx5_eswitch *esw = table->dev->priv.eswitch;
+ unsigned long index;
+ struct mlx5_sf *sf;
+
+ /* At this point, no new user commands can start and no vhca event can
+ * arrive. It is safe to destroy all user created SFs.
+ */
+ xa_for_each(&table->port_indices, index, sf) {
+ mlx5_esw_offloads_sf_vport_disable(esw, sf->hw_fn_id);
+ mlx5_sf_id_erase(table, sf);
+ mlx5_sf_dealloc(table, sf);
+ }
+}
+
+static void mlx5_sf_table_disable(struct mlx5_sf_table *table)
+{
+ if (!refcount_read(&table->refcount))
+ return;
+
+ /* Balances with refcount_set; drop the reference so that new user cmd cannot start
+ * and new vhca event handler cannot run.
+ */
+ mlx5_sf_table_put(table);
+ wait_for_completion(&table->disable_complete);
+
+ mlx5_sf_deactivate_all(table);
+}
+
+static int mlx5_sf_esw_event(struct notifier_block *nb, unsigned long event, void *data)
+{
+ struct mlx5_sf_table *table = container_of(nb, struct mlx5_sf_table, esw_nb);
+ const struct mlx5_esw_event_info *mode = data;
+
+ switch (mode->new_mode) {
+ case MLX5_ESWITCH_OFFLOADS:
+ mlx5_sf_table_enable(table);
+ break;
+ case MLX5_ESWITCH_LEGACY:
+ mlx5_sf_table_disable(table);
+ break;
+ default:
+ break;
+ }
+
+ return 0;
+}
+
+static bool mlx5_sf_table_supported(const struct mlx5_core_dev *dev)
+{
+ return dev->priv.eswitch && MLX5_ESWITCH_MANAGER(dev) &&
+ mlx5_sf_hw_table_supported(dev);
+}
+
+int mlx5_sf_table_init(struct mlx5_core_dev *dev)
+{
+ struct mlx5_sf_table *table;
+ int err;
+
+ if (!mlx5_sf_table_supported(dev) || !mlx5_vhca_event_supported(dev))
+ return 0;
+
+ table = kzalloc(sizeof(*table), GFP_KERNEL);
+ if (!table)
+ return -ENOMEM;
+
+ mutex_init(&table->sf_state_lock);
+ table->dev = dev;
+ xa_init(&table->port_indices);
+ dev->priv.sf_table = table;
+ refcount_set(&table->refcount, 0);
+ table->esw_nb.notifier_call = mlx5_sf_esw_event;
+ err = mlx5_esw_event_notifier_register(dev->priv.eswitch, &table->esw_nb);
+ if (err)
+ goto reg_err;
+
+ table->vhca_nb.notifier_call = mlx5_sf_vhca_event;
+ err = mlx5_vhca_event_notifier_register(table->dev, &table->vhca_nb);
+ if (err)
+ goto vhca_err;
+
+ return 0;
+
+vhca_err:
+ mlx5_esw_event_notifier_unregister(dev->priv.eswitch, &table->esw_nb);
+reg_err:
+ mutex_destroy(&table->sf_state_lock);
+ kfree(table);
+ dev->priv.sf_table = NULL;
+ return err;
+}
+
+void mlx5_sf_table_cleanup(struct mlx5_core_dev *dev)
+{
+ struct mlx5_sf_table *table = dev->priv.sf_table;
+
+ if (!table)
+ return;
+
+ mlx5_vhca_event_notifier_unregister(table->dev, &table->vhca_nb);
+ mlx5_esw_event_notifier_unregister(dev->priv.eswitch, &table->esw_nb);
+ WARN_ON(refcount_read(&table->refcount));
+ mutex_destroy(&table->sf_state_lock);
+ WARN_ON(!xa_empty(&table->port_indices));
+ kfree(table);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/diag/sf_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/diag/sf_tracepoint.h
new file mode 100644
index 000000000..8bf1cd909
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/diag/sf_tracepoint.h
@@ -0,0 +1,173 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM mlx5
+
+#if !defined(_MLX5_SF_TP_) || defined(TRACE_HEADER_MULTI_READ)
+#define _MLX5_SF_TP_
+
+#include <linux/tracepoint.h>
+#include <linux/mlx5/driver.h>
+#include "sf/vhca_event.h"
+
+TRACE_EVENT(mlx5_sf_add,
+ TP_PROTO(const struct mlx5_core_dev *dev,
+ unsigned int port_index,
+ u32 controller,
+ u16 hw_fn_id,
+ u32 sfnum),
+ TP_ARGS(dev, port_index, controller, hw_fn_id, sfnum),
+ TP_STRUCT__entry(__string(devname, dev_name(dev->device))
+ __field(unsigned int, port_index)
+ __field(u32, controller)
+ __field(u16, hw_fn_id)
+ __field(u32, sfnum)
+ ),
+ TP_fast_assign(__assign_str(devname, dev_name(dev->device));
+ __entry->port_index = port_index;
+ __entry->controller = controller;
+ __entry->hw_fn_id = hw_fn_id;
+ __entry->sfnum = sfnum;
+ ),
+ TP_printk("(%s) port_index=%u controller=%u hw_id=0x%x sfnum=%u\n",
+ __get_str(devname), __entry->port_index, __entry->controller,
+ __entry->hw_fn_id, __entry->sfnum)
+);
+
+TRACE_EVENT(mlx5_sf_free,
+ TP_PROTO(const struct mlx5_core_dev *dev,
+ unsigned int port_index,
+ u32 controller,
+ u16 hw_fn_id),
+ TP_ARGS(dev, port_index, controller, hw_fn_id),
+ TP_STRUCT__entry(__string(devname, dev_name(dev->device))
+ __field(unsigned int, port_index)
+ __field(u32, controller)
+ __field(u16, hw_fn_id)
+ ),
+ TP_fast_assign(__assign_str(devname, dev_name(dev->device));
+ __entry->port_index = port_index;
+ __entry->controller = controller;
+ __entry->hw_fn_id = hw_fn_id;
+ ),
+ TP_printk("(%s) port_index=%u controller=%u hw_id=0x%x\n",
+ __get_str(devname), __entry->port_index, __entry->controller,
+ __entry->hw_fn_id)
+);
+
+TRACE_EVENT(mlx5_sf_hwc_alloc,
+ TP_PROTO(const struct mlx5_core_dev *dev,
+ u32 controller,
+ u16 hw_fn_id,
+ u32 sfnum),
+ TP_ARGS(dev, controller, hw_fn_id, sfnum),
+ TP_STRUCT__entry(__string(devname, dev_name(dev->device))
+ __field(u32, controller)
+ __field(u16, hw_fn_id)
+ __field(u32, sfnum)
+ ),
+ TP_fast_assign(__assign_str(devname, dev_name(dev->device));
+ __entry->controller = controller;
+ __entry->hw_fn_id = hw_fn_id;
+ __entry->sfnum = sfnum;
+ ),
+ TP_printk("(%s) controller=%u hw_id=0x%x sfnum=%u\n",
+ __get_str(devname), __entry->controller, __entry->hw_fn_id,
+ __entry->sfnum)
+);
+
+TRACE_EVENT(mlx5_sf_hwc_free,
+ TP_PROTO(const struct mlx5_core_dev *dev,
+ u16 hw_fn_id),
+ TP_ARGS(dev, hw_fn_id),
+ TP_STRUCT__entry(__string(devname, dev_name(dev->device))
+ __field(u16, hw_fn_id)
+ ),
+ TP_fast_assign(__assign_str(devname, dev_name(dev->device));
+ __entry->hw_fn_id = hw_fn_id;
+ ),
+ TP_printk("(%s) hw_id=0x%x\n", __get_str(devname), __entry->hw_fn_id)
+);
+
+TRACE_EVENT(mlx5_sf_hwc_deferred_free,
+ TP_PROTO(const struct mlx5_core_dev *dev,
+ u16 hw_fn_id),
+ TP_ARGS(dev, hw_fn_id),
+ TP_STRUCT__entry(__string(devname, dev_name(dev->device))
+ __field(u16, hw_fn_id)
+ ),
+ TP_fast_assign(__assign_str(devname, dev_name(dev->device));
+ __entry->hw_fn_id = hw_fn_id;
+ ),
+ TP_printk("(%s) hw_id=0x%x\n", __get_str(devname), __entry->hw_fn_id)
+);
+
+DECLARE_EVENT_CLASS(mlx5_sf_state_template,
+ TP_PROTO(const struct mlx5_core_dev *dev,
+ u32 port_index,
+ u32 controller,
+ u16 hw_fn_id),
+ TP_ARGS(dev, port_index, controller, hw_fn_id),
+ TP_STRUCT__entry(__string(devname, dev_name(dev->device))
+ __field(unsigned int, port_index)
+ __field(u32, controller)
+ __field(u16, hw_fn_id)),
+ TP_fast_assign(__assign_str(devname, dev_name(dev->device));
+ __entry->port_index = port_index;
+ __entry->controller = controller;
+ __entry->hw_fn_id = hw_fn_id;
+ ),
+ TP_printk("(%s) port_index=%u controller=%u hw_id=0x%x\n",
+ __get_str(devname), __entry->port_index, __entry->controller,
+ __entry->hw_fn_id)
+);
+
+DEFINE_EVENT(mlx5_sf_state_template, mlx5_sf_activate,
+ TP_PROTO(const struct mlx5_core_dev *dev,
+ u32 port_index,
+ u32 controller,
+ u16 hw_fn_id),
+ TP_ARGS(dev, port_index, controller, hw_fn_id)
+ );
+
+DEFINE_EVENT(mlx5_sf_state_template, mlx5_sf_deactivate,
+ TP_PROTO(const struct mlx5_core_dev *dev,
+ u32 port_index,
+ u32 controller,
+ u16 hw_fn_id),
+ TP_ARGS(dev, port_index, controller, hw_fn_id)
+ );
+
+TRACE_EVENT(mlx5_sf_update_state,
+ TP_PROTO(const struct mlx5_core_dev *dev,
+ unsigned int port_index,
+ u32 controller,
+ u16 hw_fn_id,
+ u8 state),
+ TP_ARGS(dev, port_index, controller, hw_fn_id, state),
+ TP_STRUCT__entry(__string(devname, dev_name(dev->device))
+ __field(unsigned int, port_index)
+ __field(u32, controller)
+ __field(u16, hw_fn_id)
+ __field(u8, state)
+ ),
+ TP_fast_assign(__assign_str(devname, dev_name(dev->device));
+ __entry->port_index = port_index;
+ __entry->controller = controller;
+ __entry->hw_fn_id = hw_fn_id;
+ __entry->state = state;
+ ),
+ TP_printk("(%s) port_index=%u controller=%u hw_id=0x%x state=%u\n",
+ __get_str(devname), __entry->port_index, __entry->controller,
+ __entry->hw_fn_id, __entry->state)
+);
+
+#endif /* _MLX5_SF_TP_ */
+
+/* This part must be outside protection */
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH sf/diag
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE sf_tracepoint
+#include <trace/define_trace.h>
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/diag/vhca_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/diag/vhca_tracepoint.h
new file mode 100644
index 000000000..fd814a190
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/diag/vhca_tracepoint.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM mlx5
+
+#if !defined(_MLX5_SF_VHCA_TP_) || defined(TRACE_HEADER_MULTI_READ)
+#define _MLX5_SF_VHCA_TP_
+
+#include <linux/tracepoint.h>
+#include <linux/mlx5/driver.h>
+#include "sf/vhca_event.h"
+
+TRACE_EVENT(mlx5_sf_vhca_event,
+ TP_PROTO(const struct mlx5_core_dev *dev,
+ const struct mlx5_vhca_state_event *event),
+ TP_ARGS(dev, event),
+ TP_STRUCT__entry(__string(devname, dev_name(dev->device))
+ __field(u16, hw_fn_id)
+ __field(u32, sfnum)
+ __field(u8, vhca_state)
+ ),
+ TP_fast_assign(__assign_str(devname, dev_name(dev->device));
+ __entry->hw_fn_id = event->function_id;
+ __entry->sfnum = event->sw_function_id;
+ __entry->vhca_state = event->new_vhca_state;
+ ),
+ TP_printk("(%s) hw_id=0x%x sfnum=%u vhca_state=%d\n",
+ __get_str(devname), __entry->hw_fn_id,
+ __entry->sfnum, __entry->vhca_state)
+);
+
+#endif /* _MLX5_SF_VHCA_TP_ */
+
+/* This part must be outside protection */
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH sf/diag
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE vhca_tracepoint
+#include <trace/define_trace.h>
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c
new file mode 100644
index 000000000..17aa34898
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c
@@ -0,0 +1,364 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2020 Mellanox Technologies Ltd */
+#include <linux/mlx5/driver.h>
+#include "vhca_event.h"
+#include "priv.h"
+#include "sf.h"
+#include "mlx5_ifc_vhca_event.h"
+#include "ecpf.h"
+#include "mlx5_core.h"
+#include "eswitch.h"
+#include "diag/sf_tracepoint.h"
+
+struct mlx5_sf_hw {
+ u32 usr_sfnum;
+ u8 allocated: 1;
+ u8 pending_delete: 1;
+};
+
+struct mlx5_sf_hwc_table {
+ struct mlx5_sf_hw *sfs;
+ int max_fn;
+ u16 start_fn_id;
+};
+
+enum mlx5_sf_hwc_index {
+ MLX5_SF_HWC_LOCAL,
+ MLX5_SF_HWC_EXTERNAL,
+ MLX5_SF_HWC_MAX,
+};
+
+struct mlx5_sf_hw_table {
+ struct mlx5_core_dev *dev;
+ struct mutex table_lock; /* Serializes sf deletion and vhca state change handler. */
+ struct notifier_block vhca_nb;
+ struct mlx5_sf_hwc_table hwc[MLX5_SF_HWC_MAX];
+};
+
+static struct mlx5_sf_hwc_table *
+mlx5_sf_controller_to_hwc(struct mlx5_core_dev *dev, u32 controller)
+{
+ int idx = !!controller;
+
+ return &dev->priv.sf_hw_table->hwc[idx];
+}
+
+u16 mlx5_sf_sw_to_hw_id(struct mlx5_core_dev *dev, u32 controller, u16 sw_id)
+{
+ struct mlx5_sf_hwc_table *hwc;
+
+ hwc = mlx5_sf_controller_to_hwc(dev, controller);
+ return hwc->start_fn_id + sw_id;
+}
+
+static u16 mlx5_sf_hw_to_sw_id(struct mlx5_sf_hwc_table *hwc, u16 hw_id)
+{
+ return hw_id - hwc->start_fn_id;
+}
+
+static struct mlx5_sf_hwc_table *
+mlx5_sf_table_fn_to_hwc(struct mlx5_sf_hw_table *table, u16 fn_id)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(table->hwc); i++) {
+ if (table->hwc[i].max_fn &&
+ fn_id >= table->hwc[i].start_fn_id &&
+ fn_id < (table->hwc[i].start_fn_id + table->hwc[i].max_fn))
+ return &table->hwc[i];
+ }
+ return NULL;
+}
+
+static int mlx5_sf_hw_table_id_alloc(struct mlx5_sf_hw_table *table, u32 controller,
+ u32 usr_sfnum)
+{
+ struct mlx5_sf_hwc_table *hwc;
+ int free_idx = -1;
+ int i;
+
+ hwc = mlx5_sf_controller_to_hwc(table->dev, controller);
+ if (!hwc->sfs)
+ return -ENOSPC;
+
+ for (i = 0; i < hwc->max_fn; i++) {
+ if (!hwc->sfs[i].allocated && free_idx == -1) {
+ free_idx = i;
+ continue;
+ }
+
+ if (hwc->sfs[i].allocated && hwc->sfs[i].usr_sfnum == usr_sfnum)
+ return -EEXIST;
+ }
+
+ if (free_idx == -1)
+ return -ENOSPC;
+
+ hwc->sfs[free_idx].usr_sfnum = usr_sfnum;
+ hwc->sfs[free_idx].allocated = true;
+ return free_idx;
+}
+
+static void mlx5_sf_hw_table_id_free(struct mlx5_sf_hw_table *table, u32 controller, int id)
+{
+ struct mlx5_sf_hwc_table *hwc;
+
+ hwc = mlx5_sf_controller_to_hwc(table->dev, controller);
+ hwc->sfs[id].allocated = false;
+ hwc->sfs[id].pending_delete = false;
+}
+
+int mlx5_sf_hw_table_sf_alloc(struct mlx5_core_dev *dev, u32 controller, u32 usr_sfnum)
+{
+ struct mlx5_sf_hw_table *table = dev->priv.sf_hw_table;
+ u16 hw_fn_id;
+ int sw_id;
+ int err;
+
+ if (!table)
+ return -EOPNOTSUPP;
+
+ mutex_lock(&table->table_lock);
+ sw_id = mlx5_sf_hw_table_id_alloc(table, controller, usr_sfnum);
+ if (sw_id < 0) {
+ err = sw_id;
+ goto exist_err;
+ }
+
+ hw_fn_id = mlx5_sf_sw_to_hw_id(dev, controller, sw_id);
+ err = mlx5_cmd_alloc_sf(dev, hw_fn_id);
+ if (err)
+ goto err;
+
+ err = mlx5_modify_vhca_sw_id(dev, hw_fn_id, usr_sfnum);
+ if (err)
+ goto vhca_err;
+
+ if (controller) {
+ /* If this SF is for external controller, SF manager
+ * needs to arm firmware to receive the events.
+ */
+ err = mlx5_vhca_event_arm(dev, hw_fn_id);
+ if (err)
+ goto vhca_err;
+ }
+
+ trace_mlx5_sf_hwc_alloc(dev, controller, hw_fn_id, usr_sfnum);
+ mutex_unlock(&table->table_lock);
+ return sw_id;
+
+vhca_err:
+ mlx5_cmd_dealloc_sf(dev, hw_fn_id);
+err:
+ mlx5_sf_hw_table_id_free(table, controller, sw_id);
+exist_err:
+ mutex_unlock(&table->table_lock);
+ return err;
+}
+
+void mlx5_sf_hw_table_sf_free(struct mlx5_core_dev *dev, u32 controller, u16 id)
+{
+ struct mlx5_sf_hw_table *table = dev->priv.sf_hw_table;
+ u16 hw_fn_id;
+
+ mutex_lock(&table->table_lock);
+ hw_fn_id = mlx5_sf_sw_to_hw_id(dev, controller, id);
+ mlx5_cmd_dealloc_sf(dev, hw_fn_id);
+ mlx5_sf_hw_table_id_free(table, controller, id);
+ mutex_unlock(&table->table_lock);
+}
+
+static void mlx5_sf_hw_table_hwc_sf_free(struct mlx5_core_dev *dev,
+ struct mlx5_sf_hwc_table *hwc, int idx)
+{
+ mlx5_cmd_dealloc_sf(dev, hwc->start_fn_id + idx);
+ hwc->sfs[idx].allocated = false;
+ hwc->sfs[idx].pending_delete = false;
+ trace_mlx5_sf_hwc_free(dev, hwc->start_fn_id + idx);
+}
+
+void mlx5_sf_hw_table_sf_deferred_free(struct mlx5_core_dev *dev, u32 controller, u16 id)
+{
+ struct mlx5_sf_hw_table *table = dev->priv.sf_hw_table;
+ u32 out[MLX5_ST_SZ_DW(query_vhca_state_out)] = {};
+ struct mlx5_sf_hwc_table *hwc;
+ u16 hw_fn_id;
+ u8 state;
+ int err;
+
+ hw_fn_id = mlx5_sf_sw_to_hw_id(dev, controller, id);
+ hwc = mlx5_sf_controller_to_hwc(dev, controller);
+ mutex_lock(&table->table_lock);
+ err = mlx5_cmd_query_vhca_state(dev, hw_fn_id, out, sizeof(out));
+ if (err)
+ goto err;
+ state = MLX5_GET(query_vhca_state_out, out, vhca_state_context.vhca_state);
+ if (state == MLX5_VHCA_STATE_ALLOCATED) {
+ mlx5_cmd_dealloc_sf(dev, hw_fn_id);
+ hwc->sfs[id].allocated = false;
+ } else {
+ hwc->sfs[id].pending_delete = true;
+ trace_mlx5_sf_hwc_deferred_free(dev, hw_fn_id);
+ }
+err:
+ mutex_unlock(&table->table_lock);
+}
+
+static void mlx5_sf_hw_table_hwc_dealloc_all(struct mlx5_core_dev *dev,
+ struct mlx5_sf_hwc_table *hwc)
+{
+ int i;
+
+ for (i = 0; i < hwc->max_fn; i++) {
+ if (hwc->sfs[i].allocated)
+ mlx5_sf_hw_table_hwc_sf_free(dev, hwc, i);
+ }
+}
+
+static void mlx5_sf_hw_table_dealloc_all(struct mlx5_sf_hw_table *table)
+{
+ mlx5_sf_hw_table_hwc_dealloc_all(table->dev, &table->hwc[MLX5_SF_HWC_EXTERNAL]);
+ mlx5_sf_hw_table_hwc_dealloc_all(table->dev, &table->hwc[MLX5_SF_HWC_LOCAL]);
+}
+
+static int mlx5_sf_hw_table_hwc_init(struct mlx5_sf_hwc_table *hwc, u16 max_fn, u16 base_id)
+{
+ struct mlx5_sf_hw *sfs;
+
+ if (!max_fn)
+ return 0;
+
+ sfs = kcalloc(max_fn, sizeof(*sfs), GFP_KERNEL);
+ if (!sfs)
+ return -ENOMEM;
+
+ hwc->sfs = sfs;
+ hwc->max_fn = max_fn;
+ hwc->start_fn_id = base_id;
+ return 0;
+}
+
+static void mlx5_sf_hw_table_hwc_cleanup(struct mlx5_sf_hwc_table *hwc)
+{
+ kfree(hwc->sfs);
+}
+
+int mlx5_sf_hw_table_init(struct mlx5_core_dev *dev)
+{
+ struct mlx5_sf_hw_table *table;
+ u16 max_ext_fn = 0;
+ u16 ext_base_id = 0;
+ u16 max_fn = 0;
+ u16 base_id;
+ int err;
+
+ if (!mlx5_vhca_event_supported(dev))
+ return 0;
+
+ if (mlx5_sf_supported(dev))
+ max_fn = mlx5_sf_max_functions(dev);
+
+ err = mlx5_esw_sf_max_hpf_functions(dev, &max_ext_fn, &ext_base_id);
+ if (err)
+ return err;
+
+ if (!max_fn && !max_ext_fn)
+ return 0;
+
+ table = kzalloc(sizeof(*table), GFP_KERNEL);
+ if (!table)
+ return -ENOMEM;
+
+ mutex_init(&table->table_lock);
+ table->dev = dev;
+ dev->priv.sf_hw_table = table;
+
+ base_id = mlx5_sf_start_function_id(dev);
+ err = mlx5_sf_hw_table_hwc_init(&table->hwc[MLX5_SF_HWC_LOCAL], max_fn, base_id);
+ if (err)
+ goto table_err;
+
+ err = mlx5_sf_hw_table_hwc_init(&table->hwc[MLX5_SF_HWC_EXTERNAL],
+ max_ext_fn, ext_base_id);
+ if (err)
+ goto ext_err;
+
+ mlx5_core_dbg(dev, "SF HW table: max sfs = %d, ext sfs = %d\n", max_fn, max_ext_fn);
+ return 0;
+
+ext_err:
+ mlx5_sf_hw_table_hwc_cleanup(&table->hwc[MLX5_SF_HWC_LOCAL]);
+table_err:
+ mutex_destroy(&table->table_lock);
+ kfree(table);
+ return err;
+}
+
+void mlx5_sf_hw_table_cleanup(struct mlx5_core_dev *dev)
+{
+ struct mlx5_sf_hw_table *table = dev->priv.sf_hw_table;
+
+ if (!table)
+ return;
+
+ mutex_destroy(&table->table_lock);
+ mlx5_sf_hw_table_hwc_cleanup(&table->hwc[MLX5_SF_HWC_EXTERNAL]);
+ mlx5_sf_hw_table_hwc_cleanup(&table->hwc[MLX5_SF_HWC_LOCAL]);
+ kfree(table);
+}
+
+static int mlx5_sf_hw_vhca_event(struct notifier_block *nb, unsigned long opcode, void *data)
+{
+ struct mlx5_sf_hw_table *table = container_of(nb, struct mlx5_sf_hw_table, vhca_nb);
+ const struct mlx5_vhca_state_event *event = data;
+ struct mlx5_sf_hwc_table *hwc;
+ struct mlx5_sf_hw *sf_hw;
+ u16 sw_id;
+
+ if (event->new_vhca_state != MLX5_VHCA_STATE_ALLOCATED)
+ return 0;
+
+ hwc = mlx5_sf_table_fn_to_hwc(table, event->function_id);
+ if (!hwc)
+ return 0;
+
+ sw_id = mlx5_sf_hw_to_sw_id(hwc, event->function_id);
+ sf_hw = &hwc->sfs[sw_id];
+
+ mutex_lock(&table->table_lock);
+ /* SF driver notified through firmware that SF is finally detached.
+ * Hence recycle the sf hardware id for reuse.
+ */
+ if (sf_hw->allocated && sf_hw->pending_delete)
+ mlx5_sf_hw_table_hwc_sf_free(table->dev, hwc, sw_id);
+ mutex_unlock(&table->table_lock);
+ return 0;
+}
+
+int mlx5_sf_hw_table_create(struct mlx5_core_dev *dev)
+{
+ struct mlx5_sf_hw_table *table = dev->priv.sf_hw_table;
+
+ if (!table)
+ return 0;
+
+ table->vhca_nb.notifier_call = mlx5_sf_hw_vhca_event;
+ return mlx5_vhca_event_notifier_register(dev, &table->vhca_nb);
+}
+
+void mlx5_sf_hw_table_destroy(struct mlx5_core_dev *dev)
+{
+ struct mlx5_sf_hw_table *table = dev->priv.sf_hw_table;
+
+ if (!table)
+ return;
+
+ mlx5_vhca_event_notifier_unregister(dev, &table->vhca_nb);
+ /* Dealloc SFs whose firmware event has been missed. */
+ mlx5_sf_hw_table_dealloc_all(table);
+}
+
+bool mlx5_sf_hw_table_supported(const struct mlx5_core_dev *dev)
+{
+ return !!dev->priv.sf_hw_table;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/mlx5_ifc_vhca_event.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/mlx5_ifc_vhca_event.h
new file mode 100644
index 000000000..4fc870140
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/mlx5_ifc_vhca_event.h
@@ -0,0 +1,82 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2020 Mellanox Technologies Ltd */
+
+#ifndef __MLX5_IFC_VHCA_EVENT_H__
+#define __MLX5_IFC_VHCA_EVENT_H__
+
+enum mlx5_ifc_vhca_state {
+ MLX5_VHCA_STATE_INVALID = 0x0,
+ MLX5_VHCA_STATE_ALLOCATED = 0x1,
+ MLX5_VHCA_STATE_ACTIVE = 0x2,
+ MLX5_VHCA_STATE_IN_USE = 0x3,
+ MLX5_VHCA_STATE_TEARDOWN_REQUEST = 0x4,
+};
+
+struct mlx5_ifc_vhca_state_context_bits {
+ u8 arm_change_event[0x1];
+ u8 reserved_at_1[0xb];
+ u8 vhca_state[0x4];
+ u8 reserved_at_10[0x10];
+
+ u8 sw_function_id[0x20];
+
+ u8 reserved_at_40[0x40];
+};
+
+struct mlx5_ifc_query_vhca_state_out_bits {
+ u8 status[0x8];
+ u8 reserved_at_8[0x18];
+
+ u8 syndrome[0x20];
+
+ u8 reserved_at_40[0x40];
+
+ struct mlx5_ifc_vhca_state_context_bits vhca_state_context;
+};
+
+struct mlx5_ifc_query_vhca_state_in_bits {
+ u8 opcode[0x10];
+ u8 uid[0x10];
+
+ u8 reserved_at_20[0x10];
+ u8 op_mod[0x10];
+
+ u8 embedded_cpu_function[0x1];
+ u8 reserved_at_41[0xf];
+ u8 function_id[0x10];
+
+ u8 reserved_at_60[0x20];
+};
+
+struct mlx5_ifc_vhca_state_field_select_bits {
+ u8 reserved_at_0[0x1e];
+ u8 sw_function_id[0x1];
+ u8 arm_change_event[0x1];
+};
+
+struct mlx5_ifc_modify_vhca_state_out_bits {
+ u8 status[0x8];
+ u8 reserved_at_8[0x18];
+
+ u8 syndrome[0x20];
+
+ u8 reserved_at_40[0x40];
+};
+
+struct mlx5_ifc_modify_vhca_state_in_bits {
+ u8 opcode[0x10];
+ u8 uid[0x10];
+
+ u8 reserved_at_20[0x10];
+ u8 op_mod[0x10];
+
+ u8 embedded_cpu_function[0x1];
+ u8 reserved_at_41[0xf];
+ u8 function_id[0x10];
+
+ struct mlx5_ifc_vhca_state_field_select_bits vhca_state_field_select;
+
+ struct mlx5_ifc_vhca_state_context_bits vhca_state_context;
+};
+
+#endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/priv.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/priv.h
new file mode 100644
index 000000000..7114f3fc3
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/priv.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2020 Mellanox Technologies Ltd */
+
+#ifndef __MLX5_SF_PRIV_H__
+#define __MLX5_SF_PRIV_H__
+
+#include <linux/mlx5/driver.h>
+
+int mlx5_cmd_alloc_sf(struct mlx5_core_dev *dev, u16 function_id);
+int mlx5_cmd_dealloc_sf(struct mlx5_core_dev *dev, u16 function_id);
+
+int mlx5_cmd_sf_enable_hca(struct mlx5_core_dev *dev, u16 func_id);
+int mlx5_cmd_sf_disable_hca(struct mlx5_core_dev *dev, u16 func_id);
+
+u16 mlx5_sf_sw_to_hw_id(struct mlx5_core_dev *dev, u32 controller, u16 sw_id);
+
+int mlx5_sf_hw_table_sf_alloc(struct mlx5_core_dev *dev, u32 controller, u32 usr_sfnum);
+void mlx5_sf_hw_table_sf_free(struct mlx5_core_dev *dev, u32 controller, u16 id);
+void mlx5_sf_hw_table_sf_deferred_free(struct mlx5_core_dev *dev, u32 controller, u16 id);
+bool mlx5_sf_hw_table_supported(const struct mlx5_core_dev *dev);
+
+#endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h
new file mode 100644
index 000000000..3a480e06e
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h
@@ -0,0 +1,65 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2020 Mellanox Technologies Ltd */
+
+#ifndef __MLX5_SF_H__
+#define __MLX5_SF_H__
+
+#include <linux/mlx5/driver.h>
+#include "lib/sf.h"
+
+#ifdef CONFIG_MLX5_SF_MANAGER
+
+int mlx5_sf_hw_table_init(struct mlx5_core_dev *dev);
+void mlx5_sf_hw_table_cleanup(struct mlx5_core_dev *dev);
+
+int mlx5_sf_hw_table_create(struct mlx5_core_dev *dev);
+void mlx5_sf_hw_table_destroy(struct mlx5_core_dev *dev);
+
+int mlx5_sf_table_init(struct mlx5_core_dev *dev);
+void mlx5_sf_table_cleanup(struct mlx5_core_dev *dev);
+
+int mlx5_devlink_sf_port_new(struct devlink *devlink,
+ const struct devlink_port_new_attrs *add_attr,
+ struct netlink_ext_ack *extack,
+ unsigned int *new_port_index);
+int mlx5_devlink_sf_port_del(struct devlink *devlink, unsigned int port_index,
+ struct netlink_ext_ack *extack);
+int mlx5_devlink_sf_port_fn_state_get(struct devlink_port *dl_port,
+ enum devlink_port_fn_state *state,
+ enum devlink_port_fn_opstate *opstate,
+ struct netlink_ext_ack *extack);
+int mlx5_devlink_sf_port_fn_state_set(struct devlink_port *dl_port,
+ enum devlink_port_fn_state state,
+ struct netlink_ext_ack *extack);
+#else
+
+static inline int mlx5_sf_hw_table_init(struct mlx5_core_dev *dev)
+{
+ return 0;
+}
+
+static inline void mlx5_sf_hw_table_cleanup(struct mlx5_core_dev *dev)
+{
+}
+
+static inline int mlx5_sf_hw_table_create(struct mlx5_core_dev *dev)
+{
+ return 0;
+}
+
+static inline void mlx5_sf_hw_table_destroy(struct mlx5_core_dev *dev)
+{
+}
+
+static inline int mlx5_sf_table_init(struct mlx5_core_dev *dev)
+{
+ return 0;
+}
+
+static inline void mlx5_sf_table_cleanup(struct mlx5_core_dev *dev)
+{
+}
+
+#endif
+
+#endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.c
new file mode 100644
index 000000000..d908fba96
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.c
@@ -0,0 +1,191 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2020 Mellanox Technologies Ltd */
+
+#include <linux/mlx5/driver.h>
+#include "mlx5_ifc_vhca_event.h"
+#include "mlx5_core.h"
+#include "vhca_event.h"
+#include "ecpf.h"
+#define CREATE_TRACE_POINTS
+#include "diag/vhca_tracepoint.h"
+
+struct mlx5_vhca_state_notifier {
+ struct mlx5_core_dev *dev;
+ struct mlx5_nb nb;
+ struct blocking_notifier_head n_head;
+};
+
+struct mlx5_vhca_event_work {
+ struct work_struct work;
+ struct mlx5_vhca_state_notifier *notifier;
+ struct mlx5_vhca_state_event event;
+};
+
+int mlx5_cmd_query_vhca_state(struct mlx5_core_dev *dev, u16 function_id, u32 *out, u32 outlen)
+{
+ u32 in[MLX5_ST_SZ_DW(query_vhca_state_in)] = {};
+
+ MLX5_SET(query_vhca_state_in, in, opcode, MLX5_CMD_OP_QUERY_VHCA_STATE);
+ MLX5_SET(query_vhca_state_in, in, function_id, function_id);
+ MLX5_SET(query_vhca_state_in, in, embedded_cpu_function, 0);
+
+ return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen);
+}
+
+static int mlx5_cmd_modify_vhca_state(struct mlx5_core_dev *dev, u16 function_id,
+ u32 *in, u32 inlen)
+{
+ u32 out[MLX5_ST_SZ_DW(modify_vhca_state_out)] = {};
+
+ MLX5_SET(modify_vhca_state_in, in, opcode, MLX5_CMD_OP_MODIFY_VHCA_STATE);
+ MLX5_SET(modify_vhca_state_in, in, function_id, function_id);
+ MLX5_SET(modify_vhca_state_in, in, embedded_cpu_function, 0);
+
+ return mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
+}
+
+int mlx5_modify_vhca_sw_id(struct mlx5_core_dev *dev, u16 function_id, u32 sw_fn_id)
+{
+ u32 out[MLX5_ST_SZ_DW(modify_vhca_state_out)] = {};
+ u32 in[MLX5_ST_SZ_DW(modify_vhca_state_in)] = {};
+
+ MLX5_SET(modify_vhca_state_in, in, opcode, MLX5_CMD_OP_MODIFY_VHCA_STATE);
+ MLX5_SET(modify_vhca_state_in, in, function_id, function_id);
+ MLX5_SET(modify_vhca_state_in, in, embedded_cpu_function, 0);
+ MLX5_SET(modify_vhca_state_in, in, vhca_state_field_select.sw_function_id, 1);
+ MLX5_SET(modify_vhca_state_in, in, vhca_state_context.sw_function_id, sw_fn_id);
+
+ return mlx5_cmd_exec_inout(dev, modify_vhca_state, in, out);
+}
+
+int mlx5_vhca_event_arm(struct mlx5_core_dev *dev, u16 function_id)
+{
+ u32 in[MLX5_ST_SZ_DW(modify_vhca_state_in)] = {};
+
+ MLX5_SET(modify_vhca_state_in, in, vhca_state_context.arm_change_event, 1);
+ MLX5_SET(modify_vhca_state_in, in, vhca_state_field_select.arm_change_event, 1);
+
+ return mlx5_cmd_modify_vhca_state(dev, function_id, in, sizeof(in));
+}
+
+static void
+mlx5_vhca_event_notify(struct mlx5_core_dev *dev, struct mlx5_vhca_state_event *event)
+{
+ u32 out[MLX5_ST_SZ_DW(query_vhca_state_out)] = {};
+ int err;
+
+ err = mlx5_cmd_query_vhca_state(dev, event->function_id, out, sizeof(out));
+ if (err)
+ return;
+
+ event->sw_function_id = MLX5_GET(query_vhca_state_out, out,
+ vhca_state_context.sw_function_id);
+ event->new_vhca_state = MLX5_GET(query_vhca_state_out, out,
+ vhca_state_context.vhca_state);
+
+ mlx5_vhca_event_arm(dev, event->function_id);
+ trace_mlx5_sf_vhca_event(dev, event);
+
+ blocking_notifier_call_chain(&dev->priv.vhca_state_notifier->n_head, 0, event);
+}
+
+static void mlx5_vhca_state_work_handler(struct work_struct *_work)
+{
+ struct mlx5_vhca_event_work *work = container_of(_work, struct mlx5_vhca_event_work, work);
+ struct mlx5_vhca_state_notifier *notifier = work->notifier;
+ struct mlx5_core_dev *dev = notifier->dev;
+
+ mlx5_vhca_event_notify(dev, &work->event);
+ kfree(work);
+}
+
+static int
+mlx5_vhca_state_change_notifier(struct notifier_block *nb, unsigned long type, void *data)
+{
+ struct mlx5_vhca_state_notifier *notifier =
+ mlx5_nb_cof(nb, struct mlx5_vhca_state_notifier, nb);
+ struct mlx5_vhca_event_work *work;
+ struct mlx5_eqe *eqe = data;
+
+ work = kzalloc(sizeof(*work), GFP_ATOMIC);
+ if (!work)
+ return NOTIFY_DONE;
+ INIT_WORK(&work->work, &mlx5_vhca_state_work_handler);
+ work->notifier = notifier;
+ work->event.function_id = be16_to_cpu(eqe->data.vhca_state.function_id);
+ mlx5_events_work_enqueue(notifier->dev, &work->work);
+ return NOTIFY_OK;
+}
+
+void mlx5_vhca_state_cap_handle(struct mlx5_core_dev *dev, void *set_hca_cap)
+{
+ if (!mlx5_vhca_event_supported(dev))
+ return;
+
+ MLX5_SET(cmd_hca_cap, set_hca_cap, vhca_state, 1);
+ MLX5_SET(cmd_hca_cap, set_hca_cap, event_on_vhca_state_allocated, 1);
+ MLX5_SET(cmd_hca_cap, set_hca_cap, event_on_vhca_state_active, 1);
+ MLX5_SET(cmd_hca_cap, set_hca_cap, event_on_vhca_state_in_use, 1);
+ MLX5_SET(cmd_hca_cap, set_hca_cap, event_on_vhca_state_teardown_request, 1);
+}
+
+int mlx5_vhca_event_init(struct mlx5_core_dev *dev)
+{
+ struct mlx5_vhca_state_notifier *notifier;
+
+ if (!mlx5_vhca_event_supported(dev))
+ return 0;
+
+ notifier = kzalloc(sizeof(*notifier), GFP_KERNEL);
+ if (!notifier)
+ return -ENOMEM;
+
+ dev->priv.vhca_state_notifier = notifier;
+ notifier->dev = dev;
+ BLOCKING_INIT_NOTIFIER_HEAD(&notifier->n_head);
+ MLX5_NB_INIT(&notifier->nb, mlx5_vhca_state_change_notifier, VHCA_STATE_CHANGE);
+ return 0;
+}
+
+void mlx5_vhca_event_cleanup(struct mlx5_core_dev *dev)
+{
+ if (!mlx5_vhca_event_supported(dev))
+ return;
+
+ kfree(dev->priv.vhca_state_notifier);
+ dev->priv.vhca_state_notifier = NULL;
+}
+
+void mlx5_vhca_event_start(struct mlx5_core_dev *dev)
+{
+ struct mlx5_vhca_state_notifier *notifier;
+
+ if (!dev->priv.vhca_state_notifier)
+ return;
+
+ notifier = dev->priv.vhca_state_notifier;
+ mlx5_eq_notifier_register(dev, &notifier->nb);
+}
+
+void mlx5_vhca_event_stop(struct mlx5_core_dev *dev)
+{
+ struct mlx5_vhca_state_notifier *notifier;
+
+ if (!dev->priv.vhca_state_notifier)
+ return;
+
+ notifier = dev->priv.vhca_state_notifier;
+ mlx5_eq_notifier_unregister(dev, &notifier->nb);
+}
+
+int mlx5_vhca_event_notifier_register(struct mlx5_core_dev *dev, struct notifier_block *nb)
+{
+ if (!dev->priv.vhca_state_notifier)
+ return -EOPNOTSUPP;
+ return blocking_notifier_chain_register(&dev->priv.vhca_state_notifier->n_head, nb);
+}
+
+void mlx5_vhca_event_notifier_unregister(struct mlx5_core_dev *dev, struct notifier_block *nb)
+{
+ blocking_notifier_chain_unregister(&dev->priv.vhca_state_notifier->n_head, nb);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.h
new file mode 100644
index 000000000..013cdfe90
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.h
@@ -0,0 +1,56 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2020 Mellanox Technologies Ltd */
+
+#ifndef __MLX5_VHCA_EVENT_H__
+#define __MLX5_VHCA_EVENT_H__
+
+#ifdef CONFIG_MLX5_SF
+
+struct mlx5_vhca_state_event {
+ u16 function_id;
+ u16 sw_function_id;
+ u8 new_vhca_state;
+};
+
+static inline bool mlx5_vhca_event_supported(const struct mlx5_core_dev *dev)
+{
+ return MLX5_CAP_GEN_MAX(dev, vhca_state);
+}
+
+void mlx5_vhca_state_cap_handle(struct mlx5_core_dev *dev, void *set_hca_cap);
+int mlx5_vhca_event_init(struct mlx5_core_dev *dev);
+void mlx5_vhca_event_cleanup(struct mlx5_core_dev *dev);
+void mlx5_vhca_event_start(struct mlx5_core_dev *dev);
+void mlx5_vhca_event_stop(struct mlx5_core_dev *dev);
+int mlx5_vhca_event_notifier_register(struct mlx5_core_dev *dev, struct notifier_block *nb);
+void mlx5_vhca_event_notifier_unregister(struct mlx5_core_dev *dev, struct notifier_block *nb);
+int mlx5_modify_vhca_sw_id(struct mlx5_core_dev *dev, u16 function_id, u32 sw_fn_id);
+int mlx5_vhca_event_arm(struct mlx5_core_dev *dev, u16 function_id);
+int mlx5_cmd_query_vhca_state(struct mlx5_core_dev *dev, u16 function_id,
+ u32 *out, u32 outlen);
+#else
+
+static inline void mlx5_vhca_state_cap_handle(struct mlx5_core_dev *dev, void *set_hca_cap)
+{
+}
+
+static inline int mlx5_vhca_event_init(struct mlx5_core_dev *dev)
+{
+ return 0;
+}
+
+static inline void mlx5_vhca_event_cleanup(struct mlx5_core_dev *dev)
+{
+}
+
+static inline void mlx5_vhca_event_start(struct mlx5_core_dev *dev)
+{
+}
+
+static inline void mlx5_vhca_event_stop(struct mlx5_core_dev *dev)
+{
+}
+
+#endif
+
+#endif