[PATCH net-next RFC v2 00/13] Add devlink reload action option

@@ -14,6 +14,7 @@ struct mlx5_fw_reset {
 	struct work_struct reset_request_work;
 	struct work_struct reset_reload_work;
 	struct work_struct reset_now_work;
+	struct work_struct reset_abort_work;
 	unsigned long reset_flags;
 	struct timer_list timer;
 };

@@ -266,6 +267,16 @@ static void mlx5_sync_reset_now_event(struct work_struct *work)
 	mlx5_load_one(dev, false);
 }
 
+static void mlx5_sync_reset_abort_event(struct work_struct *work)
+{
+	struct mlx5_fw_reset *fw_reset = container_of(work, struct mlx5_fw_reset,
+						      reset_abort_work);
+	struct mlx5_core_dev *dev = fw_reset->dev;
+
+	mlx5_sync_reset_clear_reset_requested(dev, true);
+	mlx5_core_warn(dev, "PCI Sync FW Update Reset Aborted.\n");
+}
+
 static void mlx5_sync_reset_events_handle(struct mlx5_fw_reset *fw_reset, struct mlx5_eqe *eqe)
 {
 	struct mlx5_eqe_sync_fw_update *sync_fw_update_eqe;

@@ -280,6 +291,9 @@ static void mlx5_sync_reset_events_handle(struct mlx5_fw_reset *fw_reset, struct
 	case MLX5_SYNC_RST_STATE_RESET_NOW:
 		queue_work(fw_reset->wq, &fw_reset->reset_now_work);
 		break;
+	case MLX5_SYNC_RST_STATE_RESET_ABORT:
+		queue_work(fw_reset->wq, &fw_reset->reset_abort_work);
+		break;
 	}
 }
 

@@ -317,6 +331,7 @@ int mlx5_fw_reset_events_init(struct mlx5_core_dev *dev)
 	INIT_WORK(&fw_reset->reset_request_work, mlx5_sync_reset_request_event);
 	INIT_WORK(&fw_reset->reset_reload_work, mlx5_sync_reset_reload_work);
 	INIT_WORK(&fw_reset->reset_now_work, mlx5_sync_reset_now_event);
+	INIT_WORK(&fw_reset->reset_abort_work, mlx5_sync_reset_abort_event);
 
 	MLX5_NB_INIT(&fw_reset->nb, fw_reset_event_notifier, GENERAL_EVENT);
 	mlx5_eq_notifier_register(dev, &fw_reset->nb);

@@ -3935,6 +3935,7 @@ static int mlx4_restart_one_up(struct pci_dev *pdev, bool reload,
 			       struct devlink *devlink);
 
 static int mlx4_devlink_reload_down(struct devlink *devlink, bool netns_change,
+				    enum devlink_reload_action action,
 				    struct netlink_ext_ack *extack)
 {
 	struct mlx4_priv *priv = devlink_priv(devlink);

@@ -3951,7 +3952,7 @@ static int mlx4_devlink_reload_down(struct devlink *devlink, bool netns_change,
 	return 0;
 }
 
-static int mlx4_devlink_reload_up(struct devlink *devlink,
+static int mlx4_devlink_reload_up(struct devlink *devlink, enum devlink_reload_action action,
 				  struct netlink_ext_ack *extack)
 {
 	struct mlx4_priv *priv = devlink_priv(devlink);

@@ -3969,6 +3970,7 @@ static int mlx4_devlink_reload_up(struct devlink *devlink,
 
 static const struct devlink_ops mlx4_devlink_ops = {
 	.port_type_set	= mlx4_devlink_port_type_set,
+	.supported_reload_actions = BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT),
 	.reload_down	= mlx4_devlink_reload_down,
 	.reload_up	= mlx4_devlink_reload_up,
 };

@@ -89,6 +89,7 @@ mlx5_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req,
 }
 
 static int mlx5_devlink_reload_down(struct devlink *devlink, bool netns_change,
+				    enum devlink_reload_action action,
 				    struct netlink_ext_ack *extack)
 {
 	struct mlx5_core_dev *dev = devlink_priv(devlink);

@@ -97,7 +98,7 @@ static int mlx5_devlink_reload_down(struct devlink *devlink, bool netns_change,
 	return 0;
 }
 
-static int mlx5_devlink_reload_up(struct devlink *devlink,
+static int mlx5_devlink_reload_up(struct devlink *devlink, enum devlink_reload_action action,
 				  struct netlink_ext_ack *extack)
 {
 	struct mlx5_core_dev *dev = devlink_priv(devlink);

@@ -118,6 +119,7 @@ static const struct devlink_ops mlx5_devlink_ops = {
 #endif
 	.flash_update = mlx5_devlink_flash_update,
 	.info_get = mlx5_devlink_info_get,
+	.supported_reload_actions = BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT),
 	.reload_down = mlx5_devlink_reload_down,
 	.reload_up = mlx5_devlink_reload_up,
 };

@@ -1113,7 +1113,7 @@ mlxsw_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req,
 
 static int
 mlxsw_devlink_core_bus_device_reload_down(struct devlink *devlink,
-					  bool netns_change,
+					  bool netns_change, enum devlink_reload_action action,
 					  struct netlink_ext_ack *extack)
 {
 	struct mlxsw_core *mlxsw_core = devlink_priv(devlink);

@@ -1126,7 +1126,7 @@ mlxsw_devlink_core_bus_device_reload_down(struct devlink *devlink,
 }
 
 static int
-mlxsw_devlink_core_bus_device_reload_up(struct devlink *devlink,
+mlxsw_devlink_core_bus_device_reload_up(struct devlink *devlink, enum devlink_reload_action action,
 					struct netlink_ext_ack *extack)
 {
 	struct mlxsw_core *mlxsw_core = devlink_priv(devlink);

@@ -1268,6 +1268,8 @@ mlxsw_devlink_trap_policer_counter_get(struct devlink *devlink,
 }
 
 static const struct devlink_ops mlxsw_devlink_ops = {
+	.supported_reload_actions	= BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT) |
+					  BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE),
 	.reload_down		= mlxsw_devlink_core_bus_device_reload_down,
 	.reload_up		= mlxsw_devlink_core_bus_device_reload_up,
 	.port_type_set			= mlxsw_devlink_port_type_set,

@@ -697,7 +697,7 @@ static int nsim_dev_reload_create(struct nsim_dev *nsim_dev,
 static void nsim_dev_reload_destroy(struct nsim_dev *nsim_dev);
 
 static int nsim_dev_reload_down(struct devlink *devlink, bool netns_change,
-				struct netlink_ext_ack *extack)
+				enum devlink_reload_action action, struct netlink_ext_ack *extack)
 {
 	struct nsim_dev *nsim_dev = devlink_priv(devlink);
 

@@ -713,7 +713,7 @@ static int nsim_dev_reload_down(struct devlink *devlink, bool netns_change,
 	return 0;
 }
 
-static int nsim_dev_reload_up(struct devlink *devlink,
+static int nsim_dev_reload_up(struct devlink *devlink, enum devlink_reload_action action,
 			      struct netlink_ext_ack *extack)
 {
 	struct nsim_dev *nsim_dev = devlink_priv(devlink);

@@ -875,6 +875,7 @@ nsim_dev_devlink_trap_policer_counter_get(struct devlink *devlink,
 }
 
 static const struct devlink_ops nsim_dev_devlink_ops = {
+	.supported_reload_actions = BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT),
 	.reload_down = nsim_dev_reload_down,
 	.reload_up = nsim_dev_reload_up,
 	.info_get = nsim_dev_info_get,

@@ -991,9 +991,10 @@ enum devlink_trap_group_generic_id {
 	}
 
 struct devlink_ops {
+	unsigned long supported_reload_actions;
 	int (*reload_down)(struct devlink *devlink, bool netns_change,
-			   struct netlink_ext_ack *extack);
-	int (*reload_up)(struct devlink *devlink,
+			   enum devlink_reload_action action, struct netlink_ext_ack *extack);
+	int (*reload_up)(struct devlink *devlink, enum devlink_reload_action action,
 			 struct netlink_ext_ack *extack);
 	int (*port_type_set)(struct devlink_port *devlink_port,
 			     enum devlink_port_type port_type);

@@ -272,6 +272,23 @@ enum {
 	DEVLINK_ATTR_TRAP_METADATA_TYPE_FA_COOKIE,
 };
 
+/**
+ * enum devlink_reload_action - Reload action.
+ * @DEVLINK_RELOAD_ACTION_FW_LIVE_PATCH: FW live patching.
+ * @DEVLINK_RELOAD_ACTION_DRIVER_REINIT: Driver entities re-instantiation.
+ * @DEVLINK_RELOAD_ACTION_FW_ACTIVATE: FW activate.
+ */
+enum devlink_reload_action {
+	DEVLINK_RELOAD_ACTION_UNSPEC,
+	DEVLINK_RELOAD_ACTION_FW_LIVE_PATCH,
+	DEVLINK_RELOAD_ACTION_DRIVER_REINIT,
+	DEVLINK_RELOAD_ACTION_FW_ACTIVATE,
+
+	/* Add new reload actions above */
+	__DEVLINK_RELOAD_ACTION_MAX,
+	DEVLINK_RELOAD_ACTION_MAX = __DEVLINK_RELOAD_ACTION_MAX - 1
+};
+
 enum devlink_attr {
 	/* don't change the order or add anything between, this is ABI! */
 	DEVLINK_ATTR_UNSPEC,

@@ -458,6 +475,8 @@ enum devlink_attr {
 	DEVLINK_ATTR_PORT_LANES,			/* u32 */
 	DEVLINK_ATTR_PORT_SPLITTABLE,			/* u8 */
 
+	DEVLINK_ATTR_RELOAD_ACTION,		/* u8 */
+
 	/* add new attributes above here, update the policy in devlink.c */
 
 	__DEVLINK_ATTR_MAX,

@@ -462,6 +462,12 @@ static int devlink_nl_put_handle(struct sk_buff *msg, struct devlink *devlink)
 	return 0;
 }
 
+static bool
+devlink_reload_action_is_supported(struct devlink *devlink, enum devlink_reload_action action)
+{
+	return test_bit(action, &devlink->ops->supported_reload_actions);
+}
+
 static int devlink_nl_fill(struct sk_buff *msg, struct devlink *devlink,
 			   enum devlink_command cmd, u32 portid,
 			   u32 seq, int flags)

@@ -2964,21 +2970,21 @@ bool devlink_is_reload_failed(const struct devlink *devlink)
 EXPORT_SYMBOL_GPL(devlink_is_reload_failed);
 
 static int devlink_reload(struct devlink *devlink, struct net *dest_net,
-			  struct netlink_ext_ack *extack)
+			  enum devlink_reload_action action, struct netlink_ext_ack *extack)
 {
 	int err;
 
 	if (!devlink->reload_enabled)
 		return -EOPNOTSUPP;
 
-	err = devlink->ops->reload_down(devlink, !!dest_net, extack);
+	err = devlink->ops->reload_down(devlink, !!dest_net, action, extack);
 	if (err)
 		return err;
 
 	if (dest_net && !net_eq(dest_net, devlink_net(devlink)))
 		devlink_reload_netns_change(devlink, dest_net);
 
-	err = devlink->ops->reload_up(devlink, extack);
+	err = devlink->ops->reload_up(devlink, action, extack);
 	devlink_reload_failed_set(devlink, !!err);
 	return err;
 }

@@ -2986,6 +2992,7 @@ static int devlink_reload(struct devlink *devlink, struct net *dest_net,
 static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info)
 {
 	struct devlink *devlink = info->user_ptr[0];
+	enum devlink_reload_action action;
 	struct net *dest_net = NULL;
 	int err;
 

@@ -3006,7 +3013,20 @@ static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info)
 			return PTR_ERR(dest_net);
 	}
 
-	err = devlink_reload(devlink, dest_net, info->extack);
+	if (info->attrs[DEVLINK_ATTR_RELOAD_ACTION])
+		action = nla_get_u8(info->attrs[DEVLINK_ATTR_RELOAD_ACTION]);
+	else
+		action = DEVLINK_RELOAD_ACTION_DRIVER_REINIT;
+
+	if (action == DEVLINK_RELOAD_ACTION_UNSPEC || action > DEVLINK_RELOAD_ACTION_MAX) {
+		NL_SET_ERR_MSG_MOD(info->extack, "Invalid reload action");
+		return -EINVAL;
+	} else if (!devlink_reload_action_is_supported(devlink, action)) {
+		NL_SET_ERR_MSG_MOD(info->extack, "Requested reload action is not supported");
+		return -EOPNOTSUPP;
+	}
+
+	err = devlink_reload(devlink, dest_net, action, info->extack);
 
 	if (dest_net)
 		put_net(dest_net);

@@ -7039,6 +7059,7 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_TRAP_POLICER_RATE] = { .type = NLA_U64 },
 	[DEVLINK_ATTR_TRAP_POLICER_BURST] = { .type = NLA_U64 },
 	[DEVLINK_ATTR_PORT_FUNCTION] = { .type = NLA_NESTED },
+	[DEVLINK_ATTR_RELOAD_ACTION] = { .type = NLA_U8 },
 };
 
 static const struct genl_ops devlink_nl_ops[] = {

@@ -7364,6 +7385,20 @@ static struct genl_family devlink_nl_family __ro_after_init = {
 	.n_mcgrps	= ARRAY_SIZE(devlink_nl_mcgrps),
 };
 
+static int devlink_reload_actions_verify(struct devlink *devlink)
+{
+	const struct devlink_ops *ops;
+
+	if (!devlink_reload_supported(devlink))
+		return 0;
+
+	ops = devlink->ops;
+	if (WARN_ON(ops->supported_reload_actions >= BIT(__DEVLINK_RELOAD_ACTION_MAX) ||
+		    ops->supported_reload_actions <= BIT(DEVLINK_RELOAD_ACTION_UNSPEC)))
+		return -EINVAL;
+	return 0;
+}
+
 /**
  *	devlink_alloc - Allocate new devlink instance resources
  *

@@ -7384,6 +7419,11 @@ struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size)
 	if (!devlink)
 		return NULL;
 	devlink->ops = ops;
+	if (devlink_reload_actions_verify(devlink)) {
+		kfree(devlink);
+		return NULL;
+	}
+
 	xa_init_flags(&devlink->snapshot_ids, XA_FLAGS_ALLOC);
 	__devlink_net_set(devlink, &init_net);
 	INIT_LIST_HEAD(&devlink->port_list);

@@ -9615,7 +9655,8 @@ static void __net_exit devlink_pernet_pre_exit(struct net *net)
 		if (net_eq(devlink_net(devlink), net)) {
 			if (WARN_ON(!devlink_reload_supported(devlink)))
 				continue;
-			err = devlink_reload(devlink, &init_net, NULL);
+			err = devlink_reload(devlink, &init_net,
+					     DEVLINK_RELOAD_ACTION_DRIVER_REINIT, NULL);
 			if (err && err != -EOPNOTSUPP)
 				pr_warn("Failed to reload devlink instance into init_net\n");
 		}

@@ -275,6 +275,24 @@ static int mlx5_devlink_large_group_num_validate(struct devlink *devlink, u32 id
 }
 #endif
 
+static int mlx5_devlink_enable_remote_dev_reset_set(struct devlink *devlink, u32 id,
+						    struct devlink_param_gset_ctx *ctx)
+{
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
+
+	mlx5_fw_enable_remote_dev_reset_set(dev, ctx->val.vbool);
+	return 0;
+}
+
+static int mlx5_devlink_enable_remote_dev_reset_get(struct devlink *devlink, u32 id,
+						    struct devlink_param_gset_ctx *ctx)
+{
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
+
+	ctx->val.vbool = mlx5_fw_enable_remote_dev_reset_get(dev);
+	return 0;
+}
+
 static const struct devlink_param mlx5_devlink_params[] = {
 	DEVLINK_PARAM_DRIVER(MLX5_DEVLINK_PARAM_ID_FLOW_STEERING_MODE,
 			     "flow_steering_mode", DEVLINK_PARAM_TYPE_STRING,

@@ -290,6 +308,9 @@ static const struct devlink_param mlx5_devlink_params[] = {
 			     NULL, NULL,
 			     mlx5_devlink_large_group_num_validate),
 #endif
+	DEVLINK_PARAM_GENERIC(ENABLE_REMOTE_DEV_RESET, BIT(DEVLINK_PARAM_CMODE_RUNTIME),
+			      mlx5_devlink_enable_remote_dev_reset_get,
+			      mlx5_devlink_enable_remote_dev_reset_set, NULL),
 };
 
 static void mlx5_devlink_set_params_init_values(struct devlink *devlink)

@@ -5,6 +5,7 @@
 
 enum {
 	MLX5_FW_RESET_FLAGS_RESET_REQUESTED,
+	MLX5_FW_RESET_FLAGS_NACK_RESET_REQUEST,
 	MLX5_FW_RESET_FLAGS_PENDING_COMP
 };
 

@@ -22,6 +23,23 @@ struct mlx5_fw_reset {
 	int ret;
 };
 
+void mlx5_fw_enable_remote_dev_reset_set(struct mlx5_core_dev *dev, bool enable)
+{
+	struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
+
+	if (enable)
+		clear_bit(MLX5_FW_RESET_FLAGS_NACK_RESET_REQUEST, &fw_reset->reset_flags);
+	else
+		set_bit(MLX5_FW_RESET_FLAGS_NACK_RESET_REQUEST, &fw_reset->reset_flags);
+}
+
+bool mlx5_fw_enable_remote_dev_reset_get(struct mlx5_core_dev *dev)
+{
+	struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
+
+	return !test_bit(MLX5_FW_RESET_FLAGS_NACK_RESET_REQUEST, &fw_reset->reset_flags);
+}
+
 static int mlx5_reg_mfrl_set(struct mlx5_core_dev *dev, u8 reset_level,
 			     u8 reset_type_sel, u8 sync_resp, bool sync_start)
 {

@@ -76,6 +94,11 @@ static int mlx5_fw_set_reset_sync_ack(struct mlx5_core_dev *dev)
 	return mlx5_reg_mfrl_set(dev, MLX5_MFRL_REG_RESET_LEVEL3, 0, 1, false);
 }
 
+static int mlx5_fw_set_reset_sync_nack(struct mlx5_core_dev *dev)
+{
+	return mlx5_reg_mfrl_set(dev, MLX5_MFRL_REG_RESET_LEVEL3, 0, 2, false);
+}
+
 static void mlx5_fw_reset_complete_reload(struct mlx5_core_dev *dev)
 {
 	struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;

@@ -164,7 +187,14 @@ static void mlx5_sync_reset_request_event(struct work_struct *work)
 	struct mlx5_fw_reset *fw_reset = container_of(work, struct mlx5_fw_reset,
 						      reset_request_work);
 	struct mlx5_core_dev *dev = fw_reset->dev;
+	int err;
 
+	if (test_bit(MLX5_FW_RESET_FLAGS_NACK_RESET_REQUEST, &fw_reset->reset_flags)) {
+		err = mlx5_fw_set_reset_sync_nack(dev);
+		mlx5_core_warn(dev, "PCI Sync FW Update Reset Nack %s",
+			       err ? "Failed" : "Sent");
+		return;
+	}
 	mlx5_sync_reset_set_reset_requested(dev);
 	if (mlx5_fw_set_reset_sync_ack(dev))
 		mlx5_core_warn(dev, "PCI Sync FW Update Reset Ack Failed.\n");

@@ -6,6 +6,8 @@
 
 #include "mlx5_core.h"
 
+void mlx5_fw_enable_remote_dev_reset_set(struct mlx5_core_dev *dev, bool enable);
+bool mlx5_fw_enable_remote_dev_reset_get(struct mlx5_core_dev *dev);
 int mlx5_reg_mfrl_query(struct mlx5_core_dev *dev, u8 *reset_level, u8 *reset_type);
 int mlx5_fw_set_reset_sync(struct mlx5_core_dev *dev, u8 reset_type_sel);
 int mlx5_fw_set_live_patch(struct mlx5_core_dev *dev);

@@ -108,3 +108,9 @@ own name.
    * - ``region_snapshot_enable``
      - Boolean
      - Enable capture of ``devlink-region`` snapshots.
+   * - ``enable_remote_dev_reset``
+     - Boolean
+     - Enable device reset by remote host. When cleared, the device driver
+       will NACK any attempt of other host to reset the device. This parameter
+       is useful for setups where a device is shared by different hosts, such
+       as multi-host setup.

@@ -420,6 +420,7 @@ enum devlink_param_generic_id {
 	DEVLINK_PARAM_GENERIC_ID_FW_LOAD_POLICY,
 	DEVLINK_PARAM_GENERIC_ID_RESET_DEV_ON_DRV_PROBE,
 	DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE,
+	DEVLINK_PARAM_GENERIC_ID_ENABLE_REMOTE_DEV_RESET,
 
 	/* add new param generic ids above here*/
 	__DEVLINK_PARAM_GENERIC_ID_MAX,

@@ -457,6 +458,9 @@ enum devlink_param_generic_id {
 #define DEVLINK_PARAM_GENERIC_ENABLE_ROCE_NAME "enable_roce"
 #define DEVLINK_PARAM_GENERIC_ENABLE_ROCE_TYPE DEVLINK_PARAM_TYPE_BOOL
 
+#define DEVLINK_PARAM_GENERIC_ENABLE_REMOTE_DEV_RESET_NAME "enable_remote_dev_reset"
+#define DEVLINK_PARAM_GENERIC_ENABLE_REMOTE_DEV_RESET_TYPE DEVLINK_PARAM_TYPE_BOOL
+
 #define DEVLINK_PARAM_GENERIC(_id, _cmodes, _get, _set, _validate)	\
 {									\
 	.id = DEVLINK_PARAM_GENERIC_ID_##_id,				\

@@ -3226,6 +3226,11 @@ static const struct devlink_param devlink_param_generic[] = {
 		.name = DEVLINK_PARAM_GENERIC_ENABLE_ROCE_NAME,
 		.type = DEVLINK_PARAM_GENERIC_ENABLE_ROCE_TYPE,
 	},
+	{
+		.id = DEVLINK_PARAM_GENERIC_ID_ENABLE_REMOTE_DEV_RESET,
+		.name = DEVLINK_PARAM_GENERIC_ENABLE_REMOTE_DEV_RESET_NAME,
+		.type = DEVLINK_PARAM_GENERIC_ENABLE_REMOTE_DEV_RESET_TYPE,
+	},
 };
 
 static int devlink_param_generic_verify(const struct devlink_param *param)

@@ -3,6 +3,20 @@
 
 #include "fw_reset.h"
 
+enum {
+	MLX5_FW_RESET_FLAGS_RESET_REQUESTED,
+};
+
+struct mlx5_fw_reset {
+	struct mlx5_core_dev *dev;
+	struct mlx5_nb nb;
+	struct workqueue_struct *wq;
+	struct work_struct reset_request_work;
+	struct work_struct reset_reload_work;
+	unsigned long reset_flags;
+	struct timer_list timer;
+};
+
 static int mlx5_reg_mfrl_set(struct mlx5_core_dev *dev, u8 reset_level,
 			     u8 reset_type_sel, u8 sync_resp, bool sync_start)
 {

@@ -44,3 +58,156 @@ int mlx5_fw_set_live_patch(struct mlx5_core_dev *dev)
 {
 	return mlx5_reg_mfrl_set(dev, MLX5_MFRL_REG_RESET_LEVEL0, 0, 0, false);
 }
+
+static int mlx5_fw_set_reset_sync_ack(struct mlx5_core_dev *dev)
+{
+	return mlx5_reg_mfrl_set(dev, MLX5_MFRL_REG_RESET_LEVEL3, 0, 1, false);
+}
+
+static void mlx5_sync_reset_reload_work(struct work_struct *work)
+{
+	struct mlx5_fw_reset *fw_reset = container_of(work, struct mlx5_fw_reset,
+						      reset_reload_work);
+	struct mlx5_core_dev *dev = fw_reset->dev;
+
+	mlx5_enter_error_state(dev, true);
+	mlx5_unload_one(dev, false);
+	if (mlx5_health_wait_pci_up(dev)) {
+		mlx5_core_err(dev, "reset reload flow aborted, PCI reads still not working\n");
+		return;
+	}
+	mlx5_load_one(dev, false);
+}
+
+static void mlx5_stop_sync_reset_poll(struct mlx5_core_dev *dev)
+{
+	struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
+
+	del_timer(&fw_reset->timer);
+}
+
+static void mlx5_sync_reset_clear_reset_requested(struct mlx5_core_dev *dev, bool poll_health)
+{
+	struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
+
+	mlx5_stop_sync_reset_poll(dev);
+	clear_bit(MLX5_FW_RESET_FLAGS_RESET_REQUESTED, &fw_reset->reset_flags);
+	if (poll_health)
+		mlx5_start_health_poll(dev);
+}
+
+#define MLX5_RESET_POLL_INTERVAL	(HZ / 10)
+static void poll_sync_reset(struct timer_list *t)
+{
+	struct mlx5_fw_reset *fw_reset = from_timer(fw_reset, t, timer);
+	struct mlx5_core_dev *dev = fw_reset->dev;
+	u32 fatal_error;
+
+	if (!test_bit(MLX5_FW_RESET_FLAGS_RESET_REQUESTED, &fw_reset->reset_flags))
+		return;
+
+	fatal_error = mlx5_health_check_fatal_sensors(dev);
+
+	if (fatal_error) {
+		mlx5_core_warn(dev, "Got Device Reset\n");
+		mlx5_sync_reset_clear_reset_requested(dev, false);
+		queue_work(fw_reset->wq, &fw_reset->reset_reload_work);
+		return;
+	}
+
+	mod_timer(&fw_reset->timer, round_jiffies(jiffies + MLX5_RESET_POLL_INTERVAL));
+}
+
+static void mlx5_start_sync_reset_poll(struct mlx5_core_dev *dev)
+{
+	struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
+
+	timer_setup(&fw_reset->timer, poll_sync_reset, 0);
+	fw_reset->timer.expires = round_jiffies(jiffies + MLX5_RESET_POLL_INTERVAL);
+	add_timer(&fw_reset->timer);
+}
+
+static void mlx5_sync_reset_set_reset_requested(struct mlx5_core_dev *dev)
+{
+	struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
+
+	mlx5_stop_health_poll(dev, true);
+	set_bit(MLX5_FW_RESET_FLAGS_RESET_REQUESTED, &fw_reset->reset_flags);
+	mlx5_start_sync_reset_poll(dev);
+}
+
+static void mlx5_sync_reset_request_event(struct work_struct *work)
+{
+	struct mlx5_fw_reset *fw_reset = container_of(work, struct mlx5_fw_reset,
+						      reset_request_work);
+	struct mlx5_core_dev *dev = fw_reset->dev;
+
+	mlx5_sync_reset_set_reset_requested(dev);
+	if (mlx5_fw_set_reset_sync_ack(dev))
+		mlx5_core_warn(dev, "PCI Sync FW Update Reset Ack Failed.\n");
+	else
+		mlx5_core_warn(dev, "PCI Sync FW Update Reset Ack. Device reset is expected.\n");
+}
+
+static void mlx5_sync_reset_events_handle(struct mlx5_fw_reset *fw_reset, struct mlx5_eqe *eqe)
+{
+	struct mlx5_eqe_sync_fw_update *sync_fw_update_eqe;
+	u8 sync_event_rst_type;
+
+	sync_fw_update_eqe = &eqe->data.sync_fw_update;
+	sync_event_rst_type = sync_fw_update_eqe->sync_rst_state & SYNC_RST_STATE_MASK;
+	switch (sync_event_rst_type) {
+	case MLX5_SYNC_RST_STATE_RESET_REQUEST:
+		queue_work(fw_reset->wq, &fw_reset->reset_request_work);
+		break;
+	}
+}
+
+static int fw_reset_event_notifier(struct notifier_block *nb, unsigned long action, void *data)
+{
+	struct mlx5_fw_reset *fw_reset = mlx5_nb_cof(nb, struct mlx5_fw_reset, nb);
+	struct mlx5_eqe *eqe = data;
+
+	switch (eqe->sub_type) {
+	case MLX5_GENERAL_SUBTYPE_PCI_SYNC_FOR_FW_UPDATE_EVENT:
+		mlx5_sync_reset_events_handle(fw_reset, eqe);
+		break;
+	default:
+		return NOTIFY_DONE;
+	}
+
+	return NOTIFY_OK;
+}
+
+int mlx5_fw_reset_events_init(struct mlx5_core_dev *dev)
+{
+	struct mlx5_fw_reset *fw_reset = kzalloc(sizeof(*fw_reset), GFP_KERNEL);
+
+	if (!fw_reset)
+		return -ENOMEM;
+	fw_reset->wq = create_singlethread_workqueue("mlx5_fw_reset_events");
+	if (!fw_reset->wq) {
+		kfree(fw_reset);
+		return -ENOMEM;
+	}
+
+	fw_reset->dev = dev;
+	dev->priv.fw_reset = fw_reset;
+
+	INIT_WORK(&fw_reset->reset_request_work, mlx5_sync_reset_request_event);
+	INIT_WORK(&fw_reset->reset_reload_work, mlx5_sync_reset_reload_work);
+
+	MLX5_NB_INIT(&fw_reset->nb, fw_reset_event_notifier, GENERAL_EVENT);
+	mlx5_eq_notifier_register(dev, &fw_reset->nb);
+
+	return 0;
+}
+
+void mlx5_fw_reset_events_cleanup(struct mlx5_core_dev *dev)
+{
+	struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
+
+	mlx5_eq_notifier_unregister(dev, &fw_reset->nb);
+	destroy_workqueue(fw_reset->wq);
+	kvfree(dev->priv.fw_reset);
+}

@@ -10,4 +10,7 @@ int mlx5_reg_mfrl_query(struct mlx5_core_dev *dev, u8 *reset_level, u8 *reset_ty
 int mlx5_fw_set_reset_sync(struct mlx5_core_dev *dev, u8 reset_type_sel);
 int mlx5_fw_set_live_patch(struct mlx5_core_dev *dev);
 
+int mlx5_fw_reset_events_init(struct mlx5_core_dev *dev);
+void mlx5_fw_reset_events_cleanup(struct mlx5_core_dev *dev);
+
 #endif

@@ -110,7 +110,7 @@ static bool sensor_fw_synd_rfr(struct mlx5_core_dev *dev)
 	return rfr && synd;
 }
 
-static u32 check_fatal_sensors(struct mlx5_core_dev *dev)
+u32 mlx5_health_check_fatal_sensors(struct mlx5_core_dev *dev)
 {
 	if (sensor_pci_not_working(dev))
 		return MLX5_SENSOR_PCI_COMM_ERR;

@@ -173,7 +173,7 @@ static bool reset_fw_if_needed(struct mlx5_core_dev *dev)
 	 * Check again to avoid a redundant 2nd reset. If the fatal erros was
 	 * PCI related a reset won't help.
 	 */
-	fatal_error = check_fatal_sensors(dev);
+	fatal_error = mlx5_health_check_fatal_sensors(dev);
 	if (fatal_error == MLX5_SENSOR_PCI_COMM_ERR ||
 	    fatal_error == MLX5_SENSOR_NIC_DISABLED ||
 	    fatal_error == MLX5_SENSOR_NIC_SW_RESET) {

@@ -195,7 +195,7 @@ void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force)
 	bool err_detected = false;
 
 	/* Mark the device as fatal in order to abort FW commands */
-	if ((check_fatal_sensors(dev) || force) &&
+	if ((mlx5_health_check_fatal_sensors(dev) || force) &&
 	    dev->state == MLX5_DEVICE_STATE_UP) {
 		dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR;
 		err_detected = true;

@@ -208,7 +208,7 @@ void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force)
 		goto unlock;
 	}
 
-	if (check_fatal_sensors(dev) || force) { /* protected state setting */
+	if (mlx5_health_check_fatal_sensors(dev) || force) { /* protected state setting */
 		dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR;
 		mlx5_cmd_flush(dev);
 	}

@@ -231,7 +231,7 @@ void mlx5_error_sw_reset(struct mlx5_core_dev *dev)
 
 	mlx5_core_err(dev, "start\n");
 
-	if (check_fatal_sensors(dev) == MLX5_SENSOR_FW_SYND_RFR) {
+	if (mlx5_health_check_fatal_sensors(dev) == MLX5_SENSOR_FW_SYND_RFR) {
 		/* Get cr-dump and reset FW semaphore */
 		lock = lock_sem_sw_reset(dev, true);
 

@@ -308,26 +308,31 @@ static void mlx5_handle_bad_state(struct mlx5_core_dev *dev)
 
 /* How much time to wait until health resetting the driver (in msecs) */
 #define MLX5_RECOVERY_WAIT_MSECS 60000
-static int mlx5_health_try_recover(struct mlx5_core_dev *dev)
+int mlx5_health_wait_pci_up(struct mlx5_core_dev *dev)
 {
 	unsigned long end;
 
-	mlx5_core_warn(dev, "handling bad device here\n");
-	mlx5_handle_bad_state(dev);
 	end = jiffies + msecs_to_jiffies(MLX5_RECOVERY_WAIT_MSECS);
 	while (sensor_pci_not_working(dev)) {
-		if (time_after(jiffies, end)) {
-			mlx5_core_err(dev,
-				      "health recovery flow aborted, PCI reads still not working\n");
-			return -EIO;
-		}
+		if (time_after(jiffies, end))
+			return -ETIMEDOUT;
 		msleep(100);
 	}
+	return 0;
+}
 
+static int mlx5_health_try_recover(struct mlx5_core_dev *dev)
+{
+	mlx5_core_warn(dev, "handling bad device here\n");
+	mlx5_handle_bad_state(dev);
+	if (mlx5_health_wait_pci_up(dev)) {
+		mlx5_core_err(dev, "health recovery flow aborted, PCI reads still not working\n");
+		return -EIO;
+	}
 	mlx5_core_err(dev, "starting health recovery flow\n");
 	mlx5_recover_device(dev);
 	if (!test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state) ||
-	    check_fatal_sensors(dev)) {
+	    mlx5_health_check_fatal_sensors(dev)) {
 		mlx5_core_err(dev, "health recovery failed\n");
 		return -EIO;
 	}

@@ -696,7 +701,7 @@ static void poll_health(struct timer_list *t)
 	if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR)
 		goto out;
 
-	fatal_error = check_fatal_sensors(dev);
+	fatal_error = mlx5_health_check_fatal_sensors(dev);
 
 	if (fatal_error && !health->fatal_error) {
 		mlx5_core_err(dev, "Fatal error %u detected\n", fatal_error);

@@ -57,6 +57,7 @@
 #include "lib/mpfs.h"
 #include "eswitch.h"
 #include "devlink.h"
+#include "fw_reset.h"
 #include "lib/mlx5.h"
 #include "fpga/core.h"
 #include "fpga/ipsec.h"

@@ -835,6 +836,12 @@ static int mlx5_init_once(struct mlx5_core_dev *dev)
 		goto err_eq_cleanup;
 	}
 
+	err = mlx5_fw_reset_events_init(dev);
+	if (err) {
+		mlx5_core_err(dev, "failed to initialize fw reset events\n");
+		goto err_events_cleanup;
+	}
+
 	mlx5_cq_debugfs_init(dev);
 
 	mlx5_init_reserved_gids(dev);

@@ -896,6 +903,8 @@ static int mlx5_init_once(struct mlx5_core_dev *dev)
 	mlx5_geneve_destroy(dev->geneve);
 	mlx5_vxlan_destroy(dev->vxlan);
 	mlx5_cq_debugfs_cleanup(dev);
+	mlx5_fw_reset_events_cleanup(dev);
+err_events_cleanup:
 	mlx5_events_cleanup(dev);
 err_eq_cleanup:
 	mlx5_eq_table_cleanup(dev);

@@ -923,6 +932,7 @@ static void mlx5_cleanup_once(struct mlx5_core_dev *dev)
 	mlx5_cleanup_clock(dev);
 	mlx5_cleanup_reserved_gids(dev);
 	mlx5_cq_debugfs_cleanup(dev);
+	mlx5_fw_reset_events_cleanup(dev);
 	mlx5_events_cleanup(dev);
 	mlx5_eq_table_cleanup(dev);
 	mlx5_irq_table_cleanup(dev);

@@ -123,6 +123,8 @@ int mlx5_cmd_force_teardown_hca(struct mlx5_core_dev *dev);
 int mlx5_cmd_fast_teardown_hca(struct mlx5_core_dev *dev);
 void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force);
 void mlx5_error_sw_reset(struct mlx5_core_dev *dev);
+u32 mlx5_health_check_fatal_sensors(struct mlx5_core_dev *dev);
+int mlx5_health_wait_pci_up(struct mlx5_core_dev *dev);
 void mlx5_disable_device(struct mlx5_core_dev *dev);
 void mlx5_recover_device(struct mlx5_core_dev *dev);
 int mlx5_sriov_init(struct mlx5_core_dev *dev);

@@ -501,6 +501,7 @@ struct mlx5_mpfs;
 struct mlx5_eswitch;
 struct mlx5_lag;
 struct mlx5_devcom;
+struct mlx5_fw_reset;
 struct mlx5_eq_table;
 struct mlx5_irq_table;
 

@@ -578,6 +579,7 @@ struct mlx5_priv {
 	struct mlx5_core_sriov	sriov;
 	struct mlx5_lag		*lag;
 	struct mlx5_devcom	*devcom;
+	struct mlx5_fw_reset	*fw_reset;
 	struct mlx5_core_roce	roce;
 	struct mlx5_fc_stats		fc_stats;
 	struct mlx5_rl_table            rl_table;

@@ -943,6 +945,8 @@ void mlx5_start_health_poll(struct mlx5_core_dev *dev);
 void mlx5_stop_health_poll(struct mlx5_core_dev *dev, bool disable_health);
 void mlx5_drain_health_wq(struct mlx5_core_dev *dev);
 void mlx5_trigger_health_work(struct mlx5_core_dev *dev);
+void mlx5_health_set_reset_requested_mode(struct mlx5_core_dev *dev);
+void mlx5_health_clear_reset_requested_mode(struct mlx5_core_dev *dev);
 int mlx5_buf_alloc(struct mlx5_core_dev *dev,
 		   int size, struct mlx5_frag_buf *buf);
 void mlx5_buf_free(struct mlx5_core_dev *dev, struct mlx5_frag_buf *buf);

@@ -13,6 +13,7 @@ struct mlx5_fw_reset {
 	struct workqueue_struct *wq;
 	struct work_struct reset_request_work;
 	struct work_struct reset_reload_work;
+	struct work_struct reset_now_work;
 	unsigned long reset_flags;
 	struct timer_list timer;
 };

@@ -149,6 +150,122 @@ static void mlx5_sync_reset_request_event(struct work_struct *work)
 		mlx5_core_warn(dev, "PCI Sync FW Update Reset Ack. Device reset is expected.\n");
 }
 
+#define MLX5_PCI_LINK_UP_TIMEOUT 2000
+
+static int mlx5_pci_link_toggle(struct mlx5_core_dev *dev)
+{
+	struct pci_bus *bridge_bus = dev->pdev->bus;
+	struct pci_dev *bridge = bridge_bus->self;
+	u16 reg16, dev_id, sdev_id;
+	unsigned long timeout;
+	struct pci_dev *sdev;
+	int cap, err;
+	u32 reg32;
+
+	/* Check that all functions under the pci bridge are PFs of
+	 * this device otherwise fail this function.
+	 */
+	err = pci_read_config_word(dev->pdev, PCI_DEVICE_ID, &dev_id);
+	if (err)
+		return err;
+	list_for_each_entry(sdev, &bridge_bus->devices, bus_list) {
+		err = pci_read_config_word(sdev, PCI_DEVICE_ID, &sdev_id);
+		if (err)
+			return err;
+		if (sdev_id != dev_id)
+			return -EPERM;
+	}
+
+	cap = pci_find_capability(bridge, PCI_CAP_ID_EXP);
+	if (!cap)
+		return -EOPNOTSUPP;
+
+	list_for_each_entry(sdev, &bridge_bus->devices, bus_list) {
+		pci_save_state(sdev);
+		pci_cfg_access_lock(sdev);
+	}
+	/* PCI link toggle */
+	err = pci_read_config_word(bridge, cap + PCI_EXP_LNKCTL, &reg16);
+	if (err)
+		return err;
+	reg16 |= PCI_EXP_LNKCTL_LD;
+	err = pci_write_config_word(bridge, cap + PCI_EXP_LNKCTL, reg16);
+	if (err)
+		return err;
+	msleep(500);
+	reg16 &= ~PCI_EXP_LNKCTL_LD;
+	err = pci_write_config_word(bridge, cap + PCI_EXP_LNKCTL, reg16);
+	if (err)
+		return err;
+
+	/* Check link */
+	err = pci_read_config_dword(bridge, cap + PCI_EXP_LNKCAP, &reg32);
+	if (err)
+		return err;
+	if (!(reg32 & PCI_EXP_LNKCAP_DLLLARC)) {
+		mlx5_core_warn(dev, "No PCI link reporting capability (0x%08x)\n", reg32);
+		msleep(1000);
+		goto restore;
+	}
+
+	timeout = jiffies + msecs_to_jiffies(MLX5_PCI_LINK_UP_TIMEOUT);
+	do {
+		err = pci_read_config_word(bridge, cap + PCI_EXP_LNKSTA, &reg16);
+		if (err)
+			return err;
+		if (reg16 & PCI_EXP_LNKSTA_DLLLA)
+			break;
+		msleep(20);
+	} while (!time_after(jiffies, timeout));
+
+	if (reg16 & PCI_EXP_LNKSTA_DLLLA) {
+		mlx5_core_info(dev, "PCI Link up\n");
+	} else {
+		mlx5_core_err(dev, "PCI link not ready (0x%04x) after %d ms\n",
+			      reg16, MLX5_PCI_LINK_UP_TIMEOUT);
+		err = -ETIMEDOUT;
+	}
+
+restore:
+	list_for_each_entry(sdev, &bridge_bus->devices, bus_list) {
+		pci_cfg_access_unlock(sdev);
+		pci_restore_state(sdev);
+	}
+
+	return err;
+}
+
+static void mlx5_sync_reset_now_event(struct work_struct *work)
+{
+	struct mlx5_fw_reset *fw_reset = container_of(work, struct mlx5_fw_reset,
+						      reset_now_work);
+	struct mlx5_core_dev *dev = fw_reset->dev;
+	int err;
+
+	mlx5_sync_reset_clear_reset_requested(dev, false);
+
+	mlx5_core_warn(dev, "Sync Reset now. Device is going to reset.\n");
+
+	err = mlx5_cmd_fast_teardown_hca(dev);
+	if (err) {
+		mlx5_core_warn(dev, "Fast teardown failed, no reset done, err %d\n", err);
+		goto done;
+	}
+
+	err = mlx5_pci_link_toggle(dev);
+	if (err) {
+		mlx5_core_warn(dev, "mlx5_pci_link_toggle failed, no reset done, err %d\n", err);
+		goto done;
+	}
+
+	mlx5_enter_error_state(dev, true);
+	mlx5_unload_one(dev, false);
+done:
+	if (err)
+		mlx5_start_health_poll(dev);
+	mlx5_load_one(dev, false);
+}
+
 static void mlx5_sync_reset_events_handle(struct mlx5_fw_reset *fw_reset, struct mlx5_eqe *eqe)
 {
 	struct mlx5_eqe_sync_fw_update *sync_fw_update_eqe;

@@ -160,6 +277,9 @@ static void mlx5_sync_reset_events_handle(struct mlx5_fw_reset *fw_reset, struct
 	case MLX5_SYNC_RST_STATE_RESET_REQUEST:
 		queue_work(fw_reset->wq, &fw_reset->reset_request_work);
 		break;
+	case MLX5_SYNC_RST_STATE_RESET_NOW:
+		queue_work(fw_reset->wq, &fw_reset->reset_now_work);
+		break;
 	}
 }
 

@@ -196,6 +316,7 @@ int mlx5_fw_reset_events_init(struct mlx5_core_dev *dev)
 
 	INIT_WORK(&fw_reset->reset_request_work, mlx5_sync_reset_request_event);
 	INIT_WORK(&fw_reset->reset_reload_work, mlx5_sync_reset_reload_work);
+	INIT_WORK(&fw_reset->reset_now_work, mlx5_sync_reset_now_event);
 
 	MLX5_NB_INIT(&fw_reset->nb, fw_reset_event_notifier, GENERAL_EVENT);
 	mlx5_eq_notifier_register(dev, &fw_reset->nb);

@@ -476,6 +476,7 @@ enum devlink_attr {
 	DEVLINK_ATTR_PORT_SPLITTABLE,			/* u8 */
 
 	DEVLINK_ATTR_RELOAD_ACTION,		/* u8 */
+	DEVLINK_ATTR_RELOAD_SUPPORTED_ACTIONS,	/* nested */
 
 	/* add new attributes above here, update the policy in devlink.c */
 

@@ -462,6 +462,11 @@ static int devlink_nl_put_handle(struct sk_buff *msg, struct devlink *devlink)
 	return 0;
 }
 
+static bool devlink_reload_supported(struct devlink *devlink)
+{
+	return devlink->ops->reload_down && devlink->ops->reload_up;
+}
+
 static bool
 devlink_reload_action_is_supported(struct devlink *devlink, enum devlink_reload_action action)
 {

@@ -472,7 +477,9 @@ static int devlink_nl_fill(struct sk_buff *msg, struct devlink *devlink,
 			   enum devlink_command cmd, u32 portid,
 			   u32 seq, int flags)
 {
+	struct nlattr *supported_actions;
 	void *hdr;
+	int i;
 
 	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
 	if (!hdr)

@@ -483,9 +490,25 @@ static int devlink_nl_fill(struct sk_buff *msg, struct devlink *devlink,
 	if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_FAILED, devlink->reload_failed))
 		goto nla_put_failure;
 
+	if (devlink_reload_supported(devlink)) {
+		supported_actions = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_SUPPORTED_ACTIONS);
+		if (!supported_actions)
+			goto nla_put_failure;
+
+		for (i = 0; i <= DEVLINK_RELOAD_ACTION_MAX; i++) {
+			if (!devlink_reload_action_is_supported(devlink, i))
+				continue;
+			if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_ACTION, i))
+				goto supported_actions_nest_cancel;
+		}
+		nla_nest_end(msg, supported_actions);
+	}
+
 	genlmsg_end(msg, hdr);
 	return 0;
 
+supported_actions_nest_cancel:
+	nla_nest_cancel(msg, supported_actions);
 nla_put_failure:
 	genlmsg_cancel(msg, hdr);
 	return -EMSGSIZE;