[PATCH v19 net-next 11/11] net/nebula-matrix: add common dev start/stop operation

["illusion.wang" <illusion.wang@nebula-matrix.com>]

This patch wires up nbl_dev_start() and nbl_dev_stop() to configure
the MSI-X map, allocate vectors, and request/enable the mailbox IRQ.
It also replaces module_pci_driver() with explicit init/exit functions
that additionally create and destroy the driver's workqueue via
nbl_common_create_wq() / nbl_common_destroy_wq(), which is needed
because the new IRQ handler schedules work through
nbl_common_queue_work().

Signed-off-by: illusion.wang <illusion.wang@nebula-matrix.com>
---
 .../nebula-matrix/nbl/nbl_common/nbl_common.c |  24 ++
 .../nebula-matrix/nbl/nbl_core/nbl_dev.c      | 250 +++++++++++++++++-
 .../nebula-matrix/nbl/nbl_hw/nbl_resource.c   |   2 +-
 .../nbl/nbl_include/nbl_def_common.h          |   6 +
 4 files changed, 280 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/nebula-matrix/nbl/nbl_common/nbl_common.c b/drivers/net/ethernet/nebula-matrix/nbl/nbl_common/nbl_common.c
index 2954cbbe0f95..bae1a7e401ce 100644
--- a/drivers/net/ethernet/nebula-matrix/nbl/nbl_common/nbl_common.c
+++ b/drivers/net/ethernet/nebula-matrix/nbl/nbl_common/nbl_common.c
@@ -6,6 +6,30 @@
 #include <linux/device.h>
 #include "nbl_common.h"
 
+void nbl_common_queue_work(struct nbl_common_info *common,
+			   struct work_struct *task)
+{
+	queue_work(common->wq, task);
+}
+
+void nbl_common_destroy_wq(struct nbl_common_info *common)
+{
+	destroy_workqueue(common->wq);
+}
+
+int nbl_common_create_wq(struct nbl_common_info *common)
+{
+	common->wq = alloc_workqueue("nbl_wq", WQ_UNBOUND, 0);
+	if (!common->wq) {
+		pr_err("Failed to create workqueue nbl_wq\n");
+		goto alloc_wq_failed;
+	}
+
+	return 0;
+alloc_wq_failed:
+	return -ENOMEM;
+}
+
 u32 nbl_common_pf_id_subtraction_mgtpf_id(struct nbl_common_info *common,
 					  u32 pf_id)
 {
diff --git a/drivers/net/ethernet/nebula-matrix/nbl/nbl_core/nbl_dev.c b/drivers/net/ethernet/nebula-matrix/nbl/nbl_core/nbl_dev.c
index 8feae561d0f1..288b2dae8681 100644
--- a/drivers/net/ethernet/nebula-matrix/nbl/nbl_core/nbl_dev.c
+++ b/drivers/net/ethernet/nebula-matrix/nbl/nbl_core/nbl_dev.c
@@ -6,6 +6,17 @@
 #include <linux/pci.h>
 #include "nbl_dev.h"
 
+static void nbl_dev_clean_mailbox_schedule(struct nbl_dev_mgt *dev_mgt);
+
+/* ----------  Interrupt config  ---------- */
+static irqreturn_t nbl_dev_clean_mailbox(int __always_unused irq, void *data)
+{
+	struct nbl_dev_mgt *dev_mgt = (struct nbl_dev_mgt *)data;
+
+	nbl_dev_clean_mailbox_schedule(dev_mgt);
+	return IRQ_HANDLED;
+}
+
 static void nbl_dev_init_msix_cnt(struct nbl_dev_mgt *dev_mgt)
 {
 	struct nbl_dev_common *dev_common = dev_mgt->common_dev;
@@ -14,6 +25,182 @@ static void nbl_dev_init_msix_cnt(struct nbl_dev_mgt *dev_mgt)
 	msix_info->serv_info[NBL_MSIX_MAILBOX_TYPE].num = 1;
 }
 
+static int nbl_dev_request_mailbox_irq(struct nbl_dev_mgt *dev_mgt)
+{
+	struct nbl_dev_common *dev_common = dev_mgt->common_dev;
+	struct nbl_msix_info *msix_info = &dev_common->msix_info;
+	struct nbl_common_info *common = dev_mgt->common;
+	u16 local_vec_id;
+	int irq_num;
+	int err;
+
+	if (!msix_info->serv_info[NBL_MSIX_MAILBOX_TYPE].num)
+		return 0;
+
+	local_vec_id =
+		msix_info->serv_info[NBL_MSIX_MAILBOX_TYPE].base_vector_id;
+	irq_num = pci_irq_vector(common->pdev, local_vec_id);
+	if (irq_num < 0) {
+		dev_err(common->dev, "Failed to get mailbox IRQ vector: %d\n",
+			irq_num);
+		return irq_num;
+	}
+
+	snprintf(dev_common->mailbox_name, sizeof(dev_common->mailbox_name),
+		 "nbl_mailbox@pci:%s", pci_name(common->pdev));
+	err = request_irq(irq_num, nbl_dev_clean_mailbox, 0,
+			  dev_common->mailbox_name, dev_mgt);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static void nbl_dev_free_mailbox_irq(struct nbl_dev_mgt *dev_mgt)
+{
+	struct nbl_dev_common *dev_common = dev_mgt->common_dev;
+	struct nbl_msix_info *msix_info = &dev_common->msix_info;
+	struct nbl_common_info *common = dev_mgt->common;
+	u16 local_vec_id;
+	int irq_num;
+
+	if (!msix_info->serv_info[NBL_MSIX_MAILBOX_TYPE].num)
+		return;
+
+	local_vec_id =
+		msix_info->serv_info[NBL_MSIX_MAILBOX_TYPE].base_vector_id;
+	irq_num = pci_irq_vector(common->pdev, local_vec_id);
+	if (irq_num >= 0)
+		free_irq(irq_num, dev_mgt);
+}
+
+static int nbl_dev_enable_mailbox_irq(struct nbl_dev_mgt *dev_mgt)
+{
+	struct nbl_dispatch_ops *disp_ops = dev_mgt->disp_ops_tbl->ops;
+	struct nbl_channel_ops *chan_ops = dev_mgt->chan_ops_tbl->ops;
+	struct nbl_dev_common *dev_common = dev_mgt->common_dev;
+	struct nbl_msix_info *msix_info = &dev_common->msix_info;
+	u16 local_vec_id;
+
+	if (!msix_info->serv_info[NBL_MSIX_MAILBOX_TYPE].num)
+		return 0;
+
+	local_vec_id =
+		msix_info->serv_info[NBL_MSIX_MAILBOX_TYPE].base_vector_id;
+	chan_ops->set_queue_state(dev_mgt->chan_ops_tbl->priv,
+				  NBL_CHAN_INTERRUPT_READY,
+				  NBL_CHAN_TYPE_MAILBOX, true);
+
+	return disp_ops->set_mailbox_irq(dev_mgt->disp_ops_tbl->priv,
+					    local_vec_id, true);
+}
+
+static int nbl_dev_disable_mailbox_irq(struct nbl_dev_mgt *dev_mgt)
+{
+	struct nbl_dispatch_ops *disp_ops = dev_mgt->disp_ops_tbl->ops;
+	struct nbl_channel_ops *chan_ops = dev_mgt->chan_ops_tbl->ops;
+	struct nbl_dev_common *dev_common = dev_mgt->common_dev;
+	struct nbl_msix_info *msix_info = &dev_common->msix_info;
+	u16 local_vec_id;
+
+	if (!msix_info->serv_info[NBL_MSIX_MAILBOX_TYPE].num)
+		return 0;
+
+	local_vec_id =
+		msix_info->serv_info[NBL_MSIX_MAILBOX_TYPE].base_vector_id;
+	/*
+	 * Disable order: software state first, then hardware.
+	 *
+	 * Review suggested HW-then-state for symmetry with enable, but that
+	 * causes "Channel waiting ack failed" errors. The reason: after
+	 * set_mailbox_irq(..., false) disables the hardware, the device may
+	 * still be sending ACKs for in-flight messages. If we then switch to
+	 * polling mode (clear INTERRUPT_READY), the ACK handler won't process
+	 * those pending ACKs, leading to "waiting ack failed" and "Skip ack
+	 * with invalid status" errors.
+	 *
+	 * The original state-then-HW order avoids this: we switch to polling
+	 * first, so any late interrupts are silently ignored (no ACK expected),
+	 * then we disable the hardware. The theoretical window where an
+	 * interrupt could fire and be ignored is harmless here because this
+	 * function is only called on the error path of nbl_dev_start(),
+	 * immediately followed by nbl_dev_free_mailbox_irq() and
+	 * cancel_work_sync(&clean_mbx_task). The channel is torn down right
+	 * after, so no descriptors can be left stuck.
+	 *
+	 * Do NOT change to HW-then-state.
+	 */
+	chan_ops->set_queue_state(dev_mgt->chan_ops_tbl->priv,
+				  NBL_CHAN_INTERRUPT_READY,
+				  NBL_CHAN_TYPE_MAILBOX, false);
+
+	return disp_ops->set_mailbox_irq(dev_mgt->disp_ops_tbl->priv,
+					    local_vec_id, false);
+}
+
+static int nbl_dev_configure_msix_map(struct nbl_dev_mgt *dev_mgt)
+{
+	struct nbl_dispatch_ops *disp_ops = dev_mgt->disp_ops_tbl->ops;
+	struct nbl_dev_common *dev_common = dev_mgt->common_dev;
+	struct nbl_msix_info *msix_info = &dev_common->msix_info;
+	bool mask_en = msix_info->serv_info[NBL_MSIX_NET_TYPE].hw_self_mask_en;
+	u16 msix_net_num = msix_info->serv_info[NBL_MSIX_NET_TYPE].num;
+	u16 msix_not_net_num = 0;
+	int err, i;
+
+	msix_info->serv_info[NBL_MSIX_VIRTIO_TYPE].base_vector_id = 0;
+	for (i = NBL_MSIX_NET_TYPE; i < NBL_MSIX_TYPE_MAX; i++)
+		msix_info->serv_info[i].base_vector_id =
+			msix_info->serv_info[i - 1].base_vector_id +
+			msix_info->serv_info[i - 1].num;
+
+	for (i = NBL_MSIX_MAILBOX_TYPE; i < NBL_MSIX_TYPE_MAX; i++)
+		msix_not_net_num += msix_info->serv_info[i].num;
+
+	err = disp_ops->configure_msix_map(dev_mgt->disp_ops_tbl->priv,
+					   msix_net_num, msix_not_net_num,
+					   mask_en);
+
+	return err;
+}
+
+static int nbl_dev_destroy_msix_map(struct nbl_dev_mgt *dev_mgt)
+{
+	struct nbl_dispatch_ops *disp_ops = dev_mgt->disp_ops_tbl->ops;
+
+	return disp_ops->destroy_msix_map(dev_mgt->disp_ops_tbl->priv);
+}
+
+static int nbl_dev_init_interrupt_scheme(struct nbl_dev_mgt *dev_mgt)
+{
+	struct nbl_dev_common *dev_common = dev_mgt->common_dev;
+	struct nbl_msix_info *msix_info = &dev_common->msix_info;
+	struct nbl_common_info *common = dev_mgt->common;
+	int needed = 0;
+	int err;
+	int i;
+
+	for (i = 0; i < NBL_MSIX_TYPE_MAX; i++)
+		needed += msix_info->serv_info[i].num;
+
+	err = pci_alloc_irq_vectors(common->pdev, needed, needed,
+				    PCI_IRQ_MSIX | PCI_IRQ_AFFINITY);
+	if (err < 0) {
+		dev_err(common->dev,
+			"pci_alloc_irq_vectors failed, err = %d\n", err);
+		return err;
+	}
+
+	return 0;
+}
+
+static void nbl_dev_clear_interrupt_scheme(struct nbl_dev_mgt *dev_mgt)
+{
+	struct nbl_common_info *common = dev_mgt->common;
+
+	pci_free_irq_vectors(common->pdev);
+}
+
 /* ----------  Channel config  ---------- */
 static void nbl_dev_setup_chan_qinfo(struct nbl_dev_mgt *dev_mgt, u8 chan_type)
 {
@@ -72,6 +259,14 @@ static void nbl_dev_clean_mailbox_task(struct work_struct *work)
 				      NBL_CHAN_TYPE_MAILBOX);
 }
 
+static void nbl_dev_clean_mailbox_schedule(struct nbl_dev_mgt *dev_mgt)
+{
+	struct nbl_dev_common *common_dev = dev_mgt->common_dev;
+	struct nbl_common_info *common = dev_mgt->common;
+
+	nbl_common_queue_work(common, &common_dev->clean_mbx_task);
+}
+
 /* ----------  Dev init process  ---------- */
 static int nbl_dev_setup_common_dev(struct nbl_adapter *adapter)
 {
@@ -189,7 +384,7 @@ int nbl_dev_init(struct nbl_adapter *adapter)
 	dev_mgt->disp_ops_tbl = disp_ops_tbl;
 	dev_mgt->chan_ops_tbl = chan_ops_tbl;
 	adapter->core.dev_mgt = dev_mgt;
-
+	ret = nbl_common_create_wq(common);
 	ret = nbl_dev_setup_common_dev(adapter);
 	if (ret)
 		return ret;
@@ -213,14 +408,67 @@ void nbl_dev_remove(struct nbl_adapter *adapter)
 	if (common->has_ctrl)
 		nbl_dev_remove_ctrl_dev(adapter);
 	nbl_dev_remove_common_dev(adapter);
+	nbl_common_destroy_wq(common);
 }
 
 /* ----------  Dev start process  ---------- */
 int nbl_dev_start(struct nbl_adapter *adapter)
 {
+	struct nbl_dev_mgt *dev_mgt = adapter->core.dev_mgt;
+	struct nbl_dev_common *common_dev = dev_mgt->common_dev;
+	int cleanup_ret;
+	int ret;
+
+	ret = nbl_dev_configure_msix_map(dev_mgt);
+	if (ret)
+		return ret;
+
+	ret = nbl_dev_init_interrupt_scheme(dev_mgt);
+	if (ret)
+		goto init_interrupt_scheme_err;
+	ret = nbl_dev_request_mailbox_irq(dev_mgt);
+	if (ret)
+		goto mailbox_request_irq_err;
+	ret = nbl_dev_enable_mailbox_irq(dev_mgt);
+	if (ret)
+		goto enable_mailbox_irq_err;
+
 	return 0;
+enable_mailbox_irq_err:
+	cleanup_ret = nbl_dev_disable_mailbox_irq(dev_mgt);
+	/* just log err*/
+	if (cleanup_ret)
+		dev_err(dev_mgt->common->dev,
+			"Failed to disable mailbox IRQ: %d\n", cleanup_ret);
+	nbl_dev_free_mailbox_irq(dev_mgt);
+	cancel_work_sync(&common_dev->clean_mbx_task);
+mailbox_request_irq_err:
+	nbl_dev_clear_interrupt_scheme(dev_mgt);
+init_interrupt_scheme_err:
+	cleanup_ret =  nbl_dev_destroy_msix_map(dev_mgt);
+	/* just log err*/
+	if (cleanup_ret)
+		dev_err(dev_mgt->common->dev,
+			"Failed to destroy MSI-X map: %d\n", cleanup_ret);
+	return ret;
 }
 
 void nbl_dev_stop(struct nbl_adapter *adapter)
 {
+	struct nbl_dev_mgt *dev_mgt = adapter->core.dev_mgt;
+	struct nbl_dev_common *common_dev = dev_mgt->common_dev;
+	int ret;
+
+	/* just log err*/
+	ret = nbl_dev_disable_mailbox_irq(dev_mgt);
+	if (ret)
+		dev_err(dev_mgt->common->dev,
+			"Failed to disable mailbox IRQ: %d\n", ret);
+	nbl_dev_free_mailbox_irq(dev_mgt);
+	cancel_work_sync(&common_dev->clean_mbx_task);
+	nbl_dev_clear_interrupt_scheme(dev_mgt);
+	ret = nbl_dev_destroy_msix_map(dev_mgt);
+	if (ret)
+		dev_err(dev_mgt->common->dev,
+			"Failed to destroy MSI-X map: %d\n", ret);
 }
diff --git a/drivers/net/ethernet/nebula-matrix/nbl/nbl_hw/nbl_resource.c b/drivers/net/ethernet/nebula-matrix/nbl/nbl_hw/nbl_resource.c
index 6742da7c6637..e8d43bef8687 100644
--- a/drivers/net/ethernet/nebula-matrix/nbl/nbl_hw/nbl_resource.c
+++ b/drivers/net/ethernet/nebula-matrix/nbl/nbl_hw/nbl_resource.c
@@ -112,7 +112,7 @@ int nbl_res_get_eth_id(struct nbl_resource_mgt *res_mgt, u16 func_id,
 		return -EINVAL;
 	}
 	if (abs_pf_id != pfid) {
-		dev_err(dev, "invalid pf id %u\n", pfid);
+		dev_err(dev, "invalid pf id %u vsi %u\n", pfid, vsi_id);
 		return -EINVAL;
 	}
 	rel_pf_id = abs_pf_id - common->mgt_pf;
diff --git a/drivers/net/ethernet/nebula-matrix/nbl/nbl_include/nbl_def_common.h b/drivers/net/ethernet/nebula-matrix/nbl/nbl_include/nbl_def_common.h
index bc741b7df7b9..4621b3ce5856 100644
--- a/drivers/net/ethernet/nebula-matrix/nbl/nbl_include/nbl_def_common.h
+++ b/drivers/net/ethernet/nebula-matrix/nbl/nbl_include/nbl_def_common.h
@@ -29,6 +29,7 @@ struct nbl_hash_tbl_mgt;
 	})
 
 struct nbl_common_info {
+	struct workqueue_struct *wq;
 	struct pci_dev *pdev;
 	struct device *dev;
 	u32 msg_enable;
@@ -61,6 +62,11 @@ struct nbl_hash_tbl_del_key {
 	void (*action_func)(void *priv, void *key, void *data);
 };
 
+void nbl_common_queue_work(struct nbl_common_info *common,
+			   struct work_struct *task);
+
+void nbl_common_destroy_wq(struct nbl_common_info *common);
+int nbl_common_create_wq(struct nbl_common_info *common);
 u32 nbl_common_pf_id_subtraction_mgtpf_id(struct nbl_common_info *common,
 					  u32 pf_id);
 
-- 
2.47.3