net: mana: Add support for auxiliary device servicing events

JIRA: https://issues.redhat.com/browse/RHEL-80096

commit 505cc26
Author: Shiraz Saleem <shirazsaleem@microsoft.com>
Date:   Wed May 7 08:59:05 2025 -0700

    net: mana: Add support for auxiliary device servicing events

    Handle soc servicing events which require the rdma auxiliary device resources to
    be cleaned up during a suspend, and re-initialized during a resume.

    Signed-off-by: Shiraz Saleem <shirazsaleem@microsoft.com>
    Signed-off-by: Konstantin Taranov <kotaranov@microsoft.com>
    Link: https://patch.msgid.link/1746633545-17653-5-git-send-email-kotaranov@linux.microsoft.com
    Signed-off-by: Leon Romanovsky <leon@kernel.org>

Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>

Author: Maxim Levitsky

drivers/net/ethernet/microsoft/mana/gdma_main.c

@@ -392,6 +392,7 @@ static void mana_gd_process_eqe(struct gdma_queue *eq)
 	case GDMA_EQE_HWC_INIT_EQ_ID_DB:
 	case GDMA_EQE_HWC_INIT_DATA:
 	case GDMA_EQE_HWC_INIT_DONE:
+	case GDMA_EQE_HWC_SOC_SERVICE:
 	case GDMA_EQE_RNIC_QP_FATAL:
 		if (!eq->eq.callback)
 			break;
@@ -1469,10 +1470,14 @@ static int mana_gd_setup(struct pci_dev *pdev)
 	mana_gd_init_registers(pdev);
 	mana_smc_init(&gc->shm_channel, gc->dev, gc->shm_base);
 
+	gc->service_wq = alloc_ordered_workqueue("gdma_service_wq", 0);
+	if (!gc->service_wq)
+		return -ENOMEM;
+
 	err = mana_gd_setup_irqs(pdev);
 	if (err) {
 		dev_err(gc->dev, "Failed to setup IRQs: %d\n", err);
-		return err;
+		goto free_workqueue;
 	}
 
 	err = mana_hwc_create_channel(gc);
@@ -1498,6 +1503,8 @@ static int mana_gd_setup(struct pci_dev *pdev)
 	mana_hwc_destroy_channel(gc);
 remove_irq:
 	mana_gd_remove_irqs(pdev);
+free_workqueue:
+	destroy_workqueue(gc->service_wq);
 	dev_err(&pdev->dev, "%s failed (error %d)\n", __func__, err);
 	return err;
 }
@@ -1509,6 +1516,8 @@ static void mana_gd_cleanup(struct pci_dev *pdev)
 	mana_hwc_destroy_channel(gc);
 
 	mana_gd_remove_irqs(pdev);
+
+	destroy_workqueue(gc->service_wq);
 	dev_dbg(&pdev->dev, "mana gdma cleanup successful\n");
 }
 

drivers/net/ethernet/microsoft/mana/hw_channel.c

@@ -111,11 +111,13 @@ static void mana_hwc_handle_resp(struct hw_channel_context *hwc, u32 resp_len,
 static void mana_hwc_init_event_handler(void *ctx, struct gdma_queue *q_self,
 					struct gdma_event *event)
 {
+	union hwc_init_soc_service_type service_data;
 	struct hw_channel_context *hwc = ctx;
 	struct gdma_dev *gd = hwc->gdma_dev;
 	union hwc_init_type_data type_data;
 	union hwc_init_eq_id_db eq_db;
 	u32 type, val;
+	int ret;
 
 	switch (event->type) {
 	case GDMA_EQE_HWC_INIT_EQ_ID_DB:
@@ -198,7 +200,24 @@ static void mana_hwc_init_event_handler(void *ctx, struct gdma_queue *q_self,
 		}
 
 		break;
+	case GDMA_EQE_HWC_SOC_SERVICE:
+		service_data.as_uint32 = event->details[0];
+		type = service_data.type;
 
+		switch (type) {
+		case GDMA_SERVICE_TYPE_RDMA_SUSPEND:
+		case GDMA_SERVICE_TYPE_RDMA_RESUME:
+			ret = mana_rdma_service_event(gd->gdma_context, type);
+			if (ret)
+				dev_err(hwc->dev, "Failed to schedule adev service event: %d\n",
+					ret);
+			break;
+		default:
+			dev_warn(hwc->dev, "Received unknown SOC service type %u\n", type);
+			break;
+		}
+
+		break;
 	default:
 		dev_warn(hwc->dev, "Received unknown gdma event %u\n", event->type);
 		/* Ignore unknown events, which should never happen. */

drivers/net/ethernet/microsoft/mana/mana_en.c

@@ -2991,6 +2991,70 @@ static int add_adev(struct gdma_dev *gd, const char *name)
 	return ret;
 }
 
+static void mana_rdma_service_handle(struct work_struct *work)
+{
+	struct mana_service_work *serv_work =
+		container_of(work, struct mana_service_work, work);
+	struct gdma_dev *gd = serv_work->gdma_dev;
+	struct device *dev = gd->gdma_context->dev;
+	int ret;
+
+	if (READ_ONCE(gd->rdma_teardown))
+		goto out;
+
+	switch (serv_work->event) {
+	case GDMA_SERVICE_TYPE_RDMA_SUSPEND:
+		if (!gd->adev || gd->is_suspended)
+			break;
+
+		remove_adev(gd);
+		gd->is_suspended = true;
+		break;
+
+	case GDMA_SERVICE_TYPE_RDMA_RESUME:
+		if (!gd->is_suspended)
+			break;
+
+		ret = add_adev(gd, "rdma");
+		if (ret)
+			dev_err(dev, "Failed to add adev on resume: %d\n", ret);
+		else
+			gd->is_suspended = false;
+		break;
+
+	default:
+		dev_warn(dev, "unknown adev service event %u\n",
+			 serv_work->event);
+		break;
+	}
+
+out:
+	kfree(serv_work);
+}
+
+int mana_rdma_service_event(struct gdma_context *gc, enum gdma_service_type event)
+{
+	struct gdma_dev *gd = &gc->mana_ib;
+	struct mana_service_work *serv_work;
+
+	if (gd->dev_id.type != GDMA_DEVICE_MANA_IB) {
+		/* RDMA device is not detected on pci */
+		return 0;
+	}
+
+	serv_work = kzalloc(sizeof(*serv_work), GFP_ATOMIC);
+	if (!serv_work)
+		return -ENOMEM;
+
+	serv_work->event = event;
+	serv_work->gdma_dev = gd;
+
+	INIT_WORK(&serv_work->work, mana_rdma_service_handle);
+	queue_work(gc->service_wq, &serv_work->work);
+
+	return 0;
+}
+
 int mana_probe(struct gdma_dev *gd, bool resuming)
 {
 	struct gdma_context *gc = gd->gdma_context;
@@ -3171,11 +3235,16 @@ int mana_rdma_probe(struct gdma_dev *gd)
 
 void mana_rdma_remove(struct gdma_dev *gd)
 {
+	struct gdma_context *gc = gd->gdma_context;
+
 	if (gd->dev_id.type != GDMA_DEVICE_MANA_IB) {
 		/* RDMA device is not detected on pci */
 		return;
 	}
 
+	WRITE_ONCE(gd->rdma_teardown, true);
+	flush_workqueue(gc->service_wq);
+
 	if (gd->adev)
 		remove_adev(gd);
 

include/net/mana/gdma.h

@@ -60,6 +60,7 @@ enum gdma_eqe_type {
 	GDMA_EQE_HWC_INIT_DONE		= 131,
 	GDMA_EQE_HWC_SOC_RECONFIG	= 132,
 	GDMA_EQE_HWC_SOC_RECONFIG_DATA	= 133,
+	GDMA_EQE_HWC_SOC_SERVICE	= 134,
 	GDMA_EQE_RNIC_QP_FATAL		= 176,
 };
 
@@ -70,6 +71,18 @@ enum {
 	GDMA_DEVICE_MANA_IB	= 3,
 };
 
+enum gdma_service_type {
+	GDMA_SERVICE_TYPE_NONE		= 0,
+	GDMA_SERVICE_TYPE_RDMA_SUSPEND	= 1,
+	GDMA_SERVICE_TYPE_RDMA_RESUME	= 2,
+};
+
+struct mana_service_work {
+	struct work_struct work;
+	struct gdma_dev *gdma_dev;
+	enum gdma_service_type event;
+};
+
 struct gdma_resource {
 	/* Protect the bitmap */
 	spinlock_t lock;
@@ -224,6 +237,8 @@ struct gdma_dev {
 	void *driver_data;
 
 	struct auxiliary_device *adev;
+	bool is_suspended;
+	bool rdma_teardown;
 };
 
 /* MANA_PAGE_SIZE is the DMA unit */
@@ -409,6 +424,8 @@ struct gdma_context {
 	struct gdma_dev		mana_ib;
 
 	u64 pf_cap_flags1;
+
+	struct workqueue_struct *service_wq;
 };
 
 static inline bool mana_gd_is_mana(struct gdma_dev *gd)
@@ -891,4 +908,6 @@ int mana_gd_destroy_dma_region(struct gdma_context *gc, u64 dma_region_handle);
 void mana_register_debugfs(void);
 void mana_unregister_debugfs(void);
 
+int mana_rdma_service_event(struct gdma_context *gc, enum gdma_service_type event);
+
 #endif /* _GDMA_H */

include/net/mana/hw_channel.h

@@ -49,6 +49,15 @@ union hwc_init_type_data {
 	};
 }; /* HW DATA */
 
+union hwc_init_soc_service_type {
+	u32 as_uint32;
+
+	struct {
+		u32 value	: 28;
+		u32 type	:  4;
+	};
+}; /* HW DATA */
+
 struct hwc_rx_oob {
 	u32 type	: 6;
 	u32 eom		: 1;