net: mana: Handle hardware recovery events when probing the device

When MANA is being probed, it's possible that hardware is in recovery
mode and the device may get GDMA_EQE_HWC_RESET_REQUEST over HWC in the
middle of the probe. Detect such condition and go through the recovery
service procedure.

Signed-off-by: Long Li <[e-mail]>
Reviewed-by: Haiyang Zhang <[e-mail]>
Link: https://patch.msgid.link/[e-mail]
Signed-off-by: Jakub Kicinski <[e-mail]>

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

···
 
 struct dentry *mana_debugfs_root;
 
+struct mana_dev_recovery {
+	struct list_head list;
+	struct pci_dev *pdev;
+	enum gdma_eqe_type type;
+};
+
+static struct mana_dev_recovery_work {
+	struct list_head dev_list;
+	struct delayed_work work;
+
+	/* Lock for dev_list above */
+	spinlock_t lock;
+} mana_dev_recovery_work;
+
 static u32 mana_gd_r32(struct gdma_context *g, u64 offset)
 {
 	return readl(g->bar0_va + offset);
···
 
 #define MANA_SERVICE_PERIOD 10
 
+static void mana_serv_rescan(struct pci_dev *pdev)
+{
+	struct pci_bus *parent;
+
+	pci_lock_rescan_remove();
+
+	parent = pdev->bus;
+	if (!parent) {
+		dev_err(&pdev->dev, "MANA service: no parent bus\n");
+		goto out;
+	}
+
+	pci_stop_and_remove_bus_device(pdev);
+	pci_rescan_bus(parent);
+
+out:
+	pci_unlock_rescan_remove();
+}
+
 static void mana_serv_fpga(struct pci_dev *pdev)
 {
 	struct pci_bus *bus, *parent;
···
 {
 	struct gdma_context *gc = pci_get_drvdata(pdev);
 	struct hw_channel_context *hwc;
+	int ret;
 
 	if (!gc) {
-		dev_err(&pdev->dev, "MANA service: no GC\n");
+		/* Perform PCI rescan on device if GC is not set up */
+		dev_err(&pdev->dev, "MANA service: GC not setup, rescanning\n");
+		mana_serv_rescan(pdev);
 		return;
 	}
 
···
 
 	msleep(MANA_SERVICE_PERIOD * 1000);
 
-	mana_gd_resume(pdev);
+	ret = mana_gd_resume(pdev);
+	if (ret == -ETIMEDOUT || ret == -EPROTO) {
+		/* Perform PCI rescan on device if we failed on HWC */
+		dev_err(&pdev->dev, "MANA service: resume failed, rescanning\n");
+		mana_serv_rescan(pdev);
+		goto out;
+	}
 
-	dev_info(&pdev->dev, "MANA reset cycle completed\n");
+	if (ret)
+		dev_info(&pdev->dev, "MANA reset cycle failed err %d\n", ret);
+	else
+		dev_info(&pdev->dev, "MANA reset cycle completed\n");
 
 out:
 	gc->in_service = false;
···
 	enum gdma_eqe_type type;
 };
 
-static void mana_serv_func(struct work_struct *w)
+static void mana_do_service(enum gdma_eqe_type type, struct pci_dev *pdev)
 {
-	struct mana_serv_work *mns_wk;
-	struct pci_dev *pdev;
-
-	mns_wk = container_of(w, struct mana_serv_work, serv_work);
-	pdev = mns_wk->pdev;
-
-	if (!pdev)
-		goto out;
-
-	switch (mns_wk->type) {
+	switch (type) {
 	case GDMA_EQE_HWC_FPGA_RECONFIG:
 		mana_serv_fpga(pdev);
 		break;
···
 		break;
 
 	default:
-		dev_err(&pdev->dev, "MANA service: unknown type %d\n",
-			mns_wk->type);
+		dev_err(&pdev->dev, "MANA service: unknown type %d\n", type);
 		break;
 	}
+}
 
-out:
+static void mana_recovery_delayed_func(struct work_struct *w)
+{
+	struct mana_dev_recovery_work *work;
+	struct mana_dev_recovery *dev;
+	unsigned long flags;
+
+	work = container_of(w, struct mana_dev_recovery_work, work.work);
+
+	spin_lock_irqsave(&work->lock, flags);
+
+	while (!list_empty(&work->dev_list)) {
+		dev = list_first_entry(&work->dev_list,
+				       struct mana_dev_recovery, list);
+		list_del(&dev->list);
+		spin_unlock_irqrestore(&work->lock, flags);
+
+		mana_do_service(dev->type, dev->pdev);
+		pci_dev_put(dev->pdev);
+		kfree(dev);
+
+		spin_lock_irqsave(&work->lock, flags);
+	}
+
+	spin_unlock_irqrestore(&work->lock, flags);
+}
+
+static void mana_serv_func(struct work_struct *w)
+{
+	struct mana_serv_work *mns_wk;
+	struct pci_dev *pdev;
+
+	mns_wk = container_of(w, struct mana_serv_work, serv_work);
+	pdev = mns_wk->pdev;
+
+	if (pdev)
+		mana_do_service(mns_wk->type, pdev);
+
 	pci_dev_put(pdev);
 	kfree(mns_wk);
 	module_put(THIS_MODULE);
···
 	case GDMA_EQE_HWC_FPGA_RECONFIG:
 	case GDMA_EQE_HWC_RESET_REQUEST:
 		dev_info(gc->dev, "Recv MANA service type:%d\n", type);
+
+		if (!test_and_set_bit(GC_PROBE_SUCCEEDED, &gc->flags)) {
+			/*
+			 * Device is in probe and we received a hardware reset
+			 * event, the probe function will detect that the flag
+			 * has changed and perform service procedure.
+			 */
+			dev_info(gc->dev,
+				 "Service is to be processed in probe\n");
+			break;
+		}
 
 		if (gc->in_service) {
 			dev_info(gc->dev, "Already in service\n");
···
 	if (err)
 		goto cleanup_mana;
 
+	/*
+	 * If a hardware reset event has occurred over HWC during probe,
+	 * rollback and perform hardware reset procedure.
+	 */
+	if (test_and_set_bit(GC_PROBE_SUCCEEDED, &gc->flags)) {
+		err = -EPROTO;
+		goto cleanup_mana_rdma;
+	}
+
 	return 0;
 
+cleanup_mana_rdma:
+	mana_rdma_remove(&gc->mana_ib);
 cleanup_mana:
 	mana_remove(&gc->mana, false);
 cleanup_gd:
···
 disable_dev:
 	pci_disable_device(pdev);
 	dev_err(&pdev->dev, "gdma probe failed: err = %d\n", err);
+
+	/*
+	 * Hardware could be in recovery mode and the HWC returns TIMEDOUT or
+	 * EPROTO from mana_gd_setup(), mana_probe() or mana_rdma_probe(), or
+	 * we received a hardware reset event over HWC interrupt. In this case,
+	 * perform the device recovery procedure after MANA_SERVICE_PERIOD
+	 * seconds.
+	 */
+	if (err == -ETIMEDOUT || err == -EPROTO) {
+		struct mana_dev_recovery *dev;
+		unsigned long flags;
+
+		dev_info(&pdev->dev, "Start MANA recovery mode\n");
+
+		dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+		if (!dev)
+			return err;
+
+		dev->pdev = pci_dev_get(pdev);
+		dev->type = GDMA_EQE_HWC_RESET_REQUEST;
+
+		spin_lock_irqsave(&mana_dev_recovery_work.lock, flags);
+		list_add_tail(&dev->list, &mana_dev_recovery_work.dev_list);
+		spin_unlock_irqrestore(&mana_dev_recovery_work.lock, flags);
+
+		schedule_delayed_work(&mana_dev_recovery_work.work,
+				      secs_to_jiffies(MANA_SERVICE_PERIOD));
+	}
+
 	return err;
 }
 
···
 {
 	int err;
 
+	INIT_LIST_HEAD(&mana_dev_recovery_work.dev_list);
+	spin_lock_init(&mana_dev_recovery_work.lock);
+	INIT_DELAYED_WORK(&mana_dev_recovery_work.work, mana_recovery_delayed_func);
+
 	mana_debugfs_root = debugfs_create_dir("mana", NULL);
 
 	err = pci_register_driver(&mana_driver);
···
 
 static void __exit mana_driver_exit(void)
 {
+	struct mana_dev_recovery *dev;
+	unsigned long flags;
+
+	disable_delayed_work_sync(&mana_dev_recovery_work.work);
+
+	spin_lock_irqsave(&mana_dev_recovery_work.lock, flags);
+	while (!list_empty(&mana_dev_recovery_work.dev_list)) {
+		dev = list_first_entry(&mana_dev_recovery_work.dev_list,
+				       struct mana_dev_recovery, list);
+		list_del(&dev->list);
+		pci_dev_put(dev->pdev);
+		kfree(dev);
+	}
+	spin_unlock_irqrestore(&mana_dev_recovery_work.lock, flags);
+
 	pci_unregister_driver(&mana_driver);
 
 	debugfs_remove(mana_debugfs_root);

include/net/mana/gdma.h

···
 	char name[MANA_IRQ_NAME_SZ];
 };
 
+enum gdma_context_flags {
+	GC_PROBE_SUCCEEDED	= 0,
+};
+
 struct gdma_context {
 	struct device		*dev;
 	struct dentry		*mana_pci_debugfs;
···
 	u64 pf_cap_flags1;
 
 	struct workqueue_struct *service_wq;
+
+	unsigned long		flags;
 };
 
 static inline bool mana_gd_is_mana(struct gdma_dev *gd)
···
 /* Driver can send HWC periodically to query stats */
 #define GDMA_DRV_CAP_FLAG_1_PERIODIC_STATS_QUERY BIT(21)
 
+/* Driver can handle hardware recovery events during probe */
+#define GDMA_DRV_CAP_FLAG_1_PROBE_RECOVERY BIT(22)
+
 #define GDMA_DRV_CAP_FLAGS1 \
 	(GDMA_DRV_CAP_FLAG_1_EQ_SHARING_MULTI_VPORT | \
 	 GDMA_DRV_CAP_FLAG_1_NAPI_WKDONE_FIX | \
···
 	 GDMA_DRV_CAP_FLAG_1_HANDLE_RECONFIG_EQE | \
 	 GDMA_DRV_CAP_FLAG_1_HW_VPORT_LINK_AWARE | \
 	 GDMA_DRV_CAP_FLAG_1_PERIODIC_STATS_QUERY | \
-	 GDMA_DRV_CAP_FLAG_1_SKB_LINEARIZE)
+	 GDMA_DRV_CAP_FLAG_1_SKB_LINEARIZE | \
+	 GDMA_DRV_CAP_FLAG_1_PROBE_RECOVERY)
 
 #define GDMA_DRV_CAP_FLAGS2 0