[SIG-CLOUD-10] LE-3924 LE-3920 LE-3916

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

@@ -8,6 +8,7 @@
 #include <linux/version.h>
 
 #include <net/mana/mana.h>
+#include <net/mana/hw_channel.h>
 
 struct dentry *mana_debugfs_root;
 
@@ -63,6 +64,24 @@ static void mana_gd_init_registers(struct pci_dev *pdev)
 		mana_gd_init_vf_regs(pdev);
 }
 
+/* Suppress logging when we set timeout to zero */
+bool mana_need_log(struct gdma_context *gc, int err)
+{
+	struct hw_channel_context *hwc;
+
+	if (err != -ETIMEDOUT)
+		return true;
+
+	if (!gc)
+		return true;
+
+	hwc = gc->hwc.driver_data;
+	if (hwc && hwc->hwc_timeout == 0)
+		return false;
+
+	return true;
+}
+
 static int mana_gd_query_max_resources(struct pci_dev *pdev)
 {
 	struct gdma_context *gc = pci_get_drvdata(pdev);
@@ -266,8 +285,9 @@ static int mana_gd_disable_queue(struct gdma_queue *queue)
 
 	err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp), &resp);
 	if (err || resp.hdr.status) {
-		dev_err(gc->dev, "Failed to disable queue: %d, 0x%x\n", err,
-			resp.hdr.status);
+		if (mana_need_log(gc, err))
+			dev_err(gc->dev, "Failed to disable queue: %d, 0x%x\n", err,
+				resp.hdr.status);
 		return err ? err : -EPROTO;
 	}
 
@@ -350,11 +370,113 @@ void mana_gd_ring_cq(struct gdma_queue *cq, u8 arm_bit)
 			      head, arm_bit);
 }
 
+#define MANA_SERVICE_PERIOD 10
+
+static void mana_serv_fpga(struct pci_dev *pdev)
+{
+	struct pci_bus *bus, *parent;
+
+	pci_lock_rescan_remove();
+
+	bus = pdev->bus;
+	if (!bus) {
+		dev_err(&pdev->dev, "MANA service: no bus\n");
+		goto out;
+	}
+
+	parent = bus->parent;
+	if (!parent) {
+		dev_err(&pdev->dev, "MANA service: no parent bus\n");
+		goto out;
+	}
+
+	pci_stop_and_remove_bus_device(bus->self);
+
+	msleep(MANA_SERVICE_PERIOD * 1000);
+
+	pci_rescan_bus(parent);
+
+out:
+	pci_unlock_rescan_remove();
+}
+
+static void mana_serv_reset(struct pci_dev *pdev)
+{
+	struct gdma_context *gc = pci_get_drvdata(pdev);
+	struct hw_channel_context *hwc;
+
+	if (!gc) {
+		dev_err(&pdev->dev, "MANA service: no GC\n");
+		return;
+	}
+
+	hwc = gc->hwc.driver_data;
+	if (!hwc) {
+		dev_err(&pdev->dev, "MANA service: no HWC\n");
+		goto out;
+	}
+
+	/* HWC is not responding in this case, so don't wait */
+	hwc->hwc_timeout = 0;
+
+	dev_info(&pdev->dev, "MANA reset cycle start\n");
+
+	mana_gd_suspend(pdev, PMSG_SUSPEND);
+
+	msleep(MANA_SERVICE_PERIOD * 1000);
+
+	mana_gd_resume(pdev);
+
+	dev_info(&pdev->dev, "MANA reset cycle completed\n");
+
+out:
+	gc->in_service = false;
+}
+
+struct mana_serv_work {
+	struct work_struct serv_work;
+	struct pci_dev *pdev;
+	enum gdma_eqe_type type;
+};
+
+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)
+		goto out;
+
+	switch (mns_wk->type) {
+	case GDMA_EQE_HWC_FPGA_RECONFIG:
+		mana_serv_fpga(pdev);
+		break;
+
+	case GDMA_EQE_HWC_RESET_REQUEST:
+		mana_serv_reset(pdev);
+		break;
+
+	default:
+		dev_err(&pdev->dev, "MANA service: unknown type %d\n",
+			mns_wk->type);
+		break;
+	}
+
+out:
+	pci_dev_put(pdev);
+	kfree(mns_wk);
+	module_put(THIS_MODULE);
+}
+
 static void mana_gd_process_eqe(struct gdma_queue *eq)
 {
 	u32 head = eq->head % (eq->queue_size / GDMA_EQE_SIZE);
 	struct gdma_context *gc = eq->gdma_dev->gdma_context;
 	struct gdma_eqe *eq_eqe_ptr = eq->queue_mem_ptr;
+	struct mana_serv_work *mns_wk;
 	union gdma_eqe_info eqe_info;
 	enum gdma_eqe_type type;
 	struct gdma_event event;
@@ -398,6 +520,35 @@ static void mana_gd_process_eqe(struct gdma_queue *eq)
 		eq->eq.callback(eq->eq.context, eq, &event);
 		break;
 
+	case GDMA_EQE_HWC_FPGA_RECONFIG:
+	case GDMA_EQE_HWC_RESET_REQUEST:
+		dev_info(gc->dev, "Recv MANA service type:%d\n", type);
+
+		if (gc->in_service) {
+			dev_info(gc->dev, "Already in service\n");
+			break;
+		}
+
+		if (!try_module_get(THIS_MODULE)) {
+			dev_info(gc->dev, "Module is unloading\n");
+			break;
+		}
+
+		mns_wk = kzalloc(sizeof(*mns_wk), GFP_ATOMIC);
+		if (!mns_wk) {
+			module_put(THIS_MODULE);
+			break;
+		}
+
+		dev_info(gc->dev, "Start MANA service type:%d\n", type);
+		gc->in_service = true;
+		mns_wk->pdev = to_pci_dev(gc->dev);
+		mns_wk->type = type;
+		pci_dev_get(mns_wk->pdev);
+		INIT_WORK(&mns_wk->serv_work, mana_serv_func);
+		schedule_work(&mns_wk->serv_work);
+		break;
+
 	default:
 		break;
 	}
@@ -539,7 +690,8 @@ int mana_gd_test_eq(struct gdma_context *gc, struct gdma_queue *eq)
 
 	err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp), &resp);
 	if (err) {
-		dev_err(dev, "test_eq failed: %d\n", err);
+		if (mana_need_log(gc, err))
+			dev_err(dev, "test_eq failed: %d\n", err);
 		goto out;
 	}
 
@@ -574,7 +726,7 @@ static void mana_gd_destroy_eq(struct gdma_context *gc, bool flush_evenets,
 
 	if (flush_evenets) {
 		err = mana_gd_test_eq(gc, queue);
-		if (err)
+		if (err && mana_need_log(gc, err))
 			dev_warn(gc->dev, "Failed to flush EQ: %d\n", err);
 	}
 
@@ -720,8 +872,9 @@ int mana_gd_destroy_dma_region(struct gdma_context *gc, u64 dma_region_handle)
 
 	err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp), &resp);
 	if (err || resp.hdr.status) {
-		dev_err(gc->dev, "Failed to destroy DMA region: %d, 0x%x\n",
-			err, resp.hdr.status);
+		if (mana_need_log(gc, err))
+			dev_err(gc->dev, "Failed to destroy DMA region: %d, 0x%x\n",
+				err, resp.hdr.status);
 		return -EPROTO;
 	}
 
@@ -1020,8 +1173,9 @@ int mana_gd_deregister_device(struct gdma_dev *gd)
 
 	err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp), &resp);
 	if (err || resp.hdr.status) {
-		dev_err(gc->dev, "Failed to deregister device: %d, 0x%x\n",
-			err, resp.hdr.status);
+		if (mana_need_log(gc, err))
+			dev_err(gc->dev, "Failed to deregister device: %d, 0x%x\n",
+				err, resp.hdr.status);
 		if (!err)
 			err = -EPROTO;
 	}
@@ -1621,7 +1775,7 @@ static void mana_gd_remove(struct pci_dev *pdev)
 }
 
 /* The 'state' parameter is not used. */
-static int mana_gd_suspend(struct pci_dev *pdev, pm_message_t state)
+int mana_gd_suspend(struct pci_dev *pdev, pm_message_t state)
 {
 	struct gdma_context *gc = pci_get_drvdata(pdev);
 
@@ -1636,7 +1790,7 @@ static int mana_gd_suspend(struct pci_dev *pdev, pm_message_t state)
  * fail -- if this happens, it's safer to just report an error than try to undo
  * what has been done.
  */
-static int mana_gd_resume(struct pci_dev *pdev)
+int mana_gd_resume(struct pci_dev *pdev)
 {
 	struct gdma_context *gc = pci_get_drvdata(pdev);
 	int err;

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

@@ -2,6 +2,7 @@
 /* Copyright (c) 2021, Microsoft Corporation. */
 
 #include <net/mana/gdma.h>
+#include <net/mana/mana.h>
 #include <net/mana/hw_channel.h>
 #include <linux/vmalloc.h>
 
@@ -860,7 +861,9 @@ int mana_hwc_send_request(struct hw_channel_context *hwc, u32 req_len,
 
 	if (!wait_for_completion_timeout(&ctx->comp_event,
 					 (msecs_to_jiffies(hwc->hwc_timeout)))) {
-		dev_err(hwc->dev, "HWC: Request timed out!\n");
+		if (hwc->hwc_timeout != 0)
+			dev_err(hwc->dev, "HWC: Request timed out!\n");
+
 		err = -ETIMEDOUT;
 		goto out;
 	}
@@ -871,8 +874,9 @@ int mana_hwc_send_request(struct hw_channel_context *hwc, u32 req_len,
 	}
 
 	if (ctx->status_code && ctx->status_code != GDMA_STATUS_MORE_ENTRIES) {
-		dev_err(hwc->dev, "HWC: Failed hw_channel req: 0x%x\n",
-			ctx->status_code);
+		if (req_msg->req.msg_type != MANA_QUERY_PHY_STAT)
+			dev_err(hwc->dev, "HWC: Failed hw_channel req: 0x%x\n",
+				ctx->status_code);
 		err = -EPROTO;
 		goto out;
 	}