Merge branch 'mana-misc'

Dexuan Cui says:

====================
net: mana: some misc patches

Patch 1 is a small fix.

Patch 2 reports OS info to the PF driver.
Before the patch, the req fields were all zeros.

Patch 3 fixes and cleans up the error handling of HWC creation failure.

Patch 4 adds the callbacks for hibernation/kexec. It's based on patch 3.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

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

@@ -3,6 +3,8 @@
 
 #include <linux/module.h>
 #include <linux/pci.h>
+#include <linux/utsname.h>
+#include <linux/version.h>
 
 #include "mana.h"
 
@@ -848,6 +850,15 @@ int mana_gd_verify_vf_version(struct pci_dev *pdev)
 	req.gd_drv_cap_flags3 = GDMA_DRV_CAP_FLAGS3;
 	req.gd_drv_cap_flags4 = GDMA_DRV_CAP_FLAGS4;
 
+	req.drv_ver = 0;	/* Unused*/
+	req.os_type = 0x10;	/* Linux */
+	req.os_ver_major = LINUX_VERSION_MAJOR;
+	req.os_ver_minor = LINUX_VERSION_PATCHLEVEL;
+	req.os_ver_build = LINUX_VERSION_SUBLEVEL;
+	strscpy(req.os_ver_str1, utsname()->sysname, sizeof(req.os_ver_str1));
+	strscpy(req.os_ver_str2, utsname()->release, sizeof(req.os_ver_str2));
+	strscpy(req.os_ver_str3, utsname()->version, sizeof(req.os_ver_str3));
+
 	err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp), &resp);
 	if (err || resp.hdr.status) {
 		dev_err(gc->dev, "VfVerifyVersionOutput: %d, status=0x%x\n",
@@ -1247,6 +1258,52 @@ static void mana_gd_remove_irqs(struct pci_dev *pdev)
 	gc->irq_contexts = NULL;
 }
 
+static int mana_gd_setup(struct pci_dev *pdev)
+{
+	struct gdma_context *gc = pci_get_drvdata(pdev);
+	int err;
+
+	mana_gd_init_registers(pdev);
+	mana_smc_init(&gc->shm_channel, gc->dev, gc->shm_base);
+
+	err = mana_gd_setup_irqs(pdev);
+	if (err)
+		return err;
+
+	err = mana_hwc_create_channel(gc);
+	if (err)
+		goto remove_irq;
+
+	err = mana_gd_verify_vf_version(pdev);
+	if (err)
+		goto destroy_hwc;
+
+	err = mana_gd_query_max_resources(pdev);
+	if (err)
+		goto destroy_hwc;
+
+	err = mana_gd_detect_devices(pdev);
+	if (err)
+		goto destroy_hwc;
+
+	return 0;
+
+destroy_hwc:
+	mana_hwc_destroy_channel(gc);
+remove_irq:
+	mana_gd_remove_irqs(pdev);
+	return err;
+}
+
+static void mana_gd_cleanup(struct pci_dev *pdev)
+{
+	struct gdma_context *gc = pci_get_drvdata(pdev);
+
+	mana_hwc_destroy_channel(gc);
+
+	mana_gd_remove_irqs(pdev);
+}
+
 static int mana_gd_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	struct gdma_context *gc;
@@ -1276,6 +1333,9 @@ static int mana_gd_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (!gc)
 		goto release_region;
 
+	mutex_init(&gc->eq_test_event_mutex);
+	pci_set_drvdata(pdev, gc);
+
 	bar0_va = pci_iomap(pdev, bar, 0);
 	if (!bar0_va)
 		goto free_gc;
@@ -1283,49 +1343,23 @@ static int mana_gd_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	gc->bar0_va = bar0_va;
 	gc->dev = &pdev->dev;
 
-	pci_set_drvdata(pdev, gc);
 
-	mana_gd_init_registers(pdev);
-
-	mana_smc_init(&gc->shm_channel, gc->dev, gc->shm_base);
-
-	err = mana_gd_setup_irqs(pdev);
+	err = mana_gd_setup(pdev);
 	if (err)
 		goto unmap_bar;
 
-	mutex_init(&gc->eq_test_event_mutex);
-
-	err = mana_hwc_create_channel(gc);
-	if (err)
-		goto remove_irq;
-
-	err = mana_gd_verify_vf_version(pdev);
-	if (err)
-		goto remove_irq;
-
-	err = mana_gd_query_max_resources(pdev);
-	if (err)
-		goto remove_irq;
-
-	err = mana_gd_detect_devices(pdev);
+	err = mana_probe(&gc->mana, false);
 	if (err)
-		goto remove_irq;
-
-	err = mana_probe(&gc->mana);
-	if (err)
-		goto clean_up_gdma;
+		goto cleanup_gd;
 
 	return 0;
 
-clean_up_gdma:
-	mana_hwc_destroy_channel(gc);
-	vfree(gc->cq_table);
-	gc->cq_table = NULL;
-remove_irq:
-	mana_gd_remove_irqs(pdev);
+cleanup_gd:
+	mana_gd_cleanup(pdev);
 unmap_bar:
 	pci_iounmap(pdev, bar0_va);
 free_gc:
+	pci_set_drvdata(pdev, NULL);
 	vfree(gc);
 release_region:
 	pci_release_regions(pdev);
@@ -1340,13 +1374,9 @@ static void mana_gd_remove(struct pci_dev *pdev)
 {
 	struct gdma_context *gc = pci_get_drvdata(pdev);
 
-	mana_remove(&gc->mana);
+	mana_remove(&gc->mana, false);
 
-	mana_hwc_destroy_channel(gc);
-	vfree(gc->cq_table);
-	gc->cq_table = NULL;
-
-	mana_gd_remove_irqs(pdev);
+	mana_gd_cleanup(pdev);
 
 	pci_iounmap(pdev, gc->bar0_va);
 
@@ -1357,6 +1387,52 @@ static void mana_gd_remove(struct pci_dev *pdev)
 	pci_disable_device(pdev);
 }
 
+/* The 'state' parameter is not used. */
+static int mana_gd_suspend(struct pci_dev *pdev, pm_message_t state)
+{
+	struct gdma_context *gc = pci_get_drvdata(pdev);
+
+	mana_remove(&gc->mana, true);
+
+	mana_gd_cleanup(pdev);
+
+	return 0;
+}
+
+/* In case the NIC hardware stops working, the suspend and resume callbacks will
+ * 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)
+{
+	struct gdma_context *gc = pci_get_drvdata(pdev);
+	int err;
+
+	err = mana_gd_setup(pdev);
+	if (err)
+		return err;
+
+	err = mana_probe(&gc->mana, true);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+/* Quiesce the device for kexec. This is also called upon reboot/shutdown. */
+static void mana_gd_shutdown(struct pci_dev *pdev)
+{
+	struct gdma_context *gc = pci_get_drvdata(pdev);
+
+	dev_info(&pdev->dev, "Shutdown was calledd\n");
+
+	mana_remove(&gc->mana, true);
+
+	mana_gd_cleanup(pdev);
+
+	pci_disable_device(pdev);
+}
+
 #ifndef PCI_VENDOR_ID_MICROSOFT
 #define PCI_VENDOR_ID_MICROSOFT 0x1414
 #endif
@@ -1371,6 +1447,9 @@ static struct pci_driver mana_driver = {
 	.id_table	= mana_id_table,
 	.probe		= mana_gd_probe,
 	.remove		= mana_gd_remove,
+	.suspend	= mana_gd_suspend,
+	.resume		= mana_gd_resume,
+	.shutdown	= mana_gd_shutdown,
 };
 
 module_pci_driver(mana_driver);

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

@@ -309,9 +309,6 @@ static void mana_hwc_comp_event(void *ctx, struct gdma_queue *q_self)
 
 static void mana_hwc_destroy_cq(struct gdma_context *gc, struct hwc_cq *hwc_cq)
 {
-	if (!hwc_cq)
-		return;
-
 	kfree(hwc_cq->comp_buf);
 
 	if (hwc_cq->gdma_cq)
@@ -446,9 +443,6 @@ static void mana_hwc_dealloc_dma_buf(struct hw_channel_context *hwc,
 static void mana_hwc_destroy_wq(struct hw_channel_context *hwc,
 				struct hwc_wq *hwc_wq)
 {
-	if (!hwc_wq)
-		return;
-
 	mana_hwc_dealloc_dma_buf(hwc, hwc_wq->msg_buf);
 
 	if (hwc_wq->gdma_wq)
@@ -621,6 +615,7 @@ static int mana_hwc_establish_channel(struct gdma_context *gc, u16 *q_depth,
 	*max_req_msg_size = hwc->hwc_init_max_req_msg_size;
 	*max_resp_msg_size = hwc->hwc_init_max_resp_msg_size;
 
+	/* Both were set in mana_hwc_init_event_handler(). */
 	if (WARN_ON(cq->id >= gc->max_num_cqs))
 		return -EPROTO;
 
@@ -636,9 +631,6 @@ static int mana_hwc_establish_channel(struct gdma_context *gc, u16 *q_depth,
 static int mana_hwc_init_queues(struct hw_channel_context *hwc, u16 q_depth,
 				u32 max_req_msg_size, u32 max_resp_msg_size)
 {
-	struct hwc_wq *hwc_rxq = NULL;
-	struct hwc_wq *hwc_txq = NULL;
-	struct hwc_cq *hwc_cq = NULL;
 	int err;
 
 	err = mana_hwc_init_inflight_msg(hwc, q_depth);
@@ -651,44 +643,32 @@ static int mana_hwc_init_queues(struct hw_channel_context *hwc, u16 q_depth,
 	err = mana_hwc_create_cq(hwc, q_depth * 2,
 				 mana_hwc_init_event_handler, hwc,
 				 mana_hwc_rx_event_handler, hwc,
-				 mana_hwc_tx_event_handler, hwc, &hwc_cq);
+				 mana_hwc_tx_event_handler, hwc, &hwc->cq);
 	if (err) {
 		dev_err(hwc->dev, "Failed to create HWC CQ: %d\n", err);
 		goto out;
 	}
-	hwc->cq = hwc_cq;
 
 	err = mana_hwc_create_wq(hwc, GDMA_RQ, q_depth, max_req_msg_size,
-				 hwc_cq, &hwc_rxq);
+				 hwc->cq, &hwc->rxq);
 	if (err) {
 		dev_err(hwc->dev, "Failed to create HWC RQ: %d\n", err);
 		goto out;
 	}
-	hwc->rxq = hwc_rxq;
 
 	err = mana_hwc_create_wq(hwc, GDMA_SQ, q_depth, max_resp_msg_size,
-				 hwc_cq, &hwc_txq);
+				 hwc->cq, &hwc->txq);
 	if (err) {
 		dev_err(hwc->dev, "Failed to create HWC SQ: %d\n", err);
 		goto out;
 	}
-	hwc->txq = hwc_txq;
 
 	hwc->num_inflight_msg = q_depth;
 	hwc->max_req_msg_size = max_req_msg_size;
 
 	return 0;
 out:
-	if (hwc_txq)
-		mana_hwc_destroy_wq(hwc, hwc_txq);
-
-	if (hwc_rxq)
-		mana_hwc_destroy_wq(hwc, hwc_rxq);
-
-	if (hwc_cq)
-		mana_hwc_destroy_cq(hwc->gdma_dev->gdma_context, hwc_cq);
-
-	mana_gd_free_res_map(&hwc->inflight_msg_res);
+	/* mana_hwc_create_channel() will do the cleanup.*/
 	return err;
 }
 
@@ -716,6 +696,9 @@ int mana_hwc_create_channel(struct gdma_context *gc)
 	gd->pdid = INVALID_PDID;
 	gd->doorbell = INVALID_DOORBELL;
 
+	/* mana_hwc_init_queues() only creates the required data structures,
+	 * and doesn't touch the HWC device.
+	 */
 	err = mana_hwc_init_queues(hwc, HW_CHANNEL_VF_BOOTSTRAP_QUEUE_DEPTH,
 				   HW_CHANNEL_MAX_REQUEST_SIZE,
 				   HW_CHANNEL_MAX_RESPONSE_SIZE);
@@ -741,42 +724,50 @@ int mana_hwc_create_channel(struct gdma_context *gc)
 
 	return 0;
 out:
-	kfree(hwc);
+	mana_hwc_destroy_channel(gc);
 	return err;
 }
 
 void mana_hwc_destroy_channel(struct gdma_context *gc)
 {
 	struct hw_channel_context *hwc = gc->hwc.driver_data;
-	struct hwc_caller_ctx *ctx;
 
-	mana_smc_teardown_hwc(&gc->shm_channel, false);
+	if (!hwc)
+		return;
+
+	/* gc->max_num_cqs is set in mana_hwc_init_event_handler(). If it's
+	 * non-zero, the HWC worked and we should tear down the HWC here.
+	 */
+	if (gc->max_num_cqs > 0) {
+		mana_smc_teardown_hwc(&gc->shm_channel, false);
+		gc->max_num_cqs = 0;
+	}
 
-	ctx = hwc->caller_ctx;
-	kfree(ctx);
+	kfree(hwc->caller_ctx);
 	hwc->caller_ctx = NULL;
 
-	mana_hwc_destroy_wq(hwc, hwc->txq);
-	hwc->txq = NULL;
+	if (hwc->txq)
+		mana_hwc_destroy_wq(hwc, hwc->txq);
 
-	mana_hwc_destroy_wq(hwc, hwc->rxq);
-	hwc->rxq = NULL;
+	if (hwc->rxq)
+		mana_hwc_destroy_wq(hwc, hwc->rxq);
 
-	mana_hwc_destroy_cq(hwc->gdma_dev->gdma_context, hwc->cq);
-	hwc->cq = NULL;
+	if (hwc->cq)
+		mana_hwc_destroy_cq(hwc->gdma_dev->gdma_context, hwc->cq);
 
 	mana_gd_free_res_map(&hwc->inflight_msg_res);
 
 	hwc->num_inflight_msg = 0;
 
-	if (hwc->gdma_dev->pdid != INVALID_PDID) {
-		hwc->gdma_dev->doorbell = INVALID_DOORBELL;
-		hwc->gdma_dev->pdid = INVALID_PDID;
-	}
+	hwc->gdma_dev->doorbell = INVALID_DOORBELL;
+	hwc->gdma_dev->pdid = INVALID_PDID;
 
 	kfree(hwc);
 	gc->hwc.driver_data = NULL;
 	gc->hwc.gdma_context = NULL;
+
+	vfree(gc->cq_table);
+	gc->cq_table = NULL;
 }
 
 int mana_hwc_send_request(struct hw_channel_context *hwc, u32 req_len,

drivers/net/ethernet/microsoft/mana/mana.h

@@ -374,8 +374,8 @@ int mana_alloc_queues(struct net_device *ndev);
 int mana_attach(struct net_device *ndev);
 int mana_detach(struct net_device *ndev, bool from_close);
 
-int mana_probe(struct gdma_dev *gd);
-void mana_remove(struct gdma_dev *gd);
+int mana_probe(struct gdma_dev *gd, bool resuming);
+void mana_remove(struct gdma_dev *gd, bool suspending);
 
 extern const struct ethtool_ops mana_ethtool_ops;
 

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

@@ -1599,7 +1599,8 @@ static int mana_init_port(struct net_device *ndev)
 	err = mana_query_vport_cfg(apc, port_idx, &max_txq, &max_rxq,
 				   &num_indirect_entries);
 	if (err) {
-		netdev_err(ndev, "Failed to query info for vPort 0\n");
+		netdev_err(ndev, "Failed to query info for vPort %d\n",
+			   port_idx);
 		goto reset_apc;
 	}
 
@@ -1827,11 +1828,12 @@ static int mana_probe_port(struct mana_context *ac, int port_idx,
 	return err;
 }
 
-int mana_probe(struct gdma_dev *gd)
+int mana_probe(struct gdma_dev *gd, bool resuming)
 {
 	struct gdma_context *gc = gd->gdma_context;
+	struct mana_context *ac = gd->driver_data;
 	struct device *dev = gc->dev;
-	struct mana_context *ac;
+	u16 num_ports = 0;
 	int err;
 	int i;
 
@@ -1843,44 +1845,70 @@ int mana_probe(struct gdma_dev *gd)
 	if (err)
 		return err;
 
-	ac = kzalloc(sizeof(*ac), GFP_KERNEL);
-	if (!ac)
-		return -ENOMEM;
+	if (!resuming) {
+		ac = kzalloc(sizeof(*ac), GFP_KERNEL);
+		if (!ac)
+			return -ENOMEM;
 
-	ac->gdma_dev = gd;
-	ac->num_ports = 1;
-	gd->driver_data = ac;
+		ac->gdma_dev = gd;
+		gd->driver_data = ac;
+	}
 
 	err = mana_create_eq(ac);
 	if (err)
 		goto out;
 
 	err = mana_query_device_cfg(ac, MANA_MAJOR_VERSION, MANA_MINOR_VERSION,
-				    MANA_MICRO_VERSION, &ac->num_ports);
+				    MANA_MICRO_VERSION, &num_ports);
 	if (err)
 		goto out;
 
+	if (!resuming) {
+		ac->num_ports = num_ports;
+	} else {
+		if (ac->num_ports != num_ports) {
+			dev_err(dev, "The number of vPorts changed: %d->%d\n",
+				ac->num_ports, num_ports);
+			err = -EPROTO;
+			goto out;
+		}
+	}
+
+	if (ac->num_ports == 0)
+		dev_err(dev, "Failed to detect any vPort\n");
+
 	if (ac->num_ports > MAX_PORTS_IN_MANA_DEV)
 		ac->num_ports = MAX_PORTS_IN_MANA_DEV;
 
-	for (i = 0; i < ac->num_ports; i++) {
-		err = mana_probe_port(ac, i, &ac->ports[i]);
-		if (err)
-			break;
+	if (!resuming) {
+		for (i = 0; i < ac->num_ports; i++) {
+			err = mana_probe_port(ac, i, &ac->ports[i]);
+			if (err)
+				break;
+		}
+	} else {
+		for (i = 0; i < ac->num_ports; i++) {
+			rtnl_lock();
+			err = mana_attach(ac->ports[i]);
+			rtnl_unlock();
+			if (err)
+				break;
+		}
 	}
 out:
 	if (err)
-		mana_remove(gd);
+		mana_remove(gd, false);
 
 	return err;
 }
 
-void mana_remove(struct gdma_dev *gd)
+void mana_remove(struct gdma_dev *gd, bool suspending)
 {
 	struct gdma_context *gc = gd->gdma_context;
 	struct mana_context *ac = gd->driver_data;
 	struct device *dev = gc->dev;
 	struct net_device *ndev;
+	int err;
 	int i;
 
 	for (i = 0; i < ac->num_ports; i++) {
@@ -1896,7 +1924,16 @@ void mana_remove(struct gdma_dev *gd)
 		 */
 		rtnl_lock();
 
-		mana_detach(ndev, false);
+		err = mana_detach(ndev, false);
+		if (err)
+			netdev_err(ndev, "Failed to detach vPort %d: %d\n",
+				   i, err);
+
+		if (suspending) {
+			/* No need to unregister the ndev. */
+			rtnl_unlock();
+			continue;
+		}
 
 		unregister_netdevice(ndev);
 
@@ -1909,6 +1946,10 @@ void mana_remove(struct gdma_dev *gd)
 
 out:
 	mana_gd_deregister_device(gd);
+
+	if (suspending)
+		return;
+
 	gd->driver_data = NULL;
 	gd->gdma_context = NULL;
 	kfree(ac);