Merge branch 'hv_netvsc-associate-VF-and-PV-device-by-serial-number'

Stephen Hemminger says:

====================
hv_netvsc: associate VF and PV device by serial number

The Hyper-V implementation of PCI controller has concept of 32 bit serial number
(not to be confused with PCI-E serial number).  This value is sent in the protocol
from the host to indicate SR-IOV VF device is attached to a synthetic NIC.

Using the serial number (instead of MAC address) to associate the two devices
avoids lots of potential problems when there are duplicate MAC addresses from
tunnels or layered devices.

The patch set is broken into two parts, one is for the PCI controller
and the other is for the netvsc device. Normally, these go through different
trees but sending them together here for better review. The PCI changes
were submitted previously, but the main review comment was "why do you
need this?". This is why.

v2 - slot name can be shorter.
     remove locking when creating pci_slots; see comment for explaination
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 73 insertions, 25 deletions

diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 31c3d77b4733f0..fe01e141c8f87d 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -1203,6 +1203,9 @@ static void netvsc_send_vf(struct net_device *ndev,
 
 	net_device_ctx->vf_alloc = nvmsg->msg.v4_msg.vf_assoc.allocated;
 	net_device_ctx->vf_serial = nvmsg->msg.v4_msg.vf_assoc.serial;
+	netdev_info(ndev, "VF slot %u %s\n",
+		    net_device_ctx->vf_serial,
+		    net_device_ctx->vf_alloc ? "added" : "removed");
 }
 
 static  void netvsc_receive_inband(struct net_device *ndev,
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 915fbd66a02b5e..3af6d8d1523375 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -1894,20 +1894,6 @@ out_unlock:
 	rtnl_unlock();
 }
 
-static struct net_device *get_netvsc_bymac(const u8 *mac)
-{
-	struct net_device_context *ndev_ctx;
-
-	list_for_each_entry(ndev_ctx, &netvsc_dev_list, list) {
-		struct net_device *dev = hv_get_drvdata(ndev_ctx->device_ctx);
-
-		if (ether_addr_equal(mac, dev->perm_addr))
-			return dev;
-	}
-
-	return NULL;
-}
-
 static struct net_device *get_netvsc_byref(struct net_device *vf_netdev)
 {
 	struct net_device_context *net_device_ctx;
@@ -2036,26 +2022,48 @@ static void netvsc_vf_setup(struct work_struct *w)
 	rtnl_unlock();
 }
 
+/* Find netvsc by VMBus serial number.
+ * The PCI hyperv controller records the serial number as the slot.
+ */
+static struct net_device *get_netvsc_byslot(const struct net_device *vf_netdev)
+{
+	struct device *parent = vf_netdev->dev.parent;
+	struct net_device_context *ndev_ctx;
+	struct pci_dev *pdev;
+
+	if (!parent || !dev_is_pci(parent))
+		return NULL; /* not a PCI device */
+
+	pdev = to_pci_dev(parent);
+	if (!pdev->slot) {
+		netdev_notice(vf_netdev, "no PCI slot information\n");
+		return NULL;
+	}
+
+	list_for_each_entry(ndev_ctx, &netvsc_dev_list, list) {
+		if (!ndev_ctx->vf_alloc)
+			continue;
+
+		if (ndev_ctx->vf_serial == pdev->slot->number)
+			return hv_get_drvdata(ndev_ctx->device_ctx);
+	}
+
+	netdev_notice(vf_netdev,
+		      "no netdev found for slot %u\n", pdev->slot->number);
+	return NULL;
+}
+
 static int netvsc_register_vf(struct net_device *vf_netdev)
 {
-	struct net_device *ndev;
 	struct net_device_context *net_device_ctx;
-	struct device *pdev = vf_netdev->dev.parent;
 	struct netvsc_device *netvsc_dev;
+	struct net_device *ndev;
 	int ret;
 
 	if (vf_netdev->addr_len != ETH_ALEN)
 		return NOTIFY_DONE;
 
-	if (!pdev || !dev_is_pci(pdev) || dev_is_pf(pdev))
-		return NOTIFY_DONE;
-
-	/*
-	 * We will use the MAC address to locate the synthetic interface to
-	 * associate with the VF interface. If we don't find a matching
-	 * synthetic interface, move on.
-	 */
-	ndev = get_netvsc_bymac(vf_netdev->perm_addr);
+	ndev = get_netvsc_byslot(vf_netdev);
 	if (!ndev)
 		return NOTIFY_DONE;
 
diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c
index c00f82cc54aaca..ee80e79db21a24 100644
--- a/drivers/pci/controller/pci-hyperv.c
+++ b/drivers/pci/controller/pci-hyperv.c
@@ -89,6 +89,9 @@ static enum pci_protocol_version_t pci_protocol_version;
 
 #define STATUS_REVISION_MISMATCH 0xC0000059
 
+/* space for 32bit serial number as string */
+#define SLOT_NAME_SIZE 11
+
 /*
  * Message Types
  */
@@ -494,6 +497,7 @@ struct hv_pci_dev {
 	struct list_head list_entry;
 	refcount_t refs;
 	enum hv_pcichild_state state;
+	struct pci_slot *pci_slot;
 	struct pci_function_description desc;
 	bool reported_missing;
 	struct hv_pcibus_device *hbus;
@@ -1457,6 +1461,34 @@ static void prepopulate_bars(struct hv_pcibus_device *hbus)
 	spin_unlock_irqrestore(&hbus->device_list_lock, flags);
 }
 
+/*
+ * Assign entries in sysfs pci slot directory.
+ *
+ * Note that this function does not need to lock the children list
+ * because it is called from pci_devices_present_work which
+ * is serialized with hv_eject_device_work because they are on the
+ * same ordered workqueue. Therefore hbus->children list will not change
+ * even when pci_create_slot sleeps.
+ */
+static void hv_pci_assign_slots(struct hv_pcibus_device *hbus)
+{
+	struct hv_pci_dev *hpdev;
+	char name[SLOT_NAME_SIZE];
+	int slot_nr;
+
+	list_for_each_entry(hpdev, &hbus->children, list_entry) {
+		if (hpdev->pci_slot)
+			continue;
+
+		slot_nr = PCI_SLOT(wslot_to_devfn(hpdev->desc.win_slot.slot));
+		snprintf(name, SLOT_NAME_SIZE, "%u", hpdev->desc.ser);
+		hpdev->pci_slot = pci_create_slot(hbus->pci_bus, slot_nr,
+					  name, NULL);
+		if (!hpdev->pci_slot)
+			pr_warn("pci_create slot %s failed\n", name);
+	}
+}
+
 /**
  * create_root_hv_pci_bus() - Expose a new root PCI bus
  * @hbus:	Root PCI bus, as understood by this driver
@@ -1480,6 +1512,7 @@ static int create_root_hv_pci_bus(struct hv_pcibus_device *hbus)
 	pci_lock_rescan_remove();
 	pci_scan_child_bus(hbus->pci_bus);
 	pci_bus_assign_resources(hbus->pci_bus);
+	hv_pci_assign_slots(hbus);
 	pci_bus_add_devices(hbus->pci_bus);
 	pci_unlock_rescan_remove();
 	hbus->state = hv_pcibus_installed;
@@ -1742,6 +1775,7 @@ static void pci_devices_present_work(struct work_struct *work)
 		 */
 		pci_lock_rescan_remove();
 		pci_scan_child_bus(hbus->pci_bus);
+		hv_pci_assign_slots(hbus);
 		pci_unlock_rescan_remove();
 		break;
 
@@ -1858,6 +1892,9 @@ static void hv_eject_device_work(struct work_struct *work)
 	list_del(&hpdev->list_entry);
 	spin_unlock_irqrestore(&hpdev->hbus->device_list_lock, flags);
 
+	if (hpdev->pci_slot)
+		pci_destroy_slot(hpdev->pci_slot);
+
 	memset(&ctxt, 0, sizeof(ctxt));
 	ejct_pkt = (struct pci_eject_response *)&ctxt.pkt.message;
 	ejct_pkt->message_type.type = PCI_EJECTION_COMPLETE;