[PATCH 07/22] powerpc/eeh: Function to tear down address mapping

[Gavin Shan]

The patch introduces function kvm_vfio_eeh_dev_unmap(), which is
expected to be called on IOCTL command issued to the VM device, in
order to tear down the address mapping for VFIO PCI device.

Signed-off-by: Gavin Shan <gwshan at linux.vnet.ibm.com>
---
 arch/powerpc/kernel/eeh_pe.c | 82 ++++++++++++++++++++++++++++++++++++++++++++
 include/linux/kvm_host.h     |  7 ++++
 2 files changed, 89 insertions(+)

diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c
index 200cd5a..8398efc 100644
--- a/arch/powerpc/kernel/eeh_pe.c
+++ b/arch/powerpc/kernel/eeh_pe.c
@@ -420,6 +420,88 @@ int kvm_vfio_eeh_dev_map(struct kvm *kvm, int domain,
 }
 EXPORT_SYMBOL_GPL(kvm_vfio_eeh_dev_map);
 
+ /**
+  * kvm_vfio_eeh_dev_unmap - Tear down address mapping for VFIO PCI device
+  *
+  * @kvm: VM descriptor
+  * @domain: host domain
+  * @bdn: host bus/device/function number
+  *
+  * Tear down address mapping for VFIO PCI device.
+  */
+int kvm_vfio_eeh_dev_unmap(struct kvm *kvm, int domain, int bdn)
+{
+	struct pci_bus *bus;
+	struct pci_dev *dev;
+	struct eeh_pe *pe;
+	struct eeh_dev *edev, *tmp;
+	int bus_no, devfn;
+	bool passed;
+
+	/* Find the PCI device in host side */
+	bus_no = (bdn >> 8) & 0xff;
+	devfn = bdn & 0xff;
+	bus = pci_find_bus(domain, bus_no);
+	if (!bus) {
+		pr_warn("%s: PCI bus %04x:%02x not found\n",
+			__func__, domain, bus_no);
+		return -ENODEV;
+	}
+
+	dev = pci_get_slot(bus, devfn);
+	if (!dev) {
+		pr_warn("%s: PCI device %04x:%02x:%02x.%01x not found\n",
+			__func__, domain, bus_no,
+			PCI_SLOT(devfn), PCI_FUNC(devfn));
+		return -ENODEV;
+	}
+
+	/* Mark the EEH device as non-passed */
+	edev = pci_dev_to_eeh_dev(dev);
+	if (!edev) {
+		pr_warn("%s: No EEH dev for PCI device %s\n",
+			__func__, pci_name(dev));
+		return -ENODEV;
+	} else if (!eeh_dev_passed(edev)    ||
+		   !eeh_pe_passed(edev->pe) ||
+		   edev->gaddr.kvm != kvm   ||
+		   edev->pe->gaddr.kvm != kvm) {
+		pr_warn("%s: Non-passsed PCI dev %s or PE\n",
+			__func__, pci_name(dev));
+		return 0;
+	}
+	memset(&edev->gaddr, 0, sizeof(edev->gaddr));
+	eeh_dev_set_passed(edev, false);
+	pr_debug("EEH: Host PCI device %s returned\n",
+		pci_name(dev));
+
+	/*
+	 * Mark the PE as non-passed if all PCI devices
+	 * except P2P bridges are non-passed.
+	 */
+	pe = edev->pe;
+	passed = false;
+	eeh_pe_for_each_dev(pe, edev, tmp) {
+		dev = eeh_dev_to_pci_dev(edev);
+		if (dev && dev->subordinate)
+			continue;
+		if (eeh_dev_passed(edev)) {
+			passed = true;
+			break;
+		}
+	}
+
+	if (!passed) {
+		memset(&pe->gaddr, 0, sizeof(pe->gaddr));
+		eeh_pe_set_passed(pe, false);
+		pr_debug("EEH: PHB#%x-PE#%x returned to host\n",
+			pe->phb->global_number, pe->addr);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_vfio_eeh_dev_unmap);
+
 static void *__kvmppc_eeh_vfio_release(void *data, void *flag)
 {
 	struct eeh_pe *pe = (struct eeh_pe *)data;
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 294ce48..520b3d0 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1106,14 +1106,21 @@ static inline void kvm_vcpu_set_dy_eligible(struct kvm_vcpu *vcpu, bool val)
 #ifdef CONFIG_KVM_EEH
 typedef int (*kvm_vfio_dev_eeh_map)(struct kvm *kvm, int domain,
 				    int bdn, unsigned long buid, int gbdn);
+typedef int (*kvm_vfio_dev_eeh_unmap)(struct kvm *kvm, int domain, int bdn);
 extern int kvm_vfio_eeh_dev_map(struct kvm *kvm, int domain,
 				int bdn, unsigned long buid, int gbdn);
+extern int kvm_vfio_eeh_dev_unmap(struct kvm *kvm, int domain, int bdn);
 #else
 static inline int kvm_vfio_eeh_dev_map(struct kvm *kvm, int domain,
 				       int bdn, unsigned long buid, int gbdn)
 {
 	return 0;
 }
+
+static inline int kvm_vfio_eeh_dev_unmap(struct kvm *kvm, int domain, int bdn)
+{
+	return 0;
+}
 #endif /* CONFIG_KVM_EEH */
 
 #endif
-- 
1.8.3.2