[PATCH 06/22] powerpc/eeh: Function for address mapping

[Gavin Shan]

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

Signed-off-by: Gavin Shan <gwshan at linux.vnet.ibm.com>
---
 arch/powerpc/kernel/eeh_pe.c | 88 ++++++++++++++++++++++++++++++++++++++++++++
 include/linux/kvm_host.h     | 14 +++++++
 2 files changed, 102 insertions(+)

diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c
index 9e73188..200cd5a 100644
--- a/arch/powerpc/kernel/eeh_pe.c
+++ b/arch/powerpc/kernel/eeh_pe.c
@@ -332,6 +332,94 @@ struct eeh_dev *eeh_vfio_dev_get(struct eeh_vfio_pci_addr *addr)
 	return NULL;
 }
 
+/**
+ * kvm_vfio_eeh_dev_map - Build the address mapping for VFIO device
+ *
+ * @kvm: VM descriptor
+ * @domain: host domain of PCI device
+ * @bdn: host bus/device/function number
+ * @buid: BUID of guest PHB
+ * @gbdn: guest bus/device/function number
+ *
+ * Build the address mapping between host and guest deivce. It's called
+ * while passing through PCI device from host to guest.
+ */
+int kvm_vfio_eeh_dev_map(struct kvm *kvm, int domain,
+			 int bdn, unsigned long buid, int gbdn)
+{
+	struct pci_bus *bus, *pe_bus;
+	struct pci_dev *dev;
+	struct eeh_dev *edev;
+	struct eeh_pe *pe;
+	int bus_no, devfn;
+
+	/* 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 passed. We allow dynamic change
+	 * on the address mapping.
+	 */
+	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;
+	}
+
+	/*
+	 * The PE configuration address is exactly PCI config address
+	 * of the PE primary bus. That has format 00BBSS00 defined in
+	 * PAPR.
+	 */
+	pe = edev->pe;
+	if (!eeh_pe_passed(pe)) {
+		pe_bus = eeh_pe_bus_get(pe);
+		BUG_ON(!pe_bus);
+
+		pe->gaddr.kvm		= kvm;
+		pe->gaddr.buid_hi	= BUID_HI(buid);
+		pe->gaddr.buid_lo	= BUID_LO(buid);
+		pe->gaddr.pe_addr	= pe_bus->number << 16;
+		eeh_pe_set_passed(pe, true);
+	} else if (pe->gaddr.kvm != kvm ||
+		   pe->gaddr.buid_hi != BUID_HI(buid) ||
+		   pe->gaddr.buid_lo != BUID_LO(buid)) {
+		pr_warn("%s: Mismatched VM or PHB on passing %s\n",
+			__func__, pci_name(dev));
+		return -EINVAL;
+	}
+
+	edev->gaddr.kvm		= kvm;
+	edev->gaddr.buid_hi	= BUID_HI(buid);
+	edev->gaddr.buid_lo	= BUID_LO(buid);
+	edev->gaddr.bus		= (gbdn >> 8) & 0xff;
+	edev->gaddr.devfn	= gbdn & 0xff;
+	eeh_dev_set_passed(edev, true);
+
+	pr_debug("EEH: Host PCI device %s passed to %lx-%02x:%02x.%01x\n",
+		 pci_name(dev), buid, (gbdn >> 8) & 0xff,
+		 PCI_SLOT(gbdn & 0xff), PCI_FUNC(gbdn & 0xff));
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_vfio_eeh_dev_map);
+
 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 7d21cf9..294ce48 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1102,5 +1102,19 @@ static inline void kvm_vcpu_set_dy_eligible(struct kvm_vcpu *vcpu, bool val)
 {
 }
 #endif /* CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT */
+
+#ifdef CONFIG_KVM_EEH
+typedef int (*kvm_vfio_dev_eeh_map)(struct kvm *kvm, int domain,
+				    int bdn, unsigned long buid, int gbdn);
+extern int kvm_vfio_eeh_dev_map(struct kvm *kvm, int domain,
+				int bdn, unsigned long buid, int gbdn);
+#else
+static inline int kvm_vfio_eeh_dev_map(struct kvm *kvm, int domain,
+				       int bdn, unsigned long buid, int gbdn)
+{
+	return 0;
+}
+#endif /* CONFIG_KVM_EEH */
+
 #endif
 
-- 
1.8.3.2