1 files changed, 141 insertions, 132 deletions

diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index 91220cc25854..b94f727251b6 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -23,9 +23,11 @@
 
 #include <xen/features.h>
 #include <xen/events.h>
+#include <xen/pci.h>
 #include <asm/xen/pci.h>
 #include <asm/xen/cpuid.h>
 #include <asm/apic.h>
+#include <asm/acpi.h>
 #include <asm/i8259.h>
 
 static int xen_pcifront_enable_irq(struct pci_dev *dev)
@@ -60,10 +62,9 @@ static int xen_pcifront_enable_irq(struct pci_dev *dev)
 }
 
 #ifdef CONFIG_ACPI
-static int xen_register_pirq(u32 gsi, int gsi_override, int triggering,
-			     bool set_pirq)
+static int xen_register_pirq(u32 gsi, int triggering, bool set_pirq)
 {
-	int rc, pirq = -1, irq = -1;
+	int rc, pirq = -1, irq;
 	struct physdev_map_pirq map_irq;
 	int shareable = 0;
 	char *name;
@@ -94,9 +95,6 @@ static int xen_register_pirq(u32 gsi, int gsi_override, int triggering,
 		name = "ioapic-level";
 	}
 
-	if (gsi_override >= 0)
-		gsi = gsi_override;
-
 	irq = xen_bind_pirq_gsi_to_irq(gsi, map_irq.pirq, shareable, name);
 	if (irq < 0)
 		goto out;
@@ -112,12 +110,12 @@ static int acpi_register_gsi_xen_hvm(struct device *dev, u32 gsi,
 	if (!xen_hvm_domain())
 		return -1;
 
-	return xen_register_pirq(gsi, -1 /* no GSI override */, trigger,
+	return xen_register_pirq(gsi, trigger,
 				 false /* no mapping of GSI to PIRQ */);
 }
 
-#ifdef CONFIG_XEN_DOM0
-static int xen_register_gsi(u32 gsi, int gsi_override, int triggering, int polarity)
+#ifdef CONFIG_XEN_PV_DOM0
+static int xen_register_gsi(u32 gsi, int triggering, int polarity)
 {
 	int rc, irq;
 	struct physdev_setup_gsi setup_gsi;
@@ -128,7 +126,7 @@ static int xen_register_gsi(u32 gsi, int gsi_override, int triggering, int polar
 	printk(KERN_DEBUG "xen: registering gsi %u triggering %d polarity %d\n",
 			gsi, triggering, polarity);
 
-	irq = xen_register_pirq(gsi, gsi_override, triggering, true);
+	irq = xen_register_pirq(gsi, triggering, true);
 
 	setup_gsi.gsi = gsi;
 	setup_gsi.triggering = (triggering == ACPI_EDGE_SENSITIVE ? 0 : 1);
@@ -148,18 +146,24 @@ static int xen_register_gsi(u32 gsi, int gsi_override, int triggering, int polar
 static int acpi_register_gsi_xen(struct device *dev, u32 gsi,
 				 int trigger, int polarity)
 {
-	return xen_register_gsi(gsi, -1 /* no GSI override */, trigger, polarity);
+	return xen_register_gsi(gsi, trigger, polarity);
 }
 #endif
 #endif
 
 #if defined(CONFIG_PCI_MSI)
 #include <linux/msi.h>
-#include <asm/msidef.h>
 
 struct xen_pci_frontend_ops *xen_pci_frontend;
 EXPORT_SYMBOL_GPL(xen_pci_frontend);
 
+struct xen_msi_ops {
+	int (*setup_msi_irqs)(struct pci_dev *dev, int nvec, int type);
+	void (*teardown_msi_irqs)(struct pci_dev *dev);
+};
+
+static struct xen_msi_ops xen_msi_ops __ro_after_init;
+
 static int xen_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 {
 	int irq, ret, i;
@@ -180,7 +184,7 @@ static int xen_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 	if (ret)
 		goto error;
 	i = 0;
-	for_each_pci_msi_entry(msidesc, dev) {
+	msi_for_each_desc(msidesc, &dev->dev, MSI_DESC_NOTASSOCIATED) {
 		irq = xen_bind_pirq_msi_to_irq(dev, msidesc, v[i],
 					       (type == PCI_CAP_ID_MSI) ? nvec : 1,
 					       (type == PCI_CAP_ID_MSIX) ?
@@ -206,23 +210,20 @@ free:
 	return ret;
 }
 
-#define XEN_PIRQ_MSI_DATA  (MSI_DATA_TRIGGER_EDGE | \
-		MSI_DATA_LEVEL_ASSERT | (3 << 8) | MSI_DATA_VECTOR(0))
-
 static void xen_msi_compose_msg(struct pci_dev *pdev, unsigned int pirq,
 		struct msi_msg *msg)
 {
-	/* We set vector == 0 to tell the hypervisor we don't care about it,
-	 * but we want a pirq setup instead.
-	 * We use the dest_id field to pass the pirq that we want. */
-	msg->address_hi = MSI_ADDR_BASE_HI | MSI_ADDR_EXT_DEST_ID(pirq);
-	msg->address_lo =
-		MSI_ADDR_BASE_LO |
-		MSI_ADDR_DEST_MODE_PHYSICAL |
-		MSI_ADDR_REDIRECTION_CPU |
-		MSI_ADDR_DEST_ID(pirq);
-
-	msg->data = XEN_PIRQ_MSI_DATA;
+	/*
+	 * We set vector == 0 to tell the hypervisor we don't care about
+	 * it, but we want a pirq setup instead.  We use the dest_id fields
+	 * to pass the pirq that we want.
+	 */
+	memset(msg, 0, sizeof(*msg));
+	msg->address_hi = X86_MSI_BASE_ADDRESS_HIGH;
+	msg->arch_addr_hi.destid_8_31 = pirq >> 8;
+	msg->arch_addr_lo.destid_0_7 = pirq & 0xFF;
+	msg->arch_addr_lo.base_address = X86_MSI_BASE_ADDRESS_LOW;
+	msg->arch_data.delivery_mode = APIC_DELIVERY_MODE_EXTINT;
 }
 
 static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
@@ -234,7 +235,7 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 	if (type == PCI_CAP_ID_MSI && nvec > 1)
 		return 1;
 
-	for_each_pci_msi_entry(msidesc, dev) {
+	msi_for_each_desc(msidesc, &dev->dev, MSI_DESC_NOTASSOCIATED) {
 		pirq = xen_allocate_pirq_msi(dev, msidesc);
 		if (pirq < 0) {
 			irq = -ENODEV;
@@ -261,7 +262,7 @@ error:
 	return irq;
 }
 
-#ifdef CONFIG_XEN_DOM0
+#ifdef CONFIG_XEN_PV_DOM0
 static bool __read_mostly pci_seg_supported = true;
 
 static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
@@ -269,7 +270,7 @@ static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 	int ret = 0;
 	struct msi_desc *msidesc;
 
-	for_each_pci_msi_entry(msidesc, dev) {
+	msi_for_each_desc(msidesc, &dev->dev, MSI_DESC_NOTASSOCIATED) {
 		struct physdev_map_pirq map_irq;
 		domid_t domid;
 
@@ -305,7 +306,7 @@ static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 				return -EINVAL;
 
 			map_irq.table_base = pci_resource_start(dev, bir);
-			map_irq.entry_nr = msidesc->msi_attrib.entry_nr;
+			map_irq.entry_nr = msidesc->msi_index;
 		}
 
 		ret = -EINVAL;
@@ -350,10 +351,13 @@ out:
 	return ret;
 }
 
-static void xen_initdom_restore_msi_irqs(struct pci_dev *dev)
+bool xen_initdom_restore_msi(struct pci_dev *dev)
 {
 	int ret = 0;
 
+	if (!xen_initial_domain())
+		return true;
+
 	if (pci_seg_supported) {
 		struct physdev_pci_device restore_ext;
 
@@ -374,29 +378,118 @@ static void xen_initdom_restore_msi_irqs(struct pci_dev *dev)
 		ret = HYPERVISOR_physdev_op(PHYSDEVOP_restore_msi, &restore);
 		WARN(ret && ret != -ENOSYS, "restore_msi -> %d\n", ret);
 	}
+	return false;
 }
-#endif
+#else /* CONFIG_XEN_PV_DOM0 */
+#define xen_initdom_setup_msi_irqs	NULL
+#endif /* !CONFIG_XEN_PV_DOM0 */
 
 static void xen_teardown_msi_irqs(struct pci_dev *dev)
 {
 	struct msi_desc *msidesc;
+	int i;
+
+	msi_for_each_desc(msidesc, &dev->dev, MSI_DESC_ASSOCIATED) {
+		for (i = 0; i < msidesc->nvec_used; i++)
+			xen_destroy_irq(msidesc->irq + i);
+	}
+}
 
-	msidesc = first_pci_msi_entry(dev);
-	if (msidesc->msi_attrib.is_msix)
+static void xen_pv_teardown_msi_irqs(struct pci_dev *dev)
+{
+	if (dev->msix_enabled)
 		xen_pci_frontend_disable_msix(dev);
 	else
 		xen_pci_frontend_disable_msi(dev);
 
-	/* Free the IRQ's and the msidesc using the generic code. */
-	default_teardown_msi_irqs(dev);
+	xen_teardown_msi_irqs(dev);
 }
 
-static void xen_teardown_msi_irq(unsigned int irq)
+static int xen_msi_domain_alloc_irqs(struct irq_domain *domain,
+				     struct device *dev,  int nvec)
 {
-	xen_destroy_irq(irq);
+	int type;
+
+	if (WARN_ON_ONCE(!dev_is_pci(dev)))
+		return -EINVAL;
+
+	type = to_pci_dev(dev)->msix_enabled ? PCI_CAP_ID_MSIX : PCI_CAP_ID_MSI;
+
+	return xen_msi_ops.setup_msi_irqs(to_pci_dev(dev), nvec, type);
 }
 
-#endif
+static void xen_msi_domain_free_irqs(struct irq_domain *domain,
+				     struct device *dev)
+{
+	if (WARN_ON_ONCE(!dev_is_pci(dev)))
+		return;
+
+	xen_msi_ops.teardown_msi_irqs(to_pci_dev(dev));
+}
+
+static struct msi_domain_ops xen_pci_msi_domain_ops = {
+	.domain_alloc_irqs	= xen_msi_domain_alloc_irqs,
+	.domain_free_irqs	= xen_msi_domain_free_irqs,
+};
+
+static struct msi_domain_info xen_pci_msi_domain_info = {
+	.ops			= &xen_pci_msi_domain_ops,
+};
+
+/*
+ * This irq domain is a blatant violation of the irq domain design, but
+ * distangling XEN into real irq domains is not a job for mere mortals with
+ * limited XENology. But it's the least dangerous way for a mere mortal to
+ * get rid of the arch_*_msi_irqs() hackery in order to store the irq
+ * domain pointer in struct device. This irq domain wrappery allows to do
+ * that without breaking XEN terminally.
+ */
+static __init struct irq_domain *xen_create_pci_msi_domain(void)
+{
+	struct irq_domain *d = NULL;
+	struct fwnode_handle *fn;
+
+	fn = irq_domain_alloc_named_fwnode("XEN-MSI");
+	if (fn)
+		d = msi_create_irq_domain(fn, &xen_pci_msi_domain_info, NULL);
+
+	/* FIXME: No idea how to survive if this fails */
+	BUG_ON(!d);
+
+	return d;
+}
+
+static __init void xen_setup_pci_msi(void)
+{
+	if (xen_pv_domain()) {
+		if (xen_initial_domain())
+			xen_msi_ops.setup_msi_irqs = xen_initdom_setup_msi_irqs;
+		else
+			xen_msi_ops.setup_msi_irqs = xen_setup_msi_irqs;
+		xen_msi_ops.teardown_msi_irqs = xen_pv_teardown_msi_irqs;
+	} else if (xen_hvm_domain()) {
+		xen_msi_ops.setup_msi_irqs = xen_hvm_setup_msi_irqs;
+		xen_msi_ops.teardown_msi_irqs = xen_teardown_msi_irqs;
+	} else {
+		WARN_ON_ONCE(1);
+		return;
+	}
+
+	/*
+	 * Override the PCI/MSI irq domain init function. No point
+	 * in allocating the native domain and never use it.
+	 */
+	x86_init.irqs.create_pci_msi_domain = xen_create_pci_msi_domain;
+	/*
+	 * With XEN PIRQ/Eventchannels in use PCI/MSI[-X] masking is solely
+	 * controlled by the hypervisor.
+	 */
+	pci_msi_ignore_mask = 1;
+}
+
+#else /* CONFIG_PCI_MSI */
+static inline void xen_setup_pci_msi(void) { }
+#endif /* CONFIG_PCI_MSI */
 
 int __init pci_xen_init(void)
 {
@@ -413,17 +506,12 @@ int __init pci_xen_init(void)
 	/* Keep ACPI out of the picture */
 	acpi_noirq_set();
 
-#ifdef CONFIG_PCI_MSI
-	x86_msi.setup_msi_irqs = xen_setup_msi_irqs;
-	x86_msi.teardown_msi_irq = xen_teardown_msi_irq;
-	x86_msi.teardown_msi_irqs = xen_teardown_msi_irqs;
-	pci_msi_ignore_mask = 1;
-#endif
+	xen_setup_pci_msi();
 	return 0;
 }
 
 #ifdef CONFIG_PCI_MSI
-void __init xen_msi_init(void)
+static void __init xen_hvm_msi_init(void)
 {
 	if (!disable_apic) {
 		/*
@@ -438,9 +526,7 @@ void __init xen_msi_init(void)
 		    ((eax & XEN_HVM_CPUID_APIC_ACCESS_VIRT) && boot_cpu_has(X86_FEATURE_APIC)))
 			return;
 	}
-
-	x86_msi.setup_msi_irqs = xen_hvm_setup_msi_irqs;
-	x86_msi.teardown_msi_irq = xen_teardown_msi_irq;
+	xen_setup_pci_msi();
 }
 #endif
 
@@ -463,22 +549,17 @@ int __init pci_xen_hvm_init(void)
 	 * We need to wait until after x2apic is initialized
 	 * before we can set MSI IRQ ops.
 	 */
-	x86_platform.apic_post_init = xen_msi_init;
+	x86_platform.apic_post_init = xen_hvm_msi_init;
 #endif
 	return 0;
 }
 
-#ifdef CONFIG_XEN_DOM0
+#ifdef CONFIG_XEN_PV_DOM0
 int __init pci_xen_initial_domain(void)
 {
 	int irq;
 
-#ifdef CONFIG_PCI_MSI
-	x86_msi.setup_msi_irqs = xen_initdom_setup_msi_irqs;
-	x86_msi.teardown_msi_irq = xen_teardown_msi_irq;
-	x86_msi.restore_msi_irqs = xen_initdom_restore_msi_irqs;
-	pci_msi_ignore_mask = 1;
-#endif
+	xen_setup_pci_msi();
 	__acpi_register_gsi = acpi_register_gsi_xen;
 	__acpi_unregister_gsi = NULL;
 	/*
@@ -491,7 +572,7 @@ int __init pci_xen_initial_domain(void)
 		if (acpi_get_override_irq(irq, &trigger, &polarity) == -1)
 			continue;
 
-		xen_register_pirq(irq, -1 /* no GSI override */,
+		xen_register_pirq(irq,
 			trigger ? ACPI_LEVEL_SENSITIVE : ACPI_EDGE_SENSITIVE,
 			true /* Map GSI to PIRQ */);
 	}
@@ -501,77 +582,5 @@ int __init pci_xen_initial_domain(void)
 	}
 	return 0;
 }
-
-struct xen_device_domain_owner {
-	domid_t domain;
-	struct pci_dev *dev;
-	struct list_head list;
-};
-
-static DEFINE_SPINLOCK(dev_domain_list_spinlock);
-static struct list_head dev_domain_list = LIST_HEAD_INIT(dev_domain_list);
-
-static struct xen_device_domain_owner *find_device(struct pci_dev *dev)
-{
-	struct xen_device_domain_owner *owner;
-
-	list_for_each_entry(owner, &dev_domain_list, list) {
-		if (owner->dev == dev)
-			return owner;
-	}
-	return NULL;
-}
-
-int xen_find_device_domain_owner(struct pci_dev *dev)
-{
-	struct xen_device_domain_owner *owner;
-	int domain = -ENODEV;
-
-	spin_lock(&dev_domain_list_spinlock);
-	owner = find_device(dev);
-	if (owner)
-		domain = owner->domain;
-	spin_unlock(&dev_domain_list_spinlock);
-	return domain;
-}
-EXPORT_SYMBOL_GPL(xen_find_device_domain_owner);
-
-int xen_register_device_domain_owner(struct pci_dev *dev, uint16_t domain)
-{
-	struct xen_device_domain_owner *owner;
-
-	owner = kzalloc(sizeof(struct xen_device_domain_owner), GFP_KERNEL);
-	if (!owner)
-		return -ENODEV;
-
-	spin_lock(&dev_domain_list_spinlock);
-	if (find_device(dev)) {
-		spin_unlock(&dev_domain_list_spinlock);
-		kfree(owner);
-		return -EEXIST;
-	}
-	owner->domain = domain;
-	owner->dev = dev;
-	list_add_tail(&owner->list, &dev_domain_list);
-	spin_unlock(&dev_domain_list_spinlock);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(xen_register_device_domain_owner);
-
-int xen_unregister_device_domain_owner(struct pci_dev *dev)
-{
-	struct xen_device_domain_owner *owner;
-
-	spin_lock(&dev_domain_list_spinlock);
-	owner = find_device(dev);
-	if (!owner) {
-		spin_unlock(&dev_domain_list_spinlock);
-		return -ENODEV;
-	}
-	list_del(&owner->list);
-	spin_unlock(&dev_domain_list_spinlock);
-	kfree(owner);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(xen_unregister_device_domain_owner);
 #endif
+