Merge tag 'irq-msi-2022-01-13' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull MSI irq updates from Thomas Gleixner:
 "Rework of the MSI interrupt infrastructure.

  This is a treewide cleanup and consolidation of MSI interrupt handling
  in preparation for further changes in this area which are necessary
  to:

   - address existing shortcomings in the VFIO area

   - support the upcoming Interrupt Message Store functionality which
     decouples the message store from the PCI config/MMIO space"

* tag 'irq-msi-2022-01-13' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (94 commits)
  genirq/msi: Populate sysfs entry only once
  PCI/MSI: Unbreak pci_irq_get_affinity()
  genirq/msi: Convert storage to xarray
  genirq/msi: Simplify sysfs handling
  genirq/msi: Add abuse prevention comment to msi header
  genirq/msi: Mop up old interfaces
  genirq/msi: Convert to new functions
  genirq/msi: Make interrupt allocation less convoluted
  platform-msi: Simplify platform device MSI code
  platform-msi: Let core code handle MSI descriptors
  bus: fsl-mc-msi: Simplify MSI descriptor handling
  soc: ti: ti_sci_inta_msi: Remove ti_sci_inta_msi_domain_free_irqs()
  soc: ti: ti_sci_inta_msi: Rework MSI descriptor allocation
  NTB/msi: Convert to msi_on_each_desc()
  PCI: hv: Rework MSI handling
  powerpc/mpic_u3msi: Use msi_for_each-desc()
  powerpc/fsl_msi: Use msi_for_each_desc()
  powerpc/pasemi/msi: Convert to msi_on_each_dec()
  powerpc/cell/axon_msi: Convert to msi_on_each_desc()
  powerpc/4xx/hsta: Rework MSI handling
  ...

6 files changed, 48 insertions, 82 deletions

diff --git a/arch/x86/hyperv/irqdomain.c b/arch/x86/hyperv/irqdomain.c
index 514fc64e23d5..7e0f6bedc248 100644
--- a/arch/x86/hyperv/irqdomain.c
+++ b/arch/x86/hyperv/irqdomain.c
@@ -253,64 +253,43 @@ static int hv_unmap_msi_interrupt(struct pci_dev *dev, struct hv_interrupt_entry
 	return hv_unmap_interrupt(hv_build_pci_dev_id(dev).as_uint64, old_entry);
 }
 
-static void hv_teardown_msi_irq_common(struct pci_dev *dev, struct msi_desc *msidesc, int irq)
+static void hv_teardown_msi_irq(struct pci_dev *dev, struct irq_data *irqd)
 {
-	u64 status;
 	struct hv_interrupt_entry old_entry;
-	struct irq_desc *desc;
-	struct irq_data *data;
 	struct msi_msg msg;
+	u64 status;
 
-	desc = irq_to_desc(irq);
-	if (!desc) {
-		pr_debug("%s: no irq desc\n", __func__);
-		return;
-	}
-
-	data = &desc->irq_data;
-	if (!data) {
-		pr_debug("%s: no irq data\n", __func__);
-		return;
-	}
-
-	if (!data->chip_data) {
+	if (!irqd->chip_data) {
 		pr_debug("%s: no chip data\n!", __func__);
 		return;
 	}
 
-	old_entry = *(struct hv_interrupt_entry *)data->chip_data;
+	old_entry = *(struct hv_interrupt_entry *)irqd->chip_data;
 	entry_to_msi_msg(&old_entry, &msg);
 
-	kfree(data->chip_data);
-	data->chip_data = NULL;
+	kfree(irqd->chip_data);
+	irqd->chip_data = NULL;
 
 	status = hv_unmap_msi_interrupt(dev, &old_entry);
 
-	if (status != HV_STATUS_SUCCESS) {
+	if (status != HV_STATUS_SUCCESS)
 		pr_err("%s: hypercall failed, status %lld\n", __func__, status);
-		return;
-	}
 }
 
-static void hv_msi_domain_free_irqs(struct irq_domain *domain, struct device *dev)
+static void hv_msi_free_irq(struct irq_domain *domain,
+			    struct msi_domain_info *info, unsigned int virq)
 {
-	int i;
-	struct msi_desc *entry;
-	struct pci_dev *pdev;
+	struct irq_data *irqd = irq_get_irq_data(virq);
+	struct msi_desc *desc;
 
-	if (WARN_ON_ONCE(!dev_is_pci(dev)))
+	if (!irqd)
 		return;
 
-	pdev = to_pci_dev(dev);
+	desc = irq_data_get_msi_desc(irqd);
+	if (!desc || !desc->irq || WARN_ON_ONCE(!dev_is_pci(desc->dev)))
+		return;
 
-	for_each_pci_msi_entry(entry, pdev) {
-		if (entry->irq) {
-			for (i = 0; i < entry->nvec_used; i++) {
-				hv_teardown_msi_irq_common(pdev, entry, entry->irq + i);
-				irq_domain_free_irqs(entry->irq + i, 1);
-			}
-		}
-	}
+	hv_teardown_msi_irq(to_pci_dev(desc->dev), irqd);
 }
 
 /*
@@ -329,7 +308,7 @@ static struct irq_chip hv_pci_msi_controller = {
 };
 
 static struct msi_domain_ops pci_msi_domain_ops = {
-	.domain_free_irqs	= hv_msi_domain_free_irqs,
+	.msi_free		= hv_msi_free_irq,
 	.msi_prepare		= pci_msi_prepare,
 };
 
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index 5c69f7eb5d47..22b7412c08f6 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -289,12 +289,6 @@ struct x86_platform_ops {
 	struct x86_hyper_runtime hyper;
 };
 
-struct pci_dev;
-
-struct x86_msi_ops {
-	void (*restore_msi_irqs)(struct pci_dev *dev);
-};
-
 struct x86_apic_ops {
 	unsigned int	(*io_apic_read)   (unsigned int apic, unsigned int reg);
 	void		(*restore)(void);
diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h
index 5adab895127e..1bf2ad34188a 100644
--- a/arch/x86/include/asm/xen/hypervisor.h
+++ b/arch/x86/include/asm/xen/hypervisor.h
@@ -57,6 +57,14 @@ static inline bool __init xen_x2apic_para_available(void)
 }
 #endif
 
+struct pci_dev;
+
+#ifdef CONFIG_XEN_PV_DOM0
+bool xen_initdom_restore_msi(struct pci_dev *dev);
+#else
+static inline bool xen_initdom_restore_msi(struct pci_dev *dev) { return true; }
+#endif
+
 #ifdef CONFIG_HOTPLUG_CPU
 void xen_arch_register_cpu(int num);
 void xen_arch_unregister_cpu(int num);
diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c
index dbacb9ec8843..7517eb05bdc1 100644
--- a/arch/x86/kernel/apic/msi.c
+++ b/arch/x86/kernel/apic/msi.c
@@ -19,6 +19,7 @@
 #include <asm/hw_irq.h>
 #include <asm/apic.h>
 #include <asm/irq_remapping.h>
+#include <asm/xen/hypervisor.h>
 
 struct irq_domain *x86_pci_msi_default_domain __ro_after_init;
 
@@ -159,11 +160,8 @@ static struct irq_chip pci_msi_controller = {
 int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec,
 		    msi_alloc_info_t *arg)
 {
-	struct pci_dev *pdev = to_pci_dev(dev);
-	struct msi_desc *desc = first_pci_msi_entry(pdev);
-
 	init_irq_alloc_info(arg, NULL);
-	if (desc->msi_attrib.is_msix) {
+	if (to_pci_dev(dev)->msix_enabled) {
 		arg->type = X86_IRQ_ALLOC_TYPE_PCI_MSIX;
 	} else {
 		arg->type = X86_IRQ_ALLOC_TYPE_PCI_MSI;
@@ -345,3 +343,8 @@ void dmar_free_hwirq(int irq)
 	irq_domain_free_irqs(irq, 1);
 }
 #endif
+
+bool arch_restore_msi_irqs(struct pci_dev *dev)
+{
+	return xen_initdom_restore_msi(dev);
+}
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index 8b395821cb8d..7d20c1d34a3c 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -145,18 +145,6 @@ struct x86_platform_ops x86_platform __ro_after_init = {
 
 EXPORT_SYMBOL_GPL(x86_platform);
 
-#if defined(CONFIG_PCI_MSI)
-struct x86_msi_ops x86_msi __ro_after_init = {
-	.restore_msi_irqs	= default_restore_msi_irqs,
-};
-
-/* MSI arch specific hooks */
-void arch_restore_msi_irqs(struct pci_dev *dev)
-{
-	x86_msi.restore_msi_irqs(dev);
-}
-#endif
-
 struct x86_apic_ops x86_apic_ops __ro_after_init = {
 	.io_apic_read	= native_io_apic_read,
 	.restore	= native_restore_boot_irq_mode,
diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index 12da00558631..9bb1e2941179 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -184,7 +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) ?
@@ -235,7 +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;
@@ -270,7 +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;
 
@@ -306,7 +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;
@@ -351,10 +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;
 
@@ -375,10 +378,10 @@ 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;
 }
 #else /* CONFIG_XEN_PV_DOM0 */
 #define xen_initdom_setup_msi_irqs	NULL
-#define xen_initdom_restore_msi_irqs	NULL
 #endif /* !CONFIG_XEN_PV_DOM0 */
 
 static void xen_teardown_msi_irqs(struct pci_dev *dev)
@@ -386,19 +389,15 @@ static void xen_teardown_msi_irqs(struct pci_dev *dev)
 	struct msi_desc *msidesc;
 	int i;
 
-	for_each_pci_msi_entry(msidesc, dev) {
-		if (msidesc->irq) {
-			for (i = 0; i < msidesc->nvec_used; i++)
-				xen_destroy_irq(msidesc->irq + 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);
 	}
 }
 
 static void xen_pv_teardown_msi_irqs(struct pci_dev *dev)
 {
-	struct msi_desc *msidesc = first_pci_msi_entry(dev);
-
-	if (msidesc->msi_attrib.is_msix)
+	if (dev->msix_enabled)
 		xen_pci_frontend_disable_msix(dev);
 	else
 		xen_pci_frontend_disable_msi(dev);
@@ -414,10 +413,7 @@ static int xen_msi_domain_alloc_irqs(struct irq_domain *domain,
 	if (WARN_ON_ONCE(!dev_is_pci(dev)))
 		return -EINVAL;
 
-	if (first_msi_entry(dev)->msi_attrib.is_msix)
-		type = PCI_CAP_ID_MSIX;
-	else
-		type = PCI_CAP_ID_MSI;
+	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);
 }
@@ -466,12 +462,10 @@ static __init struct irq_domain *xen_create_pci_msi_domain(void)
 static __init void xen_setup_pci_msi(void)
 {
 	if (xen_pv_domain()) {
-		if (xen_initial_domain()) {
+		if (xen_initial_domain())
 			xen_msi_ops.setup_msi_irqs = xen_initdom_setup_msi_irqs;
-			x86_msi.restore_msi_irqs = xen_initdom_restore_msi_irqs;
-		} else {
+		else
 			xen_msi_ops.setup_msi_irqs = xen_setup_msi_irqs;
-		}
 		xen_msi_ops.teardown_msi_irqs = xen_pv_teardown_msi_irqs;
 		pci_msi_ignore_mask = 1;
 	} else if (xen_hvm_domain()) {