1 files changed, 287 insertions, 82 deletions

diff --git a/drivers/pci/msi/irqdomain.c b/drivers/pci/msi/irqdomain.c
index e9cf318e6670..e33bcc872699 100644
--- a/drivers/pci/msi/irqdomain.c
+++ b/drivers/pci/msi/irqdomain.c
@@ -14,7 +14,7 @@ int pci_msi_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 
 	domain = dev_get_msi_domain(&dev->dev);
 	if (domain && irq_domain_is_hierarchy(domain))
-		return msi_domain_alloc_irqs_descs_locked(domain, &dev->dev, nvec);
+		return msi_domain_alloc_irqs_all_locked(&dev->dev, MSI_DEFAULT_DOMAIN, nvec);
 
 	return pci_msi_legacy_setup_msi_irqs(dev, nvec, type);
 }
@@ -24,11 +24,12 @@ void pci_msi_teardown_msi_irqs(struct pci_dev *dev)
 	struct irq_domain *domain;
 
 	domain = dev_get_msi_domain(&dev->dev);
-	if (domain && irq_domain_is_hierarchy(domain))
-		msi_domain_free_irqs_descs_locked(domain, &dev->dev);
-	else
+	if (domain && irq_domain_is_hierarchy(domain)) {
+		msi_domain_free_irqs_all_locked(&dev->dev, MSI_DEFAULT_DOMAIN);
+	} else {
 		pci_msi_legacy_teardown_msi_irqs(dev);
-	msi_free_msi_descs(&dev->dev);
+		msi_free_msi_descs(&dev->dev);
+	}
 }
 
 /**
@@ -63,51 +64,6 @@ static irq_hw_number_t pci_msi_domain_calc_hwirq(struct msi_desc *desc)
 		(pci_domain_nr(dev->bus) & 0xFFFFFFFF) << 27;
 }
 
-static inline bool pci_msi_desc_is_multi_msi(struct msi_desc *desc)
-{
-	return !desc->pci.msi_attrib.is_msix && desc->nvec_used > 1;
-}
-
-/**
- * pci_msi_domain_check_cap - Verify that @domain supports the capabilities
- *			      for @dev
- * @domain:	The interrupt domain to check
- * @info:	The domain info for verification
- * @dev:	The device to check
- *
- * Returns:
- *  0 if the functionality is supported
- *  1 if Multi MSI is requested, but the domain does not support it
- *  -ENOTSUPP otherwise
- */
-static int pci_msi_domain_check_cap(struct irq_domain *domain,
-				    struct msi_domain_info *info,
-				    struct device *dev)
-{
-	struct msi_desc *desc = msi_first_desc(dev, MSI_DESC_ALL);
-
-	/* Special handling to support __pci_enable_msi_range() */
-	if (pci_msi_desc_is_multi_msi(desc) &&
-	    !(info->flags & MSI_FLAG_MULTI_PCI_MSI))
-		return 1;
-
-	if (desc->pci.msi_attrib.is_msix) {
-		if (!(info->flags & MSI_FLAG_PCI_MSIX))
-			return -ENOTSUPP;
-
-		if (info->flags & MSI_FLAG_MSIX_CONTIGUOUS) {
-			unsigned int idx = 0;
-
-			/* Check for gaps in the entry indices */
-			msi_for_each_desc(desc, dev, MSI_DESC_ALL) {
-				if (desc->msi_index != idx++)
-					return -ENOTSUPP;
-			}
-		}
-	}
-	return 0;
-}
-
 static void pci_msi_domain_set_desc(msi_alloc_info_t *arg,
 				    struct msi_desc *desc)
 {
@@ -117,7 +73,6 @@ static void pci_msi_domain_set_desc(msi_alloc_info_t *arg,
 
 static struct msi_domain_ops pci_msi_domain_ops_default = {
 	.set_desc	= pci_msi_domain_set_desc,
-	.msi_check	= pci_msi_domain_check_cap,
 };
 
 static void pci_msi_domain_update_dom_ops(struct msi_domain_info *info)
@@ -129,8 +84,6 @@ static void pci_msi_domain_update_dom_ops(struct msi_domain_info *info)
 	} else {
 		if (ops->set_desc == NULL)
 			ops->set_desc = pci_msi_domain_set_desc;
-		if (ops->msi_check == NULL)
-			ops->msi_check = pci_msi_domain_check_cap;
 	}
 }
 
@@ -162,8 +115,6 @@ struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode,
 					     struct msi_domain_info *info,
 					     struct irq_domain *parent)
 {
-	struct irq_domain *domain;
-
 	if (WARN_ON(info->flags & MSI_FLAG_LEVEL_CAPABLE))
 		info->flags &= ~MSI_FLAG_LEVEL_CAPABLE;
 
@@ -172,23 +123,298 @@ struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode,
 	if (info->flags & MSI_FLAG_USE_DEF_CHIP_OPS)
 		pci_msi_domain_update_chip_ops(info);
 
+	/* Let the core code free MSI descriptors when freeing interrupts */
+	info->flags |= MSI_FLAG_FREE_MSI_DESCS;
+
 	info->flags |= MSI_FLAG_ACTIVATE_EARLY | MSI_FLAG_DEV_SYSFS;
 	if (IS_ENABLED(CONFIG_GENERIC_IRQ_RESERVATION_MODE))
 		info->flags |= MSI_FLAG_MUST_REACTIVATE;
 
 	/* PCI-MSI is oneshot-safe */
 	info->chip->flags |= IRQCHIP_ONESHOT_SAFE;
+	/* Let the core update the bus token */
+	info->bus_token = DOMAIN_BUS_PCI_MSI;
 
-	domain = msi_create_irq_domain(fwnode, info, parent);
-	if (!domain)
-		return NULL;
-
-	irq_domain_update_bus_token(domain, DOMAIN_BUS_PCI_MSI);
-	return domain;
+	return msi_create_irq_domain(fwnode, info, parent);
 }
 EXPORT_SYMBOL_GPL(pci_msi_create_irq_domain);
 
 /*
+ * Per device MSI[-X] domain functionality
+ */
+static void pci_device_domain_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc)
+{
+	arg->desc = desc;
+	arg->hwirq = desc->msi_index;
+}
+
+static void pci_irq_mask_msi(struct irq_data *data)
+{
+	struct msi_desc *desc = irq_data_get_msi_desc(data);
+
+	pci_msi_mask(desc, BIT(data->irq - desc->irq));
+}
+
+static void pci_irq_unmask_msi(struct irq_data *data)
+{
+	struct msi_desc *desc = irq_data_get_msi_desc(data);
+
+	pci_msi_unmask(desc, BIT(data->irq - desc->irq));
+}
+
+#ifdef CONFIG_GENERIC_IRQ_RESERVATION_MODE
+# define MSI_REACTIVATE		MSI_FLAG_MUST_REACTIVATE
+#else
+# define MSI_REACTIVATE		0
+#endif
+
+#define MSI_COMMON_FLAGS	(MSI_FLAG_FREE_MSI_DESCS |	\
+				 MSI_FLAG_ACTIVATE_EARLY |	\
+				 MSI_FLAG_DEV_SYSFS |		\
+				 MSI_REACTIVATE)
+
+static const struct msi_domain_template pci_msi_template = {
+	.chip = {
+		.name			= "PCI-MSI",
+		.irq_mask		= pci_irq_mask_msi,
+		.irq_unmask		= pci_irq_unmask_msi,
+		.irq_write_msi_msg	= pci_msi_domain_write_msg,
+		.flags			= IRQCHIP_ONESHOT_SAFE,
+	},
+
+	.ops = {
+		.set_desc		= pci_device_domain_set_desc,
+	},
+
+	.info = {
+		.flags			= MSI_COMMON_FLAGS | MSI_FLAG_MULTI_PCI_MSI,
+		.bus_token		= DOMAIN_BUS_PCI_DEVICE_MSI,
+	},
+};
+
+static void pci_irq_mask_msix(struct irq_data *data)
+{
+	pci_msix_mask(irq_data_get_msi_desc(data));
+}
+
+static void pci_irq_unmask_msix(struct irq_data *data)
+{
+	pci_msix_unmask(irq_data_get_msi_desc(data));
+}
+
+static void pci_msix_prepare_desc(struct irq_domain *domain, msi_alloc_info_t *arg,
+				  struct msi_desc *desc)
+{
+	/* Don't fiddle with preallocated MSI descriptors */
+	if (!desc->pci.mask_base)
+		msix_prepare_msi_desc(to_pci_dev(desc->dev), desc);
+}
+
+static const struct msi_domain_template pci_msix_template = {
+	.chip = {
+		.name			= "PCI-MSIX",
+		.irq_mask		= pci_irq_mask_msix,
+		.irq_unmask		= pci_irq_unmask_msix,
+		.irq_write_msi_msg	= pci_msi_domain_write_msg,
+		.flags			= IRQCHIP_ONESHOT_SAFE,
+	},
+
+	.ops = {
+		.prepare_desc		= pci_msix_prepare_desc,
+		.set_desc		= pci_device_domain_set_desc,
+	},
+
+	.info = {
+		.flags			= MSI_COMMON_FLAGS | MSI_FLAG_PCI_MSIX |
+					  MSI_FLAG_PCI_MSIX_ALLOC_DYN,
+		.bus_token		= DOMAIN_BUS_PCI_DEVICE_MSIX,
+	},
+};
+
+static bool pci_match_device_domain(struct pci_dev *pdev, enum irq_domain_bus_token bus_token)
+{
+	return msi_match_device_irq_domain(&pdev->dev, MSI_DEFAULT_DOMAIN, bus_token);
+}
+
+static bool pci_create_device_domain(struct pci_dev *pdev, const struct msi_domain_template *tmpl,
+				     unsigned int hwsize)
+{
+	struct irq_domain *domain = dev_get_msi_domain(&pdev->dev);
+
+	if (!domain || !irq_domain_is_msi_parent(domain))
+		return true;
+
+	return msi_create_device_irq_domain(&pdev->dev, MSI_DEFAULT_DOMAIN, tmpl,
+					    hwsize, NULL, NULL);
+}
+
+/**
+ * pci_setup_msi_device_domain - Setup a device MSI interrupt domain
+ * @pdev:	The PCI device to create the domain on
+ *
+ * Return:
+ *  True when:
+ *	- The device does not have a MSI parent irq domain associated,
+ *	  which keeps the legacy architecture specific and the global
+ *	  PCI/MSI domain models working
+ *	- The MSI domain exists already
+ *	- The MSI domain was successfully allocated
+ *  False when:
+ *	- MSI-X is enabled
+ *	- The domain creation fails.
+ *
+ * The created MSI domain is preserved until:
+ *	- The device is removed
+ *	- MSI is disabled and a MSI-X domain is created
+ */
+bool pci_setup_msi_device_domain(struct pci_dev *pdev)
+{
+	if (WARN_ON_ONCE(pdev->msix_enabled))
+		return false;
+
+	if (pci_match_device_domain(pdev, DOMAIN_BUS_PCI_DEVICE_MSI))
+		return true;
+	if (pci_match_device_domain(pdev, DOMAIN_BUS_PCI_DEVICE_MSIX))
+		msi_remove_device_irq_domain(&pdev->dev, MSI_DEFAULT_DOMAIN);
+
+	return pci_create_device_domain(pdev, &pci_msi_template, 1);
+}
+
+/**
+ * pci_setup_msix_device_domain - Setup a device MSI-X interrupt domain
+ * @pdev:	The PCI device to create the domain on
+ * @hwsize:	The size of the MSI-X vector table
+ *
+ * Return:
+ *  True when:
+ *	- The device does not have a MSI parent irq domain associated,
+ *	  which keeps the legacy architecture specific and the global
+ *	  PCI/MSI domain models working
+ *	- The MSI-X domain exists already
+ *	- The MSI-X domain was successfully allocated
+ *  False when:
+ *	- MSI is enabled
+ *	- The domain creation fails.
+ *
+ * The created MSI-X domain is preserved until:
+ *	- The device is removed
+ *	- MSI-X is disabled and a MSI domain is created
+ */
+bool pci_setup_msix_device_domain(struct pci_dev *pdev, unsigned int hwsize)
+{
+	if (WARN_ON_ONCE(pdev->msi_enabled))
+		return false;
+
+	if (pci_match_device_domain(pdev, DOMAIN_BUS_PCI_DEVICE_MSIX))
+		return true;
+	if (pci_match_device_domain(pdev, DOMAIN_BUS_PCI_DEVICE_MSI))
+		msi_remove_device_irq_domain(&pdev->dev, MSI_DEFAULT_DOMAIN);
+
+	return pci_create_device_domain(pdev, &pci_msix_template, hwsize);
+}
+
+/**
+ * pci_msi_domain_supports - Check for support of a particular feature flag
+ * @pdev:		The PCI device to operate on
+ * @feature_mask:	The feature mask to check for (full match)
+ * @mode:		If ALLOW_LEGACY this grants the feature when there is no irq domain
+ *			associated to the device. If DENY_LEGACY the lack of an irq domain
+ *			makes the feature unsupported
+ */
+bool pci_msi_domain_supports(struct pci_dev *pdev, unsigned int feature_mask,
+			     enum support_mode mode)
+{
+	struct msi_domain_info *info;
+	struct irq_domain *domain;
+	unsigned int supported;
+
+	domain = dev_get_msi_domain(&pdev->dev);
+
+	if (!domain || !irq_domain_is_hierarchy(domain))
+		return mode == ALLOW_LEGACY;
+
+	if (!irq_domain_is_msi_parent(domain)) {
+		/*
+		 * For "global" PCI/MSI interrupt domains the associated
+		 * msi_domain_info::flags is the authoritive source of
+		 * information.
+		 */
+		info = domain->host_data;
+		supported = info->flags;
+	} else {
+		/*
+		 * For MSI parent domains the supported feature set
+		 * is avaliable in the parent ops. This makes checks
+		 * possible before actually instantiating the
+		 * per device domain because the parent is never
+		 * expanding the PCI/MSI functionality.
+		 */
+		supported = domain->msi_parent_ops->supported_flags;
+	}
+
+	return (supported & feature_mask) == feature_mask;
+}
+
+/**
+ * pci_create_ims_domain - Create a secondary IMS domain for a PCI device
+ * @pdev:	The PCI device to operate on
+ * @template:	The MSI info template which describes the domain
+ * @hwsize:	The size of the hardware entry table or 0 if the domain
+ *		is purely software managed
+ * @data:	Optional pointer to domain specific data to be stored
+ *		in msi_domain_info::data
+ *
+ * Return: True on success, false otherwise
+ *
+ * An IMS domain is expected to have the following constraints:
+ *	- The index space is managed by the core code
+ *
+ *	- There is no requirement for consecutive index ranges
+ *
+ *	- The interrupt chip must provide the following callbacks:
+ *		- irq_mask()
+ *		- irq_unmask()
+ *		- irq_write_msi_msg()
+ *
+ *	- The interrupt chip must provide the following optional callbacks
+ *	  when the irq_mask(), irq_unmask() and irq_write_msi_msg() callbacks
+ *	  cannot operate directly on hardware, e.g. in the case that the
+ *	  interrupt message store is in queue memory:
+ *		- irq_bus_lock()
+ *		- irq_bus_unlock()
+ *
+ *	  These callbacks are invoked from preemptible task context and are
+ *	  allowed to sleep. In this case the mandatory callbacks above just
+ *	  store the information. The irq_bus_unlock() callback is supposed
+ *	  to make the change effective before returning.
+ *
+ *	- Interrupt affinity setting is handled by the underlying parent
+ *	  interrupt domain and communicated to the IMS domain via
+ *	  irq_write_msi_msg().
+ *
+ * The domain is automatically destroyed when the PCI device is removed.
+ */
+bool pci_create_ims_domain(struct pci_dev *pdev, const struct msi_domain_template *template,
+			   unsigned int hwsize, void *data)
+{
+	struct irq_domain *domain = dev_get_msi_domain(&pdev->dev);
+
+	if (!domain || !irq_domain_is_msi_parent(domain))
+		return false;
+
+	if (template->info.bus_token != DOMAIN_BUS_PCI_DEVICE_IMS ||
+	    !(template->info.flags & MSI_FLAG_ALLOC_SIMPLE_MSI_DESCS) ||
+	    !(template->info.flags & MSI_FLAG_FREE_MSI_DESCS) ||
+	    !template->chip.irq_mask || !template->chip.irq_unmask ||
+	    !template->chip.irq_write_msi_msg || template->chip.irq_set_affinity)
+		return false;
+
+	return msi_create_device_irq_domain(&pdev->dev, MSI_SECONDARY_DOMAIN, template,
+					    hwsize, data, NULL);
+}
+EXPORT_SYMBOL_GPL(pci_create_ims_domain);
+
+/*
  * Users of the generic MSI infrastructure expect a device to have a single ID,
  * so with DMA aliases we have to pick the least-worst compromise. Devices with
  * DMA phantom functions tend to still emit MSIs from the real function number,
@@ -257,24 +483,3 @@ struct irq_domain *pci_msi_get_device_domain(struct pci_dev *pdev)
 					     DOMAIN_BUS_PCI_MSI);
 	return dom;
 }
-
-/**
- * pci_dev_has_special_msi_domain - Check whether the device is handled by
- *				    a non-standard PCI-MSI domain
- * @pdev:	The PCI device to check.
- *
- * Returns: True if the device irqdomain or the bus irqdomain is
- * non-standard PCI/MSI.
- */
-bool pci_dev_has_special_msi_domain(struct pci_dev *pdev)
-{
-	struct irq_domain *dom = dev_get_msi_domain(&pdev->dev);
-
-	if (!dom)
-		dom = dev_get_msi_domain(&pdev->bus->dev);
-
-	if (!dom)
-		return true;
-
-	return dom->bus_token != DOMAIN_BUS_PCI_MSI;
-}