PCI/MSI: Provide post-enable dynamic allocation interfaces for MSI-X

MSI-X vectors can be allocated after the initial MSI-X enablement, but this
needs explicit support of the underlying interrupt domains.

Provide a function to query the ability and functions to allocate/free
individual vectors post-enable.

The allocation can either request a specific index in the MSI-X table or
with the index argument MSI_ANY_INDEX it allocates the next free vector.

The return value is a struct msi_map which on success contains both index
and the Linux interrupt number. In case of failure index is negative and
the Linux interrupt number is 0.

The allocation function is for a single MSI-X index at a time as that's
sufficient for the most urgent use case VFIO to get rid of the 'disable
MSI-X, reallocate, enable-MSI-X' cycle which is prone to lost interrupts
and redirections to the legacy and obviously unhandled INTx.

As single index allocation is also sufficient for the use cases Jason
Gunthorpe pointed out: Allocation of a MSI-X or IMS vector for a network
queue. See Link below.

Signed-off-by: Thomas Gleixner <[email protected]>
Reviewed-by: Kevin Tian <[email protected]>
Acked-by: Bjorn Helgaas <[email protected]>
Acked-by: Marc Zyngier <[email protected]>
Link: https://lore.kernel.org/all/[email protected]
Link: https://lore.kernel.org/r/[email protected]

Author: KAGA-KOKO

drivers/pci/msi/api.c

@@ -112,6 +112,73 @@ int pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries,
 }
 EXPORT_SYMBOL(pci_enable_msix_range);
 
+/**
+ * pci_msix_can_alloc_dyn - Query whether dynamic allocation after enabling
+ *			    MSI-X is supported
+ *
+ * @dev:	PCI device to operate on
+ *
+ * Return: True if supported, false otherwise
+ */
+bool pci_msix_can_alloc_dyn(struct pci_dev *dev)
+{
+	if (!dev->msix_cap)
+		return false;
+
+	return pci_msi_domain_supports(dev, MSI_FLAG_PCI_MSIX_ALLOC_DYN, DENY_LEGACY);
+}
+EXPORT_SYMBOL_GPL(pci_msix_can_alloc_dyn);
+
+/**
+ * pci_msix_alloc_irq_at - Allocate an MSI-X interrupt after enabling MSI-X
+ *			   at a given MSI-X vector index or any free vector index
+ *
+ * @dev:	PCI device to operate on
+ * @index:	Index to allocate. If @index == MSI_ANY_INDEX this allocates
+ *		the next free index in the MSI-X table
+ * @affdesc:	Optional pointer to an affinity descriptor structure. NULL otherwise
+ *
+ * Return: A struct msi_map
+ *
+ *	On success msi_map::index contains the allocated index (>= 0) and
+ *	msi_map::virq contains the allocated Linux interrupt number (> 0).
+ *
+ *	On fail msi_map::index contains the error code and msi_map::virq
+ *	is set to 0.
+ */
+struct msi_map pci_msix_alloc_irq_at(struct pci_dev *dev, unsigned int index,
+				     const struct irq_affinity_desc *affdesc)
+{
+	struct msi_map map = { .index = -ENOTSUPP };
+
+	if (!dev->msix_enabled)
+		return map;
+
+	if (!pci_msix_can_alloc_dyn(dev))
+		return map;
+
+	return msi_domain_alloc_irq_at(&dev->dev, MSI_DEFAULT_DOMAIN, index, affdesc, NULL);
+}
+EXPORT_SYMBOL_GPL(pci_msix_alloc_irq_at);
+
+/**
+ * pci_msix_free_irq - Free an interrupt on a PCI/MSIX interrupt domain
+ *		      which was allocated via pci_msix_alloc_irq_at()
+ *
+ * @dev:	The PCI device to operate on
+ * @map:	A struct msi_map describing the interrupt to free
+ *		as returned from the allocation function.
+ */
+void pci_msix_free_irq(struct pci_dev *dev, struct msi_map map)
+{
+	if (WARN_ON_ONCE(map.index < 0 || map.virq <= 0))
+		return;
+	if (WARN_ON_ONCE(!pci_msix_can_alloc_dyn(dev)))
+		return;
+	msi_domain_free_irqs_range(&dev->dev, MSI_DEFAULT_DOMAIN, map.index, map.index);
+}
+EXPORT_SYMBOL_GPL(pci_msix_free_irq);
+
 /**
  * pci_disable_msix() - Disable MSI-X interrupt mode on device
  * @dev: the PCI device to operate on

drivers/pci/msi/irqdomain.c

@@ -225,7 +225,8 @@ static const struct msi_domain_template pci_msix_template = {
 	},
 
 	.info = {
-		.flags			= MSI_COMMON_FLAGS | MSI_FLAG_PCI_MSIX,
+		.flags			= MSI_COMMON_FLAGS | MSI_FLAG_PCI_MSIX |
+					  MSI_FLAG_PCI_MSIX_ALLOC_DYN,
 		.bus_token		= DOMAIN_BUS_PCI_DEVICE_MSIX,
 	},
 };

include/linux/pci.h

@@ -38,6 +38,7 @@
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/resource_ext.h>
+#include <linux/msi_api.h>
 #include <uapi/linux/pci.h>
 
 #include <linux/pci_ids.h>
@@ -1559,6 +1560,11 @@ int pci_alloc_irq_vectors_affinity(struct pci_dev *dev, unsigned int min_vecs,
 				   unsigned int max_vecs, unsigned int flags,
 				   struct irq_affinity *affd);
 
+bool pci_msix_can_alloc_dyn(struct pci_dev *dev);
+struct msi_map pci_msix_alloc_irq_at(struct pci_dev *dev, unsigned int index,
+				     const struct irq_affinity_desc *affdesc);
+void pci_msix_free_irq(struct pci_dev *pdev, struct msi_map map);
+
 void pci_free_irq_vectors(struct pci_dev *dev);
 int pci_irq_vector(struct pci_dev *dev, unsigned int nr);
 const struct cpumask *pci_irq_get_affinity(struct pci_dev *pdev, int vec);