cxl: Add support for interrupts on the Mellanox CX4

The Mellanox CX4 in cxl mode uses a hybrid interrupt model, where
interrupts are routed from the networking hardware to the XSL using the
MSIX table, and from there will be transformed back into an MSIX
interrupt using the cxl style interrupts (i.e. using IVTE entries and
ranges to map a PE and AFU interrupt number to an MSIX address).

We want to hide the implementation details of cxl interrupts as much as
possible. To this end, we use a special version of the MSI setup &
teardown routines in the PHB while in cxl mode to allocate the cxl
interrupts and configure the IVTE entries in the process element.

This function does not configure the MSIX table - the CX4 card uses a
custom format in that table and it would not be appropriate to fill that
out in generic code. The rest of the functionality is similar to the
"Full MSI-X mode" described in the CAIA, and this could be easily
extended to support other adapters that use that mode in the future.

The interrupts will be associated with the default context. If the
maximum number of interrupts per context has been limited (e.g. by the
mlx5 driver), it will automatically allocate additional kernel contexts
to associate extra interrupts as required. These contexts will be
started using the same WED that was used to start the default context.

Signed-off-by: Ian Munsie <imunsie@au1.ibm.com>
Reviewed-by: Andrew Donnellan <andrew.donnellan@au1.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

3 files changed, 90 insertions, 0 deletions

diff --git a/arch/powerpc/platforms/powernv/pci-cxl.c b/arch/powerpc/platforms/powernv/pci-cxl.c
index 831bbfb4e278..3f342077628b 100644
--- a/arch/powerpc/platforms/powernv/pci-cxl.c
+++ b/arch/powerpc/platforms/powernv/pci-cxl.c
@@ -8,6 +8,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/msi.h>
 #include <asm/pci-bridge.h>
 #include <asm/pnv-pci.h>
 #include <asm/opal.h>
@@ -281,3 +282,86 @@ void pnv_cxl_disable_device(struct pci_dev *dev)
 	cxl_pci_disable_device(dev);
 	cxl_afu_put(afu);
 }
+
+/*
+ * This is a special version of pnv_setup_msi_irqs for cards in cxl mode. This
+ * function handles setting up the IVTE entries for the XSL to use.
+ *
+ * We are currently not filling out the MSIX table, since the only currently
+ * supported adapter (CX4) uses a custom MSIX table format in cxl mode and it
+ * is up to their driver to fill that out. In the future we may fill out the
+ * MSIX table (and change the IVTE entries to be an index to the MSIX table)
+ * for adapters implementing the Full MSI-X mode described in the CAIA.
+ */
+int pnv_cxl_cx4_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
+{
+	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
+	struct pnv_phb *phb = hose->private_data;
+	struct msi_desc *entry;
+	struct cxl_context *ctx = NULL;
+	unsigned int virq;
+	int hwirq;
+	int afu_irq = 0;
+	int rc;
+
+	if (WARN_ON(!phb) || !phb->msi_bmp.bitmap)
+		return -ENODEV;
+
+	if (pdev->no_64bit_msi && !phb->msi32_support)
+		return -ENODEV;
+
+	rc = cxl_cx4_setup_msi_irqs(pdev, nvec, type);
+	if (rc)
+		return rc;
+
+	for_each_pci_msi_entry(entry, pdev) {
+		if (!entry->msi_attrib.is_64 && !phb->msi32_support) {
+			pr_warn("%s: Supports only 64-bit MSIs\n",
+				pci_name(pdev));
+			return -ENXIO;
+		}
+
+		hwirq = cxl_next_msi_hwirq(pdev, &ctx, &afu_irq);
+		if (WARN_ON(hwirq <= 0))
+			return (hwirq ? hwirq : -ENOMEM);
+
+		virq = irq_create_mapping(NULL, hwirq);
+		if (virq == NO_IRQ) {
+			pr_warn("%s: Failed to map cxl mode MSI to linux irq\n",
+				pci_name(pdev));
+			return -ENOMEM;
+		}
+
+		rc = pnv_cxl_ioda_msi_setup(pdev, hwirq, virq);
+		if (rc) {
+			pr_warn("%s: Failed to setup cxl mode MSI\n", pci_name(pdev));
+			irq_dispose_mapping(virq);
+			return rc;
+		}
+
+		irq_set_msi_desc(virq, entry);
+	}
+
+	return 0;
+}
+
+void pnv_cxl_cx4_teardown_msi_irqs(struct pci_dev *pdev)
+{
+	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
+	struct pnv_phb *phb = hose->private_data;
+	struct msi_desc *entry;
+	irq_hw_number_t hwirq;
+
+	if (WARN_ON(!phb))
+		return;
+
+	for_each_pci_msi_entry(entry, pdev) {
+		if (entry->irq == NO_IRQ)
+			continue;
+		hwirq = virq_to_hw(entry->irq);
+		irq_set_msi_desc(entry->irq, NULL);
+		irq_dispose_mapping(entry->irq);
+	}
+
+	cxl_cx4_teardown_msi_irqs(pdev);
+}
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 104c0405f47c..530d4afbe2fd 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -3465,6 +3465,10 @@ static const struct pci_controller_ops pnv_npu_ioda_controller_ops = {
 const struct pci_controller_ops pnv_cxl_cx4_ioda_controller_ops = {
 	.dma_dev_setup		= pnv_pci_dma_dev_setup,
 	.dma_bus_setup		= pnv_pci_dma_bus_setup,
+#ifdef CONFIG_PCI_MSI
+	.setup_msi_irqs		= pnv_cxl_cx4_setup_msi_irqs,
+	.teardown_msi_irqs	= pnv_cxl_cx4_teardown_msi_irqs,
+#endif
 	.enable_device_hook	= pnv_cxl_enable_device_hook,
 	.disable_device		= pnv_cxl_disable_device,
 	.release_device		= pnv_pci_release_device,
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index 20c9a6b1c64d..f0c276c05f50 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -247,6 +247,8 @@ extern void pnv_npu_release_ownership(struct pnv_ioda_pe *npe);
 /* cxl functions */
 extern bool pnv_cxl_enable_device_hook(struct pci_dev *dev);
 extern void pnv_cxl_disable_device(struct pci_dev *dev);
+extern int pnv_cxl_cx4_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type);
+extern void pnv_cxl_cx4_teardown_msi_irqs(struct pci_dev *pdev);
 
 
 /* phb ops (cxl switches these when enabling the kernel api on the phb) */