irqchip/gic-v3-its: Provide MSI parent for PCI/MSI[-X]

The its_pci_msi_prepare() function from the ITS-PCI/MSI code provides the
'global' PCI/MSI domains. Move this function to the ITS-MSI parent code and
amend the function to use the domain hardware size, which is the MSI[X]
vector count, for allocating the ITS slots for the PCI device.

Enable PCI matching in msi_parent_ops and provide the necessary update to
the ITS specific child domain initialization function so that the prepare
callback gets invoked on allocations.

The latter might be optimized to do the allocation right at the point where
the child domain is initialized, but keep it simple for now.

Signed-off-by: Thomas Gleixner <[email protected]>
Signed-off-by: Anna-Maria Behnsen <[email protected]>
Signed-off-by: Shivamurthy Shastri <[email protected]>
Signed-off-by: Thomas Gleixner <[email protected]>
Link: https://lore.kernel.org/r/[email protected]

Author: KAGA-KOKO

drivers/irqchip/Makefile

@@ -33,7 +33,6 @@ obj-$(CONFIG_IRQ_MSI_LIB)		+= irq-msi-lib.o
 obj-$(CONFIG_ARM_GIC_V2M)		+= irq-gic-v2m.o
 obj-$(CONFIG_ARM_GIC_V3)		+= irq-gic-v3.o irq-gic-v3-mbi.o irq-gic-common.o
 obj-$(CONFIG_ARM_GIC_V3_ITS)		+= irq-gic-v3-its.o irq-gic-v3-its-platform-msi.o irq-gic-v4.o irq-gic-v3-its-msi-parent.o
-obj-$(CONFIG_ARM_GIC_V3_ITS_PCI)	+= irq-gic-v3-its-pci-msi.o
 obj-$(CONFIG_ARM_GIC_V3_ITS_FSL_MC)	+= irq-gic-v3-its-fsl-mc-msi.o
 obj-$(CONFIG_PARTITION_PERCPU)		+= irq-partition-percpu.o
 obj-$(CONFIG_HISILICON_IRQ_MBIGEN)	+= irq-mbigen.o

drivers/irqchip/irq-gic-v3-its-msi-parent.c

@@ -1,31 +1,139 @@
 // SPDX-License-Identifier: GPL-2.0-only
+// Copyright (C) 2013-2015 ARM Limited, All Rights Reserved.
+// Author: Marc Zyngier <[email protected]>
 // Copyright (C) 2022 Linutronix GmbH
 // Copyright (C) 2022 Intel
 
+#include <linux/pci.h>
+
 #include "irq-gic-common.h"
 #include "irq-msi-lib.h"
 
 #define ITS_MSI_FLAGS_REQUIRED  (MSI_FLAG_USE_DEF_DOM_OPS |	\
-				 MSI_FLAG_USE_DEF_CHIP_OPS)
+				 MSI_FLAG_USE_DEF_CHIP_OPS |	\
+				 MSI_FLAG_PCI_MSI_MASK_PARENT)
 
 #define ITS_MSI_FLAGS_SUPPORTED (MSI_GENERIC_FLAGS_MASK |	\
 				 MSI_FLAG_PCI_MSIX      |	\
-				 MSI_FLAG_MULTI_PCI_MSI |	\
-				 MSI_FLAG_PCI_MSI_MASK_PARENT)
+				 MSI_FLAG_MULTI_PCI_MSI)
+
+#ifdef CONFIG_PCI_MSI
+static int its_pci_msi_vec_count(struct pci_dev *pdev, void *data)
+{
+	int msi, msix, *count = data;
+
+	msi = max(pci_msi_vec_count(pdev), 0);
+	msix = max(pci_msix_vec_count(pdev), 0);
+	*count += max(msi, msix);
+
+	return 0;
+}
+
+static int its_get_pci_alias(struct pci_dev *pdev, u16 alias, void *data)
+{
+	struct pci_dev **alias_dev = data;
+
+	*alias_dev = pdev;
+
+	return 0;
+}
+
+static int its_pci_msi_prepare(struct irq_domain *domain, struct device *dev,
+			       int nvec, msi_alloc_info_t *info)
+{
+	struct pci_dev *pdev, *alias_dev;
+	struct msi_domain_info *msi_info;
+	int alias_count = 0, minnvec = 1;
+
+	if (!dev_is_pci(dev))
+		return -EINVAL;
+
+	pdev = to_pci_dev(dev);
+	/*
+	 * If pdev is downstream of any aliasing bridges, take an upper
+	 * bound of how many other vectors could map to the same DevID.
+	 * Also tell the ITS that the signalling will come from a proxy
+	 * device, and that special allocation rules apply.
+	 */
+	pci_for_each_dma_alias(pdev, its_get_pci_alias, &alias_dev);
+	if (alias_dev != pdev) {
+		if (alias_dev->subordinate)
+			pci_walk_bus(alias_dev->subordinate,
+				     its_pci_msi_vec_count, &alias_count);
+		info->flags |= MSI_ALLOC_FLAGS_PROXY_DEVICE;
+	}
+
+	/* ITS specific DeviceID, as the core ITS ignores dev. */
+	info->scratchpad[0].ul = pci_msi_domain_get_msi_rid(domain, pdev);
+
+	/*
+	 * @domain->msi_domain_info->hwsize contains the size of the
+	 * MSI[-X] domain, but vector allocation happens one by one. This
+	 * needs some thought when MSI comes into play as the size of MSI
+	 * might be unknown at domain creation time and therefore set to
+	 * MSI_MAX_INDEX.
+	 */
+	msi_info = msi_get_domain_info(domain);
+	if (msi_info->hwsize > nvec)
+		nvec = msi_info->hwsize;
+
+	/*
+	 * Always allocate a power of 2, and special case device 0 for
+	 * broken systems where the DevID is not wired (and all devices
+	 * appear as DevID 0). For that reason, we generously allocate a
+	 * minimum of 32 MSIs for DevID 0. If you want more because all
+	 * your devices are aliasing to DevID 0, consider fixing your HW.
+	 */
+	nvec = max(nvec, alias_count);
+	if (!info->scratchpad[0].ul)
+		minnvec = 32;
+	nvec = max_t(int, minnvec, roundup_pow_of_two(nvec));
+
+	msi_info = msi_get_domain_info(domain->parent);
+	return msi_info->ops->msi_prepare(domain->parent, dev, nvec, info);
+}
+#else /* CONFIG_PCI_MSI */
+#define its_pci_msi_prepare	NULL
+#endif /* !CONFIG_PCI_MSI */
 
 static bool its_init_dev_msi_info(struct device *dev, struct irq_domain *domain,
 				  struct irq_domain *real_parent, struct msi_domain_info *info)
 {
 	if (!msi_lib_init_dev_msi_info(dev, domain, real_parent, info))
 		return false;
 
+	switch(info->bus_token) {
+	case DOMAIN_BUS_PCI_DEVICE_MSI:
+	case DOMAIN_BUS_PCI_DEVICE_MSIX:
+		/*
+		 * FIXME: This probably should be done after a (not yet
+		 * existing) post domain creation callback once to make
+		 * support for dynamic post-enable MSI-X allocations
+		 * work without having to reevaluate the domain size
+		 * over and over. It is known already at allocation
+		 * time via info->hwsize.
+		 *
+		 * That should work perfectly fine for MSI/MSI-X but needs
+		 * some thoughts for purely software managed MSI domains
+		 * where the index space is only limited artificially via
+		 * %MSI_MAX_INDEX.
+		 */
+		info->ops->msi_prepare = its_pci_msi_prepare;
+		break;
+	default:
+		/* Confused. How did the lib return true? */
+		WARN_ON_ONCE(1);
+		return false;
+	}
+
 	return true;
 }
 
 const struct msi_parent_ops gic_v3_its_msi_parent_ops = {
 	.supported_flags	= ITS_MSI_FLAGS_SUPPORTED,
 	.required_flags		= ITS_MSI_FLAGS_REQUIRED,
 	.bus_select_token	= DOMAIN_BUS_NEXUS,
+	.bus_select_mask	= MATCH_PCI_MSI,
 	.prefix			= "ITS-",
 	.init_dev_msi_info	= its_init_dev_msi_info,
 };