Merge branch 'irq-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull irq updates from Thomas Gleixner:
 "The irq department delivers:

   - Expand the generic infrastructure handling the irq migration on CPU
     hotplug and convert X86 over to it. (Thomas Gleixner)

     Aside of consolidating code this is a preparatory change for:

   - Finalizing the affinity management for multi-queue devices. The
     main change here is to shut down interrupts which are affine to a
     outgoing CPU and reenabling them when the CPU comes online again.
     That avoids moving interrupts pointlessly around and breaking and
     reestablishing affinities for no value. (Christoph Hellwig)

     Note: This contains also the BLOCK-MQ and NVME changes which depend
     on the rework of the irq core infrastructure. Jens acked them and
     agreed that they should go with the irq changes.

   - Consolidation of irq domain code (Marc Zyngier)

   - State tracking consolidation in the core code (Jeffy Chen)

   - Add debug infrastructure for hierarchical irq domains (Thomas
     Gleixner)

   - Infrastructure enhancement for managing generic interrupt chips via
     devmem (Bartosz Golaszewski)

   - Constification work all over the place (Tobias Klauser)

   - Two new interrupt controller drivers for MVEBU (Thomas Petazzoni)

   - The usual set of fixes, updates and enhancements all over the
     place"

* 'irq-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (112 commits)
  irqchip/or1k-pic: Fix interrupt acknowledgement
  irqchip/irq-mvebu-gicp: Allocate enough memory for spi_bitmap
  irqchip/gic-v3: Fix out-of-bound access in gic_set_affinity
  nvme: Allocate queues for all possible CPUs
  blk-mq: Create hctx for each present CPU
  blk-mq: Include all present CPUs in the default queue mapping
  genirq: Avoid unnecessary low level irq function calls
  genirq: Set irq masked state when initializing irq_desc
  genirq/timings: Add infrastructure for estimating the next interrupt arrival time
  genirq/timings: Add infrastructure to track the interrupt timings
  genirq/debugfs: Remove pointless NULL pointer check
  irqchip/gic-v3-its: Don't assume GICv3 hardware supports 16bit INTID
  irqchip/gic-v3-its: Add ACPI NUMA node mapping
  irqchip/gic-v3-its-platform-msi: Make of_device_ids const
  irqchip/gic-v3-its: Make of_device_ids const
  irqchip/irq-mvebu-icu: Add new driver for Marvell ICU
  irqchip/irq-mvebu-gicp: Add new driver for Marvell GICP
  dt-bindings/interrupt-controller: Add DT binding for the Marvell ICU
  genirq/irqdomain: Remove auto-recursive hierarchy support
  irqchip/MSI: Use irq_domain_update_bus_token instead of an open coded access
  ...

31 files changed, 1067 insertions, 113 deletions

diff --git a/drivers/base/platform-msi.c b/drivers/base/platform-msi.c
index d35e9a20caf7..e5473525e7b2 100644
--- a/drivers/base/platform-msi.c
+++ b/drivers/base/platform-msi.c
@@ -195,7 +195,7 @@ struct irq_domain *platform_msi_create_irq_domain(struct fwnode_handle *fwnode,
 
 	domain = msi_create_irq_domain(fwnode, info, parent);
 	if (domain)
-		domain->bus_token = DOMAIN_BUS_PLATFORM_MSI;
+		irq_domain_update_bus_token(domain, DOMAIN_BUS_PLATFORM_MSI);
 
 	return domain;
 }
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 0f1219fa8561..5c9759ed22ca 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -4384,21 +4384,29 @@ static void ir_compose_msi_msg(struct irq_data *irq_data, struct msi_msg *msg)
 }
 
 static struct irq_chip amd_ir_chip = {
-	.irq_ack = ir_ack_apic_edge,
-	.irq_set_affinity = amd_ir_set_affinity,
-	.irq_set_vcpu_affinity = amd_ir_set_vcpu_affinity,
-	.irq_compose_msi_msg = ir_compose_msi_msg,
+	.name			= "AMD-IR",
+	.irq_ack		= ir_ack_apic_edge,
+	.irq_set_affinity	= amd_ir_set_affinity,
+	.irq_set_vcpu_affinity	= amd_ir_set_vcpu_affinity,
+	.irq_compose_msi_msg	= ir_compose_msi_msg,
 };
 
 int amd_iommu_create_irq_domain(struct amd_iommu *iommu)
 {
-	iommu->ir_domain = irq_domain_add_tree(NULL, &amd_ir_domain_ops, iommu);
+	struct fwnode_handle *fn;
+
+	fn = irq_domain_alloc_named_id_fwnode("AMD-IR", iommu->index);
+	if (!fn)
+		return -ENOMEM;
+	iommu->ir_domain = irq_domain_create_tree(fn, &amd_ir_domain_ops, iommu);
+	irq_domain_free_fwnode(fn);
 	if (!iommu->ir_domain)
 		return -ENOMEM;
 
 	iommu->ir_domain->parent = arch_get_ir_parent_domain();
-	iommu->msi_domain = arch_create_msi_irq_domain(iommu->ir_domain);
-
+	iommu->msi_domain = arch_create_remap_msi_irq_domain(iommu->ir_domain,
+							     "AMD-IR-MSI",
+							     iommu->index);
 	return 0;
 }
 
diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c
index a190cbd76ef7..8fc641ea2e41 100644
--- a/drivers/iommu/intel_irq_remapping.c
+++ b/drivers/iommu/intel_irq_remapping.c
@@ -500,8 +500,9 @@ static void iommu_enable_irq_remapping(struct intel_iommu *iommu)
 static int intel_setup_irq_remapping(struct intel_iommu *iommu)
 {
 	struct ir_table *ir_table;
-	struct page *pages;
+	struct fwnode_handle *fn;
 	unsigned long *bitmap;
+	struct page *pages;
 
 	if (iommu->ir_table)
 		return 0;
@@ -525,15 +526,24 @@ static int intel_setup_irq_remapping(struct intel_iommu *iommu)
 		goto out_free_pages;
 	}
 
-	iommu->ir_domain = irq_domain_add_hierarchy(arch_get_ir_parent_domain(),
-						    0, INTR_REMAP_TABLE_ENTRIES,
-						    NULL, &intel_ir_domain_ops,
-						    iommu);
+	fn = irq_domain_alloc_named_id_fwnode("INTEL-IR", iommu->seq_id);
+	if (!fn)
+		goto out_free_bitmap;
+
+	iommu->ir_domain =
+		irq_domain_create_hierarchy(arch_get_ir_parent_domain(),
+					    0, INTR_REMAP_TABLE_ENTRIES,
+					    fn, &intel_ir_domain_ops,
+					    iommu);
+	irq_domain_free_fwnode(fn);
 	if (!iommu->ir_domain) {
 		pr_err("IR%d: failed to allocate irqdomain\n", iommu->seq_id);
 		goto out_free_bitmap;
 	}
-	iommu->ir_msi_domain = arch_create_msi_irq_domain(iommu->ir_domain);
+	iommu->ir_msi_domain =
+		arch_create_remap_msi_irq_domain(iommu->ir_domain,
+						 "INTEL-IR-MSI",
+						 iommu->seq_id);
 
 	ir_table->base = page_address(pages);
 	ir_table->bitmap = bitmap;
@@ -1205,10 +1215,11 @@ static int intel_ir_set_vcpu_affinity(struct irq_data *data, void *info)
 }
 
 static struct irq_chip intel_ir_chip = {
-	.irq_ack = ir_ack_apic_edge,
-	.irq_set_affinity = intel_ir_set_affinity,
-	.irq_compose_msi_msg = intel_ir_compose_msi_msg,
-	.irq_set_vcpu_affinity = intel_ir_set_vcpu_affinity,
+	.name			= "INTEL-IR",
+	.irq_ack		= ir_ack_apic_edge,
+	.irq_set_affinity	= intel_ir_set_affinity,
+	.irq_compose_msi_msg	= intel_ir_compose_msi_msg,
+	.irq_set_vcpu_affinity	= intel_ir_set_vcpu_affinity,
 };
 
 static void intel_irq_remapping_prepare_irte(struct intel_ir_data *data,
diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index 478f8ace2664..676232a94f9f 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -268,6 +268,12 @@ config IRQ_MXS
 	select IRQ_DOMAIN
 	select STMP_DEVICE
 
+config MVEBU_GICP
+	bool
+
+config MVEBU_ICU
+	bool
+
 config MVEBU_ODMI
 	bool
 	select GENERIC_MSI_IRQ_DOMAIN
diff --git a/drivers/irqchip/Makefile b/drivers/irqchip/Makefile
index b64c59b838a0..e88d856cc09c 100644
--- a/drivers/irqchip/Makefile
+++ b/drivers/irqchip/Makefile
@@ -69,10 +69,12 @@ obj-$(CONFIG_ARCH_SA1100)		+= irq-sa11x0.o
 obj-$(CONFIG_INGENIC_IRQ)		+= irq-ingenic.o
 obj-$(CONFIG_IMX_GPCV2)			+= irq-imx-gpcv2.o
 obj-$(CONFIG_PIC32_EVIC)		+= irq-pic32-evic.o
+obj-$(CONFIG_MVEBU_GICP)		+= irq-mvebu-gicp.o
+obj-$(CONFIG_MVEBU_ICU)			+= irq-mvebu-icu.o
 obj-$(CONFIG_MVEBU_ODMI)		+= irq-mvebu-odmi.o
 obj-$(CONFIG_MVEBU_PIC)			+= irq-mvebu-pic.o
 obj-$(CONFIG_LS_SCFG_MSI)		+= irq-ls-scfg-msi.o
 obj-$(CONFIG_EZNPS_GIC)			+= irq-eznps.o
-obj-$(CONFIG_ARCH_ASPEED)		+= irq-aspeed-vic.o
+obj-$(CONFIG_ARCH_ASPEED)		+= irq-aspeed-vic.o irq-aspeed-i2c-ic.o
 obj-$(CONFIG_STM32_EXTI) 		+= irq-stm32-exti.o
 obj-$(CONFIG_QCOM_IRQ_COMBINER)		+= qcom-irq-combiner.o
diff --git a/drivers/irqchip/irq-armada-370-xp.c b/drivers/irqchip/irq-armada-370-xp.c
index eb0d4d41b156..b207b2c3aa55 100644
--- a/drivers/irqchip/irq-armada-370-xp.c
+++ b/drivers/irqchip/irq-armada-370-xp.c
@@ -34,25 +34,104 @@
 #include <asm/smp_plat.h>
 #include <asm/mach/irq.h>
 
-/* Interrupt Controller Registers Map */
-#define ARMADA_370_XP_INT_SET_MASK_OFFS		(0x48)
-#define ARMADA_370_XP_INT_CLEAR_MASK_OFFS	(0x4C)
-#define ARMADA_370_XP_INT_FABRIC_MASK_OFFS	(0x54)
-#define ARMADA_370_XP_INT_CAUSE_PERF(cpu)	(1 << cpu)
+/*
+ * Overall diagram of the Armada XP interrupt controller:
+ *
+ *    To CPU 0                 To CPU 1
+ *
+ *       /\                       /\
+ *       ||                       ||
+ * +---------------+     +---------------+
+ * |               |	 |               |
+ * |    per-CPU    |	 |    per-CPU    |
+ * |  mask/unmask  |	 |  mask/unmask  |
+ * |     CPU0      |	 |     CPU1      |
+ * |               |	 |               |
+ * +---------------+	 +---------------+
+ *        /\                       /\
+ *        ||                       ||
+ *        \\_______________________//
+ *                     ||
+ *            +-------------------+
+ *            |                   |
+ *            | Global interrupt  |
+ *            |    mask/unmask    |
+ *            |                   |
+ *            +-------------------+
+ *                     /\
+ *                     ||
+ *               interrupt from
+ *                   device
+ *
+ * The "global interrupt mask/unmask" is modified using the
+ * ARMADA_370_XP_INT_SET_ENABLE_OFFS and
+ * ARMADA_370_XP_INT_CLEAR_ENABLE_OFFS registers, which are relative
+ * to "main_int_base".
+ *
+ * The "per-CPU mask/unmask" is modified using the
+ * ARMADA_370_XP_INT_SET_MASK_OFFS and
+ * ARMADA_370_XP_INT_CLEAR_MASK_OFFS registers, which are relative to
+ * "per_cpu_int_base". This base address points to a special address,
+ * which automatically accesses the registers of the current CPU.
+ *
+ * The per-CPU mask/unmask can also be adjusted using the global
+ * per-interrupt ARMADA_370_XP_INT_SOURCE_CTL register, which we use
+ * to configure interrupt affinity.
+ *
+ * Due to this model, all interrupts need to be mask/unmasked at two
+ * different levels: at the global level and at the per-CPU level.
+ *
+ * This driver takes the following approach to deal with this:
+ *
+ *  - For global interrupts:
+ *
+ *    At ->map() time, a global interrupt is unmasked at the per-CPU
+ *    mask/unmask level. It is therefore unmasked at this level for
+ *    the current CPU, running the ->map() code. This allows to have
+ *    the interrupt unmasked at this level in non-SMP
+ *    configurations. In SMP configurations, the ->set_affinity()
+ *    callback is called, which using the
+ *    ARMADA_370_XP_INT_SOURCE_CTL() readjusts the per-CPU mask/unmask
+ *    for the interrupt.
+ *
+ *    The ->mask() and ->unmask() operations only mask/unmask the
+ *    interrupt at the "global" level.
+ *
+ *    So, a global interrupt is enabled at the per-CPU level as soon
+ *    as it is mapped. At run time, the masking/unmasking takes place
+ *    at the global level.
+ *
+ *  - For per-CPU interrupts
+ *
+ *    At ->map() time, a per-CPU interrupt is unmasked at the global
+ *    mask/unmask level.
+ *
+ *    The ->mask() and ->unmask() operations mask/unmask the interrupt
+ *    at the per-CPU level.
+ *
+ *    So, a per-CPU interrupt is enabled at the global level as soon
+ *    as it is mapped. At run time, the masking/unmasking takes place
+ *    at the per-CPU level.
+ */
 
+/* Registers relative to main_int_base */
 #define ARMADA_370_XP_INT_CONTROL		(0x00)
+#define ARMADA_370_XP_SW_TRIG_INT_OFFS		(0x04)
 #define ARMADA_370_XP_INT_SET_ENABLE_OFFS	(0x30)
 #define ARMADA_370_XP_INT_CLEAR_ENABLE_OFFS	(0x34)
 #define ARMADA_370_XP_INT_SOURCE_CTL(irq)	(0x100 + irq*4)
 #define ARMADA_370_XP_INT_SOURCE_CPU_MASK	0xF
 #define ARMADA_370_XP_INT_IRQ_FIQ_MASK(cpuid)	((BIT(0) | BIT(8)) << cpuid)
 
-#define ARMADA_370_XP_CPU_INTACK_OFFS		(0x44)
+/* Registers relative to per_cpu_int_base */
+#define ARMADA_370_XP_IN_DRBEL_CAUSE_OFFS	(0x08)
+#define ARMADA_370_XP_IN_DRBEL_MSK_OFFS		(0x0c)
 #define ARMADA_375_PPI_CAUSE			(0x10)
-
-#define ARMADA_370_XP_SW_TRIG_INT_OFFS           (0x4)
-#define ARMADA_370_XP_IN_DRBEL_MSK_OFFS          (0xc)
-#define ARMADA_370_XP_IN_DRBEL_CAUSE_OFFS        (0x8)
+#define ARMADA_370_XP_CPU_INTACK_OFFS		(0x44)
+#define ARMADA_370_XP_INT_SET_MASK_OFFS		(0x48)
+#define ARMADA_370_XP_INT_CLEAR_MASK_OFFS	(0x4C)
+#define ARMADA_370_XP_INT_FABRIC_MASK_OFFS	(0x54)
+#define ARMADA_370_XP_INT_CAUSE_PERF(cpu)	(1 << cpu)
 
 #define ARMADA_370_XP_MAX_PER_CPU_IRQS		(28)
 
@@ -281,13 +360,11 @@ static int armada_370_xp_mpic_irq_map(struct irq_domain *h,
 		irq_set_percpu_devid(virq);
 		irq_set_chip_and_handler(virq, &armada_370_xp_irq_chip,
 					handle_percpu_devid_irq);
-
 	} else {
 		irq_set_chip_and_handler(virq, &armada_370_xp_irq_chip,
 					handle_level_irq);
 	}
 	irq_set_probe(virq);
-	irq_clear_status_flags(virq, IRQ_NOAUTOEN);
 
 	return 0;
 }
@@ -345,16 +422,40 @@ static void armada_mpic_send_doorbell(const struct cpumask *mask,
 		ARMADA_370_XP_SW_TRIG_INT_OFFS);
 }
 
+static void armada_xp_mpic_reenable_percpu(void)
+{
+	unsigned int irq;
+
+	/* Re-enable per-CPU interrupts that were enabled before suspend */
+	for (irq = 0; irq < ARMADA_370_XP_MAX_PER_CPU_IRQS; irq++) {
+		struct irq_data *data;
+		int virq;
+
+		virq = irq_linear_revmap(armada_370_xp_mpic_domain, irq);
+		if (virq == 0)
+			continue;
+
+		data = irq_get_irq_data(virq);
+
+		if (!irq_percpu_is_enabled(virq))
+			continue;
+
+		armada_370_xp_irq_unmask(data);
+	}
+}
+
 static int armada_xp_mpic_starting_cpu(unsigned int cpu)
 {
 	armada_xp_mpic_perf_init();
 	armada_xp_mpic_smp_cpu_init();
+	armada_xp_mpic_reenable_percpu();
 	return 0;
 }
 
 static int mpic_cascaded_starting_cpu(unsigned int cpu)
 {
 	armada_xp_mpic_perf_init();
+	armada_xp_mpic_reenable_percpu();
 	enable_percpu_irq(parent_irq, IRQ_TYPE_NONE);
 	return 0;
 }
@@ -502,16 +603,27 @@ static void armada_370_xp_mpic_resume(void)
 		if (virq == 0)
 			continue;
 
-		if (!is_percpu_irq(irq))
+		data = irq_get_irq_data(virq);
+
+		if (!is_percpu_irq(irq)) {
+			/* Non per-CPU interrupts */
 			writel(irq, per_cpu_int_base +
 			       ARMADA_370_XP_INT_CLEAR_MASK_OFFS);
-		else
+			if (!irqd_irq_disabled(data))
+				armada_370_xp_irq_unmask(data);
+		} else {
+			/* Per-CPU interrupts */
 			writel(irq, main_int_base +
 			       ARMADA_370_XP_INT_SET_ENABLE_OFFS);
 
-		data = irq_get_irq_data(virq);
-		if (!irqd_irq_disabled(data))
-			armada_370_xp_irq_unmask(data);
+			/*
+			 * Re-enable on the current CPU,
+			 * armada_xp_mpic_reenable_percpu() will take
+			 * care of secondary CPUs when they come up.
+			 */
+			if (irq_percpu_is_enabled(virq))
+				armada_370_xp_irq_unmask(data);
+		}
 	}
 
 	/* Reconfigure doorbells for IPIs and MSIs */
@@ -563,7 +675,7 @@ static int __init armada_370_xp_mpic_of_init(struct device_node *node,
 		irq_domain_add_linear(node, nr_irqs,
 				&armada_370_xp_mpic_irq_ops, NULL);
 	BUG_ON(!armada_370_xp_mpic_domain);
-	armada_370_xp_mpic_domain->bus_token = DOMAIN_BUS_WIRED;
+	irq_domain_update_bus_token(armada_370_xp_mpic_domain, DOMAIN_BUS_WIRED);
 
 	/* Setup for the boot CPU */
 	armada_xp_mpic_perf_init();
diff --git a/drivers/irqchip/irq-aspeed-i2c-ic.c b/drivers/irqchip/irq-aspeed-i2c-ic.c
new file mode 100644
index 000000000000..815b88dd18f2
--- /dev/null
+++ b/drivers/irqchip/irq-aspeed-i2c-ic.c
@@ -0,0 +1,115 @@
+/*
+ *  Aspeed 24XX/25XX I2C Interrupt Controller.
+ *
+ *  Copyright (C) 2012-2017 ASPEED Technology Inc.
+ *  Copyright 2017 IBM Corporation
+ *  Copyright 2017 Google, Inc.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2 as
+ *  published by the Free Software Foundation.
+ */
+
+#include <linux/irq.h>
+#include <linux/irqchip.h>
+#include <linux/irqchip/chained_irq.h>
+#include <linux/irqdomain.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/io.h>
+
+
+#define ASPEED_I2C_IC_NUM_BUS 14
+
+struct aspeed_i2c_ic {
+	void __iomem		*base;
+	int			parent_irq;
+	struct irq_domain	*irq_domain;
+};
+
+/*
+ * The aspeed chip provides a single hardware interrupt for all of the I2C
+ * busses, so we use a dummy interrupt chip to translate this single interrupt
+ * into multiple interrupts, each associated with a single I2C bus.
+ */
+static void aspeed_i2c_ic_irq_handler(struct irq_desc *desc)
+{
+	struct aspeed_i2c_ic *i2c_ic = irq_desc_get_handler_data(desc);
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	unsigned long bit, status;
+	unsigned int bus_irq;
+
+	chained_irq_enter(chip, desc);
+	status = readl(i2c_ic->base);
+	for_each_set_bit(bit, &status, ASPEED_I2C_IC_NUM_BUS) {
+		bus_irq = irq_find_mapping(i2c_ic->irq_domain, bit);
+		generic_handle_irq(bus_irq);
+	}
+	chained_irq_exit(chip, desc);
+}
+
+/*
+ * Set simple handler and mark IRQ as valid. Nothing interesting to do here
+ * since we are using a dummy interrupt chip.
+ */
+static int aspeed_i2c_ic_map_irq_domain(struct irq_domain *domain,
+					unsigned int irq, irq_hw_number_t hwirq)
+{
+	irq_set_chip_and_handler(irq, &dummy_irq_chip, handle_simple_irq);
+	irq_set_chip_data(irq, domain->host_data);
+
+	return 0;
+}
+
+static const struct irq_domain_ops aspeed_i2c_ic_irq_domain_ops = {
+	.map = aspeed_i2c_ic_map_irq_domain,
+};
+
+static int __init aspeed_i2c_ic_of_init(struct device_node *node,
+					struct device_node *parent)
+{
+	struct aspeed_i2c_ic *i2c_ic;
+	int ret = 0;
+
+	i2c_ic = kzalloc(sizeof(*i2c_ic), GFP_KERNEL);
+	if (!i2c_ic)
+		return -ENOMEM;
+
+	i2c_ic->base = of_iomap(node, 0);
+	if (IS_ERR(i2c_ic->base)) {
+		ret = PTR_ERR(i2c_ic->base);
+		goto err_free_ic;
+	}
+
+	i2c_ic->parent_irq = irq_of_parse_and_map(node, 0);
+	if (i2c_ic->parent_irq < 0) {
+		ret = i2c_ic->parent_irq;
+		goto err_iounmap;
+	}
+
+	i2c_ic->irq_domain = irq_domain_add_linear(node, ASPEED_I2C_IC_NUM_BUS,
+						   &aspeed_i2c_ic_irq_domain_ops,
+						   NULL);
+	if (!i2c_ic->irq_domain) {
+		ret = -ENOMEM;
+		goto err_iounmap;
+	}
+
+	i2c_ic->irq_domain->name = "aspeed-i2c-domain";
+
+	irq_set_chained_handler_and_data(i2c_ic->parent_irq,
+					 aspeed_i2c_ic_irq_handler, i2c_ic);
+
+	pr_info("i2c controller registered, irq %d\n", i2c_ic->parent_irq);
+
+	return 0;
+
+err_iounmap:
+	iounmap(i2c_ic->base);
+err_free_ic:
+	kfree(i2c_ic);
+	return ret;
+}
+
+IRQCHIP_DECLARE(ast2400_i2c_ic, "aspeed,ast2400-i2c-ic", aspeed_i2c_ic_of_init);
+IRQCHIP_DECLARE(ast2500_i2c_ic, "aspeed,ast2500-i2c-ic", aspeed_i2c_ic_of_init);
diff --git a/drivers/irqchip/irq-aspeed-vic.c b/drivers/irqchip/irq-aspeed-vic.c
index d24451d5bf8a..03ba477ea0d0 100644
--- a/drivers/irqchip/irq-aspeed-vic.c
+++ b/drivers/irqchip/irq-aspeed-vic.c
@@ -186,7 +186,7 @@ static int avic_map(struct irq_domain *d, unsigned int irq,
 	return 0;
 }
 
-static struct irq_domain_ops avic_dom_ops = {
+static const struct irq_domain_ops avic_dom_ops = {
 	.map = avic_map,
 	.xlate = irq_domain_xlate_onetwocell,
 };
@@ -227,4 +227,5 @@ static int __init avic_of_init(struct device_node *node,
 	return 0;
 }
 
-IRQCHIP_DECLARE(aspeed_new_vic, "aspeed,ast2400-vic", avic_of_init);
+IRQCHIP_DECLARE(ast2400_vic, "aspeed,ast2400-vic", avic_of_init);
+IRQCHIP_DECLARE(ast2500_vic, "aspeed,ast2500-vic", avic_of_init);
diff --git a/drivers/irqchip/irq-gic-v2m.c b/drivers/irqchip/irq-gic-v2m.c
index 863e073c6f7f..993a8426a453 100644
--- a/drivers/irqchip/irq-gic-v2m.c
+++ b/drivers/irqchip/irq-gic-v2m.c
@@ -280,7 +280,7 @@ static int gicv2m_allocate_domains(struct irq_domain *parent)
 		return -ENOMEM;
 	}
 
-	inner_domain->bus_token = DOMAIN_BUS_NEXUS;
+	irq_domain_update_bus_token(inner_domain, DOMAIN_BUS_NEXUS);
 	inner_domain->parent = parent;
 	pci_domain = pci_msi_create_irq_domain(v2m->fwnode,
 					       &gicv2m_msi_domain_info,
diff --git a/drivers/irqchip/irq-gic-v3-its-pci-msi.c b/drivers/irqchip/irq-gic-v3-its-pci-msi.c
index aee1c60d7ab5..77931214d954 100644
--- a/drivers/irqchip/irq-gic-v3-its-pci-msi.c
+++ b/drivers/irqchip/irq-gic-v3-its-pci-msi.c
@@ -41,27 +41,22 @@ static struct irq_chip its_msi_irq_chip = {
 	.irq_write_msi_msg	= pci_msi_domain_write_msg,
 };
 
-struct its_pci_alias {
-	struct pci_dev	*pdev;
-	u32		count;
-};
-
-static int its_pci_msi_vec_count(struct pci_dev *pdev)
+static int its_pci_msi_vec_count(struct pci_dev *pdev, void *data)
 {
-	int msi, msix;
+	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 max(msi, msix);
+	return 0;
 }
 
 static int its_get_pci_alias(struct pci_dev *pdev, u16 alias, void *data)
 {
-	struct its_pci_alias *dev_alias = data;
+	struct pci_dev **alias_dev = data;
 
-	if (pdev != dev_alias->pdev)
-		dev_alias->count += its_pci_msi_vec_count(pdev);
+	*alias_dev = pdev;
 
 	return 0;
 }
@@ -69,9 +64,9 @@ static int its_get_pci_alias(struct pci_dev *pdev, u16 alias, void *data)
 static int its_pci_msi_prepare(struct irq_domain *domain, struct device *dev,
 			       int nvec, msi_alloc_info_t *info)
 {
-	struct pci_dev *pdev;
-	struct its_pci_alias dev_alias;
+	struct pci_dev *pdev, *alias_dev;
 	struct msi_domain_info *msi_info;
+	int alias_count = 0;
 
 	if (!dev_is_pci(dev))
 		return -EINVAL;
@@ -79,16 +74,20 @@ static int its_pci_msi_prepare(struct irq_domain *domain, struct device *dev,
 	msi_info = msi_get_domain_info(domain->parent);
 
 	pdev = to_pci_dev(dev);
-	dev_alias.pdev = pdev;
-	dev_alias.count = nvec;
-
-	pci_for_each_dma_alias(pdev, its_get_pci_alias, &dev_alias);
+	/*
+	 * If pdev is downstream of any aliasing bridges, take an upper
+	 * bound of how many other vectors could map to the same DevID.
+	 */
+	pci_for_each_dma_alias(pdev, its_get_pci_alias, &alias_dev);
+	if (alias_dev != pdev && alias_dev->subordinate)
+		pci_walk_bus(alias_dev->subordinate, its_pci_msi_vec_count,
+			     &alias_count);
 
 	/* ITS specific DeviceID, as the core ITS ignores dev. */
 	info->scratchpad[0].ul = pci_msi_domain_get_msi_rid(domain, pdev);
 
 	return msi_info->ops->msi_prepare(domain->parent,
-					  dev, dev_alias.count, info);
+					  dev, max(nvec, alias_count), info);
 }
 
 static struct msi_domain_ops its_pci_msi_ops = {
diff --git a/drivers/irqchip/irq-gic-v3-its-platform-msi.c b/drivers/irqchip/irq-gic-v3-its-platform-msi.c
index 9e9dda33eb17..249240d9a425 100644
--- a/drivers/irqchip/irq-gic-v3-its-platform-msi.c
+++ b/drivers/irqchip/irq-gic-v3-its-platform-msi.c
@@ -86,7 +86,7 @@ static struct msi_domain_info its_pmsi_domain_info = {
 	.chip	= &its_pmsi_irq_chip,
 };
 
-static struct of_device_id its_device_id[] = {
+static const struct of_device_id its_device_id[] = {
 	{	.compatible	= "arm,gic-v3-its",	},
 	{},
 };
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 45ea193325d2..68932873eebc 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -644,9 +644,12 @@ static int its_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 	if (cpu >= nr_cpu_ids)
 		return -EINVAL;
 
-	target_col = &its_dev->its->collections[cpu];
-	its_send_movi(its_dev, target_col, id);
-	its_dev->event_map.col_map[id] = cpu;
+	/* don't set the affinity when the target cpu is same as current one */
+	if (cpu != its_dev->event_map.col_map[id]) {
+		target_col = &its_dev->its->collections[cpu];
+		its_send_movi(its_dev, target_col, id);
+		its_dev->event_map.col_map[id] = cpu;
+	}
 
 	return IRQ_SET_MASK_OK_DONE;
 }
@@ -688,9 +691,11 @@ static struct irq_chip its_irq_chip = {
  */
 #define IRQS_PER_CHUNK_SHIFT	5
 #define IRQS_PER_CHUNK		(1 << IRQS_PER_CHUNK_SHIFT)
+#define ITS_MAX_LPI_NRBITS	16 /* 64K LPIs */
 
 static unsigned long *lpi_bitmap;
 static u32 lpi_chunks;
+static u32 lpi_id_bits;
 static DEFINE_SPINLOCK(lpi_lock);
 
 static int its_lpi_to_chunk(int lpi)
@@ -786,17 +791,13 @@ static void its_lpi_free(struct event_lpi_map *map)
 }
 
 /*
- * We allocate 64kB for PROPBASE. That gives us at most 64K LPIs to
+ * We allocate memory for PROPBASE to cover 2 ^ lpi_id_bits LPIs to
  * deal with (one configuration byte per interrupt). PENDBASE has to
  * be 64kB aligned (one bit per LPI, plus 8192 bits for SPI/PPI/SGI).
  */
-#define LPI_PROPBASE_SZ		SZ_64K
-#define LPI_PENDBASE_SZ		(LPI_PROPBASE_SZ / 8 + SZ_1K)
-
-/*
- * This is how many bits of ID we need, including the useless ones.
- */
-#define LPI_NRBITS		ilog2(LPI_PROPBASE_SZ + SZ_8K)
+#define LPI_NRBITS		lpi_id_bits
+#define LPI_PROPBASE_SZ		ALIGN(BIT(LPI_NRBITS), SZ_64K)
+#define LPI_PENDBASE_SZ		ALIGN(BIT(LPI_NRBITS) / 8, SZ_64K)
 
 #define LPI_PROP_DEFAULT_PRIO	0xa0
 
@@ -804,6 +805,7 @@ static int __init its_alloc_lpi_tables(void)
 {
 	phys_addr_t paddr;
 
+	lpi_id_bits = min_t(u32, gic_rdists->id_bits, ITS_MAX_LPI_NRBITS);
 	gic_rdists->prop_page = alloc_pages(GFP_NOWAIT,
 					   get_order(LPI_PROPBASE_SZ));
 	if (!gic_rdists->prop_page) {
@@ -822,7 +824,7 @@ static int __init its_alloc_lpi_tables(void)
 	/* Make sure the GIC will observe the written configuration */
 	gic_flush_dcache_to_poc(page_address(gic_rdists->prop_page), LPI_PROPBASE_SZ);
 
-	return 0;
+	return its_lpi_init(lpi_id_bits);
 }
 
 static const char *its_base_type_string[] = {
@@ -1097,7 +1099,7 @@ static void its_cpu_init_lpis(void)
 		 * hence the 'max(LPI_PENDBASE_SZ, SZ_64K)' below.
 		 */
 		pend_page = alloc_pages(GFP_NOWAIT | __GFP_ZERO,
-					get_order(max(LPI_PENDBASE_SZ, SZ_64K)));
+					get_order(max_t(u32, LPI_PENDBASE_SZ, SZ_64K)));
 		if (!pend_page) {
 			pr_err("Failed to allocate PENDBASE for CPU%d\n",
 			       smp_processor_id());
@@ -1661,7 +1663,7 @@ static int its_init_domain(struct fwnode_handle *handle, struct its_node *its)
 	}
 
 	inner_domain->parent = its_parent;
-	inner_domain->bus_token = DOMAIN_BUS_NEXUS;
+	irq_domain_update_bus_token(inner_domain, DOMAIN_BUS_NEXUS);
 	inner_domain->flags |= IRQ_DOMAIN_FLAG_MSI_REMAP;
 	info->ops = &its_msi_domain_ops;
 	info->data = its;
@@ -1801,7 +1803,7 @@ int its_cpu_init(void)
 	return 0;
 }
 
-static struct of_device_id its_device_id[] = {
+static const struct of_device_id its_device_id[] = {
 	{	.compatible	= "arm,gic-v3-its",	},
 	{},
 };
@@ -1833,6 +1835,78 @@ static int __init its_of_probe(struct device_node *node)
 
 #define ACPI_GICV3_ITS_MEM_SIZE (SZ_128K)
 
+#if defined(CONFIG_ACPI_NUMA) && (ACPI_CA_VERSION >= 0x20170531)
+struct its_srat_map {
+	/* numa node id */
+	u32	numa_node;
+	/* GIC ITS ID */
+	u32	its_id;
+};
+
+static struct its_srat_map its_srat_maps[MAX_NUMNODES] __initdata;
+static int its_in_srat __initdata;
+
+static int __init acpi_get_its_numa_node(u32 its_id)
+{