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:

   - new core infrastructure to allow better management of multi-queue
     devices (interrupt spreading, node aware descriptor allocation ...)

   - a new interrupt flow handler to support the new fangled Intel VMD
     devices.

   - yet another new interrupt controller driver.

   - a series of fixes which addresses sparse warnings, missing
     includes, missing static declarations etc from Ben Dooks.

   - a fix for the error handling in the hierarchical domain allocation
     code.

   - the usual pile of small updates to core and driver code"

* 'irq-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (46 commits)
  genirq: Fix missing irq allocation affinity hint
  irqdomain: Fix irq_domain_alloc_irqs_recursive() error handling
  irq/Documentation: Correct result of echnoing 5 to smp_affinity
  MAINTAINERS: Remove Jiang Liu from irq domains
  genirq/msi: Fix broken debug output
  genirq: Add a helper to spread an affinity mask for MSI/MSI-X vectors
  genirq/msi: Make use of affinity aware allocations
  genirq: Use affinity hint in irqdesc allocation
  genirq: Add affinity hint to irq allocation
  genirq: Introduce IRQD_AFFINITY_MANAGED flag
  genirq/msi: Remove unused MSI_FLAG_IDENTITY_MAP
  irqchip/s3c24xx: Fixup IO accessors for big endian
  irqchip/exynos-combiner: Fix usage of __raw IO
  irqdomain: Fix disposal of mappings for interrupt hierarchies
  irqchip/aspeed-vic: Add irq controller for Aspeed
  doc/devicetree: Add Aspeed VIC bindings
  x86/PCI/VMD: Use untracked irq handler
  genirq: Add untracked irq handler
  irqchip/mips-gic: Populate irq_domain names
  irqchip/gicv3-its: Implement two-level(indirect) device table support
  ...

Documentation/devicetree/bindings/interrupt-controller/arm,gic.txt

@@ -21,6 +21,7 @@ Main node required properties:
 	"arm,pl390"
 	"arm,tc11mp-gic"
 	"brcm,brahma-b15-gic"
+	"nvidia,tegra210-agic"
 	"qcom,msm-8660-qgic"
 	"qcom,msm-qgic2"
 - interrupt-controller : Identifies the node as an interrupt controller
@@ -68,7 +69,7 @@ Optional
 	"ic_clk" (for "arm,arm11mp-gic")
 	"PERIPHCLKEN" (for "arm,cortex-a15-gic")
 	"PERIPHCLK", "PERIPHCLKEN" (for "arm,cortex-a9-gic")
-	"clk" (for "arm,gic-400")
+	"clk" (for "arm,gic-400" and "nvidia,tegra210")
 	"gclk" (for "arm,pl390")
 
 - power-domains : A phandle and PM domain specifier as defined by bindings of

Documentation/devicetree/bindings/interrupt-controller/aspeed,ast2400-vic.txt

+Aspeed Vectored Interrupt Controller
+
+These bindings are for the Aspeed AST2400 interrupt controller register layout.
+The SoC has an legacy register layout, but this driver does not support that
+mode of operation.
+
+Required properties:
+
+- compatible : should be "aspeed,ast2400-vic".
+
+- interrupt-controller : Identifies the node as an interrupt controller
+- #interrupt-cells : Specifies the number of cells needed to encode an
+  interrupt source. The value shall be 1.
+
+Example:
+
+ vic: interrupt-controller@1e6c0080 {
+      compatible = "aspeed,ast2400-vic";
+      interrupt-controller;
+      #interrupt-cells = <1>;
+      reg = <0x1e6c0080 0x80>;
+ };

Documentation/filesystems/proc.txt

@@ -725,7 +725,7 @@ IRQ, you can set it by doing:
   > echo 1 > /proc/irq/10/smp_affinity
 
 This means that only the first CPU will handle the IRQ, but you can also echo
-5 which means that only the first and fourth CPU can handle the IRQ.
+5 which means that only the first and third CPU can handle the IRQ.
 
 The contents of each smp_affinity file is the same by default:
 

MAINTAINERS

@@ -6235,7 +6235,6 @@ F:	Documentation/devicetree/bindings/interrupt-controller/
 F:	drivers/irqchip/
 
 IRQ DOMAINS (IRQ NUMBER MAPPING LIBRARY)
-M:	Jiang Liu <jiang.liu@linux.intel.com>
 M:	Marc Zyngier <marc.zyngier@arm.com>
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git irq/core

arch/sparc/kernel/irq_64.c

@@ -242,7 +242,7 @@ unsigned int irq_alloc(unsigned int dev_handle, unsigned int dev_ino)
 {
 	int irq;
 
-	irq = __irq_alloc_descs(-1, 1, 1, numa_node_id(), NULL);
+	irq = __irq_alloc_descs(-1, 1, 1, numa_node_id(), NULL, NULL);
 	if (irq <= 0)
 		goto out;
 

arch/x86/kernel/apic/io_apic.c

@@ -981,7 +981,7 @@ static int alloc_irq_from_domain(struct irq_domain *domain, int ioapic, u32 gsi,
 
 	return __irq_domain_alloc_irqs(domain, irq, 1,
 				       ioapic_alloc_attr_node(info),
-				       info, legacy);
+				       info, legacy, NULL);
 }
 
 /*
@@ -1014,7 +1014,8 @@ static int alloc_isa_irq_from_domain(struct irq_domain *domain,
 					  info->ioapic_pin))
 			return -ENOMEM;
 	} else {
-		irq = __irq_domain_alloc_irqs(domain, irq, 1, node, info, true);
+		irq = __irq_domain_alloc_irqs(domain, irq, 1, node, info, true,
+					      NULL);
 		if (irq >= 0) {
 			irq_data = irq_domain_get_irq_data(domain, irq);
 			data = irq_data->chip_data;

arch/x86/pci/vmd.c

@@ -195,7 +195,7 @@ static int vmd_msi_init(struct irq_domain *domain, struct msi_domain_info *info,
 	vmdirq->virq = virq;
 
 	irq_domain_set_info(domain, virq, vmdirq->irq->vmd_vector, info->chip,
-			    vmdirq, handle_simple_irq, vmd, NULL);
+			    vmdirq, handle_untracked_irq, vmd, NULL);
 	return 0;
 }
 

drivers/irqchip/Kconfig

@@ -8,6 +8,12 @@ config ARM_GIC
 	select IRQ_DOMAIN_HIERARCHY
 	select MULTI_IRQ_HANDLER
 
+config ARM_GIC_PM
+	bool
+	depends on PM
+	select ARM_GIC
+	select PM_CLK
+
 config ARM_GIC_MAX_NR
 	int
 	default 2 if ARCH_REALVIEW

drivers/irqchip/Makefile

@@ -24,6 +24,7 @@ obj-$(CONFIG_ARCH_SUNXI)		+= irq-sun4i.o
 obj-$(CONFIG_ARCH_SUNXI)		+= irq-sunxi-nmi.o
 obj-$(CONFIG_ARCH_SPEAR3XX)		+= spear-shirq.o
 obj-$(CONFIG_ARM_GIC)			+= irq-gic.o irq-gic-common.o
+obj-$(CONFIG_ARM_GIC_PM)		+= irq-gic-pm.o
 obj-$(CONFIG_REALVIEW_DT)		+= irq-gic-realview.o
 obj-$(CONFIG_ARM_GIC_V2M)		+= irq-gic-v2m.o
 obj-$(CONFIG_ARM_GIC_V3)		+= irq-gic-v3.o irq-gic-common.o
@@ -69,3 +70,4 @@ obj-$(CONFIG_PIC32_EVIC)		+= irq-pic32-evic.o
 obj-$(CONFIG_MVEBU_ODMI)		+= irq-mvebu-odmi.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

drivers/irqchip/exynos-combiner.c

@@ -55,14 +55,14 @@ static void combiner_mask_irq(struct irq_data *data)
 {
 	u32 mask = 1 << (data->hwirq % 32);
 
-	__raw_writel(mask, combiner_base(data) + COMBINER_ENABLE_CLEAR);
+	writel_relaxed(mask, combiner_base(data) + COMBINER_ENABLE_CLEAR);
 }
 
 static void combiner_unmask_irq(struct irq_data *data)
 {
 	u32 mask = 1 << (data->hwirq % 32);
 
-	__raw_writel(mask, combiner_base(data) + COMBINER_ENABLE_SET);
+	writel_relaxed(mask, combiner_base(data) + COMBINER_ENABLE_SET);
 }
 
 static void combiner_handle_cascade_irq(struct irq_desc *desc)
@@ -75,7 +75,7 @@ static void combiner_handle_cascade_irq(struct irq_desc *desc)
 	chained_irq_enter(chip, desc);
 
 	spin_lock(&irq_controller_lock);
-	status = __raw_readl(chip_data->base + COMBINER_INT_STATUS);
+	status = readl_relaxed(chip_data->base + COMBINER_INT_STATUS);
 	spin_unlock(&irq_controller_lock);
 	status &= chip_data->irq_mask;
 
@@ -135,7 +135,7 @@ static void __init combiner_init_one(struct combiner_chip_data *combiner_data,
 	combiner_data->parent_irq = irq;
 
 	/* Disable all interrupts */
-	__raw_writel(combiner_data->irq_mask, base + COMBINER_ENABLE_CLEAR);
+	writel_relaxed(combiner_data->irq_mask, base + COMBINER_ENABLE_CLEAR);
 }
 
 static int combiner_irq_domain_xlate(struct irq_domain *d,
@@ -218,7 +218,7 @@ static int combiner_suspend(void)
 
 	for (i = 0; i < max_nr; i++)
 		combiner_data[i].pm_save =
-			__raw_readl(combiner_data[i].base + COMBINER_ENABLE_SET);
+			readl_relaxed(combiner_data[i].base + COMBINER_ENABLE_SET);
 
 	return 0;
 }
@@ -235,9 +235,9 @@ static void combiner_resume(void)
 	int i;
 
 	for (i = 0; i < max_nr; i++) {
-		__raw_writel(combiner_data[i].irq_mask,
+		writel_relaxed(combiner_data[i].irq_mask,
 			     combiner_data[i].base + COMBINER_ENABLE_CLEAR);
-		__raw_writel(combiner_data[i].pm_save,
+		writel_relaxed(combiner_data[i].pm_save,
 			     combiner_data[i].base + COMBINER_ENABLE_SET);
 	}
 }

drivers/irqchip/irq-armada-370-xp.c

@@ -541,7 +541,7 @@ static void armada_370_xp_mpic_resume(void)
 		writel(1, per_cpu_int_base + ARMADA_370_XP_INT_CLEAR_MASK_OFFS);
 }
 
-struct syscore_ops armada_370_xp_mpic_syscore_ops = {
+static struct syscore_ops armada_370_xp_mpic_syscore_ops = {
 	.suspend	= armada_370_xp_mpic_suspend,
 	.resume		= armada_370_xp_mpic_resume,
 };

drivers/irqchip/irq-aspeed-vic.c

+/*
+ *  Copyright (C) 2015 - Ben Herrenschmidt, IBM Corp.
+ *
+ *  Driver for Aspeed "new" VIC as found in SoC generation 3 and later
+ *
+ *  Based on irq-vic.c:
+ *
+ *  Copyright (C) 1999 - 2003 ARM Limited
+ *  Copyright (C) 2000 Deep Blue Solutions Ltd
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/export.h>
+#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/irqchip.h>
+#include <linux/irqchip/chained_irq.h>
+#include <linux/irqdomain.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/syscore_ops.h>
+#include <linux/device.h>
+#include <linux/slab.h>
+
+#include <asm/exception.h>
+#include <asm/irq.h>
+
+/* These definitions correspond to the "new mapping" of the
+ * register set that interleaves "high" and "low". The offsets
+ * below are for the "low" register, add 4 to get to the high one
+ */
+#define AVIC_IRQ_STATUS		0x00
+#define AVIC_FIQ_STATUS		0x08
+#define AVIC_RAW_STATUS		0x10
+#define AVIC_INT_SELECT		0x18
+#define AVIC_INT_ENABLE		0x20
+#define AVIC_INT_ENABLE_CLR	0x28
+#define AVIC_INT_TRIGGER	0x30
+#define AVIC_INT_TRIGGER_CLR	0x38
+#define AVIC_INT_SENSE		0x40
+#define AVIC_INT_DUAL_EDGE	0x48
+#define AVIC_INT_EVENT		0x50
+#define AVIC_EDGE_CLR		0x58
+#define AVIC_EDGE_STATUS	0x60
+
+#define NUM_IRQS		64
+
+struct aspeed_vic {
+	void __iomem		*base;
+	u32			edge_sources[2];
+	struct irq_domain	*dom;
+};
+static struct aspeed_vic *system_avic;
+
+static void vic_init_hw(struct aspeed_vic *vic)
+{
+	u32 sense;
+
+	/* Disable all interrupts */
+	writel(0xffffffff, vic->base + AVIC_INT_ENABLE_CLR);
+	writel(0xffffffff, vic->base + AVIC_INT_ENABLE_CLR + 4);
+
+	/* Make sure no soft trigger is on */
+	writel(0xffffffff, vic->base + AVIC_INT_TRIGGER_CLR);
+	writel(0xffffffff, vic->base + AVIC_INT_TRIGGER_CLR + 4);
+
+	/* Set everything to be IRQ */
+	writel(0, vic->base + AVIC_INT_SELECT);
+	writel(0, vic->base + AVIC_INT_SELECT + 4);
+
+	/* Some interrupts have a programable high/low level trigger
+	 * (4 GPIO direct inputs), for now we assume this was configured
+	 * by firmware. We read which ones are edge now.
+	 */
+	sense = readl(vic->base + AVIC_INT_SENSE);
+	vic->edge_sources[0] = ~sense;
+	sense = readl(vic->base + AVIC_INT_SENSE + 4);
+	vic->edge_sources[1] = ~sense;
+
+	/* Clear edge detection latches */
+	writel(0xffffffff, vic->base + AVIC_EDGE_CLR);
+	writel(0xffffffff, vic->base + AVIC_EDGE_CLR + 4);
+}
+
+static void __exception_irq_entry avic_handle_irq(struct pt_regs *regs)
+{
+	struct aspeed_vic *vic = system_avic;
+	u32 stat, irq;
+
+	for (;;) {
+		irq = 0;
+		stat = readl_relaxed(vic->base + AVIC_IRQ_STATUS);
+		if (!stat) {
+			stat = readl_relaxed(vic->base + AVIC_IRQ_STATUS + 4);
+			irq = 32;
+		}
+		if (stat == 0)
+			break;
+		irq += ffs(stat) - 1;
+		handle_domain_irq(vic->dom, irq, regs);
+	}
+}
+
+static void avic_ack_irq(struct irq_data *d)
+{
+	struct aspeed_vic *vic = irq_data_get_irq_chip_data(d);
+	unsigned int sidx = d->hwirq >> 5;
+	unsigned int sbit = 1u << (d->hwirq & 0x1f);
+
+	/* Clear edge latch for edge interrupts, nop for level */
+	if (vic->edge_sources[sidx] & sbit)
+		writel(sbit, vic->base + AVIC_EDGE_CLR + sidx * 4);
+}
+
+static void avic_mask_irq(struct irq_data *d)
+{
+	struct aspeed_vic *vic = irq_data_get_irq_chip_data(d);
+	unsigned int sidx = d->hwirq >> 5;
+	unsigned int sbit = 1u << (d->hwirq & 0x1f);
+
+	writel(sbit, vic->base + AVIC_INT_ENABLE_CLR + sidx * 4);
+}
+
+static void avic_unmask_irq(struct irq_data *d)
+{
+	struct aspeed_vic *vic = irq_data_get_irq_chip_data(d);
+	unsigned int sidx = d->hwirq >> 5;
+	unsigned int sbit = 1u << (d->hwirq & 0x1f);
+
+	writel(sbit, vic->base + AVIC_INT_ENABLE + sidx * 4);
+}
+
+/* For level irq, faster than going through a nop "ack" and mask */
+static void avic_mask_ack_irq(struct irq_data *d)
+{
+	struct aspeed_vic *vic = irq_data_get_irq_chip_data(d);
+	unsigned int sidx = d->hwirq >> 5;
+	unsigned int sbit = 1u << (d->hwirq & 0x1f);
+
+	/* First mask */
+	writel(sbit, vic->base + AVIC_INT_ENABLE_CLR + sidx * 4);
+
+	/* Then clear edge latch for edge interrupts */
+	if (vic->edge_sources[sidx] & sbit)
+		writel(sbit, vic->base + AVIC_EDGE_CLR + sidx * 4);
+}
+
+static struct irq_chip avic_chip = {
+	.name		= "AVIC",
+	.irq_ack	= avic_ack_irq,
+	.irq_mask	= avic_mask_irq,
+	.irq_unmask	= avic_unmask_irq,
+	.irq_mask_ack	= avic_mask_ack_irq,
+};
+
+static int avic_map(struct irq_domain *d, unsigned int irq,
+		    irq_hw_number_t hwirq)
+{
+	struct aspeed_vic *vic = d->host_data;
+	unsigned int sidx = hwirq >> 5;
+	unsigned int sbit = 1u << (hwirq & 0x1f);
+
+	/* Check if interrupt exists */
+	if (sidx > 1)
+		return -EPERM;
+
+	if (vic->edge_sources[sidx] & sbit)
+		irq_set_chip_and_handler(irq, &avic_chip, handle_edge_irq);
+	else
+		irq_set_chip_and_handler(irq, &avic_chip, handle_level_irq);
+	irq_set_chip_data(irq, vic);
+	irq_set_probe(irq);
+	return 0;
+}
+
+static struct irq_domain_ops avic_dom_ops = {
+	.map = avic_map,
+	.xlate = irq_domain_xlate_onetwocell,
+};
+
+static int __init avic_of_init(struct device_node *node,
+			       struct device_node *parent)
+{
+	void __iomem *regs;
+	struct aspeed_vic *vic;
+
+	if (WARN(parent, "non-root Aspeed VIC not supported"))
+		return -EINVAL;
+	if (WARN(system_avic, "duplicate Aspeed VIC not supported"))
+		return -EINVAL;
+
+	regs = of_iomap(node, 0);
+	if (WARN_ON(!regs))
+		return -EIO;
+
+	vic = kzalloc(sizeof(struct aspeed_vic), GFP_KERNEL);
+	if (WARN_ON(!vic)) {
+		iounmap(regs);
+		return -ENOMEM;
+	}
+	vic->base = regs;
+
+	/* Initialize soures, all masked */
+	vic_init_hw(vic);
+
+	/* Ready to receive interrupts */
+	system_avic = vic;
+	set_handle_irq(avic_handle_irq);
+
+	/* Register our domain */
+	vic->dom = irq_domain_add_simple(node, NUM_IRQS, 0,
+					 &avic_dom_ops, vic);
+
+	return 0;
+}
+
+IRQCHIP_DECLARE(aspeed_new_vic, "aspeed,ast2400-vic", avic_of_init);

drivers/irqchip/irq-bcm2835.c

@@ -52,7 +52,6 @@
 #include <linux/irqdomain.h>
 
 #include <asm/exception.h>
-#include <asm/mach/irq.h>
 
 /* Put the bank and irq (32 bits) into the hwirq */
 #define MAKE_HWIRQ(b, n)	((b << 5) | (n))
@@ -242,7 +241,7 @@ static void __exception_irq_entry bcm2835_handle_irq(
 	u32 hwirq;
 
 	while ((hwirq = get_next_armctrl_hwirq()) != ~0)
-		handle_IRQ(irq_linear_revmap(intc.domain, hwirq), regs);
+		handle_domain_irq(intc.domain, hwirq, regs);
 }
 
 static void bcm2836_chained_handle_irq(struct irq_desc *desc)

drivers/irqchip/irq-bcm2836.c

@@ -180,7 +180,7 @@ __exception_irq_entry bcm2836_arm_irqchip_handle_irq(struct pt_regs *regs)
 	} else if (stat) {
 		u32 hwirq = ffs(stat) - 1;
 
-		handle_IRQ(irq_linear_revmap(intc.domain, hwirq), regs);
+		handle_domain_irq(intc.domain, hwirq, regs);
 	}
 }
 
@@ -224,7 +224,7 @@ static struct notifier_block bcm2836_arm_irqchip_cpu_notifier = {
 };
 
 #ifdef CONFIG_ARM
-int __init bcm2836_smp_boot_secondary(unsigned int cpu,
+static int __init bcm2836_smp_boot_secondary(unsigned int cpu,
 					     struct task_struct *idle)
 {
 	unsigned long secondary_startup_phys =

drivers/irqchip/irq-bcm7120-l2.c

@@ -215,7 +215,7 @@ static int __init bcm7120_l2_intc_iomap_3380(struct device_node *dn,
 	return 0;
 }
 
-int __init bcm7120_l2_intc_probe(struct device_node *dn,
+static int __init bcm7120_l2_intc_probe(struct device_node *dn,
 				 struct device_node *parent,
 				 int (*iomap_regs_fn)(struct device_node *,
 					struct bcm7120_l2_intc_data *),
@@ -339,14 +339,14 @@ int __init bcm7120_l2_intc_probe(struct device_node *dn,
 	return ret;
 }
 
-int __init bcm7120_l2_intc_probe_7120(struct device_node *dn,
+static int __init bcm7120_l2_intc_probe_7120(struct device_node *dn,
 					     struct device_node *parent)
 {
 	return bcm7120_l2_intc_probe(dn, parent, bcm7120_l2_intc_iomap_7120,
 				     "BCM7120 L2");
 }
 
-int __init bcm7120_l2_intc_probe_3380(struct device_node *dn,
+static int __init bcm7120_l2_intc_probe_3380(struct device_node *dn,
 					     struct device_node *parent)
 {
 	return bcm7120_l2_intc_probe(dn, parent, bcm7120_l2_intc_iomap_3380,

drivers/irqchip/irq-brcmstb-l2.c

@@ -112,7 +112,7 @@ static void brcmstb_l2_intc_resume(struct irq_data *d)
 	irq_gc_unlock(gc);
 }
 
-int __init brcmstb_l2_intc_of_init(struct device_node *np,
+static int __init brcmstb_l2_intc_of_init(struct device_node *np,
 					  struct device_node *parent)
 {
 	unsigned int clr = IRQ_NOREQUEST | IRQ_NOPROBE | IRQ_NOAUTOEN;

drivers/irqchip/irq-gic-common.c

@@ -90,7 +90,7 @@ int gic_configure_irq(unsigned int irq, unsigned int type,
 	return ret;
 }
 
-void __init gic_dist_config(void __iomem *base, int gic_irqs,
+void gic_dist_config(void __iomem *base, int gic_irqs,
 		     void (*sync_access)(void))
 {
 	unsigned int i;

drivers/irqchip/irq-gic-pm.c

+/*
+ * Copyright (C) 2016 NVIDIA CORPORATION, All Rights Reserved.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+#include <linux/module.h>
+#include <linux/clk.h>
+#include <linux/of_device.h>
+#include <linux/of_irq.h>
+#include <linux/irqchip/arm-gic.h>
+#include <linux/platform_device.h>
+#include <linux/pm_clock.h>
+#include <linux/pm_runtime.h>
+#include <linux/slab.h>
+
+struct gic_clk_data {
+	unsigned int num_clocks;
+	const char *const *clocks;
+};
+
+static int gic_runtime_resume(struct device *dev)
+{
+	struct gic_chip_data *gic = dev_get_drvdata(dev);
+	int ret;
+
+	ret = pm_clk_resume(dev);
+	if (ret)
+		return ret;
+
+	/*
+	 * On the very first resume, the pointer to the driver data
+	 * will be NULL and this is intentional, because we do not
+	 * want to restore the GIC on the very first resume. So if
+	 * the pointer is not valid just return.
+	 */
+	if (!gic)
+		return 0;
+
+	gic_dist_restore(gic);
+	gic_cpu_restore(gic);
+
+	return 0;
+}
+
+static int gic_runtime_suspend(struct device *dev)
+{
+	struct gic_chip_data *gic = dev_get_drvdata(dev);
+
+	gic_dist_save(gic);
+	gic_cpu_save(gic);
+
+	return pm_clk_suspend(dev);
+}
+
+static int gic_get_clocks(struct device *dev, const struct gic_clk_data *data)
+{
+	struct clk *clk;
+	unsigned int i;
+	int ret;
+
+	if (!dev || !data)
+		return -EINVAL;
+
+	ret = pm_clk_create(dev);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < data->num_clocks; i++) {
+		clk = of_clk_get_by_name(dev->of_node, data->clocks[i]);
+		if (IS_ERR(clk)) {
+			dev_err(dev, "failed to get clock %s\n",
+				data->clocks[i]);
+			ret = PTR_ERR(clk);
+			goto error;
+		}
+
+		ret = pm_clk_add_clk(dev, clk);
+		if (ret) {
+			dev_err(dev, "failed to add clock at index %d\n", i);
+			clk_put(clk);
+			goto error;
+		}
+	}
+
+	return 0;
+
+error:
+	pm_clk_destroy(dev);
+
+	return ret;
+}
+
+static int gic_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	const struct gic_clk_data *data;
+	struct gic_chip_data *gic;
+	int ret, irq;
+
+	data = of_device_get_match_data(&pdev->dev);
+	if (!data) {
+		dev_err(&pdev->dev, "no device match found\n");
+		return -ENODEV;
+	}
+
+	irq = irq_of_parse_and_map(dev->of_node, 0);
+	if (!irq) {
+		dev_err(dev, "no parent interrupt found!\n");
+		return -EINVAL;
+	}
+
+	ret = gic_get_clocks(dev, data);
+	if (ret)
+		goto irq_dispose;
+
+	pm_runtime_enable(dev);
+
+	ret = pm_runtime_get_sync(dev);
+	if (ret < 0)
+		goto rpm_disable;
+
+	ret = gic_of_init_child(dev, &gic, irq);
+	if (ret)
+		goto rpm_put;
+
+	platform_set_drvdata(pdev, gic);
+
+	pm_runtime_put(dev);
+
+	dev_info(dev, "GIC IRQ controller registered\n");
+
+	return 0;
+
+rpm_put:
+	pm_runtime_put_sync(dev);
+rpm_disable:
+	pm_runtime_disable(dev);
+	pm_clk_destroy(dev);
+irq_dispose:
+	irq_dispose_mapping(irq);
+
+	return ret;
+}
+
+static const struct dev_pm_ops gic_pm_ops = {
+	SET_RUNTIME_PM_OPS(gic_runtime_suspend,
+			   gic_runtime_resume, NULL)
+};
+
+static const char * const gic400_clocks[] = {
+	"clk",
+};
+
+static const struct gic_clk_data gic400_data = {
+	.num_clocks = ARRAY_SIZE(gic400_clocks),
+	.clocks = gic400_clocks,
+};
+
+static const struct of_device_id gic_match[] = {
+	{ .compatible = "nvidia,tegra210-agic",	.data = &gic400_data },
+	{},
+};
+MODULE_DEVICE_TABLE(of, gic_match);
+
+static struct platform_driver gic_driver = {
+	.probe		= gic_probe,
+	.driver		= {
+		.name	= "gic",
+		.of_match_table	= gic_match,
+		.pm	= &gic_pm_ops,
+	}
+};
+
+builtin_platform_driver(gic_driver);

drivers/irqchip/irq-gic-v2m.c

@@ -24,6 +24,7 @@
 #include <linux/of_pci.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
+#include <linux/irqchip/arm-gic.h>
 
 /*
 * MSI_TYPER:

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

@@ -56,13 +56,14 @@ struct its_collection {
 };
 
 /*
- * The ITS_BASER structure - contains memory information and cached
- * value of BASER register configuration.
+ * The ITS_BASER structure - contains memory information, cached
+ * value of BASER register configuration and ITS page size.
  */
 struct its_baser {
 	void		*base;
 	u64		val;
 	u32		order;
+	u32		psz;
 };
 
 /*
@@ -824,106 +825,58 @@ static const char *its_base_type_string[] = {
 	[GITS_BASER_TYPE_RESERVED7] 	= "Reserved (7)",
 };
 
-static void its_free_tables(struct its_node *its)
+static u64 its_read_baser(struct its_node *its, struct its_baser *baser)
 {
-	int i;
+	u32 idx = baser - its->tables;
 
-	for (i = 0; i < GITS_BASER_NR_REGS; i++) {
-		if (its->tables[i].base) {
-			free_pages((unsigned long)its->tables[i].base,
-				   its->tables[i].order);
-			its->tables[i].base = NULL;
-		}
-	}
+	return readq_relaxed(its->base + GITS_BASER + (idx << 3));
 }
 
-static int its_alloc_tables(const char *node_name, struct its_node *its)
+static void its_write_baser(struct its_node *its, struct its_baser *baser,
+			    u64 val)
 {
-	int err;
-	int i;
-	int psz = SZ_64K;
-	u64 shr = GITS_BASER_InnerShareable;
-	u64 cache;
-	u64 typer;
-	u32 ids;
-
-	if (its->flags & ITS_FLAGS_WORKAROUND_CAVIUM_22375) {
-		/*
-		 * erratum 22375: only alloc 8MB table size
-		 * erratum 24313: ignore memory access type
-		 */
-		cache	= 0;
-		ids	= 0x14;			/* 20 bits, 8MB */
-	} else {
-		cache	= GITS_BASER_WaWb;
-		typer	= readq_relaxed(its->base + GITS_TYPER);
-		ids	= GITS_TYPER_DEVBITS(typer);
-	}
+	u32 idx = baser - its->tables;
 
-	its->device_ids = ids;
+	writeq_relaxed(val, its->base + GITS_BASER + (idx << 3));
+	baser->val = its_read_baser(its, baser);
+}
 
-	for (i = 0; i < GITS_BASER_NR_REGS; i++) {
-		u64 val = readq_relaxed(its->base + GITS_BASER + i * 8);
+static int its_setup_baser(struct its_node *its, struct its_baser *baser,
+			   u64 cache, u64 shr, u32 psz, u32 order,
+			   bool indirect)
+{
+	u64 val = its_read_baser(its, baser);
+	u64 esz = GITS_BASER_ENTRY_SIZE(val);
 	u64 type = GITS_BASER_TYPE(val);
-		u64 entry_size = GITS_BASER_ENTRY_SIZE(val);
-		int order = get_order(psz);
-		int alloc_pages;
-		u64 tmp;
+	u32 alloc_pages;
 	void *base;
-
-		if (type == GITS_BASER_TYPE_NONE)
-			continue;
-
-		/*
-		 * Allocate as many entries as required to fit the
-		 * range of device IDs that the ITS can grok... The ID
-		 * space being incredibly sparse, this results in a
-		 * massive waste of memory.
-		 *
-		 * For other tables, only allocate a single page.
-		 */
-		if (type == GITS_BASER_TYPE_DEVICE) {
-			/*
-			 * 'order' was initialized earlier to the default page
-			 * granule of the the ITS.  We can't have an allocation
-			 * smaller than that.  If the requested allocation
-			 * is smaller, round up to the default page granule.
-			 */
-			order = max(get_order((1UL << ids) * entry_size),
-				    order);
-			if (order >= MAX_ORDER) {
-				order = MAX_ORDER - 1;
-				pr_warn("%s: Device Table too large, reduce its page order to %u\n",
-					node_name, order);
-			}
-		}
+	u64 tmp;
 
 retry_alloc_baser:
 	alloc_pages = (PAGE_ORDER_TO_SIZE(order) / psz);
 	if (alloc_pages > GITS_BASER_PAGES_MAX) {
+		pr_warn("ITS@%pa: %s too large, reduce ITS pages %u->%u\n",
+			&its->phys_base, its_base_type_string[type],
+			alloc_pages, GITS_BASER_PAGES_MAX);
 		alloc_pages = GITS_BASER_PAGES_MAX;
 		order = get_order(GITS_BASER_PAGES_MAX * psz);
-			pr_warn("%s: Device Table too large, reduce its page order to %u (%u pages)\n",
-				node_name, order, alloc_pages);
 	}
 
 	base = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, order);
-		if (!base) {
-			err = -ENOMEM;
-			goto out_free;
-		}
-
-		its->tables[i].base = base;
-		its->tables[i].order = order;
+	if (!base)
+		return -ENOMEM;
 
 retry_baser:
 	val = (virt_to_phys(base)				 |
 		(type << GITS_BASER_TYPE_SHIFT)			 |
-		       ((entry_size - 1) << GITS_BASER_ENTRY_SIZE_SHIFT) |
+		((esz - 1) << GITS_BASER_ENTRY_SIZE_SHIFT)	 |
+		((alloc_pages - 1) << GITS_BASER_PAGES_SHIFT)	 |
 		cache						 |
 		shr						 |
 		GITS_BASER_VALID);
 
+	val |=	indirect ? GITS_BASER_INDIRECT : 0x0;
+
 	switch (psz) {
 	case SZ_4K:
 		val |= GITS_BASER_PAGE_SIZE_4K;
@@ -936,11 +889,8 @@ static int its_alloc_tables(const char *node_name, struct its_node *its)
 		break;
 	}
 
-		val |= alloc_pages - 1;
-		its->tables[i].val = val;
-
-		writeq_relaxed(val, its->base + GITS_BASER + i * 8);
-		tmp = readq_relaxed(its->base + GITS_BASER + i * 8);
+	its_write_baser(its, baser, val);
+	tmp = baser->val;
 
 	if ((val ^ tmp) & GITS_BASER_SHAREABILITY_MASK) {
 		/*
@@ -965,7 +915,7 @@ static int its_alloc_tables(const char *node_name, struct its_node *its)
 		 * something is horribly wrong...
 		 */
 		free_pages((unsigned long)base, order);
-			its->tables[i].base = NULL;
+		baser->base = NULL;
 
 		switch (psz) {
 		case SZ_16K:
@@ -978,26 +928,138 @@ static int its_alloc_tables(const char *node_name, struct its_node *its)
 	}
 
 	if (val != tmp) {
-			pr_err("ITS: %s: GITS_BASER%d doesn't stick: %lx %lx\n",
-			       node_name, i,
+		pr_err("ITS@%pa: %s doesn't stick: %lx %lx\n",
+		       &its->phys_base, its_base_type_string[type],
 		       (unsigned long) val, (unsigned long) tmp);
-			err = -ENXIO;
-			goto out_free;
+		free_pages((unsigned long)base, order);
+		return -ENXIO;
 	}
 
-		pr_info("ITS: allocated %d %s @%lx (psz %dK, shr %d)\n",
-			(int)(PAGE_ORDER_TO_SIZE(order) / entry_size),
+	baser->order = order;
+	baser->base = base;
+	baser->psz = psz;
+	tmp = indirect ? GITS_LVL1_ENTRY_SIZE : esz;
+
+	pr_info("ITS@%pa: allocated %d %s @%lx (%s, esz %d, psz %dK, shr %d)\n",
+		&its->phys_base, (int)(PAGE_ORDER_TO_SIZE(order) / tmp),
 		its_base_type_string[type],
 		(unsigned long)virt_to_phys(base),
+		indirect ? "indirect" : "flat", (int)esz,
 		psz / SZ_1K, (int)shr >> GITS_BASER_SHAREABILITY_SHIFT);
-	}
 
 	return 0;
+}
 
-out_free:
-	its_free_tables(its);
+static bool its_parse_baser_device(struct its_node *its, struct its_baser *baser,
+				   u32 psz, u32 *order)
+{
+	u64 esz = GITS_BASER_ENTRY_SIZE(its_read_baser(its, baser));
+	u64 val = GITS_BASER_InnerShareable | GITS_BASER_WaWb;
+	u32 ids = its->device_ids;
+	u32 new_order = *order;
+	bool indirect = false;
+
+	/* No need to enable Indirection if memory requirement < (psz*2)bytes */
+	if ((esz << ids) > (psz * 2)) {
+		/*
+		 * Find out whether hw supports a single or two-level table by
+		 * table by reading bit at offset '62' after writing '1' to it.
+		 */
+		its_write_baser(its, baser, val | GITS_BASER_INDIRECT);
+		indirect = !!(baser->val & GITS_BASER_INDIRECT);
+
+		if (indirect) {
+			/*
+			 * The size of the lvl2 table is equal to ITS page size
+			 * which is 'psz'. For computing lvl1 table size,
+			 * subtract ID bits that sparse lvl2 table from 'ids'
+			 * which is reported by ITS hardware times lvl1 table
+			 * entry size.
+			 */
+			ids -= ilog2(psz / esz);
+			esz = GITS_LVL1_ENTRY_SIZE;
+		}
+	}
+
+	/*
+	 * Allocate as many entries as required to fit the
+	 * range of device IDs that the ITS can grok... The ID
+	 * space being incredibly sparse, this results in a
+	 * massive waste of memory if two-level device table
+	 * feature is not supported by hardware.
+	 */
+	new_order = max_t(u32, get_order(esz << ids), new_order);
+	if (new_order >= MAX_ORDER) {
+		new_order = MAX_ORDER - 1;
+		ids = ilog2(PAGE_ORDER_TO_SIZE(new_order) / esz);
+		pr_warn("ITS@%pa: Device Table too large, reduce ids %u->%u\n",
+			&its->phys_base, its->device_ids, ids);
+	}
+
+	*order = new_order;
+
+	return indirect;
+}
+
+static void its_free_tables(struct its_node *its)
+{
+	int i;
+
+	for (i = 0; i < GITS_BASER_NR_REGS; i++) {
+		if (its->tables[i].base) {
+			free_pages((unsigned long)its->tables[i].base,
+				   its->tables[i].order);
+			its->tables[i].base = NULL;
+		}
+	}
+}
+
+static int its_alloc_tables(struct its_node *its)
+{
+	u64 typer = readq_relaxed(its->base + GITS_TYPER);
+	u32 ids = GITS_TYPER_DEVBITS(typer);
+	u64 shr = GITS_BASER_InnerShareable;
+	u64 cache = GITS_BASER_WaWb;
+	u32 psz = SZ_64K;
+	int err, i;
 
+	if (its->flags & ITS_FLAGS_WORKAROUND_CAVIUM_22375) {
+		/*
+		* erratum 22375: only alloc 8MB table size
+		* erratum 24313: ignore memory access type
+		*/
+		cache   = GITS_BASER_nCnB;
+		ids     = 0x14;                 /* 20 bits, 8MB */
+	}
+
+	its->device_ids = ids;
+
+	for (i = 0; i < GITS_BASER_NR_REGS; i++) {
+		struct its_baser *baser = its->tables + i;
+		u64 val = its_read_baser(its, baser);
+		u64 type = GITS_BASER_TYPE(val);
+		u32 order = get_order(psz);
+		bool indirect = false;
+
+		if (type == GITS_BASER_TYPE_NONE)
+			continue;
+
+		if (type == GITS_BASER_TYPE_DEVICE)
+			indirect = its_parse_baser_device(its, baser, psz, &order);
+
+		err = its_setup_baser(its, baser, cache, shr, psz, order, indirect);
+		if (err < 0) {
+			its_free_tables(its);
 			return err;
+		}
+
+		/* Update settings which will be used for next BASERn */
+		psz = baser->psz;
+		cache = baser->val & GITS_BASER_CACHEABILITY_MASK;
+		shr = baser->val & GITS_BASER_SHAREABILITY_MASK;
+	}
+
+	return 0;
 }
 
 static int its_alloc_collections(struct its_node *its)
@@ -1185,10 +1247,57 @@ static struct its_baser *its_get_baser(struct its_node *its, u32 type)
 	return NULL;
 }
 
+static bool its_alloc_device_table(struct its_node *its, u32 dev_id)
+{
+	struct its_baser *baser;
+	struct page *page;
+	u32 esz, idx;
+	__le64 *table;
+
+	baser = its_get_baser(its, GITS_BASER_TYPE_DEVICE);
+
+	/* Don't allow device id that exceeds ITS hardware limit */
+	if (!baser)
+		return (ilog2(dev_id) < its->device_ids);
+
+	/* Don't allow device id that exceeds single, flat table limit */
+	esz = GITS_BASER_ENTRY_SIZE(baser->val);
+	if (!(baser->val & GITS_BASER_INDIRECT))
+		return (dev_id < (PAGE_ORDER_TO_SIZE(baser->order) / esz));
+
+	/* Compute 1st level table index & check if that exceeds table limit */
+	idx = dev_id >> ilog2(baser->psz / esz);
+	if (idx >= (PAGE_ORDER_TO_SIZE(baser->order) / GITS_LVL1_ENTRY_SIZE))
+		return false;
+
+	table = baser->base;
+
+	/* Allocate memory for 2nd level table */
+	if (!table[idx]) {
+		page = alloc_pages(GFP_KERNEL | __GFP_ZERO, get_order(baser->psz));
+		if (!page)
+			return false;
+
+		/* Flush Lvl2 table to PoC if hw doesn't support coherency */
+		if (!(baser->val & GITS_BASER_SHAREABILITY_MASK))
+			__flush_dcache_area(page_address(page), baser->psz);
+
+		table[idx] = cpu_to_le64(page_to_phys(page) | GITS_BASER_VALID);
+
+		/* Flush Lvl1 entry to PoC if hw doesn't support coherency */
+		if (!(baser->val & GITS_BASER_SHAREABILITY_MASK))
+			__flush_dcache_area(table + idx, GITS_LVL1_ENTRY_SIZE);
+
+		/* Ensure updated table contents are visible to ITS hardware */
+		dsb(sy);
+	}
+
+	return true;
+}
+
 static struct its_device *its_create_device(struct its_node *its, u32 dev_id,
 					    int nvecs)
 {
-	struct its_baser *baser;
 	struct its_device *dev;
 	unsigned long *lpi_map;
 	unsigned long flags;
@@ -1199,14 +1308,7 @@ static struct its_device *its_create_device(struct its_node *its, u32 dev_id,
 	int nr_ites;
 	int sz;
 
-	baser = its_get_baser(its, GITS_BASER_TYPE_DEVICE);
-
-	/* Don't allow 'dev_id' that exceeds single, flat table limit */
-	if (baser) {
-		if (dev_id >= (PAGE_ORDER_TO_SIZE(baser->order) /
-			      GITS_BASER_ENTRY_SIZE(baser->val)))
-			return NULL;
-	} else if (ilog2(dev_id) >= its->device_ids)
+	if (!its_alloc_device_table(its, dev_id))
 		return NULL;
 
 	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
@@ -1569,7 +1671,7 @@ static int __init its_probe(struct device_node *node,
 
 	its_enable_quirks(its);
 
-	err = its_alloc_tables(node->full_name, its);
+	err = its_alloc_tables(its);
 	if (err)
 		goto out_free_cmd;
 

drivers/irqchip/irq-gic.c

@@ -75,7 +75,7 @@ struct gic_chip_data {
 	void __iomem *raw_dist_base;
 	void __iomem *raw_cpu_base;
 	u32 percpu_offset;
-#ifdef CONFIG_CPU_PM
+#if defined(CONFIG_CPU_PM) || defined(CONFIG_ARM_GIC_PM)
 	u32 saved_spi_enable[DIV_ROUND_UP(1020, 32)];
 	u32 saved_spi_active[DIV_ROUND_UP(1020, 32)];
 	u32 saved_spi_conf[DIV_ROUND_UP(1020, 16)];
@@ -449,7 +449,7 @@ static void gic_cpu_if_up(struct gic_chip_data *gic)
 }
 
 
-static void __init gic_dist_init(struct gic_chip_data *gic)
+static void gic_dist_init(struct gic_chip_data *gic)
 {
 	unsigned int i;
 	u32 cpumask;
@@ -528,14 +528,14 @@ int gic_cpu_if_down(unsigned int gic_nr)
 	return 0;
 }
 
-#ifdef CONFIG_CPU_PM
+#if defined(CONFIG_CPU_PM) || defined(CONFIG_ARM_GIC_PM)
 /*
  * Saves the GIC distributor registers during suspend or idle.  Must be called
  * with interrupts disabled but before powering down the GIC.  After calling
  * this function, no interrupts will be delivered by the GIC, and another
  * platform-specific wakeup source must be enabled.
  */
-static void gic_dist_save(struct gic_chip_data *gic)
+void gic_dist_save(struct gic_chip_data *gic)
 {
 	unsigned int gic_irqs;
 	void __iomem *dist_base;
@@ -574,7 +574,7 @@ static void gic_dist_save(struct gic_chip_data *gic)
  * handled normally, but any edge interrupts that occured will not be seen by
  * the GIC and need to be handled by the platform-specific wakeup source.
  */
-static void gic_dist_restore(struct gic_chip_data *gic)
+void gic_dist_restore(struct gic_chip_data *gic)
 {
 	unsigned int gic_irqs;
 	unsigned int i;
@@ -620,7 +620,7 @@ static void gic_dist_restore(struct gic_chip_data *gic)
 	writel_relaxed(GICD_ENABLE, dist_base + GIC_DIST_CTRL);
 }
 
-static void gic_cpu_save(struct gic_chip_data *gic)
+void gic_cpu_save(struct gic_chip_data *gic)
 {
 	int i;
 	u32 *ptr;
@@ -650,7 +650,7 @@ static void gic_cpu_save(struct gic_chip_data *gic)
 
 }
 
-static void gic_cpu_restore(struct gic_chip_data *gic)
+void gic_cpu_restore(struct gic_chip_data *gic)
 {
 	int i;
 	u32 *ptr;
@@ -727,7 +727,7 @@ static struct notifier_block gic_notifier_block = {
 	.notifier_call = gic_notifier,
 };
 
-static int __init gic_pm_init(struct gic_chip_data *gic)
+static int gic_pm_init(struct gic_chip_data *gic)
 {
 	gic->saved_ppi_enable = __alloc_percpu(DIV_ROUND_UP(32, 32) * 4,
 		sizeof(u32));
@@ -757,7 +757,7 @@ static int __init gic_pm_init(struct gic_chip_data *gic)
 	return -ENOMEM;
 }
 #else
-static int __init gic_pm_init(struct gic_chip_data *gic)
+static int gic_pm_init(struct gic_chip_data *gic)
 {
 	return 0;
 }
@@ -1032,32 +1032,31 @@ static const struct irq_domain_ops gic_irq_domain_ops = {
 	.unmap = gic_irq_domain_unmap,
 };
 
-static int __init __gic_init_bases(struct gic_chip_data *gic, int irq_start,
-				   struct fwnode_handle *handle)
+static void gic_init_chip(struct gic_chip_data *gic, struct device *dev,
+			  const char *name, bool use_eoimode1)
 {
-	irq_hw_number_t hwirq_base;
-	int gic_irqs, irq_base, i, ret;
-
-	if (WARN_ON(!gic || gic->domain))
-		return -EINVAL;
-
 	/* Initialize irq_chip */
 	gic->chip = gic_chip;
+	gic->chip.name = name;
+	gic->chip.parent_device = dev;
 
-	if (static_key_true(&supports_deactivate) && gic == &gic_data[0]) {
+	if (use_eoimode1) {
 		gic->chip.irq_mask = gic_eoimode1_mask_irq;
 		gic->chip.irq_eoi = gic_eoimode1_eoi_irq;
 		gic->chip.irq_set_vcpu_affinity = gic_irq_set_vcpu_affinity;
-		gic->chip.name = kasprintf(GFP_KERNEL, "GICv2");
-	} else {
-		gic->chip.name = kasprintf(GFP_KERNEL, "GIC-%d",
-					   (int)(gic - &gic_data[0]));
 	}
 
 #ifdef CONFIG_SMP
 	if (gic == &gic_data[0])
 		gic->chip.irq_set_affinity = gic_set_affinity;
 #endif
+}
+
+static int gic_init_bases(struct gic_chip_data *gic, int irq_start,
+			  struct fwnode_handle *handle)
+{
+	irq_hw_number_t hwirq_base;
+	int gic_irqs, irq_base, ret;
 
 	if (IS_ENABLED(CONFIG_GIC_NON_BANKED) && gic->percpu_offset) {
 		/* Frankein-GIC without banked registers... */
@@ -1138,6 +1137,36 @@ static int __init __gic_init_bases(struct gic_chip_data *gic, int irq_start,
 		goto error;
 	}
 
+	gic_dist_init(gic);
+	ret = gic_cpu_init(gic);
+	if (ret)
+		goto error;
+
+	ret = gic_pm_init(gic);
+	if (ret)
+		goto error;
+
+	return 0;
+
+error:
+	if (IS_ENABLED(CONFIG_GIC_NON_BANKED) && gic->percpu_offset) {
+		free_percpu(gic->dist_base.percpu_base);
+		free_percpu(gic->cpu_base.percpu_base);
+	}
+
+	return ret;
+}
+
+static int __init __gic_init_bases(struct gic_chip_data *gic,
+				   int irq_start,
+				   struct fwnode_handle *handle)
+{
+	char *name;
+	int i, ret;
+
+	if (WARN_ON(!gic || gic->domain))
+		return -EINVAL;
+
 	if (gic == &gic_data[0]) {
 		/*
 		 * Initialize the CPU interface map to all CPUs.
@@ -1155,24 +1184,17 @@ static int __init __gic_init_bases(struct gic_chip_data *gic, int irq_start,
 			pr_info("GIC: Using split EOI/Deactivate mode\n");
 	}
 
-	gic_dist_init(gic);
-	ret = gic_cpu_init(gic);
-	if (ret)
-		goto error;
-
-	ret = gic_pm_init(gic);
-	if (ret)
-		goto error;
-
-	return 0;
-
-error:
-	if (IS_ENABLED(CONFIG_GIC_NON_BANKED) && gic->percpu_offset) {
-		free_percpu(gic->dist_base.percpu_base);
-		free_percpu(gic->cpu_base.percpu_base);
+	if (static_key_true(&supports_deactivate) && gic == &gic_data[0]) {
+		name = kasprintf(GFP_KERNEL, "GICv2");
+		gic_init_chip(gic, NULL, name, true);
+	} else {
+		name = kasprintf(GFP_KERNEL, "GIC-%d", (int)(gic-&gic_data[0]));
+		gic_init_chip(gic, NULL, name, false);
 	}
 
-	kfree(gic->chip.name);
+	ret = gic_init_bases(gic, irq_start, handle);
+	if (ret)
+		kfree(name);
 
 	return ret;
 }
@@ -1250,7 +1272,7 @@ static bool gic_check_eoimode(struct device_node *node, void __iomem **base)
 	return true;
 }
 
-static int __init gic_of_setup(struct gic_chip_data *gic, struct device_node *node)
+static int gic_of_setup(struct gic_chip_data *gic, struct device_node *node)
 {
 	if (!gic || !node)
 		return -EINVAL;
@@ -1274,6 +1296,34 @@ static int __init gic_of_setup(struct gic_chip_data *gic, struct device_node *no
 	return -ENOMEM;
 }
 
+int gic_of_init_child(struct device *dev, struct gic_chip_data **gic, int irq)
+{
+	int ret;
+
+	if (!dev || !dev->of_node || !gic || !irq)
+		return -EINVAL;
+
+	*gic = devm_kzalloc(dev, sizeof(**gic), GFP_KERNEL);
+	if (!*gic)
+		return -ENOMEM;
+
+	gic_init_chip(*gic, dev, dev->of_node->name, false);
+
+	ret = gic_of_setup(*gic, dev->of_node);
+	if (ret)
+		return ret;
+
+	ret = gic_init_bases(*gic, -1, &dev->of_node->fwnode);
+	if (ret) {
+		gic_teardown(*gic);
+		return ret;
+	}
+
+	irq_set_chained_handler_and_data(irq, gic_handle_cascade_irq, *gic);
+
+	return 0;
+}
+
 static void __init gic_of_setup_kvm_info(struct device_node *node)
 {
 	int ret;
@@ -1353,7 +1403,11 @@ IRQCHIP_DECLARE(cortex_a7_gic, "arm,cortex-a7-gic", gic_of_init);
 IRQCHIP_DECLARE(msm_8660_qgic, "qcom,msm-8660-qgic", gic_of_init);
 IRQCHIP_DECLARE(msm_qgic2, "qcom,msm-qgic2", gic_of_init);
 IRQCHIP_DECLARE(pl390, "arm,pl390", gic_of_init);
-
+#else
+int gic_of_init_child(struct device *dev, struct gic_chip_data **gic, int irq)
+{
+	return -ENOTSUPP;
+}
 #endif
 
 #ifdef CONFIG_ACPI

drivers/irqchip/irq-mips-gic.c

@@ -1042,12 +1042,14 @@ static void __init __gic_init(unsigned long gic_base_addr,
 					       &gic_irq_domain_ops, NULL);
 	if (!gic_irq_domain)
 		panic("Failed to add GIC IRQ domain");
+	gic_irq_domain->name = "mips-gic-irq";
 
 	gic_dev_domain = irq_domain_add_hierarchy(gic_irq_domain, 0,
 						  GIC_NUM_LOCAL_INTRS + gic_shared_intrs,
 						  node, &gic_dev_domain_ops, NULL);
 	if (!gic_dev_domain)
 		panic("Failed to add GIC DEV domain");
+	gic_dev_domain->name = "mips-gic-dev";
 
 	gic_ipi_domain = irq_domain_add_hierarchy(gic_irq_domain,
 						  IRQ_DOMAIN_FLAG_IPI_PER_CPU,
@@ -1056,6 +1058,7 @@ static void __init __gic_init(unsigned long gic_base_addr,
 	if (!gic_ipi_domain)
 		panic("Failed to add GIC IPI domain");
 
+	gic_ipi_domain->name = "mips-gic-ipi";
 	gic_ipi_domain->bus_token = DOMAIN_BUS_IPI;
 
 	if (node &&

drivers/irqchip/irq-omap-intc.c

@@ -23,6 +23,8 @@
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
 
+#include <linux/irqchip/irq-omap-intc.h>
+
 /* Define these here for now until we drop all board-files */
 #define OMAP24XX_IC_BASE	0x480fe000
 #define OMAP34XX_IC_BASE	0x48200000

drivers/irqchip/irq-s3c24xx.c

@@ -92,9 +92,9 @@ static void s3c_irq_mask(struct irq_data *data)
 	unsigned long mask;
 	unsigned int irqno;
 
-	mask = __raw_readl(intc->reg_mask);
+	mask = readl_relaxed(intc->reg_mask);
 	mask |= (1UL << irq_data->offset);
-	__raw_writel(mask, intc->reg_mask);
+	writel_relaxed(mask, intc->reg_mask);
 
 	if (parent_intc) {
 		parent_data = &parent_intc->irqs[irq_data->parent_irq];
@@ -119,9 +119,9 @@ static void s3c_irq_unmask(struct irq_data *data)
 	unsigned long mask;
 	unsigned int irqno;
 
-	mask = __raw_readl(intc->reg_mask);
+	mask = readl_relaxed(intc->reg_mask);
 	mask &= ~(1UL << irq_data->offset);
-	__raw_writel(mask, intc->reg_mask);
+	writel_relaxed(mask, intc->reg_mask);
 
 	if (parent_intc) {
 		irqno = irq_find_mapping(parent_intc->domain,
@@ -136,9 +136,9 @@ static inline void s3c_irq_ack(struct irq_data *data)
 	struct s3c_irq_intc *intc = irq_data->intc;
 	unsigned long bitval = 1UL << irq_data->offset;
 
-	__raw_writel(bitval, intc->reg_pending);
+	writel_relaxed(bitval, intc->reg_pending);
 	if (intc->reg_intpnd)
-		__raw_writel(bitval, intc->reg_intpnd);
+		writel_relaxed(bitval, intc->reg_intpnd);
 }
 
 static int s3c_irq_type(struct irq_data *data, unsigned int type)
@@ -172,9 +172,9 @@ static int s3c_irqext_type_set(void __iomem *gpcon_reg,
 	unsigned long newvalue = 0, value;
 
 	/* Set the GPIO to external interrupt mode */
-	value = __raw_readl(gpcon_reg);
+	value = readl_relaxed(gpcon_reg);
 	value = (value & ~(3 << gpcon_offset)) | (0x02 << gpcon_offset);
-	__raw_writel(value, gpcon_reg);
+	writel_relaxed(value, gpcon_reg);
 
 	/* Set the external interrupt to pointed trigger type */
 	switch (type)
@@ -208,9 +208,9 @@ static int s3c_irqext_type_set(void __iomem *gpcon_reg,
 			return -EINVAL;
 	}
 
-	value = __raw_readl(extint_reg);
+	value = readl_relaxed(extint_reg);
 	value = (value & ~(7 << extint_offset)) | (newvalue << extint_offset);
-	__raw_writel(value, extint_reg);
+	writel_relaxed(value, extint_reg);
 
 	return 0;
 }
@@ -315,8 +315,8 @@ static void s3c_irq_demux(struct irq_desc *desc)
 
 	chained_irq_enter(chip, desc);
 
-	src = __raw_readl(sub_intc->reg_pending);
-	msk = __raw_readl(sub_intc->reg_mask);
+	src = readl_relaxed(sub_intc->reg_pending);
+	msk = readl_relaxed(sub_intc->reg_mask);
 
 	src &= ~msk;
 	src &= irq_data->sub_bits;
@@ -337,7 +337,7 @@ static inline int s3c24xx_handle_intc(struct s3c_irq_intc *intc,
 	int pnd;
 	int offset;
 
-	pnd = __raw_readl(intc->reg_intpnd);
+	pnd = readl_relaxed(intc->reg_intpnd);
 	if (!pnd)
 		return false;
 
@@ -352,7 +352,7 @@ static inline int s3c24xx_handle_intc(struct s3c_irq_intc *intc,
 	 *
 	 * Thanks to Klaus, Shannon, et al for helping to debug this problem
 	 */
-	offset = __raw_readl(intc->reg_intpnd + 4);
+	offset = readl_relaxed(intc->reg_intpnd + 4);
 
 	/* Find the bit manually, when the offset is wrong.
 	 * The pending register only ever contains the one bit of the next
@@ -406,7 +406,7 @@ int s3c24xx_set_fiq(unsigned int irq, bool on)
 		intmod = 0;
 	}
 
-	__raw_writel(intmod, S3C2410_INTMOD);
+	writel_relaxed(intmod, S3C2410_INTMOD);
 	return 0;
 }
 
@@ -508,14 +508,14 @@ static void s3c24xx_clear_intc(struct s3c_irq_intc *intc)
 
 	last = 0;
 	for (i = 0; i < 4; i++) {
-		pend = __raw_readl(reg_source);
+		pend = readl_relaxed(reg_source);
 
 		if (pend == 0 || pend == last)
 			break;
 
-		__raw_writel(pend, intc->reg_pending);
+		writel_relaxed(pend, intc->reg_pending);
 		if (intc->reg_intpnd)
-			__raw_writel(pend, intc->reg_intpnd);
+			writel_relaxed(pend, intc->reg_intpnd);
 
 		pr_info("irq: clearing pending status %08x\n", (int)pend);
 		last = pend;

drivers/irqchip/irq-sirfsoc.c

@@ -29,6 +29,11 @@
 
 static struct irq_domain *sirfsoc_irqdomain;
 
+static void __iomem *sirfsoc_irq_get_regbase(void)
+{
+	return (void __iomem __force *)sirfsoc_irqdomain->host_data;
+}
+
 static __init void sirfsoc_alloc_gc(void __iomem *base)
 {
 	unsigned int clr = IRQ_NOREQUEST | IRQ_NOPROBE | IRQ_NOAUTOEN;
@@ -53,7 +58,7 @@ static __init void sirfsoc_alloc_gc(void __iomem *base)
 
 static void __exception_irq_entry sirfsoc_handle_irq(struct pt_regs *regs)
 {
-	void __iomem *base = sirfsoc_irqdomain->host_data;
+	void __iomem *base = sirfsoc_irq_get_regbase();
 	u32 irqstat;
 
 	irqstat = readl_relaxed(base + SIRFSOC_INIT_IRQ_ID);
@@ -94,7 +99,7 @@ static struct sirfsoc_irq_status sirfsoc_irq_st;
 
 static int sirfsoc_irq_suspend(void)
 {
-	void __iomem *base = sirfsoc_irqdomain->host_data;
+	void __iomem *base = sirfsoc_irq_get_regbase();
 
 	sirfsoc_irq_st.mask0 = readl_relaxed(base + SIRFSOC_INT_RISC_MASK0);
 	sirfsoc_irq_st.mask1 = readl_relaxed(base + SIRFSOC_INT_RISC_MASK1);
@@ -106,7 +111,7 @@ static int sirfsoc_irq_suspend(void)
 
 static void sirfsoc_irq_resume(void)
 {
-	void __iomem *base = sirfsoc_irqdomain->host_data;
+	void __iomem *base = sirfsoc_irq_get_regbase();
 
 	writel_relaxed(sirfsoc_irq_st.mask0, base + SIRFSOC_INT_RISC_MASK0);
 	writel_relaxed(sirfsoc_irq_st.mask1, base + SIRFSOC_INT_RISC_MASK1);

drivers/irqchip/irq-tegra.c

@@ -90,7 +90,7 @@ static struct tegra_ictlr_info *lic;
 
 static inline void tegra_ictlr_write_mask(struct irq_data *d, unsigned long reg)
 {
-	void __iomem *base = d->chip_data;
+	void __iomem *base = (void __iomem __force *)d->chip_data;
 	u32 mask;
 
 	mask = BIT(d->hwirq % 32);
@@ -266,7 +266,7 @@ static int tegra_ictlr_domain_alloc(struct irq_domain *domain,
 
 		irq_domain_set_hwirq_and_chip(domain, virq + i, hwirq + i,
 					      &tegra_ictlr_chip,
-					      info->base[ictlr]);
+					      (void __force *)info->base[ictlr]);
 	}
 
 	parent_fwspec = *fwspec;

drivers/irqchip/irq-vic.c

@@ -167,7 +167,7 @@ static int vic_suspend(void)
 	return 0;
 }
 
-struct syscore_ops vic_syscore_ops = {
+static struct syscore_ops vic_syscore_ops = {
 	.suspend	= vic_suspend,
 	.resume		= vic_resume,
 };
@@ -517,7 +517,8 @@ int __init vic_init_cascaded(void __iomem *base, unsigned int parent_irq,
 EXPORT_SYMBOL_GPL(vic_init_cascaded);
 
 #ifdef CONFIG_OF
-int __init vic_of_init(struct device_node *node, struct device_node *parent)
+static int __init vic_of_init(struct device_node *node,
+			      struct device_node *parent)
 {
 	void __iomem *regs;
 	u32 interrupt_mask = ~0;

include/linux/interrupt.h

@@ -278,6 +278,8 @@ extern int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m);
 extern int
 irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify);
 
+struct cpumask *irq_create_affinity_mask(unsigned int *nr_vecs);
+
 #else /* CONFIG_SMP */
 
 static inline int irq_set_affinity(unsigned int irq, const struct cpumask *m)
@@ -308,6 +310,12 @@ irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify)
 {
 	return 0;
 }
+
+static inline struct cpumask *irq_create_affinity_mask(unsigned int *nr_vecs)
+{
+	*nr_vecs = 1;
+	return NULL;
+}
 #endif /* CONFIG_SMP */
 
 /*

include/linux/irq.h

@@ -197,6 +197,7 @@ struct irq_data {
  * IRQD_IRQ_INPROGRESS		- In progress state of the interrupt
  * IRQD_WAKEUP_ARMED		- Wakeup mode armed
  * IRQD_FORWARDED_TO_VCPU	- The interrupt is forwarded to a VCPU
+ * IRQD_AFFINITY_MANAGED	- Affinity is auto-managed by the kernel
  */
 enum {
 	IRQD_TRIGGER_MASK		= 0xf,
@@ -212,6 +213,7 @@ enum {
 	IRQD_IRQ_INPROGRESS		= (1 << 18),
 	IRQD_WAKEUP_ARMED		= (1 << 19),
 	IRQD_FORWARDED_TO_VCPU		= (1 << 20),
+	IRQD_AFFINITY_MANAGED		= (1 << 21),
 };
 
 #define __irqd_to_state(d) ACCESS_PRIVATE((d)->common, state_use_accessors)
@@ -305,6 +307,11 @@ static inline void irqd_clr_forwarded_to_vcpu(struct irq_data *d)
 	__irqd_to_state(d) &= ~IRQD_FORWARDED_TO_VCPU;
 }
 
+static inline bool irqd_affinity_is_managed(struct irq_data *d)
+{
+	return __irqd_to_state(d) & IRQD_AFFINITY_MANAGED;
+}
+
 #undef __irqd_to_state
 
 static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d)
@@ -315,6 +322,7 @@ static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d)
 /**
  * struct irq_chip - hardware interrupt chip descriptor
  *
+ * @parent_device:	pointer to parent device for irqchip
  * @name:		name for /proc/interrupts
  * @irq_startup:	start up the interrupt (defaults to ->enable if NULL)
  * @irq_shutdown:	shut down the interrupt (defaults to ->disable if NULL)
@@ -354,6 +362,7 @@ static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d)
  * @flags:		chip specific flags
  */
 struct irq_chip {
+	struct device	*parent_device;
 	const char	*name;
 	unsigned int	(*irq_startup)(struct irq_data *data);
 	void		(*irq_shutdown)(struct irq_data *data);
@@ -482,12 +491,15 @@ extern void handle_fasteoi_irq(struct irq_desc *desc);
 extern void handle_edge_irq(struct irq_desc *desc);
 extern void handle_edge_eoi_irq(struct irq_desc *desc);
 extern void handle_simple_irq(struct irq_desc *desc);
+extern void handle_untracked_irq(struct irq_desc *desc);
 extern void handle_percpu_irq(struct irq_desc *desc);
 extern void handle_percpu_devid_irq(struct irq_desc *desc);
 extern void handle_bad_irq(struct irq_desc *desc);
 extern void handle_nested_irq(unsigned int irq);
 
 extern int irq_chip_compose_msi_msg(struct irq_data *data, struct msi_msg *msg);
+extern int irq_chip_pm_get(struct irq_data *data);
+extern int irq_chip_pm_put(struct irq_data *data);
 #ifdef	CONFIG_IRQ_DOMAIN_HIERARCHY
 extern void irq_chip_enable_parent(struct irq_data *data);
 extern void irq_chip_disable_parent(struct irq_data *data);
@@ -701,11 +713,11 @@ static inline struct cpumask *irq_data_get_affinity_mask(struct irq_data *d)
 unsigned int arch_dynirq_lower_bound(unsigned int from);
 
 int __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node,
-		struct module *owner);
+		      struct module *owner, const struct cpumask *affinity);
 
 /* use macros to avoid needing export.h for THIS_MODULE */
 #define irq_alloc_descs(irq, from, cnt, node)	\
-	__irq_alloc_descs(irq, from, cnt, node, THIS_MODULE)
+	__irq_alloc_descs(irq, from, cnt, node, THIS_MODULE, NULL)
 
 #define irq_alloc_desc(node)			\
 	irq_alloc_descs(-1, 0, 1, node)

include/linux/irqchip/arm-gic-v3.h

@@ -204,6 +204,7 @@
 #define GITS_BASER_NR_REGS		8
 
 #define GITS_BASER_VALID		(1UL << 63)
+#define GITS_BASER_INDIRECT		(1UL << 62)
 #define GITS_BASER_nCnB			(0UL << 59)
 #define GITS_BASER_nC			(1UL << 59)
 #define GITS_BASER_RaWt			(2UL << 59)
@@ -228,6 +229,7 @@
 #define GITS_BASER_PAGE_SIZE_64K	(2UL << GITS_BASER_PAGE_SIZE_SHIFT)
 #define GITS_BASER_PAGE_SIZE_MASK	(3UL << GITS_BASER_PAGE_SIZE_SHIFT)
 #define GITS_BASER_PAGES_MAX		256
+#define GITS_BASER_PAGES_SHIFT		(0)
 
 #define GITS_BASER_TYPE_NONE		0
 #define GITS_BASER_TYPE_DEVICE		1
@@ -238,6 +240,8 @@
 #define GITS_BASER_TYPE_RESERVED6	6
 #define GITS_BASER_TYPE_RESERVED7	7
 
+#define GITS_LVL1_ENTRY_SIZE           (8UL)
+
 /*
  * ITS commands
  */

include/linux/irqchip/arm-gic.h

@@ -101,9 +101,14 @@
 #include <linux/irqdomain.h>
 
 struct device_node;
+struct gic_chip_data;
 
 void gic_cascade_irq(unsigned int gic_nr, unsigned int irq);
 int gic_cpu_if_down(unsigned int gic_nr);
+void gic_cpu_save(struct gic_chip_data *gic);
+void gic_cpu_restore(struct gic_chip_data *gic);
+void gic_dist_save(struct gic_chip_data *gic);
+void gic_dist_restore(struct gic_chip_data *gic);
 
 /*
  * Subdrivers that need some preparatory work can initialize their
@@ -111,6 +116,12 @@ int gic_cpu_if_down(unsigned int gic_nr);
  */
 int gic_of_init(struct device_node *node, struct device_node *parent);
 
+/*
+ * Initialises and registers a non-root or child GIC chip. Memory for
+ * the gic_chip_data structure is dynamically allocated.
+ */
+int gic_of_init_child(struct device *dev, struct gic_chip_data **gic, int irq);
+
 /*
  * Legacy platforms not converted to DT yet must use this to init
  * their GIC

include/linux/irqdomain.h

@@ -39,6 +39,7 @@ struct irq_domain;
 struct of_device_id;
 struct irq_chip;
 struct irq_data;
+struct cpumask;
 
 /* Number of irqs reserved for a legacy isa controller */
 #define NUM_ISA_INTERRUPTS	16
@@ -217,7 +218,8 @@ extern struct irq_domain *irq_find_matching_fwspec(struct irq_fwspec *fwspec,
 						   enum irq_domain_bus_token bus_token);
 extern void irq_set_default_host(struct irq_domain *host);
 extern int irq_domain_alloc_descs(int virq, unsigned int nr_irqs,
-				  irq_hw_number_t hwirq, int node);
+				  irq_hw_number_t hwirq, int node,
+				  const struct cpumask *affinity);
 
 static inline struct fwnode_handle *of_node_to_fwnode(struct device_node *node)
 {
@@ -389,7 +391,7 @@ static inline struct irq_domain *irq_domain_add_hierarchy(struct irq_domain *par
 
 extern int __irq_domain_alloc_irqs(struct irq_domain *domain, int irq_base,
 				   unsigned int nr_irqs, int node, void *arg,
-				   bool realloc);
+				   bool realloc, const struct cpumask *affinity);
 extern void irq_domain_free_irqs(unsigned int virq, unsigned int nr_irqs);
 extern void irq_domain_activate_irq(struct irq_data *irq_data);
 extern void irq_domain_deactivate_irq(struct irq_data *irq_data);
@@ -397,7 +399,8 @@ extern void irq_domain_deactivate_irq(struct irq_data *irq_data);
 static inline int irq_domain_alloc_irqs(struct irq_domain *domain,
 			unsigned int nr_irqs, int node, void *arg)
 {
-	return __irq_domain_alloc_irqs(domain, -1, nr_irqs, node, arg, false);
+	return __irq_domain_alloc_irqs(domain, -1, nr_irqs, node, arg, false,
+				       NULL);
 }
 
 extern int irq_domain_alloc_irqs_recursive(struct irq_domain *domain,
@@ -452,6 +455,9 @@ static inline int irq_domain_alloc_irqs(struct irq_domain *domain,
 	return -1;
 }
 
+static inline void irq_domain_free_irqs(unsigned int virq,
+					unsigned int nr_irqs) { }
+
 static inline bool irq_domain_is_hierarchy(struct irq_domain *domain)
 {
 	return false;

include/linux/msi.h

@@ -47,6 +47,7 @@ struct fsl_mc_msi_desc {
  * @nvec_used:	The number of vectors used
  * @dev:	Pointer to the device which uses this descriptor
  * @msg:	The last set MSI message cached for reuse
+ * @affinity:	Optional pointer to a cpu affinity mask for this descriptor
  *
  * @masked:	[PCI MSI/X] Mask bits
  * @is_msix:	[PCI MSI/X] True if MSI-X
@@ -67,6 +68,7 @@ struct msi_desc {
 	unsigned int			nvec_used;
 	struct device			*dev;
 	struct msi_msg			msg;
+	const struct cpumask		*affinity;
 
 	union {
 		/* PCI MSI/X specific data */
@@ -264,12 +266,10 @@ enum {
 	 * callbacks.
 	 */
 	MSI_FLAG_USE_DEF_CHIP_OPS	= (1 << 1),
-	/* Build identity map between hwirq and irq */
-	MSI_FLAG_IDENTITY_MAP		= (1 << 2),
 	/* Support multiple PCI MSI interrupts */
-	MSI_FLAG_MULTI_PCI_MSI		= (1 << 3),
+	MSI_FLAG_MULTI_PCI_MSI		= (1 << 2),
 	/* Support PCI MSIX interrupts */
-	MSI_FLAG_PCI_MSIX		= (1 << 4),
+	MSI_FLAG_PCI_MSIX		= (1 << 3),
 };
 
 int msi_domain_set_affinity(struct irq_data *data, const struct cpumask *mask,

kernel/irq/Makefile

@@ -9,3 +9,4 @@ obj-$(CONFIG_GENERIC_IRQ_MIGRATION) += cpuhotplug.o
 obj-$(CONFIG_PM_SLEEP) += pm.o
 obj-$(CONFIG_GENERIC_MSI_IRQ) += msi.o
 obj-$(CONFIG_GENERIC_IRQ_IPI) += ipi.o
+obj-$(CONFIG_SMP) += affinity.o

kernel/irq/affinity.c

+
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/cpu.h>
+
+static int get_first_sibling(unsigned int cpu)
+{
+	unsigned int ret;
+
+	ret = cpumask_first(topology_sibling_cpumask(cpu));
+	if (ret < nr_cpu_ids)
+		return ret;
+	return cpu;
+}
+
+/*
+ * Take a map of online CPUs and the number of available interrupt vectors
+ * and generate an output cpumask suitable for spreading MSI/MSI-X vectors
+ * so that they are distributed as good as possible around the CPUs.  If
+ * more vectors than CPUs are available we'll map one to each CPU,
+ * otherwise we map one to the first sibling of each socket.
+ *
+ * If there are more vectors than CPUs we will still only have one bit
+ * set per CPU, but interrupt code will keep on assigning the vectors from
+ * the start of the bitmap until we run out of vectors.
+ */
+struct cpumask *irq_create_affinity_mask(unsigned int *nr_vecs)
+{
+	struct cpumask *affinity_mask;
+	unsigned int max_vecs = *nr_vecs;
+
+	if (max_vecs == 1)
+		return NULL;
+
+	affinity_mask = kzalloc(cpumask_size(), GFP_KERNEL);
+	if (!affinity_mask) {
+		*nr_vecs = 1;
+		return NULL;
+	}
+
+	if (max_vecs >= num_online_cpus()) {
+		cpumask_copy(affinity_mask, cpu_online_mask);
+		*nr_vecs = num_online_cpus();
+	} else {
+		unsigned int vecs = 0, cpu;
+
+		for_each_online_cpu(cpu) {
+			if (cpu == get_first_sibling(cpu)) {
+				cpumask_set_cpu(cpu, affinity_mask);
+				vecs++;
+			}
+
+			if (--max_vecs == 0)
+				break;
+		}
+		*nr_vecs = vecs;
+	}
+
+	return affinity_mask;
+}

kernel/irq/chip.c

@@ -426,6 +426,49 @@ void handle_simple_irq(struct irq_desc *desc)
 }
 EXPORT_SYMBOL_GPL(handle_simple_irq);
 
+/**
+ *	handle_untracked_irq - Simple and software-decoded IRQs.
+ *	@desc:	the interrupt description structure for this irq
+ *
+ *	Untracked interrupts are sent from a demultiplexing interrupt
+ *	handler when the demultiplexer does not know which device it its
+ *	multiplexed irq domain generated the interrupt. IRQ's handled
+ *	through here are not subjected to stats tracking, randomness, or
+ *	spurious interrupt detection.
+ *
+ *	Note: Like handle_simple_irq, the caller is expected to handle
+ *	the ack, clear, mask and unmask issues if necessary.
+ */
+void handle_untracked_irq(struct irq_desc *desc)
+{
+	unsigned int flags = 0;
+
+	raw_spin_lock(&desc->lock);
+
+	if (!irq_may_run(desc))
+		goto out_unlock;
+
+	desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
+
+	if (unlikely(!desc->action || irqd_irq_disabled(&desc->irq_data))) {
+		desc->istate |= IRQS_PENDING;
+		goto out_unlock;
+	}
+
+	desc->istate &= ~IRQS_PENDING;
+	irqd_set(&desc->irq_data, IRQD_IRQ_INPROGRESS);
+	raw_spin_unlock(&desc->lock);
+
+	__handle_irq_event_percpu(desc, &flags);
+
+	raw_spin_lock(&desc->lock);
+	irqd_clear(&desc->irq_data, IRQD_IRQ_INPROGRESS);
+
+out_unlock:
+	raw_spin_unlock(&desc->lock);
+}
+EXPORT_SYMBOL_GPL(handle_untracked_irq);
+
 /*
  * Called unconditionally from handle_level_irq() and only for oneshot
  * interrupts from handle_fasteoi_irq()
@@ -1093,3 +1136,43 @@ int irq_chip_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 
 	return 0;
 }
+
+/**
+ * irq_chip_pm_get - Enable power for an IRQ chip
+ * @data:	Pointer to interrupt specific data
+ *
+ * Enable the power to the IRQ chip referenced by the interrupt data
+ * structure.
+ */
+int irq_chip_pm_get(struct irq_data *data)
+{
+	int retval;
+
+	if (IS_ENABLED(CONFIG_PM) && data->chip->parent_device) {
+		retval = pm_runtime_get_sync(data->chip->parent_device);
+		if (retval < 0) {
+			pm_runtime_put_noidle(data->chip->parent_device);
+			return retval;
+		}
+	}
+
+	return 0;
+}
+
+/**
+ * irq_chip_pm_put - Disable power for an IRQ chip
+ * @data:	Pointer to interrupt specific data
+ *
+ * Disable the power to the IRQ chip referenced by the interrupt data
+ * structure, belongs. Note that power will only be disabled, once this
+ * function has been called for all IRQs that have called irq_chip_pm_get().
+ */
+int irq_chip_pm_put(struct irq_data *data)
+{
+	int retval = 0;
+
+	if (IS_ENABLED(CONFIG_PM) && data->chip->parent_device)
+		retval = pm_runtime_put(data->chip->parent_device);
+
+	return (retval < 0) ? retval : 0;
+}

kernel/irq/handle.c

@@ -132,10 +132,10 @@ void __irq_wake_thread(struct irq_desc *desc, struct irqaction *action)
 	wake_up_process(action->thread);
 }
 
-irqreturn_t handle_irq_event_percpu(struct irq_desc *desc)
+irqreturn_t __handle_irq_event_percpu(struct irq_desc *desc, unsigned int *flags)
 {
 	irqreturn_t retval = IRQ_NONE;
-	unsigned int flags = 0, irq = desc->irq_data.irq;
+	unsigned int irq = desc->irq_data.irq;
 	struct irqaction *action;
 
 	for_each_action_of_desc(desc, action) {
@@ -164,7 +164,7 @@ irqreturn_t handle_irq_event_percpu(struct irq_desc *desc)
 
 			/* Fall through to add to randomness */
 		case IRQ_HANDLED:
-			flags |= action->flags;
+			*flags |= action->flags;
 			break;
 
 		default:
@@ -174,7 +174,17 @@ irqreturn_t handle_irq_event_percpu(struct irq_desc *desc)
 		retval |= res;
 	}
 
-	add_interrupt_randomness(irq, flags);
+	return retval;
+}
+
+irqreturn_t handle_irq_event_percpu(struct irq_desc *desc)
+{
+	irqreturn_t retval;
+	unsigned int flags = 0;
+
+	retval = __handle_irq_event_percpu(desc, &flags);
+
+	add_interrupt_randomness(desc->irq_data.irq, flags);
 
 	if (!noirqdebug)
 		note_interrupt(desc, retval);

kernel/irq/internals.h

@@ -7,6 +7,7 @@
  */
 #include <linux/irqdesc.h>
 #include <linux/kernel_stat.h>
+#include <linux/pm_runtime.h>
 
 #ifdef CONFIG_SPARSE_IRQ
 # define IRQ_BITMAP_BITS	(NR_IRQS + 8196)
@@ -83,6 +84,7 @@ extern void irq_mark_irq(unsigned int irq);
 
 extern void init_kstat_irqs(struct irq_desc *desc, int node, int nr);
 
+irqreturn_t __handle_irq_event_percpu(struct irq_desc *desc, unsigned int *flags);
 irqreturn_t handle_irq_event_percpu(struct irq_desc *desc);
 irqreturn_t handle_irq_event(struct irq_desc *desc);
 
@@ -105,6 +107,8 @@ static inline void unregister_handler_proc(unsigned int irq,
 					   struct irqaction *action) { }
 #endif
 
+extern bool irq_can_set_affinity_usr(unsigned int irq);
+
 extern int irq_select_affinity_usr(unsigned int irq, struct cpumask *mask);
 
 extern void irq_set_thread_affinity(struct irq_desc *desc);

kernel/irq/ipi.c

@@ -76,14 +76,14 @@ int irq_reserve_ipi(struct irq_domain *domain,
 		}
 	}
 
-	virq = irq_domain_alloc_descs(-1, nr_irqs, 0, NUMA_NO_NODE);
+	virq = irq_domain_alloc_descs(-1, nr_irqs, 0, NUMA_NO_NODE, NULL);
 	if (virq <= 0) {
 		pr_warn("Can't reserve IPI, failed to alloc descs\n");
 		return -ENOMEM;
 	}
 
 	virq = __irq_domain_alloc_irqs(domain, virq, nr_irqs, NUMA_NO_NODE,
-				       (void *) dest, true);
+				       (void *) dest, true, NULL);
 
 	if (virq <= 0) {
 		pr_warn("Can't reserve IPI, failed to alloc hw irqs\n");

kernel/irq/irqdesc.c

@@ -68,9 +68,13 @@ static int alloc_masks(struct irq_desc *desc, gfp_t gfp, int node)
 	return 0;
 }
 
-static void desc_smp_init(struct irq_desc *desc, int node)
+static void desc_smp_init(struct irq_desc *desc, int node,
+			  const struct cpumask *affinity)
 {
-	cpumask_copy(desc->irq_common_data.affinity, irq_default_affinity);
+	if (!affinity)
+		affinity = irq_default_affinity;
+	cpumask_copy(desc->irq_common_data.affinity, affinity);
+
 #ifdef CONFIG_GENERIC_PENDING_IRQ
 	cpumask_clear(desc->pending_mask);
 #endif
@@ -82,11 +86,12 @@ static void desc_smp_init(struct irq_desc *desc, int node)
 #else
 static inline int
 alloc_masks(struct irq_desc *desc, gfp_t gfp, int node) { return 0; }
-static inline void desc_smp_init(struct irq_desc *desc, int node) { }
+static inline void
+desc_smp_init(struct irq_desc *desc, int node, const struct cpumask *affinity) { }
 #endif
 
 static void desc_set_defaults(unsigned int irq, struct irq_desc *desc, int node,
-		struct module *owner)
+			      const struct cpumask *affinity, struct module *owner)
 {
 	int cpu;
 
@@ -107,7 +112,7 @@ static void desc_set_defaults(unsigned int irq, struct irq_desc *desc, int node,
 	desc->owner = owner;
 	for_each_possible_cpu(cpu)
 		*per_cpu_ptr(desc->kstat_irqs, cpu) = 0;
-	desc_smp_init(desc, node);
+	desc_smp_init(desc, node, affinity);
 }
 
 int nr_irqs = NR_IRQS;
@@ -158,7 +163,9 @@ void irq_unlock_sparse(void)
 	mutex_unlock(&sparse_irq_lock);
 }
 
-static struct irq_desc *alloc_desc(int irq, int node, struct module *owner)
+static struct irq_desc *alloc_desc(int irq, int node, unsigned int flags,
+				   const struct cpumask *affinity,
+				   struct module *owner)
 {
 	struct irq_desc *desc;
 	gfp_t gfp = GFP_KERNEL;
@@ -178,7 +185,8 @@ static struct irq_desc *alloc_desc(int irq, int node, struct module *owner)
 	lockdep_set_class(&desc->lock, &irq_desc_lock_class);
 	init_rcu_head(&desc->rcu);
 
-	desc_set_defaults(irq, desc, node, owner);
+	desc_set_defaults(irq, desc, node, affinity, owner);
+	irqd_set(&desc->irq_data, flags);
 
 	return desc;
 
@@ -223,13 +231,32 @@ static void free_desc(unsigned int irq)
 }
 
 static int alloc_descs(unsigned int start, unsigned int cnt, int node,
-		       struct module *owner)
+		       const struct cpumask *affinity, struct module *owner)
 {
+	const struct cpumask *mask = NULL;
 	struct irq_desc *desc;
-	int i;
+	unsigned int flags;
+	int i, cpu = -1;
+
+	if (affinity && cpumask_empty(affinity))
+		return -EINVAL;
+
+	flags = affinity ? IRQD_AFFINITY_MANAGED : 0;
 
 	for (i = 0; i < cnt; i++) {
-		desc = alloc_desc(start + i, node, owner);
+		if (affinity) {
+			cpu = cpumask_next(cpu, affinity);
+			if (cpu >= nr_cpu_ids)
+				cpu = cpumask_first(affinity);
+			node = cpu_to_node(cpu);
+
+			/*
+			 * For single allocations we use the caller provided
+			 * mask otherwise we use the mask of the target cpu
+			 */
+			mask = cnt == 1 ? affinity : cpumask_of(cpu);
+		}
+		desc = alloc_desc(start + i, node, flags, mask, owner);
 		if (!desc)
 			goto err;
 		mutex_lock(&sparse_irq_lock);
@@ -277,7 +304,7 @@ int __init early_irq_init(void)
 		nr_irqs = initcnt;
 
 	for (i = 0; i < initcnt; i++) {
-		desc = alloc_desc(i, node, NULL);
+		desc = alloc_desc(i, node, 0, NULL, NULL);
 		set_bit(i, allocated_irqs);
 		irq_insert_desc(i, desc);
 	}
@@ -311,7 +338,7 @@ int __init early_irq_init(void)
 		alloc_masks(&desc[i], GFP_KERNEL, node);
 		raw_spin_lock_init(&desc[i].lock);
 		lockdep_set_class(&desc[i].lock, &irq_desc_lock_class);
-		desc_set_defaults(i, &desc[i], node, NULL);
+		desc_set_defaults(i, &desc[i], node, NULL, NULL);
 	}
 	return arch_early_irq_init();
 }
@@ -328,11 +355,12 @@ static void free_desc(unsigned int irq)
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&desc->lock, flags);
-	desc_set_defaults(irq, desc, irq_desc_get_node(desc), NULL);
+	desc_set_defaults(irq, desc, irq_desc_get_node(desc), NULL, NULL);
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 }
 
 static inline int alloc_descs(unsigned int start, unsigned int cnt, int node,
+			      const struct cpumask *affinity,
 			      struct module *owner)
 {
 	u32 i;
@@ -453,12 +481,15 @@ EXPORT_SYMBOL_GPL(irq_free_descs);
  * @cnt:	Number of consecutive irqs to allocate.
  * @node:	Preferred node on which the irq descriptor should be allocated
  * @owner:	Owning module (can be NULL)
+ * @affinity:	Optional pointer to an affinity mask which hints where the
+ *		irq descriptors should be allocated and which default
+ *		affinities to use
  *
  * Returns the first irq number or error code
  */
 int __ref
 __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node,
-		  struct module *owner)
+		  struct module *owner, const struct cpumask *affinity)
 {
 	int start, ret;
 
@@ -494,7 +525,7 @@ __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node,
 
 	bitmap_set(allocated_irqs, start, cnt);
 	mutex_unlock(&sparse_irq_lock);
-	return alloc_descs(start, cnt, node, owner);
+	return alloc_descs(start, cnt, node, affinity, owner);
 
 err:
 	mutex_unlock(&sparse_irq_lock);
@@ -512,7 +543,7 @@ EXPORT_SYMBOL_GPL(__irq_alloc_descs);
  */
 unsigned int irq_alloc_hwirqs(int cnt, int node)
 {
-	int i, irq = __irq_alloc_descs(-1, 0, cnt, node, NULL);
+	int i, irq = __irq_alloc_descs(-1, 0, cnt, node, NULL, NULL);
 
 	if (irq < 0)
 		return 0;

kernel/irq/irqdomain.c

@@ -481,7 +481,7 @@ unsigned int irq_create_mapping(struct irq_domain *domain,
 	}
 
 	/* Allocate a virtual interrupt number */
-	virq = irq_domain_alloc_descs(-1, 1, hwirq, of_node_to_nid(of_node));
+	virq = irq_domain_alloc_descs(-1, 1, hwirq, of_node_to_nid(of_node), NULL);
 	if (virq <= 0) {
 		pr_debug("-> virq allocation failed\n");
 		return 0;
@@ -567,6 +567,7 @@ static void of_phandle_args_to_fwspec(struct of_phandle_args *irq_data,
 unsigned int irq_create_fwspec_mapping(struct irq_fwspec *fwspec)
 {
 	struct irq_domain *domain;
+	struct irq_data *irq_data;
 	irq_hw_number_t hwirq;
 	unsigned int type = IRQ_TYPE_NONE;
 	int virq;
@@ -588,15 +589,46 @@ unsigned int irq_create_fwspec_mapping(struct irq_fwspec *fwspec)
 	if (irq_domain_translate(domain, fwspec, &hwirq, &type))
 		return 0;
 
-	if (irq_domain_is_hierarchy(domain)) {
+	/*
+	 * WARN if the irqchip returns a type with bits
+	 * outside the sense mask set and clear these bits.
+	 */
+	if (WARN_ON(type & ~IRQ_TYPE_SENSE_MASK))
+		type &= IRQ_TYPE_SENSE_MASK;
+
 	/*
 	 * If we've already configured this interrupt,
 	 * don't do it again, or hell will break loose.
 	 */
 	virq = irq_find_mapping(domain, hwirq);
-		if (virq)
+	if (virq) {
+		/*
+		 * If the trigger type is not specified or matches the
+		 * current trigger type then we are done so return the
+		 * interrupt number.
+		 */
+		if (type == IRQ_TYPE_NONE || type == irq_get_trigger_type(virq))
 			return virq;
 
+		/*
+		 * If the trigger type has not been set yet, then set
+		 * it now and return the interrupt number.
+		 */
+		if (irq_get_trigger_type(virq) == IRQ_TYPE_NONE) {
+			irq_data = irq_get_irq_data(virq);
+			if (!irq_data)
+				return 0;
+
+			irqd_set_trigger_type(irq_data, type);
+			return virq;
+		}
+
+		pr_warn("type mismatch, failed to map hwirq-%lu for %s!\n",
+			hwirq, of_node_full_name(to_of_node(fwspec->fwnode)));
+		return 0;
+	}
+
+	if (irq_domain_is_hierarchy(domain)) {
 		virq = irq_domain_alloc_irqs(domain, 1, NUMA_NO_NODE, fwspec);
 		if (virq <= 0)
 			return 0;
@@ -607,10 +639,18 @@ unsigned int irq_create_fwspec_mapping(struct irq_fwspec *fwspec)
 			return virq;
 	}
 
-	/* Set type if specified and different than the current one */
-	if (type != IRQ_TYPE_NONE &&
-	    type != irq_get_trigger_type(virq))
-		irq_set_irq_type(virq, type);
+	irq_data = irq_get_irq_data(virq);
+	if (!irq_data) {
+		if (irq_domain_is_hierarchy(domain))
+			irq_domain_free_irqs(virq, 1);
+		else
+			irq_dispose_mapping(virq);
+		return 0;
+	}
+
+	/* Store trigger type */
+	irqd_set_trigger_type(irq_data, type);
+
 	return virq;
 }
 EXPORT_SYMBOL_GPL(irq_create_fwspec_mapping);
@@ -640,8 +680,12 @@ void irq_dispose_mapping(unsigned int virq)
 	if (WARN_ON(domain == NULL))
 		return;
 
+	if (irq_domain_is_hierarchy(domain)) {
+		irq_domain_free_irqs(virq, 1);
+	} else {
 		irq_domain_disassociate(domain, virq);
 		irq_free_desc(virq);
+	}
 }
 EXPORT_SYMBOL_GPL(irq_dispose_mapping);
 
@@ -835,19 +879,23 @@ const struct irq_domain_ops irq_domain_simple_ops = {
 EXPORT_SYMBOL_GPL(irq_domain_simple_ops);
 
 int irq_domain_alloc_descs(int virq, unsigned int cnt, irq_hw_number_t hwirq,
-			   int node)
+			   int node, const struct cpumask *affinity)
 {
 	unsigned int hint;
 
 	if (virq >= 0) {
-		virq = irq_alloc_descs(virq, virq, cnt, node);
+		virq = __irq_alloc_descs(virq, virq, cnt, node, THIS_MODULE,
+					 affinity);
 	} else {
 		hint = hwirq % nr_irqs;
 		if (hint == 0)
 			hint++;
-		virq = irq_alloc_descs_from(hint, cnt, node);
-		if (virq <= 0 && hint > 1)
-			virq = irq_alloc_descs_from(1, cnt, node);
+		virq = __irq_alloc_descs(-1, hint, cnt, node, THIS_MODULE,
+					 affinity);
+		if (virq <= 0 && hint > 1) {
+			virq = __irq_alloc_descs(-1, 1, cnt, node, THIS_MODULE,
+						 affinity);
+		}
 	}
 
 	return virq;
@@ -1144,7 +1192,9 @@ int irq_domain_alloc_irqs_recursive(struct irq_domain *domain,
 	if (recursive)
 		ret = irq_domain_alloc_irqs_recursive(parent, irq_base,
 						      nr_irqs, arg);
-	if (ret >= 0)
+	if (ret < 0)
+		return ret;
+
 	ret = domain->ops->alloc(domain, irq_base, nr_irqs, arg);
 	if (ret < 0 && recursive)
 		irq_domain_free_irqs_recursive(parent, irq_base, nr_irqs);
@@ -1160,6 +1210,7 @@ int irq_domain_alloc_irqs_recursive(struct irq_domain *domain,
  * @node:	NUMA node id for memory allocation
  * @arg:	domain specific argument
  * @realloc:	IRQ descriptors have already been allocated if true
+ * @affinity:	Optional irq affinity mask for multiqueue devices
  *
  * Allocate IRQ numbers and initialized all data structures to support
  * hierarchy IRQ domains.
@@ -1175,7 +1226,7 @@ int irq_domain_alloc_irqs_recursive(struct irq_domain *domain,
  */
 int __irq_domain_alloc_irqs(struct irq_domain *domain, int irq_base,
 			    unsigned int nr_irqs, int node, void *arg,
-			    bool realloc)
+			    bool realloc, const struct cpumask *affinity)
 {
 	int i, ret, virq;
 
@@ -1193,7 +1244,8 @@ int __irq_domain_alloc_irqs(struct irq_domain *domain, int irq_base,
 	if (realloc && irq_base >= 0) {
 		virq = irq_base;
 	} else {
-		virq = irq_domain_alloc_descs(irq_base, nr_irqs, 0, node);
+		virq = irq_domain_alloc_descs(irq_base, nr_irqs, 0, node,
+					      affinity);
 		if (virq < 0) {
 			pr_debug("cannot allocate IRQ(base %d, count %d)\n",
 				 irq_base, nr_irqs);

kernel/irq/manage.c

@@ -115,12 +115,12 @@ EXPORT_SYMBOL(synchronize_irq);
 #ifdef CONFIG_SMP
 cpumask_var_t irq_default_affinity;
 
-static int __irq_can_set_affinity(struct irq_desc *desc)
+static bool __irq_can_set_affinity(struct irq_desc *desc)
 {
 	if (!desc || !irqd_can_balance(&desc->irq_data) ||
 	    !desc->irq_data.chip || !desc->irq_data.chip->irq_set_affinity)
-		return 0;
-	return 1;
+		return false;
+	return true;
 }
 
 /**
@@ -133,6 +133,21 @@ int irq_can_set_affinity(unsigned int irq)
 	return __irq_can_set_affinity(irq_to_desc(irq));
 }
 
+/**
+ * irq_can_set_affinity_usr - Check if affinity of a irq can be set from user space
+ * @irq:	Interrupt to check
+ *
+ * Like irq_can_set_affinity() above, but additionally checks for the
+ * AFFINITY_MANAGED flag.
+ */
+bool irq_can_set_affinity_usr(unsigned int irq)
+{
+	struct irq_desc *desc = irq_to_desc(irq);
+
+	return __irq_can_set_affinity(desc) &&
+		!irqd_affinity_is_managed(&desc->irq_data);
+}
+
 /**
  *	irq_set_thread_affinity - Notify irq threads to adjust affinity
  *	@desc:		irq descriptor which has affitnity changed
@@ -338,10 +353,11 @@ static int setup_affinity(struct irq_desc *desc, struct cpumask *mask)
 		return 0;
 
 	/*
-	 * Preserve an userspace affinity setup, but make sure that
-	 * one of the targets is online.
+	 * Preserve the managed affinity setting and an userspace affinity
+	 * setup, but make sure that one of the targets is online.
 	 */
-	if (irqd_has_set(&desc->irq_data, IRQD_AFFINITY_SET)) {
+	if (irqd_affinity_is_managed(&desc->irq_data) ||
+	    irqd_has_set(&desc->irq_data, IRQD_AFFINITY_SET)) {
 		if (cpumask_intersects(desc->irq_common_data.affinity,
 				       cpu_online_mask))
 			set = desc->irq_common_data.affinity;
@@ -1116,6 +1132,13 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 
 	new->irq = irq;
 
+	/*
+	 * If the trigger type is not specified by the caller,
+	 * then use the default for this interrupt.
+	 */
+	if (!(new->flags & IRQF_TRIGGER_MASK))
+		new->flags |= irqd_get_trigger_type(&desc->irq_data);
+
 	/*
 	 * Check whether the interrupt nests into another interrupt
 	 * thread.
@@ -1409,10 +1432,18 @@ int setup_irq(unsigned int irq, struct irqaction *act)
 
 	if (!desc || WARN_ON(irq_settings_is_per_cpu_devid(desc)))
 		return -EINVAL;
+
+	retval = irq_chip_pm_get(&desc->irq_data);
+	if (retval < 0)
+		return retval;
+
 	chip_bus_lock(desc);
 	retval = __setup_irq(irq, desc, act);
 	chip_bus_sync_unlock(desc);
 
+	if (retval)
+		irq_chip_pm_put(&desc->irq_data);
+
 	return retval;
 }
 EXPORT_SYMBOL_GPL(setup_irq);
@@ -1506,6 +1537,7 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id)
 		}
 	}
 
+	irq_chip_pm_put(&desc->irq_data);
 	module_put(desc->owner);
 	kfree(action->secondary);
 	return action;
@@ -1648,11 +1680,16 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler,
 	action->name = devname;
 	action->dev_id = dev_id;
 
+	retval = irq_chip_pm_get(&desc->irq_data);
+	if (retval < 0)
+		return retval;
+
 	chip_bus_lock(desc);
 	retval = __setup_irq(irq, desc, action);
 	chip_bus_sync_unlock(desc);
 
 	if (retval) {
+		irq_chip_pm_put(&desc->irq_data);
 		kfree(action->secondary);
 		kfree(action);
 	}
@@ -1730,7 +1767,14 @@ void enable_percpu_irq(unsigned int irq, unsigned int type)
 	if (!desc)
 		return;
 
+	/*
+	 * If the trigger type is not specified by the caller, then
+	 * use the default for this interrupt.
+	 */
 	type &= IRQ_TYPE_SENSE_MASK;
+	if (type == IRQ_TYPE_NONE)
+		type = irqd_get_trigger_type(&desc->irq_data);
+
 	if (type != IRQ_TYPE_NONE) {
 		int ret;
 
@@ -1822,6 +1866,7 @@ static struct irqaction *__free_percpu_irq(unsigned int irq, void __percpu *dev_
 
 	unregister_handler_proc(irq, action);
 
+	irq_chip_pm_put(&desc->irq_data);
 	module_put(desc->owner);
 	return action;
 
@@ -1884,10 +1929,18 @@ int setup_percpu_irq(unsigned int irq, struct irqaction *act)
 
 	if (!desc || !irq_settings_is_per_cpu_devid(desc))
 		return -EINVAL;
+
+	retval = irq_chip_pm_get(&desc->irq_data);
+	if (retval < 0)
+		return retval;
+
 	chip_bus_lock(desc);
 	retval = __setup_irq(irq, desc, act);
 	chip_bus_sync_unlock(desc);
 
+	if (retval)
+		irq_chip_pm_put(&desc->irq_data);
+
 	return retval;
 }
 
@@ -1931,12 +1984,18 @@ int request_percpu_irq(unsigned int irq, irq_handler_t handler,
 	action->name = devname;
 	action->percpu_dev_id = dev_id;
 
+	retval = irq_chip_pm_get(&desc->irq_data);
+	if (retval < 0)
+		return retval;
+
 	chip_bus_lock(desc);
 	retval = __setup_irq(irq, desc, action);
 	chip_bus_sync_unlock(desc);
 
-	if (retval)
+	if (retval) {
+		irq_chip_pm_put(&desc->irq_data);
 		kfree(action);
+	}
 
 	return retval;
 }

kernel/irq/msi.c

@@ -324,7 +324,7 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
 	struct msi_domain_ops *ops = info->ops;
 	msi_alloc_info_t arg;
 	struct msi_desc *desc;
-	int i, ret, virq = -1;
+	int i, ret, virq;
 
 	ret = msi_domain_prepare_irqs(domain, dev, nvec, &arg);
 	if (ret)
@@ -332,13 +332,10 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
 
 	for_each_msi_entry(desc, dev) {
 		ops->set_desc(&arg, desc);
-		if (info->flags & MSI_FLAG_IDENTITY_MAP)
-			virq = (int)ops->get_hwirq(info, &arg);
-		else
-			virq = -1;
 
-		virq = __irq_domain_alloc_irqs(domain, virq, desc->nvec_used,
-					       dev_to_node(dev), &arg, false);
+		virq = __irq_domain_alloc_irqs(domain, -1, desc->nvec_used,
+					       dev_to_node(dev), &arg, false,
+					       desc->affinity);
 		if (virq < 0) {
 			ret = -ENOSPC;
 			if (ops->handle_error)
@@ -356,6 +353,7 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
 		ops->msi_finish(&arg, 0);
 
 	for_each_msi_entry(desc, dev) {
+		virq = desc->irq;
 		if (desc->nvec_used == 1)
 			dev_dbg(dev, "irq %d for MSI\n", virq);
 		else

kernel/irq/proc.c

@@ -96,7 +96,7 @@ static ssize_t write_irq_affinity(int type, struct file *file,
 	cpumask_var_t new_value;
 	int err;
 
-	if (!irq_can_set_affinity(irq) || no_irq_affinity)
+	if (!irq_can_set_affinity_usr(irq) || no_irq_affinity)
 		return -EIO;
 
 	if (!alloc_cpumask_var(&new_value, GFP_KERNEL))
@@ -311,7 +311,6 @@ void register_handler_proc(unsigned int irq, struct irqaction *action)
 					!name_unique(irq, action))
 		return;
 
-	memset(name, 0, MAX_NAMELEN);
 	snprintf(name, MAX_NAMELEN, "%s", action->name);
 
 	/* create /proc/irq/1234/handler/ */
@@ -340,7 +339,6 @@ void register_irq_proc(unsigned int irq, struct irq_desc *desc)
 	if (desc->dir)
 		goto out_unlock;
 
-	memset(name, 0, MAX_NAMELEN);
 	sprintf(name, "%d", irq);
 
 	/* create /proc/irq/1234 */
@@ -386,7 +384,6 @@ void unregister_irq_proc(unsigned int irq, struct irq_desc *desc)
 #endif
 	remove_proc_entry("spurious", desc->dir);
 
-	memset(name, 0, MAX_NAMELEN);
 	sprintf(name, "%u", irq);
 	remove_proc_entry(name, root_irq_dir);
 }
@@ -421,12 +418,8 @@ void init_irq_proc(void)
 	/*
 	 * Create entries for all existing IRQs.
 	 */
-	for_each_irq_desc(irq, desc) {
-		if (!desc)
-			continue;
-
+	for_each_irq_desc(irq, desc)
 		register_irq_proc(irq, desc);
-	}
 }
 
 #ifdef CONFIG_GENERIC_IRQ_SHOW