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

@@ -0,0 +1,22 @@
+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

@@ -0,0 +1,230 @@
+/*
+ *  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);
 	}
 }
 
@@ -224,8 +224,8 @@ 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)
+					     struct task_struct *idle)
 {
 	unsigned long secondary_startup_phys =
 		(unsigned long)virt_to_phys((void *)secondary_startup);

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 *),
@@ -339,15 +339,15 @@ out_unmap:
 	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)
+					     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)
+					     struct device_node *parent)
 {
 	return bcm7120_l2_intc_probe(dn, parent, bcm7120_l2_intc_iomap_3380,
 				     "BCM3380 L2");

drivers/irqchip/irq-brcmstb-l2.c

@@ -112,8 +112,8 @@ 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)
+					  struct device_node *parent)
 {
 	unsigned int clr = IRQ_NOREQUEST | IRQ_NOPROBE | IRQ_NOAUTOEN;
 	struct brcmstb_l2_intc_data *data;

drivers/irqchip/irq-gic-common.c

@@ -90,8 +90,8 @@ 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))
+		     void (*sync_access)(void))
 {
 	unsigned int i;
 

drivers/irqchip/irq-gic-pm.c

@@ -0,0 +1,184 @@
+/*
+ * 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
+ * The ITS_BASER structure - contains memory information, cached
- * value of BASER register configuration.
+ * value of BASER register configuration and ITS page size.
  */
 struct its_baser {
 	void		*base;
 	u64		val;
 	u32		order;
+	u32		psz;
 };
 
 /*
@@ -824,6 +825,182 @@ static const char *its_base_type_string[] = {
 	[GITS_BASER_TYPE_RESERVED7] 	= "Reserved (7)",
 };
 
+static u64 its_read_baser(struct its_node *its, struct its_baser *baser)
+{
+	u32 idx = baser - its->tables;
+
+	return readq_relaxed(its->base + GITS_BASER + (idx << 3));
+}
+
+static void its_write_baser(struct its_node *its, struct its_baser *baser,
+			    u64 val)
+{
+	u32 idx = baser - its->tables;
+
+	writeq_relaxed(val, its->base + GITS_BASER + (idx << 3));
+	baser->val = its_read_baser(its, baser);
+}
+
+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);
+	u32 alloc_pages;
+	void *base;
+	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);
+	}
+
+	base = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, order);
+	if (!base)
+		return -ENOMEM;
+
+retry_baser:
+	val = (virt_to_phys(base)				 |
+		(type << GITS_BASER_TYPE_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;
+		break;
+	case SZ_16K:
+		val |= GITS_BASER_PAGE_SIZE_16K;
+		break;
+	case SZ_64K:
+		val |= GITS_BASER_PAGE_SIZE_64K;
+		break;
+	}
+
+	its_write_baser(its, baser, val);
+	tmp = baser->val;
+
+	if ((val ^ tmp) & GITS_BASER_SHAREABILITY_MASK) {
+		/*
+		 * Shareability didn't stick. Just use
+		 * whatever the read reported, which is likely
+		 * to be the only thing this redistributor
+		 * supports. If that's zero, make it
+		 * non-cacheable as well.
+		 */
+		shr = tmp & GITS_BASER_SHAREABILITY_MASK;
+		if (!shr) {
+			cache = GITS_BASER_nC;
+			__flush_dcache_area(base, PAGE_ORDER_TO_SIZE(order));
+		}
+		goto retry_baser;
+	}
+
+	if ((val ^ tmp) & GITS_BASER_PAGE_SIZE_MASK) {
+		/*
+		 * Page size didn't stick. Let's try a smaller
+		 * size and retry. If we reach 4K, then
+		 * something is horribly wrong...
+		 */
+		free_pages((unsigned long)base, order);
+		baser->base = NULL;
+
+		switch (psz) {
+		case SZ_16K:
+			psz = SZ_4K;
+			goto retry_alloc_baser;
+		case SZ_64K:
+			psz = SZ_16K;
+			goto retry_alloc_baser;
+		}
+	}
+
+	if (val != tmp) {
+		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);
+		free_pages((unsigned long)base, order);
+		return -ENXIO;
+	}
+
+	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;
+}
+
+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;
@@ -837,167 +1014,52 @@ static void its_free_tables(struct its_node *its)
 	}
 }
 
-static int its_alloc_tables(const char *node_name, struct its_node *its)
+static int its_alloc_tables(struct its_node *its)
 {
-	int err;
+	u64 typer = readq_relaxed(its->base + GITS_TYPER);
-	int i;
+	u32 ids = GITS_TYPER_DEVBITS(typer);
-	int psz = SZ_64K;
 	u64 shr = GITS_BASER_InnerShareable;
-	u64 cache;
+	u64 cache = GITS_BASER_WaWb;
-	u64 typer;
+	u32 psz = SZ_64K;
-	u32 ids;
+	int err, i;
 
 	if (its->flags & ITS_FLAGS_WORKAROUND_CAVIUM_22375) {
 		/*
-		 * erratum 22375: only alloc 8MB table size
+		* erratum 22375: only alloc 8MB table size
-		 * erratum 24313: ignore memory access type
+		* erratum 24313: ignore memory access type
-		 */
+		*/
-		cache	= 0;
+		cache   = GITS_BASER_nCnB;
-		ids	= 0x14;			/* 20 bits, 8MB */
+		ids     = 0x14;                 /* 20 bits, 8MB */
-	} else {
-		cache	= GITS_BASER_WaWb;
-		typer	= readq_relaxed(its->base + GITS_TYPER);
-		ids	= GITS_TYPER_DEVBITS(typer);
 	}
 
 	its->device_ids = ids;
 
 	for (i = 0; i < GITS_BASER_NR_REGS; i++) {
-		u64 val = readq_relaxed(its->base + GITS_BASER + i * 8);
+		struct its_baser *baser = its->tables + i;
+		u64 val = its_read_baser(its, baser);
 		u64 type = GITS_BASER_TYPE(val);
-		u64 entry_size = GITS_BASER_ENTRY_SIZE(val);
+		u32 order = get_order(psz);
-		int order = get_order(psz);
+		bool indirect = false;
-		int alloc_pages;
-		u64 tmp;
-		void *base;
 
 		if (type == GITS_BASER_TYPE_NONE)
 			continue;
 
-		/*
+		if (type == GITS_BASER_TYPE_DEVICE)
-		 * Allocate as many entries as required to fit the
+			indirect = its_parse_baser_device(its, baser, psz, &order);
-		 * range of device IDs that the ITS can grok... The ID
+
-		 * space being incredibly sparse, this results in a
+		err = its_setup_baser(its, baser, cache, shr, psz, order, indirect);
-		 * massive waste of memory.
+		if (err < 0) {
-		 *
+			its_free_tables(its);
-		 * For other tables, only allocate a single page.
+			return err;
-		 */
-		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);
-			}
 		}
 
-retry_alloc_baser:
+		/* Update settings which will be used for next BASERn */
-		alloc_pages = (PAGE_ORDER_TO_SIZE(order) / psz);
+		psz = baser->psz;
-		if (alloc_pages > GITS_BASER_PAGES_MAX) {
+		cache = baser->val & GITS_BASER_CACHEABILITY_MASK;
-			alloc_pages = GITS_BASER_PAGES_MAX;
+		shr = baser->val & GITS_BASER_SHAREABILITY_MASK;
-			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;
-
-retry_baser:
-		val = (virt_to_phys(base) 				 |
-		       (type << GITS_BASER_TYPE_SHIFT)			 |
-		       ((entry_size - 1) << GITS_BASER_ENTRY_SIZE_SHIFT) |
-		       cache						 |
-		       shr						 |
-		       GITS_BASER_VALID);
-
-		switch (psz) {
-		case SZ_4K:
-			val |= GITS_BASER_PAGE_SIZE_4K;
-			break;
-		case SZ_16K:
-			val |= GITS_BASER_PAGE_SIZE_16K;
-			break;
-		case SZ_64K:
-			val |= GITS_BASER_PAGE_SIZE_64K;
-			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);
-
-		if ((val ^ tmp) & GITS_BASER_SHAREABILITY_MASK) {
-			/*
-			 * Shareability didn't stick. Just use
-			 * whatever the read reported, which is likely
-			 * to be the only thing this redistributor
-			 * supports. If that's zero, make it
-			 * non-cacheable as well.
-			 */
-			shr = tmp & GITS_BASER_SHAREABILITY_MASK;
-			if (!shr) {
-				cache = GITS_BASER_nC;
-				__flush_dcache_area(base, PAGE_ORDER_TO_SIZE(order));
-			}
-			goto retry_baser;
-		}
-
-		if ((val ^ tmp) & GITS_BASER_PAGE_SIZE_MASK) {
-			/*
-			 * Page size didn't stick. Let's try a smaller
-			 * size and retry. If we reach 4K, then
-			 * something is horribly wrong...
-			 */
-			free_pages((unsigned long)base, order);
-			its->tables[i].base = NULL;
-
-			switch (psz) {
-			case SZ_16K:
-				psz = SZ_4K;
-				goto retry_alloc_baser;
-			case SZ_64K:
-				psz = SZ_16K;
-				goto retry_alloc_baser;
-			}
-		}
-
-		if (val != tmp) {
-			pr_err("ITS: %s: GITS_BASER%d doesn't stick: %lx %lx\n",
-			       node_name, i,
-			       (unsigned long) val, (unsigned long) tmp);
-			err = -ENXIO;
-			goto out_free;
-		}
-
-		pr_info("ITS: allocated %d %s @%lx (psz %dK, shr %d)\n",
-			(int)(PAGE_ORDER_TO_SIZE(order) / entry_size),
-			its_base_type_string[type],
-			(unsigned long)virt_to_phys(base),
-			psz / SZ_1K, (int)shr >> GITS_BASER_SHAREABILITY_SHIFT);
 	}
 
 	return 0;
-
-out_free:
-	its_free_tables(its);
-
-	return err;
 }
 
 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);
+	if (!its_alloc_device_table(its, dev_id))
-
-	/* 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)
 		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;