Merge tag 'irqchip-4.15' of git://git.kernel.org/pub/scm/linux/kernel/git/maz/arm-platforms into irq/core

Pull irqchip updates for 4.15 from Marc Zyngier

- GICv4 updates (improved performance, errata workarounds)
- Workaround for Socionext's pre-ITS erratum
- Meson GPIO interrupt controller
- BCM7271 L2 interrupt controller
- GICv3 range selector support
- various cleanups

Documentation/arm64/silicon-errata.txt

@@ -70,6 +70,7 @@ stable kernels.
 |                |                 |                 |                             |
 | Hisilicon      | Hip0{5,6,7}     | #161010101      | HISILICON_ERRATUM_161010101 |
 | Hisilicon      | Hip0{6,7}       | #161010701      | N/A                         |
+| Hisilicon      | Hip07           | #161600802      | HISILICON_ERRATUM_161600802 |
 |                |                 |                 |                             |
 | Qualcomm Tech. | Falkor v1       | E1003           | QCOM_FALKOR_ERRATUM_1003    |
 | Qualcomm Tech. | Falkor v1       | E1009           | QCOM_FALKOR_ERRATUM_1009    |

Documentation/devicetree/bindings/interrupt-controller/amlogic,meson-gpio-intc.txt

@@ -0,0 +1,35 @@
+Amlogic meson GPIO interrupt controller
+
+Meson SoCs contains an interrupt controller which is able to watch the SoC
+pads and generate an interrupt on edge or level. The controller is essentially
+a 256 pads to 8 GIC interrupt multiplexer, with a filter block to select edge
+or level and polarity. It does not expose all 256 mux inputs because the
+documentation shows that the upper part is not mapped to any pad. The actual
+number of interrupt exposed depends on the SoC.
+
+Required properties:
+
+- compatible : must have "amlogic,meson8-gpio-intc” and either
+   “amlogic,meson8b-gpio-intc” for meson8b SoCs (S805) or
+   “amlogic,meson-gxbb-gpio-intc” for GXBB SoCs (S905) or
+   “amlogic,meson-gxl-gpio-intc” for GXL SoCs (S905X, S912)
+- interrupt-parent : a phandle to the GIC the interrupts are routed to.
+   Usually this is provided at the root level of the device tree as it is
+   common to most of the SoC.
+- reg : Specifies base physical address and size of the registers.
+- interrupt-controller : Identifies the node as an interrupt controller.
+- #interrupt-cells : Specifies the number of cells needed to encode an
+   interrupt source. The value must be 2.
+- meson,channel-interrupts: Array with the 8 upstream hwirq numbers. These
+   are the hwirqs used on the parent interrupt controller.
+
+Example:
+
+gpio_interrupt: interrupt-controller@9880 {
+	compatible = "amlogic,meson-gxbb-gpio-intc",
+		     "amlogic,meson-gpio-intc";
+	reg = <0x0 0x9880 0x0 0x10>;
+	interrupt-controller;
+	#interrupt-cells = <2>;
+	meson,channel-interrupts = <64 65 66 67 68 69 70 71>;
+};

Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.txt

@@ -75,6 +75,10 @@ These nodes must have the following properties:
 - reg: Specifies the base physical address and size of the ITS
   registers.
 
+Optional:
+- socionext,synquacer-pre-its: (u32, u32) tuple describing the untranslated
+  address and size of the pre-ITS window.
+
 The main GIC node must contain the appropriate #address-cells,
 #size-cells and ranges properties for the reg property of all ITS
 nodes.

Documentation/devicetree/bindings/interrupt-controller/brcm,l2-intc.txt

@@ -2,7 +2,8 @@ Broadcom Generic Level 2 Interrupt Controller
 
 Required properties:
 
-- compatible: should be "brcm,l2-intc"
+- compatible: should be "brcm,l2-intc" for latched interrupt controllers
+              should be "brcm,bcm7271-l2-intc" for level interrupt controllers
 - reg: specifies the base physical address and size of the registers
 - interrupt-controller: identifies the node as an interrupt controller
 - #interrupt-cells: specifies the number of cells needed to encode an

Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.txt

@@ -13,6 +13,9 @@ Required properties:
     - "renesas,irqc-r8a7793" (R-Car M2-N)
     - "renesas,irqc-r8a7794" (R-Car E2)
     - "renesas,intc-ex-r8a7795" (R-Car H3)
+    - "renesas,intc-ex-r8a7796" (R-Car M3-W)
+    - "renesas,intc-ex-r8a77970" (R-Car V3M)
+    - "renesas,intc-ex-r8a77995" (R-Car D3)
 - #interrupt-cells: has to be <2>: an interrupt index and flags, as defined in
   interrupts.txt in this directory
 - clocks: Must contain a reference to the functional clock.

arch/arm/include/asm/arch_gicv3.h

@@ -196,6 +196,11 @@ static inline void gic_write_ctlr(u32 val)
 	isb();
 }
 
+static inline u32 gic_read_ctlr(void)
+{
+	return read_sysreg(ICC_CTLR);
+}
+
 static inline void gic_write_grpen1(u32 val)
 {
 	write_sysreg(val, ICC_IGRPEN1);

arch/arm64/Kconfig

@@ -539,6 +539,25 @@ config QCOM_QDF2400_ERRATUM_0065
 
 	  If unsure, say Y.
 
+
+config SOCIONEXT_SYNQUACER_PREITS
+	bool "Socionext Synquacer: Workaround for GICv3 pre-ITS"
+	default y
+	help
+	  Socionext Synquacer SoCs implement a separate h/w block to generate
+	  MSI doorbell writes with non-zero values for the device ID.
+
+	  If unsure, say Y.
+
+config HISILICON_ERRATUM_161600802
+	bool "Hip07 161600802: Erroneous redistributor VLPI base"
+	default y
+	help
+	  The HiSilicon Hip07 SoC usees the wrong redistributor base
+	  when issued ITS commands such as VMOVP and VMAPP, and requires
+	  a 128kB offset to be applied to the target address in this commands.
+
+	  If unsure, say Y.
 endmenu
 
 

arch/arm64/include/asm/arch_gicv3.h

@@ -87,6 +87,11 @@ static inline void gic_write_ctlr(u32 val)
 	isb();
 }
 
+static inline u32 gic_read_ctlr(void)
+{
+	return read_sysreg_s(SYS_ICC_CTLR_EL1);
+}
+
 static inline void gic_write_grpen1(u32 val)
 {
 	write_sysreg_s(val, SYS_ICC_IGRPEN1_EL1);

drivers/irqchip/Kconfig

@@ -324,4 +324,12 @@ config IRQ_UNIPHIER_AIDET
 	help
 	  Support for the UniPhier AIDET (ARM Interrupt Detector).
 
+config MESON_IRQ_GPIO
+       bool "Meson GPIO Interrupt Multiplexer"
+       depends on ARCH_MESON || COMPILE_TEST
+       select IRQ_DOMAIN
+       select IRQ_DOMAIN_HIERARCHY
+       help
+         Support Meson SoC Family GPIO Interrupt Multiplexer
+
 endmenu

drivers/irqchip/Makefile

@@ -79,3 +79,4 @@ obj-$(CONFIG_ARCH_ASPEED)		+= irq-aspeed-vic.o irq-aspeed-i2c-ic.o
 obj-$(CONFIG_STM32_EXTI) 		+= irq-stm32-exti.o
 obj-$(CONFIG_QCOM_IRQ_COMBINER)		+= qcom-irq-combiner.o
 obj-$(CONFIG_IRQ_UNIPHIER_AIDET)	+= irq-uniphier-aidet.o
+obj-$(CONFIG_MESON_IRQ_GPIO)		+= irq-meson-gpio.o

drivers/irqchip/irq-aspeed-i2c-ic.c

@@ -76,8 +76,8 @@ static int __init aspeed_i2c_ic_of_init(struct device_node *node,
 		return -ENOMEM;
 
 	i2c_ic->base = of_iomap(node, 0);
-	if (IS_ERR(i2c_ic->base)) {
-		ret = PTR_ERR(i2c_ic->base);
+	if (!i2c_ic->base) {
+		ret = -ENOMEM;
 		goto err_free_ic;
 	}
 

drivers/irqchip/irq-brcmstb-l2.c

@@ -1,7 +1,7 @@
 /*
  * Generic Broadcom Set Top Box Level 2 Interrupt controller driver
  *
- * Copyright (C) 2014 Broadcom Corporation
+ * Copyright (C) 2014-2017 Broadcom
  *
  * 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
@@ -31,35 +31,82 @@
 #include <linux/irqchip.h>
 #include <linux/irqchip/chained_irq.h>
 
-/* Register offsets in the L2 interrupt controller */
-#define CPU_STATUS	0x00
-#define CPU_SET		0x04
-#define CPU_CLEAR	0x08
-#define CPU_MASK_STATUS	0x0c
-#define CPU_MASK_SET	0x10
-#define CPU_MASK_CLEAR	0x14
+struct brcmstb_intc_init_params {
+	irq_flow_handler_t handler;
+	int cpu_status;
+	int cpu_clear;
+	int cpu_mask_status;
+	int cpu_mask_set;
+	int cpu_mask_clear;
+};
+
+/* Register offsets in the L2 latched interrupt controller */
+static const struct brcmstb_intc_init_params l2_edge_intc_init = {
+	.handler		= handle_edge_irq,
+	.cpu_status		= 0x00,
+	.cpu_clear		= 0x08,
+	.cpu_mask_status	= 0x0c,
+	.cpu_mask_set		= 0x10,
+	.cpu_mask_clear		= 0x14
+};
+
+/* Register offsets in the L2 level interrupt controller */
+static const struct brcmstb_intc_init_params l2_lvl_intc_init = {
+	.handler		= handle_level_irq,
+	.cpu_status		= 0x00,
+	.cpu_clear		= -1, /* Register not present */
+	.cpu_mask_status	= 0x04,
+	.cpu_mask_set		= 0x08,
+	.cpu_mask_clear		= 0x0C
+};
 
 /* L2 intc private data structure */
 struct brcmstb_l2_intc_data {
-	int parent_irq;
-	void __iomem *base;
 	struct irq_domain *domain;
+	struct irq_chip_generic *gc;
+	int status_offset;
+	int mask_offset;
 	bool can_wake;
 	u32 saved_mask; /* for suspend/resume */
 };
 
+/**
+ * brcmstb_l2_mask_and_ack - Mask and ack pending interrupt
+ * @d: irq_data
+ *
+ * Chip has separate enable/disable registers instead of a single mask
+ * register and pending interrupt is acknowledged by setting a bit.
+ *
+ * Note: This function is generic and could easily be added to the
+ * generic irqchip implementation if there ever becomes a will to do so.
+ * Perhaps with a name like irq_gc_mask_disable_and_ack_set().
+ *
+ * e.g.: https://patchwork.kernel.org/patch/9831047/
+ */
+static void brcmstb_l2_mask_and_ack(struct irq_data *d)
+{
+	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
+	struct irq_chip_type *ct = irq_data_get_chip_type(d);
+	u32 mask = d->mask;
+
+	irq_gc_lock(gc);
+	irq_reg_writel(gc, mask, ct->regs.disable);
+	*ct->mask_cache &= ~mask;
+	irq_reg_writel(gc, mask, ct->regs.ack);
+	irq_gc_unlock(gc);
+}
+
 static void brcmstb_l2_intc_irq_handle(struct irq_desc *desc)
 {
 	struct brcmstb_l2_intc_data *b = irq_desc_get_handler_data(desc);
-	struct irq_chip_generic *gc = irq_get_domain_generic_chip(b->domain, 0);
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 	unsigned int irq;
 	u32 status;
 
 	chained_irq_enter(chip, desc);
 
-	status = irq_reg_readl(gc, CPU_STATUS) &
-		~(irq_reg_readl(gc, CPU_MASK_STATUS));
+	status = irq_reg_readl(b->gc, b->status_offset) &
+		~(irq_reg_readl(b->gc, b->mask_offset));
 
 	if (status == 0) {
 		raw_spin_lock(&desc->lock);
@@ -70,10 +117,8 @@ static void brcmstb_l2_intc_irq_handle(struct irq_desc *desc)
 
 	do {
 		irq = ffs(status) - 1;
-		/* ack at our level */
-		irq_reg_writel(gc, 1 << irq, CPU_CLEAR);
 		status &= ~(1 << irq);
-		generic_handle_irq(irq_find_mapping(b->domain, irq));
+		generic_handle_irq(irq_linear_revmap(b->domain, irq));
 	} while (status);
 out:
 	chained_irq_exit(chip, desc);
@@ -82,16 +127,17 @@ out:
 static void brcmstb_l2_intc_suspend(struct irq_data *d)
 {
 	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
+	struct irq_chip_type *ct = irq_data_get_chip_type(d);
 	struct brcmstb_l2_intc_data *b = gc->private;
 
 	irq_gc_lock(gc);
 	/* Save the current mask */
-	b->saved_mask = irq_reg_readl(gc, CPU_MASK_STATUS);
+	b->saved_mask = irq_reg_readl(gc, ct->regs.mask);
 
 	if (b->can_wake) {
 		/* Program the wakeup mask */
-		irq_reg_writel(gc, ~gc->wake_active, CPU_MASK_SET);
-		irq_reg_writel(gc, gc->wake_active, CPU_MASK_CLEAR);
+		irq_reg_writel(gc, ~gc->wake_active, ct->regs.disable);
+		irq_reg_writel(gc, gc->wake_active, ct->regs.enable);
 	}
 	irq_gc_unlock(gc);
 }
@@ -99,49 +145,56 @@ static void brcmstb_l2_intc_suspend(struct irq_data *d)
 static void brcmstb_l2_intc_resume(struct irq_data *d)
 {
 	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
+	struct irq_chip_type *ct = irq_data_get_chip_type(d);
 	struct brcmstb_l2_intc_data *b = gc->private;
 
 	irq_gc_lock(gc);
-	/* Clear unmasked non-wakeup interrupts */
-	irq_reg_writel(gc, ~b->saved_mask & ~gc->wake_active, CPU_CLEAR);
+	if (ct->chip.irq_ack) {
+		/* Clear unmasked non-wakeup interrupts */
+		irq_reg_writel(gc, ~b->saved_mask & ~gc->wake_active,
+				ct->regs.ack);
+	}
 
 	/* Restore the saved mask */
-	irq_reg_writel(gc, b->saved_mask, CPU_MASK_SET);
-	irq_reg_writel(gc, ~b->saved_mask, CPU_MASK_CLEAR);
+	irq_reg_writel(gc, b->saved_mask, ct->regs.disable);
+	irq_reg_writel(gc, ~b->saved_mask, ct->regs.enable);
 	irq_gc_unlock(gc);
 }
 
 static int __init brcmstb_l2_intc_of_init(struct device_node *np,
-					  struct device_node *parent)
+					  struct device_node *parent,
+					  const struct brcmstb_intc_init_params
+					  *init_params)
 {
 	unsigned int clr = IRQ_NOREQUEST | IRQ_NOPROBE | IRQ_NOAUTOEN;
 	struct brcmstb_l2_intc_data *data;
-	struct irq_chip_generic *gc;
 	struct irq_chip_type *ct;
 	int ret;
 	unsigned int flags;
+	int parent_irq;
+	void __iomem *base;
 
 	data = kzalloc(sizeof(*data), GFP_KERNEL);
 	if (!data)
 		return -ENOMEM;
 
-	data->base = of_iomap(np, 0);
-	if (!data->base) {
+	base = of_iomap(np, 0);
+	if (!base) {
 		pr_err("failed to remap intc L2 registers\n");
 		ret = -ENOMEM;
 		goto out_free;
 	}
 
 	/* Disable all interrupts by default */
-	writel(0xffffffff, data->base + CPU_MASK_SET);
+	writel(0xffffffff, base + init_params->cpu_mask_set);
 
 	/* Wakeup interrupts may be retained from S5 (cold boot) */
 	data->can_wake = of_property_read_bool(np, "brcm,irq-can-wake");
-	if (!data->can_wake)
-		writel(0xffffffff, data->base + CPU_CLEAR);
+	if (!data->can_wake && (init_params->cpu_clear >= 0))
+		writel(0xffffffff, base + init_params->cpu_clear);
 
-	data->parent_irq = irq_of_parse_and_map(np, 0);
-	if (!data->parent_irq) {
+	parent_irq = irq_of_parse_and_map(np, 0);
+	if (!parent_irq) {
 		pr_err("failed to find parent interrupt\n");
 		ret = -EINVAL;
 		goto out_unmap;
@@ -163,29 +216,39 @@ static int __init brcmstb_l2_intc_of_init(struct device_node *np,
 
 	/* Allocate a single Generic IRQ chip for this node */
 	ret = irq_alloc_domain_generic_chips(data->domain, 32, 1,
-				np->full_name, handle_edge_irq, clr, 0, flags);
+			np->full_name, init_params->handler, clr, 0, flags);
 	if (ret) {
 		pr_err("failed to allocate generic irq chip\n");
 		goto out_free_domain;
 	}
 
 	/* Set the IRQ chaining logic */
-	irq_set_chained_handler_and_data(data->parent_irq,
+	irq_set_chained_handler_and_data(parent_irq,
 					 brcmstb_l2_intc_irq_handle, data);
 
-	gc = irq_get_domain_generic_chip(data->domain, 0);
-	gc->reg_base = data->base;
-	gc->private = data;
-	ct = gc->chip_types;
-
-	ct->chip.irq_ack = irq_gc_ack_set_bit;
-	ct->regs.ack = CPU_CLEAR;
+	data->gc = irq_get_domain_generic_chip(data->domain, 0);
+	data->gc->reg_base = base;
+	data->gc->private = data;
+	data->status_offset = init_params->cpu_status;
+	data->mask_offset = init_params->cpu_mask_status;
+
+	ct = data->gc->chip_types;
+
+	if (init_params->cpu_clear >= 0) {
+		ct->regs.ack = init_params->cpu_clear;
+		ct->chip.irq_ack = irq_gc_ack_set_bit;
+		ct->chip.irq_mask_ack = brcmstb_l2_mask_and_ack;
+	} else {
+		/* No Ack - but still slightly more efficient to define this */
+		ct->chip.irq_mask_ack = irq_gc_mask_disable_reg;
+	}
 
 	ct->chip.irq_mask = irq_gc_mask_disable_reg;
-	ct->regs.disable = CPU_MASK_SET;
+	ct->regs.disable = init_params->cpu_mask_set;
+	ct->regs.mask = init_params->cpu_mask_status;
 
 	ct->chip.irq_unmask = irq_gc_unmask_enable_reg;
-	ct->regs.enable = CPU_MASK_CLEAR;
+	ct->regs.enable = init_params->cpu_mask_clear;
 
 	ct->chip.irq_suspend = brcmstb_l2_intc_suspend;
 	ct->chip.irq_resume = brcmstb_l2_intc_resume;
@@ -195,21 +258,35 @@ static int __init brcmstb_l2_intc_of_init(struct device_node *np,
 		/* This IRQ chip can wake the system, set all child interrupts
 		 * in wake_enabled mask
 		 */
-		gc->wake_enabled = 0xffffffff;
+		data->gc->wake_enabled = 0xffffffff;
 		ct->chip.irq_set_wake = irq_gc_set_wake;
 	}
 
 	pr_info("registered L2 intc (mem: 0x%p, parent irq: %d)\n",
-			data->base, data->parent_irq);
+			base, parent_irq);
 
 	return 0;
 
 out_free_domain:
 	irq_domain_remove(data->domain);
 out_unmap:
-	iounmap(data->base);
+	iounmap(base);
 out_free:
 	kfree(data);
 	return ret;
 }
-IRQCHIP_DECLARE(brcmstb_l2_intc, "brcm,l2-intc", brcmstb_l2_intc_of_init);
+
+int __init brcmstb_l2_edge_intc_of_init(struct device_node *np,
+	struct device_node *parent)
+{
+	return brcmstb_l2_intc_of_init(np, parent, &l2_edge_intc_init);
+}
+IRQCHIP_DECLARE(brcmstb_l2_intc, "brcm,l2-intc", brcmstb_l2_edge_intc_of_init);
+
+int __init brcmstb_l2_lvl_intc_of_init(struct device_node *np,
+	struct device_node *parent)
+{
+	return brcmstb_l2_intc_of_init(np, parent, &l2_lvl_intc_init);
+}
+IRQCHIP_DECLARE(bcm7271_l2_intc, "brcm,bcm7271-l2-intc",
+	brcmstb_l2_lvl_intc_of_init);

drivers/irqchip/irq-gic-common.c

@@ -40,8 +40,9 @@ void gic_enable_quirks(u32 iidr, const struct gic_quirk *quirks,
 	for (; quirks->desc; quirks++) {
 		if (quirks->iidr != (quirks->mask & iidr))
 			continue;
-		quirks->init(data);
-		pr_info("GIC: enabling workaround for %s\n", quirks->desc);
+		if (quirks->init(data))
+			pr_info("GIC: enabling workaround for %s\n",
+				quirks->desc);
 	}
 }
 

drivers/irqchip/irq-gic-common.h

@@ -23,7 +23,7 @@
 
 struct gic_quirk {
 	const char *desc;
-	void (*init)(void *data);
+	bool (*init)(void *data);
 	u32 iidr;
 	u32 mask;
 };

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

@@ -83,6 +83,8 @@ struct its_baser {
 	u32		psz;
 };
 
+struct its_device;
+
 /*
  * The ITS structure - contains most of the infrastructure, with the
  * top-level MSI domain, the command queue, the collections, and the
@@ -97,12 +99,18 @@ struct its_node {
 	struct its_cmd_block	*cmd_write;
 	struct its_baser	tables[GITS_BASER_NR_REGS];
 	struct its_collection	*collections;
+	struct fwnode_handle	*fwnode_handle;
+	u64			(*get_msi_base)(struct its_device *its_dev);
 	struct list_head	its_device_list;
 	u64			flags;
+	unsigned long		list_nr;
 	u32			ite_size;
 	u32			device_ids;
 	int			numa_node;
+	unsigned int		msi_domain_flags;
+	u32			pre_its_base; /* for Socionext Synquacer */
 	bool			is_v4;
+	int			vlpi_redist_offset;
 };
 
 #define ITS_ITT_ALIGN		SZ_256
@@ -148,12 +156,6 @@ static DEFINE_SPINLOCK(its_lock);
 static struct rdists *gic_rdists;
 static struct irq_domain *its_parent;
 
-/*
- * We have a maximum number of 16 ITSs in the whole system if we're
- * using the ITSList mechanism
- */
-#define ITS_LIST_MAX		16
-
 static unsigned long its_list_map;
 static u16 vmovp_seq_num;
 static DEFINE_RAW_SPINLOCK(vmovp_lock);
@@ -268,10 +270,12 @@ struct its_cmd_block {
 #define ITS_CMD_QUEUE_SZ		SZ_64K
 #define ITS_CMD_QUEUE_NR_ENTRIES	(ITS_CMD_QUEUE_SZ / sizeof(struct its_cmd_block))
 
-typedef struct its_collection *(*its_cmd_builder_t)(struct its_cmd_block *,
+typedef struct its_collection *(*its_cmd_builder_t)(struct its_node *,
+						    struct its_cmd_block *,
 						    struct its_cmd_desc *);
 
-typedef struct its_vpe *(*its_cmd_vbuilder_t)(struct its_cmd_block *,
+typedef struct its_vpe *(*its_cmd_vbuilder_t)(struct its_node *,
+					      struct its_cmd_block *,
 					      struct its_cmd_desc *);
 
 static void its_mask_encode(u64 *raw_cmd, u64 val, int h, int l)
@@ -375,7 +379,8 @@ static inline void its_fixup_cmd(struct its_cmd_block *cmd)
 	cmd->raw_cmd[3] = cpu_to_le64(cmd->raw_cmd[3]);
 }
 
-static struct its_collection *its_build_mapd_cmd(struct its_cmd_block *cmd,
+static struct its_collection *its_build_mapd_cmd(struct its_node *its,
+						 struct its_cmd_block *cmd,
 						 struct its_cmd_desc *desc)
 {
 	unsigned long itt_addr;
@@ -395,7 +400,8 @@ static struct its_collection *its_build_mapd_cmd(struct its_cmd_block *cmd,
 	return NULL;
 }
 
-static struct its_collection *its_build_mapc_cmd(struct its_cmd_block *cmd,
+static struct its_collection *its_build_mapc_cmd(struct its_node *its,
+						 struct its_cmd_block *cmd,
 						 struct its_cmd_desc *desc)
 {
 	its_encode_cmd(cmd, GITS_CMD_MAPC);
@@ -408,7 +414,8 @@ static struct its_collection *its_build_mapc_cmd(struct its_cmd_block *cmd,
 	return desc->its_mapc_cmd.col;
 }
 
-static struct its_collection *its_build_mapti_cmd(struct its_cmd_block *cmd,
+static struct its_collection *its_build_mapti_cmd(struct its_node *its,
+						  struct its_cmd_block *cmd,
 						  struct its_cmd_desc *desc)
 {
 	struct its_collection *col;
@@ -427,7 +434,8 @@ static struct its_collection *its_build_mapti_cmd(struct its_cmd_block *cmd,
 	return col;
 }
 
-static struct its_collection *its_build_movi_cmd(struct its_cmd_block *cmd,
+static struct its_collection *its_build_movi_cmd(struct its_node *its,
+						 struct its_cmd_block *cmd,
 						 struct its_cmd_desc *desc)
 {
 	struct its_collection *col;
@@ -445,7 +453,8 @@ static struct its_collection *its_build_movi_cmd(struct its_cmd_block *cmd,
 	return col;
 }
 
-static struct its_collection *its_build_discard_cmd(struct its_cmd_block *cmd,
+static struct its_collection *its_build_discard_cmd(struct its_node *its,
+						    struct its_cmd_block *cmd,
 						    struct its_cmd_desc *desc)
 {
 	struct its_collection *col;
@@ -462,7 +471,8 @@ static struct its_collection *its_build_discard_cmd(struct its_cmd_block *cmd,
 	return col;
 }
 
-static struct its_collection *its_build_inv_cmd(struct its_cmd_block *cmd,
+static struct its_collection *its_build_inv_cmd(struct its_node *its,
+						struct its_cmd_block *cmd,
 						struct its_cmd_desc *desc)
 {
 	struct its_collection *col;
@@ -479,7 +489,8 @@ static struct its_collection *its_build_inv_cmd(struct its_cmd_block *cmd,
 	return col;
 }
 
-static struct its_collection *its_build_int_cmd(struct its_cmd_block *cmd,
+static struct its_collection *its_build_int_cmd(struct its_node *its,
+						struct its_cmd_block *cmd,
 						struct its_cmd_desc *desc)
 {
 	struct its_collection *col;
@@ -496,7 +507,8 @@ static struct its_collection *its_build_int_cmd(struct its_cmd_block *cmd,
 	return col;
 }
 
-static struct its_collection *its_build_clear_cmd(struct its_cmd_block *cmd,
+static struct its_collection *its_build_clear_cmd(struct its_node *its,
+						  struct its_cmd_block *cmd,
 						  struct its_cmd_desc *desc)
 {
 	struct its_collection *col;
@@ -513,7 +525,8 @@ static struct its_collection *its_build_clear_cmd(struct its_cmd_block *cmd,
 	return col;
 }
 
-static struct its_collection *its_build_invall_cmd(struct its_cmd_block *cmd,
+static struct its_collection *its_build_invall_cmd(struct its_node *its,
+						   struct its_cmd_block *cmd,
 						   struct its_cmd_desc *desc)
 {
 	its_encode_cmd(cmd, GITS_CMD_INVALL);
@@ -524,7 +537,8 @@ static struct its_collection *its_build_invall_cmd(struct its_cmd_block *cmd,
 	return NULL;
 }
 
-static struct its_vpe *its_build_vinvall_cmd(struct its_cmd_block *cmd,
+static struct its_vpe *its_build_vinvall_cmd(struct its_node *its,
+					     struct its_cmd_block *cmd,
 					     struct its_cmd_desc *desc)
 {
 	its_encode_cmd(cmd, GITS_CMD_VINVALL);
@@ -535,17 +549,20 @@ static struct its_vpe *its_build_vinvall_cmd(struct its_cmd_block *cmd,
 	return desc->its_vinvall_cmd.vpe;
 }
 
-static struct its_vpe *its_build_vmapp_cmd(struct its_cmd_block *cmd,
+static struct its_vpe *its_build_vmapp_cmd(struct its_node *its,
+					   struct its_cmd_block *cmd,
 					   struct its_cmd_desc *desc)
 {
 	unsigned long vpt_addr;
+	u64 target;
 
 	vpt_addr = virt_to_phys(page_address(desc->its_vmapp_cmd.vpe->vpt_page));
+	target = desc->its_vmapp_cmd.col->target_address + its->vlpi_redist_offset;
 
 	its_encode_cmd(cmd, GITS_CMD_VMAPP);
 	its_encode_vpeid(cmd, desc->its_vmapp_cmd.vpe->vpe_id);
 	its_encode_valid(cmd, desc->its_vmapp_cmd.valid);
-	its_encode_target(cmd, desc->its_vmapp_cmd.col->target_address);
+	its_encode_target(cmd, target);
 	its_encode_vpt_addr(cmd, vpt_addr);
 	its_encode_vpt_size(cmd, LPI_NRBITS - 1);
 
@@ -554,7 +571,8 @@ static struct its_vpe *its_build_vmapp_cmd(struct its_cmd_block *cmd,
 	return desc->its_vmapp_cmd.vpe;
 }
 
-static struct its_vpe *its_build_vmapti_cmd(struct its_cmd_block *cmd,
+static struct its_vpe *its_build_vmapti_cmd(struct its_node *its,
+					    struct its_cmd_block *cmd,
 					    struct its_cmd_desc *desc)
 {
 	u32 db;
@@ -576,7 +594,8 @@ static struct its_vpe *its_build_vmapti_cmd(struct its_cmd_block *cmd,
 	return desc->its_vmapti_cmd.vpe;
 }
 
-static struct its_vpe *its_build_vmovi_cmd(struct its_cmd_block *cmd,
+static struct its_vpe *its_build_vmovi_cmd(struct its_node *its,
+					   struct its_cmd_block *cmd,
 					   struct its_cmd_desc *desc)
 {
 	u32 db;
@@ -598,14 +617,18 @@ static struct its_vpe *its_build_vmovi_cmd(struct its_cmd_block *cmd,
 	return desc->its_vmovi_cmd.vpe;
 }
 
-static struct its_vpe *its_build_vmovp_cmd(struct its_cmd_block *cmd,
+static struct its_vpe *its_build_vmovp_cmd(struct its_node *its,
+					   struct its_cmd_block *cmd,
 					   struct its_cmd_desc *desc)
 {
+	u64 target;
+
+	target = desc->its_vmovp_cmd.col->target_address + its->vlpi_redist_offset;
 	its_encode_cmd(cmd, GITS_CMD_VMOVP);
 	its_encode_seq_num(cmd, desc->its_vmovp_cmd.seq_num);
 	its_encode_its_list(cmd, desc->its_vmovp_cmd.its_list);
 	its_encode_vpeid(cmd, desc->its_vmovp_cmd.vpe->vpe_id);
-	its_encode_target(cmd, desc->its_vmovp_cmd.col->target_address);
+	its_encode_target(cmd, target);
 
 	its_fixup_cmd(cmd);
 
@@ -684,9 +707,9 @@ static void its_flush_cmd(struct its_node *its, struct its_cmd_block *cmd)
 		dsb(ishst);
 }
 
-static void its_wait_for_range_completion(struct its_node *its,
-					  struct its_cmd_block *from,
-					  struct its_cmd_block *to)
+static int its_wait_for_range_completion(struct its_node *its,
+					 struct its_cmd_block *from,
+					 struct its_cmd_block *to)
 {
 	u64 rd_idx, from_idx, to_idx;
 	u32 count = 1000000;	/* 1s! */
@@ -707,12 +730,15 @@ static void its_wait_for_range_completion(struct its_node *its,
 
 		count--;
 		if (!count) {
-			pr_err_ratelimited("ITS queue timeout\n");
-			return;
+			pr_err_ratelimited("ITS queue timeout (%llu %llu %llu)\n",
+					   from_idx, to_idx, rd_idx);
+			return -1;
 		}
 		cpu_relax();
 		udelay(1);
 	}
+
+	return 0;
 }
 
 /* Warning, macro hell follows */
@@ -732,7 +758,7 @@ void name(struct its_node *its,						\
 		raw_spin_unlock_irqrestore(&its->lock, flags);		\
 		return;							\
 	}								\
-	sync_obj = builder(cmd, desc);					\
+	sync_obj = builder(its, cmd, desc);				\
 	its_flush_cmd(its, cmd);					\
 									\
 	if (sync_obj) {							\
@@ -740,7 +766,7 @@ void name(struct its_node *its,						\
 		if (!sync_cmd)						\
 			goto post;					\
 									\
-		buildfn(sync_cmd, sync_obj);				\
+		buildfn(its, sync_cmd, sync_obj);			\
 		its_flush_cmd(its, sync_cmd);				\
 	}								\
 									\
@@ -748,10 +774,12 @@ post:									\
 	next_cmd = its_post_commands(its);				\
 	raw_spin_unlock_irqrestore(&its->lock, flags);			\
 									\
-	its_wait_for_range_completion(its, cmd, next_cmd);		\
+	if (its_wait_for_range_completion(its, cmd, next_cmd))		\
+		pr_err_ratelimited("ITS cmd %ps failed\n", builder);	\
 }
 
-static void its_build_sync_cmd(struct its_cmd_block *sync_cmd,
+static void its_build_sync_cmd(struct its_node *its,
+			       struct its_cmd_block *sync_cmd,
 			       struct its_collection *sync_col)
 {
 	its_encode_cmd(sync_cmd, GITS_CMD_SYNC);
@@ -763,7 +791,8 @@ static void its_build_sync_cmd(struct its_cmd_block *sync_cmd,
 static BUILD_SINGLE_CMD_FUNC(its_send_single_command, its_cmd_builder_t,
 			     struct its_collection, its_build_sync_cmd)
 
-static void its_build_vsync_cmd(struct its_cmd_block *sync_cmd,
+static void its_build_vsync_cmd(struct its_node *its,
+				struct its_cmd_block *sync_cmd,
 				struct its_vpe *sync_vpe)
 {
 	its_encode_cmd(sync_cmd, GITS_CMD_VSYNC);
@@ -895,21 +924,16 @@ static void its_send_vmovi(struct its_device *dev, u32 id)
 	its_send_single_vcommand(dev->its, its_build_vmovi_cmd, &desc);
 }
 
-static void its_send_vmapp(struct its_vpe *vpe, bool valid)
+static void its_send_vmapp(struct its_node *its,
+			   struct its_vpe *vpe, bool valid)
 {
 	struct its_cmd_desc desc;
-	struct its_node *its;
 
 	desc.its_vmapp_cmd.vpe = vpe;
 	desc.its_vmapp_cmd.valid = valid;
+	desc.its_vmapp_cmd.col = &its->collections[vpe->col_idx];
 
-	list_for_each_entry(its, &its_nodes, entry) {
-		if (!its->is_v4)
-			continue;
-
-		desc.its_vmapp_cmd.col = &its->collections[vpe->col_idx];
-		its_send_single_vcommand(its, its_build_vmapp_cmd, &desc);
-	}
+	its_send_single_vcommand(its, its_build_vmapp_cmd, &desc);
 }
 
 static void its_send_vmovp(struct its_vpe *vpe)
@@ -947,6 +971,9 @@ static void its_send_vmovp(struct its_vpe *vpe)
 		if (!its->is_v4)
 			continue;
 
+		if (!vpe->its_vm->vlpi_count[its->list_nr])
+			continue;
+
 		desc.its_vmovp_cmd.col = &its->collections[col_id];
 		its_send_single_vcommand(its, its_build_vmovp_cmd, &desc);
 	}
@@ -954,18 +981,12 @@ static void its_send_vmovp(struct its_vpe *vpe)
 	raw_spin_unlock_irqrestore(&vmovp_lock, flags);
 }
 
-static void its_send_vinvall(struct its_vpe *vpe)
+static void its_send_vinvall(struct its_node *its, struct its_vpe *vpe)
 {
 	struct its_cmd_desc desc;
-	struct its_node *its;
 
 	desc.its_vinvall_cmd.vpe = vpe;
-
-	list_for_each_entry(its, &its_nodes, entry) {
-		if (!its->is_v4)
-			continue;
-		its_send_single_vcommand(its, its_build_vinvall_cmd, &desc);
-	}
+	its_send_single_vcommand(its, its_build_vinvall_cmd, &desc);
 }
 
 /*
@@ -1095,6 +1116,13 @@ static int its_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 	return IRQ_SET_MASK_OK_DONE;
 }
 
+static u64 its_irq_get_msi_base(struct its_device *its_dev)
+{
+	struct its_node *its = its_dev->its;
+
+	return its->phys_base + GITS_TRANSLATER;
+}
+
 static void its_irq_compose_msi_msg(struct irq_data *d, struct msi_msg *msg)
 {
 	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
@@ -1102,7 +1130,7 @@ static void its_irq_compose_msi_msg(struct irq_data *d, struct msi_msg *msg)
 	u64 addr;
 
 	its = its_dev->its;
-	addr = its->phys_base + GITS_TRANSLATER;
+	addr = its->get_msi_base(its_dev);
 
 	msg->address_lo		= lower_32_bits(addr);
 	msg->address_hi		= upper_32_bits(addr);
@@ -1129,6 +1157,60 @@ static int its_irq_set_irqchip_state(struct irq_data *d,
 	return 0;
 }
 
+static void its_map_vm(struct its_node *its, struct its_vm *vm)
+{
+	unsigned long flags;
+
+	/* Not using the ITS list? Everything is always mapped. */
+	if (!its_list_map)
+		return;
+
+	raw_spin_lock_irqsave(&vmovp_lock, flags);
+
+	/*
+	 * If the VM wasn't mapped yet, iterate over the vpes and get
+	 * them mapped now.
+	 */
+	vm->vlpi_count[its->list_nr]++;
+
+	if (vm->vlpi_count[its->list_nr] == 1) {
+		int i;
+
+		for (i = 0; i < vm->nr_vpes; i++) {
+			struct its_vpe *vpe = vm->vpes[i];
+			struct irq_data *d = irq_get_irq_data(vpe->irq);
+
+			/* Map the VPE to the first possible CPU */
+			vpe->col_idx = cpumask_first(cpu_online_mask);
+			its_send_vmapp(its, vpe, true);
+			its_send_vinvall(its, vpe);
+			irq_data_update_effective_affinity(d, cpumask_of(vpe->col_idx));
+		}
+	}
+
+	raw_spin_unlock_irqrestore(&vmovp_lock, flags);
+}
+
+static void its_unmap_vm(struct its_node *its, struct its_vm *vm)
+{
+	unsigned long flags;
+
+	/* Not using the ITS list? Everything is always mapped. */
+	if (!its_list_map)
+		return;
+
+	raw_spin_lock_irqsave(&vmovp_lock, flags);
+
+	if (!--vm->vlpi_count[its->list_nr]) {
+		int i;
+
+		for (i = 0; i < vm->nr_vpes; i++)
+			its_send_vmapp(its, vm->vpes[i], false);
+	}
+
+	raw_spin_unlock_irqrestore(&vmovp_lock, flags);
+}
+
 static int its_vlpi_map(struct irq_data *d, struct its_cmd_info *info)
 {
 	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
@@ -1164,6 +1246,9 @@ static int its_vlpi_map(struct irq_data *d, struct its_cmd_info *info)
 		/* Already mapped, move it around */
 		its_send_vmovi(its_dev, event);
 	} else {
+		/* Ensure all the VPEs are mapped on this ITS */
+		its_map_vm(its_dev->its, info->map->vm);
+
 		/* Drop the physical mapping */
 		its_send_discard(its_dev, event);
 
@@ -1225,6 +1310,9 @@ static int its_vlpi_unmap(struct irq_data *d)
 				    LPI_PROP_ENABLED |
 				    LPI_PROP_GROUP1));
 
+	/* Potentially unmap the VM from this ITS */
+	its_unmap_vm(its_dev->its, its_dev->event_map.vm);
+
 	/*
 	 * Drop the refcount and make the device available again if
 	 * this was the last VLPI.
@@ -1650,23 +1738,14 @@ static void its_free_tables(struct its_node *its)
 
 static int its_alloc_tables(struct its_node *its)
 {
-	u64 typer = gic_read_typer(its->base + GITS_TYPER);
-	u32 ids = GITS_TYPER_DEVBITS(typer);
 	u64 shr = GITS_BASER_InnerShareable;
 	u64 cache = GITS_BASER_RaWaWb;
 	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;
+	if (its->flags & ITS_FLAGS_WORKAROUND_CAVIUM_22375)
+		/* erratum 24313: ignore memory access type */
+		cache = GITS_BASER_nCnB;
 
 	for (i = 0; i < GITS_BASER_NR_REGS; i++) {
 		struct its_baser *baser = its->tables + i;
@@ -2372,6 +2451,8 @@ static int its_vpe_set_affinity(struct irq_data *d,
 		its_vpe_db_proxy_move(vpe, from, cpu);
 	}
 
+	irq_data_update_effective_affinity(d, cpumask_of(cpu));
+
 	return IRQ_SET_MASK_OK_DONE;
 }
 
@@ -2439,6 +2520,26 @@ static void its_vpe_deschedule(struct its_vpe *vpe)
 	}
 }
 
+static void its_vpe_invall(struct its_vpe *vpe)
+{
+	struct its_node *its;
+
+	list_for_each_entry(its, &its_nodes, entry) {
+		if (!its->is_v4)
+			continue;
+
+		if (its_list_map && !vpe->its_vm->vlpi_count[its->list_nr])
+			continue;
+
+		/*
+		 * Sending a VINVALL to a single ITS is enough, as all
+		 * we need is to reach the redistributors.
+		 */
+		its_send_vinvall(its, vpe);
+		return;
+	}
+}
+
 static int its_vpe_set_vcpu_affinity(struct irq_data *d, void *vcpu_info)
 {
 	struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
@@ -2454,7 +2555,7 @@ static int its_vpe_set_vcpu_affinity(struct irq_data *d, void *vcpu_info)
 		return 0;
 
 	case INVALL_VPE:
-		its_send_vinvall(vpe);
+		its_vpe_invall(vpe);
 		return 0;
 
 	default:
@@ -2683,11 +2784,25 @@ static int its_vpe_irq_domain_activate(struct irq_domain *domain,
 				       struct irq_data *d, bool early)
 {
 	struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
+	struct its_node *its;
+
+	/* If we use the list map, we issue VMAPP on demand... */
+	if (its_list_map)
+		return true;
 
 	/* Map the VPE to the first possible CPU */
 	vpe->col_idx = cpumask_first(cpu_online_mask);
-	its_send_vmapp(vpe, true);
-	its_send_vinvall(vpe);
+
+	list_for_each_entry(its, &its_nodes, entry) {
+		if (!its->is_v4)
+			continue;
+
+		its_send_vmapp(its, vpe, true);
+		its_send_vinvall(its, vpe);
+	}
+
+	irq_data_update_effective_affinity(d, cpumask_of(vpe->col_idx));
+
 	return 0;
 }
 
@@ -2695,8 +2810,21 @@ static void its_vpe_irq_domain_deactivate(struct irq_domain *domain,
 					  struct irq_data *d)
 {
 	struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
+	struct its_node *its;
 
-	its_send_vmapp(vpe, false);
+	/*
+	 * If we use the list map, we unmap the VPE once no VLPIs are
+	 * associated with the VM.
+	 */
+	if (its_list_map)
+		return;
+
+	list_for_each_entry(its, &its_nodes, entry) {
+		if (!its->is_v4)
+			continue;
+
+		its_send_vmapp(its, vpe, false);
+	}
 }
 
 static const struct irq_domain_ops its_vpe_domain_ops = {
@@ -2739,26 +2867,85 @@ static int its_force_quiescent(void __iomem *base)
 	}
 }
 
-static void __maybe_unused its_enable_quirk_cavium_22375(void *data)
+static bool __maybe_unused its_enable_quirk_cavium_22375(void *data)
 {
 	struct its_node *its = data;
 
+	/* erratum 22375: only alloc 8MB table size */
+	its->device_ids = 0x14;		/* 20 bits, 8MB */
 	its->flags |= ITS_FLAGS_WORKAROUND_CAVIUM_22375;
+
+	return true;
 }
 
-static void __maybe_unused its_enable_quirk_cavium_23144(void *data)
+static bool __maybe_unused its_enable_quirk_cavium_23144(void *data)
 {
 	struct its_node *its = data;
 
 	its->flags |= ITS_FLAGS_WORKAROUND_CAVIUM_23144;
+
+	return true;
 }
 
-static void __maybe_unused its_enable_quirk_qdf2400_e0065(void *data)
+static bool __maybe_unused its_enable_quirk_qdf2400_e0065(void *data)
 {
 	struct its_node *its = data;
 
 	/* On QDF2400, the size of the ITE is 16Bytes */
 	its->ite_size = 16;
+
+	return true;
+}
+
+static u64 its_irq_get_msi_base_pre_its(struct its_device *its_dev)
+{
+	struct its_node *its = its_dev->its;
+
+	/*
+	 * The Socionext Synquacer SoC has a so-called 'pre-ITS',
+	 * which maps 32-bit writes targeted at a separate window of
+	 * size '4 << device_id_bits' onto writes to GITS_TRANSLATER
+	 * with device ID taken from bits [device_id_bits + 1:2] of
+	 * the window offset.
+	 */
+	return its->pre_its_base + (its_dev->device_id << 2);
+}
+
+static bool __maybe_unused its_enable_quirk_socionext_synquacer(void *data)
+{
+	struct its_node *its = data;
+	u32 pre_its_window[2];
+	u32 ids;
+
+	if (!fwnode_property_read_u32_array(its->fwnode_handle,
+					   "socionext,synquacer-pre-its",
+					   pre_its_window,
+					   ARRAY_SIZE(pre_its_window))) {
+
+		its->pre_its_base = pre_its_window[0];
+		its->get_msi_base = its_irq_get_msi_base_pre_its;
+
+		ids = ilog2(pre_its_window[1]) - 2;
+		if (its->device_ids > ids)
+			its->device_ids = ids;
+
+		/* the pre-ITS breaks isolation, so disable MSI remapping */
+		its->msi_domain_flags &= ~IRQ_DOMAIN_FLAG_MSI_REMAP;
+		return true;
+	}
+	return false;
+}
+
+static bool __maybe_unused its_enable_quirk_hip07_161600802(void *data)
+{
+	struct its_node *its = data;
+
+	/*
+	 * Hip07 insists on using the wrong address for the VLPI
+	 * page. Trick it into doing the right thing...
+	 */
+	its->vlpi_redist_offset = SZ_128K;
+	return true;
 }
 
 static const struct gic_quirk its_quirks[] = {
@@ -2785,6 +2972,27 @@ static const struct gic_quirk its_quirks[] = {
 		.mask	= 0xffffffff,
 		.init	= its_enable_quirk_qdf2400_e0065,
 	},
+#endif
+#ifdef CONFIG_SOCIONEXT_SYNQUACER_PREITS
+	{
+		/*
+		 * The Socionext Synquacer SoC incorporates ARM's own GIC-500
+		 * implementation, but with a 'pre-ITS' added that requires
+		 * special handling in software.
+		 */
+		.desc	= "ITS: Socionext Synquacer pre-ITS",
+		.iidr	= 0x0001143b,
+		.mask	= 0xffffffff,
+		.init	= its_enable_quirk_socionext_synquacer,
+	},
+#endif
+#ifdef CONFIG_HISILICON_ERRATUM_161600802
+	{
+		.desc	= "ITS: Hip07 erratum 161600802",
+		.iidr	= 0x00000004,
+		.mask	= 0xffffffff,
+		.init	= its_enable_quirk_hip07_161600802,
+	},
 #endif
 	{
 	}
@@ -2814,7 +3022,7 @@ static int its_init_domain(struct fwnode_handle *handle, struct its_node *its)
 
 	inner_domain->parent = its_parent;
 	irq_domain_update_bus_token(inner_domain, DOMAIN_BUS_NEXUS);
-	inner_domain->flags |= IRQ_DOMAIN_FLAG_MSI_REMAP;
+	inner_domain->flags |= its->msi_domain_flags;
 	info->ops = &its_msi_domain_ops;
 	info->data = its;
 	inner_domain->host_data = info;
@@ -2875,8 +3083,8 @@ static int __init its_compute_its_list_map(struct resource *res,
 	 * locking. Should this change, we should address
 	 * this.
 	 */
-	its_number = find_first_zero_bit(&its_list_map, ITS_LIST_MAX);
-	if (its_number >= ITS_LIST_MAX) {
+	its_number = find_first_zero_bit(&its_list_map, GICv4_ITS_LIST_MAX);
+	if (its_number >= GICv4_ITS_LIST_MAX) {
 		pr_err("ITS@%pa: No ITSList entry available!\n",
 		       &res->start);
 		return -EINVAL;
@@ -2944,6 +3152,7 @@ static int __init its_probe_one(struct resource *res,
 	its->base = its_base;
 	its->phys_base = res->start;
 	its->ite_size = GITS_TYPER_ITT_ENTRY_SIZE(typer);
+	its->device_ids = GITS_TYPER_DEVBITS(typer);
 	its->is_v4 = !!(typer & GITS_TYPER_VLPIS);
 	if (its->is_v4) {
 		if (!(typer & GITS_TYPER_VMOVP)) {
@@ -2951,6 +3160,8 @@ static int __init its_probe_one(struct resource *res,
 			if (err < 0)
 				goto out_free_its;
 
+			its->list_nr = err;
+
 			pr_info("ITS@%pa: Using ITS number %d\n",
 				&res->start, err);
 		} else {
@@ -2967,6 +3178,9 @@ static int __init its_probe_one(struct resource *res,
 		goto out_free_its;
 	}
 	its->cmd_write = its->cmd_base;
+	its->fwnode_handle = handle;
+	its->get_msi_base = its_irq_get_msi_base;
+	its->msi_domain_flags = IRQ_DOMAIN_FLAG_MSI_REMAP;
 
 	its_enable_quirks(its);
 

drivers/irqchip/irq-gic-v3.c

@@ -55,6 +55,7 @@ struct gic_chip_data {
 	struct irq_domain	*domain;
 	u64			redist_stride;
 	u32			nr_redist_regions;
+	bool			has_rss;
 	unsigned int		irq_nr;
 	struct partition_desc	*ppi_descs[16];
 };
@@ -63,7 +64,9 @@ static struct gic_chip_data gic_data __read_mostly;
 static struct static_key supports_deactivate = STATIC_KEY_INIT_TRUE;
 
 static struct gic_kvm_info gic_v3_kvm_info;
+static DEFINE_PER_CPU(bool, has_rss);
 
+#define MPIDR_RS(mpidr)			(((mpidr) & 0xF0UL) >> 4)
 #define gic_data_rdist()		(this_cpu_ptr(gic_data.rdists.rdist))
 #define gic_data_rdist_rd_base()	(gic_data_rdist()->rd_base)
 #define gic_data_rdist_sgi_base()	(gic_data_rdist_rd_base() + SZ_64K)
@@ -526,6 +529,10 @@ static void gic_update_vlpi_properties(void)
 
 static void gic_cpu_sys_reg_init(void)
 {
+	int i, cpu = smp_processor_id();
+	u64 mpidr = cpu_logical_map(cpu);
+	u64 need_rss = MPIDR_RS(mpidr);
+
 	/*
 	 * Need to check that the SRE bit has actually been set. If
 	 * not, it means that SRE is disabled at EL2. We're going to
@@ -557,6 +564,30 @@ static void gic_cpu_sys_reg_init(void)
 
 	/* ... and let's hit the road... */
 	gic_write_grpen1(1);
+
+	/* Keep the RSS capability status in per_cpu variable */
+	per_cpu(has_rss, cpu) = !!(gic_read_ctlr() & ICC_CTLR_EL1_RSS);
+
+	/* Check all the CPUs have capable of sending SGIs to other CPUs */
+	for_each_online_cpu(i) {
+		bool have_rss = per_cpu(has_rss, i) && per_cpu(has_rss, cpu);
+
+		need_rss |= MPIDR_RS(cpu_logical_map(i));
+		if (need_rss && (!have_rss))
+			pr_crit("CPU%d (%lx) can't SGI CPU%d (%lx), no RSS\n",
+				cpu, (unsigned long)mpidr,
+				i, (unsigned long)cpu_logical_map(i));
+	}
+
+	/**
+	 * GIC spec says, when ICC_CTLR_EL1.RSS==1 and GICD_TYPER.RSS==0,
+	 * writing ICC_ASGI1R_EL1 register with RS != 0 is a CONSTRAINED
+	 * UNPREDICTABLE choice of :
+	 *   - The write is ignored.
+	 *   - The RS field is treated as 0.
+	 */
+	if (need_rss && (!gic_data.has_rss))
+		pr_crit_once("RSS is required but GICD doesn't support it\n");
 }
 
 static int gic_dist_supports_lpis(void)
@@ -591,6 +622,9 @@ static void gic_cpu_init(void)
 
 #ifdef CONFIG_SMP
 
+#define MPIDR_TO_SGI_RS(mpidr)	(MPIDR_RS(mpidr) << ICC_SGI1R_RS_SHIFT)
+#define MPIDR_TO_SGI_CLUSTER_ID(mpidr)	((mpidr) & ~0xFUL)
+
 static int gic_starting_cpu(unsigned int cpu)
 {
 	gic_cpu_init();
@@ -605,13 +639,6 @@ static u16 gic_compute_target_list(int *base_cpu, const struct cpumask *mask,
 	u16 tlist = 0;
 
 	while (cpu < nr_cpu_ids) {
-		/*
-		 * If we ever get a cluster of more than 16 CPUs, just
-		 * scream and skip that CPU.
-		 */
-		if (WARN_ON((mpidr & 0xff) >= 16))
-			goto out;
-
 		tlist |= 1 << (mpidr & 0xf);
 
 		next_cpu = cpumask_next(cpu, mask);
@@ -621,7 +648,7 @@ static u16 gic_compute_target_list(int *base_cpu, const struct cpumask *mask,
 
 		mpidr = cpu_logical_map(cpu);
 
-		if (cluster_id != (mpidr & ~0xffUL)) {
+		if (cluster_id != MPIDR_TO_SGI_CLUSTER_ID(mpidr)) {
 			cpu--;
 			goto out;
 		}
@@ -643,6 +670,7 @@ static void gic_send_sgi(u64 cluster_id, u16 tlist, unsigned int irq)
 	       MPIDR_TO_SGI_AFFINITY(cluster_id, 2)	|
 	       irq << ICC_SGI1R_SGI_ID_SHIFT		|
 	       MPIDR_TO_SGI_AFFINITY(cluster_id, 1)	|
+	       MPIDR_TO_SGI_RS(cluster_id)		|
 	       tlist << ICC_SGI1R_TARGET_LIST_SHIFT);
 
 	pr_debug("CPU%d: ICC_SGI1R_EL1 %llx\n", smp_processor_id(), val);
@@ -663,7 +691,7 @@ static void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
 	smp_wmb();
 
 	for_each_cpu(cpu, mask) {
-		unsigned long cluster_id = cpu_logical_map(cpu) & ~0xffUL;
+		u64 cluster_id = MPIDR_TO_SGI_CLUSTER_ID(cpu_logical_map(cpu));
 		u16 tlist;
 
 		tlist = gic_compute_target_list(&cpu, mask, cluster_id);
@@ -1007,6 +1035,10 @@ static int __init gic_init_bases(void __iomem *dist_base,
 		goto out_free;
 	}
 
+	gic_data.has_rss = !!(typer & GICD_TYPER_RSS);
+	pr_info("Distributor has %sRange Selector support\n",
+		gic_data.has_rss ? "" : "no ");
+
 	set_handle_irq(gic_handle_irq);
 
 	gic_update_vlpi_properties();

drivers/irqchip/irq-meson-gpio.c

@@ -0,0 +1,414 @@
+/*
+ * Copyright (c) 2015 Endless Mobile, Inc.
+ * Author: Carlo Caione <carlo@endlessm.com>
+ * Copyright (c) 2016 BayLibre, SAS.
+ * Author: Jerome Brunet <jbrunet@baylibre.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License 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/>.
+ * The full GNU General Public License is included in this distribution
+ * in the file called COPYING.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/irq.h>
+#include <linux/irqdomain.h>
+#include <linux/irqchip.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+
+#define NUM_CHANNEL 8
+#define MAX_INPUT_MUX 256
+
+#define REG_EDGE_POL	0x00
+#define REG_PIN_03_SEL	0x04
+#define REG_PIN_47_SEL	0x08
+#define REG_FILTER_SEL	0x0c
+
+#define REG_EDGE_POL_MASK(x)	(BIT(x) | BIT(16 + (x)))
+#define REG_EDGE_POL_EDGE(x)	BIT(x)
+#define REG_EDGE_POL_LOW(x)	BIT(16 + (x))
+#define REG_PIN_SEL_SHIFT(x)	(((x) % 4) * 8)
+#define REG_FILTER_SEL_SHIFT(x)	((x) * 4)
+
+struct meson_gpio_irq_params {
+	unsigned int nr_hwirq;
+};
+
+static const struct meson_gpio_irq_params meson8b_params = {
+	.nr_hwirq = 119,
+};
+
+static const struct meson_gpio_irq_params gxbb_params = {
+	.nr_hwirq = 133,
+};
+
+static const struct meson_gpio_irq_params gxl_params = {
+	.nr_hwirq = 110,
+};
+
+static const struct of_device_id meson_irq_gpio_matches[] = {
+	{ .compatible = "amlogic,meson8b-gpio-intc", .data = &meson8b_params },
+	{ .compatible = "amlogic,meson-gxbb-gpio-intc", .data = &gxbb_params },
+	{ .compatible = "amlogic,meson-gxl-gpio-intc", .data = &gxl_params },
+	{ }
+};
+
+struct meson_gpio_irq_controller {
+	unsigned int nr_hwirq;
+	void __iomem *base;
+	u32 channel_irqs[NUM_CHANNEL];
+	DECLARE_BITMAP(channel_map, NUM_CHANNEL);
+	spinlock_t lock;
+};
+
+static void meson_gpio_irq_update_bits(struct meson_gpio_irq_controller *ctl,
+				       unsigned int reg, u32 mask, u32 val)
+{
+	u32 tmp;
+
+	tmp = readl_relaxed(ctl->base + reg);
+	tmp &= ~mask;
+	tmp |= val;
+	writel_relaxed(tmp, ctl->base + reg);
+}
+
+static unsigned int meson_gpio_irq_channel_to_reg(unsigned int channel)
+{
+	return (channel < 4) ? REG_PIN_03_SEL : REG_PIN_47_SEL;
+}
+
+static int
+meson_gpio_irq_request_channel(struct meson_gpio_irq_controller *ctl,
+			       unsigned long  hwirq,
+			       u32 **channel_hwirq)
+{
+	unsigned int reg, idx;
+
+	spin_lock(&ctl->lock);
+
+	/* Find a free channel */
+	idx = find_first_zero_bit(ctl->channel_map, NUM_CHANNEL);
+	if (idx >= NUM_CHANNEL) {
+		spin_unlock(&ctl->lock);
+		pr_err("No channel available\n");
+		return -ENOSPC;
+	}
+
+	/* Mark the channel as used */
+	set_bit(idx, ctl->channel_map);
+
+	/*
+	 * Setup the mux of the channel to route the signal of the pad
+	 * to the appropriate input of the GIC
+	 */
+	reg = meson_gpio_irq_channel_to_reg(idx);
+	meson_gpio_irq_update_bits(ctl, reg,
+				   0xff << REG_PIN_SEL_SHIFT(idx),
+				   hwirq << REG_PIN_SEL_SHIFT(idx));
+
+	/*
+	 * Get the hwirq number assigned to this channel through
+	 * a pointer the channel_irq table. The added benifit of this
+	 * method is that we can also retrieve the channel index with
+	 * it, using the table base.
+	 */
+	*channel_hwirq = &(ctl->channel_irqs[idx]);
+
+	spin_unlock(&ctl->lock);
+
+	pr_debug("hwirq %lu assigned to channel %d - irq %u\n",
+		 hwirq, idx, **channel_hwirq);
+
+	return 0;
+}
+
+static unsigned int
+meson_gpio_irq_get_channel_idx(struct meson_gpio_irq_controller *ctl,
+			       u32 *channel_hwirq)
+{
+	return channel_hwirq - ctl->channel_irqs;
+}
+
+static void
+meson_gpio_irq_release_channel(struct meson_gpio_irq_controller *ctl,
+			       u32 *channel_hwirq)
+{
+	unsigned int idx;
+
+	idx = meson_gpio_irq_get_channel_idx(ctl, channel_hwirq);
+	clear_bit(idx, ctl->channel_map);
+}
+
+static int meson_gpio_irq_type_setup(struct meson_gpio_irq_controller *ctl,
+				     unsigned int type,
+				     u32 *channel_hwirq)
+{
+	u32 val = 0;
+	unsigned int idx;
+
+	idx = meson_gpio_irq_get_channel_idx(ctl, channel_hwirq);
+
+	/*
+	 * The controller has a filter block to operate in either LEVEL or
+	 * EDGE mode, then signal is sent to the GIC. To enable LEVEL_LOW and
+	 * EDGE_FALLING support (which the GIC does not support), the filter
+	 * block is also able to invert the input signal it gets before
+	 * providing it to the GIC.
+	 */
+	type &= IRQ_TYPE_SENSE_MASK;
+
+	if (type == IRQ_TYPE_EDGE_BOTH)
+		return -EINVAL;
+
+	if (type & (IRQ_TYPE_EDGE_RISING | IRQ_TYPE_EDGE_FALLING))
+		val |= REG_EDGE_POL_EDGE(idx);
+
+	if (type & (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_EDGE_FALLING))
+		val |= REG_EDGE_POL_LOW(idx);
+
+	spin_lock(&ctl->lock);
+
+	meson_gpio_irq_update_bits(ctl, REG_EDGE_POL,
+				   REG_EDGE_POL_MASK(idx), val);
+
+	spin_unlock(&ctl->lock);
+
+	return 0;
+}
+
+static unsigned int meson_gpio_irq_type_output(unsigned int type)
+{
+	unsigned int sense = type & IRQ_TYPE_SENSE_MASK;
+
+	type &= ~IRQ_TYPE_SENSE_MASK;
+
+	/*
+	 * The polarity of the signal provided to the GIC should always
+	 * be high.
+	 */
+	if (sense & (IRQ_TYPE_LEVEL_HIGH | IRQ_TYPE_LEVEL_LOW))
+		type |= IRQ_TYPE_LEVEL_HIGH;
+	else if (sense & (IRQ_TYPE_EDGE_RISING | IRQ_TYPE_EDGE_FALLING))
+		type |= IRQ_TYPE_EDGE_RISING;
+
+	return type;
+}
+
+static int meson_gpio_irq_set_type(struct irq_data *data, unsigned int type)
+{
+	struct meson_gpio_irq_controller *ctl = data->domain->host_data;
+	u32 *channel_hwirq = irq_data_get_irq_chip_data(data);
+	int ret;
+
+	ret = meson_gpio_irq_type_setup(ctl, type, channel_hwirq);
+	if (ret)
+		return ret;
+
+	return irq_chip_set_type_parent(data,
+					meson_gpio_irq_type_output(type));
+}
+
+static struct irq_chip meson_gpio_irq_chip = {
+	.name			= "meson-gpio-irqchip",
+	.irq_mask		= irq_chip_mask_parent,
+	.irq_unmask		= irq_chip_unmask_parent,
+	.irq_eoi		= irq_chip_eoi_parent,
+	.irq_set_type		= meson_gpio_irq_set_type,
+	.irq_retrigger		= irq_chip_retrigger_hierarchy,
+#ifdef CONFIG_SMP
+	.irq_set_affinity	= irq_chip_set_affinity_parent,
+#endif
+	.flags			= IRQCHIP_SET_TYPE_MASKED,
+};
+
+static int meson_gpio_irq_domain_translate(struct irq_domain *domain,
+					   struct irq_fwspec *fwspec,
+					   unsigned long *hwirq,
+					   unsigned int *type)
+{
+	if (is_of_node(fwspec->fwnode) && fwspec->param_count == 2) {
+		*hwirq	= fwspec->param[0];
+		*type	= fwspec->param[1];
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
+static int meson_gpio_irq_allocate_gic_irq(struct irq_domain *domain,
+					   unsigned int virq,
+					   u32 hwirq,
+					   unsigned int type)
+{
+	struct irq_fwspec fwspec;
+
+	fwspec.fwnode = domain->parent->fwnode;
+	fwspec.param_count = 3;
+	fwspec.param[0] = 0;	/* SPI */
+	fwspec.param[1] = hwirq;
+	fwspec.param[2] = meson_gpio_irq_type_output(type);
+
+	return irq_domain_alloc_irqs_parent(domain, virq, 1, &fwspec);
+}
+
+static int meson_gpio_irq_domain_alloc(struct irq_domain *domain,
+				       unsigned int virq,
+				       unsigned int nr_irqs,
+				       void *data)
+{
+	struct irq_fwspec *fwspec = data;
+	struct meson_gpio_irq_controller *ctl = domain->host_data;
+	unsigned long hwirq;
+	u32 *channel_hwirq;
+	unsigned int type;
+	int ret;
+
+	if (WARN_ON(nr_irqs != 1))
+		return -EINVAL;
+
+	ret = meson_gpio_irq_domain_translate(domain, fwspec, &hwirq, &type);
+	if (ret)
+		return ret;
+
+	ret = meson_gpio_irq_request_channel(ctl, hwirq, &channel_hwirq);
+	if (ret)
+		return ret;
+
+	ret = meson_gpio_irq_allocate_gic_irq(domain, virq,
+					      *channel_hwirq, type);
+	if (ret < 0) {
+		pr_err("failed to allocate gic irq %u\n", *channel_hwirq);
+		meson_gpio_irq_release_channel(ctl, channel_hwirq);
+		return ret;
+	}
+
+	irq_domain_set_hwirq_and_chip(domain, virq, hwirq,
+				      &meson_gpio_irq_chip, channel_hwirq);
+
+	return 0;
+}
+
+static void meson_gpio_irq_domain_free(struct irq_domain *domain,
+				       unsigned int virq,
+				       unsigned int nr_irqs)
+{
+	struct meson_gpio_irq_controller *ctl = domain->host_data;
+	struct irq_data *irq_data;
+	u32 *channel_hwirq;
+
+	if (WARN_ON(nr_irqs != 1))
+		return;
+
+	irq_domain_free_irqs_parent(domain, virq, 1);
+
+	irq_data = irq_domain_get_irq_data(domain, virq);
+	channel_hwirq = irq_data_get_irq_chip_data(irq_data);
+
+	meson_gpio_irq_release_channel(ctl, channel_hwirq);
+}
+
+static const struct irq_domain_ops meson_gpio_irq_domain_ops = {
+	.alloc		= meson_gpio_irq_domain_alloc,
+	.free		= meson_gpio_irq_domain_free,
+	.translate	= meson_gpio_irq_domain_translate,
+};
+
+static int __init meson_gpio_irq_parse_dt(struct device_node *node,
+					  struct meson_gpio_irq_controller *ctl)
+{
+	const struct of_device_id *match;
+	const struct meson_gpio_irq_params *params;
+	int ret;
+
+	match = of_match_node(meson_irq_gpio_matches, node);
+	if (!match)
+		return -ENODEV;
+
+	params = match->data;
+	ctl->nr_hwirq = params->nr_hwirq;
+
+	ret = of_property_read_variable_u32_array(node,
+						  "amlogic,channel-interrupts",
+						  ctl->channel_irqs,
+						  NUM_CHANNEL,
+						  NUM_CHANNEL);
+	if (ret < 0) {
+		pr_err("can't get %d channel interrupts\n", NUM_CHANNEL);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int __init meson_gpio_irq_of_init(struct device_node *node,
+					 struct device_node *parent)
+{
+	struct irq_domain *domain, *parent_domain;
+	struct meson_gpio_irq_controller *ctl;
+	int ret;
+
+	if (!parent) {
+		pr_err("missing parent interrupt node\n");
+		return -ENODEV;
+	}
+
+	parent_domain = irq_find_host(parent);
+	if (!parent_domain) {
+		pr_err("unable to obtain parent domain\n");
+		return -ENXIO;
+	}
+
+	ctl = kzalloc(sizeof(*ctl), GFP_KERNEL);
+	if (!ctl)
+		return -ENOMEM;
+
+	spin_lock_init(&ctl->lock);
+
+	ctl->base = of_iomap(node, 0);
+	if (!ctl->base) {
+		ret = -ENOMEM;
+		goto free_ctl;
+	}
+
+	ret = meson_gpio_irq_parse_dt(node, ctl);
+	if (ret)
+		goto free_channel_irqs;
+
+	domain = irq_domain_create_hierarchy(parent_domain, 0, ctl->nr_hwirq,
+					     of_node_to_fwnode(node),
+					     &meson_gpio_irq_domain_ops,
+					     ctl);
+	if (!domain) {
+		pr_err("failed to add domain\n");
+		ret = -ENODEV;
+		goto free_channel_irqs;
+	}
+
+	pr_info("%d to %d gpio interrupt mux initialized\n",
+		ctl->nr_hwirq, NUM_CHANNEL);
+
+	return 0;
+
+free_channel_irqs:
+	iounmap(ctl->base);
+free_ctl:
+	kfree(ctl);
+
+	return ret;
+}
+
+IRQCHIP_DECLARE(meson_gpio_intc, "amlogic,meson-gpio-intc",
+		meson_gpio_irq_of_init);

drivers/irqchip/irq-renesas-intc-irqpin.c

@@ -389,9 +389,8 @@ MODULE_DEVICE_TABLE(of, intc_irqpin_dt_ids);
 
 static int intc_irqpin_probe(struct platform_device *pdev)
 {
-	const struct intc_irqpin_config *config = NULL;
+	const struct intc_irqpin_config *config;
 	struct device *dev = &pdev->dev;
-	const struct of_device_id *of_id;
 	struct intc_irqpin_priv *p;
 	struct intc_irqpin_iomem *i;
 	struct resource *io[INTC_IRQPIN_REG_NR];
@@ -422,11 +421,9 @@ static int intc_irqpin_probe(struct platform_device *pdev)
 	p->pdev = pdev;
 	platform_set_drvdata(pdev, p);
 
-	of_id = of_match_device(intc_irqpin_dt_ids, dev);
-	if (of_id && of_id->data) {
-		config = of_id->data;
+	config = of_device_get_match_data(dev);
+	if (config)
 		p->needs_clk = config->needs_clk;
-	}
 
 	p->clk = devm_clk_get(dev, NULL);
 	if (IS_ERR(p->clk)) {

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

@@ -68,6 +68,7 @@
 #define GICD_CTLR_ENABLE_SS_G1		(1U << 1)
 #define GICD_CTLR_ENABLE_SS_G0		(1U << 0)
 
+#define GICD_TYPER_RSS			(1U << 26)
 #define GICD_TYPER_LPIS			(1U << 17)
 #define GICD_TYPER_MBIS			(1U << 16)
 
@@ -459,6 +460,7 @@
 #define ICC_CTLR_EL1_SEIS_MASK		(0x1 << ICC_CTLR_EL1_SEIS_SHIFT)
 #define ICC_CTLR_EL1_A3V_SHIFT		15
 #define ICC_CTLR_EL1_A3V_MASK		(0x1 << ICC_CTLR_EL1_A3V_SHIFT)
+#define ICC_CTLR_EL1_RSS		(0x1 << 18)
 #define ICC_PMR_EL1_SHIFT		0
 #define ICC_PMR_EL1_MASK		(0xff << ICC_PMR_EL1_SHIFT)
 #define ICC_BPR0_EL1_SHIFT		0
@@ -547,6 +549,8 @@
 #define ICC_SGI1R_AFFINITY_2_SHIFT	32
 #define ICC_SGI1R_AFFINITY_2_MASK	(0xffULL << ICC_SGI1R_AFFINITY_2_SHIFT)
 #define ICC_SGI1R_IRQ_ROUTING_MODE_BIT	40
+#define ICC_SGI1R_RS_SHIFT		44
+#define ICC_SGI1R_RS_MASK		(0xfULL << ICC_SGI1R_RS_SHIFT)
 #define ICC_SGI1R_AFFINITY_3_SHIFT	48
 #define ICC_SGI1R_AFFINITY_3_MASK	(0xffULL << ICC_SGI1R_AFFINITY_3_SHIFT)
 

include/linux/irqchip/arm-gic-v4.h

@@ -20,6 +20,12 @@
 
 struct its_vpe;
 
+/*
+ * Maximum number of ITTs when GITS_TYPER.VMOVP == 0, using the
+ * ITSList mechanism to perform inter-ITS synchronization.
+ */
+#define GICv4_ITS_LIST_MAX		16
+
 /* Embedded in kvm.arch */
 struct its_vm {
 	struct fwnode_handle	*fwnode;
@@ -30,6 +36,7 @@ struct its_vm {
 	irq_hw_number_t		db_lpi_base;
 	unsigned long		*db_bitmap;
 	int			nr_db_lpis;
+	u32			vlpi_count[GICv4_ITS_LIST_MAX];
 };
 
 /* Embedded in kvm_vcpu.arch */

include/linux/irqdomain.h

@@ -32,6 +32,7 @@
 #include <linux/types.h>
 #include <linux/irqhandler.h>
 #include <linux/of.h>
+#include <linux/mutex.h>
 #include <linux/radix-tree.h>
 
 struct device_node;
@@ -176,6 +177,7 @@ struct irq_domain {
 	unsigned int revmap_direct_max_irq;
 	unsigned int revmap_size;
 	struct radix_tree_root revmap_tree;
+	struct mutex revmap_tree_mutex;
 	unsigned int linear_revmap[];
 };
 

kernel/irq/irqdomain.c

@@ -21,7 +21,6 @@
 static LIST_HEAD(irq_domain_list);
 static DEFINE_MUTEX(irq_domain_mutex);
 
-static DEFINE_MUTEX(revmap_trees_mutex);
 static struct irq_domain *irq_default_domain;
 
 static void irq_domain_check_hierarchy(struct irq_domain *domain);
@@ -211,6 +210,7 @@ struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, int size,
 
 	/* Fill structure */
 	INIT_RADIX_TREE(&domain->revmap_tree, GFP_KERNEL);
+	mutex_init(&domain->revmap_tree_mutex);
 	domain->ops = ops;
 	domain->host_data = host_data;
 	domain->hwirq_max = hwirq_max;
@@ -462,9 +462,9 @@ static void irq_domain_clear_mapping(struct irq_domain *domain,
 	if (hwirq < domain->revmap_size) {
 		domain->linear_revmap[hwirq] = 0;
 	} else {
-		mutex_lock(&revmap_trees_mutex);
+		mutex_lock(&domain->revmap_tree_mutex);
 		radix_tree_delete(&domain->revmap_tree, hwirq);
-		mutex_unlock(&revmap_trees_mutex);
+		mutex_unlock(&domain->revmap_tree_mutex);
 	}
 }
 
@@ -475,9 +475,9 @@ static void irq_domain_set_mapping(struct irq_domain *domain,
 	if (hwirq < domain->revmap_size) {
 		domain->linear_revmap[hwirq] = irq_data->irq;
 	} else {
-		mutex_lock(&revmap_trees_mutex);
+		mutex_lock(&domain->revmap_tree_mutex);
 		radix_tree_insert(&domain->revmap_tree, hwirq, irq_data);
-		mutex_unlock(&revmap_trees_mutex);
+		mutex_unlock(&domain->revmap_tree_mutex);
 	}
 }
 
@@ -945,7 +945,7 @@ static int virq_debug_show(struct seq_file *m, void *private)
 	struct irq_desc *desc;
 	struct irq_domain *domain;
 	struct radix_tree_iter iter;
-	void **slot;
+	void __rcu **slot;
 	int i;
 
 	seq_printf(m, " %-16s  %-6s  %-10s  %-10s  %s\n",
@@ -1453,17 +1453,17 @@ out_free_desc:
 /* The irq_data was moved, fix the revmap to refer to the new location */
 static void irq_domain_fix_revmap(struct irq_data *d)
 {
-	void **slot;
+	void __rcu **slot;
 
 	if (d->hwirq < d->domain->revmap_size)
 		return; /* Not using radix tree. */
 
 	/* Fix up the revmap. */
-	mutex_lock(&revmap_trees_mutex);
+	mutex_lock(&d->domain->revmap_tree_mutex);
 	slot = radix_tree_lookup_slot(&d->domain->revmap_tree, d->hwirq);
 	if (slot)
 		radix_tree_replace_slot(&d->domain->revmap_tree, slot, d);
-	mutex_unlock(&revmap_trees_mutex);
+	mutex_unlock(&d->domain->revmap_tree_mutex);
 }
 
 /**