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

Pull irq core updates from Thomas Gleixner:
 "A rather large update for the interrupt core code and the irq chip drivers:

   - Add a new bitmap matrix allocator and supporting changes, which is
     used to replace the x86 vector allocator which comes with separate
     pull request. This allows to replace the convoluted nested loop
     allocation function in x86 with a facility which supports the
     recently added property of managed interrupts proper and allows to
     switch to a best effort vector reservation scheme, which addresses
     problems with vector exhaustion.

   - A large update to the ARM GIC-V3-ITS driver adding support for
     range selectors.

   - New interrupt controllers:
       - Meson and Meson8 GPIO
       - BCM7271 L2
       - Socionext EXIU

     If you expected that this will stop at some point, I have to
     disappoint you. There are new ones posted already. Sigh!

   - STM32 interrupt controller support for new platforms.

   - A pile of fixes, cleanups and updates to the MIPS GIC driver

   - The usual small fixes, cleanups and updates all over the place.
     Most visible one is to move the irq chip drivers Kconfig switches
     into a separate Kconfig menu"

* 'irq-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (70 commits)
  genirq: Fix type of shifting literal 1 in __setup_irq()
  irqdomain: Drop pointless NULL check in virq_debug_show_one
  genirq/proc: Return proper error code when irq_set_affinity() fails
  irq/work: Use llist_for_each_entry_safe
  irqchip: mips-gic: Print warning if inherited GIC base is used
  irqchip/mips-gic: Add pr_fmt and reword pr_* messages
  irqchip/stm32: Move the wakeup on interrupt mask
  irqchip/stm32: Fix initial values
  irqchip/stm32: Add stm32h7 support
  dt-bindings/interrupt-controllers: Add compatible string for stm32h7
  irqchip/stm32: Add multi-bank management
  irqchip/stm32: Select GENERIC_IRQ_CHIP
  irqchip/exiu: Add support for Socionext Synquacer EXIU controller
  dt-bindings: Add description of Socionext EXIU interrupt controller
  irqchip/gic-v3-its: Fix VPE activate callback return value
  irqchip: mips-gic: Make IPI bitmaps static
  irqchip: mips-gic: Share register writes in gic_set_type()
  irqchip: mips-gic: Remove gic_vpes variable
  irqchip: mips-gic: Use num_possible_cpus() to reserve IPIs
  irqchip: mips-gic: Configure EIC when CPUs come online
  ...

Documentation/admin-guide/kernel-parameters.txt

@@ -1716,6 +1716,13 @@
 	irqaffinity=	[SMP] Set the default irq affinity mask
 			The argument is a cpu list, as described above.
 
+	irqchip.gicv2_force_probe=
+			[ARM, ARM64]
+			Format: <bool>
+			Force the kernel to look for the second 4kB page
+			of a GICv2 controller even if the memory range
+			exposed by the device tree is too small.
+
 	irqfixup	[HW]
 			When an interrupt is not handled search all handlers
 			for it. Intended to get systems with badly broken

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 +1,36 @@
+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,meson8-gpio-intc” for meson8 SoCs (S802) or
+   “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.

Documentation/devicetree/bindings/interrupt-controller/socionext,synquacer-exiu.txt

@@ -0,0 +1,32 @@
+Socionext SynQuacer External Interrupt Unit (EXIU)
+
+The Socionext Synquacer SoC has an external interrupt unit (EXIU)
+that forwards a block of 32 configurable input lines to 32 adjacent
+level-high type GICv3 SPIs.
+
+Required properties:
+
+- compatible           : Should be "socionext,synquacer-exiu".
+- reg                  : Specifies base physical address and size of the
+                         control 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 3.
+- interrupt-parent     : phandle of the GIC these interrupts are routed to.
+- socionext,spi-base   : The SPI number of the first SPI of the 32 adjacent
+                         ones the EXIU forwards its interrups to.
+
+Notes:
+
+- Only SPIs can use the EXIU as an interrupt parent.
+
+Example:
+
+	exiu: interrupt-controller@510c0000 {
+		compatible = "socionext,synquacer-exiu";
+		reg = <0x0 0x510c0000 0x0 0x20>;
+		interrupt-controller;
+		interrupt-parent = <&gic>;
+		#interrupt-cells = <3>;
+		socionext,spi-base = <112>;
+	};

Documentation/devicetree/bindings/interrupt-controller/st,stm32-exti.txt

@@ -2,7 +2,9 @@ STM32 External Interrupt Controller
 
 Required properties:
 
-- compatible: Should be "st,stm32-exti"
+- compatible: Should be:
+    "st,stm32-exti"
+    "st,stm32h7-exti"
 - reg: Specifies base physical address and size of the registers
 - interrupt-controller: Indentifies the node as an interrupt controller
 - #interrupt-cells: Specifies the number of cells to encode an interrupt

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

@@ -556,6 +556,25 @@ 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/Kconfig.platforms

@@ -161,6 +161,9 @@ config ARCH_SEATTLE
 config ARCH_SHMOBILE
 	bool
 
+config ARCH_SYNQUACER
+	bool "Socionext SynQuacer SoC Family"
+
 config ARCH_RENESAS
 	bool "Renesas SoC Platforms"
 	select ARCH_SHMOBILE

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);

arch/x86/include/asm/irqdomain.h

@@ -42,8 +42,8 @@ extern int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq,
 			      unsigned int nr_irqs, void *arg);
 extern void mp_irqdomain_free(struct irq_domain *domain, unsigned int virq,
 			      unsigned int nr_irqs);
-extern void mp_irqdomain_activate(struct irq_domain *domain,
-				  struct irq_data *irq_data);
+extern int mp_irqdomain_activate(struct irq_domain *domain,
+				 struct irq_data *irq_data, bool early);
 extern void mp_irqdomain_deactivate(struct irq_domain *domain,
 				    struct irq_data *irq_data);
 extern int mp_irqdomain_ioapic_idx(struct irq_domain *domain);

arch/x86/kernel/apic/htirq.c

@@ -112,8 +112,8 @@ static void htirq_domain_free(struct irq_domain *domain, unsigned int virq,
 	irq_domain_free_irqs_top(domain, virq, nr_irqs);
 }
 
-static void htirq_domain_activate(struct irq_domain *domain,
-				  struct irq_data *irq_data)
+static int htirq_domain_activate(struct irq_domain *domain,
+				 struct irq_data *irq_data, bool early)
 {
 	struct ht_irq_msg msg;
 	struct irq_cfg *cfg = irqd_cfg(irq_data);
@@ -132,6 +132,7 @@ static void htirq_domain_activate(struct irq_domain *domain,
 			HT_IRQ_LOW_MT_ARBITRATED) |
 		HT_IRQ_LOW_IRQ_MASKED;
 	write_ht_irq_msg(irq_data->irq, &msg);
+	return 0;
 }
 
 static void htirq_domain_deactivate(struct irq_domain *domain,

arch/x86/kernel/apic/io_apic.c

@@ -2097,7 +2097,7 @@ static inline void __init check_timer(void)
 				unmask_ioapic_irq(irq_get_irq_data(0));
 		}
 		irq_domain_deactivate_irq(irq_data);
-		irq_domain_activate_irq(irq_data);
+		irq_domain_activate_irq(irq_data, false);
 		if (timer_irq_works()) {
 			if (disable_timer_pin_1 > 0)
 				clear_IO_APIC_pin(0, pin1);
@@ -2119,7 +2119,7 @@ static inline void __init check_timer(void)
 		 */
 		replace_pin_at_irq_node(data, node, apic1, pin1, apic2, pin2);
 		irq_domain_deactivate_irq(irq_data);
-		irq_domain_activate_irq(irq_data);
+		irq_domain_activate_irq(irq_data, false);
 		legacy_pic->unmask(0);
 		if (timer_irq_works()) {
 			apic_printk(APIC_QUIET, KERN_INFO "....... works.\n");
@@ -2978,8 +2978,8 @@ void mp_irqdomain_free(struct irq_domain *domain, unsigned int virq,
 	irq_domain_free_irqs_top(domain, virq, nr_irqs);
 }
 
-void mp_irqdomain_activate(struct irq_domain *domain,
-			   struct irq_data *irq_data)
+int mp_irqdomain_activate(struct irq_domain *domain,
+			  struct irq_data *irq_data, bool early)
 {
 	unsigned long flags;
 	struct irq_pin_list *entry;
@@ -2989,6 +2989,7 @@ void mp_irqdomain_activate(struct irq_domain *domain,
 	for_each_irq_pin(entry, data->irq_2_pin)
 		__ioapic_write_entry(entry->apic, entry->pin, data->entry);
 	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
+	return 0;
 }
 
 void mp_irqdomain_deactivate(struct irq_domain *domain,

arch/x86/platform/uv/uv_irq.c

@@ -127,10 +127,11 @@ static void uv_domain_free(struct irq_domain *domain, unsigned int virq,
  * Re-target the irq to the specified CPU and enable the specified MMR located
  * on the specified blade to allow the sending of MSIs to the specified CPU.
  */
-static void uv_domain_activate(struct irq_domain *domain,
-			       struct irq_data *irq_data)
+static int uv_domain_activate(struct irq_domain *domain,
+			      struct irq_data *irq_data, bool early)
 {
 	uv_program_mmr(irqd_cfg(irq_data), irq_data->chip_data);
+	return 0;
 }
 
 /*

drivers/gpio/gpio-xgene-sb.c

@@ -140,8 +140,9 @@ static int xgene_gpio_sb_to_irq(struct gpio_chip *gc, u32 gpio)
 	return irq_create_fwspec_mapping(&fwspec);
 }
 
-static void xgene_gpio_sb_domain_activate(struct irq_domain *d,
-		struct irq_data *irq_data)
+static int xgene_gpio_sb_domain_activate(struct irq_domain *d,
+					 struct irq_data *irq_data,
+					 bool early)
 {
 	struct xgene_gpio_sb *priv = d->host_data;
 	u32 gpio = HWIRQ_TO_GPIO(priv, irq_data->hwirq);
@@ -150,11 +151,12 @@ static void xgene_gpio_sb_domain_activate(struct irq_domain *d,
 		dev_err(priv->gc.parent,
 		"Unable to configure XGene GPIO standby pin %d as IRQ\n",
 				gpio);
-		return;
+		return -ENOSPC;
 	}
 
 	xgene_gpio_set_bit(&priv->gc, priv->regs + MPA_GPIO_SEL_LO,
 			gpio * 2, 1);
+	return 0;
 }
 
 static void xgene_gpio_sb_domain_deactivate(struct irq_domain *d,

drivers/iommu/amd_iommu.c

@@ -4173,8 +4173,8 @@ static void irq_remapping_free(struct irq_domain *domain, unsigned int virq,
 	irq_domain_free_irqs_common(domain, virq, nr_irqs);
 }
 
-static void irq_remapping_activate(struct irq_domain *domain,
-				   struct irq_data *irq_data)
+static int irq_remapping_activate(struct irq_domain *domain,
+				  struct irq_data *irq_data, bool early)
 {
 	struct amd_ir_data *data = irq_data->chip_data;
 	struct irq_2_irte *irte_info = &data->irq_2_irte;
@@ -4183,6 +4183,7 @@ static void irq_remapping_activate(struct irq_domain *domain,
 	if (iommu)
 		iommu->irte_ops->activate(data->entry, irte_info->devid,
 					  irte_info->index);
+	return 0;
 }
 
 static void irq_remapping_deactivate(struct irq_domain *domain,

drivers/iommu/intel_irq_remapping.c

@@ -1390,12 +1390,13 @@ static void intel_irq_remapping_free(struct irq_domain *domain,
 	irq_domain_free_irqs_common(domain, virq, nr_irqs);
 }
 
-static void intel_irq_remapping_activate(struct irq_domain *domain,
-					 struct irq_data *irq_data)
+static int intel_irq_remapping_activate(struct irq_domain *domain,
+					struct irq_data *irq_data, bool early)
 {
 	struct intel_ir_data *data = irq_data->chip_data;
 
 	modify_irte(&data->irq_2_iommu, &data->irte_entry);
+	return 0;
 }
 
 static void intel_irq_remapping_deactivate(struct irq_domain *domain,

drivers/irqchip/Kconfig

@@ -1,3 +1,5 @@
+menu "IRQ chip support"
+
 config IRQCHIP
 	def_bool y
 	depends on OF_IRQ
@@ -307,6 +309,7 @@ config EZNPS_GIC
 config STM32_EXTI
 	bool
 	select IRQ_DOMAIN
+	select GENERIC_IRQ_CHIP
 
 config QCOM_IRQ_COMBINER
 	bool "QCOM IRQ combiner support"
@@ -324,3 +327,13 @@ config IRQ_UNIPHIER_AIDET
 	select IRQ_DOMAIN_HIERARCHY
 	help
 	  Support for the UniPhier AIDET (ARM Interrupt Detector).
+
+config MESON_IRQ_GPIO
+       bool "Meson GPIO Interrupt Multiplexer"
+       depends on ARCH_MESON
+       select IRQ_DOMAIN
+       select IRQ_DOMAIN_HIERARCHY
+       help
+         Support Meson SoC Family GPIO Interrupt Multiplexer
+
+endmenu

drivers/irqchip/Makefile

@@ -81,3 +81,5 @@ 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-$(CONFIG_ARCH_SYNQUACER)		+= irq-sni-exiu.o
+obj-$(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
@@ -152,12 +160,6 @@ 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);
@@ -272,10 +274,12 @@ 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)
@@ -379,7 +383,8 @@ 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;
@@ -399,7 +404,8 @@ 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);
@@ -412,7 +418,8 @@ 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;
@@ -431,7 +438,8 @@ 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;
@@ -449,7 +457,8 @@ 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;
@@ -466,7 +475,8 @@ 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;
@@ -483,7 +493,8 @@ 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;
@@ -500,7 +511,8 @@ 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;
@@ -517,7 +529,8 @@ 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);
@@ -528,7 +541,8 @@ 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);
@@ -539,17 +553,20 @@ 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);
 
@@ -558,7 +575,8 @@ 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;
@@ -580,7 +598,8 @@ 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;
@@ -602,14 +621,18 @@ 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);
 
@@ -688,9 +711,9 @@ 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! */
@@ -711,12 +734,15 @@ 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 */
@@ -736,7 +762,7 @@ 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) {							\
@@ -744,7 +770,7 @@ 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);				\
 	}								\
 									\
@@ -752,10 +778,12 @@ 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);
@@ -767,7 +795,8 @@ 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);
@@ -899,21 +928,16 @@ 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)
@@ -951,6 +975,9 @@ 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);
 	}
@@ -958,18 +985,12 @@ 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);
 }
 
 /*
@@ -991,9 +1012,15 @@ static void lpi_write_config(struct irq_data *d, u8 clr, u8 set)
 	if (irqd_is_forwarded_to_vcpu(d)) {
 		struct its_device *its_dev = irq_data_get_irq_chip_data(d);
 		u32 event = its_get_event_id(d);
+		struct its_vlpi_map *map;
 
 		prop_page = its_dev->event_map.vm->vprop_page;
-		hwirq = its_dev->event_map.vlpi_maps[event].vintid;
+		map = &its_dev->event_map.vlpi_maps[event];
+		hwirq = map->vintid;
+
+		/* Remember the updated property */
+		map->properties &= ~clr;
+		map->properties |= set | LPI_PROP_GROUP1;
 	} else {
 		prop_page = gic_rdists->prop_page;
 		hwirq = d->hwirq;
@@ -1099,6 +1126,13 @@ 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);
@@ -1106,7 +1140,7 @@ 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);
@@ -1133,6 +1167,60 @@ 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);
@@ -1168,12 +1256,23 @@ 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);
+
+		/*
+		 * Flag the interrupt as forwarded so that we can
+		 * start poking the virtual property table.
+		 */
+		irqd_set_forwarded_to_vcpu(d);
+
+		/* Write out the property to the prop table */
+		lpi_write_config(d, 0xff, info->map->properties);
+
 		/* Drop the physical mapping */
 		its_send_discard(its_dev, event);
 
 		/* and install the virtual one */
 		its_send_vmapti(its_dev, event);
-		irqd_set_forwarded_to_vcpu(d);
 
 		/* Increment the number of VLPIs */
 		its_dev->event_map.nr_vlpis++;
@@ -1229,6 +1328,9 @@ 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.
@@ -1669,23 +1771,14 @@ 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;
@@ -2209,8 +2302,8 @@ static int its_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
 	return 0;
 }
 
-static void its_irq_domain_activate(struct irq_domain *domain,
-				    struct irq_data *d)
+static int its_irq_domain_activate(struct irq_domain *domain,
+				   struct irq_data *d, bool early)
 {
 	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
 	u32 event = its_get_event_id(d);
@@ -2228,6 +2321,7 @@ static void its_irq_domain_activate(struct irq_domain *domain,
 
 	/* Map the GIC IRQ and event to the device */
 	its_send_mapti(its_dev, d->hwirq, event);
+	return 0;
 }
 
 static void its_irq_domain_deactivate(struct irq_domain *domain,
@@ -2394,6 +2488,8 @@ 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;
 }
 
@@ -2461,6 +2557,26 @@ 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);
@@ -2476,7 +2592,7 @@ 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:
@@ -2701,23 +2817,51 @@ static int its_vpe_irq_domain_alloc(struct irq_domain *domain, unsigned int virq
 	return err;
 }
 
-static void its_vpe_irq_domain_activate(struct irq_domain *domain,
-					struct irq_data *d)
+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 0;
 
 	/* 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;
 }
 
 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;
+
+	/*
+	 * If we use the list map, we unmap the VPE once no VLPIs are
+	 * associated with the VM.
+	 */
+	if (its_list_map)
+		return;
 
-	its_send_vmapp(vpe, false);
+	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 = {
@@ -2760,26 +2904,85 @@ 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[] = {
@@ -2806,6 +3009,27 @@ 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
 	{
 	}
@@ -2835,7 +3059,7 @@ 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;
@@ -2896,8 +3120,8 @@ 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;
@@ -2965,6 +3189,7 @@ 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)) {
@@ -2972,6 +3197,8 @@ 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 {
@@ -2988,6 +3215,9 @@ 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-gic.c

@@ -1256,6 +1256,19 @@ static void gic_teardown(struct gic_chip_data *gic)
 
 #ifdef CONFIG_OF
 static int gic_cnt __initdata;
+static bool gicv2_force_probe;
+
+static int __init gicv2_force_probe_cfg(char *buf)
+{
+	return strtobool(buf, &gicv2_force_probe);
+}
+early_param("irqchip.gicv2_force_probe", gicv2_force_probe_cfg);
+
+static bool gic_check_gicv2(void __iomem *base)
+{
+	u32 val = readl_relaxed(base + GIC_CPU_IDENT);
+	return (val & 0xff0fff) == 0x02043B;
+}
 
 static bool gic_check_eoimode(struct device_node *node, void __iomem **base)
 {
@@ -1265,20 +1278,60 @@ static bool gic_check_eoimode(struct device_node *node, void __iomem **base)
 
 	if (!is_hyp_mode_available())
 		return false;
-	if (resource_size(&cpuif_res) < SZ_8K)
-		return false;
-	if (resource_size(&cpuif_res) == SZ_128K) {
-		u32 val_low, val_high;
+	if (resource_size(&cpuif_res) < SZ_8K) {
+		void __iomem *alt;
+		/*
+		 * Check for a stupid firmware that only exposes the
+		 * first page of a GICv2.
+		 */
+		if (!gic_check_gicv2(*base))
+			return false;
 
+		if (!gicv2_force_probe) {
+			pr_warn("GIC: GICv2 detected, but range too small and irqchip.gicv2_force_probe not set\n");
+			return false;
+		}
+
+		alt = ioremap(cpuif_res.start, SZ_8K);
+		if (!alt)
+			return false;
+		if (!gic_check_gicv2(alt + SZ_4K)) {
+			/*
+			 * The first page was that of a GICv2, and
+			 * the second was *something*. Let's trust it
+			 * to be a GICv2, and update the mapping.
+			 */
+			pr_warn("GIC: GICv2 at %pa, but range is too small (broken DT?), assuming 8kB\n",
+				&cpuif_res.start);
+			iounmap(*base);
+			*base = alt;
+			return true;
+		}
+
+		/*
+		 * We detected *two* initial GICv2 pages in a
+		 * row. Could be a GICv2 aliased over two 64kB
+		 * pages. Update the resource, map the iospace, and
+		 * pray.
+		 */
+		iounmap(alt);
+		alt = ioremap(cpuif_res.start, SZ_128K);
+		if (!alt)
+			return false;
+		pr_warn("GIC: Aliased GICv2 at %pa, trying to find the canonical range over 128kB\n",
+			&cpuif_res.start);
+		cpuif_res.end = cpuif_res.start + SZ_128K -1;
+		iounmap(*base);
+		*base = alt;
+	}
+	if (resource_size(&cpuif_res) == SZ_128K) {
 		/*
-		 * Verify that we have the first 4kB of a GIC400
+		 * Verify that we have the first 4kB of a GICv2
 		 * aliased over the first 64kB by checking the
 		 * GICC_IIDR register on both ends.
 		 */
-		val_low = readl_relaxed(*base + GIC_CPU_IDENT);
-		val_high = readl_relaxed(*base + GIC_CPU_IDENT + 0xf000);
-		if ((val_low & 0xffff0fff) != 0x0202043B ||
-		    val_low != val_high)
+		if (!gic_check_gicv2(*base) ||
+		    !gic_check_gicv2(*base + 0xf000))
 			return false;
 
 		/*

drivers/irqchip/irq-meson-gpio.c

@@ -0,0 +1,419 @@
+/*
+ * 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 meson8_params = {
+	.nr_hwirq = 134,
+};
+
+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,meson8-gpio-intc", .data = &meson8_params },
+	{ .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-mips-gic.c

@@ -6,8 +6,12 @@
  * Copyright (C) 2008 Ralf Baechle (ralf@linux-mips.org)
  * Copyright (C) 2012 MIPS Technologies, Inc.  All rights reserved.
  */
+
+#define pr_fmt(fmt) "irq-mips-gic: " fmt
+
 #include <linux/bitmap.h>
 #include <linux/clocksource.h>
+#include <linux/cpuhotplug.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
@@ -48,12 +52,16 @@ static DEFINE_SPINLOCK(gic_lock);
 static struct irq_domain *gic_irq_domain;
 static struct irq_domain *gic_ipi_domain;
 static int gic_shared_intrs;
-static int gic_vpes;
 static unsigned int gic_cpu_pin;
 static unsigned int timer_cpu_pin;
 static struct irq_chip gic_level_irq_controller, gic_edge_irq_controller;
-DECLARE_BITMAP(ipi_resrv, GIC_MAX_INTRS);
-DECLARE_BITMAP(ipi_available, GIC_MAX_INTRS);
+static DECLARE_BITMAP(ipi_resrv, GIC_MAX_INTRS);
+static DECLARE_BITMAP(ipi_available, GIC_MAX_INTRS);
+
+static struct gic_all_vpes_chip_data {
+	u32	map;
+	bool	mask;
+} gic_all_vpes_chip_data[GIC_NUM_LOCAL_INTRS];
 
 static void gic_clear_pcpu_masks(unsigned int intr)
 {
@@ -194,46 +202,46 @@ static void gic_ack_irq(struct irq_data *d)
 
 static int gic_set_type(struct irq_data *d, unsigned int type)
 {
-	unsigned int irq = GIC_HWIRQ_TO_SHARED(d->hwirq);
+	unsigned int irq, pol, trig, dual;
 	unsigned long flags;
-	bool is_edge;
+
+	irq = GIC_HWIRQ_TO_SHARED(d->hwirq);
 
 	spin_lock_irqsave(&gic_lock, flags);
 	switch (type & IRQ_TYPE_SENSE_MASK) {
 	case IRQ_TYPE_EDGE_FALLING:
-		change_gic_pol(irq, GIC_POL_FALLING_EDGE);
-		change_gic_trig(irq, GIC_TRIG_EDGE);
-		change_gic_dual(irq, GIC_DUAL_SINGLE);
-		is_edge = true;
+		pol = GIC_POL_FALLING_EDGE;
+		trig = GIC_TRIG_EDGE;
+		dual = GIC_DUAL_SINGLE;
 		break;
 	case IRQ_TYPE_EDGE_RISING:
-		change_gic_pol(irq, GIC_POL_RISING_EDGE);
-		change_gic_trig(irq, GIC_TRIG_EDGE);
-		change_gic_dual(irq, GIC_DUAL_SINGLE);
-		is_edge = true;
+		pol = GIC_POL_RISING_EDGE;
+		trig = GIC_TRIG_EDGE;
+		dual = GIC_DUAL_SINGLE;
 		break;
 	case IRQ_TYPE_EDGE_BOTH:
-		/* polarity is irrelevant in this case */
-		change_gic_trig(irq, GIC_TRIG_EDGE);
-		change_gic_dual(irq, GIC_DUAL_DUAL);
-		is_edge = true;
+		pol = 0; /* Doesn't matter */
+		trig = GIC_TRIG_EDGE;
+		dual = GIC_DUAL_DUAL;
 		break;
 	case IRQ_TYPE_LEVEL_LOW:
-		change_gic_pol(irq, GIC_POL_ACTIVE_LOW);
-		change_gic_trig(irq, GIC_TRIG_LEVEL);
-		change_gic_dual(irq, GIC_DUAL_SINGLE);
-		is_edge = false;
+		pol = GIC_POL_ACTIVE_LOW;
+		trig = GIC_TRIG_LEVEL;
+		dual = GIC_DUAL_SINGLE;
 		break;
 	case IRQ_TYPE_LEVEL_HIGH:
 	default:
-		change_gic_pol(irq, GIC_POL_ACTIVE_HIGH);
-		change_gic_trig(irq, GIC_TRIG_LEVEL);
-		change_gic_dual(irq, GIC_DUAL_SINGLE);
-		is_edge = false;
+		pol = GIC_POL_ACTIVE_HIGH;
+		trig = GIC_TRIG_LEVEL;
+		dual = GIC_DUAL_SINGLE;
 		break;
 	}
 
-	if (is_edge)
+	change_gic_pol(irq, pol);
+	change_gic_trig(irq, trig);
+	change_gic_dual(irq, dual);
+
+	if (trig == GIC_TRIG_EDGE)
 		irq_set_chip_handler_name_locked(d, &gic_edge_irq_controller,
 						 handle_edge_irq, NULL);
 	else
@@ -338,13 +346,17 @@ static struct irq_chip gic_local_irq_controller = {
 
 static void gic_mask_local_irq_all_vpes(struct irq_data *d)
 {
-	int intr = GIC_HWIRQ_TO_LOCAL(d->hwirq);
-	int i;
+	struct gic_all_vpes_chip_data *cd;
 	unsigned long flags;
+	int intr, cpu;
+
+	intr = GIC_HWIRQ_TO_LOCAL(d->hwirq);
+	cd = irq_data_get_irq_chip_data(d);
+	cd->mask = false;
 
 	spin_lock_irqsave(&gic_lock, flags);
-	for (i = 0; i < gic_vpes; i++) {
-		write_gic_vl_other(mips_cm_vp_id(i));
+	for_each_online_cpu(cpu) {
+		write_gic_vl_other(mips_cm_vp_id(cpu));
 		write_gic_vo_rmask(BIT(intr));
 	}
 	spin_unlock_irqrestore(&gic_lock, flags);
@@ -352,22 +364,40 @@ static void gic_mask_local_irq_all_vpes(struct irq_data *d)
 
 static void gic_unmask_local_irq_all_vpes(struct irq_data *d)
 {
-	int intr = GIC_HWIRQ_TO_LOCAL(d->hwirq);
-	int i;
+	struct gic_all_vpes_chip_data *cd;
 	unsigned long flags;
+	int intr, cpu;
+
+	intr = GIC_HWIRQ_TO_LOCAL(d->hwirq);
+	cd = irq_data_get_irq_chip_data(d);
+	cd->mask = true;
 
 	spin_lock_irqsave(&gic_lock, flags);
-	for (i = 0; i < gic_vpes; i++) {
-		write_gic_vl_other(mips_cm_vp_id(i));
+	for_each_online_cpu(cpu) {
+		write_gic_vl_other(mips_cm_vp_id(cpu));
 		write_gic_vo_smask(BIT(intr));
 	}
 	spin_unlock_irqrestore(&gic_lock, flags);
 }
 
+static void gic_all_vpes_irq_cpu_online(struct irq_data *d)
+{
+	struct gic_all_vpes_chip_data *cd;
+	unsigned int intr;
+
+	intr = GIC_HWIRQ_TO_LOCAL(d->hwirq);
+	cd = irq_data_get_irq_chip_data(d);
+
+	write_gic_vl_map(intr, cd->map);
+	if (cd->mask)
+		write_gic_vl_smask(BIT(intr));
+}
+
 static struct irq_chip gic_all_vpes_local_irq_controller = {
-	.name			=	"MIPS GIC Local",
-	.irq_mask		=	gic_mask_local_irq_all_vpes,
-	.irq_unmask		=	gic_unmask_local_irq_all_vpes,
+	.name			= "MIPS GIC Local",
+	.irq_mask		= gic_mask_local_irq_all_vpes,
+	.irq_unmask		= gic_unmask_local_irq_all_vpes,
+	.irq_cpu_online		= gic_all_vpes_irq_cpu_online,
 };
 
 static void __gic_irq_dispatch(void)
@@ -382,39 +412,6 @@ static void gic_irq_dispatch(struct irq_desc *desc)
 	gic_handle_shared_int(true);
 }
 
-static int gic_local_irq_domain_map(struct irq_domain *d, unsigned int virq,
-				    irq_hw_number_t hw)
-{
-	int intr = GIC_HWIRQ_TO_LOCAL(hw);
-	int i;
-	unsigned long flags;
-	u32 val;
-
-	if (!gic_local_irq_is_routable(intr))
-		return -EPERM;
-
-	if (intr > GIC_LOCAL_INT_FDC) {
-		pr_err("Invalid local IRQ %d\n", intr);
-		return -EINVAL;
-	}
-
-	if (intr == GIC_LOCAL_INT_TIMER) {
-		/* CONFIG_MIPS_CMP workaround (see __gic_init) */
-		val = GIC_MAP_PIN_MAP_TO_PIN | timer_cpu_pin;
-	} else {
-		val = GIC_MAP_PIN_MAP_TO_PIN | gic_cpu_pin;
-	}
-
-	spin_lock_irqsave(&gic_lock, flags);
-	for (i = 0; i < gic_vpes; i++) {
-		write_gic_vl_other(mips_cm_vp_id(i));
-		write_gic_vo_map(intr, val);
-	}
-	spin_unlock_irqrestore(&gic_lock, flags);
-
-	return 0;
-}
-
 static int gic_shared_irq_domain_map(struct irq_domain *d, unsigned int virq,
 				     irq_hw_number_t hw, unsigned int cpu)
 {
@@ -457,7 +454,11 @@ static int gic_irq_domain_xlate(struct irq_domain *d, struct device_node *ctrlr,
 static int gic_irq_domain_map(struct irq_domain *d, unsigned int virq,
 			      irq_hw_number_t hwirq)
 {
-	int err;
+	struct gic_all_vpes_chip_data *cd;
+	unsigned long flags;
+	unsigned int intr;
+	int err, cpu;
+	u32 map;
 
 	if (hwirq >= GIC_SHARED_HWIRQ_BASE) {
 		/* verify that shared irqs don't conflict with an IPI irq */
@@ -474,8 +475,14 @@ static int gic_irq_domain_map(struct irq_domain *d, unsigned int virq,
 		return gic_shared_irq_domain_map(d, virq, hwirq, 0);
 	}
 
-	switch (GIC_HWIRQ_TO_LOCAL(hwirq)) {
+	intr = GIC_HWIRQ_TO_LOCAL(hwirq);
+	map = GIC_MAP_PIN_MAP_TO_PIN | gic_cpu_pin;
+
+	switch (intr) {
 	case GIC_LOCAL_INT_TIMER:
+		/* CONFIG_MIPS_CMP workaround (see __gic_init) */
+		map = GIC_MAP_PIN_MAP_TO_PIN | timer_cpu_pin;
+		/* fall-through */
 	case GIC_LOCAL_INT_PERFCTR:
 	case GIC_LOCAL_INT_FDC:
 		/*
@@ -483,9 +490,11 @@ static int gic_irq_domain_map(struct irq_domain *d, unsigned int virq,
 		 * the rest of the MIPS kernel code does not use the
 		 * percpu IRQ API for them.
 		 */
+		cd = &gic_all_vpes_chip_data[intr];
+		cd->map = map;
 		err = irq_domain_set_hwirq_and_chip(d, virq, hwirq,
 						    &gic_all_vpes_local_irq_controller,
-						    NULL);
+						    cd);
 		if (err)
 			return err;
 
@@ -504,7 +513,17 @@ static int gic_irq_domain_map(struct irq_domain *d, unsigned int virq,
 		break;
 	}
 
-	return gic_local_irq_domain_map(d, virq, hwirq);
+	if (!gic_local_irq_is_routable(intr))
+		return -EPERM;
+
+	spin_lock_irqsave(&gic_lock, flags);
+	for_each_online_cpu(cpu) {
+		write_gic_vl_other(mips_cm_vp_id(cpu));
+		write_gic_vo_map(intr, map);
+	}
+	spin_unlock_irqrestore(&gic_lock, flags);
+
+	return 0;
 }
 
 static int gic_irq_domain_alloc(struct irq_domain *d, unsigned int virq,
@@ -636,11 +655,25 @@ static const struct irq_domain_ops gic_ipi_domain_ops = {
 	.match = gic_ipi_domain_match,
 };
 
+static int gic_cpu_startup(unsigned int cpu)
+{
+	/* Enable or disable EIC */
+	change_gic_vl_ctl(GIC_VX_CTL_EIC,
+			  cpu_has_veic ? GIC_VX_CTL_EIC : 0);
+
+	/* Clear all local IRQ masks (ie. disable all local interrupts) */
+	write_gic_vl_rmask(~0);
+
+	/* Invoke irq_cpu_online callbacks to enable desired interrupts */
+	irq_cpu_online();
+
+	return 0;
+}
 
 static int __init gic_of_init(struct device_node *node,
 			      struct device_node *parent)
 {
-	unsigned int cpu_vec, i, j, gicconfig, cpu, v[2];
+	unsigned int cpu_vec, i, gicconfig, v[2], num_ipis;
 	unsigned long reserved;
 	phys_addr_t gic_base;
 	struct resource res;
@@ -655,7 +688,7 @@ static int __init gic_of_init(struct device_node *node,
 
 	cpu_vec = find_first_zero_bit(&reserved, hweight_long(ST0_IM));
 	if (cpu_vec == hweight_long(ST0_IM)) {
-		pr_err("No CPU vectors available for GIC\n");
+		pr_err("No CPU vectors available\n");
 		return -ENODEV;
 	}
 
@@ -668,8 +701,10 @@ static int __init gic_of_init(struct device_node *node,
 			gic_base = read_gcr_gic_base() &
 				~CM_GCR_GIC_BASE_GICEN;
 			gic_len = 0x20000;
+			pr_warn("Using inherited base address %pa\n",
+				&gic_base);
 		} else {
-			pr_err("Failed to get GIC memory range\n");
+			pr_err("Failed to get memory range\n");
 			return -ENODEV;
 		}
 	} else {
@@ -690,17 +725,7 @@ static int __init gic_of_init(struct device_node *node,
 	gic_shared_intrs >>= __ffs(GIC_CONFIG_NUMINTERRUPTS);
 	gic_shared_intrs = (gic_shared_intrs + 1) * 8;
 
-	gic_vpes = gicconfig & GIC_CONFIG_PVPS;
-	gic_vpes >>= __ffs(GIC_CONFIG_PVPS);
-	gic_vpes = gic_vpes + 1;
-
 	if (cpu_has_veic) {
-		/* Set EIC mode for all VPEs */
-		for_each_present_cpu(cpu) {
-			write_gic_vl_other(mips_cm_vp_id(cpu));
-			write_gic_vo_ctl(GIC_VX_CTL_EIC);
-		}
-
 		/* Always use vector 1 in EIC mode */
 		gic_cpu_pin = 0;
 		timer_cpu_pin = gic_cpu_pin;
@@ -737,7 +762,7 @@ static int __init gic_of_init(struct device_node *node,
 					       gic_shared_intrs, 0,
 					       &gic_irq_domain_ops, NULL);
 	if (!gic_irq_domain) {
-		pr_err("Failed to add GIC IRQ domain");
+		pr_err("Failed to add IRQ domain");
 		return -ENXIO;
 	}
 
@@ -746,7 +771,7 @@ static int __init gic_of_init(struct device_node *node,
 						  GIC_NUM_LOCAL_INTRS + gic_shared_intrs,
 						  node, &gic_ipi_domain_ops, NULL);
 	if (!gic_ipi_domain) {
-		pr_err("Failed to add GIC IPI domain");
+		pr_err("Failed to add IPI domain");
 		return -ENXIO;
 	}
 
@@ -756,10 +781,12 @@ static int __init gic_of_init(struct device_node *node,
 	    !of_property_read_u32_array(node, "mti,reserved-ipi-vectors", v, 2)) {
 		bitmap_set(ipi_resrv, v[0], v[1]);
 	} else {
-		/* Make the last 2 * gic_vpes available for IPIs */
-		bitmap_set(ipi_resrv,
-			   gic_shared_intrs - 2 * gic_vpes,
-			   2 * gic_vpes);
+		/*
+		 * Reserve 2 interrupts per possible CPU/VP for use as IPIs,
+		 * meeting the requirements of arch/mips SMP.
+		 */
+		num_ipis = 2 * num_possible_cpus();
+		bitmap_set(ipi_resrv, gic_shared_intrs - num_ipis, num_ipis);
 	}
 
 	bitmap_copy(ipi_available, ipi_resrv, GIC_MAX_INTRS);
@@ -773,15 +800,8 @@ static int __init gic_of_init(struct device_node *node,
 		write_gic_rmask(i);
 	}
 
-	for (i = 0; i < gic_vpes; i++) {
-		write_gic_vl_other(mips_cm_vp_id(i));
-		for (j = 0; j < GIC_NUM_LOCAL_INTRS; j++) {
-			if (!gic_local_irq_is_routable(j))
-				continue;
-			write_gic_vo_rmask(BIT(j));
-		}
-	}
-
-	return 0;
+	return cpuhp_setup_state(CPUHP_AP_IRQ_MIPS_GIC_STARTING,
+				 "irqchip/mips/gic:starting",
+				 gic_cpu_startup, NULL);
 }
 IRQCHIP_DECLARE(mips_gic, "mti,gic", gic_of_init);

drivers/irqchip/irq-omap-intc.c

@@ -25,10 +25,6 @@
 
 #include <linux/irqchip/irq-omap-intc.h>
 
-/* Define these here for now until we drop all board-files */
-#define OMAP24XX_IC_BASE	0x480fe000
-#define OMAP34XX_IC_BASE	0x48200000
-
 /* selected INTC register offsets */
 
 #define INTC_REVISION		0x0000
@@ -70,8 +66,8 @@ static struct omap_intc_regs intc_context;
 
 static struct irq_domain *domain;
 static void __iomem *omap_irq_base;
-static int omap_nr_pending = 3;
-static int omap_nr_irqs = 96;
+static int omap_nr_pending;
+static int omap_nr_irqs;
 
 static void intc_writel(u32 reg, u32 val)
 {
@@ -364,14 +360,6 @@ omap_intc_handle_irq(struct pt_regs *regs)
 	handle_domain_irq(domain, irqnr, regs);
 }
 
-void __init omap3_init_irq(void)
-{
-	omap_nr_irqs = 96;
-	omap_nr_pending = 3;
-	omap_init_irq(OMAP34XX_IC_BASE, NULL);
-	set_handle_irq(omap_intc_handle_irq);
-}
-
 static int __init intc_of_init(struct device_node *node,
 			     struct device_node *parent)
 {

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)) {

drivers/irqchip/irq-sni-exiu.c

@@ -0,0 +1,227 @@
+/*
+ * Driver for Socionext External Interrupt Unit (EXIU)
+ *
+ * Copyright (c) 2017 Linaro, Ltd. <ard.biesheuvel@linaro.org>
+ *
+ * Based on irq-tegra.c:
+ *   Copyright (C) 2011 Google, Inc.
+ *   Copyright (C) 2010,2013, NVIDIA Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/irqchip.h>
+#include <linux/irqdomain.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+
+#define NUM_IRQS	32
+
+#define EIMASK		0x00
+#define EISRCSEL	0x04
+#define EIREQSTA	0x08
+#define EIRAWREQSTA	0x0C
+#define EIREQCLR	0x10
+#define EILVL		0x14
+#define EIEDG		0x18
+#define EISIR		0x1C
+
+struct exiu_irq_data {
+	void __iomem	*base;
+	u32		spi_base;
+};
+
+static void exiu_irq_eoi(struct irq_data *d)
+{
+	struct exiu_irq_data *data = irq_data_get_irq_chip_data(d);
+
+	writel(BIT(d->hwirq), data->base + EIREQCLR);
+	irq_chip_eoi_parent(d);
+}
+
+static void exiu_irq_mask(struct irq_data *d)
+{
+	struct exiu_irq_data *data = irq_data_get_irq_chip_data(d);
+	u32 val;
+
+	val = readl_relaxed(data->base + EIMASK) | BIT(d->hwirq);
+	writel_relaxed(val, data->base + EIMASK);
+	irq_chip_mask_parent(d);
+}
+
+static void exiu_irq_unmask(struct irq_data *d)
+{
+	struct exiu_irq_data *data = irq_data_get_irq_chip_data(d);
+	u32 val;
+
+	val = readl_relaxed(data->base + EIMASK) & ~BIT(d->hwirq);
+	writel_relaxed(val, data->base + EIMASK);
+	irq_chip_unmask_parent(d);
+}
+
+static void exiu_irq_enable(struct irq_data *d)
+{
+	struct exiu_irq_data *data = irq_data_get_irq_chip_data(d);
+	u32 val;
+
+	/* clear interrupts that were latched while disabled */
+	writel_relaxed(BIT(d->hwirq), data->base + EIREQCLR);
+
+	val = readl_relaxed(data->base + EIMASK) & ~BIT(d->hwirq);
+	writel_relaxed(val, data->base + EIMASK);
+	irq_chip_enable_parent(d);
+}
+
+static int exiu_irq_set_type(struct irq_data *d, unsigned int type)
+{
+	struct exiu_irq_data *data = irq_data_get_irq_chip_data(d);
+	u32 val;
+
+	val = readl_relaxed(data->base + EILVL);
+	if (type == IRQ_TYPE_EDGE_RISING || type == IRQ_TYPE_LEVEL_HIGH)
+		val |= BIT(d->hwirq);
+	else
+		val &= ~BIT(d->hwirq);
+	writel_relaxed(val, data->base + EILVL);
+
+	val = readl_relaxed(data->base + EIEDG);
+	if (type == IRQ_TYPE_LEVEL_LOW || type == IRQ_TYPE_LEVEL_HIGH)
+		val &= ~BIT(d->hwirq);
+	else
+		val |= BIT(d->hwirq);
+	writel_relaxed(val, data->base + EIEDG);
+
+	writel_relaxed(BIT(d->hwirq), data->base + EIREQCLR);
+
+	return irq_chip_set_type_parent(d, IRQ_TYPE_LEVEL_HIGH);
+}
+
+static struct irq_chip exiu_irq_chip = {
+	.name			= "EXIU",
+	.irq_eoi		= exiu_irq_eoi,
+	.irq_enable		= exiu_irq_enable,
+	.irq_mask		= exiu_irq_mask,
+	.irq_unmask		= exiu_irq_unmask,
+	.irq_set_type		= exiu_irq_set_type,
+	.irq_set_affinity	= irq_chip_set_affinity_parent,
+	.flags			= IRQCHIP_SET_TYPE_MASKED |
+				  IRQCHIP_SKIP_SET_WAKE |
+				  IRQCHIP_EOI_THREADED |
+				  IRQCHIP_MASK_ON_SUSPEND,
+};
+
+static int exiu_domain_translate(struct irq_domain *domain,
+				 struct irq_fwspec *fwspec,
+				 unsigned long *hwirq,
+				 unsigned int *type)
+{
+	struct exiu_irq_data *info = domain->host_data;
+
+	if (is_of_node(fwspec->fwnode)) {
+		if (fwspec->param_count != 3)
+			return -EINVAL;
+
+		if (fwspec->param[0] != GIC_SPI)
+			return -EINVAL; /* No PPI should point to this domain */
+
+		*hwirq = fwspec->param[1] - info->spi_base;
+		*type = fwspec->param[2] & IRQ_TYPE_SENSE_MASK;
+		return 0;
+	}
+	return -EINVAL;
+}
+
+static int exiu_domain_alloc(struct irq_domain *dom, unsigned int virq,
+			     unsigned int nr_irqs, void *data)
+{
+	struct irq_fwspec *fwspec = data;
+	struct irq_fwspec parent_fwspec;
+	struct exiu_irq_data *info = dom->host_data;
+	irq_hw_number_t hwirq;
+
+	if (fwspec->param_count != 3)
+		return -EINVAL;	/* Not GIC compliant */
+	if (fwspec->param[0] != GIC_SPI)
+		return -EINVAL;	/* No PPI should point to this domain */
+
+	WARN_ON(nr_irqs != 1);
+	hwirq = fwspec->param[1] - info->spi_base;
+	irq_domain_set_hwirq_and_chip(dom, virq, hwirq, &exiu_irq_chip, info);
+
+	parent_fwspec = *fwspec;
+	parent_fwspec.fwnode = dom->parent->fwnode;
+	return irq_domain_alloc_irqs_parent(dom, virq, nr_irqs, &parent_fwspec);
+}
+
+static const struct irq_domain_ops exiu_domain_ops = {
+	.translate	= exiu_domain_translate,
+	.alloc		= exiu_domain_alloc,
+	.free		= irq_domain_free_irqs_common,
+};
+
+static int __init exiu_init(struct device_node *node,
+			    struct device_node *parent)
+{
+	struct irq_domain *parent_domain, *domain;
+	struct exiu_irq_data *data;
+	int err;
+
+	if (!parent) {
+		pr_err("%pOF: no parent, giving up\n", node);
+		return -ENODEV;
+	}
+
+	parent_domain = irq_find_host(parent);
+	if (!parent_domain) {
+		pr_err("%pOF: unable to obtain parent domain\n", node);
+		return -ENXIO;
+	}
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	if (of_property_read_u32(node, "socionext,spi-base", &data->spi_base)) {
+		pr_err("%pOF: failed to parse 'spi-base' property\n", node);
+		err = -ENODEV;
+		goto out_free;
+	}
+
+	data->base = of_iomap(node, 0);
+	if (IS_ERR(data->base)) {
+		err = PTR_ERR(data->base);
+		goto out_free;
+	}
+
+	/* clear and mask all interrupts */
+	writel_relaxed(0xFFFFFFFF, data->base + EIREQCLR);
+	writel_relaxed(0xFFFFFFFF, data->base + EIMASK);
+
+	domain = irq_domain_add_hierarchy(parent_domain, 0, NUM_IRQS, node,
+					  &exiu_domain_ops, data);
+	if (!domain) {
+		pr_err("%pOF: failed to allocate domain\n", node);
+		err = -ENOMEM;
+		goto out_unmap;
+	}
+
+	pr_info("%pOF: %d interrupts forwarded to %pOF\n", node, NUM_IRQS,
+		parent);
+
+	return 0;
+
+out_unmap:
+	iounmap(data->base);
+out_free:
+	kfree(data);
+	return err;
+}
+IRQCHIP_DECLARE(exiu, "socionext,synquacer-exiu", exiu_init);

drivers/irqchip/irq-stm32-exti.c

@@ -14,27 +14,99 @@
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
 
-#define EXTI_IMR	0x0
-#define EXTI_EMR	0x4
-#define EXTI_RTSR	0x8
-#define EXTI_FTSR	0xc
-#define EXTI_SWIER	0x10
-#define EXTI_PR		0x14
+#define IRQS_PER_BANK 32
+
+struct stm32_exti_bank {
+	u32 imr_ofst;
+	u32 emr_ofst;
+	u32 rtsr_ofst;
+	u32 ftsr_ofst;
+	u32 swier_ofst;
+	u32 pr_ofst;
+};
+
+static const struct stm32_exti_bank stm32f4xx_exti_b1 = {
+	.imr_ofst	= 0x00,
+	.emr_ofst	= 0x04,
+	.rtsr_ofst	= 0x08,
+	.ftsr_ofst	= 0x0C,
+	.swier_ofst	= 0x10,
+	.pr_ofst	= 0x14,
+};
+
+static const struct stm32_exti_bank *stm32f4xx_exti_banks[] = {
+	&stm32f4xx_exti_b1,
+};
+
+static const struct stm32_exti_bank stm32h7xx_exti_b1 = {
+	.imr_ofst	= 0x80,
+	.emr_ofst	= 0x84,
+	.rtsr_ofst	= 0x00,
+	.ftsr_ofst	= 0x04,
+	.swier_ofst	= 0x08,
+	.pr_ofst	= 0x88,
+};
+
+static const struct stm32_exti_bank stm32h7xx_exti_b2 = {
+	.imr_ofst	= 0x90,
+	.emr_ofst	= 0x94,
+	.rtsr_ofst	= 0x20,
+	.ftsr_ofst	= 0x24,
+	.swier_ofst	= 0x28,
+	.pr_ofst	= 0x98,
+};
+
+static const struct stm32_exti_bank stm32h7xx_exti_b3 = {
+	.imr_ofst	= 0xA0,
+	.emr_ofst	= 0xA4,
+	.rtsr_ofst	= 0x40,
+	.ftsr_ofst	= 0x44,
+	.swier_ofst	= 0x48,
+	.pr_ofst	= 0xA8,
+};
+
+static const struct stm32_exti_bank *stm32h7xx_exti_banks[] = {
+	&stm32h7xx_exti_b1,
+	&stm32h7xx_exti_b2,
+	&stm32h7xx_exti_b3,
+};
+
+static unsigned long stm32_exti_pending(struct irq_chip_generic *gc)
+{
+	const struct stm32_exti_bank *stm32_bank = gc->private;
+
+	return irq_reg_readl(gc, stm32_bank->pr_ofst);
+}
+
+static void stm32_exti_irq_ack(struct irq_chip_generic *gc, u32 mask)
+{
+	const struct stm32_exti_bank *stm32_bank = gc->private;
+
+	irq_reg_writel(gc, mask, stm32_bank->pr_ofst);
+}
 
 static void stm32_irq_handler(struct irq_desc *desc)
 {
 	struct irq_domain *domain = irq_desc_get_handler_data(desc);
-	struct irq_chip_generic *gc = domain->gc->gc[0];
 	struct irq_chip *chip = irq_desc_get_chip(desc);
+	unsigned int virq, nbanks = domain->gc->num_chips;
+	struct irq_chip_generic *gc;
+	const struct stm32_exti_bank *stm32_bank;
 	unsigned long pending;
-	int n;
+	int n, i, irq_base = 0;
 
 	chained_irq_enter(chip, desc);
 
-	while ((pending = irq_reg_readl(gc, EXTI_PR))) {
-		for_each_set_bit(n, &pending, BITS_PER_LONG) {
-			generic_handle_irq(irq_find_mapping(domain, n));
-			irq_reg_writel(gc, BIT(n), EXTI_PR);
+	for (i = 0; i < nbanks; i++, irq_base += IRQS_PER_BANK) {
+		gc = irq_get_domain_generic_chip(domain, irq_base);
+		stm32_bank = gc->private;
+
+		while ((pending = stm32_exti_pending(gc))) {
+			for_each_set_bit(n, &pending, IRQS_PER_BANK) {
+				virq = irq_find_mapping(domain, irq_base + n);
+				generic_handle_irq(virq);
+				stm32_exti_irq_ack(gc, BIT(n));
+			}
 		}
 	}
 
@@ -44,13 +116,14 @@ static void stm32_irq_handler(struct irq_desc *desc)
 static int stm32_irq_set_type(struct irq_data *data, unsigned int type)
 {
 	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(data);
-	int pin = data->hwirq;
+	const struct stm32_exti_bank *stm32_bank = gc->private;
+	int pin = data->hwirq % IRQS_PER_BANK;
 	u32 rtsr, ftsr;
 
 	irq_gc_lock(gc);
 
-	rtsr = irq_reg_readl(gc, EXTI_RTSR);
-	ftsr = irq_reg_readl(gc, EXTI_FTSR);
+	rtsr = irq_reg_readl(gc, stm32_bank->rtsr_ofst);
+	ftsr = irq_reg_readl(gc, stm32_bank->ftsr_ofst);
 
 	switch (type) {
 	case IRQ_TYPE_EDGE_RISING:
@@ -70,8 +143,8 @@ static int stm32_irq_set_type(struct irq_data *data, unsigned int type)
 		return -EINVAL;
 	}
 
-	irq_reg_writel(gc, rtsr, EXTI_RTSR);
-	irq_reg_writel(gc, ftsr, EXTI_FTSR);
+	irq_reg_writel(gc, rtsr, stm32_bank->rtsr_ofst);
+	irq_reg_writel(gc, ftsr, stm32_bank->ftsr_ofst);
 
 	irq_gc_unlock(gc);
 
@@ -81,17 +154,18 @@ static int stm32_irq_set_type(struct irq_data *data, unsigned int type)
 static int stm32_irq_set_wake(struct irq_data *data, unsigned int on)
 {
 	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(data);
-	int pin = data->hwirq;
-	u32 emr;
+	const struct stm32_exti_bank *stm32_bank = gc->private;
+	int pin = data->hwirq % IRQS_PER_BANK;
+	u32 imr;
 
 	irq_gc_lock(gc);
 
-	emr = irq_reg_readl(gc, EXTI_EMR);
+	imr = irq_reg_readl(gc, stm32_bank->imr_ofst);
 	if (on)
-		emr |= BIT(pin);
+		imr |= BIT(pin);
 	else
-		emr &= ~BIT(pin);
-	irq_reg_writel(gc, emr, EXTI_EMR);
+		imr &= ~BIT(pin);
+	irq_reg_writel(gc, imr, stm32_bank->imr_ofst);
 
 	irq_gc_unlock(gc);
 
@@ -101,11 +175,12 @@ static int stm32_irq_set_wake(struct irq_data *data, unsigned int on)
 static int stm32_exti_alloc(struct irq_domain *d, unsigned int virq,
 			    unsigned int nr_irqs, void *data)
 {
-	struct irq_chip_generic *gc = d->gc->gc[0];
+	struct irq_chip_generic *gc;
 	struct irq_fwspec *fwspec = data;
 	irq_hw_number_t hwirq;
 
 	hwirq = fwspec->param[0];
+	gc = irq_get_domain_generic_chip(d, hwirq);
 
 	irq_map_generic_chip(d, virq, hwirq);
 	irq_domain_set_info(d, virq, hwirq, &gc->chip_types->chip, gc,
@@ -129,8 +204,9 @@ struct irq_domain_ops irq_exti_domain_ops = {
 	.free	= stm32_exti_free,
 };
 
-static int __init stm32_exti_init(struct device_node *node,
-				  struct device_node *parent)
+static int
+__init stm32_exti_init(const struct stm32_exti_bank **stm32_exti_banks,
+		       int bank_nr, struct device_node *node)
 {
 	unsigned int clr = IRQ_NOREQUEST | IRQ_NOPROBE | IRQ_NOAUTOEN;
 	int nr_irqs, nr_exti, ret, i;
@@ -144,23 +220,16 @@ static int __init stm32_exti_init(struct device_node *node,
 		return -ENOMEM;
 	}
 
-	/* Determine number of irqs supported */
-	writel_relaxed(~0UL, base + EXTI_RTSR);
-	nr_exti = fls(readl_relaxed(base + EXTI_RTSR));
-	writel_relaxed(0, base + EXTI_RTSR);
-
-	pr_info("%pOF: %d External IRQs detected\n", node, nr_exti);
-
-	domain = irq_domain_add_linear(node, nr_exti,
+	domain = irq_domain_add_linear(node, bank_nr * IRQS_PER_BANK,
 				       &irq_exti_domain_ops, NULL);
 	if (!domain) {
 		pr_err("%s: Could not register interrupt domain.\n",
-				node->name);
+		       node->name);
 		ret = -ENOMEM;
 		goto out_unmap;
 	}
 
-	ret = irq_alloc_domain_generic_chips(domain, nr_exti, 1, "exti",
+	ret = irq_alloc_domain_generic_chips(domain, IRQS_PER_BANK, 1, "exti",
 					     handle_edge_irq, clr, 0, 0);
 	if (ret) {
 		pr_err("%pOF: Could not allocate generic interrupt chip.\n",
@@ -168,18 +237,41 @@ static int __init stm32_exti_init(struct device_node *node,
 		goto out_free_domain;
 	}
 
-	gc = domain->gc->gc[0];
-	gc->reg_base                         = base;
-	gc->chip_types->type               = IRQ_TYPE_EDGE_BOTH;
-	gc->chip_types->chip.name          = gc->chip_types[0].chip.name;
-	gc->chip_types->chip.irq_ack       = irq_gc_ack_set_bit;
-	gc->chip_types->chip.irq_mask      = irq_gc_mask_clr_bit;
-	gc->chip_types->chip.irq_unmask    = irq_gc_mask_set_bit;
-	gc->chip_types->chip.irq_set_type  = stm32_irq_set_type;
-	gc->chip_types->chip.irq_set_wake  = stm32_irq_set_wake;
-	gc->chip_types->regs.ack           = EXTI_PR;
-	gc->chip_types->regs.mask          = EXTI_IMR;
-	gc->chip_types->handler            = handle_edge_irq;
+	for (i = 0; i < bank_nr; i++) {
+		const struct stm32_exti_bank *stm32_bank = stm32_exti_banks[i];
+		u32 irqs_mask;
+
+		gc = irq_get_domain_generic_chip(domain, i * IRQS_PER_BANK);
+
+		gc->reg_base = base;
+		gc->chip_types->type = IRQ_TYPE_EDGE_BOTH;
+		gc->chip_types->chip.irq_ack = irq_gc_ack_set_bit;
+		gc->chip_types->chip.irq_mask = irq_gc_mask_clr_bit;
+		gc->chip_types->chip.irq_unmask = irq_gc_mask_set_bit;
+		gc->chip_types->chip.irq_set_type = stm32_irq_set_type;
+		gc->chip_types->chip.irq_set_wake = stm32_irq_set_wake;
+		gc->chip_types->regs.ack = stm32_bank->pr_ofst;
+		gc->chip_types->regs.mask = stm32_bank->imr_ofst;
+		gc->private = (void *)stm32_bank;
+
+		/* Determine number of irqs supported */
+		writel_relaxed(~0UL, base + stm32_bank->rtsr_ofst);
+		irqs_mask = readl_relaxed(base + stm32_bank->rtsr_ofst);
+		nr_exti = fls(readl_relaxed(base + stm32_bank->rtsr_ofst));
+
+		/*
+		 * This IP has no reset, so after hot reboot we should
+		 * clear registers to avoid residue
+		 */
+		writel_relaxed(0, base + stm32_bank->imr_ofst);
+		writel_relaxed(0, base + stm32_bank->emr_ofst);
+		writel_relaxed(0, base + stm32_bank->rtsr_ofst);
+		writel_relaxed(0, base + stm32_bank->ftsr_ofst);
+		writel_relaxed(~0UL, base + stm32_bank->pr_ofst);
+
+		pr_info("%s: bank%d, External IRQs available:%#x\n",
+			node->full_name, i, irqs_mask);
+	}
 
 	nr_irqs = of_irq_count(node);
 	for (i = 0; i < nr_irqs; i++) {
@@ -198,4 +290,20 @@ out_unmap:
 	return ret;
 }
 
-IRQCHIP_DECLARE(stm32_exti, "st,stm32-exti", stm32_exti_init);
+static int __init stm32f4_exti_of_init(struct device_node *np,
+				       struct device_node *parent)
+{
+	return stm32_exti_init(stm32f4xx_exti_banks,
+			ARRAY_SIZE(stm32f4xx_exti_banks), np);
+}
+
+IRQCHIP_DECLARE(stm32f4_exti, "st,stm32-exti", stm32f4_exti_of_init);
+
+static int __init stm32h7_exti_of_init(struct device_node *np,
+				       struct device_node *parent)
+{
+	return stm32_exti_init(stm32h7xx_exti_banks,
+			ARRAY_SIZE(stm32h7xx_exti_banks), np);
+}
+
+IRQCHIP_DECLARE(stm32h7_exti, "st,stm32h7-exti", stm32h7_exti_of_init);

drivers/pinctrl/stm32/pinctrl-stm32.c

@@ -289,13 +289,14 @@ static int stm32_gpio_domain_translate(struct irq_domain *d,
 	return 0;
 }
 
-static void stm32_gpio_domain_activate(struct irq_domain *d,
-				       struct irq_data *irq_data)
+static int stm32_gpio_domain_activate(struct irq_domain *d,
+				      struct irq_data *irq_data, bool early)
 {
 	struct stm32_gpio_bank *bank = d->host_data;
 	struct stm32_pinctrl *pctl = dev_get_drvdata(bank->gpio_chip.parent);
 
 	regmap_field_write(pctl->irqmux[irq_data->hwirq], bank->bank_nr);
+	return 0;
 }
 
 static int stm32_gpio_domain_alloc(struct irq_domain *d,

include/linux/cpuhotplug.h

@@ -99,6 +99,7 @@ enum cpuhp_state {
 	CPUHP_AP_IRQ_HIP04_STARTING,
 	CPUHP_AP_IRQ_ARMADA_XP_STARTING,
 	CPUHP_AP_IRQ_BCM2836_STARTING,
+	CPUHP_AP_IRQ_MIPS_GIC_STARTING,
 	CPUHP_AP_ARM_MVEBU_COHERENCY,
 	CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING,
 	CPUHP_AP_PERF_X86_STARTING,

include/linux/irq.h

@@ -1114,6 +1114,28 @@ static inline u32 irq_reg_readl(struct irq_chip_generic *gc,
 		return readl(gc->reg_base + reg_offset);
 }
 
+struct irq_matrix;
+struct irq_matrix *irq_alloc_matrix(unsigned int matrix_bits,
+				    unsigned int alloc_start,
+				    unsigned int alloc_end);
+void irq_matrix_online(struct irq_matrix *m);
+void irq_matrix_offline(struct irq_matrix *m);
+void irq_matrix_assign_system(struct irq_matrix *m, unsigned int bit, bool replace);
+int irq_matrix_reserve_managed(struct irq_matrix *m, const struct cpumask *msk);
+void irq_matrix_remove_managed(struct irq_matrix *m, const struct cpumask *msk);
+int irq_matrix_alloc_managed(struct irq_matrix *m, unsigned int cpu);
+void irq_matrix_reserve(struct irq_matrix *m);
+void irq_matrix_remove_reserved(struct irq_matrix *m);
+int irq_matrix_alloc(struct irq_matrix *m, const struct cpumask *msk,
+		     bool reserved, unsigned int *mapped_cpu);
+void irq_matrix_free(struct irq_matrix *m, unsigned int cpu,
+		     unsigned int bit, bool managed);
+void irq_matrix_assign(struct irq_matrix *m, unsigned int bit);
+unsigned int irq_matrix_available(struct irq_matrix *m, bool cpudown);
+unsigned int irq_matrix_allocated(struct irq_matrix *m);
+unsigned int irq_matrix_reserved(struct irq_matrix *m);
+void irq_matrix_debug_show(struct seq_file *sf, struct irq_matrix *m, int ind);
+
 /* Contrary to Linux irqs, for hardware irqs the irq number 0 is valid */
 #define INVALID_HWIRQ	(~0UL)
 irq_hw_number_t ipi_get_hwirq(unsigned int irq, unsigned int cpu);

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)
 
@@ -461,6 +462,7 @@
 #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
@@ -549,6 +551,8 @@
 #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 */
@@ -64,12 +71,14 @@ struct its_vpe {
  * @vm:		Pointer to the GICv4 notion of a VM
  * @vpe:	Pointer to the GICv4 notion of a virtual CPU (VPE)
  * @vintid:	Virtual LPI number
+ * @properties:	Priority and enable bits (as written in the prop table)
  * @db_enabled:	Is the VPE doorbell to be generated?
  */
 struct its_vlpi_map {
 	struct its_vm		*vm;
 	struct its_vpe		*vpe;
 	u32			vintid;
+	u8			properties;
 	bool			db_enabled;
 };
 

include/linux/irqchip/irq-omap-intc.h

@@ -18,8 +18,6 @@
 #ifndef __INCLUDE_LINUX_IRQCHIP_IRQ_OMAP_INTC_H
 #define __INCLUDE_LINUX_IRQCHIP_IRQ_OMAP_INTC_H
 
-void omap3_init_irq(void);
-
 int omap_irq_pending(void);
 void omap_intc_save_context(void);
 void omap_intc_restore_context(void);

include/linux/irqdesc.h

@@ -94,6 +94,7 @@ struct irq_desc {
 #endif
 #ifdef CONFIG_GENERIC_IRQ_DEBUGFS
 	struct dentry		*debugfs_file;
+	const char		*dev_name;
 #endif
 #ifdef CONFIG_SPARSE_IRQ
 	struct rcu_head		rcu;

include/linux/irqdomain.h

@@ -33,6 +33,7 @@
 #include <linux/types.h>
 #include <linux/irqhandler.h>
 #include <linux/of.h>
+#include <linux/mutex.h>
 #include <linux/radix-tree.h>
 
 struct device_node;
@@ -41,6 +42,7 @@ struct of_device_id;
 struct irq_chip;
 struct irq_data;
 struct cpumask;
+struct seq_file;
 
 /* Number of irqs reserved for a legacy isa controller */
 #define NUM_ISA_INTERRUPTS	16
@@ -105,18 +107,21 @@ struct irq_domain_ops {
 	int (*xlate)(struct irq_domain *d, struct device_node *node,
 		     const u32 *intspec, unsigned int intsize,
 		     unsigned long *out_hwirq, unsigned int *out_type);
-
 #ifdef	CONFIG_IRQ_DOMAIN_HIERARCHY
 	/* extended V2 interfaces to support hierarchy irq_domains */
 	int (*alloc)(struct irq_domain *d, unsigned int virq,
 		     unsigned int nr_irqs, void *arg);
 	void (*free)(struct irq_domain *d, unsigned int virq,
 		     unsigned int nr_irqs);
-	void (*activate)(struct irq_domain *d, struct irq_data *irq_data);
+	int (*activate)(struct irq_domain *d, struct irq_data *irqd, bool early);
 	void (*deactivate)(struct irq_domain *d, struct irq_data *irq_data);
 	int (*translate)(struct irq_domain *d, struct irq_fwspec *fwspec,
 			 unsigned long *out_hwirq, unsigned int *out_type);
 #endif
+#ifdef CONFIG_GENERIC_IRQ_DEBUGFS
+	void (*debug_show)(struct seq_file *m, struct irq_domain *d,
+			   struct irq_data *irqd, int ind);
+#endif
 };
 
 extern struct irq_domain_ops irq_generic_chip_ops;
@@ -134,8 +139,8 @@ struct irq_domain_chip_generic;
  * @mapcount: The number of mapped interrupts
  *
  * Optional elements
- * @of_node: Pointer to device tree nodes associated with the irq_domain. Used
- *           when decoding device tree interrupt specifiers.
+ * @fwnode: Pointer to firmware node associated with the irq_domain. Pretty easy
+ *          to swap it for the of_node via the irq_domain_get_of_node accessor
  * @gc: Pointer to a list of generic chips. There is a helper function for
  *      setting up one or more generic chips for interrupt controllers
  *      drivers using the generic chip library which uses this pointer.
@@ -173,6 +178,7 @@ 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[];
 };
 
@@ -438,7 +444,7 @@ extern int __irq_domain_alloc_irqs(struct irq_domain *domain, int irq_base,
 				   unsigned int nr_irqs, int node, void *arg,
 				   bool realloc, const struct cpumask *affinity);
 extern void irq_domain_free_irqs(unsigned int virq, unsigned int nr_irqs);
-extern void irq_domain_activate_irq(struct irq_data *irq_data);
+extern int irq_domain_activate_irq(struct irq_data *irq_data, bool early);
 extern void irq_domain_deactivate_irq(struct irq_data *irq_data);
 
 static inline int irq_domain_alloc_irqs(struct irq_domain *domain,
@@ -508,8 +514,6 @@ static inline bool irq_domain_is_msi_remap(struct irq_domain *domain)
 extern bool irq_domain_hierarchical_is_msi_remap(struct irq_domain *domain);
 
 #else	/* CONFIG_IRQ_DOMAIN_HIERARCHY */
-static inline void irq_domain_activate_irq(struct irq_data *data) { }
-static inline void irq_domain_deactivate_irq(struct irq_data *data) { }
 static inline int irq_domain_alloc_irqs(struct irq_domain *domain,
 			unsigned int nr_irqs, int node, void *arg)
 {
@@ -558,8 +562,6 @@ irq_domain_hierarchical_is_msi_remap(struct irq_domain *domain)
 
 #else /* CONFIG_IRQ_DOMAIN */
 static inline void irq_dispose_mapping(unsigned int virq) { }
-static inline void irq_domain_activate_irq(struct irq_data *data) { }
-static inline void irq_domain_deactivate_irq(struct irq_data *data) { }
 static inline struct irq_domain *irq_find_matching_fwnode(
 	struct fwnode_handle *fwnode, enum irq_domain_bus_token bus_token)
 {

include/linux/msi.h

@@ -284,6 +284,11 @@ enum {
 	MSI_FLAG_PCI_MSIX		= (1 << 3),
 	/* Needs early activate, required for PCI */
 	MSI_FLAG_ACTIVATE_EARLY		= (1 << 4),
+	/*
+	 * Must reactivate when irq is started even when
+	 * MSI_FLAG_ACTIVATE_EARLY has been set.
+	 */
+	MSI_FLAG_MUST_REACTIVATE	= (1 << 5),
 };
 
 int msi_domain_set_affinity(struct irq_data *data, const struct cpumask *mask,

include/trace/events/irq_matrix.h

@@ -0,0 +1,201 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM irq_matrix
+
+#if !defined(_TRACE_IRQ_MATRIX_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_IRQ_MATRIX_H
+
+#include <linux/tracepoint.h>
+
+struct irq_matrix;
+struct cpumap;
+
+DECLARE_EVENT_CLASS(irq_matrix_global,
+
+	TP_PROTO(struct irq_matrix *matrix),
+
+	TP_ARGS(matrix),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	online_maps		)
+		__field(	unsigned int,	global_available	)
+		__field(	unsigned int,	global_reserved		)
+		__field(	unsigned int,	total_allocated		)
+	),
+
+	TP_fast_assign(
+		__entry->online_maps		= matrix->online_maps;
+		__entry->global_available	= matrix->global_available;
+		__entry->global_reserved	= matrix->global_reserved;
+		__entry->total_allocated	= matrix->total_allocated;
+	),
+
+	TP_printk("online_maps=%d global_avl=%u, global_rsvd=%u, total_alloc=%u",
+		  __entry->online_maps, __entry->global_available,
+		  __entry->global_reserved, __entry->total_allocated)
+);
+
+DECLARE_EVENT_CLASS(irq_matrix_global_update,
+
+	TP_PROTO(int bit, struct irq_matrix *matrix),
+
+	TP_ARGS(bit, matrix),
+
+	TP_STRUCT__entry(
+		__field(	int,		bit			)
+		__field(	unsigned int,	online_maps		)
+		__field(	unsigned int,	global_available	)
+		__field(	unsigned int,	global_reserved		)
+		__field(	unsigned int,	total_allocated		)
+	),
+
+	TP_fast_assign(
+		__entry->bit			= bit;
+		__entry->online_maps		= matrix->online_maps;
+		__entry->global_available	= matrix->global_available;
+		__entry->global_reserved	= matrix->global_reserved;
+		__entry->total_allocated	= matrix->total_allocated;
+	),
+
+	TP_printk("bit=%d online_maps=%d global_avl=%u, global_rsvd=%u, total_alloc=%u",
+		  __entry->bit, __entry->online_maps,
+		  __entry->global_available, __entry->global_reserved,
+		  __entry->total_allocated)
+);
+
+DECLARE_EVENT_CLASS(irq_matrix_cpu,
+
+	TP_PROTO(int bit, unsigned int cpu, struct irq_matrix *matrix,
+		 struct cpumap *cmap),
+
+	TP_ARGS(bit, cpu, matrix, cmap),
+
+	TP_STRUCT__entry(
+		__field(	int,		bit			)
+		__field(	unsigned int,	cpu			)
+		__field(	bool,		online			)
+		__field(	unsigned int,	available		)
+		__field(	unsigned int,	allocated		)
+		__field(	unsigned int,	managed			)
+		__field(	unsigned int,	online_maps		)
+		__field(	unsigned int,	global_available	)
+		__field(	unsigned int,	global_reserved		)
+		__field(	unsigned int,	total_allocated		)
+	),
+
+	TP_fast_assign(
+		__entry->bit			= bit;
+		__entry->cpu			= cpu;
+		__entry->online			= cmap->online;
+		__entry->available		= cmap->available;
+		__entry->allocated		= cmap->allocated;
+		__entry->managed		= cmap->managed;
+		__entry->online_maps		= matrix->online_maps;
+		__entry->global_available	= matrix->global_available;
+		__entry->global_reserved	= matrix->global_reserved;
+		__entry->total_allocated	= matrix->total_allocated;
+	),
+
+	TP_printk("bit=%d cpu=%u online=%d avl=%u alloc=%u managed=%u online_maps=%u global_avl=%u, global_rsvd=%u, total_alloc=%u",
+		  __entry->bit, __entry->cpu, __entry->online,
+		  __entry->available, __entry->allocated,
+		  __entry->managed, __entry->online_maps,
+		  __entry->global_available, __entry->global_reserved,
+		  __entry->total_allocated)
+);
+
+DEFINE_EVENT(irq_matrix_global, irq_matrix_online,
+
+	TP_PROTO(struct irq_matrix *matrix),
+
+	TP_ARGS(matrix)
+);
+
+DEFINE_EVENT(irq_matrix_global, irq_matrix_offline,
+
+	TP_PROTO(struct irq_matrix *matrix),
+
+	TP_ARGS(matrix)
+);
+
+DEFINE_EVENT(irq_matrix_global, irq_matrix_reserve,
+
+	TP_PROTO(struct irq_matrix *matrix),
+
+	TP_ARGS(matrix)
+);
+
+DEFINE_EVENT(irq_matrix_global, irq_matrix_remove_reserved,
+
+	TP_PROTO(struct irq_matrix *matrix),
+
+	TP_ARGS(matrix)
+);
+
+DEFINE_EVENT(irq_matrix_global_update, irq_matrix_assign_system,
+
+	TP_PROTO(int bit, struct irq_matrix *matrix),
+
+	TP_ARGS(bit, matrix)
+);
+
+DEFINE_EVENT(irq_matrix_cpu, irq_matrix_alloc_reserved,
+
+	TP_PROTO(int bit, unsigned int cpu,
+		 struct irq_matrix *matrix, struct cpumap *cmap),
+
+	TP_ARGS(bit, cpu, matrix, cmap)
+);
+
+DEFINE_EVENT(irq_matrix_cpu, irq_matrix_reserve_managed,
+
+	TP_PROTO(int bit, unsigned int cpu,
+		 struct irq_matrix *matrix, struct cpumap *cmap),
+
+	TP_ARGS(bit, cpu, matrix, cmap)
+);
+
+DEFINE_EVENT(irq_matrix_cpu, irq_matrix_remove_managed,
+
+	TP_PROTO(int bit, unsigned int cpu,
+		 struct irq_matrix *matrix, struct cpumap *cmap),
+
+	TP_ARGS(bit, cpu, matrix, cmap)
+);
+
+DEFINE_EVENT(irq_matrix_cpu, irq_matrix_alloc_managed,
+
+	TP_PROTO(int bit, unsigned int cpu,
+		 struct irq_matrix *matrix, struct cpumap *cmap),
+
+	TP_ARGS(bit, cpu, matrix, cmap)
+);
+
+DEFINE_EVENT(irq_matrix_cpu, irq_matrix_assign,
+
+	TP_PROTO(int bit, unsigned int cpu,
+		 struct irq_matrix *matrix, struct cpumap *cmap),
+
+	TP_ARGS(bit, cpu, matrix, cmap)
+);
+
+DEFINE_EVENT(irq_matrix_cpu, irq_matrix_alloc,
+
+	TP_PROTO(int bit, unsigned int cpu,
+		 struct irq_matrix *matrix, struct cpumap *cmap),
+
+	TP_ARGS(bit, cpu, matrix, cmap)
+);
+
+DEFINE_EVENT(irq_matrix_cpu, irq_matrix_free,
+
+	TP_PROTO(int bit, unsigned int cpu,
+		 struct irq_matrix *matrix, struct cpumap *cmap),
+
+	TP_ARGS(bit, cpu, matrix, cmap)
+);
+
+
+#endif /*  _TRACE_IRQ_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>

kernel/irq/Kconfig

@@ -97,6 +97,9 @@ config HANDLE_DOMAIN_IRQ
 config IRQ_TIMINGS
 	bool
 
+config GENERIC_IRQ_MATRIX_ALLOCATOR
+	bool
+
 config IRQ_DOMAIN_DEBUG
 	bool "Expose hardware/virtual IRQ mapping via debugfs"
 	depends on IRQ_DOMAIN && DEBUG_FS

kernel/irq/Makefile

@@ -14,3 +14,4 @@ obj-$(CONFIG_GENERIC_MSI_IRQ) += msi.o
 obj-$(CONFIG_GENERIC_IRQ_IPI) += ipi.o
 obj-$(CONFIG_SMP) += affinity.o
 obj-$(CONFIG_GENERIC_IRQ_DEBUGFS) += debugfs.o
+obj-$(CONFIG_GENERIC_IRQ_MATRIX_ALLOCATOR) += matrix.o

kernel/irq/autoprobe.c

@@ -54,7 +54,7 @@ unsigned long probe_irq_on(void)
 			if (desc->irq_data.chip->irq_set_type)
 				desc->irq_data.chip->irq_set_type(&desc->irq_data,
 							 IRQ_TYPE_PROBE);
-			irq_startup(desc, IRQ_NORESEND, IRQ_START_FORCE);
+			irq_activate_and_startup(desc, IRQ_NORESEND);
 		}
 		raw_spin_unlock_irq(&desc->lock);
 	}

kernel/irq/chip.c

@@ -207,20 +207,24 @@ __irq_startup_managed(struct irq_desc *desc, struct cpumask *aff, bool force)
 		 * Catch code which fiddles with enable_irq() on a managed
 		 * and potentially shutdown IRQ. Chained interrupt
 		 * installment or irq auto probing should not happen on
-		 * managed irqs either. Emit a warning, break the affinity
-		 * and start it up as a normal interrupt.
+		 * managed irqs either.
 		 */
 		if (WARN_ON_ONCE(force))
-			return IRQ_STARTUP_NORMAL;
+			return IRQ_STARTUP_ABORT;
 		/*
 		 * The interrupt was requested, but there is no online CPU
 		 * in it's affinity mask. Put it into managed shutdown
 		 * state and let the cpu hotplug mechanism start it up once
 		 * a CPU in the mask becomes available.
 		 */
-		irqd_set_managed_shutdown(d);
 		return IRQ_STARTUP_ABORT;
 	}
+	/*
+	 * Managed interrupts have reserved resources, so this should not
+	 * happen.
+	 */
+	if (WARN_ON(irq_domain_activate_irq(d, false)))
+		return IRQ_STARTUP_ABORT;
 	return IRQ_STARTUP_MANAGED;
 }
 #else
@@ -236,7 +240,9 @@ static int __irq_startup(struct irq_desc *desc)
 	struct irq_data *d = irq_desc_get_irq_data(desc);
 	int ret = 0;
 
-	irq_domain_activate_irq(d);
+	/* Warn if this interrupt is not activated but try nevertheless */
+	WARN_ON_ONCE(!irqd_is_activated(d));
+
 	if (d->chip->irq_startup) {
 		ret = d->chip->irq_startup(d);
 		irq_state_clr_disabled(desc);
@@ -269,6 +275,7 @@ int irq_startup(struct irq_desc *desc, bool resend, bool force)
 			ret = __irq_startup(desc);
 			break;
 		case IRQ_STARTUP_ABORT:
+			irqd_set_managed_shutdown(d);
 			return 0;
 		}
 	}
@@ -278,6 +285,22 @@ int irq_startup(struct irq_desc *desc, bool resend, bool force)
 	return ret;
 }
 
+int irq_activate(struct irq_desc *desc)
+{
+	struct irq_data *d = irq_desc_get_irq_data(desc);
+
+	if (!irqd_affinity_is_managed(d))
+		return irq_domain_activate_irq(d, false);
+	return 0;
+}
+
+void irq_activate_and_startup(struct irq_desc *desc, bool resend)
+{
+	if (WARN_ON(irq_activate(desc)))
+		return;
+	irq_startup(desc, resend, IRQ_START_FORCE);
+}
+
 static void __irq_disable(struct irq_desc *desc, bool mask);
 
 void irq_shutdown(struct irq_desc *desc)
@@ -953,7 +976,7 @@ __irq_do_set_handler(struct irq_desc *desc, irq_flow_handler_t handle,
 		irq_settings_set_norequest(desc);
 		irq_settings_set_nothread(desc);
 		desc->action = &chained_action;
-		irq_startup(desc, IRQ_RESEND, IRQ_START_FORCE);
+		irq_activate_and_startup(desc, IRQ_RESEND);
 	}
 }
 

kernel/irq/debugfs.c

@@ -81,6 +81,8 @@ irq_debug_show_data(struct seq_file *m, struct irq_data *data, int ind)
 		   data->domain ? data->domain->name : "");
 	seq_printf(m, "%*shwirq:   0x%lx\n", ind + 1, "", data->hwirq);
 	irq_debug_show_chip(m, data, ind + 1);
+	if (data->domain && data->domain->ops && data->domain->ops->debug_show)
+		data->domain->ops->debug_show(m, NULL, data, ind + 1);
 #ifdef	CONFIG_IRQ_DOMAIN_HIERARCHY
 	if (!data->parent_data)
 		return;
@@ -149,6 +151,7 @@ static int irq_debug_show(struct seq_file *m, void *p)
 	raw_spin_lock_irq(&desc->lock);
 	data = irq_desc_get_irq_data(desc);
 	seq_printf(m, "handler:  %pf\n", desc->handle_irq);
+	seq_printf(m, "device:   %s\n", desc->dev_name);
 	seq_printf(m, "status:   0x%08x\n", desc->status_use_accessors);
 	irq_debug_show_bits(m, 0, desc->status_use_accessors, irqdesc_states,
 			    ARRAY_SIZE(irqdesc_states));
@@ -226,6 +229,15 @@ static const struct file_operations dfs_irq_ops = {
 	.release	= single_release,
 };
 
+void irq_debugfs_copy_devname(int irq, struct device *dev)
+{
+	struct irq_desc *desc = irq_to_desc(irq);
+	const char *name = dev_name(dev);
+
+	if (name)
+		desc->dev_name = kstrdup(name, GFP_KERNEL);
+}
+
 void irq_add_debugfs_entry(unsigned int irq, struct irq_desc *desc)
 {
 	char name [10];

kernel/irq/internals.h

@@ -75,6 +75,8 @@ extern void __enable_irq(struct irq_desc *desc);
 #define IRQ_START_FORCE	true
 #define IRQ_START_COND	false
 
+extern int irq_activate(struct irq_desc *desc);
+extern void irq_activate_and_startup(struct irq_desc *desc, bool resend);
 extern int irq_startup(struct irq_desc *desc, bool resend, bool force);
 
 extern void irq_shutdown(struct irq_desc *desc);
@@ -437,6 +439,18 @@ static inline bool irq_fixup_move_pending(struct irq_desc *desc, bool fclear)
 }
 #endif /* !CONFIG_GENERIC_PENDING_IRQ */
 
+#if !defined(CONFIG_IRQ_DOMAIN) || !defined(CONFIG_IRQ_DOMAIN_HIERARCHY)
+static inline int irq_domain_activate_irq(struct irq_data *data, bool early)
+{
+	irqd_set_activated(data);
+	return 0;
+}
+static inline void irq_domain_deactivate_irq(struct irq_data *data)
+{
+	irqd_clr_activated(data);
+}
+#endif
+
 #ifdef CONFIG_GENERIC_IRQ_DEBUGFS
 #include <linux/debugfs.h>
 
@@ -444,7 +458,9 @@ void irq_add_debugfs_entry(unsigned int irq, struct irq_desc *desc);
 static inline void irq_remove_debugfs_entry(struct irq_desc *desc)
 {
 	debugfs_remove(desc->debugfs_file);
+	kfree(desc->dev_name);
 }
+void irq_debugfs_copy_devname(int irq, struct device *dev);
 # ifdef CONFIG_IRQ_DOMAIN
 void irq_domain_debugfs_init(struct dentry *root);
 # else
@@ -459,4 +475,7 @@ static inline void irq_add_debugfs_entry(unsigned int irq, struct irq_desc *d)
 static inline void irq_remove_debugfs_entry(struct irq_desc *d)
 {
 }
+static inline void irq_debugfs_copy_devname(int irq, struct device *dev)
+{
+}
 #endif /* CONFIG_GENERIC_IRQ_DEBUGFS */

kernel/irq/irqdesc.c

@@ -27,7 +27,7 @@ static struct lock_class_key irq_desc_lock_class;
 #if defined(CONFIG_SMP)
 static int __init irq_affinity_setup(char *str)
 {
-	zalloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT);
+	alloc_bootmem_cpumask_var(&irq_default_affinity);
 	cpulist_parse(str, irq_default_affinity);
 	/*
 	 * Set at least the boot cpu. We don't want to end up with
@@ -40,10 +40,8 @@ __setup("irqaffinity=", irq_affinity_setup);
 
 static void __init init_irq_default_affinity(void)
 {
-#ifdef CONFIG_CPUMASK_OFFSTACK
-	if (!irq_default_affinity)
+	if (!cpumask_available(irq_default_affinity))
 		zalloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT);
-#endif
 	if (cpumask_empty(irq_default_affinity))
 		cpumask_setall(irq_default_affinity);
 }
@@ -448,7 +446,7 @@ static int alloc_descs(unsigned int start, unsigned int cnt, int node,
 		}
 	}
 
-	flags = affinity ? IRQD_AFFINITY_MANAGED : 0;
+	flags = affinity ? IRQD_AFFINITY_MANAGED | IRQD_MANAGED_SHUTDOWN : 0;
 	mask = NULL;
 
 	for (i = 0; i < cnt; i++) {
@@ -462,6 +460,7 @@ static int alloc_descs(unsigned int start, unsigned int cnt, int node,
 			goto err;
 		irq_insert_desc(start + i, desc);
 		irq_sysfs_add(start + i, desc);
+		irq_add_debugfs_entry(start + i, desc);
 	}
 	bitmap_set(allocated_irqs, start, cnt);
 	return start;

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);
 	}
 }
 
@@ -921,8 +921,7 @@ static void virq_debug_show_one(struct seq_file *m, struct irq_desc *desc)
 		chip = irq_data_get_irq_chip(data);
 		seq_printf(m, "%-15s  ", (chip && chip->name) ? chip->name : "none");
 
-		seq_printf(m, data ? "0x%p  " : "  %p  ",
-			   irq_data_get_irq_chip_data(data));
+		seq_printf(m, "0x%p  ", irq_data_get_irq_chip_data(data));
 
 		seq_printf(m, "   %c    ", (desc->action && desc->action->handler) ? '*' : ' ');
 		direct = (irq == hwirq) && (irq < domain->revmap_direct_max_irq);
@@ -1459,11 +1458,11 @@ static void irq_domain_fix_revmap(struct irq_data *d)
 		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);
 }
 
 /**
@@ -1682,28 +1681,36 @@ void irq_domain_free_irqs_parent(struct irq_domain *domain,
 }
 EXPORT_SYMBOL_GPL(irq_domain_free_irqs_parent);
 
-static void __irq_domain_activate_irq(struct irq_data *irq_data)
+static void __irq_domain_deactivate_irq(struct irq_data *irq_data)
 {
 	if (irq_data && irq_data->domain) {
 		struct irq_domain *domain = irq_data->domain;
 
+		if (domain->ops->deactivate)
+			domain->ops->deactivate(domain, irq_data);
 		if (irq_data->parent_data)
-			__irq_domain_activate_irq(irq_data->parent_data);
-		if (domain->ops->activate)
-			domain->ops->activate(domain, irq_data);
+			__irq_domain_deactivate_irq(irq_data->parent_data);
 	}
 }
 
-static void __irq_domain_deactivate_irq(struct irq_data *irq_data)
+static int __irq_domain_activate_irq(struct irq_data *irqd, bool early)
 {
-	if (irq_data && irq_data->domain) {
-		struct irq_domain *domain = irq_data->domain;
+	int ret = 0;
 
-		if (domain->ops->deactivate)
-			domain->ops->deactivate(domain, irq_data);
-		if (irq_data->parent_data)
-			__irq_domain_deactivate_irq(irq_data->parent_data);
+	if (irqd && irqd->domain) {
+		struct irq_domain *domain = irqd->domain;
+
+		if (irqd->parent_data)
+			ret = __irq_domain_activate_irq(irqd->parent_data,
+							early);
+		if (!ret && domain->ops->activate) {
+			ret = domain->ops->activate(domain, irqd, early);
+			/* Rollback in case of error */
+			if (ret && irqd->parent_data)
+				__irq_domain_deactivate_irq(irqd->parent_data);
+		}
 	}
+	return ret;
 }
 
 /**
@@ -1714,12 +1721,15 @@ static void __irq_domain_deactivate_irq(struct irq_data *irq_data)
  * This is the second step to call domain_ops->activate to program interrupt
  * controllers, so the interrupt could actually get delivered.
  */
-void irq_domain_activate_irq(struct irq_data *irq_data)
+int irq_domain_activate_irq(struct irq_data *irq_data, bool early)
 {
-	if (!irqd_is_activated(irq_data)) {
-		__irq_domain_activate_irq(irq_data);
+	int ret = 0;
+
+	if (!irqd_is_activated(irq_data))
+		ret = __irq_domain_activate_irq(irq_data, early);
+	if (!ret)
 		irqd_set_activated(irq_data);
-	}
+	return ret;
 }
 
 /**
@@ -1810,6 +1820,8 @@ irq_domain_debug_show_one(struct seq_file *m, struct irq_domain *d, int ind)
 		   d->revmap_size + d->revmap_direct_max_irq);
 	seq_printf(m, "%*smapped: %u\n", ind + 1, "", d->mapcount);
 	seq_printf(m, "%*sflags:  0x%08x\n", ind +1 , "", d->flags);
+	if (d->ops && d->ops->debug_show)
+		d->ops->debug_show(m, d, NULL, ind + 1);
 #ifdef	CONFIG_IRQ_DOMAIN_HIERARCHY
 	if (!d->parent)
 		return;

kernel/irq/manage.c

@@ -398,7 +398,8 @@ int irq_select_affinity_usr(unsigned int irq)
 /**
  *	irq_set_vcpu_affinity - Set vcpu affinity for the interrupt
  *	@irq: interrupt number to set affinity
- *	@vcpu_info: vCPU specific data
+ *	@vcpu_info: vCPU specific data or pointer to a percpu array of vCPU
+ *	            specific data for percpu_devid interrupts
  *
  *	This function uses the vCPU specific data to set the vCPU
  *	affinity for an irq. The vCPU specific data is passed from
@@ -536,7 +537,7 @@ void __enable_irq(struct irq_desc *desc)
 		 * time. If it was already started up, then irq_startup()
 		 * will invoke irq_enable() under the hood.
 		 */
-		irq_startup(desc, IRQ_RESEND, IRQ_START_COND);
+		irq_startup(desc, IRQ_RESEND, IRQ_START_FORCE);
 		break;
 	}
 	default:
@@ -1305,7 +1306,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 		 * thread_mask assigned. See the loop above which or's
 		 * all existing action->thread_mask bits.
 		 */
-		new->thread_mask = 1 << ffz(thread_mask);
+		new->thread_mask = 1UL << ffz(thread_mask);
 
 	} else if (new->handler == irq_default_primary_handler &&
 		   !(desc->irq_data.chip->flags & IRQCHIP_ONESHOT_SAFE)) {
@@ -1342,6 +1343,21 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 				goto out_unlock;
 		}
 
+		/*
+		 * Activate the interrupt. That activation must happen
+		 * independently of IRQ_NOAUTOEN. request_irq() can fail
+		 * and the callers are supposed to handle
+		 * that. enable_irq() of an interrupt requested with
+		 * IRQ_NOAUTOEN is not supposed to fail. The activation
+		 * keeps it in shutdown mode, it merily associates
+		 * resources if necessary and if that's not possible it
+		 * fails. Interrupts which are in managed shutdown mode
+		 * will simply ignore that activation request.
+		 */
+		ret = irq_activate(desc);
+		if (ret)
+			goto out_unlock;
+
 		desc->istate &= ~(IRQS_AUTODETECT | IRQS_SPURIOUS_DISABLED | \
 				  IRQS_ONESHOT | IRQS_WAITING);
 		irqd_clear(&desc->irq_data, IRQD_IRQ_INPROGRESS);
@@ -1417,7 +1433,6 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 		wake_up_process(new->secondary->thread);
 
 	register_irq_proc(irq, desc);
-	irq_add_debugfs_entry(irq, desc);
 	new->dir = NULL;
 	register_handler_proc(irq, new);
 	return 0;

kernel/irq/matrix.c

@@ -0,0 +1,443 @@
+/*
+ * Copyright (C) 2017 Thomas Gleixner <tglx@linutronix.de>
+ *
+ * SPDX-License-Identifier: GPL-2.0
+ */
+#include <linux/spinlock.h>
+#include <linux/seq_file.h>
+#include <linux/bitmap.h>
+#include <linux/percpu.h>
+#include <linux/cpu.h>
+#include <linux/irq.h>
+
+#define IRQ_MATRIX_SIZE	(BITS_TO_LONGS(IRQ_MATRIX_BITS) * sizeof(unsigned long))
+
+struct cpumap {
+	unsigned int		available;
+	unsigned int		allocated;
+	unsigned int		managed;
+	bool			online;
+	unsigned long		alloc_map[IRQ_MATRIX_SIZE];
+	unsigned long		managed_map[IRQ_MATRIX_SIZE];
+};
+
+struct irq_matrix {
+	unsigned int		matrix_bits;
+	unsigned int		alloc_start;
+	unsigned int		alloc_end;
+	unsigned int		alloc_size;
+	unsigned int		global_available;
+	unsigned int		global_reserved;
+	unsigned int		systembits_inalloc;
+	unsigned int		total_allocated;
+	unsigned int		online_maps;
+	struct cpumap __percpu	*maps;
+	unsigned long		scratch_map[IRQ_MATRIX_SIZE];
+	unsigned long		system_map[IRQ_MATRIX_SIZE];
+};
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/irq_matrix.h>
+
+/**
+ * irq_alloc_matrix - Allocate a irq_matrix structure and initialize it
+ * @matrix_bits:	Number of matrix bits must be <= IRQ_MATRIX_BITS
+ * @alloc_start:	From which bit the allocation search starts
+ * @alloc_end:		At which bit the allocation search ends, i.e first
+ *			invalid bit
+ */
+__init struct irq_matrix *irq_alloc_matrix(unsigned int matrix_bits,
+					   unsigned int alloc_start,
+					   unsigned int alloc_end)
+{
+	struct irq_matrix *m;
+
+	if (matrix_bits > IRQ_MATRIX_BITS)
+		return NULL;
+
+	m = kzalloc(sizeof(*m), GFP_KERNEL);
+	if (!m)
+		return NULL;
+
+	m->matrix_bits = matrix_bits;
+	m->alloc_start = alloc_start;
+	m->alloc_end = alloc_end;
+	m->alloc_size = alloc_end - alloc_start;
+	m->maps = alloc_percpu(*m->maps);
+	if (!m->maps) {
+		kfree(m);
+		return NULL;
+	}
+	return m;
+}
+
+/**
+ * irq_matrix_online - Bring the local CPU matrix online
+ * @m:		Matrix pointer
+ */
+void irq_matrix_online(struct irq_matrix *m)
+{
+	struct cpumap *cm = this_cpu_ptr(m->maps);
+
+	BUG_ON(cm->online);
+
+	bitmap_zero(cm->alloc_map, m->matrix_bits);
+	cm->available = m->alloc_size - (cm->managed + m->systembits_inalloc);
+	cm->allocated = 0;
+	m->global_available += cm->available;
+	cm->online = true;
+	m->online_maps++;
+	trace_irq_matrix_online(m);
+}
+
+/**
+ * irq_matrix_offline - Bring the local CPU matrix offline
+ * @m:		Matrix pointer
+ */
+void irq_matrix_offline(struct irq_matrix *m)
+{
+	struct cpumap *cm = this_cpu_ptr(m->maps);
+
+	/* Update the global available size */
+	m->global_available -= cm->available;
+	cm->online = false;
+	m->online_maps--;
+	trace_irq_matrix_offline(m);
+}
+
+static unsigned int matrix_alloc_area(struct irq_matrix *m, struct cpumap *cm,
+				      unsigned int num, bool managed)
+{
+	unsigned int area, start = m->alloc_start;
+	unsigned int end = m->alloc_end;
+
+	bitmap_or(m->scratch_map, cm->managed_map, m->system_map, end);
+	bitmap_or(m->scratch_map, m->scratch_map, cm->alloc_map, end);
+	area = bitmap_find_next_zero_area(m->scratch_map, end, start, num, 0);
+	if (area >= end)
+		return area;
+	if (managed)
+		bitmap_set(cm->managed_map, area, num);
+	else
+		bitmap_set(cm->alloc_map, area, num);
+	return area;
+}
+
+/**
+ * irq_matrix_assign_system - Assign system wide entry in the matrix
+ * @m:		Matrix pointer
+ * @bit:	Which bit to reserve
+ * @replace:	Replace an already allocated vector with a system
+ *		vector at the same bit position.
+ *
+ * The BUG_ON()s below are on purpose. If this goes wrong in the
+ * early boot process, then the chance to survive is about zero.
+ * If this happens when the system is life, it's not much better.
+ */
+void irq_matrix_assign_system(struct irq_matrix *m, unsigned int bit,
+			      bool replace)
+{
+	struct cpumap *cm = this_cpu_ptr(m->maps);
+
+	BUG_ON(bit > m->matrix_bits);
+	BUG_ON(m->online_maps > 1 || (m->online_maps && !replace));
+
+	set_bit(bit, m->system_map);
+	if (replace) {
+		BUG_ON(!test_and_clear_bit(bit, cm->alloc_map));
+		cm->allocated--;
+		m->total_allocated--;
+	}
+	if (bit >= m->alloc_start && bit < m->alloc_end)
+		m->systembits_inalloc++;
+
+	trace_irq_matrix_assign_system(bit, m);
+}
+
+/**
+ * irq_matrix_reserve_managed - Reserve a managed interrupt in a CPU map
+ * @m:		Matrix pointer
+ * @msk:	On which CPUs the bits should be reserved.
+ *
+ * Can be called for offline CPUs. Note, this will only reserve one bit
+ * on all CPUs in @msk, but it's not guaranteed that the bits are at the
+ * same offset on all CPUs
+ */
+int irq_matrix_reserve_managed(struct irq_matrix *m, const struct cpumask *msk)
+{
+	unsigned int cpu, failed_cpu;
+
+	for_each_cpu(cpu, msk) {
+		struct cpumap *cm = per_cpu_ptr(m->maps, cpu);
+		unsigned int bit;
+
+		bit = matrix_alloc_area(m, cm, 1, true);
+		if (bit >= m->alloc_end)
+			goto cleanup;
+		cm->managed++;
+		if (cm->online) {
+			cm->available--;
+			m->global_available--;
+		}
+		trace_irq_matrix_reserve_managed(bit, cpu, m, cm);
+	}
+	return 0;
+cleanup:
+	failed_cpu = cpu;
+	for_each_cpu(cpu, msk) {
+		if (cpu == failed_cpu)
+			break;
+		irq_matrix_remove_managed(m, cpumask_of(cpu));
+	}
+	return -ENOSPC;
+}
+
+/**
+ * irq_matrix_remove_managed - Remove managed interrupts in a CPU map
+ * @m:		Matrix pointer
+ * @msk:	On which CPUs the bits should be removed
+ *
+ * Can be called for offline CPUs
+ *
+ * This removes not allocated managed interrupts from the map. It does
+ * not matter which one because the managed interrupts free their
+ * allocation when they shut down. If not, the accounting is screwed,
+ * but all what can be done at this point is warn about it.
+ */
+void irq_matrix_remove_managed(struct irq_matrix *m, const struct cpumask *msk)
+{
+	unsigned int cpu;
+
+	for_each_cpu(cpu, msk) {
+		struct cpumap *cm = per_cpu_ptr(m->maps, cpu);
+		unsigned int bit, end = m->alloc_end;
+
+		if (WARN_ON_ONCE(!cm->managed))
+			continue;
+
+		/* Get managed bit which are not allocated */
+		bitmap_andnot(m->scratch_map, cm->managed_map, cm->alloc_map, end);
+
+		bit = find_first_bit(m->scratch_map, end);
+		if (WARN_ON_ONCE(bit >= end))
+			continue;
+
+		clear_bit(bit, cm->managed_map);
+
+		cm->managed--;
+		if (cm->online) {
+			cm->available++;
+			m->global_available++;
+		}
+		trace_irq_matrix_remove_managed(bit, cpu, m, cm);
+	}
+}
+
+/**
+ * irq_matrix_alloc_managed - Allocate a managed interrupt in a CPU map
+ * @m:		Matrix pointer
+ * @cpu:	On which CPU the interrupt should be allocated
+ */
+int irq_matrix_alloc_managed(struct irq_matrix *m, unsigned int cpu)
+{
+	struct cpumap *cm = per_cpu_ptr(m->maps, cpu);
+	unsigned int bit, end = m->alloc_end;
+
+	/* Get managed bit which are not allocated */
+	bitmap_andnot(m->scratch_map, cm->managed_map, cm->alloc_map, end);
+	bit = find_first_bit(m->scratch_map, end);
+	if (bit >= end)
+		return -ENOSPC;
+	set_bit(bit, cm->alloc_map);
+	cm->allocated++;
+	m->total_allocated++;
+	trace_irq_matrix_alloc_managed(bit, cpu, m, cm);
+	return bit;
+}
+
+/**
+ * irq_matrix_assign - Assign a preallocated interrupt in the local CPU map
+ * @m:		Matrix pointer
+ * @bit:	Which bit to mark
+ *
+ * This should only be used to mark preallocated vectors
+ */
+void irq_matrix_assign(struct irq_matrix *m, unsigned int bit)
+{
+	struct cpumap *cm = this_cpu_ptr(m->maps);
+
+	if (WARN_ON_ONCE(bit < m->alloc_start || bit >= m->alloc_end))
+		return;
+	if (WARN_ON_ONCE(test_and_set_bit(bit, cm->alloc_map)))
+		return;
+	cm->allocated++;
+	m->total_allocated++;
+	cm->available--;
+	m->global_available--;
+	trace_irq_matrix_assign(bit, smp_processor_id(), m, cm);
+}
+
+/**
+ * irq_matrix_reserve - Reserve interrupts
+ * @m:		Matrix pointer
+ *
+ * This is merily a book keeping call. It increments the number of globally
+ * reserved interrupt bits w/o actually allocating them. This allows to
+ * setup interrupt descriptors w/o assigning low level resources to it.
+ * The actual allocation happens when the interrupt gets activated.
+ */
+void irq_matrix_reserve(struct irq_matrix *m)
+{
+	if (m->global_reserved <= m->global_available &&
+	    m->global_reserved + 1 > m->global_available)
+		pr_warn("Interrupt reservation exceeds available resources\n");
+
+	m->global_reserved++;
+	trace_irq_matrix_reserve(m);
+}
+
+/**
+ * irq_matrix_remove_reserved - Remove interrupt reservation
+ * @m:		Matrix pointer
+ *
+ * This is merily a book keeping call. It decrements the number of globally
+ * reserved interrupt bits. This is used to undo irq_matrix_reserve() when the
+ * interrupt was never in use and a real vector allocated, which undid the
+ * reservation.
+ */
+void irq_matrix_remove_reserved(struct irq_matrix *m)
+{
+	m->global_reserved--;
+	trace_irq_matrix_remove_reserved(m);
+}
+
+/**
+ * irq_matrix_alloc - Allocate a regular interrupt in a CPU map
+ * @m:		Matrix pointer
+ * @msk:	Which CPUs to search in
+ * @reserved:	Allocate previously reserved interrupts
+ * @mapped_cpu: Pointer to store the CPU for which the irq was allocated
+ */
+int irq_matrix_alloc(struct irq_matrix *m, const struct cpumask *msk,
+		     bool reserved, unsigned int *mapped_cpu)
+{
+	unsigned int cpu;
+
+	for_each_cpu(cpu, msk) {
+		struct cpumap *cm = per_cpu_ptr(m->maps, cpu);
+		unsigned int bit;
+
+		if (!cm->online)
+			continue;
+
+		bit = matrix_alloc_area(m, cm, 1, false);
+		if (bit < m->alloc_end) {
+			cm->allocated++;
+			cm->available--;
+			m->total_allocated++;
+			m->global_available--;
+			if (reserved)
+				m->global_reserved--;
+			*mapped_cpu = cpu;
+			trace_irq_matrix_alloc(bit, cpu, m, cm);
+			return bit;
+		}
+	}
+	return -ENOSPC;
+}
+
+/**
+ * irq_matrix_free - Free allocated interrupt in the matrix
+ * @m:		Matrix pointer
+ * @cpu:	Which CPU map needs be updated
+ * @bit:	The bit to remove
+ * @managed:	If true, the interrupt is managed and not accounted
+ *		as available.
+ */
+void irq_matrix_free(struct irq_matrix *m, unsigned int cpu,
+		     unsigned int bit, bool managed)
+{
+	struct cpumap *cm = per_cpu_ptr(m->maps, cpu);
+
+	if (WARN_ON_ONCE(bit < m->alloc_start || bit >= m->alloc_end))
+		return;
+
+	if (cm->online) {
+		clear_bit(bit, cm->alloc_map);
+		cm->allocated--;
+		m->total_allocated--;
+		if (!managed) {
+			cm->available++;
+			m->global_available++;
+		}
+	}
+	trace_irq_matrix_free(bit, cpu, m, cm);
+}
+
+/**
+ * irq_matrix_available - Get the number of globally available irqs
+ * @m:		Pointer to the matrix to query
+ * @cpudown:	If true, the local CPU is about to go down, adjust
+ *		the number of available irqs accordingly
+ */
+unsigned int irq_matrix_available(struct irq_matrix *m, bool cpudown)
+{
+	struct cpumap *cm = this_cpu_ptr(m->maps);
+
+	return m->global_available - cpudown ? cm->available : 0;
+}
+
+/**
+ * irq_matrix_reserved - Get the number of globally reserved irqs
+ * @m:		Pointer to the matrix to query
+ */
+unsigned int irq_matrix_reserved(struct irq_matrix *m)
+{
+	return m->global_reserved;
+}
+
+/**
+ * irq_matrix_allocated - Get the number of allocated irqs on the local cpu
+ * @m:		Pointer to the matrix to search
+ *
+ * This returns number of allocated irqs
+ */
+unsigned int irq_matrix_allocated(struct irq_matrix *m)
+{
+	struct cpumap *cm = this_cpu_ptr(m->maps);
+
+	return cm->allocated;
+}
+
+#ifdef CONFIG_GENERIC_IRQ_DEBUGFS
+/**
+ * irq_matrix_debug_show - Show detailed allocation information
+ * @sf:		Pointer to the seq_file to print to
+ * @m:		Pointer to the matrix allocator
+ * @ind:	Indentation for the print format
+ *
+ * Note, this is a lockless snapshot.
+ */
+void irq_matrix_debug_show(struct seq_file *sf, struct irq_matrix *m, int ind)
+{
+	unsigned int nsys = bitmap_weight(m->system_map, m->matrix_bits);
+	int cpu;
+
+	seq_printf(sf, "Online bitmaps:   %6u\n", m->online_maps);
+	seq_printf(sf, "Global available: %6u\n", m->global_available);
+	seq_printf(sf, "Global reserved:  %6u\n", m->global_reserved);
+	seq_printf(sf, "Total allocated:  %6u\n", m->total_allocated);
+	seq_printf(sf, "System: %u: %*pbl\n", nsys, m->matrix_bits,
+		   m->system_map);
+	seq_printf(sf, "%*s| CPU | avl | man | act | vectors\n", ind, " ");
+	cpus_read_lock();
+	for_each_online_cpu(cpu) {
+		struct cpumap *cm = per_cpu_ptr(m->maps, cpu);
+
+		seq_printf(sf, "%*s %4d  %4u  %4u  %4u  %*pbl\n", ind, " ",
+			   cpu, cm->available, cm->managed, cm->allocated,
+			   m->matrix_bits, cm->alloc_map);
+	}
+	cpus_read_unlock();
+}
+#endif

kernel/irq/msi.c

@@ -16,6 +16,8 @@
 #include <linux/msi.h>
 #include <linux/slab.h>
 
+#include "internals.h"
+
 /**
  * alloc_msi_entry - Allocate an initialize msi_entry
  * @dev:	Pointer to the device for which this is allocated
@@ -100,13 +102,14 @@ int msi_domain_set_affinity(struct irq_data *irq_data,
 	return ret;
 }
 
-static void msi_domain_activate(struct irq_domain *domain,
-				struct irq_data *irq_data)
+static int msi_domain_activate(struct irq_domain *domain,
+			       struct irq_data *irq_data, bool early)
 {
 	struct msi_msg msg;
 
 	BUG_ON(irq_chip_compose_msi_msg(irq_data, &msg));
 	irq_chip_write_msi_msg(irq_data, &msg);
+	return 0;
 }
 
 static void msi_domain_deactivate(struct irq_domain *domain,
@@ -373,8 +376,10 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
 			return ret;
 		}
 
-		for (i = 0; i < desc->nvec_used; i++)
+		for (i = 0; i < desc->nvec_used; i++) {
 			irq_set_msi_desc_off(virq, i, desc);
+			irq_debugfs_copy_devname(virq + i, dev);
+		}
 	}
 
 	if (ops->msi_finish)
@@ -396,11 +401,28 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
 			struct irq_data *irq_data;
 
 			irq_data = irq_domain_get_irq_data(domain, desc->irq);
-			irq_domain_activate_irq(irq_data);
+			ret = irq_domain_activate_irq(irq_data, true);
+			if (ret)
+				goto cleanup;
+			if (info->flags & MSI_FLAG_MUST_REACTIVATE)
+				irqd_clr_activated(irq_data);
 		}
 	}
-
 	return 0;
+
+cleanup:
+	for_each_msi_entry(desc, dev) {
+		struct irq_data *irqd;
+
+		if (desc->irq == virq)
+			break;
+
+		irqd = irq_domain_get_irq_data(domain, desc->irq);
+		if (irqd_is_activated(irqd))
+			irq_domain_deactivate_irq(irqd);
+	}
+	msi_domain_free_irqs(domain, dev);
+	return ret;
 }
 
 /**

kernel/irq/proc.c

@@ -155,8 +155,9 @@ static ssize_t write_irq_affinity(int type, struct file *file,
 		 */
 		err = irq_select_affinity_usr(irq) ? -EINVAL : count;
 	} else {
-		irq_set_affinity(irq, new_value);
-		err = count;
+		err = irq_set_affinity(irq, new_value);
+		if (!err)
+			err = count;
 	}
 
 free_cpumask:

kernel/irq_work.c

@@ -131,9 +131,9 @@ bool irq_work_needs_cpu(void)
 
 static void irq_work_run_list(struct llist_head *list)
 {
-	unsigned long flags;
-	struct irq_work *work;
+	struct irq_work *work, *tmp;
 	struct llist_node *llnode;
+	unsigned long flags;
 
 	BUG_ON(!irqs_disabled());
 
@@ -141,11 +141,7 @@ static void irq_work_run_list(struct llist_head *list)
 		return;
 
 	llnode = llist_del_all(list);
-	while (llnode != NULL) {
-		work = llist_entry(llnode, struct irq_work, llnode);
-
-		llnode = llist_next(llnode);
-
+	llist_for_each_entry_safe(work, tmp, llnode, llnode) {
 		/*
 		 * Clear the PENDING bit, after this point the @work
 		 * can be re-used.