Update Linux to v5.10.109

Sourced from [1]

[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz

Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index 97f9c00..dc062e8 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -148,7 +148,7 @@
 config DW_APB_ICTL
 	bool
 	select GENERIC_IRQ_CHIP
-	select IRQ_DOMAIN
+	select IRQ_DOMAIN_HIERARCHY
 
 config FARADAY_FTINTC010
 	bool
@@ -180,7 +180,6 @@
 	select GENERIC_IRQ_CHIP
 	select GENERIC_IRQ_IPI if SYS_SUPPORTS_MULTITHREADING
 	select IRQ_DOMAIN
-	select IRQ_DOMAIN_HIERARCHY if GENERIC_IRQ_IPI
 	select GENERIC_IRQ_EFFECTIVE_AFF_MASK
 
 config CLPS711X_IRQCHIP
@@ -232,12 +231,12 @@
 	  interrupt pins, as found on SH/R-Mobile and R-Car Gen1 SoCs.
 
 config RENESAS_IRQC
-	bool "Renesas R-Mobile APE6 and R-Car IRQC support" if COMPILE_TEST
+	bool "Renesas R-Mobile APE6, R-Car Gen{2,3} and RZ/G{1,2} IRQC support" if COMPILE_TEST
 	select GENERIC_IRQ_CHIP
 	select IRQ_DOMAIN
 	help
 	  Enable support for the Renesas Interrupt Controller for external
-	  devices, as found on R-Mobile APE6, R-Car Gen2, and R-Car Gen3 SoCs.
+	  devices, as found on R-Mobile APE6, R-Car Gen{2,3} and RZ/G{1,2} SoCs.
 
 config RENESAS_RZA1_IRQC
 	bool "Renesas RZ/A1 IRQC support" if COMPILE_TEST
@@ -246,6 +245,14 @@
 	  Enable support for the Renesas RZ/A1 Interrupt Controller, to use up
 	  to 8 external interrupts with configurable sense select.
 
+config SL28CPLD_INTC
+	bool "Kontron sl28cpld IRQ controller"
+	depends on MFD_SL28CPLD=y || COMPILE_TEST
+	select REGMAP_IRQ
+	help
+	  Interrupt controller driver for the board management controller
+	  found on the Kontron sl28 CPLD.
+
 config ST_IRQCHIP
 	bool
 	select REGMAP
@@ -307,7 +314,6 @@
 config MIPS_GIC
 	bool
 	select GENERIC_IRQ_IPI
-	select IRQ_DOMAIN_HIERARCHY
 	select MIPS_CM
 
 config INGENIC_IRQ
@@ -370,6 +376,10 @@
 config MVEBU_SEI
         bool
 
+config LS_EXTIRQ
+	def_bool y if SOC_LS1021A || ARCH_LAYERSCAPE
+	select MFD_SYSCON
+
 config LS_SCFG_MSI
 	def_bool y if SOC_LS1021A || ARCH_LAYERSCAPE
 	depends on PCI && PCI_MSI
@@ -415,6 +425,7 @@
 config GOLDFISH_PIC
        bool "Goldfish programmable interrupt controller"
        depends on MIPS && (GOLDFISH || COMPILE_TEST)
+       select GENERIC_IRQ_CHIP
        select IRQ_DOMAIN
        help
          Say yes here to enable Goldfish interrupt controller driver used
@@ -434,7 +445,7 @@
 	help
 	  Say yes here to enable C-SKY SMP interrupt controller driver used
 	  for C-SKY SMP system.
-	  In fact it's not mmio map in hw and it use ld/st to visit the
+	  In fact it's not mmio map in hardware and it uses ld/st to visit the
 	  controller's register inside CPU.
 
 config CSKY_APB_INTC
@@ -442,7 +453,7 @@
 	depends on CSKY
 	help
 	  Say yes here to enable C-SKY APB interrupt controller driver used
-	  by C-SKY single core SOC system. It use mmio map apb-bus to visit
+	  by C-SKY single core SOC system. It uses mmio map apb-bus to visit
 	  the controller's register.
 
 config IMX_IRQSTEER
@@ -453,6 +464,13 @@
 	help
 	  Support for the i.MX IRQSTEER interrupt multiplexer/remapper.
 
+config IMX_INTMUX
+	bool "i.MX INTMUX support" if COMPILE_TEST
+	default y if ARCH_MXC
+	select IRQ_DOMAIN
+	help
+	  Support for the i.MX INTMUX interrupt multiplexer.
+
 config LS1X_IRQ
 	bool "Loongson-1 Interrupt Controller"
 	depends on MACH_LOONGSON32
@@ -483,9 +501,33 @@
 	  If you wish to use interrupt aggregator irq resources managed by the
 	  TI System Controller, say Y here. Otherwise, say N.
 
+config TI_PRUSS_INTC
+	tristate "TI PRU-ICSS Interrupt Controller"
+	depends on ARCH_DAVINCI || SOC_AM33XX || SOC_AM43XX || SOC_DRA7XX || ARCH_KEYSTONE || ARCH_K3
+	select IRQ_DOMAIN
+	help
+	  This enables support for the PRU-ICSS Local Interrupt Controller
+	  present within a PRU-ICSS subsystem present on various TI SoCs.
+	  The PRUSS INTC enables various interrupts to be routed to multiple
+	  different processors within the SoC.
+
+config RISCV_INTC
+	bool "RISC-V Local Interrupt Controller"
+	depends on RISCV
+	default y
+	help
+	   This enables support for the per-HART local interrupt controller
+	   found in standard RISC-V systems.  The per-HART local interrupt
+	   controller handles timer interrupts, software interrupts, and
+	   hardware interrupts. Without a per-HART local interrupt controller,
+	   a RISC-V system will be unable to handle any interrupts.
+
+	   If you don't know what to do here, say Y.
+
 config SIFIVE_PLIC
 	bool "SiFive Platform-Level Interrupt Controller"
 	depends on RISCV
+	select IRQ_DOMAIN_HIERARCHY
 	help
 	   This enables support for the PLIC chip found in SiFive (and
 	   potentially other) RISC-V systems.  The PLIC controls devices
@@ -495,4 +537,65 @@
 
 	   If you don't know what to do here, say Y.
 
+config EXYNOS_IRQ_COMBINER
+	bool "Samsung Exynos IRQ combiner support" if COMPILE_TEST
+	depends on (ARCH_EXYNOS && ARM) || COMPILE_TEST
+	help
+	  Say yes here to add support for the IRQ combiner devices embedded
+	  in Samsung Exynos chips.
+
+config LOONGSON_LIOINTC
+	bool "Loongson Local I/O Interrupt Controller"
+	depends on MACH_LOONGSON64
+	default y
+	select IRQ_DOMAIN
+	select GENERIC_IRQ_CHIP
+	help
+	  Support for the Loongson Local I/O Interrupt Controller.
+
+config LOONGSON_HTPIC
+	bool "Loongson3 HyperTransport PIC Controller"
+	depends on MACH_LOONGSON64
+	default y
+	select IRQ_DOMAIN
+	select GENERIC_IRQ_CHIP
+	help
+	  Support for the Loongson-3 HyperTransport PIC Controller.
+
+config LOONGSON_HTVEC
+	bool "Loongson3 HyperTransport Interrupt Vector Controller"
+	depends on MACH_LOONGSON64
+	default MACH_LOONGSON64
+	select IRQ_DOMAIN_HIERARCHY
+	help
+	  Support for the Loongson3 HyperTransport Interrupt Vector Controller.
+
+config LOONGSON_PCH_PIC
+	bool "Loongson PCH PIC Controller"
+	depends on MACH_LOONGSON64 || COMPILE_TEST
+	default MACH_LOONGSON64
+	select IRQ_DOMAIN_HIERARCHY
+	select IRQ_FASTEOI_HIERARCHY_HANDLERS
+	help
+	  Support for the Loongson PCH PIC Controller.
+
+config LOONGSON_PCH_MSI
+	bool "Loongson PCH MSI Controller"
+	depends on MACH_LOONGSON64 || COMPILE_TEST
+	depends on PCI
+	default MACH_LOONGSON64
+	select IRQ_DOMAIN_HIERARCHY
+	select PCI_MSI
+	help
+	  Support for the Loongson PCH MSI Controller.
+
+config MST_IRQ
+	bool "MStar Interrupt Controller"
+	depends on ARCH_MEDIATEK || ARCH_MSTARV7 || COMPILE_TEST
+	default ARCH_MEDIATEK
+	select IRQ_DOMAIN
+	select IRQ_DOMAIN_HIERARCHY
+	help
+	  Support MStar Interrupt Controller.
+
 endmenu
diff --git a/drivers/irqchip/Makefile b/drivers/irqchip/Makefile
index cc7c439..94c2885 100644
--- a/drivers/irqchip/Makefile
+++ b/drivers/irqchip/Makefile
@@ -7,16 +7,16 @@
 obj-$(CONFIG_ATH79)			+= irq-ath79-misc.o
 obj-$(CONFIG_ARCH_BCM2835)		+= irq-bcm2835.o
 obj-$(CONFIG_ARCH_BCM2835)		+= irq-bcm2836.o
+obj-$(CONFIG_ARCH_ACTIONS)		+= irq-owl-sirq.o
 obj-$(CONFIG_DAVINCI_AINTC)		+= irq-davinci-aintc.o
 obj-$(CONFIG_DAVINCI_CP_INTC)		+= irq-davinci-cp-intc.o
-obj-$(CONFIG_ARCH_EXYNOS)		+= exynos-combiner.o
+obj-$(CONFIG_EXYNOS_IRQ_COMBINER)	+= exynos-combiner.o
 obj-$(CONFIG_FARADAY_FTINTC010)		+= irq-ftintc010.o
 obj-$(CONFIG_ARCH_HIP04)		+= irq-hip04.o
 obj-$(CONFIG_ARCH_LPC32XX)		+= irq-lpc32xx.o
 obj-$(CONFIG_ARCH_MMP)			+= irq-mmp.o
 obj-$(CONFIG_IRQ_MXS)			+= irq-mxs.o
 obj-$(CONFIG_ARCH_TEGRA)		+= irq-tegra.o
-obj-$(CONFIG_ARCH_S3C24XX)		+= irq-s3c24xx.o
 obj-$(CONFIG_DW_APB_ICTL)		+= irq-dw-apb-ictl.o
 obj-$(CONFIG_CLPS711X_IRQCHIP)		+= irq-clps711x.o
 obj-$(CONFIG_OMPIC)			+= irq-ompic.o
@@ -84,9 +84,10 @@
 obj-$(CONFIG_MVEBU_ODMI)		+= irq-mvebu-odmi.o
 obj-$(CONFIG_MVEBU_PIC)			+= irq-mvebu-pic.o
 obj-$(CONFIG_MVEBU_SEI)			+= irq-mvebu-sei.o
+obj-$(CONFIG_LS_EXTIRQ)			+= irq-ls-extirq.o
 obj-$(CONFIG_LS_SCFG_MSI)		+= irq-ls-scfg-msi.o
 obj-$(CONFIG_EZNPS_GIC)			+= irq-eznps.o
-obj-$(CONFIG_ARCH_ASPEED)		+= irq-aspeed-vic.o irq-aspeed-i2c-ic.o
+obj-$(CONFIG_ARCH_ASPEED)		+= irq-aspeed-vic.o irq-aspeed-i2c-ic.o irq-aspeed-scu-ic.o
 obj-$(CONFIG_STM32_EXTI) 		+= irq-stm32-exti.o
 obj-$(CONFIG_QCOM_IRQ_COMBINER)		+= qcom-irq-combiner.o
 obj-$(CONFIG_IRQ_UNIPHIER_AIDET)	+= irq-uniphier-aidet.o
@@ -97,9 +98,19 @@
 obj-$(CONFIG_QCOM_PDC)			+= qcom-pdc.o
 obj-$(CONFIG_CSKY_MPINTC)		+= irq-csky-mpintc.o
 obj-$(CONFIG_CSKY_APB_INTC)		+= irq-csky-apb-intc.o
+obj-$(CONFIG_RISCV_INTC)		+= irq-riscv-intc.o
 obj-$(CONFIG_SIFIVE_PLIC)		+= irq-sifive-plic.o
 obj-$(CONFIG_IMX_IRQSTEER)		+= irq-imx-irqsteer.o
+obj-$(CONFIG_IMX_INTMUX)		+= irq-imx-intmux.o
 obj-$(CONFIG_MADERA_IRQ)		+= irq-madera.o
 obj-$(CONFIG_LS1X_IRQ)			+= irq-ls1x.o
 obj-$(CONFIG_TI_SCI_INTR_IRQCHIP)	+= irq-ti-sci-intr.o
 obj-$(CONFIG_TI_SCI_INTA_IRQCHIP)	+= irq-ti-sci-inta.o
+obj-$(CONFIG_TI_PRUSS_INTC)		+= irq-pruss-intc.o
+obj-$(CONFIG_LOONGSON_LIOINTC)		+= irq-loongson-liointc.o
+obj-$(CONFIG_LOONGSON_HTPIC)		+= irq-loongson-htpic.o
+obj-$(CONFIG_LOONGSON_HTVEC)		+= irq-loongson-htvec.o
+obj-$(CONFIG_LOONGSON_PCH_PIC)		+= irq-loongson-pch-pic.o
+obj-$(CONFIG_LOONGSON_PCH_MSI)		+= irq-loongson-pch-msi.o
+obj-$(CONFIG_MST_IRQ)			+= irq-mst-intc.o
+obj-$(CONFIG_SL28CPLD_INTC)		+= irq-sl28cpld.o
diff --git a/drivers/irqchip/irq-armada-370-xp.c b/drivers/irqchip/irq-armada-370-xp.c
index c9bdc52..84f2741 100644
--- a/drivers/irqchip/irq-armada-370-xp.c
+++ b/drivers/irqchip/irq-armada-370-xp.c
@@ -232,17 +232,13 @@
 	int hwirq, i;
 
 	mutex_lock(&msi_used_lock);
-
-	hwirq = bitmap_find_next_zero_area(msi_used, PCI_MSI_DOORBELL_NR,
-					   0, nr_irqs, 0);
-	if (hwirq >= PCI_MSI_DOORBELL_NR) {
-		mutex_unlock(&msi_used_lock);
-		return -ENOSPC;
-	}
-
-	bitmap_set(msi_used, hwirq, nr_irqs);
+	hwirq = bitmap_find_free_region(msi_used, PCI_MSI_DOORBELL_NR,
+					order_base_2(nr_irqs));
 	mutex_unlock(&msi_used_lock);
 
+	if (hwirq < 0)
+		return -ENOSPC;
+
 	for (i = 0; i < nr_irqs; i++) {
 		irq_domain_set_info(domain, virq + i, hwirq + i,
 				    &armada_370_xp_msi_bottom_irq_chip,
@@ -250,7 +246,7 @@
 				    NULL, NULL);
 	}
 
-	return hwirq;
+	return 0;
 }
 
 static void armada_370_xp_msi_free(struct irq_domain *domain,
@@ -259,7 +255,7 @@
 	struct irq_data *d = irq_domain_get_irq_data(domain, virq);
 
 	mutex_lock(&msi_used_lock);
-	bitmap_clear(msi_used, d->hwirq, nr_irqs);
+	bitmap_release_region(msi_used, d->hwirq, order_base_2(nr_irqs));
 	mutex_unlock(&msi_used_lock);
 }
 
@@ -310,7 +306,134 @@
 }
 #endif
 
+static void armada_xp_mpic_perf_init(void)
+{
+	unsigned long cpuid = cpu_logical_map(smp_processor_id());
+
+	/* Enable Performance Counter Overflow interrupts */
+	writel(ARMADA_370_XP_INT_CAUSE_PERF(cpuid),
+	       per_cpu_int_base + ARMADA_370_XP_INT_FABRIC_MASK_OFFS);
+}
+
 #ifdef CONFIG_SMP
+static struct irq_domain *ipi_domain;
+
+static void armada_370_xp_ipi_mask(struct irq_data *d)
+{
+	u32 reg;
+	reg = readl(per_cpu_int_base + ARMADA_370_XP_IN_DRBEL_MSK_OFFS);
+	reg &= ~BIT(d->hwirq);
+	writel(reg, per_cpu_int_base + ARMADA_370_XP_IN_DRBEL_MSK_OFFS);
+}
+
+static void armada_370_xp_ipi_unmask(struct irq_data *d)
+{
+	u32 reg;
+	reg = readl(per_cpu_int_base + ARMADA_370_XP_IN_DRBEL_MSK_OFFS);
+	reg |= BIT(d->hwirq);
+	writel(reg, per_cpu_int_base + ARMADA_370_XP_IN_DRBEL_MSK_OFFS);
+}
+
+static void armada_370_xp_ipi_send_mask(struct irq_data *d,
+					const struct cpumask *mask)
+{
+	unsigned long map = 0;
+	int cpu;
+
+	/* Convert our logical CPU mask into a physical one. */
+	for_each_cpu(cpu, mask)
+		map |= 1 << cpu_logical_map(cpu);
+
+	/*
+	 * Ensure that stores to Normal memory are visible to the
+	 * other CPUs before issuing the IPI.
+	 */
+	dsb();
+
+	/* submit softirq */
+	writel((map << 8) | d->hwirq, main_int_base +
+		ARMADA_370_XP_SW_TRIG_INT_OFFS);
+}
+
+static void armada_370_xp_ipi_eoi(struct irq_data *d)
+{
+	writel(~BIT(d->hwirq), per_cpu_int_base + ARMADA_370_XP_IN_DRBEL_CAUSE_OFFS);
+}
+
+static struct irq_chip ipi_irqchip = {
+	.name		= "IPI",
+	.irq_mask	= armada_370_xp_ipi_mask,
+	.irq_unmask	= armada_370_xp_ipi_unmask,
+	.irq_eoi	= armada_370_xp_ipi_eoi,
+	.ipi_send_mask	= armada_370_xp_ipi_send_mask,
+};
+
+static int armada_370_xp_ipi_alloc(struct irq_domain *d,
+					 unsigned int virq,
+					 unsigned int nr_irqs, void *args)
+{
+	int i;
+
+	for (i = 0; i < nr_irqs; i++) {
+		irq_set_percpu_devid(virq + i);
+		irq_domain_set_info(d, virq + i, i, &ipi_irqchip,
+				    d->host_data,
+				    handle_percpu_devid_fasteoi_ipi,
+				    NULL, NULL);
+	}
+
+	return 0;
+}
+
+static void armada_370_xp_ipi_free(struct irq_domain *d,
+					 unsigned int virq,
+					 unsigned int nr_irqs)
+{
+	/* Not freeing IPIs */
+}
+
+static const struct irq_domain_ops ipi_domain_ops = {
+	.alloc	= armada_370_xp_ipi_alloc,
+	.free	= armada_370_xp_ipi_free,
+};
+
+static void ipi_resume(void)
+{
+	int i;
+
+	for (i = 0; i < IPI_DOORBELL_END; i++) {
+		int irq;
+
+		irq = irq_find_mapping(ipi_domain, i);
+		if (irq <= 0)
+			continue;
+		if (irq_percpu_is_enabled(irq)) {
+			struct irq_data *d;
+			d = irq_domain_get_irq_data(ipi_domain, irq);
+			armada_370_xp_ipi_unmask(d);
+		}
+	}
+}
+
+static __init void armada_xp_ipi_init(struct device_node *node)
+{
+	int base_ipi;
+
+	ipi_domain = irq_domain_create_linear(of_node_to_fwnode(node),
+					      IPI_DOORBELL_END,
+					      &ipi_domain_ops, NULL);
+	if (WARN_ON(!ipi_domain))
+		return;
+
+	irq_domain_update_bus_token(ipi_domain, DOMAIN_BUS_IPI);
+	base_ipi = __irq_domain_alloc_irqs(ipi_domain, -1, IPI_DOORBELL_END,
+					   NUMA_NO_NODE, NULL, false, NULL);
+	if (WARN_ON(!base_ipi))
+		return;
+
+	set_smp_ipi_range(base_ipi, IPI_DOORBELL_END);
+}
+
 static DEFINE_RAW_SPINLOCK(irq_controller_lock);
 
 static int armada_xp_set_affinity(struct irq_data *d,
@@ -334,6 +457,70 @@
 
 	return IRQ_SET_MASK_OK;
 }
+
+static void armada_xp_mpic_smp_cpu_init(void)
+{
+	u32 control;
+	int nr_irqs, i;
+
+	control = readl(main_int_base + ARMADA_370_XP_INT_CONTROL);
+	nr_irqs = (control >> 2) & 0x3ff;
+
+	for (i = 0; i < nr_irqs; i++)
+		writel(i, per_cpu_int_base + ARMADA_370_XP_INT_SET_MASK_OFFS);
+
+	/* Disable all IPIs */
+	writel(0, per_cpu_int_base + ARMADA_370_XP_IN_DRBEL_MSK_OFFS);
+
+	/* Clear pending IPIs */
+	writel(0, per_cpu_int_base + ARMADA_370_XP_IN_DRBEL_CAUSE_OFFS);
+
+	/* Unmask IPI interrupt */
+	writel(0, per_cpu_int_base + ARMADA_370_XP_INT_CLEAR_MASK_OFFS);
+}
+
+static void armada_xp_mpic_reenable_percpu(void)
+{
+	unsigned int irq;
+
+	/* Re-enable per-CPU interrupts that were enabled before suspend */
+	for (irq = 0; irq < ARMADA_370_XP_MAX_PER_CPU_IRQS; irq++) {
+		struct irq_data *data;
+		int virq;
+
+		virq = irq_linear_revmap(armada_370_xp_mpic_domain, irq);
+		if (virq == 0)
+			continue;
+
+		data = irq_get_irq_data(virq);
+
+		if (!irq_percpu_is_enabled(virq))
+			continue;
+
+		armada_370_xp_irq_unmask(data);
+	}
+
+	ipi_resume();
+}
+
+static int armada_xp_mpic_starting_cpu(unsigned int cpu)
+{
+	armada_xp_mpic_perf_init();
+	armada_xp_mpic_smp_cpu_init();
+	armada_xp_mpic_reenable_percpu();
+	return 0;
+}
+
+static int mpic_cascaded_starting_cpu(unsigned int cpu)
+{
+	armada_xp_mpic_perf_init();
+	armada_xp_mpic_reenable_percpu();
+	enable_percpu_irq(parent_irq, IRQ_TYPE_NONE);
+	return 0;
+}
+#else
+static void armada_xp_mpic_smp_cpu_init(void) {}
+static void ipi_resume(void) {}
 #endif
 
 static struct irq_chip armada_370_xp_irq_chip = {
@@ -372,98 +559,6 @@
 	return 0;
 }
 
-static void armada_xp_mpic_smp_cpu_init(void)
-{
-	u32 control;
-	int nr_irqs, i;
-
-	control = readl(main_int_base + ARMADA_370_XP_INT_CONTROL);
-	nr_irqs = (control >> 2) & 0x3ff;
-
-	for (i = 0; i < nr_irqs; i++)
-		writel(i, per_cpu_int_base + ARMADA_370_XP_INT_SET_MASK_OFFS);
-
-	/* Clear pending IPIs */
-	writel(0, per_cpu_int_base + ARMADA_370_XP_IN_DRBEL_CAUSE_OFFS);
-
-	/* Enable first 8 IPIs */
-	writel(IPI_DOORBELL_MASK, per_cpu_int_base +
-		ARMADA_370_XP_IN_DRBEL_MSK_OFFS);
-
-	/* Unmask IPI interrupt */
-	writel(0, per_cpu_int_base + ARMADA_370_XP_INT_CLEAR_MASK_OFFS);
-}
-
-static void armada_xp_mpic_perf_init(void)
-{
-	unsigned long cpuid = cpu_logical_map(smp_processor_id());
-
-	/* Enable Performance Counter Overflow interrupts */
-	writel(ARMADA_370_XP_INT_CAUSE_PERF(cpuid),
-	       per_cpu_int_base + ARMADA_370_XP_INT_FABRIC_MASK_OFFS);
-}
-
-#ifdef CONFIG_SMP
-static void armada_mpic_send_doorbell(const struct cpumask *mask,
-				      unsigned int irq)
-{
-	int cpu;
-	unsigned long map = 0;
-
-	/* Convert our logical CPU mask into a physical one. */
-	for_each_cpu(cpu, mask)
-		map |= 1 << cpu_logical_map(cpu);
-
-	/*
-	 * Ensure that stores to Normal memory are visible to the
-	 * other CPUs before issuing the IPI.
-	 */
-	dsb();
-
-	/* submit softirq */
-	writel((map << 8) | irq, main_int_base +
-		ARMADA_370_XP_SW_TRIG_INT_OFFS);
-}
-
-static void armada_xp_mpic_reenable_percpu(void)
-{
-	unsigned int irq;
-
-	/* Re-enable per-CPU interrupts that were enabled before suspend */
-	for (irq = 0; irq < ARMADA_370_XP_MAX_PER_CPU_IRQS; irq++) {
-		struct irq_data *data;
-		int virq;
-
-		virq = irq_linear_revmap(armada_370_xp_mpic_domain, irq);
-		if (virq == 0)
-			continue;
-
-		data = irq_get_irq_data(virq);
-
-		if (!irq_percpu_is_enabled(virq))
-			continue;
-
-		armada_370_xp_irq_unmask(data);
-	}
-}
-
-static int armada_xp_mpic_starting_cpu(unsigned int cpu)
-{
-	armada_xp_mpic_perf_init();
-	armada_xp_mpic_smp_cpu_init();
-	armada_xp_mpic_reenable_percpu();
-	return 0;
-}
-
-static int mpic_cascaded_starting_cpu(unsigned int cpu)
-{
-	armada_xp_mpic_perf_init();
-	armada_xp_mpic_reenable_percpu();
-	enable_percpu_irq(parent_irq, IRQ_TYPE_NONE);
-	return 0;
-}
-#endif
-
 static const struct irq_domain_ops armada_370_xp_mpic_irq_ops = {
 	.map = armada_370_xp_mpic_irq_map,
 	.xlate = irq_domain_xlate_onecell,
@@ -562,22 +657,15 @@
 #ifdef CONFIG_SMP
 		/* IPI Handling */
 		if (irqnr == 0) {
-			u32 ipimask, ipinr;
+			unsigned long ipimask;
+			int ipi;
 
 			ipimask = readl_relaxed(per_cpu_int_base +
 						ARMADA_370_XP_IN_DRBEL_CAUSE_OFFS)
 				& IPI_DOORBELL_MASK;
 
-			writel(~ipimask, per_cpu_int_base +
-				ARMADA_370_XP_IN_DRBEL_CAUSE_OFFS);
-
-			/* Handle all pending doorbells */
-			for (ipinr = IPI_DOORBELL_START;
-			     ipinr < IPI_DOORBELL_END; ipinr++) {
-				if (ipimask & (0x1 << ipinr))
-					handle_IPI(ipinr, regs);
-			}
-			continue;
+			for_each_set_bit(ipi, &ipimask, IPI_DOORBELL_END)
+				handle_domain_irq(ipi_domain, ipi, regs);
 		}
 #endif
 
@@ -636,6 +724,8 @@
 		writel(0, per_cpu_int_base + ARMADA_370_XP_INT_CLEAR_MASK_OFFS);
 	if (doorbell_mask_reg & PCI_MSI_DOORBELL_MASK)
 		writel(1, per_cpu_int_base + ARMADA_370_XP_INT_CLEAR_MASK_OFFS);
+
+	ipi_resume();
 }
 
 static struct syscore_ops armada_370_xp_mpic_syscore_ops = {
@@ -691,7 +781,7 @@
 		irq_set_default_host(armada_370_xp_mpic_domain);
 		set_handle_irq(armada_370_xp_handle_irq);
 #ifdef CONFIG_SMP
-		set_smp_cross_call(armada_mpic_send_doorbell);
+		armada_xp_ipi_init(node);
 		cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_ARMADA_XP_STARTING,
 					  "irqchip/armada/ipi:starting",
 					  armada_xp_mpic_starting_cpu, NULL);
diff --git a/drivers/irqchip/irq-aspeed-scu-ic.c b/drivers/irqchip/irq-aspeed-scu-ic.c
new file mode 100644
index 0000000..0f0aac7
--- /dev/null
+++ b/drivers/irqchip/irq-aspeed-scu-ic.c
@@ -0,0 +1,239 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Aspeed AST24XX, AST25XX, and AST26XX SCU Interrupt Controller
+ * Copyright 2019 IBM Corporation
+ *
+ * Eddie James <eajames@linux.ibm.com>
+ */
+
+#include <linux/bitops.h>
+#include <linux/irq.h>
+#include <linux/irqchip.h>
+#include <linux/irqchip/chained_irq.h>
+#include <linux/irqdomain.h>
+#include <linux/mfd/syscon.h>
+#include <linux/of_irq.h>
+#include <linux/regmap.h>
+
+#define ASPEED_SCU_IC_REG		0x018
+#define ASPEED_SCU_IC_SHIFT		0
+#define ASPEED_SCU_IC_ENABLE		GENMASK(6, ASPEED_SCU_IC_SHIFT)
+#define ASPEED_SCU_IC_NUM_IRQS		7
+#define ASPEED_SCU_IC_STATUS_SHIFT	16
+
+#define ASPEED_AST2600_SCU_IC0_REG	0x560
+#define ASPEED_AST2600_SCU_IC0_SHIFT	0
+#define ASPEED_AST2600_SCU_IC0_ENABLE	\
+	GENMASK(5, ASPEED_AST2600_SCU_IC0_SHIFT)
+#define ASPEED_AST2600_SCU_IC0_NUM_IRQS	6
+
+#define ASPEED_AST2600_SCU_IC1_REG	0x570
+#define ASPEED_AST2600_SCU_IC1_SHIFT	4
+#define ASPEED_AST2600_SCU_IC1_ENABLE	\
+	GENMASK(5, ASPEED_AST2600_SCU_IC1_SHIFT)
+#define ASPEED_AST2600_SCU_IC1_NUM_IRQS	2
+
+struct aspeed_scu_ic {
+	unsigned long irq_enable;
+	unsigned long irq_shift;
+	unsigned int num_irqs;
+	unsigned int reg;
+	struct regmap *scu;
+	struct irq_domain *irq_domain;
+};
+
+static void aspeed_scu_ic_irq_handler(struct irq_desc *desc)
+{
+	unsigned int irq;
+	unsigned int sts;
+	unsigned long bit;
+	unsigned long enabled;
+	unsigned long max;
+	unsigned long status;
+	struct aspeed_scu_ic *scu_ic = irq_desc_get_handler_data(desc);
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	unsigned int mask = scu_ic->irq_enable << ASPEED_SCU_IC_STATUS_SHIFT;
+
+	chained_irq_enter(chip, desc);
+
+	/*
+	 * The SCU IC has just one register to control its operation and read
+	 * status. The interrupt enable bits occupy the lower 16 bits of the
+	 * register, while the interrupt status bits occupy the upper 16 bits.
+	 * The status bit for a given interrupt is always 16 bits shifted from
+	 * the enable bit for the same interrupt.
+	 * Therefore, perform the IRQ operations in the enable bit space by
+	 * shifting the status down to get the mapping and then back up to
+	 * clear the bit.
+	 */
+	regmap_read(scu_ic->scu, scu_ic->reg, &sts);
+	enabled = sts & scu_ic->irq_enable;
+	status = (sts >> ASPEED_SCU_IC_STATUS_SHIFT) & enabled;
+
+	bit = scu_ic->irq_shift;
+	max = scu_ic->num_irqs + bit;
+
+	for_each_set_bit_from(bit, &status, max) {
+		irq = irq_find_mapping(scu_ic->irq_domain,
+				       bit - scu_ic->irq_shift);
+		generic_handle_irq(irq);
+
+		regmap_write_bits(scu_ic->scu, scu_ic->reg, mask,
+				  BIT(bit + ASPEED_SCU_IC_STATUS_SHIFT));
+	}
+
+	chained_irq_exit(chip, desc);
+}
+
+static void aspeed_scu_ic_irq_mask(struct irq_data *data)
+{
+	struct aspeed_scu_ic *scu_ic = irq_data_get_irq_chip_data(data);
+	unsigned int mask = BIT(data->hwirq + scu_ic->irq_shift) |
+		(scu_ic->irq_enable << ASPEED_SCU_IC_STATUS_SHIFT);
+
+	/*
+	 * Status bits are cleared by writing 1. In order to prevent the mask
+	 * operation from clearing the status bits, they should be under the
+	 * mask and written with 0.
+	 */
+	regmap_update_bits(scu_ic->scu, scu_ic->reg, mask, 0);
+}
+
+static void aspeed_scu_ic_irq_unmask(struct irq_data *data)
+{
+	struct aspeed_scu_ic *scu_ic = irq_data_get_irq_chip_data(data);
+	unsigned int bit = BIT(data->hwirq + scu_ic->irq_shift);
+	unsigned int mask = bit |
+		(scu_ic->irq_enable << ASPEED_SCU_IC_STATUS_SHIFT);
+
+	/*
+	 * Status bits are cleared by writing 1. In order to prevent the unmask
+	 * operation from clearing the status bits, they should be under the
+	 * mask and written with 0.
+	 */
+	regmap_update_bits(scu_ic->scu, scu_ic->reg, mask, bit);
+}
+
+static int aspeed_scu_ic_irq_set_affinity(struct irq_data *data,
+					  const struct cpumask *dest,
+					  bool force)
+{
+	return -EINVAL;
+}
+
+static struct irq_chip aspeed_scu_ic_chip = {
+	.name			= "aspeed-scu-ic",
+	.irq_mask		= aspeed_scu_ic_irq_mask,
+	.irq_unmask		= aspeed_scu_ic_irq_unmask,
+	.irq_set_affinity	= aspeed_scu_ic_irq_set_affinity,
+};
+
+static int aspeed_scu_ic_map(struct irq_domain *domain, unsigned int irq,
+			     irq_hw_number_t hwirq)
+{
+	irq_set_chip_and_handler(irq, &aspeed_scu_ic_chip, handle_level_irq);
+	irq_set_chip_data(irq, domain->host_data);
+
+	return 0;
+}
+
+static const struct irq_domain_ops aspeed_scu_ic_domain_ops = {
+	.map = aspeed_scu_ic_map,
+};
+
+static int aspeed_scu_ic_of_init_common(struct aspeed_scu_ic *scu_ic,
+					struct device_node *node)
+{
+	int irq;
+	int rc = 0;
+
+	if (!node->parent) {
+		rc = -ENODEV;
+		goto err;
+	}
+
+	scu_ic->scu = syscon_node_to_regmap(node->parent);
+	if (IS_ERR(scu_ic->scu)) {
+		rc = PTR_ERR(scu_ic->scu);
+		goto err;
+	}
+
+	irq = irq_of_parse_and_map(node, 0);
+	if (irq < 0) {
+		rc = irq;
+		goto err;
+	}
+
+	scu_ic->irq_domain = irq_domain_add_linear(node, scu_ic->num_irqs,
+						   &aspeed_scu_ic_domain_ops,
+						   scu_ic);
+	if (!scu_ic->irq_domain) {
+		rc = -ENOMEM;
+		goto err;
+	}
+
+	irq_set_chained_handler_and_data(irq, aspeed_scu_ic_irq_handler,
+					 scu_ic);
+
+	return 0;
+
+err:
+	kfree(scu_ic);
+
+	return rc;
+}
+
+static int __init aspeed_scu_ic_of_init(struct device_node *node,
+					struct device_node *parent)
+{
+	struct aspeed_scu_ic *scu_ic = kzalloc(sizeof(*scu_ic), GFP_KERNEL);
+
+	if (!scu_ic)
+		return -ENOMEM;
+
+	scu_ic->irq_enable = ASPEED_SCU_IC_ENABLE;
+	scu_ic->irq_shift = ASPEED_SCU_IC_SHIFT;
+	scu_ic->num_irqs = ASPEED_SCU_IC_NUM_IRQS;
+	scu_ic->reg = ASPEED_SCU_IC_REG;
+
+	return aspeed_scu_ic_of_init_common(scu_ic, node);
+}
+
+static int __init aspeed_ast2600_scu_ic0_of_init(struct device_node *node,
+						 struct device_node *parent)
+{
+	struct aspeed_scu_ic *scu_ic = kzalloc(sizeof(*scu_ic), GFP_KERNEL);
+
+	if (!scu_ic)
+		return -ENOMEM;
+
+	scu_ic->irq_enable = ASPEED_AST2600_SCU_IC0_ENABLE;
+	scu_ic->irq_shift = ASPEED_AST2600_SCU_IC0_SHIFT;
+	scu_ic->num_irqs = ASPEED_AST2600_SCU_IC0_NUM_IRQS;
+	scu_ic->reg = ASPEED_AST2600_SCU_IC0_REG;
+
+	return aspeed_scu_ic_of_init_common(scu_ic, node);
+}
+
+static int __init aspeed_ast2600_scu_ic1_of_init(struct device_node *node,
+						 struct device_node *parent)
+{
+	struct aspeed_scu_ic *scu_ic = kzalloc(sizeof(*scu_ic), GFP_KERNEL);
+
+	if (!scu_ic)
+		return -ENOMEM;
+
+	scu_ic->irq_enable = ASPEED_AST2600_SCU_IC1_ENABLE;
+	scu_ic->irq_shift = ASPEED_AST2600_SCU_IC1_SHIFT;
+	scu_ic->num_irqs = ASPEED_AST2600_SCU_IC1_NUM_IRQS;
+	scu_ic->reg = ASPEED_AST2600_SCU_IC1_REG;
+
+	return aspeed_scu_ic_of_init_common(scu_ic, node);
+}
+
+IRQCHIP_DECLARE(ast2400_scu_ic, "aspeed,ast2400-scu-ic", aspeed_scu_ic_of_init);
+IRQCHIP_DECLARE(ast2500_scu_ic, "aspeed,ast2500-scu-ic", aspeed_scu_ic_of_init);
+IRQCHIP_DECLARE(ast2600_scu_ic0, "aspeed,ast2600-scu-ic0",
+		aspeed_ast2600_scu_ic0_of_init);
+IRQCHIP_DECLARE(ast2600_scu_ic1, "aspeed,ast2600-scu-ic1",
+		aspeed_ast2600_scu_ic1_of_init);
diff --git a/drivers/irqchip/irq-ativic32.c b/drivers/irqchip/irq-ativic32.c
index 85cf6e0..476d602 100644
--- a/drivers/irqchip/irq-ativic32.c
+++ b/drivers/irqchip/irq-ativic32.c
@@ -92,7 +92,7 @@
 	return 0;
 }
 
-static struct irq_domain_ops ativic32_ops = {
+static const struct irq_domain_ops ativic32_ops = {
 	.map = ativic32_irq_domain_map,
 	.xlate = irq_domain_xlate_onecell
 };
diff --git a/drivers/irqchip/irq-atmel-aic.c b/drivers/irqchip/irq-atmel-aic.c
index bb1ad45..2c999dc 100644
--- a/drivers/irqchip/irq-atmel-aic.c
+++ b/drivers/irqchip/irq-atmel-aic.c
@@ -83,7 +83,7 @@
 	irq_reg_writel(gc, d->mask, AT91_AIC_ISCR);
 	irq_gc_unlock(gc);
 
-	return 0;
+	return 1;
 }
 
 static int aic_set_type(struct irq_data *d, unsigned type)
diff --git a/drivers/irqchip/irq-atmel-aic5.c b/drivers/irqchip/irq-atmel-aic5.c
index 2933349..fb4ad2a 100644
--- a/drivers/irqchip/irq-atmel-aic5.c
+++ b/drivers/irqchip/irq-atmel-aic5.c
@@ -128,7 +128,7 @@
 	irq_reg_writel(bgc, 1, AT91_AIC5_ISCR);
 	irq_gc_unlock(bgc);
 
-	return 0;
+	return 1;
 }
 
 static int aic5_set_type(struct irq_data *d, unsigned type)
@@ -310,10 +310,16 @@
 	aic_common_rtc_irq_fixup();
 }
 
+static void __init sam9x60_aic_irq_fixup(void)
+{
+	aic_common_rtc_irq_fixup();
+	aic_common_rtt_irq_fixup();
+}
+
 static const struct of_device_id aic5_irq_fixups[] __initconst = {
 	{ .compatible = "atmel,sama5d3", .data = sama5d3_aic_irq_fixup },
 	{ .compatible = "atmel,sama5d4", .data = sama5d3_aic_irq_fixup },
-	{ .compatible = "microchip,sam9x60", .data = sama5d3_aic_irq_fixup },
+	{ .compatible = "microchip,sam9x60", .data = sam9x60_aic_irq_fixup },
 	{ /* sentinel */ },
 };
 
diff --git a/drivers/irqchip/irq-bcm2835.c b/drivers/irqchip/irq-bcm2835.c
index 418245d..a1e004a 100644
--- a/drivers/irqchip/irq-bcm2835.c
+++ b/drivers/irqchip/irq-bcm2835.c
@@ -61,6 +61,7 @@
 					| SHORTCUT1_MASK | SHORTCUT2_MASK)
 
 #define REG_FIQ_CONTROL		0x0c
+#define FIQ_CONTROL_ENABLE	BIT(7)
 
 #define NR_BANKS		3
 #define IRQS_PER_BANK		32
@@ -135,6 +136,7 @@
 {
 	void __iomem *base;
 	int irq, b, i;
+	u32 reg;
 
 	base = of_iomap(node, 0);
 	if (!base)
@@ -157,6 +159,19 @@
 				handle_level_irq);
 			irq_set_probe(irq);
 		}
+
+		reg = readl_relaxed(intc.enable[b]);
+		if (reg) {
+			writel_relaxed(reg, intc.disable[b]);
+			pr_err(FW_BUG "Bootloader left irq enabled: "
+			       "bank %d irq %*pbl\n", b, IRQS_PER_BANK, &reg);
+		}
+	}
+
+	reg = readl_relaxed(base + REG_FIQ_CONTROL);
+	if (reg & FIQ_CONTROL_ENABLE) {
+		writel_relaxed(0, base + REG_FIQ_CONTROL);
+		pr_err(FW_BUG "Bootloader left fiq enabled\n");
 	}
 
 	if (is_2836) {
diff --git a/drivers/irqchip/irq-bcm2836.c b/drivers/irqchip/irq-bcm2836.c
index 2038693..cbc7c74 100644
--- a/drivers/irqchip/irq-bcm2836.c
+++ b/drivers/irqchip/irq-bcm2836.c
@@ -10,6 +10,7 @@
 #include <linux/of_irq.h>
 #include <linux/irqchip.h>
 #include <linux/irqdomain.h>
+#include <linux/irqchip/chained_irq.h>
 #include <linux/irqchip/irq-bcm2836.h>
 
 #include <asm/exception.h>
@@ -89,12 +90,24 @@
 	.irq_unmask	= bcm2836_arm_irqchip_unmask_gpu_irq,
 };
 
+static void bcm2836_arm_irqchip_dummy_op(struct irq_data *d)
+{
+}
+
+static struct irq_chip bcm2836_arm_irqchip_dummy = {
+	.name		= "bcm2836-dummy",
+	.irq_eoi	= bcm2836_arm_irqchip_dummy_op,
+};
+
 static int bcm2836_map(struct irq_domain *d, unsigned int irq,
 		       irq_hw_number_t hw)
 {
 	struct irq_chip *chip;
 
 	switch (hw) {
+	case LOCAL_IRQ_MAILBOX0:
+		chip = &bcm2836_arm_irqchip_dummy;
+		break;
 	case LOCAL_IRQ_CNTPSIRQ:
 	case LOCAL_IRQ_CNTPNSIRQ:
 	case LOCAL_IRQ_CNTHPIRQ:
@@ -127,17 +140,7 @@
 	u32 stat;
 
 	stat = readl_relaxed(intc.base + LOCAL_IRQ_PENDING0 + 4 * cpu);
-	if (stat & BIT(LOCAL_IRQ_MAILBOX0)) {
-#ifdef CONFIG_SMP
-		void __iomem *mailbox0 = (intc.base +
-					  LOCAL_MAILBOX0_CLR0 + 16 * cpu);
-		u32 mbox_val = readl(mailbox0);
-		u32 ipi = ffs(mbox_val) - 1;
-
-		writel(1 << ipi, mailbox0);
-		handle_IPI(ipi, regs);
-#endif
-	} else if (stat) {
+	if (stat) {
 		u32 hwirq = ffs(stat) - 1;
 
 		handle_domain_irq(intc.domain, hwirq, regs);
@@ -145,8 +148,35 @@
 }
 
 #ifdef CONFIG_SMP
-static void bcm2836_arm_irqchip_send_ipi(const struct cpumask *mask,
-					 unsigned int ipi)
+static struct irq_domain *ipi_domain;
+
+static void bcm2836_arm_irqchip_handle_ipi(struct irq_desc *desc)
+{
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	int cpu = smp_processor_id();
+	u32 mbox_val;
+
+	chained_irq_enter(chip, desc);
+
+	mbox_val = readl_relaxed(intc.base + LOCAL_MAILBOX0_CLR0 + 16 * cpu);
+	if (mbox_val) {
+		int hwirq = ffs(mbox_val) - 1;
+		generic_handle_irq(irq_find_mapping(ipi_domain, hwirq));
+	}
+
+	chained_irq_exit(chip, desc);
+}
+
+static void bcm2836_arm_irqchip_ipi_eoi(struct irq_data *d)
+{
+	int cpu = smp_processor_id();
+
+	writel_relaxed(BIT(d->hwirq),
+		       intc.base + LOCAL_MAILBOX0_CLR0 + 16 * cpu);
+}
+
+static void bcm2836_arm_irqchip_ipi_send_mask(struct irq_data *d,
+					      const struct cpumask *mask)
 {
 	int cpu;
 	void __iomem *mailbox0_base = intc.base + LOCAL_MAILBOX0_SET0;
@@ -157,11 +187,47 @@
 	 */
 	smp_wmb();
 
-	for_each_cpu(cpu, mask)	{
-		writel(1 << ipi, mailbox0_base + 16 * cpu);
-	}
+	for_each_cpu(cpu, mask)
+		writel_relaxed(BIT(d->hwirq), mailbox0_base + 16 * cpu);
 }
 
+static struct irq_chip bcm2836_arm_irqchip_ipi = {
+	.name		= "IPI",
+	.irq_mask	= bcm2836_arm_irqchip_dummy_op,
+	.irq_unmask	= bcm2836_arm_irqchip_dummy_op,
+	.irq_eoi	= bcm2836_arm_irqchip_ipi_eoi,
+	.ipi_send_mask	= bcm2836_arm_irqchip_ipi_send_mask,
+};
+
+static int bcm2836_arm_irqchip_ipi_alloc(struct irq_domain *d,
+					 unsigned int virq,
+					 unsigned int nr_irqs, void *args)
+{
+	int i;
+
+	for (i = 0; i < nr_irqs; i++) {
+		irq_set_percpu_devid(virq + i);
+		irq_domain_set_info(d, virq + i, i, &bcm2836_arm_irqchip_ipi,
+				    d->host_data,
+				    handle_percpu_devid_fasteoi_ipi,
+				    NULL, NULL);
+	}
+
+	return 0;
+}
+
+static void bcm2836_arm_irqchip_ipi_free(struct irq_domain *d,
+					 unsigned int virq,
+					 unsigned int nr_irqs)
+{
+	/* Not freeing IPIs */
+}
+
+static const struct irq_domain_ops ipi_domain_ops = {
+	.alloc	= bcm2836_arm_irqchip_ipi_alloc,
+	.free	= bcm2836_arm_irqchip_ipi_free,
+};
+
 static int bcm2836_cpu_starting(unsigned int cpu)
 {
 	bcm2836_arm_irqchip_unmask_per_cpu_irq(LOCAL_MAILBOX_INT_CONTROL0, 0,
@@ -175,6 +241,52 @@
 					     cpu);
 	return 0;
 }
+
+#define BITS_PER_MBOX	32
+
+static void __init bcm2836_arm_irqchip_smp_init(void)
+{
+	struct irq_fwspec ipi_fwspec = {
+		.fwnode		= intc.domain->fwnode,
+		.param_count	= 1,
+		.param		= {
+			[0]	= LOCAL_IRQ_MAILBOX0,
+		},
+	};
+	int base_ipi, mux_irq;
+
+	mux_irq = irq_create_fwspec_mapping(&ipi_fwspec);
+	if (WARN_ON(mux_irq <= 0))
+		return;
+
+	ipi_domain = irq_domain_create_linear(intc.domain->fwnode,
+					      BITS_PER_MBOX, &ipi_domain_ops,
+					      NULL);
+	if (WARN_ON(!ipi_domain))
+		return;
+
+	ipi_domain->flags |= IRQ_DOMAIN_FLAG_IPI_SINGLE;
+	irq_domain_update_bus_token(ipi_domain, DOMAIN_BUS_IPI);
+
+	base_ipi = __irq_domain_alloc_irqs(ipi_domain, -1, BITS_PER_MBOX,
+					   NUMA_NO_NODE, NULL,
+					   false, NULL);
+
+	if (WARN_ON(!base_ipi))
+		return;
+
+	set_smp_ipi_range(base_ipi, BITS_PER_MBOX);
+
+	irq_set_chained_handler_and_data(mux_irq,
+					 bcm2836_arm_irqchip_handle_ipi, NULL);
+
+	/* Unmask IPIs to the boot CPU. */
+	cpuhp_setup_state(CPUHP_AP_IRQ_BCM2836_STARTING,
+			  "irqchip/bcm2836:starting", bcm2836_cpu_starting,
+			  bcm2836_cpu_dying);
+}
+#else
+#define bcm2836_arm_irqchip_smp_init()	do { } while(0)
 #endif
 
 static const struct irq_domain_ops bcm2836_arm_irqchip_intc_ops = {
@@ -182,19 +294,6 @@
 	.map = bcm2836_map,
 };
 
-static void
-bcm2836_arm_irqchip_smp_init(void)
-{
-#ifdef CONFIG_SMP
-	/* Unmask IPIs to the boot CPU. */
-	cpuhp_setup_state(CPUHP_AP_IRQ_BCM2836_STARTING,
-			  "irqchip/bcm2836:starting", bcm2836_cpu_starting,
-			  bcm2836_cpu_dying);
-
-	set_smp_cross_call(bcm2836_arm_irqchip_send_ipi);
-#endif
-}
-
 /*
  * The LOCAL_IRQ_CNT* timer firings are based off of the external
  * oscillator with some scaling.  The firmware sets up CNTFRQ to
@@ -232,6 +331,8 @@
 	if (!intc.domain)
 		panic("%pOF: unable to create IRQ domain\n", node);
 
+	irq_domain_update_bus_token(intc.domain, DOMAIN_BUS_WIRED);
+
 	bcm2836_arm_irqchip_smp_init();
 
 	set_handle_irq(bcm2836_arm_irqchip_handle_irq);
diff --git a/drivers/irqchip/irq-bcm6345-l1.c b/drivers/irqchip/irq-bcm6345-l1.c
index e348378..1bd0621 100644
--- a/drivers/irqchip/irq-bcm6345-l1.c
+++ b/drivers/irqchip/irq-bcm6345-l1.c
@@ -140,7 +140,7 @@
 		for_each_set_bit(hwirq, &pending, IRQS_PER_WORD) {
 			irq = irq_linear_revmap(intc->domain, base + hwirq);
 			if (irq)
-				do_IRQ(irq);
+				generic_handle_irq(irq);
 			else
 				spurious_interrupt();
 		}
diff --git a/drivers/irqchip/irq-bcm7038-l1.c b/drivers/irqchip/irq-bcm7038-l1.c
index 58bec21..9dc9bf8 100644
--- a/drivers/irqchip/irq-bcm7038-l1.c
+++ b/drivers/irqchip/irq-bcm7038-l1.c
@@ -27,6 +27,10 @@
 #include <linux/types.h>
 #include <linux/irqchip.h>
 #include <linux/irqchip/chained_irq.h>
+#include <linux/syscore_ops.h>
+#ifdef CONFIG_ARM
+#include <asm/smp_plat.h>
+#endif
 
 #define IRQS_PER_WORD		32
 #define REG_BYTES_PER_IRQ_WORD	(sizeof(u32) * 4)
@@ -39,12 +43,17 @@
 	unsigned int		n_words;
 	struct irq_domain	*domain;
 	struct bcm7038_l1_cpu	*cpus[NR_CPUS];
+#ifdef CONFIG_PM_SLEEP
+	struct list_head	list;
+	u32			wake_mask[MAX_WORDS];
+#endif
+	u32			irq_fwd_mask[MAX_WORDS];
 	u8			affinity[MAX_WORDS * IRQS_PER_WORD];
 };
 
 struct bcm7038_l1_cpu {
 	void __iomem		*map_base;
-	u32			mask_cache[0];
+	u32			mask_cache[];
 };
 
 /*
@@ -249,6 +258,7 @@
 	resource_size_t sz;
 	struct bcm7038_l1_cpu *cpu;
 	unsigned int i, n_words, parent_irq;
+	int ret;
 
 	if (of_address_to_resource(dn, idx, &res))
 		return -EINVAL;
@@ -262,6 +272,14 @@
 	else if (intc->n_words != n_words)
 		return -EINVAL;
 
+	ret = of_property_read_u32_array(dn , "brcm,int-fwd-mask",
+					 intc->irq_fwd_mask, n_words);
+	if (ret != 0 && ret != -EINVAL) {
+		/* property exists but has the wrong number of words */
+		pr_err("invalid brcm,int-fwd-mask property\n");
+		return -EINVAL;
+	}
+
 	cpu = intc->cpus[idx] = kzalloc(sizeof(*cpu) + n_words * sizeof(u32),
 					GFP_KERNEL);
 	if (!cpu)
@@ -272,8 +290,11 @@
 		return -ENOMEM;
 
 	for (i = 0; i < n_words; i++) {
-		l1_writel(0xffffffff, cpu->map_base + reg_mask_set(intc, i));
-		cpu->mask_cache[i] = 0xffffffff;
+		l1_writel(~intc->irq_fwd_mask[i],
+			  cpu->map_base + reg_mask_set(intc, i));
+		l1_writel(intc->irq_fwd_mask[i],
+			  cpu->map_base + reg_mask_clr(intc, i));
+		cpu->mask_cache[i] = ~intc->irq_fwd_mask[i];
 	}
 
 	parent_irq = irq_of_parse_and_map(dn, idx);
@@ -291,6 +312,87 @@
 	return 0;
 }
 
+#ifdef CONFIG_PM_SLEEP
+/*
+ * We keep a list of bcm7038_l1_chip used for suspend/resume. This hack is
+ * used because the struct chip_type suspend/resume hooks are not called
+ * unless chip_type is hooked onto a generic_chip. Since this driver does
+ * not use generic_chip, we need to manually hook our resume/suspend to
+ * syscore_ops.
+ */
+static LIST_HEAD(bcm7038_l1_intcs_list);
+static DEFINE_RAW_SPINLOCK(bcm7038_l1_intcs_lock);
+
+static int bcm7038_l1_suspend(void)
+{
+	struct bcm7038_l1_chip *intc;
+	int boot_cpu, word;
+	u32 val;
+
+	/* Wakeup interrupt should only come from the boot cpu */
+#ifdef CONFIG_SMP
+	boot_cpu = cpu_logical_map(0);
+#else
+	boot_cpu = 0;
+#endif
+
+	list_for_each_entry(intc, &bcm7038_l1_intcs_list, list) {
+		for (word = 0; word < intc->n_words; word++) {
+			val = intc->wake_mask[word] | intc->irq_fwd_mask[word];
+			l1_writel(~val,
+				intc->cpus[boot_cpu]->map_base + reg_mask_set(intc, word));
+			l1_writel(val,
+				intc->cpus[boot_cpu]->map_base + reg_mask_clr(intc, word));
+		}
+	}
+
+	return 0;
+}
+
+static void bcm7038_l1_resume(void)
+{
+	struct bcm7038_l1_chip *intc;
+	int boot_cpu, word;
+
+#ifdef CONFIG_SMP
+	boot_cpu = cpu_logical_map(0);
+#else
+	boot_cpu = 0;
+#endif
+
+	list_for_each_entry(intc, &bcm7038_l1_intcs_list, list) {
+		for (word = 0; word < intc->n_words; word++) {
+			l1_writel(intc->cpus[boot_cpu]->mask_cache[word],
+				intc->cpus[boot_cpu]->map_base + reg_mask_set(intc, word));
+			l1_writel(~intc->cpus[boot_cpu]->mask_cache[word],
+				intc->cpus[boot_cpu]->map_base + reg_mask_clr(intc, word));
+		}
+	}
+}
+
+static struct syscore_ops bcm7038_l1_syscore_ops = {
+	.suspend	= bcm7038_l1_suspend,
+	.resume		= bcm7038_l1_resume,
+};
+
+static int bcm7038_l1_set_wake(struct irq_data *d, unsigned int on)
+{
+	struct bcm7038_l1_chip *intc = irq_data_get_irq_chip_data(d);
+	unsigned long flags;
+	u32 word = d->hwirq / IRQS_PER_WORD;
+	u32 mask = BIT(d->hwirq % IRQS_PER_WORD);
+
+	raw_spin_lock_irqsave(&intc->lock, flags);
+	if (on)
+		intc->wake_mask[word] |= mask;
+	else
+		intc->wake_mask[word] &= ~mask;
+	raw_spin_unlock_irqrestore(&intc->lock, flags);
+
+	return 0;
+}
+#endif
+
 static struct irq_chip bcm7038_l1_irq_chip = {
 	.name			= "bcm7038-l1",
 	.irq_mask		= bcm7038_l1_mask,
@@ -299,11 +401,21 @@
 #ifdef CONFIG_SMP
 	.irq_cpu_offline	= bcm7038_l1_cpu_offline,
 #endif
+#ifdef CONFIG_PM_SLEEP
+	.irq_set_wake		= bcm7038_l1_set_wake,
+#endif
 };
 
 static int bcm7038_l1_map(struct irq_domain *d, unsigned int virq,
 			  irq_hw_number_t hw_irq)
 {
+	struct bcm7038_l1_chip *intc = d->host_data;
+	u32 mask = BIT(hw_irq % IRQS_PER_WORD);
+	u32 word = hw_irq / IRQS_PER_WORD;
+
+	if (intc->irq_fwd_mask[word] & mask)
+		return -EPERM;
+
 	irq_set_chip_and_handler(virq, &bcm7038_l1_irq_chip, handle_level_irq);
 	irq_set_chip_data(virq, d->host_data);
 	irqd_set_single_target(irq_desc_get_irq_data(irq_to_desc(virq)));
@@ -315,7 +427,7 @@
 	.map			= bcm7038_l1_map,
 };
 
-int __init bcm7038_l1_of_init(struct device_node *dn,
+static int __init bcm7038_l1_of_init(struct device_node *dn,
 			      struct device_node *parent)
 {
 	struct bcm7038_l1_chip *intc;
@@ -344,6 +456,16 @@
 		goto out_unmap;
 	}
 
+#ifdef CONFIG_PM_SLEEP
+	/* Add bcm7038_l1_chip into a list */
+	raw_spin_lock(&bcm7038_l1_intcs_lock);
+	list_add_tail(&intc->list, &bcm7038_l1_intcs_list);
+	raw_spin_unlock(&bcm7038_l1_intcs_lock);
+
+	if (list_is_singular(&bcm7038_l1_intcs_list))
+		register_syscore_ops(&bcm7038_l1_syscore_ops);
+#endif
+
 	pr_info("registered BCM7038 L1 intc (%pOF, IRQs: %d)\n",
 		dn, IRQS_PER_WORD * intc->n_words);
 
diff --git a/drivers/irqchip/irq-bcm7120-l2.c b/drivers/irqchip/irq-bcm7120-l2.c
index 586df35..c7c9e97 100644
--- a/drivers/irqchip/irq-bcm7120-l2.c
+++ b/drivers/irqchip/irq-bcm7120-l2.c
@@ -143,6 +143,9 @@
 
 	irq_set_chained_handler_and_data(parent_irq,
 					 bcm7120_l2_intc_irq_handle, l1_data);
+	if (data->can_wake)
+		enable_irq_wake(parent_irq);
+
 	return 0;
 }
 
@@ -247,6 +250,8 @@
 	if (ret < 0)
 		goto out_free_l1_data;
 
+	data->can_wake = of_property_read_bool(dn, "brcm,irq-can-wake");
+
 	for (irq = 0; irq < data->num_parent_irqs; irq++) {
 		ret = bcm7120_l2_intc_init_one(dn, data, irq, valid_mask);
 		if (ret)
@@ -274,9 +279,6 @@
 		goto out_free_domain;
 	}
 
-	if (of_property_read_bool(dn, "brcm,irq-can-wake"))
-		data->can_wake = true;
-
 	for (idx = 0; idx < data->n_words; idx++) {
 		irq = idx * IRQS_PER_WORD;
 		gc = irq_get_domain_generic_chip(data->domain, irq);
diff --git a/drivers/irqchip/irq-brcmstb-l2.c b/drivers/irqchip/irq-brcmstb-l2.c
index 0298ede..cdd6a42 100644
--- a/drivers/irqchip/irq-brcmstb-l2.c
+++ b/drivers/irqchip/irq-brcmstb-l2.c
@@ -254,6 +254,7 @@
 		 */
 		data->gc->wake_enabled = 0xffffffff;
 		ct->chip.irq_set_wake = irq_gc_set_wake;
+		enable_irq_wake(parent_irq);
 	}
 
 	pr_info("registered L2 intc (%pOF, parent irq: %d)\n", np, parent_irq);
@@ -275,6 +276,10 @@
 	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);
+IRQCHIP_DECLARE(brcmstb_hif_spi_l2_intc, "brcm,hif-spi-l2-intc",
+		brcmstb_l2_edge_intc_of_init);
+IRQCHIP_DECLARE(brcmstb_upg_aux_aon_l2_intc, "brcm,upg-aux-aon-l2-intc",
+		brcmstb_l2_edge_intc_of_init);
 
 static int __init brcmstb_l2_lvl_intc_of_init(struct device_node *np,
 	struct device_node *parent)
diff --git a/drivers/irqchip/irq-dw-apb-ictl.c b/drivers/irqchip/irq-dw-apb-ictl.c
index e4550e9..54b09d6 100644
--- a/drivers/irqchip/irq-dw-apb-ictl.c
+++ b/drivers/irqchip/irq-dw-apb-ictl.c
@@ -17,6 +17,7 @@
 #include <linux/irqchip/chained_irq.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
+#include <linux/interrupt.h>
 
 #define APB_INT_ENABLE_L	0x00
 #define APB_INT_ENABLE_H	0x04
@@ -26,7 +27,28 @@
 #define APB_INT_FINALSTATUS_H	0x34
 #define APB_INT_BASE_OFFSET	0x04
 
-static void dw_apb_ictl_handler(struct irq_desc *desc)
+/* irq domain of the primary interrupt controller. */
+static struct irq_domain *dw_apb_ictl_irq_domain;
+
+static void __irq_entry dw_apb_ictl_handle_irq(struct pt_regs *regs)
+{
+	struct irq_domain *d = dw_apb_ictl_irq_domain;
+	int n;
+
+	for (n = 0; n < d->revmap_size; n += 32) {
+		struct irq_chip_generic *gc = irq_get_domain_generic_chip(d, n);
+		u32 stat = readl_relaxed(gc->reg_base + APB_INT_FINALSTATUS_L);
+
+		while (stat) {
+			u32 hwirq = ffs(stat) - 1;
+
+			handle_domain_irq(d, hwirq, regs);
+			stat &= ~BIT(hwirq);
+		}
+	}
+}
+
+static void dw_apb_ictl_handle_irq_cascaded(struct irq_desc *desc)
 {
 	struct irq_domain *d = irq_desc_get_handler_data(desc);
 	struct irq_chip *chip = irq_desc_get_chip(desc);
@@ -43,13 +65,37 @@
 			u32 virq = irq_find_mapping(d, gc->irq_base + hwirq);
 
 			generic_handle_irq(virq);
-			stat &= ~(1 << hwirq);
+			stat &= ~BIT(hwirq);
 		}
 	}
 
 	chained_irq_exit(chip, desc);
 }
 
+static int dw_apb_ictl_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
+				unsigned int nr_irqs, void *arg)
+{
+	int i, ret;
+	irq_hw_number_t hwirq;
+	unsigned int type = IRQ_TYPE_NONE;
+	struct irq_fwspec *fwspec = arg;
+
+	ret = irq_domain_translate_onecell(domain, fwspec, &hwirq, &type);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < nr_irqs; i++)
+		irq_map_generic_chip(domain, virq + i, hwirq + i);
+
+	return 0;
+}
+
+static const struct irq_domain_ops dw_apb_ictl_irq_domain_ops = {
+	.translate = irq_domain_translate_onecell,
+	.alloc = dw_apb_ictl_irq_domain_alloc,
+	.free = irq_domain_free_irqs_top,
+};
+
 #ifdef CONFIG_PM
 static void dw_apb_ictl_resume(struct irq_data *d)
 {
@@ -68,19 +114,27 @@
 static int __init dw_apb_ictl_init(struct device_node *np,
 				   struct device_node *parent)
 {
+	const struct irq_domain_ops *domain_ops;
 	unsigned int clr = IRQ_NOREQUEST | IRQ_NOPROBE | IRQ_NOAUTOEN;
 	struct resource r;
 	struct irq_domain *domain;
 	struct irq_chip_generic *gc;
 	void __iomem *iobase;
-	int ret, nrirqs, irq, i;
+	int ret, nrirqs, parent_irq, i;
 	u32 reg;
 
-	/* Map the parent interrupt for the chained handler */
-	irq = irq_of_parse_and_map(np, 0);
-	if (irq <= 0) {
-		pr_err("%pOF: unable to parse irq\n", np);
-		return -EINVAL;
+	if (!parent) {
+		/* Used as the primary interrupt controller */
+		parent_irq = 0;
+		domain_ops = &dw_apb_ictl_irq_domain_ops;
+	} else {
+		/* Map the parent interrupt for the chained handler */
+		parent_irq = irq_of_parse_and_map(np, 0);
+		if (parent_irq <= 0) {
+			pr_err("%pOF: unable to parse irq\n", np);
+			return -EINVAL;
+		}
+		domain_ops = &irq_generic_chip_ops;
 	}
 
 	ret = of_address_to_resource(np, 0, &r);
@@ -120,8 +174,7 @@
 	else
 		nrirqs = fls(readl_relaxed(iobase + APB_INT_ENABLE_L));
 
-	domain = irq_domain_add_linear(np, nrirqs,
-				       &irq_generic_chip_ops, NULL);
+	domain = irq_domain_add_linear(np, nrirqs, domain_ops, NULL);
 	if (!domain) {
 		pr_err("%pOF: unable to add irq domain\n", np);
 		ret = -ENOMEM;
@@ -146,7 +199,13 @@
 		gc->chip_types[0].chip.irq_resume = dw_apb_ictl_resume;
 	}
 
-	irq_set_chained_handler_and_data(irq, dw_apb_ictl_handler, domain);
+	if (parent_irq) {
+		irq_set_chained_handler_and_data(parent_irq,
+				dw_apb_ictl_handle_irq_cascaded, domain);
+	} else {
+		dw_apb_ictl_irq_domain = domain;
+		set_handle_irq(dw_apb_ictl_handle_irq);
+	}
 
 	return 0;
 
diff --git a/drivers/irqchip/irq-gic-common.c b/drivers/irqchip/irq-gic-common.c
index 8252000..f47b41d 100644
--- a/drivers/irqchip/irq-gic-common.c
+++ b/drivers/irqchip/irq-gic-common.c
@@ -152,9 +152,6 @@
 		writel_relaxed(GICD_INT_DEF_PRI_X4,
 					base + GIC_DIST_PRI + i * 4 / 4);
 
-	/* Ensure all SGI interrupts are now enabled */
-	writel_relaxed(GICD_INT_EN_SET_SGI, base + GIC_DIST_ENABLE_SET);
-
 	if (sync_access)
 		sync_access();
 }
diff --git a/drivers/irqchip/irq-gic-v2m.c b/drivers/irqchip/irq-gic-v2m.c
index e88e75c..fbec07d 100644
--- a/drivers/irqchip/irq-gic-v2m.c
+++ b/drivers/irqchip/irq-gic-v2m.c
@@ -17,6 +17,7 @@
 #include <linux/irq.h>
 #include <linux/irqdomain.h>
 #include <linux/kernel.h>
+#include <linux/pci.h>
 #include <linux/msi.h>
 #include <linux/of_address.h>
 #include <linux/of_pci.h>
diff --git a/drivers/irqchip/irq-gic-v3-its-fsl-mc-msi.c b/drivers/irqchip/irq-gic-v3-its-fsl-mc-msi.c
index 606efa6..634263d 100644
--- a/drivers/irqchip/irq-gic-v3-its-fsl-mc-msi.c
+++ b/drivers/irqchip/irq-gic-v3-its-fsl-mc-msi.c
@@ -7,6 +7,8 @@
  *
  */
 
+#include <linux/acpi.h>
+#include <linux/acpi_iort.h>
 #include <linux/of_device.h>
 #include <linux/of_address.h>
 #include <linux/irq.h>
@@ -23,6 +25,19 @@
 	.irq_set_affinity = msi_domain_set_affinity
 };
 
+static u32 fsl_mc_msi_domain_get_msi_id(struct irq_domain *domain,
+					struct fsl_mc_device *mc_dev)
+{
+	struct device_node *of_node;
+	u32 out_id;
+
+	of_node = irq_domain_get_of_node(domain);
+	out_id = of_node ? of_msi_map_id(&mc_dev->dev, of_node, mc_dev->icid) :
+			iort_msi_map_id(&mc_dev->dev, mc_dev->icid);
+
+	return out_id;
+}
+
 static int its_fsl_mc_msi_prepare(struct irq_domain *msi_domain,
 				  struct device *dev,
 				  int nvec, msi_alloc_info_t *info)
@@ -43,7 +58,8 @@
 	 * NOTE: This device id corresponds to the IOMMU stream ID
 	 * associated with the DPRC object (ICID).
 	 */
-	info->scratchpad[0].ul = mc_bus_dev->icid;
+	info->scratchpad[0].ul = fsl_mc_msi_domain_get_msi_id(msi_domain,
+							      mc_bus_dev);
 	msi_info = msi_get_domain_info(msi_domain->parent);
 
 	/* Allocate at least 32 MSIs, and always as a power of 2 */
@@ -66,12 +82,71 @@
 	{},
 };
 
-static int __init its_fsl_mc_msi_init(void)
+static void __init its_fsl_mc_msi_init_one(struct fwnode_handle *handle,
+					  const char *name)
 {
-	struct device_node *np;
 	struct irq_domain *parent;
 	struct irq_domain *mc_msi_domain;
 
+	parent = irq_find_matching_fwnode(handle, DOMAIN_BUS_NEXUS);
+	if (!parent || !msi_get_domain_info(parent)) {
+		pr_err("%s: unable to locate ITS domain\n", name);
+		return;
+	}
+
+	mc_msi_domain = fsl_mc_msi_create_irq_domain(handle,
+						&its_fsl_mc_msi_domain_info,
+						parent);
+	if (!mc_msi_domain) {
+		pr_err("%s: unable to create fsl-mc domain\n", name);
+		return;
+	}
+
+	pr_info("fsl-mc MSI: %s domain created\n", name);
+}
+
+#ifdef CONFIG_ACPI
+static int __init
+its_fsl_mc_msi_parse_madt(union acpi_subtable_headers *header,
+			  const unsigned long end)
+{
+	struct acpi_madt_generic_translator *its_entry;
+	struct fwnode_handle *dom_handle;
+	const char *node_name;
+	int err = 0;
+
+	its_entry = (struct acpi_madt_generic_translator *)header;
+	node_name = kasprintf(GFP_KERNEL, "ITS@0x%lx",
+			      (long)its_entry->base_address);
+
+	dom_handle = iort_find_domain_token(its_entry->translation_id);
+	if (!dom_handle) {
+		pr_err("%s: Unable to locate ITS domain handle\n", node_name);
+		err = -ENXIO;
+		goto out;
+	}
+
+	its_fsl_mc_msi_init_one(dom_handle, node_name);
+
+out:
+	kfree(node_name);
+	return err;
+}
+
+
+static void __init its_fsl_mc_acpi_msi_init(void)
+{
+	acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_TRANSLATOR,
+			      its_fsl_mc_msi_parse_madt, 0);
+}
+#else
+static inline void its_fsl_mc_acpi_msi_init(void) { }
+#endif
+
+static void __init its_fsl_mc_of_msi_init(void)
+{
+	struct device_node *np;
+
 	for (np = of_find_matching_node(NULL, its_device_id); np;
 	     np = of_find_matching_node(np, its_device_id)) {
 		if (!of_device_is_available(np))
@@ -79,23 +154,15 @@
 		if (!of_property_read_bool(np, "msi-controller"))
 			continue;
 
-		parent = irq_find_matching_host(np, DOMAIN_BUS_NEXUS);
-		if (!parent || !msi_get_domain_info(parent)) {
-			pr_err("%pOF: unable to locate ITS domain\n", np);
-			continue;
-		}
-
-		mc_msi_domain = fsl_mc_msi_create_irq_domain(
-						 of_node_to_fwnode(np),
-						 &its_fsl_mc_msi_domain_info,
-						 parent);
-		if (!mc_msi_domain) {
-			pr_err("%pOF: unable to create fsl-mc domain\n", np);
-			continue;
-		}
-
-		pr_info("fsl-mc MSI: %pOF domain created\n", np);
+		its_fsl_mc_msi_init_one(of_node_to_fwnode(np),
+					np->full_name);
 	}
+}
+
+static int __init its_fsl_mc_msi_init(void)
+{
+	its_fsl_mc_of_msi_init();
+	its_fsl_mc_acpi_msi_init();
 
 	return 0;
 }
diff --git a/drivers/irqchip/irq-gic-v3-its-pci-msi.c b/drivers/irqchip/irq-gic-v3-its-pci-msi.c
index 229d586..87711e0 100644
--- a/drivers/irqchip/irq-gic-v3-its-pci-msi.c
+++ b/drivers/irqchip/irq-gic-v3-its-pci-msi.c
@@ -5,6 +5,7 @@
  */
 
 #include <linux/acpi_iort.h>
+#include <linux/pci.h>
 #include <linux/msi.h>
 #include <linux/of.h>
 #include <linux/of_irq.h>
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index f298313..42b2953 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -6,6 +6,7 @@
 
 #include <linux/acpi.h>
 #include <linux/acpi_iort.h>
+#include <linux/bitfield.h>
 #include <linux/bitmap.h>
 #include <linux/cpu.h>
 #include <linux/crash_dump.h>
@@ -13,6 +14,7 @@
 #include <linux/dma-iommu.h>
 #include <linux/efi.h>
 #include <linux/interrupt.h>
+#include <linux/iopoll.h>
 #include <linux/irqdomain.h>
 #include <linux/list.h>
 #include <linux/log2.h>
@@ -94,6 +96,7 @@
 	struct mutex		dev_alloc_lock;
 	struct list_head	entry;
 	void __iomem		*base;
+	void __iomem		*sgir_base;
 	phys_addr_t		phys_base;
 	struct its_cmd_block	*cmd_base;
 	struct its_cmd_block	*cmd_write;
@@ -101,24 +104,36 @@
 	struct its_collection	*collections;
 	struct fwnode_handle	*fwnode_handle;
 	u64			(*get_msi_base)(struct its_device *its_dev);
+	u64			typer;
 	u64			cbaser_save;
 	u32			ctlr_save;
+	u32			mpidr;
 	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 is_v4(its)		(!!((its)->typer & GITS_TYPER_VLPIS))
+#define is_v4_1(its)		(!!((its)->typer & GITS_TYPER_VMAPP))
+#define device_ids(its)		(FIELD_GET(GITS_TYPER_DEVBITS, (its)->typer) + 1)
+
 #define ITS_ITT_ALIGN		SZ_256
 
 /* The maximum number of VPEID bits supported by VLPI commands */
-#define ITS_MAX_VPEID_BITS	(16)
+#define ITS_MAX_VPEID_BITS						\
+	({								\
+		int nvpeid = 16;					\
+		if (gic_rdists->has_rvpeid &&				\
+		    gic_rdists->gicd_typer2 & GICD_TYPER2_VIL)		\
+			nvpeid = 1 + (gic_rdists->gicd_typer2 &		\
+				      GICD_TYPER2_VID);			\
+									\
+		nvpeid;							\
+	})
 #define ITS_MAX_VPEID		(1 << (ITS_MAX_VPEID_BITS))
 
 /* Convert page order to size in bytes */
@@ -129,7 +144,7 @@
 	u16			*col_map;
 	irq_hw_number_t		lpi_base;
 	int			nr_lpis;
-	struct mutex		vlpi_lock;
+	raw_spinlock_t		vlpi_lock;
 	struct its_vm		*vm;
 	struct its_vlpi_map	*vlpi_maps;
 	int			nr_vlpis;
@@ -158,6 +173,13 @@
 	int			next_victim;
 } vpe_proxy;
 
+struct cpu_lpi_count {
+	atomic_t	managed;
+	atomic_t	unmanaged;
+};
+
+static DEFINE_PER_CPU(struct cpu_lpi_count, cpu_lpi_count);
+
 static LIST_HEAD(its_nodes);
 static DEFINE_RAW_SPINLOCK(its_lock);
 static struct rdists *gic_rdists;
@@ -174,22 +196,37 @@
 #define gic_data_rdist_rd_base()	(gic_data_rdist()->rd_base)
 #define gic_data_rdist_vlpi_base()	(gic_data_rdist_rd_base() + SZ_128K)
 
+/*
+ * Skip ITSs that have no vLPIs mapped, unless we're on GICv4.1, as we
+ * always have vSGIs mapped.
+ */
+static bool require_its_list_vmovp(struct its_vm *vm, struct its_node *its)
+{
+	return (gic_rdists->has_rvpeid || vm->vlpi_count[its->list_nr]);
+}
+
 static u16 get_its_list(struct its_vm *vm)
 {
 	struct its_node *its;
 	unsigned long its_list = 0;
 
 	list_for_each_entry(its, &its_nodes, entry) {
-		if (!its->is_v4)
+		if (!is_v4(its))
 			continue;
 
-		if (vm->vlpi_count[its->list_nr])
+		if (require_its_list_vmovp(vm, its))
 			__set_bit(its->list_nr, &its_list);
 	}
 
 	return (u16)its_list;
 }
 
+static inline u32 its_get_event_id(struct irq_data *d)
+{
+	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
+	return d->hwirq - its_dev->event_map.lpi_base;
+}
+
 static struct its_collection *dev_event_to_col(struct its_device *its_dev,
 					       u32 event)
 {
@@ -198,6 +235,64 @@
 	return its->collections + its_dev->event_map.col_map[event];
 }
 
+static struct its_vlpi_map *dev_event_to_vlpi_map(struct its_device *its_dev,
+					       u32 event)
+{
+	if (WARN_ON_ONCE(event >= its_dev->event_map.nr_lpis))
+		return NULL;
+
+	return &its_dev->event_map.vlpi_maps[event];
+}
+
+static struct its_vlpi_map *get_vlpi_map(struct irq_data *d)
+{
+	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);
+
+		return dev_event_to_vlpi_map(its_dev, event);
+	}
+
+	return NULL;
+}
+
+static int vpe_to_cpuid_lock(struct its_vpe *vpe, unsigned long *flags)
+{
+	raw_spin_lock_irqsave(&vpe->vpe_lock, *flags);
+	return vpe->col_idx;
+}
+
+static void vpe_to_cpuid_unlock(struct its_vpe *vpe, unsigned long flags)
+{
+	raw_spin_unlock_irqrestore(&vpe->vpe_lock, flags);
+}
+
+static int irq_to_cpuid_lock(struct irq_data *d, unsigned long *flags)
+{
+	struct its_vlpi_map *map = get_vlpi_map(d);
+	int cpu;
+
+	if (map) {
+		cpu = vpe_to_cpuid_lock(map->vpe, flags);
+	} else {
+		/* Physical LPIs are already locked via the irq_desc lock */
+		struct its_device *its_dev = irq_data_get_irq_chip_data(d);
+		cpu = its_dev->event_map.col_map[its_get_event_id(d)];
+		/* Keep GCC quiet... */
+		*flags = 0;
+	}
+
+	return cpu;
+}
+
+static void irq_to_cpuid_unlock(struct irq_data *d, unsigned long flags)
+{
+	struct its_vlpi_map *map = get_vlpi_map(d);
+
+	if (map)
+		vpe_to_cpuid_unlock(map->vpe, flags);
+}
+
 static struct its_collection *valid_col(struct its_collection *col)
 {
 	if (WARN_ON_ONCE(col->target_address & GENMASK_ULL(15, 0)))
@@ -297,6 +392,19 @@
 			u16 seq_num;
 			u16 its_list;
 		} its_vmovp_cmd;
+
+		struct {
+			struct its_vpe *vpe;
+		} its_invdb_cmd;
+
+		struct {
+			struct its_vpe *vpe;
+			u8 sgi;
+			u8 priority;
+			bool enable;
+			bool group;
+			bool clear;
+		} its_vsgi_cmd;
 	};
 };
 
@@ -304,7 +412,10 @@
  * The ITS command block, which is what the ITS actually parses.
  */
 struct its_cmd_block {
-	u64	raw_cmd[4];
+	union {
+		u64	raw_cmd[4];
+		__le64	raw_cmd_le[4];
+	};
 };
 
 #define ITS_CMD_QUEUE_SZ		SZ_64K
@@ -410,13 +521,70 @@
 	its_mask_encode(&cmd->raw_cmd[3], vpt_size, 4, 0);
 }
 
+static void its_encode_vconf_addr(struct its_cmd_block *cmd, u64 vconf_pa)
+{
+	its_mask_encode(&cmd->raw_cmd[0], vconf_pa >> 16, 51, 16);
+}
+
+static void its_encode_alloc(struct its_cmd_block *cmd, bool alloc)
+{
+	its_mask_encode(&cmd->raw_cmd[0], alloc, 8, 8);
+}
+
+static void its_encode_ptz(struct its_cmd_block *cmd, bool ptz)
+{
+	its_mask_encode(&cmd->raw_cmd[0], ptz, 9, 9);
+}
+
+static void its_encode_vmapp_default_db(struct its_cmd_block *cmd,
+					u32 vpe_db_lpi)
+{
+	its_mask_encode(&cmd->raw_cmd[1], vpe_db_lpi, 31, 0);
+}
+
+static void its_encode_vmovp_default_db(struct its_cmd_block *cmd,
+					u32 vpe_db_lpi)
+{
+	its_mask_encode(&cmd->raw_cmd[3], vpe_db_lpi, 31, 0);
+}
+
+static void its_encode_db(struct its_cmd_block *cmd, bool db)
+{
+	its_mask_encode(&cmd->raw_cmd[2], db, 63, 63);
+}
+
+static void its_encode_sgi_intid(struct its_cmd_block *cmd, u8 sgi)
+{
+	its_mask_encode(&cmd->raw_cmd[0], sgi, 35, 32);
+}
+
+static void its_encode_sgi_priority(struct its_cmd_block *cmd, u8 prio)
+{
+	its_mask_encode(&cmd->raw_cmd[0], prio >> 4, 23, 20);
+}
+
+static void its_encode_sgi_group(struct its_cmd_block *cmd, bool grp)
+{
+	its_mask_encode(&cmd->raw_cmd[0], grp, 10, 10);
+}
+
+static void its_encode_sgi_clear(struct its_cmd_block *cmd, bool clr)
+{
+	its_mask_encode(&cmd->raw_cmd[0], clr, 9, 9);
+}
+
+static void its_encode_sgi_enable(struct its_cmd_block *cmd, bool en)
+{
+	its_mask_encode(&cmd->raw_cmd[0], en, 8, 8);
+}
+
 static inline void its_fixup_cmd(struct its_cmd_block *cmd)
 {
 	/* Let's fixup BE commands */
-	cmd->raw_cmd[0] = cpu_to_le64(cmd->raw_cmd[0]);
-	cmd->raw_cmd[1] = cpu_to_le64(cmd->raw_cmd[1]);
-	cmd->raw_cmd[2] = cpu_to_le64(cmd->raw_cmd[2]);
-	cmd->raw_cmd[3] = cpu_to_le64(cmd->raw_cmd[3]);
+	cmd->raw_cmd_le[0] = cpu_to_le64(cmd->raw_cmd[0]);
+	cmd->raw_cmd_le[1] = cpu_to_le64(cmd->raw_cmd[1]);
+	cmd->raw_cmd_le[2] = cpu_to_le64(cmd->raw_cmd[2]);
+	cmd->raw_cmd_le[3] = cpu_to_le64(cmd->raw_cmd[3]);
 }
 
 static struct its_collection *its_build_mapd_cmd(struct its_node *its,
@@ -574,7 +742,7 @@
 
 	its_fixup_cmd(cmd);
 
-	return NULL;
+	return desc->its_invall_cmd.col;
 }
 
 static struct its_vpe *its_build_vinvall_cmd(struct its_node *its,
@@ -593,19 +761,45 @@
 					   struct its_cmd_block *cmd,
 					   struct its_cmd_desc *desc)
 {
-	unsigned long vpt_addr;
+	unsigned long vpt_addr, vconf_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;
+	bool alloc;
 
 	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);
+
+	if (!desc->its_vmapp_cmd.valid) {
+		if (is_v4_1(its)) {
+			alloc = !atomic_dec_return(&desc->its_vmapp_cmd.vpe->vmapp_count);
+			its_encode_alloc(cmd, alloc);
+		}
+
+		goto out;
+	}
+
+	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_target(cmd, target);
 	its_encode_vpt_addr(cmd, vpt_addr);
 	its_encode_vpt_size(cmd, LPI_NRBITS - 1);
 
+	if (!is_v4_1(its))
+		goto out;
+
+	vconf_addr = virt_to_phys(page_address(desc->its_vmapp_cmd.vpe->its_vm->vprop_page));
+
+	alloc = !atomic_fetch_inc(&desc->its_vmapp_cmd.vpe->vmapp_count);
+
+	its_encode_alloc(cmd, alloc);
+
+	/* We can only signal PTZ when alloc==1. Why do we have two bits? */
+	its_encode_ptz(cmd, alloc);
+	its_encode_vconf_addr(cmd, vconf_addr);
+	its_encode_vmapp_default_db(cmd, desc->its_vmapp_cmd.vpe->vpe_db_lpi);
+
+out:
 	its_fixup_cmd(cmd);
 
 	return valid_vpe(its, desc->its_vmapp_cmd.vpe);
@@ -617,7 +811,7 @@
 {
 	u32 db;
 
-	if (desc->its_vmapti_cmd.db_enabled)
+	if (!is_v4_1(its) && desc->its_vmapti_cmd.db_enabled)
 		db = desc->its_vmapti_cmd.vpe->vpe_db_lpi;
 	else
 		db = 1023;
@@ -640,7 +834,7 @@
 {
 	u32 db;
 
-	if (desc->its_vmovi_cmd.db_enabled)
+	if (!is_v4_1(its) && desc->its_vmovi_cmd.db_enabled)
 		db = desc->its_vmovi_cmd.vpe->vpe_db_lpi;
 	else
 		db = 1023;
@@ -670,11 +864,105 @@
 	its_encode_vpeid(cmd, desc->its_vmovp_cmd.vpe->vpe_id);
 	its_encode_target(cmd, target);
 
+	if (is_v4_1(its)) {
+		its_encode_db(cmd, true);
+		its_encode_vmovp_default_db(cmd, desc->its_vmovp_cmd.vpe->vpe_db_lpi);
+	}
+
 	its_fixup_cmd(cmd);
 
 	return valid_vpe(its, desc->its_vmovp_cmd.vpe);
 }
 
+static struct its_vpe *its_build_vinv_cmd(struct its_node *its,
+					  struct its_cmd_block *cmd,
+					  struct its_cmd_desc *desc)
+{
+	struct its_vlpi_map *map;
+
+	map = dev_event_to_vlpi_map(desc->its_inv_cmd.dev,
+				    desc->its_inv_cmd.event_id);
+
+	its_encode_cmd(cmd, GITS_CMD_INV);
+	its_encode_devid(cmd, desc->its_inv_cmd.dev->device_id);
+	its_encode_event_id(cmd, desc->its_inv_cmd.event_id);
+
+	its_fixup_cmd(cmd);
+
+	return valid_vpe(its, map->vpe);
+}
+
+static struct its_vpe *its_build_vint_cmd(struct its_node *its,
+					  struct its_cmd_block *cmd,
+					  struct its_cmd_desc *desc)
+{
+	struct its_vlpi_map *map;
+
+	map = dev_event_to_vlpi_map(desc->its_int_cmd.dev,
+				    desc->its_int_cmd.event_id);
+
+	its_encode_cmd(cmd, GITS_CMD_INT);
+	its_encode_devid(cmd, desc->its_int_cmd.dev->device_id);
+	its_encode_event_id(cmd, desc->its_int_cmd.event_id);
+
+	its_fixup_cmd(cmd);
+
+	return valid_vpe(its, map->vpe);
+}
+
+static struct its_vpe *its_build_vclear_cmd(struct its_node *its,
+					    struct its_cmd_block *cmd,
+					    struct its_cmd_desc *desc)
+{
+	struct its_vlpi_map *map;
+
+	map = dev_event_to_vlpi_map(desc->its_clear_cmd.dev,
+				    desc->its_clear_cmd.event_id);
+
+	its_encode_cmd(cmd, GITS_CMD_CLEAR);
+	its_encode_devid(cmd, desc->its_clear_cmd.dev->device_id);
+	its_encode_event_id(cmd, desc->its_clear_cmd.event_id);
+
+	its_fixup_cmd(cmd);
+
+	return valid_vpe(its, map->vpe);
+}
+
+static struct its_vpe *its_build_invdb_cmd(struct its_node *its,
+					   struct its_cmd_block *cmd,
+					   struct its_cmd_desc *desc)
+{
+	if (WARN_ON(!is_v4_1(its)))
+		return NULL;
+
+	its_encode_cmd(cmd, GITS_CMD_INVDB);
+	its_encode_vpeid(cmd, desc->its_invdb_cmd.vpe->vpe_id);
+
+	its_fixup_cmd(cmd);
+
+	return valid_vpe(its, desc->its_invdb_cmd.vpe);
+}
+
+static struct its_vpe *its_build_vsgi_cmd(struct its_node *its,
+					  struct its_cmd_block *cmd,
+					  struct its_cmd_desc *desc)
+{
+	if (WARN_ON(!is_v4_1(its)))
+		return NULL;
+
+	its_encode_cmd(cmd, GITS_CMD_VSGI);
+	its_encode_vpeid(cmd, desc->its_vsgi_cmd.vpe->vpe_id);
+	its_encode_sgi_intid(cmd, desc->its_vsgi_cmd.sgi);
+	its_encode_sgi_priority(cmd, desc->its_vsgi_cmd.priority);
+	its_encode_sgi_group(cmd, desc->its_vsgi_cmd.group);
+	its_encode_sgi_clear(cmd, desc->its_vsgi_cmd.clear);
+	its_encode_sgi_enable(cmd, desc->its_vsgi_cmd.enable);
+
+	its_fixup_cmd(cmd);
+
+	return valid_vpe(its, desc->its_vsgi_cmd.vpe);
+}
+
 static u64 its_cmd_ptr_to_offset(struct its_node *its,
 				 struct its_cmd_block *ptr)
 {
@@ -952,7 +1240,7 @@
 
 static void its_send_vmapti(struct its_device *dev, u32 id)
 {
-	struct its_vlpi_map *map = &dev->event_map.vlpi_maps[id];
+	struct its_vlpi_map *map = dev_event_to_vlpi_map(dev, id);
 	struct its_cmd_desc desc;
 
 	desc.its_vmapti_cmd.vpe = map->vpe;
@@ -966,7 +1254,7 @@
 
 static void its_send_vmovi(struct its_device *dev, u32 id)
 {
-	struct its_vlpi_map *map = &dev->event_map.vlpi_maps[id];
+	struct its_vlpi_map *map = dev_event_to_vlpi_map(dev, id);
 	struct its_cmd_desc desc;
 
 	desc.its_vmovi_cmd.vpe = map->vpe;
@@ -1020,10 +1308,10 @@
 
 	/* Emit VMOVPs */
 	list_for_each_entry(its, &its_nodes, entry) {
-		if (!its->is_v4)
+		if (!is_v4(its))
 			continue;
 
-		if (!vpe->its_vm->vlpi_count[its->list_nr])
+		if (!require_its_list_vmovp(vpe->its_vm, its))
 			continue;
 
 		desc.its_vmovp_cmd.col = &its->collections[col_id];
@@ -1041,29 +1329,68 @@
 	its_send_single_vcommand(its, its_build_vinvall_cmd, &desc);
 }
 
+static void its_send_vinv(struct its_device *dev, u32 event_id)
+{
+	struct its_cmd_desc desc;
+
+	/*
+	 * There is no real VINV command. This is just a normal INV,
+	 * with a VSYNC instead of a SYNC.
+	 */
+	desc.its_inv_cmd.dev = dev;
+	desc.its_inv_cmd.event_id = event_id;
+
+	its_send_single_vcommand(dev->its, its_build_vinv_cmd, &desc);
+}
+
+static void its_send_vint(struct its_device *dev, u32 event_id)
+{
+	struct its_cmd_desc desc;
+
+	/*
+	 * There is no real VINT command. This is just a normal INT,
+	 * with a VSYNC instead of a SYNC.
+	 */
+	desc.its_int_cmd.dev = dev;
+	desc.its_int_cmd.event_id = event_id;
+
+	its_send_single_vcommand(dev->its, its_build_vint_cmd, &desc);
+}
+
+static void its_send_vclear(struct its_device *dev, u32 event_id)
+{
+	struct its_cmd_desc desc;
+
+	/*
+	 * There is no real VCLEAR command. This is just a normal CLEAR,
+	 * with a VSYNC instead of a SYNC.
+	 */
+	desc.its_clear_cmd.dev = dev;
+	desc.its_clear_cmd.event_id = event_id;
+
+	its_send_single_vcommand(dev->its, its_build_vclear_cmd, &desc);
+}
+
+static void its_send_invdb(struct its_node *its, struct its_vpe *vpe)
+{
+	struct its_cmd_desc desc;
+
+	desc.its_invdb_cmd.vpe = vpe;
+	its_send_single_vcommand(its, its_build_invdb_cmd, &desc);
+}
+
 /*
  * irqchip functions - assumes MSI, mostly.
  */
-
-static inline u32 its_get_event_id(struct irq_data *d)
-{
-	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
-	return d->hwirq - its_dev->event_map.lpi_base;
-}
-
 static void lpi_write_config(struct irq_data *d, u8 clr, u8 set)
 {
+	struct its_vlpi_map *map = get_vlpi_map(d);
 	irq_hw_number_t hwirq;
 	void *va;
 	u8 *cfg;
 
-	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;
-
-		va = page_address(its_dev->event_map.vm->vprop_page);
-		map = &its_dev->event_map.vlpi_maps[event];
+	if (map) {
+		va = page_address(map->vm->vprop_page);
 		hwirq = map->vintid;
 
 		/* Remember the updated property */
@@ -1089,23 +1416,76 @@
 		dsb(ishst);
 }
 
+static void wait_for_syncr(void __iomem *rdbase)
+{
+	while (readl_relaxed(rdbase + GICR_SYNCR) & 1)
+		cpu_relax();
+}
+
+static void direct_lpi_inv(struct irq_data *d)
+{
+	struct its_vlpi_map *map = get_vlpi_map(d);
+	void __iomem *rdbase;
+	unsigned long flags;
+	u64 val;
+	int cpu;
+
+	if (map) {
+		struct its_device *its_dev = irq_data_get_irq_chip_data(d);
+
+		WARN_ON(!is_v4_1(its_dev->its));
+
+		val  = GICR_INVLPIR_V;
+		val |= FIELD_PREP(GICR_INVLPIR_VPEID, map->vpe->vpe_id);
+		val |= FIELD_PREP(GICR_INVLPIR_INTID, map->vintid);
+	} else {
+		val = d->hwirq;
+	}
+
+	/* Target the redistributor this LPI is currently routed to */
+	cpu = irq_to_cpuid_lock(d, &flags);
+	raw_spin_lock(&gic_data_rdist_cpu(cpu)->rd_lock);
+	rdbase = per_cpu_ptr(gic_rdists->rdist, cpu)->rd_base;
+	gic_write_lpir(val, rdbase + GICR_INVLPIR);
+
+	wait_for_syncr(rdbase);
+	raw_spin_unlock(&gic_data_rdist_cpu(cpu)->rd_lock);
+	irq_to_cpuid_unlock(d, flags);
+}
+
 static void lpi_update_config(struct irq_data *d, u8 clr, u8 set)
 {
 	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
 
 	lpi_write_config(d, clr, set);
-	its_send_inv(its_dev, its_get_event_id(d));
+	if (gic_rdists->has_direct_lpi &&
+	    (is_v4_1(its_dev->its) || !irqd_is_forwarded_to_vcpu(d)))
+		direct_lpi_inv(d);
+	else if (!irqd_is_forwarded_to_vcpu(d))
+		its_send_inv(its_dev, its_get_event_id(d));
+	else
+		its_send_vinv(its_dev, its_get_event_id(d));
 }
 
 static void its_vlpi_set_doorbell(struct irq_data *d, bool enable)
 {
 	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
 	u32 event = its_get_event_id(d);
+	struct its_vlpi_map *map;
 
-	if (its_dev->event_map.vlpi_maps[event].db_enabled == enable)
+	/*
+	 * GICv4.1 does away with the per-LPI nonsense, nothing to do
+	 * here.
+	 */
+	if (is_v4_1(its_dev->its))
 		return;
 
-	its_dev->event_map.vlpi_maps[event].db_enabled = enable;
+	map = dev_event_to_vlpi_map(its_dev, event);
+
+	if (map->db_enabled == enable)
+		return;
+
+	map->db_enabled = enable;
 
 	/*
 	 * More fun with the architecture:
@@ -1136,42 +1516,159 @@
 	lpi_update_config(d, 0, LPI_PROP_ENABLED);
 }
 
+static __maybe_unused u32 its_read_lpi_count(struct irq_data *d, int cpu)
+{
+	if (irqd_affinity_is_managed(d))
+		return atomic_read(&per_cpu_ptr(&cpu_lpi_count, cpu)->managed);
+
+	return atomic_read(&per_cpu_ptr(&cpu_lpi_count, cpu)->unmanaged);
+}
+
+static void its_inc_lpi_count(struct irq_data *d, int cpu)
+{
+	if (irqd_affinity_is_managed(d))
+		atomic_inc(&per_cpu_ptr(&cpu_lpi_count, cpu)->managed);
+	else
+		atomic_inc(&per_cpu_ptr(&cpu_lpi_count, cpu)->unmanaged);
+}
+
+static void its_dec_lpi_count(struct irq_data *d, int cpu)
+{
+	if (irqd_affinity_is_managed(d))
+		atomic_dec(&per_cpu_ptr(&cpu_lpi_count, cpu)->managed);
+	else
+		atomic_dec(&per_cpu_ptr(&cpu_lpi_count, cpu)->unmanaged);
+}
+
+static unsigned int cpumask_pick_least_loaded(struct irq_data *d,
+					      const struct cpumask *cpu_mask)
+{
+	unsigned int cpu = nr_cpu_ids, tmp;
+	int count = S32_MAX;
+
+	for_each_cpu(tmp, cpu_mask) {
+		int this_count = its_read_lpi_count(d, tmp);
+		if (this_count < count) {
+			cpu = tmp;
+		        count = this_count;
+		}
+	}
+
+	return cpu;
+}
+
+/*
+ * As suggested by Thomas Gleixner in:
+ * https://lore.kernel.org/r/87h80q2aoc.fsf@nanos.tec.linutronix.de
+ */
+static int its_select_cpu(struct irq_data *d,
+			  const struct cpumask *aff_mask)
+{
+	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
+	cpumask_var_t tmpmask;
+	int cpu, node;
+
+	if (!alloc_cpumask_var(&tmpmask, GFP_ATOMIC))
+		return -ENOMEM;
+
+	node = its_dev->its->numa_node;
+
+	if (!irqd_affinity_is_managed(d)) {
+		/* First try the NUMA node */
+		if (node != NUMA_NO_NODE) {
+			/*
+			 * Try the intersection of the affinity mask and the
+			 * node mask (and the online mask, just to be safe).
+			 */
+			cpumask_and(tmpmask, cpumask_of_node(node), aff_mask);
+			cpumask_and(tmpmask, tmpmask, cpu_online_mask);
+
+			/*
+			 * Ideally, we would check if the mask is empty, and
+			 * try again on the full node here.
+			 *
+			 * But it turns out that the way ACPI describes the
+			 * affinity for ITSs only deals about memory, and
+			 * not target CPUs, so it cannot describe a single
+			 * ITS placed next to two NUMA nodes.
+			 *
+			 * Instead, just fallback on the online mask. This
+			 * diverges from Thomas' suggestion above.
+			 */
+			cpu = cpumask_pick_least_loaded(d, tmpmask);
+			if (cpu < nr_cpu_ids)
+				goto out;
+
+			/* If we can't cross sockets, give up */
+			if ((its_dev->its->flags & ITS_FLAGS_WORKAROUND_CAVIUM_23144))
+				goto out;
+
+			/* If the above failed, expand the search */
+		}
+
+		/* Try the intersection of the affinity and online masks */
+		cpumask_and(tmpmask, aff_mask, cpu_online_mask);
+
+		/* If that doesn't fly, the online mask is the last resort */
+		if (cpumask_empty(tmpmask))
+			cpumask_copy(tmpmask, cpu_online_mask);
+
+		cpu = cpumask_pick_least_loaded(d, tmpmask);
+	} else {
+		cpumask_and(tmpmask, irq_data_get_affinity_mask(d), cpu_online_mask);
+
+		/* If we cannot cross sockets, limit the search to that node */
+		if ((its_dev->its->flags & ITS_FLAGS_WORKAROUND_CAVIUM_23144) &&
+		    node != NUMA_NO_NODE)
+			cpumask_and(tmpmask, tmpmask, cpumask_of_node(node));
+
+		cpu = cpumask_pick_least_loaded(d, tmpmask);
+	}
+out:
+	free_cpumask_var(tmpmask);
+
+	pr_debug("IRQ%d -> %*pbl CPU%d\n", d->irq, cpumask_pr_args(aff_mask), cpu);
+	return cpu;
+}
+
 static int its_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 			    bool force)
 {
-	unsigned int cpu;
-	const struct cpumask *cpu_mask = cpu_online_mask;
 	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
 	struct its_collection *target_col;
 	u32 id = its_get_event_id(d);
+	int cpu, prev_cpu;
 
 	/* A forwarded interrupt should use irq_set_vcpu_affinity */
 	if (irqd_is_forwarded_to_vcpu(d))
 		return -EINVAL;
 
-       /* lpi cannot be routed to a redistributor that is on a foreign node */
-	if (its_dev->its->flags & ITS_FLAGS_WORKAROUND_CAVIUM_23144) {
-		if (its_dev->its->numa_node >= 0) {
-			cpu_mask = cpumask_of_node(its_dev->its->numa_node);
-			if (!cpumask_intersects(mask_val, cpu_mask))
-				return -EINVAL;
-		}
-	}
+	prev_cpu = its_dev->event_map.col_map[id];
+	its_dec_lpi_count(d, prev_cpu);
 
-	cpu = cpumask_any_and(mask_val, cpu_mask);
+	if (!force)
+		cpu = its_select_cpu(d, mask_val);
+	else
+		cpu = cpumask_pick_least_loaded(d, mask_val);
 
-	if (cpu >= nr_cpu_ids)
-		return -EINVAL;
+	if (cpu < 0 || cpu >= nr_cpu_ids)
+		goto err;
 
 	/* don't set the affinity when the target cpu is same as current one */
-	if (cpu != its_dev->event_map.col_map[id]) {
+	if (cpu != prev_cpu) {
 		target_col = &its_dev->its->collections[cpu];
 		its_send_movi(its_dev, target_col, id);
 		its_dev->event_map.col_map[id] = cpu;
 		irq_data_update_effective_affinity(d, cpumask_of(cpu));
 	}
 
+	its_inc_lpi_count(d, cpu);
+
 	return IRQ_SET_MASK_OK_DONE;
+
+err:
+	its_inc_lpi_count(d, prev_cpu);
+	return -EINVAL;
 }
 
 static u64 its_irq_get_msi_base(struct its_device *its_dev)
@@ -1207,20 +1704,51 @@
 	if (which != IRQCHIP_STATE_PENDING)
 		return -EINVAL;
 
-	if (state)
-		its_send_int(its_dev, event);
-	else
-		its_send_clear(its_dev, event);
+	if (irqd_is_forwarded_to_vcpu(d)) {
+		if (state)
+			its_send_vint(its_dev, event);
+		else
+			its_send_vclear(its_dev, event);
+	} else {
+		if (state)
+			its_send_int(its_dev, event);
+		else
+			its_send_clear(its_dev, event);
+	}
 
 	return 0;
 }
 
+static int its_irq_retrigger(struct irq_data *d)
+{
+	return !its_irq_set_irqchip_state(d, IRQCHIP_STATE_PENDING, true);
+}
+
+/*
+ * Two favourable cases:
+ *
+ * (a) Either we have a GICv4.1, and all vPEs have to be mapped at all times
+ *     for vSGI delivery
+ *
+ * (b) Or the ITSs do not use a list map, meaning that VMOVP is cheap enough
+ *     and we're better off mapping all VPEs always
+ *
+ * If neither (a) nor (b) is true, then we map vPEs on demand.
+ *
+ */
+static bool gic_requires_eager_mapping(void)
+{
+	if (!its_list_map || gic_rdists->has_rvpeid)
+		return true;
+
+	return false;
+}
+
 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)
+	if (gic_requires_eager_mapping())
 		return;
 
 	raw_spin_lock_irqsave(&vmovp_lock, flags);
@@ -1254,7 +1782,7 @@
 	unsigned long flags;
 
 	/* Not using the ITS list? Everything is always mapped. */
-	if (!its_list_map)
+	if (gic_requires_eager_mapping())
 		return;
 
 	raw_spin_lock_irqsave(&vmovp_lock, flags);
@@ -1278,13 +1806,13 @@
 	if (!info->map)
 		return -EINVAL;
 
-	mutex_lock(&its_dev->event_map.vlpi_lock);
+	raw_spin_lock(&its_dev->event_map.vlpi_lock);
 
 	if (!its_dev->event_map.vm) {
 		struct its_vlpi_map *maps;
 
 		maps = kcalloc(its_dev->event_map.nr_lpis, sizeof(*maps),
-			       GFP_KERNEL);
+			       GFP_ATOMIC);
 		if (!maps) {
 			ret = -ENOMEM;
 			goto out;
@@ -1327,29 +1855,30 @@
 	}
 
 out:
-	mutex_unlock(&its_dev->event_map.vlpi_lock);
+	raw_spin_unlock(&its_dev->event_map.vlpi_lock);
 	return ret;
 }
 
 static int its_vlpi_get(struct irq_data *d, struct its_cmd_info *info)
 {
 	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
-	u32 event = its_get_event_id(d);
+	struct its_vlpi_map *map;
 	int ret = 0;
 
-	mutex_lock(&its_dev->event_map.vlpi_lock);
+	raw_spin_lock(&its_dev->event_map.vlpi_lock);
 
-	if (!its_dev->event_map.vm ||
-	    !its_dev->event_map.vlpi_maps[event].vm) {
+	map = get_vlpi_map(d);
+
+	if (!its_dev->event_map.vm || !map) {
 		ret = -EINVAL;
 		goto out;
 	}
 
 	/* Copy our mapping information to the incoming request */
-	*info->map = its_dev->event_map.vlpi_maps[event];
+	*info->map = *map;
 
 out:
-	mutex_unlock(&its_dev->event_map.vlpi_lock);
+	raw_spin_unlock(&its_dev->event_map.vlpi_lock);
 	return ret;
 }
 
@@ -1359,7 +1888,7 @@
 	u32 event = its_get_event_id(d);
 	int ret = 0;
 
-	mutex_lock(&its_dev->event_map.vlpi_lock);
+	raw_spin_lock(&its_dev->event_map.vlpi_lock);
 
 	if (!its_dev->event_map.vm || !irqd_is_forwarded_to_vcpu(d)) {
 		ret = -EINVAL;
@@ -1389,7 +1918,7 @@
 	}
 
 out:
-	mutex_unlock(&its_dev->event_map.vlpi_lock);
+	raw_spin_unlock(&its_dev->event_map.vlpi_lock);
 	return ret;
 }
 
@@ -1415,7 +1944,7 @@
 	struct its_cmd_info *info = vcpu_info;
 
 	/* Need a v4 ITS */
-	if (!its_dev->its->is_v4)
+	if (!is_v4(its_dev->its))
 		return -EINVAL;
 
 	/* Unmap request? */
@@ -1446,6 +1975,7 @@
 	.irq_set_affinity	= its_set_affinity,
 	.irq_compose_msi_msg	= its_irq_compose_msi_msg,
 	.irq_set_irqchip_state	= its_irq_set_irqchip_state,
+	.irq_retrigger		= its_irq_retrigger,
 	.irq_set_vcpu_affinity	= its_irq_set_vcpu_affinity,
 };
 
@@ -1667,7 +2197,7 @@
 
 	addr_end = addr + size - 1;
 
-	for_each_reserved_mem_region(i, &start, &end) {
+	for_each_reserved_mem_range(i, &start, &end) {
 		if (addr >= start && addr_end <= end)
 			return true;
 	}
@@ -1751,18 +2281,17 @@
 }
 
 static int its_setup_baser(struct its_node *its, struct its_baser *baser,
-			   u64 cache, u64 shr, u32 psz, u32 order,
-			   bool indirect)
+			   u64 cache, u64 shr, u32 order, bool indirect)
 {
 	u64 val = its_read_baser(its, baser);
 	u64 esz = GITS_BASER_ENTRY_SIZE(val);
 	u64 type = GITS_BASER_TYPE(val);
 	u64 baser_phys, tmp;
-	u32 alloc_pages;
+	u32 alloc_pages, psz;
 	struct page *page;
 	void *base;
 
-retry_alloc_baser:
+	psz = baser->psz;
 	alloc_pages = (PAGE_ORDER_TO_SIZE(order) / psz);
 	if (alloc_pages > GITS_BASER_PAGES_MAX) {
 		pr_warn("ITS@%pa: %s too large, reduce ITS pages %u->%u\n",
@@ -1835,25 +2364,6 @@
 		goto retry_baser;
 	}
 
-	if ((val ^ tmp) & GITS_BASER_PAGE_SIZE_MASK) {
-		/*
-		 * Page size didn't stick. Let's try a smaller
-		 * size and retry. If we reach 4K, then
-		 * something is horribly wrong...
-		 */
-		free_pages((unsigned long)base, order);
-		baser->base = NULL;
-
-		switch (psz) {
-		case SZ_16K:
-			psz = SZ_4K;
-			goto retry_alloc_baser;
-		case SZ_64K:
-			psz = SZ_16K;
-			goto retry_alloc_baser;
-		}
-	}
-
 	if (val != tmp) {
 		pr_err("ITS@%pa: %s doesn't stick: %llx %llx\n",
 		       &its->phys_base, its_base_type_string[type],
@@ -1879,13 +2389,14 @@
 
 static bool its_parse_indirect_baser(struct its_node *its,
 				     struct its_baser *baser,
-				     u32 psz, u32 *order, u32 ids)
+				     u32 *order, u32 ids)
 {
 	u64 tmp = its_read_baser(its, baser);
 	u64 type = GITS_BASER_TYPE(tmp);
 	u64 esz = GITS_BASER_ENTRY_SIZE(tmp);
 	u64 val = GITS_BASER_InnerShareable | GITS_BASER_RaWaWb;
 	u32 new_order = *order;
+	u32 psz = baser->psz;
 	bool indirect = false;
 
 	/* No need to enable Indirection if memory requirement < (psz*2)bytes */
@@ -1921,9 +2432,9 @@
 	if (new_order >= MAX_ORDER) {
 		new_order = MAX_ORDER - 1;
 		ids = ilog2(PAGE_ORDER_TO_SIZE(new_order) / (int)esz);
-		pr_warn("ITS@%pa: %s Table too large, reduce ids %u->%u\n",
+		pr_warn("ITS@%pa: %s Table too large, reduce ids %llu->%u\n",
 			&its->phys_base, its_base_type_string[type],
-			its->device_ids, ids);
+			device_ids(its), ids);
 	}
 
 	*order = new_order;
@@ -1931,6 +2442,65 @@
 	return indirect;
 }
 
+static u32 compute_common_aff(u64 val)
+{
+	u32 aff, clpiaff;
+
+	aff = FIELD_GET(GICR_TYPER_AFFINITY, val);
+	clpiaff = FIELD_GET(GICR_TYPER_COMMON_LPI_AFF, val);
+
+	return aff & ~(GENMASK(31, 0) >> (clpiaff * 8));
+}
+
+static u32 compute_its_aff(struct its_node *its)
+{
+	u64 val;
+	u32 svpet;
+
+	/*
+	 * Reencode the ITS SVPET and MPIDR as a GICR_TYPER, and compute
+	 * the resulting affinity. We then use that to see if this match
+	 * our own affinity.
+	 */
+	svpet = FIELD_GET(GITS_TYPER_SVPET, its->typer);
+	val  = FIELD_PREP(GICR_TYPER_COMMON_LPI_AFF, svpet);
+	val |= FIELD_PREP(GICR_TYPER_AFFINITY, its->mpidr);
+	return compute_common_aff(val);
+}
+
+static struct its_node *find_sibling_its(struct its_node *cur_its)
+{
+	struct its_node *its;
+	u32 aff;
+
+	if (!FIELD_GET(GITS_TYPER_SVPET, cur_its->typer))
+		return NULL;
+
+	aff = compute_its_aff(cur_its);
+
+	list_for_each_entry(its, &its_nodes, entry) {
+		u64 baser;
+
+		if (!is_v4_1(its) || its == cur_its)
+			continue;
+
+		if (!FIELD_GET(GITS_TYPER_SVPET, its->typer))
+			continue;
+
+		if (aff != compute_its_aff(its))
+			continue;
+
+		/* GICv4.1 guarantees that the vPE table is GITS_BASER2 */
+		baser = its->tables[2].val;
+		if (!(baser & GITS_BASER_VALID))
+			continue;
+
+		return its;
+	}
+
+	return NULL;
+}
+
 static void its_free_tables(struct its_node *its)
 {
 	int i;
@@ -1944,11 +2514,58 @@
 	}
 }
 
+static int its_probe_baser_psz(struct its_node *its, struct its_baser *baser)
+{
+	u64 psz = SZ_64K;
+
+	while (psz) {
+		u64 val, gpsz;
+
+		val = its_read_baser(its, baser);
+		val &= ~GITS_BASER_PAGE_SIZE_MASK;
+
+		switch (psz) {
+		case SZ_64K:
+			gpsz = GITS_BASER_PAGE_SIZE_64K;
+			break;
+		case SZ_16K:
+			gpsz = GITS_BASER_PAGE_SIZE_16K;
+			break;
+		case SZ_4K:
+		default:
+			gpsz = GITS_BASER_PAGE_SIZE_4K;
+			break;
+		}
+
+		gpsz >>= GITS_BASER_PAGE_SIZE_SHIFT;
+
+		val |= FIELD_PREP(GITS_BASER_PAGE_SIZE_MASK, gpsz);
+		its_write_baser(its, baser, val);
+
+		if (FIELD_GET(GITS_BASER_PAGE_SIZE_MASK, baser->val) == gpsz)
+			break;
+
+		switch (psz) {
+		case SZ_64K:
+			psz = SZ_16K;
+			break;
+		case SZ_16K:
+			psz = SZ_4K;
+			break;
+		case SZ_4K:
+		default:
+			return -1;
+		}
+	}
+
+	baser->psz = psz;
+	return 0;
+}
+
 static int its_alloc_tables(struct its_node *its)
 {
 	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)
@@ -1959,34 +2576,49 @@
 		struct its_baser *baser = its->tables + i;
 		u64 val = its_read_baser(its, baser);
 		u64 type = GITS_BASER_TYPE(val);
-		u32 order = get_order(psz);
 		bool indirect = false;
+		u32 order;
 
-		switch (type) {
-		case GITS_BASER_TYPE_NONE:
+		if (type == GITS_BASER_TYPE_NONE)
 			continue;
 
+		if (its_probe_baser_psz(its, baser)) {
+			its_free_tables(its);
+			return -ENXIO;
+		}
+
+		order = get_order(baser->psz);
+
+		switch (type) {
 		case GITS_BASER_TYPE_DEVICE:
-			indirect = its_parse_indirect_baser(its, baser,
-							    psz, &order,
-							    its->device_ids);
+			indirect = its_parse_indirect_baser(its, baser, &order,
+							    device_ids(its));
 			break;
 
 		case GITS_BASER_TYPE_VCPU:
-			indirect = its_parse_indirect_baser(its, baser,
-							    psz, &order,
+			if (is_v4_1(its)) {
+				struct its_node *sibling;
+
+				WARN_ON(i != 2);
+				if ((sibling = find_sibling_its(its))) {
+					*baser = sibling->tables[2];
+					its_write_baser(its, baser, baser->val);
+					continue;
+				}
+			}
+
+			indirect = its_parse_indirect_baser(its, baser, &order,
 							    ITS_MAX_VPEID_BITS);
 			break;
 		}
 
-		err = its_setup_baser(its, baser, cache, shr, psz, order, indirect);
+		err = its_setup_baser(its, baser, cache, shr, order, indirect);
 		if (err < 0) {
 			its_free_tables(its);
 			return err;
 		}
 
 		/* Update settings which will be used for next BASERn */
-		psz = baser->psz;
 		cache = baser->val & GITS_BASER_CACHEABILITY_MASK;
 		shr = baser->val & GITS_BASER_SHAREABILITY_MASK;
 	}
@@ -1994,6 +2626,291 @@
 	return 0;
 }
 
+static u64 inherit_vpe_l1_table_from_its(void)
+{
+	struct its_node *its;
+	u64 val;
+	u32 aff;
+
+	val = gic_read_typer(gic_data_rdist_rd_base() + GICR_TYPER);
+	aff = compute_common_aff(val);
+
+	list_for_each_entry(its, &its_nodes, entry) {
+		u64 baser, addr;
+
+		if (!is_v4_1(its))
+			continue;
+
+		if (!FIELD_GET(GITS_TYPER_SVPET, its->typer))
+			continue;
+
+		if (aff != compute_its_aff(its))
+			continue;
+
+		/* GICv4.1 guarantees that the vPE table is GITS_BASER2 */
+		baser = its->tables[2].val;
+		if (!(baser & GITS_BASER_VALID))
+			continue;
+
+		/* We have a winner! */
+		gic_data_rdist()->vpe_l1_base = its->tables[2].base;
+
+		val  = GICR_VPROPBASER_4_1_VALID;
+		if (baser & GITS_BASER_INDIRECT)
+			val |= GICR_VPROPBASER_4_1_INDIRECT;
+		val |= FIELD_PREP(GICR_VPROPBASER_4_1_PAGE_SIZE,
+				  FIELD_GET(GITS_BASER_PAGE_SIZE_MASK, baser));
+		switch (FIELD_GET(GITS_BASER_PAGE_SIZE_MASK, baser)) {
+		case GIC_PAGE_SIZE_64K:
+			addr = GITS_BASER_ADDR_48_to_52(baser);
+			break;
+		default:
+			addr = baser & GENMASK_ULL(47, 12);
+			break;
+		}
+		val |= FIELD_PREP(GICR_VPROPBASER_4_1_ADDR, addr >> 12);
+		val |= FIELD_PREP(GICR_VPROPBASER_SHAREABILITY_MASK,
+				  FIELD_GET(GITS_BASER_SHAREABILITY_MASK, baser));
+		val |= FIELD_PREP(GICR_VPROPBASER_INNER_CACHEABILITY_MASK,
+				  FIELD_GET(GITS_BASER_INNER_CACHEABILITY_MASK, baser));
+		val |= FIELD_PREP(GICR_VPROPBASER_4_1_SIZE, GITS_BASER_NR_PAGES(baser) - 1);
+
+		return val;
+	}
+
+	return 0;
+}
+
+static u64 inherit_vpe_l1_table_from_rd(cpumask_t **mask)
+{
+	u32 aff;
+	u64 val;
+	int cpu;
+
+	val = gic_read_typer(gic_data_rdist_rd_base() + GICR_TYPER);
+	aff = compute_common_aff(val);
+
+	for_each_possible_cpu(cpu) {
+		void __iomem *base = gic_data_rdist_cpu(cpu)->rd_base;
+
+		if (!base || cpu == smp_processor_id())
+			continue;
+
+		val = gic_read_typer(base + GICR_TYPER);
+		if (aff != compute_common_aff(val))
+			continue;
+
+		/*
+		 * At this point, we have a victim. This particular CPU
+		 * has already booted, and has an affinity that matches
+		 * ours wrt CommonLPIAff. Let's use its own VPROPBASER.
+		 * Make sure we don't write the Z bit in that case.
+		 */
+		val = gicr_read_vpropbaser(base + SZ_128K + GICR_VPROPBASER);
+		val &= ~GICR_VPROPBASER_4_1_Z;
+
+		gic_data_rdist()->vpe_l1_base = gic_data_rdist_cpu(cpu)->vpe_l1_base;
+		*mask = gic_data_rdist_cpu(cpu)->vpe_table_mask;
+
+		return val;
+	}
+
+	return 0;
+}
+
+static bool allocate_vpe_l2_table(int cpu, u32 id)
+{
+	void __iomem *base = gic_data_rdist_cpu(cpu)->rd_base;
+	unsigned int psz, esz, idx, npg, gpsz;
+	u64 val;
+	struct page *page;
+	__le64 *table;
+
+	if (!gic_rdists->has_rvpeid)
+		return true;
+
+	/* Skip non-present CPUs */
+	if (!base)
+		return true;
+
+	val  = gicr_read_vpropbaser(base + SZ_128K + GICR_VPROPBASER);
+
+	esz  = FIELD_GET(GICR_VPROPBASER_4_1_ENTRY_SIZE, val) + 1;
+	gpsz = FIELD_GET(GICR_VPROPBASER_4_1_PAGE_SIZE, val);
+	npg  = FIELD_GET(GICR_VPROPBASER_4_1_SIZE, val) + 1;
+
+	switch (gpsz) {
+	default:
+		WARN_ON(1);
+		fallthrough;
+	case GIC_PAGE_SIZE_4K:
+		psz = SZ_4K;
+		break;
+	case GIC_PAGE_SIZE_16K:
+		psz = SZ_16K;
+		break;
+	case GIC_PAGE_SIZE_64K:
+		psz = SZ_64K;
+		break;
+	}
+
+	/* Don't allow vpe_id that exceeds single, flat table limit */
+	if (!(val & GICR_VPROPBASER_4_1_INDIRECT))
+		return (id < (npg * psz / (esz * SZ_8)));
+
+	/* Compute 1st level table index & check if that exceeds table limit */
+	idx = id >> ilog2(psz / (esz * SZ_8));
+	if (idx >= (npg * psz / GITS_LVL1_ENTRY_SIZE))
+		return false;
+
+	table = gic_data_rdist_cpu(cpu)->vpe_l1_base;
+
+	/* Allocate memory for 2nd level table */
+	if (!table[idx]) {
+		page = alloc_pages(GFP_KERNEL | __GFP_ZERO, get_order(psz));
+		if (!page)
+			return false;
+
+		/* Flush Lvl2 table to PoC if hw doesn't support coherency */
+		if (!(val & GICR_VPROPBASER_SHAREABILITY_MASK))
+			gic_flush_dcache_to_poc(page_address(page), psz);
+
+		table[idx] = cpu_to_le64(page_to_phys(page) | GITS_BASER_VALID);
+
+		/* Flush Lvl1 entry to PoC if hw doesn't support coherency */
+		if (!(val & GICR_VPROPBASER_SHAREABILITY_MASK))
+			gic_flush_dcache_to_poc(table + idx, GITS_LVL1_ENTRY_SIZE);
+
+		/* Ensure updated table contents are visible to RD hardware */
+		dsb(sy);
+	}
+
+	return true;
+}
+
+static int allocate_vpe_l1_table(void)
+{
+	void __iomem *vlpi_base = gic_data_rdist_vlpi_base();
+	u64 val, gpsz, npg, pa;
+	unsigned int psz = SZ_64K;
+	unsigned int np, epp, esz;
+	struct page *page;
+
+	if (!gic_rdists->has_rvpeid)
+		return 0;
+
+	/*
+	 * if VPENDBASER.Valid is set, disable any previously programmed
+	 * VPE by setting PendingLast while clearing Valid. This has the
+	 * effect of making sure no doorbell will be generated and we can
+	 * then safely clear VPROPBASER.Valid.
+	 */
+	if (gicr_read_vpendbaser(vlpi_base + GICR_VPENDBASER) & GICR_VPENDBASER_Valid)
+		gicr_write_vpendbaser(GICR_VPENDBASER_PendingLast,
+				      vlpi_base + GICR_VPENDBASER);
+
+	/*
+	 * If we can inherit the configuration from another RD, let's do
+	 * so. Otherwise, we have to go through the allocation process. We
+	 * assume that all RDs have the exact same requirements, as
+	 * nothing will work otherwise.
+	 */
+	val = inherit_vpe_l1_table_from_rd(&gic_data_rdist()->vpe_table_mask);
+	if (val & GICR_VPROPBASER_4_1_VALID)
+		goto out;
+
+	gic_data_rdist()->vpe_table_mask = kzalloc(sizeof(cpumask_t), GFP_ATOMIC);
+	if (!gic_data_rdist()->vpe_table_mask)
+		return -ENOMEM;
+
+	val = inherit_vpe_l1_table_from_its();
+	if (val & GICR_VPROPBASER_4_1_VALID)
+		goto out;
+
+	/* First probe the page size */
+	val = FIELD_PREP(GICR_VPROPBASER_4_1_PAGE_SIZE, GIC_PAGE_SIZE_64K);
+	gicr_write_vpropbaser(val, vlpi_base + GICR_VPROPBASER);
+	val = gicr_read_vpropbaser(vlpi_base + GICR_VPROPBASER);
+	gpsz = FIELD_GET(GICR_VPROPBASER_4_1_PAGE_SIZE, val);
+	esz = FIELD_GET(GICR_VPROPBASER_4_1_ENTRY_SIZE, val);
+
+	switch (gpsz) {
+	default:
+		gpsz = GIC_PAGE_SIZE_4K;
+		fallthrough;
+	case GIC_PAGE_SIZE_4K:
+		psz = SZ_4K;
+		break;
+	case GIC_PAGE_SIZE_16K:
+		psz = SZ_16K;
+		break;
+	case GIC_PAGE_SIZE_64K:
+		psz = SZ_64K;
+		break;
+	}
+
+	/*
+	 * Start populating the register from scratch, including RO fields
+	 * (which we want to print in debug cases...)
+	 */
+	val = 0;
+	val |= FIELD_PREP(GICR_VPROPBASER_4_1_PAGE_SIZE, gpsz);
+	val |= FIELD_PREP(GICR_VPROPBASER_4_1_ENTRY_SIZE, esz);
+
+	/* How many entries per GIC page? */
+	esz++;
+	epp = psz / (esz * SZ_8);
+
+	/*
+	 * If we need more than just a single L1 page, flag the table
+	 * as indirect and compute the number of required L1 pages.
+	 */
+	if (epp < ITS_MAX_VPEID) {
+		int nl2;
+
+		val |= GICR_VPROPBASER_4_1_INDIRECT;
+
+		/* Number of L2 pages required to cover the VPEID space */
+		nl2 = DIV_ROUND_UP(ITS_MAX_VPEID, epp);
+
+		/* Number of L1 pages to point to the L2 pages */
+		npg = DIV_ROUND_UP(nl2 * SZ_8, psz);
+	} else {
+		npg = 1;
+	}
+
+	val |= FIELD_PREP(GICR_VPROPBASER_4_1_SIZE, npg - 1);
+
+	/* Right, that's the number of CPU pages we need for L1 */
+	np = DIV_ROUND_UP(npg * psz, PAGE_SIZE);
+
+	pr_debug("np = %d, npg = %lld, psz = %d, epp = %d, esz = %d\n",
+		 np, npg, psz, epp, esz);
+	page = alloc_pages(GFP_ATOMIC | __GFP_ZERO, get_order(np * PAGE_SIZE));
+	if (!page)
+		return -ENOMEM;
+
+	gic_data_rdist()->vpe_l1_base = page_address(page);
+	pa = virt_to_phys(page_address(page));
+	WARN_ON(!IS_ALIGNED(pa, psz));
+
+	val |= FIELD_PREP(GICR_VPROPBASER_4_1_ADDR, pa >> 12);
+	val |= GICR_VPROPBASER_RaWb;
+	val |= GICR_VPROPBASER_InnerShareable;
+	val |= GICR_VPROPBASER_4_1_Z;
+	val |= GICR_VPROPBASER_4_1_VALID;
+
+out:
+	gicr_write_vpropbaser(val, vlpi_base + GICR_VPROPBASER);
+	cpumask_set_cpu(smp_processor_id(), gic_data_rdist()->vpe_table_mask);
+
+	pr_debug("CPU%d: VPROPBASER = %llx %*pbl\n",
+		 smp_processor_id(), val,
+		 cpumask_pr_args(gic_data_rdist()->vpe_table_mask));
+
+	return 0;
+}
+
 static int its_alloc_collections(struct its_node *its)
 {
 	int i;
@@ -2085,18 +3002,20 @@
 	return 0;
 }
 
-static u64 its_clear_vpend_valid(void __iomem *vlpi_base)
+static u64 its_clear_vpend_valid(void __iomem *vlpi_base, u64 clr, u64 set)
 {
 	u32 count = 1000000;	/* 1s! */
 	bool clean;
 	u64 val;
 
-	val = gits_read_vpendbaser(vlpi_base + GICR_VPENDBASER);
+	val = gicr_read_vpendbaser(vlpi_base + GICR_VPENDBASER);
 	val &= ~GICR_VPENDBASER_Valid;
-	gits_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER);
+	val &= ~clr;
+	val |= set;
+	gicr_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER);
 
 	do {
-		val = gits_read_vpendbaser(vlpi_base + GICR_VPENDBASER);
+		val = gicr_read_vpendbaser(vlpi_base + GICR_VPENDBASER);
 		clean = !(val & GICR_VPENDBASER_Dirty);
 		if (!clean) {
 			count--;
@@ -2105,6 +3024,11 @@
 		}
 	} while (!clean && count);
 
+	if (unlikely(val & GICR_VPENDBASER_Dirty)) {
+		pr_err_ratelimited("ITS virtual pending table not cleaning\n");
+		val |= GICR_VPENDBASER_PendingLast;
+	}
+
 	return val;
 }
 
@@ -2193,7 +3117,7 @@
 	val |= GICR_CTLR_ENABLE_LPIS;
 	writel_relaxed(val, rbase + GICR_CTLR);
 
-	if (gic_rdists->has_vlpis) {
+	if (gic_rdists->has_vlpis && !gic_rdists->has_rvpeid) {
 		void __iomem *vlpi_base = gic_data_rdist_vlpi_base();
 
 		/*
@@ -2206,15 +3130,24 @@
 		val = (LPI_NRBITS - 1) & GICR_VPROPBASER_IDBITS_MASK;
 		pr_debug("GICv4: CPU%d: Init IDbits to 0x%llx for GICR_VPROPBASER\n",
 			smp_processor_id(), val);
-		gits_write_vpropbaser(val, vlpi_base + GICR_VPROPBASER);
+		gicr_write_vpropbaser(val, vlpi_base + GICR_VPROPBASER);
 
 		/*
 		 * Also clear Valid bit of GICR_VPENDBASER, in case some
 		 * ancient programming gets left in and has possibility of
 		 * corrupting memory.
 		 */
-		val = its_clear_vpend_valid(vlpi_base);
-		WARN_ON(val & GICR_VPENDBASER_Dirty);
+		val = its_clear_vpend_valid(vlpi_base, 0, 0);
+	}
+
+	if (allocate_vpe_l1_table()) {
+		/*
+		 * If the allocation has failed, we're in massive trouble.
+		 * Disable direct injection, and pray that no VM was
+		 * already running...
+		 */
+		gic_rdists->has_rvpeid = false;
+		gic_rdists->has_vlpis = false;
 	}
 
 	/* Make sure the GIC has seen the above */
@@ -2360,7 +3293,7 @@
 
 	/* Don't allow device id that exceeds ITS hardware limit */
 	if (!baser)
-		return (ilog2(dev_id) < its->device_ids);
+		return (ilog2(dev_id) < device_ids(its));
 
 	return its_alloc_table_entry(its, baser, dev_id);
 }
@@ -2368,6 +3301,7 @@
 static bool its_alloc_vpe_table(u32 vpe_id)
 {
 	struct its_node *its;
+	int cpu;
 
 	/*
 	 * Make sure the L2 tables are allocated on *all* v4 ITSs. We
@@ -2379,7 +3313,7 @@
 	list_for_each_entry(its, &its_nodes, entry) {
 		struct its_baser *baser;
 
-		if (!its->is_v4)
+		if (!is_v4(its))
 			continue;
 
 		baser = its_get_baser(its, GITS_BASER_TYPE_VCPU);
@@ -2390,6 +3324,19 @@
 			return false;
 	}
 
+	/* Non v4.1? No need to iterate RDs and go back early. */
+	if (!gic_rdists->has_rvpeid)
+		return true;
+
+	/*
+	 * Make sure the L2 tables are allocated for all copies of
+	 * the L1 table on *all* v4.1 RDs.
+	 */
+	for_each_possible_cpu(cpu) {
+		if (!allocate_vpe_l2_table(cpu, vpe_id))
+			return false;
+	}
+
 	return true;
 }
 
@@ -2418,7 +3365,7 @@
 	 * sized as a power of two (and you need at least one bit...).
 	 */
 	nr_ites = max(2, nvecs);
-	sz = nr_ites * its->ite_size;
+	sz = nr_ites * (FIELD_GET(GITS_TYPER_ITT_ENTRY_SIZE, its->typer) + 1);
 	sz = max(sz, ITS_ITT_ALIGN) + ITS_ITT_ALIGN - 1;
 	itt = kzalloc_node(sz, GFP_KERNEL, its->numa_node);
 	if (alloc_lpis) {
@@ -2449,7 +3396,7 @@
 	dev->event_map.col_map = col_map;
 	dev->event_map.lpi_base = lpi_base;
 	dev->event_map.nr_lpis = nr_lpis;
-	mutex_init(&dev->event_map.vlpi_lock);
+	raw_spin_lock_init(&dev->event_map.vlpi_lock);
 	dev->device_id = dev_id;
 	INIT_LIST_HEAD(&dev->entry);
 
@@ -2470,6 +3417,7 @@
 	raw_spin_lock_irqsave(&its_dev->its->lock, flags);
 	list_del(&its_dev->entry);
 	raw_spin_unlock_irqrestore(&its_dev->its->lock, flags);
+	kfree(its_dev->event_map.col_map);
 	kfree(its_dev->itt);
 	kfree(its_dev);
 }
@@ -2616,22 +3564,13 @@
 {
 	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
 	u32 event = its_get_event_id(d);
-	const struct cpumask *cpu_mask = cpu_online_mask;
 	int cpu;
 
-	/* get the cpu_mask of local node */
-	if (its_dev->its->numa_node >= 0)
-		cpu_mask = cpumask_of_node(its_dev->its->numa_node);
+	cpu = its_select_cpu(d, cpu_online_mask);
+	if (cpu < 0 || cpu >= nr_cpu_ids)
+		return -EINVAL;
 
-	/* Bind the LPI to the first possible CPU */
-	cpu = cpumask_first_and(cpu_mask, cpu_online_mask);
-	if (cpu >= nr_cpu_ids) {
-		if (its_dev->its->flags & ITS_FLAGS_WORKAROUND_CAVIUM_23144)
-			return -EINVAL;
-
-		cpu = cpumask_first(cpu_online_mask);
-	}
-
+	its_inc_lpi_count(d, cpu);
 	its_dev->event_map.col_map[event] = cpu;
 	irq_data_update_effective_affinity(d, cpumask_of(cpu));
 
@@ -2646,6 +3585,7 @@
 	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
 	u32 event = its_get_event_id(d);
 
+	its_dec_lpi_count(d, its_dev->event_map.col_map[event]);
 	/* Stop the delivery of interrupts */
 	its_send_discard(its_dev, event);
 }
@@ -2681,7 +3621,6 @@
 		its_lpi_free(its_dev->event_map.lpi_map,
 			     its_dev->event_map.lpi_base,
 			     its_dev->event_map.nr_lpis);
-		kfree(its_dev->event_map.col_map);
 
 		/* Unmap device/itt */
 		its_send_mapd(its_dev, 0);
@@ -2703,7 +3642,7 @@
 /*
  * This is insane.
  *
- * If a GICv4 doesn't implement Direct LPIs (which is extremely
+ * If a GICv4.0 doesn't implement Direct LPIs (which is extremely
  * likely), the only way to perform an invalidate is to use a fake
  * device to issue an INV command, implying that the LPI has first
  * been mapped to some event on that device. Since this is not exactly
@@ -2711,9 +3650,20 @@
  * only issue an UNMAP if we're short on available slots.
  *
  * Broken by design(tm).
+ *
+ * GICv4.1, on the other hand, mandates that we're able to invalidate
+ * by writing to a MMIO register. It doesn't implement the whole of
+ * DirectLPI, but that's good enough. And most of the time, we don't
+ * even have to invalidate anything, as the redistributor can be told
+ * whether to generate a doorbell or not (we thus leave it enabled,
+ * always).
  */
 static void its_vpe_db_proxy_unmap_locked(struct its_vpe *vpe)
 {
+	/* GICv4.1 doesn't use a proxy, so nothing to do here */
+	if (gic_rdists->has_rvpeid)
+		return;
+
 	/* Already unmapped? */
 	if (vpe->vpe_proxy_event == -1)
 		return;
@@ -2736,6 +3686,10 @@
 
 static void its_vpe_db_proxy_unmap(struct its_vpe *vpe)
 {
+	/* GICv4.1 doesn't use a proxy, so nothing to do here */
+	if (gic_rdists->has_rvpeid)
+		return;
+
 	if (!gic_rdists->has_direct_lpi) {
 		unsigned long flags;
 
@@ -2747,6 +3701,10 @@
 
 static void its_vpe_db_proxy_map_locked(struct its_vpe *vpe)
 {
+	/* GICv4.1 doesn't use a proxy, so nothing to do here */
+	if (gic_rdists->has_rvpeid)
+		return;
+
 	/* Already mapped? */
 	if (vpe->vpe_proxy_event != -1)
 		return;
@@ -2769,13 +3727,16 @@
 	unsigned long flags;
 	struct its_collection *target_col;
 
+	/* GICv4.1 doesn't use a proxy, so nothing to do here */
+	if (gic_rdists->has_rvpeid)
+		return;
+
 	if (gic_rdists->has_direct_lpi) {
 		void __iomem *rdbase;
 
 		rdbase = per_cpu_ptr(gic_rdists->rdist, from)->rd_base;
 		gic_write_lpir(vpe->vpe_db_lpi, rdbase + GICR_CLRLPIR);
-		while (gic_read_lpir(rdbase + GICR_SYNCR) & 1)
-			cpu_relax();
+		wait_for_syncr(rdbase);
 
 		return;
 	}
@@ -2796,27 +3757,60 @@
 				bool force)
 {
 	struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
-	int cpu = cpumask_first(mask_val);
+	int from, cpu = cpumask_first(mask_val);
+	unsigned long flags;
 
 	/*
 	 * Changing affinity is mega expensive, so let's be as lazy as
 	 * we can and only do it if we really have to. Also, if mapped
 	 * into the proxy device, we need to move the doorbell
 	 * interrupt to its new location.
+	 *
+	 * Another thing is that changing the affinity of a vPE affects
+	 * *other interrupts* such as all the vLPIs that are routed to
+	 * this vPE. This means that the irq_desc lock is not enough to
+	 * protect us, and that we must ensure nobody samples vpe->col_idx
+	 * during the update, hence the lock below which must also be
+	 * taken on any vLPI handling path that evaluates vpe->col_idx.
 	 */
-	if (vpe->col_idx != cpu) {
-		int from = vpe->col_idx;
+	from = vpe_to_cpuid_lock(vpe, &flags);
+	if (from == cpu)
+		goto out;
 
-		vpe->col_idx = cpu;
-		its_send_vmovp(vpe);
-		its_vpe_db_proxy_move(vpe, from, cpu);
-	}
+	vpe->col_idx = cpu;
 
+	/*
+	 * GICv4.1 allows us to skip VMOVP if moving to a cpu whose RD
+	 * is sharing its VPE table with the current one.
+	 */
+	if (gic_data_rdist_cpu(cpu)->vpe_table_mask &&
+	    cpumask_test_cpu(from, gic_data_rdist_cpu(cpu)->vpe_table_mask))
+		goto out;
+
+	its_send_vmovp(vpe);
+	its_vpe_db_proxy_move(vpe, from, cpu);
+
+out:
 	irq_data_update_effective_affinity(d, cpumask_of(cpu));
+	vpe_to_cpuid_unlock(vpe, flags);
 
 	return IRQ_SET_MASK_OK_DONE;
 }
 
+static void its_wait_vpt_parse_complete(void)
+{
+	void __iomem *vlpi_base = gic_data_rdist_vlpi_base();
+	u64 val;
+
+	if (!gic_rdists->has_vpend_valid_dirty)
+		return;
+
+	WARN_ON_ONCE(readq_relaxed_poll_timeout_atomic(vlpi_base + GICR_VPENDBASER,
+						       val,
+						       !(val & GICR_VPENDBASER_Dirty),
+						       10, 500));
+}
+
 static void its_vpe_schedule(struct its_vpe *vpe)
 {
 	void __iomem *vlpi_base = gic_data_rdist_vlpi_base();
@@ -2828,12 +3822,12 @@
 	val |= (LPI_NRBITS - 1) & GICR_VPROPBASER_IDBITS_MASK;
 	val |= GICR_VPROPBASER_RaWb;
 	val |= GICR_VPROPBASER_InnerShareable;
-	gits_write_vpropbaser(val, vlpi_base + GICR_VPROPBASER);
+	gicr_write_vpropbaser(val, vlpi_base + GICR_VPROPBASER);
 
 	val  = virt_to_phys(page_address(vpe->vpt_page)) &
 		GENMASK_ULL(51, 16);
 	val |= GICR_VPENDBASER_RaWaWb;
-	val |= GICR_VPENDBASER_NonShareable;
+	val |= GICR_VPENDBASER_InnerShareable;
 	/*
 	 * There is no good way of finding out if the pending table is
 	 * empty as we can race against the doorbell interrupt very
@@ -2846,7 +3840,9 @@
 	val |= GICR_VPENDBASER_PendingLast;
 	val |= vpe->idai ? GICR_VPENDBASER_IDAI : 0;
 	val |= GICR_VPENDBASER_Valid;
-	gits_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER);
+	gicr_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER);
+
+	its_wait_vpt_parse_complete();
 }
 
 static void its_vpe_deschedule(struct its_vpe *vpe)
@@ -2854,16 +3850,10 @@
 	void __iomem *vlpi_base = gic_data_rdist_vlpi_base();
 	u64 val;
 
-	val = its_clear_vpend_valid(vlpi_base);
+	val = its_clear_vpend_valid(vlpi_base, 0, 0);
 
-	if (unlikely(val & GICR_VPENDBASER_Dirty)) {
-		pr_err_ratelimited("ITS virtual pending table not cleaning\n");
-		vpe->idai = false;
-		vpe->pending_last = true;
-	} else {
-		vpe->idai = !!(val & GICR_VPENDBASER_IDAI);
-		vpe->pending_last = !!(val & GICR_VPENDBASER_PendingLast);
-	}
+	vpe->idai = !!(val & GICR_VPENDBASER_IDAI);
+	vpe->pending_last = !!(val & GICR_VPENDBASER_PendingLast);
 }
 
 static void its_vpe_invall(struct its_vpe *vpe)
@@ -2871,7 +3861,7 @@
 	struct its_node *its;
 
 	list_for_each_entry(its, &its_nodes, entry) {
-		if (!its->is_v4)
+		if (!is_v4(its))
 			continue;
 
 		if (its_list_map && !vpe->its_vm->vlpi_count[its->list_nr])
@@ -2929,10 +3919,12 @@
 	if (gic_rdists->has_direct_lpi) {
 		void __iomem *rdbase;
 
+		/* Target the redistributor this VPE is currently known on */
+		raw_spin_lock(&gic_data_rdist_cpu(vpe->col_idx)->rd_lock);
 		rdbase = per_cpu_ptr(gic_rdists->rdist, vpe->col_idx)->rd_base;
-		gic_write_lpir(vpe->vpe_db_lpi, rdbase + GICR_INVLPIR);
-		while (gic_read_lpir(rdbase + GICR_SYNCR) & 1)
-			cpu_relax();
+		gic_write_lpir(d->parent_data->hwirq, rdbase + GICR_INVLPIR);
+		wait_for_syncr(rdbase);
+		raw_spin_unlock(&gic_data_rdist_cpu(vpe->col_idx)->rd_lock);
 	} else {
 		its_vpe_send_cmd(vpe, its_send_inv);
 	}
@@ -2974,8 +3966,7 @@
 			gic_write_lpir(vpe->vpe_db_lpi, rdbase + GICR_SETLPIR);
 		} else {
 			gic_write_lpir(vpe->vpe_db_lpi, rdbase + GICR_CLRLPIR);
-			while (gic_read_lpir(rdbase + GICR_SYNCR) & 1)
-				cpu_relax();
+			wait_for_syncr(rdbase);
 		}
 	} else {
 		if (state)
@@ -3003,6 +3994,373 @@
 	.irq_set_vcpu_affinity	= its_vpe_set_vcpu_affinity,
 };
 
+static struct its_node *find_4_1_its(void)
+{
+	static struct its_node *its = NULL;
+
+	if (!its) {
+		list_for_each_entry(its, &its_nodes, entry) {
+			if (is_v4_1(its))
+				return its;
+		}
+
+		/* Oops? */
+		its = NULL;
+	}
+
+	return its;
+}
+
+static void its_vpe_4_1_send_inv(struct irq_data *d)
+{
+	struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
+	struct its_node *its;
+
+	/*
+	 * GICv4.1 wants doorbells to be invalidated using the
+	 * INVDB command in order to be broadcast to all RDs. Send
+	 * it to the first valid ITS, and let the HW do its magic.
+	 */
+	its = find_4_1_its();
+	if (its)
+		its_send_invdb(its, vpe);
+}
+
+static void its_vpe_4_1_mask_irq(struct irq_data *d)
+{
+	lpi_write_config(d->parent_data, LPI_PROP_ENABLED, 0);
+	its_vpe_4_1_send_inv(d);
+}
+
+static void its_vpe_4_1_unmask_irq(struct irq_data *d)
+{
+	lpi_write_config(d->parent_data, 0, LPI_PROP_ENABLED);
+	its_vpe_4_1_send_inv(d);
+}
+
+static void its_vpe_4_1_schedule(struct its_vpe *vpe,
+				 struct its_cmd_info *info)
+{
+	void __iomem *vlpi_base = gic_data_rdist_vlpi_base();
+	u64 val = 0;
+
+	/* Schedule the VPE */
+	val |= GICR_VPENDBASER_Valid;
+	val |= info->g0en ? GICR_VPENDBASER_4_1_VGRP0EN : 0;
+	val |= info->g1en ? GICR_VPENDBASER_4_1_VGRP1EN : 0;
+	val |= FIELD_PREP(GICR_VPENDBASER_4_1_VPEID, vpe->vpe_id);
+
+	gicr_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER);
+
+	its_wait_vpt_parse_complete();
+}
+
+static void its_vpe_4_1_deschedule(struct its_vpe *vpe,
+				   struct its_cmd_info *info)
+{
+	void __iomem *vlpi_base = gic_data_rdist_vlpi_base();
+	u64 val;
+
+	if (info->req_db) {
+		unsigned long flags;
+
+		/*
+		 * vPE is going to block: make the vPE non-resident with
+		 * PendingLast clear and DB set. The GIC guarantees that if
+		 * we read-back PendingLast clear, then a doorbell will be
+		 * delivered when an interrupt comes.
+		 *
+		 * Note the locking to deal with the concurrent update of
+		 * pending_last from the doorbell interrupt handler that can
+		 * run concurrently.
+		 */
+		raw_spin_lock_irqsave(&vpe->vpe_lock, flags);
+		val = its_clear_vpend_valid(vlpi_base,
+					    GICR_VPENDBASER_PendingLast,
+					    GICR_VPENDBASER_4_1_DB);
+		vpe->pending_last = !!(val & GICR_VPENDBASER_PendingLast);
+		raw_spin_unlock_irqrestore(&vpe->vpe_lock, flags);
+	} else {
+		/*
+		 * We're not blocking, so just make the vPE non-resident
+		 * with PendingLast set, indicating that we'll be back.
+		 */
+		val = its_clear_vpend_valid(vlpi_base,
+					    0,
+					    GICR_VPENDBASER_PendingLast);
+		vpe->pending_last = true;
+	}
+}
+
+static void its_vpe_4_1_invall(struct its_vpe *vpe)
+{
+	void __iomem *rdbase;
+	unsigned long flags;
+	u64 val;
+	int cpu;
+
+	val  = GICR_INVALLR_V;
+	val |= FIELD_PREP(GICR_INVALLR_VPEID, vpe->vpe_id);
+
+	/* Target the redistributor this vPE is currently known on */
+	cpu = vpe_to_cpuid_lock(vpe, &flags);
+	raw_spin_lock(&gic_data_rdist_cpu(cpu)->rd_lock);
+	rdbase = per_cpu_ptr(gic_rdists->rdist, cpu)->rd_base;
+	gic_write_lpir(val, rdbase + GICR_INVALLR);
+
+	wait_for_syncr(rdbase);
+	raw_spin_unlock(&gic_data_rdist_cpu(cpu)->rd_lock);
+	vpe_to_cpuid_unlock(vpe, flags);
+}
+
+static int its_vpe_4_1_set_vcpu_affinity(struct irq_data *d, void *vcpu_info)
+{
+	struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
+	struct its_cmd_info *info = vcpu_info;
+
+	switch (info->cmd_type) {
+	case SCHEDULE_VPE:
+		its_vpe_4_1_schedule(vpe, info);
+		return 0;
+
+	case DESCHEDULE_VPE:
+		its_vpe_4_1_deschedule(vpe, info);
+		return 0;
+
+	case INVALL_VPE:
+		its_vpe_4_1_invall(vpe);
+		return 0;
+
+	default:
+		return -EINVAL;
+	}
+}
+
+static struct irq_chip its_vpe_4_1_irq_chip = {
+	.name			= "GICv4.1-vpe",
+	.irq_mask		= its_vpe_4_1_mask_irq,
+	.irq_unmask		= its_vpe_4_1_unmask_irq,
+	.irq_eoi		= irq_chip_eoi_parent,
+	.irq_set_affinity	= its_vpe_set_affinity,
+	.irq_set_vcpu_affinity	= its_vpe_4_1_set_vcpu_affinity,
+};
+
+static void its_configure_sgi(struct irq_data *d, bool clear)
+{
+	struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
+	struct its_cmd_desc desc;
+
+	desc.its_vsgi_cmd.vpe = vpe;
+	desc.its_vsgi_cmd.sgi = d->hwirq;
+	desc.its_vsgi_cmd.priority = vpe->sgi_config[d->hwirq].priority;
+	desc.its_vsgi_cmd.enable = vpe->sgi_config[d->hwirq].enabled;
+	desc.its_vsgi_cmd.group = vpe->sgi_config[d->hwirq].group;
+	desc.its_vsgi_cmd.clear = clear;
+
+	/*
+	 * GICv4.1 allows us to send VSGI commands to any ITS as long as the
+	 * destination VPE is mapped there. Since we map them eagerly at
+	 * activation time, we're pretty sure the first GICv4.1 ITS will do.
+	 */
+	its_send_single_vcommand(find_4_1_its(), its_build_vsgi_cmd, &desc);
+}
+
+static void its_sgi_mask_irq(struct irq_data *d)
+{
+	struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
+
+	vpe->sgi_config[d->hwirq].enabled = false;
+	its_configure_sgi(d, false);
+}
+
+static void its_sgi_unmask_irq(struct irq_data *d)
+{
+	struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
+
+	vpe->sgi_config[d->hwirq].enabled = true;
+	its_configure_sgi(d, false);
+}
+
+static int its_sgi_set_affinity(struct irq_data *d,
+				const struct cpumask *mask_val,
+				bool force)
+{
+	/*
+	 * There is no notion of affinity for virtual SGIs, at least
+	 * not on the host (since they can only be targetting a vPE).
+	 * Tell the kernel we've done whatever it asked for.
+	 */
+	irq_data_update_effective_affinity(d, mask_val);
+	return IRQ_SET_MASK_OK;
+}
+
+static int its_sgi_set_irqchip_state(struct irq_data *d,
+				     enum irqchip_irq_state which,
+				     bool state)
+{
+	if (which != IRQCHIP_STATE_PENDING)
+		return -EINVAL;
+
+	if (state) {
+		struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
+		struct its_node *its = find_4_1_its();
+		u64 val;
+
+		val  = FIELD_PREP(GITS_SGIR_VPEID, vpe->vpe_id);
+		val |= FIELD_PREP(GITS_SGIR_VINTID, d->hwirq);
+		writeq_relaxed(val, its->sgir_base + GITS_SGIR - SZ_128K);
+	} else {
+		its_configure_sgi(d, true);
+	}
+
+	return 0;
+}
+
+static int its_sgi_get_irqchip_state(struct irq_data *d,
+				     enum irqchip_irq_state which, bool *val)
+{
+	struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
+	void __iomem *base;
+	unsigned long flags;
+	u32 count = 1000000;	/* 1s! */
+	u32 status;
+	int cpu;
+
+	if (which != IRQCHIP_STATE_PENDING)
+		return -EINVAL;
+
+	/*
+	 * Locking galore! We can race against two different events:
+	 *
+	 * - Concurent vPE affinity change: we must make sure it cannot
+	 *   happen, or we'll talk to the wrong redistributor. This is
+	 *   identical to what happens with vLPIs.
+	 *
+	 * - Concurrent VSGIPENDR access: As it involves accessing two
+	 *   MMIO registers, this must be made atomic one way or another.
+	 */
+	cpu = vpe_to_cpuid_lock(vpe, &flags);
+	raw_spin_lock(&gic_data_rdist_cpu(cpu)->rd_lock);
+	base = gic_data_rdist_cpu(cpu)->rd_base + SZ_128K;
+	writel_relaxed(vpe->vpe_id, base + GICR_VSGIR);
+	do {
+		status = readl_relaxed(base + GICR_VSGIPENDR);
+		if (!(status & GICR_VSGIPENDR_BUSY))
+			goto out;
+
+		count--;
+		if (!count) {
+			pr_err_ratelimited("Unable to get SGI status\n");
+			goto out;
+		}
+		cpu_relax();
+		udelay(1);
+	} while (count);
+
+out:
+	raw_spin_unlock(&gic_data_rdist_cpu(cpu)->rd_lock);
+	vpe_to_cpuid_unlock(vpe, flags);
+
+	if (!count)
+		return -ENXIO;
+
+	*val = !!(status & (1 << d->hwirq));
+
+	return 0;
+}
+
+static int its_sgi_set_vcpu_affinity(struct irq_data *d, void *vcpu_info)
+{
+	struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
+	struct its_cmd_info *info = vcpu_info;
+
+	switch (info->cmd_type) {
+	case PROP_UPDATE_VSGI:
+		vpe->sgi_config[d->hwirq].priority = info->priority;
+		vpe->sgi_config[d->hwirq].group = info->group;
+		its_configure_sgi(d, false);
+		return 0;
+
+	default:
+		return -EINVAL;
+	}
+}
+
+static struct irq_chip its_sgi_irq_chip = {
+	.name			= "GICv4.1-sgi",
+	.irq_mask		= its_sgi_mask_irq,
+	.irq_unmask		= its_sgi_unmask_irq,
+	.irq_set_affinity	= its_sgi_set_affinity,
+	.irq_set_irqchip_state	= its_sgi_set_irqchip_state,
+	.irq_get_irqchip_state	= its_sgi_get_irqchip_state,
+	.irq_set_vcpu_affinity	= its_sgi_set_vcpu_affinity,
+};
+
+static int its_sgi_irq_domain_alloc(struct irq_domain *domain,
+				    unsigned int virq, unsigned int nr_irqs,
+				    void *args)
+{
+	struct its_vpe *vpe = args;
+	int i;
+
+	/* Yes, we do want 16 SGIs */
+	WARN_ON(nr_irqs != 16);
+
+	for (i = 0; i < 16; i++) {
+		vpe->sgi_config[i].priority = 0;
+		vpe->sgi_config[i].enabled = false;
+		vpe->sgi_config[i].group = false;
+
+		irq_domain_set_hwirq_and_chip(domain, virq + i, i,
+					      &its_sgi_irq_chip, vpe);
+		irq_set_status_flags(virq + i, IRQ_DISABLE_UNLAZY);
+	}
+
+	return 0;
+}
+
+static void its_sgi_irq_domain_free(struct irq_domain *domain,
+				    unsigned int virq,
+				    unsigned int nr_irqs)
+{
+	/* Nothing to do */
+}
+
+static int its_sgi_irq_domain_activate(struct irq_domain *domain,
+				       struct irq_data *d, bool reserve)
+{
+	/* Write out the initial SGI configuration */
+	its_configure_sgi(d, false);
+	return 0;
+}
+
+static void its_sgi_irq_domain_deactivate(struct irq_domain *domain,
+					  struct irq_data *d)
+{
+	struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
+
+	/*
+	 * The VSGI command is awkward:
+	 *
+	 * - To change the configuration, CLEAR must be set to false,
+	 *   leaving the pending bit unchanged.
+	 * - To clear the pending bit, CLEAR must be set to true, leaving
+	 *   the configuration unchanged.
+	 *
+	 * You just can't do both at once, hence the two commands below.
+	 */
+	vpe->sgi_config[d->hwirq].enabled = false;
+	its_configure_sgi(d, false);
+	its_configure_sgi(d, true);
+}
+
+static const struct irq_domain_ops its_sgi_domain_ops = {
+	.alloc		= its_sgi_irq_domain_alloc,
+	.free		= its_sgi_irq_domain_free,
+	.activate	= its_sgi_irq_domain_activate,
+	.deactivate	= its_sgi_irq_domain_deactivate,
+};
+
 static int its_vpe_id_alloc(void)
 {
 	return ida_simple_get(&its_vpeid_ida, 0, ITS_MAX_VPEID, GFP_KERNEL);
@@ -3036,9 +4394,13 @@
 		return -ENOMEM;
 	}
 
+	raw_spin_lock_init(&vpe->vpe_lock);
 	vpe->vpe_id = vpe_id;
 	vpe->vpt_page = vpt_page;
-	vpe->vpe_proxy_event = -1;
+	if (gic_rdists->has_rvpeid)
+		atomic_set(&vpe->vmapp_count, 0);
+	else
+		vpe->vpe_proxy_event = -1;
 
 	return 0;
 }
@@ -3080,6 +4442,7 @@
 static int its_vpe_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
 				    unsigned int nr_irqs, void *args)
 {
+	struct irq_chip *irqchip = &its_vpe_irq_chip;
 	struct its_vm *vm = args;
 	unsigned long *bitmap;
 	struct page *vprop_page;
@@ -3107,6 +4470,9 @@
 	vm->nr_db_lpis = nr_ids;
 	vm->vprop_page = vprop_page;
 
+	if (gic_rdists->has_rvpeid)
+		irqchip = &its_vpe_4_1_irq_chip;
+
 	for (i = 0; i < nr_irqs; i++) {
 		vm->vpes[i]->vpe_db_lpi = base + i;
 		err = its_vpe_init(vm->vpes[i]);
@@ -3117,13 +4483,13 @@
 		if (err)
 			break;
 		irq_domain_set_hwirq_and_chip(domain, virq + i, i,
-					      &its_vpe_irq_chip, vm->vpes[i]);
+					      irqchip, vm->vpes[i]);
 		set_bit(i, bitmap);
 	}
 
 	if (err) {
 		if (i > 0)
-			its_vpe_irq_domain_free(domain, virq, i - 1);
+			its_vpe_irq_domain_free(domain, virq, i);
 
 		its_lpi_free(bitmap, base, nr_ids);
 		its_free_prop_table(vprop_page);
@@ -3138,15 +4504,19 @@
 	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)
+	/*
+	 * If we use the list map, we issue VMAPP on demand... Unless
+	 * we're on a GICv4.1 and we eagerly map the VPE on all ITSs
+	 * so that VSGIs can work.
+	 */
+	if (!gic_requires_eager_mapping())
 		return 0;
 
 	/* Map the VPE to the first possible CPU */
 	vpe->col_idx = cpumask_first(cpu_online_mask);
 
 	list_for_each_entry(its, &its_nodes, entry) {
-		if (!its->is_v4)
+		if (!is_v4(its))
 			continue;
 
 		its_send_vmapp(its, vpe, true);
@@ -3165,14 +4535,14 @@
 	struct its_node *its;
 
 	/*
-	 * If we use the list map, we unmap the VPE once no VLPIs are
-	 * associated with the VM.
+	 * If we use the list map on GICv4.0, we unmap the VPE once no
+	 * VLPIs are associated with the VM.
 	 */
-	if (its_list_map)
+	if (!gic_requires_eager_mapping())
 		return;
 
 	list_for_each_entry(its, &its_nodes, entry) {
-		if (!its->is_v4)
+		if (!is_v4(its))
 			continue;
 
 		its_send_vmapp(its, vpe, false);
@@ -3223,8 +4593,9 @@
 {
 	struct its_node *its = data;
 
-	/* erratum 22375: only alloc 8MB table size */
-	its->device_ids = 0x14;		/* 20 bits, 8MB */
+	/* erratum 22375: only alloc 8MB table size (20 bits) */
+	its->typer &= ~GITS_TYPER_DEVBITS;
+	its->typer |= FIELD_PREP(GITS_TYPER_DEVBITS, 20 - 1);
 	its->flags |= ITS_FLAGS_WORKAROUND_CAVIUM_22375;
 
 	return true;
@@ -3244,7 +4615,8 @@
 	struct its_node *its = data;
 
 	/* On QDF2400, the size of the ITE is 16Bytes */
-	its->ite_size = 16;
+	its->typer &= ~GITS_TYPER_ITT_ENTRY_SIZE;
+	its->typer |= FIELD_PREP(GITS_TYPER_ITT_ENTRY_SIZE, 16 - 1);
 
 	return true;
 }
@@ -3278,8 +4650,10 @@
 		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;
+		if (device_ids(its) > ids) {
+			its->typer &= ~GITS_TYPER_DEVBITS;
+			its->typer |= FIELD_PREP(GITS_TYPER_DEVBITS, ids - 1);
+		}
 
 		/* the pre-ITS breaks isolation, so disable MSI remapping */
 		its->msi_domain_flags &= ~IRQ_DOMAIN_FLAG_MSI_REMAP;
@@ -3506,7 +4880,7 @@
 	}
 
 	/* Use the last possible DevID */
-	devid = GENMASK(its->device_ids - 1, 0);
+	devid = GENMASK(device_ids(its) - 1, 0);
 	vpe_proxy.dev = its_create_device(its, devid, entries, false);
 	if (!vpe_proxy.dev) {
 		kfree(vpe_proxy.vpes);
@@ -3572,7 +4946,7 @@
 	struct page *page;
 	int err;
 
-	its_base = ioremap(res->start, resource_size(res));
+	its_base = ioremap(res->start, SZ_64K);
 	if (!its_base) {
 		pr_warn("ITS@%pa: Unable to map ITS registers\n", &res->start);
 		return -ENOMEM;
@@ -3604,12 +4978,10 @@
 	INIT_LIST_HEAD(&its->entry);
 	INIT_LIST_HEAD(&its->its_device_list);
 	typer = gic_read_typer(its_base + GITS_TYPER);
+	its->typer = typer;
 	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 (is_v4(its)) {
 		if (!(typer & GITS_TYPER_VMOVP)) {
 			err = its_compute_its_list_map(res, its_base);
 			if (err < 0)
@@ -3622,6 +4994,21 @@
 		} else {
 			pr_info("ITS@%pa: Single VMOVP capable\n", &res->start);
 		}
+
+		if (is_v4_1(its)) {
+			u32 svpet = FIELD_GET(GITS_TYPER_SVPET, typer);
+
+			its->sgir_base = ioremap(res->start + SZ_128K, SZ_64K);
+			if (!its->sgir_base) {
+				err = -ENOMEM;
+				goto out_free_its;
+			}
+
+			its->mpidr = readl_relaxed(its_base + GITS_MPIDR);
+
+			pr_info("ITS@%pa: Using GICv4.1 mode %08x %08x\n",
+				&res->start, its->mpidr, svpet);
+		}
 	}
 
 	its->numa_node = numa_node;
@@ -3630,7 +5017,7 @@
 				get_order(ITS_CMD_QUEUE_SZ));
 	if (!page) {
 		err = -ENOMEM;
-		goto out_free_its;
+		goto out_unmap_sgir;
 	}
 	its->cmd_base = (void *)page_address(page);
 	its->cmd_write = its->cmd_base;
@@ -3676,7 +5063,7 @@
 	gits_write_cwriter(0, its->base + GITS_CWRITER);
 	ctlr = readl_relaxed(its->base + GITS_CTLR);
 	ctlr |= GITS_CTLR_ENABLE;
-	if (its->is_v4)
+	if (is_v4(its))
 		ctlr |= GITS_CTLR_ImDe;
 	writel_relaxed(ctlr, its->base + GITS_CTLR);
 
@@ -3694,6 +5081,9 @@
 	its_free_tables(its);
 out_free_cmd:
 	free_pages((unsigned long)its->cmd_base, get_order(ITS_CMD_QUEUE_SZ));
+out_unmap_sgir:
+	if (its->sgir_base)
+		iounmap(its->sgir_base);
 out_free_its:
 	kfree(its);
 out_unmap:
@@ -3869,7 +5259,12 @@
 		return -EINVAL;
 	}
 
-	node = acpi_map_pxm_to_node(its_affinity->proximity_domain);
+	/*
+	 * Note that in theory a new proximity node could be created by this
+	 * entry as it is an SRAT resource allocation structure.
+	 * We do not currently support doing so.
+	 */
+	node = pxm_to_node(its_affinity->proximity_domain);
 
 	if (node == NUMA_NO_NODE || node >= MAX_NUMNODES) {
 		pr_err("SRAT: Invalid NUMA node %d in ITS affinity\n", node);
@@ -3977,8 +5372,11 @@
 	struct device_node *of_node;
 	struct its_node *its;
 	bool has_v4 = false;
+	bool has_v4_1 = false;
 	int err;
 
+	gic_rdists = rdists;
+
 	its_parent = parent_domain;
 	of_node = to_of_node(handle);
 	if (of_node)
@@ -3991,18 +5389,29 @@
 		return -ENXIO;
 	}
 
-	gic_rdists = rdists;
-
 	err = allocate_lpi_tables();
 	if (err)
 		return err;
 
-	list_for_each_entry(its, &its_nodes, entry)
-		has_v4 |= its->is_v4;
+	list_for_each_entry(its, &its_nodes, entry) {
+		has_v4 |= is_v4(its);
+		has_v4_1 |= is_v4_1(its);
+	}
+
+	/* Don't bother with inconsistent systems */
+	if (WARN_ON(!has_v4_1 && rdists->has_rvpeid))
+		rdists->has_rvpeid = false;
 
 	if (has_v4 & rdists->has_vlpis) {
+		const struct irq_domain_ops *sgi_ops;
+
+		if (has_v4_1)
+			sgi_ops = &its_sgi_domain_ops;
+		else
+			sgi_ops = NULL;
+
 		if (its_init_vpe_domain() ||
-		    its_init_v4(parent_domain, &its_vpe_domain_ops)) {
+		    its_init_v4(parent_domain, &its_vpe_domain_ops, sgi_ops)) {
 			rdists->has_vlpis = false;
 			pr_err("ITS: Disabling GICv4 support\n");
 		}
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index 9d0b42c..04d1b39 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -34,6 +34,9 @@
 #define GICD_INT_NMI_PRI	(GICD_INT_DEF_PRI & ~0x80)
 
 #define FLAGS_WORKAROUND_GICR_WAKER_MSM8996	(1ULL << 0)
+#define FLAGS_WORKAROUND_CAVIUM_ERRATUM_38539	(1ULL << 1)
+
+#define GIC_IRQ_TYPE_PARTITION	(GIC_IRQ_TYPE_LPI + 1)
 
 struct redist_region {
 	void __iomem		*redist_base;
@@ -74,19 +77,50 @@
  *
  * If SCR_EL3.FIQ == 1, the values writen to/read from PMR and RPR at non-secure
  * EL1 are subject to a similar operation thus matching the priorities presented
- * from the (re)distributor when security is enabled.
+ * from the (re)distributor when security is enabled. When SCR_EL3.FIQ == 0,
+ * these values are unchanched by the GIC.
  *
  * see GICv3/GICv4 Architecture Specification (IHI0069D):
  * - section 4.8.1 Non-secure accesses to register fields for Secure interrupt
  *   priorities.
  * - Figure 4-7 Secure read of the priority field for a Non-secure Group 1
  *   interrupt.
- *
- * For now, we only support pseudo-NMIs if we have non-secure view of
- * priorities.
  */
 static DEFINE_STATIC_KEY_FALSE(supports_pseudo_nmis);
 
+/*
+ * Global static key controlling whether an update to PMR allowing more
+ * interrupts requires to be propagated to the redistributor (DSB SY).
+ * And this needs to be exported for modules to be able to enable
+ * interrupts...
+ */
+DEFINE_STATIC_KEY_FALSE(gic_pmr_sync);
+EXPORT_SYMBOL(gic_pmr_sync);
+
+DEFINE_STATIC_KEY_FALSE(gic_nonsecure_priorities);
+EXPORT_SYMBOL(gic_nonsecure_priorities);
+
+/*
+ * When the Non-secure world has access to group 0 interrupts (as a
+ * consequence of SCR_EL3.FIQ == 0), reading the ICC_RPR_EL1 register will
+ * return the Distributor's view of the interrupt priority.
+ *
+ * When GIC security is enabled (GICD_CTLR.DS == 0), the interrupt priority
+ * written by software is moved to the Non-secure range by the Distributor.
+ *
+ * If both are true (which is when gic_nonsecure_priorities gets enabled),
+ * we need to shift down the priority programmed by software to match it
+ * against the value returned by ICC_RPR_EL1.
+ */
+#define GICD_INT_RPR_PRI(priority)					\
+	({								\
+		u32 __priority = (priority);				\
+		if (static_branch_unlikely(&gic_nonsecure_priorities))	\
+			__priority = 0x80 | (__priority >> 1);		\
+									\
+		__priority;						\
+	})
+
 /* ppi_nmi_refs[n] == number of cpus having ppi[n + 16] set as NMI */
 static refcount_t *ppi_nmi_refs;
 
@@ -102,6 +136,7 @@
 #define DEFAULT_PMR_VALUE	0xf0
 
 enum gic_intid_range {
+	SGI_RANGE,
 	PPI_RANGE,
 	SPI_RANGE,
 	EPPI_RANGE,
@@ -113,6 +148,8 @@
 static enum gic_intid_range __get_intid_range(irq_hw_number_t hwirq)
 {
 	switch (hwirq) {
+	case 0 ... 15:
+		return SGI_RANGE;
 	case 16 ... 31:
 		return PPI_RANGE;
 	case 32 ... 1019:
@@ -138,15 +175,22 @@
 	return d->hwirq;
 }
 
-static inline int gic_irq_in_rdist(struct irq_data *d)
+static inline bool gic_irq_in_rdist(struct irq_data *d)
 {
-	enum gic_intid_range range = get_intid_range(d);
-	return range == PPI_RANGE || range == EPPI_RANGE;
+	switch (get_intid_range(d)) {
+	case SGI_RANGE:
+	case PPI_RANGE:
+	case EPPI_RANGE:
+		return true;
+	default:
+		return false;
+	}
 }
 
 static inline void __iomem *gic_dist_base(struct irq_data *d)
 {
 	switch (get_intid_range(d)) {
+	case SGI_RANGE:
 	case PPI_RANGE:
 	case EPPI_RANGE:
 		/* SGI+PPI -> SGI_base for this CPU */
@@ -174,7 +218,7 @@
 		}
 		cpu_relax();
 		udelay(1);
-	};
+	}
 }
 
 /* Wait for completion of a distributor change */
@@ -231,7 +275,7 @@
 			break;
 		cpu_relax();
 		udelay(1);
-	};
+	}
 	if (!count)
 		pr_err_ratelimited("redistributor failed to %s...\n",
 				   enable ? "wakeup" : "sleep");
@@ -243,6 +287,7 @@
 static u32 convert_offset_index(struct irq_data *d, u32 offset, u32 *index)
 {
 	switch (get_intid_range(d)) {
+	case SGI_RANGE:
 	case PPI_RANGE:
 	case SPI_RANGE:
 		*index = d->hwirq;
@@ -362,7 +407,7 @@
 {
 	u32 reg;
 
-	if (d->hwirq >= 8192) /* PPI/SPI only */
+	if (d->hwirq >= 8192) /* SGI/PPI/SPI only */
 		return -EINVAL;
 
 	switch (which) {
@@ -529,12 +574,12 @@
 	u32 offset, index;
 	int ret;
 
-	/* Interrupt configuration for SGIs can't be changed */
-	if (irq < 16)
-		return -EINVAL;
-
 	range = get_intid_range(d);
 
+	/* Interrupt configuration for SGIs can't be changed */
+	if (range == SGI_RANGE)
+		return type != IRQ_TYPE_EDGE_RISING ? -EINVAL : 0;
+
 	/* SPIs have restrictions on the supported types */
 	if ((range == SPI_RANGE || range == ESPI_RANGE) &&
 	    type != IRQ_TYPE_LEVEL_HIGH && type != IRQ_TYPE_EDGE_RISING)
@@ -562,6 +607,9 @@
 
 static int gic_irq_set_vcpu_affinity(struct irq_data *d, void *vcpu)
 {
+	if (get_intid_range(d) == SGI_RANGE)
+		return -EINVAL;
+
 	if (vcpu)
 		irqd_set_forwarded_to_vcpu(d);
 	else
@@ -615,18 +663,52 @@
 		nmi_exit();
 }
 
+static u32 do_read_iar(struct pt_regs *regs)
+{
+	u32 iar;
+
+	if (gic_supports_nmi() && unlikely(!interrupts_enabled(regs))) {
+		u64 pmr;
+
+		/*
+		 * We were in a context with IRQs disabled. However, the
+		 * entry code has set PMR to a value that allows any
+		 * interrupt to be acknowledged, and not just NMIs. This can
+		 * lead to surprising effects if the NMI has been retired in
+		 * the meantime, and that there is an IRQ pending. The IRQ
+		 * would then be taken in NMI context, something that nobody
+		 * wants to debug twice.
+		 *
+		 * Until we sort this, drop PMR again to a level that will
+		 * actually only allow NMIs before reading IAR, and then
+		 * restore it to what it was.
+		 */
+		pmr = gic_read_pmr();
+		gic_pmr_mask_irqs();
+		isb();
+
+		iar = gic_read_iar();
+
+		gic_write_pmr(pmr);
+	} else {
+		iar = gic_read_iar();
+	}
+
+	return iar;
+}
+
 static asmlinkage void __exception_irq_entry gic_handle_irq(struct pt_regs *regs)
 {
 	u32 irqnr;
 
-	irqnr = gic_read_iar();
+	irqnr = do_read_iar(regs);
 
 	/* Check for special IDs first */
 	if ((irqnr >= 1020 && irqnr <= 1023))
 		return;
 
 	if (gic_supports_nmi() &&
-	    unlikely(gic_read_rpr() == GICD_INT_NMI_PRI)) {
+	    unlikely(gic_read_rpr() == GICD_INT_RPR_PRI(GICD_INT_NMI_PRI))) {
 		gic_handle_nmi(irqnr, regs);
 		return;
 	}
@@ -636,38 +718,14 @@
 		gic_arch_enable_irqs();
 	}
 
-	/* Treat anything but SGIs in a uniform way */
-	if (likely(irqnr > 15)) {
-		int err;
-
-		if (static_branch_likely(&supports_deactivate_key))
-			gic_write_eoir(irqnr);
-		else
-			isb();
-
-		err = handle_domain_irq(gic_data.domain, irqnr, regs);
-		if (err) {
-			WARN_ONCE(true, "Unexpected interrupt received!\n");
-			gic_deactivate_unhandled(irqnr);
-		}
-		return;
-	}
-	if (irqnr < 16) {
+	if (static_branch_likely(&supports_deactivate_key))
 		gic_write_eoir(irqnr);
-		if (static_branch_likely(&supports_deactivate_key))
-			gic_write_dir(irqnr);
-#ifdef CONFIG_SMP
-		/*
-		 * Unlike GICv2, we don't need an smp_rmb() here.
-		 * The control dependency from gic_read_iar to
-		 * the ISB in gic_write_eoir is enough to ensure
-		 * that any shared data read by handle_IPI will
-		 * be read after the ACK.
-		 */
-		handle_IPI(irqnr, regs);
-#else
-		WARN_ONCE(true, "Unexpected SGI received!\n");
-#endif
+	else
+		isb();
+
+	if (handle_domain_irq(gic_data.domain, irqnr, regs)) {
+		WARN_ONCE(true, "Unexpected interrupt received!\n");
+		gic_deactivate_unhandled(irqnr);
 	}
 }
 
@@ -714,6 +772,7 @@
 	unsigned int i;
 	u64 affinity;
 	void __iomem *base = gic_data.dist_base;
+	u32 val;
 
 	/* Disable the distributor */
 	writel_relaxed(0, base + GICD_CTLR);
@@ -746,9 +805,14 @@
 	/* Now do the common stuff, and wait for the distributor to drain */
 	gic_dist_config(base, GIC_LINE_NR, gic_dist_wait_for_rwp);
 
+	val = GICD_CTLR_ARE_NS | GICD_CTLR_ENABLE_G1A | GICD_CTLR_ENABLE_G1;
+	if (gic_data.rdists.gicd_typer2 & GICD_TYPER2_nASSGIcap) {
+		pr_info("Enabling SGIs without active state\n");
+		val |= GICD_CTLR_nASSGIreq;
+	}
+
 	/* Enable distributor with ARE, Group1 */
-	writel_relaxed(GICD_CTLR_ARE_NS | GICD_CTLR_ENABLE_G1A | GICD_CTLR_ENABLE_G1,
-		       base + GICD_CTLR);
+	writel_relaxed(val, base + GICD_CTLR);
 
 	/*
 	 * Set all global interrupts to the boot CPU only. ARE must be
@@ -819,6 +883,7 @@
 	typer = gic_read_typer(ptr + GICR_TYPER);
 	if ((typer >> 32) == aff) {
 		u64 offset = ptr - region->redist_base;
+		raw_spin_lock_init(&gic_data_rdist()->rd_lock);
 		gic_data_rdist_rd_base() = ptr;
 		gic_data_rdist()->phys_base = region->phys_base + offset;
 
@@ -849,8 +914,38 @@
 					 void __iomem *ptr)
 {
 	u64 typer = gic_read_typer(ptr + GICR_TYPER);
+
+	/* Boot-time cleanip */
+	if ((typer & GICR_TYPER_VLPIS) && (typer & GICR_TYPER_RVPEID)) {
+		u64 val;
+
+		/* Deactivate any present vPE */
+		val = gicr_read_vpendbaser(ptr + SZ_128K + GICR_VPENDBASER);
+		if (val & GICR_VPENDBASER_Valid)
+			gicr_write_vpendbaser(GICR_VPENDBASER_PendingLast,
+					      ptr + SZ_128K + GICR_VPENDBASER);
+
+		/* Mark the VPE table as invalid */
+		val = gicr_read_vpropbaser(ptr + SZ_128K + GICR_VPROPBASER);
+		val &= ~GICR_VPROPBASER_4_1_VALID;
+		gicr_write_vpropbaser(val, ptr + SZ_128K + GICR_VPROPBASER);
+	}
+
 	gic_data.rdists.has_vlpis &= !!(typer & GICR_TYPER_VLPIS);
-	gic_data.rdists.has_direct_lpi &= !!(typer & GICR_TYPER_DirectLPIS);
+
+	/* RVPEID implies some form of DirectLPI, no matter what the doc says... :-/ */
+	gic_data.rdists.has_rvpeid &= !!(typer & GICR_TYPER_RVPEID);
+	gic_data.rdists.has_direct_lpi &= (!!(typer & GICR_TYPER_DirectLPIS) |
+					   gic_data.rdists.has_rvpeid);
+	gic_data.rdists.has_vpend_valid_dirty &= !!(typer & GICR_TYPER_DIRTY);
+
+	/* Detect non-sensical configurations */
+	if (WARN_ON_ONCE(gic_data.rdists.has_rvpeid && !gic_data.rdists.has_vlpis)) {
+		gic_data.rdists.has_direct_lpi = false;
+		gic_data.rdists.has_vlpis = false;
+		gic_data.rdists.has_rvpeid = false;
+	}
+
 	gic_data.ppi_nr = min(GICR_TYPER_NR_PPIS(typer), gic_data.ppi_nr);
 
 	return 1;
@@ -863,9 +958,11 @@
 	if (WARN_ON(gic_data.ppi_nr == UINT_MAX))
 		gic_data.ppi_nr = 0;
 	pr_info("%d PPIs implemented\n", gic_data.ppi_nr);
-	pr_info("%sVLPI support, %sdirect LPI support\n",
-		!gic_data.rdists.has_vlpis ? "no " : "",
-		!gic_data.rdists.has_direct_lpi ? "no " : "");
+	if (gic_data.rdists.has_vlpis)
+		pr_info("GICv4 features: %s%s%s\n",
+			gic_data.rdists.has_direct_lpi ? "DirectLPI " : "",
+			gic_data.rdists.has_rvpeid ? "RVPEID " : "",
+			gic_data.rdists.has_vpend_valid_dirty ? "Valid+Dirty " : "");
 }
 
 /* Check whether it's single security state view */
@@ -899,14 +996,20 @@
 	/* Set priority mask register */
 	if (!gic_prio_masking_enabled()) {
 		write_gicreg(DEFAULT_PMR_VALUE, ICC_PMR_EL1);
-	} else {
+	} else if (gic_supports_nmi()) {
 		/*
 		 * Mismatch configuration with boot CPU, the system is likely
 		 * to die as interrupt masking will not work properly on all
 		 * CPUs
+		 *
+		 * The boot CPU calls this function before enabling NMI support,
+		 * and as a result we'll never see this warning in the boot path
+		 * for that CPU.
 		 */
-		WARN_ON(gic_supports_nmi() && group0 &&
-			!gic_dist_security_disabled());
+		if (static_branch_unlikely(&gic_nonsecure_priorities))
+			WARN_ON(!group0 || gic_dist_security_disabled());
+		else
+			WARN_ON(group0 && !gic_dist_security_disabled());
 	}
 
 	/*
@@ -932,10 +1035,10 @@
 		case 7:
 			write_gicreg(0, ICC_AP0R3_EL1);
 			write_gicreg(0, ICC_AP0R2_EL1);
-		/* Fall through */
+			fallthrough;
 		case 6:
 			write_gicreg(0, ICC_AP0R1_EL1);
-		/* Fall through */
+			fallthrough;
 		case 5:
 		case 4:
 			write_gicreg(0, ICC_AP0R0_EL1);
@@ -949,10 +1052,10 @@
 	case 7:
 		write_gicreg(0, ICC_AP1R3_EL1);
 		write_gicreg(0, ICC_AP1R2_EL1);
-		/* Fall through */
+		fallthrough;
 	case 6:
 		write_gicreg(0, ICC_AP1R1_EL1);
-		/* Fall through */
+		fallthrough;
 	case 5:
 	case 4:
 		write_gicreg(0, ICC_AP1R0_EL1);
@@ -1092,11 +1195,11 @@
 	gic_write_sgi1r(val);
 }
 
-static void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
+static void gic_ipi_send_mask(struct irq_data *d, const struct cpumask *mask)
 {
 	int cpu;
 
-	if (WARN_ON(irq >= 16))
+	if (WARN_ON(d->hwirq >= 16))
 		return;
 
 	/*
@@ -1110,19 +1213,33 @@
 		u16 tlist;
 
 		tlist = gic_compute_target_list(&cpu, mask, cluster_id);
-		gic_send_sgi(cluster_id, tlist, irq);
+		gic_send_sgi(cluster_id, tlist, d->hwirq);
 	}
 
 	/* Force the above writes to ICC_SGI1R_EL1 to be executed */
 	isb();
 }
 
-static void gic_smp_init(void)
+static void __init gic_smp_init(void)
 {
-	set_smp_cross_call(gic_raise_softirq);
+	struct irq_fwspec sgi_fwspec = {
+		.fwnode		= gic_data.fwnode,
+		.param_count	= 1,
+	};
+	int base_sgi;
+
 	cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_GIC_STARTING,
 				  "irqchip/arm/gicv3:starting",
 				  gic_starting_cpu, NULL);
+
+	/* Register all 8 non-secure SGIs */
+	base_sgi = __irq_domain_alloc_irqs(gic_data.domain, -1, 8,
+					   NUMA_NO_NODE, &sgi_fwspec,
+					   false, NULL);
+	if (WARN_ON(base_sgi <= 0))
+		return;
+
+	set_smp_ipi_range(base_sgi, 8);
 }
 
 static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
@@ -1171,9 +1288,15 @@
 }
 #else
 #define gic_set_affinity	NULL
+#define gic_ipi_send_mask	NULL
 #define gic_smp_init()		do { } while(0)
 #endif
 
+static int gic_retrigger(struct irq_data *data)
+{
+	return !gic_irq_set_irqchip_state(data, IRQCHIP_STATE_PENDING, true);
+}
+
 #ifdef CONFIG_CPU_PM
 static int gic_cpu_pm_notifier(struct notifier_block *self,
 			       unsigned long cmd, void *v)
@@ -1209,10 +1332,12 @@
 	.irq_eoi		= gic_eoi_irq,
 	.irq_set_type		= gic_set_type,
 	.irq_set_affinity	= gic_set_affinity,
+	.irq_retrigger          = gic_retrigger,
 	.irq_get_irqchip_state	= gic_irq_get_irqchip_state,
 	.irq_set_irqchip_state	= gic_irq_set_irqchip_state,
 	.irq_nmi_setup		= gic_irq_nmi_setup,
 	.irq_nmi_teardown	= gic_irq_nmi_teardown,
+	.ipi_send_mask		= gic_ipi_send_mask,
 	.flags			= IRQCHIP_SET_TYPE_MASKED |
 				  IRQCHIP_SKIP_SET_WAKE |
 				  IRQCHIP_MASK_ON_SUSPEND,
@@ -1225,11 +1350,13 @@
 	.irq_eoi		= gic_eoimode1_eoi_irq,
 	.irq_set_type		= gic_set_type,
 	.irq_set_affinity	= gic_set_affinity,
+	.irq_retrigger          = gic_retrigger,
 	.irq_get_irqchip_state	= gic_irq_get_irqchip_state,
 	.irq_set_irqchip_state	= gic_irq_set_irqchip_state,
 	.irq_set_vcpu_affinity	= gic_irq_set_vcpu_affinity,
 	.irq_nmi_setup		= gic_irq_nmi_setup,
 	.irq_nmi_teardown	= gic_irq_nmi_teardown,
+	.ipi_send_mask		= gic_ipi_send_mask,
 	.flags			= IRQCHIP_SET_TYPE_MASKED |
 				  IRQCHIP_SKIP_SET_WAKE |
 				  IRQCHIP_MASK_ON_SUSPEND,
@@ -1239,17 +1366,24 @@
 			      irq_hw_number_t hw)
 {
 	struct irq_chip *chip = &gic_chip;
+	struct irq_data *irqd = irq_desc_get_irq_data(irq_to_desc(irq));
 
 	if (static_branch_likely(&supports_deactivate_key))
 		chip = &gic_eoimode1_chip;
 
 	switch (__get_intid_range(hw)) {
+	case SGI_RANGE:
+		irq_set_percpu_devid(irq);
+		irq_domain_set_info(d, irq, hw, chip, d->host_data,
+				    handle_percpu_devid_fasteoi_ipi,
+				    NULL, NULL);
+		break;
+
 	case PPI_RANGE:
 	case EPPI_RANGE:
 		irq_set_percpu_devid(irq);
 		irq_domain_set_info(d, irq, hw, chip, d->host_data,
 				    handle_percpu_devid_irq, NULL, NULL);
-		irq_set_status_flags(irq, IRQ_NOAUTOEN);
 		break;
 
 	case SPI_RANGE:
@@ -1257,7 +1391,7 @@
 		irq_domain_set_info(d, irq, hw, chip, d->host_data,
 				    handle_fasteoi_irq, NULL, NULL);
 		irq_set_probe(irq);
-		irqd_set_single_target(irq_desc_get_irq_data(irq_to_desc(irq)));
+		irqd_set_single_target(irqd);
 		break;
 
 	case LPI_RANGE:
@@ -1271,16 +1405,22 @@
 		return -EPERM;
 	}
 
+	/* Prevents SW retriggers which mess up the ACK/EOI ordering */
+	irqd_set_handle_enforce_irqctx(irqd);
 	return 0;
 }
 
-#define GIC_IRQ_TYPE_PARTITION	(GIC_IRQ_TYPE_LPI + 1)
-
 static int gic_irq_domain_translate(struct irq_domain *d,
 				    struct irq_fwspec *fwspec,
 				    unsigned long *hwirq,
 				    unsigned int *type)
 {
+	if (fwspec->param_count == 1 && fwspec->param[0] < 16) {
+		*hwirq = fwspec->param[0];
+		*type = IRQ_TYPE_EDGE_RISING;
+		return 0;
+	}
+
 	if (is_of_node(fwspec->fwnode)) {
 		if (fwspec->param_count < 3)
 			return -EINVAL;
@@ -1441,6 +1581,15 @@
 	return true;
 }
 
+static bool gic_enable_quirk_cavium_38539(void *data)
+{
+	struct gic_chip_data *d = data;
+
+	d->flags |= FLAGS_WORKAROUND_CAVIUM_ERRATUM_38539;
+
+	return true;
+}
+
 static bool gic_enable_quirk_hip06_07(void *data)
 {
 	struct gic_chip_data *d = data;
@@ -1480,6 +1629,19 @@
 		.init	= gic_enable_quirk_hip06_07,
 	},
 	{
+		/*
+		 * Reserved register accesses generate a Synchronous
+		 * External Abort. This erratum applies to:
+		 * - ThunderX: CN88xx
+		 * - OCTEON TX: CN83xx, CN81xx
+		 * - OCTEON TX2: CN93xx, CN96xx, CN98xx, CNF95xx*
+		 */
+		.desc	= "GICv3: Cavium erratum 38539",
+		.iidr	= 0xa000034c,
+		.mask	= 0xe8f00fff,
+		.init	= gic_enable_quirk_cavium_38539,
+	},
+	{
 	}
 };
 
@@ -1490,11 +1652,6 @@
 	if (!gic_prio_masking_enabled())
 		return;
 
-	if (gic_has_group0() && !gic_dist_security_disabled()) {
-		pr_warn("SCR_EL3.FIQ is cleared, cannot enable use of pseudo-NMIs\n");
-		return;
-	}
-
 	ppi_nmi_refs = kcalloc(gic_data.ppi_nr, sizeof(*ppi_nmi_refs), GFP_KERNEL);
 	if (!ppi_nmi_refs)
 		return;
@@ -1502,6 +1659,47 @@
 	for (i = 0; i < gic_data.ppi_nr; i++)
 		refcount_set(&ppi_nmi_refs[i], 0);
 
+	/*
+	 * Linux itself doesn't use 1:N distribution, so has no need to
+	 * set PMHE. The only reason to have it set is if EL3 requires it
+	 * (and we can't change it).
+	 */
+	if (gic_read_ctlr() & ICC_CTLR_EL1_PMHE_MASK)
+		static_branch_enable(&gic_pmr_sync);
+
+	pr_info("Pseudo-NMIs enabled using %s ICC_PMR_EL1 synchronisation\n",
+		static_branch_unlikely(&gic_pmr_sync) ? "forced" : "relaxed");
+
+	/*
+	 * How priority values are used by the GIC depends on two things:
+	 * the security state of the GIC (controlled by the GICD_CTRL.DS bit)
+	 * and if Group 0 interrupts can be delivered to Linux in the non-secure
+	 * world as FIQs (controlled by the SCR_EL3.FIQ bit). These affect the
+	 * the ICC_PMR_EL1 register and the priority that software assigns to
+	 * interrupts:
+	 *
+	 * GICD_CTRL.DS | SCR_EL3.FIQ | ICC_PMR_EL1 | Group 1 priority
+	 * -----------------------------------------------------------
+	 *      1       |      -      |  unchanged  |    unchanged
+	 * -----------------------------------------------------------
+	 *      0       |      1      |  non-secure |    non-secure
+	 * -----------------------------------------------------------
+	 *      0       |      0      |  unchanged  |    non-secure
+	 *
+	 * where non-secure means that the value is right-shifted by one and the
+	 * MSB bit set, to make it fit in the non-secure priority range.
+	 *
+	 * In the first two cases, where ICC_PMR_EL1 and the interrupt priority
+	 * are both either modified or unchanged, we can use the same set of
+	 * priorities.
+	 *
+	 * In the last case, where only the interrupt priorities are modified to
+	 * be in the non-secure range, we use a different PMR value to mask IRQs
+	 * and the rest of the values that we use remain unchanged.
+	 */
+	if (gic_has_group0() && !gic_dist_security_disabled())
+		static_branch_enable(&gic_nonsecure_priorities);
+
 	static_branch_enable(&supports_pseudo_nmis);
 
 	if (static_branch_likely(&supports_deactivate_key))
@@ -1542,18 +1740,29 @@
 
 	pr_info("%d SPIs implemented\n", GIC_LINE_NR - 32);
 	pr_info("%d Extended SPIs implemented\n", GIC_ESPI_NR);
+
+	/*
+	 * ThunderX1 explodes on reading GICD_TYPER2, in violation of the
+	 * architecture spec (which says that reserved registers are RES0).
+	 */
+	if (!(gic_data.flags & FLAGS_WORKAROUND_CAVIUM_ERRATUM_38539))
+		gic_data.rdists.gicd_typer2 = readl_relaxed(gic_data.dist_base + GICD_TYPER2);
+
 	gic_data.domain = irq_domain_create_tree(handle, &gic_irq_domain_ops,
 						 &gic_data);
-	irq_domain_update_bus_token(gic_data.domain, DOMAIN_BUS_WIRED);
 	gic_data.rdists.rdist = alloc_percpu(typeof(*gic_data.rdists.rdist));
+	gic_data.rdists.has_rvpeid = true;
 	gic_data.rdists.has_vlpis = true;
 	gic_data.rdists.has_direct_lpi = true;
+	gic_data.rdists.has_vpend_valid_dirty = true;
 
 	if (WARN_ON(!gic_data.domain) || WARN_ON(!gic_data.rdists.rdist)) {
 		err = -ENOMEM;
 		goto out_free;
 	}
 
+	irq_domain_update_bus_token(gic_data.domain, DOMAIN_BUS_WIRED);
+
 	gic_data.has_rss = !!(typer & GICD_TYPER_RSS);
 	pr_info("Distributor has %sRange Selector support\n",
 		gic_data.has_rss ? "" : "no ");
@@ -1568,9 +1777,9 @@
 
 	gic_update_rdist_properties();
 
-	gic_smp_init();
 	gic_dist_init();
 	gic_cpu_init();
+	gic_smp_init();
 	gic_cpu_pm_init();
 
 	if (gic_dist_supports_lpis()) {
@@ -1719,6 +1928,7 @@
 		gic_v3_kvm_info.vcpu = r;
 
 	gic_v3_kvm_info.has_v4 = gic_data.rdists.has_vlpis;
+	gic_v3_kvm_info.has_v4_1 = gic_data.rdists.has_rvpeid;
 	gic_set_kvm_info(&gic_v3_kvm_info);
 }
 
@@ -2034,11 +2244,12 @@
 	}
 
 	gic_v3_kvm_info.has_v4 = gic_data.rdists.has_vlpis;
+	gic_v3_kvm_info.has_v4_1 = gic_data.rdists.has_rvpeid;
 	gic_set_kvm_info(&gic_v3_kvm_info);
 }
 
 static int __init
-gic_acpi_init(struct acpi_subtable_header *header, const unsigned long end)
+gic_acpi_init(union acpi_subtable_headers *header, const unsigned long end)
 {
 	struct acpi_madt_generic_distributor *dist;
 	struct fwnode_handle *domain_handle;
diff --git a/drivers/irqchip/irq-gic-v4.c b/drivers/irqchip/irq-gic-v4.c
index 563e87e..0c18714 100644
--- a/drivers/irqchip/irq-gic-v4.c
+++ b/drivers/irqchip/irq-gic-v4.c
@@ -85,6 +85,53 @@
 
 static struct irq_domain *gic_domain;
 static const struct irq_domain_ops *vpe_domain_ops;
+static const struct irq_domain_ops *sgi_domain_ops;
+
+static bool has_v4_1(void)
+{
+	return !!sgi_domain_ops;
+}
+
+static int its_alloc_vcpu_sgis(struct its_vpe *vpe, int idx)
+{
+	char *name;
+	int sgi_base;
+
+	if (!has_v4_1())
+		return 0;
+
+	name = kasprintf(GFP_KERNEL, "GICv4-sgi-%d", task_pid_nr(current));
+	if (!name)
+		goto err;
+
+	vpe->fwnode = irq_domain_alloc_named_id_fwnode(name, idx);
+	if (!vpe->fwnode)
+		goto err;
+
+	kfree(name);
+	name = NULL;
+
+	vpe->sgi_domain = irq_domain_create_linear(vpe->fwnode, 16,
+						   sgi_domain_ops, vpe);
+	if (!vpe->sgi_domain)
+		goto err;
+
+	sgi_base = __irq_domain_alloc_irqs(vpe->sgi_domain, -1, 16,
+					       NUMA_NO_NODE, vpe,
+					       false, NULL);
+	if (sgi_base <= 0)
+		goto err;
+
+	return 0;
+
+err:
+	if (vpe->sgi_domain)
+		irq_domain_remove(vpe->sgi_domain);
+	if (vpe->fwnode)
+		irq_domain_free_fwnode(vpe->fwnode);
+	kfree(name);
+	return -ENOMEM;
+}
 
 int its_alloc_vcpu_irqs(struct its_vm *vm)
 {
@@ -112,8 +159,13 @@
 	if (vpe_base_irq <= 0)
 		goto err;
 
-	for (i = 0; i < vm->nr_vpes; i++)
+	for (i = 0; i < vm->nr_vpes; i++) {
+		int ret;
 		vm->vpes[i]->irq = vpe_base_irq + i;
+		ret = its_alloc_vcpu_sgis(vm->vpes[i], i);
+		if (ret)
+			goto err;
+	}
 
 	return 0;
 
@@ -126,8 +178,28 @@
 	return -ENOMEM;
 }
 
+static void its_free_sgi_irqs(struct its_vm *vm)
+{
+	int i;
+
+	if (!has_v4_1())
+		return;
+
+	for (i = 0; i < vm->nr_vpes; i++) {
+		unsigned int irq = irq_find_mapping(vm->vpes[i]->sgi_domain, 0);
+
+		if (WARN_ON(!irq))
+			continue;
+
+		irq_domain_free_irqs(irq, 16);
+		irq_domain_remove(vm->vpes[i]->sgi_domain);
+		irq_domain_free_fwnode(vm->vpes[i]->fwnode);
+	}
+}
+
 void its_free_vcpu_irqs(struct its_vm *vm)
 {
+	its_free_sgi_irqs(vm);
 	irq_domain_free_irqs(vm->vpes[0]->irq, vm->nr_vpes);
 	irq_domain_remove(vm->domain);
 	irq_domain_free_fwnode(vm->fwnode);
@@ -138,15 +210,52 @@
 	return irq_set_vcpu_affinity(vpe->irq, info);
 }
 
-int its_schedule_vpe(struct its_vpe *vpe, bool on)
+int its_make_vpe_non_resident(struct its_vpe *vpe, bool db)
 {
-	struct its_cmd_info info;
+	struct irq_desc *desc = irq_to_desc(vpe->irq);
+	struct its_cmd_info info = { };
+	int ret;
 
 	WARN_ON(preemptible());
 
-	info.cmd_type = on ? SCHEDULE_VPE : DESCHEDULE_VPE;
+	info.cmd_type = DESCHEDULE_VPE;
+	if (has_v4_1()) {
+		/* GICv4.1 can directly deal with doorbells */
+		info.req_db = db;
+	} else {
+		/* Undo the nested disable_irq() calls... */
+		while (db && irqd_irq_disabled(&desc->irq_data))
+			enable_irq(vpe->irq);
+	}
 
-	return its_send_vpe_cmd(vpe, &info);
+	ret = its_send_vpe_cmd(vpe, &info);
+	if (!ret)
+		vpe->resident = false;
+
+	return ret;
+}
+
+int its_make_vpe_resident(struct its_vpe *vpe, bool g0en, bool g1en)
+{
+	struct its_cmd_info info = { };
+	int ret;
+
+	WARN_ON(preemptible());
+
+	info.cmd_type = SCHEDULE_VPE;
+	if (has_v4_1()) {
+		info.g0en = g0en;
+		info.g1en = g1en;
+	} else {
+		/* Disabled the doorbell, as we're about to enter the guest */
+		disable_irq_nosync(vpe->irq);
+	}
+
+	ret = its_send_vpe_cmd(vpe, &info);
+	if (!ret)
+		vpe->resident = true;
+
+	return ret;
 }
 
 int its_invall_vpe(struct its_vpe *vpe)
@@ -211,12 +320,28 @@
 	return irq_set_vcpu_affinity(irq, &info);
 }
 
-int its_init_v4(struct irq_domain *domain, const struct irq_domain_ops *ops)
+int its_prop_update_vsgi(int irq, u8 priority, bool group)
+{
+	struct its_cmd_info info = {
+		.cmd_type = PROP_UPDATE_VSGI,
+		{
+			.priority	= priority,
+			.group		= group,
+		},
+	};
+
+	return irq_set_vcpu_affinity(irq, &info);
+}
+
+int its_init_v4(struct irq_domain *domain,
+		const struct irq_domain_ops *vpe_ops,
+		const struct irq_domain_ops *sgi_ops)
 {
 	if (domain) {
 		pr_info("ITS: Enabling GICv4 support\n");
 		gic_domain = domain;
-		vpe_domain_ops = ops;
+		vpe_domain_ops = vpe_ops;
+		sgi_domain_ops = sgi_ops;
 		return 0;
 	}
 
diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index 882204d..176f5f0 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -83,9 +83,6 @@
 #endif
 	struct irq_domain *domain;
 	unsigned int gic_irqs;
-#ifdef CONFIG_GIC_NON_BANKED
-	void __iomem *(*get_base)(union gic_base *);
-#endif
 };
 
 #ifdef CONFIG_BL_SWITCHER
@@ -110,6 +107,8 @@
 
 #endif
 
+static DEFINE_STATIC_KEY_FALSE(needs_rmw_access);
+
 /*
  * The GIC mapping of CPU interfaces does not necessarily match
  * the logical CPU numbering.  Let's use a mapping as returned
@@ -124,36 +123,30 @@
 
 static struct gic_kvm_info gic_v2_kvm_info;
 
+static DEFINE_PER_CPU(u32, sgi_intid);
+
 #ifdef CONFIG_GIC_NON_BANKED
-static void __iomem *gic_get_percpu_base(union gic_base *base)
+static DEFINE_STATIC_KEY_FALSE(frankengic_key);
+
+static void enable_frankengic(void)
 {
-	return raw_cpu_read(*base->percpu_base);
+	static_branch_enable(&frankengic_key);
 }
 
-static void __iomem *gic_get_common_base(union gic_base *base)
+static inline void __iomem *__get_base(union gic_base *base)
 {
+	if (static_branch_unlikely(&frankengic_key))
+		return raw_cpu_read(*base->percpu_base);
+
 	return base->common_base;
 }
 
-static inline void __iomem *gic_data_dist_base(struct gic_chip_data *data)
-{
-	return data->get_base(&data->dist_base);
-}
-
-static inline void __iomem *gic_data_cpu_base(struct gic_chip_data *data)
-{
-	return data->get_base(&data->cpu_base);
-}
-
-static inline void gic_set_base_accessor(struct gic_chip_data *data,
-					 void __iomem *(*f)(union gic_base *))
-{
-	data->get_base = f;
-}
+#define gic_data_dist_base(d)	__get_base(&(d)->dist_base)
+#define gic_data_cpu_base(d)	__get_base(&(d)->cpu_base)
 #else
 #define gic_data_dist_base(d)	((d)->dist_base.common_base)
 #define gic_data_cpu_base(d)	((d)->cpu_base.common_base)
-#define gic_set_base_accessor(d, f)
+#define enable_frankengic()	do { } while(0)
 #endif
 
 static inline void __iomem *gic_dist_base(struct irq_data *d)
@@ -226,16 +219,26 @@
 
 static void gic_eoi_irq(struct irq_data *d)
 {
-	writel_relaxed(gic_irq(d), gic_cpu_base(d) + GIC_CPU_EOI);
+	u32 hwirq = gic_irq(d);
+
+	if (hwirq < 16)
+		hwirq = this_cpu_read(sgi_intid);
+
+	writel_relaxed(hwirq, gic_cpu_base(d) + GIC_CPU_EOI);
 }
 
 static void gic_eoimode1_eoi_irq(struct irq_data *d)
 {
+	u32 hwirq = gic_irq(d);
+
 	/* Do not deactivate an IRQ forwarded to a vcpu. */
 	if (irqd_is_forwarded_to_vcpu(d))
 		return;
 
-	writel_relaxed(gic_irq(d), gic_cpu_base(d) + GIC_CPU_DEACTIVATE);
+	if (hwirq < 16)
+		hwirq = this_cpu_read(sgi_intid);
+
+	writel_relaxed(hwirq, gic_cpu_base(d) + GIC_CPU_DEACTIVATE);
 }
 
 static int gic_irq_set_irqchip_state(struct irq_data *d,
@@ -295,7 +298,7 @@
 
 	/* Interrupt configuration for SGIs can't be changed */
 	if (gicirq < 16)
-		return -EINVAL;
+		return type != IRQ_TYPE_EDGE_RISING ? -EINVAL : 0;
 
 	/* SPIs have restrictions on the supported types */
 	if (gicirq >= 32 && type != IRQ_TYPE_LEVEL_HIGH &&
@@ -315,7 +318,7 @@
 static int gic_irq_set_vcpu_affinity(struct irq_data *d, void *vcpu)
 {
 	/* Only interrupts on the primary GIC can be forwarded to a vcpu. */
-	if (cascading_gic_irq(d))
+	if (cascading_gic_irq(d) || gic_irq(d) < 16)
 		return -EINVAL;
 
 	if (vcpu)
@@ -325,27 +328,10 @@
 	return 0;
 }
 
-#ifdef CONFIG_SMP
-static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
-			    bool force)
+static int gic_retrigger(struct irq_data *data)
 {
-	void __iomem *reg = gic_dist_base(d) + GIC_DIST_TARGET + gic_irq(d);
-	unsigned int cpu;
-
-	if (!force)
-		cpu = cpumask_any_and(mask_val, cpu_online_mask);
-	else
-		cpu = cpumask_first(mask_val);
-
-	if (cpu >= NR_GIC_CPU_IF || cpu >= nr_cpu_ids)
-		return -EINVAL;
-
-	writeb_relaxed(gic_cpu_map[cpu], reg);
-	irq_data_update_effective_affinity(d, cpumask_of(cpu));
-
-	return IRQ_SET_MASK_OK_DONE;
+	return !gic_irq_set_irqchip_state(data, IRQCHIP_STATE_PENDING, true);
 }
-#endif
 
 static void __exception_irq_entry gic_handle_irq(struct pt_regs *regs)
 {
@@ -357,31 +343,33 @@
 		irqstat = readl_relaxed(cpu_base + GIC_CPU_INTACK);
 		irqnr = irqstat & GICC_IAR_INT_ID_MASK;
 
-		if (likely(irqnr > 15 && irqnr < 1020)) {
-			if (static_branch_likely(&supports_deactivate_key))
-				writel_relaxed(irqstat, cpu_base + GIC_CPU_EOI);
-			isb();
-			handle_domain_irq(gic->domain, irqnr, regs);
-			continue;
-		}
-		if (irqnr < 16) {
+		if (unlikely(irqnr >= 1020))
+			break;
+
+		if (static_branch_likely(&supports_deactivate_key))
 			writel_relaxed(irqstat, cpu_base + GIC_CPU_EOI);
-			if (static_branch_likely(&supports_deactivate_key))
-				writel_relaxed(irqstat, cpu_base + GIC_CPU_DEACTIVATE);
-#ifdef CONFIG_SMP
-			/*
-			 * Ensure any shared data written by the CPU sending
-			 * the IPI is read after we've read the ACK register
-			 * on the GIC.
-			 *
-			 * Pairs with the write barrier in gic_raise_softirq
-			 */
+		isb();
+
+		/*
+		 * Ensure any shared data written by the CPU sending the IPI
+		 * is read after we've read the ACK register on the GIC.
+		 *
+		 * Pairs with the write barrier in gic_ipi_send_mask
+		 */
+		if (irqnr <= 15) {
 			smp_rmb();
-			handle_IPI(irqnr, regs);
-#endif
-			continue;
+
+			/*
+			 * The GIC encodes the source CPU in GICC_IAR,
+			 * leading to the deactivation to fail if not
+			 * written back as is to GICC_EOI.  Stash the INTID
+			 * away for gic_eoi_irq() to write back.  This only
+			 * works because we don't nest SGIs...
+			 */
+			this_cpu_write(sgi_intid, irqstat);
 		}
-		break;
+
+		handle_domain_irq(gic->domain, irqnr, regs);
 	} while (1);
 }
 
@@ -417,6 +405,7 @@
 	.irq_unmask		= gic_unmask_irq,
 	.irq_eoi		= gic_eoi_irq,
 	.irq_set_type		= gic_set_type,
+	.irq_retrigger          = gic_retrigger,
 	.irq_get_irqchip_state	= gic_irq_get_irqchip_state,
 	.irq_set_irqchip_state	= gic_irq_set_irqchip_state,
 	.flags			= IRQCHIP_SET_TYPE_MASKED |
@@ -728,11 +717,6 @@
 	int i;
 
 	for (i = 0; i < CONFIG_ARM_GIC_MAX_NR; i++) {
-#ifdef CONFIG_GIC_NON_BANKED
-		/* Skip over unused GICs */
-		if (!gic_data[i].get_base)
-			continue;
-#endif
 		switch (cmd) {
 		case CPU_PM_ENTER:
 			gic_cpu_save(&gic_data[i]);
@@ -795,14 +779,56 @@
 #endif
 
 #ifdef CONFIG_SMP
-static void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
+static void rmw_writeb(u8 bval, void __iomem *addr)
+{
+	static DEFINE_RAW_SPINLOCK(rmw_lock);
+	unsigned long offset = (unsigned long)addr & 3UL;
+	unsigned long shift = offset * 8;
+	unsigned long flags;
+	u32 val;
+
+	raw_spin_lock_irqsave(&rmw_lock, flags);
+
+	addr -= offset;
+	val = readl_relaxed(addr);
+	val &= ~GENMASK(shift + 7, shift);
+	val |= bval << shift;
+	writel_relaxed(val, addr);
+
+	raw_spin_unlock_irqrestore(&rmw_lock, flags);
+}
+
+static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
+			    bool force)
+{
+	void __iomem *reg = gic_dist_base(d) + GIC_DIST_TARGET + gic_irq(d);
+	unsigned int cpu;
+
+	if (!force)
+		cpu = cpumask_any_and(mask_val, cpu_online_mask);
+	else
+		cpu = cpumask_first(mask_val);
+
+	if (cpu >= NR_GIC_CPU_IF || cpu >= nr_cpu_ids)
+		return -EINVAL;
+
+	if (static_branch_unlikely(&needs_rmw_access))
+		rmw_writeb(gic_cpu_map[cpu], reg);
+	else
+		writeb_relaxed(gic_cpu_map[cpu], reg);
+	irq_data_update_effective_affinity(d, cpumask_of(cpu));
+
+	return IRQ_SET_MASK_OK_DONE;
+}
+
+static void gic_ipi_send_mask(struct irq_data *d, const struct cpumask *mask)
 {
 	int cpu;
 	unsigned long flags, map = 0;
 
 	if (unlikely(nr_cpu_ids == 1)) {
 		/* Only one CPU? let's do a self-IPI... */
-		writel_relaxed(2 << 24 | irq,
+		writel_relaxed(2 << 24 | d->hwirq,
 			       gic_data_dist_base(&gic_data[0]) + GIC_DIST_SOFTINT);
 		return;
 	}
@@ -820,10 +846,41 @@
 	dmb(ishst);
 
 	/* this always happens on GIC0 */
-	writel_relaxed(map << 16 | irq, gic_data_dist_base(&gic_data[0]) + GIC_DIST_SOFTINT);
+	writel_relaxed(map << 16 | d->hwirq, gic_data_dist_base(&gic_data[0]) + GIC_DIST_SOFTINT);
 
 	gic_unlock_irqrestore(flags);
 }
+
+static int gic_starting_cpu(unsigned int cpu)
+{
+	gic_cpu_init(&gic_data[0]);
+	return 0;
+}
+
+static __init void gic_smp_init(void)
+{
+	struct irq_fwspec sgi_fwspec = {
+		.fwnode		= gic_data[0].domain->fwnode,
+		.param_count	= 1,
+	};
+	int base_sgi;
+
+	cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_GIC_STARTING,
+				  "irqchip/arm/gic:starting",
+				  gic_starting_cpu, NULL);
+
+	base_sgi = __irq_domain_alloc_irqs(gic_data[0].domain, -1, 8,
+					   NUMA_NO_NODE, &sgi_fwspec,
+					   false, NULL);
+	if (WARN_ON(base_sgi <= 0))
+		return;
+
+	set_smp_ipi_range(base_sgi, 8);
+}
+#else
+#define gic_smp_init()		do { } while(0)
+#define gic_set_affinity	NULL
+#define gic_ipi_send_mask	NULL
 #endif
 
 #ifdef CONFIG_BL_SWITCHER
@@ -969,18 +1026,30 @@
 				irq_hw_number_t hw)
 {
 	struct gic_chip_data *gic = d->host_data;
+	struct irq_data *irqd = irq_desc_get_irq_data(irq_to_desc(irq));
 
-	if (hw < 32) {
+	switch (hw) {
+	case 0 ... 15:
+		irq_set_percpu_devid(irq);
+		irq_domain_set_info(d, irq, hw, &gic->chip, d->host_data,
+				    handle_percpu_devid_fasteoi_ipi,
+				    NULL, NULL);
+		break;
+	case 16 ... 31:
 		irq_set_percpu_devid(irq);
 		irq_domain_set_info(d, irq, hw, &gic->chip, d->host_data,
 				    handle_percpu_devid_irq, NULL, NULL);
-		irq_set_status_flags(irq, IRQ_NOAUTOEN);
-	} else {
+		break;
+	default:
 		irq_domain_set_info(d, irq, hw, &gic->chip, d->host_data,
 				    handle_fasteoi_irq, NULL, NULL);
 		irq_set_probe(irq);
-		irqd_set_single_target(irq_desc_get_irq_data(irq_to_desc(irq)));
+		irqd_set_single_target(irqd);
+		break;
 	}
+
+	/* Prevents SW retriggers which mess up the ACK/EOI ordering */
+	irqd_set_handle_enforce_irqctx(irqd);
 	return 0;
 }
 
@@ -993,19 +1062,26 @@
 				    unsigned long *hwirq,
 				    unsigned int *type)
 {
+	if (fwspec->param_count == 1 && fwspec->param[0] < 16) {
+		*hwirq = fwspec->param[0];
+		*type = IRQ_TYPE_EDGE_RISING;
+		return 0;
+	}
+
 	if (is_of_node(fwspec->fwnode)) {
 		if (fwspec->param_count < 3)
 			return -EINVAL;
 
-		/* Get the interrupt number and add 16 to skip over SGIs */
-		*hwirq = fwspec->param[1] + 16;
-
-		/*
-		 * For SPIs, we need to add 16 more to get the GIC irq
-		 * ID number
-		 */
-		if (!fwspec->param[0])
-			*hwirq += 16;
+		switch (fwspec->param[0]) {
+		case 0:			/* SPI */
+			*hwirq = fwspec->param[1] + 32;
+			break;
+		case 1:			/* PPI */
+			*hwirq = fwspec->param[1] + 16;
+			break;
+		default:
+			return -EINVAL;
+		}
 
 		*type = fwspec->param[2] & IRQ_TYPE_SENSE_MASK;
 
@@ -1028,12 +1104,6 @@
 	return -EINVAL;
 }
 
-static int gic_starting_cpu(unsigned int cpu)
-{
-	gic_cpu_init(&gic_data[0]);
-	return 0;
-}
-
 static int gic_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
 				unsigned int nr_irqs, void *arg)
 {
@@ -1080,10 +1150,10 @@
 		gic->chip.irq_set_vcpu_affinity = gic_irq_set_vcpu_affinity;
 	}
 
-#ifdef CONFIG_SMP
-	if (gic == &gic_data[0])
+	if (gic == &gic_data[0]) {
 		gic->chip.irq_set_affinity = gic_set_affinity;
-#endif
+		gic->chip.ipi_send_mask = gic_ipi_send_mask;
+	}
 }
 
 static int gic_init_bases(struct gic_chip_data *gic,
@@ -1113,7 +1183,7 @@
 				gic->raw_cpu_base + offset;
 		}
 
-		gic_set_base_accessor(gic, gic_get_percpu_base);
+		enable_frankengic();
 	} else {
 		/* Normal, sane GIC... */
 		WARN(gic->percpu_offset,
@@ -1121,7 +1191,6 @@
 		     gic->percpu_offset);
 		gic->dist_base.common_base = gic->raw_dist_base;
 		gic->cpu_base.common_base = gic->raw_cpu_base;
-		gic_set_base_accessor(gic, gic_get_common_base);
 	}
 
 	/*
@@ -1200,12 +1269,7 @@
 		 */
 		for (i = 0; i < NR_GIC_CPU_IF; i++)
 			gic_cpu_map[i] = 0xff;
-#ifdef CONFIG_SMP
-		set_smp_cross_call(gic_raise_softirq);
-#endif
-		cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_GIC_STARTING,
-					  "irqchip/arm/gic:starting",
-					  gic_starting_cpu, NULL);
+
 		set_handle_irq(gic_handle_irq);
 		if (static_branch_likely(&supports_deactivate_key))
 			pr_info("GIC: Using split EOI/Deactivate mode\n");
@@ -1222,6 +1286,8 @@
 	ret = gic_init_bases(gic, handle);
 	if (ret)
 		kfree(name);
+	else if (gic == &gic_data[0])
+		gic_smp_init();
 
 	return ret;
 }
@@ -1342,6 +1408,30 @@
 	return true;
 }
 
+static bool gic_enable_rmw_access(void *data)
+{
+	/*
+	 * The EMEV2 class of machines has a broken interconnect, and
+	 * locks up on accesses that are less than 32bit. So far, only
+	 * the affinity setting requires it.
+	 */
+	if (of_machine_is_compatible("renesas,emev2")) {
+		static_branch_enable(&needs_rmw_access);
+		return true;
+	}
+
+	return false;
+}
+
+static const struct gic_quirk gic_quirks[] = {
+	{
+		.desc		= "broken byte access",
+		.compatible	= "arm,pl390",
+		.init		= gic_enable_rmw_access,
+	},
+	{ },
+};
+
 static int gic_of_setup(struct gic_chip_data *gic, struct device_node *node)
 {
 	if (!gic || !node)
@@ -1358,6 +1448,8 @@
 	if (of_property_read_u32(node, "cpu-offset", &gic->percpu_offset))
 		gic->percpu_offset = 0;
 
+	gic_enable_of_quirks(node, gic_quirks, gic);
+
 	return 0;
 
 error:
@@ -1585,7 +1677,7 @@
 	gic_set_kvm_info(&gic_v2_kvm_info);
 }
 
-static int __init gic_v2_acpi_init(struct acpi_subtable_header *header,
+static int __init gic_v2_acpi_init(union acpi_subtable_headers *header,
 				   const unsigned long end)
 {
 	struct acpi_madt_generic_distributor *dist;
diff --git a/drivers/irqchip/irq-hip04.c b/drivers/irqchip/irq-hip04.c
index 130caa1..9b73dcf 100644
--- a/drivers/irqchip/irq-hip04.c
+++ b/drivers/irqchip/irq-hip04.c
@@ -171,6 +171,29 @@
 
 	return IRQ_SET_MASK_OK;
 }
+
+static void hip04_ipi_send_mask(struct irq_data *d, const struct cpumask *mask)
+{
+	int cpu;
+	unsigned long flags, map = 0;
+
+	raw_spin_lock_irqsave(&irq_controller_lock, flags);
+
+	/* Convert our logical CPU mask into a physical one. */
+	for_each_cpu(cpu, mask)
+		map |= hip04_cpu_map[cpu];
+
+	/*
+	 * Ensure that stores to Normal memory are visible to the
+	 * other CPUs before they observe us issuing the IPI.
+	 */
+	dmb(ishst);
+
+	/* this always happens on GIC0 */
+	writel_relaxed(map << 8 | d->hwirq, hip04_data.dist_base + GIC_DIST_SOFTINT);
+
+	raw_spin_unlock_irqrestore(&irq_controller_lock, flags);
+}
 #endif
 
 static void __exception_irq_entry hip04_handle_irq(struct pt_regs *regs)
@@ -182,19 +205,9 @@
 		irqstat = readl_relaxed(cpu_base + GIC_CPU_INTACK);
 		irqnr = irqstat & GICC_IAR_INT_ID_MASK;
 
-		if (likely(irqnr > 15 && irqnr <= HIP04_MAX_IRQS)) {
+		if (irqnr <= HIP04_MAX_IRQS)
 			handle_domain_irq(hip04_data.domain, irqnr, regs);
-			continue;
-		}
-		if (irqnr < 16) {
-			writel_relaxed(irqstat, cpu_base + GIC_CPU_EOI);
-#ifdef CONFIG_SMP
-			handle_IPI(irqnr, regs);
-#endif
-			continue;
-		}
-		break;
-	} while (1);
+	} while (irqnr > HIP04_MAX_IRQS);
 }
 
 static struct irq_chip hip04_irq_chip = {
@@ -205,6 +218,7 @@
 	.irq_set_type		= hip04_irq_set_type,
 #ifdef CONFIG_SMP
 	.irq_set_affinity	= hip04_irq_set_affinity,
+	.ipi_send_mask		= hip04_ipi_send_mask,
 #endif
 	.flags			= IRQCHIP_SET_TYPE_MASKED |
 				  IRQCHIP_SKIP_SET_WAKE |
@@ -279,39 +293,17 @@
 	writel_relaxed(1, base + GIC_CPU_CTRL);
 }
 
-#ifdef CONFIG_SMP
-static void hip04_raise_softirq(const struct cpumask *mask, unsigned int irq)
-{
-	int cpu;
-	unsigned long flags, map = 0;
-
-	raw_spin_lock_irqsave(&irq_controller_lock, flags);
-
-	/* Convert our logical CPU mask into a physical one. */
-	for_each_cpu(cpu, mask)
-		map |= hip04_cpu_map[cpu];
-
-	/*
-	 * Ensure that stores to Normal memory are visible to the
-	 * other CPUs before they observe us issuing the IPI.
-	 */
-	dmb(ishst);
-
-	/* this always happens on GIC0 */
-	writel_relaxed(map << 8 | irq, hip04_data.dist_base + GIC_DIST_SOFTINT);
-
-	raw_spin_unlock_irqrestore(&irq_controller_lock, flags);
-}
-#endif
-
 static int hip04_irq_domain_map(struct irq_domain *d, unsigned int irq,
 				irq_hw_number_t hw)
 {
-	if (hw < 32) {
+	if (hw < 16) {
+		irq_set_percpu_devid(irq);
+		irq_set_chip_and_handler(irq, &hip04_irq_chip,
+					 handle_percpu_devid_fasteoi_ipi);
+	} else if (hw < 32) {
 		irq_set_percpu_devid(irq);
 		irq_set_chip_and_handler(irq, &hip04_irq_chip,
 					 handle_percpu_devid_irq);
-		irq_set_status_flags(irq, IRQ_NOAUTOEN);
 	} else {
 		irq_set_chip_and_handler(irq, &hip04_irq_chip,
 					 handle_fasteoi_irq);
@@ -328,10 +320,13 @@
 				  unsigned long *out_hwirq,
 				  unsigned int *out_type)
 {
-	unsigned long ret = 0;
-
 	if (irq_domain_get_of_node(d) != controller)
 		return -EINVAL;
+	if (intsize == 1 && intspec[0] < 16) {
+		*out_hwirq = intspec[0];
+		*out_type = IRQ_TYPE_EDGE_RISING;
+		return 0;
+	}
 	if (intsize < 3)
 		return -EINVAL;
 
@@ -344,7 +339,7 @@
 
 	*out_type = intspec[2] & IRQ_TYPE_SENSE_MASK;
 
-	return ret;
+	return 0;
 }
 
 static int hip04_irq_starting_cpu(unsigned int cpu)
@@ -361,7 +356,6 @@
 static int __init
 hip04_of_init(struct device_node *node, struct device_node *parent)
 {
-	irq_hw_number_t hwirq_base = 16;
 	int nr_irqs, irq_base, i;
 
 	if (WARN_ON(!node))
@@ -390,24 +384,21 @@
 		nr_irqs = HIP04_MAX_IRQS;
 	hip04_data.nr_irqs = nr_irqs;
 
-	nr_irqs -= hwirq_base; /* calculate # of irqs to allocate */
-
-	irq_base = irq_alloc_descs(-1, hwirq_base, nr_irqs, numa_node_id());
+	irq_base = irq_alloc_descs(-1, 0, nr_irqs, numa_node_id());
 	if (irq_base < 0) {
 		pr_err("failed to allocate IRQ numbers\n");
 		return -EINVAL;
 	}
 
 	hip04_data.domain = irq_domain_add_legacy(node, nr_irqs, irq_base,
-						  hwirq_base,
+						  0,
 						  &hip04_irq_domain_ops,
 						  &hip04_data);
-
 	if (WARN_ON(!hip04_data.domain))
 		return -EINVAL;
 
 #ifdef CONFIG_SMP
-	set_smp_cross_call(hip04_raise_softirq);
+	set_smp_ipi_range(irq_base, 16);
 #endif
 	set_handle_irq(hip04_handle_irq);
 
diff --git a/drivers/irqchip/irq-i8259.c b/drivers/irqchip/irq-i8259.c
index d000870..b6f6aa7 100644
--- a/drivers/irqchip/irq-i8259.c
+++ b/drivers/irqchip/irq-i8259.c
@@ -268,15 +268,6 @@
 	raw_spin_unlock_irqrestore(&i8259A_lock, flags);
 }
 
-/*
- * IRQ2 is cascade interrupt to second interrupt controller
- */
-static struct irqaction irq2 = {
-	.handler = no_action,
-	.name = "cascade",
-	.flags = IRQF_NO_THREAD,
-};
-
 static struct resource pic1_io_resource = {
 	.name = "pic1",
 	.start = PIC_MASTER_CMD,
@@ -311,6 +302,10 @@
  */
 struct irq_domain * __init __init_i8259_irqs(struct device_node *node)
 {
+	/*
+	 * PIC_CASCADE_IR is cascade interrupt to second interrupt controller
+	 */
+	int irq = I8259A_IRQ_BASE + PIC_CASCADE_IR;
 	struct irq_domain *domain;
 
 	insert_resource(&ioport_resource, &pic1_io_resource);
@@ -323,7 +318,8 @@
 	if (!domain)
 		panic("Failed to add i8259 IRQ domain");
 
-	setup_irq(I8259A_IRQ_BASE + PIC_CASCADE_IR, &irq2);
+	if (request_irq(irq, no_action, IRQF_NO_THREAD, "cascade", NULL))
+		pr_err("Failed to register cascade interrupt\n");
 	register_syscore_ops(&i8259_syscore_ops);
 	return domain;
 }
diff --git a/drivers/irqchip/irq-imx-gpcv2.c b/drivers/irqchip/irq-imx-gpcv2.c
index 4f74c15..7031ef4 100644
--- a/drivers/irqchip/irq-imx-gpcv2.c
+++ b/drivers/irqchip/irq-imx-gpcv2.c
@@ -259,7 +259,7 @@
 		case 4:
 			writel_relaxed(~0, reg + GPC_IMR1_CORE2);
 			writel_relaxed(~0, reg + GPC_IMR1_CORE3);
-			/* fall through */
+			fallthrough;
 		case 2:
 			writel_relaxed(~0, reg + GPC_IMR1_CORE0);
 			writel_relaxed(~0, reg + GPC_IMR1_CORE1);
diff --git a/drivers/irqchip/irq-imx-intmux.c b/drivers/irqchip/irq-imx-intmux.c
new file mode 100644
index 0000000..7709f97
--- /dev/null
+++ b/drivers/irqchip/irq-imx-intmux.c
@@ -0,0 +1,368 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright 2017 NXP
+
+/*                     INTMUX Block Diagram
+ *
+ *                               ________________
+ * interrupt source #  0  +---->|                |
+ *                        |     |                |
+ * interrupt source #  1  +++-->|                |
+ *            ...         | |   |   channel # 0  |--------->interrupt out # 0
+ *            ...         | |   |                |
+ *            ...         | |   |                |
+ * interrupt source # X-1 +++-->|________________|
+ *                        | | |
+ *                        | | |
+ *                        | | |  ________________
+ *                        +---->|                |
+ *                        | | | |                |
+ *                        | +-->|                |
+ *                        | | | |   channel # 1  |--------->interrupt out # 1
+ *                        | | +>|                |
+ *                        | | | |                |
+ *                        | | | |________________|
+ *                        | | |
+ *                        | | |
+ *                        | | |       ...
+ *                        | | |       ...
+ *                        | | |
+ *                        | | |  ________________
+ *                        +---->|                |
+ *                          | | |                |
+ *                          +-->|                |
+ *                            | |   channel # N  |--------->interrupt out # N
+ *                            +>|                |
+ *                              |                |
+ *                              |________________|
+ *
+ *
+ * N: Interrupt Channel Instance Number (N=7)
+ * X: Interrupt Source Number for each channel (X=32)
+ *
+ * The INTMUX interrupt multiplexer has 8 channels, each channel receives 32
+ * interrupt sources and generates 1 interrupt output.
+ *
+ */
+
+#include <linux/clk.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/irqchip/chained_irq.h>
+#include <linux/irqdomain.h>
+#include <linux/kernel.h>
+#include <linux/of_irq.h>
+#include <linux/of_platform.h>
+#include <linux/spinlock.h>
+#include <linux/pm_runtime.h>
+
+#define CHANIER(n)	(0x10 + (0x40 * n))
+#define CHANIPR(n)	(0x20 + (0x40 * n))
+
+#define CHAN_MAX_NUM		0x8
+
+struct intmux_irqchip_data {
+	struct irq_chip		chip;
+	u32			saved_reg;
+	int			chanidx;
+	int			irq;
+	struct irq_domain	*domain;
+};
+
+struct intmux_data {
+	raw_spinlock_t			lock;
+	void __iomem			*regs;
+	struct clk			*ipg_clk;
+	int				channum;
+	struct intmux_irqchip_data	irqchip_data[];
+};
+
+static void imx_intmux_irq_mask(struct irq_data *d)
+{
+	struct intmux_irqchip_data *irqchip_data = d->chip_data;
+	int idx = irqchip_data->chanidx;
+	struct intmux_data *data = container_of(irqchip_data, struct intmux_data,
+						irqchip_data[idx]);
+	unsigned long flags;
+	void __iomem *reg;
+	u32 val;
+
+	raw_spin_lock_irqsave(&data->lock, flags);
+	reg = data->regs + CHANIER(idx);
+	val = readl_relaxed(reg);
+	/* disable the interrupt source of this channel */
+	val &= ~BIT(d->hwirq);
+	writel_relaxed(val, reg);
+	raw_spin_unlock_irqrestore(&data->lock, flags);
+}
+
+static void imx_intmux_irq_unmask(struct irq_data *d)
+{
+	struct intmux_irqchip_data *irqchip_data = d->chip_data;
+	int idx = irqchip_data->chanidx;
+	struct intmux_data *data = container_of(irqchip_data, struct intmux_data,
+						irqchip_data[idx]);
+	unsigned long flags;
+	void __iomem *reg;
+	u32 val;
+
+	raw_spin_lock_irqsave(&data->lock, flags);
+	reg = data->regs + CHANIER(idx);
+	val = readl_relaxed(reg);
+	/* enable the interrupt source of this channel */
+	val |= BIT(d->hwirq);
+	writel_relaxed(val, reg);
+	raw_spin_unlock_irqrestore(&data->lock, flags);
+}
+
+static struct irq_chip imx_intmux_irq_chip = {
+	.name		= "intmux",
+	.irq_mask	= imx_intmux_irq_mask,
+	.irq_unmask	= imx_intmux_irq_unmask,
+};
+
+static int imx_intmux_irq_map(struct irq_domain *h, unsigned int irq,
+			      irq_hw_number_t hwirq)
+{
+	struct intmux_irqchip_data *data = h->host_data;
+
+	irq_set_chip_data(irq, data);
+	irq_set_chip_and_handler(irq, &data->chip, handle_level_irq);
+
+	return 0;
+}
+
+static int imx_intmux_irq_xlate(struct irq_domain *d, struct device_node *node,
+				const u32 *intspec, unsigned int intsize,
+				unsigned long *out_hwirq, unsigned int *out_type)
+{
+	struct intmux_irqchip_data *irqchip_data = d->host_data;
+	int idx = irqchip_data->chanidx;
+	struct intmux_data *data = container_of(irqchip_data, struct intmux_data,
+						irqchip_data[idx]);
+
+	/*
+	 * two cells needed in interrupt specifier:
+	 * the 1st cell: hw interrupt number
+	 * the 2nd cell: channel index
+	 */
+	if (WARN_ON(intsize != 2))
+		return -EINVAL;
+
+	if (WARN_ON(intspec[1] >= data->channum))
+		return -EINVAL;
+
+	*out_hwirq = intspec[0];
+	*out_type = IRQ_TYPE_LEVEL_HIGH;
+
+	return 0;
+}
+
+static int imx_intmux_irq_select(struct irq_domain *d, struct irq_fwspec *fwspec,
+				 enum irq_domain_bus_token bus_token)
+{
+	struct intmux_irqchip_data *irqchip_data = d->host_data;
+
+	/* Not for us */
+	if (fwspec->fwnode != d->fwnode)
+		return false;
+
+	return irqchip_data->chanidx == fwspec->param[1];
+}
+
+static const struct irq_domain_ops imx_intmux_domain_ops = {
+	.map		= imx_intmux_irq_map,
+	.xlate		= imx_intmux_irq_xlate,
+	.select		= imx_intmux_irq_select,
+};
+
+static void imx_intmux_irq_handler(struct irq_desc *desc)
+{
+	struct intmux_irqchip_data *irqchip_data = irq_desc_get_handler_data(desc);
+	int idx = irqchip_data->chanidx;
+	struct intmux_data *data = container_of(irqchip_data, struct intmux_data,
+						irqchip_data[idx]);
+	unsigned long irqstat;
+	int pos, virq;
+
+	chained_irq_enter(irq_desc_get_chip(desc), desc);
+
+	/* read the interrupt source pending status of this channel */
+	irqstat = readl_relaxed(data->regs + CHANIPR(idx));
+
+	for_each_set_bit(pos, &irqstat, 32) {
+		virq = irq_find_mapping(irqchip_data->domain, pos);
+		if (virq)
+			generic_handle_irq(virq);
+	}
+
+	chained_irq_exit(irq_desc_get_chip(desc), desc);
+}
+
+static int imx_intmux_probe(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	struct irq_domain *domain;
+	struct intmux_data *data;
+	int channum;
+	int i, ret;
+
+	channum = platform_irq_count(pdev);
+	if (channum == -EPROBE_DEFER) {
+		return -EPROBE_DEFER;
+	} else if (channum > CHAN_MAX_NUM) {
+		dev_err(&pdev->dev, "supports up to %d multiplex channels\n",
+			CHAN_MAX_NUM);
+		return -EINVAL;
+	}
+
+	data = devm_kzalloc(&pdev->dev, struct_size(data, irqchip_data, channum), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->regs = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(data->regs)) {
+		dev_err(&pdev->dev, "failed to initialize reg\n");
+		return PTR_ERR(data->regs);
+	}
+
+	data->ipg_clk = devm_clk_get(&pdev->dev, "ipg");
+	if (IS_ERR(data->ipg_clk))
+		return dev_err_probe(&pdev->dev, PTR_ERR(data->ipg_clk),
+				     "failed to get ipg clk\n");
+
+	data->channum = channum;
+	raw_spin_lock_init(&data->lock);
+
+	pm_runtime_get_noresume(&pdev->dev);
+	pm_runtime_set_active(&pdev->dev);
+	pm_runtime_enable(&pdev->dev);
+
+	ret = clk_prepare_enable(data->ipg_clk);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to enable ipg clk: %d\n", ret);
+		return ret;
+	}
+
+	for (i = 0; i < channum; i++) {
+		data->irqchip_data[i].chip = imx_intmux_irq_chip;
+		data->irqchip_data[i].chip.parent_device = &pdev->dev;
+		data->irqchip_data[i].chanidx = i;
+
+		data->irqchip_data[i].irq = irq_of_parse_and_map(np, i);
+		if (data->irqchip_data[i].irq <= 0) {
+			ret = -EINVAL;
+			dev_err(&pdev->dev, "failed to get irq\n");
+			goto out;
+		}
+
+		domain = irq_domain_add_linear(np, 32, &imx_intmux_domain_ops,
+					       &data->irqchip_data[i]);
+		if (!domain) {
+			ret = -ENOMEM;
+			dev_err(&pdev->dev, "failed to create IRQ domain\n");
+			goto out;
+		}
+		data->irqchip_data[i].domain = domain;
+
+		/* disable all interrupt sources of this channel firstly */
+		writel_relaxed(0, data->regs + CHANIER(i));
+
+		irq_set_chained_handler_and_data(data->irqchip_data[i].irq,
+						 imx_intmux_irq_handler,
+						 &data->irqchip_data[i]);
+	}
+
+	platform_set_drvdata(pdev, data);
+
+	/*
+	 * Let pm_runtime_put() disable clock.
+	 * If CONFIG_PM is not enabled, the clock will stay powered.
+	 */
+	pm_runtime_put(&pdev->dev);
+
+	return 0;
+out:
+	clk_disable_unprepare(data->ipg_clk);
+	return ret;
+}
+
+static int imx_intmux_remove(struct platform_device *pdev)
+{
+	struct intmux_data *data = platform_get_drvdata(pdev);
+	int i;
+
+	for (i = 0; i < data->channum; i++) {
+		/* disable all interrupt sources of this channel */
+		writel_relaxed(0, data->regs + CHANIER(i));
+
+		irq_set_chained_handler_and_data(data->irqchip_data[i].irq,
+						 NULL, NULL);
+
+		irq_domain_remove(data->irqchip_data[i].domain);
+	}
+
+	pm_runtime_disable(&pdev->dev);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM
+static int imx_intmux_runtime_suspend(struct device *dev)
+{
+	struct intmux_data *data = dev_get_drvdata(dev);
+	struct intmux_irqchip_data *irqchip_data;
+	int i;
+
+	for (i = 0; i < data->channum; i++) {
+		irqchip_data = &data->irqchip_data[i];
+		irqchip_data->saved_reg = readl_relaxed(data->regs + CHANIER(i));
+	}
+
+	clk_disable_unprepare(data->ipg_clk);
+
+	return 0;
+}
+
+static int imx_intmux_runtime_resume(struct device *dev)
+{
+	struct intmux_data *data = dev_get_drvdata(dev);
+	struct intmux_irqchip_data *irqchip_data;
+	int ret, i;
+
+	ret = clk_prepare_enable(data->ipg_clk);
+	if (ret) {
+		dev_err(dev, "failed to enable ipg clk: %d\n", ret);
+		return ret;
+	}
+
+	for (i = 0; i < data->channum; i++) {
+		irqchip_data = &data->irqchip_data[i];
+		writel_relaxed(irqchip_data->saved_reg, data->regs + CHANIER(i));
+	}
+
+	return 0;
+}
+#endif
+
+static const struct dev_pm_ops imx_intmux_pm_ops = {
+	SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				      pm_runtime_force_resume)
+	SET_RUNTIME_PM_OPS(imx_intmux_runtime_suspend,
+			   imx_intmux_runtime_resume, NULL)
+};
+
+static const struct of_device_id imx_intmux_id[] = {
+	{ .compatible = "fsl,imx-intmux", },
+	{ /* sentinel */ },
+};
+
+static struct platform_driver imx_intmux_driver = {
+	.driver = {
+		.name = "imx-intmux",
+		.of_match_table = imx_intmux_id,
+		.pm = &imx_intmux_pm_ops,
+	},
+	.probe = imx_intmux_probe,
+	.remove = imx_intmux_remove,
+};
+builtin_platform_driver(imx_intmux_driver);
diff --git a/drivers/irqchip/irq-imx-irqsteer.c b/drivers/irqchip/irq-imx-irqsteer.c
index 290531e..1edf769 100644
--- a/drivers/irqchip/irq-imx-irqsteer.c
+++ b/drivers/irqchip/irq-imx-irqsteer.c
@@ -158,12 +158,9 @@
 	}
 
 	data->ipg_clk = devm_clk_get(&pdev->dev, "ipg");
-	if (IS_ERR(data->ipg_clk)) {
-		ret = PTR_ERR(data->ipg_clk);
-		if (ret != -EPROBE_DEFER)
-			dev_err(&pdev->dev, "failed to get ipg clk: %d\n", ret);
-		return ret;
-	}
+	if (IS_ERR(data->ipg_clk))
+		return dev_err_probe(&pdev->dev, PTR_ERR(data->ipg_clk),
+				     "failed to get ipg clk\n");
 
 	raw_spin_lock_init(&data->lock);
 
diff --git a/drivers/irqchip/irq-ingenic-tcu.c b/drivers/irqchip/irq-ingenic-tcu.c
index 02a8272..b938d1d 100644
--- a/drivers/irqchip/irq-ingenic-tcu.c
+++ b/drivers/irqchip/irq-ingenic-tcu.c
@@ -181,3 +181,4 @@
 IRQCHIP_DECLARE(jz4725b_tcu_irq, "ingenic,jz4725b-tcu", ingenic_tcu_irq_init);
 IRQCHIP_DECLARE(jz4760_tcu_irq, "ingenic,jz4760-tcu", ingenic_tcu_irq_init);
 IRQCHIP_DECLARE(jz4770_tcu_irq, "ingenic,jz4770-tcu", ingenic_tcu_irq_init);
+IRQCHIP_DECLARE(x1000_tcu_irq, "ingenic,x1000-tcu", ingenic_tcu_irq_init);
diff --git a/drivers/irqchip/irq-ingenic.c b/drivers/irqchip/irq-ingenic.c
index 31bc11f..ea36bb0 100644
--- a/drivers/irqchip/irq-ingenic.c
+++ b/drivers/irqchip/irq-ingenic.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  Copyright (C) 2009-2010, Lars-Peter Clausen <lars@metafoo.de>
- *  JZ4740 platform IRQ support
+ *  Ingenic XBurst platform IRQ support
  */
 
 #include <linux/errno.h>
@@ -10,7 +10,6 @@
 #include <linux/interrupt.h>
 #include <linux/ioport.h>
 #include <linux/irqchip.h>
-#include <linux/irqchip/ingenic.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
 #include <linux/timex.h>
@@ -18,10 +17,10 @@
 #include <linux/delay.h>
 
 #include <asm/io.h>
-#include <asm/mach-jz4740/irq.h>
 
 struct ingenic_intc_data {
 	void __iomem *base;
+	struct irq_domain *domain;
 	unsigned num_chips;
 };
 
@@ -35,46 +34,30 @@
 static irqreturn_t intc_cascade(int irq, void *data)
 {
 	struct ingenic_intc_data *intc = irq_get_handler_data(irq);
-	uint32_t irq_reg;
+	struct irq_domain *domain = intc->domain;
+	struct irq_chip_generic *gc;
+	uint32_t pending;
 	unsigned i;
 
 	for (i = 0; i < intc->num_chips; i++) {
-		irq_reg = readl(intc->base + (i * CHIP_SIZE) +
-				JZ_REG_INTC_PENDING);
-		if (!irq_reg)
+		gc = irq_get_domain_generic_chip(domain, i * 32);
+
+		pending = irq_reg_readl(gc, JZ_REG_INTC_PENDING);
+		if (!pending)
 			continue;
 
-		generic_handle_irq(__fls(irq_reg) + (i * 32) + JZ4740_IRQ_BASE);
+		while (pending) {
+			int bit = __fls(pending);
+
+			irq = irq_linear_revmap(domain, bit + (i * 32));
+			generic_handle_irq(irq);
+			pending &= ~BIT(bit);
+		}
 	}
 
 	return IRQ_HANDLED;
 }
 
-static void intc_irq_set_mask(struct irq_chip_generic *gc, uint32_t mask)
-{
-	struct irq_chip_regs *regs = &gc->chip_types->regs;
-
-	writel(mask, gc->reg_base + regs->enable);
-	writel(~mask, gc->reg_base + regs->disable);
-}
-
-void ingenic_intc_irq_suspend(struct irq_data *data)
-{
-	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(data);
-	intc_irq_set_mask(gc, gc->wake_active);
-}
-
-void ingenic_intc_irq_resume(struct irq_data *data)
-{
-	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(data);
-	intc_irq_set_mask(gc, gc->mask_cache);
-}
-
-static struct irqaction intc_cascade_action = {
-	.handler = intc_cascade,
-	.name = "SoC intc cascade interrupt",
-};
-
 static int __init ingenic_intc_of_init(struct device_node *node,
 				       unsigned num_chips)
 {
@@ -108,25 +91,26 @@
 		goto out_unmap_irq;
 	}
 
-	domain = irq_domain_add_legacy(node, num_chips * 32,
-				       JZ4740_IRQ_BASE, 0,
-				       &irq_domain_simple_ops, NULL);
+	domain = irq_domain_add_linear(node, num_chips * 32,
+				       &irq_generic_chip_ops, NULL);
 	if (!domain) {
 		err = -ENOMEM;
 		goto out_unmap_base;
 	}
 
-	for (i = 0; i < num_chips; i++) {
-		/* Mask all irqs */
-		writel(0xffffffff, intc->base + (i * CHIP_SIZE) +
-		       JZ_REG_INTC_SET_MASK);
+	intc->domain = domain;
 
-		gc = irq_alloc_generic_chip("INTC", 1,
-					    JZ4740_IRQ_BASE + (i * 32),
-					    intc->base + (i * CHIP_SIZE),
-					    handle_level_irq);
+	err = irq_alloc_domain_generic_chips(domain, 32, 1, "INTC",
+					     handle_level_irq, 0,
+					     IRQ_NOPROBE | IRQ_LEVEL, 0);
+	if (err)
+		goto out_domain_remove;
+
+	for (i = 0; i < num_chips; i++) {
+		gc = irq_get_domain_generic_chip(domain, i * 32);
 
 		gc->wake_enabled = IRQ_MSK(32);
+		gc->reg_base = intc->base + (i * CHIP_SIZE);
 
 		ct = gc->chip_types;
 		ct->regs.enable = JZ_REG_INTC_CLEAR_MASK;
@@ -135,16 +119,19 @@
 		ct->chip.irq_mask = irq_gc_mask_disable_reg;
 		ct->chip.irq_mask_ack = irq_gc_mask_disable_reg;
 		ct->chip.irq_set_wake = irq_gc_set_wake;
-		ct->chip.irq_suspend = ingenic_intc_irq_suspend;
-		ct->chip.irq_resume = ingenic_intc_irq_resume;
+		ct->chip.flags = IRQCHIP_MASK_ON_SUSPEND;
 
-		irq_setup_generic_chip(gc, IRQ_MSK(32), 0, 0,
-				       IRQ_NOPROBE | IRQ_LEVEL);
+		/* Mask all irqs */
+		irq_reg_writel(gc, IRQ_MSK(32), JZ_REG_INTC_SET_MASK);
 	}
 
-	setup_irq(parent_irq, &intc_cascade_action);
+	if (request_irq(parent_irq, intc_cascade, IRQF_NO_SUSPEND,
+			"SoC intc cascade interrupt", NULL))
+		pr_err("Failed to register SoC intc cascade interrupt\n");
 	return 0;
 
+out_domain_remove:
+	irq_domain_remove(domain);
 out_unmap_base:
 	iounmap(intc->base);
 out_unmap_irq:
diff --git a/drivers/irqchip/irq-loongson-htpic.c b/drivers/irqchip/irq-loongson-htpic.c
new file mode 100644
index 0000000..63f7280
--- /dev/null
+++ b/drivers/irqchip/irq-loongson-htpic.c
@@ -0,0 +1,147 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  Copyright (C) 2020, Jiaxun Yang <jiaxun.yang@flygoat.com>
+ *  Loongson HTPIC IRQ support
+ */
+
+#include <linux/init.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/irqchip.h>
+#include <linux/irqchip/chained_irq.h>
+#include <linux/irq.h>
+#include <linux/io.h>
+#include <linux/syscore_ops.h>
+
+#include <asm/i8259.h>
+
+#define HTPIC_MAX_PARENT_IRQ	4
+#define HTINT_NUM_VECTORS	8
+#define HTINT_EN_OFF		0x20
+
+struct loongson_htpic {
+	void __iomem *base;
+	struct irq_domain *domain;
+};
+
+static struct loongson_htpic *htpic;
+
+static void htpic_irq_dispatch(struct irq_desc *desc)
+{
+	struct loongson_htpic *priv = irq_desc_get_handler_data(desc);
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	uint32_t pending;
+
+	chained_irq_enter(chip, desc);
+	pending = readl(priv->base);
+	/* Ack all IRQs at once, otherwise IRQ flood might happen */
+	writel(pending, priv->base);
+
+	if (!pending)
+		spurious_interrupt();
+
+	while (pending) {
+		int bit = __ffs(pending);
+
+		if (unlikely(bit > 15)) {
+			spurious_interrupt();
+			break;
+		}
+
+		generic_handle_irq(irq_linear_revmap(priv->domain, bit));
+		pending &= ~BIT(bit);
+	}
+	chained_irq_exit(chip, desc);
+}
+
+static void htpic_reg_init(void)
+{
+	int i;
+
+	for (i = 0; i < HTINT_NUM_VECTORS; i++) {
+		uint32_t val;
+
+		/* Disable all HT Vectors */
+		writel(0x0, htpic->base + HTINT_EN_OFF + i * 0x4);
+		val = readl(htpic->base + i * 0x4);
+		/* Ack all possible pending IRQs */
+		writel(GENMASK(31, 0), htpic->base + i * 0x4);
+	}
+
+	/* Enable 16 vectors for PIC */
+	writel(0xffff, htpic->base + HTINT_EN_OFF);
+}
+
+static void htpic_resume(void)
+{
+	htpic_reg_init();
+}
+
+struct syscore_ops htpic_syscore_ops = {
+	.resume		= htpic_resume,
+};
+
+int __init htpic_of_init(struct device_node *node, struct device_node *parent)
+{
+	unsigned int parent_irq[4];
+	int i, err;
+	int num_parents = 0;
+
+	if (htpic) {
+		pr_err("loongson-htpic: Only one HTPIC is allowed in the system\n");
+		return -ENODEV;
+	}
+
+	htpic = kzalloc(sizeof(*htpic), GFP_KERNEL);
+	if (!htpic)
+		return -ENOMEM;
+
+	htpic->base = of_iomap(node, 0);
+	if (!htpic->base) {
+		err = -ENODEV;
+		goto out_free;
+	}
+
+	htpic->domain = __init_i8259_irqs(node);
+	if (!htpic->domain) {
+		pr_err("loongson-htpic: Failed to initialize i8259 IRQs\n");
+		err = -ENOMEM;
+		goto out_iounmap;
+	}
+
+	/* Interrupt may come from any of the 4 interrupt line */
+	for (i = 0; i < HTPIC_MAX_PARENT_IRQ; i++) {
+		parent_irq[i] = irq_of_parse_and_map(node, i);
+		if (parent_irq[i] <= 0)
+			break;
+
+		num_parents++;
+	}
+
+	if (!num_parents) {
+		pr_err("loongson-htpic: Failed to get parent irqs\n");
+		err = -ENODEV;
+		goto out_remove_domain;
+	}
+
+	htpic_reg_init();
+
+	for (i = 0; i < num_parents; i++) {
+		irq_set_chained_handler_and_data(parent_irq[i],
+						htpic_irq_dispatch, htpic);
+	}
+
+	register_syscore_ops(&htpic_syscore_ops);
+
+	return 0;
+
+out_remove_domain:
+	irq_domain_remove(htpic->domain);
+out_iounmap:
+	iounmap(htpic->base);
+out_free:
+	kfree(htpic);
+	return err;
+}
+
+IRQCHIP_DECLARE(loongson_htpic, "loongson,htpic-1.0", htpic_of_init);
diff --git a/drivers/irqchip/irq-loongson-htvec.c b/drivers/irqchip/irq-loongson-htvec.c
new file mode 100644
index 0000000..6392aaf
--- /dev/null
+++ b/drivers/irqchip/irq-loongson-htvec.c
@@ -0,0 +1,218 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  Copyright (C) 2020, Jiaxun Yang <jiaxun.yang@flygoat.com>
+ *  Loongson HyperTransport Interrupt Vector support
+ */
+
+#define pr_fmt(fmt) "htvec: " fmt
+
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/irqchip.h>
+#include <linux/irqdomain.h>
+#include <linux/irqchip/chained_irq.h>
+#include <linux/kernel.h>
+#include <linux/platform_device.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/of_platform.h>
+
+/* Registers */
+#define HTVEC_EN_OFF		0x20
+#define HTVEC_MAX_PARENT_IRQ	8
+
+#define VEC_COUNT_PER_REG	32
+#define VEC_REG_IDX(irq_id)	((irq_id) / VEC_COUNT_PER_REG)
+#define VEC_REG_BIT(irq_id)	((irq_id) % VEC_COUNT_PER_REG)
+
+struct htvec {
+	int			num_parents;
+	void __iomem		*base;
+	struct irq_domain	*htvec_domain;
+	raw_spinlock_t		htvec_lock;
+};
+
+static void htvec_irq_dispatch(struct irq_desc *desc)
+{
+	int i;
+	u32 pending;
+	bool handled = false;
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	struct htvec *priv = irq_desc_get_handler_data(desc);
+
+	chained_irq_enter(chip, desc);
+
+	for (i = 0; i < priv->num_parents; i++) {
+		pending = readl(priv->base + 4 * i);
+		while (pending) {
+			int bit = __ffs(pending);
+
+			generic_handle_irq(irq_linear_revmap(priv->htvec_domain, bit +
+							     VEC_COUNT_PER_REG * i));
+			pending &= ~BIT(bit);
+			handled = true;
+		}
+	}
+
+	if (!handled)
+		spurious_interrupt();
+
+	chained_irq_exit(chip, desc);
+}
+
+static void htvec_ack_irq(struct irq_data *d)
+{
+	struct htvec *priv = irq_data_get_irq_chip_data(d);
+
+	writel(BIT(VEC_REG_BIT(d->hwirq)),
+	       priv->base + VEC_REG_IDX(d->hwirq) * 4);
+}
+
+static void htvec_mask_irq(struct irq_data *d)
+{
+	u32 reg;
+	void __iomem *addr;
+	struct htvec *priv = irq_data_get_irq_chip_data(d);
+
+	raw_spin_lock(&priv->htvec_lock);
+	addr = priv->base + HTVEC_EN_OFF;
+	addr += VEC_REG_IDX(d->hwirq) * 4;
+	reg = readl(addr);
+	reg &= ~BIT(VEC_REG_BIT(d->hwirq));
+	writel(reg, addr);
+	raw_spin_unlock(&priv->htvec_lock);
+}
+
+static void htvec_unmask_irq(struct irq_data *d)
+{
+	u32 reg;
+	void __iomem *addr;
+	struct htvec *priv = irq_data_get_irq_chip_data(d);
+
+	raw_spin_lock(&priv->htvec_lock);
+	addr = priv->base + HTVEC_EN_OFF;
+	addr += VEC_REG_IDX(d->hwirq) * 4;
+	reg = readl(addr);
+	reg |= BIT(VEC_REG_BIT(d->hwirq));
+	writel(reg, addr);
+	raw_spin_unlock(&priv->htvec_lock);
+}
+
+static struct irq_chip htvec_irq_chip = {
+	.name			= "LOONGSON_HTVEC",
+	.irq_mask		= htvec_mask_irq,
+	.irq_unmask		= htvec_unmask_irq,
+	.irq_ack		= htvec_ack_irq,
+};
+
+static int htvec_domain_alloc(struct irq_domain *domain, unsigned int virq,
+			      unsigned int nr_irqs, void *arg)
+{
+	int ret;
+	unsigned long hwirq;
+	unsigned int type, i;
+	struct htvec *priv = domain->host_data;
+
+	ret = irq_domain_translate_onecell(domain, arg, &hwirq, &type);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < nr_irqs; i++) {
+		irq_domain_set_info(domain, virq + i, hwirq + i, &htvec_irq_chip,
+				    priv, handle_edge_irq, NULL, NULL);
+	}
+
+	return 0;
+}
+
+static void htvec_domain_free(struct irq_domain *domain, unsigned int virq,
+				  unsigned int nr_irqs)
+{
+	int i;
+
+	for (i = 0; i < nr_irqs; i++) {
+		struct irq_data *d = irq_domain_get_irq_data(domain, virq + i);
+
+		irq_set_handler(virq + i, NULL);
+		irq_domain_reset_irq_data(d);
+	}
+}
+
+static const struct irq_domain_ops htvec_domain_ops = {
+	.translate	= irq_domain_translate_onecell,
+	.alloc		= htvec_domain_alloc,
+	.free		= htvec_domain_free,
+};
+
+static void htvec_reset(struct htvec *priv)
+{
+	u32 idx;
+
+	/* Clear IRQ cause registers, mask all interrupts */
+	for (idx = 0; idx < priv->num_parents; idx++) {
+		writel_relaxed(0x0, priv->base + HTVEC_EN_OFF + 4 * idx);
+		writel_relaxed(0xFFFFFFFF, priv->base + 4 * idx);
+	}
+}
+
+static int htvec_of_init(struct device_node *node,
+				struct device_node *parent)
+{
+	struct htvec *priv;
+	int err, parent_irq[8], i;
+
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	raw_spin_lock_init(&priv->htvec_lock);
+	priv->base = of_iomap(node, 0);
+	if (!priv->base) {
+		err = -ENOMEM;
+		goto free_priv;
+	}
+
+	/* Interrupt may come from any of the 8 interrupt lines */
+	for (i = 0; i < HTVEC_MAX_PARENT_IRQ; i++) {
+		parent_irq[i] = irq_of_parse_and_map(node, i);
+		if (parent_irq[i] <= 0)
+			break;
+
+		priv->num_parents++;
+	}
+
+	if (!priv->num_parents) {
+		pr_err("Failed to get parent irqs\n");
+		err = -ENODEV;
+		goto iounmap_base;
+	}
+
+	priv->htvec_domain = irq_domain_create_linear(of_node_to_fwnode(node),
+					(VEC_COUNT_PER_REG * priv->num_parents),
+					&htvec_domain_ops, priv);
+	if (!priv->htvec_domain) {
+		pr_err("Failed to create IRQ domain\n");
+		err = -ENOMEM;
+		goto irq_dispose;
+	}
+
+	htvec_reset(priv);
+
+	for (i = 0; i < priv->num_parents; i++)
+		irq_set_chained_handler_and_data(parent_irq[i],
+						 htvec_irq_dispatch, priv);
+
+	return 0;
+
+irq_dispose:
+	for (; i > 0; i--)
+		irq_dispose_mapping(parent_irq[i - 1]);
+iounmap_base:
+	iounmap(priv->base);
+free_priv:
+	kfree(priv);
+
+	return err;
+}
+
+IRQCHIP_DECLARE(htvec, "loongson,htvec-1.0", htvec_of_init);
diff --git a/drivers/irqchip/irq-loongson-liointc.c b/drivers/irqchip/irq-loongson-liointc.c
new file mode 100644
index 0000000..9ed1bc4
--- /dev/null
+++ b/drivers/irqchip/irq-loongson-liointc.c
@@ -0,0 +1,272 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  Copyright (C) 2020, Jiaxun Yang <jiaxun.yang@flygoat.com>
+ *  Loongson Local IO Interrupt Controller support
+ */
+
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/interrupt.h>
+#include <linux/ioport.h>
+#include <linux/irqchip.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/io.h>
+#include <linux/smp.h>
+#include <linux/irqchip/chained_irq.h>
+
+#include <boot_param.h>
+
+#define LIOINTC_CHIP_IRQ	32
+#define LIOINTC_NUM_PARENT 4
+
+#define LIOINTC_INTC_CHIP_START	0x20
+
+#define LIOINTC_REG_INTC_STATUS	(LIOINTC_INTC_CHIP_START + 0x20)
+#define LIOINTC_REG_INTC_EN_STATUS	(LIOINTC_INTC_CHIP_START + 0x04)
+#define LIOINTC_REG_INTC_ENABLE	(LIOINTC_INTC_CHIP_START + 0x08)
+#define LIOINTC_REG_INTC_DISABLE	(LIOINTC_INTC_CHIP_START + 0x0c)
+#define LIOINTC_REG_INTC_POL	(LIOINTC_INTC_CHIP_START + 0x10)
+#define LIOINTC_REG_INTC_EDGE	(LIOINTC_INTC_CHIP_START + 0x14)
+
+#define LIOINTC_SHIFT_INTx	4
+
+#define LIOINTC_ERRATA_IRQ	10
+
+struct liointc_handler_data {
+	struct liointc_priv	*priv;
+	u32			parent_int_map;
+};
+
+struct liointc_priv {
+	struct irq_chip_generic		*gc;
+	struct liointc_handler_data	handler[LIOINTC_NUM_PARENT];
+	u8				map_cache[LIOINTC_CHIP_IRQ];
+	bool				has_lpc_irq_errata;
+};
+
+static void liointc_chained_handle_irq(struct irq_desc *desc)
+{
+	struct liointc_handler_data *handler = irq_desc_get_handler_data(desc);
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	struct irq_chip_generic *gc = handler->priv->gc;
+	u32 pending;
+
+	chained_irq_enter(chip, desc);
+
+	pending = readl(gc->reg_base + LIOINTC_REG_INTC_STATUS);
+
+	if (!pending) {
+		/* Always blame LPC IRQ if we have that bug */
+		if (handler->priv->has_lpc_irq_errata &&
+			(handler->parent_int_map & gc->mask_cache &
+			BIT(LIOINTC_ERRATA_IRQ)))
+			pending = BIT(LIOINTC_ERRATA_IRQ);
+		else
+			spurious_interrupt();
+	}
+
+	while (pending) {
+		int bit = __ffs(pending);
+
+		generic_handle_irq(irq_find_mapping(gc->domain, bit));
+		pending &= ~BIT(bit);
+	}
+
+	chained_irq_exit(chip, desc);
+}
+
+static void liointc_set_bit(struct irq_chip_generic *gc,
+				unsigned int offset,
+				u32 mask, bool set)
+{
+	if (set)
+		writel(readl(gc->reg_base + offset) | mask,
+				gc->reg_base + offset);
+	else
+		writel(readl(gc->reg_base + offset) & ~mask,
+				gc->reg_base + offset);
+}
+
+static int liointc_set_type(struct irq_data *data, unsigned int type)
+{
+	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(data);
+	u32 mask = data->mask;
+	unsigned long flags;
+
+	irq_gc_lock_irqsave(gc, flags);
+	switch (type) {
+	case IRQ_TYPE_LEVEL_HIGH:
+		liointc_set_bit(gc, LIOINTC_REG_INTC_EDGE, mask, false);
+		liointc_set_bit(gc, LIOINTC_REG_INTC_POL, mask, true);
+		break;
+	case IRQ_TYPE_LEVEL_LOW:
+		liointc_set_bit(gc, LIOINTC_REG_INTC_EDGE, mask, false);
+		liointc_set_bit(gc, LIOINTC_REG_INTC_POL, mask, false);
+		break;
+	case IRQ_TYPE_EDGE_RISING:
+		liointc_set_bit(gc, LIOINTC_REG_INTC_EDGE, mask, true);
+		liointc_set_bit(gc, LIOINTC_REG_INTC_POL, mask, true);
+		break;
+	case IRQ_TYPE_EDGE_FALLING:
+		liointc_set_bit(gc, LIOINTC_REG_INTC_EDGE, mask, true);
+		liointc_set_bit(gc, LIOINTC_REG_INTC_POL, mask, false);
+		break;
+	default:
+		irq_gc_unlock_irqrestore(gc, flags);
+		return -EINVAL;
+	}
+	irq_gc_unlock_irqrestore(gc, flags);
+
+	irqd_set_trigger_type(data, type);
+	return 0;
+}
+
+static void liointc_resume(struct irq_chip_generic *gc)
+{
+	struct liointc_priv *priv = gc->private;
+	unsigned long flags;
+	int i;
+
+	irq_gc_lock_irqsave(gc, flags);
+	/* Disable all at first */
+	writel(0xffffffff, gc->reg_base + LIOINTC_REG_INTC_DISABLE);
+	/* Restore map cache */
+	for (i = 0; i < LIOINTC_CHIP_IRQ; i++)
+		writeb(priv->map_cache[i], gc->reg_base + i);
+	/* Restore mask cache */
+	writel(gc->mask_cache, gc->reg_base + LIOINTC_REG_INTC_ENABLE);
+	irq_gc_unlock_irqrestore(gc, flags);
+}
+
+static const char * const parent_names[] = {"int0", "int1", "int2", "int3"};
+
+int __init liointc_of_init(struct device_node *node,
+				struct device_node *parent)
+{
+	struct irq_chip_generic *gc;
+	struct irq_domain *domain;
+	struct irq_chip_type *ct;
+	struct liointc_priv *priv;
+	void __iomem *base;
+	u32 of_parent_int_map[LIOINTC_NUM_PARENT];
+	int parent_irq[LIOINTC_NUM_PARENT];
+	bool have_parent = FALSE;
+	int sz, i, err = 0;
+
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	base = of_iomap(node, 0);
+	if (!base) {
+		err = -ENODEV;
+		goto out_free_priv;
+	}
+
+	for (i = 0; i < LIOINTC_NUM_PARENT; i++) {
+		parent_irq[i] = of_irq_get_byname(node, parent_names[i]);
+		if (parent_irq[i] > 0)
+			have_parent = TRUE;
+	}
+	if (!have_parent) {
+		err = -ENODEV;
+		goto out_iounmap;
+	}
+
+	sz = of_property_read_variable_u32_array(node,
+						"loongson,parent_int_map",
+						&of_parent_int_map[0],
+						LIOINTC_NUM_PARENT,
+						LIOINTC_NUM_PARENT);
+	if (sz < 4) {
+		pr_err("loongson-liointc: No parent_int_map\n");
+		err = -ENODEV;
+		goto out_iounmap;
+	}
+
+	for (i = 0; i < LIOINTC_NUM_PARENT; i++)
+		priv->handler[i].parent_int_map = of_parent_int_map[i];
+
+	/* Setup IRQ domain */
+	domain = irq_domain_add_linear(node, 32,
+					&irq_generic_chip_ops, priv);
+	if (!domain) {
+		pr_err("loongson-liointc: cannot add IRQ domain\n");
+		err = -EINVAL;
+		goto out_iounmap;
+	}
+
+	err = irq_alloc_domain_generic_chips(domain, 32, 1,
+					node->full_name, handle_level_irq,
+					IRQ_NOPROBE, 0, 0);
+	if (err) {
+		pr_err("loongson-liointc: unable to register IRQ domain\n");
+		goto out_free_domain;
+	}
+
+
+	/* Disable all IRQs */
+	writel(0xffffffff, base + LIOINTC_REG_INTC_DISABLE);
+	/* Set to level triggered */
+	writel(0x0, base + LIOINTC_REG_INTC_EDGE);
+
+	/* Generate parent INT part of map cache */
+	for (i = 0; i < LIOINTC_NUM_PARENT; i++) {
+		u32 pending = priv->handler[i].parent_int_map;
+
+		while (pending) {
+			int bit = __ffs(pending);
+
+			priv->map_cache[bit] = BIT(i) << LIOINTC_SHIFT_INTx;
+			pending &= ~BIT(bit);
+		}
+	}
+
+	for (i = 0; i < LIOINTC_CHIP_IRQ; i++) {
+		/* Generate core part of map cache */
+		priv->map_cache[i] |= BIT(loongson_sysconf.boot_cpu_id);
+		writeb(priv->map_cache[i], base + i);
+	}
+
+	gc = irq_get_domain_generic_chip(domain, 0);
+	gc->private = priv;
+	gc->reg_base = base;
+	gc->domain = domain;
+	gc->resume = liointc_resume;
+
+	ct = gc->chip_types;
+	ct->regs.enable = LIOINTC_REG_INTC_ENABLE;
+	ct->regs.disable = LIOINTC_REG_INTC_DISABLE;
+	ct->chip.irq_unmask = irq_gc_unmask_enable_reg;
+	ct->chip.irq_mask = irq_gc_mask_disable_reg;
+	ct->chip.irq_mask_ack = irq_gc_mask_disable_reg;
+	ct->chip.irq_set_type = liointc_set_type;
+
+	gc->mask_cache = 0;
+	priv->gc = gc;
+
+	for (i = 0; i < LIOINTC_NUM_PARENT; i++) {
+		if (parent_irq[i] <= 0)
+			continue;
+
+		priv->handler[i].priv = priv;
+		irq_set_chained_handler_and_data(parent_irq[i],
+				liointc_chained_handle_irq, &priv->handler[i]);
+	}
+
+	return 0;
+
+out_free_domain:
+	irq_domain_remove(domain);
+out_iounmap:
+	iounmap(base);
+out_free_priv:
+	kfree(priv);
+
+	return err;
+}
+
+IRQCHIP_DECLARE(loongson_liointc_1_0, "loongson,liointc-1.0", liointc_of_init);
+IRQCHIP_DECLARE(loongson_liointc_1_0a, "loongson,liointc-1.0a", liointc_of_init);
diff --git a/drivers/irqchip/irq-loongson-pch-msi.c b/drivers/irqchip/irq-loongson-pch-msi.c
new file mode 100644
index 0000000..32562b7
--- /dev/null
+++ b/drivers/irqchip/irq-loongson-pch-msi.c
@@ -0,0 +1,250 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  Copyright (C) 2020, Jiaxun Yang <jiaxun.yang@flygoat.com>
+ *  Loongson PCH MSI support
+ */
+
+#define pr_fmt(fmt) "pch-msi: " fmt
+
+#include <linux/irqchip.h>
+#include <linux/msi.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/of_pci.h>
+#include <linux/pci.h>
+#include <linux/slab.h>
+
+struct pch_msi_data {
+	struct mutex	msi_map_lock;
+	phys_addr_t	doorbell;
+	u32		irq_first;	/* The vector number that MSIs starts */
+	u32		num_irqs;	/* The number of vectors for MSIs */
+	unsigned long	*msi_map;
+};
+
+static void pch_msi_mask_msi_irq(struct irq_data *d)
+{
+	pci_msi_mask_irq(d);
+	irq_chip_mask_parent(d);
+}
+
+static void pch_msi_unmask_msi_irq(struct irq_data *d)
+{
+	irq_chip_unmask_parent(d);
+	pci_msi_unmask_irq(d);
+}
+
+static struct irq_chip pch_msi_irq_chip = {
+	.name			= "PCH PCI MSI",
+	.irq_mask		= pch_msi_mask_msi_irq,
+	.irq_unmask		= pch_msi_unmask_msi_irq,
+	.irq_ack		= irq_chip_ack_parent,
+	.irq_set_affinity	= irq_chip_set_affinity_parent,
+};
+
+static int pch_msi_allocate_hwirq(struct pch_msi_data *priv, int num_req)
+{
+	int first;
+
+	mutex_lock(&priv->msi_map_lock);
+
+	first = bitmap_find_free_region(priv->msi_map, priv->num_irqs,
+					get_count_order(num_req));
+	if (first < 0) {
+		mutex_unlock(&priv->msi_map_lock);
+		return -ENOSPC;
+	}
+
+	mutex_unlock(&priv->msi_map_lock);
+
+	return priv->irq_first + first;
+}
+
+static void pch_msi_free_hwirq(struct pch_msi_data *priv,
+				int hwirq, int num_req)
+{
+	int first = hwirq - priv->irq_first;
+
+	mutex_lock(&priv->msi_map_lock);
+	bitmap_release_region(priv->msi_map, first, get_count_order(num_req));
+	mutex_unlock(&priv->msi_map_lock);
+}
+
+static void pch_msi_compose_msi_msg(struct irq_data *data,
+					struct msi_msg *msg)
+{
+	struct pch_msi_data *priv = irq_data_get_irq_chip_data(data);
+
+	msg->address_hi = upper_32_bits(priv->doorbell);
+	msg->address_lo = lower_32_bits(priv->doorbell);
+	msg->data = data->hwirq;
+}
+
+static struct msi_domain_info pch_msi_domain_info = {
+	.flags	= MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS |
+		  MSI_FLAG_MULTI_PCI_MSI | MSI_FLAG_PCI_MSIX,
+	.chip	= &pch_msi_irq_chip,
+};
+
+static struct irq_chip middle_irq_chip = {
+	.name			= "PCH MSI",
+	.irq_mask		= irq_chip_mask_parent,
+	.irq_unmask		= irq_chip_unmask_parent,
+	.irq_ack		= irq_chip_ack_parent,
+	.irq_set_affinity	= irq_chip_set_affinity_parent,
+	.irq_compose_msi_msg	= pch_msi_compose_msi_msg,
+};
+
+static int pch_msi_parent_domain_alloc(struct irq_domain *domain,
+					unsigned int virq, int hwirq)
+{
+	struct irq_fwspec fwspec;
+
+	fwspec.fwnode = domain->parent->fwnode;
+	fwspec.param_count = 1;
+	fwspec.param[0] = hwirq;
+
+	return irq_domain_alloc_irqs_parent(domain, virq, 1, &fwspec);
+}
+
+static int pch_msi_middle_domain_alloc(struct irq_domain *domain,
+					   unsigned int virq,
+					   unsigned int nr_irqs, void *args)
+{
+	struct pch_msi_data *priv = domain->host_data;
+	int hwirq, err, i;
+
+	hwirq = pch_msi_allocate_hwirq(priv, nr_irqs);
+	if (hwirq < 0)
+		return hwirq;
+
+	for (i = 0; i < nr_irqs; i++) {
+		err = pch_msi_parent_domain_alloc(domain, virq + i, hwirq + i);
+		if (err)
+			goto err_hwirq;
+
+		irq_domain_set_hwirq_and_chip(domain, virq + i, hwirq + i,
+					      &middle_irq_chip, priv);
+	}
+
+	return 0;
+
+err_hwirq:
+	pch_msi_free_hwirq(priv, hwirq, nr_irqs);
+	irq_domain_free_irqs_parent(domain, virq, i - 1);
+
+	return err;
+}
+
+static void pch_msi_middle_domain_free(struct irq_domain *domain,
+					   unsigned int virq,
+					   unsigned int nr_irqs)
+{
+	struct irq_data *d = irq_domain_get_irq_data(domain, virq);
+	struct pch_msi_data *priv = irq_data_get_irq_chip_data(d);
+
+	irq_domain_free_irqs_parent(domain, virq, nr_irqs);
+	pch_msi_free_hwirq(priv, d->hwirq, nr_irqs);
+}
+
+static const struct irq_domain_ops pch_msi_middle_domain_ops = {
+	.alloc	= pch_msi_middle_domain_alloc,
+	.free	= pch_msi_middle_domain_free,
+};
+
+static int pch_msi_init_domains(struct pch_msi_data *priv,
+				struct device_node *node,
+				struct irq_domain *parent)
+{
+	struct irq_domain *middle_domain, *msi_domain;
+
+	middle_domain = irq_domain_create_linear(of_node_to_fwnode(node),
+						priv->num_irqs,
+						&pch_msi_middle_domain_ops,
+						priv);
+	if (!middle_domain) {
+		pr_err("Failed to create the MSI middle domain\n");
+		return -ENOMEM;
+	}
+
+	middle_domain->parent = parent;
+	irq_domain_update_bus_token(middle_domain, DOMAIN_BUS_NEXUS);
+
+	msi_domain = pci_msi_create_irq_domain(of_node_to_fwnode(node),
+					       &pch_msi_domain_info,
+					       middle_domain);
+	if (!msi_domain) {
+		pr_err("Failed to create PCI MSI domain\n");
+		irq_domain_remove(middle_domain);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static int pch_msi_init(struct device_node *node,
+			    struct device_node *parent)
+{
+	struct pch_msi_data *priv;
+	struct irq_domain *parent_domain;
+	struct resource res;
+	int ret;
+
+	parent_domain = irq_find_host(parent);
+	if (!parent_domain) {
+		pr_err("Failed to find the parent domain\n");
+		return -ENXIO;
+	}
+
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	mutex_init(&priv->msi_map_lock);
+
+	ret = of_address_to_resource(node, 0, &res);
+	if (ret) {
+		pr_err("Failed to allocate resource\n");
+		goto err_priv;
+	}
+
+	priv->doorbell = res.start;
+
+	if (of_property_read_u32(node, "loongson,msi-base-vec",
+				&priv->irq_first)) {
+		pr_err("Unable to parse MSI vec base\n");
+		ret = -EINVAL;
+		goto err_priv;
+	}
+
+	if (of_property_read_u32(node, "loongson,msi-num-vecs",
+				&priv->num_irqs)) {
+		pr_err("Unable to parse MSI vec number\n");
+		ret = -EINVAL;
+		goto err_priv;
+	}
+
+	priv->msi_map = bitmap_zalloc(priv->num_irqs, GFP_KERNEL);
+	if (!priv->msi_map) {
+		ret = -ENOMEM;
+		goto err_priv;
+	}
+
+	pr_debug("Registering %d MSIs, starting at %d\n",
+		 priv->num_irqs, priv->irq_first);
+
+	ret = pch_msi_init_domains(priv, node, parent_domain);
+	if (ret)
+		goto err_map;
+
+	return 0;
+
+err_map:
+	kfree(priv->msi_map);
+err_priv:
+	kfree(priv);
+	return ret;
+}
+
+IRQCHIP_DECLARE(pch_msi, "loongson,pch-msi-1.0", pch_msi_init);
diff --git a/drivers/irqchip/irq-loongson-pch-pic.c b/drivers/irqchip/irq-loongson-pch-pic.c
new file mode 100644
index 0000000..90e1ad6
--- /dev/null
+++ b/drivers/irqchip/irq-loongson-pch-pic.c
@@ -0,0 +1,256 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  Copyright (C) 2020, Jiaxun Yang <jiaxun.yang@flygoat.com>
+ *  Loongson PCH PIC support
+ */
+
+#define pr_fmt(fmt) "pch-pic: " fmt
+
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/irqchip.h>
+#include <linux/irqdomain.h>
+#include <linux/kernel.h>
+#include <linux/platform_device.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/of_platform.h>
+
+/* Registers */
+#define PCH_PIC_MASK		0x20
+#define PCH_PIC_HTMSI_EN	0x40
+#define PCH_PIC_EDGE		0x60
+#define PCH_PIC_CLR		0x80
+#define PCH_PIC_AUTO0		0xc0
+#define PCH_PIC_AUTO1		0xe0
+#define PCH_INT_ROUTE(irq)	(0x100 + irq)
+#define PCH_INT_HTVEC(irq)	(0x200 + irq)
+#define PCH_PIC_POL		0x3e0
+
+#define PIC_COUNT_PER_REG	32
+#define PIC_REG_COUNT		2
+#define PIC_COUNT		(PIC_COUNT_PER_REG * PIC_REG_COUNT)
+#define PIC_REG_IDX(irq_id)	((irq_id) / PIC_COUNT_PER_REG)
+#define PIC_REG_BIT(irq_id)	((irq_id) % PIC_COUNT_PER_REG)
+
+struct pch_pic {
+	void __iomem		*base;
+	struct irq_domain	*pic_domain;
+	u32			ht_vec_base;
+	raw_spinlock_t		pic_lock;
+};
+
+static void pch_pic_bitset(struct pch_pic *priv, int offset, int bit)
+{
+	u32 reg;
+	void __iomem *addr = priv->base + offset + PIC_REG_IDX(bit) * 4;
+
+	raw_spin_lock(&priv->pic_lock);
+	reg = readl(addr);
+	reg |= BIT(PIC_REG_BIT(bit));
+	writel(reg, addr);
+	raw_spin_unlock(&priv->pic_lock);
+}
+
+static void pch_pic_bitclr(struct pch_pic *priv, int offset, int bit)
+{
+	u32 reg;
+	void __iomem *addr = priv->base + offset + PIC_REG_IDX(bit) * 4;
+
+	raw_spin_lock(&priv->pic_lock);
+	reg = readl(addr);
+	reg &= ~BIT(PIC_REG_BIT(bit));
+	writel(reg, addr);
+	raw_spin_unlock(&priv->pic_lock);
+}
+
+static void pch_pic_mask_irq(struct irq_data *d)
+{
+	struct pch_pic *priv = irq_data_get_irq_chip_data(d);
+
+	pch_pic_bitset(priv, PCH_PIC_MASK, d->hwirq);
+	irq_chip_mask_parent(d);
+}
+
+static void pch_pic_unmask_irq(struct irq_data *d)
+{
+	struct pch_pic *priv = irq_data_get_irq_chip_data(d);
+
+	writel(BIT(PIC_REG_BIT(d->hwirq)),
+			priv->base + PCH_PIC_CLR + PIC_REG_IDX(d->hwirq) * 4);
+
+	irq_chip_unmask_parent(d);
+	pch_pic_bitclr(priv, PCH_PIC_MASK, d->hwirq);
+}
+
+static int pch_pic_set_type(struct irq_data *d, unsigned int type)
+{
+	struct pch_pic *priv = irq_data_get_irq_chip_data(d);
+	int ret = 0;
+
+	switch (type) {
+	case IRQ_TYPE_EDGE_RISING:
+		pch_pic_bitset(priv, PCH_PIC_EDGE, d->hwirq);
+		pch_pic_bitclr(priv, PCH_PIC_POL, d->hwirq);
+		irq_set_handler_locked(d, handle_edge_irq);
+		break;
+	case IRQ_TYPE_EDGE_FALLING:
+		pch_pic_bitset(priv, PCH_PIC_EDGE, d->hwirq);
+		pch_pic_bitset(priv, PCH_PIC_POL, d->hwirq);
+		irq_set_handler_locked(d, handle_edge_irq);
+		break;
+	case IRQ_TYPE_LEVEL_HIGH:
+		pch_pic_bitclr(priv, PCH_PIC_EDGE, d->hwirq);
+		pch_pic_bitclr(priv, PCH_PIC_POL, d->hwirq);
+		irq_set_handler_locked(d, handle_level_irq);
+		break;
+	case IRQ_TYPE_LEVEL_LOW:
+		pch_pic_bitclr(priv, PCH_PIC_EDGE, d->hwirq);
+		pch_pic_bitset(priv, PCH_PIC_POL, d->hwirq);
+		irq_set_handler_locked(d, handle_level_irq);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
+static void pch_pic_ack_irq(struct irq_data *d)
+{
+	unsigned int reg;
+	struct pch_pic *priv = irq_data_get_irq_chip_data(d);
+
+	reg = readl(priv->base + PCH_PIC_EDGE + PIC_REG_IDX(d->hwirq) * 4);
+	if (reg & BIT(PIC_REG_BIT(d->hwirq))) {
+		writel(BIT(PIC_REG_BIT(d->hwirq)),
+			priv->base + PCH_PIC_CLR + PIC_REG_IDX(d->hwirq) * 4);
+	}
+	irq_chip_ack_parent(d);
+}
+
+static struct irq_chip pch_pic_irq_chip = {
+	.name			= "PCH PIC",
+	.irq_mask		= pch_pic_mask_irq,
+	.irq_unmask		= pch_pic_unmask_irq,
+	.irq_ack		= pch_pic_ack_irq,
+	.irq_set_affinity	= irq_chip_set_affinity_parent,
+	.irq_set_type		= pch_pic_set_type,
+};
+
+static int pch_pic_alloc(struct irq_domain *domain, unsigned int virq,
+			      unsigned int nr_irqs, void *arg)
+{
+	int err;
+	unsigned int type;
+	unsigned long hwirq;
+	struct irq_fwspec *fwspec = arg;
+	struct irq_fwspec parent_fwspec;
+	struct pch_pic *priv = domain->host_data;
+
+	err = irq_domain_translate_twocell(domain, fwspec, &hwirq, &type);
+	if (err)
+		return err;
+
+	parent_fwspec.fwnode = domain->parent->fwnode;
+	parent_fwspec.param_count = 1;
+	parent_fwspec.param[0] = hwirq + priv->ht_vec_base;
+
+	err = irq_domain_alloc_irqs_parent(domain, virq, 1, &parent_fwspec);
+	if (err)
+		return err;
+
+	irq_domain_set_info(domain, virq, hwirq,
+			    &pch_pic_irq_chip, priv,
+			    handle_level_irq, NULL, NULL);
+	irq_set_probe(virq);
+
+	return 0;
+}
+
+static const struct irq_domain_ops pch_pic_domain_ops = {
+	.translate	= irq_domain_translate_twocell,
+	.alloc		= pch_pic_alloc,
+	.free		= irq_domain_free_irqs_parent,
+};
+
+static void pch_pic_reset(struct pch_pic *priv)
+{
+	int i;
+
+	for (i = 0; i < PIC_COUNT; i++) {
+		/* Write vectore ID */
+		writeb(priv->ht_vec_base + i, priv->base + PCH_INT_HTVEC(i));
+		/* Hardcode route to HT0 Lo */
+		writeb(1, priv->base + PCH_INT_ROUTE(i));
+	}
+
+	for (i = 0; i < PIC_REG_COUNT; i++) {
+		/* Clear IRQ cause registers, mask all interrupts */
+		writel_relaxed(0xFFFFFFFF, priv->base + PCH_PIC_MASK + 4 * i);
+		writel_relaxed(0xFFFFFFFF, priv->base + PCH_PIC_CLR + 4 * i);
+		/* Clear auto bounce, we don't need that */
+		writel_relaxed(0, priv->base + PCH_PIC_AUTO0 + 4 * i);
+		writel_relaxed(0, priv->base + PCH_PIC_AUTO1 + 4 * i);
+		/* Enable HTMSI transformer */
+		writel_relaxed(0xFFFFFFFF, priv->base + PCH_PIC_HTMSI_EN + 4 * i);
+	}
+}
+
+static int pch_pic_of_init(struct device_node *node,
+				struct device_node *parent)
+{
+	struct pch_pic *priv;
+	struct irq_domain *parent_domain;
+	int err;
+
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	raw_spin_lock_init(&priv->pic_lock);
+	priv->base = of_iomap(node, 0);
+	if (!priv->base) {
+		err = -ENOMEM;
+		goto free_priv;
+	}
+
+	parent_domain = irq_find_host(parent);
+	if (!parent_domain) {
+		pr_err("Failed to find the parent domain\n");
+		err = -ENXIO;
+		goto iounmap_base;
+	}
+
+	if (of_property_read_u32(node, "loongson,pic-base-vec",
+				&priv->ht_vec_base)) {
+		pr_err("Failed to determine pic-base-vec\n");
+		err = -EINVAL;
+		goto iounmap_base;
+	}
+
+	priv->pic_domain = irq_domain_create_hierarchy(parent_domain, 0,
+						       PIC_COUNT,
+						       of_node_to_fwnode(node),
+						       &pch_pic_domain_ops,
+						       priv);
+	if (!priv->pic_domain) {
+		pr_err("Failed to create IRQ domain\n");
+		err = -ENOMEM;
+		goto iounmap_base;
+	}
+
+	pch_pic_reset(priv);
+
+	return 0;
+
+iounmap_base:
+	iounmap(priv->base);
+free_priv:
+	kfree(priv);
+
+	return err;
+}
+
+IRQCHIP_DECLARE(pch_pic, "loongson,pch-pic-1.0", pch_pic_of_init);
diff --git a/drivers/irqchip/irq-ls-extirq.c b/drivers/irqchip/irq-ls-extirq.c
new file mode 100644
index 0000000..4d1179f
--- /dev/null
+++ b/drivers/irqchip/irq-ls-extirq.c
@@ -0,0 +1,197 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define pr_fmt(fmt) "irq-ls-extirq: " fmt
+
+#include <linux/irq.h>
+#include <linux/irqchip.h>
+#include <linux/irqdomain.h>
+#include <linux/of.h>
+#include <linux/mfd/syscon.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+
+#define MAXIRQ 12
+#define LS1021A_SCFGREVCR 0x200
+
+struct ls_extirq_data {
+	struct regmap		*syscon;
+	u32			intpcr;
+	bool			bit_reverse;
+	u32			nirq;
+	struct irq_fwspec	map[MAXIRQ];
+};
+
+static int
+ls_extirq_set_type(struct irq_data *data, unsigned int type)
+{
+	struct ls_extirq_data *priv = data->chip_data;
+	irq_hw_number_t hwirq = data->hwirq;
+	u32 value, mask;
+
+	if (priv->bit_reverse)
+		mask = 1U << (31 - hwirq);
+	else
+		mask = 1U << hwirq;
+
+	switch (type) {
+	case IRQ_TYPE_LEVEL_LOW:
+		type = IRQ_TYPE_LEVEL_HIGH;
+		value = mask;
+		break;
+	case IRQ_TYPE_EDGE_FALLING:
+		type = IRQ_TYPE_EDGE_RISING;
+		value = mask;
+		break;
+	case IRQ_TYPE_LEVEL_HIGH:
+	case IRQ_TYPE_EDGE_RISING:
+		value = 0;
+		break;
+	default:
+		return -EINVAL;
+	}
+	regmap_update_bits(priv->syscon, priv->intpcr, mask, value);
+
+	return irq_chip_set_type_parent(data, type);
+}
+
+static struct irq_chip ls_extirq_chip = {
+	.name			= "ls-extirq",
+	.irq_mask		= irq_chip_mask_parent,
+	.irq_unmask		= irq_chip_unmask_parent,
+	.irq_eoi		= irq_chip_eoi_parent,
+	.irq_set_type		= ls_extirq_set_type,
+	.irq_retrigger		= irq_chip_retrigger_hierarchy,
+	.irq_set_affinity	= irq_chip_set_affinity_parent,
+	.flags                  = IRQCHIP_SET_TYPE_MASKED,
+};
+
+static int
+ls_extirq_domain_alloc(struct irq_domain *domain, unsigned int virq,
+		       unsigned int nr_irqs, void *arg)
+{
+	struct ls_extirq_data *priv = domain->host_data;
+	struct irq_fwspec *fwspec = arg;
+	irq_hw_number_t hwirq;
+
+	if (fwspec->param_count != 2)
+		return -EINVAL;
+
+	hwirq = fwspec->param[0];
+	if (hwirq >= priv->nirq)
+		return -EINVAL;
+
+	irq_domain_set_hwirq_and_chip(domain, virq, hwirq, &ls_extirq_chip,
+				      priv);
+
+	return irq_domain_alloc_irqs_parent(domain, virq, 1, &priv->map[hwirq]);
+}
+
+static const struct irq_domain_ops extirq_domain_ops = {
+	.xlate		= irq_domain_xlate_twocell,
+	.alloc		= ls_extirq_domain_alloc,
+	.free		= irq_domain_free_irqs_common,
+};
+
+static int
+ls_extirq_parse_map(struct ls_extirq_data *priv, struct device_node *node)
+{
+	const __be32 *map;
+	u32 mapsize;
+	int ret;
+
+	map = of_get_property(node, "interrupt-map", &mapsize);
+	if (!map)
+		return -ENOENT;
+	if (mapsize % sizeof(*map))
+		return -EINVAL;
+	mapsize /= sizeof(*map);
+
+	while (mapsize) {
+		struct device_node *ipar;
+		u32 hwirq, intsize, j;
+
+		if (mapsize < 3)
+			return -EINVAL;
+		hwirq = be32_to_cpup(map);
+		if (hwirq >= MAXIRQ)
+			return -EINVAL;
+		priv->nirq = max(priv->nirq, hwirq + 1);
+
+		ipar = of_find_node_by_phandle(be32_to_cpup(map + 2));
+		map += 3;
+		mapsize -= 3;
+		if (!ipar)
+			return -EINVAL;
+		priv->map[hwirq].fwnode = &ipar->fwnode;
+		ret = of_property_read_u32(ipar, "#interrupt-cells", &intsize);
+		if (ret)
+			return ret;
+
+		if (intsize > mapsize)
+			return -EINVAL;
+
+		priv->map[hwirq].param_count = intsize;
+		for (j = 0; j < intsize; ++j)
+			priv->map[hwirq].param[j] = be32_to_cpup(map++);
+		mapsize -= intsize;
+	}
+	return 0;
+}
+
+static int __init
+ls_extirq_of_init(struct device_node *node, struct device_node *parent)
+{
+
+	struct irq_domain *domain, *parent_domain;
+	struct ls_extirq_data *priv;
+	int ret;
+
+	parent_domain = irq_find_host(parent);
+	if (!parent_domain) {
+		pr_err("Cannot find parent domain\n");
+		return -ENODEV;
+	}
+
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->syscon = syscon_node_to_regmap(node->parent);
+	if (IS_ERR(priv->syscon)) {
+		ret = PTR_ERR(priv->syscon);
+		pr_err("Failed to lookup parent regmap\n");
+		goto out;
+	}
+	ret = of_property_read_u32(node, "reg", &priv->intpcr);
+	if (ret) {
+		pr_err("Missing INTPCR offset value\n");
+		goto out;
+	}
+
+	ret = ls_extirq_parse_map(priv, node);
+	if (ret)
+		goto out;
+
+	if (of_device_is_compatible(node, "fsl,ls1021a-extirq")) {
+		u32 revcr;
+
+		ret = regmap_read(priv->syscon, LS1021A_SCFGREVCR, &revcr);
+		if (ret)
+			goto out;
+		priv->bit_reverse = (revcr != 0);
+	}
+
+	domain = irq_domain_add_hierarchy(parent_domain, 0, priv->nirq, node,
+					  &extirq_domain_ops, priv);
+	if (!domain)
+		ret = -ENOMEM;
+
+out:
+	if (ret)
+		kfree(priv);
+	return ret;
+}
+
+IRQCHIP_DECLARE(ls1021a_extirq, "fsl,ls1021a-extirq", ls_extirq_of_init);
diff --git a/drivers/irqchip/irq-meson-gpio.c b/drivers/irqchip/irq-meson-gpio.c
index 829084b..bc7aebc 100644
--- a/drivers/irqchip/irq-meson-gpio.c
+++ b/drivers/irqchip/irq-meson-gpio.c
@@ -24,50 +24,101 @@
 #define REG_PIN_47_SEL	0x08
 #define REG_FILTER_SEL	0x0c
 
+/* use for A1 like chips */
+#define REG_PIN_A1_SEL	0x04
+
 /*
  * Note: The S905X3 datasheet reports that BOTH_EDGE is controlled by
  * bits 24 to 31. Tests on the actual HW show that these bits are
  * stuck at 0. Bits 8 to 15 are responsive and have the expected
  * effect.
  */
-#define REG_EDGE_POL_EDGE(x)	BIT(x)
-#define REG_EDGE_POL_LOW(x)	BIT(16 + (x))
-#define REG_BOTH_EDGE(x)	BIT(8 + (x))
-#define REG_EDGE_POL_MASK(x)    (	\
-		REG_EDGE_POL_EDGE(x) |	\
-		REG_EDGE_POL_LOW(x)  |	\
-		REG_BOTH_EDGE(x))
+#define REG_EDGE_POL_EDGE(params, x)	BIT((params)->edge_single_offset + (x))
+#define REG_EDGE_POL_LOW(params, x)	BIT((params)->pol_low_offset + (x))
+#define REG_BOTH_EDGE(params, x)	BIT((params)->edge_both_offset + (x))
+#define REG_EDGE_POL_MASK(params, x)    (	\
+		REG_EDGE_POL_EDGE(params, x) |	\
+		REG_EDGE_POL_LOW(params, x)  |	\
+		REG_BOTH_EDGE(params, x))
 #define REG_PIN_SEL_SHIFT(x)	(((x) % 4) * 8)
 #define REG_FILTER_SEL_SHIFT(x)	((x) * 4)
 
+struct meson_gpio_irq_controller;
+static void meson8_gpio_irq_sel_pin(struct meson_gpio_irq_controller *ctl,
+				    unsigned int channel, unsigned long hwirq);
+static void meson_gpio_irq_init_dummy(struct meson_gpio_irq_controller *ctl);
+static void meson_a1_gpio_irq_sel_pin(struct meson_gpio_irq_controller *ctl,
+				      unsigned int channel,
+				      unsigned long hwirq);
+static void meson_a1_gpio_irq_init(struct meson_gpio_irq_controller *ctl);
+
+struct irq_ctl_ops {
+	void (*gpio_irq_sel_pin)(struct meson_gpio_irq_controller *ctl,
+				 unsigned int channel, unsigned long hwirq);
+	void (*gpio_irq_init)(struct meson_gpio_irq_controller *ctl);
+};
+
 struct meson_gpio_irq_params {
 	unsigned int nr_hwirq;
 	bool support_edge_both;
+	unsigned int edge_both_offset;
+	unsigned int edge_single_offset;
+	unsigned int pol_low_offset;
+	unsigned int pin_sel_mask;
+	struct irq_ctl_ops ops;
 };
 
+#define INIT_MESON_COMMON(irqs, init, sel)			\
+	.nr_hwirq = irqs,					\
+	.ops = {						\
+		.gpio_irq_init = init,				\
+		.gpio_irq_sel_pin = sel,			\
+	},
+
+#define INIT_MESON8_COMMON_DATA(irqs)				\
+	INIT_MESON_COMMON(irqs, meson_gpio_irq_init_dummy,	\
+			  meson8_gpio_irq_sel_pin)		\
+	.edge_single_offset = 0,				\
+	.pol_low_offset = 16,					\
+	.pin_sel_mask = 0xff,					\
+
+#define INIT_MESON_A1_COMMON_DATA(irqs)				\
+	INIT_MESON_COMMON(irqs, meson_a1_gpio_irq_init,		\
+			  meson_a1_gpio_irq_sel_pin)		\
+	.support_edge_both = true,				\
+	.edge_both_offset = 16,					\
+	.edge_single_offset = 8,				\
+	.pol_low_offset = 0,					\
+	.pin_sel_mask = 0x7f,					\
+
 static const struct meson_gpio_irq_params meson8_params = {
-	.nr_hwirq = 134,
+	INIT_MESON8_COMMON_DATA(134)
 };
 
 static const struct meson_gpio_irq_params meson8b_params = {
-	.nr_hwirq = 119,
+	INIT_MESON8_COMMON_DATA(119)
 };
 
 static const struct meson_gpio_irq_params gxbb_params = {
-	.nr_hwirq = 133,
+	INIT_MESON8_COMMON_DATA(133)
 };
 
 static const struct meson_gpio_irq_params gxl_params = {
-	.nr_hwirq = 110,
+	INIT_MESON8_COMMON_DATA(110)
 };
 
 static const struct meson_gpio_irq_params axg_params = {
-	.nr_hwirq = 100,
+	INIT_MESON8_COMMON_DATA(100)
 };
 
 static const struct meson_gpio_irq_params sm1_params = {
-	.nr_hwirq = 100,
+	INIT_MESON8_COMMON_DATA(100)
 	.support_edge_both = true,
+	.edge_both_offset = 8,
+};
+
+static const struct meson_gpio_irq_params a1_params = {
+	INIT_MESON_A1_COMMON_DATA(62)
 };
 
 static const struct of_device_id meson_irq_gpio_matches[] = {
@@ -78,6 +129,7 @@
 	{ .compatible = "amlogic,meson-axg-gpio-intc", .data = &axg_params },
 	{ .compatible = "amlogic,meson-g12a-gpio-intc", .data = &axg_params },
 	{ .compatible = "amlogic,meson-sm1-gpio-intc", .data = &sm1_params },
+	{ .compatible = "amlogic,meson-a1-gpio-intc", .data = &a1_params },
 	{ }
 };
 
@@ -92,17 +144,56 @@
 static void meson_gpio_irq_update_bits(struct meson_gpio_irq_controller *ctl,
 				       unsigned int reg, u32 mask, u32 val)
 {
+	unsigned long flags;
 	u32 tmp;
 
+	spin_lock_irqsave(&ctl->lock, flags);
+
 	tmp = readl_relaxed(ctl->base + reg);
 	tmp &= ~mask;
 	tmp |= val;
 	writel_relaxed(tmp, ctl->base + reg);
+
+	spin_unlock_irqrestore(&ctl->lock, flags);
 }
 
-static unsigned int meson_gpio_irq_channel_to_reg(unsigned int channel)
+static void meson_gpio_irq_init_dummy(struct meson_gpio_irq_controller *ctl)
 {
-	return (channel < 4) ? REG_PIN_03_SEL : REG_PIN_47_SEL;
+}
+
+static void meson8_gpio_irq_sel_pin(struct meson_gpio_irq_controller *ctl,
+				    unsigned int channel, unsigned long hwirq)
+{
+	unsigned int reg_offset;
+	unsigned int bit_offset;
+
+	reg_offset = (channel < 4) ? REG_PIN_03_SEL : REG_PIN_47_SEL;
+	bit_offset = REG_PIN_SEL_SHIFT(channel);
+
+	meson_gpio_irq_update_bits(ctl, reg_offset,
+				   ctl->params->pin_sel_mask << bit_offset,
+				   hwirq << bit_offset);
+}
+
+static void meson_a1_gpio_irq_sel_pin(struct meson_gpio_irq_controller *ctl,
+				      unsigned int channel,
+				      unsigned long hwirq)
+{
+	unsigned int reg_offset;
+	unsigned int bit_offset;
+
+	bit_offset = ((channel % 2) == 0) ? 0 : 16;
+	reg_offset = REG_PIN_A1_SEL + ((channel / 2) << 2);
+
+	meson_gpio_irq_update_bits(ctl, reg_offset,
+				   ctl->params->pin_sel_mask << bit_offset,
+				   hwirq << bit_offset);
+}
+
+/* For a1 or later chips like a1 there is a switch to enable/disable irq */
+static void meson_a1_gpio_irq_init(struct meson_gpio_irq_controller *ctl)
+{
+	meson_gpio_irq_update_bits(ctl, REG_EDGE_POL, BIT(31), BIT(31));
 }
 
 static int
@@ -110,14 +201,15 @@
 			       unsigned long  hwirq,
 			       u32 **channel_hwirq)
 {
-	unsigned int reg, idx;
+	unsigned long flags;
+	unsigned int idx;
 
-	spin_lock(&ctl->lock);
+	spin_lock_irqsave(&ctl->lock, flags);
 
 	/* Find a free channel */
 	idx = find_first_zero_bit(ctl->channel_map, NUM_CHANNEL);
 	if (idx >= NUM_CHANNEL) {
-		spin_unlock(&ctl->lock);
+		spin_unlock_irqrestore(&ctl->lock, flags);
 		pr_err("No channel available\n");
 		return -ENOSPC;
 	}
@@ -125,14 +217,13 @@
 	/* Mark the channel as used */
 	set_bit(idx, ctl->channel_map);
 
+	spin_unlock_irqrestore(&ctl->lock, flags);
+
 	/*
 	 * 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));
+	ctl->params->ops.gpio_irq_sel_pin(ctl, idx, hwirq);
 
 	/*
 	 * Get the hwirq number assigned to this channel through
@@ -142,8 +233,6 @@
 	 */
 	*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);
 
@@ -173,7 +262,9 @@
 {
 	u32 val = 0;
 	unsigned int idx;
+	const struct meson_gpio_irq_params *params;
 
+	params = ctl->params;
 	idx = meson_gpio_irq_get_channel_idx(ctl, channel_hwirq);
 
 	/*
@@ -190,24 +281,20 @@
 	 * precedence over the other edge/polarity settings
 	 */
 	if (type == IRQ_TYPE_EDGE_BOTH) {
-		if (!ctl->params->support_edge_both)
+		if (!params->support_edge_both)
 			return -EINVAL;
 
-		val |= REG_BOTH_EDGE(idx);
+		val |= REG_BOTH_EDGE(params, idx);
 	} else {
 		if (type & (IRQ_TYPE_EDGE_RISING | IRQ_TYPE_EDGE_FALLING))
-			val |= REG_EDGE_POL_EDGE(idx);
+			val |= REG_EDGE_POL_EDGE(params, idx);
 
 		if (type & (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_EDGE_FALLING))
-			val |= REG_EDGE_POL_LOW(idx);
+			val |= REG_EDGE_POL_LOW(params, idx);
 	}
 
-	spin_lock(&ctl->lock);
-
 	meson_gpio_irq_update_bits(ctl, REG_EDGE_POL,
-				   REG_EDGE_POL_MASK(idx), val);
-
-	spin_unlock(&ctl->lock);
+				   REG_EDGE_POL_MASK(params, idx), val);
 
 	return 0;
 }
@@ -371,6 +458,8 @@
 		return ret;
 	}
 
+	ctl->params->ops.gpio_irq_init(ctl);
+
 	return 0;
 }
 
diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c
index f398546..2158859 100644
--- a/drivers/irqchip/irq-mips-gic.c
+++ b/drivers/irqchip/irq-mips-gic.c
@@ -46,7 +46,7 @@
 
 void __iomem *mips_gic_base;
 
-DEFINE_PER_CPU_READ_MOSTLY(unsigned long[GIC_MAX_LONGS], pcpu_masks);
+static DEFINE_PER_CPU_READ_MOSTLY(unsigned long[GIC_MAX_LONGS], pcpu_masks);
 
 static DEFINE_SPINLOCK(gic_lock);
 static struct irq_domain *gic_irq_domain;
@@ -480,7 +480,7 @@
 	case GIC_LOCAL_INT_TIMER:
 		/* CONFIG_MIPS_CMP workaround (see __gic_init) */
 		map = GIC_MAP_PIN_MAP_TO_PIN | timer_cpu_pin;
-		/* fall-through */
+		fallthrough;
 	case GIC_LOCAL_INT_PERFCTR:
 	case GIC_LOCAL_INT_FDC:
 		/*
@@ -617,8 +617,8 @@
 	return ret;
 }
 
-void gic_ipi_domain_free(struct irq_domain *d, unsigned int virq,
-			 unsigned int nr_irqs)
+static void gic_ipi_domain_free(struct irq_domain *d, unsigned int virq,
+				unsigned int nr_irqs)
 {
 	irq_hw_number_t base_hwirq;
 	struct irq_data *data;
@@ -631,8 +631,8 @@
 	bitmap_set(ipi_available, base_hwirq, nr_irqs);
 }
 
-int gic_ipi_domain_match(struct irq_domain *d, struct device_node *node,
-			 enum irq_domain_bus_token bus_token)
+static int gic_ipi_domain_match(struct irq_domain *d, struct device_node *node,
+				enum irq_domain_bus_token bus_token)
 {
 	bool is_ipi;
 
@@ -716,7 +716,7 @@
 		__sync();
 	}
 
-	mips_gic_base = ioremap_nocache(gic_base, gic_len);
+	mips_gic_base = ioremap(gic_base, gic_len);
 
 	gicconfig = read_gic_config();
 	gic_shared_intrs = gicconfig & GIC_CONFIG_NUMINTERRUPTS;
diff --git a/drivers/irqchip/irq-mst-intc.c b/drivers/irqchip/irq-mst-intc.c
new file mode 100644
index 0000000..143657b
--- /dev/null
+++ b/drivers/irqchip/irq-mst-intc.c
@@ -0,0 +1,199 @@
+// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause)
+/*
+ * Copyright (c) 2020 MediaTek Inc.
+ * Author Mark-PK Tsai <mark-pk.tsai@mediatek.com>
+ */
+#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 <linux/slab.h>
+#include <linux/spinlock.h>
+
+#define INTC_MASK	0x0
+#define INTC_EOI	0x20
+
+struct mst_intc_chip_data {
+	raw_spinlock_t	lock;
+	unsigned int	irq_start, nr_irqs;
+	void __iomem	*base;
+	bool		no_eoi;
+};
+
+static void mst_set_irq(struct irq_data *d, u32 offset)
+{
+	irq_hw_number_t hwirq = irqd_to_hwirq(d);
+	struct mst_intc_chip_data *cd = irq_data_get_irq_chip_data(d);
+	u16 val, mask;
+	unsigned long flags;
+
+	mask = 1 << (hwirq % 16);
+	offset += (hwirq / 16) * 4;
+
+	raw_spin_lock_irqsave(&cd->lock, flags);
+	val = readw_relaxed(cd->base + offset) | mask;
+	writew_relaxed(val, cd->base + offset);
+	raw_spin_unlock_irqrestore(&cd->lock, flags);
+}
+
+static void mst_clear_irq(struct irq_data *d, u32 offset)
+{
+	irq_hw_number_t hwirq = irqd_to_hwirq(d);
+	struct mst_intc_chip_data *cd = irq_data_get_irq_chip_data(d);
+	u16 val, mask;
+	unsigned long flags;
+
+	mask = 1 << (hwirq % 16);
+	offset += (hwirq / 16) * 4;
+
+	raw_spin_lock_irqsave(&cd->lock, flags);
+	val = readw_relaxed(cd->base + offset) & ~mask;
+	writew_relaxed(val, cd->base + offset);
+	raw_spin_unlock_irqrestore(&cd->lock, flags);
+}
+
+static void mst_intc_mask_irq(struct irq_data *d)
+{
+	mst_set_irq(d, INTC_MASK);
+	irq_chip_mask_parent(d);
+}
+
+static void mst_intc_unmask_irq(struct irq_data *d)
+{
+	mst_clear_irq(d, INTC_MASK);
+	irq_chip_unmask_parent(d);
+}
+
+static void mst_intc_eoi_irq(struct irq_data *d)
+{
+	struct mst_intc_chip_data *cd = irq_data_get_irq_chip_data(d);
+
+	if (!cd->no_eoi)
+		mst_set_irq(d, INTC_EOI);
+
+	irq_chip_eoi_parent(d);
+}
+
+static struct irq_chip mst_intc_chip = {
+	.name			= "mst-intc",
+	.irq_mask		= mst_intc_mask_irq,
+	.irq_unmask		= mst_intc_unmask_irq,
+	.irq_eoi		= mst_intc_eoi_irq,
+	.irq_get_irqchip_state	= irq_chip_get_parent_state,
+	.irq_set_irqchip_state	= irq_chip_set_parent_state,
+	.irq_set_affinity	= irq_chip_set_affinity_parent,
+	.irq_set_vcpu_affinity	= irq_chip_set_vcpu_affinity_parent,
+	.irq_set_type		= irq_chip_set_type_parent,
+	.irq_retrigger		= irq_chip_retrigger_hierarchy,
+	.flags			= IRQCHIP_SET_TYPE_MASKED |
+				  IRQCHIP_SKIP_SET_WAKE |
+				  IRQCHIP_MASK_ON_SUSPEND,
+};
+
+static int mst_intc_domain_translate(struct irq_domain *d,
+				     struct irq_fwspec *fwspec,
+				     unsigned long *hwirq,
+				     unsigned int *type)
+{
+	struct mst_intc_chip_data *cd = d->host_data;
+
+	if (is_of_node(fwspec->fwnode)) {
+		if (fwspec->param_count != 3)
+			return -EINVAL;
+
+		/* No PPI should point to this domain */
+		if (fwspec->param[0] != 0)
+			return -EINVAL;
+
+		if (fwspec->param[1] >= cd->nr_irqs)
+			return -EINVAL;
+
+		*hwirq = fwspec->param[1];
+		*type = fwspec->param[2] & IRQ_TYPE_SENSE_MASK;
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
+static int mst_intc_domain_alloc(struct irq_domain *domain, unsigned int virq,
+				 unsigned int nr_irqs, void *data)
+{
+	int i;
+	irq_hw_number_t hwirq;
+	struct irq_fwspec parent_fwspec, *fwspec = data;
+	struct mst_intc_chip_data *cd = domain->host_data;
+
+	/* Not GIC compliant */
+	if (fwspec->param_count != 3)
+		return -EINVAL;
+
+	/* No PPI should point to this domain */
+	if (fwspec->param[0])
+		return -EINVAL;
+
+	hwirq = fwspec->param[1];
+	for (i = 0; i < nr_irqs; i++)
+		irq_domain_set_hwirq_and_chip(domain, virq + i, hwirq + i,
+					      &mst_intc_chip,
+					      domain->host_data);
+
+	parent_fwspec = *fwspec;
+	parent_fwspec.fwnode = domain->parent->fwnode;
+	parent_fwspec.param[1] = cd->irq_start + hwirq;
+	return irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, &parent_fwspec);
+}
+
+static const struct irq_domain_ops mst_intc_domain_ops = {
+	.translate	= mst_intc_domain_translate,
+	.alloc		= mst_intc_domain_alloc,
+	.free		= irq_domain_free_irqs_common,
+};
+
+static int __init mst_intc_of_init(struct device_node *dn,
+				   struct device_node *parent)
+{
+	struct irq_domain *domain, *domain_parent;
+	struct mst_intc_chip_data *cd;
+	u32 irq_start, irq_end;
+
+	domain_parent = irq_find_host(parent);
+	if (!domain_parent) {
+		pr_err("mst-intc: interrupt-parent not found\n");
+		return -EINVAL;
+	}
+
+	if (of_property_read_u32_index(dn, "mstar,irqs-map-range", 0, &irq_start) ||
+	    of_property_read_u32_index(dn, "mstar,irqs-map-range", 1, &irq_end))
+		return -EINVAL;
+
+	cd = kzalloc(sizeof(*cd), GFP_KERNEL);
+	if (!cd)
+		return -ENOMEM;
+
+	cd->base = of_iomap(dn, 0);
+	if (!cd->base) {
+		kfree(cd);
+		return -ENOMEM;
+	}
+
+	cd->no_eoi = of_property_read_bool(dn, "mstar,intc-no-eoi");
+	raw_spin_lock_init(&cd->lock);
+	cd->irq_start = irq_start;
+	cd->nr_irqs = irq_end - irq_start + 1;
+	domain = irq_domain_add_hierarchy(domain_parent, 0, cd->nr_irqs, dn,
+					  &mst_intc_domain_ops, cd);
+	if (!domain) {
+		iounmap(cd->base);
+		kfree(cd);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+IRQCHIP_DECLARE(mst_intc, "mstar,mst-intc", mst_intc_of_init);
diff --git a/drivers/irqchip/irq-mvebu-icu.c b/drivers/irqchip/irq-mvebu-icu.c
index 547045d..91adf77 100644
--- a/drivers/irqchip/irq-mvebu-icu.c
+++ b/drivers/irqchip/irq-mvebu-icu.c
@@ -66,7 +66,7 @@
 	unsigned int type;
 };
 
-DEFINE_STATIC_KEY_FALSE(legacy_bindings);
+static DEFINE_STATIC_KEY_FALSE(legacy_bindings);
 
 static void mvebu_icu_init(struct mvebu_icu *icu,
 			   struct mvebu_icu_msi_data *msi_data,
diff --git a/drivers/irqchip/irq-nvic.c b/drivers/irqchip/irq-nvic.c
index a166d30..21cb31f 100644
--- a/drivers/irqchip/irq-nvic.c
+++ b/drivers/irqchip/irq-nvic.c
@@ -26,7 +26,7 @@
 
 #define NVIC_ISER		0x000
 #define NVIC_ICER		0x080
-#define NVIC_IPR		0x300
+#define NVIC_IPR		0x400
 
 #define NVIC_MAX_BANKS		16
 /*
@@ -45,17 +45,6 @@
 	handle_IRQ(irq, regs);
 }
 
-static int nvic_irq_domain_translate(struct irq_domain *d,
-				     struct irq_fwspec *fwspec,
-				     unsigned long *hwirq, unsigned int *type)
-{
-	if (WARN_ON(fwspec->param_count < 1))
-		return -EINVAL;
-	*hwirq = fwspec->param[0];
-	*type = IRQ_TYPE_NONE;
-	return 0;
-}
-
 static int nvic_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
 				unsigned int nr_irqs, void *arg)
 {
@@ -64,7 +53,7 @@
 	unsigned int type = IRQ_TYPE_NONE;
 	struct irq_fwspec *fwspec = arg;
 
-	ret = nvic_irq_domain_translate(domain, fwspec, &hwirq, &type);
+	ret = irq_domain_translate_onecell(domain, fwspec, &hwirq, &type);
 	if (ret)
 		return ret;
 
@@ -75,7 +64,7 @@
 }
 
 static const struct irq_domain_ops nvic_irq_domain_ops = {
-	.translate = nvic_irq_domain_translate,
+	.translate = irq_domain_translate_onecell,
 	.alloc = nvic_irq_domain_alloc,
 	.free = irq_domain_free_irqs_top,
 };
diff --git a/drivers/irqchip/irq-owl-sirq.c b/drivers/irqchip/irq-owl-sirq.c
new file mode 100644
index 0000000..6e41274
--- /dev/null
+++ b/drivers/irqchip/irq-owl-sirq.c
@@ -0,0 +1,359 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Actions Semi Owl SoCs SIRQ interrupt controller driver
+ *
+ * Copyright (C) 2014 Actions Semi Inc.
+ * David Liu <liuwei@actions-semi.com>
+ *
+ * Author: Parthiban Nallathambi <pn@denx.de>
+ * Author: Saravanan Sekar <sravanhome@gmail.com>
+ * Author: Cristian Ciocaltea <cristian.ciocaltea@gmail.com>
+ */
+
+#include <linux/bitfield.h>
+#include <linux/interrupt.h>
+#include <linux/irqchip.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+
+#define NUM_SIRQ			3
+
+#define INTC_EXTCTL_PENDING		BIT(0)
+#define INTC_EXTCTL_CLK_SEL		BIT(4)
+#define INTC_EXTCTL_EN			BIT(5)
+#define INTC_EXTCTL_TYPE_MASK		GENMASK(7, 6)
+#define INTC_EXTCTL_TYPE_HIGH		0
+#define INTC_EXTCTL_TYPE_LOW		BIT(6)
+#define INTC_EXTCTL_TYPE_RISING		BIT(7)
+#define INTC_EXTCTL_TYPE_FALLING	(BIT(6) | BIT(7))
+
+/* S500 & S700 SIRQ control register masks */
+#define INTC_EXTCTL_SIRQ0_MASK		GENMASK(23, 16)
+#define INTC_EXTCTL_SIRQ1_MASK		GENMASK(15, 8)
+#define INTC_EXTCTL_SIRQ2_MASK		GENMASK(7, 0)
+
+/* S900 SIRQ control register offsets, relative to controller base address */
+#define INTC_EXTCTL0			0x0000
+#define INTC_EXTCTL1			0x0328
+#define INTC_EXTCTL2			0x032c
+
+struct owl_sirq_params {
+	/* INTC_EXTCTL reg shared for all three SIRQ lines */
+	bool reg_shared;
+	/* INTC_EXTCTL reg offsets relative to controller base address */
+	u16 reg_offset[NUM_SIRQ];
+};
+
+struct owl_sirq_chip_data {
+	const struct owl_sirq_params	*params;
+	void __iomem			*base;
+	raw_spinlock_t			lock;
+	u32				ext_irqs[NUM_SIRQ];
+};
+
+/* S500 & S700 SoCs */
+static const struct owl_sirq_params owl_sirq_s500_params = {
+	.reg_shared = true,
+	.reg_offset = { 0, 0, 0 },
+};
+
+/* S900 SoC */
+static const struct owl_sirq_params owl_sirq_s900_params = {
+	.reg_shared = false,
+	.reg_offset = { INTC_EXTCTL0, INTC_EXTCTL1, INTC_EXTCTL2 },
+};
+
+static u32 owl_field_get(u32 val, u32 index)
+{
+	switch (index) {
+	case 0:
+		return FIELD_GET(INTC_EXTCTL_SIRQ0_MASK, val);
+	case 1:
+		return FIELD_GET(INTC_EXTCTL_SIRQ1_MASK, val);
+	case 2:
+	default:
+		return FIELD_GET(INTC_EXTCTL_SIRQ2_MASK, val);
+	}
+}
+
+static u32 owl_field_prep(u32 val, u32 index)
+{
+	switch (index) {
+	case 0:
+		return FIELD_PREP(INTC_EXTCTL_SIRQ0_MASK, val);
+	case 1:
+		return FIELD_PREP(INTC_EXTCTL_SIRQ1_MASK, val);
+	case 2:
+	default:
+		return FIELD_PREP(INTC_EXTCTL_SIRQ2_MASK, val);
+	}
+}
+
+static u32 owl_sirq_read_extctl(struct owl_sirq_chip_data *data, u32 index)
+{
+	u32 val;
+
+	val = readl_relaxed(data->base + data->params->reg_offset[index]);
+	if (data->params->reg_shared)
+		val = owl_field_get(val, index);
+
+	return val;
+}
+
+static void owl_sirq_write_extctl(struct owl_sirq_chip_data *data,
+				  u32 extctl, u32 index)
+{
+	u32 val;
+
+	if (data->params->reg_shared) {
+		val = readl_relaxed(data->base + data->params->reg_offset[index]);
+		val &= ~owl_field_prep(0xff, index);
+		extctl = owl_field_prep(extctl, index) | val;
+	}
+
+	writel_relaxed(extctl, data->base + data->params->reg_offset[index]);
+}
+
+static void owl_sirq_clear_set_extctl(struct owl_sirq_chip_data *d,
+				      u32 clear, u32 set, u32 index)
+{
+	unsigned long flags;
+	u32 val;
+
+	raw_spin_lock_irqsave(&d->lock, flags);
+	val = owl_sirq_read_extctl(d, index);
+	val &= ~clear;
+	val |= set;
+	owl_sirq_write_extctl(d, val, index);
+	raw_spin_unlock_irqrestore(&d->lock, flags);
+}
+
+static void owl_sirq_eoi(struct irq_data *data)
+{
+	struct owl_sirq_chip_data *chip_data = irq_data_get_irq_chip_data(data);
+
+	/*
+	 * Software must clear external interrupt pending, when interrupt type
+	 * is edge triggered, so we need per SIRQ based clearing.
+	 */
+	if (!irqd_is_level_type(data))
+		owl_sirq_clear_set_extctl(chip_data, 0, INTC_EXTCTL_PENDING,
+					  data->hwirq);
+
+	irq_chip_eoi_parent(data);
+}
+
+static void owl_sirq_mask(struct irq_data *data)
+{
+	struct owl_sirq_chip_data *chip_data = irq_data_get_irq_chip_data(data);
+
+	owl_sirq_clear_set_extctl(chip_data, INTC_EXTCTL_EN, 0, data->hwirq);
+	irq_chip_mask_parent(data);
+}
+
+static void owl_sirq_unmask(struct irq_data *data)
+{
+	struct owl_sirq_chip_data *chip_data = irq_data_get_irq_chip_data(data);
+
+	owl_sirq_clear_set_extctl(chip_data, 0, INTC_EXTCTL_EN, data->hwirq);
+	irq_chip_unmask_parent(data);
+}
+
+/*
+ * GIC does not handle falling edge or active low, hence SIRQ shall be
+ * programmed to convert falling edge to rising edge signal and active
+ * low to active high signal.
+ */
+static int owl_sirq_set_type(struct irq_data *data, unsigned int type)
+{
+	struct owl_sirq_chip_data *chip_data = irq_data_get_irq_chip_data(data);
+	u32 sirq_type;
+
+	switch (type) {
+	case IRQ_TYPE_LEVEL_LOW:
+		sirq_type = INTC_EXTCTL_TYPE_LOW;
+		type = IRQ_TYPE_LEVEL_HIGH;
+		break;
+	case IRQ_TYPE_LEVEL_HIGH:
+		sirq_type = INTC_EXTCTL_TYPE_HIGH;
+		break;
+	case IRQ_TYPE_EDGE_FALLING:
+		sirq_type = INTC_EXTCTL_TYPE_FALLING;
+		type = IRQ_TYPE_EDGE_RISING;
+		break;
+	case IRQ_TYPE_EDGE_RISING:
+		sirq_type = INTC_EXTCTL_TYPE_RISING;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	owl_sirq_clear_set_extctl(chip_data, INTC_EXTCTL_TYPE_MASK, sirq_type,
+				  data->hwirq);
+
+	return irq_chip_set_type_parent(data, type);
+}
+
+static struct irq_chip owl_sirq_chip = {
+	.name		= "owl-sirq",
+	.irq_mask	= owl_sirq_mask,
+	.irq_unmask	= owl_sirq_unmask,
+	.irq_eoi	= owl_sirq_eoi,
+	.irq_set_type	= owl_sirq_set_type,
+	.irq_retrigger	= irq_chip_retrigger_hierarchy,
+#ifdef CONFIG_SMP
+	.irq_set_affinity = irq_chip_set_affinity_parent,
+#endif
+};
+
+static int owl_sirq_domain_translate(struct irq_domain *d,
+				     struct irq_fwspec *fwspec,
+				     unsigned long *hwirq,
+				     unsigned int *type)
+{
+	if (!is_of_node(fwspec->fwnode))
+		return -EINVAL;
+
+	if (fwspec->param_count != 2 || fwspec->param[0] >= NUM_SIRQ)
+		return -EINVAL;
+
+	*hwirq = fwspec->param[0];
+	*type = fwspec->param[1];
+
+	return 0;
+}
+
+static int owl_sirq_domain_alloc(struct irq_domain *domain, unsigned int virq,
+				 unsigned int nr_irqs, void *data)
+{
+	struct owl_sirq_chip_data *chip_data = domain->host_data;
+	struct irq_fwspec *fwspec = data;
+	struct irq_fwspec parent_fwspec;
+	irq_hw_number_t hwirq;
+	unsigned int type;
+	int ret;
+
+	if (WARN_ON(nr_irqs != 1))
+		return -EINVAL;
+
+	ret = owl_sirq_domain_translate(domain, fwspec, &hwirq, &type);
+	if (ret)
+		return ret;
+
+	switch (type) {
+	case IRQ_TYPE_EDGE_RISING:
+	case IRQ_TYPE_LEVEL_HIGH:
+		break;
+	case IRQ_TYPE_EDGE_FALLING:
+		type = IRQ_TYPE_EDGE_RISING;
+		break;
+	case IRQ_TYPE_LEVEL_LOW:
+		type = IRQ_TYPE_LEVEL_HIGH;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	irq_domain_set_hwirq_and_chip(domain, virq, hwirq, &owl_sirq_chip,
+				      chip_data);
+
+	parent_fwspec.fwnode = domain->parent->fwnode;
+	parent_fwspec.param_count = 3;
+	parent_fwspec.param[0] = GIC_SPI;
+	parent_fwspec.param[1] = chip_data->ext_irqs[hwirq];
+	parent_fwspec.param[2] = type;
+
+	return irq_domain_alloc_irqs_parent(domain, virq, 1, &parent_fwspec);
+}
+
+static const struct irq_domain_ops owl_sirq_domain_ops = {
+	.translate	= owl_sirq_domain_translate,
+	.alloc		= owl_sirq_domain_alloc,
+	.free		= irq_domain_free_irqs_common,
+};
+
+static int __init owl_sirq_init(const struct owl_sirq_params *params,
+				struct device_node *node,
+				struct device_node *parent)
+{
+	struct irq_domain *domain, *parent_domain;
+	struct owl_sirq_chip_data *chip_data;
+	int ret, i;
+
+	parent_domain = irq_find_host(parent);
+	if (!parent_domain) {
+		pr_err("%pOF: failed to find sirq parent domain\n", node);
+		return -ENXIO;
+	}
+
+	chip_data = kzalloc(sizeof(*chip_data), GFP_KERNEL);
+	if (!chip_data)
+		return -ENOMEM;
+
+	raw_spin_lock_init(&chip_data->lock);
+
+	chip_data->params = params;
+
+	chip_data->base = of_iomap(node, 0);
+	if (!chip_data->base) {
+		pr_err("%pOF: failed to map sirq registers\n", node);
+		ret = -ENXIO;
+		goto out_free;
+	}
+
+	for (i = 0; i < NUM_SIRQ; i++) {
+		struct of_phandle_args irq;
+
+		ret = of_irq_parse_one(node, i, &irq);
+		if (ret) {
+			pr_err("%pOF: failed to parse interrupt %d\n", node, i);
+			goto out_unmap;
+		}
+
+		if (WARN_ON(irq.args_count != 3)) {
+			ret = -EINVAL;
+			goto out_unmap;
+		}
+
+		chip_data->ext_irqs[i] = irq.args[1];
+
+		/* Set 24MHz external interrupt clock freq */
+		owl_sirq_clear_set_extctl(chip_data, 0, INTC_EXTCTL_CLK_SEL, i);
+	}
+
+	domain = irq_domain_add_hierarchy(parent_domain, 0, NUM_SIRQ, node,
+					  &owl_sirq_domain_ops, chip_data);
+	if (!domain) {
+		pr_err("%pOF: failed to add domain\n", node);
+		ret = -ENOMEM;
+		goto out_unmap;
+	}
+
+	return 0;
+
+out_unmap:
+	iounmap(chip_data->base);
+out_free:
+	kfree(chip_data);
+
+	return ret;
+}
+
+static int __init owl_sirq_s500_of_init(struct device_node *node,
+					struct device_node *parent)
+{
+	return owl_sirq_init(&owl_sirq_s500_params, node, parent);
+}
+
+IRQCHIP_DECLARE(owl_sirq_s500, "actions,s500-sirq", owl_sirq_s500_of_init);
+IRQCHIP_DECLARE(owl_sirq_s700, "actions,s700-sirq", owl_sirq_s500_of_init);
+
+static int __init owl_sirq_s900_of_init(struct device_node *node,
+					struct device_node *parent)
+{
+	return owl_sirq_init(&owl_sirq_s900_params, node, parent);
+}
+
+IRQCHIP_DECLARE(owl_sirq_s900, "actions,s900-sirq", owl_sirq_s900_of_init);
diff --git a/drivers/irqchip/irq-pruss-intc.c b/drivers/irqchip/irq-pruss-intc.c
new file mode 100644
index 0000000..92fb578
--- /dev/null
+++ b/drivers/irqchip/irq-pruss-intc.c
@@ -0,0 +1,664 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * PRU-ICSS INTC IRQChip driver for various TI SoCs
+ *
+ * Copyright (C) 2016-2020 Texas Instruments Incorporated - http://www.ti.com/
+ *
+ * Author(s):
+ *	Andrew F. Davis <afd@ti.com>
+ *	Suman Anna <s-anna@ti.com>
+ *	Grzegorz Jaszczyk <grzegorz.jaszczyk@linaro.org> for Texas Instruments
+ *
+ * Copyright (C) 2019 David Lechner <david@lechnology.com>
+ */
+
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/irqchip/chained_irq.h>
+#include <linux/irqdomain.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+
+/*
+ * Number of host interrupts reaching the main MPU sub-system. Note that this
+ * is not the same as the total number of host interrupts supported by the PRUSS
+ * INTC instance
+ */
+#define MAX_NUM_HOST_IRQS	8
+
+/* minimum starting host interrupt number for MPU */
+#define FIRST_PRU_HOST_INT	2
+
+/* PRU_ICSS_INTC registers */
+#define PRU_INTC_REVID		0x0000
+#define PRU_INTC_CR		0x0004
+#define PRU_INTC_GER		0x0010
+#define PRU_INTC_GNLR		0x001c
+#define PRU_INTC_SISR		0x0020
+#define PRU_INTC_SICR		0x0024
+#define PRU_INTC_EISR		0x0028
+#define PRU_INTC_EICR		0x002c
+#define PRU_INTC_HIEISR		0x0034
+#define PRU_INTC_HIDISR		0x0038
+#define PRU_INTC_GPIR		0x0080
+#define PRU_INTC_SRSR(x)	(0x0200 + (x) * 4)
+#define PRU_INTC_SECR(x)	(0x0280 + (x) * 4)
+#define PRU_INTC_ESR(x)		(0x0300 + (x) * 4)
+#define PRU_INTC_ECR(x)		(0x0380 + (x) * 4)
+#define PRU_INTC_CMR(x)		(0x0400 + (x) * 4)
+#define PRU_INTC_HMR(x)		(0x0800 + (x) * 4)
+#define PRU_INTC_HIPIR(x)	(0x0900 + (x) * 4)
+#define PRU_INTC_SIPR(x)	(0x0d00 + (x) * 4)
+#define PRU_INTC_SITR(x)	(0x0d80 + (x) * 4)
+#define PRU_INTC_HINLR(x)	(0x1100 + (x) * 4)
+#define PRU_INTC_HIER		0x1500
+
+/* CMR register bit-field macros */
+#define CMR_EVT_MAP_MASK	0xf
+#define CMR_EVT_MAP_BITS	8
+#define CMR_EVT_PER_REG		4
+
+/* HMR register bit-field macros */
+#define HMR_CH_MAP_MASK		0xf
+#define HMR_CH_MAP_BITS		8
+#define HMR_CH_PER_REG		4
+
+/* HIPIR register bit-fields */
+#define INTC_HIPIR_NONE_HINT	0x80000000
+
+#define MAX_PRU_SYS_EVENTS 160
+#define MAX_PRU_CHANNELS 20
+
+/**
+ * struct pruss_intc_map_record - keeps track of actual mapping state
+ * @value: The currently mapped value (channel or host)
+ * @ref_count: Keeps track of number of current users of this resource
+ */
+struct pruss_intc_map_record {
+	u8 value;
+	u8 ref_count;
+};
+
+/**
+ * struct pruss_intc_match_data - match data to handle SoC variations
+ * @num_system_events: number of input system events handled by the PRUSS INTC
+ * @num_host_events: number of host events (which is equal to number of
+ *		     channels) supported by the PRUSS INTC
+ */
+struct pruss_intc_match_data {
+	u8 num_system_events;
+	u8 num_host_events;
+};
+
+/**
+ * struct pruss_intc - PRUSS interrupt controller structure
+ * @event_channel: current state of system event to channel mappings
+ * @channel_host: current state of channel to host mappings
+ * @irqs: kernel irq numbers corresponding to PRUSS host interrupts
+ * @base: base virtual address of INTC register space
+ * @domain: irq domain for this interrupt controller
+ * @soc_config: cached PRUSS INTC IP configuration data
+ * @dev: PRUSS INTC device pointer
+ * @lock: mutex to serialize interrupts mapping
+ */
+struct pruss_intc {
+	struct pruss_intc_map_record event_channel[MAX_PRU_SYS_EVENTS];
+	struct pruss_intc_map_record channel_host[MAX_PRU_CHANNELS];
+	unsigned int irqs[MAX_NUM_HOST_IRQS];
+	void __iomem *base;
+	struct irq_domain *domain;
+	const struct pruss_intc_match_data *soc_config;
+	struct device *dev;
+	struct mutex lock; /* PRUSS INTC lock */
+};
+
+/**
+ * struct pruss_host_irq_data - PRUSS host irq data structure
+ * @intc: PRUSS interrupt controller pointer
+ * @host_irq: host irq number
+ */
+struct pruss_host_irq_data {
+	struct pruss_intc *intc;
+	u8 host_irq;
+};
+
+static inline u32 pruss_intc_read_reg(struct pruss_intc *intc, unsigned int reg)
+{
+	return readl_relaxed(intc->base + reg);
+}
+
+static inline void pruss_intc_write_reg(struct pruss_intc *intc,
+					unsigned int reg, u32 val)
+{
+	writel_relaxed(val, intc->base + reg);
+}
+
+static void pruss_intc_update_cmr(struct pruss_intc *intc, unsigned int evt,
+				  u8 ch)
+{
+	u32 idx, offset, val;
+
+	idx = evt / CMR_EVT_PER_REG;
+	offset = (evt % CMR_EVT_PER_REG) * CMR_EVT_MAP_BITS;
+
+	val = pruss_intc_read_reg(intc, PRU_INTC_CMR(idx));
+	val &= ~(CMR_EVT_MAP_MASK << offset);
+	val |= ch << offset;
+	pruss_intc_write_reg(intc, PRU_INTC_CMR(idx), val);
+
+	dev_dbg(intc->dev, "SYSEV%u -> CH%d (CMR%d 0x%08x)\n", evt, ch,
+		idx, pruss_intc_read_reg(intc, PRU_INTC_CMR(idx)));
+}
+
+static void pruss_intc_update_hmr(struct pruss_intc *intc, u8 ch, u8 host)
+{
+	u32 idx, offset, val;
+
+	idx = ch / HMR_CH_PER_REG;
+	offset = (ch % HMR_CH_PER_REG) * HMR_CH_MAP_BITS;
+
+	val = pruss_intc_read_reg(intc, PRU_INTC_HMR(idx));
+	val &= ~(HMR_CH_MAP_MASK << offset);
+	val |= host << offset;
+	pruss_intc_write_reg(intc, PRU_INTC_HMR(idx), val);
+
+	dev_dbg(intc->dev, "CH%d -> HOST%d (HMR%d 0x%08x)\n", ch, host, idx,
+		pruss_intc_read_reg(intc, PRU_INTC_HMR(idx)));
+}
+
+/**
+ * pruss_intc_map() - configure the PRUSS INTC
+ * @intc: PRUSS interrupt controller pointer
+ * @hwirq: the system event number
+ *
+ * Configures the PRUSS INTC with the provided configuration from the one parsed
+ * in the xlate function.
+ */
+static void pruss_intc_map(struct pruss_intc *intc, unsigned long hwirq)
+{
+	struct device *dev = intc->dev;
+	u8 ch, host, reg_idx;
+	u32 val;
+
+	mutex_lock(&intc->lock);
+
+	intc->event_channel[hwirq].ref_count++;
+
+	ch = intc->event_channel[hwirq].value;
+	host = intc->channel_host[ch].value;
+
+	pruss_intc_update_cmr(intc, hwirq, ch);
+
+	reg_idx = hwirq / 32;
+	val = BIT(hwirq  % 32);
+
+	/* clear and enable system event */
+	pruss_intc_write_reg(intc, PRU_INTC_ESR(reg_idx), val);
+	pruss_intc_write_reg(intc, PRU_INTC_SECR(reg_idx), val);
+
+	if (++intc->channel_host[ch].ref_count == 1) {
+		pruss_intc_update_hmr(intc, ch, host);
+
+		/* enable host interrupts */
+		pruss_intc_write_reg(intc, PRU_INTC_HIEISR, host);
+	}
+
+	dev_dbg(dev, "mapped system_event = %lu channel = %d host = %d",
+		hwirq, ch, host);
+
+	mutex_unlock(&intc->lock);
+}
+
+/**
+ * pruss_intc_unmap() - unconfigure the PRUSS INTC
+ * @intc: PRUSS interrupt controller pointer
+ * @hwirq: the system event number
+ *
+ * Undo whatever was done in pruss_intc_map() for a PRU core.
+ * Mappings are reference counted, so resources are only disabled when there
+ * are no longer any users.
+ */
+static void pruss_intc_unmap(struct pruss_intc *intc, unsigned long hwirq)
+{
+	u8 ch, host, reg_idx;
+	u32 val;
+
+	mutex_lock(&intc->lock);
+
+	ch = intc->event_channel[hwirq].value;
+	host = intc->channel_host[ch].value;
+
+	if (--intc->channel_host[ch].ref_count == 0) {
+		/* disable host interrupts */
+		pruss_intc_write_reg(intc, PRU_INTC_HIDISR, host);
+
+		/* clear the map using reset value 0 */
+		pruss_intc_update_hmr(intc, ch, 0);
+	}
+
+	intc->event_channel[hwirq].ref_count--;
+	reg_idx = hwirq / 32;
+	val = BIT(hwirq  % 32);
+
+	/* disable system events */
+	pruss_intc_write_reg(intc, PRU_INTC_ECR(reg_idx), val);
+	/* clear any pending status */
+	pruss_intc_write_reg(intc, PRU_INTC_SECR(reg_idx), val);
+
+	/* clear the map using reset value 0 */
+	pruss_intc_update_cmr(intc, hwirq, 0);
+
+	dev_dbg(intc->dev, "unmapped system_event = %lu channel = %d host = %d\n",
+		hwirq, ch, host);
+
+	mutex_unlock(&intc->lock);
+}
+
+static void pruss_intc_init(struct pruss_intc *intc)
+{
+	const struct pruss_intc_match_data *soc_config = intc->soc_config;
+	int num_chnl_map_regs, num_host_intr_regs, num_event_type_regs, i;
+
+	num_chnl_map_regs = DIV_ROUND_UP(soc_config->num_system_events,
+					 CMR_EVT_PER_REG);
+	num_host_intr_regs = DIV_ROUND_UP(soc_config->num_host_events,
+					  HMR_CH_PER_REG);
+	num_event_type_regs = DIV_ROUND_UP(soc_config->num_system_events, 32);
+
+	/*
+	 * configure polarity (SIPR register) to active high and
+	 * type (SITR register) to level interrupt for all system events
+	 */
+	for (i = 0; i < num_event_type_regs; i++) {
+		pruss_intc_write_reg(intc, PRU_INTC_SIPR(i), 0xffffffff);
+		pruss_intc_write_reg(intc, PRU_INTC_SITR(i), 0);
+	}
+
+	/* clear all interrupt channel map registers, 4 events per register */
+	for (i = 0; i < num_chnl_map_regs; i++)
+		pruss_intc_write_reg(intc, PRU_INTC_CMR(i), 0);
+
+	/* clear all host interrupt map registers, 4 channels per register */
+	for (i = 0; i < num_host_intr_regs; i++)
+		pruss_intc_write_reg(intc, PRU_INTC_HMR(i), 0);
+
+	/* global interrupt enable */
+	pruss_intc_write_reg(intc, PRU_INTC_GER, 1);
+}
+
+static void pruss_intc_irq_ack(struct irq_data *data)
+{
+	struct pruss_intc *intc = irq_data_get_irq_chip_data(data);
+	unsigned int hwirq = data->hwirq;
+
+	pruss_intc_write_reg(intc, PRU_INTC_SICR, hwirq);
+}
+
+static void pruss_intc_irq_mask(struct irq_data *data)
+{
+	struct pruss_intc *intc = irq_data_get_irq_chip_data(data);
+	unsigned int hwirq = data->hwirq;
+
+	pruss_intc_write_reg(intc, PRU_INTC_EICR, hwirq);
+}
+
+static void pruss_intc_irq_unmask(struct irq_data *data)
+{
+	struct pruss_intc *intc = irq_data_get_irq_chip_data(data);
+	unsigned int hwirq = data->hwirq;
+
+	pruss_intc_write_reg(intc, PRU_INTC_EISR, hwirq);
+}
+
+static int pruss_intc_irq_reqres(struct irq_data *data)
+{
+	if (!try_module_get(THIS_MODULE))
+		return -ENODEV;
+
+	return 0;
+}
+
+static void pruss_intc_irq_relres(struct irq_data *data)
+{
+	module_put(THIS_MODULE);
+}
+
+static int pruss_intc_irq_get_irqchip_state(struct irq_data *data,
+					    enum irqchip_irq_state which,
+					    bool *state)
+{
+	struct pruss_intc *intc = irq_data_get_irq_chip_data(data);
+	u32 reg, mask, srsr;
+
+	if (which != IRQCHIP_STATE_PENDING)
+		return -EINVAL;
+
+	reg = PRU_INTC_SRSR(data->hwirq / 32);
+	mask = BIT(data->hwirq % 32);
+
+	srsr = pruss_intc_read_reg(intc, reg);
+
+	*state = !!(srsr & mask);
+
+	return 0;
+}
+
+static int pruss_intc_irq_set_irqchip_state(struct irq_data *data,
+					    enum irqchip_irq_state which,
+					    bool state)
+{
+	struct pruss_intc *intc = irq_data_get_irq_chip_data(data);
+
+	if (which != IRQCHIP_STATE_PENDING)
+		return -EINVAL;
+
+	if (state)
+		pruss_intc_write_reg(intc, PRU_INTC_SISR, data->hwirq);
+	else
+		pruss_intc_write_reg(intc, PRU_INTC_SICR, data->hwirq);
+
+	return 0;
+}
+
+static struct irq_chip pruss_irqchip = {
+	.name			= "pruss-intc",
+	.irq_ack		= pruss_intc_irq_ack,
+	.irq_mask		= pruss_intc_irq_mask,
+	.irq_unmask		= pruss_intc_irq_unmask,
+	.irq_request_resources	= pruss_intc_irq_reqres,
+	.irq_release_resources	= pruss_intc_irq_relres,
+	.irq_get_irqchip_state	= pruss_intc_irq_get_irqchip_state,
+	.irq_set_irqchip_state	= pruss_intc_irq_set_irqchip_state,
+};
+
+static int pruss_intc_validate_mapping(struct pruss_intc *intc, int event,
+				       int channel, int host)
+{
+	struct device *dev = intc->dev;
+	int ret = 0;
+
+	mutex_lock(&intc->lock);
+
+	/* check if sysevent already assigned */
+	if (intc->event_channel[event].ref_count > 0 &&
+	    intc->event_channel[event].value != channel) {
+		dev_err(dev, "event %d (req. ch %d) already assigned to channel %d\n",
+			event, channel, intc->event_channel[event].value);
+		ret = -EBUSY;
+		goto unlock;
+	}
+
+	/* check if channel already assigned */
+	if (intc->channel_host[channel].ref_count > 0 &&
+	    intc->channel_host[channel].value != host) {
+		dev_err(dev, "channel %d (req. host %d) already assigned to host %d\n",
+			channel, host, intc->channel_host[channel].value);
+		ret = -EBUSY;
+		goto unlock;
+	}
+
+	intc->event_channel[event].value = channel;
+	intc->channel_host[channel].value = host;
+
+unlock:
+	mutex_unlock(&intc->lock);
+	return ret;
+}
+
+static int
+pruss_intc_irq_domain_xlate(struct irq_domain *d, struct device_node *node,
+			    const u32 *intspec, unsigned int intsize,
+			    unsigned long *out_hwirq, unsigned int *out_type)
+{
+	struct pruss_intc *intc = d->host_data;
+	struct device *dev = intc->dev;
+	int ret, sys_event, channel, host;
+
+	if (intsize < 3)
+		return -EINVAL;
+
+	sys_event = intspec[0];
+	if (sys_event < 0 || sys_event >= intc->soc_config->num_system_events) {
+		dev_err(dev, "%d is not valid event number\n", sys_event);
+		return -EINVAL;
+	}
+
+	channel = intspec[1];
+	if (channel < 0 || channel >= intc->soc_config->num_host_events) {
+		dev_err(dev, "%d is not valid channel number", channel);
+		return -EINVAL;
+	}
+
+	host = intspec[2];
+	if (host < 0 || host >= intc->soc_config->num_host_events) {
+		dev_err(dev, "%d is not valid host irq number\n", host);
+		return -EINVAL;
+	}
+
+	/* check if requested sys_event was already mapped, if so validate it */
+	ret = pruss_intc_validate_mapping(intc, sys_event, channel, host);
+	if (ret)
+		return ret;
+
+	*out_hwirq = sys_event;
+	*out_type = IRQ_TYPE_LEVEL_HIGH;
+
+	return 0;
+}
+
+static int pruss_intc_irq_domain_map(struct irq_domain *d, unsigned int virq,
+				     irq_hw_number_t hw)
+{
+	struct pruss_intc *intc = d->host_data;
+
+	pruss_intc_map(intc, hw);
+
+	irq_set_chip_data(virq, intc);
+	irq_set_chip_and_handler(virq, &pruss_irqchip, handle_level_irq);
+
+	return 0;
+}
+
+static void pruss_intc_irq_domain_unmap(struct irq_domain *d, unsigned int virq)
+{
+	struct pruss_intc *intc = d->host_data;
+	unsigned long hwirq = irqd_to_hwirq(irq_get_irq_data(virq));
+
+	irq_set_chip_and_handler(virq, NULL, NULL);
+	irq_set_chip_data(virq, NULL);
+	pruss_intc_unmap(intc, hwirq);
+}
+
+static const struct irq_domain_ops pruss_intc_irq_domain_ops = {
+	.xlate	= pruss_intc_irq_domain_xlate,
+	.map	= pruss_intc_irq_domain_map,
+	.unmap	= pruss_intc_irq_domain_unmap,
+};
+
+static void pruss_intc_irq_handler(struct irq_desc *desc)
+{
+	unsigned int irq = irq_desc_get_irq(desc);
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	struct pruss_host_irq_data *host_irq_data = irq_get_handler_data(irq);
+	struct pruss_intc *intc = host_irq_data->intc;
+	u8 host_irq = host_irq_data->host_irq + FIRST_PRU_HOST_INT;
+
+	chained_irq_enter(chip, desc);
+
+	while (true) {
+		u32 hipir;
+		unsigned int virq;
+		int hwirq;
+
+		/* get highest priority pending PRUSS system event */
+		hipir = pruss_intc_read_reg(intc, PRU_INTC_HIPIR(host_irq));
+		if (hipir & INTC_HIPIR_NONE_HINT)
+			break;
+
+		hwirq = hipir & GENMASK(9, 0);
+		virq = irq_find_mapping(intc->domain, hwirq);
+
+		/*
+		 * NOTE: manually ACK any system events that do not have a
+		 * handler mapped yet
+		 */
+		if (WARN_ON_ONCE(!virq))
+			pruss_intc_write_reg(intc, PRU_INTC_SICR, hwirq);
+		else
+			generic_handle_irq(virq);
+	}
+
+	chained_irq_exit(chip, desc);
+}
+
+static const char * const irq_names[MAX_NUM_HOST_IRQS] = {
+	"host_intr0", "host_intr1", "host_intr2", "host_intr3",
+	"host_intr4", "host_intr5", "host_intr6", "host_intr7",
+};
+
+static int pruss_intc_probe(struct platform_device *pdev)
+{
+	const struct pruss_intc_match_data *data;
+	struct device *dev = &pdev->dev;
+	struct pruss_intc *intc;
+	struct pruss_host_irq_data *host_data;
+	int i, irq, ret;
+	u8 max_system_events, irqs_reserved = 0;
+
+	data = of_device_get_match_data(dev);
+	if (!data)
+		return -ENODEV;
+
+	max_system_events = data->num_system_events;
+
+	intc = devm_kzalloc(dev, sizeof(*intc), GFP_KERNEL);
+	if (!intc)
+		return -ENOMEM;
+
+	intc->soc_config = data;
+	intc->dev = dev;
+	platform_set_drvdata(pdev, intc);
+
+	intc->base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(intc->base))
+		return PTR_ERR(intc->base);
+
+	ret = of_property_read_u8(dev->of_node, "ti,irqs-reserved",
+				  &irqs_reserved);
+
+	/*
+	 * The irqs-reserved is used only for some SoC's therefore not having
+	 * this property is still valid
+	 */
+	if (ret < 0 && ret != -EINVAL)
+		return ret;
+
+	pruss_intc_init(intc);
+
+	mutex_init(&intc->lock);
+
+	intc->domain = irq_domain_add_linear(dev->of_node, max_system_events,
+					     &pruss_intc_irq_domain_ops, intc);
+	if (!intc->domain)
+		return -ENOMEM;
+
+	for (i = 0; i < MAX_NUM_HOST_IRQS; i++) {
+		if (irqs_reserved & BIT(i))
+			continue;
+
+		irq = platform_get_irq_byname(pdev, irq_names[i]);
+		if (irq <= 0) {
+			ret = (irq == 0) ? -EINVAL : irq;
+			goto fail_irq;
+		}
+
+		intc->irqs[i] = irq;
+
+		host_data = devm_kzalloc(dev, sizeof(*host_data), GFP_KERNEL);
+		if (!host_data) {
+			ret = -ENOMEM;
+			goto fail_irq;
+		}
+
+		host_data->intc = intc;
+		host_data->host_irq = i;
+
+		irq_set_handler_data(irq, host_data);
+		irq_set_chained_handler(irq, pruss_intc_irq_handler);
+	}
+
+	return 0;
+
+fail_irq:
+	while (--i >= 0) {
+		if (intc->irqs[i])
+			irq_set_chained_handler_and_data(intc->irqs[i], NULL,
+							 NULL);
+	}
+
+	irq_domain_remove(intc->domain);
+
+	return ret;
+}
+
+static int pruss_intc_remove(struct platform_device *pdev)
+{
+	struct pruss_intc *intc = platform_get_drvdata(pdev);
+	u8 max_system_events = intc->soc_config->num_system_events;
+	unsigned int hwirq;
+	int i;
+
+	for (i = 0; i < MAX_NUM_HOST_IRQS; i++) {
+		if (intc->irqs[i])
+			irq_set_chained_handler_and_data(intc->irqs[i], NULL,
+							 NULL);
+	}
+
+	for (hwirq = 0; hwirq < max_system_events; hwirq++)
+		irq_dispose_mapping(irq_find_mapping(intc->domain, hwirq));
+
+	irq_domain_remove(intc->domain);
+
+	return 0;
+}
+
+static const struct pruss_intc_match_data pruss_intc_data = {
+	.num_system_events = 64,
+	.num_host_events = 10,
+};
+
+static const struct pruss_intc_match_data icssg_intc_data = {
+	.num_system_events = 160,
+	.num_host_events = 20,
+};
+
+static const struct of_device_id pruss_intc_of_match[] = {
+	{
+		.compatible = "ti,pruss-intc",
+		.data = &pruss_intc_data,
+	},
+	{
+		.compatible = "ti,icssg-intc",
+		.data = &icssg_intc_data,
+	},
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, pruss_intc_of_match);
+
+static struct platform_driver pruss_intc_driver = {
+	.driver = {
+		.name = "pruss-intc",
+		.of_match_table = pruss_intc_of_match,
+		.suppress_bind_attrs = true,
+	},
+	.probe  = pruss_intc_probe,
+	.remove = pruss_intc_remove,
+};
+module_platform_driver(pruss_intc_driver);
+
+MODULE_AUTHOR("Andrew F. Davis <afd@ti.com>");
+MODULE_AUTHOR("Suman Anna <s-anna@ti.com>");
+MODULE_AUTHOR("Grzegorz Jaszczyk <grzegorz.jaszczyk@linaro.org>");
+MODULE_DESCRIPTION("TI PRU-ICSS INTC Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/irqchip/irq-renesas-intc-irqpin.c b/drivers/irqchip/irq-renesas-intc-irqpin.c
index f82bc60..cb7f60b 100644
--- a/drivers/irqchip/irq-renesas-intc-irqpin.c
+++ b/drivers/irqchip/irq-renesas-intc-irqpin.c
@@ -71,8 +71,7 @@
 };
 
 struct intc_irqpin_config {
-	unsigned int irlm_bit;
-	unsigned needs_irlm:1;
+	int irlm_bit;		/* -1 if non-existent */
 };
 
 static unsigned long intc_irqpin_read32(void __iomem *iomem)
@@ -349,11 +348,10 @@
 
 static const struct intc_irqpin_config intc_irqpin_irlm_r8a777x = {
 	.irlm_bit = 23, /* ICR0.IRLM0 */
-	.needs_irlm = 1,
 };
 
 static const struct intc_irqpin_config intc_irqpin_rmobile = {
-	.needs_irlm = 0,
+	.irlm_bit = -1,
 };
 
 static const struct of_device_id intc_irqpin_dt_ids[] = {
@@ -460,8 +458,8 @@
 			goto err0;
 		}
 
-		i->iomem = devm_ioremap_nocache(dev, io[k]->start,
-						resource_size(io[k]));
+		i->iomem = devm_ioremap(dev, io[k]->start,
+					resource_size(io[k]));
 		if (!i->iomem) {
 			dev_err(dev, "failed to remap IOMEM\n");
 			ret = -ENXIO;
@@ -470,7 +468,7 @@
 	}
 
 	/* configure "individual IRQ mode" where needed */
-	if (config && config->needs_irlm) {
+	if (config && config->irlm_bit >= 0) {
 		if (io[INTC_IRQPIN_REG_IRLM])
 			intc_irqpin_read_modify_write(p, INTC_IRQPIN_REG_IRLM,
 						      config->irlm_bit, 1, 1);
diff --git a/drivers/irqchip/irq-riscv-intc.c b/drivers/irqchip/irq-riscv-intc.c
new file mode 100644
index 0000000..8017f6d
--- /dev/null
+++ b/drivers/irqchip/irq-riscv-intc.c
@@ -0,0 +1,138 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ * Copyright (C) 2017-2018 SiFive
+ * Copyright (C) 2020 Western Digital Corporation or its affiliates.
+ */
+
+#define pr_fmt(fmt) "riscv-intc: " fmt
+#include <linux/atomic.h>
+#include <linux/bits.h>
+#include <linux/cpu.h>
+#include <linux/irq.h>
+#include <linux/irqchip.h>
+#include <linux/irqdomain.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/smp.h>
+
+static struct irq_domain *intc_domain;
+
+static asmlinkage void riscv_intc_irq(struct pt_regs *regs)
+{
+	unsigned long cause = regs->cause & ~CAUSE_IRQ_FLAG;
+
+	if (unlikely(cause >= BITS_PER_LONG))
+		panic("unexpected interrupt cause");
+
+	switch (cause) {
+#ifdef CONFIG_SMP
+	case RV_IRQ_SOFT:
+		/*
+		 * We only use software interrupts to pass IPIs, so if a
+		 * non-SMP system gets one, then we don't know what to do.
+		 */
+		handle_IPI(regs);
+		break;
+#endif
+	default:
+		handle_domain_irq(intc_domain, cause, regs);
+		break;
+	}
+}
+
+/*
+ * On RISC-V systems local interrupts are masked or unmasked by writing
+ * the SIE (Supervisor Interrupt Enable) CSR.  As CSRs can only be written
+ * on the local hart, these functions can only be called on the hart that
+ * corresponds to the IRQ chip.
+ */
+
+static void riscv_intc_irq_mask(struct irq_data *d)
+{
+	csr_clear(CSR_IE, BIT(d->hwirq));
+}
+
+static void riscv_intc_irq_unmask(struct irq_data *d)
+{
+	csr_set(CSR_IE, BIT(d->hwirq));
+}
+
+static int riscv_intc_cpu_starting(unsigned int cpu)
+{
+	csr_set(CSR_IE, BIT(RV_IRQ_SOFT));
+	return 0;
+}
+
+static int riscv_intc_cpu_dying(unsigned int cpu)
+{
+	csr_clear(CSR_IE, BIT(RV_IRQ_SOFT));
+	return 0;
+}
+
+static struct irq_chip riscv_intc_chip = {
+	.name = "RISC-V INTC",
+	.irq_mask = riscv_intc_irq_mask,
+	.irq_unmask = riscv_intc_irq_unmask,
+};
+
+static int riscv_intc_domain_map(struct irq_domain *d, unsigned int irq,
+				 irq_hw_number_t hwirq)
+{
+	irq_set_percpu_devid(irq);
+	irq_domain_set_info(d, irq, hwirq, &riscv_intc_chip, d->host_data,
+			    handle_percpu_devid_irq, NULL, NULL);
+
+	return 0;
+}
+
+static const struct irq_domain_ops riscv_intc_domain_ops = {
+	.map	= riscv_intc_domain_map,
+	.xlate	= irq_domain_xlate_onecell,
+};
+
+static int __init riscv_intc_init(struct device_node *node,
+				  struct device_node *parent)
+{
+	int rc, hartid;
+
+	hartid = riscv_of_parent_hartid(node);
+	if (hartid < 0) {
+		pr_warn("unable to find hart id for %pOF\n", node);
+		return 0;
+	}
+
+	/*
+	 * The DT will have one INTC DT node under each CPU (or HART)
+	 * DT node so riscv_intc_init() function will be called once
+	 * for each INTC DT node. We only need to do INTC initialization
+	 * for the INTC DT node belonging to boot CPU (or boot HART).
+	 */
+	if (riscv_hartid_to_cpuid(hartid) != smp_processor_id())
+		return 0;
+
+	intc_domain = irq_domain_add_linear(node, BITS_PER_LONG,
+					    &riscv_intc_domain_ops, NULL);
+	if (!intc_domain) {
+		pr_err("unable to add IRQ domain\n");
+		return -ENXIO;
+	}
+
+	rc = set_handle_irq(&riscv_intc_irq);
+	if (rc) {
+		pr_err("failed to set irq handler\n");
+		return rc;
+	}
+
+	cpuhp_setup_state(CPUHP_AP_IRQ_RISCV_STARTING,
+			  "irqchip/riscv/intc:starting",
+			  riscv_intc_cpu_starting,
+			  riscv_intc_cpu_dying);
+
+	pr_info("%d local interrupts mapped\n", BITS_PER_LONG);
+
+	return 0;
+}
+
+IRQCHIP_DECLARE(riscv, "riscv,cpu-intc", riscv_intc_init);
diff --git a/drivers/irqchip/irq-s3c24xx.c b/drivers/irqchip/irq-s3c24xx.c
deleted file mode 100644
index d2031fe..0000000
--- a/drivers/irqchip/irq-s3c24xx.c
+++ /dev/null
@@ -1,1330 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * S3C24XX IRQ handling
- *
- * Copyright (c) 2003-2004 Simtec Electronics
- *	Ben Dooks <ben@simtec.co.uk>
- * Copyright (c) 2012 Heiko Stuebner <heiko@sntech.de>
-*/
-
-#include <linux/init.h>
-#include <linux/slab.h>
-#include <linux/module.h>
-#include <linux/io.h>
-#include <linux/err.h>
-#include <linux/interrupt.h>
-#include <linux/ioport.h>
-#include <linux/device.h>
-#include <linux/irqdomain.h>
-#include <linux/irqchip.h>
-#include <linux/irqchip/chained_irq.h>
-#include <linux/of.h>
-#include <linux/of_irq.h>
-#include <linux/of_address.h>
-
-#include <asm/exception.h>
-#include <asm/mach/irq.h>
-
-#include <mach/regs-irq.h>
-#include <mach/regs-gpio.h>
-
-#include <plat/cpu.h>
-#include <plat/regs-irqtype.h>
-#include <plat/pm.h>
-
-#define S3C_IRQTYPE_NONE	0
-#define S3C_IRQTYPE_EINT	1
-#define S3C_IRQTYPE_EDGE	2
-#define S3C_IRQTYPE_LEVEL	3
-
-struct s3c_irq_data {
-	unsigned int type;
-	unsigned long offset;
-	unsigned long parent_irq;
-
-	/* data gets filled during init */
-	struct s3c_irq_intc *intc;
-	unsigned long sub_bits;
-	struct s3c_irq_intc *sub_intc;
-};
-
-/*
- * Structure holding the controller data
- * @reg_pending		register holding pending irqs
- * @reg_intpnd		special register intpnd in main intc
- * @reg_mask		mask register
- * @domain		irq_domain of the controller
- * @parent		parent controller for ext and sub irqs
- * @irqs		irq-data, always s3c_irq_data[32]
- */
-struct s3c_irq_intc {
-	void __iomem		*reg_pending;
-	void __iomem		*reg_intpnd;
-	void __iomem		*reg_mask;
-	struct irq_domain	*domain;
-	struct s3c_irq_intc	*parent;
-	struct s3c_irq_data	*irqs;
-};
-
-/*
- * Array holding pointers to the global controller structs
- * [0] ... main_intc
- * [1] ... sub_intc
- * [2] ... main_intc2 on s3c2416
- */
-static struct s3c_irq_intc *s3c_intc[3];
-
-static void s3c_irq_mask(struct irq_data *data)
-{
-	struct s3c_irq_data *irq_data = irq_data_get_irq_chip_data(data);
-	struct s3c_irq_intc *intc = irq_data->intc;
-	struct s3c_irq_intc *parent_intc = intc->parent;
-	struct s3c_irq_data *parent_data;
-	unsigned long mask;
-	unsigned int irqno;
-
-	mask = readl_relaxed(intc->reg_mask);
-	mask |= (1UL << irq_data->offset);
-	writel_relaxed(mask, intc->reg_mask);
-
-	if (parent_intc) {
-		parent_data = &parent_intc->irqs[irq_data->parent_irq];
-
-		/* check to see if we need to mask the parent IRQ
-		 * The parent_irq is always in main_intc, so the hwirq
-		 * for find_mapping does not need an offset in any case.
-		 */
-		if ((mask & parent_data->sub_bits) == parent_data->sub_bits) {
-			irqno = irq_find_mapping(parent_intc->domain,
-					 irq_data->parent_irq);
-			s3c_irq_mask(irq_get_irq_data(irqno));
-		}
-	}
-}
-
-static void s3c_irq_unmask(struct irq_data *data)
-{
-	struct s3c_irq_data *irq_data = irq_data_get_irq_chip_data(data);
-	struct s3c_irq_intc *intc = irq_data->intc;
-	struct s3c_irq_intc *parent_intc = intc->parent;
-	unsigned long mask;
-	unsigned int irqno;
-
-	mask = readl_relaxed(intc->reg_mask);
-	mask &= ~(1UL << irq_data->offset);
-	writel_relaxed(mask, intc->reg_mask);
-
-	if (parent_intc) {
-		irqno = irq_find_mapping(parent_intc->domain,
-					 irq_data->parent_irq);
-		s3c_irq_unmask(irq_get_irq_data(irqno));
-	}
-}
-
-static inline void s3c_irq_ack(struct irq_data *data)
-{
-	struct s3c_irq_data *irq_data = irq_data_get_irq_chip_data(data);
-	struct s3c_irq_intc *intc = irq_data->intc;
-	unsigned long bitval = 1UL << irq_data->offset;
-
-	writel_relaxed(bitval, intc->reg_pending);
-	if (intc->reg_intpnd)
-		writel_relaxed(bitval, intc->reg_intpnd);
-}
-
-static int s3c_irq_type(struct irq_data *data, unsigned int type)
-{
-	switch (type) {
-	case IRQ_TYPE_NONE:
-		break;
-	case IRQ_TYPE_EDGE_RISING:
-	case IRQ_TYPE_EDGE_FALLING:
-	case IRQ_TYPE_EDGE_BOTH:
-		irq_set_handler(data->irq, handle_edge_irq);
-		break;
-	case IRQ_TYPE_LEVEL_LOW:
-	case IRQ_TYPE_LEVEL_HIGH:
-		irq_set_handler(data->irq, handle_level_irq);
-		break;
-	default:
-		pr_err("No such irq type %d\n", type);
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-static int s3c_irqext_type_set(void __iomem *gpcon_reg,
-			       void __iomem *extint_reg,
-			       unsigned long gpcon_offset,
-			       unsigned long extint_offset,
-			       unsigned int type)
-{
-	unsigned long newvalue = 0, value;
-
-	/* Set the GPIO to external interrupt mode */
-	value = readl_relaxed(gpcon_reg);
-	value = (value & ~(3 << gpcon_offset)) | (0x02 << gpcon_offset);
-	writel_relaxed(value, gpcon_reg);
-
-	/* Set the external interrupt to pointed trigger type */
-	switch (type)
-	{
-		case IRQ_TYPE_NONE:
-			pr_warn("No edge setting!\n");
-			break;
-
-		case IRQ_TYPE_EDGE_RISING:
-			newvalue = S3C2410_EXTINT_RISEEDGE;
-			break;
-
-		case IRQ_TYPE_EDGE_FALLING:
-			newvalue = S3C2410_EXTINT_FALLEDGE;
-			break;
-
-		case IRQ_TYPE_EDGE_BOTH:
-			newvalue = S3C2410_EXTINT_BOTHEDGE;
-			break;
-
-		case IRQ_TYPE_LEVEL_LOW:
-			newvalue = S3C2410_EXTINT_LOWLEV;
-			break;
-
-		case IRQ_TYPE_LEVEL_HIGH:
-			newvalue = S3C2410_EXTINT_HILEV;
-			break;
-
-		default:
-			pr_err("No such irq type %d\n", type);
-			return -EINVAL;
-	}
-
-	value = readl_relaxed(extint_reg);
-	value = (value & ~(7 << extint_offset)) | (newvalue << extint_offset);
-	writel_relaxed(value, extint_reg);
-
-	return 0;
-}
-
-static int s3c_irqext_type(struct irq_data *data, unsigned int type)
-{
-	void __iomem *extint_reg;
-	void __iomem *gpcon_reg;
-	unsigned long gpcon_offset, extint_offset;
-
-	if ((data->hwirq >= 4) && (data->hwirq <= 7)) {
-		gpcon_reg = S3C2410_GPFCON;
-		extint_reg = S3C24XX_EXTINT0;
-		gpcon_offset = (data->hwirq) * 2;
-		extint_offset = (data->hwirq) * 4;
-	} else if ((data->hwirq >= 8) && (data->hwirq <= 15)) {
-		gpcon_reg = S3C2410_GPGCON;
-		extint_reg = S3C24XX_EXTINT1;
-		gpcon_offset = (data->hwirq - 8) * 2;
-		extint_offset = (data->hwirq - 8) * 4;
-	} else if ((data->hwirq >= 16) && (data->hwirq <= 23)) {
-		gpcon_reg = S3C2410_GPGCON;
-		extint_reg = S3C24XX_EXTINT2;
-		gpcon_offset = (data->hwirq - 8) * 2;
-		extint_offset = (data->hwirq - 16) * 4;
-	} else {
-		return -EINVAL;
-	}
-
-	return s3c_irqext_type_set(gpcon_reg, extint_reg, gpcon_offset,
-				   extint_offset, type);
-}
-
-static int s3c_irqext0_type(struct irq_data *data, unsigned int type)
-{
-	void __iomem *extint_reg;
-	void __iomem *gpcon_reg;
-	unsigned long gpcon_offset, extint_offset;
-
-	if (data->hwirq <= 3) {
-		gpcon_reg = S3C2410_GPFCON;
-		extint_reg = S3C24XX_EXTINT0;
-		gpcon_offset = (data->hwirq) * 2;
-		extint_offset = (data->hwirq) * 4;
-	} else {
-		return -EINVAL;
-	}
-
-	return s3c_irqext_type_set(gpcon_reg, extint_reg, gpcon_offset,
-				   extint_offset, type);
-}
-
-static struct irq_chip s3c_irq_chip = {
-	.name		= "s3c",
-	.irq_ack	= s3c_irq_ack,
-	.irq_mask	= s3c_irq_mask,
-	.irq_unmask	= s3c_irq_unmask,
-	.irq_set_type	= s3c_irq_type,
-	.irq_set_wake	= s3c_irq_wake
-};
-
-static struct irq_chip s3c_irq_level_chip = {
-	.name		= "s3c-level",
-	.irq_mask	= s3c_irq_mask,
-	.irq_unmask	= s3c_irq_unmask,
-	.irq_ack	= s3c_irq_ack,
-	.irq_set_type	= s3c_irq_type,
-};
-
-static struct irq_chip s3c_irqext_chip = {
-	.name		= "s3c-ext",
-	.irq_mask	= s3c_irq_mask,
-	.irq_unmask	= s3c_irq_unmask,
-	.irq_ack	= s3c_irq_ack,
-	.irq_set_type	= s3c_irqext_type,
-	.irq_set_wake	= s3c_irqext_wake
-};
-
-static struct irq_chip s3c_irq_eint0t4 = {
-	.name		= "s3c-ext0",
-	.irq_ack	= s3c_irq_ack,
-	.irq_mask	= s3c_irq_mask,
-	.irq_unmask	= s3c_irq_unmask,
-	.irq_set_wake	= s3c_irq_wake,
-	.irq_set_type	= s3c_irqext0_type,
-};
-
-static void s3c_irq_demux(struct irq_desc *desc)
-{
-	struct irq_chip *chip = irq_desc_get_chip(desc);
-	struct s3c_irq_data *irq_data = irq_desc_get_chip_data(desc);
-	struct s3c_irq_intc *intc = irq_data->intc;
-	struct s3c_irq_intc *sub_intc = irq_data->sub_intc;
-	unsigned int n, offset, irq;
-	unsigned long src, msk;
-
-	/* we're using individual domains for the non-dt case
-	 * and one big domain for the dt case where the subintc
-	 * starts at hwirq number 32.
-	 */
-	offset = irq_domain_get_of_node(intc->domain) ? 32 : 0;
-
-	chained_irq_enter(chip, desc);
-
-	src = readl_relaxed(sub_intc->reg_pending);
-	msk = readl_relaxed(sub_intc->reg_mask);
-
-	src &= ~msk;
-	src &= irq_data->sub_bits;
-
-	while (src) {
-		n = __ffs(src);
-		src &= ~(1 << n);
-		irq = irq_find_mapping(sub_intc->domain, offset + n);
-		generic_handle_irq(irq);
-	}
-
-	chained_irq_exit(chip, desc);
-}
-
-static inline int s3c24xx_handle_intc(struct s3c_irq_intc *intc,
-				      struct pt_regs *regs, int intc_offset)
-{
-	int pnd;
-	int offset;
-
-	pnd = readl_relaxed(intc->reg_intpnd);
-	if (!pnd)
-		return false;
-
-	/* non-dt machines use individual domains */
-	if (!irq_domain_get_of_node(intc->domain))
-		intc_offset = 0;
-
-	/* We have a problem that the INTOFFSET register does not always
-	 * show one interrupt. Occasionally we get two interrupts through
-	 * the prioritiser, and this causes the INTOFFSET register to show
-	 * what looks like the logical-or of the two interrupt numbers.
-	 *
-	 * Thanks to Klaus, Shannon, et al for helping to debug this problem
-	 */
-	offset = readl_relaxed(intc->reg_intpnd + 4);
-
-	/* Find the bit manually, when the offset is wrong.
-	 * The pending register only ever contains the one bit of the next
-	 * interrupt to handle.
-	 */
-	if (!(pnd & (1 << offset)))
-		offset =  __ffs(pnd);
-
-	handle_domain_irq(intc->domain, intc_offset + offset, regs);
-	return true;
-}
-
-asmlinkage void __exception_irq_entry s3c24xx_handle_irq(struct pt_regs *regs)
-{
-	do {
-		if (likely(s3c_intc[0]))
-			if (s3c24xx_handle_intc(s3c_intc[0], regs, 0))
-				continue;
-
-		if (s3c_intc[2])
-			if (s3c24xx_handle_intc(s3c_intc[2], regs, 64))
-				continue;
-
-		break;
-	} while (1);
-}
-
-#ifdef CONFIG_FIQ
-/**
- * s3c24xx_set_fiq - set the FIQ routing
- * @irq: IRQ number to route to FIQ on processor.
- * @on: Whether to route @irq to the FIQ, or to remove the FIQ routing.
- *
- * Change the state of the IRQ to FIQ routing depending on @irq and @on. If
- * @on is true, the @irq is checked to see if it can be routed and the
- * interrupt controller updated to route the IRQ. If @on is false, the FIQ
- * routing is cleared, regardless of which @irq is specified.
- */
-int s3c24xx_set_fiq(unsigned int irq, bool on)
-{
-	u32 intmod;
-	unsigned offs;
-
-	if (on) {
-		offs = irq - FIQ_START;
-		if (offs > 31)
-			return -EINVAL;
-
-		intmod = 1 << offs;
-	} else {
-		intmod = 0;
-	}
-
-	writel_relaxed(intmod, S3C2410_INTMOD);
-	return 0;
-}
-
-EXPORT_SYMBOL_GPL(s3c24xx_set_fiq);
-#endif
-
-static int s3c24xx_irq_map(struct irq_domain *h, unsigned int virq,
-							irq_hw_number_t hw)
-{
-	struct s3c_irq_intc *intc = h->host_data;
-	struct s3c_irq_data *irq_data = &intc->irqs[hw];
-	struct s3c_irq_intc *parent_intc;
-	struct s3c_irq_data *parent_irq_data;
-	unsigned int irqno;
-
-	/* attach controller pointer to irq_data */
-	irq_data->intc = intc;
-	irq_data->offset = hw;
-
-	parent_intc = intc->parent;
-
-	/* set handler and flags */
-	switch (irq_data->type) {
-	case S3C_IRQTYPE_NONE:
-		return 0;
-	case S3C_IRQTYPE_EINT:
-		/* On the S3C2412, the EINT0to3 have a parent irq
-		 * but need the s3c_irq_eint0t4 chip
-		 */
-		if (parent_intc && (!soc_is_s3c2412() || hw >= 4))
-			irq_set_chip_and_handler(virq, &s3c_irqext_chip,
-						 handle_edge_irq);
-		else
-			irq_set_chip_and_handler(virq, &s3c_irq_eint0t4,
-						 handle_edge_irq);
-		break;
-	case S3C_IRQTYPE_EDGE:
-		if (parent_intc || intc->reg_pending == S3C2416_SRCPND2)
-			irq_set_chip_and_handler(virq, &s3c_irq_level_chip,
-						 handle_edge_irq);
-		else
-			irq_set_chip_and_handler(virq, &s3c_irq_chip,
-						 handle_edge_irq);
-		break;
-	case S3C_IRQTYPE_LEVEL:
-		if (parent_intc)
-			irq_set_chip_and_handler(virq, &s3c_irq_level_chip,
-						 handle_level_irq);
-		else
-			irq_set_chip_and_handler(virq, &s3c_irq_chip,
-						 handle_level_irq);
-		break;
-	default:
-		pr_err("irq-s3c24xx: unsupported irqtype %d\n", irq_data->type);
-		return -EINVAL;
-	}
-
-	irq_set_chip_data(virq, irq_data);
-
-	if (parent_intc && irq_data->type != S3C_IRQTYPE_NONE) {
-		if (irq_data->parent_irq > 31) {
-			pr_err("irq-s3c24xx: parent irq %lu is out of range\n",
-			       irq_data->parent_irq);
-			return -EINVAL;
-		}
-
-		parent_irq_data = &parent_intc->irqs[irq_data->parent_irq];
-		parent_irq_data->sub_intc = intc;
-		parent_irq_data->sub_bits |= (1UL << hw);
-
-		/* attach the demuxer to the parent irq */
-		irqno = irq_find_mapping(parent_intc->domain,
-					 irq_data->parent_irq);
-		if (!irqno) {
-			pr_err("irq-s3c24xx: could not find mapping for parent irq %lu\n",
-			       irq_data->parent_irq);
-			return -EINVAL;
-		}
-		irq_set_chained_handler(irqno, s3c_irq_demux);
-	}
-
-	return 0;
-}
-
-static const struct irq_domain_ops s3c24xx_irq_ops = {
-	.map = s3c24xx_irq_map,
-	.xlate = irq_domain_xlate_twocell,
-};
-
-static void s3c24xx_clear_intc(struct s3c_irq_intc *intc)
-{
-	void __iomem *reg_source;
-	unsigned long pend;
-	unsigned long last;
-	int i;
-
-	/* if intpnd is set, read the next pending irq from there */
-	reg_source = intc->reg_intpnd ? intc->reg_intpnd : intc->reg_pending;
-
-	last = 0;
-	for (i = 0; i < 4; i++) {
-		pend = readl_relaxed(reg_source);
-
-		if (pend == 0 || pend == last)
-			break;
-
-		writel_relaxed(pend, intc->reg_pending);
-		if (intc->reg_intpnd)
-			writel_relaxed(pend, intc->reg_intpnd);
-
-		pr_info("irq: clearing pending status %08x\n", (int)pend);
-		last = pend;
-	}
-}
-
-static struct s3c_irq_intc * __init s3c24xx_init_intc(struct device_node *np,
-				       struct s3c_irq_data *irq_data,
-				       struct s3c_irq_intc *parent,
-				       unsigned long address)
-{
-	struct s3c_irq_intc *intc;
-	void __iomem *base = (void *)0xf6000000; /* static mapping */
-	int irq_num;
-	int irq_start;
-	int ret;
-
-	intc = kzalloc(sizeof(struct s3c_irq_intc), GFP_KERNEL);
-	if (!intc)
-		return ERR_PTR(-ENOMEM);
-
-	intc->irqs = irq_data;
-
-	if (parent)
-		intc->parent = parent;
-
-	/* select the correct data for the controller.
-	 * Need to hard code the irq num start and offset
-	 * to preserve the static mapping for now
-	 */
-	switch (address) {
-	case 0x4a000000:
-		pr_debug("irq: found main intc\n");
-		intc->reg_pending = base;
-		intc->reg_mask = base + 0x08;
-		intc->reg_intpnd = base + 0x10;
-		irq_num = 32;
-		irq_start = S3C2410_IRQ(0);
-		break;
-	case 0x4a000018:
-		pr_debug("irq: found subintc\n");
-		intc->reg_pending = base + 0x18;
-		intc->reg_mask = base + 0x1c;
-		irq_num = 29;
-		irq_start = S3C2410_IRQSUB(0);
-		break;
-	case 0x4a000040:
-		pr_debug("irq: found intc2\n");
-		intc->reg_pending = base + 0x40;
-		intc->reg_mask = base + 0x48;
-		intc->reg_intpnd = base + 0x50;
-		irq_num = 8;
-		irq_start = S3C2416_IRQ(0);
-		break;
-	case 0x560000a4:
-		pr_debug("irq: found eintc\n");
-		base = (void *)0xfd000000;
-
-		intc->reg_mask = base + 0xa4;
-		intc->reg_pending = base + 0xa8;
-		irq_num = 24;
-		irq_start = S3C2410_IRQ(32);
-		break;
-	default:
-		pr_err("irq: unsupported controller address\n");
-		ret = -EINVAL;
-		goto err;
-	}
-
-	/* now that all the data is complete, init the irq-domain */
-	s3c24xx_clear_intc(intc);
-	intc->domain = irq_domain_add_legacy(np, irq_num, irq_start,
-					     0, &s3c24xx_irq_ops,
-					     intc);
-	if (!intc->domain) {
-		pr_err("irq: could not create irq-domain\n");
-		ret = -EINVAL;
-		goto err;
-	}
-
-	set_handle_irq(s3c24xx_handle_irq);
-
-	return intc;
-
-err:
-	kfree(intc);
-	return ERR_PTR(ret);
-}
-
-static struct s3c_irq_data __maybe_unused init_eint[32] = {
-	{ .type = S3C_IRQTYPE_NONE, }, /* reserved */
-	{ .type = S3C_IRQTYPE_NONE, }, /* reserved */
-	{ .type = S3C_IRQTYPE_NONE, }, /* reserved */
-	{ .type = S3C_IRQTYPE_NONE, }, /* reserved */
-	{ .type = S3C_IRQTYPE_EINT, .parent_irq = 4 }, /* EINT4 */
-	{ .type = S3C_IRQTYPE_EINT, .parent_irq = 4 }, /* EINT5 */
-	{ .type = S3C_IRQTYPE_EINT, .parent_irq = 4 }, /* EINT6 */
-	{ .type = S3C_IRQTYPE_EINT, .parent_irq = 4 }, /* EINT7 */
-	{ .type = S3C_IRQTYPE_EINT, .parent_irq = 5 }, /* EINT8 */
-	{ .type = S3C_IRQTYPE_EINT, .parent_irq = 5 }, /* EINT9 */
-	{ .type = S3C_IRQTYPE_EINT, .parent_irq = 5 }, /* EINT10 */
-	{ .type = S3C_IRQTYPE_EINT, .parent_irq = 5 }, /* EINT11 */
-	{ .type = S3C_IRQTYPE_EINT, .parent_irq = 5 }, /* EINT12 */
-	{ .type = S3C_IRQTYPE_EINT, .parent_irq = 5 }, /* EINT13 */
-	{ .type = S3C_IRQTYPE_EINT, .parent_irq = 5 }, /* EINT14 */
-	{ .type = S3C_IRQTYPE_EINT, .parent_irq = 5 }, /* EINT15 */
-	{ .type = S3C_IRQTYPE_EINT, .parent_irq = 5 }, /* EINT16 */
-	{ .type = S3C_IRQTYPE_EINT, .parent_irq = 5 }, /* EINT17 */
-	{ .type = S3C_IRQTYPE_EINT, .parent_irq = 5 }, /* EINT18 */
-	{ .type = S3C_IRQTYPE_EINT, .parent_irq = 5 }, /* EINT19 */
-	{ .type = S3C_IRQTYPE_EINT, .parent_irq = 5 }, /* EINT20 */
-	{ .type = S3C_IRQTYPE_EINT, .parent_irq = 5 }, /* EINT21 */
-	{ .type = S3C_IRQTYPE_EINT, .parent_irq = 5 }, /* EINT22 */
-	{ .type = S3C_IRQTYPE_EINT, .parent_irq = 5 }, /* EINT23 */
-};
-
-#ifdef CONFIG_CPU_S3C2410
-static struct s3c_irq_data init_s3c2410base[32] = {
-	{ .type = S3C_IRQTYPE_EINT, }, /* EINT0 */
-	{ .type = S3C_IRQTYPE_EINT, }, /* EINT1 */
-	{ .type = S3C_IRQTYPE_EINT, }, /* EINT2 */
-	{ .type = S3C_IRQTYPE_EINT, }, /* EINT3 */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* EINT4to7 */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* EINT8to23 */
-	{ .type = S3C_IRQTYPE_NONE, }, /* reserved */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* nBATT_FLT */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* TICK */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* WDT */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* TIMER0 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* TIMER1 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* TIMER2 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* TIMER3 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* TIMER4 */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* UART2 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* LCD */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* DMA0 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* DMA1 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* DMA2 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* DMA3 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* SDI */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* SPI0 */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* UART1 */
-	{ .type = S3C_IRQTYPE_NONE, }, /* reserved */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* USBD */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* USBH */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* IIC */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* UART0 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* SPI1 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* RTC */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* ADCPARENT */
-};
-
-static struct s3c_irq_data init_s3c2410subint[32] = {
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 28 }, /* UART0-RX */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 28 }, /* UART0-TX */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 28 }, /* UART0-ERR */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 23 }, /* UART1-RX */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 23 }, /* UART1-TX */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 23 }, /* UART1-ERR */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 15 }, /* UART2-RX */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 15 }, /* UART2-TX */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 15 }, /* UART2-ERR */
-	{ .type = S3C_IRQTYPE_EDGE, .parent_irq = 31 }, /* TC */
-	{ .type = S3C_IRQTYPE_EDGE, .parent_irq = 31 }, /* ADC */
-};
-
-void __init s3c2410_init_irq(void)
-{
-#ifdef CONFIG_FIQ
-	init_FIQ(FIQ_START);
-#endif
-
-	s3c_intc[0] = s3c24xx_init_intc(NULL, &init_s3c2410base[0], NULL,
-					0x4a000000);
-	if (IS_ERR(s3c_intc[0])) {
-		pr_err("irq: could not create main interrupt controller\n");
-		return;
-	}
-
-	s3c_intc[1] = s3c24xx_init_intc(NULL, &init_s3c2410subint[0],
-					s3c_intc[0], 0x4a000018);
-	s3c24xx_init_intc(NULL, &init_eint[0], s3c_intc[0], 0x560000a4);
-}
-#endif
-
-#ifdef CONFIG_CPU_S3C2412
-static struct s3c_irq_data init_s3c2412base[32] = {
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* EINT0 */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* EINT1 */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* EINT2 */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* EINT3 */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* EINT4to7 */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* EINT8to23 */
-	{ .type = S3C_IRQTYPE_NONE, }, /* reserved */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* nBATT_FLT */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* TICK */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* WDT */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* TIMER0 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* TIMER1 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* TIMER2 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* TIMER3 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* TIMER4 */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* UART2 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* LCD */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* DMA0 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* DMA1 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* DMA2 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* DMA3 */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* SDI/CF */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* SPI0 */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* UART1 */
-	{ .type = S3C_IRQTYPE_NONE, }, /* reserved */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* USBD */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* USBH */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* IIC */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* UART0 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* SPI1 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* RTC */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* ADCPARENT */
-};
-
-static struct s3c_irq_data init_s3c2412eint[32] = {
-	{ .type = S3C_IRQTYPE_EINT, .parent_irq = 0 }, /* EINT0 */
-	{ .type = S3C_IRQTYPE_EINT, .parent_irq = 1 }, /* EINT1 */
-	{ .type = S3C_IRQTYPE_EINT, .parent_irq = 2 }, /* EINT2 */
-	{ .type = S3C_IRQTYPE_EINT, .parent_irq = 3 }, /* EINT3 */
-	{ .type = S3C_IRQTYPE_EINT, .parent_irq = 4 }, /* EINT4 */
-	{ .type = S3C_IRQTYPE_EINT, .parent_irq = 4 }, /* EINT5 */
-	{ .type = S3C_IRQTYPE_EINT, .parent_irq = 4 }, /* EINT6 */
-	{ .type = S3C_IRQTYPE_EINT, .parent_irq = 4 }, /* EINT7 */
-	{ .type = S3C_IRQTYPE_EINT, .parent_irq = 5 }, /* EINT8 */
-	{ .type = S3C_IRQTYPE_EINT, .parent_irq = 5 }, /* EINT9 */
-	{ .type = S3C_IRQTYPE_EINT, .parent_irq = 5 }, /* EINT10 */
-	{ .type = S3C_IRQTYPE_EINT, .parent_irq = 5 }, /* EINT11 */
-	{ .type = S3C_IRQTYPE_EINT, .parent_irq = 5 }, /* EINT12 */
-	{ .type = S3C_IRQTYPE_EINT, .parent_irq = 5 }, /* EINT13 */
-	{ .type = S3C_IRQTYPE_EINT, .parent_irq = 5 }, /* EINT14 */
-	{ .type = S3C_IRQTYPE_EINT, .parent_irq = 5 }, /* EINT15 */
-	{ .type = S3C_IRQTYPE_EINT, .parent_irq = 5 }, /* EINT16 */
-	{ .type = S3C_IRQTYPE_EINT, .parent_irq = 5 }, /* EINT17 */
-	{ .type = S3C_IRQTYPE_EINT, .parent_irq = 5 }, /* EINT18 */
-	{ .type = S3C_IRQTYPE_EINT, .parent_irq = 5 }, /* EINT19 */
-	{ .type = S3C_IRQTYPE_EINT, .parent_irq = 5 }, /* EINT20 */
-	{ .type = S3C_IRQTYPE_EINT, .parent_irq = 5 }, /* EINT21 */
-	{ .type = S3C_IRQTYPE_EINT, .parent_irq = 5 }, /* EINT22 */
-	{ .type = S3C_IRQTYPE_EINT, .parent_irq = 5 }, /* EINT23 */
-};
-
-static struct s3c_irq_data init_s3c2412subint[32] = {
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 28 }, /* UART0-RX */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 28 }, /* UART0-TX */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 28 }, /* UART0-ERR */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 23 }, /* UART1-RX */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 23 }, /* UART1-TX */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 23 }, /* UART1-ERR */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 15 }, /* UART2-RX */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 15 }, /* UART2-TX */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 15 }, /* UART2-ERR */
-	{ .type = S3C_IRQTYPE_EDGE, .parent_irq = 31 }, /* TC */
-	{ .type = S3C_IRQTYPE_EDGE, .parent_irq = 31 }, /* ADC */
-	{ .type = S3C_IRQTYPE_NONE, },
-	{ .type = S3C_IRQTYPE_NONE, },
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 21 }, /* SDI */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 21 }, /* CF */
-};
-
-void __init s3c2412_init_irq(void)
-{
-	pr_info("S3C2412: IRQ Support\n");
-
-#ifdef CONFIG_FIQ
-	init_FIQ(FIQ_START);
-#endif
-
-	s3c_intc[0] = s3c24xx_init_intc(NULL, &init_s3c2412base[0], NULL,
-					0x4a000000);
-	if (IS_ERR(s3c_intc[0])) {
-		pr_err("irq: could not create main interrupt controller\n");
-		return;
-	}
-
-	s3c24xx_init_intc(NULL, &init_s3c2412eint[0], s3c_intc[0], 0x560000a4);
-	s3c_intc[1] = s3c24xx_init_intc(NULL, &init_s3c2412subint[0],
-					s3c_intc[0], 0x4a000018);
-}
-#endif
-
-#ifdef CONFIG_CPU_S3C2416
-static struct s3c_irq_data init_s3c2416base[32] = {
-	{ .type = S3C_IRQTYPE_EINT, }, /* EINT0 */
-	{ .type = S3C_IRQTYPE_EINT, }, /* EINT1 */
-	{ .type = S3C_IRQTYPE_EINT, }, /* EINT2 */
-	{ .type = S3C_IRQTYPE_EINT, }, /* EINT3 */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* EINT4to7 */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* EINT8to23 */
-	{ .type = S3C_IRQTYPE_NONE, }, /* reserved */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* nBATT_FLT */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* TICK */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* WDT/AC97 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* TIMER0 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* TIMER1 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* TIMER2 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* TIMER3 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* TIMER4 */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* UART2 */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* LCD */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* DMA */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* UART3 */
-	{ .type = S3C_IRQTYPE_NONE, }, /* reserved */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* SDI1 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* SDI0 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* SPI0 */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* UART1 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* NAND */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* USBD */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* USBH */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* IIC */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* UART0 */
-	{ .type = S3C_IRQTYPE_NONE, },
-	{ .type = S3C_IRQTYPE_EDGE, }, /* RTC */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* ADCPARENT */
-};
-
-static struct s3c_irq_data init_s3c2416subint[32] = {
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 28 }, /* UART0-RX */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 28 }, /* UART0-TX */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 28 }, /* UART0-ERR */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 23 }, /* UART1-RX */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 23 }, /* UART1-TX */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 23 }, /* UART1-ERR */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 15 }, /* UART2-RX */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 15 }, /* UART2-TX */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 15 }, /* UART2-ERR */
-	{ .type = S3C_IRQTYPE_EDGE, .parent_irq = 31 }, /* TC */
-	{ .type = S3C_IRQTYPE_EDGE, .parent_irq = 31 }, /* ADC */
-	{ .type = S3C_IRQTYPE_NONE }, /* reserved */
-	{ .type = S3C_IRQTYPE_NONE }, /* reserved */
-	{ .type = S3C_IRQTYPE_NONE }, /* reserved */
-	{ .type = S3C_IRQTYPE_NONE }, /* reserved */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 16 }, /* LCD2 */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 16 }, /* LCD3 */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 16 }, /* LCD4 */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 17 }, /* DMA0 */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 17 }, /* DMA1 */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 17 }, /* DMA2 */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 17 }, /* DMA3 */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 17 }, /* DMA4 */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 17 }, /* DMA5 */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 18 }, /* UART3-RX */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 18 }, /* UART3-TX */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 18 }, /* UART3-ERR */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 9 }, /* WDT */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 9 }, /* AC97 */
-};
-
-static struct s3c_irq_data init_s3c2416_second[32] = {
-	{ .type = S3C_IRQTYPE_EDGE }, /* 2D */
-	{ .type = S3C_IRQTYPE_NONE }, /* reserved */
-	{ .type = S3C_IRQTYPE_NONE }, /* reserved */
-	{ .type = S3C_IRQTYPE_NONE }, /* reserved */
-	{ .type = S3C_IRQTYPE_EDGE }, /* PCM0 */
-	{ .type = S3C_IRQTYPE_NONE }, /* reserved */
-	{ .type = S3C_IRQTYPE_EDGE }, /* I2S0 */
-};
-
-void __init s3c2416_init_irq(void)
-{
-	pr_info("S3C2416: IRQ Support\n");
-
-#ifdef CONFIG_FIQ
-	init_FIQ(FIQ_START);
-#endif
-
-	s3c_intc[0] = s3c24xx_init_intc(NULL, &init_s3c2416base[0], NULL,
-					0x4a000000);
-	if (IS_ERR(s3c_intc[0])) {
-		pr_err("irq: could not create main interrupt controller\n");
-		return;
-	}
-
-	s3c24xx_init_intc(NULL, &init_eint[0], s3c_intc[0], 0x560000a4);
-	s3c_intc[1] = s3c24xx_init_intc(NULL, &init_s3c2416subint[0],
-					s3c_intc[0], 0x4a000018);
-
-	s3c_intc[2] = s3c24xx_init_intc(NULL, &init_s3c2416_second[0],
-					NULL, 0x4a000040);
-}
-
-#endif
-
-#ifdef CONFIG_CPU_S3C2440
-static struct s3c_irq_data init_s3c2440base[32] = {
-	{ .type = S3C_IRQTYPE_EINT, }, /* EINT0 */
-	{ .type = S3C_IRQTYPE_EINT, }, /* EINT1 */
-	{ .type = S3C_IRQTYPE_EINT, }, /* EINT2 */
-	{ .type = S3C_IRQTYPE_EINT, }, /* EINT3 */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* EINT4to7 */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* EINT8to23 */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* CAM */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* nBATT_FLT */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* TICK */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* WDT/AC97 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* TIMER0 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* TIMER1 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* TIMER2 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* TIMER3 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* TIMER4 */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* UART2 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* LCD */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* DMA0 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* DMA1 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* DMA2 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* DMA3 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* SDI */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* SPI0 */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* UART1 */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* NFCON */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* USBD */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* USBH */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* IIC */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* UART0 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* SPI1 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* RTC */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* ADCPARENT */
-};
-
-static struct s3c_irq_data init_s3c2440subint[32] = {
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 28 }, /* UART0-RX */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 28 }, /* UART0-TX */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 28 }, /* UART0-ERR */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 23 }, /* UART1-RX */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 23 }, /* UART1-TX */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 23 }, /* UART1-ERR */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 15 }, /* UART2-RX */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 15 }, /* UART2-TX */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 15 }, /* UART2-ERR */
-	{ .type = S3C_IRQTYPE_EDGE, .parent_irq = 31 }, /* TC */
-	{ .type = S3C_IRQTYPE_EDGE, .parent_irq = 31 }, /* ADC */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 6 }, /* CAM_C */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 6 }, /* CAM_P */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 9 }, /* WDT */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 9 }, /* AC97 */
-};
-
-void __init s3c2440_init_irq(void)
-{
-	pr_info("S3C2440: IRQ Support\n");
-
-#ifdef CONFIG_FIQ
-	init_FIQ(FIQ_START);
-#endif
-
-	s3c_intc[0] = s3c24xx_init_intc(NULL, &init_s3c2440base[0], NULL,
-					0x4a000000);
-	if (IS_ERR(s3c_intc[0])) {
-		pr_err("irq: could not create main interrupt controller\n");
-		return;
-	}
-
-	s3c24xx_init_intc(NULL, &init_eint[0], s3c_intc[0], 0x560000a4);
-	s3c_intc[1] = s3c24xx_init_intc(NULL, &init_s3c2440subint[0],
-					s3c_intc[0], 0x4a000018);
-}
-#endif
-
-#ifdef CONFIG_CPU_S3C2442
-static struct s3c_irq_data init_s3c2442base[32] = {
-	{ .type = S3C_IRQTYPE_EINT, }, /* EINT0 */
-	{ .type = S3C_IRQTYPE_EINT, }, /* EINT1 */
-	{ .type = S3C_IRQTYPE_EINT, }, /* EINT2 */
-	{ .type = S3C_IRQTYPE_EINT, }, /* EINT3 */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* EINT4to7 */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* EINT8to23 */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* CAM */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* nBATT_FLT */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* TICK */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* WDT */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* TIMER0 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* TIMER1 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* TIMER2 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* TIMER3 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* TIMER4 */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* UART2 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* LCD */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* DMA0 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* DMA1 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* DMA2 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* DMA3 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* SDI */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* SPI0 */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* UART1 */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* NFCON */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* USBD */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* USBH */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* IIC */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* UART0 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* SPI1 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* RTC */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* ADCPARENT */
-};
-
-static struct s3c_irq_data init_s3c2442subint[32] = {
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 28 }, /* UART0-RX */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 28 }, /* UART0-TX */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 28 }, /* UART0-ERR */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 23 }, /* UART1-RX */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 23 }, /* UART1-TX */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 23 }, /* UART1-ERR */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 15 }, /* UART2-RX */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 15 }, /* UART2-TX */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 15 }, /* UART2-ERR */
-	{ .type = S3C_IRQTYPE_EDGE, .parent_irq = 31 }, /* TC */
-	{ .type = S3C_IRQTYPE_EDGE, .parent_irq = 31 }, /* ADC */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 6 }, /* CAM_C */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 6 }, /* CAM_P */
-};
-
-void __init s3c2442_init_irq(void)
-{
-	pr_info("S3C2442: IRQ Support\n");
-
-#ifdef CONFIG_FIQ
-	init_FIQ(FIQ_START);
-#endif
-
-	s3c_intc[0] = s3c24xx_init_intc(NULL, &init_s3c2442base[0], NULL,
-					0x4a000000);
-	if (IS_ERR(s3c_intc[0])) {
-		pr_err("irq: could not create main interrupt controller\n");
-		return;
-	}
-
-	s3c24xx_init_intc(NULL, &init_eint[0], s3c_intc[0], 0x560000a4);
-	s3c_intc[1] = s3c24xx_init_intc(NULL, &init_s3c2442subint[0],
-					s3c_intc[0], 0x4a000018);
-}
-#endif
-
-#ifdef CONFIG_CPU_S3C2443
-static struct s3c_irq_data init_s3c2443base[32] = {
-	{ .type = S3C_IRQTYPE_EINT, }, /* EINT0 */
-	{ .type = S3C_IRQTYPE_EINT, }, /* EINT1 */
-	{ .type = S3C_IRQTYPE_EINT, }, /* EINT2 */
-	{ .type = S3C_IRQTYPE_EINT, }, /* EINT3 */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* EINT4to7 */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* EINT8to23 */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* CAM */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* nBATT_FLT */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* TICK */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* WDT/AC97 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* TIMER0 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* TIMER1 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* TIMER2 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* TIMER3 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* TIMER4 */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* UART2 */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* LCD */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* DMA */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* UART3 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* CFON */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* SDI1 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* SDI0 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* SPI0 */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* UART1 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* NAND */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* USBD */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* USBH */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* IIC */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* UART0 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* SPI1 */
-	{ .type = S3C_IRQTYPE_EDGE, }, /* RTC */
-	{ .type = S3C_IRQTYPE_LEVEL, }, /* ADCPARENT */
-};
-
-
-static struct s3c_irq_data init_s3c2443subint[32] = {
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 28 }, /* UART0-RX */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 28 }, /* UART0-TX */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 28 }, /* UART0-ERR */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 23 }, /* UART1-RX */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 23 }, /* UART1-TX */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 23 }, /* UART1-ERR */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 15 }, /* UART2-RX */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 15 }, /* UART2-TX */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 15 }, /* UART2-ERR */
-	{ .type = S3C_IRQTYPE_EDGE, .parent_irq = 31 }, /* TC */
-	{ .type = S3C_IRQTYPE_EDGE, .parent_irq = 31 }, /* ADC */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 6 }, /* CAM_C */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 6 }, /* CAM_P */
-	{ .type = S3C_IRQTYPE_NONE }, /* reserved */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 16 }, /* LCD1 */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 16 }, /* LCD2 */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 16 }, /* LCD3 */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 16 }, /* LCD4 */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 17 }, /* DMA0 */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 17 }, /* DMA1 */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 17 }, /* DMA2 */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 17 }, /* DMA3 */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 17 }, /* DMA4 */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 17 }, /* DMA5 */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 18 }, /* UART3-RX */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 18 }, /* UART3-TX */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 18 }, /* UART3-ERR */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 9 }, /* WDT */
-	{ .type = S3C_IRQTYPE_LEVEL, .parent_irq = 9 }, /* AC97 */
-};
-
-void __init s3c2443_init_irq(void)
-{
-	pr_info("S3C2443: IRQ Support\n");
-
-#ifdef CONFIG_FIQ
-	init_FIQ(FIQ_START);
-#endif
-
-	s3c_intc[0] = s3c24xx_init_intc(NULL, &init_s3c2443base[0], NULL,
-					0x4a000000);
-	if (IS_ERR(s3c_intc[0])) {
-		pr_err("irq: could not create main interrupt controller\n");
-		return;
-	}
-
-	s3c24xx_init_intc(NULL, &init_eint[0], s3c_intc[0], 0x560000a4);
-	s3c_intc[1] = s3c24xx_init_intc(NULL, &init_s3c2443subint[0],
-					s3c_intc[0], 0x4a000018);
-}
-#endif
-
-#ifdef CONFIG_OF
-static int s3c24xx_irq_map_of(struct irq_domain *h, unsigned int virq,
-							irq_hw_number_t hw)
-{
-	unsigned int ctrl_num = hw / 32;
-	unsigned int intc_hw = hw % 32;
-	struct s3c_irq_intc *intc = s3c_intc[ctrl_num];
-	struct s3c_irq_intc *parent_intc = intc->parent;
-	struct s3c_irq_data *irq_data = &intc->irqs[intc_hw];
-
-	/* attach controller pointer to irq_data */
-	irq_data->intc = intc;
-	irq_data->offset = intc_hw;
-
-	if (!parent_intc)
-		irq_set_chip_and_handler(virq, &s3c_irq_chip, handle_edge_irq);
-	else
-		irq_set_chip_and_handler(virq, &s3c_irq_level_chip,
-					 handle_edge_irq);
-
-	irq_set_chip_data(virq, irq_data);
-
-	return 0;
-}
-
-/* Translate our of irq notation
- * format: <ctrl_num ctrl_irq parent_irq type>
- */
-static int s3c24xx_irq_xlate_of(struct irq_domain *d, struct device_node *n,
-			const u32 *intspec, unsigned int intsize,
-			irq_hw_number_t *out_hwirq, unsigned int *out_type)
-{
-	struct s3c_irq_intc *intc;
-	struct s3c_irq_intc *parent_intc;
-	struct s3c_irq_data *irq_data;
-	struct s3c_irq_data *parent_irq_data;
-	int irqno;
-
-	if (WARN_ON(intsize < 4))
-		return -EINVAL;
-
-	if (intspec[0] > 2 || !s3c_intc[intspec[0]]) {
-		pr_err("controller number %d invalid\n", intspec[0]);
-		return -EINVAL;
-	}
-	intc = s3c_intc[intspec[0]];
-
-	*out_hwirq = intspec[0] * 32 + intspec[2];
-	*out_type = intspec[3] & IRQ_TYPE_SENSE_MASK;
-
-	parent_intc = intc->parent;
-	if (parent_intc) {
-		irq_data = &intc->irqs[intspec[2]];
-		irq_data->parent_irq = intspec[1];
-		parent_irq_data = &parent_intc->irqs[irq_data->parent_irq];
-		parent_irq_data->sub_intc = intc;
-		parent_irq_data->sub_bits |= (1UL << intspec[2]);
-
-		/* parent_intc is always s3c_intc[0], so no offset */
-		irqno = irq_create_mapping(parent_intc->domain, intspec[1]);
-		if (irqno < 0) {
-			pr_err("irq: could not map parent interrupt\n");
-			return irqno;
-		}
-
-		irq_set_chained_handler(irqno, s3c_irq_demux);
-	}
-
-	return 0;
-}
-
-static const struct irq_domain_ops s3c24xx_irq_ops_of = {
-	.map = s3c24xx_irq_map_of,
-	.xlate = s3c24xx_irq_xlate_of,
-};
-
-struct s3c24xx_irq_of_ctrl {
-	char			*name;
-	unsigned long		offset;
-	struct s3c_irq_intc	**handle;
-	struct s3c_irq_intc	**parent;
-	struct irq_domain_ops	*ops;
-};
-
-static int __init s3c_init_intc_of(struct device_node *np,
-			struct device_node *interrupt_parent,
-			struct s3c24xx_irq_of_ctrl *s3c_ctrl, int num_ctrl)
-{
-	struct s3c_irq_intc *intc;
-	struct s3c24xx_irq_of_ctrl *ctrl;
-	struct irq_domain *domain;
-	void __iomem *reg_base;
-	int i;
-
-	reg_base = of_iomap(np, 0);
-	if (!reg_base) {
-		pr_err("irq-s3c24xx: could not map irq registers\n");
-		return -EINVAL;
-	}
-
-	domain = irq_domain_add_linear(np, num_ctrl * 32,
-						     &s3c24xx_irq_ops_of, NULL);
-	if (!domain) {
-		pr_err("irq: could not create irq-domain\n");
-		return -EINVAL;
-	}
-
-	for (i = 0; i < num_ctrl; i++) {
-		ctrl = &s3c_ctrl[i];
-
-		pr_debug("irq: found controller %s\n", ctrl->name);
-
-		intc = kzalloc(sizeof(struct s3c_irq_intc), GFP_KERNEL);
-		if (!intc)
-			return -ENOMEM;
-
-		intc->domain = domain;
-		intc->irqs = kcalloc(32, sizeof(struct s3c_irq_data),
-				     GFP_KERNEL);
-		if (!intc->irqs) {
-			kfree(intc);
-			return -ENOMEM;
-		}
-
-		if (ctrl->parent) {
-			intc->reg_pending = reg_base + ctrl->offset;
-			intc->reg_mask = reg_base + ctrl->offset + 0x4;
-
-			if (*(ctrl->parent)) {
-				intc->parent = *(ctrl->parent);
-			} else {
-				pr_warn("irq: parent of %s missing\n",
-					ctrl->name);
-				kfree(intc->irqs);
-				kfree(intc);
-				continue;
-			}
-		} else {
-			intc->reg_pending = reg_base + ctrl->offset;
-			intc->reg_mask = reg_base + ctrl->offset + 0x08;
-			intc->reg_intpnd = reg_base + ctrl->offset + 0x10;
-		}
-
-		s3c24xx_clear_intc(intc);
-		s3c_intc[i] = intc;
-	}
-
-	set_handle_irq(s3c24xx_handle_irq);
-
-	return 0;
-}
-
-static struct s3c24xx_irq_of_ctrl s3c2410_ctrl[] = {
-	{
-		.name = "intc",
-		.offset = 0,
-	}, {
-		.name = "subintc",
-		.offset = 0x18,
-		.parent = &s3c_intc[0],
-	}
-};
-
-int __init s3c2410_init_intc_of(struct device_node *np,
-			struct device_node *interrupt_parent)
-{
-	return s3c_init_intc_of(np, interrupt_parent,
-				s3c2410_ctrl, ARRAY_SIZE(s3c2410_ctrl));
-}
-IRQCHIP_DECLARE(s3c2410_irq, "samsung,s3c2410-irq", s3c2410_init_intc_of);
-
-static struct s3c24xx_irq_of_ctrl s3c2416_ctrl[] = {
-	{
-		.name = "intc",
-		.offset = 0,
-	}, {
-		.name = "subintc",
-		.offset = 0x18,
-		.parent = &s3c_intc[0],
-	}, {
-		.name = "intc2",
-		.offset = 0x40,
-	}
-};
-
-int __init s3c2416_init_intc_of(struct device_node *np,
-			struct device_node *interrupt_parent)
-{
-	return s3c_init_intc_of(np, interrupt_parent,
-				s3c2416_ctrl, ARRAY_SIZE(s3c2416_ctrl));
-}
-IRQCHIP_DECLARE(s3c2416_irq, "samsung,s3c2416-irq", s3c2416_init_intc_of);
-#endif
diff --git a/drivers/irqchip/irq-sifive-plic.c b/drivers/irqchip/irq-sifive-plic.c
index 7d0a12f..bd99ee0 100644
--- a/drivers/irqchip/irq-sifive-plic.c
+++ b/drivers/irqchip/irq-sifive-plic.c
@@ -4,10 +4,12 @@
  * Copyright (C) 2018 Christoph Hellwig
  */
 #define pr_fmt(fmt) "plic: " fmt
+#include <linux/cpu.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/irq.h>
 #include <linux/irqchip.h>
+#include <linux/irqchip/chained_irq.h>
 #include <linux/irqdomain.h>
 #include <linux/module.h>
 #include <linux/of.h>
@@ -55,7 +57,14 @@
 #define     CONTEXT_THRESHOLD		0x00
 #define     CONTEXT_CLAIM		0x04
 
-static void __iomem *plic_regs;
+#define	PLIC_DISABLE_THRESHOLD		0x7
+#define	PLIC_ENABLE_THRESHOLD		0
+
+struct plic_priv {
+	struct cpumask lmask;
+	struct irq_domain *irqdomain;
+	void __iomem *regs;
+};
 
 struct plic_handler {
 	bool			present;
@@ -66,7 +75,10 @@
 	 */
 	raw_spinlock_t		enable_lock;
 	void __iomem		*enable_base;
+	struct plic_priv	*priv;
 };
+static int plic_parent_irq;
+static bool plic_cpuhp_setup_done;
 static DEFINE_PER_CPU(struct plic_handler, plic_handlers);
 
 static inline void plic_toggle(struct plic_handler *handler,
@@ -84,31 +96,40 @@
 }
 
 static inline void plic_irq_toggle(const struct cpumask *mask,
-				   int hwirq, int enable)
+				   struct irq_data *d, int enable)
 {
 	int cpu;
+	struct plic_priv *priv = irq_data_get_irq_chip_data(d);
 
-	writel(enable, plic_regs + PRIORITY_BASE + hwirq * PRIORITY_PER_ID);
+	writel(enable, priv->regs + PRIORITY_BASE + d->hwirq * PRIORITY_PER_ID);
 	for_each_cpu(cpu, mask) {
 		struct plic_handler *handler = per_cpu_ptr(&plic_handlers, cpu);
 
-		if (handler->present)
-			plic_toggle(handler, hwirq, enable);
+		if (handler->present &&
+		    cpumask_test_cpu(cpu, &handler->priv->lmask))
+			plic_toggle(handler, d->hwirq, enable);
 	}
 }
 
 static void plic_irq_unmask(struct irq_data *d)
 {
-	unsigned int cpu = cpumask_any_and(irq_data_get_affinity_mask(d),
-					   cpu_online_mask);
+	struct cpumask amask;
+	unsigned int cpu;
+	struct plic_priv *priv = irq_data_get_irq_chip_data(d);
+
+	cpumask_and(&amask, &priv->lmask, cpu_online_mask);
+	cpu = cpumask_any_and(irq_data_get_affinity_mask(d),
+					   &amask);
 	if (WARN_ON_ONCE(cpu >= nr_cpu_ids))
 		return;
-	plic_irq_toggle(cpumask_of(cpu), d->hwirq, 1);
+	plic_irq_toggle(cpumask_of(cpu), d, 1);
 }
 
 static void plic_irq_mask(struct irq_data *d)
 {
-	plic_irq_toggle(cpu_possible_mask, d->hwirq, 0);
+	struct plic_priv *priv = irq_data_get_irq_chip_data(d);
+
+	plic_irq_toggle(&priv->lmask, d, 0);
 }
 
 #ifdef CONFIG_SMP
@@ -116,17 +137,21 @@
 			     const struct cpumask *mask_val, bool force)
 {
 	unsigned int cpu;
+	struct cpumask amask;
+	struct plic_priv *priv = irq_data_get_irq_chip_data(d);
+
+	cpumask_and(&amask, &priv->lmask, mask_val);
 
 	if (force)
-		cpu = cpumask_first(mask_val);
+		cpu = cpumask_first(&amask);
 	else
-		cpu = cpumask_any_and(mask_val, cpu_online_mask);
+		cpu = cpumask_any_and(&amask, cpu_online_mask);
 
 	if (cpu >= nr_cpu_ids)
 		return -EINVAL;
 
-	plic_irq_toggle(cpu_possible_mask, d->hwirq, 0);
-	plic_irq_toggle(cpumask_of(cpu), d->hwirq, 1);
+	plic_irq_toggle(&priv->lmask, d, 0);
+	plic_irq_toggle(cpumask_of(cpu), d, !irqd_irq_masked(d));
 
 	irq_data_update_effective_affinity(d, cpumask_of(cpu));
 
@@ -138,7 +163,13 @@
 {
 	struct plic_handler *handler = this_cpu_ptr(&plic_handlers);
 
-	writel(d->hwirq, handler->hart_base + CONTEXT_CLAIM);
+	if (irqd_irq_masked(d)) {
+		plic_irq_unmask(d);
+		writel(d->hwirq, handler->hart_base + CONTEXT_CLAIM);
+		plic_irq_mask(d);
+	} else {
+		writel(d->hwirq, handler->hart_base + CONTEXT_CLAIM);
+	}
 }
 
 static struct irq_chip plic_chip = {
@@ -154,36 +185,61 @@
 static int plic_irqdomain_map(struct irq_domain *d, unsigned int irq,
 			      irq_hw_number_t hwirq)
 {
-	irq_set_chip_and_handler(irq, &plic_chip, handle_fasteoi_irq);
-	irq_set_chip_data(irq, NULL);
+	struct plic_priv *priv = d->host_data;
+
+	irq_domain_set_info(d, irq, hwirq, &plic_chip, d->host_data,
+			    handle_fasteoi_irq, NULL, NULL);
 	irq_set_noprobe(irq);
+	irq_set_affinity(irq, &priv->lmask);
+	return 0;
+}
+
+static int plic_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
+				 unsigned int nr_irqs, void *arg)
+{
+	int i, ret;
+	irq_hw_number_t hwirq;
+	unsigned int type;
+	struct irq_fwspec *fwspec = arg;
+
+	ret = irq_domain_translate_onecell(domain, fwspec, &hwirq, &type);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < nr_irqs; i++) {
+		ret = plic_irqdomain_map(domain, virq + i, hwirq + i);
+		if (ret)
+			return ret;
+	}
+
 	return 0;
 }
 
 static const struct irq_domain_ops plic_irqdomain_ops = {
-	.map		= plic_irqdomain_map,
-	.xlate		= irq_domain_xlate_onecell,
+	.translate	= irq_domain_translate_onecell,
+	.alloc		= plic_irq_domain_alloc,
+	.free		= irq_domain_free_irqs_top,
 };
 
-static struct irq_domain *plic_irqdomain;
-
 /*
  * Handling an interrupt is a two-step process: first you claim the interrupt
  * by reading the claim register, then you complete the interrupt by writing
  * that source ID back to the same claim register.  This automatically enables
  * and disables the interrupt, so there's nothing else to do.
  */
-static void plic_handle_irq(struct pt_regs *regs)
+static void plic_handle_irq(struct irq_desc *desc)
 {
 	struct plic_handler *handler = this_cpu_ptr(&plic_handlers);
+	struct irq_chip *chip = irq_desc_get_chip(desc);
 	void __iomem *claim = handler->hart_base + CONTEXT_CLAIM;
 	irq_hw_number_t hwirq;
 
 	WARN_ON_ONCE(!handler->present);
 
-	csr_clear(sie, SIE_SEIE);
+	chained_irq_enter(chip, desc);
+
 	while ((hwirq = readl(claim))) {
-		int irq = irq_find_mapping(plic_irqdomain, hwirq);
+		int irq = irq_find_mapping(handler->priv->irqdomain, hwirq);
 
 		if (unlikely(irq <= 0))
 			pr_warn_ratelimited("can't find mapping for hwirq %lu\n",
@@ -191,21 +247,36 @@
 		else
 			generic_handle_irq(irq);
 	}
-	csr_set(sie, SIE_SEIE);
+
+	chained_irq_exit(chip, desc);
 }
 
-/*
- * Walk up the DT tree until we find an active RISC-V core (HART) node and
- * extract the cpuid from it.
- */
-static int plic_find_hart_id(struct device_node *node)
+static void plic_set_threshold(struct plic_handler *handler, u32 threshold)
 {
-	for (; node; node = node->parent) {
-		if (of_device_is_compatible(node, "riscv"))
-			return riscv_of_processor_hartid(node);
-	}
+	/* priority must be > threshold to trigger an interrupt */
+	writel(threshold, handler->hart_base + CONTEXT_THRESHOLD);
+}
 
-	return -1;
+static int plic_dying_cpu(unsigned int cpu)
+{
+	if (plic_parent_irq)
+		disable_percpu_irq(plic_parent_irq);
+
+	return 0;
+}
+
+static int plic_starting_cpu(unsigned int cpu)
+{
+	struct plic_handler *handler = this_cpu_ptr(&plic_handlers);
+
+	if (plic_parent_irq)
+		enable_percpu_irq(plic_parent_irq,
+				  irq_get_trigger_type(plic_parent_irq));
+	else
+		pr_warn("cpu%d: parent irq not available\n", cpu);
+	plic_set_threshold(handler, PLIC_ENABLE_THRESHOLD);
+
+	return 0;
 }
 
 static int __init plic_init(struct device_node *node,
@@ -213,16 +284,19 @@
 {
 	int error = 0, nr_contexts, nr_handlers = 0, i;
 	u32 nr_irqs;
+	struct plic_priv *priv;
+	struct plic_handler *handler;
 
-	if (plic_regs) {
-		pr_warn("PLIC already present.\n");
-		return -ENXIO;
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->regs = of_iomap(node, 0);
+	if (WARN_ON(!priv->regs)) {
+		error = -EIO;
+		goto out_free_priv;
 	}
 
-	plic_regs = of_iomap(node, 0);
-	if (WARN_ON(!plic_regs))
-		return -EIO;
-
 	error = -EINVAL;
 	of_property_read_u32(node, "riscv,ndev", &nr_irqs);
 	if (WARN_ON(!nr_irqs))
@@ -231,32 +305,31 @@
 	nr_contexts = of_irq_count(node);
 	if (WARN_ON(!nr_contexts))
 		goto out_iounmap;
-	if (WARN_ON(nr_contexts < num_possible_cpus()))
-		goto out_iounmap;
 
 	error = -ENOMEM;
-	plic_irqdomain = irq_domain_add_linear(node, nr_irqs + 1,
-			&plic_irqdomain_ops, NULL);
-	if (WARN_ON(!plic_irqdomain))
+	priv->irqdomain = irq_domain_add_linear(node, nr_irqs + 1,
+			&plic_irqdomain_ops, priv);
+	if (WARN_ON(!priv->irqdomain))
 		goto out_iounmap;
 
 	for (i = 0; i < nr_contexts; i++) {
 		struct of_phandle_args parent;
-		struct plic_handler *handler;
 		irq_hw_number_t hwirq;
 		int cpu, hartid;
-		u32 threshold = 0;
 
 		if (of_irq_parse_one(node, i, &parent)) {
 			pr_err("failed to parse parent for context %d.\n", i);
 			continue;
 		}
 
-		/* skip contexts other than supervisor external interrupt */
-		if (parent.args[0] != IRQ_S_EXT)
+		/*
+		 * Skip contexts other than external interrupts for our
+		 * privilege level.
+		 */
+		if (parent.args[0] != RV_IRQ_EXT)
 			continue;
 
-		hartid = plic_find_hart_id(parent.np);
+		hartid = riscv_of_parent_hartid(parent.np);
 		if (hartid < 0) {
 			pr_warn("failed to parse hart ID for context %d.\n", i);
 			continue;
@@ -268,6 +341,14 @@
 			continue;
 		}
 
+		/* Find parent domain and register chained handler */
+		if (!plic_parent_irq && irq_find_host(parent.np)) {
+			plic_parent_irq = irq_of_parse_and_map(node, i);
+			if (plic_parent_irq)
+				irq_set_chained_handler(plic_parent_irq,
+							plic_handle_irq);
+		}
+
 		/*
 		 * When running in M-mode we need to ignore the S-mode handler.
 		 * Here we assume it always comes later, but that might be a
@@ -276,34 +357,47 @@
 		handler = per_cpu_ptr(&plic_handlers, cpu);
 		if (handler->present) {
 			pr_warn("handler already present for context %d.\n", i);
-			threshold = 0xffffffff;
+			plic_set_threshold(handler, PLIC_DISABLE_THRESHOLD);
 			goto done;
 		}
 
+		cpumask_set_cpu(cpu, &priv->lmask);
 		handler->present = true;
 		handler->hart_base =
-			plic_regs + CONTEXT_BASE + i * CONTEXT_PER_HART;
+			priv->regs + CONTEXT_BASE + i * CONTEXT_PER_HART;
 		raw_spin_lock_init(&handler->enable_lock);
 		handler->enable_base =
-			plic_regs + ENABLE_BASE + i * ENABLE_PER_HART;
-
+			priv->regs + ENABLE_BASE + i * ENABLE_PER_HART;
+		handler->priv = priv;
 done:
-		/* priority must be > threshold to trigger an interrupt */
-		writel(threshold, handler->hart_base + CONTEXT_THRESHOLD);
 		for (hwirq = 1; hwirq <= nr_irqs; hwirq++)
 			plic_toggle(handler, hwirq, 0);
 		nr_handlers++;
 	}
 
-	pr_info("mapped %d interrupts with %d handlers for %d contexts.\n",
-		nr_irqs, nr_handlers, nr_contexts);
-	set_handle_irq(plic_handle_irq);
+	/*
+	 * We can have multiple PLIC instances so setup cpuhp state only
+	 * when context handler for current/boot CPU is present.
+	 */
+	handler = this_cpu_ptr(&plic_handlers);
+	if (handler->present && !plic_cpuhp_setup_done) {
+		cpuhp_setup_state(CPUHP_AP_IRQ_SIFIVE_PLIC_STARTING,
+				  "irqchip/sifive/plic:starting",
+				  plic_starting_cpu, plic_dying_cpu);
+		plic_cpuhp_setup_done = true;
+	}
+
+	pr_info("%pOFP: mapped %d interrupts with %d handlers for"
+		" %d contexts.\n", node, nr_irqs, nr_handlers, nr_contexts);
 	return 0;
 
 out_iounmap:
-	iounmap(plic_regs);
+	iounmap(priv->regs);
+out_free_priv:
+	kfree(priv);
 	return error;
 }
 
 IRQCHIP_DECLARE(sifive_plic, "sifive,plic-1.0.0", plic_init);
 IRQCHIP_DECLARE(riscv_plic0, "riscv,plic0", plic_init); /* for legacy systems */
+IRQCHIP_DECLARE(thead_c900_plic, "thead,c900-plic", plic_init); /* for firmware driver */
diff --git a/drivers/irqchip/irq-sl28cpld.c b/drivers/irqchip/irq-sl28cpld.c
new file mode 100644
index 0000000..0aa50d0
--- /dev/null
+++ b/drivers/irqchip/irq-sl28cpld.c
@@ -0,0 +1,96 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * sl28cpld interrupt controller driver
+ *
+ * Copyright 2020 Kontron Europe GmbH
+ */
+
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/mod_devicetable.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/property.h>
+#include <linux/regmap.h>
+
+#define INTC_IE 0x00
+#define INTC_IP 0x01
+
+static const struct regmap_irq sl28cpld_irqs[] = {
+	REGMAP_IRQ_REG_LINE(0, 8),
+	REGMAP_IRQ_REG_LINE(1, 8),
+	REGMAP_IRQ_REG_LINE(2, 8),
+	REGMAP_IRQ_REG_LINE(3, 8),
+	REGMAP_IRQ_REG_LINE(4, 8),
+	REGMAP_IRQ_REG_LINE(5, 8),
+	REGMAP_IRQ_REG_LINE(6, 8),
+	REGMAP_IRQ_REG_LINE(7, 8),
+};
+
+struct sl28cpld_intc {
+	struct regmap *regmap;
+	struct regmap_irq_chip chip;
+	struct regmap_irq_chip_data *irq_data;
+};
+
+static int sl28cpld_intc_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct sl28cpld_intc *irqchip;
+	int irq;
+	u32 base;
+	int ret;
+
+	if (!dev->parent)
+		return -ENODEV;
+
+	irqchip = devm_kzalloc(dev, sizeof(*irqchip), GFP_KERNEL);
+	if (!irqchip)
+		return -ENOMEM;
+
+	irqchip->regmap = dev_get_regmap(dev->parent, NULL);
+	if (!irqchip->regmap)
+		return -ENODEV;
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return irq;
+
+	ret = device_property_read_u32(&pdev->dev, "reg", &base);
+	if (ret)
+		return -EINVAL;
+
+	irqchip->chip.name = "sl28cpld-intc";
+	irqchip->chip.irqs = sl28cpld_irqs;
+	irqchip->chip.num_irqs = ARRAY_SIZE(sl28cpld_irqs);
+	irqchip->chip.num_regs = 1;
+	irqchip->chip.status_base = base + INTC_IP;
+	irqchip->chip.mask_base = base + INTC_IE;
+	irqchip->chip.mask_invert = true,
+	irqchip->chip.ack_base = base + INTC_IP;
+
+	return devm_regmap_add_irq_chip_fwnode(dev, dev_fwnode(dev),
+					       irqchip->regmap, irq,
+					       IRQF_SHARED | IRQF_ONESHOT, 0,
+					       &irqchip->chip,
+					       &irqchip->irq_data);
+}
+
+static const struct of_device_id sl28cpld_intc_of_match[] = {
+	{ .compatible = "kontron,sl28cpld-intc" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, sl28cpld_intc_of_match);
+
+static struct platform_driver sl28cpld_intc_driver = {
+	.probe = sl28cpld_intc_probe,
+	.driver = {
+		.name = "sl28cpld-intc",
+		.of_match_table = sl28cpld_intc_of_match,
+	}
+};
+module_platform_driver(sl28cpld_intc_driver);
+
+MODULE_DESCRIPTION("sl28cpld Interrupt Controller Driver");
+MODULE_AUTHOR("Michael Walle <michael@walle.cc>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/irqchip/irq-stm32-exti.c b/drivers/irqchip/irq-stm32-exti.c
index a8322a4..8662d7b 100644
--- a/drivers/irqchip/irq-stm32-exti.c
+++ b/drivers/irqchip/irq-stm32-exti.c
@@ -25,7 +25,6 @@
 #define IRQS_PER_BANK 32
 
 #define HWSPNLCK_TIMEOUT	1000 /* usec */
-#define HWSPNLCK_RETRY_DELAY	100  /* usec */
 
 struct stm32_exti_bank {
 	u32 imr_ofst;
@@ -42,6 +41,7 @@
 struct stm32_desc_irq {
 	u32 exti;
 	u32 irq_parent;
+	struct irq_chip *chip;
 };
 
 struct stm32_exti_drv_data {
@@ -166,27 +166,45 @@
 	&stm32mp1_exti_b3,
 };
 
+static struct irq_chip stm32_exti_h_chip;
+static struct irq_chip stm32_exti_h_chip_direct;
+
 static const struct stm32_desc_irq stm32mp1_desc_irq[] = {
-	{ .exti = 0, .irq_parent = 6 },
-	{ .exti = 1, .irq_parent = 7 },
-	{ .exti = 2, .irq_parent = 8 },
-	{ .exti = 3, .irq_parent = 9 },
-	{ .exti = 4, .irq_parent = 10 },
-	{ .exti = 5, .irq_parent = 23 },
-	{ .exti = 6, .irq_parent = 64 },
-	{ .exti = 7, .irq_parent = 65 },
-	{ .exti = 8, .irq_parent = 66 },
-	{ .exti = 9, .irq_parent = 67 },
-	{ .exti = 10, .irq_parent = 40 },
-	{ .exti = 11, .irq_parent = 42 },
-	{ .exti = 12, .irq_parent = 76 },
-	{ .exti = 13, .irq_parent = 77 },
-	{ .exti = 14, .irq_parent = 121 },
-	{ .exti = 15, .irq_parent = 127 },
-	{ .exti = 16, .irq_parent = 1 },
-	{ .exti = 65, .irq_parent = 144 },
-	{ .exti = 68, .irq_parent = 143 },
-	{ .exti = 73, .irq_parent = 129 },
+	{ .exti = 0, .irq_parent = 6, .chip = &stm32_exti_h_chip },
+	{ .exti = 1, .irq_parent = 7, .chip = &stm32_exti_h_chip },
+	{ .exti = 2, .irq_parent = 8, .chip = &stm32_exti_h_chip },
+	{ .exti = 3, .irq_parent = 9, .chip = &stm32_exti_h_chip },
+	{ .exti = 4, .irq_parent = 10, .chip = &stm32_exti_h_chip },
+	{ .exti = 5, .irq_parent = 23, .chip = &stm32_exti_h_chip },
+	{ .exti = 6, .irq_parent = 64, .chip = &stm32_exti_h_chip },
+	{ .exti = 7, .irq_parent = 65, .chip = &stm32_exti_h_chip },
+	{ .exti = 8, .irq_parent = 66, .chip = &stm32_exti_h_chip },
+	{ .exti = 9, .irq_parent = 67, .chip = &stm32_exti_h_chip },
+	{ .exti = 10, .irq_parent = 40, .chip = &stm32_exti_h_chip },
+	{ .exti = 11, .irq_parent = 42, .chip = &stm32_exti_h_chip },
+	{ .exti = 12, .irq_parent = 76, .chip = &stm32_exti_h_chip },
+	{ .exti = 13, .irq_parent = 77, .chip = &stm32_exti_h_chip },
+	{ .exti = 14, .irq_parent = 121, .chip = &stm32_exti_h_chip },
+	{ .exti = 15, .irq_parent = 127, .chip = &stm32_exti_h_chip },
+	{ .exti = 16, .irq_parent = 1, .chip = &stm32_exti_h_chip },
+	{ .exti = 19, .irq_parent = 3, .chip = &stm32_exti_h_chip_direct },
+	{ .exti = 21, .irq_parent = 31, .chip = &stm32_exti_h_chip_direct },
+	{ .exti = 22, .irq_parent = 33, .chip = &stm32_exti_h_chip_direct },
+	{ .exti = 23, .irq_parent = 72, .chip = &stm32_exti_h_chip_direct },
+	{ .exti = 24, .irq_parent = 95, .chip = &stm32_exti_h_chip_direct },
+	{ .exti = 25, .irq_parent = 107, .chip = &stm32_exti_h_chip_direct },
+	{ .exti = 30, .irq_parent = 52, .chip = &stm32_exti_h_chip_direct },
+	{ .exti = 47, .irq_parent = 93, .chip = &stm32_exti_h_chip_direct },
+	{ .exti = 48, .irq_parent = 138, .chip = &stm32_exti_h_chip_direct },
+	{ .exti = 50, .irq_parent = 139, .chip = &stm32_exti_h_chip_direct },
+	{ .exti = 52, .irq_parent = 140, .chip = &stm32_exti_h_chip_direct },
+	{ .exti = 53, .irq_parent = 141, .chip = &stm32_exti_h_chip_direct },
+	{ .exti = 54, .irq_parent = 135, .chip = &stm32_exti_h_chip_direct },
+	{ .exti = 61, .irq_parent = 100, .chip = &stm32_exti_h_chip_direct },
+	{ .exti = 65, .irq_parent = 144, .chip = &stm32_exti_h_chip },
+	{ .exti = 68, .irq_parent = 143, .chip = &stm32_exti_h_chip },
+	{ .exti = 70, .irq_parent = 62, .chip = &stm32_exti_h_chip_direct },
+	{ .exti = 73, .irq_parent = 129, .chip = &stm32_exti_h_chip },
 };
 
 static const struct stm32_exti_drv_data stm32mp1_drv_data = {
@@ -196,22 +214,23 @@
 	.irq_nr = ARRAY_SIZE(stm32mp1_desc_irq),
 };
 
-static int stm32_exti_to_irq(const struct stm32_exti_drv_data *drv_data,
-			     irq_hw_number_t hwirq)
+static const struct
+stm32_desc_irq *stm32_exti_get_desc(const struct stm32_exti_drv_data *drv_data,
+				    irq_hw_number_t hwirq)
 {
-	const struct stm32_desc_irq *desc_irq;
+	const struct stm32_desc_irq *desc = NULL;
 	int i;
 
 	if (!drv_data->desc_irqs)
-		return -EINVAL;
+		return NULL;
 
 	for (i = 0; i < drv_data->irq_nr; i++) {
-		desc_irq = &drv_data->desc_irqs[i];
-		if (desc_irq->exti == hwirq)
-			return desc_irq->irq_parent;
+		desc = &drv_data->desc_irqs[i];
+		if (desc->exti == hwirq)
+			break;
 	}
 
-	return -EINVAL;
+	return desc;
 }
 
 static unsigned long stm32_exti_pending(struct irq_chip_generic *gc)
@@ -277,55 +296,24 @@
 	return 0;
 }
 
-static int stm32_exti_hwspin_lock(struct stm32_exti_chip_data *chip_data)
-{
-	int ret, timeout = 0;
-
-	if (!chip_data->host_data->hwlock)
-		return 0;
-
-	/*
-	 * Use the x_raw API since we are under spin_lock protection.
-	 * Do not use the x_timeout API because we are under irq_disable
-	 * mode (see __setup_irq())
-	 */
-	do {
-		ret = hwspin_trylock_raw(chip_data->host_data->hwlock);
-		if (!ret)
-			return 0;
-
-		udelay(HWSPNLCK_RETRY_DELAY);
-		timeout += HWSPNLCK_RETRY_DELAY;
-	} while (timeout < HWSPNLCK_TIMEOUT);
-
-	if (ret == -EBUSY)
-		ret = -ETIMEDOUT;
-
-	if (ret)
-		pr_err("%s can't get hwspinlock (%d)\n", __func__, ret);
-
-	return ret;
-}
-
-static void stm32_exti_hwspin_unlock(struct stm32_exti_chip_data *chip_data)
-{
-	if (chip_data->host_data->hwlock)
-		hwspin_unlock_raw(chip_data->host_data->hwlock);
-}
-
 static int stm32_irq_set_type(struct irq_data *d, unsigned int type)
 {
 	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
 	struct stm32_exti_chip_data *chip_data = gc->private;
 	const struct stm32_exti_bank *stm32_bank = chip_data->reg_bank;
+	struct hwspinlock *hwlock = chip_data->host_data->hwlock;
 	u32 rtsr, ftsr;
 	int err;
 
 	irq_gc_lock(gc);
 
-	err = stm32_exti_hwspin_lock(chip_data);
-	if (err)
-		goto unlock;
+	if (hwlock) {
+		err = hwspin_lock_timeout_in_atomic(hwlock, HWSPNLCK_TIMEOUT);
+		if (err) {
+			pr_err("%s can't get hwspinlock (%d)\n", __func__, err);
+			goto unlock;
+		}
+	}
 
 	rtsr = irq_reg_readl(gc, stm32_bank->rtsr_ofst);
 	ftsr = irq_reg_readl(gc, stm32_bank->ftsr_ofst);
@@ -338,7 +326,8 @@
 	irq_reg_writel(gc, ftsr, stm32_bank->ftsr_ofst);
 
 unspinlock:
-	stm32_exti_hwspin_unlock(chip_data);
+	if (hwlock)
+		hwspin_unlock_in_atomic(hwlock);
 unlock:
 	irq_gc_unlock(gc);
 
@@ -514,15 +503,20 @@
 {
 	struct stm32_exti_chip_data *chip_data = irq_data_get_irq_chip_data(d);
 	const struct stm32_exti_bank *stm32_bank = chip_data->reg_bank;
+	struct hwspinlock *hwlock = chip_data->host_data->hwlock;
 	void __iomem *base = chip_data->host_data->base;
 	u32 rtsr, ftsr;
 	int err;
 
 	raw_spin_lock(&chip_data->rlock);
 
-	err = stm32_exti_hwspin_lock(chip_data);
-	if (err)
-		goto unlock;
+	if (hwlock) {
+		err = hwspin_lock_timeout_in_atomic(hwlock, HWSPNLCK_TIMEOUT);
+		if (err) {
+			pr_err("%s can't get hwspinlock (%d)\n", __func__, err);
+			goto unlock;
+		}
+	}
 
 	rtsr = readl_relaxed(base + stm32_bank->rtsr_ofst);
 	ftsr = readl_relaxed(base + stm32_bank->ftsr_ofst);
@@ -535,7 +529,8 @@
 	writel_relaxed(ftsr, base + stm32_bank->ftsr_ofst);
 
 unspinlock:
-	stm32_exti_hwspin_unlock(chip_data);
+	if (hwlock)
+		hwspin_unlock_in_atomic(hwlock);
 unlock:
 	raw_spin_unlock(&chip_data->rlock);
 
@@ -614,42 +609,71 @@
 	unregister_syscore_ops(&stm32_exti_h_syscore_ops);
 }
 
+static int stm32_exti_h_retrigger(struct irq_data *d)
+{
+	struct stm32_exti_chip_data *chip_data = irq_data_get_irq_chip_data(d);
+	const struct stm32_exti_bank *stm32_bank = chip_data->reg_bank;
+	void __iomem *base = chip_data->host_data->base;
+	u32 mask = BIT(d->hwirq % IRQS_PER_BANK);
+
+	writel_relaxed(mask, base + stm32_bank->swier_ofst);
+
+	return 0;
+}
+
 static struct irq_chip stm32_exti_h_chip = {
 	.name			= "stm32-exti-h",
 	.irq_eoi		= stm32_exti_h_eoi,
 	.irq_mask		= stm32_exti_h_mask,
 	.irq_unmask		= stm32_exti_h_unmask,
-	.irq_retrigger		= irq_chip_retrigger_hierarchy,
+	.irq_retrigger		= stm32_exti_h_retrigger,
 	.irq_set_type		= stm32_exti_h_set_type,
 	.irq_set_wake		= stm32_exti_h_set_wake,
 	.flags			= IRQCHIP_MASK_ON_SUSPEND,
 	.irq_set_affinity	= IS_ENABLED(CONFIG_SMP) ? stm32_exti_h_set_affinity : NULL,
 };
 
+static struct irq_chip stm32_exti_h_chip_direct = {
+	.name			= "stm32-exti-h-direct",
+	.irq_eoi		= irq_chip_eoi_parent,
+	.irq_ack		= irq_chip_ack_parent,
+	.irq_mask		= irq_chip_mask_parent,
+	.irq_unmask		= irq_chip_unmask_parent,
+	.irq_retrigger		= irq_chip_retrigger_hierarchy,
+	.irq_set_type		= irq_chip_set_type_parent,
+	.irq_set_wake		= stm32_exti_h_set_wake,
+	.flags			= IRQCHIP_MASK_ON_SUSPEND,
+	.irq_set_affinity	= IS_ENABLED(CONFIG_SMP) ? irq_chip_set_affinity_parent : NULL,
+};
+
 static int stm32_exti_h_domain_alloc(struct irq_domain *dm,
 				     unsigned int virq,
 				     unsigned int nr_irqs, void *data)
 {
 	struct stm32_exti_host_data *host_data = dm->host_data;
 	struct stm32_exti_chip_data *chip_data;
+	const struct stm32_desc_irq *desc;
 	struct irq_fwspec *fwspec = data;
 	struct irq_fwspec p_fwspec;
 	irq_hw_number_t hwirq;
-	int p_irq, bank;
+	int bank;
 
 	hwirq = fwspec->param[0];
 	bank  = hwirq / IRQS_PER_BANK;
 	chip_data = &host_data->chips_data[bank];
 
-	irq_domain_set_hwirq_and_chip(dm, virq, hwirq,
-				      &stm32_exti_h_chip, chip_data);
 
-	p_irq = stm32_exti_to_irq(host_data->drv_data, hwirq);
-	if (p_irq >= 0) {
+	desc = stm32_exti_get_desc(host_data->drv_data, hwirq);
+	if (!desc)
+		return -EINVAL;
+
+	irq_domain_set_hwirq_and_chip(dm, virq, hwirq, desc->chip,
+				      chip_data);
+	if (desc->irq_parent) {
 		p_fwspec.fwnode = dm->parent->fwnode;
 		p_fwspec.param_count = 3;
 		p_fwspec.param[0] = GIC_SPI;
-		p_fwspec.param[1] = p_irq;
+		p_fwspec.param[1] = desc->irq_parent;
 		p_fwspec.param[2] = IRQ_TYPE_LEVEL_HIGH;
 
 		return irq_domain_alloc_irqs_parent(dm, virq, 1, &p_fwspec);
diff --git a/drivers/irqchip/irq-ti-sci-inta.c b/drivers/irqchip/irq-ti-sci-inta.c
index 0a35499..532d0ae 100644
--- a/drivers/irqchip/irq-ti-sci-inta.c
+++ b/drivers/irqchip/irq-ti-sci-inta.c
@@ -2,12 +2,13 @@
 /*
  * Texas Instruments' K3 Interrupt Aggregator irqchip driver
  *
- * Copyright (C) 2018-2019 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2018-2019 Texas Instruments Incorporated - https://www.ti.com/
  *	Lokesh Vutla <lokeshvutla@ti.com>
  */
 
 #include <linux/err.h>
 #include <linux/io.h>
+#include <linux/irq.h>
 #include <linux/irqchip.h>
 #include <linux/irqdomain.h>
 #include <linux/interrupt.h>
@@ -83,6 +84,18 @@
  * @vint_mutex:		Mutex to protect vint_list
  * @base:		Base address of the memory mapped IO registers
  * @pdev:		Pointer to platform device.
+ * @ti_sci_id:		TI-SCI device identifier
+ * @unmapped_cnt:	Number of @unmapped_dev_ids entries
+ * @unmapped_dev_ids:	Pointer to an array of TI-SCI device identifiers of
+ *			unmapped event sources.
+ *			Unmapped Events are not part of the Global Event Map and
+ *			they are converted to Global event within INTA to be
+ *			received by the same INTA to generate an interrupt.
+ *			In case an interrupt request comes for a device which is
+ *			generating Unmapped Event, we must use the INTA's TI-SCI
+ *			device identifier in place of the source device
+ *			identifier to let sysfw know where it has to program the
+ *			Global Event number.
  */
 struct ti_sci_inta_irq_domain {
 	const struct ti_sci_handle *sci;
@@ -93,11 +106,38 @@
 	struct mutex vint_mutex;
 	void __iomem *base;
 	struct platform_device *pdev;
+	u32 ti_sci_id;
+
+	int unmapped_cnt;
+	u16 *unmapped_dev_ids;
 };
 
 #define to_vint_desc(e, i) container_of(e, struct ti_sci_inta_vint_desc, \
 					events[i])
 
+static u16 ti_sci_inta_get_dev_id(struct ti_sci_inta_irq_domain *inta, u32 hwirq)
+{
+	u16 dev_id = HWIRQ_TO_DEVID(hwirq);
+	int i;
+
+	if (inta->unmapped_cnt == 0)
+		return dev_id;
+
+	/*
+	 * For devices sending Unmapped Events we must use the INTA's TI-SCI
+	 * device identifier number to be able to convert it to a Global Event
+	 * and map it to an interrupt.
+	 */
+	for (i = 0; i < inta->unmapped_cnt; i++) {
+		if (dev_id == inta->unmapped_dev_ids[i]) {
+			dev_id = inta->ti_sci_id;
+			break;
+		}
+	}
+
+	return dev_id;
+}
+
 /**
  * ti_sci_inta_irq_handler() - Chained IRQ handler for the vint irqs
  * @desc:	Pointer to irq_desc corresponding to the irq
@@ -129,6 +169,37 @@
 }
 
 /**
+ * ti_sci_inta_xlate_irq() - Translate hwirq to parent's hwirq.
+ * @inta:	IRQ domain corresponding to Interrupt Aggregator
+ * @irq:	Hardware irq corresponding to the above irq domain
+ *
+ * Return parent irq number if translation is available else -ENOENT.
+ */
+static int ti_sci_inta_xlate_irq(struct ti_sci_inta_irq_domain *inta,
+				 u16 vint_id)
+{
+	struct device_node *np = dev_of_node(&inta->pdev->dev);
+	u32 base, parent_base, size;
+	const __be32 *range;
+	int len;
+
+	range = of_get_property(np, "ti,interrupt-ranges", &len);
+	if (!range)
+		return vint_id;
+
+	for (len /= sizeof(*range); len >= 3; len -= 3) {
+		base = be32_to_cpu(*range++);
+		parent_base = be32_to_cpu(*range++);
+		size = be32_to_cpu(*range++);
+
+		if (base <= vint_id && vint_id < base + size)
+			return vint_id - base + parent_base;
+	}
+
+	return -ENOENT;
+}
+
+/**
  * ti_sci_inta_alloc_parent_irq() - Allocate parent irq to Interrupt aggregator
  * @domain:	IRQ domain corresponding to Interrupt Aggregator
  *
@@ -139,30 +210,52 @@
 	struct ti_sci_inta_irq_domain *inta = domain->host_data;
 	struct ti_sci_inta_vint_desc *vint_desc;
 	struct irq_fwspec parent_fwspec;
+	struct device_node *parent_node;
 	unsigned int parent_virq;
+	int p_hwirq, ret;
 	u16 vint_id;
 
 	vint_id = ti_sci_get_free_resource(inta->vint);
 	if (vint_id == TI_SCI_RESOURCE_NULL)
 		return ERR_PTR(-EINVAL);
 
+	p_hwirq = ti_sci_inta_xlate_irq(inta, vint_id);
+	if (p_hwirq < 0) {
+		ret = p_hwirq;
+		goto free_vint;
+	}
+
 	vint_desc = kzalloc(sizeof(*vint_desc), GFP_KERNEL);
-	if (!vint_desc)
-		return ERR_PTR(-ENOMEM);
+	if (!vint_desc) {
+		ret = -ENOMEM;
+		goto free_vint;
+	}
 
 	vint_desc->domain = domain;
 	vint_desc->vint_id = vint_id;
 	INIT_LIST_HEAD(&vint_desc->list);
 
-	parent_fwspec.fwnode = of_node_to_fwnode(of_irq_find_parent(dev_of_node(&inta->pdev->dev)));
-	parent_fwspec.param_count = 2;
-	parent_fwspec.param[0] = inta->pdev->id;
-	parent_fwspec.param[1] = vint_desc->vint_id;
+	parent_node = of_irq_find_parent(dev_of_node(&inta->pdev->dev));
+	parent_fwspec.fwnode = of_node_to_fwnode(parent_node);
+
+	if (of_device_is_compatible(parent_node, "arm,gic-v3")) {
+		/* Parent is GIC */
+		parent_fwspec.param_count = 3;
+		parent_fwspec.param[0] = 0;
+		parent_fwspec.param[1] = p_hwirq - 32;
+		parent_fwspec.param[2] = IRQ_TYPE_LEVEL_HIGH;
+	} else {
+		/* Parent is Interrupt Router */
+		parent_fwspec.param_count = 1;
+		parent_fwspec.param[0] = p_hwirq;
+	}
 
 	parent_virq = irq_create_fwspec_mapping(&parent_fwspec);
 	if (parent_virq == 0) {
-		kfree(vint_desc);
-		return ERR_PTR(-EINVAL);
+		dev_err(&inta->pdev->dev, "Parent IRQ allocation failed\n");
+		ret = -EINVAL;
+		goto free_vint_desc;
+
 	}
 	vint_desc->parent_virq = parent_virq;
 
@@ -171,6 +264,11 @@
 					 ti_sci_inta_irq_handler, vint_desc);
 
 	return vint_desc;
+free_vint_desc:
+	kfree(vint_desc);
+free_vint:
+	ti_sci_release_resource(inta->vint, vint_id);
+	return ERR_PTR(ret);
 }
 
 /**
@@ -190,7 +288,7 @@
 	u16 dev_id, dev_index;
 	int err;
 
-	dev_id = HWIRQ_TO_DEVID(hwirq);
+	dev_id = ti_sci_inta_get_dev_id(inta, hwirq);
 	dev_index = HWIRQ_TO_IRQID(hwirq);
 
 	event_desc = &vint_desc->events[free_bit];
@@ -202,7 +300,7 @@
 
 	err = inta->sci->ops.rm_irq_ops.set_event_map(inta->sci,
 						      dev_id, dev_index,
-						      inta->pdev->id,
+						      inta->ti_sci_id,
 						      vint_desc->vint_id,
 						      event_desc->global_event,
 						      free_bit);
@@ -247,8 +345,8 @@
 	/* No free bits available. Allocate a new vint */
 	vint_desc = ti_sci_inta_alloc_parent_irq(domain);
 	if (IS_ERR(vint_desc)) {
-		mutex_unlock(&inta->vint_mutex);
-		return ERR_PTR(PTR_ERR(vint_desc));
+		event_desc = ERR_CAST(vint_desc);
+		goto unlock;
 	}
 
 	free_bit = find_first_zero_bit(vint_desc->event_map,
@@ -260,6 +358,7 @@
 	if (IS_ERR(event_desc))
 		clear_bit(free_bit, vint_desc->event_map);
 
+unlock:
 	mutex_unlock(&inta->vint_mutex);
 	return event_desc;
 }
@@ -290,15 +389,16 @@
 {
 	struct ti_sci_inta_vint_desc *vint_desc;
 	struct ti_sci_inta_irq_domain *inta;
+	u16 dev_id;
 
 	vint_desc = to_vint_desc(event_desc, event_desc->vint_bit);
 	inta = vint_desc->domain->host_data;
+	dev_id = ti_sci_inta_get_dev_id(inta, hwirq);
 	/* free event irq */
 	mutex_lock(&inta->vint_mutex);
 	inta->sci->ops.rm_irq_ops.free_event_map(inta->sci,
-						 HWIRQ_TO_DEVID(hwirq),
-						 HWIRQ_TO_IRQID(hwirq),
-						 inta->pdev->id,
+						 dev_id, HWIRQ_TO_IRQID(hwirq),
+						 inta->ti_sci_id,
 						 vint_desc->vint_id,
 						 event_desc->global_event,
 						 event_desc->vint_bit);
@@ -432,8 +532,6 @@
 	default:
 		return -EINVAL;
 	}
-
-	return -EINVAL;
 }
 
 static struct irq_chip ti_sci_inta_irq_chip = {
@@ -514,6 +612,41 @@
 	.chip	= &ti_sci_inta_msi_irq_chip,
 };
 
+static int ti_sci_inta_get_unmapped_sources(struct ti_sci_inta_irq_domain *inta)
+{
+	struct device *dev = &inta->pdev->dev;
+	struct device_node *node = dev_of_node(dev);
+	struct of_phandle_iterator it;
+	int count, err, ret, i;
+
+	count = of_count_phandle_with_args(node, "ti,unmapped-event-sources", NULL);
+	if (count <= 0)
+		return 0;
+
+	inta->unmapped_dev_ids = devm_kcalloc(dev, count,
+					      sizeof(*inta->unmapped_dev_ids),
+					      GFP_KERNEL);
+	if (!inta->unmapped_dev_ids)
+		return -ENOMEM;
+
+	i = 0;
+	of_for_each_phandle(&it, err, node, "ti,unmapped-event-sources", NULL, 0) {
+		u32 dev_id;
+
+		ret = of_property_read_u32(it.node, "ti,sci-dev-id", &dev_id);
+		if (ret) {
+			dev_err(dev, "ti,sci-dev-id read failure for %pOFf\n", it.node);
+			of_node_put(it.node);
+			return ret;
+		}
+		inta->unmapped_dev_ids[i++] = dev_id;
+	}
+
+	inta->unmapped_cnt = count;
+
+	return 0;
+}
+
 static int ti_sci_inta_irq_domain_probe(struct platform_device *pdev)
 {
 	struct irq_domain *parent_domain, *domain, *msi_domain;
@@ -540,29 +673,25 @@
 
 	inta->pdev = pdev;
 	inta->sci = devm_ti_sci_get_by_phandle(dev, "ti,sci");
-	if (IS_ERR(inta->sci)) {
-		ret = PTR_ERR(inta->sci);
-		if (ret != -EPROBE_DEFER)
-			dev_err(dev, "ti,sci read fail %d\n", ret);
-		inta->sci = NULL;
-		return ret;
-	}
+	if (IS_ERR(inta->sci))
+		return dev_err_probe(dev, PTR_ERR(inta->sci),
+				     "ti,sci read fail\n");
 
-	ret = of_property_read_u32(dev->of_node, "ti,sci-dev-id", &pdev->id);
+	ret = of_property_read_u32(dev->of_node, "ti,sci-dev-id", &inta->ti_sci_id);
 	if (ret) {
 		dev_err(dev, "missing 'ti,sci-dev-id' property\n");
 		return -EINVAL;
 	}
 
-	inta->vint = devm_ti_sci_get_of_resource(inta->sci, dev, pdev->id,
-						 "ti,sci-rm-range-vint");
+	inta->vint = devm_ti_sci_get_resource(inta->sci, dev, inta->ti_sci_id,
+					      TI_SCI_RESASG_SUBTYPE_IA_VINT);
 	if (IS_ERR(inta->vint)) {
 		dev_err(dev, "VINT resource allocation failed\n");
 		return PTR_ERR(inta->vint);
 	}
 
-	inta->global_event = devm_ti_sci_get_of_resource(inta->sci, dev, pdev->id,
-						"ti,sci-rm-range-global-event");
+	inta->global_event = devm_ti_sci_get_resource(inta->sci, dev, inta->ti_sci_id,
+						      TI_SCI_RESASG_SUBTYPE_GLOBAL_EVENT_SEVT);
 	if (IS_ERR(inta->global_event)) {
 		dev_err(dev, "Global event resource allocation failed\n");
 		return PTR_ERR(inta->global_event);
@@ -573,6 +702,10 @@
 	if (IS_ERR(inta->base))
 		return PTR_ERR(inta->base);
 
+	ret = ti_sci_inta_get_unmapped_sources(inta);
+	if (ret)
+		return ret;
+
 	domain = irq_domain_add_linear(dev_of_node(dev),
 				       ti_sci_get_num_resources(inta->vint),
 				       &ti_sci_inta_irq_domain_ops, inta);
@@ -593,6 +726,8 @@
 	INIT_LIST_HEAD(&inta->vint_list);
 	mutex_init(&inta->vint_mutex);
 
+	dev_info(dev, "Interrupt Aggregator domain %d created\n", inta->ti_sci_id);
+
 	return 0;
 }
 
@@ -611,6 +746,6 @@
 };
 module_platform_driver(ti_sci_inta_irq_domain_driver);
 
-MODULE_AUTHOR("Lokesh Vutla <lokeshvutla@ticom>");
+MODULE_AUTHOR("Lokesh Vutla <lokeshvutla@ti.com>");
 MODULE_DESCRIPTION("K3 Interrupt Aggregator driver over TI SCI protocol");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/irqchip/irq-ti-sci-intr.c b/drivers/irqchip/irq-ti-sci-intr.c
index 59d51a2..fe8fad2 100644
--- a/drivers/irqchip/irq-ti-sci-intr.c
+++ b/drivers/irqchip/irq-ti-sci-intr.c
@@ -2,7 +2,7 @@
 /*
  * Texas Instruments' K3 Interrupt Router irqchip driver
  *
- * Copyright (C) 2018-2019 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2018-2019 Texas Instruments Incorporated - https://www.ti.com/
  *	Lokesh Vutla <lokeshvutla@ti.com>
  */
 
@@ -17,29 +17,20 @@
 #include <linux/of_irq.h>
 #include <linux/soc/ti/ti_sci_protocol.h>
 
-#define TI_SCI_DEV_ID_MASK	0xffff
-#define TI_SCI_DEV_ID_SHIFT	16
-#define TI_SCI_IRQ_ID_MASK	0xffff
-#define TI_SCI_IRQ_ID_SHIFT	0
-#define HWIRQ_TO_DEVID(hwirq)	(((hwirq) >> (TI_SCI_DEV_ID_SHIFT)) & \
-				 (TI_SCI_DEV_ID_MASK))
-#define HWIRQ_TO_IRQID(hwirq)	((hwirq) & (TI_SCI_IRQ_ID_MASK))
-#define TO_HWIRQ(dev, index)	((((dev) & TI_SCI_DEV_ID_MASK) << \
-				 TI_SCI_DEV_ID_SHIFT) | \
-				((index) & TI_SCI_IRQ_ID_MASK))
-
 /**
  * struct ti_sci_intr_irq_domain - Structure representing a TISCI based
  *				   Interrupt Router IRQ domain.
  * @sci:	Pointer to TISCI handle
- * @dst_irq:	TISCI resource pointer representing GIC irq controller.
- * @dst_id:	TISCI device ID of the GIC irq controller.
+ * @out_irqs:	TISCI resource pointer representing INTR irqs.
+ * @dev:	Struct device pointer.
+ * @ti_sci_id:	TI-SCI device identifier
  * @type:	Specifies the trigger type supported by this Interrupt Router
  */
 struct ti_sci_intr_irq_domain {
 	const struct ti_sci_handle *sci;
-	struct ti_sci_resource *dst_irq;
-	u32 dst_id;
+	struct ti_sci_resource *out_irqs;
+	struct device *dev;
+	u32 ti_sci_id;
 	u32 type;
 };
 
@@ -70,16 +61,45 @@
 {
 	struct ti_sci_intr_irq_domain *intr = domain->host_data;
 
-	if (fwspec->param_count != 2)
+	if (fwspec->param_count != 1)
 		return -EINVAL;
 
-	*hwirq = TO_HWIRQ(fwspec->param[0], fwspec->param[1]);
+	*hwirq = fwspec->param[0];
 	*type = intr->type;
 
 	return 0;
 }
 
 /**
+ * ti_sci_intr_xlate_irq() - Translate hwirq to parent's hwirq.
+ * @intr:	IRQ domain corresponding to Interrupt Router
+ * @irq:	Hardware irq corresponding to the above irq domain
+ *
+ * Return parent irq number if translation is available else -ENOENT.
+ */
+static int ti_sci_intr_xlate_irq(struct ti_sci_intr_irq_domain *intr, u32 irq)
+{
+	struct device_node *np = dev_of_node(intr->dev);
+	u32 base, pbase, size, len;
+	const __be32 *range;
+
+	range = of_get_property(np, "ti,interrupt-ranges", &len);
+	if (!range)
+		return irq;
+
+	for (len /= sizeof(*range); len >= 3; len -= 3) {
+		base = be32_to_cpu(*range++);
+		pbase = be32_to_cpu(*range++);
+		size = be32_to_cpu(*range++);
+
+		if (base <= irq && irq < base + size)
+			return irq - base + pbase;
+	}
+
+	return -ENOENT;
+}
+
+/**
  * ti_sci_intr_irq_domain_free() - Free the specified IRQs from the domain.
  * @domain:	Domain to which the irqs belong
  * @virq:	Linux virtual IRQ to be freed.
@@ -89,66 +109,76 @@
 					unsigned int virq, unsigned int nr_irqs)
 {
 	struct ti_sci_intr_irq_domain *intr = domain->host_data;
-	struct irq_data *data, *parent_data;
-	u16 dev_id, irq_index;
+	struct irq_data *data;
+	int out_irq;
 
-	parent_data = irq_domain_get_irq_data(domain->parent, virq);
 	data = irq_domain_get_irq_data(domain, virq);
-	irq_index = HWIRQ_TO_IRQID(data->hwirq);
-	dev_id = HWIRQ_TO_DEVID(data->hwirq);
+	out_irq = (uintptr_t)data->chip_data;
 
-	intr->sci->ops.rm_irq_ops.free_irq(intr->sci, dev_id, irq_index,
-					   intr->dst_id, parent_data->hwirq);
-	ti_sci_release_resource(intr->dst_irq, parent_data->hwirq);
+	intr->sci->ops.rm_irq_ops.free_irq(intr->sci,
+					   intr->ti_sci_id, data->hwirq,
+					   intr->ti_sci_id, out_irq);
+	ti_sci_release_resource(intr->out_irqs, out_irq);
 	irq_domain_free_irqs_parent(domain, virq, 1);
 	irq_domain_reset_irq_data(data);
 }
 
 /**
- * ti_sci_intr_alloc_gic_irq() - Allocate GIC specific IRQ
+ * ti_sci_intr_alloc_parent_irq() - Allocate parent IRQ
  * @domain:	Pointer to the interrupt router IRQ domain
  * @virq:	Corresponding Linux virtual IRQ number
  * @hwirq:	Corresponding hwirq for the IRQ within this IRQ domain
  *
- * Returns 0 if all went well else appropriate error pointer.
+ * Returns intr output irq if all went well else appropriate error pointer.
  */
-static int ti_sci_intr_alloc_gic_irq(struct irq_domain *domain,
-				     unsigned int virq, u32 hwirq)
+static int ti_sci_intr_alloc_parent_irq(struct irq_domain *domain,
+					unsigned int virq, u32 hwirq)
 {
 	struct ti_sci_intr_irq_domain *intr = domain->host_data;
+	struct device_node *parent_node;
 	struct irq_fwspec fwspec;
-	u16 dev_id, irq_index;
-	u16 dst_irq;
-	int err;
+	int p_hwirq, err = 0;
+	u16 out_irq;
 
-	dev_id = HWIRQ_TO_DEVID(hwirq);
-	irq_index = HWIRQ_TO_IRQID(hwirq);
-
-	dst_irq = ti_sci_get_free_resource(intr->dst_irq);
-	if (dst_irq == TI_SCI_RESOURCE_NULL)
+	out_irq = ti_sci_get_free_resource(intr->out_irqs);
+	if (out_irq == TI_SCI_RESOURCE_NULL)
 		return -EINVAL;
 
-	fwspec.fwnode = domain->parent->fwnode;
-	fwspec.param_count = 3;
-	fwspec.param[0] = 0;	/* SPI */
-	fwspec.param[1] = dst_irq - 32; /* SPI offset */
-	fwspec.param[2] = intr->type;
+	p_hwirq = ti_sci_intr_xlate_irq(intr, out_irq);
+	if (p_hwirq < 0)
+		goto err_irqs;
+
+	parent_node = of_irq_find_parent(dev_of_node(intr->dev));
+	fwspec.fwnode = of_node_to_fwnode(parent_node);
+
+	if (of_device_is_compatible(parent_node, "arm,gic-v3")) {
+		/* Parent is GIC */
+		fwspec.param_count = 3;
+		fwspec.param[0] = 0;	/* SPI */
+		fwspec.param[1] = p_hwirq - 32; /* SPI offset */
+		fwspec.param[2] = intr->type;
+	} else {
+		/* Parent is Interrupt Router */
+		fwspec.param_count = 1;
+		fwspec.param[0] = p_hwirq;
+	}
 
 	err = irq_domain_alloc_irqs_parent(domain, virq, 1, &fwspec);
 	if (err)
 		goto err_irqs;
 
-	err = intr->sci->ops.rm_irq_ops.set_irq(intr->sci, dev_id, irq_index,
-						intr->dst_id, dst_irq);
+	err = intr->sci->ops.rm_irq_ops.set_irq(intr->sci,
+						intr->ti_sci_id, hwirq,
+						intr->ti_sci_id, out_irq);
 	if (err)
 		goto err_msg;
 
-	return 0;
+	return out_irq;
 
 err_msg:
 	irq_domain_free_irqs_parent(domain, virq, 1);
 err_irqs:
-	ti_sci_release_resource(intr->dst_irq, dst_irq);
+	ti_sci_release_resource(intr->out_irqs, out_irq);
 	return err;
 }
 
@@ -168,18 +198,19 @@
 	struct irq_fwspec *fwspec = data;
 	unsigned long hwirq;
 	unsigned int flags;
-	int err;
+	int err, out_irq;
 
 	err = ti_sci_intr_irq_domain_translate(domain, fwspec, &hwirq, &flags);
 	if (err)
 		return err;
 
-	err = ti_sci_intr_alloc_gic_irq(domain, virq, hwirq);
-	if (err)
-		return err;
+	out_irq = ti_sci_intr_alloc_parent_irq(domain, virq, hwirq);
+	if (out_irq < 0)
+		return out_irq;
 
 	irq_domain_set_hwirq_and_chip(domain, virq, hwirq,
-				      &ti_sci_intr_irq_chip, NULL);
+				      &ti_sci_intr_irq_chip,
+				      (void *)(uintptr_t)out_irq);
 
 	return 0;
 }
@@ -214,6 +245,7 @@
 	if (!intr)
 		return -ENOMEM;
 
+	intr->dev = dev;
 	ret = of_property_read_u32(dev_of_node(dev), "ti,intr-trigger-type",
 				   &intr->type);
 	if (ret) {
@@ -222,27 +254,23 @@
 	}
 
 	intr->sci = devm_ti_sci_get_by_phandle(dev, "ti,sci");
-	if (IS_ERR(intr->sci)) {
-		ret = PTR_ERR(intr->sci);
-		if (ret != -EPROBE_DEFER)
-			dev_err(dev, "ti,sci read fail %d\n", ret);
-		intr->sci = NULL;
-		return ret;
-	}
+	if (IS_ERR(intr->sci))
+		return dev_err_probe(dev, PTR_ERR(intr->sci),
+				     "ti,sci read fail\n");
 
-	ret = of_property_read_u32(dev_of_node(dev), "ti,sci-dst-id",
-				   &intr->dst_id);
+	ret = of_property_read_u32(dev_of_node(dev), "ti,sci-dev-id",
+				   &intr->ti_sci_id);
 	if (ret) {
-		dev_err(dev, "missing 'ti,sci-dst-id' property\n");
+		dev_err(dev, "missing 'ti,sci-dev-id' property\n");
 		return -EINVAL;
 	}
 
-	intr->dst_irq = devm_ti_sci_get_of_resource(intr->sci, dev,
-						    intr->dst_id,
-						    "ti,sci-rm-range-girq");
-	if (IS_ERR(intr->dst_irq)) {
+	intr->out_irqs = devm_ti_sci_get_resource(intr->sci, dev,
+						  intr->ti_sci_id,
+						  TI_SCI_RESASG_SUBTYPE_IR_OUTPUT);
+	if (IS_ERR(intr->out_irqs)) {
 		dev_err(dev, "Destination irq resource allocation failed\n");
-		return PTR_ERR(intr->dst_irq);
+		return PTR_ERR(intr->out_irqs);
 	}
 
 	domain = irq_domain_add_hierarchy(parent_domain, 0, 0, dev_of_node(dev),
@@ -252,6 +280,8 @@
 		return -ENOMEM;
 	}
 
+	dev_info(dev, "Interrupt Router %d domain created\n", intr->ti_sci_id);
+
 	return 0;
 }
 
diff --git a/drivers/irqchip/irq-vic.c b/drivers/irqchip/irq-vic.c
index f3f20a3..e460363 100644
--- a/drivers/irqchip/irq-vic.c
+++ b/drivers/irqchip/irq-vic.c
@@ -27,7 +27,10 @@
 
 #define VIC_IRQ_STATUS			0x00
 #define VIC_FIQ_STATUS			0x04
+#define VIC_RAW_STATUS			0x08
 #define VIC_INT_SELECT			0x0c	/* 1 = FIQ, 0 = IRQ */
+#define VIC_INT_ENABLE			0x10	/* 1 = enable, 0 = disable */
+#define VIC_INT_ENABLE_CLEAR		0x14
 #define VIC_INT_SOFT			0x18
 #define VIC_INT_SOFT_CLEAR		0x1c
 #define VIC_PROTECT			0x20
@@ -428,7 +431,7 @@
 	vic_register(base, 0, irq_start, vic_sources, 0, node);
 }
 
-void __init __vic_init(void __iomem *base, int parent_irq, int irq_start,
+static void __init __vic_init(void __iomem *base, int parent_irq, int irq_start,
 			      u32 vic_sources, u32 resume_sources,
 			      struct device_node *node)
 {
@@ -452,7 +455,7 @@
 		return;
 	default:
 		printk(KERN_WARNING "VIC: unknown vendor, continuing anyways\n");
-		/* fall through */
+		fallthrough;
 	case AMBA_VENDOR_ARM:
 		break;
 	}
@@ -481,27 +484,6 @@
 	__vic_init(base, 0, irq_start, vic_sources, resume_sources, NULL);
 }
 
-/**
- * vic_init_cascaded() - initialise a cascaded vectored interrupt controller
- * @base: iomem base address
- * @parent_irq: the parent IRQ we're cascaded off
- * @vic_sources: bitmask of interrupt sources to allow
- * @resume_sources: bitmask of interrupt sources to allow for resume
- *
- * This returns the base for the new interrupts or negative on error.
- */
-int __init vic_init_cascaded(void __iomem *base, unsigned int parent_irq,
-			      u32 vic_sources, u32 resume_sources)
-{
-	struct vic_device *v;
-
-	v = &vic_devices[vic_id];
-	__vic_init(base, parent_irq, 0, vic_sources, resume_sources, NULL);
-	/* Return out acquired base */
-	return v->irq;
-}
-EXPORT_SYMBOL_GPL(vic_init_cascaded);
-
 #ifdef CONFIG_OF
 static int __init vic_of_init(struct device_node *node,
 			      struct device_node *parent)
@@ -509,9 +491,7 @@
 	void __iomem *regs;
 	u32 interrupt_mask = ~0;
 	u32 wakeup_mask = ~0;
-
-	if (WARN(parent, "non-root VICs are not supported"))
-		return -EINVAL;
+	int parent_irq;
 
 	regs = of_iomap(node, 0);
 	if (WARN_ON(!regs))
@@ -519,11 +499,14 @@
 
 	of_property_read_u32(node, "valid-mask", &interrupt_mask);
 	of_property_read_u32(node, "valid-wakeup-mask", &wakeup_mask);
+	parent_irq = of_irq_get(node, 0);
+	if (parent_irq < 0)
+		parent_irq = 0;
 
 	/*
 	 * Passing 0 as first IRQ makes the simple domain allocate descriptors
 	 */
-	__vic_init(regs, 0, 0, interrupt_mask, wakeup_mask, node);
+	__vic_init(regs, parent_irq, 0, interrupt_mask, wakeup_mask, node);
 
 	return 0;
 }
diff --git a/drivers/irqchip/irq-xilinx-intc.c b/drivers/irqchip/irq-xilinx-intc.c
index e3043de..1d3d273 100644
--- a/drivers/irqchip/irq-xilinx-intc.c
+++ b/drivers/irqchip/irq-xilinx-intc.c
@@ -38,29 +38,31 @@
 	void		__iomem *base;
 	struct		irq_domain *root_domain;
 	u32		intr_mask;
+	u32		nr_irq;
 };
 
-static struct xintc_irq_chip *xintc_irqc;
+static struct xintc_irq_chip *primary_intc;
 
-static void xintc_write(int reg, u32 data)
+static void xintc_write(struct xintc_irq_chip *irqc, int reg, u32 data)
 {
 	if (static_branch_unlikely(&xintc_is_be))
-		iowrite32be(data, xintc_irqc->base + reg);
+		iowrite32be(data, irqc->base + reg);
 	else
-		iowrite32(data, xintc_irqc->base + reg);
+		iowrite32(data, irqc->base + reg);
 }
 
-static unsigned int xintc_read(int reg)
+static u32 xintc_read(struct xintc_irq_chip *irqc, int reg)
 {
 	if (static_branch_unlikely(&xintc_is_be))
-		return ioread32be(xintc_irqc->base + reg);
+		return ioread32be(irqc->base + reg);
 	else
-		return ioread32(xintc_irqc->base + reg);
+		return ioread32(irqc->base + reg);
 }
 
 static void intc_enable_or_unmask(struct irq_data *d)
 {
-	unsigned long mask = 1 << d->hwirq;
+	struct xintc_irq_chip *irqc = irq_data_get_irq_chip_data(d);
+	unsigned long mask = BIT(d->hwirq);
 
 	pr_debug("irq-xilinx: enable_or_unmask: %ld\n", d->hwirq);
 
@@ -69,30 +71,35 @@
 	 * acks the irq before calling the interrupt handler
 	 */
 	if (irqd_is_level_type(d))
-		xintc_write(IAR, mask);
+		xintc_write(irqc, IAR, mask);
 
-	xintc_write(SIE, mask);
+	xintc_write(irqc, SIE, mask);
 }
 
 static void intc_disable_or_mask(struct irq_data *d)
 {
+	struct xintc_irq_chip *irqc = irq_data_get_irq_chip_data(d);
+
 	pr_debug("irq-xilinx: disable: %ld\n", d->hwirq);
-	xintc_write(CIE, 1 << d->hwirq);
+	xintc_write(irqc, CIE, BIT(d->hwirq));
 }
 
 static void intc_ack(struct irq_data *d)
 {
+	struct xintc_irq_chip *irqc = irq_data_get_irq_chip_data(d);
+
 	pr_debug("irq-xilinx: ack: %ld\n", d->hwirq);
-	xintc_write(IAR, 1 << d->hwirq);
+	xintc_write(irqc, IAR, BIT(d->hwirq));
 }
 
 static void intc_mask_ack(struct irq_data *d)
 {
-	unsigned long mask = 1 << d->hwirq;
+	struct xintc_irq_chip *irqc = irq_data_get_irq_chip_data(d);
+	unsigned long mask = BIT(d->hwirq);
 
 	pr_debug("irq-xilinx: disable_and_ack: %ld\n", d->hwirq);
-	xintc_write(CIE, mask);
-	xintc_write(IAR, mask);
+	xintc_write(irqc, CIE, mask);
+	xintc_write(irqc, IAR, mask);
 }
 
 static struct irq_chip intc_dev = {
@@ -103,13 +110,28 @@
 	.irq_mask_ack = intc_mask_ack,
 };
 
+static unsigned int xintc_get_irq_local(struct xintc_irq_chip *irqc)
+{
+	unsigned int irq = 0;
+	u32 hwirq;
+
+	hwirq = xintc_read(irqc, IVR);
+	if (hwirq != -1U)
+		irq = irq_find_mapping(irqc->root_domain, hwirq);
+
+	pr_debug("irq-xilinx: hwirq=%d, irq=%d\n", hwirq, irq);
+
+	return irq;
+}
+
 unsigned int xintc_get_irq(void)
 {
-	unsigned int hwirq, irq = -1;
+	unsigned int irq = -1;
+	u32 hwirq;
 
-	hwirq = xintc_read(IVR);
+	hwirq = xintc_read(primary_intc, IVR);
 	if (hwirq != -1U)
-		irq = irq_find_mapping(xintc_irqc->root_domain, hwirq);
+		irq = irq_find_mapping(primary_intc->root_domain, hwirq);
 
 	pr_debug("irq-xilinx: hwirq=%d, irq=%d\n", hwirq, irq);
 
@@ -118,15 +140,18 @@
 
 static int xintc_map(struct irq_domain *d, unsigned int irq, irq_hw_number_t hw)
 {
-	if (xintc_irqc->intr_mask & (1 << hw)) {
+	struct xintc_irq_chip *irqc = d->host_data;
+
+	if (irqc->intr_mask & BIT(hw)) {
 		irq_set_chip_and_handler_name(irq, &intc_dev,
-						handle_edge_irq, "edge");
+					      handle_edge_irq, "edge");
 		irq_clear_status_flags(irq, IRQ_LEVEL);
 	} else {
 		irq_set_chip_and_handler_name(irq, &intc_dev,
-						handle_level_irq, "level");
+					      handle_level_irq, "level");
 		irq_set_status_flags(irq, IRQ_LEVEL);
 	}
+	irq_set_chip_data(irq, irqc);
 	return 0;
 }
 
@@ -138,12 +163,14 @@
 static void xil_intc_irq_handler(struct irq_desc *desc)
 {
 	struct irq_chip *chip = irq_desc_get_chip(desc);
+	struct xintc_irq_chip *irqc;
 	u32 pending;
 
+	irqc = irq_data_get_irq_handler_data(&desc->irq_data);
 	chained_irq_enter(chip, desc);
 	do {
-		pending = xintc_get_irq();
-		if (pending == -1U)
+		pending = xintc_get_irq_local(irqc);
+		if (pending == 0)
 			break;
 		generic_handle_irq(pending);
 	} while (true);
@@ -153,28 +180,19 @@
 static int __init xilinx_intc_of_init(struct device_node *intc,
 					     struct device_node *parent)
 {
-	u32 nr_irq;
-	int ret, irq;
 	struct xintc_irq_chip *irqc;
-
-	if (xintc_irqc) {
-		pr_err("irq-xilinx: Multiple instances aren't supported\n");
-		return -EINVAL;
-	}
+	int ret, irq;
 
 	irqc = kzalloc(sizeof(*irqc), GFP_KERNEL);
 	if (!irqc)
 		return -ENOMEM;
-
-	xintc_irqc = irqc;
-
 	irqc->base = of_iomap(intc, 0);
 	BUG_ON(!irqc->base);
 
-	ret = of_property_read_u32(intc, "xlnx,num-intr-inputs", &nr_irq);
+	ret = of_property_read_u32(intc, "xlnx,num-intr-inputs", &irqc->nr_irq);
 	if (ret < 0) {
 		pr_err("irq-xilinx: unable to read xlnx,num-intr-inputs\n");
-		goto err_alloc;
+		goto error;
 	}
 
 	ret = of_property_read_u32(intc, "xlnx,kind-of-intr", &irqc->intr_mask);
@@ -183,34 +201,35 @@
 		irqc->intr_mask = 0;
 	}
 
-	if (irqc->intr_mask >> nr_irq)
+	if (irqc->intr_mask >> irqc->nr_irq)
 		pr_warn("irq-xilinx: mismatch in kind-of-intr param\n");
 
 	pr_info("irq-xilinx: %pOF: num_irq=%d, edge=0x%x\n",
-		intc, nr_irq, irqc->intr_mask);
+		intc, irqc->nr_irq, irqc->intr_mask);
 
 
 	/*
 	 * Disable all external interrupts until they are
 	 * explicity requested.
 	 */
-	xintc_write(IER, 0);
+	xintc_write(irqc, IER, 0);
 
 	/* Acknowledge any pending interrupts just in case. */
-	xintc_write(IAR, 0xffffffff);
+	xintc_write(irqc, IAR, 0xffffffff);
 
 	/* Turn on the Master Enable. */
-	xintc_write(MER, MER_HIE | MER_ME);
-	if (!(xintc_read(MER) & (MER_HIE | MER_ME))) {
+	xintc_write(irqc, MER, MER_HIE | MER_ME);
+	if (xintc_read(irqc, MER) != (MER_HIE | MER_ME)) {
 		static_branch_enable(&xintc_is_be);
-		xintc_write(MER, MER_HIE | MER_ME);
+		xintc_write(irqc, MER, MER_HIE | MER_ME);
 	}
 
-	irqc->root_domain = irq_domain_add_linear(intc, nr_irq,
+	irqc->root_domain = irq_domain_add_linear(intc, irqc->nr_irq,
 						  &xintc_irq_domain_ops, irqc);
 	if (!irqc->root_domain) {
 		pr_err("irq-xilinx: Unable to create IRQ domain\n");
-		goto err_alloc;
+		ret = -EINVAL;
+		goto error;
 	}
 
 	if (parent) {
@@ -222,16 +241,17 @@
 		} else {
 			pr_err("irq-xilinx: interrupts property not in DT\n");
 			ret = -EINVAL;
-			goto err_alloc;
+			goto error;
 		}
 	} else {
-		irq_set_default_host(irqc->root_domain);
+		primary_intc = irqc;
+		irq_set_default_host(primary_intc->root_domain);
 	}
 
 	return 0;
 
-err_alloc:
-	xintc_irqc = NULL;
+error:
+	iounmap(irqc->base);
 	kfree(irqc);
 	return ret;
 
diff --git a/drivers/irqchip/irq-zevio.c b/drivers/irqchip/irq-zevio.c
index 5a7efeb..84163f1 100644
--- a/drivers/irqchip/irq-zevio.c
+++ b/drivers/irqchip/irq-zevio.c
@@ -51,7 +51,7 @@
 	while (readl(zevio_irq_io + IO_STATUS)) {
 		irqnr = readl(zevio_irq_io + IO_CURRENT);
 		handle_domain_irq(zevio_irq_domain, irqnr, regs);
-	};
+	}
 }
 
 static void __init zevio_init_irq_base(void __iomem *base)
diff --git a/drivers/irqchip/irqchip.c b/drivers/irqchip/irqchip.c
index 2b35e68..3570f0a 100644
--- a/drivers/irqchip/irqchip.c
+++ b/drivers/irqchip/irqchip.c
@@ -10,8 +10,10 @@
 
 #include <linux/acpi.h>
 #include <linux/init.h>
+#include <linux/of_device.h>
 #include <linux/of_irq.h>
 #include <linux/irqchip.h>
+#include <linux/platform_device.h>
 
 /*
  * This special of_device_id is the sentinel at the end of the
@@ -20,7 +22,7 @@
  * special section.
  */
 static const struct of_device_id
-irqchip_of_match_end __used __section(__irqchip_of_table_end);
+irqchip_of_match_end __used __section("__irqchip_of_table_end");
 
 extern struct of_device_id __irqchip_of_table[];
 
@@ -29,3 +31,30 @@
 	of_irq_init(__irqchip_of_table);
 	acpi_probe_device_table(irqchip);
 }
+
+int platform_irqchip_probe(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	struct device_node *par_np = of_irq_find_parent(np);
+	of_irq_init_cb_t irq_init_cb = of_device_get_match_data(&pdev->dev);
+
+	if (!irq_init_cb)
+		return -EINVAL;
+
+	if (par_np == np)
+		par_np = NULL;
+
+	/*
+	 * If there's a parent interrupt controller and  none of the parent irq
+	 * domains have been registered, that means the parent interrupt
+	 * controller has not been initialized yet.  it's not time for this
+	 * interrupt controller to initialize. So, defer probe of this
+	 * interrupt controller. The actual initialization callback of this
+	 * interrupt controller can check for specific domains as necessary.
+	 */
+	if (par_np && !irq_find_matching_host(par_np, DOMAIN_BUS_ANY))
+		return -EPROBE_DEFER;
+
+	return irq_init_cb(np, par_np);
+}
+EXPORT_SYMBOL_GPL(platform_irqchip_probe);
diff --git a/drivers/irqchip/qcom-irq-combiner.c b/drivers/irqchip/qcom-irq-combiner.c
index abfe592..aa54bfc 100644
--- a/drivers/irqchip/qcom-irq-combiner.c
+++ b/drivers/irqchip/qcom-irq-combiner.c
@@ -33,7 +33,7 @@
 	int                 parent_irq;
 	u32                 nirqs;
 	u32                 nregs;
-	struct combiner_reg regs[0];
+	struct combiner_reg regs[];
 };
 
 static inline int irq_nr(u32 reg, u32 bit)
diff --git a/drivers/irqchip/qcom-pdc.c b/drivers/irqchip/qcom-pdc.c
index faa7d61..5dc63c2 100644
--- a/drivers/irqchip/qcom-pdc.c
+++ b/drivers/irqchip/qcom-pdc.c
@@ -1,10 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * Copyright (c) 2017-2018, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2017-2019, The Linux Foundation. All rights reserved.
  */
 
 #include <linux/err.h>
 #include <linux/init.h>
+#include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/irqchip.h>
 #include <linux/irqdomain.h>
@@ -13,12 +14,13 @@
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_device.h>
+#include <linux/soc/qcom/irq.h>
 #include <linux/spinlock.h>
-#include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/types.h>
 
-#define PDC_MAX_IRQS		126
+#define PDC_MAX_IRQS		168
+#define PDC_MAX_GPIO_IRQS	256
 
 #define CLEAR_INTR(reg, intr)	(reg & ~(1 << intr))
 #define ENABLE_INTR(reg, intr)	(reg | (1 << intr))
@@ -26,6 +28,8 @@
 #define IRQ_ENABLE_BANK		0x10
 #define IRQ_i_CFG		0x110
 
+#define PDC_NO_PARENT_IRQ	~0UL
+
 struct pdc_pin_region {
 	u32 pin_base;
 	u32 parent_base;
@@ -47,6 +51,26 @@
 	return readl_relaxed(pdc_base + reg + i * sizeof(u32));
 }
 
+static int qcom_pdc_gic_get_irqchip_state(struct irq_data *d,
+					  enum irqchip_irq_state which,
+					  bool *state)
+{
+	if (d->hwirq == GPIO_NO_WAKE_IRQ)
+		return 0;
+
+	return irq_chip_get_parent_state(d, which, state);
+}
+
+static int qcom_pdc_gic_set_irqchip_state(struct irq_data *d,
+					  enum irqchip_irq_state which,
+					  bool value)
+{
+	if (d->hwirq == GPIO_NO_WAKE_IRQ)
+		return 0;
+
+	return irq_chip_set_parent_state(d, which, value);
+}
+
 static void pdc_enable_intr(struct irq_data *d, bool on)
 {
 	int pin_out = d->hwirq;
@@ -63,15 +87,37 @@
 	raw_spin_unlock(&pdc_lock);
 }
 
+static void qcom_pdc_gic_disable(struct irq_data *d)
+{
+	if (d->hwirq == GPIO_NO_WAKE_IRQ)
+		return;
+
+	pdc_enable_intr(d, false);
+	irq_chip_disable_parent(d);
+}
+
+static void qcom_pdc_gic_enable(struct irq_data *d)
+{
+	if (d->hwirq == GPIO_NO_WAKE_IRQ)
+		return;
+
+	pdc_enable_intr(d, true);
+	irq_chip_enable_parent(d);
+}
+
 static void qcom_pdc_gic_mask(struct irq_data *d)
 {
-	pdc_enable_intr(d, false);
+	if (d->hwirq == GPIO_NO_WAKE_IRQ)
+		return;
+
 	irq_chip_mask_parent(d);
 }
 
 static void qcom_pdc_gic_unmask(struct irq_data *d)
 {
-	pdc_enable_intr(d, true);
+	if (d->hwirq == GPIO_NO_WAKE_IRQ)
+		return;
+
 	irq_chip_unmask_parent(d);
 }
 
@@ -113,6 +159,11 @@
 {
 	int pin_out = d->hwirq;
 	enum pdc_irq_config_bits pdc_type;
+	enum pdc_irq_config_bits old_pdc_type;
+	int ret;
+
+	if (pin_out == GPIO_NO_WAKE_IRQ)
+		return 0;
 
 	switch (type) {
 	case IRQ_TYPE_EDGE_RISING:
@@ -138,9 +189,26 @@
 		return -EINVAL;
 	}
 
+	old_pdc_type = pdc_reg_read(IRQ_i_CFG, pin_out);
 	pdc_reg_write(IRQ_i_CFG, pin_out, pdc_type);
 
-	return irq_chip_set_type_parent(d, type);
+	ret = irq_chip_set_type_parent(d, type);
+	if (ret)
+		return ret;
+
+	/*
+	 * When we change types the PDC can give a phantom interrupt.
+	 * Clear it.  Specifically the phantom shows up when reconfiguring
+	 * polarity of interrupt without changing the state of the signal
+	 * but let's be consistent and clear it always.
+	 *
+	 * Doing this works because we have IRQCHIP_SET_TYPE_MASKED so the
+	 * interrupt will be cleared before the rest of the system sees it.
+	 */
+	if (old_pdc_type != pdc_type)
+		irq_chip_set_parent_state(d, IRQCHIP_STATE_PENDING, false);
+
+	return 0;
 }
 
 static struct irq_chip qcom_pdc_gic_chip = {
@@ -148,11 +216,16 @@
 	.irq_eoi		= irq_chip_eoi_parent,
 	.irq_mask		= qcom_pdc_gic_mask,
 	.irq_unmask		= qcom_pdc_gic_unmask,
+	.irq_disable		= qcom_pdc_gic_disable,
+	.irq_enable		= qcom_pdc_gic_enable,
+	.irq_get_irqchip_state	= qcom_pdc_gic_get_irqchip_state,
+	.irq_set_irqchip_state	= qcom_pdc_gic_set_irqchip_state,
 	.irq_retrigger		= irq_chip_retrigger_hierarchy,
 	.irq_set_type		= qcom_pdc_gic_set_type,
 	.flags			= IRQCHIP_MASK_ON_SUSPEND |
 				  IRQCHIP_SET_TYPE_MASKED |
-				  IRQCHIP_SKIP_SET_WAKE,
+				  IRQCHIP_SKIP_SET_WAKE |
+				  IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND,
 	.irq_set_vcpu_affinity	= irq_chip_set_vcpu_affinity_parent,
 	.irq_set_affinity	= irq_chip_set_affinity_parent,
 };
@@ -169,8 +242,7 @@
 			return (region->parent_base + pin - region->pin_base);
 	}
 
-	WARN_ON(1);
-	return ~0UL;
+	return PDC_NO_PARENT_IRQ;
 }
 
 static int qcom_pdc_translate(struct irq_domain *d, struct irq_fwspec *fwspec,
@@ -199,17 +271,17 @@
 
 	ret = qcom_pdc_translate(domain, fwspec, &hwirq, &type);
 	if (ret)
-		return -EINVAL;
-
-	parent_hwirq = get_parent_hwirq(hwirq);
-	if (parent_hwirq == ~0UL)
-		return -EINVAL;
+		return ret;
 
 	ret  = irq_domain_set_hwirq_and_chip(domain, virq, hwirq,
 					     &qcom_pdc_gic_chip, NULL);
 	if (ret)
 		return ret;
 
+	parent_hwirq = get_parent_hwirq(hwirq);
+	if (parent_hwirq == PDC_NO_PARENT_IRQ)
+		return 0;
+
 	if (type & IRQ_TYPE_EDGE_BOTH)
 		type = IRQ_TYPE_EDGE_RISING;
 
@@ -232,9 +304,64 @@
 	.free		= irq_domain_free_irqs_common,
 };
 
+static int qcom_pdc_gpio_alloc(struct irq_domain *domain, unsigned int virq,
+			       unsigned int nr_irqs, void *data)
+{
+	struct irq_fwspec *fwspec = data;
+	struct irq_fwspec parent_fwspec;
+	irq_hw_number_t hwirq, parent_hwirq;
+	unsigned int type;
+	int ret;
+
+	ret = qcom_pdc_translate(domain, fwspec, &hwirq, &type);
+	if (ret)
+		return ret;
+
+	ret = irq_domain_set_hwirq_and_chip(domain, virq, hwirq,
+					    &qcom_pdc_gic_chip, NULL);
+	if (ret)
+		return ret;
+
+	if (hwirq == GPIO_NO_WAKE_IRQ)
+		return 0;
+
+	parent_hwirq = get_parent_hwirq(hwirq);
+	if (parent_hwirq == PDC_NO_PARENT_IRQ)
+		return 0;
+
+	if (type & IRQ_TYPE_EDGE_BOTH)
+		type = IRQ_TYPE_EDGE_RISING;
+
+	if (type & IRQ_TYPE_LEVEL_MASK)
+		type = IRQ_TYPE_LEVEL_HIGH;
+
+	parent_fwspec.fwnode      = domain->parent->fwnode;
+	parent_fwspec.param_count = 3;
+	parent_fwspec.param[0]    = 0;
+	parent_fwspec.param[1]    = parent_hwirq;
+	parent_fwspec.param[2]    = type;
+
+	return irq_domain_alloc_irqs_parent(domain, virq, nr_irqs,
+					    &parent_fwspec);
+}
+
+static int qcom_pdc_gpio_domain_select(struct irq_domain *d,
+				       struct irq_fwspec *fwspec,
+				       enum irq_domain_bus_token bus_token)
+{
+	return bus_token == DOMAIN_BUS_WAKEUP;
+}
+
+static const struct irq_domain_ops qcom_pdc_gpio_ops = {
+	.select		= qcom_pdc_gpio_domain_select,
+	.alloc		= qcom_pdc_gpio_alloc,
+	.free		= irq_domain_free_irqs_common,
+};
+
 static int pdc_setup_pin_mapping(struct device_node *np)
 {
-	int ret, n;
+	int ret, n, i;
+	u32 irq_index, reg_index, val;
 
 	n = of_property_count_elems_of_size(np, "qcom,pdc-ranges", sizeof(u32));
 	if (n <= 0 || n % 3)
@@ -263,6 +390,14 @@
 						 &pdc_region[n].cnt);
 		if (ret)
 			return ret;
+
+		for (i = 0; i < pdc_region[n].cnt; i++) {
+			reg_index = (i + pdc_region[n].pin_base) >> 5;
+			irq_index = (i + pdc_region[n].pin_base) & 0x1f;
+			val = pdc_reg_read(IRQ_ENABLE_BANK, reg_index);
+			val &= ~BIT(irq_index);
+			pdc_reg_write(IRQ_ENABLE_BANK, reg_index, val);
+		}
 	}
 
 	return 0;
@@ -270,7 +405,7 @@
 
 static int qcom_pdc_init(struct device_node *node, struct device_node *parent)
 {
-	struct irq_domain *parent_domain, *pdc_domain;
+	struct irq_domain *parent_domain, *pdc_domain, *pdc_gpio_domain;
 	int ret;
 
 	pdc_base = of_iomap(node, 0);
@@ -301,12 +436,27 @@
 		goto fail;
 	}
 
+	pdc_gpio_domain = irq_domain_create_hierarchy(parent_domain,
+					IRQ_DOMAIN_FLAG_QCOM_PDC_WAKEUP,
+					PDC_MAX_GPIO_IRQS,
+					of_fwnode_handle(node),
+					&qcom_pdc_gpio_ops, NULL);
+	if (!pdc_gpio_domain) {
+		pr_err("%pOF: PDC domain add failed for GPIO domain\n", node);
+		ret = -ENOMEM;
+		goto remove;
+	}
+
+	irq_domain_update_bus_token(pdc_gpio_domain, DOMAIN_BUS_WAKEUP);
+
 	return 0;
 
+remove:
+	irq_domain_remove(pdc_domain);
 fail:
 	kfree(pdc_region);
 	iounmap(pdc_base);
 	return ret;
 }
 
-IRQCHIP_DECLARE(pdc_sdm845, "qcom,sdm845-pdc", qcom_pdc_init);
+IRQCHIP_DECLARE(qcom_pdc, "qcom,pdc", qcom_pdc_init);