Merge tag 'irq-core-2024-11-18' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull interrupt subsystem updates from Thomas Gleixner:
 "Tree wide:

   - Make nr_irqs static to the core code and provide accessor functions
     to remove existing and prevent future aliasing problems with local
     variables or function arguments of the same name.

  Core code:

   - Prevent freeing an interrupt in the devres code which is not
     managed by devres in the first place.

   - Use seq_put_decimal_ull_width() for decimal values output in
     /proc/interrupts which increases performance significantly as it
     avoids parsing the format strings over and over.

   - Optimize raising the timer and hrtimer soft interrupts by using the
     'set bit only' variants instead of the combined version which
     checks whether ksoftirqd should be woken up. The latter is a
     pointless exercise as both soft interrupts are raised in the
     context of the timer interrupt and therefore never wake up
     ksoftirqd.

   - Delegate timer/hrtimer soft interrupt processing to a dedicated
     thread on RT.

     Timer and hrtimer soft interrupts are always processed in ksoftirqd
     on RT enabled kernels. This can lead to high latencies when other
     soft interrupts are delegated to ksoftirqd as well.

     The separate thread allows to run them seperately under a RT
     scheduling policy to reduce the latency overhead.

  Drivers:

   - New drivers or extensions of existing drivers to support Renesas
     RZ/V2H(P), Aspeed AST27XX, T-HEAD C900 and ATMEL sam9x7 interrupt
     chips

   - Support for multi-cluster GICs on MIPS.

     MIPS CPUs can come with multiple CPU clusters, where each CPU
     cluster has its own GIC (Generic Interrupt Controller). This
     requires to access the GIC of a remote cluster through a redirect
     register block.

     This is encapsulated into a set of helper functions to keep the
     complexity out of the actual code paths which handle the GIC
     details.

   - Support for encrypted guests in the ARM GICV3 ITS driver

     The ITS page needs to be shared with the hypervisor and therefore
     must be decrypted.

   - Small cleanups and fixes all over the place"

* tag 'irq-core-2024-11-18' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (50 commits)
  irqchip/riscv-aplic: Prevent crash when MSI domain is missing
  genirq/proc: Use seq_put_decimal_ull_width() for decimal values
  softirq: Use a dedicated thread for timer wakeups on PREEMPT_RT.
  timers: Use __raise_softirq_irqoff() to raise the softirq.
  hrtimer: Use __raise_softirq_irqoff() to raise the softirq
  riscv: defconfig: Enable T-HEAD C900 ACLINT SSWI drivers
  irqchip: Add T-HEAD C900 ACLINT SSWI driver
  dt-bindings: interrupt-controller: Add T-HEAD C900 ACLINT SSWI device
  irqchip/stm32mp-exti: Use of_property_present() for non-boolean properties
  irqchip/mips-gic: Fix selection of GENERIC_IRQ_EFFECTIVE_AFF_MASK
  irqchip/mips-gic: Prevent indirect access to clusters without CPU cores
  irqchip/mips-gic: Multi-cluster support
  irqchip/mips-gic: Setup defaults in each cluster
  irqchip/mips-gic: Support multi-cluster in for_each_online_cpu_gic()
  irqchip/mips-gic: Replace open coded online CPU iterations
  genirq/irqdesc: Use str_enabled_disabled() helper in wakeup_show()
  genirq/devres: Don't free interrupt which is not managed by devres
  irqchip/gic-v3-its: Fix over allocation in itt_alloc_pool()
  irqchip/aspeed-intc: Add AST27XX INTC support
  dt-bindings: interrupt-controller: Add support for ASPEED AST27XX INTC
  ...

12 files changed, 1212 insertions, 76 deletions

diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index d82bcab233a1..55d7122121e2 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -258,6 +258,13 @@ config RENESAS_RZG2L_IRQC
 	  Enable support for the Renesas RZ/G2L (and alike SoC) Interrupt Controller
 	  for external devices.
 
+config RENESAS_RZV2H_ICU
+	bool "Renesas RZ/V2H(P) ICU support" if COMPILE_TEST
+	select GENERIC_IRQ_CHIP
+	select IRQ_DOMAIN_HIERARCHY
+	help
+	  Enable support for the Renesas RZ/V2H(P) Interrupt Control Unit (ICU)
+
 config SL28CPLD_INTC
 	bool "Kontron sl28cpld IRQ controller"
 	depends on MFD_SL28CPLD=y || COMPILE_TEST
@@ -338,6 +345,7 @@ config KEYSTONE_IRQ
 
 config MIPS_GIC
 	bool
+	select GENERIC_IRQ_EFFECTIVE_AFF_MASK if SMP
 	select GENERIC_IRQ_IPI if SMP
 	select IRQ_DOMAIN_HIERARCHY
 	select MIPS_CM
@@ -604,6 +612,18 @@ config STARFIVE_JH8100_INTC
 
 	  If you don't know what to do here, say Y.
 
+config THEAD_C900_ACLINT_SSWI
+	bool "THEAD C9XX ACLINT S-mode IPI Interrupt Controller"
+	depends on RISCV
+	depends on SMP
+	select IRQ_DOMAIN_HIERARCHY
+	select GENERIC_IRQ_IPI_MUX
+	help
+	  This enables support for T-HEAD specific ACLINT SSWI device
+	  support.
+
+	  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
diff --git a/drivers/irqchip/Makefile b/drivers/irqchip/Makefile
index e3679ec2b9f7..25e9ad29b8c4 100644
--- a/drivers/irqchip/Makefile
+++ b/drivers/irqchip/Makefile
@@ -51,6 +51,7 @@ obj-$(CONFIG_RENESAS_INTC_IRQPIN)	+= irq-renesas-intc-irqpin.o
 obj-$(CONFIG_RENESAS_IRQC)		+= irq-renesas-irqc.o
 obj-$(CONFIG_RENESAS_RZA1_IRQC)		+= irq-renesas-rza1.o
 obj-$(CONFIG_RENESAS_RZG2L_IRQC)	+= irq-renesas-rzg2l.o
+obj-$(CONFIG_RENESAS_RZV2H_ICU)		+= irq-renesas-rzv2h.o
 obj-$(CONFIG_VERSATILE_FPGA_IRQ)	+= irq-versatile-fpga.o
 obj-$(CONFIG_ARCH_NSPIRE)		+= irq-zevio.o
 obj-$(CONFIG_ARCH_VT8500)		+= irq-vt8500.o
@@ -84,6 +85,7 @@ 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_ARCH_ASPEED)		+= irq-aspeed-vic.o irq-aspeed-i2c-ic.o irq-aspeed-scu-ic.o
+obj-$(CONFIG_ARCH_ASPEED)		+= irq-aspeed-intc.o
 obj-$(CONFIG_STM32MP_EXTI)		+= irq-stm32mp-exti.o
 obj-$(CONFIG_STM32_EXTI) 		+= irq-stm32-exti.o
 obj-$(CONFIG_QCOM_IRQ_COMBINER)		+= qcom-irq-combiner.o
@@ -101,6 +103,7 @@ obj-$(CONFIG_RISCV_APLIC_MSI)		+= irq-riscv-aplic-msi.o
 obj-$(CONFIG_RISCV_IMSIC)		+= irq-riscv-imsic-state.o irq-riscv-imsic-early.o irq-riscv-imsic-platform.o
 obj-$(CONFIG_SIFIVE_PLIC)		+= irq-sifive-plic.o
 obj-$(CONFIG_STARFIVE_JH8100_INTC)	+= irq-starfive-jh8100-intc.o
+obj-$(CONFIG_THEAD_C900_ACLINT_SSWI)	+= irq-thead-c900-aclint-sswi.o
 obj-$(CONFIG_IMX_IRQSTEER)		+= irq-imx-irqsteer.o
 obj-$(CONFIG_IMX_INTMUX)		+= irq-imx-intmux.o
 obj-$(CONFIG_IMX_MU_MSI)		+= irq-imx-mu-msi.o
diff --git a/drivers/irqchip/irq-aspeed-intc.c b/drivers/irqchip/irq-aspeed-intc.c
new file mode 100644
index 000000000000..bd3b759b4b2c
--- /dev/null
+++ b/drivers/irqchip/irq-aspeed-intc.c
@@ -0,0 +1,139 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *  Aspeed Interrupt Controller.
+ *
+ *  Copyright (C) 2023 ASPEED Technology Inc.
+ */
+
+#include <linux/bitops.h>
+#include <linux/irq.h>
+#include <linux/irqchip.h>
+#include <linux/irqchip/chained_irq.h>
+#include <linux/irqdomain.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/io.h>
+#include <linux/spinlock.h>
+
+#define INTC_INT_ENABLE_REG	0x00
+#define INTC_INT_STATUS_REG	0x04
+#define INTC_IRQS_PER_WORD	32
+
+struct aspeed_intc_ic {
+	void __iomem		*base;
+	raw_spinlock_t		gic_lock;
+	raw_spinlock_t		intc_lock;
+	struct irq_domain	*irq_domain;
+};
+
+static void aspeed_intc_ic_irq_handler(struct irq_desc *desc)
+{
+	struct aspeed_intc_ic *intc_ic = irq_desc_get_handler_data(desc);
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+
+	chained_irq_enter(chip, desc);
+
+	scoped_guard(raw_spinlock, &intc_ic->gic_lock) {
+		unsigned long bit, status;
+
+		status = readl(intc_ic->base + INTC_INT_STATUS_REG);
+		for_each_set_bit(bit, &status, INTC_IRQS_PER_WORD) {
+			generic_handle_domain_irq(intc_ic->irq_domain, bit);
+			writel(BIT(bit), intc_ic->base + INTC_INT_STATUS_REG);
+		}
+	}
+
+	chained_irq_exit(chip, desc);
+}
+
+static void aspeed_intc_irq_mask(struct irq_data *data)
+{
+	struct aspeed_intc_ic *intc_ic = irq_data_get_irq_chip_data(data);
+	unsigned int mask = readl(intc_ic->base + INTC_INT_ENABLE_REG) & ~BIT(data->hwirq);
+
+	guard(raw_spinlock)(&intc_ic->intc_lock);
+	writel(mask, intc_ic->base + INTC_INT_ENABLE_REG);
+}
+
+static void aspeed_intc_irq_unmask(struct irq_data *data)
+{
+	struct aspeed_intc_ic *intc_ic = irq_data_get_irq_chip_data(data);
+	unsigned int unmask = readl(intc_ic->base + INTC_INT_ENABLE_REG) | BIT(data->hwirq);
+
+	guard(raw_spinlock)(&intc_ic->intc_lock);
+	writel(unmask, intc_ic->base + INTC_INT_ENABLE_REG);
+}
+
+static struct irq_chip aspeed_intc_chip = {
+	.name			= "ASPEED INTC",
+	.irq_mask		= aspeed_intc_irq_mask,
+	.irq_unmask		= aspeed_intc_irq_unmask,
+};
+
+static int aspeed_intc_ic_map_irq_domain(struct irq_domain *domain, unsigned int irq,
+					 irq_hw_number_t hwirq)
+{
+	irq_set_chip_and_handler(irq, &aspeed_intc_chip, handle_level_irq);
+	irq_set_chip_data(irq, domain->host_data);
+
+	return 0;
+}
+
+static const struct irq_domain_ops aspeed_intc_ic_irq_domain_ops = {
+	.map = aspeed_intc_ic_map_irq_domain,
+};
+
+static int __init aspeed_intc_ic_of_init(struct device_node *node,
+					 struct device_node *parent)
+{
+	struct aspeed_intc_ic *intc_ic;
+	int irq, i, ret = 0;
+
+	intc_ic = kzalloc(sizeof(*intc_ic), GFP_KERNEL);
+	if (!intc_ic)
+		return -ENOMEM;
+
+	intc_ic->base = of_iomap(node, 0);
+	if (!intc_ic->base) {
+		pr_err("Failed to iomap intc_ic base\n");
+		ret = -ENOMEM;
+		goto err_free_ic;
+	}
+	writel(0xffffffff, intc_ic->base + INTC_INT_STATUS_REG);
+	writel(0x0, intc_ic->base + INTC_INT_ENABLE_REG);
+
+	intc_ic->irq_domain = irq_domain_add_linear(node, INTC_IRQS_PER_WORD,
+						    &aspeed_intc_ic_irq_domain_ops, intc_ic);
+	if (!intc_ic->irq_domain) {
+		ret = -ENOMEM;
+		goto err_iounmap;
+	}
+
+	raw_spin_lock_init(&intc_ic->gic_lock);
+	raw_spin_lock_init(&intc_ic->intc_lock);
+
+	/* Check all the irq numbers valid. If not, unmaps all the base and frees the data. */
+	for (i = 0; i < of_irq_count(node); i++) {
+		irq = irq_of_parse_and_map(node, i);
+		if (!irq) {
+			pr_err("Failed to get irq number\n");
+			ret = -EINVAL;
+			goto err_iounmap;
+		}
+	}
+
+	for (i = 0; i < of_irq_count(node); i++) {
+		irq = irq_of_parse_and_map(node, i);
+		irq_set_chained_handler_and_data(irq, aspeed_intc_ic_irq_handler, intc_ic);
+	}
+
+	return 0;
+
+err_iounmap:
+	iounmap(intc_ic->base);
+err_free_ic:
+	kfree(intc_ic);
+	return ret;
+}
+
+IRQCHIP_DECLARE(ast2700_intc_ic, "aspeed,ast2700-intc-ic", aspeed_intc_ic_of_init);
diff --git a/drivers/irqchip/irq-atmel-aic5.c b/drivers/irqchip/irq-atmel-aic5.c
index c0f55dc7b050..e98c2875af9e 100644
--- a/drivers/irqchip/irq-atmel-aic5.c
+++ b/drivers/irqchip/irq-atmel-aic5.c
@@ -319,6 +319,7 @@ 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 = sam9x60_aic_irq_fixup },
+	{ .compatible = "microchip,sam9x7", .data = sam9x60_aic_irq_fixup },
 	{ /* sentinel */ },
 };
 
@@ -405,3 +406,11 @@ static int __init sam9x60_aic5_of_init(struct device_node *node,
 	return aic5_of_init(node, parent, NR_SAM9X60_IRQS);
 }
 IRQCHIP_DECLARE(sam9x60_aic5, "microchip,sam9x60-aic", sam9x60_aic5_of_init);
+
+#define NR_SAM9X7_IRQS		70
+
+static int __init sam9x7_aic5_of_init(struct device_node *node, struct device_node *parent)
+{
+	return aic5_of_init(node, parent, NR_SAM9X7_IRQS);
+}
+IRQCHIP_DECLARE(sam9x7_aic5, "microchip,sam9x7-aic", sam9x7_aic5_of_init);
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 52f625e07658..16acce0f102d 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -12,12 +12,14 @@
 #include <linux/crash_dump.h>
 #include <linux/delay.h>
 #include <linux/efi.h>
+#include <linux/genalloc.h>
 #include <linux/interrupt.h>
 #include <linux/iommu.h>
 #include <linux/iopoll.h>
 #include <linux/irqdomain.h>
 #include <linux/list.h>
 #include <linux/log2.h>
+#include <linux/mem_encrypt.h>
 #include <linux/memblock.h>
 #include <linux/mm.h>
 #include <linux/msi.h>
@@ -27,6 +29,7 @@
 #include <linux/of_pci.h>
 #include <linux/of_platform.h>
 #include <linux/percpu.h>
+#include <linux/set_memory.h>
 #include <linux/slab.h>
 #include <linux/syscore_ops.h>
 
@@ -164,6 +167,7 @@ struct its_device {
 	struct its_node		*its;
 	struct event_lpi_map	event_map;
 	void			*itt;
+	u32			itt_sz;
 	u32			nr_ites;
 	u32			device_id;
 	bool			shared;
@@ -199,6 +203,87 @@ static DEFINE_IDA(its_vpeid_ida);
 #define gic_data_rdist_rd_base()	(gic_data_rdist()->rd_base)
 #define gic_data_rdist_vlpi_base()	(gic_data_rdist_rd_base() + SZ_128K)
 
+static struct page *its_alloc_pages_node(int node, gfp_t gfp,
+					 unsigned int order)
+{
+	struct page *page;
+	int ret = 0;
+
+	page = alloc_pages_node(node, gfp, order);
+
+	if (!page)
+		return NULL;
+
+	ret = set_memory_decrypted((unsigned long)page_address(page),
+				   1 << order);
+	/*
+	 * If set_memory_decrypted() fails then we don't know what state the
+	 * page is in, so we can't free it. Instead we leak it.
+	 * set_memory_decrypted() will already have WARNed.
+	 */
+	if (ret)
+		return NULL;
+
+	return page;
+}
+
+static struct page *its_alloc_pages(gfp_t gfp, unsigned int order)
+{
+	return its_alloc_pages_node(NUMA_NO_NODE, gfp, order);
+}
+
+static void its_free_pages(void *addr, unsigned int order)
+{
+	/*
+	 * If the memory cannot be encrypted again then we must leak the pages.
+	 * set_memory_encrypted() will already have WARNed.
+	 */
+	if (set_memory_encrypted((unsigned long)addr, 1 << order))
+		return;
+	free_pages((unsigned long)addr, order);
+}
+
+static struct gen_pool *itt_pool;
+
+static void *itt_alloc_pool(int node, int size)
+{
+	unsigned long addr;
+	struct page *page;
+
+	if (size >= PAGE_SIZE) {
+		page = its_alloc_pages_node(node, GFP_KERNEL | __GFP_ZERO, get_order(size));
+
+		return page ? page_address(page) : NULL;
+	}
+
+	do {
+		addr = gen_pool_alloc(itt_pool, size);
+		if (addr)
+			break;
+
+		page = its_alloc_pages_node(node, GFP_KERNEL | __GFP_ZERO, 0);
+		if (!page)
+			break;
+
+		gen_pool_add(itt_pool, (unsigned long)page_address(page), PAGE_SIZE, node);
+	} while (!addr);
+
+	return (void *)addr;
+}
+
+static void itt_free_pool(void *addr, int size)
+{
+	if (!addr)
+		return;
+
+	if (size >= PAGE_SIZE) {
+		its_free_pages(addr, get_order(size));
+		return;
+	}
+
+	gen_pool_free(itt_pool, (unsigned long)addr, size);
+}
+
 /*
  * Skip ITSs that have no vLPIs mapped, unless we're on GICv4.1, as we
  * always have vSGIs mapped.
@@ -621,7 +706,6 @@ static struct its_collection *its_build_mapd_cmd(struct its_node *its,
 	u8 size = ilog2(desc->its_mapd_cmd.dev->nr_ites);
 
 	itt_addr = virt_to_phys(desc->its_mapd_cmd.dev->itt);
-	itt_addr = ALIGN(itt_addr, ITS_ITT_ALIGN);
 
 	its_encode_cmd(cmd, GITS_CMD_MAPD);
 	its_encode_devid(cmd, desc->its_mapd_cmd.dev->device_id);
@@ -2181,7 +2265,8 @@ static struct page *its_allocate_prop_table(gfp_t gfp_flags)
 {
 	struct page *prop_page;
 
-	prop_page = alloc_pages(gfp_flags, get_order(LPI_PROPBASE_SZ));
+	prop_page = its_alloc_pages(gfp_flags,
+				    get_order(LPI_PROPBASE_SZ));
 	if (!prop_page)
 		return NULL;
 
@@ -2192,8 +2277,7 @@ static struct page *its_allocate_prop_table(gfp_t gfp_flags)
 
 static void its_free_prop_table(struct page *prop_page)
 {
-	free_pages((unsigned long)page_address(prop_page),
-		   get_order(LPI_PROPBASE_SZ));
+	its_free_pages(page_address(prop_page), get_order(LPI_PROPBASE_SZ));
 }
 
 static bool gic_check_reserved_range(phys_addr_t addr, unsigned long size)
@@ -2315,7 +2399,7 @@ static int its_setup_baser(struct its_node *its, struct its_baser *baser,
 		order = get_order(GITS_BASER_PAGES_MAX * psz);
 	}
 
-	page = alloc_pages_node(its->numa_node, GFP_KERNEL | __GFP_ZERO, order);
+	page = its_alloc_pages_node(its->numa_node, GFP_KERNEL | __GFP_ZERO, order);
 	if (!page)
 		return -ENOMEM;
 
@@ -2328,7 +2412,7 @@ static int its_setup_baser(struct its_node *its, struct its_baser *baser,
 		/* 52bit PA is supported only when PageSize=64K */
 		if (psz != SZ_64K) {
 			pr_err("ITS: no 52bit PA support when psz=%d\n", psz);
-			free_pages((unsigned long)base, order);
+			its_free_pages(base, order);
 			return -ENXIO;
 		}
 
@@ -2384,7 +2468,7 @@ retry_baser:
 		pr_err("ITS@%pa: %s doesn't stick: %llx %llx\n",
 		       &its->phys_base, its_base_type_string[type],
 		       val, tmp);
-		free_pages((unsigned long)base, order);
+		its_free_pages(base, order);
 		return -ENXIO;
 	}
 
@@ -2523,8 +2607,7 @@ static void its_free_tables(struct its_node *its)
 
 	for (i = 0; i < GITS_BASER_NR_REGS; i++) {
 		if (its->tables[i].base) {
-			free_pages((unsigned long)its->tables[i].base,
-				   its->tables[i].order);
+			its_free_pages(its->tables[i].base, its->tables[i].order);
 			its->tables[i].base = NULL;
 		}
 	}
@@ -2790,7 +2873,7 @@ static bool allocate_vpe_l2_table(int cpu, u32 id)
 
 	/* Allocate memory for 2nd level table */
 	if (!table[idx]) {
-		page = alloc_pages(GFP_KERNEL | __GFP_ZERO, get_order(psz));
+		page = its_alloc_pages(GFP_KERNEL | __GFP_ZERO, get_order(psz));
 		if (!page)
 			return false;
 
@@ -2909,7 +2992,7 @@ static int allocate_vpe_l1_table(void)
 
 	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));
+	page = its_alloc_pages(GFP_ATOMIC | __GFP_ZERO, get_order(np * PAGE_SIZE));
 	if (!page)
 		return -ENOMEM;
 
@@ -2955,8 +3038,7 @@ static struct page *its_allocate_pending_table(gfp_t gfp_flags)
 {
 	struct page *pend_page;
 
-	pend_page = alloc_pages(gfp_flags | __GFP_ZERO,
-				get_order(LPI_PENDBASE_SZ));
+	pend_page = its_alloc_pages(gfp_flags | __GFP_ZERO, get_order(LPI_PENDBASE_SZ));
 	if (!pend_page)
 		return NULL;
 
@@ -2968,7 +3050,7 @@ static struct page *its_allocate_pending_table(gfp_t gfp_flags)
 
 static void its_free_pending_table(struct page *pt)
 {
-	free_pages((unsigned long)page_address(pt), get_order(LPI_PENDBASE_SZ));
+	its_free_pages(page_address(pt), get_order(LPI_PENDBASE_SZ));
 }
 
 /*
@@ -3303,8 +3385,8 @@ static bool its_alloc_table_entry(struct its_node *its,
 
 	/* Allocate memory for 2nd level table */
 	if (!table[idx]) {
-		page = alloc_pages_node(its->numa_node, GFP_KERNEL | __GFP_ZERO,
-					get_order(baser->psz));
+		page = its_alloc_pages_node(its->numa_node, GFP_KERNEL | __GFP_ZERO,
+					    get_order(baser->psz));
 		if (!page)
 			return false;
 
@@ -3399,15 +3481,18 @@ static struct its_device *its_create_device(struct its_node *its, u32 dev_id,
 	if (WARN_ON(!is_power_of_2(nvecs)))
 		nvecs = roundup_pow_of_two(nvecs);
 
-	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
 	/*
 	 * Even if the device wants a single LPI, the ITT must be
 	 * sized as a power of two (and you need at least one bit...).
 	 */
 	nr_ites = max(2, nvecs);
 	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);
+	sz = max(sz, ITS_ITT_ALIGN);
+
+	itt = itt_alloc_pool(its->numa_node, sz);
+
+	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+
 	if (alloc_lpis) {
 		lpi_map = its_lpi_alloc(nvecs, &lpi_base, &nr_lpis);
 		if (lpi_map)
@@ -3419,9 +3504,9 @@ static struct its_device *its_create_device(struct its_node *its, u32 dev_id,
 		lpi_base = 0;
 	}
 
-	if (!dev || !itt ||  !col_map || (!lpi_map && alloc_lpis)) {
+	if (!dev || !itt || !col_map || (!lpi_map && alloc_lpis)) {
 		kfree(dev);
-		kfree(itt);
+		itt_free_pool(itt, sz);
 		bitmap_free(lpi_map);
 		kfree(col_map);
 		return NULL;
@@ -3431,6 +3516,7 @@ static struct its_device *its_create_device(struct its_node *its, u32 dev_id,
 
 	dev->its = its;
 	dev->itt = itt;
+	dev->itt_sz = sz;
 	dev->nr_ites = nr_ites;
 	dev->event_map.lpi_map = lpi_map;
 	dev->event_map.col_map = col_map;
@@ -3458,7 +3544,7 @@ static void its_free_device(struct its_device *its_dev)
 	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);
+	itt_free_pool(its_dev->itt, its_dev->itt_sz);
 	kfree(its_dev);
 }
 
@@ -5132,8 +5218,9 @@ static int __init its_probe_one(struct its_node *its)
 		}
 	}
 
-	page = alloc_pages_node(its->numa_node, GFP_KERNEL | __GFP_ZERO,
-				get_order(ITS_CMD_QUEUE_SZ));
+	page = its_alloc_pages_node(its->numa_node,
+				    GFP_KERNEL | __GFP_ZERO,
+				    get_order(ITS_CMD_QUEUE_SZ));
 	if (!page) {
 		err = -ENOMEM;
 		goto out_unmap_sgir;
@@ -5197,7 +5284,7 @@ static int __init its_probe_one(struct its_node *its)
 out_free_tables:
 	its_free_tables(its);
 out_free_cmd:
-	free_pages((unsigned long)its->cmd_base, get_order(ITS_CMD_QUEUE_SZ));
+	its_free_pages(its->cmd_base, get_order(ITS_CMD_QUEUE_SZ));
 out_unmap_sgir:
 	if (its->sgir_base)
 		iounmap(its->sgir_base);
@@ -5683,6 +5770,10 @@ int __init its_init(struct fwnode_handle *handle, struct rdists *rdists,
 	bool has_v4_1 = false;
 	int err;
 
+	itt_pool = gen_pool_create(get_order(ITS_ITT_ALIGN), -1);
+	if (!itt_pool)
+		return -ENOMEM;
+
 	gic_rdists = rdists;
 
 	lpi_prop_prio = irq_prio;
diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c
index 76253e864f23..bca8053864b2 100644
--- a/drivers/irqchip/irq-mips-gic.c
+++ b/drivers/irqchip/irq-mips-gic.c
@@ -66,6 +66,87 @@ static struct gic_all_vpes_chip_data {
 	bool	mask;
 } gic_all_vpes_chip_data[GIC_NUM_LOCAL_INTRS];
 
+static int __gic_with_next_online_cpu(int prev)
+{
+	unsigned int cpu;
+
+	/* Discover the next online CPU */
+	cpu = cpumask_next(prev, cpu_online_mask);
+
+	/* If there isn't one, we're done */
+	if (cpu >= nr_cpu_ids)
+		return cpu;
+
+	/*
+	 * Move the access lock to the next CPU's GIC local register block.
+	 *
+	 * Set GIC_VL_OTHER. Since the caller holds gic_lock nothing can
+	 * clobber the written value.
+	 */
+	write_gic_vl_other(mips_cm_vp_id(cpu));
+
+	return cpu;
+}
+
+static inline void gic_unlock_cluster(void)
+{
+	if (mips_cps_multicluster_cpus())
+		mips_cm_unlock_other();
+}
+
+/**
+ * for_each_online_cpu_gic() - Iterate over online CPUs, access local registers
+ * @cpu: An integer variable to hold the current CPU number
+ * @gic_lock: A pointer to raw spin lock used as a guard
+ *
+ * Iterate over online CPUs & configure the other/redirect register region to
+ * access each CPUs GIC local register block, which can be accessed from the
+ * loop body using read_gic_vo_*() or write_gic_vo_*() accessor functions or
+ * their derivatives.
+ */
+#define for_each_online_cpu_gic(cpu, gic_lock)		\
+	guard(raw_spinlock_irqsave)(gic_lock);		\
+	for ((cpu) = __gic_with_next_online_cpu(-1);	\
+	     (cpu) < nr_cpu_ids;			\
+	     gic_unlock_cluster(),			\
+	     (cpu) = __gic_with_next_online_cpu(cpu))
+
+/**
+ * gic_irq_lock_cluster() - Lock redirect block access to IRQ's cluster
+ * @d: struct irq_data corresponding to the interrupt we're interested in
+ *
+ * Locks redirect register block access to the global register block of the GIC
+ * within the remote cluster that the IRQ corresponding to @d is affine to,
+ * returning true when this redirect block setup & locking has been performed.
+ *
+ * If @d is affine to the local cluster then no locking is performed and this
+ * function will return false, indicating to the caller that it should access
+ * the local clusters registers without the overhead of indirection through the
+ * redirect block.
+ *
+ * In summary, if this function returns true then the caller should access GIC
+ * registers using redirect register block accessors & then call
+ * mips_cm_unlock_other() when done. If this function returns false then the
+ * caller should trivially access GIC registers in the local cluster.
+ *
+ * Returns true if locking performed, else false.
+ */
+static bool gic_irq_lock_cluster(struct irq_data *d)
+{
+	unsigned int cpu, cl;
+
+	cpu = cpumask_first(irq_data_get_effective_affinity_mask(d));
+	BUG_ON(cpu >= NR_CPUS);
+
+	cl = cpu_cluster(&cpu_data[cpu]);
+	if (cl == cpu_cluster(&current_cpu_data))
+		return false;
+	if (mips_cps_numcores(cl) == 0)
+		return false;
+	mips_cm_lock_other(cl, 0, 0, CM_GCR_Cx_OTHER_BLOCK_GLOBAL);
+	return true;
+}
+
 static void gic_clear_pcpu_masks(unsigned int intr)
 {
 	unsigned int i;
@@ -112,7 +193,12 @@ static void gic_send_ipi(struct irq_data *d, unsigned int cpu)
 {
 	irq_hw_number_t hwirq = GIC_HWIRQ_TO_SHARED(irqd_to_hwirq(d));
 
-	write_gic_wedge(GIC_WEDGE_RW | hwirq);
+	if (gic_irq_lock_cluster(d)) {
+		write_gic_redir_wedge(GIC_WEDGE_RW | hwirq);
+		mips_cm_unlock_other();
+	} else {
+		write_gic_wedge(GIC_WEDGE_RW | hwirq);
+	}
 }
 
 int gic_get_c0_compare_int(void)
@@ -180,7 +266,13 @@ static void gic_mask_irq(struct irq_data *d)
 {
 	unsigned int intr = GIC_HWIRQ_TO_SHARED(d->hwirq);
 
-	write_gic_rmask(intr);
+	if (gic_irq_lock_cluster(d)) {
+		write_gic_redir_rmask(intr);
+		mips_cm_unlock_other();
+	} else {
+		write_gic_rmask(intr);
+	}
+
 	gic_clear_pcpu_masks(intr);
 }
 
@@ -189,7 +281,12 @@ static void gic_unmask_irq(struct irq_data *d)
 	unsigned int intr = GIC_HWIRQ_TO_SHARED(d->hwirq);
 	unsigned int cpu;
 
-	write_gic_smask(intr);
+	if (gic_irq_lock_cluster(d)) {
+		write_gic_redir_smask(intr);
+		mips_cm_unlock_other();
+	} else {
+		write_gic_smask(intr);
+	}
 
 	gic_clear_pcpu_masks(intr);
 	cpu = cpumask_first(irq_data_get_effective_affinity_mask(d));
@@ -200,7 +297,12 @@ static void gic_ack_irq(struct irq_data *d)
 {
 	unsigned int irq = GIC_HWIRQ_TO_SHARED(d->hwirq);
 
-	write_gic_wedge(irq);
+	if (gic_irq_lock_cluster(d)) {
+		write_gic_redir_wedge(irq);
+		mips_cm_unlock_other();
+	} else {
+		write_gic_wedge(irq);
+	}
 }
 
 static int gic_set_type(struct irq_data *d, unsigned int type)
@@ -240,9 +342,16 @@ static int gic_set_type(struct irq_data *d, unsigned int type)
 		break;
 	}
 
-	change_gic_pol(irq, pol);
-	change_gic_trig(irq, trig);
-	change_gic_dual(irq, dual);
+	if (gic_irq_lock_cluster(d)) {
+		change_gic_redir_pol(irq, pol);
+		change_gic_redir_trig(irq, trig);
+		change_gic_redir_dual(irq, dual);
+		mips_cm_unlock_other();
+	} else {
+		change_gic_pol(irq, pol);
+		change_gic_trig(irq, trig);
+		change_gic_dual(irq, dual);
+	}
 
 	if (trig == GIC_TRIG_EDGE)
 		irq_set_chip_handler_name_locked(d, &gic_edge_irq_controller,
@@ -260,25 +369,72 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *cpumask,
 			    bool force)
 {
 	unsigned int irq = GIC_HWIRQ_TO_SHARED(d->hwirq);
+	unsigned int cpu, cl, old_cpu, old_cl;
 	unsigned long flags;
-	unsigned int cpu;
 
+	/*
+	 * The GIC specifies that we can only route an interrupt to one VP(E),
+	 * ie. CPU in Linux parlance, at a time. Therefore we always route to
+	 * the first online CPU in the mask.
+	 */
 	cpu = cpumask_first_and(cpumask, cpu_online_mask);
 	if (cpu >= NR_CPUS)
 		return -EINVAL;
 
-	/* Assumption : cpumask refers to a single CPU */
-	raw_spin_lock_irqsave(&gic_lock, flags);
+	old_cpu = cpumask_first(irq_data_get_effective_affinity_mask(d));
+	old_cl = cpu_cluster(&cpu_data[old_cpu]);
+	cl = cpu_cluster(&cpu_data[cpu]);
 
-	/* Re-route this IRQ */
-	write_gic_map_vp(irq, BIT(mips_cm_vp_id(cpu)));
+	raw_spin_lock_irqsave(&gic_lock, flags);
 
-	/* Update the pcpu_masks */
-	gic_clear_pcpu_masks(irq);
-	if (read_gic_mask(irq))
-		set_bit(irq, per_cpu_ptr(pcpu_masks, cpu));
+	/*
+	 * If we're moving affinity between clusters, stop routing the
+	 * interrupt to any VP(E) in the old cluster.
+	 */
+	if (cl != old_cl) {
+		if (gic_irq_lock_cluster(d)) {
+			write_gic_redir_map_vp(irq, 0);
+			mips_cm_unlock_other();
+		} else {
+			write_gic_map_vp(irq, 0);
+		}
+	}
 
+	/*
+	 * Update effective affinity - after this gic_irq_lock_cluster() will
+	 * begin operating on the new cluster.
+	 */
 	irq_data_update_effective_affinity(d, cpumask_of(cpu));
+
+	/*
+	 * If we're moving affinity between clusters, configure the interrupt
+	 * trigger type in the new cluster.
+	 */
+	if (cl != old_cl)
+		gic_set_type(d, irqd_get_trigger_type(d));
+
+	/* Route the interrupt to its new VP(E) */
+	if (gic_irq_lock_cluster(d)) {
+		write_gic_redir_map_pin(irq,
+					GIC_MAP_PIN_MAP_TO_PIN | gic_cpu_pin);
+		write_gic_redir_map_vp(irq, BIT(mips_cm_vp_id(cpu)));
+
+		/* Update the pcpu_masks */
+		gic_clear_pcpu_masks(irq);
+		if (read_gic_redir_mask(irq))
+			set_bit(irq, per_cpu_ptr(pcpu_masks, cpu));
+
+		mips_cm_unlock_other();
+	} else {
+		write_gic_map_pin(irq, GIC_MAP_PIN_MAP_TO_PIN | gic_cpu_pin);
+		write_gic_map_vp(irq, BIT(mips_cm_vp_id(cpu)));
+
+		/* Update the pcpu_masks */
+		gic_clear_pcpu_masks(irq);
+		if (read_gic_mask(irq))
+			set_bit(irq, per_cpu_ptr(pcpu_masks, cpu));
+	}
+
 	raw_spin_unlock_irqrestore(&gic_lock, flags);
 
 	return IRQ_SET_MASK_OK;
@@ -350,37 +506,33 @@ static struct irq_chip gic_local_irq_controller = {
 static void gic_mask_local_irq_all_vpes(struct irq_data *d)
 {
 	struct gic_all_vpes_chip_data *cd;
-	unsigned long flags;
 	int intr, cpu;
 
+	if (!mips_cps_multicluster_cpus())
+		return;
+
 	intr = GIC_HWIRQ_TO_LOCAL(d->hwirq);
 	cd = irq_data_get_irq_chip_data(d);
 	cd->mask = false;
 
-	raw_spin_lock_irqsave(&gic_lock, flags);
-	for_each_online_cpu(cpu) {
-		write_gic_vl_other(mips_cm_vp_id(cpu));
+	for_each_online_cpu_gic(cpu, &gic_lock)
 		write_gic_vo_rmask(BIT(intr));
-	}
-	raw_spin_unlock_irqrestore(&gic_lock, flags);
 }
 
 static void gic_unmask_local_irq_all_vpes(struct irq_data *d)
 {
 	struct gic_all_vpes_chip_data *cd;
-	unsigned long flags;
 	int intr, cpu;
 
+	if (!mips_cps_multicluster_cpus())
+		return;
+
 	intr = GIC_HWIRQ_TO_LOCAL(d->hwirq);
 	cd = irq_data_get_irq_chip_data(d);
 	cd->mask = true;
 
-	raw_spin_lock_irqsave(&gic_lock, flags);
-	for_each_online_cpu(cpu) {
-		write_gic_vl_other(mips_cm_vp_id(cpu));
+	for_each_online_cpu_gic(cpu, &gic_lock)
 		write_gic_vo_smask(BIT(intr));
-	}
-	raw_spin_unlock_irqrestore(&gic_lock, flags);
 }
 
 static void gic_all_vpes_irq_cpu_online(void)
@@ -436,11 +588,21 @@ static int gic_shared_irq_domain_map(struct irq_domain *d, unsigned int virq,
 	unsigned long flags;
 
 	data = irq_get_irq_data(virq);
+	irq_data_update_effective_affinity(data, cpumask_of(cpu));
 
 	raw_spin_lock_irqsave(&gic_lock, flags);
-	write_gic_map_pin(intr, GIC_MAP_PIN_MAP_TO_PIN | gic_cpu_pin);
-	write_gic_map_vp(intr, BIT(mips_cm_vp_id(cpu)));
-	irq_data_update_effective_affinity(data, cpumask_of(cpu));
+
+	/* Route the interrupt to its VP(E) */
+	if (gic_irq_lock_cluster(data)) {
+		write_gic_redir_map_pin(intr,
+					GIC_MAP_PIN_MAP_TO_PIN | gic_cpu_pin);
+		write_gic_redir_map_vp(intr, BIT(mips_cm_vp_id(cpu)));
+		mips_cm_unlock_other();
+	} else {
+		write_gic_map_pin(intr, GIC_MAP_PIN_MAP_TO_PIN | gic_cpu_pin);
+		write_gic_map_vp(intr, BIT(mips_cm_vp_id(cpu)));
+	}
+
 	raw_spin_unlock_irqrestore(&gic_lock, flags);
 
 	return 0;
@@ -469,7 +631,6 @@ static int gic_irq_domain_map(struct irq_domain *d, unsigned int virq,
 			      irq_hw_number_t hwirq)
 {
 	struct gic_all_vpes_chip_data *cd;
-	unsigned long flags;
 	unsigned int intr;
 	int err, cpu;
 	u32 map;
@@ -533,12 +694,10 @@ static int gic_irq_domain_map(struct irq_domain *d, unsigned int virq,
 	if (!gic_local_irq_is_routable(intr))
 		return -EPERM;
 
-	raw_spin_lock_irqsave(&gic_lock, flags);
-	for_each_online_cpu(cpu) {
-		write_gic_vl_other(mips_cm_vp_id(cpu));
-		write_gic_vo_map(mips_gic_vx_map_reg(intr), map);
+	if (mips_cps_multicluster_cpus()) {
+		for_each_online_cpu_gic(cpu, &gic_lock)
+			write_gic_vo_map(mips_gic_vx_map_reg(intr), map);
 	}
-	raw_spin_unlock_irqrestore(&gic_lock, flags);
 
 	return 0;
 }
@@ -621,6 +780,9 @@ static int gic_ipi_domain_alloc(struct irq_domain *d, unsigned int virq,
 		if (ret)
 			goto error;
 
+		/* Set affinity to cpu.  */
+		irq_data_update_effective_affinity(irq_get_irq_data(virq + i),
+						   cpumask_of(cpu));
 		ret = irq_set_irq_type(virq + i, IRQ_TYPE_EDGE_RISING);
 		if (ret)
 			goto error;
@@ -734,7 +896,7 @@ static int gic_cpu_startup(unsigned int cpu)
 static int __init gic_of_init(struct device_node *node,
 			      struct device_node *parent)
 {
-	unsigned int cpu_vec, i, gicconfig;
+	unsigned int cpu_vec, i, gicconfig, cl, nclusters;
 	unsigned long reserved;
 	phys_addr_t gic_base;
 	struct resource res;
@@ -815,11 +977,32 @@ static int __init gic_of_init(struct device_node *node,
 
 	board_bind_eic_interrupt = &gic_bind_eic_interrupt;
 
-	/* Setup defaults */
-	for (i = 0; i < gic_shared_intrs; i++) {
-		change_gic_pol(i, GIC_POL_ACTIVE_HIGH);
-		change_gic_trig(i, GIC_TRIG_LEVEL);
-		write_gic_rmask(i);
+	/*
+	 * Initialise each cluster's GIC shared registers to sane default
+	 * values.
+	 * Otherwise, the IPI set up will be erased if we move code
+	 * to gic_cpu_startup for each cpu.
+	 */
+	nclusters = mips_cps_numclusters();
+	for (cl = 0; cl < nclusters; cl++) {
+		if (cl == cpu_cluster(&current_cpu_data)) {
+			for (i = 0; i < gic_shared_intrs; i++) {
+				change_gic_pol(i, GIC_POL_ACTIVE_HIGH);
+				change_gic_trig(i, GIC_TRIG_LEVEL);
+				write_gic_rmask(i);
+			}
+		} else if (mips_cps_numcores(cl) != 0) {
+			mips_cm_lock_other(cl, 0, 0, CM_GCR_Cx_OTHER_BLOCK_GLOBAL);
+			for (i = 0; i < gic_shared_intrs; i++) {
+				change_gic_redir_pol(i, GIC_POL_ACTIVE_HIGH);
+				change_gic_redir_trig(i, GIC_TRIG_LEVEL);
+				write_gic_redir_rmask(i);
+			}
+			mips_cm_unlock_other();
+
+		} else {
+			pr_warn("No CPU cores on the cluster %d skip it\n", cl);
+		}
 	}
 
 	return cpuhp_setup_state(CPUHP_AP_IRQ_MIPS_GIC_STARTING,
diff --git a/drivers/irqchip/irq-renesas-rzv2h.c b/drivers/irqchip/irq-renesas-rzv2h.c
new file mode 100644
index 000000000000..fe2d29e91026
--- /dev/null
+++ b/drivers/irqchip/irq-renesas-rzv2h.c
@@ -0,0 +1,513 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Renesas RZ/V2H(P) ICU Driver
+ *
+ * Based on irq-renesas-rzg2l.c
+ *
+ * Copyright (C) 2024 Renesas Electronics Corporation.
+ *
+ * Author: Fabrizio Castro <fabrizio.castro.jz@renesas.com>
+ */
+
+#include <linux/bitfield.h>
+#include <linux/cleanup.h>
+#include <linux/clk.h>
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/irqchip.h>
+#include <linux/irqdomain.h>
+#include <linux/of_address.h>
+#include <linux/of_platform.h>
+#include <linux/pm_runtime.h>
+#include <linux/reset.h>
+#include <linux/spinlock.h>
+#include <linux/syscore_ops.h>
+
+/* DT "interrupts" indexes */
+#define ICU_IRQ_START				1
+#define ICU_IRQ_COUNT				16
+#define ICU_TINT_START				(ICU_IRQ_START + ICU_IRQ_COUNT)
+#define ICU_TINT_COUNT				32
+#define ICU_NUM_IRQ				(ICU_TINT_START + ICU_TINT_COUNT)
+
+/* Registers */
+#define ICU_NSCNT				0x00
+#define ICU_NSCLR				0x04
+#define ICU_NITSR				0x08
+#define ICU_ISCTR				0x10
+#define ICU_ISCLR				0x14
+#define ICU_IITSR				0x18
+#define ICU_TSCTR				0x20
+#define ICU_TSCLR				0x24
+#define ICU_TITSR(k)				(0x28 + (k) * 4)
+#define ICU_TSSR(k)				(0x30 + (k) * 4)
+
+/* NMI */
+#define ICU_NMI_EDGE_FALLING			0
+#define ICU_NMI_EDGE_RISING			1
+
+#define ICU_NSCLR_NCLR				BIT(0)
+
+/* IRQ */
+#define ICU_IRQ_LEVEL_LOW			0
+#define ICU_IRQ_EDGE_FALLING			1
+#define ICU_IRQ_EDGE_RISING			2
+#define ICU_IRQ_EDGE_BOTH			3
+
+#define ICU_IITSR_IITSEL_PREP(iitsel, n)	((iitsel) << ((n) * 2))
+#define ICU_IITSR_IITSEL_GET(iitsr, n)		(((iitsr) >> ((n) * 2)) & 0x03)
+#define ICU_IITSR_IITSEL_MASK(n)		ICU_IITSR_IITSEL_PREP(0x03, n)
+
+/* TINT */
+#define ICU_TINT_EDGE_RISING			0
+#define ICU_TINT_EDGE_FALLING			1
+#define ICU_TINT_LEVEL_HIGH			2
+#define ICU_TINT_LEVEL_LOW			3
+
+#define ICU_TSSR_K(tint_nr)			((tint_nr) / 4)
+#define ICU_TSSR_TSSEL_N(tint_nr)		((tint_nr) % 4)
+#define ICU_TSSR_TSSEL_PREP(tssel, n)		((tssel) << ((n) * 8))
+#define ICU_TSSR_TSSEL_MASK(n)			ICU_TSSR_TSSEL_PREP(0x7F, n)
+#define ICU_TSSR_TIEN(n)			(BIT(7) << ((n) * 8))
+
+#define ICU_TITSR_K(tint_nr)			((tint_nr) / 16)
+#define ICU_TITSR_TITSEL_N(tint_nr)		((tint_nr) % 16)
+#define ICU_TITSR_TITSEL_PREP(titsel, n)	ICU_IITSR_IITSEL_PREP(titsel, n)
+#define ICU_TITSR_TITSEL_MASK(n)		ICU_IITSR_IITSEL_MASK(n)
+#define ICU_TITSR_TITSEL_GET(titsr, n)		ICU_IITSR_IITSEL_GET(titsr, n)
+
+#define ICU_TINT_EXTRACT_HWIRQ(x)		FIELD_GET(GENMASK(15, 0), (x))
+#define ICU_TINT_EXTRACT_GPIOINT(x)		FIELD_GET(GENMASK(31, 16), (x))
+#define ICU_PB5_TINT				0x55
+
+/**
+ * struct rzv2h_icu_priv - Interrupt Control Unit controller private data structure.
+ * @base:	Controller's base address
+ * @irqchip:	Pointer to struct irq_chip
+ * @fwspec:	IRQ firmware specific data
+ * @lock:	Lock to serialize access to hardware registers
+ */
+struct rzv2h_icu_priv {
+	void __iomem			*base;
+	const struct irq_chip		*irqchip;
+	struct irq_fwspec		fwspec[ICU_NUM_IRQ];
+	raw_spinlock_t			lock;
+};
+
+static inline struct rzv2h_icu_priv *irq_data_to_priv(struct irq_data *data)
+{
+	return data->domain->host_data;
+}
+
+static void rzv2h_icu_eoi(struct irq_data *d)
+{
+	struct rzv2h_icu_priv *priv = irq_data_to_priv(d);
+	unsigned int hw_irq = irqd_to_hwirq(d);
+	unsigned int tintirq_nr;
+	u32 bit;
+
+	scoped_guard(raw_spinlock, &priv->lock) {
+		if (hw_irq >= ICU_TINT_START) {
+			tintirq_nr = hw_irq - ICU_TINT_START;
+			bit = BIT(tintirq_nr);
+			if (!irqd_is_level_type(d))
+				writel_relaxed(bit, priv->base + ICU_TSCLR);
+		} else if (hw_irq >= ICU_IRQ_START) {
+			tintirq_nr = hw_irq - ICU_IRQ_START;
+			bit = BIT(tintirq_nr);
+			if (!irqd_is_level_type(d))
+				writel_relaxed(bit, priv->base + ICU_ISCLR);
+		} else {
+			writel_relaxed(ICU_NSCLR_NCLR, priv->base + ICU_NSCLR);
+		}
+	}
+
+	irq_chip_eoi_parent(d);
+}
+
+static void rzv2h_tint_irq_endisable(struct irq_data *d, bool enable)
+{
+	struct rzv2h_icu_priv *priv = irq_data_to_priv(d);
+	unsigned int hw_irq = irqd_to_hwirq(d);
+	u32 tint_nr, tssel_n, k, tssr;
+
+	if (hw_irq < ICU_TINT_START)
+		return;
+
+	tint_nr = hw_irq - ICU_TINT_START;
+	k = ICU_TSSR_K(tint_nr);
+	tssel_n = ICU_TSSR_TSSEL_N(tint_nr);
+
+	guard(raw_spinlock)(&priv->lock);
+	tssr = readl_relaxed(priv->base + ICU_TSSR(k));
+	if (enable)
+		tssr |= ICU_TSSR_TIEN(tssel_n);
+	else
+		tssr &= ~ICU_TSSR_TIEN(tssel_n);
+	writel_relaxed(tssr, priv->base + ICU_TSSR(k));
+}
+
+static void rzv2h_icu_irq_disable(struct irq_data *d)
+{
+	irq_chip_disable_parent(d);
+	rzv2h_tint_irq_endisable(d, false);
+}
+
+static void rzv2h_icu_irq_enable(struct irq_data *d)
+{
+	rzv2h_tint_irq_endisable(d, true);
+	irq_chip_enable_parent(d);
+}
+
+static int rzv2h_nmi_set_type(struct irq_data *d, unsigned int type)
+{
+	struct rzv2h_icu_priv *priv = irq_data_to_priv(d);
+	u32 sense;
+
+	switch (type & IRQ_TYPE_SENSE_MASK) {
+	case IRQ_TYPE_EDGE_FALLING:
+		sense = ICU_NMI_EDGE_FALLING;
+		break;
+
+	case IRQ_TYPE_EDGE_RISING:
+		sense = ICU_NMI_EDGE_RISING;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	writel_relaxed(sense, priv->base + ICU_NITSR);
+
+	return 0;
+}
+
+static void rzv2h_clear_irq_int(struct rzv2h_icu_priv *priv, unsigned int hwirq)
+{
+	unsigned int irq_nr = hwirq - ICU_IRQ_START;
+	u32 isctr, iitsr, iitsel;
+	u32 bit = BIT(irq_nr);
+
+	isctr = readl_relaxed(priv->base + ICU_ISCTR);
+	iitsr = readl_relaxed(priv->base + ICU_IITSR);
+	iitsel = ICU_IITSR_IITSEL_GET(iitsr, irq_nr);
+
+	/*
+	 * When level sensing is used, the interrupt flag gets automatically cleared when the
+	 * interrupt signal is de-asserted by the source of the interrupt request, therefore clear
+	 * the interrupt only for edge triggered interrupts.
+	 */
+	if ((isctr & bit) && (iitsel != ICU_IRQ_LEVEL_LOW))
+		writel_relaxed(bit, priv->base + ICU_ISCLR);
+}
+
+static int rzv2h_irq_set_type(struct irq_data *d, unsigned int type)
+{
+	struct rzv2h_icu_priv *priv = irq_data_to_priv(d);
+	unsigned int hwirq = irqd_to_hwirq(d);
+	u32 irq_nr = hwirq - ICU_IRQ_START;
+	u32 iitsr, sense;
+
+	switch (type & IRQ_TYPE_SENSE_MASK) {
+	case IRQ_TYPE_LEVEL_LOW:
+		sense = ICU_IRQ_LEVEL_LOW;
+		break;
+
+	case IRQ_TYPE_EDGE_FALLING:
+		sense = ICU_IRQ_EDGE_FALLING;
+		break;
+
+	case IRQ_TYPE_EDGE_RISING:
+		sense = ICU_IRQ_EDGE_RISING;
+		break;
+
+	case IRQ_TYPE_EDGE_BOTH:
+		sense = ICU_IRQ_EDGE_BOTH;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	guard(raw_spinlock)(&priv->lock);
+	iitsr = readl_relaxed(priv->base + ICU_IITSR);
+	iitsr &= ~ICU_IITSR_IITSEL_MASK(irq_nr);
+	iitsr |= ICU_IITSR_IITSEL_PREP(sense, irq_nr);
+	rzv2h_clear_irq_int(priv, hwirq);
+	writel_relaxed(iitsr, priv->base + ICU_IITSR);
+
+	return 0;
+}
+
+static void rzv2h_clear_tint_int(struct rzv2h_icu_priv *priv, unsigned int hwirq)
+{
+	unsigned int tint_nr = hwirq - ICU_TINT_START;
+	int titsel_n = ICU_TITSR_TITSEL_N(tint_nr);
+	u32 tsctr, titsr, titsel;
+	u32 bit = BIT(tint_nr);
+	int k = tint_nr / 16;
+
+	tsctr = readl_relaxed(priv->base + ICU_TSCTR);
+	titsr = readl_relaxed(priv->base + ICU_TITSR(k));
+	titsel = ICU_TITSR_TITSEL_GET(titsr, titsel_n);
+
+	/*
+	 * Writing 1 to the corresponding flag from register ICU_TSCTR only has effect if
+	 * TSTATn = 1b and if it's a rising edge or a falling edge interrupt.
+	 */
+	if ((tsctr & bit) && ((titsel == ICU_TINT_EDGE_RISING) ||
+			      (titsel == ICU_TINT_EDGE_FALLING)))
+		writel_relaxed(bit, priv->base + ICU_TSCLR);
+}
+
+static int rzv2h_tint_set_type(struct irq_data *d, unsigned int type)
+{
+	u32 titsr, titsr_k, titsel_n, tien;
+	struct rzv2h_icu_priv *priv;
+	u32 tssr, tssr_k, tssel_n;
+	unsigned int hwirq;
+	u32 tint, sense;
+	int tint_nr;
+
+	switch (type & IRQ_TYPE_SENSE_MASK) {
+	case IRQ_TYPE_LEVEL_LOW:
+		sense = ICU_TINT_LEVEL_LOW;
+		break;
+
+	case IRQ_TYPE_LEVEL_HIGH:
+		sense = ICU_TINT_LEVEL_HIGH;
+		break;
+
+	case IRQ_TYPE_EDGE_RISING:
+		sense = ICU_TINT_EDGE_RISING;
+		break;
+
+	case IRQ_TYPE_EDGE_FALLING:
+		sense = ICU_TINT_EDGE_FALLING;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	tint = (u32)(uintptr_t)irq_data_get_irq_chip_data(d);
+	if (tint > ICU_PB5_TINT)
+		return -EINVAL;
+
+	priv = irq_data_to_priv(d);
+	hwirq = irqd_to_hwirq(d);
+
+	tint_nr = hwirq - ICU_TINT_START;
+
+	tssr_k = ICU_TSSR_K(tint_nr);
+	tssel_n = ICU_TSSR_TSSEL_N(tint_nr);
+
+	titsr_k = ICU_TITSR_K(tint_nr);
+	titsel_n = ICU_TITSR_TITSEL_N(tint_nr);
+	tien = ICU_TSSR_TIEN(titsel_n);
+
+	guard(raw_spinlock)(&priv->lock);
+
+	tssr = readl_relaxed(priv->base + ICU_TSSR(tssr_k));
+	tssr &= ~(ICU_TSSR_TSSEL_MASK(tssel_n) | tien);
+	tssr |= ICU_TSSR_TSSEL_PREP(tint, tssel_n);
+
+	writel_relaxed(tssr, priv->base + ICU_TSSR(tssr_k));
+
+	titsr = readl_relaxed(priv->base + ICU_TITSR(titsr_k));
+	titsr &= ~ICU_TITSR_TITSEL_MASK(titsel_n);
+	titsr |= ICU_TITSR_TITSEL_PREP(sense, titsel_n);
+
+	writel_relaxed(titsr, priv->base + ICU_TITSR(titsr_k));
+
+	rzv2h_clear_tint_int(priv, hwirq);
+
+	writel_relaxed(tssr | tien, priv->base + ICU_TSSR(tssr_k));
+
+	return 0;
+}
+
+static int rzv2h_icu_set_type(struct irq_data *d, unsigned int type)
+{
+	unsigned int hw_irq = irqd_to_hwirq(d);
+	int ret;
+
+	if (hw_irq >= ICU_TINT_START)
+		ret = rzv2h_tint_set_type(d, type);
+	else if (hw_irq >= ICU_IRQ_START)
+		ret = rzv2h_irq_set_type(d, type);
+	else
+		ret = rzv2h_nmi_set_type(d, type);
+
+	if (ret)
+		return ret;
+
+	return irq_chip_set_type_parent(d, IRQ_TYPE_LEVEL_HIGH);
+}
+
+static const struct irq_chip rzv2h_icu_chip = {
+	.name			= "rzv2h-icu",
+	.irq_eoi		= rzv2h_icu_eoi,
+	.irq_mask		= irq_chip_mask_parent,
+	.irq_unmask		= irq_chip_unmask_parent,
+	.irq_disable		= rzv2h_icu_irq_disable,
+	.irq_enable		= rzv2h_icu_irq_enable,
+	.irq_get_irqchip_state	= irq_chip_get_parent_state,
+	.irq_set_irqchip_state	= irq_chip_set_parent_state,
+	.irq_retrigger		= irq_chip_retrigger_hierarchy,
+	.irq_set_type		= rzv2h_icu_set_type,
+	.irq_set_affinity	= irq_chip_set_affinity_parent,
+	.flags			= IRQCHIP_SET_TYPE_MASKED,
+};
+
+static int rzv2h_icu_alloc(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs,
+			   void *arg)
+{
+	struct rzv2h_icu_priv *priv = domain->host_data;
+	unsigned long tint = 0;
+	irq_hw_number_t hwirq;
+	unsigned int type;
+	int ret;
+
+	ret = irq_domain_translate_twocell(domain, arg, &hwirq, &type);
+	if (ret)
+		return ret;
+
+	/*
+	 * For TINT interrupts the hwirq and TINT are encoded in
+	 * fwspec->param[0].
+	 * hwirq is embedded in bits 0-15.
+	 * TINT is embedded in bits 16-31.
+	 */
+	if (hwirq >= ICU_TINT_START) {
+		tint = ICU_TINT_EXTRACT_GPIOINT(hwirq);
+		hwirq = ICU_TINT_EXTRACT_HWIRQ(hwirq);
+
+		if (hwirq < ICU_TINT_START)
+			return -EINVAL;
+	}
+
+	if (hwirq > (ICU_NUM_IRQ - 1))
+		return -EINVAL;
+
+	ret = irq_domain_set_hwirq_and_chip(domain, virq, hwirq, priv->irqchip,
+					    (void *)(uintptr_t)tint);
+	if (ret)
+		return ret;
+
+	return irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, &priv->fwspec[hwirq]);
+}
+
+static const struct irq_domain_ops rzv2h_icu_domain_ops = {
+	.alloc		= rzv2h_icu_alloc,
+	.free		= irq_domain_free_irqs_common,
+	.translate	= irq_domain_translate_twocell,
+};
+
+static int rzv2h_icu_parse_interrupts(struct rzv2h_icu_priv *priv, struct device_node *np)
+{
+	struct of_phandle_args map;
+	unsigned int i;
+	int ret;
+
+	for (i = 0; i < ICU_NUM_IRQ; i++) {
+		ret = of_irq_parse_one(np, i, &map);
+		if (ret)
+			return ret;
+
+		of_phandle_args_to_fwspec(np, map.args, map.args_count, &priv->fwspec[i]);
+	}
+
+	return 0;
+}
+
+static int rzv2h_icu_init(struct device_node *node, struct device_node *parent)
+{
+	struct irq_domain *irq_domain, *parent_domain;
+	struct rzv2h_icu_priv *rzv2h_icu_data;
+	struct platform_device *pdev;
+	struct reset_control *resetn;
+	int ret;
+
+	pdev = of_find_device_by_node(node);
+	if (!pdev)
+		return -ENODEV;
+
+	parent_domain = irq_find_host(parent);
+	if (!parent_domain) {
+		dev_err(&pdev->dev, "cannot find parent domain\n");
+		ret = -ENODEV;
+		goto put_dev;
+	}
+
+	rzv2h_icu_data = devm_kzalloc(&pdev->dev, sizeof(*rzv2h_icu_data), GFP_KERNEL);
+	if (!rzv2h_icu_data) {
+		ret = -ENOMEM;
+		goto put_dev;
+	}
+
+	rzv2h_icu_data->irqchip = &rzv2h_icu_chip;
+
+	rzv2h_icu_data->base = devm_of_iomap(&pdev->dev, pdev->dev.of_node, 0, NULL);
+	if (IS_ERR(rzv2h_icu_data->base)) {
+		ret = PTR_ERR(rzv2h_icu_data->base);
+		goto put_dev;
+	}
+
+	ret = rzv2h_icu_parse_interrupts(rzv2h_icu_data, node);
+	if (ret) {
+		dev_err(&pdev->dev, "cannot parse interrupts: %d\n", ret);
+		goto put_dev;
+	}
+
+	resetn = devm_reset_control_get_exclusive(&pdev->dev, NULL);
+	if (IS_ERR(resetn)) {
+		ret = PTR_ERR(resetn);
+		goto put_dev;
+	}
+
+	ret = reset_control_deassert(resetn);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to deassert resetn pin, %d\n", ret);
+		goto put_dev;
+	}
+
+	pm_runtime_enable(&pdev->dev);
+	ret = pm_runtime_resume_and_get(&pdev->dev);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "pm_runtime_resume_and_get failed: %d\n", ret);
+		goto pm_disable;
+	}
+
+	raw_spin_lock_init(&rzv2h_icu_data->lock);
+
+	irq_domain = irq_domain_add_hierarchy(parent_domain, 0, ICU_NUM_IRQ, node,
+					      &rzv2h_icu_domain_ops, rzv2h_icu_data);
+	if (!irq_domain) {
+		dev_err(&pdev->dev, "failed to add irq domain\n");
+		ret = -ENOMEM;
+		goto pm_put;
+	}
+
+	/*
+	 * coccicheck complains about a missing put_device call before returning, but it's a false
+	 * positive. We still need &pdev->dev after successfully returning from this function.
+	 */
+	return 0;
+
+pm_put:
+	pm_runtime_put(&pdev->dev);
+pm_disable:
+	pm_runtime_disable(&pdev->dev);
+	reset_control_assert(resetn);
+put_dev:
+	put_device(&pdev->dev);
+
+	return ret;
+}
+
+IRQCHIP_PLATFORM_DRIVER_BEGIN(rzv2h_icu)
+IRQCHIP_MATCH("renesas,r9a09g057-icu", rzv2h_icu_init)
+IRQCHIP_PLATFORM_DRIVER_END(rzv2h_icu)
+MODULE_AUTHOR("Fabrizio Castro <fabrizio.castro.jz@renesas.com>");
+MODULE_DESCRIPTION("Renesas RZ/V2H(P) ICU Driver");
diff --git a/drivers/irqchip/irq-riscv-aplic-main.c b/drivers/irqchip/irq-riscv-aplic-main.c
index 900e72541db9..93e7c51f944a 100644
--- a/drivers/irqchip/irq-riscv-aplic-main.c
+++ b/drivers/irqchip/irq-riscv-aplic-main.c
@@ -207,7 +207,8 @@ static int aplic_probe(struct platform_device *pdev)
 	else
 		rc = aplic_direct_setup(dev, regs);
 	if (rc)
-		dev_err(dev, "failed to setup APLIC in %s mode\n", msi_mode ? "MSI" : "direct");
+		dev_err_probe(dev, rc, "failed to setup APLIC in %s mode\n",
+			      msi_mode ? "MSI" : "direct");
 
 #ifdef CONFIG_ACPI
 	if (!acpi_disabled)
diff --git a/drivers/irqchip/irq-riscv-aplic-msi.c b/drivers/irqchip/irq-riscv-aplic-msi.c
index 945bff28265c..fb8d1838609f 100644
--- a/drivers/irqchip/irq-riscv-aplic-msi.c
+++ b/drivers/irqchip/irq-riscv-aplic-msi.c
@@ -266,6 +266,9 @@ int aplic_msi_setup(struct device *dev, void __iomem *regs)
 			if (msi_domain)
 				dev_set_msi_domain(dev, msi_domain);
 		}
+
+		if (!dev_get_msi_domain(dev))
+			return -EPROBE_DEFER;
 	}
 
 	if (!msi_create_device_irq_domain(dev, MSI_DEFAULT_DOMAIN, &aplic_msi_template,
diff --git a/drivers/irqchip/irq-sifive-plic.c b/drivers/irqchip/irq-sifive-plic.c
index 36dbcf2d728a..bf69a4802b71 100644
--- a/drivers/irqchip/irq-sifive-plic.c
+++ b/drivers/irqchip/irq-sifive-plic.c
@@ -252,11 +252,10 @@ static int plic_irq_suspend(void)
 
 	priv = per_cpu_ptr(&plic_handlers, smp_processor_id())->priv;
 
-	for (i = 0; i < priv->nr_irqs; i++)
-		if (readl(priv->regs + PRIORITY_BASE + i * PRIORITY_PER_ID))
-			__set_bit(i, priv->prio_save);
-		else
-			__clear_bit(i, priv->prio_save);
+	for (i = 0; i < priv->nr_irqs; i++) {
+		__assign_bit(i, priv->prio_save,
+			     readl(priv->regs + PRIORITY_BASE + i * PRIORITY_PER_ID));
+	}
 
 	for_each_cpu(cpu, cpu_present_mask) {
 		struct plic_handler *handler = per_cpu_ptr(&plic_handlers, cpu);
diff --git a/drivers/irqchip/irq-stm32mp-exti.c b/drivers/irqchip/irq-stm32mp-exti.c
index 33e0cfdea654..cb83d6cc6113 100644
--- a/drivers/irqchip/irq-stm32mp-exti.c
+++ b/drivers/irqchip/irq-stm32mp-exti.c
@@ -696,8 +696,7 @@ static int stm32mp_exti_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	if (of_property_read_bool(np, "interrupts-extended"))
-		host_data->dt_has_irqs_desc = true;
+	host_data->dt_has_irqs_desc = of_property_present(np, "interrupts-extended");
 
 	return 0;
 }
diff --git a/drivers/irqchip/irq-thead-c900-aclint-sswi.c b/drivers/irqchip/irq-thead-c900-aclint-sswi.c
new file mode 100644
index 000000000000..b0e366ade427
--- /dev/null
+++ b/drivers/irqchip/irq-thead-c900-aclint-sswi.c
@@ -0,0 +1,176 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2024 Inochi Amaoto <inochiama@gmail.com>
+ */
+
+#define pr_fmt(fmt) "thead-c900-aclint-sswi: " 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/module.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/pci.h>
+#include <linux/spinlock.h>
+#include <linux/smp.h>
+#include <linux/string_choices.h>
+#include <asm/sbi.h>
+#include <asm/vendorid_list.h>
+
+#define THEAD_ACLINT_xSWI_REGISTER_SIZE		4
+
+#define THEAD_C9XX_CSR_SXSTATUS			0x5c0
+#define THEAD_C9XX_SXSTATUS_CLINTEE		BIT(17)
+
+static int sswi_ipi_virq __ro_after_init;
+static DEFINE_PER_CPU(void __iomem *, sswi_cpu_regs);
+
+static void thead_aclint_sswi_ipi_send(unsigned int cpu)
+{
+	writel_relaxed(0x1, per_cpu(sswi_cpu_regs, cpu));
+}
+
+static void thead_aclint_sswi_ipi_clear(void)
+{
+	writel_relaxed(0x0, this_cpu_read(sswi_cpu_regs));
+}
+
+static void thead_aclint_sswi_ipi_handle(struct irq_desc *desc)
+{
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+
+	chained_irq_enter(chip, desc);
+
+	csr_clear(CSR_IP, IE_SIE);
+	thead_aclint_sswi_ipi_clear();
+
+	ipi_mux_process();
+
+	chained_irq_exit(chip, desc);
+}
+
+static int thead_aclint_sswi_starting_cpu(unsigned int cpu)
+{
+	enable_percpu_irq(sswi_ipi_virq, irq_get_trigger_type(sswi_ipi_virq));
+
+	return 0;
+}
+
+static int thead_aclint_sswi_dying_cpu(unsigned int cpu)
+{
+	thead_aclint_sswi_ipi_clear();
+
+	disable_percpu_irq(sswi_ipi_virq);
+
+	return 0;
+}
+
+static int __init thead_aclint_sswi_parse_irq(struct fwnode_handle *fwnode,
+					      void __iomem *reg)
+{
+	struct of_phandle_args parent;
+	unsigned long hartid;
+	u32 contexts, i;
+	int rc, cpu;
+
+	contexts = of_irq_count(to_of_node(fwnode));
+	if (!(contexts)) {
+		pr_err("%pfwP: no ACLINT SSWI context available\n", fwnode);
+		return -EINVAL;
+	}
+
+	for (i = 0; i < contexts; i++) {
+		rc = of_irq_parse_one(to_of_node(fwnode), i, &parent);
+		if (rc)
+			return rc;
+
+		rc = riscv_of_parent_hartid(parent.np, &hartid);
+		if (rc)
+			return rc;
+
+		if (parent.args[0] != RV_IRQ_SOFT)
+			return -ENOTSUPP;
+
+		cpu = riscv_hartid_to_cpuid(hartid);
+
+		per_cpu(sswi_cpu_regs, cpu) = reg + i * THEAD_ACLINT_xSWI_REGISTER_SIZE;
+	}
+
+	pr_info("%pfwP: register %u CPU%s\n", fwnode, contexts, str_plural(contexts));
+
+	return 0;
+}
+
+static int __init thead_aclint_sswi_probe(struct fwnode_handle *fwnode)
+{
+	struct irq_domain *domain;
+	void __iomem *reg;
+	int virq, rc;
+
+	/* If it is T-HEAD CPU, check whether SSWI is enabled */
+	if (riscv_cached_mvendorid(0) == THEAD_VENDOR_ID &&
+	    !(csr_read(THEAD_C9XX_CSR_SXSTATUS) & THEAD_C9XX_SXSTATUS_CLINTEE))
+		return -ENOTSUPP;
+
+	if (!is_of_node(fwnode))
+		return -EINVAL;
+
+	reg = of_iomap(to_of_node(fwnode), 0);
+	if (!reg)
+		return -ENOMEM;
+
+	/* Parse SSWI setting */
+	rc = thead_aclint_sswi_parse_irq(fwnode, reg);
+	if (rc < 0)
+		return rc;
+
+	/* If mulitple SSWI devices are present, do not register irq again */
+	if (sswi_ipi_virq)
+		return 0;
+
+	/* Find riscv intc domain and create IPI irq mapping */
+	domain = irq_find_matching_fwnode(riscv_get_intc_hwnode(), DOMAIN_BUS_ANY);
+	if (!domain) {
+		pr_err("%pfwP: Failed to find INTC domain\n", fwnode);
+		return -ENOENT;
+	}
+
+	sswi_ipi_virq = irq_create_mapping(domain, RV_IRQ_SOFT);
+	if (!sswi_ipi_virq) {
+		pr_err("unable to create ACLINT SSWI IRQ mapping\n");
+		return -ENOMEM;
+	}
+
+	/* Register SSWI irq and handler */
+	virq = ipi_mux_create(BITS_PER_BYTE, thead_aclint_sswi_ipi_send);
+	if (virq <= 0) {
+		pr_err("unable to create muxed IPIs\n");
+		irq_dispose_mapping(sswi_ipi_virq);
+		return virq < 0 ? virq : -ENOMEM;
+	}
+
+	irq_set_chained_handler(sswi_ipi_virq, thead_aclint_sswi_ipi_handle);
+
+	cpuhp_setup_state(CPUHP_AP_IRQ_THEAD_ACLINT_SSWI_STARTING,
+			  "irqchip/thead-aclint-sswi:starting",
+			  thead_aclint_sswi_starting_cpu,
+			  thead_aclint_sswi_dying_cpu);
+
+	riscv_ipi_set_virq_range(virq, BITS_PER_BYTE);
+
+	/* Announce that SSWI is providing IPIs */
+	pr_info("providing IPIs using THEAD ACLINT SSWI\n");
+
+	return 0;
+}
+
+static int __init thead_aclint_sswi_early_probe(struct device_node *node,
+						struct device_node *parent)
+{
+	return thead_aclint_sswi_probe(&node->fwnode);
+}
+IRQCHIP_DECLARE(thead_aclint_sswi, "thead,c900-aclint-sswi", thead_aclint_sswi_early_probe);