Merge tag 'irqchip-5.7' of...

Merge tag 'irqchip-5.7' of git://git.kernel.org/pub/scm/linux/kernel/git/maz/arm-platforms into irq/core

Pull irqchip updates from Marc Zyngier:

 - Second batch of the GICv4.1 support saga
 - Level triggered interrupt support for the stm32 controller
 - Versatile-fpga chained interrupt fixes
 - DT support for cascaded VIC interrupt controller
 - RPi irqchip initialization fixes
 - Multi-instance support for the Xilinx interrupt controller
 - Multi-instance support for the PLIC interrupt controller
 - CPU hotplug support for the PLIC interrupt controller
 - Ingenic X1000 TCU support
 - Small fixes all over the shop (GICv3, GICv4, Xilinx, Atmel, sa1111)
 - Cleanups (setup_irq removal, zero-length array removal)

arch/arm/common/sa1111.c

@@ -302,10 +302,13 @@ static int sa1111_retrigger_irq(struct irq_data *d)
 			break;
 	}
 
-	if (i == 8)
+	if (i == 8) {
 		pr_err("Danger Will Robinson: failed to re-trigger IRQ%d\n",
 		       d->irq);
-	return i == 8 ? -1 : 0;
+		return 0;
+	}
+
+	return 1;
 }
 
 static int sa1111_type_irq(struct irq_data *d, unsigned int flags)

arch/microblaze/Kconfig

@@ -47,6 +47,8 @@ config MICROBLAZE
 	select CPU_NO_EFFICIENT_FFS
 	select MMU_GATHER_NO_RANGE if MMU
 	select SPARSE_IRQ
+	select GENERIC_IRQ_MULTI_HANDLER
+	select HANDLE_DOMAIN_IRQ
 
 # Endianness selection
 choice

arch/microblaze/include/asm/irq.h

@@ -14,7 +14,4 @@
 struct pt_regs;
 extern void do_IRQ(struct pt_regs *regs);
 
-/* should be defined in each interrupt controller driver */
-extern unsigned int xintc_get_irq(void);
-
 #endif /* _ASM_MICROBLAZE_IRQ_H */

arch/microblaze/kernel/irq.c

@@ -20,29 +20,10 @@
 #include <linux/irqchip.h>
 #include <linux/of_irq.h>
 
-static u32 concurrent_irq;
-
 void __irq_entry do_IRQ(struct pt_regs *regs)
 {
-	unsigned int irq;
-	struct pt_regs *old_regs = set_irq_regs(regs);
 	trace_hardirqs_off();
-
-	irq_enter();
-	irq = xintc_get_irq();
-next_irq:
-	BUG_ON(!irq);
-	generic_handle_irq(irq);
-
-	irq = xintc_get_irq();
-	if (irq != -1U) {
-		pr_debug("next irq: %d\n", irq);
-		++concurrent_irq;
-		goto next_irq;
-	}
-
-	irq_exit();
-	set_irq_regs(old_regs);
+	handle_arch_irq(regs);
 	trace_hardirqs_on();
 }
 

arch/riscv/kernel/traps.c

@@ -157,5 +157,5 @@ void __init trap_init(void)
 	/* Set the exception vector address */
 	csr_write(CSR_TVEC, &handle_exception);
 	/* Enable interrupts */
-	csr_write(CSR_IE, IE_SIE | IE_EIE);
+	csr_write(CSR_IE, IE_SIE);
 }

drivers/irqchip/Kconfig

@@ -458,7 +458,7 @@ config IMX_IRQSTEER
 	  Support for the i.MX IRQSTEER interrupt multiplexer/remapper.
 
 config IMX_INTMUX
-	def_bool y if ARCH_MXC
+	def_bool y if ARCH_MXC || COMPILE_TEST
 	select IRQ_DOMAIN
 	help
 	  Support for the i.MX INTMUX interrupt multiplexer.

drivers/irqchip/irq-atmel-aic.c

@@ -83,7 +83,7 @@ static int aic_retrigger(struct irq_data *d)
 	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)

drivers/irqchip/irq-atmel-aic5.c

@@ -128,7 +128,7 @@ static int aic5_retrigger(struct irq_data *d)
 	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)

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 @@ static int __init armctrl_of_init(struct device_node *node,
 {
 	void __iomem *base;
 	int irq, b, i;
+	u32 reg;
 
 	base = of_iomap(node, 0);
 	if (!base)
@@ -157,6 +159,19 @@ static int __init armctrl_of_init(struct device_node *node,
 				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) {

drivers/irqchip/irq-bcm7038-l1.c

@@ -50,7 +50,7 @@ struct bcm7038_l1_chip {
 
 struct bcm7038_l1_cpu {
 	void __iomem		*map_base;
-	u32			mask_cache[0];
+	u32			mask_cache[];
 };
 
 /*

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

@@ -96,6 +96,7 @@ struct its_node {
 	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;
@@ -188,6 +189,15 @@ 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)
 
+/*
+ * 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;
@@ -197,7 +207,7 @@ static u16 get_its_list(struct its_vm *vm)
 		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);
 	}
 
@@ -239,15 +249,41 @@ static struct its_vlpi_map *get_vlpi_map(struct irq_data *d)
 	return NULL;
 }
 
-static int irq_to_cpuid(struct irq_data *d)
+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_device *its_dev = irq_data_get_irq_chip_data(d);
 	struct its_vlpi_map *map = get_vlpi_map(d);
+	int cpu;
 
-	if (map)
-		return map->vpe->col_idx;
+	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);
 
-	return its_dev->event_map.col_map[its_get_event_id(d)];
+	if (map)
+		vpe_to_cpuid_unlock(map->vpe, flags);
 }
 
 static struct its_collection *valid_col(struct its_collection *col)
@@ -353,6 +389,15 @@ struct its_cmd_desc {
 		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;
 	};
 };
 
@@ -501,6 +546,31 @@ 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 */
@@ -866,6 +936,26 @@ static struct its_vpe *its_build_invdb_cmd(struct its_node *its,
 	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)
 {
@@ -1214,7 +1304,7 @@ static void its_send_vmovp(struct its_vpe *vpe)
 		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];
@@ -1321,7 +1411,7 @@ static void lpi_write_config(struct irq_data *d, u8 clr, u8 set)
 
 static void wait_for_syncr(void __iomem *rdbase)
 {
-	while (gic_read_lpir(rdbase + GICR_SYNCR) & 1)
+	while (readl_relaxed(rdbase + GICR_SYNCR) & 1)
 		cpu_relax();
 }
 
@@ -1329,7 +1419,9 @@ 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);
@@ -1344,10 +1436,14 @@ static void direct_lpi_inv(struct irq_data *d)
 	}
 
 	/* Target the redistributor this LPI is currently routed to */
-	rdbase = per_cpu_ptr(gic_rdists->rdist, irq_to_cpuid(d))->rd_base;
+	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)
@@ -1499,12 +1595,31 @@ static int its_irq_set_irqchip_state(struct irq_data *d,
 	return 0;
 }
 
+/*
+ * 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);
@@ -1538,7 +1653,7 @@ static void its_unmap_vm(struct its_node *its, struct its_vm *vm)
 	unsigned long flags;
 
 	/* Not using the ITS list? Everything is always mapped. */
-	if (!its_list_map)
+	if (gic_requires_eager_mapping())
 		return;
 
 	raw_spin_lock_irqsave(&vmovp_lock, flags);
@@ -2036,18 +2151,17 @@ static void its_write_baser(struct its_node *its, struct its_baser *baser,
 }
 
 static int its_setup_baser(struct its_node *its, struct its_baser *baser,
-			   u64 cache, u64 shr, u32 psz, u32 order,
-			   bool indirect)
+			   u64 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",
@@ -2120,25 +2234,6 @@ static int its_setup_baser(struct its_node *its, struct its_baser *baser,
 		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],
@@ -2164,13 +2259,14 @@ static int its_setup_baser(struct its_node *its, struct its_baser *baser,
 
 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 */
@@ -2288,11 +2384,58 @@ static void its_free_tables(struct its_node *its)
 	}
 }
 
+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)
@@ -2303,16 +2446,22 @@ static int its_alloc_tables(struct its_node *its)
 		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,
+			indirect = its_parse_indirect_baser(its, baser, &order,
 							    device_ids(its));
 			break;
 
@@ -2328,20 +2477,18 @@ static int its_alloc_tables(struct its_node *its)
 				}
 			}
 
-			indirect = its_parse_indirect_baser(its, baser,
-							    psz, &order,
+			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;
 	}
@@ -2452,6 +2599,10 @@ static bool allocate_vpe_l2_table(int cpu, u32 id)
 	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;
@@ -3482,17 +3633,25 @@ static int its_vpe_set_affinity(struct irq_data *d,
 {
 	struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
 	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)
+	from = vpe_to_cpuid_lock(vpe, &flags);
+	if (from == cpu)
 		goto out;
 
-	from = vpe->col_idx;
 	vpe->col_idx = cpu;
 
 	/*
@@ -3508,6 +3667,7 @@ static int its_vpe_set_affinity(struct irq_data *d,
 
 out:
 	irq_data_update_effective_affinity(d, cpumask_of(cpu));
+	vpe_to_cpuid_unlock(vpe, flags);
 
 	return IRQ_SET_MASK_OK_DONE;
 }
@@ -3528,7 +3688,7 @@ static void its_vpe_schedule(struct its_vpe *vpe)
 	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
@@ -3619,9 +3779,11 @@ static void its_vpe_send_inv(struct irq_data *d)
 		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(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);
 	}
@@ -3675,12 +3837,18 @@ static int its_vpe_set_irqchip_state(struct irq_data *d,
 	return 0;
 }
 
+static int its_vpe_retrigger(struct irq_data *d)
+{
+	return !its_vpe_set_irqchip_state(d, IRQCHIP_STATE_PENDING, true);
+}
+
 static struct irq_chip its_vpe_irq_chip = {
 	.name			= "GICv4-vpe",
 	.irq_mask		= its_vpe_mask_irq,
 	.irq_unmask		= its_vpe_unmask_irq,
 	.irq_eoi		= irq_chip_eoi_parent,
 	.irq_set_affinity	= its_vpe_set_affinity,
+	.irq_retrigger		= its_vpe_retrigger,
 	.irq_set_irqchip_state	= its_vpe_set_irqchip_state,
 	.irq_set_vcpu_affinity	= its_vpe_set_vcpu_affinity,
 };
@@ -3782,8 +3950,12 @@ static void its_vpe_4_1_invall(struct its_vpe *vpe)
 	val |= FIELD_PREP(GICR_INVALLR_VPEID, vpe->vpe_id);
 
 	/* 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(val, rdbase + GICR_INVALLR);
+
+	wait_for_syncr(rdbase);
+	raw_spin_unlock(&gic_data_rdist_cpu(vpe->col_idx)->rd_lock);
 }
 
 static int its_vpe_4_1_set_vcpu_affinity(struct irq_data *d, void *vcpu_info)
@@ -3818,6 +3990,221 @@ static struct irq_chip its_vpe_4_1_irq_chip = {
 	.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.
+	 */
+	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);
@@ -3851,6 +4238,7 @@ static int its_vpe_init(struct its_vpe *vpe)
 		return -ENOMEM;
 	}
 
+	raw_spin_lock_init(&vpe->vpe_lock);
 	vpe->vpe_id = vpe_id;
 	vpe->vpt_page = vpt_page;
 	if (gic_rdists->has_rvpeid)
@@ -3960,8 +4348,12 @@ static int its_vpe_irq_domain_activate(struct irq_domain *domain,
 	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 */
@@ -3987,10 +4379,10 @@ static void its_vpe_irq_domain_deactivate(struct irq_domain *domain,
 	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) {
@@ -4404,7 +4796,7 @@ static int __init its_probe_one(struct resource *res,
 	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;
@@ -4455,6 +4847,13 @@ static int __init its_probe_one(struct resource *res,
 
 		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",
@@ -4468,7 +4867,7 @@ static int __init its_probe_one(struct resource *res,
 				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;
@@ -4535,6 +4934,9 @@ static int __init its_probe_one(struct resource *res,
 	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:
@@ -4818,6 +5220,7 @@ int __init its_init(struct fwnode_handle *handle, struct rdists *rdists,
 	struct device_node *of_node;
 	struct its_node *its;
 	bool has_v4 = false;
+	bool has_v4_1 = false;
 	int err;
 
 	gic_rdists = rdists;
@@ -4838,12 +5241,25 @@ int __init its_init(struct fwnode_handle *handle, struct rdists *rdists,
 	if (err)
 		return err;
 
-	list_for_each_entry(its, &its_nodes, entry)
+	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");
 		}

drivers/irqchip/irq-gic-v3.c

@@ -723,6 +723,7 @@ static void __init gic_dist_init(void)
 	unsigned int i;
 	u64 affinity;
 	void __iomem *base = gic_data.dist_base;
+	u32 val;
 
 	/* Disable the distributor */
 	writel_relaxed(0, base + GICD_CTLR);
@@ -755,9 +756,14 @@ static void __init gic_dist_init(void)
 	/* 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
@@ -828,6 +834,7 @@ static int __gic_populate_rdist(struct redist_region *region, void __iomem *ptr)
 	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;
 
@@ -1581,7 +1588,6 @@ static int __init gic_init_bases(void __iomem *dist_base,
 
 	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;
@@ -1592,6 +1598,8 @@ static int __init gic_init_bases(void __iomem *dist_base,
 		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 ");
@@ -1757,6 +1765,7 @@ static void __init gic_of_setup_kvm_info(struct device_node *node)
 		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);
 }
 
@@ -2072,6 +2081,7 @@ static void __init gic_acpi_setup_kvm_info(void)
 	}
 
 	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);
 }
 

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 @@ int its_alloc_vcpu_irqs(struct its_vm *vm)
 	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 @@ int its_alloc_vcpu_irqs(struct its_vm *vm)
 	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);
@@ -138,18 +210,50 @@ static int its_send_vpe_cmd(struct its_vpe *vpe, struct its_cmd_info *info)
 	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 irq_desc *desc = irq_to_desc(vpe->irq);
+	struct its_cmd_info info = { };
+	int ret;
+
+	WARN_ON(preemptible());
+
+	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);
+	}
+
+	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;
+	struct its_cmd_info info = { };
 	int ret;
 
 	WARN_ON(preemptible());
 
-	info.cmd_type = on ? SCHEDULE_VPE : DESCHEDULE_VPE;
+	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 = on;
+		vpe->resident = true;
 
 	return ret;
 }
@@ -216,12 +320,28 @@ int its_prop_update_vlpi(int irq, u8 config, bool inv)
 	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;
 	}
 

drivers/irqchip/irq-i8259.c

@@ -268,15 +268,6 @@ static void init_8259A(int auto_eoi)
 	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 @@ static const struct irq_domain_ops i8259A_ops = {
  */
 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 @@ struct irq_domain * __init __init_i8259_irqs(struct device_node *node)
 	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;
 }

drivers/irqchip/irq-ingenic-tcu.c

@@ -180,3 +180,4 @@ static int __init ingenic_tcu_irq_init(struct device_node *np,
 IRQCHIP_DECLARE(jz4740_tcu_irq, "ingenic,jz4740-tcu", ingenic_tcu_irq_init);
 IRQCHIP_DECLARE(jz4725b_tcu_irq, "ingenic,jz4725b-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);

drivers/irqchip/irq-ingenic.c

@@ -58,11 +58,6 @@ static irqreturn_t intc_cascade(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-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)
 {
@@ -130,7 +125,9 @@ static int __init ingenic_intc_of_init(struct device_node *node,
 		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, 0,
+			"SoC intc cascade interrupt", NULL))
+		pr_err("Failed to register SoC intc cascade interrupt\n");
 	return 0;
 
 out_domain_remove:

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

@@ -461,7 +461,7 @@ static int intc_irqpin_probe(struct platform_device *pdev)
 		}
 
 		i->iomem = devm_ioremap(dev, io[k]->start,
-						resource_size(io[k]));
+					resource_size(io[k]));
 		if (!i->iomem) {
 			dev_err(dev, "failed to remap IOMEM\n");
 			ret = -ENXIO;

drivers/irqchip/irq-sifive-plic.c

@@ -4,6 +4,7 @@
  * 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>
@@ -55,7 +56,14 @@
 #define     CONTEXT_THRESHOLD		0x00
 #define     CONTEXT_CLAIM		0x04
 
-static void __iomem *plic_regs;
+#define	PLIC_DISABLE_THRESHOLD		0xf
+#define	PLIC_ENABLE_THRESHOLD		0
+
+struct plic_priv {
+	struct cpumask lmask;
+	struct irq_domain *irqdomain;
+	void __iomem *regs;
+};
 
 struct plic_handler {
 	bool			present;
@@ -66,6 +74,7 @@ struct plic_handler {
 	 */
 	raw_spinlock_t		enable_lock;
 	void __iomem		*enable_base;
+	struct plic_priv	*priv;
 };
 static DEFINE_PER_CPU(struct plic_handler, plic_handlers);
 
@@ -84,31 +93,40 @@ static inline void plic_toggle(struct plic_handler *handler,
 }
 
 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_get_chip_data(d->irq);
 
-	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_get_chip_data(d->irq);
+
+	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_get_chip_data(d->irq);
+
+	plic_irq_toggle(&priv->lmask, d, 0);
 }
 
 #ifdef CONFIG_SMP
@@ -116,17 +134,21 @@ static int plic_set_affinity(struct irq_data *d,
 			     const struct cpumask *mask_val, bool force)
 {
 	unsigned int cpu;
+	struct cpumask amask;
+	struct plic_priv *priv = irq_get_chip_data(d->irq);
+
+	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, 1);
 
 	irq_data_update_effective_affinity(d, cpumask_of(cpu));
 
@@ -187,8 +209,6 @@ static const struct irq_domain_ops plic_irqdomain_ops = {
 	.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
@@ -205,7 +225,7 @@ static void plic_handle_irq(struct pt_regs *regs)
 
 	csr_clear(CSR_IE, IE_EIE);
 	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",
@@ -230,20 +250,48 @@ static int plic_find_hart_id(struct device_node *node)
 	return -1;
 }
 
+static void plic_set_threshold(struct plic_handler *handler, u32 threshold)
+{
+	/* priority must be > threshold to trigger an interrupt */
+	writel(threshold, handler->hart_base + CONTEXT_THRESHOLD);
+}
+
+static int plic_dying_cpu(unsigned int cpu)
+{
+	struct plic_handler *handler = this_cpu_ptr(&plic_handlers);
+
+	csr_clear(CSR_IE, IE_EIE);
+	plic_set_threshold(handler, PLIC_DISABLE_THRESHOLD);
+
+	return 0;
+}
+
+static int plic_starting_cpu(unsigned int cpu)
+{
+	struct plic_handler *handler = this_cpu_ptr(&plic_handlers);
+
+	csr_set(CSR_IE, IE_EIE);
+	plic_set_threshold(handler, PLIC_ENABLE_THRESHOLD);
+
+	return 0;
+}
+
 static int __init plic_init(struct device_node *node,
 		struct device_node *parent)
 {
 	int error = 0, nr_contexts, nr_handlers = 0, i;
 	u32 nr_irqs;
+	struct plic_priv *priv;
 
-	if (plic_regs) {
-		pr_warn("PLIC already present.\n");
-		return -ENXIO;
-	}
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
 
-	plic_regs = of_iomap(node, 0);
-	if (WARN_ON(!plic_regs))
-		return -EIO;
+	priv->regs = of_iomap(node, 0);
+	if (WARN_ON(!priv->regs)) {
+		error = -EIO;
+		goto out_free_priv;
+	}
 
 	error = -EINVAL;
 	of_property_read_u32(node, "riscv,ndev", &nr_irqs);
@@ -257,9 +305,9 @@ static int __init plic_init(struct device_node *node,
 		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++) {
@@ -267,7 +315,6 @@ static int __init plic_init(struct device_node *node,
 		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);
@@ -301,32 +348,36 @@ static int __init plic_init(struct device_node *node,
 		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++;
 	}
 
+	cpuhp_setup_state(CPUHP_AP_IRQ_SIFIVE_PLIC_STARTING,
+				  "irqchip/sifive/plic:starting",
+				  plic_starting_cpu, plic_dying_cpu);
 	pr_info("mapped %d interrupts with %d handlers for %d contexts.\n",
 		nr_irqs, nr_handlers, nr_contexts);
 	set_handle_irq(plic_handle_irq);
 	return 0;
 
 out_iounmap:
-	iounmap(plic_regs);
+	iounmap(priv->regs);
+out_free_priv:
+	kfree(priv);
 	return error;
 }
 

drivers/irqchip/irq-stm32-exti.c

@@ -604,12 +604,24 @@ static void stm32_exti_h_syscore_deinit(void)
 	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,

drivers/irqchip/irq-versatile-fpga.c

@@ -6,6 +6,7 @@
 #include <linux/irq.h>
 #include <linux/io.h>
 #include <linux/irqchip.h>
+#include <linux/irqchip/chained_irq.h>
 #include <linux/irqchip/versatile-fpga.h>
 #include <linux/irqdomain.h>
 #include <linux/module.h>
@@ -68,12 +69,16 @@ static void fpga_irq_unmask(struct irq_data *d)
 
 static void fpga_irq_handle(struct irq_desc *desc)
 {
+	struct irq_chip *chip = irq_desc_get_chip(desc);
 	struct fpga_irq_data *f = irq_desc_get_handler_data(desc);
-	u32 status = readl(f->base + IRQ_STATUS);
+	u32 status;
+
+	chained_irq_enter(chip, desc);
 
+	status = readl(f->base + IRQ_STATUS);
 	if (status == 0) {
 		do_bad_IRQ(desc);
-		return;
+		goto out;
 	}
 
 	do {
@@ -82,6 +87,9 @@ static void fpga_irq_handle(struct irq_desc *desc)
 		status &= ~(1 << irq);
 		generic_handle_irq(irq_find_mapping(f->domain, irq));
 	} while (status);
+
+out:
+	chained_irq_exit(chip, desc);
 }
 
 /*
@@ -204,6 +212,9 @@ int __init fpga_irq_of_init(struct device_node *node,
 	if (of_property_read_u32(node, "valid-mask", &valid_mask))
 		valid_mask = 0;
 
+	writel(clear_mask, base + IRQ_ENABLE_CLEAR);
+	writel(clear_mask, base + FIQ_ENABLE_CLEAR);
+
 	/* Some chips are cascaded from a parent IRQ */
 	parent_irq = irq_of_parse_and_map(node, 0);
 	if (!parent_irq) {
@@ -213,9 +224,6 @@ int __init fpga_irq_of_init(struct device_node *node,
 
 	fpga_irq_init(base, node->name, 0, parent_irq, valid_mask, node);
 
-	writel(clear_mask, base + IRQ_ENABLE_CLEAR);
-	writel(clear_mask, base + FIQ_ENABLE_CLEAR);
-
 	/*
 	 * On Versatile AB/PB, some secondary interrupts have a direct
 	 * pass-thru to the primary controller for IRQs 20 and 22-31 which need

drivers/irqchip/irq-vic.c

@@ -509,9 +509,7 @@ static int __init vic_of_init(struct device_node *node,
 	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 +517,14 @@ static int __init vic_of_init(struct device_node *node,
 
 	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;
 }

drivers/irqchip/irq-xilinx-intc.c

@@ -38,29 +38,31 @@ struct xintc_irq_chip {
 	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 @@ static void intc_enable_or_unmask(struct irq_data *d)
 	 * 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 +110,14 @@ static struct irq_chip intc_dev = {
 	.irq_mask_ack = intc_mask_ack,
 };
 
-unsigned int xintc_get_irq(void)
+static unsigned int xintc_get_irq_local(struct xintc_irq_chip *irqc)
 {
-	unsigned int hwirq, irq = -1;
+	unsigned int irq = 0;
+	u32 hwirq;
 
-	hwirq = xintc_read(IVR);
+	hwirq = xintc_read(irqc, IVR);
 	if (hwirq != -1U)
-		irq = irq_find_mapping(xintc_irqc->root_domain, hwirq);
+		irq = irq_find_mapping(irqc->root_domain, hwirq);
 
 	pr_debug("irq-xilinx: hwirq=%d, irq=%d\n", hwirq, irq);
 
@@ -118,15 +126,18 @@ unsigned int xintc_get_irq(void)
 
 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;
 }
 
@@ -138,43 +149,55 @@ static const struct irq_domain_ops xintc_irq_domain_ops = {
 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);
 	chained_irq_exit(chip, desc);
 }
 
+static void xil_intc_handle_irq(struct pt_regs *regs)
+{
+	u32 hwirq;
+	struct xintc_irq_chip *irqc = primary_intc;
+
+	do {
+		hwirq = xintc_read(irqc, IVR);
+		if (likely(hwirq != -1U)) {
+			int ret;
+
+			ret = handle_domain_irq(irqc->root_domain, hwirq, regs);
+			WARN_ONCE(ret, "Unhandled HWIRQ %d\n", hwirq);
+			continue;
+		}
+
+		break;
+	} while (1);
+}
+
 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 +206,35 @@ static int __init xilinx_intc_of_init(struct device_node *intc,
 		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 +246,17 @@ static int __init xilinx_intc_of_init(struct device_node *intc,
 		} 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;
+		set_handle_irq(xil_intc_handle_irq);
 	}
 
 	return 0;
 
-err_alloc:
-	xintc_irqc = NULL;
+error:
+	iounmap(irqc->base);
 	kfree(irqc);
 	return ret;
 

drivers/irqchip/qcom-irq-combiner.c

@@ -33,7 +33,7 @@ struct combiner {
 	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)

drivers/pinctrl/stm32/pinctrl-stm32.c

@@ -92,6 +92,7 @@ struct stm32_gpio_bank {
 	u32 bank_nr;
 	u32 bank_ioport_nr;
 	u32 pin_backup[STM32_GPIO_PINS_PER_BANK];
+	u8 irq_type[STM32_GPIO_PINS_PER_BANK];
 };
 
 struct stm32_pinctrl {
@@ -303,6 +304,50 @@ static const struct gpio_chip stm32_gpio_template = {
 	.get_direction		= stm32_gpio_get_direction,
 };
 
+static void stm32_gpio_irq_trigger(struct irq_data *d)
+{
+	struct stm32_gpio_bank *bank = d->domain->host_data;
+	int level;
+
+	/* If level interrupt type then retrig */
+	level = stm32_gpio_get(&bank->gpio_chip, d->hwirq);
+	if ((level == 0 && bank->irq_type[d->hwirq] == IRQ_TYPE_LEVEL_LOW) ||
+	    (level == 1 && bank->irq_type[d->hwirq] == IRQ_TYPE_LEVEL_HIGH))
+		irq_chip_retrigger_hierarchy(d);
+}
+
+static void stm32_gpio_irq_eoi(struct irq_data *d)
+{
+	irq_chip_eoi_parent(d);
+	stm32_gpio_irq_trigger(d);
+};
+
+static int stm32_gpio_set_type(struct irq_data *d, unsigned int type)
+{
+	struct stm32_gpio_bank *bank = d->domain->host_data;
+	u32 parent_type;
+
+	switch (type) {
+	case IRQ_TYPE_EDGE_RISING:
+	case IRQ_TYPE_EDGE_FALLING:
+	case IRQ_TYPE_EDGE_BOTH:
+		parent_type = type;
+		break;
+	case IRQ_TYPE_LEVEL_HIGH:
+		parent_type = IRQ_TYPE_EDGE_RISING;
+		break;
+	case IRQ_TYPE_LEVEL_LOW:
+		parent_type = IRQ_TYPE_EDGE_FALLING;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	bank->irq_type[d->hwirq] = type;
+
+	return irq_chip_set_type_parent(d, parent_type);
+};
+
 static int stm32_gpio_irq_request_resources(struct irq_data *irq_data)
 {
 	struct stm32_gpio_bank *bank = irq_data->domain->host_data;
@@ -330,13 +375,19 @@ static void stm32_gpio_irq_release_resources(struct irq_data *irq_data)
 	gpiochip_unlock_as_irq(&bank->gpio_chip, irq_data->hwirq);
 }
 
+static void stm32_gpio_irq_unmask(struct irq_data *d)
+{
+	irq_chip_unmask_parent(d);
+	stm32_gpio_irq_trigger(d);
+}
+
 static struct irq_chip stm32_gpio_irq_chip = {
 	.name		= "stm32gpio",
-	.irq_eoi	= irq_chip_eoi_parent,
+	.irq_eoi	= stm32_gpio_irq_eoi,
 	.irq_ack	= irq_chip_ack_parent,
 	.irq_mask	= irq_chip_mask_parent,
-	.irq_unmask	= irq_chip_unmask_parent,
-	.irq_set_type	= irq_chip_set_type_parent,
+	.irq_unmask	= stm32_gpio_irq_unmask,
+	.irq_set_type	= stm32_gpio_set_type,
 	.irq_set_wake	= irq_chip_set_wake_parent,
 	.irq_request_resources = stm32_gpio_irq_request_resources,
 	.irq_release_resources = stm32_gpio_irq_release_resources,

include/kvm/arm_vgic.h

@@ -70,6 +70,7 @@ struct vgic_global {
 
 	/* Hardware has GICv4? */
 	bool			has_gicv4;
+	bool			has_gicv4_1;
 
 	/* GIC system register CPU interface */
 	struct static_key_false gicv3_cpuif;

include/linux/cpuhotplug.h

@@ -102,6 +102,7 @@ enum cpuhp_state {
 	CPUHP_AP_IRQ_ARMADA_XP_STARTING,
 	CPUHP_AP_IRQ_BCM2836_STARTING,
 	CPUHP_AP_IRQ_MIPS_GIC_STARTING,
+	CPUHP_AP_IRQ_SIFIVE_PLIC_STARTING,
 	CPUHP_AP_ARM_MVEBU_COHERENCY,
 	CPUHP_AP_MICROCODE_LOADER,
 	CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING,

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

@@ -32,6 +32,8 @@ struct gic_kvm_info {
 	struct resource vctrl;
 	/* vlpi support */
 	bool		has_v4;
+	/* rvpeid support */
+	bool		has_v4_1;
 };
 
 const struct gic_kvm_info *gic_get_kvm_info(void);

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

@@ -57,6 +57,7 @@
 #define GICD_SPENDSGIR			0x0F20
 
 #define GICD_CTLR_RWP			(1U << 31)
+#define GICD_CTLR_nASSGIreq		(1U << 8)
 #define GICD_CTLR_DS			(1U << 6)
 #define GICD_CTLR_ARE_NS		(1U << 4)
 #define GICD_CTLR_ENABLE_G1A		(1U << 1)
@@ -90,6 +91,7 @@
 #define GICD_TYPER_ESPIS(typer)						\
 	(((typer) & GICD_TYPER_ESPI) ? GICD_TYPER_SPIS((typer) >> 27) : 0)
 
+#define GICD_TYPER2_nASSGIcap		(1U << 8)
 #define GICD_TYPER2_VIL			(1U << 7)
 #define GICD_TYPER2_VID			GENMASK(4, 0)
 
@@ -320,6 +322,9 @@
 #define GICR_VPENDBASER_NonShareable					\
 	GIC_BASER_SHAREABILITY(GICR_VPENDBASER, NonShareable)
 
+#define GICR_VPENDBASER_InnerShareable					\
+	GIC_BASER_SHAREABILITY(GICR_VPENDBASER, InnerShareable)
+
 #define GICR_VPENDBASER_nCnB	GIC_BASER_CACHEABILITY(GICR_VPENDBASER, INNER, nCnB)
 #define GICR_VPENDBASER_nC 	GIC_BASER_CACHEABILITY(GICR_VPENDBASER, INNER, nC)
 #define GICR_VPENDBASER_RaWt	GIC_BASER_CACHEABILITY(GICR_VPENDBASER, INNER, RaWt)
@@ -343,6 +348,15 @@
 #define GICR_VPENDBASER_4_1_VGRP1EN	(1ULL << 58)
 #define GICR_VPENDBASER_4_1_VPEID	GENMASK_ULL(15, 0)
 
+#define GICR_VSGIR			0x0080
+
+#define GICR_VSGIR_VPEID		GENMASK(15, 0)
+
+#define GICR_VSGIPENDR			0x0088
+
+#define GICR_VSGIPENDR_BUSY		(1U << 31)
+#define GICR_VSGIPENDR_PENDING		GENMASK(15, 0)
+
 /*
  * ITS registers, offsets from ITS_base
  */
@@ -366,6 +380,11 @@
 
 #define GITS_TRANSLATER			0x10040
 
+#define GITS_SGIR			0x20020
+
+#define GITS_SGIR_VPEID			GENMASK_ULL(47, 32)
+#define GITS_SGIR_VINTID		GENMASK_ULL(3, 0)
+
 #define GITS_CTLR_ENABLE		(1U << 0)
 #define GITS_CTLR_ImDe			(1U << 1)
 #define	GITS_CTLR_ITS_NUMBER_SHIFT	4
@@ -500,8 +519,9 @@
 #define GITS_CMD_VMAPTI			GITS_CMD_GICv4(GITS_CMD_MAPTI)
 #define GITS_CMD_VMOVI			GITS_CMD_GICv4(GITS_CMD_MOVI)
 #define GITS_CMD_VSYNC			GITS_CMD_GICv4(GITS_CMD_SYNC)
-/* VMOVP and INVDB are the odd ones, as they dont have a physical counterpart */
+/* VMOVP, VSGI and INVDB are the odd ones, as they dont have a physical counterpart */
 #define GITS_CMD_VMOVP			GITS_CMD_GICv4(2)
+#define GITS_CMD_VSGI			GITS_CMD_GICv4(3)
 #define GITS_CMD_INVDB			GITS_CMD_GICv4(0xe)
 
 /*
@@ -650,6 +670,7 @@
 
 struct rdists {
 	struct {
+		raw_spinlock_t	rd_lock;
 		void __iomem	*rd_base;
 		struct page	*pend_page;
 		phys_addr_t	phys_base;

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

@@ -49,10 +49,22 @@ struct its_vpe {
 		};
 		/* GICv4.1 implementations */
 		struct {
+			struct fwnode_handle	*fwnode;
+			struct irq_domain	*sgi_domain;
+			struct {
+				u8	priority;
+				bool	enabled;
+				bool	group;
+			}			sgi_config[16];
 			atomic_t vmapp_count;
 		};
 	};
 
+	/*
+	 * Ensures mutual exclusion between affinity setting of the
+	 * vPE and vLPI operations using vpe->col_idx.
+	 */
+	raw_spinlock_t		vpe_lock;
 	/*
 	 * This collection ID is used to indirect the target
 	 * redistributor for this VPE. The ID itself isn't involved in
@@ -93,6 +105,7 @@ enum its_vcpu_info_cmd_type {
 	SCHEDULE_VPE,
 	DESCHEDULE_VPE,
 	INVALL_VPE,
+	PROP_UPDATE_VSGI,
 };
 
 struct its_cmd_info {
@@ -105,19 +118,27 @@ struct its_cmd_info {
 			bool		g0en;
 			bool		g1en;
 		};
+		struct {
+			u8		priority;
+			bool		group;
+		};
 	};
 };
 
 int its_alloc_vcpu_irqs(struct its_vm *vm);
 void its_free_vcpu_irqs(struct its_vm *vm);
-int its_schedule_vpe(struct its_vpe *vpe, bool on);
+int its_make_vpe_resident(struct its_vpe *vpe, bool g0en, bool g1en);
+int its_make_vpe_non_resident(struct its_vpe *vpe, bool db);
 int its_invall_vpe(struct its_vpe *vpe);
 int its_map_vlpi(int irq, struct its_vlpi_map *map);
 int its_get_vlpi(int irq, struct its_vlpi_map *map);
 int its_unmap_vlpi(int irq);
 int its_prop_update_vlpi(int irq, u8 config, bool inv);
+int its_prop_update_vsgi(int irq, u8 priority, bool group);
 
 struct irq_domain_ops;
-int its_init_v4(struct irq_domain *domain, const struct irq_domain_ops *ops);
+int its_init_v4(struct irq_domain *domain,
+		const struct irq_domain_ops *vpe_ops,
+		const struct irq_domain_ops *sgi_ops);
 
 #endif

virt/kvm/arm/vgic/vgic-v3.c

@@ -595,7 +595,9 @@ int vgic_v3_probe(const struct gic_kvm_info *info)
 	/* GICv4 support? */
 	if (info->has_v4) {
 		kvm_vgic_global_state.has_gicv4 = gicv4_enable;
-		kvm_info("GICv4 support %sabled\n",
+		kvm_vgic_global_state.has_gicv4_1 = info->has_v4_1 && gicv4_enable;
+		kvm_info("GICv4%s support %sabled\n",
+			 kvm_vgic_global_state.has_gicv4_1 ? ".1" : "",
 			 gicv4_enable ? "en" : "dis");
 	}
 

virt/kvm/arm/vgic/vgic-v4.c

@@ -67,10 +67,10 @@
  * it. And if we've migrated our vcpu from one CPU to another, we must
  * tell the ITS (so that the messages reach the right redistributor).
  * This is done in two steps: first issue a irq_set_affinity() on the
- * irq corresponding to the vcpu, then call its_schedule_vpe(). You
- * must be in a non-preemptible context. On exit, another call to
- * its_schedule_vpe() tells the redistributor that we're done with the
- * vcpu.
+ * irq corresponding to the vcpu, then call its_make_vpe_resident().
+ * You must be in a non-preemptible context. On exit, a call to
+ * its_make_vpe_non_resident() tells the redistributor that we're done
+ * with the vcpu.
  *
  * Finally, the doorbell handling: Each vcpu is allocated an interrupt
  * which will fire each time a VLPI is made pending whilst the vcpu is
@@ -86,7 +86,8 @@ static irqreturn_t vgic_v4_doorbell_handler(int irq, void *info)
 	struct kvm_vcpu *vcpu = info;
 
 	/* We got the message, no need to fire again */
-	if (!irqd_irq_disabled(&irq_to_desc(irq)->irq_data))
+	if (!kvm_vgic_global_state.has_gicv4_1 &&
+	    !irqd_irq_disabled(&irq_to_desc(irq)->irq_data))
 		disable_irq_nosync(irq);
 
 	vcpu->arch.vgic_cpu.vgic_v3.its_vpe.pending_last = true;
@@ -199,19 +200,11 @@ void vgic_v4_teardown(struct kvm *kvm)
 int vgic_v4_put(struct kvm_vcpu *vcpu, bool need_db)
 {
 	struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe;
-	struct irq_desc *desc = irq_to_desc(vpe->irq);
 
 	if (!vgic_supports_direct_msis(vcpu->kvm) || !vpe->resident)
 		return 0;
 
-	/*
-	 * If blocking, a doorbell is required. Undo the nested
-	 * disable_irq() calls...
-	 */
-	while (need_db && irqd_irq_disabled(&desc->irq_data))
-		enable_irq(vpe->irq);
-
-	return its_schedule_vpe(vpe, false);
+	return its_make_vpe_non_resident(vpe, need_db);
 }
 
 int vgic_v4_load(struct kvm_vcpu *vcpu)
@@ -232,18 +225,19 @@ int vgic_v4_load(struct kvm_vcpu *vcpu)
 	if (err)
 		return err;
 
-	/* Disabled the doorbell, as we're about to enter the guest */
-	disable_irq_nosync(vpe->irq);
-
-	err = its_schedule_vpe(vpe, true);
+	err = its_make_vpe_resident(vpe, false, vcpu->kvm->arch.vgic.enabled);
 	if (err)
 		return err;
 
 	/*
 	 * Now that the VPE is resident, let's get rid of a potential
-	 * doorbell interrupt that would still be pending.
+	 * doorbell interrupt that would still be pending. This is a
+	 * GICv4.0 only "feature"...
 	 */
-	return irq_set_irqchip_state(vpe->irq, IRQCHIP_STATE_PENDING, false);
+	if (!kvm_vgic_global_state.has_gicv4_1)
+		err = irq_set_irqchip_state(vpe->irq, IRQCHIP_STATE_PENDING, false);
+
+	return err;
 }
 
 static struct vgic_its *vgic_get_its(struct kvm *kvm,