Merge tag 'irqchip-5.1' of...

Merge tag 'irqchip-5.1' of git://git.kernel.org/pub/scm/linux/kernel/git/maz/arm-platforms into irq/core

Pull irqchip updates from Marc Zyngier

- Core pseudo-NMI handling code
- Allow the default irq domain to be retrieved
- A new interrupt controller for the Loongson LS1X platform
- Affinity support for the SiFive PLIC
- Better support for the iMX irqsteer driver
- NUMA aware memory allocations for GICv3
- A handful of other fixes (i8259, GICv3, PLIC)

Documentation/devicetree/bindings/interrupt-controller/fsl,irqsteer.txt

@@ -6,8 +6,9 @@ Required properties:
 	- "fsl,imx8m-irqsteer"
 	- "fsl,imx-irqsteer"
 - reg: Physical base address and size of registers.
-- interrupts: Should contain the parent interrupt line used to multiplex the
-  input interrupts.
+- interrupts: Should contain the up to 8 parent interrupt lines used to
+  multiplex the input interrupts. They should be specified sequentially
+  from output 0 to 7.
 - clocks: Should contain one clock for entry in clock-names
   see Documentation/devicetree/bindings/clock/clock-bindings.txt
 - clock-names:
@@ -16,8 +17,8 @@ Required properties:
 - #interrupt-cells: Specifies the number of cells needed to encode an
   interrupt source. The value must be 1.
 - fsl,channel: The output channel that all input IRQs should be steered into.
-- fsl,irq-groups: Number of IRQ groups managed by this controller instance.
-  Each group manages 64 input interrupts.
+- fsl,num-irqs: Number of input interrupts of this channel.
+  Should be multiple of 32 input interrupts and up to 512 interrupts.
 
 Example:
 
@@ -28,7 +29,7 @@ Example:
 		clocks = <&clk IMX8MQ_CLK_DISP_APB_ROOT>;
 		clock-names = "ipg";
 		fsl,channel = <0>;
-		fsl,irq-groups = <1>;
+		fsl,num-irqs = <64>;
 		interrupt-controller;
 		#interrupt-cells = <1>;
 	};

Documentation/devicetree/bindings/interrupt-controller/loongson,ls1x-intc.txt

+Loongson ls1x Interrupt Controller
+
+Required properties:
+
+- compatible : should be "loongson,ls1x-intc". Valid strings are:
+
+- reg : Specifies base physical address and size of the registers.
+- interrupt-controller : Identifies the node as an interrupt controller
+- #interrupt-cells : Specifies the number of cells needed to encode an
+  interrupt source. The value shall be 2.
+- interrupts : Specifies the CPU interrupt the controller is connected to.
+
+Example:
+
+intc: interrupt-controller@1fd01040 {
+	compatible = "loongson,ls1x-intc";
+	reg = <0x1fd01040 0x18>;
+
+	interrupt-controller;
+	#interrupt-cells = <2>;
+
+	interrupt-parent = <&cpu_intc>;
+	interrupts = <2>;
+};

drivers/irqchip/Kconfig

@@ -406,6 +406,15 @@ config IMX_IRQSTEER
 	help
 	  Support for the i.MX IRQSTEER interrupt multiplexer/remapper.
 
+config LS1X_IRQ
+	bool "Loongson-1 Interrupt Controller"
+	depends on MACH_LOONGSON32
+	default y
+	select IRQ_DOMAIN
+	select GENERIC_IRQ_CHIP
+	help
+	  Support for the Loongson-1 platform Interrupt Controller.
+
 endmenu
 
 config SIFIVE_PLIC

drivers/irqchip/Makefile

@@ -94,3 +94,4 @@ obj-$(CONFIG_CSKY_APB_INTC)		+= irq-csky-apb-intc.o
 obj-$(CONFIG_SIFIVE_PLIC)		+= irq-sifive-plic.o
 obj-$(CONFIG_IMX_IRQSTEER)		+= irq-imx-irqsteer.o
 obj-$(CONFIG_MADERA_IRQ)		+= irq-madera.o
+obj-$(CONFIG_LS1X_IRQ)			+= irq-ls1x.o

drivers/irqchip/irq-brcmstb-l2.c

@@ -129,8 +129,9 @@ static void brcmstb_l2_intc_suspend(struct irq_data *d)
 	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
 	struct irq_chip_type *ct = irq_data_get_chip_type(d);
 	struct brcmstb_l2_intc_data *b = gc->private;
+	unsigned long flags;
 
-	irq_gc_lock(gc);
+	irq_gc_lock_irqsave(gc, flags);
 	/* Save the current mask */
 	b->saved_mask = irq_reg_readl(gc, ct->regs.mask);
 
@@ -139,7 +140,7 @@ static void brcmstb_l2_intc_suspend(struct irq_data *d)
 		irq_reg_writel(gc, ~gc->wake_active, ct->regs.disable);
 		irq_reg_writel(gc, gc->wake_active, ct->regs.enable);
 	}
-	irq_gc_unlock(gc);
+	irq_gc_unlock_irqrestore(gc, flags);
 }
 
 static void brcmstb_l2_intc_resume(struct irq_data *d)
@@ -147,8 +148,9 @@ static void brcmstb_l2_intc_resume(struct irq_data *d)
 	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
 	struct irq_chip_type *ct = irq_data_get_chip_type(d);
 	struct brcmstb_l2_intc_data *b = gc->private;
+	unsigned long flags;
 
-	irq_gc_lock(gc);
+	irq_gc_lock_irqsave(gc, flags);
 	if (ct->chip.irq_ack) {
 		/* Clear unmasked non-wakeup interrupts */
 		irq_reg_writel(gc, ~b->saved_mask & ~gc->wake_active,
@@ -158,7 +160,7 @@ static void brcmstb_l2_intc_resume(struct irq_data *d)
 	/* Restore the saved mask */
 	irq_reg_writel(gc, b->saved_mask, ct->regs.disable);
 	irq_reg_writel(gc, ~b->saved_mask, ct->regs.enable);
-	irq_gc_unlock(gc);
+	irq_gc_unlock_irqrestore(gc, flags);
 }
 
 static int __init brcmstb_l2_intc_of_init(struct device_node *np,

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

@@ -1737,6 +1737,7 @@ static int its_setup_baser(struct its_node *its, struct its_baser *baser,
 	u64 type = GITS_BASER_TYPE(val);
 	u64 baser_phys, tmp;
 	u32 alloc_pages;
+	struct page *page;
 	void *base;
 
 retry_alloc_baser:
@@ -1749,10 +1750,11 @@ static int its_setup_baser(struct its_node *its, struct its_baser *baser,
 		order = get_order(GITS_BASER_PAGES_MAX * psz);
 	}
 
-	base = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, order);
-	if (!base)
+	page = alloc_pages_node(its->numa_node, GFP_KERNEL | __GFP_ZERO, order);
+	if (!page)
 		return -ENOMEM;
 
+	base = (void *)page_address(page);
 	baser_phys = virt_to_phys(base);
 
 	/* Check if the physical address of the memory is above 48bits */
@@ -1946,6 +1948,8 @@ static int its_alloc_tables(struct its_node *its)
 			indirect = its_parse_indirect_baser(its, baser,
 							    psz, &order,
 							    its->device_ids);
+			break;
+
 		case GITS_BASER_TYPE_VCPU:
 			indirect = its_parse_indirect_baser(its, baser,
 							    psz, &order,
@@ -2236,7 +2240,8 @@ static struct its_baser *its_get_baser(struct its_node *its, u32 type)
 	return NULL;
 }
 
-static bool its_alloc_table_entry(struct its_baser *baser, u32 id)
+static bool its_alloc_table_entry(struct its_node *its,
+				  struct its_baser *baser, u32 id)
 {
 	struct page *page;
 	u32 esz, idx;
@@ -2256,7 +2261,8 @@ static bool its_alloc_table_entry(struct its_baser *baser, u32 id)
 
 	/* Allocate memory for 2nd level table */
 	if (!table[idx]) {
-		page = alloc_pages(GFP_KERNEL | __GFP_ZERO, get_order(baser->psz));
+		page = alloc_pages_node(its->numa_node, GFP_KERNEL | __GFP_ZERO,
+					get_order(baser->psz));
 		if (!page)
 			return false;
 
@@ -2287,7 +2293,7 @@ static bool its_alloc_device_table(struct its_node *its, u32 dev_id)
 	if (!baser)
 		return (ilog2(dev_id) < its->device_ids);
 
-	return its_alloc_table_entry(baser, dev_id);
+	return its_alloc_table_entry(its, baser, dev_id);
 }
 
 static bool its_alloc_vpe_table(u32 vpe_id)
@@ -2311,7 +2317,7 @@ static bool its_alloc_vpe_table(u32 vpe_id)
 		if (!baser)
 			return false;
 
-		if (!its_alloc_table_entry(baser, vpe_id))
+		if (!its_alloc_table_entry(its, baser, vpe_id))
 			return false;
 	}
 
@@ -2345,7 +2351,7 @@ static struct its_device *its_create_device(struct its_node *its, u32 dev_id,
 	nr_ites = max(2, nvecs);
 	sz = nr_ites * its->ite_size;
 	sz = max(sz, ITS_ITT_ALIGN) + ITS_ITT_ALIGN - 1;
-	itt = kzalloc(sz, GFP_KERNEL);
+	itt = kzalloc_node(sz, GFP_KERNEL, its->numa_node);
 	if (alloc_lpis) {
 		lpi_map = its_lpi_alloc(nvecs, &lpi_base, &nr_lpis);
 		if (lpi_map)
@@ -3487,6 +3493,7 @@ static int __init its_probe_one(struct resource *res,
 	void __iomem *its_base;
 	u32 val, ctlr;
 	u64 baser, tmp, typer;
+	struct page *page;
 	int err;
 
 	its_base = ioremap(res->start, resource_size(res));
@@ -3542,12 +3549,13 @@ static int __init its_probe_one(struct resource *res,
 
 	its->numa_node = numa_node;
 
-	its->cmd_base = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
-						get_order(ITS_CMD_QUEUE_SZ));
-	if (!its->cmd_base) {
+	page = alloc_pages_node(its->numa_node, GFP_KERNEL | __GFP_ZERO,
+				get_order(ITS_CMD_QUEUE_SZ));
+	if (!page) {
 		err = -ENOMEM;
 		goto out_free_its;
 	}
+	its->cmd_base = (void *)page_address(page);
 	its->cmd_write = its->cmd_base;
 	its->fwnode_handle = handle;
 	its->get_msi_base = its_irq_get_msi_base;

drivers/irqchip/irq-i8259.c

@@ -225,14 +225,6 @@ static struct syscore_ops i8259_syscore_ops = {
 	.shutdown = i8259A_shutdown,
 };
 
-static int __init i8259A_init_sysfs(void)
-{
-	register_syscore_ops(&i8259_syscore_ops);
-	return 0;
-}
-
-device_initcall(i8259A_init_sysfs);
-
 static void init_8259A(int auto_eoi)
 {
 	unsigned long flags;
@@ -332,6 +324,7 @@ struct irq_domain * __init __init_i8259_irqs(struct device_node *node)
 		panic("Failed to add i8259 IRQ domain");
 
 	setup_irq(I8259A_IRQ_BASE + PIC_CASCADE_IR, &irq2);
+	register_syscore_ops(&i8259_syscore_ops);
 	return domain;
 }
 

drivers/irqchip/irq-imx-irqsteer.c

@@ -10,10 +10,11 @@
 #include <linux/irqchip/chained_irq.h>
 #include <linux/irqdomain.h>
 #include <linux/kernel.h>
+#include <linux/of_irq.h>
 #include <linux/of_platform.h>
 #include <linux/spinlock.h>
 
-#define CTRL_STRIDE_OFF(_t, _r)	(_t * 8 * _r)
+#define CTRL_STRIDE_OFF(_t, _r)	(_t * 4 * _r)
 #define CHANCTRL		0x0
 #define CHANMASK(n, t)		(CTRL_STRIDE_OFF(t, 0) + 0x4 * (n) + 0x4)
 #define CHANSET(n, t)		(CTRL_STRIDE_OFF(t, 1) + 0x4 * (n) + 0x4)
@@ -21,12 +22,15 @@
 #define CHAN_MINTDIS(t)		(CTRL_STRIDE_OFF(t, 3) + 0x4)
 #define CHAN_MASTRSTAT(t)	(CTRL_STRIDE_OFF(t, 3) + 0x8)
 
+#define CHAN_MAX_OUTPUT_INT	0x8
+
 struct irqsteer_data {
 	void __iomem		*regs;
 	struct clk		*ipg_clk;
-	int			irq;
+	int			irq[CHAN_MAX_OUTPUT_INT];
+	int			irq_count;
 	raw_spinlock_t		lock;
-	int			irq_groups;
+	int			reg_num;
 	int			channel;
 	struct irq_domain	*domain;
 	u32			*saved_reg;
@@ -35,7 +39,7 @@ struct irqsteer_data {
 static int imx_irqsteer_get_reg_index(struct irqsteer_data *data,
 				      unsigned long irqnum)
 {
-	return (data->irq_groups * 2 - irqnum / 32 - 1);
+	return (data->reg_num - irqnum / 32 - 1);
 }
 
 static void imx_irqsteer_irq_unmask(struct irq_data *d)
@@ -46,9 +50,9 @@ static void imx_irqsteer_irq_unmask(struct irq_data *d)
 	u32 val;
 
 	raw_spin_lock_irqsave(&data->lock, flags);
-	val = readl_relaxed(data->regs + CHANMASK(idx, data->irq_groups));
+	val = readl_relaxed(data->regs + CHANMASK(idx, data->reg_num));
 	val |= BIT(d->hwirq % 32);
-	writel_relaxed(val, data->regs + CHANMASK(idx, data->irq_groups));
+	writel_relaxed(val, data->regs + CHANMASK(idx, data->reg_num));
 	raw_spin_unlock_irqrestore(&data->lock, flags);
 }
 
@@ -60,9 +64,9 @@ static void imx_irqsteer_irq_mask(struct irq_data *d)
 	u32 val;
 
 	raw_spin_lock_irqsave(&data->lock, flags);
-	val = readl_relaxed(data->regs + CHANMASK(idx, data->irq_groups));
+	val = readl_relaxed(data->regs + CHANMASK(idx, data->reg_num));
 	val &= ~BIT(d->hwirq % 32);
-	writel_relaxed(val, data->regs + CHANMASK(idx, data->irq_groups));
+	writel_relaxed(val, data->regs + CHANMASK(idx, data->reg_num));
 	raw_spin_unlock_irqrestore(&data->lock, flags);
 }
 
@@ -87,23 +91,47 @@ static const struct irq_domain_ops imx_irqsteer_domain_ops = {
 	.xlate		= irq_domain_xlate_onecell,
 };
 
+static int imx_irqsteer_get_hwirq_base(struct irqsteer_data *data, u32 irq)
+{
+	int i;
+
+	for (i = 0; i < data->irq_count; i++) {
+		if (data->irq[i] == irq)
+			return i * 64;
+	}
+
+	return -EINVAL;
+}
+
 static void imx_irqsteer_irq_handler(struct irq_desc *desc)
 {
 	struct irqsteer_data *data = irq_desc_get_handler_data(desc);
-	int i;
+	int hwirq;
+	int irq, i;
 
 	chained_irq_enter(irq_desc_get_chip(desc), desc);
 
-	for (i = 0; i < data->irq_groups * 64; i += 32) {
-		int idx = imx_irqsteer_get_reg_index(data, i);
+	irq = irq_desc_get_irq(desc);
+	hwirq = imx_irqsteer_get_hwirq_base(data, irq);
+	if (hwirq < 0) {
+		pr_warn("%s: unable to get hwirq base for irq %d\n",
+			__func__, irq);
+		return;
+	}
+
+	for (i = 0; i < 2; i++, hwirq += 32) {
+		int idx = imx_irqsteer_get_reg_index(data, hwirq);
 		unsigned long irqmap;
 		int pos, virq;
 
+		if (hwirq >= data->reg_num * 32)
+			break;
+
 		irqmap = readl_relaxed(data->regs +
-				       CHANSTATUS(idx, data->irq_groups));
+				       CHANSTATUS(idx, data->reg_num));
 
 		for_each_set_bit(pos, &irqmap, 32) {
-			virq = irq_find_mapping(data->domain, pos + i);
+			virq = irq_find_mapping(data->domain, pos + hwirq);
 			if (virq)
 				generic_handle_irq(virq);
 		}
@@ -117,7 +145,8 @@ static int imx_irqsteer_probe(struct platform_device *pdev)
 	struct device_node *np = pdev->dev.of_node;
 	struct irqsteer_data *data;
 	struct resource *res;
-	int ret;
+	u32 irqs_num;
+	int i, ret;
 
 	data = devm_kzalloc(&pdev->dev, sizeof(*data), GFP_KERNEL);
 	if (!data)
@@ -130,12 +159,6 @@ static int imx_irqsteer_probe(struct platform_device *pdev)
 		return PTR_ERR(data->regs);
 	}
 
-	data->irq = platform_get_irq(pdev, 0);
-	if (data->irq <= 0) {
-		dev_err(&pdev->dev, "failed to get irq\n");
-		return -ENODEV;
-	}
-
 	data->ipg_clk = devm_clk_get(&pdev->dev, "ipg");
 	if (IS_ERR(data->ipg_clk)) {
 		ret = PTR_ERR(data->ipg_clk);
@@ -146,12 +169,19 @@ static int imx_irqsteer_probe(struct platform_device *pdev)
 
 	raw_spin_lock_init(&data->lock);
 
-	of_property_read_u32(np, "fsl,irq-groups", &data->irq_groups);
+	of_property_read_u32(np, "fsl,num-irqs", &irqs_num);
 	of_property_read_u32(np, "fsl,channel", &data->channel);
 
+	/*
+	 * There is one output irq for each group of 64 inputs.
+	 * One register bit map can represent 32 input interrupts.
+	 */
+	data->irq_count = DIV_ROUND_UP(irqs_num, 64);
+	data->reg_num = irqs_num / 32;
+
 	if (IS_ENABLED(CONFIG_PM_SLEEP)) {
 		data->saved_reg = devm_kzalloc(&pdev->dev,
-					sizeof(u32) * data->irq_groups * 2,
+					sizeof(u32) * data->reg_num,
 					GFP_KERNEL);
 		if (!data->saved_reg)
 			return -ENOMEM;
@@ -166,27 +196,48 @@ static int imx_irqsteer_probe(struct platform_device *pdev)
 	/* steer all IRQs into configured channel */
 	writel_relaxed(BIT(data->channel), data->regs + CHANCTRL);
 
-	data->domain = irq_domain_add_linear(np, data->irq_groups * 64,
+	data->domain = irq_domain_add_linear(np, data->reg_num * 32,
 					     &imx_irqsteer_domain_ops, data);
 	if (!data->domain) {
 		dev_err(&pdev->dev, "failed to create IRQ domain\n");
-		clk_disable_unprepare(data->ipg_clk);
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	if (!data->irq_count || data->irq_count > CHAN_MAX_OUTPUT_INT) {
+		ret = -EINVAL;
+		goto out;
 	}
 
-	irq_set_chained_handler_and_data(data->irq, imx_irqsteer_irq_handler,
-					 data);
+	for (i = 0; i < data->irq_count; i++) {
+		data->irq[i] = irq_of_parse_and_map(np, i);
+		if (!data->irq[i]) {
+			ret = -EINVAL;
+			goto out;
+		}
+
+		irq_set_chained_handler_and_data(data->irq[i],
+						 imx_irqsteer_irq_handler,
+						 data);
+	}
 
 	platform_set_drvdata(pdev, data);
 
 	return 0;
+out:
+	clk_disable_unprepare(data->ipg_clk);
+	return ret;
 }
 
 static int imx_irqsteer_remove(struct platform_device *pdev)
 {
 	struct irqsteer_data *irqsteer_data = platform_get_drvdata(pdev);
+	int i;
+
+	for (i = 0; i < irqsteer_data->irq_count; i++)
+		irq_set_chained_handler_and_data(irqsteer_data->irq[i],
+						 NULL, NULL);
 
-	irq_set_chained_handler_and_data(irqsteer_data->irq, NULL, NULL);
 	irq_domain_remove(irqsteer_data->domain);
 
 	clk_disable_unprepare(irqsteer_data->ipg_clk);
@@ -199,9 +250,9 @@ static void imx_irqsteer_save_regs(struct irqsteer_data *data)
 {
 	int i;
 
-	for (i = 0; i < data->irq_groups * 2; i++)
+	for (i = 0; i < data->reg_num; i++)
 		data->saved_reg[i] = readl_relaxed(data->regs +
-						CHANMASK(i, data->irq_groups));
+						CHANMASK(i, data->reg_num));
 }
 
 static void imx_irqsteer_restore_regs(struct irqsteer_data *data)
@@ -209,9 +260,9 @@ static void imx_irqsteer_restore_regs(struct irqsteer_data *data)
 	int i;
 
 	writel_relaxed(BIT(data->channel), data->regs + CHANCTRL);
-	for (i = 0; i < data->irq_groups * 2; i++)
+	for (i = 0; i < data->reg_num; i++)
 		writel_relaxed(data->saved_reg[i],
-			       data->regs + CHANMASK(i, data->irq_groups));
+			       data->regs + CHANMASK(i, data->reg_num));
 }
 
 static int imx_irqsteer_suspend(struct device *dev)

drivers/irqchip/irq-ls1x.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  Copyright (C) 2019, Jiaxun Yang <jiaxun.yang@flygoat.com>
+ *  Loongson-1 platform IRQ support
+ */
+
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/interrupt.h>
+#include <linux/ioport.h>
+#include <linux/irqchip.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/io.h>
+#include <linux/irqchip/chained_irq.h>
+
+#define LS_REG_INTC_STATUS	0x00
+#define LS_REG_INTC_EN	0x04
+#define LS_REG_INTC_SET	0x08
+#define LS_REG_INTC_CLR	0x0c
+#define LS_REG_INTC_POL	0x10
+#define LS_REG_INTC_EDGE	0x14
+
+/**
+ * struct ls1x_intc_priv - private ls1x-intc data.
+ * @domain:		IRQ domain.
+ * @intc_base:	IO Base of intc registers.
+ */
+
+struct ls1x_intc_priv {
+	struct irq_domain	*domain;
+	void __iomem		*intc_base;
+};
+
+
+static void ls1x_chained_handle_irq(struct irq_desc *desc)
+{
+	struct ls1x_intc_priv *priv = irq_desc_get_handler_data(desc);
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	u32 pending;
+
+	chained_irq_enter(chip, desc);
+	pending = readl(priv->intc_base + LS_REG_INTC_STATUS) &
+			readl(priv->intc_base + LS_REG_INTC_EN);
+
+	if (!pending)
+		spurious_interrupt();
+
+	while (pending) {
+		int bit = __ffs(pending);
+
+		generic_handle_irq(irq_find_mapping(priv->domain, bit));
+		pending &= ~BIT(bit);
+	}
+
+	chained_irq_exit(chip, desc);
+}
+
+static void ls_intc_set_bit(struct irq_chip_generic *gc,
+							unsigned int offset,
+							u32 mask, bool set)
+{
+	if (set)
+		writel(readl(gc->reg_base + offset) | mask,
+		gc->reg_base + offset);
+	else
+		writel(readl(gc->reg_base + offset) & ~mask,
+		gc->reg_base + offset);
+}
+
+static int ls_intc_set_type(struct irq_data *data, unsigned int type)
+{
+	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(data);
+	u32 mask = data->mask;
+
+	switch (type) {
+	case IRQ_TYPE_LEVEL_HIGH:
+		ls_intc_set_bit(gc, LS_REG_INTC_EDGE, mask, false);
+		ls_intc_set_bit(gc, LS_REG_INTC_POL, mask, true);
+		break;
+	case IRQ_TYPE_LEVEL_LOW:
+		ls_intc_set_bit(gc, LS_REG_INTC_EDGE, mask, false);
+		ls_intc_set_bit(gc, LS_REG_INTC_POL, mask, false);
+		break;
+	case IRQ_TYPE_EDGE_RISING:
+		ls_intc_set_bit(gc, LS_REG_INTC_EDGE, mask, true);
+		ls_intc_set_bit(gc, LS_REG_INTC_POL, mask, true);
+		break;
+	case IRQ_TYPE_EDGE_FALLING:
+		ls_intc_set_bit(gc, LS_REG_INTC_EDGE, mask, true);
+		ls_intc_set_bit(gc, LS_REG_INTC_POL, mask, false);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	irqd_set_trigger_type(data, type);
+	return irq_setup_alt_chip(data, type);
+}
+
+
+static int __init ls1x_intc_of_init(struct device_node *node,
+				       struct device_node *parent)
+{
+	struct irq_chip_generic *gc;
+	struct irq_chip_type *ct;
+	struct ls1x_intc_priv *priv;
+	int parent_irq, err = 0;
+
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->intc_base = of_iomap(node, 0);
+	if (!priv->intc_base) {
+		err = -ENODEV;
+		goto out_free_priv;
+	}
+
+	parent_irq = irq_of_parse_and_map(node, 0);
+	if (!parent_irq) {
+		pr_err("ls1x-irq: unable to get parent irq\n");
+		err =  -ENODEV;
+		goto out_iounmap;
+	}
+
+	/* Set up an IRQ domain */
+	priv->domain = irq_domain_add_linear(node, 32, &irq_generic_chip_ops,
+					     NULL);
+	if (!priv->domain) {
+		pr_err("ls1x-irq: cannot add IRQ domain\n");
+		goto out_iounmap;
+	}
+
+	err = irq_alloc_domain_generic_chips(priv->domain, 32, 2,
+		node->full_name, handle_level_irq,
+		IRQ_NOREQUEST | IRQ_NOPROBE | IRQ_NOAUTOEN, 0,
+		IRQ_GC_INIT_MASK_CACHE);
+	if (err) {
+		pr_err("ls1x-irq: unable to register IRQ domain\n");
+		goto out_free_domain;
+	}
+
+	/* Mask all irqs */
+	writel(0x0, priv->intc_base + LS_REG_INTC_EN);
+
+	/* Ack all irqs */
+	writel(0xffffffff, priv->intc_base + LS_REG_INTC_CLR);
+
+	/* Set all irqs to high level triggered */
+	writel(0xffffffff, priv->intc_base + LS_REG_INTC_POL);
+
+	gc = irq_get_domain_generic_chip(priv->domain, 0);
+
+	gc->reg_base = priv->intc_base;
+
+	ct = gc->chip_types;
+	ct[0].type = IRQ_TYPE_LEVEL_MASK;
+	ct[0].regs.mask = LS_REG_INTC_EN;
+	ct[0].regs.ack = LS_REG_INTC_CLR;
+	ct[0].chip.irq_unmask = irq_gc_mask_set_bit;
+	ct[0].chip.irq_mask = irq_gc_mask_clr_bit;
+	ct[0].chip.irq_ack = irq_gc_ack_set_bit;
+	ct[0].chip.irq_set_type = ls_intc_set_type;
+	ct[0].handler = handle_level_irq;
+
+	ct[1].type = IRQ_TYPE_EDGE_BOTH;
+	ct[1].regs.mask = LS_REG_INTC_EN;
+	ct[1].regs.ack = LS_REG_INTC_CLR;
+	ct[1].chip.irq_unmask = irq_gc_mask_set_bit;
+	ct[1].chip.irq_mask = irq_gc_mask_clr_bit;
+	ct[1].chip.irq_ack = irq_gc_ack_set_bit;
+	ct[1].chip.irq_set_type = ls_intc_set_type;
+	ct[1].handler = handle_edge_irq;
+
+	irq_set_chained_handler_and_data(parent_irq,
+		ls1x_chained_handle_irq, priv);
+
+	return 0;
+
+out_free_domain:
+	irq_domain_remove(priv->domain);
+out_iounmap:
+	iounmap(priv->intc_base);
+out_free_priv:
+	kfree(priv);
+
+	return err;
+}
+
+IRQCHIP_DECLARE(ls1x_intc, "loongson,ls1x-intc", ls1x_intc_of_init);

drivers/irqchip/irq-sifive-plic.c

@@ -59,62 +59,83 @@ static void __iomem *plic_regs;
 
 struct plic_handler {
 	bool			present;
-	int			ctxid;
+	void __iomem		*hart_base;
+	/*
+	 * Protect mask operations on the registers given that we can't
+	 * assume atomic memory operations work on them.
+	 */
+	raw_spinlock_t		enable_lock;
+	void __iomem		*enable_base;
 };
 static DEFINE_PER_CPU(struct plic_handler, plic_handlers);
 
-static inline void __iomem *plic_hart_offset(int ctxid)
-{
-	return plic_regs + CONTEXT_BASE + ctxid * CONTEXT_PER_HART;
-}
-
-static inline u32 __iomem *plic_enable_base(int ctxid)
-{
-	return plic_regs + ENABLE_BASE + ctxid * ENABLE_PER_HART;
-}
-
-/*
- * Protect mask operations on the registers given that we can't assume that
- * atomic memory operations work on them.
- */
-static DEFINE_RAW_SPINLOCK(plic_toggle_lock);
-
-static inline void plic_toggle(int ctxid, int hwirq, int enable)
+static inline void plic_toggle(struct plic_handler *handler,
+				int hwirq, int enable)
 {
-	u32 __iomem *reg = plic_enable_base(ctxid) + (hwirq / 32);
+	u32 __iomem *reg = handler->enable_base + (hwirq / 32) * sizeof(u32);
 	u32 hwirq_mask = 1 << (hwirq % 32);
 
-	raw_spin_lock(&plic_toggle_lock);
+	raw_spin_lock(&handler->enable_lock);
 	if (enable)
 		writel(readl(reg) | hwirq_mask, reg);
 	else
 		writel(readl(reg) & ~hwirq_mask, reg);
-	raw_spin_unlock(&plic_toggle_lock);
+	raw_spin_unlock(&handler->enable_lock);
 }
 
-static inline void plic_irq_toggle(struct irq_data *d, int enable)
+static inline void plic_irq_toggle(const struct cpumask *mask,
+				   int hwirq, int enable)
 {
 	int cpu;
 
-	writel(enable, plic_regs + PRIORITY_BASE + d->hwirq * PRIORITY_PER_ID);
-	for_each_cpu(cpu, irq_data_get_affinity_mask(d)) {
+	writel(enable, plic_regs + PRIORITY_BASE + 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->ctxid, d->hwirq, enable);
+			plic_toggle(handler, hwirq, enable);
 	}
 }
 
 static void plic_irq_enable(struct irq_data *d)
 {
-	plic_irq_toggle(d, 1);
+	unsigned int cpu = cpumask_any_and(irq_data_get_affinity_mask(d),
+					   cpu_online_mask);
+	if (WARN_ON_ONCE(cpu >= nr_cpu_ids))
+		return;
+	plic_irq_toggle(cpumask_of(cpu), d->hwirq, 1);
 }
 
 static void plic_irq_disable(struct irq_data *d)
 {
-	plic_irq_toggle(d, 0);
+	plic_irq_toggle(cpu_possible_mask, d->hwirq, 0);
 }
 
+#ifdef CONFIG_SMP
+static int plic_set_affinity(struct irq_data *d,
+			     const struct cpumask *mask_val, bool force)
+{
+	unsigned int cpu;
+
+	if (force)
+		cpu = cpumask_first(mask_val);
+	else
+		cpu = cpumask_any_and(mask_val, cpu_online_mask);
+
+	if (cpu >= nr_cpu_ids)
+		return -EINVAL;
+
+	if (!irqd_irq_disabled(d)) {
+		plic_irq_toggle(cpu_possible_mask, d->hwirq, 0);
+		plic_irq_toggle(cpumask_of(cpu), d->hwirq, 1);
+	}
+
+	irq_data_update_effective_affinity(d, cpumask_of(cpu));
+
+	return IRQ_SET_MASK_OK_DONE;
+}
+#endif
+
 static struct irq_chip plic_chip = {
 	.name		= "SiFive PLIC",
 	/*
@@ -123,6 +144,9 @@ static struct irq_chip plic_chip = {
 	 */
 	.irq_enable	= plic_irq_enable,
 	.irq_disable	= plic_irq_disable,
+#ifdef CONFIG_SMP
+	.irq_set_affinity = plic_set_affinity,
+#endif
 };
 
 static int plic_irqdomain_map(struct irq_domain *d, unsigned int irq,
@@ -150,7 +174,7 @@ static struct irq_domain *plic_irqdomain;
 static void plic_handle_irq(struct pt_regs *regs)
 {
 	struct plic_handler *handler = this_cpu_ptr(&plic_handlers);
-	void __iomem *claim = plic_hart_offset(handler->ctxid) + CONTEXT_CLAIM;
+	void __iomem *claim = handler->hart_base + CONTEXT_CLAIM;
 	irq_hw_number_t hwirq;
 
 	WARN_ON_ONCE(!handler->present);
@@ -186,7 +210,7 @@ static int plic_find_hart_id(struct device_node *node)
 static int __init plic_init(struct device_node *node,
 		struct device_node *parent)
 {
-	int error = 0, nr_handlers, nr_mapped = 0, i;
+	int error = 0, nr_contexts, nr_handlers = 0, i;
 	u32 nr_irqs;
 
 	if (plic_regs) {
@@ -203,10 +227,10 @@ static int __init plic_init(struct device_node *node,
 	if (WARN_ON(!nr_irqs))
 		goto out_iounmap;
 
-	nr_handlers = of_irq_count(node);
-	if (WARN_ON(!nr_handlers))
+	nr_contexts = of_irq_count(node);
+	if (WARN_ON(!nr_contexts))
 		goto out_iounmap;
-	if (WARN_ON(nr_handlers < num_possible_cpus()))
+	if (WARN_ON(nr_contexts < num_possible_cpus()))
 		goto out_iounmap;
 
 	error = -ENOMEM;
@@ -215,7 +239,7 @@ static int __init plic_init(struct device_node *node,
 	if (WARN_ON(!plic_irqdomain))
 		goto out_iounmap;
 
-	for (i = 0; i < nr_handlers; i++) {
+	for (i = 0; i < nr_contexts; i++) {
 		struct of_phandle_args parent;
 		struct plic_handler *handler;
 		irq_hw_number_t hwirq;
@@ -237,19 +261,33 @@ static int __init plic_init(struct device_node *node,
 		}
 
 		cpu = riscv_hartid_to_cpuid(hartid);
+		if (cpu < 0) {
+			pr_warn("Invalid cpuid for context %d\n", i);
+			continue;
+		}
+
 		handler = per_cpu_ptr(&plic_handlers, cpu);
+		if (handler->present) {
+			pr_warn("handler already present for context %d.\n", i);
+			continue;
+		}
+
 		handler->present = true;
-		handler->ctxid = i;
+		handler->hart_base =
+			plic_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;
 
 		/* priority must be > threshold to trigger an interrupt */
-		writel(0, plic_hart_offset(i) + CONTEXT_THRESHOLD);
+		writel(0, handler->hart_base + CONTEXT_THRESHOLD);
 		for (hwirq = 1; hwirq <= nr_irqs; hwirq++)
-			plic_toggle(i, hwirq, 0);
-		nr_mapped++;
+			plic_toggle(handler, hwirq, 0);
+		nr_handlers++;
 	}
 
-	pr_info("mapped %d interrupts to %d (out of %d) handlers.\n",
-		nr_irqs, nr_mapped, nr_handlers);
+	pr_info("mapped %d interrupts with %d handlers for %d contexts.\n",
+		nr_irqs, nr_handlers, nr_contexts);
 	set_handle_irq(plic_handle_irq);
 	return 0;
 

include/linux/interrupt.h

@@ -156,6 +156,10 @@ __request_percpu_irq(unsigned int irq, irq_handler_t handler,
 		     unsigned long flags, const char *devname,
 		     void __percpu *percpu_dev_id);
 
+extern int __must_check
+request_nmi(unsigned int irq, irq_handler_t handler, unsigned long flags,
+	    const char *name, void *dev);
+
 static inline int __must_check
 request_percpu_irq(unsigned int irq, irq_handler_t handler,
 		   const char *devname, void __percpu *percpu_dev_id)
@@ -164,9 +168,16 @@ request_percpu_irq(unsigned int irq, irq_handler_t handler,
 				    devname, percpu_dev_id);
 }
 
+extern int __must_check
+request_percpu_nmi(unsigned int irq, irq_handler_t handler,
+		   const char *devname, void __percpu *dev);
+
 extern const void *free_irq(unsigned int, void *);
 extern void free_percpu_irq(unsigned int, void __percpu *);
 
+extern const void *free_nmi(unsigned int irq, void *dev_id);
+extern void free_percpu_nmi(unsigned int irq, void __percpu *percpu_dev_id);
+
 struct device;
 
 extern int __must_check
@@ -217,6 +228,13 @@ extern void enable_percpu_irq(unsigned int irq, unsigned int type);
 extern bool irq_percpu_is_enabled(unsigned int irq);
 extern void irq_wake_thread(unsigned int irq, void *dev_id);
 
+extern void disable_nmi_nosync(unsigned int irq);
+extern void disable_percpu_nmi(unsigned int irq);
+extern void enable_nmi(unsigned int irq);
+extern void enable_percpu_nmi(unsigned int irq, unsigned int type);
+extern int prepare_percpu_nmi(unsigned int irq);
+extern void teardown_percpu_nmi(unsigned int irq);
+
 /* The following three functions are for the core kernel use only. */
 extern void suspend_device_irqs(void);
 extern void resume_device_irqs(void);

include/linux/irq.h

@@ -442,6 +442,8 @@ static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d)
  * @irq_set_vcpu_affinity:	optional to target a vCPU in a virtual machine
  * @ipi_send_single:	send a single IPI to destination cpus
  * @ipi_send_mask:	send an IPI to destination cpus in cpumask
+ * @irq_nmi_setup:	function called from core code before enabling an NMI
+ * @irq_nmi_teardown:	function called from core code after disabling an NMI
  * @flags:		chip specific flags
  */
 struct irq_chip {
@@ -490,6 +492,9 @@ struct irq_chip {
 	void		(*ipi_send_single)(struct irq_data *data, unsigned int cpu);
 	void		(*ipi_send_mask)(struct irq_data *data, const struct cpumask *dest);
 
+	int		(*irq_nmi_setup)(struct irq_data *data);
+	void		(*irq_nmi_teardown)(struct irq_data *data);
+
 	unsigned long	flags;
 };
 
@@ -505,6 +510,7 @@ struct irq_chip {
  * IRQCHIP_ONESHOT_SAFE:	One shot does not require mask/unmask
  * IRQCHIP_EOI_THREADED:	Chip requires eoi() on unmask in threaded mode
  * IRQCHIP_SUPPORTS_LEVEL_MSI	Chip can provide two doorbells for Level MSIs
+ * IRQCHIP_SUPPORTS_NMI:	Chip can deliver NMIs, only for root irqchips
  */
 enum {
 	IRQCHIP_SET_TYPE_MASKED		= (1 <<  0),
@@ -515,6 +521,7 @@ enum {
 	IRQCHIP_ONESHOT_SAFE		= (1 <<  5),
 	IRQCHIP_EOI_THREADED		= (1 <<  6),
 	IRQCHIP_SUPPORTS_LEVEL_MSI	= (1 <<  7),
+	IRQCHIP_SUPPORTS_NMI		= (1 <<  8),
 };
 
 #include <linux/irqdesc.h>
@@ -594,6 +601,9 @@ extern void handle_percpu_devid_irq(struct irq_desc *desc);
 extern void handle_bad_irq(struct irq_desc *desc);
 extern void handle_nested_irq(unsigned int irq);
 
+extern void handle_fasteoi_nmi(struct irq_desc *desc);
+extern void handle_percpu_devid_fasteoi_nmi(struct irq_desc *desc);
+
 extern int irq_chip_compose_msi_msg(struct irq_data *data, struct msi_msg *msg);
 extern int irq_chip_pm_get(struct irq_data *data);
 extern int irq_chip_pm_put(struct irq_data *data);

include/linux/irqdesc.h

@@ -173,6 +173,11 @@ static inline int handle_domain_irq(struct irq_domain *domain,
 {
 	return __handle_domain_irq(domain, hwirq, true, regs);
 }
+
+#ifdef CONFIG_IRQ_DOMAIN
+int handle_domain_nmi(struct irq_domain *domain, unsigned int hwirq,
+		      struct pt_regs *regs);
+#endif
 #endif
 
 /* Test to see if a driver has successfully requested an irq */

include/linux/irqdomain.h

@@ -265,6 +265,7 @@ extern struct irq_domain *irq_find_matching_fwspec(struct irq_fwspec *fwspec,
 						   enum irq_domain_bus_token bus_token);
 extern bool irq_domain_check_msi_remap(void);
 extern void irq_set_default_host(struct irq_domain *host);
+extern struct irq_domain *irq_get_default_host(void);
 extern int irq_domain_alloc_descs(int virq, unsigned int nr_irqs,
 				  irq_hw_number_t hwirq, int node,
 				  const struct irq_affinity_desc *affinity);

kernel/irq/chip.c

@@ -729,6 +729,37 @@ void handle_fasteoi_irq(struct irq_desc *desc)
 }
 EXPORT_SYMBOL_GPL(handle_fasteoi_irq);
 
+/**
+ *	handle_fasteoi_nmi - irq handler for NMI interrupt lines
+ *	@desc:	the interrupt description structure for this irq
+ *
+ *	A simple NMI-safe handler, considering the restrictions
+ *	from request_nmi.
+ *
+ *	Only a single callback will be issued to the chip: an ->eoi()
+ *	call when the interrupt has been serviced. This enables support
+ *	for modern forms of interrupt handlers, which handle the flow
+ *	details in hardware, transparently.
+ */
+void handle_fasteoi_nmi(struct irq_desc *desc)
+{
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	struct irqaction *action = desc->action;
+	unsigned int irq = irq_desc_get_irq(desc);
+	irqreturn_t res;
+
+	trace_irq_handler_entry(irq, action);
+	/*
+	 * NMIs cannot be shared, there is only one action.
+	 */
+	res = action->handler(irq, action->dev_id);
+	trace_irq_handler_exit(irq, action, res);
+
+	if (chip->irq_eoi)
+		chip->irq_eoi(&desc->irq_data);
+}
+EXPORT_SYMBOL_GPL(handle_fasteoi_nmi);
+
 /**
  *	handle_edge_irq - edge type IRQ handler
  *	@desc:	the interrupt description structure for this irq
@@ -916,6 +947,29 @@ void handle_percpu_devid_irq(struct irq_desc *desc)
 		chip->irq_eoi(&desc->irq_data);
 }
 
+/**
+ * handle_percpu_devid_fasteoi_nmi - Per CPU local NMI handler with per cpu
+ *				     dev ids
+ * @desc:	the interrupt description structure for this irq
+ *
+ * Similar to handle_fasteoi_nmi, but handling the dev_id cookie
+ * as a percpu pointer.
+ */
+void handle_percpu_devid_fasteoi_nmi(struct irq_desc *desc)
+{
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	struct irqaction *action = desc->action;
+	unsigned int irq = irq_desc_get_irq(desc);
+	irqreturn_t res;
+
+	trace_irq_handler_entry(irq, action);
+	res = action->handler(irq, raw_cpu_ptr(action->percpu_dev_id));
+	trace_irq_handler_exit(irq, action, res);
+
+	if (chip->irq_eoi)
+		chip->irq_eoi(&desc->irq_data);
+}
+
 static void
 __irq_do_set_handler(struct irq_desc *desc, irq_flow_handler_t handle,
 		     int is_chained, const char *name)

kernel/irq/debugfs.c

@@ -56,6 +56,7 @@ static const struct irq_bit_descr irqchip_flags[] = {
 	BIT_MASK_DESCR(IRQCHIP_ONESHOT_SAFE),
 	BIT_MASK_DESCR(IRQCHIP_EOI_THREADED),
 	BIT_MASK_DESCR(IRQCHIP_SUPPORTS_LEVEL_MSI),
+	BIT_MASK_DESCR(IRQCHIP_SUPPORTS_NMI),
 };
 
 static void
@@ -140,6 +141,7 @@ static const struct irq_bit_descr irqdesc_istates[] = {
 	BIT_MASK_DESCR(IRQS_WAITING),
 	BIT_MASK_DESCR(IRQS_PENDING),
 	BIT_MASK_DESCR(IRQS_SUSPENDED),
+	BIT_MASK_DESCR(IRQS_NMI),
 };
 
 
@@ -203,8 +205,8 @@ static ssize_t irq_debug_write(struct file *file, const char __user *user_buf,
 		chip_bus_lock(desc);
 		raw_spin_lock_irqsave(&desc->lock, flags);
 
-		if (irq_settings_is_level(desc)) {
-			/* Can't do level, sorry */
+		if (irq_settings_is_level(desc) || desc->istate & IRQS_NMI) {
+			/* Can't do level nor NMIs, sorry */
 			err = -EINVAL;
 		} else {
 			desc->istate |= IRQS_PENDING;

kernel/irq/internals.h

@@ -49,6 +49,7 @@ enum {
  * IRQS_WAITING			- irq is waiting
  * IRQS_PENDING			- irq is pending and replayed later
  * IRQS_SUSPENDED		- irq is suspended
+ * IRQS_NMI			- irq line is used to deliver NMIs
  */
 enum {
 	IRQS_AUTODETECT		= 0x00000001,
@@ -60,6 +61,7 @@ enum {
 	IRQS_PENDING		= 0x00000200,
 	IRQS_SUSPENDED		= 0x00000800,
 	IRQS_TIMINGS		= 0x00001000,
+	IRQS_NMI		= 0x00002000,
 };
 
 #include "debug.h"

kernel/irq/irqdesc.c

@@ -670,6 +670,41 @@ int __handle_domain_irq(struct irq_domain *domain, unsigned int hwirq,
 	set_irq_regs(old_regs);
 	return ret;
 }
+
+#ifdef CONFIG_IRQ_DOMAIN
+/**
+ * handle_domain_nmi - Invoke the handler for a HW irq belonging to a domain
+ * @domain:	The domain where to perform the lookup
+ * @hwirq:	The HW irq number to convert to a logical one
+ * @regs:	Register file coming from the low-level handling code
+ *
+ * Returns:	0 on success, or -EINVAL if conversion has failed
+ */
+int handle_domain_nmi(struct irq_domain *domain, unsigned int hwirq,
+		      struct pt_regs *regs)
+{
+	struct pt_regs *old_regs = set_irq_regs(regs);
+	unsigned int irq;
+	int ret = 0;
+
+	nmi_enter();
+
+	irq = irq_find_mapping(domain, hwirq);
+
+	/*
+	 * ack_bad_irq is not NMI-safe, just report
+	 * an invalid interrupt.
+	 */
+	if (likely(irq))
+		generic_handle_irq(irq);
+	else
+		ret = -EINVAL;
+
+	nmi_exit();
+	set_irq_regs(old_regs);
+	return ret;
+}
+#endif
 #endif
 
 /* Dynamic interrupt handling */

kernel/irq/irqdomain.c

@@ -458,6 +458,20 @@ void irq_set_default_host(struct irq_domain *domain)
 }
 EXPORT_SYMBOL_GPL(irq_set_default_host);
 
+/**
+ * irq_get_default_host() - Retrieve the "default" irq domain
+ *
+ * Returns: the default domain, if any.
+ *
+ * Modern code should never use this. This should only be used on
+ * systems that cannot implement a firmware->fwnode mapping (which
+ * both DT and ACPI provide).
+ */
+struct irq_domain *irq_get_default_host(void)
+{
+	return irq_default_domain;
+}
+
 static void irq_domain_clear_mapping(struct irq_domain *domain,
 				     irq_hw_number_t hwirq)
 {