9 files changed, 592 insertions, 197 deletions

diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index fa33c50b0e5a..5495a5ba8039 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -8,6 +8,12 @@ config ARM_GIC
 	select IRQ_DOMAIN_HIERARCHY
 	select MULTI_IRQ_HANDLER
 
+config ARM_GIC_PM
+	bool
+	depends on PM
+	select ARM_GIC
+	select PM_CLK
+
 config ARM_GIC_MAX_NR
 	int
 	default 2 if ARCH_REALVIEW
diff --git a/drivers/irqchip/Makefile b/drivers/irqchip/Makefile
index bb5dc3dad8d1..4c203b6b8163 100644
--- a/drivers/irqchip/Makefile
+++ b/drivers/irqchip/Makefile
@@ -24,6 +24,7 @@ obj-$(CONFIG_ARCH_SUNXI)		+= irq-sun4i.o
 obj-$(CONFIG_ARCH_SUNXI)		+= irq-sunxi-nmi.o
 obj-$(CONFIG_ARCH_SPEAR3XX)		+= spear-shirq.o
 obj-$(CONFIG_ARM_GIC)			+= irq-gic.o irq-gic-common.o
+obj-$(CONFIG_ARM_GIC_PM)		+= irq-gic-pm.o
 obj-$(CONFIG_REALVIEW_DT)		+= irq-gic-realview.o
 obj-$(CONFIG_ARM_GIC_V2M)		+= irq-gic-v2m.o
 obj-$(CONFIG_ARM_GIC_V3)		+= irq-gic-v3.o irq-gic-common.o
diff --git a/drivers/irqchip/irq-gic-common.c b/drivers/irqchip/irq-gic-common.c
index 89e7423f0ebb..9ae71804b5dd 100644
--- a/drivers/irqchip/irq-gic-common.c
+++ b/drivers/irqchip/irq-gic-common.c
@@ -90,8 +90,8 @@ int gic_configure_irq(unsigned int irq, unsigned int type,
 	return ret;
 }
 
-void __init gic_dist_config(void __iomem *base, int gic_irqs,
-			    void (*sync_access)(void))
+void gic_dist_config(void __iomem *base, int gic_irqs,
+		     void (*sync_access)(void))
 {
 	unsigned int i;
 
diff --git a/drivers/irqchip/irq-gic-pm.c b/drivers/irqchip/irq-gic-pm.c
new file mode 100644
index 000000000000..4cbffba3ff13
--- /dev/null
+++ b/drivers/irqchip/irq-gic-pm.c
@@ -0,0 +1,184 @@
+/*
+ * Copyright (C) 2016 NVIDIA CORPORATION, All Rights Reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+#include <linux/module.h>
+#include <linux/clk.h>
+#include <linux/of_device.h>
+#include <linux/of_irq.h>
+#include <linux/irqchip/arm-gic.h>
+#include <linux/platform_device.h>
+#include <linux/pm_clock.h>
+#include <linux/pm_runtime.h>
+#include <linux/slab.h>
+
+struct gic_clk_data {
+	unsigned int num_clocks;
+	const char *const *clocks;
+};
+
+static int gic_runtime_resume(struct device *dev)
+{
+	struct gic_chip_data *gic = dev_get_drvdata(dev);
+	int ret;
+
+	ret = pm_clk_resume(dev);
+	if (ret)
+		return ret;
+
+	/*
+	 * On the very first resume, the pointer to the driver data
+	 * will be NULL and this is intentional, because we do not
+	 * want to restore the GIC on the very first resume. So if
+	 * the pointer is not valid just return.
+	 */
+	if (!gic)
+		return 0;
+
+	gic_dist_restore(gic);
+	gic_cpu_restore(gic);
+
+	return 0;
+}
+
+static int gic_runtime_suspend(struct device *dev)
+{
+	struct gic_chip_data *gic = dev_get_drvdata(dev);
+
+	gic_dist_save(gic);
+	gic_cpu_save(gic);
+
+	return pm_clk_suspend(dev);
+}
+
+static int gic_get_clocks(struct device *dev, const struct gic_clk_data *data)
+{
+	struct clk *clk;
+	unsigned int i;
+	int ret;
+
+	if (!dev || !data)
+		return -EINVAL;
+
+	ret = pm_clk_create(dev);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < data->num_clocks; i++) {
+		clk = of_clk_get_by_name(dev->of_node, data->clocks[i]);
+		if (IS_ERR(clk)) {
+			dev_err(dev, "failed to get clock %s\n",
+				data->clocks[i]);
+			ret = PTR_ERR(clk);
+			goto error;
+		}
+
+		ret = pm_clk_add_clk(dev, clk);
+		if (ret) {
+			dev_err(dev, "failed to add clock at index %d\n", i);
+			clk_put(clk);
+			goto error;
+		}
+	}
+
+	return 0;
+
+error:
+	pm_clk_destroy(dev);
+
+	return ret;
+}
+
+static int gic_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	const struct gic_clk_data *data;
+	struct gic_chip_data *gic;
+	int ret, irq;
+
+	data = of_device_get_match_data(&pdev->dev);
+	if (!data) {
+		dev_err(&pdev->dev, "no device match found\n");
+		return -ENODEV;
+	}
+
+	irq = irq_of_parse_and_map(dev->of_node, 0);
+	if (!irq) {
+		dev_err(dev, "no parent interrupt found!\n");
+		return -EINVAL;
+	}
+
+	ret = gic_get_clocks(dev, data);
+	if (ret)
+		goto irq_dispose;
+
+	pm_runtime_enable(dev);
+
+	ret = pm_runtime_get_sync(dev);
+	if (ret < 0)
+		goto rpm_disable;
+
+	ret = gic_of_init_child(dev, &gic, irq);
+	if (ret)
+		goto rpm_put;
+
+	platform_set_drvdata(pdev, gic);
+
+	pm_runtime_put(dev);
+
+	dev_info(dev, "GIC IRQ controller registered\n");
+
+	return 0;
+
+rpm_put:
+	pm_runtime_put_sync(dev);
+rpm_disable:
+	pm_runtime_disable(dev);
+	pm_clk_destroy(dev);
+irq_dispose:
+	irq_dispose_mapping(irq);
+
+	return ret;
+}
+
+static const struct dev_pm_ops gic_pm_ops = {
+	SET_RUNTIME_PM_OPS(gic_runtime_suspend,
+			   gic_runtime_resume, NULL)
+};
+
+static const char * const gic400_clocks[] = {
+	"clk",
+};
+
+static const struct gic_clk_data gic400_data = {
+	.num_clocks = ARRAY_SIZE(gic400_clocks),
+	.clocks = gic400_clocks,
+};
+
+static const struct of_device_id gic_match[] = {
+	{ .compatible = "nvidia,tegra210-agic",	.data = &gic400_data },
+	{},
+};
+MODULE_DEVICE_TABLE(of, gic_match);
+
+static struct platform_driver gic_driver = {
+	.probe		= gic_probe,
+	.driver		= {
+		.name	= "gic",
+		.of_match_table	= gic_match,
+		.pm	= &gic_pm_ops,
+	}
+};
+
+builtin_platform_driver(gic_driver);
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 6bd881be24ea..7ceaba81efb4 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -41,6 +41,7 @@
 
 #define ITS_FLAGS_CMDQ_NEEDS_FLUSHING		(1ULL << 0)
 #define ITS_FLAGS_WORKAROUND_CAVIUM_22375	(1ULL << 1)
+#define ITS_FLAGS_WORKAROUND_CAVIUM_23144	(1ULL << 2)
 
 #define RDIST_FLAGS_PROPBASE_NEEDS_FLUSHING	(1 << 0)
 
@@ -55,13 +56,14 @@ struct its_collection {
 };
 
 /*
- * The ITS_BASER structure - contains memory information and cached
- * value of BASER register configuration.
+ * The ITS_BASER structure - contains memory information, cached
+ * value of BASER register configuration and ITS page size.
  */
 struct its_baser {
 	void		*base;
 	u64		val;
 	u32		order;
+	u32		psz;
 };
 
 /*
@@ -82,6 +84,7 @@ struct its_node {
 	u64			flags;
 	u32			ite_size;
 	u32			device_ids;
+	int			numa_node;
 };
 
 #define ITS_ITT_ALIGN		SZ_256
@@ -613,11 +616,23 @@ static void its_unmask_irq(struct irq_data *d)
 static int its_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 			    bool force)
 {
-	unsigned int cpu = cpumask_any_and(mask_val, cpu_online_mask);
+	unsigned int cpu;
+	const struct cpumask *cpu_mask = cpu_online_mask;
 	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
 	struct its_collection *target_col;
 	u32 id = its_get_event_id(d);
 
+       /* lpi cannot be routed to a redistributor that is on a foreign node */
+	if (its_dev->its->flags & ITS_FLAGS_WORKAROUND_CAVIUM_23144) {
+		if (its_dev->its->numa_node >= 0) {
+			cpu_mask = cpumask_of_node(its_dev->its->numa_node);
+			if (!cpumask_intersects(mask_val, cpu_mask))
+				return -EINVAL;
+		}
+	}
+
+	cpu = cpumask_any_and(mask_val, cpu_mask);
+
 	if (cpu >= nr_cpu_ids)
 		return -EINVAL;
 
@@ -810,180 +825,241 @@ static const char *its_base_type_string[] = {
 	[GITS_BASER_TYPE_RESERVED7] 	= "Reserved (7)",
 };
 
-static void its_free_tables(struct its_node *its)
+static u64 its_read_baser(struct its_node *its, struct its_baser *baser)
 {
-	int i;
+	u32 idx = baser - its->tables;
 
-	for (i = 0; i < GITS_BASER_NR_REGS; i++) {
-		if (its->tables[i].base) {
-			free_pages((unsigned long)its->tables[i].base,
-				   its->tables[i].order);
-			its->tables[i].base = NULL;
-		}
-	}
+	return readq_relaxed(its->base + GITS_BASER + (idx << 3));
 }
 
-static int its_alloc_tables(const char *node_name, struct its_node *its)
+static void its_write_baser(struct its_node *its, struct its_baser *baser,
+			    u64 val)
 {
-	int err;
-	int i;
-	int psz = SZ_64K;
-	u64 shr = GITS_BASER_InnerShareable;
-	u64 cache;
-	u64 typer;
-	u32 ids;
+	u32 idx = baser - its->tables;
 
-	if (its->flags & ITS_FLAGS_WORKAROUND_CAVIUM_22375) {
-		/*
-		 * erratum 22375: only alloc 8MB table size
-		 * erratum 24313: ignore memory access type
-		 */
-		cache	= 0;
-		ids	= 0x14;			/* 20 bits, 8MB */
-	} else {
-		cache	= GITS_BASER_WaWb;
-		typer	= readq_relaxed(its->base + GITS_TYPER);
-		ids	= GITS_TYPER_DEVBITS(typer);
+	writeq_relaxed(val, its->base + GITS_BASER + (idx << 3));
+	baser->val = its_read_baser(its, 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 val = its_read_baser(its, baser);
+	u64 esz = GITS_BASER_ENTRY_SIZE(val);
+	u64 type = GITS_BASER_TYPE(val);
+	u32 alloc_pages;
+	void *base;
+	u64 tmp;
+
+retry_alloc_baser:
+	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",
+			&its->phys_base, its_base_type_string[type],
+			alloc_pages, GITS_BASER_PAGES_MAX);
+		alloc_pages = GITS_BASER_PAGES_MAX;
+		order = get_order(GITS_BASER_PAGES_MAX * psz);
 	}
 
-	its->device_ids = ids;
+	base = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, order);
+	if (!base)
+		return -ENOMEM;
 
-	for (i = 0; i < GITS_BASER_NR_REGS; i++) {
-		u64 val = readq_relaxed(its->base + GITS_BASER + i * 8);
-		u64 type = GITS_BASER_TYPE(val);
-		u64 entry_size = GITS_BASER_ENTRY_SIZE(val);
-		int order = get_order(psz);
-		int alloc_pages;
-		u64 tmp;
-		void *base;
+retry_baser:
+	val = (virt_to_phys(base)				 |
+		(type << GITS_BASER_TYPE_SHIFT)			 |
+		((esz - 1) << GITS_BASER_ENTRY_SIZE_SHIFT)	 |
+		((alloc_pages - 1) << GITS_BASER_PAGES_SHIFT)	 |
+		cache						 |
+		shr						 |
+		GITS_BASER_VALID);
+
+	val |=	indirect ? GITS_BASER_INDIRECT : 0x0;
+
+	switch (psz) {
+	case SZ_4K:
+		val |= GITS_BASER_PAGE_SIZE_4K;
+		break;
+	case SZ_16K:
+		val |= GITS_BASER_PAGE_SIZE_16K;
+		break;
+	case SZ_64K:
+		val |= GITS_BASER_PAGE_SIZE_64K;
+		break;
+	}
 
-		if (type == GITS_BASER_TYPE_NONE)
-			continue;
+	its_write_baser(its, baser, val);
+	tmp = baser->val;
 
+	if ((val ^ tmp) & GITS_BASER_SHAREABILITY_MASK) {
 		/*
-		 * Allocate as many entries as required to fit the
-		 * range of device IDs that the ITS can grok... The ID
-		 * space being incredibly sparse, this results in a
-		 * massive waste of memory.
-		 *
-		 * For other tables, only allocate a single page.
+		 * Shareability didn't stick. Just use
+		 * whatever the read reported, which is likely
+		 * to be the only thing this redistributor
+		 * supports. If that's zero, make it
+		 * non-cacheable as well.
 		 */
-		if (type == GITS_BASER_TYPE_DEVICE) {
-			/*
-			 * 'order' was initialized earlier to the default page
-			 * granule of the the ITS.  We can't have an allocation
-			 * smaller than that.  If the requested allocation
-			 * is smaller, round up to the default page granule.
-			 */
-			order = max(get_order((1UL << ids) * entry_size),
-				    order);
-			if (order >= MAX_ORDER) {
-				order = MAX_ORDER - 1;
-				pr_warn("%s: Device Table too large, reduce its page order to %u\n",
-					node_name, order);
-			}
+		shr = tmp & GITS_BASER_SHAREABILITY_MASK;
+		if (!shr) {
+			cache = GITS_BASER_nC;
+			__flush_dcache_area(base, PAGE_ORDER_TO_SIZE(order));
 		}
+		goto retry_baser;
+	}
 
-retry_alloc_baser:
-		alloc_pages = (PAGE_ORDER_TO_SIZE(order) / psz);
-		if (alloc_pages > GITS_BASER_PAGES_MAX) {
-			alloc_pages = GITS_BASER_PAGES_MAX;
-			order = get_order(GITS_BASER_PAGES_MAX * psz);
-			pr_warn("%s: Device Table too large, reduce its page order to %u (%u pages)\n",
-				node_name, order, alloc_pages);
-		}
-
-		base = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, order);
-		if (!base) {
-			err = -ENOMEM;
-			goto out_free;
-		}
-
-		its->tables[i].base = base;
-		its->tables[i].order = order;
-
-retry_baser:
-		val = (virt_to_phys(base) 				 |
-		       (type << GITS_BASER_TYPE_SHIFT)			 |
-		       ((entry_size - 1) << GITS_BASER_ENTRY_SIZE_SHIFT) |
-		       cache						 |
-		       shr						 |
-		       GITS_BASER_VALID);
+	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_4K:
-			val |= GITS_BASER_PAGE_SIZE_4K;
-			break;
 		case SZ_16K:
-			val |= GITS_BASER_PAGE_SIZE_16K;
-			break;
+			psz = SZ_4K;
+			goto retry_alloc_baser;
 		case SZ_64K:
-			val |= GITS_BASER_PAGE_SIZE_64K;
-			break;
+			psz = SZ_16K;
+			goto retry_alloc_baser;
 		}
+	}
+
+	if (val != tmp) {
+		pr_err("ITS@%pa: %s doesn't stick: %lx %lx\n",
+		       &its->phys_base, its_base_type_string[type],
+		       (unsigned long) val, (unsigned long) tmp);
+		free_pages((unsigned long)base, order);
+		return -ENXIO;
+	}
+
+	baser->order = order;
+	baser->base = base;
+	baser->psz = psz;
+	tmp = indirect ? GITS_LVL1_ENTRY_SIZE : esz;
+
+	pr_info("ITS@%pa: allocated %d %s @%lx (%s, esz %d, psz %dK, shr %d)\n",
+		&its->phys_base, (int)(PAGE_ORDER_TO_SIZE(order) / tmp),
+		its_base_type_string[type],
+		(unsigned long)virt_to_phys(base),
+		indirect ? "indirect" : "flat", (int)esz,
+		psz / SZ_1K, (int)shr >> GITS_BASER_SHAREABILITY_SHIFT);
 
-		val |= alloc_pages - 1;
-		its->tables[i].val = val;
+	return 0;
+}
 
-		writeq_relaxed(val, its->base + GITS_BASER + i * 8);
-		tmp = readq_relaxed(its->base + GITS_BASER + i * 8);
+static bool its_parse_baser_device(struct its_node *its, struct its_baser *baser,
+				   u32 psz, u32 *order)
+{
+	u64 esz = GITS_BASER_ENTRY_SIZE(its_read_baser(its, baser));
+	u64 val = GITS_BASER_InnerShareable | GITS_BASER_WaWb;
+	u32 ids = its->device_ids;
+	u32 new_order = *order;
+	bool indirect = false;
+
+	/* No need to enable Indirection if memory requirement < (psz*2)bytes */
+	if ((esz << ids) > (psz * 2)) {
+		/*
+		 * Find out whether hw supports a single or two-level table by
+		 * table by reading bit at offset '62' after writing '1' to it.
+		 */
+		its_write_baser(its, baser, val | GITS_BASER_INDIRECT);
+		indirect = !!(baser->val & GITS_BASER_INDIRECT);
 
-		if ((val ^ tmp) & GITS_BASER_SHAREABILITY_MASK) {
+		if (indirect) {
 			/*
-			 * Shareability didn't stick. Just use
-			 * whatever the read reported, which is likely
-			 * to be the only thing this redistributor
-			 * supports. If that's zero, make it
-			 * non-cacheable as well.
+			 * The size of the lvl2 table is equal to ITS page size
+			 * which is 'psz'. For computing lvl1 table size,
+			 * subtract ID bits that sparse lvl2 table from 'ids'
+			 * which is reported by ITS hardware times lvl1 table
+			 * entry size.
 			 */
-			shr = tmp & GITS_BASER_SHAREABILITY_MASK;
-			if (!shr) {
-				cache = GITS_BASER_nC;
-				__flush_dcache_area(base, PAGE_ORDER_TO_SIZE(order));
-			}
-			goto retry_baser;
+			ids -= ilog2(psz / esz);
+			esz = GITS_LVL1_ENTRY_SIZE;
 		}
+	}
 
-		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);
-			its->tables[i].base = NULL;
+	/*
+	 * Allocate as many entries as required to fit the
+	 * range of device IDs that the ITS can grok... The ID
+	 * space being incredibly sparse, this results in a
+	 * massive waste of memory if two-level device table
+	 * feature is not supported by hardware.
+	 */
+	new_order = max_t(u32, get_order(esz << ids), new_order);
+	if (new_order >= MAX_ORDER) {
+		new_order = MAX_ORDER - 1;
+		ids = ilog2(PAGE_ORDER_TO_SIZE(new_order) / esz);
+		pr_warn("ITS@%pa: Device Table too large, reduce ids %u->%u\n",
+			&its->phys_base, its->device_ids, ids);
+	}
 
-			switch (psz) {
-			case SZ_16K:
-				psz = SZ_4K;
-				goto retry_alloc_baser;
-			case SZ_64K:
-				psz = SZ_16K;
-				goto retry_alloc_baser;
-			}
-		}
+	*order = new_order;
 
-		if (val != tmp) {
-			pr_err("ITS: %s: GITS_BASER%d doesn't stick: %lx %lx\n",
-			       node_name, i,
-			       (unsigned long) val, (unsigned long) tmp);
-			err = -ENXIO;
-			goto out_free;
+	return indirect;
+}
+
+static void its_free_tables(struct its_node *its)
+{
+	int i;
+
+	for (i = 0; i < GITS_BASER_NR_REGS; i++) {
+		if (its->tables[i].base) {
+			free_pages((unsigned long)its->tables[i].base,
+				   its->tables[i].order);
+			its->tables[i].base = NULL;
 		}
+	}
+}
 
-		pr_info("ITS: allocated %d %s @%lx (psz %dK, shr %d)\n",
-			(int)(PAGE_ORDER_TO_SIZE(order) / entry_size),
-			its_base_type_string[type],
-			(unsigned long)virt_to_phys(base),
-			psz / SZ_1K, (int)shr >> GITS_BASER_SHAREABILITY_SHIFT);
+static int its_alloc_tables(struct its_node *its)
+{
+	u64 typer = readq_relaxed(its->base + GITS_TYPER);
+	u32 ids = GITS_TYPER_DEVBITS(typer);
+	u64 shr = GITS_BASER_InnerShareable;
+	u64 cache = GITS_BASER_WaWb;
+	u32 psz = SZ_64K;
+	int err, i;
+
+	if (its->flags & ITS_FLAGS_WORKAROUND_CAVIUM_22375) {
+		/*
+		* erratum 22375: only alloc 8MB table size
+		* erratum 24313: ignore memory access type
+		*/
+		cache   = GITS_BASER_nCnB;
+		ids     = 0x14;                 /* 20 bits, 8MB */
 	}
 
-	return 0;
+	its->device_ids = ids;
 
-out_free:
-	its_free_tables(its);
+	for (i = 0; i < GITS_BASER_NR_REGS; i++) {
+		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;
 
-	return err;
+		if (type == GITS_BASER_TYPE_NONE)
+			continue;
+
+		if (type == GITS_BASER_TYPE_DEVICE)
+			indirect = its_parse_baser_device(its, baser, psz, &order);
+
+		err = its_setup_baser(its, baser, cache, shr, psz, 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;
+	}
+
+	return 0;
 }
 
 static int its_alloc_collections(struct its_node *its)
@@ -1101,6 +1177,16 @@ static void its_cpu_init_collection(void)
 	list_for_each_entry(its, &its_nodes, entry) {
 		u64 target;
 
+		/* avoid cross node collections and its mapping */
+		if (its->flags & ITS_FLAGS_WORKAROUND_CAVIUM_23144) {
+			struct device_node *cpu_node;
+
+			cpu_node = of_get_cpu_node(cpu, NULL);
+			if (its->numa_node != NUMA_NO_NODE &&
+				its->numa_node != of_node_to_nid(cpu_node))
+				continue;
+		}
+
 		/*
 		 * We now have to bind each collection to its target
 		 * redistributor.
@@ -1161,10 +1247,57 @@ static struct its_baser *its_get_baser(struct its_node *its, u32 type)
 	return NULL;
 }
 
+static bool its_alloc_device_table(struct its_node *its, u32 dev_id)
+{
+	struct its_baser *baser;
+	struct page *page;
+	u32 esz, idx;
+	__le64 *table;
+
+	baser = its_get_baser(its, GITS_BASER_TYPE_DEVICE);
+
+	/* Don't allow device id that exceeds ITS hardware limit */
+	if (!baser)
+		return (ilog2(dev_id) < its->device_ids);
+
+	/* Don't allow device id that exceeds single, flat table limit */
+	esz = GITS_BASER_ENTRY_SIZE(baser->val);
+	if (!(baser->val & GITS_BASER_INDIRECT))
+		return (dev_id < (PAGE_ORDER_TO_SIZE(baser->order) / esz));
+
+	/* Compute 1st level table index & check if that exceeds table limit */
+	idx = dev_id >> ilog2(baser->psz / esz);
+	if (idx >= (PAGE_ORDER_TO_SIZE(baser->order) / GITS_LVL1_ENTRY_SIZE))
+		return false;
+
+	table = baser->base;
+
+	/* Allocate memory for 2nd level table */
+	if (!table[idx]) {
+		page = alloc_pages(GFP_KERNEL | __GFP_ZERO, get_order(baser->psz));
+		if (!page)
+			return false;
+
+		/* Flush Lvl2 table to PoC if hw doesn't support coherency */
+		if (!(baser->val & GITS_BASER_SHAREABILITY_MASK))
+			__flush_dcache_area(page_address(page), baser->psz);
+
+		table[idx] = cpu_to_le64(page_to_phys(page) | GITS_BASER_VALID);
+
+		/* Flush Lvl1 entry to PoC if hw doesn't support coherency */
+		if (!(baser->val & GITS_BASER_SHAREABILITY_MASK))
+			__flush_dcache_area(table + idx, GITS_LVL1_ENTRY_SIZE);
+
+		/* Ensure updated table contents are visible to ITS hardware */
+		dsb(sy);
+	}
+
+	return true;
+}
+
 static struct its_device *its_create_device(struct its_node *its, u32 dev_id,
 					    int nvecs)
 {
-	struct its_baser *baser;
 	struct its_device *dev;
 	unsigned long *lpi_map;
 	unsigned long flags;
@@ -1175,14 +1308,7 @@ static struct its_device *its_create_device(struct its_node *its, u32 dev_id,
 	int nr_ites;
 	int sz;
 
-	baser = its_get_baser(its, GITS_BASER_TYPE_DEVICE);
-
-	/* Don't allow 'dev_id' that exceeds single, flat table limit */
-	if (baser) {
-		if (dev_id >= (PAGE_ORDER_TO_SIZE(baser->order) /
-			      GITS_BASER_ENTRY_SIZE(baser->val)))
-			return NULL;
-	} else if (ilog2(dev_id) >= its->device_ids)
+	if (!its_alloc_device_table(its, dev_id))
 		return NULL;
 
 	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
@@ -1351,9 +1477,14 @@ static void its_irq_domain_activate(struct irq_domain *domain,
 {
 	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
 	u32 event = its_get_event_id(d);
+	const struct cpumask *cpu_mask = cpu_online_mask;
+
+	/* get the cpu_mask of local node */
+	if (its_dev->its->numa_node >= 0)
+		cpu_mask = cpumask_of_node(its_dev->its->numa_node);
 
 	/* Bind the LPI to the first possible CPU */
-	its_dev->event_map.col_map[event] = cpumask_first(cpu_online_mask);
+	its_dev->event_map.col_map[event] = cpumask_first(cpu_mask);
 
 	/* Map the GIC IRQ and event to the device */
 	its_send_mapvi(its_dev, d->hwirq, event);
@@ -1443,6 +1574,13 @@ static void __maybe_unused its_enable_quirk_cavium_22375(void *data)
 	its->flags |= ITS_FLAGS_WORKAROUND_CAVIUM_22375;
 }
 
+static void __maybe_unused its_enable_quirk_cavium_23144(void *data)
+{
+	struct its_node *its = data;
+
+	its->flags |= ITS_FLAGS_WORKAROUND_CAVIUM_23144;
+}
+
 static const struct gic_quirk its_quirks[] = {
 #ifdef CONFIG_CAVIUM_ERRATUM_22375
 	{
@@ -1452,6 +1590,14 @@ static const struct gic_quirk its_quirks[] = {
 		.init	= its_enable_quirk_cavium_22375,
 	},
 #endif
+#ifdef CONFIG_CAVIUM_ERRATUM_23144
+	{
+		.desc	= "ITS: Cavium erratum 23144",
+		.iidr	= 0xa100034c,	/* ThunderX pass 1.x */
+		.mask	= 0xffff0fff,
+		.init	= its_enable_quirk_cavium_23144,
+	},
+#endif
 	{
 	}
 };
@@ -1514,6 +1660,7 @@ static int __init its_probe(struct device_node *node,
 	its->base = its_base;
 	its->phys_base = res.start;
 	its->ite_size = ((readl_relaxed(its_base + GITS_TYPER) >> 4) & 0xf) + 1;
+	its->numa_node = of_node_to_nid(node);
 
 	its->cmd_base = kzalloc(ITS_CMD_QUEUE_SZ, GFP_KERNEL);
 	if (!its->cmd_base) {
@@ -1524,7 +1671,7 @@ static int __init its_probe(struct device_node *node,
 
 	its_enable_quirks(its);
 
-	err = its_alloc_tables(node->full_name, its);
+	err = its_alloc_tables(its);
 	if (err)
 		goto out_free_cmd;
 
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index fb042ba9a3db..2c5ba0e704bf 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -155,7 +155,7 @@ static void gic_enable_redist(bool enable)
 
 	while (count--) {
 		val = readl_relaxed(rbase + GICR_WAKER);
-		if (enable ^ (val & GICR_WAKER_ChildrenAsleep))
+		if (enable ^ (bool)(val & GICR_WAKER_ChildrenAsleep))
 			break;
 		cpu_relax();
 		udelay(1);
diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index fbc4ae2afd29..1de07eb5839c 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -75,7 +75,7 @@ struct gic_chip_data {
 	void __iomem *raw_dist_base;
 	void __iomem *raw_cpu_base;
 	u32 percpu_offset;
-#ifdef CONFIG_CPU_PM
+#if defined(CONFIG_CPU_PM) || defined(CONFIG_ARM_GIC_PM)
 	u32 saved_spi_enable[DIV_ROUND_UP(1020, 32)];
 	u32 saved_spi_active[DIV_ROUND_UP(1020, 32)];
 	u32 saved_spi_conf[DIV_ROUND_UP(1020, 16)];
@@ -449,7 +449,7 @@ static void gic_cpu_if_up(struct gic_chip_data *gic)
 }
 
 
-static void __init gic_dist_init(struct gic_chip_data *gic)
+static void gic_dist_init(struct gic_chip_data *gic)
 {
 	unsigned int i;
 	u32 cpumask;
@@ -528,14 +528,14 @@ int gic_cpu_if_down(unsigned int gic_nr)
 	return 0;
 }
 
-#ifdef CONFIG_CPU_PM
+#if defined(CONFIG_CPU_PM) || defined(CONFIG_ARM_GIC_PM)
 /*
  * Saves the GIC distributor registers during suspend or idle.  Must be called
  * with interrupts disabled but before powering down the GIC.  After calling
  * this function, no interrupts will be delivered by the GIC, and another
  * platform-specific wakeup source must be enabled.
  */
-static void gic_dist_save(struct gic_chip_data *gic)
+void gic_dist_save(struct gic_chip_data *gic)
 {
 	unsigned int gic_irqs;
 	void __iomem *dist_base;
@@ -574,7 +574,7 @@ static void gic_dist_save(struct gic_chip_data *gic)
  * handled normally, but any edge interrupts that occured will not be seen by
  * the GIC and need to be handled by the platform-specific wakeup source.
  */
-static void gic_dist_restore(struct gic_chip_data *gic)
+void gic_dist_restore(struct gic_chip_data *gic)
 {
 	unsigned int gic_irqs;
 	unsigned int i;
@@ -620,7 +620,7 @@ static void gic_dist_restore(struct gic_chip_data *gic)
 	writel_relaxed(GICD_ENABLE, dist_base + GIC_DIST_CTRL);
 }
 
-static void gic_cpu_save(struct gic_chip_data *gic)
+void gic_cpu_save(struct gic_chip_data *gic)
 {
 	int i;
 	u32 *ptr;
@@ -650,7 +650,7 @@ static void gic_cpu_save(struct gic_chip_data *gic)
 
 }
 
-static void gic_cpu_restore(struct gic_chip_data *gic)
+void gic_cpu_restore(struct gic_chip_data *gic)
 {
 	int i;
 	u32 *ptr;
@@ -727,7 +727,7 @@ static struct notifier_block gic_notifier_block = {
 	.notifier_call = gic_notifier,
 };
 
-static int __init gic_pm_init(struct gic_chip_data *gic)
+static int gic_pm_init(struct gic_chip_data *gic)
 {
 	gic->saved_ppi_enable = __alloc_percpu(DIV_ROUND_UP(32, 32) * 4,
 		sizeof(u32));
@@ -757,7 +757,7 @@ free_ppi_enable:
 	return -ENOMEM;
 }
 #else
-static int __init gic_pm_init(struct gic_chip_data *gic)
+static int gic_pm_init(struct gic_chip_data *gic)
 {
 	return 0;
 }
@@ -1032,32 +1032,31 @@ static const struct irq_domain_ops gic_irq_domain_ops = {
 	.unmap = gic_irq_domain_unmap,
 };
 
-static int __init __gic_init_bases(struct gic_chip_data *gic, int irq_start,
-				   struct fwnode_handle *handle)
+static void gic_init_chip(struct gic_chip_data *gic, struct device *dev,
+			  const char *name, bool use_eoimode1)
 {
-	irq_hw_number_t hwirq_base;
-	int gic_irqs, irq_base, i, ret;
-
-	if (WARN_ON(!gic || gic->domain))
-		return -EINVAL;
-
 	/* Initialize irq_chip */
 	gic->chip = gic_chip;
+	gic->chip.name = name;
+	gic->chip.parent_device = dev;
 
-	if (static_key_true(&supports_deactivate) && gic == &gic_data[0]) {
+	if (use_eoimode1) {
 		gic->chip.irq_mask = gic_eoimode1_mask_irq;
 		gic->chip.irq_eoi = gic_eoimode1_eoi_irq;
 		gic->chip.irq_set_vcpu_affinity = gic_irq_set_vcpu_affinity;
-		gic->chip.name = kasprintf(GFP_KERNEL, "GICv2");
-	} else {
-		gic->chip.name = kasprintf(GFP_KERNEL, "GIC-%d",
-					   (int)(gic - &gic_data[0]));
 	}
 
 #ifdef CONFIG_SMP
 	if (gic == &gic_data[0])
 		gic->chip.irq_set_affinity = gic_set_affinity;
 #endif
+}
+
+static int gic_init_bases(struct gic_chip_data *gic, int irq_start,
+			  struct fwnode_handle *handle)
+{
+	irq_hw_number_t hwirq_base;
+	int gic_irqs, irq_base, ret;
 
 	if (IS_ENABLED(CONFIG_GIC_NON_BANKED) && gic->percpu_offset) {
 		/* Frankein-GIC without banked registers... */
@@ -1138,6 +1137,36 @@ static int __init __gic_init_bases(struct gic_chip_data *gic, int irq_start,
 		goto error;
 	}
 
+	gic_dist_init(gic);
+	ret = gic_cpu_init(gic);
+	if (ret)
+		goto error;
+
+	ret = gic_pm_init(gic);
+	if (ret)
+		goto error;
+
+	return 0;
+
+error:
+	if (IS_ENABLED(CONFIG_GIC_NON_BANKED) && gic->percpu_offset) {
+		free_percpu(gic->dist_base.percpu_base);
+		free_percpu(gic->cpu_base.percpu_base);
+	}
+
+	return ret;
+}
+
+static int __init __gic_init_bases(struct gic_chip_data *gic,
+				   int irq_start,
+				   struct fwnode_handle *handle)
+{
+	char *name;
+	int i, ret;
+
+	if (WARN_ON(!gic || gic->domain))
+		return -EINVAL;
+
 	if (gic == &gic_data[0]) {
 		/*
 		 * Initialize the CPU interface map to all CPUs.
@@ -1155,24 +1184,17 @@ static int __init __gic_init_bases(struct gic_chip_data *gic, int irq_start,
 			pr_info("GIC: Using split EOI/Deactivate mode\n");
 	}
 
-	gic_dist_init(gic);
-	ret = gic_cpu_init(gic);
-	if (ret)
-		goto error;
-
-	ret = gic_pm_init(gic);
-	if (ret)
-		goto error;
-
-	return 0;
-
-error:
-	if (IS_ENABLED(CONFIG_GIC_NON_BANKED) && gic->percpu_offset) {
-		free_percpu(gic->dist_base.percpu_base);
-		free_percpu(gic->cpu_base.percpu_base);
+	if (static_key_true(&supports_deactivate) && gic == &gic_data[0]) {
+		name = kasprintf(GFP_KERNEL, "GICv2");
+		gic_init_chip(gic, NULL, name, true);
+	} else {
+		name = kasprintf(GFP_KERNEL, "GIC-%d", (int)(gic-&gic_data[0]));
+		gic_init_chip(gic, NULL, name, false);
 	}
 
-	kfree(gic->chip.name);
+	ret = gic_init_bases(gic, irq_start, handle);
+	if (ret)
+		kfree(name);
 
 	return ret;
 }
@@ -1250,7 +1272,7 @@ static bool gic_check_eoimode(struct device_node *node, void __iomem **base)
 	return true;
 }
 
-static int __init gic_of_setup(struct gic_chip_data *gic, struct device_node *node)
+static int gic_of_setup(struct gic_chip_data *gic, struct device_node *node)
 {
 	if (!gic || !node)
 		return -EINVAL;
@@ -1274,6 +1296,34 @@ error:
 	return -ENOMEM;
 }
 
+int gic_of_init_child(struct device *dev, struct gic_chip_data **gic, int irq)
+{
+	int ret;
+
+	if (!dev || !dev->of_node || !gic || !irq)
+		return -EINVAL;
+
+	*gic = devm_kzalloc(dev, sizeof(**gic), GFP_KERNEL);
+	if (!*gic)
+		return -ENOMEM;
+
+	gic_init_chip(*gic, dev, dev->of_node->name, false);
+
+	ret = gic_of_setup(*gic, dev->of_node);
+	if (ret)
+		return ret;
+
+	ret = gic_init_bases(*gic, -1, &dev->of_node->fwnode);
+	if (ret) {
+		gic_teardown(*gic);
+		return ret;
+	}
+
+	irq_set_chained_handler_and_data(irq, gic_handle_cascade_irq, *gic);
+
+	return 0;
+}
+
 static void __init gic_of_setup_kvm_info(struct device_node *node)
 {
 	int ret;
@@ -1353,7 +1403,11 @@ IRQCHIP_DECLARE(cortex_a7_gic, "arm,cortex-a7-gic", gic_of_init);
 IRQCHIP_DECLARE(msm_8660_qgic, "qcom,msm-8660-qgic", gic_of_init);
 IRQCHIP_DECLARE(msm_qgic2, "qcom,msm-qgic2", gic_of_init);
 IRQCHIP_DECLARE(pl390, "arm,pl390", gic_of_init);
-
+#else
+int gic_of_init_child(struct device *dev, struct gic_chip_data **gic, int irq)
+{
+	return -ENOTSUPP;
+}
 #endif
 
 #ifdef CONFIG_ACPI
diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c
index 3b5e10aa48ab..df9a1fe23cb1 100644
--- a/drivers/irqchip/irq-mips-gic.c
+++ b/drivers/irqchip/irq-mips-gic.c
@@ -1032,12 +1032,14 @@ static void __init __gic_init(unsigned long gic_base_addr,
 					       &gic_irq_domain_ops, NULL);
 	if (!gic_irq_domain)
 		panic("Failed to add GIC IRQ domain");
+	gic_irq_domain->name = "mips-gic-irq";
 
 	gic_dev_domain = irq_domain_add_hierarchy(gic_irq_domain, 0,
 						  GIC_NUM_LOCAL_INTRS + gic_shared_intrs,
 						  node, &gic_dev_domain_ops, NULL);
 	if (!gic_dev_domain)
 		panic("Failed to add GIC DEV domain");
+	gic_dev_domain->name = "mips-gic-dev";
 
 	gic_ipi_domain = irq_domain_add_hierarchy(gic_irq_domain,
 						  IRQ_DOMAIN_FLAG_IPI_PER_CPU,
@@ -1046,6 +1048,7 @@ static void __init __gic_init(unsigned long gic_base_addr,
 	if (!gic_ipi_domain)
 		panic("Failed to add GIC IPI domain");
 
+	gic_ipi_domain->name = "mips-gic-ipi";
 	gic_ipi_domain->bus_token = DOMAIN_BUS_IPI;
 
 	if (node &&
diff --git a/drivers/irqchip/irq-pic32-evic.c b/drivers/irqchip/irq-pic32-evic.c
index e7155db01d55..73addb4b625b 100644
--- a/drivers/irqchip/irq-pic32-evic.c
+++ b/drivers/irqchip/irq-pic32-evic.c
@@ -91,7 +91,7 @@ static int pic32_set_type_edge(struct irq_data *data,
 	/* set polarity for external interrupts only */
 	for (i = 0; i < ARRAY_SIZE(priv->ext_irqs); i++) {
 		if (priv->ext_irqs[i] == data->hwirq) {
-			ret = pic32_set_ext_polarity(i + 1, flow_type);
+			ret = pic32_set_ext_polarity(i, flow_type);
 			if (ret)
 				return ret;
 		}