Merge branch 'irq-irqdomain-arm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull irq domain ARM updates from Thomas Gleixner:
 "This set of changes make use of hierarchical irqdomains to provide:

   - MSI/ITS support for GICv3
   - MSI support for GICv2m
   - Interrupt polarity extender for GICv1

  Marc has come more cleanups for the existing extension hooks of GIC in
  the pipeline, but they are going to be 3.20 material"

* 'irq-irqdomain-arm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (22 commits)
  irqchip: gicv3-its: Fix ITT allocation
  irqchip: gicv3-its: Move some alloc/free code to activate/deactivate
  irqchip: gicv3-its: Fix domain free in multi-MSI case
  irqchip: gic: Remove warning by including linux/irqdomain.h
  irqchip: gic-v2m: Add DT bindings for GICv2m
  irqchip: gic-v2m: Add support for ARM GICv2m MSI(-X) doorbell
  irqchip: mtk-sysirq: dt-bindings: Add bindings for mediatek sysirq
  irqchip: mtk-sysirq: Add sysirq interrupt polarity support
  irqchip: gic: Support hierarchy irq domain.
  irqchip: GICv3: Binding updates for ITS
  irqchip: GICv3: ITS: enable compilation of the ITS driver
  irqchip: GICv3: ITS: plug ITS init into main GICv3 code
  irqchip: GICv3: ITS: DT probing and initialization
  irqchip: GICv3: ITS: MSI support
  irqchip: GICv3: ITS: device allocation and configuration
  irqchip: GICv3: ITS: tables allocators
  irqchip: GICv3: ITS: LPI allocator
  irqchip: GICv3: ITS: irqchip implementation
  irqchip: GICv3: ITS command queue
  irqchip: GICv3: rework redistributor structure
  ...

7 files changed, 2109 insertions, 64 deletions

diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index e12cb23d786c..cc79d2a5a8c2 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -5,8 +5,15 @@ config IRQCHIP
 config ARM_GIC
 	bool
 	select IRQ_DOMAIN
+	select IRQ_DOMAIN_HIERARCHY
 	select MULTI_IRQ_HANDLER
 
+config ARM_GIC_V2M
+	bool
+	depends on ARM_GIC
+	depends on PCI && PCI_MSI
+	select PCI_MSI_IRQ_DOMAIN
+
 config GIC_NON_BANKED
 	bool
 
@@ -14,6 +21,11 @@ config ARM_GIC_V3
 	bool
 	select IRQ_DOMAIN
 	select MULTI_IRQ_HANDLER
+	select IRQ_DOMAIN_HIERARCHY
+
+config ARM_GIC_V3_ITS
+	bool
+	select PCI_MSI_IRQ_DOMAIN
 
 config ARM_NVIC
 	bool
diff --git a/drivers/irqchip/Makefile b/drivers/irqchip/Makefile
index 4954a314c31e..9516a324be6d 100644
--- a/drivers/irqchip/Makefile
+++ b/drivers/irqchip/Makefile
@@ -19,7 +19,9 @@ 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-$(CONFIG_ARM_GIC_V2M)		+= irq-gic-v2m.o
 obj-$(CONFIG_ARM_GIC_V3)		+= irq-gic-v3.o irq-gic-common.o
+obj-$(CONFIG_ARM_GIC_V3_ITS)		+= irq-gic-v3-its.o
 obj-$(CONFIG_ARM_NVIC)			+= irq-nvic.o
 obj-$(CONFIG_ARM_VIC)			+= irq-vic.o
 obj-$(CONFIG_ATMEL_AIC_IRQ)		+= irq-atmel-aic-common.o irq-atmel-aic.o
@@ -39,3 +41,4 @@ obj-$(CONFIG_BCM7120_L2_IRQ)		+= irq-bcm7120-l2.o
 obj-$(CONFIG_BRCMSTB_L2_IRQ)		+= irq-brcmstb-l2.o
 obj-$(CONFIG_KEYSTONE_IRQ)		+= irq-keystone.o
 obj-$(CONFIG_MIPS_GIC)			+= irq-mips-gic.o
+obj-$(CONFIG_ARCH_MEDIATEK)		+= irq-mtk-sysirq.o
diff --git a/drivers/irqchip/irq-gic-v2m.c b/drivers/irqchip/irq-gic-v2m.c
new file mode 100644
index 000000000000..fdf706555d72
--- /dev/null
+++ b/drivers/irqchip/irq-gic-v2m.c
@@ -0,0 +1,333 @@
+/*
+ * ARM GIC v2m MSI(-X) support
+ * Support for Message Signaled Interrupts for systems that
+ * implement ARM Generic Interrupt Controller: GICv2m.
+ *
+ * Copyright (C) 2014 Advanced Micro Devices, Inc.
+ * Authors: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
+ *	    Harish Kasiviswanathan <harish.kasiviswanathan@amd.com>
+ *	    Brandon Anderson <brandon.anderson@amd.com>
+ *
+ * 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.
+ */
+
+#define pr_fmt(fmt) "GICv2m: " fmt
+
+#include <linux/irq.h>
+#include <linux/irqdomain.h>
+#include <linux/kernel.h>
+#include <linux/of_address.h>
+#include <linux/of_pci.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+
+/*
+* MSI_TYPER:
+*     [31:26] Reserved
+*     [25:16] lowest SPI assigned to MSI
+*     [15:10] Reserved
+*     [9:0]   Numer of SPIs assigned to MSI
+*/
+#define V2M_MSI_TYPER		       0x008
+#define V2M_MSI_TYPER_BASE_SHIFT       16
+#define V2M_MSI_TYPER_BASE_MASK	       0x3FF
+#define V2M_MSI_TYPER_NUM_MASK	       0x3FF
+#define V2M_MSI_SETSPI_NS	       0x040
+#define V2M_MIN_SPI		       32
+#define V2M_MAX_SPI		       1019
+
+#define V2M_MSI_TYPER_BASE_SPI(x)      \
+	       (((x) >> V2M_MSI_TYPER_BASE_SHIFT) & V2M_MSI_TYPER_BASE_MASK)
+
+#define V2M_MSI_TYPER_NUM_SPI(x)       ((x) & V2M_MSI_TYPER_NUM_MASK)
+
+struct v2m_data {
+	spinlock_t msi_cnt_lock;
+	struct msi_controller mchip;
+	struct resource res;	/* GICv2m resource */
+	void __iomem *base;	/* GICv2m virt address */
+	u32 spi_start;		/* The SPI number that MSIs start */
+	u32 nr_spis;		/* The number of SPIs for MSIs */
+	unsigned long *bm;	/* MSI vector bitmap */
+	struct irq_domain *domain;
+};
+
+static void gicv2m_mask_msi_irq(struct irq_data *d)
+{
+	pci_msi_mask_irq(d);
+	irq_chip_mask_parent(d);
+}
+
+static void gicv2m_unmask_msi_irq(struct irq_data *d)
+{
+	pci_msi_unmask_irq(d);
+	irq_chip_unmask_parent(d);
+}
+
+static struct irq_chip gicv2m_msi_irq_chip = {
+	.name			= "MSI",
+	.irq_mask		= gicv2m_mask_msi_irq,
+	.irq_unmask		= gicv2m_unmask_msi_irq,
+	.irq_eoi		= irq_chip_eoi_parent,
+	.irq_write_msi_msg	= pci_msi_domain_write_msg,
+};
+
+static struct msi_domain_info gicv2m_msi_domain_info = {
+	.flags	= (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS |
+		   MSI_FLAG_PCI_MSIX),
+	.chip	= &gicv2m_msi_irq_chip,
+};
+
+static int gicv2m_set_affinity(struct irq_data *irq_data,
+			       const struct cpumask *mask, bool force)
+{
+	int ret;
+
+	ret = irq_chip_set_affinity_parent(irq_data, mask, force);
+	if (ret == IRQ_SET_MASK_OK)
+		ret = IRQ_SET_MASK_OK_DONE;
+
+	return ret;
+}
+
+static void gicv2m_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
+{
+	struct v2m_data *v2m = irq_data_get_irq_chip_data(data);
+	phys_addr_t addr = v2m->res.start + V2M_MSI_SETSPI_NS;
+
+	msg->address_hi = (u32) (addr >> 32);
+	msg->address_lo = (u32) (addr);
+	msg->data = data->hwirq;
+}
+
+static struct irq_chip gicv2m_irq_chip = {
+	.name			= "GICv2m",
+	.irq_mask		= irq_chip_mask_parent,
+	.irq_unmask		= irq_chip_unmask_parent,
+	.irq_eoi		= irq_chip_eoi_parent,
+	.irq_set_affinity	= gicv2m_set_affinity,
+	.irq_compose_msi_msg	= gicv2m_compose_msi_msg,
+};
+
+static int gicv2m_irq_gic_domain_alloc(struct irq_domain *domain,
+				       unsigned int virq,
+				       irq_hw_number_t hwirq)
+{
+	struct of_phandle_args args;
+	struct irq_data *d;
+	int err;
+
+	args.np = domain->parent->of_node;
+	args.args_count = 3;
+	args.args[0] = 0;
+	args.args[1] = hwirq - 32;
+	args.args[2] = IRQ_TYPE_EDGE_RISING;
+
+	err = irq_domain_alloc_irqs_parent(domain, virq, 1, &args);
+	if (err)
+		return err;
+
+	/* Configure the interrupt line to be edge */
+	d = irq_domain_get_irq_data(domain->parent, virq);
+	d->chip->irq_set_type(d, IRQ_TYPE_EDGE_RISING);
+	return 0;
+}
+
+static void gicv2m_unalloc_msi(struct v2m_data *v2m, unsigned int hwirq)
+{
+	int pos;
+
+	pos = hwirq - v2m->spi_start;
+	if (pos < 0 || pos >= v2m->nr_spis) {
+		pr_err("Failed to teardown msi. Invalid hwirq %d\n", hwirq);
+		return;
+	}
+
+	spin_lock(&v2m->msi_cnt_lock);
+	__clear_bit(pos, v2m->bm);
+	spin_unlock(&v2m->msi_cnt_lock);
+}
+
+static int gicv2m_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
+				   unsigned int nr_irqs, void *args)
+{
+	struct v2m_data *v2m = domain->host_data;
+	int hwirq, offset, err = 0;
+
+	spin_lock(&v2m->msi_cnt_lock);
+	offset = find_first_zero_bit(v2m->bm, v2m->nr_spis);
+	if (offset < v2m->nr_spis)
+		__set_bit(offset, v2m->bm);
+	else
+		err = -ENOSPC;
+	spin_unlock(&v2m->msi_cnt_lock);
+
+	if (err)
+		return err;
+
+	hwirq = v2m->spi_start + offset;
+
+	err = gicv2m_irq_gic_domain_alloc(domain, virq, hwirq);
+	if (err) {
+		gicv2m_unalloc_msi(v2m, hwirq);
+		return err;
+	}
+
+	irq_domain_set_hwirq_and_chip(domain, virq, hwirq,
+				      &gicv2m_irq_chip, v2m);
+
+	return 0;
+}
+
+static void gicv2m_irq_domain_free(struct irq_domain *domain,
+				   unsigned int virq, unsigned int nr_irqs)
+{
+	struct irq_data *d = irq_domain_get_irq_data(domain, virq);
+	struct v2m_data *v2m = irq_data_get_irq_chip_data(d);
+
+	BUG_ON(nr_irqs != 1);
+	gicv2m_unalloc_msi(v2m, d->hwirq);
+	irq_domain_free_irqs_parent(domain, virq, nr_irqs);
+}
+
+static const struct irq_domain_ops gicv2m_domain_ops = {
+	.alloc			= gicv2m_irq_domain_alloc,
+	.free			= gicv2m_irq_domain_free,
+};
+
+static bool is_msi_spi_valid(u32 base, u32 num)
+{
+	if (base < V2M_MIN_SPI) {
+		pr_err("Invalid MSI base SPI (base:%u)\n", base);
+		return false;
+	}
+
+	if ((num == 0) || (base + num > V2M_MAX_SPI)) {
+		pr_err("Number of SPIs (%u) exceed maximum (%u)\n",
+		       num, V2M_MAX_SPI - V2M_MIN_SPI + 1);
+		return false;
+	}
+
+	return true;
+}
+
+static int __init gicv2m_init_one(struct device_node *node,
+				  struct irq_domain *parent)
+{
+	int ret;
+	struct v2m_data *v2m;
+
+	v2m = kzalloc(sizeof(struct v2m_data), GFP_KERNEL);
+	if (!v2m) {
+		pr_err("Failed to allocate struct v2m_data.\n");
+		return -ENOMEM;
+	}
+
+	ret = of_address_to_resource(node, 0, &v2m->res);
+	if (ret) {
+		pr_err("Failed to allocate v2m resource.\n");
+		goto err_free_v2m;
+	}
+
+	v2m->base = ioremap(v2m->res.start, resource_size(&v2m->res));
+	if (!v2m->base) {
+		pr_err("Failed to map GICv2m resource\n");
+		ret = -ENOMEM;
+		goto err_free_v2m;
+	}
+
+	if (!of_property_read_u32(node, "arm,msi-base-spi", &v2m->spi_start) &&
+	    !of_property_read_u32(node, "arm,msi-num-spis", &v2m->nr_spis)) {
+		pr_info("Overriding V2M MSI_TYPER (base:%u, num:%u)\n",
+			v2m->spi_start, v2m->nr_spis);
+	} else {
+		u32 typer = readl_relaxed(v2m->base + V2M_MSI_TYPER);
+
+		v2m->spi_start = V2M_MSI_TYPER_BASE_SPI(typer);
+		v2m->nr_spis = V2M_MSI_TYPER_NUM_SPI(typer);
+	}
+
+	if (!is_msi_spi_valid(v2m->spi_start, v2m->nr_spis)) {
+		ret = -EINVAL;
+		goto err_iounmap;
+	}
+
+	v2m->bm = kzalloc(sizeof(long) * BITS_TO_LONGS(v2m->nr_spis),
+			  GFP_KERNEL);
+	if (!v2m->bm) {
+		ret = -ENOMEM;
+		goto err_iounmap;
+	}
+
+	v2m->domain = irq_domain_add_tree(NULL, &gicv2m_domain_ops, v2m);
+	if (!v2m->domain) {
+		pr_err("Failed to create GICv2m domain\n");
+		ret = -ENOMEM;
+		goto err_free_bm;
+	}
+
+	v2m->domain->parent = parent;
+	v2m->mchip.of_node = node;
+	v2m->mchip.domain = pci_msi_create_irq_domain(node,
+						      &gicv2m_msi_domain_info,
+						      v2m->domain);
+	if (!v2m->mchip.domain) {
+		pr_err("Failed to create MSI domain\n");
+		ret = -ENOMEM;
+		goto err_free_domains;
+	}
+
+	spin_lock_init(&v2m->msi_cnt_lock);
+
+	ret = of_pci_msi_chip_add(&v2m->mchip);
+	if (ret) {
+		pr_err("Failed to add msi_chip.\n");
+		goto err_free_domains;
+	}
+
+	pr_info("Node %s: range[%#lx:%#lx], SPI[%d:%d]\n", node->name,
+		(unsigned long)v2m->res.start, (unsigned long)v2m->res.end,
+		v2m->spi_start, (v2m->spi_start + v2m->nr_spis));
+
+	return 0;
+
+err_free_domains:
+	if (v2m->mchip.domain)
+		irq_domain_remove(v2m->mchip.domain);
+	if (v2m->domain)
+		irq_domain_remove(v2m->domain);
+err_free_bm:
+	kfree(v2m->bm);
+err_iounmap:
+	iounmap(v2m->base);
+err_free_v2m:
+	kfree(v2m);
+	return ret;
+}
+
+static struct of_device_id gicv2m_device_id[] = {
+	{	.compatible	= "arm,gic-v2m-frame",	},
+	{},
+};
+
+int __init gicv2m_of_init(struct device_node *node, struct irq_domain *parent)
+{
+	int ret = 0;
+	struct device_node *child;
+
+	for (child = of_find_matching_node(node, gicv2m_device_id); child;
+	     child = of_find_matching_node(child, gicv2m_device_id)) {
+		if (!of_find_property(child, "msi-controller", NULL))
+			continue;
+
+		ret = gicv2m_init_one(child, parent);
+		if (ret) {
+			of_node_put(node);
+			break;
+		}
+	}
+
+	return ret;
+}
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
new file mode 100644
index 000000000000..86e4684adeb1
--- /dev/null
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -0,0 +1,1425 @@
+/*
+ * Copyright (C) 2013, 2014 ARM Limited, All Rights Reserved.
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * 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/bitmap.h>
+#include <linux/cpu.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/log2.h>
+#include <linux/mm.h>
+#include <linux/msi.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/of_pci.h>
+#include <linux/of_platform.h>
+#include <linux/percpu.h>
+#include <linux/slab.h>
+
+#include <linux/irqchip/arm-gic-v3.h>
+
+#include <asm/cacheflush.h>
+#include <asm/cputype.h>
+#include <asm/exception.h>
+
+#include "irqchip.h"
+
+#define ITS_FLAGS_CMDQ_NEEDS_FLUSHING		(1 << 0)
+
+#define RDIST_FLAGS_PROPBASE_NEEDS_FLUSHING	(1 << 0)
+
+/*
+ * Collection structure - just an ID, and a redistributor address to
+ * ping. We use one per CPU as a bag of interrupts assigned to this
+ * CPU.
+ */
+struct its_collection {
+	u64			target_address;
+	u16			col_id;
+};
+
+/*
+ * The ITS structure - contains most of the infrastructure, with the
+ * msi_controller, the command queue, the collections, and the list of
+ * devices writing to it.
+ */
+struct its_node {
+	raw_spinlock_t		lock;
+	struct list_head	entry;
+	struct msi_controller	msi_chip;
+	struct irq_domain	*domain;
+	void __iomem		*base;
+	unsigned long		phys_base;
+	struct its_cmd_block	*cmd_base;
+	struct its_cmd_block	*cmd_write;
+	void			*tables[GITS_BASER_NR_REGS];
+	struct its_collection	*collections;
+	struct list_head	its_device_list;
+	u64			flags;
+	u32			ite_size;
+};
+
+#define ITS_ITT_ALIGN		SZ_256
+
+/*
+ * The ITS view of a device - belongs to an ITS, a collection, owns an
+ * interrupt translation table, and a list of interrupts.
+ */
+struct its_device {
+	struct list_head	entry;
+	struct its_node		*its;
+	struct its_collection	*collection;
+	void			*itt;
+	unsigned long		*lpi_map;
+	irq_hw_number_t		lpi_base;
+	int			nr_lpis;
+	u32			nr_ites;
+	u32			device_id;
+};
+
+static LIST_HEAD(its_nodes);
+static DEFINE_SPINLOCK(its_lock);
+static struct device_node *gic_root_node;
+static struct rdists *gic_rdists;
+
+#define gic_data_rdist()		(raw_cpu_ptr(gic_rdists->rdist))
+#define gic_data_rdist_rd_base()	(gic_data_rdist()->rd_base)
+
+/*
+ * ITS command descriptors - parameters to be encoded in a command
+ * block.
+ */
+struct its_cmd_desc {
+	union {
+		struct {
+			struct its_device *dev;
+			u32 event_id;
+		} its_inv_cmd;
+
+		struct {
+			struct its_device *dev;
+			u32 event_id;
+		} its_int_cmd;
+
+		struct {
+			struct its_device *dev;
+			int valid;
+		} its_mapd_cmd;
+
+		struct {
+			struct its_collection *col;
+			int valid;
+		} its_mapc_cmd;
+
+		struct {
+			struct its_device *dev;
+			u32 phys_id;
+			u32 event_id;
+		} its_mapvi_cmd;
+
+		struct {
+			struct its_device *dev;
+			struct its_collection *col;
+			u32 id;
+		} its_movi_cmd;
+
+		struct {
+			struct its_device *dev;
+			u32 event_id;
+		} its_discard_cmd;
+
+		struct {
+			struct its_collection *col;
+		} its_invall_cmd;
+	};
+};
+
+/*
+ * The ITS command block, which is what the ITS actually parses.
+ */
+struct its_cmd_block {
+	u64	raw_cmd[4];
+};
+
+#define ITS_CMD_QUEUE_SZ		SZ_64K
+#define ITS_CMD_QUEUE_NR_ENTRIES	(ITS_CMD_QUEUE_SZ / sizeof(struct its_cmd_block))
+
+typedef struct its_collection *(*its_cmd_builder_t)(struct its_cmd_block *,
+						    struct its_cmd_desc *);
+
+static void its_encode_cmd(struct its_cmd_block *cmd, u8 cmd_nr)
+{
+	cmd->raw_cmd[0] &= ~0xffUL;
+	cmd->raw_cmd[0] |= cmd_nr;
+}
+
+static void its_encode_devid(struct its_cmd_block *cmd, u32 devid)
+{
+	cmd->raw_cmd[0] &= ~(0xffffUL << 32);
+	cmd->raw_cmd[0] |= ((u64)devid) << 32;
+}
+
+static void its_encode_event_id(struct its_cmd_block *cmd, u32 id)
+{
+	cmd->raw_cmd[1] &= ~0xffffffffUL;
+	cmd->raw_cmd[1] |= id;
+}
+
+static void its_encode_phys_id(struct its_cmd_block *cmd, u32 phys_id)
+{
+	cmd->raw_cmd[1] &= 0xffffffffUL;
+	cmd->raw_cmd[1] |= ((u64)phys_id) << 32;
+}
+
+static void its_encode_size(struct its_cmd_block *cmd, u8 size)
+{
+	cmd->raw_cmd[1] &= ~0x1fUL;
+	cmd->raw_cmd[1] |= size & 0x1f;
+}
+
+static void its_encode_itt(struct its_cmd_block *cmd, u64 itt_addr)
+{
+	cmd->raw_cmd[2] &= ~0xffffffffffffUL;
+	cmd->raw_cmd[2] |= itt_addr & 0xffffffffff00UL;
+}
+
+static void its_encode_valid(struct its_cmd_block *cmd, int valid)
+{
+	cmd->raw_cmd[2] &= ~(1UL << 63);
+	cmd->raw_cmd[2] |= ((u64)!!valid) << 63;
+}
+
+static void its_encode_target(struct its_cmd_block *cmd, u64 target_addr)
+{
+	cmd->raw_cmd[2] &= ~(0xffffffffUL << 16);
+	cmd->raw_cmd[2] |= (target_addr & (0xffffffffUL << 16));
+}
+
+static void its_encode_collection(struct its_cmd_block *cmd, u16 col)
+{
+	cmd->raw_cmd[2] &= ~0xffffUL;
+	cmd->raw_cmd[2] |= col;
+}
+
+static inline void its_fixup_cmd(struct its_cmd_block *cmd)
+{
+	/* Let's fixup BE commands */
+	cmd->raw_cmd[0] = cpu_to_le64(cmd->raw_cmd[0]);
+	cmd->raw_cmd[1] = cpu_to_le64(cmd->raw_cmd[1]);
+	cmd->raw_cmd[2] = cpu_to_le64(cmd->raw_cmd[2]);
+	cmd->raw_cmd[3] = cpu_to_le64(cmd->raw_cmd[3]);
+}
+
+static struct its_collection *its_build_mapd_cmd(struct its_cmd_block *cmd,
+						 struct its_cmd_desc *desc)
+{
+	unsigned long itt_addr;
+	u8 size = ilog2(desc->its_mapd_cmd.dev->nr_ites);
+
+	itt_addr = virt_to_phys(desc->its_mapd_cmd.dev->itt);
+	itt_addr = ALIGN(itt_addr, ITS_ITT_ALIGN);
+
+	its_encode_cmd(cmd, GITS_CMD_MAPD);
+	its_encode_devid(cmd, desc->its_mapd_cmd.dev->device_id);
+	its_encode_size(cmd, size - 1);
+	its_encode_itt(cmd, itt_addr);
+	its_encode_valid(cmd, desc->its_mapd_cmd.valid);
+
+	its_fixup_cmd(cmd);
+
+	return desc->its_mapd_cmd.dev->collection;
+}
+
+static struct its_collection *its_build_mapc_cmd(struct its_cmd_block *cmd,
+						 struct its_cmd_desc *desc)
+{
+	its_encode_cmd(cmd, GITS_CMD_MAPC);
+	its_encode_collection(cmd, desc->its_mapc_cmd.col->col_id);
+	its_encode_target(cmd, desc->its_mapc_cmd.col->target_address);
+	its_encode_valid(cmd, desc->its_mapc_cmd.valid);
+
+	its_fixup_cmd(cmd);
+
+	return desc->its_mapc_cmd.col;
+}
+
+static struct its_collection *its_build_mapvi_cmd(struct its_cmd_block *cmd,
+						  struct its_cmd_desc *desc)
+{
+	its_encode_cmd(cmd, GITS_CMD_MAPVI);
+	its_encode_devid(cmd, desc->its_mapvi_cmd.dev->device_id);
+	its_encode_event_id(cmd, desc->its_mapvi_cmd.event_id);
+	its_encode_phys_id(cmd, desc->its_mapvi_cmd.phys_id);
+	its_encode_collection(cmd, desc->its_mapvi_cmd.dev->collection->col_id);
+
+	its_fixup_cmd(cmd);
+
+	return desc->its_mapvi_cmd.dev->collection;
+}
+
+static struct its_collection *its_build_movi_cmd(struct its_cmd_block *cmd,
+						 struct its_cmd_desc *desc)
+{
+	its_encode_cmd(cmd, GITS_CMD_MOVI);
+	its_encode_devid(cmd, desc->its_movi_cmd.dev->device_id);
+	its_encode_event_id(cmd, desc->its_movi_cmd.id);
+	its_encode_collection(cmd, desc->its_movi_cmd.col->col_id);
+
+	its_fixup_cmd(cmd);
+
+	return desc->its_movi_cmd.dev->collection;
+}
+
+static struct its_collection *its_build_discard_cmd(struct its_cmd_block *cmd,
+						    struct its_cmd_desc *desc)
+{
+	its_encode_cmd(cmd, GITS_CMD_DISCARD);
+	its_encode_devid(cmd, desc->its_discard_cmd.dev->device_id);
+	its_encode_event_id(cmd, desc->its_discard_cmd.event_id);
+
+	its_fixup_cmd(cmd);
+
+	return desc->its_discard_cmd.dev->collection;
+}
+
+static struct its_collection *its_build_inv_cmd(struct its_cmd_block *cmd,
+						struct its_cmd_desc *desc)
+{
+	its_encode_cmd(cmd, GITS_CMD_INV);
+	its_encode_devid(cmd, desc->its_inv_cmd.dev->device_id);
+	its_encode_event_id(cmd, desc->its_inv_cmd.event_id);
+
+	its_fixup_cmd(cmd);
+
+	return desc->its_inv_cmd.dev->collection;
+}
+
+static struct its_collection *its_build_invall_cmd(struct its_cmd_block *cmd,
+						   struct its_cmd_desc *desc)
+{
+	its_encode_cmd(cmd, GITS_CMD_INVALL);
+	its_encode_collection(cmd, desc->its_mapc_cmd.col->col_id);
+
+	its_fixup_cmd(cmd);
+
+	return NULL;
+}
+
+static u64 its_cmd_ptr_to_offset(struct its_node *its,
+				 struct its_cmd_block *ptr)
+{
+	return (ptr - its->cmd_base) * sizeof(*ptr);
+}
+
+static int its_queue_full(struct its_node *its)
+{
+	int widx;
+	int ridx;
+
+	widx = its->cmd_write - its->cmd_base;
+	ridx = readl_relaxed(its->base + GITS_CREADR) / sizeof(struct its_cmd_block);
+
+	/* This is incredibly unlikely to happen, unless the ITS locks up. */
+	if (((widx + 1) % ITS_CMD_QUEUE_NR_ENTRIES) == ridx)
+		return 1;
+
+	return 0;
+}
+
+static struct its_cmd_block *its_allocate_entry(struct its_node *its)
+{
+	struct its_cmd_block *cmd;
+	u32 count = 1000000;	/* 1s! */
+
+	while (its_queue_full(its)) {
+		count--;
+		if (!count) {
+			pr_err_ratelimited("ITS queue not draining\n");
+			return NULL;
+		}
+		cpu_relax();
+		udelay(1);
+	}
+
+	cmd = its->cmd_write++;
+
+	/* Handle queue wrapping */
+	if (its->cmd_write == (its->cmd_base + ITS_CMD_QUEUE_NR_ENTRIES))
+		its->cmd_write = its->cmd_base;
+
+	return cmd;
+}
+
+static struct its_cmd_block *its_post_commands(struct its_node *its)
+{
+	u64 wr = its_cmd_ptr_to_offset(its, its->cmd_write);
+
+	writel_relaxed(wr, its->base + GITS_CWRITER);
+
+	return its->cmd_write;
+}
+
+static void its_flush_cmd(struct its_node *its, struct its_cmd_block *cmd)
+{
+	/*
+	 * Make sure the commands written to memory are observable by
+	 * the ITS.
+	 */
+	if (its->flags & ITS_FLAGS_CMDQ_NEEDS_FLUSHING)
+		__flush_dcache_area(cmd, sizeof(*cmd));
+	else
+		dsb(ishst);
+}
+
+static void its_wait_for_range_completion(struct its_node *its,
+					  struct its_cmd_block *from,
+					  struct its_cmd_block *to)
+{
+	u64 rd_idx, from_idx, to_idx;
+	u32 count = 1000000;	/* 1s! */
+
+	from_idx = its_cmd_ptr_to_offset(its, from);
+	to_idx = its_cmd_ptr_to_offset(its, to);
+
+	while (1) {
+		rd_idx = readl_relaxed(its->base + GITS_CREADR);
+		if (rd_idx >= to_idx || rd_idx < from_idx)
+			break;
+
+		count--;
+		if (!count) {
+			pr_err_ratelimited("ITS queue timeout\n");
+			return;
+		}
+		cpu_relax();
+		udelay(1);
+	}
+}
+
+static void its_send_single_command(struct its_node *its,
+				    its_cmd_builder_t builder,
+				    struct its_cmd_desc *desc)
+{
+	struct its_cmd_block *cmd, *sync_cmd, *next_cmd;
+	struct its_collection *sync_col;
+
+	raw_spin_lock(&its->lock);
+
+	cmd = its_allocate_entry(its);
+	if (!cmd) {		/* We're soooooo screewed... */
+		pr_err_ratelimited("ITS can't allocate, dropping command\n");
+		raw_spin_unlock(&its->lock);
+		return;
+	}
+	sync_col = builder(cmd, desc);
+	its_flush_cmd(its, cmd);
+
+	if (sync_col) {
+		sync_cmd = its_allocate_entry(its);
+		if (!sync_cmd) {
+			pr_err_ratelimited("ITS can't SYNC, skipping\n");
+			goto post;
+		}
+		its_encode_cmd(sync_cmd, GITS_CMD_SYNC);
+		its_encode_target(sync_cmd, sync_col->target_address);
+		its_fixup_cmd(sync_cmd);
+		its_flush_cmd(its, sync_cmd);
+	}
+
+post:
+	next_cmd = its_post_commands(its);
+	raw_spin_unlock(&its->lock);
+
+	its_wait_for_range_completion(its, cmd, next_cmd);
+}
+
+static void its_send_inv(struct its_device *dev, u32 event_id)
+{
+	struct its_cmd_desc desc;
+
+	desc.its_inv_cmd.dev = dev;
+	desc.its_inv_cmd.event_id = event_id;
+
+	its_send_single_command(dev->its, its_build_inv_cmd, &desc);
+}
+
+static void its_send_mapd(struct its_device *dev, int valid)
+{
+	struct its_cmd_desc desc;
+
+	desc.its_mapd_cmd.dev = dev;
+	desc.its_mapd_cmd.valid = !!valid;
+
+	its_send_single_command(dev->its, its_build_mapd_cmd, &desc);
+}
+
+static void its_send_mapc(struct its_node *its, struct its_collection *col,
+			  int valid)
+{
+	struct its_cmd_desc desc;
+
+	desc.its_mapc_cmd.col = col;
+	desc.its_mapc_cmd.valid = !!valid;
+
+	its_send_single_command(its, its_build_mapc_cmd, &desc);
+}
+
+static void its_send_mapvi(struct its_device *dev, u32 irq_id, u32 id)
+{
+	struct its_cmd_desc desc;
+
+	desc.its_mapvi_cmd.dev = dev;
+	desc.its_mapvi_cmd.phys_id = irq_id;
+	desc.its_mapvi_cmd.event_id = id;
+
+	its_send_single_command(dev->its, its_build_mapvi_cmd, &desc);
+}
+
+static void its_send_movi(struct its_device *dev,
+			  struct its_collection *col, u32 id)
+{
+	struct its_cmd_desc desc;
+
+	desc.its_movi_cmd.dev = dev;
+	desc.its_movi_cmd.col = col;
+	desc.its_movi_cmd.id = id;
+
+	its_send_single_command(dev->its, its_build_movi_cmd, &desc);
+}
+
+static void its_send_discard(struct its_device *dev, u32 id)
+{
+	struct its_cmd_desc desc;
+
+	desc.its_discard_cmd.dev = dev;
+	desc.its_discard_cmd.event_id = id;
+
+	its_send_single_command(dev->its, its_build_discard_cmd, &desc);
+}
+
+static void its_send_invall(struct its_node *its, struct its_collection *col)
+{
+	struct its_cmd_desc desc;
+
+	desc.its_invall_cmd.col = col;
+
+	its_send_single_command(its, its_build_invall_cmd, &desc);
+}
+
+/*
+ * irqchip functions - assumes MSI, mostly.
+ */
+
+static inline u32 its_get_event_id(struct irq_data *d)
+{
+	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
+	return d->hwirq - its_dev->lpi_base;
+}
+
+static void lpi_set_config(struct irq_data *d, bool enable)
+{
+	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
+	irq_hw_number_t hwirq = d->hwirq;
+	u32 id = its_get_event_id(d);
+	u8 *cfg = page_address(gic_rdists->prop_page) + hwirq - 8192;
+
+	if (enable)
+		*cfg |= LPI_PROP_ENABLED;
+	else
+		*cfg &= ~LPI_PROP_ENABLED;
+
+	/*
+	 * Make the above write visible to the redistributors.
+	 * And yes, we're flushing exactly: One. Single. Byte.
+	 * Humpf...
+	 */
+	if (gic_rdists->flags & RDIST_FLAGS_PROPBASE_NEEDS_FLUSHING)
+		__flush_dcache_area(cfg, sizeof(*cfg));
+	else
+		dsb(ishst);
+	its_send_inv(its_dev, id);
+}
+
+static void its_mask_irq(struct irq_data *d)
+{
+	lpi_set_config(d, false);
+}
+
+static void its_unmask_irq(struct irq_data *d)
+{
+	lpi_set_config(d, true);
+}
+
+static void its_eoi_irq(struct irq_data *d)
+{
+	gic_write_eoir(d->hwirq);
+}
+
+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);
+	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
+	struct its_collection *target_col;
+	u32 id = its_get_event_id(d);
+
+	if (cpu >= nr_cpu_ids)
+		return -EINVAL;
+
+	target_col = &its_dev->its->collections[cpu];
+	its_send_movi(its_dev, target_col, id);
+	its_dev->collection = target_col;
+
+	return IRQ_SET_MASK_OK_DONE;
+}
+
+static void its_irq_compose_msi_msg(struct irq_data *d, struct msi_msg *msg)
+{
+	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
+	struct its_node *its;
+	u64 addr;
+
+	its = its_dev->its;
+	addr = its->phys_base + GITS_TRANSLATER;
+
+	msg->address_lo		= addr & ((1UL << 32) - 1);
+	msg->address_hi		= addr >> 32;
+	msg->data		= its_get_event_id(d);
+}
+
+static struct irq_chip its_irq_chip = {
+	.name			= "ITS",
+	.irq_mask		= its_mask_irq,
+	.irq_unmask		= its_unmask_irq,
+	.irq_eoi		= its_eoi_irq,
+	.irq_set_affinity	= its_set_affinity,
+	.irq_compose_msi_msg	= its_irq_compose_msi_msg,
+};
+
+static void its_mask_msi_irq(struct irq_data *d)
+{
+	pci_msi_mask_irq(d);
+	irq_chip_mask_parent(d);
+}
+
+static void its_unmask_msi_irq(struct irq_data *d)
+{
+	pci_msi_unmask_irq(d);
+	irq_chip_unmask_parent(d);
+}
+
+static struct irq_chip its_msi_irq_chip = {
+	.name			= "ITS-MSI",
+	.irq_unmask		= its_unmask_msi_irq,
+	.irq_mask		= its_mask_msi_irq,
+	.irq_eoi		= irq_chip_eoi_parent,
+	.irq_write_msi_msg	= pci_msi_domain_write_msg,
+};
+
+/*
+ * How we allocate LPIs:
+ *
+ * The GIC has id_bits bits for interrupt identifiers. From there, we
+ * must subtract 8192 which are reserved for SGIs/PPIs/SPIs. Then, as
+ * we allocate LPIs by chunks of 32, we can shift the whole thing by 5
+ * bits to the right.
+ *
+ * This gives us (((1UL << id_bits) - 8192) >> 5) possible allocations.
+ */
+#define IRQS_PER_CHUNK_SHIFT	5
+#define IRQS_PER_CHUNK		(1 << IRQS_PER_CHUNK_SHIFT)
+
+static unsigned long *lpi_bitmap;
+static u32 lpi_chunks;
+static DEFINE_SPINLOCK(lpi_lock);
+
+static int its_lpi_to_chunk(int lpi)
+{
+	return (lpi - 8192) >> IRQS_PER_CHUNK_SHIFT;
+}
+
+static int its_chunk_to_lpi(int chunk)
+{
+	return (chunk << IRQS_PER_CHUNK_SHIFT) + 8192;
+}
+
+static int its_lpi_init(u32 id_bits)
+{
+	lpi_chunks = its_lpi_to_chunk(1UL << id_bits);
+
+	lpi_bitmap = kzalloc(BITS_TO_LONGS(lpi_chunks) * sizeof(long),
+			     GFP_KERNEL);
+	if (!lpi_bitmap) {
+		lpi_chunks = 0;
+		return -ENOMEM;
+	}
+
+	pr_info("ITS: Allocated %d chunks for LPIs\n", (int)lpi_chunks);
+	return 0;
+}
+
+static unsigned long *its_lpi_alloc_chunks(int nr_irqs, int *base, int *nr_ids)
+{
+	unsigned long *bitmap = NULL;
+	int chunk_id;
+	int nr_chunks;
+	int i;
+
+	nr_chunks = DIV_ROUND_UP(nr_irqs, IRQS_PER_CHUNK);
+
+	spin_lock(&lpi_lock);
+
+	do {
+		chunk_id = bitmap_find_next_zero_area(lpi_bitmap, lpi_chunks,
+						      0, nr_chunks, 0);
+		if (chunk_id < lpi_chunks)
+			break;
+
+		nr_chunks--;
+	} while (nr_chunks > 0);
+
+	if (!nr_chunks)
+		goto out;
+
+	bitmap = kzalloc(BITS_TO_LONGS(nr_chunks * IRQS_PER_CHUNK) * sizeof (long),
+			 GFP_ATOMIC);
+	if (!bitmap)
+		goto out;
+
+	for (i = 0; i < nr_chunks; i++)
+		set_bit(chunk_id + i, lpi_bitmap);
+
+	*base = its_chunk_to_lpi(chunk_id);
+	*nr_ids = nr_chunks * IRQS_PER_CHUNK;
+
+out:
+	spin_unlock(&lpi_lock);
+
+	return bitmap;
+}
+
+static void its_lpi_free(unsigned long *bitmap, int base, int nr_ids)
+{
+	int lpi;
+
+	spin_lock(&lpi_lock);
+
+	for (lpi = base; lpi < (base + nr_ids); lpi += IRQS_PER_CHUNK) {
+		int chunk = its_lpi_to_chunk(lpi);
+		BUG_ON(chunk > lpi_chunks);