linux_dsm_epyc7002/drivers/iommu/arm-smmu.c

/*
 * IOMMU API for ARM architected SMMU implementations.
 *
 * 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, write to the Free Software
 * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
 *
 * Copyright (C) 2013 ARM Limited
 *
 * Author: Will Deacon <will.deacon@arm.com>
 *
 * This driver currently supports:
 *	- SMMUv1 and v2 implementations
 *	- Stream-matching and stream-indexing
 *	- v7/v8 long-descriptor format
 *	- Non-secure access to the SMMU
 *	- Context fault reporting
 */

#define pr_fmt(fmt) "arm-smmu: " fmt

#include <linux/delay.h>
#include <linux/dma-mapping.h>
#include <linux/err.h>
#include <linux/interrupt.h>
#include <linux/io.h>
#include <linux/iommu.h>
#include <linux/iopoll.h>
#include <linux/module.h>
#include <linux/of.h>
#include <linux/pci.h>
#include <linux/platform_device.h>
#include <linux/slab.h>
#include <linux/spinlock.h>

#include <linux/amba/bus.h>

#include "io-pgtable.h"

/* Maximum number of stream IDs assigned to a single device */
#define MAX_MASTER_STREAMIDS		MAX_PHANDLE_ARGS

/* Maximum number of context banks per SMMU */
#define ARM_SMMU_MAX_CBS		128

/* Maximum number of mapping groups per SMMU */
#define ARM_SMMU_MAX_SMRS		128

/* SMMU global address space */
#define ARM_SMMU_GR0(smmu)		((smmu)->base)
#define ARM_SMMU_GR1(smmu)		((smmu)->base + (1 << (smmu)->pgshift))

/*
 * SMMU global address space with conditional offset to access secure
 * aliases of non-secure registers (e.g. nsCR0: 0x400, nsGFSR: 0x448,
 * nsGFSYNR0: 0x450)
 */
#define ARM_SMMU_GR0_NS(smmu)						\
	((smmu)->base +							\
		((smmu->options & ARM_SMMU_OPT_SECURE_CFG_ACCESS)	\
			? 0x400 : 0))

/* Configuration registers */
#define ARM_SMMU_GR0_sCR0		0x0
#define sCR0_CLIENTPD			(1 << 0)
#define sCR0_GFRE			(1 << 1)
#define sCR0_GFIE			(1 << 2)
#define sCR0_GCFGFRE			(1 << 4)
#define sCR0_GCFGFIE			(1 << 5)
#define sCR0_USFCFG			(1 << 10)
#define sCR0_VMIDPNE			(1 << 11)
#define sCR0_PTM			(1 << 12)
#define sCR0_FB				(1 << 13)
#define sCR0_BSU_SHIFT			14
#define sCR0_BSU_MASK			0x3

/* Identification registers */
#define ARM_SMMU_GR0_ID0		0x20
#define ARM_SMMU_GR0_ID1		0x24
#define ARM_SMMU_GR0_ID2		0x28
#define ARM_SMMU_GR0_ID3		0x2c
#define ARM_SMMU_GR0_ID4		0x30
#define ARM_SMMU_GR0_ID5		0x34
#define ARM_SMMU_GR0_ID6		0x38
#define ARM_SMMU_GR0_ID7		0x3c
#define ARM_SMMU_GR0_sGFSR		0x48
#define ARM_SMMU_GR0_sGFSYNR0		0x50
#define ARM_SMMU_GR0_sGFSYNR1		0x54
#define ARM_SMMU_GR0_sGFSYNR2		0x58

#define ID0_S1TS			(1 << 30)
#define ID0_S2TS			(1 << 29)
#define ID0_NTS				(1 << 28)
#define ID0_SMS				(1 << 27)
#define ID0_ATOSNS			(1 << 26)
#define ID0_CTTW			(1 << 14)
#define ID0_NUMIRPT_SHIFT		16
#define ID0_NUMIRPT_MASK		0xff
#define ID0_NUMSIDB_SHIFT		9
#define ID0_NUMSIDB_MASK		0xf
#define ID0_NUMSMRG_SHIFT		0
#define ID0_NUMSMRG_MASK		0xff

#define ID1_PAGESIZE			(1 << 31)
#define ID1_NUMPAGENDXB_SHIFT		28
#define ID1_NUMPAGENDXB_MASK		7
#define ID1_NUMS2CB_SHIFT		16
#define ID1_NUMS2CB_MASK		0xff
#define ID1_NUMCB_SHIFT			0
#define ID1_NUMCB_MASK			0xff

#define ID2_OAS_SHIFT			4
#define ID2_OAS_MASK			0xf
#define ID2_IAS_SHIFT			0
#define ID2_IAS_MASK			0xf
#define ID2_UBS_SHIFT			8
#define ID2_UBS_MASK			0xf
#define ID2_PTFS_4K			(1 << 12)
#define ID2_PTFS_16K			(1 << 13)
#define ID2_PTFS_64K			(1 << 14)

/* Global TLB invalidation */
#define ARM_SMMU_GR0_TLBIVMID		0x64
#define ARM_SMMU_GR0_TLBIALLNSNH	0x68
#define ARM_SMMU_GR0_TLBIALLH		0x6c
#define ARM_SMMU_GR0_sTLBGSYNC		0x70
#define ARM_SMMU_GR0_sTLBGSTATUS	0x74
#define sTLBGSTATUS_GSACTIVE		(1 << 0)
#define TLB_LOOP_TIMEOUT		1000000	/* 1s! */

/* Stream mapping registers */
#define ARM_SMMU_GR0_SMR(n)		(0x800 + ((n) << 2))
#define SMR_VALID			(1 << 31)
#define SMR_MASK_SHIFT			16
#define SMR_MASK_MASK			0x7fff
#define SMR_ID_SHIFT			0
#define SMR_ID_MASK			0x7fff

#define ARM_SMMU_GR0_S2CR(n)		(0xc00 + ((n) << 2))
#define S2CR_CBNDX_SHIFT		0
#define S2CR_CBNDX_MASK			0xff
#define S2CR_TYPE_SHIFT			16
#define S2CR_TYPE_MASK			0x3
#define S2CR_TYPE_TRANS			(0 << S2CR_TYPE_SHIFT)
#define S2CR_TYPE_BYPASS		(1 << S2CR_TYPE_SHIFT)
#define S2CR_TYPE_FAULT			(2 << S2CR_TYPE_SHIFT)

/* Context bank attribute registers */
#define ARM_SMMU_GR1_CBAR(n)		(0x0 + ((n) << 2))
#define CBAR_VMID_SHIFT			0
#define CBAR_VMID_MASK			0xff
#define CBAR_S1_BPSHCFG_SHIFT		8
#define CBAR_S1_BPSHCFG_MASK		3
#define CBAR_S1_BPSHCFG_NSH		3
#define CBAR_S1_MEMATTR_SHIFT		12
#define CBAR_S1_MEMATTR_MASK		0xf
#define CBAR_S1_MEMATTR_WB		0xf
#define CBAR_TYPE_SHIFT			16
#define CBAR_TYPE_MASK			0x3
#define CBAR_TYPE_S2_TRANS		(0 << CBAR_TYPE_SHIFT)
#define CBAR_TYPE_S1_TRANS_S2_BYPASS	(1 << CBAR_TYPE_SHIFT)
#define CBAR_TYPE_S1_TRANS_S2_FAULT	(2 << CBAR_TYPE_SHIFT)
#define CBAR_TYPE_S1_TRANS_S2_TRANS	(3 << CBAR_TYPE_SHIFT)
#define CBAR_IRPTNDX_SHIFT		24
#define CBAR_IRPTNDX_MASK		0xff

#define ARM_SMMU_GR1_CBA2R(n)		(0x800 + ((n) << 2))
#define CBA2R_RW64_32BIT		(0 << 0)
#define CBA2R_RW64_64BIT		(1 << 0)

/* Translation context bank */
#define ARM_SMMU_CB_BASE(smmu)		((smmu)->base + ((smmu)->size >> 1))
#define ARM_SMMU_CB(smmu, n)		((n) * (1 << (smmu)->pgshift))

#define ARM_SMMU_CB_SCTLR		0x0
#define ARM_SMMU_CB_RESUME		0x8
#define ARM_SMMU_CB_TTBCR2		0x10
#define ARM_SMMU_CB_TTBR0_LO		0x20
#define ARM_SMMU_CB_TTBR0_HI		0x24
#define ARM_SMMU_CB_TTBR1_LO		0x28
#define ARM_SMMU_CB_TTBR1_HI		0x2c
#define ARM_SMMU_CB_TTBCR		0x30
#define ARM_SMMU_CB_S1_MAIR0		0x38
#define ARM_SMMU_CB_S1_MAIR1		0x3c
#define ARM_SMMU_CB_PAR_LO		0x50
#define ARM_SMMU_CB_PAR_HI		0x54
#define ARM_SMMU_CB_FSR			0x58
#define ARM_SMMU_CB_FAR_LO		0x60
#define ARM_SMMU_CB_FAR_HI		0x64
#define ARM_SMMU_CB_FSYNR0		0x68
#define ARM_SMMU_CB_S1_TLBIVA		0x600
#define ARM_SMMU_CB_S1_TLBIASID		0x610
#define ARM_SMMU_CB_S1_TLBIVAL		0x620
#define ARM_SMMU_CB_S2_TLBIIPAS2	0x630
#define ARM_SMMU_CB_S2_TLBIIPAS2L	0x638
#define ARM_SMMU_CB_ATS1PR		0x800
#define ARM_SMMU_CB_ATSR		0x8f0

#define SCTLR_S1_ASIDPNE		(1 << 12)
#define SCTLR_CFCFG			(1 << 7)
#define SCTLR_CFIE			(1 << 6)
#define SCTLR_CFRE			(1 << 5)
#define SCTLR_E				(1 << 4)
#define SCTLR_AFE			(1 << 2)
#define SCTLR_TRE			(1 << 1)
#define SCTLR_M				(1 << 0)
#define SCTLR_EAE_SBOP			(SCTLR_AFE | SCTLR_TRE)

#define CB_PAR_F			(1 << 0)

#define ATSR_ACTIVE			(1 << 0)

#define RESUME_RETRY			(0 << 0)
#define RESUME_TERMINATE		(1 << 0)

#define TTBCR2_SEP_SHIFT		15
#define TTBCR2_SEP_UPSTREAM		(0x7 << TTBCR2_SEP_SHIFT)

#define TTBRn_HI_ASID_SHIFT            16

#define FSR_MULTI			(1 << 31)
#define FSR_SS				(1 << 30)
#define FSR_UUT				(1 << 8)
#define FSR_ASF				(1 << 7)
#define FSR_TLBLKF			(1 << 6)
#define FSR_TLBMCF			(1 << 5)
#define FSR_EF				(1 << 4)
#define FSR_PF				(1 << 3)
#define FSR_AFF				(1 << 2)
#define FSR_TF				(1 << 1)

#define FSR_IGN				(FSR_AFF | FSR_ASF | \
					 FSR_TLBMCF | FSR_TLBLKF)
#define FSR_FAULT			(FSR_MULTI | FSR_SS | FSR_UUT | \
					 FSR_EF | FSR_PF | FSR_TF | FSR_IGN)

#define FSYNR0_WNR			(1 << 4)

static int force_stage;
module_param_named(force_stage, force_stage, int, S_IRUGO);
MODULE_PARM_DESC(force_stage,
	"Force SMMU mappings to be installed at a particular stage of translation. A value of '1' or '2' forces the corresponding stage. All other values are ignored (i.e. no stage is forced). Note that selecting a specific stage will disable support for nested translation.");

enum arm_smmu_arch_version {
	ARM_SMMU_V1 = 1,
	ARM_SMMU_V2,
};

struct arm_smmu_smr {
	u8				idx;
	u16				mask;
	u16				id;
};

struct arm_smmu_master_cfg {
	int				num_streamids;
	u16				streamids[MAX_MASTER_STREAMIDS];
	struct arm_smmu_smr		*smrs;
};

struct arm_smmu_master {
	struct device_node		*of_node;
	struct rb_node			node;
	struct arm_smmu_master_cfg	cfg;
};

struct arm_smmu_device {
	struct device			*dev;

	void __iomem			*base;
	unsigned long			size;
	unsigned long			pgshift;

#define ARM_SMMU_FEAT_COHERENT_WALK	(1 << 0)
#define ARM_SMMU_FEAT_STREAM_MATCH	(1 << 1)
#define ARM_SMMU_FEAT_TRANS_S1		(1 << 2)
#define ARM_SMMU_FEAT_TRANS_S2		(1 << 3)
#define ARM_SMMU_FEAT_TRANS_NESTED	(1 << 4)
#define ARM_SMMU_FEAT_TRANS_OPS		(1 << 5)
	u32				features;

#define ARM_SMMU_OPT_SECURE_CFG_ACCESS (1 << 0)
	u32				options;
	enum arm_smmu_arch_version	version;

	u32				num_context_banks;
	u32				num_s2_context_banks;
	DECLARE_BITMAP(context_map, ARM_SMMU_MAX_CBS);
	atomic_t			irptndx;

	u32				num_mapping_groups;
	DECLARE_BITMAP(smr_map, ARM_SMMU_MAX_SMRS);

	unsigned long			va_size;
	unsigned long			ipa_size;
	unsigned long			pa_size;

	u32				num_global_irqs;
	u32				num_context_irqs;
	unsigned int			*irqs;

	struct list_head		list;
	struct rb_root			masters;
};

struct arm_smmu_cfg {
	u8				cbndx;
	u8				irptndx;
	u32				cbar;
};
#define INVALID_IRPTNDX			0xff

#define ARM_SMMU_CB_ASID(cfg)		((cfg)->cbndx)
#define ARM_SMMU_CB_VMID(cfg)		((cfg)->cbndx + 1)

enum arm_smmu_domain_stage {
	ARM_SMMU_DOMAIN_S1 = 0,
	ARM_SMMU_DOMAIN_S2,
	ARM_SMMU_DOMAIN_NESTED,
};

struct arm_smmu_domain {
	struct arm_smmu_device		*smmu;
	struct io_pgtable_ops		*pgtbl_ops;
	spinlock_t			pgtbl_lock;
	struct arm_smmu_cfg		cfg;
	enum arm_smmu_domain_stage	stage;
	struct mutex			init_mutex; /* Protects smmu pointer */
	struct iommu_domain		domain;
};

static struct iommu_ops arm_smmu_ops;

static DEFINE_SPINLOCK(arm_smmu_devices_lock);
static LIST_HEAD(arm_smmu_devices);

struct arm_smmu_option_prop {
	u32 opt;
	const char *prop;
};

static struct arm_smmu_option_prop arm_smmu_options[] = {
	{ ARM_SMMU_OPT_SECURE_CFG_ACCESS, "calxeda,smmu-secure-config-access" },
	{ 0, NULL},
};

static struct arm_smmu_domain *to_smmu_domain(struct iommu_domain *dom)
{
	return container_of(dom, struct arm_smmu_domain, domain);
}

static void parse_driver_options(struct arm_smmu_device *smmu)
{
	int i = 0;

	do {
		if (of_property_read_bool(smmu->dev->of_node,
						arm_smmu_options[i].prop)) {
			smmu->options |= arm_smmu_options[i].opt;
			dev_notice(smmu->dev, "option %s\n",
				arm_smmu_options[i].prop);
		}
	} while (arm_smmu_options[++i].opt);
}

static struct device_node *dev_get_dev_node(struct device *dev)
{
	if (dev_is_pci(dev)) {
		struct pci_bus *bus = to_pci_dev(dev)->bus;

		while (!pci_is_root_bus(bus))
			bus = bus->parent;
		return bus->bridge->parent->of_node;
	}

	return dev->of_node;
}

static struct arm_smmu_master *find_smmu_master(struct arm_smmu_device *smmu,
						struct device_node *dev_node)
{
	struct rb_node *node = smmu->masters.rb_node;

	while (node) {
		struct arm_smmu_master *master;

		master = container_of(node, struct arm_smmu_master, node);

		if (dev_node < master->of_node)
			node = node->rb_left;
		else if (dev_node > master->of_node)
			node = node->rb_right;
		else
			return master;
	}

	return NULL;
}

static struct arm_smmu_master_cfg *
find_smmu_master_cfg(struct device *dev)
{
	struct arm_smmu_master_cfg *cfg = NULL;
	struct iommu_group *group = iommu_group_get(dev);

	if (group) {
		cfg = iommu_group_get_iommudata(group);
		iommu_group_put(group);
	}

	return cfg;
}

static int insert_smmu_master(struct arm_smmu_device *smmu,
			      struct arm_smmu_master *master)
{
	struct rb_node **new, *parent;

	new = &smmu->masters.rb_node;
	parent = NULL;
	while (*new) {
		struct arm_smmu_master *this
			= container_of(*new, struct arm_smmu_master, node);

		parent = *new;
		if (master->of_node < this->of_node)
			new = &((*new)->rb_left);
		else if (master->of_node > this->of_node)
			new = &((*new)->rb_right);
		else
			return -EEXIST;
	}

	rb_link_node(&master->node, parent, new);
	rb_insert_color(&master->node, &smmu->masters);
	return 0;
}

static int register_smmu_master(struct arm_smmu_device *smmu,
				struct device *dev,
				struct of_phandle_args *masterspec)
{
	int i;
	struct arm_smmu_master *master;

	master = find_smmu_master(smmu, masterspec->np);
	if (master) {
		dev_err(dev,
			"rejecting multiple registrations for master device %s\n",
			masterspec->np->name);
		return -EBUSY;
	}

	if (masterspec->args_count > MAX_MASTER_STREAMIDS) {
		dev_err(dev,
			"reached maximum number (%d) of stream IDs for master device %s\n",
			MAX_MASTER_STREAMIDS, masterspec->np->name);
		return -ENOSPC;
	}

	master = devm_kzalloc(dev, sizeof(*master), GFP_KERNEL);
	if (!master)
		return -ENOMEM;

	master->of_node			= masterspec->np;
	master->cfg.num_streamids	= masterspec->args_count;

	for (i = 0; i < master->cfg.num_streamids; ++i) {
		u16 streamid = masterspec->args[i];

		if (!(smmu->features & ARM_SMMU_FEAT_STREAM_MATCH) &&
		     (streamid >= smmu->num_mapping_groups)) {
			dev_err(dev,
				"stream ID for master device %s greater than maximum allowed (%d)\n",
				masterspec->np->name, smmu->num_mapping_groups);
			return -ERANGE;
		}
		master->cfg.streamids[i] = streamid;
	}
	return insert_smmu_master(smmu, master);
}

static struct arm_smmu_device *find_smmu_for_device(struct device *dev)
{
	struct arm_smmu_device *smmu;
	struct arm_smmu_master *master = NULL;
	struct device_node *dev_node = dev_get_dev_node(dev);

	spin_lock(&arm_smmu_devices_lock);
	list_for_each_entry(smmu, &arm_smmu_devices, list) {
		master = find_smmu_master(smmu, dev_node);
		if (master)
			break;
	}
	spin_unlock(&arm_smmu_devices_lock);

	return master ? smmu : NULL;
}

static int __arm_smmu_alloc_bitmap(unsigned long *map, int start, int end)
{
	int idx;

	do {
		idx = find_next_zero_bit(map, end, start);
		if (idx == end)
			return -ENOSPC;
	} while (test_and_set_bit(idx, map));

	return idx;
}

static void __arm_smmu_free_bitmap(unsigned long *map, int idx)
{
	clear_bit(idx, map);
}

/* Wait for any pending TLB invalidations to complete */
static void __arm_smmu_tlb_sync(struct arm_smmu_device *smmu)
{
	int count = 0;
	void __iomem *gr0_base = ARM_SMMU_GR0(smmu);

	writel_relaxed(0, gr0_base + ARM_SMMU_GR0_sTLBGSYNC);
	while (readl_relaxed(gr0_base + ARM_SMMU_GR0_sTLBGSTATUS)
	       & sTLBGSTATUS_GSACTIVE) {
		cpu_relax();
		if (++count == TLB_LOOP_TIMEOUT) {
			dev_err_ratelimited(smmu->dev,
			"TLB sync timed out -- SMMU may be deadlocked\n");
			return;
		}
		udelay(1);
	}
}

static void arm_smmu_tlb_sync(void *cookie)
{
	struct arm_smmu_domain *smmu_domain = cookie;
	__arm_smmu_tlb_sync(smmu_domain->smmu);
}

static void arm_smmu_tlb_inv_context(void *cookie)
{
	struct arm_smmu_domain *smmu_domain = cookie;
	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
	struct arm_smmu_device *smmu = smmu_domain->smmu;
	bool stage1 = cfg->cbar != CBAR_TYPE_S2_TRANS;
	void __iomem *base;

	if (stage1) {
		base = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, cfg->cbndx);
		writel_relaxed(ARM_SMMU_CB_ASID(cfg),
			       base + ARM_SMMU_CB_S1_TLBIASID);
	} else {
		base = ARM_SMMU_GR0(smmu);
		writel_relaxed(ARM_SMMU_CB_VMID(cfg),
			       base + ARM_SMMU_GR0_TLBIVMID);
	}

	__arm_smmu_tlb_sync(smmu);
}

static void arm_smmu_tlb_inv_range_nosync(unsigned long iova, size_t size,
					  bool leaf, void *cookie)
{
	struct arm_smmu_domain *smmu_domain = cookie;
	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
	struct arm_smmu_device *smmu = smmu_domain->smmu;
	bool stage1 = cfg->cbar != CBAR_TYPE_S2_TRANS;
	void __iomem *reg;

	if (stage1) {
		reg = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, cfg->cbndx);
		reg += leaf ? ARM_SMMU_CB_S1_TLBIVAL : ARM_SMMU_CB_S1_TLBIVA;

		if (!IS_ENABLED(CONFIG_64BIT) || smmu->version == ARM_SMMU_V1) {
			iova &= ~12UL;
			iova |= ARM_SMMU_CB_ASID(cfg);
			writel_relaxed(iova, reg);
#ifdef CONFIG_64BIT
		} else {
			iova >>= 12;
			iova |= (u64)ARM_SMMU_CB_ASID(cfg) << 48;
			writeq_relaxed(iova, reg);
#endif
		}
#ifdef CONFIG_64BIT
	} else if (smmu->version == ARM_SMMU_V2) {
		reg = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, cfg->cbndx);
		reg += leaf ? ARM_SMMU_CB_S2_TLBIIPAS2L :
			      ARM_SMMU_CB_S2_TLBIIPAS2;
		writeq_relaxed(iova >> 12, reg);
#endif
	} else {
		reg = ARM_SMMU_GR0(smmu) + ARM_SMMU_GR0_TLBIVMID;
		writel_relaxed(ARM_SMMU_CB_VMID(cfg), reg);
	}
}

static void arm_smmu_flush_pgtable(void *addr, size_t size, void *cookie)
{
	struct arm_smmu_domain *smmu_domain = cookie;
	struct arm_smmu_device *smmu = smmu_domain->smmu;
	unsigned long offset = (unsigned long)addr & ~PAGE_MASK;


	/* Ensure new page tables are visible to the hardware walker */
	if (smmu->features & ARM_SMMU_FEAT_COHERENT_WALK) {
		dsb(ishst);
	} else {
		/*
		 * If the SMMU can't walk tables in the CPU caches, treat them
		 * like non-coherent DMA since we need to flush the new entries
		 * all the way out to memory. There's no possibility of
		 * recursion here as the SMMU table walker will not be wired
		 * through another SMMU.
		 */
		dma_map_page(smmu->dev, virt_to_page(addr), offset, size,
			     DMA_TO_DEVICE);
	}
}

static struct iommu_gather_ops arm_smmu_gather_ops = {
	.tlb_flush_all	= arm_smmu_tlb_inv_context,
	.tlb_add_flush	= arm_smmu_tlb_inv_range_nosync,
	.tlb_sync	= arm_smmu_tlb_sync,
	.flush_pgtable	= arm_smmu_flush_pgtable,
};

static irqreturn_t arm_smmu_context_fault(int irq, void *dev)
{
	int flags, ret;
	u32 fsr, far, fsynr, resume;
	unsigned long iova;
	struct iommu_domain *domain = dev;
	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
	struct arm_smmu_device *smmu = smmu_domain->smmu;
	void __iomem *cb_base;

	cb_base = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, cfg->cbndx);
	fsr = readl_relaxed(cb_base + ARM_SMMU_CB_FSR);

	if (!(fsr & FSR_FAULT))
		return IRQ_NONE;

	if (fsr & FSR_IGN)
		dev_err_ratelimited(smmu->dev,
				    "Unexpected context fault (fsr 0x%x)\n",
				    fsr);

	fsynr = readl_relaxed(cb_base + ARM_SMMU_CB_FSYNR0);
	flags = fsynr & FSYNR0_WNR ? IOMMU_FAULT_WRITE : IOMMU_FAULT_READ;

	far = readl_relaxed(cb_base + ARM_SMMU_CB_FAR_LO);
	iova = far;
#ifdef CONFIG_64BIT
	far = readl_relaxed(cb_base + ARM_SMMU_CB_FAR_HI);
	iova |= ((unsigned long)far << 32);
#endif

	if (!report_iommu_fault(domain, smmu->dev, iova, flags)) {
		ret = IRQ_HANDLED;
		resume = RESUME_RETRY;
	} else {
		dev_err_ratelimited(smmu->dev,
		    "Unhandled context fault: iova=0x%08lx, fsynr=0x%x, cb=%d\n",
		    iova, fsynr, cfg->cbndx);
		ret = IRQ_NONE;
		resume = RESUME_TERMINATE;
	}

	/* Clear the faulting FSR */
	writel(fsr, cb_base + ARM_SMMU_CB_FSR);

	/* Retry or terminate any stalled transactions */
	if (fsr & FSR_SS)
		writel_relaxed(resume, cb_base + ARM_SMMU_CB_RESUME);

	return ret;
}

static irqreturn_t arm_smmu_global_fault(int irq, void *dev)
{
	u32 gfsr, gfsynr0, gfsynr1, gfsynr2;
	struct arm_smmu_device *smmu = dev;
	void __iomem *gr0_base = ARM_SMMU_GR0_NS(smmu);

	gfsr = readl_relaxed(gr0_base + ARM_SMMU_GR0_sGFSR);
	gfsynr0 = readl_relaxed(gr0_base + ARM_SMMU_GR0_sGFSYNR0);
	gfsynr1 = readl_relaxed(gr0_base + ARM_SMMU_GR0_sGFSYNR1);
	gfsynr2 = readl_relaxed(gr0_base + ARM_SMMU_GR0_sGFSYNR2);

	if (!gfsr)
		return IRQ_NONE;

	dev_err_ratelimited(smmu->dev,
		"Unexpected global fault, this could be serious\n");
	dev_err_ratelimited(smmu->dev,
		"\tGFSR 0x%08x, GFSYNR0 0x%08x, GFSYNR1 0x%08x, GFSYNR2 0x%08x\n",
		gfsr, gfsynr0, gfsynr1, gfsynr2);

	writel(gfsr, gr0_base + ARM_SMMU_GR0_sGFSR);
	return IRQ_HANDLED;
}

static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain,
				       struct io_pgtable_cfg *pgtbl_cfg)
{
	u32 reg;
	bool stage1;
	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
	struct arm_smmu_device *smmu = smmu_domain->smmu;
	void __iomem *cb_base, *gr0_base, *gr1_base;

	gr0_base = ARM_SMMU_GR0(smmu);
	gr1_base = ARM_SMMU_GR1(smmu);
	stage1 = cfg->cbar != CBAR_TYPE_S2_TRANS;
	cb_base = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, cfg->cbndx);

	if (smmu->version > ARM_SMMU_V1) {
		/*
		 * CBA2R.
		 * *Must* be initialised before CBAR thanks to VMID16
		 * architectural oversight affected some implementations.
		 */
#ifdef CONFIG_64BIT
		reg = CBA2R_RW64_64BIT;
#else
		reg = CBA2R_RW64_32BIT;
#endif
		writel_relaxed(reg, gr1_base + ARM_SMMU_GR1_CBA2R(cfg->cbndx));
	}

	/* CBAR */
	reg = cfg->cbar;
	if (smmu->version == ARM_SMMU_V1)
		reg |= cfg->irptndx << CBAR_IRPTNDX_SHIFT;

	/*
	 * Use the weakest shareability/memory types, so they are
	 * overridden by the ttbcr/pte.
	 */
	if (stage1) {
		reg |= (CBAR_S1_BPSHCFG_NSH << CBAR_S1_BPSHCFG_SHIFT) |
			(CBAR_S1_MEMATTR_WB << CBAR_S1_MEMATTR_SHIFT);
	} else {
		reg |= ARM_SMMU_CB_VMID(cfg) << CBAR_VMID_SHIFT;
	}
	writel_relaxed(reg, gr1_base + ARM_SMMU_GR1_CBAR(cfg->cbndx));

	/* TTBRs */
	if (stage1) {
		reg = pgtbl_cfg->arm_lpae_s1_cfg.ttbr[0];
		writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR0_LO);
		reg = pgtbl_cfg->arm_lpae_s1_cfg.ttbr[0] >> 32;
		reg |= ARM_SMMU_CB_ASID(cfg) << TTBRn_HI_ASID_SHIFT;
		writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR0_HI);

		reg = pgtbl_cfg->arm_lpae_s1_cfg.ttbr[1];
		writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR1_LO);
		reg = pgtbl_cfg->arm_lpae_s1_cfg.ttbr[1] >> 32;
		reg |= ARM_SMMU_CB_ASID(cfg) << TTBRn_HI_ASID_SHIFT;
		writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR1_HI);
	} else {
		reg = pgtbl_cfg->arm_lpae_s2_cfg.vttbr;
		writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR0_LO);
		reg = pgtbl_cfg->arm_lpae_s2_cfg.vttbr >> 32;
		writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR0_HI);
	}

	/* TTBCR */
	if (stage1) {
		reg = pgtbl_cfg->arm_lpae_s1_cfg.tcr;
		writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBCR);
		if (smmu->version > ARM_SMMU_V1) {
			reg = pgtbl_cfg->arm_lpae_s1_cfg.tcr >> 32;
			reg |= TTBCR2_SEP_UPSTREAM;
			writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBCR2);
		}
	} else {
		reg = pgtbl_cfg->arm_lpae_s2_cfg.vtcr;
		writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBCR);
	}

	/* MAIRs (stage-1 only) */
	if (stage1) {
		reg = pgtbl_cfg->arm_lpae_s1_cfg.mair[0];
		writel_relaxed(reg, cb_base + ARM_SMMU_CB_S1_MAIR0);
		reg = pgtbl_cfg->arm_lpae_s1_cfg.mair[1];
		writel_relaxed(reg, cb_base + ARM_SMMU_CB_S1_MAIR1);
	}

	/* SCTLR */
	reg = SCTLR_CFCFG | SCTLR_CFIE | SCTLR_CFRE | SCTLR_M | SCTLR_EAE_SBOP;
	if (stage1)
		reg |= SCTLR_S1_ASIDPNE;
#ifdef __BIG_ENDIAN
	reg |= SCTLR_E;
#endif
	writel_relaxed(reg, cb_base + ARM_SMMU_CB_SCTLR);
}

static int arm_smmu_init_domain_context(struct iommu_domain *domain,
					struct arm_smmu_device *smmu)
{
	int irq, start, ret = 0;
	unsigned long ias, oas;
	struct io_pgtable_ops *pgtbl_ops;
	struct io_pgtable_cfg pgtbl_cfg;
	enum io_pgtable_fmt fmt;
	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;

	mutex_lock(&smmu_domain->init_mutex);
	if (smmu_domain->smmu)
		goto out_unlock;

	/*
	 * Mapping the requested stage onto what we support is surprisingly
	 * complicated, mainly because the spec allows S1+S2 SMMUs without
	 * support for nested translation. That means we end up with the
	 * following table:
	 *
	 * Requested        Supported        Actual
	 *     S1               N              S1
	 *     S1             S1+S2            S1
	 *     S1               S2             S2
	 *     S1               S1             S1
	 *     N                N              N
	 *     N              S1+S2            S2
	 *     N                S2             S2
	 *     N                S1             S1
	 *
	 * Note that you can't actually request stage-2 mappings.
	 */
	if (!(smmu->features & ARM_SMMU_FEAT_TRANS_S1))
		smmu_domain->stage = ARM_SMMU_DOMAIN_S2;
	if (!(smmu->features & ARM_SMMU_FEAT_TRANS_S2))
		smmu_domain->stage = ARM_SMMU_DOMAIN_S1;

	switch (smmu_domain->stage) {
	case ARM_SMMU_DOMAIN_S1:
		cfg->cbar = CBAR_TYPE_S1_TRANS_S2_BYPASS;
		start = smmu->num_s2_context_banks;
		ias = smmu->va_size;
		oas = smmu->ipa_size;
		if (IS_ENABLED(CONFIG_64BIT))
			fmt = ARM_64_LPAE_S1;
		else
			fmt = ARM_32_LPAE_S1;
		break;
	case ARM_SMMU_DOMAIN_NESTED:
		/*
		 * We will likely want to change this if/when KVM gets
		 * involved.
		 */
	case ARM_SMMU_DOMAIN_S2:
		cfg->cbar = CBAR_TYPE_S2_TRANS;
		start = 0;
		ias = smmu->ipa_size;
		oas = smmu->pa_size;
		if (IS_ENABLED(CONFIG_64BIT))
			fmt = ARM_64_LPAE_S2;
		else
			fmt = ARM_32_LPAE_S2;
		break;
	default:
		ret = -EINVAL;
		goto out_unlock;
	}

	ret = __arm_smmu_alloc_bitmap(smmu->context_map, start,
				      smmu->num_context_banks);
	if (IS_ERR_VALUE(ret))
		goto out_unlock;

	cfg->cbndx = ret;
	if (smmu->version == ARM_SMMU_V1) {
		cfg->irptndx = atomic_inc_return(&smmu->irptndx);
		cfg->irptndx %= smmu->num_context_irqs;
	} else {
		cfg->irptndx = cfg->cbndx;
	}

	pgtbl_cfg = (struct io_pgtable_cfg) {
		.pgsize_bitmap	= arm_smmu_ops.pgsize_bitmap,
		.ias		= ias,
		.oas		= oas,
		.tlb		= &arm_smmu_gather_ops,
	};

	smmu_domain->smmu = smmu;
	pgtbl_ops = alloc_io_pgtable_ops(fmt, &pgtbl_cfg, smmu_domain);
	if (!pgtbl_ops) {
		ret = -ENOMEM;
		goto out_clear_smmu;
	}

	/* Update our support page sizes to reflect the page table format */
	arm_smmu_ops.pgsize_bitmap = pgtbl_cfg.pgsize_bitmap;

	/* Initialise the context bank with our page table cfg */
	arm_smmu_init_context_bank(smmu_domain, &pgtbl_cfg);

	/*
	 * Request context fault interrupt. Do this last to avoid the
	 * handler seeing a half-initialised domain state.
	 */
	irq = smmu->irqs[smmu->num_global_irqs + cfg->irptndx];
	ret = request_irq(irq, arm_smmu_context_fault, IRQF_SHARED,
			  "arm-smmu-context-fault", domain);
	if (IS_ERR_VALUE(ret)) {
		dev_err(smmu->dev, "failed to request context IRQ %d (%u)\n",
			cfg->irptndx, irq);
		cfg->irptndx = INVALID_IRPTNDX;
	}

	mutex_unlock(&smmu_domain->init_mutex);

	/* Publish page table ops for map/unmap */
	smmu_domain->pgtbl_ops = pgtbl_ops;
	return 0;

out_clear_smmu:
	smmu_domain->smmu = NULL;
out_unlock:
	mutex_unlock(&smmu_domain->init_mutex);
	return ret;
}

static void arm_smmu_destroy_domain_context(struct iommu_domain *domain)
{
	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
	struct arm_smmu_device *smmu = smmu_domain->smmu;
	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
	void __iomem *cb_base;
	int irq;

	if (!smmu)
		return;

	/*
	 * Disable the context bank and free the page tables before freeing
	 * it.
	 */
	cb_base = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, cfg->cbndx);
	writel_relaxed(0, cb_base + ARM_SMMU_CB_SCTLR);

	if (cfg->irptndx != INVALID_IRPTNDX) {
		irq = smmu->irqs[smmu->num_global_irqs + cfg->irptndx];
		free_irq(irq, domain);
	}

	if (smmu_domain->pgtbl_ops)
		free_io_pgtable_ops(smmu_domain->pgtbl_ops);

	__arm_smmu_free_bitmap(smmu->context_map, cfg->cbndx);
}

static struct iommu_domain *arm_smmu_domain_alloc(unsigned type)
{
	struct arm_smmu_domain *smmu_domain;

	if (type != IOMMU_DOMAIN_UNMANAGED)
		return NULL;
	/*
	 * Allocate the domain and initialise some of its data structures.
	 * We can't really do anything meaningful until we've added a
	 * master.
	 */
	smmu_domain = kzalloc(sizeof(*smmu_domain), GFP_KERNEL);
	if (!smmu_domain)
		return NULL;

	mutex_init(&smmu_domain->init_mutex);
	spin_lock_init(&smmu_domain->pgtbl_lock);

	return &smmu_domain->domain;
}

static void arm_smmu_domain_free(struct iommu_domain *domain)
{
	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);

	/*
	 * Free the domain resources. We assume that all devices have
	 * already been detached.
	 */
	arm_smmu_destroy_domain_context(domain);
	kfree(smmu_domain);
}

static int arm_smmu_master_configure_smrs(struct arm_smmu_device *smmu,
					  struct arm_smmu_master_cfg *cfg)
{
	int i;
	struct arm_smmu_smr *smrs;
	void __iomem *gr0_base = ARM_SMMU_GR0(smmu);

	if (!(smmu->features & ARM_SMMU_FEAT_STREAM_MATCH))
		return 0;

	if (cfg->smrs)
		return -EEXIST;

	smrs = kmalloc_array(cfg->num_streamids, sizeof(*smrs), GFP_KERNEL);
	if (!smrs) {
		dev_err(smmu->dev, "failed to allocate %d SMRs\n",
			cfg->num_streamids);
		return -ENOMEM;
	}

	/* Allocate the SMRs on the SMMU */
	for (i = 0; i < cfg->num_streamids; ++i) {
		int idx = __arm_smmu_alloc_bitmap(smmu->smr_map, 0,
						  smmu->num_mapping_groups);
		if (IS_ERR_VALUE(idx)) {
			dev_err(smmu->dev, "failed to allocate free SMR\n");
			goto err_free_smrs;
		}

		smrs[i] = (struct arm_smmu_smr) {
			.idx	= idx,
			.mask	= 0, /* We don't currently share SMRs */
			.id	= cfg->streamids[i],
		};
	}

	/* It worked! Now, poke the actual hardware */
	for (i = 0; i < cfg->num_streamids; ++i) {
		u32 reg = SMR_VALID | smrs[i].id << SMR_ID_SHIFT |
			  smrs[i].mask << SMR_MASK_SHIFT;
		writel_relaxed(reg, gr0_base + ARM_SMMU_GR0_SMR(smrs[i].idx));
	}

	cfg->smrs = smrs;
	return 0;

err_free_smrs:
	while (--i >= 0)
		__arm_smmu_free_bitmap(smmu->smr_map, smrs[i].idx);
	kfree(smrs);
	return -ENOSPC;
}

static void arm_smmu_master_free_smrs(struct arm_smmu_device *smmu,
				      struct arm_smmu_master_cfg *cfg)
{
	int i;
	void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
	struct arm_smmu_smr *smrs = cfg->smrs;

	if (!smrs)
		return;

	/* Invalidate the SMRs before freeing back to the allocator */
	for (i = 0; i < cfg->num_streamids; ++i) {
		u8 idx = smrs[i].idx;

		writel_relaxed(~SMR_VALID, gr0_base + ARM_SMMU_GR0_SMR(idx));
		__arm_smmu_free_bitmap(smmu->smr_map, idx);
	}

	cfg->smrs = NULL;
	kfree(smrs);
}

static int arm_smmu_domain_add_master(struct arm_smmu_domain *smmu_domain,
				      struct arm_smmu_master_cfg *cfg)
{
	int i, ret;
	struct arm_smmu_device *smmu = smmu_domain->smmu;
	void __iomem *gr0_base = ARM_SMMU_GR0(smmu);

	/* Devices in an IOMMU group may already be configured */
	ret = arm_smmu_master_configure_smrs(smmu, cfg);
	if (ret)
		return ret == -EEXIST ? 0 : ret;

	for (i = 0; i < cfg->num_streamids; ++i) {
		u32 idx, s2cr;

		idx = cfg->smrs ? cfg->smrs[i].idx : cfg->streamids[i];
		s2cr = S2CR_TYPE_TRANS |
		       (smmu_domain->cfg.cbndx << S2CR_CBNDX_SHIFT);
		writel_relaxed(s2cr, gr0_base + ARM_SMMU_GR0_S2CR(idx));
	}

	return 0;
}

static void arm_smmu_domain_remove_master(struct arm_smmu_domain *smmu_domain,
					  struct arm_smmu_master_cfg *cfg)
{
	int i;
	struct arm_smmu_device *smmu = smmu_domain->smmu;
	void __iomem *gr0_base = ARM_SMMU_GR0(smmu);

	/* An IOMMU group is torn down by the first device to be removed */
	if ((smmu->features & ARM_SMMU_FEAT_STREAM_MATCH) && !cfg->smrs)
		return;

	/*
	 * We *must* clear the S2CR first, because freeing the SMR means
	 * that it can be re-allocated immediately.
	 */
	for (i = 0; i < cfg->num_streamids; ++i) {
		u32 idx = cfg->smrs ? cfg->smrs[i].idx : cfg->streamids[i];

		writel_relaxed(S2CR_TYPE_BYPASS,
			       gr0_base + ARM_SMMU_GR0_S2CR(idx));
	}

	arm_smmu_master_free_smrs(smmu, cfg);
}

static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
{
	int ret;
	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
	struct arm_smmu_device *smmu;
	struct arm_smmu_master_cfg *cfg;

	smmu = find_smmu_for_device(dev);
	if (!smmu) {
		dev_err(dev, "cannot attach to SMMU, is it on the same bus?\n");
		return -ENXIO;
	}

	if (dev->archdata.iommu) {
		dev_err(dev, "already attached to IOMMU domain\n");
		return -EEXIST;
	}

	/* Ensure that the domain is finalised */
	ret = arm_smmu_init_domain_context(domain, smmu);
	if (IS_ERR_VALUE(ret))
		return ret;

	/*
	 * Sanity check the domain. We don't support domains across
	 * different SMMUs.
	 */
	if (smmu_domain->smmu != smmu) {
		dev_err(dev,
			"cannot attach to SMMU %s whilst already attached to domain on SMMU %s\n",
			dev_name(smmu_domain->smmu->dev), dev_name(smmu->dev));
		return -EINVAL;
	}

	/* Looks ok, so add the device to the domain */
	cfg = find_smmu_master_cfg(dev);
	if (!cfg)
		return -ENODEV;

	ret = arm_smmu_domain_add_master(smmu_domain, cfg);
	if (!ret)
		dev->archdata.iommu = domain;
	return ret;
}

static void arm_smmu_detach_dev(struct iommu_domain *domain, struct device *dev)
{
	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
	struct arm_smmu_master_cfg *cfg;

	cfg = find_smmu_master_cfg(dev);
	if (!cfg)
		return;

	dev->archdata.iommu = NULL;
	arm_smmu_domain_remove_master(smmu_domain, cfg);
}

static int arm_smmu_map(struct iommu_domain *domain, unsigned long iova,
			phys_addr_t paddr, size_t size, int prot)
{
	int ret;
	unsigned long flags;
	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
	struct io_pgtable_ops *ops= smmu_domain->pgtbl_ops;

	if (!ops)
		return -ENODEV;

	spin_lock_irqsave(&smmu_domain->pgtbl_lock, flags);
	ret = ops->map(ops, iova, paddr, size, prot);
	spin_unlock_irqrestore(&smmu_domain->pgtbl_lock, flags);
	return ret;
}

static size_t arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova,
			     size_t size)
{
	size_t ret;
	unsigned long flags;
	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
	struct io_pgtable_ops *ops= smmu_domain->pgtbl_ops;

	if (!ops)
		return 0;

	spin_lock_irqsave(&smmu_domain->pgtbl_lock, flags);
	ret = ops->unmap(ops, iova, size);
	spin_unlock_irqrestore(&smmu_domain->pgtbl_lock, flags);
	return ret;
}

static phys_addr_t arm_smmu_iova_to_phys_hard(struct iommu_domain *domain,
					      dma_addr_t iova)
{
	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
	struct arm_smmu_device *smmu = smmu_domain->smmu;
	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
	struct io_pgtable_ops *ops= smmu_domain->pgtbl_ops;
	struct device *dev = smmu->dev;
	void __iomem *cb_base;
	u32 tmp;
	u64 phys;
	unsigned long va;

	cb_base = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, cfg->cbndx);

	/* ATS1 registers can only be written atomically */
	va = iova & ~0xfffUL;
#ifdef CONFIG_64BIT
	if (smmu->version == ARM_SMMU_V2)
		writeq_relaxed(va, cb_base + ARM_SMMU_CB_ATS1PR);
	else
#endif
		writel_relaxed(va, cb_base + ARM_SMMU_CB_ATS1PR);

	if (readl_poll_timeout_atomic(cb_base + ARM_SMMU_CB_ATSR, tmp,
				      !(tmp & ATSR_ACTIVE), 5, 50)) {
		dev_err(dev,
			"iova to phys timed out on 0x%pad. Falling back to software table walk.\n",
			&iova);
		return ops->iova_to_phys(ops, iova);
	}

	phys = readl_relaxed(cb_base + ARM_SMMU_CB_PAR_LO);
	phys |= ((u64)readl_relaxed(cb_base + ARM_SMMU_CB_PAR_HI)) << 32;

	if (phys & CB_PAR_F) {
		dev_err(dev, "translation fault!\n");
		dev_err(dev, "PAR = 0x%llx\n", phys);
		return 0;
	}

	return (phys & GENMASK_ULL(39, 12)) | (iova & 0xfff);
}

static phys_addr_t arm_smmu_iova_to_phys(struct iommu_domain *domain,
					dma_addr_t iova)
{
	phys_addr_t ret;
	unsigned long flags;
	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
	struct io_pgtable_ops *ops= smmu_domain->pgtbl_ops;

	if (!ops)
		return 0;

	spin_lock_irqsave(&smmu_domain->pgtbl_lock, flags);
	if (smmu_domain->smmu->features & ARM_SMMU_FEAT_TRANS_OPS &&
			smmu_domain->stage == ARM_SMMU_DOMAIN_S1) {
		ret = arm_smmu_iova_to_phys_hard(domain, iova);
	} else {
		ret = ops->iova_to_phys(ops, iova);
	}

	spin_unlock_irqrestore(&smmu_domain->pgtbl_lock, flags);

	return ret;
}

static bool arm_smmu_capable(enum iommu_cap cap)
{
	switch (cap) {
	case IOMMU_CAP_CACHE_COHERENCY:
		/*
		 * Return true here as the SMMU can always send out coherent
		 * requests.
		 */
		return true;
	case IOMMU_CAP_INTR_REMAP:
		return true; /* MSIs are just memory writes */
	case IOMMU_CAP_NOEXEC:
		return true;
	default:
		return false;
	}
}

static int __arm_smmu_get_pci_sid(struct pci_dev *pdev, u16 alias, void *data)
{
	*((u16 *)data) = alias;
	return 0; /* Continue walking */
}

static void __arm_smmu_release_pci_iommudata(void *data)
{
	kfree(data);
}

static int arm_smmu_add_pci_device(struct pci_dev *pdev)
{
	int i, ret;
	u16 sid;
	struct iommu_group *group;
	struct arm_smmu_master_cfg *cfg;

	group = iommu_group_get_for_dev(&pdev->dev);
	if (IS_ERR(group))
		return PTR_ERR(group);

	cfg = iommu_group_get_iommudata(group);
	if (!cfg) {
		cfg = kzalloc(sizeof(*cfg), GFP_KERNEL);
		if (!cfg) {
			ret = -ENOMEM;
			goto out_put_group;
		}

		iommu_group_set_iommudata(group, cfg,
					  __arm_smmu_release_pci_iommudata);
	}

	if (cfg->num_streamids >= MAX_MASTER_STREAMIDS) {
		ret = -ENOSPC;
		goto out_put_group;
	}

	/*
	 * Assume Stream ID == Requester ID for now.
	 * We need a way to describe the ID mappings in FDT.
	 */
	pci_for_each_dma_alias(pdev, __arm_smmu_get_pci_sid, &sid);
	for (i = 0; i < cfg->num_streamids; ++i)
		if (cfg->streamids[i] == sid)
			break;

	/* Avoid duplicate SIDs, as this can lead to SMR conflicts */
	if (i == cfg->num_streamids)
		cfg->streamids[cfg->num_streamids++] = sid;

	return 0;
out_put_group:
	iommu_group_put(group);
	return ret;
}

static int arm_smmu_add_platform_device(struct device *dev)
{
	struct iommu_group *group;
	struct arm_smmu_master *master;
	struct arm_smmu_device *smmu = find_smmu_for_device(dev);

	if (!smmu)
		return -ENODEV;

	master = find_smmu_master(smmu, dev->of_node);
	if (!master)
		return -ENODEV;

	/* No automatic group creation for platform devices */
	group = iommu_group_alloc();
	if (IS_ERR(group))
		return PTR_ERR(group);

	iommu_group_set_iommudata(group, &master->cfg, NULL);
	return iommu_group_add_device(group, dev);
}

static int arm_smmu_add_device(struct device *dev)
{
	if (dev_is_pci(dev))
		return arm_smmu_add_pci_device(to_pci_dev(dev));

	return arm_smmu_add_platform_device(dev);
}

static void arm_smmu_remove_device(struct device *dev)
{
	iommu_group_remove_device(dev);
}

static int arm_smmu_domain_get_attr(struct iommu_domain *domain,
				    enum iommu_attr attr, void *data)
{
	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);

	switch (attr) {
	case DOMAIN_ATTR_NESTING:
		*(int *)data = (smmu_domain->stage == ARM_SMMU_DOMAIN_NESTED);
		return 0;
	default:
		return -ENODEV;
	}
}

static int arm_smmu_domain_set_attr(struct iommu_domain *domain,
				    enum iommu_attr attr, void *data)
{
	int ret = 0;
	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);

	mutex_lock(&smmu_domain->init_mutex);

	switch (attr) {
	case DOMAIN_ATTR_NESTING:
		if (smmu_domain->smmu) {
			ret = -EPERM;
			goto out_unlock;
		}

		if (*(int *)data)
			smmu_domain->stage = ARM_SMMU_DOMAIN_NESTED;
		else
			smmu_domain->stage = ARM_SMMU_DOMAIN_S1;

		break;
	default:
		ret = -ENODEV;
	}

out_unlock:
	mutex_unlock(&smmu_domain->init_mutex);
	return ret;
}

static struct iommu_ops arm_smmu_ops = {
	.capable		= arm_smmu_capable,
	.domain_alloc		= arm_smmu_domain_alloc,
	.domain_free		= arm_smmu_domain_free,
	.attach_dev		= arm_smmu_attach_dev,
	.detach_dev		= arm_smmu_detach_dev,
	.map			= arm_smmu_map,
	.unmap			= arm_smmu_unmap,
	.map_sg			= default_iommu_map_sg,
	.iova_to_phys		= arm_smmu_iova_to_phys,
	.add_device		= arm_smmu_add_device,
	.remove_device		= arm_smmu_remove_device,
	.domain_get_attr	= arm_smmu_domain_get_attr,
	.domain_set_attr	= arm_smmu_domain_set_attr,
	.pgsize_bitmap		= -1UL, /* Restricted during device attach */
};

static void arm_smmu_device_reset(struct arm_smmu_device *smmu)
{
	void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
	void __iomem *cb_base;
	int i = 0;
	u32 reg;

	/* clear global FSR */
	reg = readl_relaxed(ARM_SMMU_GR0_NS(smmu) + ARM_SMMU_GR0_sGFSR);
	writel(reg, ARM_SMMU_GR0_NS(smmu) + ARM_SMMU_GR0_sGFSR);

	/* Mark all SMRn as invalid and all S2CRn as bypass */
	for (i = 0; i < smmu->num_mapping_groups; ++i) {
		writel_relaxed(0, gr0_base + ARM_SMMU_GR0_SMR(i));
		writel_relaxed(S2CR_TYPE_BYPASS,
			gr0_base + ARM_SMMU_GR0_S2CR(i));
	}

	/* Make sure all context banks are disabled and clear CB_FSR  */
	for (i = 0; i < smmu->num_context_banks; ++i) {
		cb_base = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, i);
		writel_relaxed(0, cb_base + ARM_SMMU_CB_SCTLR);
		writel_relaxed(FSR_FAULT, cb_base + ARM_SMMU_CB_FSR);
	}

	/* Invalidate the TLB, just in case */
	writel_relaxed(0, gr0_base + ARM_SMMU_GR0_TLBIALLH);
	writel_relaxed(0, gr0_base + ARM_SMMU_GR0_TLBIALLNSNH);

	reg = readl_relaxed(ARM_SMMU_GR0_NS(smmu) + ARM_SMMU_GR0_sCR0);

	/* Enable fault reporting */
	reg |= (sCR0_GFRE | sCR0_GFIE | sCR0_GCFGFRE | sCR0_GCFGFIE);

	/* Disable TLB broadcasting. */
	reg |= (sCR0_VMIDPNE | sCR0_PTM);

	/* Enable client access, but bypass when no mapping is found */
	reg &= ~(sCR0_CLIENTPD | sCR0_USFCFG);

	/* Disable forced broadcasting */
	reg &= ~sCR0_FB;

	/* Don't upgrade barriers */
	reg &= ~(sCR0_BSU_MASK << sCR0_BSU_SHIFT);

	/* Push the button */
	__arm_smmu_tlb_sync(smmu);
	writel(reg, ARM_SMMU_GR0_NS(smmu) + ARM_SMMU_GR0_sCR0);
}

static int arm_smmu_id_size_to_bits(int size)
{
	switch (size) {
	case 0:
		return 32;
	case 1:
		return 36;
	case 2:
		return 40;
	case 3:
		return 42;
	case 4:
		return 44;
	case 5:
	default:
		return 48;
	}
}

static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
{
	unsigned long size;
	void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
	u32 id;

	dev_notice(smmu->dev, "probing hardware configuration...\n");
	dev_notice(smmu->dev, "SMMUv%d with:\n", smmu->version);

	/* ID0 */
	id = readl_relaxed(gr0_base + ARM_SMMU_GR0_ID0);

	/* Restrict available stages based on module parameter */
	if (force_stage == 1)
		id &= ~(ID0_S2TS | ID0_NTS);
	else if (force_stage == 2)
		id &= ~(ID0_S1TS | ID0_NTS);

	if (id & ID0_S1TS) {
		smmu->features |= ARM_SMMU_FEAT_TRANS_S1;
		dev_notice(smmu->dev, "\tstage 1 translation\n");
	}

	if (id & ID0_S2TS) {
		smmu->features |= ARM_SMMU_FEAT_TRANS_S2;
		dev_notice(smmu->dev, "\tstage 2 translation\n");
	}

	if (id & ID0_NTS) {
		smmu->features |= ARM_SMMU_FEAT_TRANS_NESTED;
		dev_notice(smmu->dev, "\tnested translation\n");
	}

	if (!(smmu->features &
		(ARM_SMMU_FEAT_TRANS_S1 | ARM_SMMU_FEAT_TRANS_S2))) {
		dev_err(smmu->dev, "\tno translation support!\n");
		return -ENODEV;
	}

	if ((id & ID0_S1TS) && ((smmu->version == 1) || !(id & ID0_ATOSNS))) {
		smmu->features |= ARM_SMMU_FEAT_TRANS_OPS;
		dev_notice(smmu->dev, "\taddress translation ops\n");
	}

	if (id & ID0_CTTW) {
		smmu->features |= ARM_SMMU_FEAT_COHERENT_WALK;
		dev_notice(smmu->dev, "\tcoherent table walk\n");
	}

	if (id & ID0_SMS) {
		u32 smr, sid, mask;

		smmu->features |= ARM_SMMU_FEAT_STREAM_MATCH;
		smmu->num_mapping_groups = (id >> ID0_NUMSMRG_SHIFT) &
					   ID0_NUMSMRG_MASK;
		if (smmu->num_mapping_groups == 0) {
			dev_err(smmu->dev,
				"stream-matching supported, but no SMRs present!\n");
			return -ENODEV;
		}

		smr = SMR_MASK_MASK << SMR_MASK_SHIFT;
		smr |= (SMR_ID_MASK << SMR_ID_SHIFT);
		writel_relaxed(smr, gr0_base + ARM_SMMU_GR0_SMR(0));
		smr = readl_relaxed(gr0_base + ARM_SMMU_GR0_SMR(0));

		mask = (smr >> SMR_MASK_SHIFT) & SMR_MASK_MASK;
		sid = (smr >> SMR_ID_SHIFT) & SMR_ID_MASK;
		if ((mask & sid) != sid) {
			dev_err(smmu->dev,
				"SMR mask bits (0x%x) insufficient for ID field (0x%x)\n",
				mask, sid);
			return -ENODEV;
		}

		dev_notice(smmu->dev,
			   "\tstream matching with %u register groups, mask 0x%x",
			   smmu->num_mapping_groups, mask);
	} else {
		smmu->num_mapping_groups = (id >> ID0_NUMSIDB_SHIFT) &
					   ID0_NUMSIDB_MASK;
	}

	/* ID1 */
	id = readl_relaxed(gr0_base + ARM_SMMU_GR0_ID1);
	smmu->pgshift = (id & ID1_PAGESIZE) ? 16 : 12;

	/* Check for size mismatch of SMMU address space from mapped region */
	size = 1 << (((id >> ID1_NUMPAGENDXB_SHIFT) & ID1_NUMPAGENDXB_MASK) + 1);
	size *= 2 << smmu->pgshift;
	if (smmu->size != size)
		dev_warn(smmu->dev,
			"SMMU address space size (0x%lx) differs from mapped region size (0x%lx)!\n",
			size, smmu->size);

	smmu->num_s2_context_banks = (id >> ID1_NUMS2CB_SHIFT) & ID1_NUMS2CB_MASK;
	smmu->num_context_banks = (id >> ID1_NUMCB_SHIFT) & ID1_NUMCB_MASK;
	if (smmu->num_s2_context_banks > smmu->num_context_banks) {
		dev_err(smmu->dev, "impossible number of S2 context banks!\n");
		return -ENODEV;
	}
	dev_notice(smmu->dev, "\t%u context banks (%u stage-2 only)\n",
		   smmu->num_context_banks, smmu->num_s2_context_banks);

	/* ID2 */
	id = readl_relaxed(gr0_base + ARM_SMMU_GR0_ID2);
	size = arm_smmu_id_size_to_bits((id >> ID2_IAS_SHIFT) & ID2_IAS_MASK);
	smmu->ipa_size = size;

	/* The output mask is also applied for bypass */
	size = arm_smmu_id_size_to_bits((id >> ID2_OAS_SHIFT) & ID2_OAS_MASK);
	smmu->pa_size = size;

	/*
	 * What the page table walker can address actually depends on which
	 * descriptor format is in use, but since a) we don't know that yet,
	 * and b) it can vary per context bank, this will have to do...
	 */
	if (dma_set_mask_and_coherent(smmu->dev, DMA_BIT_MASK(size)))
		dev_warn(smmu->dev,
			 "failed to set DMA mask for table walker\n");

	if (smmu->version == ARM_SMMU_V1) {
		smmu->va_size = smmu->ipa_size;
		size = SZ_4K | SZ_2M | SZ_1G;
	} else {
		size = (id >> ID2_UBS_SHIFT) & ID2_UBS_MASK;
		smmu->va_size = arm_smmu_id_size_to_bits(size);
#ifndef CONFIG_64BIT
		smmu->va_size = min(32UL, smmu->va_size);
#endif
		size = 0;
		if (id & ID2_PTFS_4K)
			size |= SZ_4K | SZ_2M | SZ_1G;
		if (id & ID2_PTFS_16K)
			size |= SZ_16K | SZ_32M;
		if (id & ID2_PTFS_64K)
			size |= SZ_64K | SZ_512M;
	}

	arm_smmu_ops.pgsize_bitmap &= size;
	dev_notice(smmu->dev, "\tSupported page sizes: 0x%08lx\n", size);

	if (smmu->features & ARM_SMMU_FEAT_TRANS_S1)
		dev_notice(smmu->dev, "\tStage-1: %lu-bit VA -> %lu-bit IPA\n",
			   smmu->va_size, smmu->ipa_size);

	if (smmu->features & ARM_SMMU_FEAT_TRANS_S2)
		dev_notice(smmu->dev, "\tStage-2: %lu-bit IPA -> %lu-bit PA\n",
			   smmu->ipa_size, smmu->pa_size);

	return 0;
}

static const struct of_device_id arm_smmu_of_match[] = {
	{ .compatible = "arm,smmu-v1", .data = (void *)ARM_SMMU_V1 },
	{ .compatible = "arm,smmu-v2", .data = (void *)ARM_SMMU_V2 },
	{ .compatible = "arm,mmu-400", .data = (void *)ARM_SMMU_V1 },
	{ .compatible = "arm,mmu-401", .data = (void *)ARM_SMMU_V1 },
	{ .compatible = "arm,mmu-500", .data = (void *)ARM_SMMU_V2 },
	{ },
};
MODULE_DEVICE_TABLE(of, arm_smmu_of_match);

static int arm_smmu_device_dt_probe(struct platform_device *pdev)
{
	const struct of_device_id *of_id;
	struct resource *res;
	struct arm_smmu_device *smmu;
	struct device *dev = &pdev->dev;
	struct rb_node *node;
	struct of_phandle_args masterspec;
	int num_irqs, i, err;

	smmu = devm_kzalloc(dev, sizeof(*smmu), GFP_KERNEL);
	if (!smmu) {
		dev_err(dev, "failed to allocate arm_smmu_device\n");
		return -ENOMEM;
	}
	smmu->dev = dev;

	of_id = of_match_node(arm_smmu_of_match, dev->of_node);
	smmu->version = (enum arm_smmu_arch_version)of_id->data;

	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
	smmu->base = devm_ioremap_resource(dev, res);
	if (IS_ERR(smmu->base))
		return PTR_ERR(smmu->base);
	smmu->size = resource_size(res);

	if (of_property_read_u32(dev->of_node, "#global-interrupts",
				 &smmu->num_global_irqs)) {
		dev_err(dev, "missing #global-interrupts property\n");
		return -ENODEV;
	}

	num_irqs = 0;
	while ((res = platform_get_resource(pdev, IORESOURCE_IRQ, num_irqs))) {
		num_irqs++;
		if (num_irqs > smmu->num_global_irqs)
			smmu->num_context_irqs++;
	}

	if (!smmu->num_context_irqs) {
		dev_err(dev, "found %d interrupts but expected at least %d\n",
			num_irqs, smmu->num_global_irqs + 1);
		return -ENODEV;
	}

	smmu->irqs = devm_kzalloc(dev, sizeof(*smmu->irqs) * num_irqs,
				  GFP_KERNEL);
	if (!smmu->irqs) {
		dev_err(dev, "failed to allocate %d irqs\n", num_irqs);
		return -ENOMEM;
	}

	for (i = 0; i < num_irqs; ++i) {
		int irq = platform_get_irq(pdev, i);

		if (irq < 0) {
			dev_err(dev, "failed to get irq index %d\n", i);
			return -ENODEV;
		}
		smmu->irqs[i] = irq;
	}

	err = arm_smmu_device_cfg_probe(smmu);
	if (err)
		return err;

	i = 0;
	smmu->masters = RB_ROOT;
	while (!of_parse_phandle_with_args(dev->of_node, "mmu-masters",
					   "#stream-id-cells", i,
					   &masterspec)) {
		err = register_smmu_master(smmu, dev, &masterspec);
		if (err) {
			dev_err(dev, "failed to add master %s\n",
				masterspec.np->name);
			goto out_put_masters;
		}

		i++;
	}
	dev_notice(dev, "registered %d master devices\n", i);

	parse_driver_options(smmu);

	if (smmu->version > ARM_SMMU_V1 &&
	    smmu->num_context_banks != smmu->num_context_irqs) {
		dev_err(dev,
			"found only %d context interrupt(s) but %d required\n",
			smmu->num_context_irqs, smmu->num_context_banks);
		err = -ENODEV;
		goto out_put_masters;
	}

	for (i = 0; i < smmu->num_global_irqs; ++i) {
		err = request_irq(smmu->irqs[i],
				  arm_smmu_global_fault,
				  IRQF_SHARED,
				  "arm-smmu global fault",
				  smmu);
		if (err) {
			dev_err(dev, "failed to request global IRQ %d (%u)\n",
				i, smmu->irqs[i]);
			goto out_free_irqs;
		}
	}

	INIT_LIST_HEAD(&smmu->list);
	spin_lock(&arm_smmu_devices_lock);
	list_add(&smmu->list, &arm_smmu_devices);
	spin_unlock(&arm_smmu_devices_lock);

	arm_smmu_device_reset(smmu);
	return 0;

out_free_irqs:
	while (i--)
		free_irq(smmu->irqs[i], smmu);

out_put_masters:
	for (node = rb_first(&smmu->masters); node; node = rb_next(node)) {
		struct arm_smmu_master *master
			= container_of(node, struct arm_smmu_master, node);
		of_node_put(master->of_node);
	}

	return err;
}

static int arm_smmu_device_remove(struct platform_device *pdev)
{
	int i;
	struct device *dev = &pdev->dev;
	struct arm_smmu_device *curr, *smmu = NULL;
	struct rb_node *node;

	spin_lock(&arm_smmu_devices_lock);
	list_for_each_entry(curr, &arm_smmu_devices, list) {
		if (curr->dev == dev) {
			smmu = curr;
			list_del(&smmu->list);
			break;
		}
	}
	spin_unlock(&arm_smmu_devices_lock);

	if (!smmu)
		return -ENODEV;

	for (node = rb_first(&smmu->masters); node; node = rb_next(node)) {
		struct arm_smmu_master *master
			= container_of(node, struct arm_smmu_master, node);
		of_node_put(master->of_node);
	}

	if (!bitmap_empty(smmu->context_map, ARM_SMMU_MAX_CBS))
		dev_err(dev, "removing device with active domains!\n");

	for (i = 0; i < smmu->num_global_irqs; ++i)
		free_irq(smmu->irqs[i], smmu);

	/* Turn the thing off */
	writel(sCR0_CLIENTPD, ARM_SMMU_GR0_NS(smmu) + ARM_SMMU_GR0_sCR0);
	return 0;
}

static struct platform_driver arm_smmu_driver = {
	.driver	= {
		.name		= "arm-smmu",
		.of_match_table	= of_match_ptr(arm_smmu_of_match),
	},
	.probe	= arm_smmu_device_dt_probe,
	.remove	= arm_smmu_device_remove,
};

static int __init arm_smmu_init(void)
{
	struct device_node *np;
	int ret;

	/*
	 * Play nice with systems that don't have an ARM SMMU by checking that
	 * an ARM SMMU exists in the system before proceeding with the driver
	 * and IOMMU bus operation registration.
	 */
	np = of_find_matching_node(NULL, arm_smmu_of_match);
	if (!np)
		return 0;

	of_node_put(np);

	ret = platform_driver_register(&arm_smmu_driver);
	if (ret)
		return ret;

	/* Oh, for a proper bus abstraction */
	if (!iommu_present(&platform_bus_type))
		bus_set_iommu(&platform_bus_type, &arm_smmu_ops);

#ifdef CONFIG_ARM_AMBA
	if (!iommu_present(&amba_bustype))
		bus_set_iommu(&amba_bustype, &arm_smmu_ops);
#endif

#ifdef CONFIG_PCI
	if (!iommu_present(&pci_bus_type))
		bus_set_iommu(&pci_bus_type, &arm_smmu_ops);
#endif

	return 0;
}

static void __exit arm_smmu_exit(void)
{
	return platform_driver_unregister(&arm_smmu_driver);
}

subsys_initcall(arm_smmu_init);
module_exit(arm_smmu_exit);

MODULE_DESCRIPTION("IOMMU API for ARM architected SMMU implementations");
MODULE_AUTHOR("Will Deacon <will.deacon@arm.com>");
MODULE_LICENSE("GPL v2");