iommu/arm: Add support for ARM Ltd. System MMU architecture

This patch adds support for SMMUs implementing the ARM System MMU
architecture versions 1 or 2. Both arm and arm64 are supported, although
the v7s descriptor format is not used.

Cc: Rob Herring <robherring2@gmail.com>
Cc: Andreas Herrmann <andreas.herrmann@calxeda.com>
Cc: Olav Haugan <ohaugan@codeaurora.org>
Cc: Joerg Roedel <joro@8bytes.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Acked-by: Andreas Herrmann <andreas.herrmann@calxeda.com>
Signed-off-by: Joerg Roedel <joro@8bytes.org>

3 files changed, 1983 insertions, 0 deletions

diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index c332fb98480d..957cfd4f8065 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -261,4 +261,17 @@ config SHMOBILE_IOMMU_L1SIZE
 	default 256 if SHMOBILE_IOMMU_ADDRSIZE_64MB
 	default 128 if SHMOBILE_IOMMU_ADDRSIZE_32MB
 
+config ARM_SMMU
+	bool "ARM Ltd. System MMU (SMMU) Support"
+	depends on ARM64 || (ARM_LPAE && OF)
+	select IOMMU_API
+	select ARM_DMA_USE_IOMMU if ARM
+	help
+	  Support for implementations of the ARM System MMU architecture
+	  versions 1 and 2. The driver supports both v7l and v8l table
+	  formats with 4k and 64k page sizes.
+
+	  Say Y here if your SoC includes an IOMMU device implementing
+	  the ARM SMMU architecture.
+
 endif # IOMMU_SUPPORT
diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile
index ef0e5207ad69..bbe7041212dd 100644
--- a/drivers/iommu/Makefile
+++ b/drivers/iommu/Makefile
@@ -3,6 +3,7 @@ obj-$(CONFIG_OF_IOMMU)	+= of_iommu.o
 obj-$(CONFIG_MSM_IOMMU) += msm_iommu.o msm_iommu_dev.o
 obj-$(CONFIG_AMD_IOMMU) += amd_iommu.o amd_iommu_init.o
 obj-$(CONFIG_AMD_IOMMU_V2) += amd_iommu_v2.o
+obj-$(CONFIG_ARM_SMMU) += arm-smmu.o
 obj-$(CONFIG_DMAR_TABLE) += dmar.o
 obj-$(CONFIG_INTEL_IOMMU) += iova.o intel-iommu.o
 obj-$(CONFIG_IRQ_REMAP) += intel_irq_remapping.o irq_remapping.o
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
new file mode 100644
index 000000000000..ebd0a4cff049
--- /dev/null
+++ b/drivers/iommu/arm-smmu.c
@@ -0,0 +1,1969 @@
+/*
+ * 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
+ *	- 4k and 64k pages, with contiguous pte hints.
+ *	- Up to 39-bit addressing
+ *	- 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/mm.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+
+#include <linux/amba/bus.h>
+
+#include <asm/pgalloc.h>
+
+/* Maximum number of stream IDs assigned to a single device */
+#define MAX_MASTER_STREAMIDS		8
+
+/* 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
+
+/* Number of VMIDs per SMMU */
+#define ARM_SMMU_NUM_VMIDS		256
+
+/* SMMU global address space */
+#define ARM_SMMU_GR0(smmu)		((smmu)->base)
+#define ARM_SMMU_GR1(smmu)		((smmu)->base + (smmu)->pagesize)
+
+/* Page table bits */
+#define ARM_SMMU_PTE_PAGE		(((pteval_t)3) << 0)
+#define ARM_SMMU_PTE_CONT		(((pteval_t)1) << 52)
+#define ARM_SMMU_PTE_AF			(((pteval_t)1) << 10)
+#define ARM_SMMU_PTE_SH_NS		(((pteval_t)0) << 8)
+#define ARM_SMMU_PTE_SH_OS		(((pteval_t)2) << 8)
+#define ARM_SMMU_PTE_SH_IS		(((pteval_t)3) << 8)
+
+#if PAGE_SIZE == SZ_4K
+#define ARM_SMMU_PTE_CONT_ENTRIES	16
+#elif PAGE_SIZE == SZ_64K
+#define ARM_SMMU_PTE_CONT_ENTRIES	32
+#else
+#define ARM_SMMU_PTE_CONT_ENTRIES	1
+#endif
+
+#define ARM_SMMU_PTE_CONT_SIZE		(PAGE_SIZE * ARM_SMMU_PTE_CONT_ENTRIES)
+#define ARM_SMMU_PTE_CONT_MASK		(~(ARM_SMMU_PTE_CONT_SIZE - 1))
+#define ARM_SMMU_PTE_HWTABLE_SIZE	(PTRS_PER_PTE * sizeof(pte_t))
+
+/* Stage-1 PTE */
+#define ARM_SMMU_PTE_AP_UNPRIV		(((pteval_t)1) << 6)
+#define ARM_SMMU_PTE_AP_RDONLY		(((pteval_t)2) << 6)
+#define ARM_SMMU_PTE_ATTRINDX_SHIFT	2
+
+/* Stage-2 PTE */
+#define ARM_SMMU_PTE_HAP_FAULT		(((pteval_t)0) << 6)
+#define ARM_SMMU_PTE_HAP_READ		(((pteval_t)1) << 6)
+#define ARM_SMMU_PTE_HAP_WRITE		(((pteval_t)2) << 6)
+#define ARM_SMMU_PTE_MEMATTR_OIWB	(((pteval_t)0xf) << 2)
+#define ARM_SMMU_PTE_MEMATTR_NC		(((pteval_t)0x5) << 2)
+#define ARM_SMMU_PTE_MEMATTR_DEV	(((pteval_t)0x1) << 2)
+
+/* 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 ARM_SMMU_GR0_PIDR0		0xfe0
+#define ARM_SMMU_GR0_PIDR1		0xfe4
+#define ARM_SMMU_GR0_PIDR2		0xfe8
+
+#define ID0_S1TS			(1 << 30)
+#define ID0_S2TS			(1 << 29)
+#define ID0_NTS				(1 << 28)
+#define ID0_SMS				(1 << 27)
+#define ID0_PTFS_SHIFT			24
+#define ID0_PTFS_MASK			0x2
+#define ID0_PTFS_V8_ONLY		0x2
+#define ID0_CTTW			(1 << 14)
+#define ID0_NUMIRPT_SHIFT		16
+#define ID0_NUMIRPT_MASK		0xff
+#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)
+
+#define PIDR2_ARCH_SHIFT		4
+#define PIDR2_ARCH_MASK			0xf
+
+/* Global TLB invalidation */
+#define ARM_SMMU_GR0_STLBIALL		0x60
+#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_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) * (smmu)->pagesize)
+
+#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_TTBCR		0x30
+#define ARM_SMMU_CB_S1_MAIR0		0x38
+#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 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 RESUME_RETRY			(0 << 0)
+#define RESUME_TERMINATE		(1 << 0)
+
+#define TTBCR_EAE			(1 << 31)
+
+#define TTBCR_PASIZE_SHIFT		16
+#define TTBCR_PASIZE_MASK		0x7
+
+#define TTBCR_TG0_4K			(0 << 14)
+#define TTBCR_TG0_64K			(1 << 14)
+
+#define TTBCR_SH0_SHIFT			12
+#define TTBCR_SH0_MASK			0x3
+#define TTBCR_SH_NS			0
+#define TTBCR_SH_OS			2
+#define TTBCR_SH_IS			3
+
+#define TTBCR_ORGN0_SHIFT		10
+#define TTBCR_IRGN0_SHIFT		8
+#define TTBCR_RGN_MASK			0x3
+#define TTBCR_RGN_NC			0
+#define TTBCR_RGN_WBWA			1
+#define TTBCR_RGN_WT			2
+#define TTBCR_RGN_WB			3
+
+#define TTBCR_SL0_SHIFT			6
+#define TTBCR_SL0_MASK			0x3
+#define TTBCR_SL0_LVL_2			0
+#define TTBCR_SL0_LVL_1			1
+
+#define TTBCR_T1SZ_SHIFT		16
+#define TTBCR_T0SZ_SHIFT		0
+#define TTBCR_SZ_MASK			0xf
+
+#define TTBCR2_SEP_SHIFT		15
+#define TTBCR2_SEP_MASK			0x7
+
+#define TTBCR2_PASIZE_SHIFT		0
+#define TTBCR2_PASIZE_MASK		0x7
+
+/* Common definitions for PASize and SEP fields */
+#define TTBCR2_ADDR_32			0
+#define TTBCR2_ADDR_36			1
+#define TTBCR2_ADDR_40			2
+#define TTBCR2_ADDR_42			3
+#define TTBCR2_ADDR_44			4
+#define TTBCR2_ADDR_48			5
+
+#define MAIR_ATTR_SHIFT(n)		((n) << 3)
+#define MAIR_ATTR_MASK			0xff
+#define MAIR_ATTR_DEVICE		0x04
+#define MAIR_ATTR_NC			0x44
+#define MAIR_ATTR_WBRWA			0xff
+#define MAIR_ATTR_IDX_NC		0
+#define MAIR_ATTR_IDX_CACHE		1
+#define MAIR_ATTR_IDX_DEV		2
+
+#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)
+
+#define FSYNR0_WNR			(1 << 4)
+
+struct arm_smmu_smr {
+	u8				idx;
+	u16				mask;
+	u16				id;
+};
+
+struct arm_smmu_master {
+	struct device_node		*of_node;
+
+	/*
+	 * The following is specific to the master's position in the
+	 * SMMU chain.
+	 */
+	struct rb_node			node;
+	int				num_streamids;
+	u16				streamids[MAX_MASTER_STREAMIDS];
+
+	/*
+	 * We only need to allocate these on the root SMMU, as we
+	 * configure unmatched streams to bypass translation.
+	 */
+	struct arm_smmu_smr		*smrs;
+};
+
+struct arm_smmu_device {
+	struct device			*dev;
+	struct device_node		*parent_of_node;
+
+	void __iomem			*base;
+	unsigned long			size;
+	unsigned long			pagesize;
+
+#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)
+	u32				features;
+	int				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			input_size;
+	unsigned long			s1_output_size;
+	unsigned long			s2_output_size;
+
+	u32				num_global_irqs;
+	u32				num_context_irqs;
+	unsigned int			*irqs;
+
+	DECLARE_BITMAP(vmid_map, ARM_SMMU_NUM_VMIDS);
+
+	struct list_head		list;
+	struct rb_root			masters;
+};
+
+struct arm_smmu_cfg {
+	struct arm_smmu_device		*smmu;
+	u8				vmid;
+	u8				cbndx;
+	u8				irptndx;
+	u32				cbar;
+	pgd_t				*pgd;
+};
+
+struct arm_smmu_domain {
+	/*
+	 * A domain can span across multiple, chained SMMUs and requires
+	 * all devices within the domain to follow the same translation
+	 * path.
+	 */
+	struct arm_smmu_device		*leaf_smmu;
+	struct arm_smmu_cfg		root_cfg;
+	phys_addr_t			output_mask;
+
+	spinlock_t			lock;
+};
+
+static DEFINE_SPINLOCK(arm_smmu_devices_lock);
+static LIST_HEAD(arm_smmu_devices);
+
+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 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;
+		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->num_streamids	= masterspec->args_count;
+
+	for (i = 0; i < master->num_streamids; ++i)
+		master->streamids[i] = masterspec->args[i];
+
+	return insert_smmu_master(smmu, master);
+}
+
+static struct arm_smmu_device *find_parent_smmu(struct arm_smmu_device *smmu)
+{
+	struct arm_smmu_device *parent;
+
+	if (!smmu->parent_of_node)
+		return NULL;
+
+	spin_lock(&arm_smmu_devices_lock);
+	list_for_each_entry(parent, &arm_smmu_devices, list)
+		if (parent->dev->of_node == smmu->parent_of_node)
+			goto out_unlock;
+
+	parent = NULL;
+	dev_warn(smmu->dev,
+		 "Failed to find SMMU parent despite parent in DT\n");
+out_unlock:
+	spin_unlock(&arm_smmu_devices_lock);
+	return parent;
+}
+
+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 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 = domain->priv;
+	struct arm_smmu_cfg *root_cfg = &smmu_domain->root_cfg;
+	struct arm_smmu_device *smmu = root_cfg->smmu;
+	void __iomem *cb_base;
+
+	cb_base = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, root_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%u)\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 {
+		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(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);
+
+	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_NONE;
+}
+
+static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain)
+{
+	u32 reg;
+	bool stage1;
+	struct arm_smmu_cfg *root_cfg = &smmu_domain->root_cfg;
+	struct arm_smmu_device *smmu = root_cfg->smmu;
+	void __iomem *cb_base, *gr0_base, *gr1_base;
+
+	gr0_base = ARM_SMMU_GR0(smmu);
+	gr1_base = ARM_SMMU_GR1(smmu);
+	stage1 = root_cfg->cbar != CBAR_TYPE_S2_TRANS;
+	cb_base = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, root_cfg->cbndx);
+
+	/* CBAR */
+	reg = root_cfg->cbar |
+	      (root_cfg->vmid << CBAR_VMID_SHIFT);
+	if (smmu->version == 1)
+	      reg |= root_cfg->irptndx << CBAR_IRPTNDX_SHIFT;
+
+	/* Use the weakest memory type, so it is overridden by the pte */
+	if (stage1)
+		reg |= (CBAR_S1_MEMATTR_WB << CBAR_S1_MEMATTR_SHIFT);
+	writel_relaxed(reg, gr1_base + ARM_SMMU_GR1_CBAR(root_cfg->cbndx));
+
+	if (smmu->version > 1) {
+		/* CBA2R */
+#ifdef CONFIG_64BIT
+		reg = CBA2R_RW64_64BIT;
+#else
+		reg = CBA2R_RW64_32BIT;
+#endif
+		writel_relaxed(reg,
+			       gr1_base + ARM_SMMU_GR1_CBA2R(root_cfg->cbndx));
+
+		/* TTBCR2 */
+		switch (smmu->input_size) {
+		case 32:
+			reg = (TTBCR2_ADDR_32 << TTBCR2_SEP_SHIFT);
+			break;
+		case 36:
+			reg = (TTBCR2_ADDR_36 << TTBCR2_SEP_SHIFT);
+			break;
+		case 39:
+			reg = (TTBCR2_ADDR_40 << TTBCR2_SEP_SHIFT);
+			break;
+		case 42:
+			reg = (TTBCR2_ADDR_42 << TTBCR2_SEP_SHIFT);
+			break;
+		case 44:
+			reg = (TTBCR2_ADDR_44 << TTBCR2_SEP_SHIFT);
+			break;
+		case 48:
+			reg = (TTBCR2_ADDR_48 << TTBCR2_SEP_SHIFT);
+			break;
+		}
+
+		switch (smmu->s1_output_size) {
+		case 32:
+			reg |= (TTBCR2_ADDR_32 << TTBCR2_PASIZE_SHIFT);
+			break;
+		case 36:
+			reg |= (TTBCR2_ADDR_36 << TTBCR2_PASIZE_SHIFT);
+			break;
+		case 39:
+			reg |= (TTBCR2_ADDR_40 << TTBCR2_PASIZE_SHIFT);
+			break;
+		case 42:
+			reg |= (TTBCR2_ADDR_42 << TTBCR2_PASIZE_SHIFT);
+			break;
+		case 44:
+			reg |= (TTBCR2_ADDR_44 << TTBCR2_PASIZE_SHIFT);
+			break;
+		case 48:
+			reg |= (TTBCR2_ADDR_48 << TTBCR2_PASIZE_SHIFT);
+			break;
+		}
+
+		if (stage1)
+			writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBCR2);
+	}
+
+	/* TTBR0 */
+	reg = __pa(root_cfg->pgd);
+#ifndef __BIG_ENDIAN
+	writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR0_LO);
+	reg = (phys_addr_t)__pa(root_cfg->pgd) >> 32;
+	writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR0_HI);
+#else
+	writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR0_HI);
+	reg = (phys_addr_t)__pa(root_cfg->pgd) >> 32;
+	writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR0_LO);
+#endif
+
+	/*
+	 * TTBCR
+	 * We use long descriptor, with inner-shareable WBWA tables in TTBR0.
+	 */
+	if (smmu->version > 1) {
+		if (PAGE_SIZE == SZ_4K)
+			reg = TTBCR_TG0_4K;
+		else
+			reg = TTBCR_TG0_64K;
+
+		if (!stage1) {
+			switch (smmu->s2_output_size) {
+			case 32:
+				reg |= (TTBCR2_ADDR_32 << TTBCR_PASIZE_SHIFT);
+				break;
+			case 36:
+				reg |= (TTBCR2_ADDR_36 << TTBCR_PASIZE_SHIFT);
+				break;
+			case 40:
+				reg |= (TTBCR2_ADDR_40 << TTBCR_PASIZE_SHIFT);
+				break;
+			case 42:
+				reg |= (TTBCR2_ADDR_42 << TTBCR_PASIZE_SHIFT);
+				break;
+			case 44:
+				reg |= (TTBCR2_ADDR_44 << TTBCR_PASIZE_SHIFT);
+				break;
+			case 48:
+				reg |= (TTBCR2_ADDR_48 << TTBCR_PASIZE_SHIFT);
+				break;
+			}
+		} else {
+			reg |= (64 - smmu->s1_output_size) << TTBCR_T0SZ_SHIFT;
+		}
+	} else {
+		reg = 0;
+	}
+
+	reg |= TTBCR_EAE |
+	      (TTBCR_SH_IS << TTBCR_SH0_SHIFT) |
+	      (TTBCR_RGN_WBWA << TTBCR_ORGN0_SHIFT) |
+	      (TTBCR_RGN_WBWA << TTBCR_IRGN0_SHIFT) |
+	      (TTBCR_SL0_LVL_1 << TTBCR_SL0_SHIFT);
+	writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBCR);
+
+	/* MAIR0 (stage-1 only) */
+	if (stage1) {
+		reg = (MAIR_ATTR_NC << MAIR_ATTR_SHIFT(MAIR_ATTR_IDX_NC)) |
+		      (MAIR_ATTR_WBRWA << MAIR_ATTR_SHIFT(MAIR_ATTR_IDX_CACHE)) |
+		      (MAIR_ATTR_DEVICE << MAIR_ATTR_SHIFT(MAIR_ATTR_IDX_DEV));
+		writel_relaxed(reg, cb_base + ARM_SMMU_CB_S1_MAIR0);
+	}
+
+	/* Nuke the TLB */
+	writel_relaxed(root_cfg->vmid, gr0_base + ARM_SMMU_GR0_TLBIVMID);
+	arm_smmu_tlb_sync(smmu);
+
+	/* 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(reg, cb_base + ARM_SMMU_CB_SCTLR);
+}
+
+static int arm_smmu_init_domain_context(struct iommu_domain *domain,
+					struct device *dev)
+{
+	int irq, ret, start;
+	struct arm_smmu_domain *smmu_domain = domain->priv;
+	struct arm_smmu_cfg *root_cfg = &smmu_domain->root_cfg;
+	struct arm_smmu_device *smmu, *parent;
+
+	/*
+	 * Walk the SMMU chain to find the root device for this chain.
+	 * We assume that no masters have translations which terminate
+	 * early, and therefore check that the root SMMU does indeed have
+	 * a StreamID for the master in question.
+	 */
+	parent = dev->archdata.iommu;
+	smmu_domain->output_mask = -1;
+	do {
+		smmu = parent;
+		smmu_domain->output_mask &= (1ULL << smmu->s2_output_size) - 1;
+	} while ((parent = find_parent_smmu(smmu)));
+
+	if (!find_smmu_master(smmu, dev->of_node)) {
+		dev_err(dev, "unable to find root SMMU for device\n");
+		return -ENODEV;
+	}
+
+	ret = __arm_smmu_alloc_bitmap(smmu->vmid_map, 0, ARM_SMMU_NUM_VMIDS);
+	if (IS_ERR_VALUE(ret))
+		return ret;
+
+	root_cfg->vmid = ret;
+	if (smmu->features & ARM_SMMU_FEAT_TRANS_NESTED) {
+		/*
+		 * We will likely want to change this if/when KVM gets
+		 * involved.
+		 */
+		root_cfg->cbar = CBAR_TYPE_S1_TRANS_S2_BYPASS;
+		start = smmu->num_s2_context_banks;
+	} else if (smmu->features & ARM_SMMU_FEAT_TRANS_S2) {
+		root_cfg->cbar = CBAR_TYPE_S2_TRANS;
+		start = 0;
+	} else {
+		root_cfg->cbar = CBAR_TYPE_S1_TRANS_S2_BYPASS;
+		start = smmu->num_s2_context_banks;
+	}
+
+	ret = __arm_smmu_alloc_bitmap(smmu->context_map, start,
+				      smmu->num_context_banks);
+	if (IS_ERR_VALUE(ret))
+		goto out_free_vmid;
+
+	root_cfg->cbndx = ret;
+
+	if (smmu->version == 1) {
+		root_cfg->irptndx = atomic_inc_return(&smmu->irptndx);
+		root_cfg->irptndx %= smmu->num_context_irqs;
+	} else {
+		root_cfg->irptndx = root_cfg->cbndx;
+	}
+
+	irq = smmu->irqs[smmu->num_global_irqs + root_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",
+			root_cfg->irptndx, irq);
+		root_cfg->irptndx = -1;
+		goto out_free_context;
+	}
+
+	root_cfg->smmu = smmu;
+	arm_smmu_init_context_bank(smmu_domain);
+	return ret;
+
+out_free_context:
+	__arm_smmu_free_bitmap(smmu->context_map, root_cfg->cbndx);
+out_free_vmid:
+	__arm_smmu_free_bitmap(smmu->vmid_map, root_cfg->vmid);
+	return ret;
+}
+
+static void arm_smmu_destroy_domain_context(struct iommu_domain *domain)
+{
+	struct arm_smmu_domain *smmu_domain = domain->priv;
+	struct arm_smmu_cfg *root_cfg = &smmu_domain->root_cfg;
+	struct arm_smmu_device *smmu = root_cfg->smmu;
+	int irq;
+
+	if (!smmu)
+		return;
+
+	if (root_cfg->irptndx != -1) {
+		irq = smmu->irqs[smmu->num_global_irqs + root_cfg->irptndx];
+		free_irq(irq, domain);
+	}
+
+	__arm_smmu_free_bitmap(smmu->vmid_map, root_cfg->vmid);
+	__arm_smmu_free_bitmap(smmu->context_map, root_cfg->cbndx);
+}
+
+static int arm_smmu_domain_init(struct iommu_domain *domain)
+{
+	struct arm_smmu_domain *smmu_domain;
+	pgd_t *pgd;
+
+	/*
+	 * 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 -ENOMEM;
+
+	pgd = kzalloc(PTRS_PER_PGD * sizeof(pgd_t), GFP_KERNEL);
+	if (!pgd)
+		goto out_free_domain;
+	smmu_domain->root_cfg.pgd = pgd;
+
+	spin_lock_init(&smmu_domain->lock);
+	domain->priv = smmu_domain;
+	return 0;
+
+out_free_domain:
+	kfree(smmu_domain);
+	return -ENOMEM;
+}
+
+static void arm_smmu_free_ptes(pmd_t *pmd)
+{
+	pgtable_t table = pmd_pgtable(*pmd);
+	pgtable_page_dtor(table);
+	__free_page(table);
+}
+
+static void arm_smmu_free_pmds(pud_t *pud)
+{
+	int i;
+	pmd_t *pmd, *pmd_base = pmd_offset(pud, 0);
+
+	pmd = pmd_base;
+	for (i = 0; i < PTRS_PER_PMD; ++i) {
+		if (pmd_none(*pmd))
+			continue;
+
+		arm_smmu_free_ptes(pmd);
+		pmd++;
+	}
+
+	pmd_free(NULL, pmd_base);
+}
+
+static void arm_smmu_free_puds(pgd_t *pgd)
+{
+	int i;
+	pud_t *pud, *pud_base = pud_offset(pgd, 0);
+
+	pud = pud_base;
+	for (i = 0; i < PTRS_PER_PUD; ++i) {
+		if (pud_none(*pud))
+			continue;
+
+		arm_smmu_free_pmds(pud);
+		pud++;
+	}
+
+	pud_free(NULL, pud_base);
+}
+
+static void arm_smmu_free_pgtables(struct arm_smmu_domain *smmu_domain)
+{
+	int i;
+	struct arm_smmu_cfg *root_cfg = &smmu_domain->root_cfg;
+	pgd_t *pgd, *pgd_base = root_cfg->pgd;
+
+	/*
+	 * Recursively free the page tables for this domain. We don't
+	 * care about speculative TLB filling, because the TLB will be
+	 * nuked next time this context bank is re-allocated and no devices
+	 * currently map to these tables.
+	 */
+	pgd = pgd_base;
+	for (i = 0; i < PTRS_PER_PGD; ++i) {
+		if (pgd_none(*pgd))
+			continue;
+		arm_smmu_free_puds(pgd);
+		pgd++;
+	}
+
+	kfree(pgd_base);
+}
+
+static void arm_smmu_domain_destroy(struct iommu_domain *domain)
+{
+	struct arm_smmu_domain *smmu_domain = domain->priv;
+	arm_smmu_destroy_domain_context(domain);
+	arm_smmu_free_pgtables(smmu_domain);
+	kfree(smmu_domain);
+}
+
+static int arm_smmu_master_configure_smrs(struct arm_smmu_device *smmu,
+					  struct arm_smmu_master *master)
+{
+	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 (master->smrs)
+		return -EEXIST;
+
+	smrs = kmalloc(sizeof(*smrs) * master->num_streamids, GFP_KERNEL);
+	if (!smrs) {
+		dev_err(smmu->dev, "failed to allocate %d SMRs for master %s\n",
+			master->num_streamids, master->of_node->name);
+		return -ENOMEM;
+	}
+
+	/* Allocate the SMRs on the root SMMU */
+	for (i = 0; i < master->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	= master->streamids[i],
+		};
+	}
+
+	/* It worked! Now, poke the actual hardware */
+	for (i = 0; i < master->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));
+	}
+
+	master->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 *master)
+{
+	int i;
+	void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
+	struct arm_smmu_smr *smrs = master->smrs;
+
+	/* Invalidate the SMRs before freeing back to the allocator */
+	for (i = 0; i < master->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);
+	}
+
+	master->smrs = NULL;
+	kfree(smrs);
+}
+
+static void arm_smmu_bypass_stream_mapping(struct arm_smmu_device *smmu,
+					   struct arm_smmu_master *master)
+{
+	int i;
+	void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
+
+	for (i = 0; i < master->num_streamids; ++i) {
+		u16 sid = master->streamids[i];
+		writel_relaxed(S2CR_TYPE_BYPASS,
+			       gr0_base + ARM_SMMU_GR0_S2CR(sid));
+	}
+}
+
+static int arm_smmu_domain_add_master(struct arm_smmu_domain *smmu_domain,
+				      struct arm_smmu_master *master)
+{
+	int i, ret;
+	struct arm_smmu_device *parent, *smmu = smmu_domain->root_cfg.smmu;
+	void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
+
+	ret = arm_smmu_master_configure_smrs(smmu, master);
+	if (ret)
+		return ret;
+
+	/* Bypass the leaves */
+	smmu = smmu_domain->leaf_smmu;
+	while ((parent = find_parent_smmu(smmu))) {
+		/*
+		 * We won't have a StreamID match for anything but the root
+		 * smmu, so we only need to worry about StreamID indexing,
+		 * where we must install bypass entries in the S2CRs.
+		 */
+		if (smmu->features & ARM_SMMU_FEAT_STREAM_MATCH)
+			continue;
+
+		arm_smmu_bypass_stream_mapping(smmu, master);
+		smmu = parent;
+	}
+
+	/* Now we're at the root, time to point at our context bank */
+	for (i = 0; i < master->num_streamids; ++i) {
+		u32 idx, s2cr;
+		idx = master->smrs ? master->smrs[i].idx : master->streamids[i];
+		s2cr = (S2CR_TYPE_TRANS << S2CR_TYPE_SHIFT) |
+		       (smmu_domain->root_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 *master)</