iommu/arm-smmu: Add initial driver support for ARM SMMUv3 devices

Version three of the ARM SMMU architecture introduces significant
changes and improvements over previous versions of the specification,
necessitating a new driver in the Linux kernel.

The main change to the programming interface is that the majority of the
configuration data has been moved from MMIO registers to in-memory data
structures, with communication between the CPU and the SMMU being
mediated via in-memory circular queues.

This patch adds an initial driver for SMMUv3 to Linux. We currently
support pinned stage-1 (DMA) and stage-2 (KVM VFIO) mappings using the
generic IO-pgtable code.

Cc: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>

1 files changed, 2670 insertions, 0 deletions

diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
new file mode 100644
index 000000000000..f14130121298
--- /dev/null
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -0,0 +1,2670 @@
+/*
+ * IOMMU API for ARM architected SMMUv3 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, see <http://www.gnu.org/licenses/>.
+ *
+ * Copyright (C) 2015 ARM Limited
+ *
+ * Author: Will Deacon <will.deacon@arm.com>
+ *
+ * This driver is powered by bad coffee and bombay mix.
+ */
+
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/interrupt.h>
+#include <linux/iommu.h>
+#include <linux/iopoll.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/pci.h>
+#include <linux/platform_device.h>
+
+#include "io-pgtable.h"
+
+/* MMIO registers */
+#define ARM_SMMU_IDR0			0x0
+#define IDR0_ST_LVL_SHIFT		27
+#define IDR0_ST_LVL_MASK		0x3
+#define IDR0_ST_LVL_2LVL		(1 << IDR0_ST_LVL_SHIFT)
+#define IDR0_STALL_MODEL		(3 << 24)
+#define IDR0_TTENDIAN_SHIFT		21
+#define IDR0_TTENDIAN_MASK		0x3
+#define IDR0_TTENDIAN_LE		(2 << IDR0_TTENDIAN_SHIFT)
+#define IDR0_TTENDIAN_BE		(3 << IDR0_TTENDIAN_SHIFT)
+#define IDR0_TTENDIAN_MIXED		(0 << IDR0_TTENDIAN_SHIFT)
+#define IDR0_CD2L			(1 << 19)
+#define IDR0_VMID16			(1 << 18)
+#define IDR0_PRI			(1 << 16)
+#define IDR0_SEV			(1 << 14)
+#define IDR0_MSI			(1 << 13)
+#define IDR0_ASID16			(1 << 12)
+#define IDR0_ATS			(1 << 10)
+#define IDR0_HYP			(1 << 9)
+#define IDR0_COHACC			(1 << 4)
+#define IDR0_TTF_SHIFT			2
+#define IDR0_TTF_MASK			0x3
+#define IDR0_TTF_AARCH64		(2 << IDR0_TTF_SHIFT)
+#define IDR0_S1P			(1 << 1)
+#define IDR0_S2P			(1 << 0)
+
+#define ARM_SMMU_IDR1			0x4
+#define IDR1_TABLES_PRESET		(1 << 30)
+#define IDR1_QUEUES_PRESET		(1 << 29)
+#define IDR1_REL			(1 << 28)
+#define IDR1_CMDQ_SHIFT			21
+#define IDR1_CMDQ_MASK			0x1f
+#define IDR1_EVTQ_SHIFT			16
+#define IDR1_EVTQ_MASK			0x1f
+#define IDR1_PRIQ_SHIFT			11
+#define IDR1_PRIQ_MASK			0x1f
+#define IDR1_SSID_SHIFT			6
+#define IDR1_SSID_MASK			0x1f
+#define IDR1_SID_SHIFT			0
+#define IDR1_SID_MASK			0x3f
+
+#define ARM_SMMU_IDR5			0x14
+#define IDR5_STALL_MAX_SHIFT		16
+#define IDR5_STALL_MAX_MASK		0xffff
+#define IDR5_GRAN64K			(1 << 6)
+#define IDR5_GRAN16K			(1 << 5)
+#define IDR5_GRAN4K			(1 << 4)
+#define IDR5_OAS_SHIFT			0
+#define IDR5_OAS_MASK			0x7
+#define IDR5_OAS_32_BIT			(0 << IDR5_OAS_SHIFT)
+#define IDR5_OAS_36_BIT			(1 << IDR5_OAS_SHIFT)
+#define IDR5_OAS_40_BIT			(2 << IDR5_OAS_SHIFT)
+#define IDR5_OAS_42_BIT			(3 << IDR5_OAS_SHIFT)
+#define IDR5_OAS_44_BIT			(4 << IDR5_OAS_SHIFT)
+#define IDR5_OAS_48_BIT			(5 << IDR5_OAS_SHIFT)
+
+#define ARM_SMMU_CR0			0x20
+#define CR0_CMDQEN			(1 << 3)
+#define CR0_EVTQEN			(1 << 2)
+#define CR0_PRIQEN			(1 << 1)
+#define CR0_SMMUEN			(1 << 0)
+
+#define ARM_SMMU_CR0ACK			0x24
+
+#define ARM_SMMU_CR1			0x28
+#define CR1_SH_NSH			0
+#define CR1_SH_OSH			2
+#define CR1_SH_ISH			3
+#define CR1_CACHE_NC			0
+#define CR1_CACHE_WB			1
+#define CR1_CACHE_WT			2
+#define CR1_TABLE_SH_SHIFT		10
+#define CR1_TABLE_OC_SHIFT		8
+#define CR1_TABLE_IC_SHIFT		6
+#define CR1_QUEUE_SH_SHIFT		4
+#define CR1_QUEUE_OC_SHIFT		2
+#define CR1_QUEUE_IC_SHIFT		0
+
+#define ARM_SMMU_CR2			0x2c
+#define CR2_PTM				(1 << 2)
+#define CR2_RECINVSID			(1 << 1)
+#define CR2_E2H				(1 << 0)
+
+#define ARM_SMMU_IRQ_CTRL		0x50
+#define IRQ_CTRL_EVTQ_IRQEN		(1 << 2)
+#define IRQ_CTRL_GERROR_IRQEN		(1 << 0)
+
+#define ARM_SMMU_IRQ_CTRLACK		0x54
+
+#define ARM_SMMU_GERROR			0x60
+#define GERROR_SFM_ERR			(1 << 8)
+#define GERROR_MSI_GERROR_ABT_ERR	(1 << 7)
+#define GERROR_MSI_PRIQ_ABT_ERR		(1 << 6)
+#define GERROR_MSI_EVTQ_ABT_ERR		(1 << 5)
+#define GERROR_MSI_CMDQ_ABT_ERR		(1 << 4)
+#define GERROR_PRIQ_ABT_ERR		(1 << 3)
+#define GERROR_EVTQ_ABT_ERR		(1 << 2)
+#define GERROR_CMDQ_ERR			(1 << 0)
+#define GERROR_ERR_MASK			0xfd
+
+#define ARM_SMMU_GERRORN		0x64
+
+#define ARM_SMMU_GERROR_IRQ_CFG0	0x68
+#define ARM_SMMU_GERROR_IRQ_CFG1	0x70
+#define ARM_SMMU_GERROR_IRQ_CFG2	0x74
+
+#define ARM_SMMU_STRTAB_BASE		0x80
+#define STRTAB_BASE_RA			(1UL << 62)
+#define STRTAB_BASE_ADDR_SHIFT		6
+#define STRTAB_BASE_ADDR_MASK		0x3ffffffffffUL
+
+#define ARM_SMMU_STRTAB_BASE_CFG	0x88
+#define STRTAB_BASE_CFG_LOG2SIZE_SHIFT	0
+#define STRTAB_BASE_CFG_LOG2SIZE_MASK	0x3f
+#define STRTAB_BASE_CFG_SPLIT_SHIFT	6
+#define STRTAB_BASE_CFG_SPLIT_MASK	0x1f
+#define STRTAB_BASE_CFG_FMT_SHIFT	16
+#define STRTAB_BASE_CFG_FMT_MASK	0x3
+#define STRTAB_BASE_CFG_FMT_LINEAR	(0 << STRTAB_BASE_CFG_FMT_SHIFT)
+#define STRTAB_BASE_CFG_FMT_2LVL	(1 << STRTAB_BASE_CFG_FMT_SHIFT)
+
+#define ARM_SMMU_CMDQ_BASE		0x90
+#define ARM_SMMU_CMDQ_PROD		0x98
+#define ARM_SMMU_CMDQ_CONS		0x9c
+
+#define ARM_SMMU_EVTQ_BASE		0xa0
+#define ARM_SMMU_EVTQ_PROD		0x100a8
+#define ARM_SMMU_EVTQ_CONS		0x100ac
+#define ARM_SMMU_EVTQ_IRQ_CFG0		0xb0
+#define ARM_SMMU_EVTQ_IRQ_CFG1		0xb8
+#define ARM_SMMU_EVTQ_IRQ_CFG2		0xbc
+
+#define ARM_SMMU_PRIQ_BASE		0xc0
+#define ARM_SMMU_PRIQ_PROD		0x100c8
+#define ARM_SMMU_PRIQ_CONS		0x100cc
+#define ARM_SMMU_PRIQ_IRQ_CFG0		0xd0
+#define ARM_SMMU_PRIQ_IRQ_CFG1		0xd8
+#define ARM_SMMU_PRIQ_IRQ_CFG2		0xdc
+
+/* Common MSI config fields */
+#define MSI_CFG0_SH_SHIFT		60
+#define MSI_CFG0_SH_NSH			(0UL << MSI_CFG0_SH_SHIFT)
+#define MSI_CFG0_SH_OSH			(2UL << MSI_CFG0_SH_SHIFT)
+#define MSI_CFG0_SH_ISH			(3UL << MSI_CFG0_SH_SHIFT)
+#define MSI_CFG0_MEMATTR_SHIFT		56
+#define MSI_CFG0_MEMATTR_DEVICE_nGnRE	(0x1 << MSI_CFG0_MEMATTR_SHIFT)
+#define MSI_CFG0_ADDR_SHIFT		2
+#define MSI_CFG0_ADDR_MASK		0x3fffffffffffUL
+
+#define Q_IDX(q, p)			((p) & ((1 << (q)->max_n_shift) - 1))
+#define Q_WRP(q, p)			((p) & (1 << (q)->max_n_shift))
+#define Q_OVERFLOW_FLAG			(1 << 31)
+#define Q_OVF(q, p)			((p) & Q_OVERFLOW_FLAG)
+#define Q_ENT(q, p)			((q)->base +			\
+					 Q_IDX(q, p) * (q)->ent_dwords)
+
+#define Q_BASE_RWA			(1UL << 62)
+#define Q_BASE_ADDR_SHIFT		5
+#define Q_BASE_ADDR_MASK		0xfffffffffffUL
+#define Q_BASE_LOG2SIZE_SHIFT		0
+#define Q_BASE_LOG2SIZE_MASK		0x1fUL
+
+/*
+ * Stream table.
+ *
+ * Linear: Enough to cover 1 << IDR1.SIDSIZE entries
+ * 2lvl: 8k L1 entries, 256 lazy entries per table (each table covers a PCI bus)
+ */
+#define STRTAB_L1_SZ_SHIFT		16
+#define STRTAB_SPLIT			8
+
+#define STRTAB_L1_DESC_DWORDS		1
+#define STRTAB_L1_DESC_SPAN_SHIFT	0
+#define STRTAB_L1_DESC_SPAN_MASK	0x1fUL
+#define STRTAB_L1_DESC_L2PTR_SHIFT	6
+#define STRTAB_L1_DESC_L2PTR_MASK	0x3ffffffffffUL
+
+#define STRTAB_STE_DWORDS		8
+#define STRTAB_STE_0_V			(1UL << 0)
+#define STRTAB_STE_0_CFG_SHIFT		1
+#define STRTAB_STE_0_CFG_MASK		0x7UL
+#define STRTAB_STE_0_CFG_ABORT		(0UL << STRTAB_STE_0_CFG_SHIFT)
+#define STRTAB_STE_0_CFG_BYPASS		(4UL << STRTAB_STE_0_CFG_SHIFT)
+#define STRTAB_STE_0_CFG_S1_TRANS	(5UL << STRTAB_STE_0_CFG_SHIFT)
+#define STRTAB_STE_0_CFG_S2_TRANS	(6UL << STRTAB_STE_0_CFG_SHIFT)
+
+#define STRTAB_STE_0_S1FMT_SHIFT	4
+#define STRTAB_STE_0_S1FMT_LINEAR	(0UL << STRTAB_STE_0_S1FMT_SHIFT)
+#define STRTAB_STE_0_S1CTXPTR_SHIFT	6
+#define STRTAB_STE_0_S1CTXPTR_MASK	0x3ffffffffffUL
+#define STRTAB_STE_0_S1CDMAX_SHIFT	59
+#define STRTAB_STE_0_S1CDMAX_MASK	0x1fUL
+
+#define STRTAB_STE_1_S1C_CACHE_NC	0UL
+#define STRTAB_STE_1_S1C_CACHE_WBRA	1UL
+#define STRTAB_STE_1_S1C_CACHE_WT	2UL
+#define STRTAB_STE_1_S1C_CACHE_WB	3UL
+#define STRTAB_STE_1_S1C_SH_NSH		0UL
+#define STRTAB_STE_1_S1C_SH_OSH		2UL
+#define STRTAB_STE_1_S1C_SH_ISH		3UL
+#define STRTAB_STE_1_S1CIR_SHIFT	2
+#define STRTAB_STE_1_S1COR_SHIFT	4
+#define STRTAB_STE_1_S1CSH_SHIFT	6
+
+#define STRTAB_STE_1_S1STALLD		(1UL << 27)
+
+#define STRTAB_STE_1_EATS_ABT		0UL
+#define STRTAB_STE_1_EATS_TRANS		1UL
+#define STRTAB_STE_1_EATS_S1CHK		2UL
+#define STRTAB_STE_1_EATS_SHIFT		28
+
+#define STRTAB_STE_1_STRW_NSEL1		0UL
+#define STRTAB_STE_1_STRW_EL2		2UL
+#define STRTAB_STE_1_STRW_SHIFT		30
+
+#define STRTAB_STE_2_S2VMID_SHIFT	0
+#define STRTAB_STE_2_S2VMID_MASK	0xffffUL
+#define STRTAB_STE_2_VTCR_SHIFT		32
+#define STRTAB_STE_2_VTCR_MASK		0x7ffffUL
+#define STRTAB_STE_2_S2AA64		(1UL << 51)
+#define STRTAB_STE_2_S2ENDI		(1UL << 52)
+#define STRTAB_STE_2_S2PTW		(1UL << 54)
+#define STRTAB_STE_2_S2R		(1UL << 58)
+
+#define STRTAB_STE_3_S2TTB_SHIFT	4
+#define STRTAB_STE_3_S2TTB_MASK		0xfffffffffffUL
+
+/* Context descriptor (stage-1 only) */
+#define CTXDESC_CD_DWORDS		8
+#define CTXDESC_CD_0_TCR_T0SZ_SHIFT	0
+#define ARM64_TCR_T0SZ_SHIFT		0
+#define ARM64_TCR_T0SZ_MASK		0x1fUL
+#define CTXDESC_CD_0_TCR_TG0_SHIFT	6
+#define ARM64_TCR_TG0_SHIFT		14
+#define ARM64_TCR_TG0_MASK		0x3UL
+#define CTXDESC_CD_0_TCR_IRGN0_SHIFT	8
+#define ARM64_TCR_IRGN0_SHIFT		24
+#define ARM64_TCR_IRGN0_MASK		0x3UL
+#define CTXDESC_CD_0_TCR_ORGN0_SHIFT	10
+#define ARM64_TCR_ORGN0_SHIFT		26
+#define ARM64_TCR_ORGN0_MASK		0x3UL
+#define CTXDESC_CD_0_TCR_SH0_SHIFT	12
+#define ARM64_TCR_SH0_SHIFT		12
+#define ARM64_TCR_SH0_MASK		0x3UL
+#define CTXDESC_CD_0_TCR_EPD0_SHIFT	14
+#define ARM64_TCR_EPD0_SHIFT		7
+#define ARM64_TCR_EPD0_MASK		0x1UL
+#define CTXDESC_CD_0_TCR_EPD1_SHIFT	30
+#define ARM64_TCR_EPD1_SHIFT		23
+#define ARM64_TCR_EPD1_MASK		0x1UL
+
+#define CTXDESC_CD_0_ENDI		(1UL << 15)
+#define CTXDESC_CD_0_V			(1UL << 31)
+
+#define CTXDESC_CD_0_TCR_IPS_SHIFT	32
+#define ARM64_TCR_IPS_SHIFT		32
+#define ARM64_TCR_IPS_MASK		0x7UL
+#define CTXDESC_CD_0_TCR_TBI0_SHIFT	38
+#define ARM64_TCR_TBI0_SHIFT		37
+#define ARM64_TCR_TBI0_MASK		0x1UL
+
+#define CTXDESC_CD_0_AA64		(1UL << 41)
+#define CTXDESC_CD_0_R			(1UL << 45)
+#define CTXDESC_CD_0_A			(1UL << 46)
+#define CTXDESC_CD_0_ASET_SHIFT		47
+#define CTXDESC_CD_0_ASET_SHARED	(0UL << CTXDESC_CD_0_ASET_SHIFT)
+#define CTXDESC_CD_0_ASET_PRIVATE	(1UL << CTXDESC_CD_0_ASET_SHIFT)
+#define CTXDESC_CD_0_ASID_SHIFT		48
+#define CTXDESC_CD_0_ASID_MASK		0xffffUL
+
+#define CTXDESC_CD_1_TTB0_SHIFT		4
+#define CTXDESC_CD_1_TTB0_MASK		0xfffffffffffUL
+
+#define CTXDESC_CD_3_MAIR_SHIFT		0
+
+/* Convert between AArch64 (CPU) TCR format and SMMU CD format */
+#define ARM_SMMU_TCR2CD(tcr, fld)					\
+	(((tcr) >> ARM64_TCR_##fld##_SHIFT & ARM64_TCR_##fld##_MASK)	\
+	 << CTXDESC_CD_0_TCR_##fld##_SHIFT)
+
+/* Command queue */
+#define CMDQ_ENT_DWORDS			2
+#define CMDQ_MAX_SZ_SHIFT		8
+
+#define CMDQ_ERR_SHIFT			24
+#define CMDQ_ERR_MASK			0x7f
+#define CMDQ_ERR_CERROR_NONE_IDX	0
+#define CMDQ_ERR_CERROR_ILL_IDX		1
+#define CMDQ_ERR_CERROR_ABT_IDX		2
+
+#define CMDQ_0_OP_SHIFT			0
+#define CMDQ_0_OP_MASK			0xffUL
+#define CMDQ_0_SSV			(1UL << 11)
+
+#define CMDQ_PREFETCH_0_SID_SHIFT	32
+#define CMDQ_PREFETCH_1_SIZE_SHIFT	0
+#define CMDQ_PREFETCH_1_ADDR_MASK	~0xfffUL
+
+#define CMDQ_CFGI_0_SID_SHIFT		32
+#define CMDQ_CFGI_0_SID_MASK		0xffffffffUL
+#define CMDQ_CFGI_1_LEAF		(1UL << 0)
+#define CMDQ_CFGI_1_RANGE_SHIFT		0
+#define CMDQ_CFGI_1_RANGE_MASK		0x1fUL
+
+#define CMDQ_TLBI_0_VMID_SHIFT		32
+#define CMDQ_TLBI_0_ASID_SHIFT		48
+#define CMDQ_TLBI_1_LEAF		(1UL << 0)
+#define CMDQ_TLBI_1_ADDR_MASK		~0xfffUL
+
+#define CMDQ_PRI_0_SSID_SHIFT		12
+#define CMDQ_PRI_0_SSID_MASK		0xfffffUL
+#define CMDQ_PRI_0_SID_SHIFT		32
+#define CMDQ_PRI_0_SID_MASK		0xffffffffUL
+#define CMDQ_PRI_1_GRPID_SHIFT		0
+#define CMDQ_PRI_1_GRPID_MASK		0x1ffUL
+#define CMDQ_PRI_1_RESP_SHIFT		12
+#define CMDQ_PRI_1_RESP_DENY		(0UL << CMDQ_PRI_1_RESP_SHIFT)
+#define CMDQ_PRI_1_RESP_FAIL		(1UL << CMDQ_PRI_1_RESP_SHIFT)
+#define CMDQ_PRI_1_RESP_SUCC		(2UL << CMDQ_PRI_1_RESP_SHIFT)
+
+#define CMDQ_SYNC_0_CS_SHIFT		12
+#define CMDQ_SYNC_0_CS_NONE		(0UL << CMDQ_SYNC_0_CS_SHIFT)
+#define CMDQ_SYNC_0_CS_SEV		(2UL << CMDQ_SYNC_0_CS_SHIFT)
+
+/* Event queue */
+#define EVTQ_ENT_DWORDS			4
+#define EVTQ_MAX_SZ_SHIFT		7
+
+#define EVTQ_0_ID_SHIFT			0
+#define EVTQ_0_ID_MASK			0xffUL
+
+/* PRI queue */
+#define PRIQ_ENT_DWORDS			2
+#define PRIQ_MAX_SZ_SHIFT		8
+
+#define PRIQ_0_SID_SHIFT		0
+#define PRIQ_0_SID_MASK			0xffffffffUL
+#define PRIQ_0_SSID_SHIFT		32
+#define PRIQ_0_SSID_MASK		0xfffffUL
+#define PRIQ_0_OF			(1UL << 57)
+#define PRIQ_0_PERM_PRIV		(1UL << 58)
+#define PRIQ_0_PERM_EXEC		(1UL << 59)
+#define PRIQ_0_PERM_READ		(1UL << 60)
+#define PRIQ_0_PERM_WRITE		(1UL << 61)
+#define PRIQ_0_PRG_LAST			(1UL << 62)
+#define PRIQ_0_SSID_V			(1UL << 63)
+
+#define PRIQ_1_PRG_IDX_SHIFT		0
+#define PRIQ_1_PRG_IDX_MASK		0x1ffUL
+#define PRIQ_1_ADDR_SHIFT		12
+#define PRIQ_1_ADDR_MASK		0xfffffffffffffUL
+
+/* High-level queue structures */
+#define ARM_SMMU_POLL_TIMEOUT_US	100
+
+static bool disable_bypass;
+module_param_named(disable_bypass, disable_bypass, bool, S_IRUGO);
+MODULE_PARM_DESC(disable_bypass,
+	"Disable bypass streams such that incoming transactions from devices that are not attached to an iommu domain will report an abort back to the device and will not be allowed to pass through the SMMU.");
+
+enum pri_resp {
+	PRI_RESP_DENY,
+	PRI_RESP_FAIL,
+	PRI_RESP_SUCC,
+};
+
+struct arm_smmu_cmdq_ent {
+	/* Common fields */
+	u8				opcode;
+	bool				substream_valid;
+
+	/* Command-specific fields */
+	union {
+		#define CMDQ_OP_PREFETCH_CFG	0x1
+		struct {
+			u32			sid;
+			u8			size;
+			u64			addr;
+		} prefetch;
+
+		#define CMDQ_OP_CFGI_STE	0x3
+		#define CMDQ_OP_CFGI_ALL	0x4
+		struct {
+			u32			sid;
+			union {
+				bool		leaf;
+				u8		span;
+			};
+		} cfgi;
+
+		#define CMDQ_OP_TLBI_NH_ASID	0x11
+		#define CMDQ_OP_TLBI_NH_VA	0x12
+		#define CMDQ_OP_TLBI_EL2_ALL	0x20
+		#define CMDQ_OP_TLBI_S12_VMALL	0x28
+		#define CMDQ_OP_TLBI_S2_IPA	0x2a
+		#define CMDQ_OP_TLBI_NSNH_ALL	0x30
+		struct {
+			u16			asid;
+			u16			vmid;
+			bool			leaf;
+			u64			addr;
+		} tlbi;
+
+		#define CMDQ_OP_PRI_RESP	0x41
+		struct {
+			u32			sid;
+			u32			ssid;
+			u16			grpid;
+			enum pri_resp		resp;
+		} pri;
+
+		#define CMDQ_OP_CMD_SYNC	0x46
+	};
+};
+
+struct arm_smmu_queue {
+	int				irq; /* Wired interrupt */
+
+	__le64				*base;
+	dma_addr_t			base_dma;
+	u64				q_base;
+
+	size_t				ent_dwords;
+	u32				max_n_shift;
+	u32				prod;
+	u32				cons;
+
+	u32 __iomem			*prod_reg;
+	u32 __iomem			*cons_reg;
+};
+
+struct arm_smmu_cmdq {
+	struct arm_smmu_queue		q;
+	spinlock_t			lock;
+};
+
+struct arm_smmu_evtq {
+	struct arm_smmu_queue		q;
+	u32				max_stalls;
+};
+
+struct arm_smmu_priq {
+	struct arm_smmu_queue		q;
+};
+
+/* High-level stream table and context descriptor structures */
+struct arm_smmu_strtab_l1_desc {
+	u8				span;
+
+	__le64				*l2ptr;
+	dma_addr_t			l2ptr_dma;
+};
+
+struct arm_smmu_s1_cfg {
+	__le64				*cdptr;
+	dma_addr_t			cdptr_dma;
+
+	struct arm_smmu_ctx_desc {
+		u16	asid;
+		u64	ttbr;
+		u64	tcr;
+		u64	mair;
+	}				cd;
+};
+
+struct arm_smmu_s2_cfg {
+	u16				vmid;
+	u64				vttbr;
+	u64				vtcr;
+};
+
+struct arm_smmu_strtab_ent {
+	bool				valid;
+
+	bool				bypass;	/* Overrides s1/s2 config */
+	struct arm_smmu_s1_cfg		*s1_cfg;
+	struct arm_smmu_s2_cfg		*s2_cfg;
+};
+
+struct arm_smmu_strtab_cfg {
+	__le64				*strtab;
+	dma_addr_t			strtab_dma;
+	struct arm_smmu_strtab_l1_desc	*l1_desc;
+	unsigned int			num_l1_ents;
+
+	u64				strtab_base;
+	u32				strtab_base_cfg;
+};
+
+/* An SMMUv3 instance */
+struct arm_smmu_device {
+	struct device			*dev;
+	void __iomem			*base;
+
+#define ARM_SMMU_FEAT_2_LVL_STRTAB	(1 << 0)
+#define ARM_SMMU_FEAT_2_LVL_CDTAB	(1 << 1)
+#define ARM_SMMU_FEAT_TT_LE		(1 << 2)
+#define ARM_SMMU_FEAT_TT_BE		(1 << 3)
+#define ARM_SMMU_FEAT_PRI		(1 << 4)
+#define ARM_SMMU_FEAT_ATS		(1 << 5)
+#define ARM_SMMU_FEAT_SEV		(1 << 6)
+#define ARM_SMMU_FEAT_MSI		(1 << 7)
+#define ARM_SMMU_FEAT_COHERENCY		(1 << 8)
+#define ARM_SMMU_FEAT_TRANS_S1		(1 << 9)
+#define ARM_SMMU_FEAT_TRANS_S2		(1 << 10)
+#define ARM_SMMU_FEAT_STALLS		(1 << 11)
+#define ARM_SMMU_FEAT_HYP		(1 << 12)
+	u32				features;
+
+	struct arm_smmu_cmdq		cmdq;
+	struct arm_smmu_evtq		evtq;
+	struct arm_smmu_priq		priq;
+
+	int				gerr_irq;
+
+	unsigned long			ias; /* IPA */
+	unsigned long			oas; /* PA */
+
+#define ARM_SMMU_MAX_ASIDS		(1 << 16)
+	unsigned int			asid_bits;
+	DECLARE_BITMAP(asid_map, ARM_SMMU_MAX_ASIDS);
+
+#define ARM_SMMU_MAX_VMIDS		(1 << 16)
+	unsigned int			vmid_bits;
+	DECLARE_BITMAP(vmid_map, ARM_SMMU_MAX_VMIDS);
+
+	unsigned int			ssid_bits;
+	unsigned int			sid_bits;
+
+	struct arm_smmu_strtab_cfg	strtab_cfg;
+	struct list_head		list;
+};
+
+/* SMMU private data for an IOMMU group */
+struct arm_smmu_group {
+	struct arm_smmu_device		*smmu;
+	struct arm_smmu_domain		*domain;
+	int				num_sids;
+	u32				*sids;
+	struct arm_smmu_strtab_ent	ste;
+};
+
+/* SMMU private data for an IOMMU domain */
+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 mutex			init_mutex; /* Protects smmu pointer */
+
+	struct io_pgtable_ops		*pgtbl_ops;
+	spinlock_t			pgtbl_lock;
+
+	enum arm_smmu_domain_stage	stage;
+	union {
+		struct arm_smmu_s1_cfg	s1_cfg;
+		struct arm_smmu_s2_cfg	s2_cfg;
+	};
+
+	struct iommu_domain		domain;
+};
+
+/* Our list of SMMU instances */
+static DEFINE_SPINLOCK(arm_smmu_devices_lock);
+static LIST_HEAD(arm_smmu_devices);
+
+static struct arm_smmu_domain *to_smmu_domain(struct iommu_domain *dom)
+{
+	return container_of(dom, struct arm_smmu_domain, domain);
+}
+
+/* Low-level queue manipulation functions */
+static bool queue_full(struct arm_smmu_queue *q)
+{
+	return Q_IDX(q, q->prod) == Q_IDX(q, q->cons) &&
+	       Q_WRP(q, q->prod) != Q_WRP(q, q->cons);
+}
+
+static bool queue_empty(struct arm_smmu_queue *q)
+{
+	return Q_IDX(q, q->prod) == Q_IDX(q, q->cons) &&
+	       Q_WRP(q, q->prod) == Q_WRP(q, q->cons);
+}
+
+static void queue_sync_cons(struct arm_smmu_queue *q)
+{
+	q->cons = readl_relaxed(q->cons_reg);
+}
+
+static void queue_inc_cons(struct arm_smmu_queue *q)
+{
+	u32 cons = (Q_WRP(q, q->cons) | Q_IDX(q, q->cons)) + 1;
+
+	q->cons = Q_OVF(q, q->cons) | Q_WRP(q, cons) | Q_IDX(q, cons);
+	writel(q->cons, q->cons_reg);
+}
+
+static int queue_sync_prod(struct arm_smmu_queue *q)
+{
+	int ret = 0;
+	u32 prod = readl_relaxed(q->prod_reg);
+
+	if (Q_OVF(q, prod) != Q_OVF(q, q->prod))
+		ret = -EOVERFLOW;
+
+	q->prod = prod;
+	return ret;
+}
+
+static void queue_inc_prod(struct arm_smmu_queue *q)
+{
+	u32 prod = (Q_WRP(q, q->prod) | Q_IDX(q, q->prod)) + 1;
+
+	q->prod = Q_OVF(q, q->prod) | Q_WRP(q, prod) | Q_IDX(q, prod);
+	writel(q->prod, q->prod_reg);
+}
+
+static bool __queue_cons_before(struct arm_smmu_queue *q, u32 until)
+{
+	if (Q_WRP(q, q->cons) == Q_WRP(q, until))
+		return Q_IDX(q, q->cons) < Q_IDX(q, until);
+
+	return Q_IDX(q, q->cons) >= Q_IDX(q, until);
+}
+
+static int queue_poll_cons(struct arm_smmu_queue *q, u32 until, bool wfe)
+{
+	ktime_t timeout = ktime_add_us(ktime_get(), ARM_SMMU_POLL_TIMEOUT_US);
+
+	while (queue_sync_cons(q), __queue_cons_before(q, until)) {
+		if (ktime_compare(ktime_get(), timeout) > 0)
+			return -ETIMEDOUT;
+
+		if (wfe) {
+			wfe();
+		} else {
+			cpu_relax();
+			udelay(1);
+		}
+	}
+
+	return 0;
+}
+
+static void queue_write(__le64 *dst, u64 *src, size_t n_dwords)
+{
+	int i;
+
+	for (i = 0; i < n_dwords; ++i)
+		*dst++ = cpu_to_le64(*src++);
+}
+
+static int queue_insert_raw(struct arm_smmu_queue *q, u64 *ent)
+{
+	if (queue_full(q))
+		return -ENOSPC;
+
+	queue_write(Q_ENT(q, q->prod), ent, q->ent_dwords);
+	queue_inc_prod(q);
+	return 0;
+}
+
+static void queue_read(__le64 *dst, u64 *src, size_t n_dwords)
+{
+	int i;
+
+	for (i = 0; i < n_dwords; ++i)
+		*dst++ = le64_to_cpu(*src++);
+}
+
+static int queue_remove_raw(struct arm_smmu_queue *q, u64 *ent)
+{
+	if (queue_empty(q))
+		return -EAGAIN;
+
+	queue_read(ent, Q_ENT(q, q->cons), q->ent_dwords);
+	queue_inc_cons(q);
+	return 0;
+}
+
+/* High-level queue accessors */
+static int arm_smmu_cmdq_build_cmd(u64 *cmd, struct arm_smmu_cmdq_ent *ent)
+{
+	memset(cmd, 0, CMDQ_ENT_DWORDS << 3);
+	cmd[0] |= (ent->opcode & CMDQ_0_OP_MASK) << CMDQ_0_OP_SHIFT;
+
+	switch (ent->opcode) {
+	case CMDQ_OP_TLBI_EL2_ALL:
+	case CMDQ_OP_TLBI_NSNH_ALL:
+		break;
+	case CMDQ_OP_PREFETCH_CFG:
+		cmd[0] |= (u64)ent->prefetch.sid << CMDQ_PREFETCH_0_SID_SHIFT;
+		cmd[1] |= ent->prefetch.size << CMDQ_PREFETCH_1_SIZE_SHIFT;
+		cmd[1] |= ent->prefetch.addr & CMDQ_PREFETCH_1_ADDR_MASK;
+		break;
+	case CMDQ_OP_CFGI_STE:
+		cmd[0] |= (u64)ent->cfgi.sid << CMDQ_CFGI_0_SID_SHIFT;
+		cmd[1] |= ent->cfgi.leaf ? CMDQ_CFGI_1_LEAF : 0;
+		break;
+	case CMDQ_OP_CFGI_ALL:
+		/* Cover the entire SID range */
+		cmd[1] |= CMDQ_CFGI_1_RANGE_MASK << CMDQ_CFGI_1_RANGE_SHIFT;
+		break;
+	case CMDQ_OP_TLBI_NH_VA:
+		cmd[0] |= (u64)ent->tlbi.asid << CMDQ_TLBI_0_ASID_SHIFT;
+		/* Fallthrough */
+	case CMDQ_OP_TLBI_S2_IPA:
+		cmd[0] |= (u64)ent->tlbi.vmid << CMDQ_TLBI_0_VMID_SHIFT;
+		cmd[1] |= ent->tlbi.leaf ? CMDQ_TLBI_1_LEAF : 0;
+		cmd[1] |= ent->tlbi.addr & CMDQ_TLBI_1_ADDR_MASK;
+		break;
+	case CMDQ_OP_TLBI_NH_ASID:
+		cmd[0] |= (u64)ent->tlbi.asid << CMDQ_TLBI_0_ASID_SHIFT;
+		/* Fallthrough */
+	case CMDQ_OP_TLBI_S12_VMALL:
+		cmd[0] |= (u64)ent->tlbi.vmid << CMDQ_TLBI_0_VMID_SHIFT;
+		break;
+	case CMDQ_OP_PRI_RESP:
+		cmd[0] |= ent->substream_valid ? CMDQ_0_SSV : 0;
+		cmd[0] |= ent->pri.ssid << CMDQ_PRI_0_SSID_SHIFT;
+		cmd[0] |= (u64)ent->pri.sid << CMDQ_PRI_0_SID_SHIFT;
+		cmd[1] |= ent->pri.grpid << CMDQ_PRI_1_GRPID_SHIFT;
+		switch (ent->pri.resp) {
+		case PRI_RESP_DENY:
+			cmd[1] |= CMDQ_PRI_1_RESP_DENY;
+			break;
+		case PRI_RESP_FAIL:
+			cmd[1] |= CMDQ_PRI_1_RESP_FAIL;
+			break;
+		case PRI_RESP_SUCC:
+			cmd[1] |= CMDQ_PRI_1_RESP_SUCC;
+			break;
+		default:
+			return -EINVAL;
+		}
+		break;
+	case CMDQ_OP_CMD_SYNC:
+		cmd[0] |= CMDQ_SYNC_0_CS_SEV;
+		break;
+	default:
+		return -ENOENT;
+	}
+
+	return 0;
+}
+
+static void arm_smmu_cmdq_skip_err(struct arm_smmu_device *smmu)
+{
+	static const char *cerror_str[] = {
+		[CMDQ_ERR_CERROR_NONE_IDX]	= "No error",
+		[CMDQ_ERR_CERROR_ILL_IDX]	= "Illegal command",
+		[CMDQ_ERR_CERROR_ABT_IDX]	= "Abort on command fetch",
+	};
+
+	int i;
+	u64 cmd[CMDQ_ENT_DWORDS];
+	struct arm_smmu_queue *q = &smmu->cmdq.q;
+	u32 cons = readl_relaxed(q->cons_reg);
+	u32 idx = cons >> CMDQ_ERR_SHIFT & CMDQ_ERR_MASK;
+	struct arm_smmu_cmdq_ent cmd_sync = {
+		.opcode = CMDQ_OP_CMD_SYNC,
+	};
+
+	dev_err(smmu->dev, "CMDQ error (cons 0x%08x): %s\n", cons,
+		cerror_str[idx]);
+
+	switch (idx) {
+	case CMDQ_ERR_CERROR_ILL_IDX:
+		break;
+	case CMDQ_ERR_CERROR_ABT_IDX:
+		dev_err(smmu->dev, "retrying command fetch\n");
+	case CMDQ_ERR_CERROR_NONE_IDX:
+		return;
+	}
+
+	/*
+	 * We may have concurrent producers, so we need to be careful
+	 * not to touch any of the shadow cmdq state.
+	 */
+	queue_read(cmd, Q_ENT(q, idx), q->ent_dwords);
+	dev_err(smmu->dev, "skipping command in error state:\n");
+	for (i = 0; i < ARRAY_SIZE(cmd); ++i)
+		dev_err(smmu->dev, "\t0x%016llx\n", (unsigned long long)cmd[i]);
+
+	/* Convert the erroneous command into a CMD_SYNC */
+	if (arm_smmu_cmdq_build_cmd(cmd, &cmd_sync)) {
+		dev_err(smmu->dev, "failed to convert to CMD_SYNC\n");
+		return;
+	}
+
+	queue_write(cmd, Q_ENT(q, idx), q->ent_dwords);
+}
+
+static void arm_smmu_cmdq_issue_cmd(struct arm_smmu_device *smmu,
+				    struct arm_smmu_cmdq_ent *ent)
+{
+	u32 until;
+	u64 cmd[CMDQ_ENT_DWORDS];
+	bool wfe = !!(smmu->features & ARM_SMMU_FEAT_SEV);
+	struct arm_smmu_queue *q = &smmu->cmdq.q;
+
+	if (arm_smmu_cmdq_build_cmd(cmd, ent)) {
+		dev_warn(smmu->dev, "ignoring unknown CMDQ opcode 0x%x\n",
+			 ent->opcode);
+		return;
+	}
+
+	spin_lock(&smmu->cmdq.lock);
+	while (until = q->prod + 1, queue_insert_raw(q, cmd) == -ENOSPC) {
+		/*
+		 * Keep the queue locked, otherwise the producer could wrap
+		 * twice and we could see a future consumer pointer that looks
+		 * like it's behind us.
+		 */
+		if (queue_poll_cons(q, until, wfe))
+			dev_err_ratelimited(smmu->dev, "CMDQ timeout\n");
+	}
+
+	if (ent->opcode == CMDQ_OP_CMD_SYNC && queue_poll_cons(q, until, wfe))
+		dev_err_ratelimited(smmu->dev, "CMD_SYNC timeout\n");
+	spin_unlock(&smmu->cmdq.lock);
+}
+
+/* Context descriptor manipulation functions */
+static u64 arm_smmu_cpu_tcr_to_cd(u64 tcr)
+{
+	u64 val = 0;
+
+	/* Repack the TCR. Just care about TTBR0 for now */
+	val |= ARM_SMMU_TCR2CD(tcr, T0SZ);
+	val |= ARM_SMMU_TCR2CD(tcr, TG0);
+	val |= ARM_SMMU_TCR2CD(tcr, IRGN0);
+	val |= ARM_SMMU_TCR2CD(tcr, ORGN0);
+	val |= ARM_SMMU_TCR2CD(tcr, SH0);
+	val |= ARM_SMMU_TCR2CD(tcr, EPD0);
+	val |= ARM_SMMU_TCR2CD(tcr, EPD1);
+	val |= ARM_SMMU_TCR2CD(tcr, IPS);
+	val |= ARM_SMMU_TCR2CD(tcr, TBI0);
+
+	return val;
+}
+
+static void arm_smmu_write_ctx_desc(struct arm_smmu_device *smmu,
+				    struct arm_smmu_s1_cfg *cfg)
+{
+	u64 val;
+
+	/*
+	 * We don't need to issue any invalidation here, as we'll invalidate
+	 * the STE when installing the new entry anyway.
+	 */
+	val = arm_smmu_cpu_tcr_to_cd(cfg->cd.tcr) |
+#ifdef __BIG_ENDIAN
+	      CTXDESC_CD_0_ENDI |
+#endif
+	      CTXDESC_CD_0_R | CTXDESC_CD_0_A | CTXDESC_CD_0_ASET_PRIVATE |
+	      CTXDESC_CD_0_AA64 | (u64)cfg->cd.asid << CTXDESC_CD_0_ASID_SHIFT |
+	      CTXDESC_CD_0_V;
+	cfg->cdptr[0] = cpu_to_le64(val);
+
+	val = cfg->cd.ttbr & CTXDESC_CD_1_TTB0_MASK << CTXDESC_CD_1_TTB0_SHIFT;
+	cfg->cdptr[1] = cpu_to_le64(val);
+
+	cfg->cdptr[3] = cpu_to_le64(cfg->cd.mair << CTXDESC_CD_3_MAIR_SHIFT);
+}
+
+/* Stream table manipulation functions */
+static void
+arm_smmu_write_strtab_l1_desc(__le64 *dst, struct arm_smmu_strtab_l1_desc *desc)
+{
+	u64 val = 0;
+
+	val |= (desc->span & STRTAB_L1_DESC_SPAN_MASK)
+		<< STRTAB_L1_DESC_SPAN_SHIFT;
+	val |= desc->l2ptr_dma &
+	       STRTAB_L1_DESC_L2PTR_MASK << STRTAB_L1_DESC_L2PTR_SHIFT;
+
+	*dst = cpu_to_le64(val);
+}
+
+static void arm_smmu_sync_ste_for_sid(struct arm_smmu_device *smmu, u32 sid)
+{
+	struct arm_smmu_cmdq_ent cmd = {
+		.opcode	= CMDQ_OP_CFGI_STE,
+		.cfgi	= {
+			.sid	= sid,
+			.leaf	= true,
+		},
+	};
+
+	arm_smmu_cmdq_issue_cmd(smmu, &cmd);
+	cmd.opcode = CMDQ_OP_CMD_SYNC;
+	arm_smmu_cmdq_issue_cmd(smmu, &cmd);
+}
+
+static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid,
+				      __le64 *dst, struct arm_smmu_strtab_ent *ste)
+{
+	/*
+	 * This is hideously complicated, but we only really care about
+	 * three cases at the moment:
+	 *
+	 * 1. Invalid (all zero) -> bypass  (init)
+	 * 2. Bypass -> translation (attach)
+	 * 3. Translation -> bypass (detach)
+	 *
+	 * Given that we can't update the STE atomically and the SMMU
+	 * doesn't read the thing in a defined order, that leaves us
+	 * with the following maintenance requirements:
+	 *
+	 * 1. Update Config, return (init time STEs aren't live)
+	 * 2. Write everything apart from dword 0, sync, write dword 0, sync
+	 * 3. Update Config, sync
+	 */
+	u64 val = le64_to_cpu(dst[0]);
+	bool ste_live = false;
+	struct arm_smmu_cmdq_ent prefetch_cmd = {
+		.opcode		= CMDQ_OP_PREFETCH_CFG,
+		.prefetch	= {
+			.sid	= sid,
+		},
+	};
+
+	if (val & STRTAB_STE_0_V) {
+		u64 cfg;
+
+		cfg = val & STRTAB_STE_0_CFG_MASK << STRTAB_STE_0_CFG_SHIFT;
+		switch (cfg) {
+		case STRTAB_STE_0_CFG_BYPASS:
+			break;
+		case STRTAB_STE_0_CFG_S1_TRANS:
+		case STRTAB_STE_0_CFG_S2_TRANS:
+			ste_live = true;
+			break;
+		default:
+			BUG(); /* STE corruption */
+		}
+	}
+
+	/* Nuke the existing Config, as we're going to rewrite it */
+	val &= ~(STRTAB_STE_0_CFG_MASK << STRTAB_STE_0_CFG_SHIFT);
+
+	if (ste->valid)
+		val |= STRTAB_STE_0_V;
+	else
+		val &= ~STRTAB_STE_0_V;
+
+	if (ste->bypass) {
+		val |= disable_bypass ? STRTAB_STE_0_CFG_ABORT
+				      : STRTAB_STE_0_CFG_BYPASS;
+		dst[0] = cpu_to_le64(val);
+		dst[2] = 0; /* Nuke the VMID */
+		if (ste_live)
+			arm_smmu_sync_ste_for_sid(smmu, sid);
+		return;
+	}
+
+	if (ste->s1_cfg) {
+		BUG_ON(ste_live);
+		dst[1] = cpu_to_le64(
+			 STRTAB_STE_1_S1C_CACHE_WBRA
+			 << STRTAB_STE_1_S1CIR_SHIFT |
+			 STRTAB_STE_1_S1C_CACHE_WBRA
+			 << STRTAB_STE_1_S1COR_SHIFT |
+			 STRTAB_STE_1_S1C_SH_ISH << STRTAB_STE_1_S1CSH_SHIFT |
+			 STRTAB_STE_1_S1STALLD |
+#ifdef CONFIG_PCI_ATS
+			 STRTAB_STE_1_EATS_TRANS << STRTAB_STE_1_EATS_SHIFT |
+#endif
+			 STRTAB_STE_1_STRW_NSEL1 << STRTAB_STE_1_STRW_SHIFT);
+
+		val |= (ste->s1_cfg->cdptr_dma & STRTAB_STE_0_S1CTXPTR_MASK
+		        << STRTAB_STE_0_S1CTXPTR_SHIFT) |
+			STRTAB_STE_0_CFG_S1_TRANS;
+
+	}
+
+	if (ste->s2_cfg) {
+		BUG_ON(ste_live);
+		dst[2] = cpu_to_le64(
+			 ste->s2_cfg->vmid << STRTAB_STE_2_S2VMID_SHIFT |
+			 (ste->s2_cfg->vtcr & STRTAB_STE_2_VTCR_MASK)
+			  << STRTAB_STE_2_VTCR_SHIFT |
+#ifdef __BIG_ENDIAN
+			 STRTAB_STE_2_S2ENDI |
+#endif
+			 STRTAB_STE_2_S2PTW | STRTAB_STE_2_S2AA64 |
+			 STRTAB_STE_2_S2R);
+
+		dst[3] = cpu_to_le64(ste->s2_cfg->vttbr &
+			 STRTAB_STE_3_S2TTB_MASK << STRTAB_STE_3_S2TTB_SHIFT);
+
+		val |= STRTAB_STE_0_CFG_S2_TRANS;
+	}
+
+	arm_smmu_sync_ste_for_sid(smmu, sid);
+	dst[0] = cpu_to_le64(val);
+	arm_smmu_sync_ste_for_sid(smmu, sid);
+
+	/* It's likely that we'll want to use the new STE soon */
+	arm_smmu_cmdq_issue_cmd(smmu, &prefetch_cmd);
+}
+
+static void arm_smmu_init_bypass_stes(u64 *strtab, unsigned int nent)
+{
+	unsigned int i;
+	struct arm_smmu_strtab_ent ste = {
+		.valid	= true,
+		.bypass	= true,
+	};
+
+	for (i = 0; i < nent; ++i) {
+		arm_smmu_write_strtab_ent(NULL, -1, strtab, &ste);
+		strtab += STRTAB_STE_DWORDS;
+	}
+}
+
+static int arm_smmu_init_l2_strtab(struct arm_smmu_device *smmu, u32 sid)
+{
+	size_t size;
+	void *strtab;
+	struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg;
+	struct arm_smmu_strtab_l1_desc *desc = &cfg->l1_desc[sid >> STRTAB_SPLIT];
+
+	if (desc->l2ptr)
+		return 0;
+
+	size = 1 << (STRTAB_SPLIT + ilog2(STRTAB_STE_DWORDS) + 3);
+	strtab = &cfg->strtab[sid >> STRTAB_SPLIT << STRTAB_L1_DESC_DWORDS];
+
+	desc->span = STRTAB_SPLIT + 1;
+	desc->l2ptr = dma_zalloc_coherent(smmu->dev, size, &desc->l2ptr_dma,
+					  GFP_KERNEL);
+	if (!desc->l2ptr) {
+		dev_err(smmu->dev,
+			"failed to allocate l2 stream table for SID %u\n",
+			sid);
+		return -ENOMEM;
+	}
+
+	arm_smmu_init_bypass_stes(desc->l2ptr, 1 << STRTAB_SPLIT);
+	arm_smmu_write_strtab_l1_desc(strtab, desc);
+	return 0;
+}
+
+/* IRQ and event handlers */
+static irqreturn_t arm_smmu_evtq_thread(int irq, void *dev)
+{
+	int i;
+	struct arm_smmu_device *smmu = dev;
+	struct arm_smmu_queue *q = &smmu->evtq.q;
+	u64 evt[EVTQ_ENT_DWORDS];
+
+	while (!queue_remove_raw(q, evt)) {
+		u8 id = evt[0] >> EVTQ_0_ID_SHIFT & EVTQ_0_ID_MASK;
+
+		dev_info(smmu->dev, "event 0x%02x received:\n", id);
+		for (i = 0; i < ARRAY_SIZE(evt); ++i)
+			dev_info(smmu->dev, "\t0x%016llx\n",
+				 (unsigned long long)evt[i]);
+	}
+
+	/* Sync our overflow flag, as we believe we're up to speed */
+	q->cons = Q_OVF(q, q->prod) | Q_WRP(q, q->cons) | Q_IDX(q, q->cons);
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t arm_smmu_evtq_handler(int irq, void *dev)
+{
+	irqreturn_t ret = IRQ_WAKE_THREAD;
+	struct arm_smmu_device *smmu = dev;
+	struct arm_smmu_queue *q = &smmu->evtq.q;
+
+	/*
+	 * Not much we can do on overflow, so scream and pretend we're
+	 * trying harder.
+	 */
+	if (queue_sync_prod(q) == -EOVERFLOW)
+		dev_err(smmu->dev, "EVTQ overflow detected -- events lost\n");
+	else if (queue_empty(q))
+		ret = IRQ_NONE;
+
+	return ret;
+}
+
+static irqreturn_t arm_smmu_priq_thread(int irq, void *dev)
+{
+	struct arm_smmu_device *smmu = dev;
+	struct arm_smmu_queue *q = &smmu->priq.q;
+	u64 evt[PRIQ_ENT_DWORDS];