Merge tag 'arm-smmu-updates' of git://git.kernel.org/pub/scm/linux/kernel/git/will/linux into arm/smmu

Arm SMMU updates for 5.6

- Support for building, and {un,}loading the SMMU drivers as modules

- Minor cleanups

- SMMUv3:
  * Non-critical fix to encoding of TLBI_NH_VA invalidation command
  * Fix broken sanity check on size of MMIO resource during probe
  * Support for Substream IDs which will soon be provided by PCI PASIDs

- io-pgtable:
  * Finish off the TTBR1 preparation work partially merged last cycle
  * Ensure correct memory attributes for non-cacheable mappings

- SMMU:
  * Namespace public #defines to avoid collisions with arch/arm64/
  * Avoid using valid SMR register when probing mask size

12 files changed, 749 insertions, 406 deletions

diff --git a/drivers/iommu/arm-smmu-impl.c b/drivers/iommu/arm-smmu-impl.c
index b2fe72a8f019..74d97a886e93 100644
--- a/drivers/iommu/arm-smmu-impl.c
+++ b/drivers/iommu/arm-smmu-impl.c
@@ -119,7 +119,7 @@ int arm_mmu500_reset(struct arm_smmu_device *smmu)
 	 * Secure has also cleared SACR.CACHE_LOCK for this to take effect...
 	 */
 	reg = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_ID7);
-	major = FIELD_GET(ID7_MAJOR, reg);
+	major = FIELD_GET(ARM_SMMU_ID7_MAJOR, reg);
 	reg = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_sACR);
 	if (major >= 2)
 		reg &= ~ARM_MMU500_ACR_CACHE_LOCK;
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index 03dc97842875..5e04c1f3992a 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -223,9 +223,15 @@
 
 #define STRTAB_STE_0_S1FMT		GENMASK_ULL(5, 4)
 #define STRTAB_STE_0_S1FMT_LINEAR	0
+#define STRTAB_STE_0_S1FMT_64K_L2	2
 #define STRTAB_STE_0_S1CTXPTR_MASK	GENMASK_ULL(51, 6)
 #define STRTAB_STE_0_S1CDMAX		GENMASK_ULL(63, 59)
 
+#define STRTAB_STE_1_S1DSS		GENMASK_ULL(1, 0)
+#define STRTAB_STE_1_S1DSS_TERMINATE	0x0
+#define STRTAB_STE_1_S1DSS_BYPASS	0x1
+#define STRTAB_STE_1_S1DSS_SSID0	0x2
+
 #define STRTAB_STE_1_S1C_CACHE_NC	0UL
 #define STRTAB_STE_1_S1C_CACHE_WBRA	1UL
 #define STRTAB_STE_1_S1C_CACHE_WT	2UL
@@ -250,6 +256,13 @@
 
 #define STRTAB_STE_2_S2VMID		GENMASK_ULL(15, 0)
 #define STRTAB_STE_2_VTCR		GENMASK_ULL(50, 32)
+#define STRTAB_STE_2_VTCR_S2T0SZ	GENMASK_ULL(5, 0)
+#define STRTAB_STE_2_VTCR_S2SL0		GENMASK_ULL(7, 6)
+#define STRTAB_STE_2_VTCR_S2IR0		GENMASK_ULL(9, 8)
+#define STRTAB_STE_2_VTCR_S2OR0		GENMASK_ULL(11, 10)
+#define STRTAB_STE_2_VTCR_S2SH0		GENMASK_ULL(13, 12)
+#define STRTAB_STE_2_VTCR_S2TG		GENMASK_ULL(15, 14)
+#define STRTAB_STE_2_VTCR_S2PS		GENMASK_ULL(18, 16)
 #define STRTAB_STE_2_S2AA64		(1UL << 51)
 #define STRTAB_STE_2_S2ENDI		(1UL << 52)
 #define STRTAB_STE_2_S2PTW		(1UL << 54)
@@ -257,30 +270,34 @@
 
 #define STRTAB_STE_3_S2TTB_MASK		GENMASK_ULL(51, 4)
 
-/* Context descriptor (stage-1 only) */
+/*
+ * Context descriptors.
+ *
+ * Linear: when less than 1024 SSIDs are supported
+ * 2lvl: at most 1024 L1 entries,
+ *       1024 lazy entries per table.
+ */
+#define CTXDESC_SPLIT			10
+#define CTXDESC_L2_ENTRIES		(1 << CTXDESC_SPLIT)
+
+#define CTXDESC_L1_DESC_DWORDS		1
+#define CTXDESC_L1_DESC_V		(1UL << 0)
+#define CTXDESC_L1_DESC_L2PTR_MASK	GENMASK_ULL(51, 12)
+
 #define CTXDESC_CD_DWORDS		8
 #define CTXDESC_CD_0_TCR_T0SZ		GENMASK_ULL(5, 0)
-#define ARM64_TCR_T0SZ			GENMASK_ULL(5, 0)
 #define CTXDESC_CD_0_TCR_TG0		GENMASK_ULL(7, 6)
-#define ARM64_TCR_TG0			GENMASK_ULL(15, 14)
 #define CTXDESC_CD_0_TCR_IRGN0		GENMASK_ULL(9, 8)
-#define ARM64_TCR_IRGN0			GENMASK_ULL(9, 8)
 #define CTXDESC_CD_0_TCR_ORGN0		GENMASK_ULL(11, 10)
-#define ARM64_TCR_ORGN0			GENMASK_ULL(11, 10)
 #define CTXDESC_CD_0_TCR_SH0		GENMASK_ULL(13, 12)
-#define ARM64_TCR_SH0			GENMASK_ULL(13, 12)
 #define CTXDESC_CD_0_TCR_EPD0		(1ULL << 14)
-#define ARM64_TCR_EPD0			(1ULL << 7)
 #define CTXDESC_CD_0_TCR_EPD1		(1ULL << 30)
-#define ARM64_TCR_EPD1			(1ULL << 23)
 
 #define CTXDESC_CD_0_ENDI		(1UL << 15)
 #define CTXDESC_CD_0_V			(1UL << 31)
 
 #define CTXDESC_CD_0_TCR_IPS		GENMASK_ULL(34, 32)
-#define ARM64_TCR_IPS			GENMASK_ULL(34, 32)
 #define CTXDESC_CD_0_TCR_TBI0		(1ULL << 38)
-#define ARM64_TCR_TBI0			(1ULL << 37)
 
 #define CTXDESC_CD_0_AA64		(1UL << 41)
 #define CTXDESC_CD_0_S			(1UL << 44)
@@ -291,9 +308,11 @@
 
 #define CTXDESC_CD_1_TTB0_MASK		GENMASK_ULL(51, 4)
 
-/* Convert between AArch64 (CPU) TCR format and SMMU CD format */
-#define ARM_SMMU_TCR2CD(tcr, fld)	FIELD_PREP(CTXDESC_CD_0_TCR_##fld, \
-					FIELD_GET(ARM64_TCR_##fld, tcr))
+/*
+ * When the SMMU only supports linear context descriptor tables, pick a
+ * reasonable size limit (64kB).
+ */
+#define CTXDESC_LINEAR_CDMAX		ilog2(SZ_64K / (CTXDESC_CD_DWORDS << 3))
 
 /* Command queue */
 #define CMDQ_ENT_SZ_SHIFT		4
@@ -322,6 +341,7 @@
 #define CMDQ_PREFETCH_1_SIZE		GENMASK_ULL(4, 0)
 #define CMDQ_PREFETCH_1_ADDR_MASK	GENMASK_ULL(63, 12)
 
+#define CMDQ_CFGI_0_SSID		GENMASK_ULL(31, 12)
 #define CMDQ_CFGI_0_SID			GENMASK_ULL(63, 32)
 #define CMDQ_CFGI_1_LEAF		(1UL << 0)
 #define CMDQ_CFGI_1_RANGE		GENMASK_ULL(4, 0)
@@ -435,8 +455,11 @@ struct arm_smmu_cmdq_ent {
 
 		#define CMDQ_OP_CFGI_STE	0x3
 		#define CMDQ_OP_CFGI_ALL	0x4
+		#define CMDQ_OP_CFGI_CD		0x5
+		#define CMDQ_OP_CFGI_CD_ALL	0x6
 		struct {
 			u32			sid;
+			u32			ssid;
 			union {
 				bool		leaf;
 				u8		span;
@@ -542,16 +565,30 @@ struct arm_smmu_strtab_l1_desc {
 	dma_addr_t			l2ptr_dma;
 };
 
+struct arm_smmu_ctx_desc {
+	u16				asid;
+	u64				ttbr;
+	u64				tcr;
+	u64				mair;
+};
+
+struct arm_smmu_l1_ctx_desc {
+	__le64				*l2ptr;
+	dma_addr_t			l2ptr_dma;
+};
+
+struct arm_smmu_ctx_desc_cfg {
+	__le64				*cdtab;
+	dma_addr_t			cdtab_dma;
+	struct arm_smmu_l1_ctx_desc	*l1_desc;
+	unsigned int			num_l1_ents;
+};
+
 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_ctx_desc_cfg	cdcfg;
+	struct arm_smmu_ctx_desc	cd;
+	u8				s1fmt;
+	u8				s1cdmax;
 };
 
 struct arm_smmu_s2_cfg {
@@ -633,6 +670,7 @@ struct arm_smmu_master {
 	u32				*sids;
 	unsigned int			num_sids;
 	bool				ats_enabled;
+	unsigned int			ssid_bits;
 };
 
 /* SMMU private data for an IOMMU domain */
@@ -842,15 +880,22 @@ static int arm_smmu_cmdq_build_cmd(u64 *cmd, struct arm_smmu_cmdq_ent *ent)
 		cmd[1] |= FIELD_PREP(CMDQ_PREFETCH_1_SIZE, ent->prefetch.size);
 		cmd[1] |= ent->prefetch.addr & CMDQ_PREFETCH_1_ADDR_MASK;
 		break;
+	case CMDQ_OP_CFGI_CD:
+		cmd[0] |= FIELD_PREP(CMDQ_CFGI_0_SSID, ent->cfgi.ssid);
+		/* Fallthrough */
 	case CMDQ_OP_CFGI_STE:
 		cmd[0] |= FIELD_PREP(CMDQ_CFGI_0_SID, ent->cfgi.sid);
 		cmd[1] |= FIELD_PREP(CMDQ_CFGI_1_LEAF, ent->cfgi.leaf);
 		break;
+	case CMDQ_OP_CFGI_CD_ALL:
+		cmd[0] |= FIELD_PREP(CMDQ_CFGI_0_SID, ent->cfgi.sid);
+		break;
 	case CMDQ_OP_CFGI_ALL:
 		/* Cover the entire SID range */
 		cmd[1] |= FIELD_PREP(CMDQ_CFGI_1_RANGE, 31);
 		break;
 	case CMDQ_OP_TLBI_NH_VA:
+		cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_VMID, ent->tlbi.vmid);
 		cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_ASID, ent->tlbi.asid);
 		cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_LEAF, ent->tlbi.leaf);
 		cmd[1] |= ent->tlbi.addr & CMDQ_TLBI_1_VA_MASK;
@@ -1438,50 +1483,238 @@ static int arm_smmu_cmdq_issue_sync(struct arm_smmu_device *smmu)
 }
 
 /* Context descriptor manipulation functions */
-static u64 arm_smmu_cpu_tcr_to_cd(u64 tcr)
+static void arm_smmu_sync_cd(struct arm_smmu_domain *smmu_domain,
+			     int ssid, bool leaf)
 {
-	u64 val = 0;
+	size_t i;
+	unsigned long flags;
+	struct arm_smmu_master *master;
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	struct arm_smmu_cmdq_ent cmd = {
+		.opcode	= CMDQ_OP_CFGI_CD,
+		.cfgi	= {
+			.ssid	= ssid,
+			.leaf	= leaf,
+		},
+	};
+
+	spin_lock_irqsave(&smmu_domain->devices_lock, flags);
+	list_for_each_entry(master, &smmu_domain->devices, domain_head) {
+		for (i = 0; i < master->num_sids; i++) {
+			cmd.cfgi.sid = master->sids[i];
+			arm_smmu_cmdq_issue_cmd(smmu, &cmd);
+		}
+	}
+	spin_unlock_irqrestore(&smmu_domain->devices_lock, flags);
 
-	/* 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);
+	arm_smmu_cmdq_issue_sync(smmu);
+}
 
-	return val;
+static int arm_smmu_alloc_cd_leaf_table(struct arm_smmu_device *smmu,
+					struct arm_smmu_l1_ctx_desc *l1_desc)
+{
+	size_t size = CTXDESC_L2_ENTRIES * (CTXDESC_CD_DWORDS << 3);
+
+	l1_desc->l2ptr = dmam_alloc_coherent(smmu->dev, size,
+					     &l1_desc->l2ptr_dma, GFP_KERNEL);
+	if (!l1_desc->l2ptr) {
+		dev_warn(smmu->dev,
+			 "failed to allocate context descriptor table\n");
+		return -ENOMEM;
+	}
+	return 0;
 }
 
-static void arm_smmu_write_ctx_desc(struct arm_smmu_device *smmu,
-				    struct arm_smmu_s1_cfg *cfg)
+static void arm_smmu_write_cd_l1_desc(__le64 *dst,
+				      struct arm_smmu_l1_ctx_desc *l1_desc)
 {
-	u64 val;
+	u64 val = (l1_desc->l2ptr_dma & CTXDESC_L1_DESC_L2PTR_MASK) |
+		  CTXDESC_L1_DESC_V;
+
+	WRITE_ONCE(*dst, cpu_to_le64(val));
+}
+
+static __le64 *arm_smmu_get_cd_ptr(struct arm_smmu_domain *smmu_domain,
+				   u32 ssid)
+{
+	__le64 *l1ptr;
+	unsigned int idx;
+	struct arm_smmu_l1_ctx_desc *l1_desc;
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	struct arm_smmu_ctx_desc_cfg *cdcfg = &smmu_domain->s1_cfg.cdcfg;
+
+	if (smmu_domain->s1_cfg.s1fmt == STRTAB_STE_0_S1FMT_LINEAR)
+		return cdcfg->cdtab + ssid * CTXDESC_CD_DWORDS;
+
+	idx = ssid >> CTXDESC_SPLIT;
+	l1_desc = &cdcfg->l1_desc[idx];
+	if (!l1_desc->l2ptr) {
+		if (arm_smmu_alloc_cd_leaf_table(smmu, l1_desc))
+			return NULL;
+
+		l1ptr = cdcfg->cdtab + idx * CTXDESC_L1_DESC_DWORDS;
+		arm_smmu_write_cd_l1_desc(l1ptr, l1_desc);
+		/* An invalid L1CD can be cached */
+		arm_smmu_sync_cd(smmu_domain, ssid, false);
+	}
+	idx = ssid & (CTXDESC_L2_ENTRIES - 1);
+	return l1_desc->l2ptr + idx * CTXDESC_CD_DWORDS;
+}
 
+static int arm_smmu_write_ctx_desc(struct arm_smmu_domain *smmu_domain,
+				   int ssid, struct arm_smmu_ctx_desc *cd)
+{
 	/*
-	 * We don't need to issue any invalidation here, as we'll invalidate
-	 * the STE when installing the new entry anyway.
+	 * This function handles the following cases:
+	 *
+	 * (1) Install primary CD, for normal DMA traffic (SSID = 0).
+	 * (2) Install a secondary CD, for SID+SSID traffic.
+	 * (3) Update ASID of a CD. Atomically write the first 64 bits of the
+	 *     CD, then invalidate the old entry and mappings.
+	 * (4) Remove a secondary CD.
 	 */
-	val = arm_smmu_cpu_tcr_to_cd(cfg->cd.tcr) |
+	u64 val;
+	bool cd_live;
+	__le64 *cdptr;
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+
+	if (WARN_ON(ssid >= (1 << smmu_domain->s1_cfg.s1cdmax)))
+		return -E2BIG;
+
+	cdptr = arm_smmu_get_cd_ptr(smmu_domain, ssid);
+	if (!cdptr)
+		return -ENOMEM;
+
+	val = le64_to_cpu(cdptr[0]);
+	cd_live = !!(val & CTXDESC_CD_0_V);
+
+	if (!cd) { /* (4) */
+		val = 0;
+	} else if (cd_live) { /* (3) */
+		val &= ~CTXDESC_CD_0_ASID;
+		val |= FIELD_PREP(CTXDESC_CD_0_ASID, cd->asid);
+		/*
+		 * Until CD+TLB invalidation, both ASIDs may be used for tagging
+		 * this substream's traffic
+		 */
+	} else { /* (1) and (2) */
+		cdptr[1] = cpu_to_le64(cd->ttbr & CTXDESC_CD_1_TTB0_MASK);
+		cdptr[2] = 0;
+		cdptr[3] = cpu_to_le64(cd->mair);
+
+		/*
+		 * STE is live, and the SMMU might read dwords of this CD in any
+		 * order. Ensure that it observes valid values before reading
+		 * V=1.
+		 */
+		arm_smmu_sync_cd(smmu_domain, ssid, true);
+
+		val = cd->tcr |
 #ifdef __BIG_ENDIAN
-	      CTXDESC_CD_0_ENDI |
+			CTXDESC_CD_0_ENDI |
 #endif
-	      CTXDESC_CD_0_R | CTXDESC_CD_0_A | CTXDESC_CD_0_ASET |
-	      CTXDESC_CD_0_AA64 | FIELD_PREP(CTXDESC_CD_0_ASID, cfg->cd.asid) |
-	      CTXDESC_CD_0_V;
+			CTXDESC_CD_0_R | CTXDESC_CD_0_A | CTXDESC_CD_0_ASET |
+			CTXDESC_CD_0_AA64 |
+			FIELD_PREP(CTXDESC_CD_0_ASID, cd->asid) |
+			CTXDESC_CD_0_V;
+
+		/* STALL_MODEL==0b10 && CD.S==0 is ILLEGAL */
+		if (smmu->features & ARM_SMMU_FEAT_STALL_FORCE)
+			val |= CTXDESC_CD_0_S;
+	}
+
+	/*
+	 * The SMMU accesses 64-bit values atomically. See IHI0070Ca 3.21.3
+	 * "Configuration structures and configuration invalidation completion"
+	 *
+	 *   The size of single-copy atomic reads made by the SMMU is
+	 *   IMPLEMENTATION DEFINED but must be at least 64 bits. Any single
+	 *   field within an aligned 64-bit span of a structure can be altered
+	 *   without first making the structure invalid.
+	 */
+	WRITE_ONCE(cdptr[0], cpu_to_le64(val));
+	arm_smmu_sync_cd(smmu_domain, ssid, true);
+	return 0;
+}
+
+static int arm_smmu_alloc_cd_tables(struct arm_smmu_domain *smmu_domain)
+{
+	int ret;
+	size_t l1size;
+	size_t max_contexts;
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	struct arm_smmu_s1_cfg *cfg = &smmu_domain->s1_cfg;
+	struct arm_smmu_ctx_desc_cfg *cdcfg = &cfg->cdcfg;
 
-	/* STALL_MODEL==0b10 && CD.S==0 is ILLEGAL */
-	if (smmu->features & ARM_SMMU_FEAT_STALL_FORCE)
-		val |= CTXDESC_CD_0_S;
+	max_contexts = 1 << cfg->s1cdmax;
 
-	cfg->cdptr[0] = cpu_to_le64(val);
+	if (!(smmu->features & ARM_SMMU_FEAT_2_LVL_CDTAB) ||
+	    max_contexts <= CTXDESC_L2_ENTRIES) {
+		cfg->s1fmt = STRTAB_STE_0_S1FMT_LINEAR;
+		cdcfg->num_l1_ents = max_contexts;
 
-	val = cfg->cd.ttbr & CTXDESC_CD_1_TTB0_MASK;
-	cfg->cdptr[1] = cpu_to_le64(val);
+		l1size = max_contexts * (CTXDESC_CD_DWORDS << 3);
+	} else {
+		cfg->s1fmt = STRTAB_STE_0_S1FMT_64K_L2;
+		cdcfg->num_l1_ents = DIV_ROUND_UP(max_contexts,
+						  CTXDESC_L2_ENTRIES);
+
+		cdcfg->l1_desc = devm_kcalloc(smmu->dev, cdcfg->num_l1_ents,
+					      sizeof(*cdcfg->l1_desc),
+					      GFP_KERNEL);
+		if (!cdcfg->l1_desc)
+			return -ENOMEM;
+
+		l1size = cdcfg->num_l1_ents * (CTXDESC_L1_DESC_DWORDS << 3);
+	}
+
+	cdcfg->cdtab = dmam_alloc_coherent(smmu->dev, l1size, &cdcfg->cdtab_dma,
+					   GFP_KERNEL);
+	if (!cdcfg->cdtab) {
+		dev_warn(smmu->dev, "failed to allocate context descriptor\n");
+		ret = -ENOMEM;
+		goto err_free_l1;
+	}
+
+	return 0;
+
+err_free_l1:
+	if (cdcfg->l1_desc) {
+		devm_kfree(smmu->dev, cdcfg->l1_desc);
+		cdcfg->l1_desc = NULL;
+	}
+	return ret;
+}
+
+static void arm_smmu_free_cd_tables(struct arm_smmu_domain *smmu_domain)
+{
+	int i;
+	size_t size, l1size;
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	struct arm_smmu_ctx_desc_cfg *cdcfg = &smmu_domain->s1_cfg.cdcfg;
+
+	if (cdcfg->l1_desc) {
+		size = CTXDESC_L2_ENTRIES * (CTXDESC_CD_DWORDS << 3);
+
+		for (i = 0; i < cdcfg->num_l1_ents; i++) {
+			if (!cdcfg->l1_desc[i].l2ptr)
+				continue;
+
+			dmam_free_coherent(smmu->dev, size,
+					   cdcfg->l1_desc[i].l2ptr,
+					   cdcfg->l1_desc[i].l2ptr_dma);
+		}
+		devm_kfree(smmu->dev, cdcfg->l1_desc);
+		cdcfg->l1_desc = NULL;
+
+		l1size = cdcfg->num_l1_ents * (CTXDESC_L1_DESC_DWORDS << 3);
+	} else {
+		l1size = cdcfg->num_l1_ents * (CTXDESC_CD_DWORDS << 3);
+	}
 
-	cfg->cdptr[3] = cpu_to_le64(cfg->cd.mair);
+	dmam_free_coherent(smmu->dev, l1size, cdcfg->cdtab, cdcfg->cdtab_dma);
+	cdcfg->cdtab_dma = 0;
+	cdcfg->cdtab = NULL;
 }
 
 /* Stream table manipulation functions */
@@ -1603,6 +1836,7 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 	if (s1_cfg) {
 		BUG_ON(ste_live);
 		dst[1] = cpu_to_le64(
+			 FIELD_PREP(STRTAB_STE_1_S1DSS, STRTAB_STE_1_S1DSS_SSID0) |
 			 FIELD_PREP(STRTAB_STE_1_S1CIR, STRTAB_STE_1_S1C_CACHE_WBRA) |
 			 FIELD_PREP(STRTAB_STE_1_S1COR, STRTAB_STE_1_S1C_CACHE_WBRA) |
 			 FIELD_PREP(STRTAB_STE_1_S1CSH, ARM_SMMU_SH_ISH) |
@@ -1612,8 +1846,10 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 		   !(smmu->features & ARM_SMMU_FEAT_STALL_FORCE))
 			dst[1] |= cpu_to_le64(STRTAB_STE_1_S1STALLD);
 
-		val |= (s1_cfg->cdptr_dma & STRTAB_STE_0_S1CTXPTR_MASK) |
-			FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_S1_TRANS);
+		val |= (s1_cfg->cdcfg.cdtab_dma & STRTAB_STE_0_S1CTXPTR_MASK) |
+			FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_S1_TRANS) |
+			FIELD_PREP(STRTAB_STE_0_S1CDMAX, s1_cfg->s1cdmax) |
+			FIELD_PREP(STRTAB_STE_0_S1FMT, s1_cfg->s1fmt);
 	}
 
 	if (s2_cfg) {
@@ -1637,7 +1873,8 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 						 STRTAB_STE_1_EATS_TRANS));
 
 	arm_smmu_sync_ste_for_sid(smmu, sid);
-	dst[0] = cpu_to_le64(val);
+	/* See comment in arm_smmu_write_ctx_desc() */
+	WRITE_ONCE(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 */
@@ -1670,7 +1907,7 @@ static int arm_smmu_init_l2_strtab(struct arm_smmu_device *smmu, u32 sid)
 
 	desc->span = STRTAB_SPLIT + 1;
 	desc->l2ptr = dmam_alloc_coherent(smmu->dev, size, &desc->l2ptr_dma,
-					  GFP_KERNEL | __GFP_ZERO);
+					  GFP_KERNEL);
 	if (!desc->l2ptr) {
 		dev_err(smmu->dev,
 			"failed to allocate l2 stream table for SID %u\n",
@@ -2126,12 +2363,8 @@ static void arm_smmu_domain_free(struct iommu_domain *domain)
 	if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) {
 		struct arm_smmu_s1_cfg *cfg = &smmu_domain->s1_cfg;
 
-		if (cfg->cdptr) {
-			dmam_free_coherent(smmu_domain->smmu->dev,
-					   CTXDESC_CD_DWORDS << 3,
-					   cfg->cdptr,
-					   cfg->cdptr_dma);
-
+		if (cfg->cdcfg.cdtab) {
+			arm_smmu_free_cd_tables(smmu_domain);
 			arm_smmu_bitmap_free(smmu->asid_map, cfg->cd.asid);
 		}
 	} else {
@@ -2144,55 +2377,82 @@ static void arm_smmu_domain_free(struct iommu_domain *domain)
 }
 
 static int arm_smmu_domain_finalise_s1(struct arm_smmu_domain *smmu_domain,
+				       struct arm_smmu_master *master,
 				       struct io_pgtable_cfg *pgtbl_cfg)
 {
 	int ret;
 	int asid;
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
 	struct arm_smmu_s1_cfg *cfg = &smmu_domain->s1_cfg;
+	typeof(&pgtbl_cfg->arm_lpae_s1_cfg.tcr) tcr = &pgtbl_cfg->arm_lpae_s1_cfg.tcr;
 
 	asid = arm_smmu_bitmap_alloc(smmu->asid_map, smmu->asid_bits);
 	if (asid < 0)
 		return asid;
 
-	cfg->cdptr = dmam_alloc_coherent(smmu->dev, CTXDESC_CD_DWORDS << 3,
-					 &cfg->cdptr_dma,
-					 GFP_KERNEL | __GFP_ZERO);
-	if (!cfg->cdptr) {
-		dev_warn(smmu->dev, "failed to allocate context descriptor\n");
-		ret = -ENOMEM;
+	cfg->s1cdmax = master->ssid_bits;
+
+	ret = arm_smmu_alloc_cd_tables(smmu_domain);
+	if (ret)
 		goto out_free_asid;
-	}
 
 	cfg->cd.asid	= (u16)asid;
-	cfg->cd.ttbr	= pgtbl_cfg->arm_lpae_s1_cfg.ttbr[0];
-	cfg->cd.tcr	= pgtbl_cfg->arm_lpae_s1_cfg.tcr;
+	cfg->cd.ttbr	= pgtbl_cfg->arm_lpae_s1_cfg.ttbr;
+	cfg->cd.tcr	= FIELD_PREP(CTXDESC_CD_0_TCR_T0SZ, tcr->tsz) |
+			  FIELD_PREP(CTXDESC_CD_0_TCR_TG0, tcr->tg) |
+			  FIELD_PREP(CTXDESC_CD_0_TCR_IRGN0, tcr->irgn) |
+			  FIELD_PREP(CTXDESC_CD_0_TCR_ORGN0, tcr->orgn) |
+			  FIELD_PREP(CTXDESC_CD_0_TCR_SH0, tcr->sh) |
+			  FIELD_PREP(CTXDESC_CD_0_TCR_IPS, tcr->ips) |
+			  CTXDESC_CD_0_TCR_EPD1 | CTXDESC_CD_0_AA64;
 	cfg->cd.mair	= pgtbl_cfg->arm_lpae_s1_cfg.mair;
+
+	/*
+	 * Note that this will end up calling arm_smmu_sync_cd() before
+	 * the master has been added to the devices list for this domain.
+	 * This isn't an issue because the STE hasn't been installed yet.
+	 */
+	ret = arm_smmu_write_ctx_desc(smmu_domain, 0, &cfg->cd);
+	if (ret)
+		goto out_free_cd_tables;
+
 	return 0;
 
+out_free_cd_tables:
+	arm_smmu_free_cd_tables(smmu_domain);
 out_free_asid:
 	arm_smmu_bitmap_free(smmu->asid_map, asid);
 	return ret;
 }
 
 static int arm_smmu_domain_finalise_s2(struct arm_smmu_domain *smmu_domain,
+				       struct arm_smmu_master *master,
 				       struct io_pgtable_cfg *pgtbl_cfg)
 {
 	int vmid;
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
 	struct arm_smmu_s2_cfg *cfg = &smmu_domain->s2_cfg;
+	typeof(&pgtbl_cfg->arm_lpae_s2_cfg.vtcr) vtcr;
 
 	vmid = arm_smmu_bitmap_alloc(smmu->vmid_map, smmu->vmid_bits);
 	if (vmid < 0)
 		return vmid;
 
+	vtcr = &pgtbl_cfg->arm_lpae_s2_cfg.vtcr;
 	cfg->vmid	= (u16)vmid;
 	cfg->vttbr	= pgtbl_cfg->arm_lpae_s2_cfg.vttbr;
-	cfg->vtcr	= pgtbl_cfg->arm_lpae_s2_cfg.vtcr;
+	cfg->vtcr	= FIELD_PREP(STRTAB_STE_2_VTCR_S2T0SZ, vtcr->tsz) |
+			  FIELD_PREP(STRTAB_STE_2_VTCR_S2SL0, vtcr->sl) |
+			  FIELD_PREP(STRTAB_STE_2_VTCR_S2IR0, vtcr->irgn) |
+			  FIELD_PREP(STRTAB_STE_2_VTCR_S2OR0, vtcr->orgn) |
+			  FIELD_PREP(STRTAB_STE_2_VTCR_S2SH0, vtcr->sh) |
+			  FIELD_PREP(STRTAB_STE_2_VTCR_S2TG, vtcr->tg) |
+			  FIELD_PREP(STRTAB_STE_2_VTCR_S2PS, vtcr->ps);
 	return 0;
 }
 
-static int arm_smmu_domain_finalise(struct iommu_domain *domain)
+static int arm_smmu_domain_finalise(struct iommu_domain *domain,
+				    struct arm_smmu_master *master)
 {
 	int ret;
 	unsigned long ias, oas;
@@ -2200,6 +2460,7 @@ static int arm_smmu_domain_finalise(struct iommu_domain *domain)
 	struct io_pgtable_cfg pgtbl_cfg;
 	struct io_pgtable_ops *pgtbl_ops;
 	int (*finalise_stage_fn)(struct arm_smmu_domain *,
+				 struct arm_smmu_master *,
 				 struct io_pgtable_cfg *);
 	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
@@ -2254,7 +2515,7 @@ static int arm_smmu_domain_finalise(struct iommu_domain *domain)
 	domain->geometry.aperture_end = (1UL << pgtbl_cfg.ias) - 1;
 	domain->geometry.force_aperture = true;
 
-	ret = finalise_stage_fn(smmu_domain, &pgtbl_cfg);
+	ret = finalise_stage_fn(smmu_domain, master, &pgtbl_cfg);
 	if (ret < 0) {
 		free_io_pgtable_ops(pgtbl_ops);
 		return ret;
@@ -2407,7 +2668,7 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 
 	if (!smmu_domain->smmu) {
 		smmu_domain->smmu = smmu;
-		ret = arm_smmu_domain_finalise(domain);
+		ret = arm_smmu_domain_finalise(domain, master);
 		if (ret) {
 			smmu_domain->smmu = NULL;
 			goto out_unlock;
@@ -2419,6 +2680,13 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 			dev_name(smmu->dev));
 		ret = -ENXIO;
 		goto out_unlock;
+	} else if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1 &&
+		   master->ssid_bits != smmu_domain->s1_cfg.s1cdmax) {
+		dev_err(dev,
+			"cannot attach to incompatible domain (%u SSID bits != %u)\n",
+			smmu_domain->s1_cfg.s1cdmax, master->ssid_bits);
+		ret = -EINVAL;
+		goto out_unlock;
 	}
 
 	master->domain = smmu_domain;
@@ -2426,9 +2694,6 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 	if (smmu_domain->stage != ARM_SMMU_DOMAIN_BYPASS)
 		master->ats_enabled = arm_smmu_ats_supported(master);
 
-	if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1)
-		arm_smmu_write_ctx_desc(smmu, &smmu_domain->s1_cfg);
-
 	arm_smmu_install_ste_for_dev(master);
 
 	spin_lock_irqsave(&smmu_domain->devices_lock, flags);
@@ -2529,51 +2794,66 @@ static int arm_smmu_add_device(struct device *dev)
 
 	if (!fwspec || fwspec->ops != &arm_smmu_ops)
 		return -ENODEV;
-	/*
-	 * We _can_ actually withstand dodgy bus code re-calling add_device()
-	 * without an intervening remove_device()/of_xlate() sequence, but
-	 * we're not going to do so quietly...
-	 */
-	if (WARN_ON_ONCE(fwspec->iommu_priv)) {
-		master = fwspec->iommu_priv;
-		smmu = master->smmu;
-	} else {
-		smmu = arm_smmu_get_by_fwnode(fwspec->iommu_fwnode);
-		if (!smmu)
-			return -ENODEV;
-		master = kzalloc(sizeof(*master), GFP_KERNEL);
-		if (!master)
-			return -ENOMEM;
 
-		master->dev = dev;
-		master->smmu = smmu;
-		master->sids = fwspec->ids;
-		master->num_sids = fwspec->num_ids;
-		fwspec->iommu_priv = master;
-	}
+	if (WARN_ON_ONCE(fwspec->iommu_priv))
+		return -EBUSY;
+
+	smmu = arm_smmu_get_by_fwnode(fwspec->iommu_fwnode);
+	if (!smmu)
+		return -ENODEV;
+
+	master = kzalloc(sizeof(*master), GFP_KERNEL);
+	if (!master)
+		return -ENOMEM;
+
+	master->dev = dev;
+	master->smmu = smmu;
+	master->sids = fwspec->ids;
+	master->num_sids = fwspec->num_ids;
+	fwspec->iommu_priv = master;
 
 	/* Check the SIDs are in range of the SMMU and our stream table */
 	for (i = 0; i < master->num_sids; i++) {
 		u32 sid = master->sids[i];
 
-		if (!arm_smmu_sid_in_range(smmu, sid))
-			return -ERANGE;
+		if (!arm_smmu_sid_in_range(smmu, sid)) {
+			ret = -ERANGE;
+			goto err_free_master;
+		}
 
 		/* Ensure l2 strtab is initialised */
 		if (smmu->features & ARM_SMMU_FEAT_2_LVL_STRTAB) {
 			ret = arm_smmu_init_l2_strtab(smmu, sid);
 			if (ret)
-				return ret;
+				goto err_free_master;
 		}
 	}
 
+	master->ssid_bits = min(smmu->ssid_bits, fwspec->num_pasid_bits);
+
+	if (!(smmu->features & ARM_SMMU_FEAT_2_LVL_CDTAB))
+		master->ssid_bits = min_t(u8, master->ssid_bits,
+					  CTXDESC_LINEAR_CDMAX);
+
+	ret = iommu_device_link(&smmu->iommu, dev);
+	if (ret)
+		goto err_free_master;
+
 	group = iommu_group_get_for_dev(dev);
-	if (!IS_ERR(group)) {
-		iommu_group_put(group);
-		iommu_device_link(&smmu->iommu, dev);
+	if (IS_ERR(group)) {
+		ret = PTR_ERR(group);
+		goto err_unlink;
 	}
 
-	return PTR_ERR_OR_ZERO(group);
+	iommu_group_put(group);
+	return 0;
+
+err_unlink:
+	iommu_device_unlink(&smmu->iommu, dev);
+err_free_master:
+	kfree(master);
+	fwspec->iommu_priv = NULL;
+	return ret;
 }
 
 static void arm_smmu_remove_device(struct device *dev)
@@ -2733,7 +3013,6 @@ static struct iommu_ops arm_smmu_ops = {
 	.get_resv_regions	= arm_smmu_get_resv_regions,
 	.put_resv_regions	= arm_smmu_put_resv_regions,
 	.pgsize_bitmap		= -1UL, /* Restricted during device attach */
-	.owner			= THIS_MODULE,
 };
 
 /* Probing and initialisation functions */
@@ -2879,7 +3158,7 @@ static int arm_smmu_init_strtab_2lvl(struct arm_smmu_device *smmu)
 
 	l1size = cfg->num_l1_ents * (STRTAB_L1_DESC_DWORDS << 3);
 	strtab = dmam_alloc_coherent(smmu->dev, l1size, &cfg->strtab_dma,
-				     GFP_KERNEL | __GFP_ZERO);
+				     GFP_KERNEL);
 	if (!strtab) {
 		dev_err(smmu->dev,
 			"failed to allocate l1 stream table (%u bytes)\n",
@@ -2906,7 +3185,7 @@ static int arm_smmu_init_strtab_linear(struct arm_smmu_device *smmu)
 
 	size = (1 << smmu->sid_bits) * (STRTAB_STE_DWORDS << 3);
 	strtab = dmam_alloc_coherent(smmu->dev, size, &cfg->strtab_dma,
-				     GFP_KERNEL | __GFP_ZERO);
+				     GFP_KERNEL);
 	if (!strtab) {
 		dev_err(smmu->dev,
 			"failed to allocate linear stream table (%u bytes)\n",
@@ -3632,7 +3911,7 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
 
 	/* Base address */
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (resource_size(res) + 1 < arm_smmu_resource_size(smmu)) {
+	if (resource_size(res) < arm_smmu_resource_size(smmu)) {
 		dev_err(dev, "MMIO region too small (%pr)\n", res);
 		return -EINVAL;
 	}
@@ -3722,7 +4001,7 @@ MODULE_DEVICE_TABLE(of, arm_smmu_of_match);
 static struct platform_driver arm_smmu_driver = {
 	.driver	= {
 		.name			= "arm-smmu-v3",
-		.of_match_table		= of_match_ptr(arm_smmu_of_match),
+		.of_match_table		= arm_smmu_of_match,
 		.suppress_bind_attrs	= true,
 	},
 	.probe	= arm_smmu_device_probe,
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 5ef1f2e100d7..cca94c30b301 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -271,7 +271,7 @@ static void __arm_smmu_tlb_sync(struct arm_smmu_device *smmu, int page,
 	for (delay = 1; delay < TLB_LOOP_TIMEOUT; delay *= 2) {
 		for (spin_cnt = TLB_SPIN_COUNT; spin_cnt > 0; spin_cnt--) {
 			reg = arm_smmu_readl(smmu, page, status);
-			if (!(reg & sTLBGSTATUS_GSACTIVE))
+			if (!(reg & ARM_SMMU_sTLBGSTATUS_GSACTIVE))
 				return;
 			cpu_relax();
 		}
@@ -478,7 +478,7 @@ static irqreturn_t arm_smmu_context_fault(int irq, void *dev)
 	int idx = smmu_domain->cfg.cbndx;
 
 	fsr = arm_smmu_cb_read(smmu, idx, ARM_SMMU_CB_FSR);
-	if (!(fsr & FSR_FAULT))
+	if (!(fsr & ARM_SMMU_FSR_FAULT))
 		return IRQ_NONE;
 
 	fsynr = arm_smmu_cb_read(smmu, idx, ARM_SMMU_CB_FSYNR0);
@@ -510,7 +510,7 @@ static irqreturn_t arm_smmu_global_fault(int irq, void *dev)
 
 	if (__ratelimit(&rs)) {
 		if (IS_ENABLED(CONFIG_ARM_SMMU_DISABLE_BYPASS_BY_DEFAULT) &&
-		    (gfsr & sGFSR_USF))
+		    (gfsr & ARM_SMMU_sGFSR_USF))
 			dev_err(smmu->dev,
 				"Blocked unknown Stream ID 0x%hx; boot with \"arm-smmu.disable_bypass=0\" to allow, but this may have security implications\n",
 				(u16)gfsynr1);
@@ -540,26 +540,28 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain,
 		if (cfg->fmt == ARM_SMMU_CTX_FMT_AARCH32_S) {
 			cb->tcr[0] = pgtbl_cfg->arm_v7s_cfg.tcr;
 		} else {
-			cb->tcr[0] = pgtbl_cfg->arm_lpae_s1_cfg.tcr;
-			cb->tcr[1] = pgtbl_cfg->arm_lpae_s1_cfg.tcr >> 32;
-			cb->tcr[1] |= FIELD_PREP(TCR2_SEP, TCR2_SEP_UPSTREAM);
+			cb->tcr[0] = arm_smmu_lpae_tcr(pgtbl_cfg);
+			cb->tcr[1] = arm_smmu_lpae_tcr2(pgtbl_cfg);
 			if (cfg->fmt == ARM_SMMU_CTX_FMT_AARCH64)
-				cb->tcr[1] |= TCR2_AS;
+				cb->tcr[1] |= ARM_SMMU_TCR2_AS;
+			else
+				cb->tcr[0] |= ARM_SMMU_TCR_EAE;
 		}
 	} else {
-		cb->tcr[0] = pgtbl_cfg->arm_lpae_s2_cfg.vtcr;
+		cb->tcr[0] = arm_smmu_lpae_vtcr(pgtbl_cfg);
 	}
 
 	/* TTBRs */
 	if (stage1) {
 		if (cfg->fmt == ARM_SMMU_CTX_FMT_AARCH32_S) {
-			cb->ttbr[0] = pgtbl_cfg->arm_v7s_cfg.ttbr[0];
-			cb->ttbr[1] = pgtbl_cfg->arm_v7s_cfg.ttbr[1];
+			cb->ttbr[0] = pgtbl_cfg->arm_v7s_cfg.ttbr;
+			cb->ttbr[1] = 0;
 		} else {
-			cb->ttbr[0] = pgtbl_cfg->arm_lpae_s1_cfg.ttbr[0];
-			cb->ttbr[0] |= FIELD_PREP(TTBRn_ASID, cfg->asid);
-			cb->ttbr[1] = pgtbl_cfg->arm_lpae_s1_cfg.ttbr[1];
-			cb->ttbr[1] |= FIELD_PREP(TTBRn_ASID, cfg->asid);
+			cb->ttbr[0] = pgtbl_cfg->arm_lpae_s1_cfg.ttbr;
+			cb->ttbr[0] |= FIELD_PREP(ARM_SMMU_TTBRn_ASID,
+						  cfg->asid);
+			cb->ttbr[1] = FIELD_PREP(ARM_SMMU_TTBRn_ASID,
+						 cfg->asid);
 		}
 	} else {
 		cb->ttbr[0] = pgtbl_cfg->arm_lpae_s2_cfg.vttbr;
@@ -595,31 +597,33 @@ static void arm_smmu_write_context_bank(struct arm_smmu_device *smmu, int idx)
 	/* CBA2R */
 	if (smmu->version > ARM_SMMU_V1) {
 		if (cfg->fmt == ARM_SMMU_CTX_FMT_AARCH64)
-			reg = CBA2R_VA64;
+			reg = ARM_SMMU_CBA2R_VA64;
 		else
 			reg = 0;
 		/* 16-bit VMIDs live in CBA2R */
 		if (smmu->features & ARM_SMMU_FEAT_VMID16)
-			reg |= FIELD_PREP(CBA2R_VMID16, cfg->vmid);
+			reg |= FIELD_PREP(ARM_SMMU_CBA2R_VMID16, cfg->vmid);
 
 		arm_smmu_gr1_write(smmu, ARM_SMMU_GR1_CBA2R(idx), reg);
 	}
 
 	/* CBAR */
-	reg = FIELD_PREP(CBAR_TYPE, cfg->cbar);
+	reg = FIELD_PREP(ARM_SMMU_CBAR_TYPE, cfg->cbar);
 	if (smmu->version < ARM_SMMU_V2)
-		reg |= FIELD_PREP(CBAR_IRPTNDX, cfg->irptndx);
+		reg |= FIELD_PREP(ARM_SMMU_CBAR_IRPTNDX, cfg->irptndx);
 
 	/*
 	 * Use the weakest shareability/memory types, so they are
 	 * overridden by the ttbcr/pte.
 	 */
 	if (stage1) {
-		reg |= FIELD_PREP(CBAR_S1_BPSHCFG, CBAR_S1_BPSHCFG_NSH) |
-			FIELD_PREP(CBAR_S1_MEMATTR, CBAR_S1_MEMATTR_WB);
+		reg |= FIELD_PREP(ARM_SMMU_CBAR_S1_BPSHCFG,
+				  ARM_SMMU_CBAR_S1_BPSHCFG_NSH) |
+		       FIELD_PREP(ARM_SMMU_CBAR_S1_MEMATTR,
+				  ARM_SMMU_CBAR_S1_MEMATTR_WB);
 	} else if (!(smmu->features & ARM_SMMU_FEAT_VMID16)) {
 		/* 8-bit VMIDs live in CBAR */
-		reg |= FIELD_PREP(CBAR_VMID, cfg->vmid);
+		reg |= FIELD_PREP(ARM_SMMU_CBAR_VMID, cfg->vmid);
 	}
 	arm_smmu_gr1_write(smmu, ARM_SMMU_GR1_CBAR(idx), reg);
 
@@ -651,11 +655,12 @@ static void arm_smmu_write_context_bank(struct arm_smmu_device *smmu, int idx)
 	}
 
 	/* SCTLR */
-	reg = SCTLR_CFIE | SCTLR_CFRE | SCTLR_AFE | SCTLR_TRE | SCTLR_M;
+	reg = ARM_SMMU_SCTLR_CFIE | ARM_SMMU_SCTLR_CFRE | ARM_SMMU_SCTLR_AFE |
+	      ARM_SMMU_SCTLR_TRE | ARM_SMMU_SCTLR_M;
 	if (stage1)
-		reg |= SCTLR_S1_ASIDPNE;
+		reg |= ARM_SMMU_SCTLR_S1_ASIDPNE;
 	if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN))
-		reg |= SCTLR_E;
+		reg |= ARM_SMMU_SCTLR_E;
 
 	arm_smmu_cb_write(smmu, idx, ARM_SMMU_CB_SCTLR, reg);
 }
@@ -837,7 +842,7 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 	if (ret < 0) {
 		dev_err(smmu->dev, "failed to request context IRQ %d (%u)\n",
 			cfg->irptndx, irq);
-		cfg->irptndx = INVALID_IRPTNDX;
+		cfg->irptndx = ARM_SMMU_INVALID_IRPTNDX;
 	}
 
 	mutex_unlock(&smmu_domain->init_mutex);
@@ -875,7 +880,7 @@ static void arm_smmu_destroy_domain_context(struct iommu_domain *domain)
 	smmu->cbs[cfg->cbndx].cfg = NULL;
 	arm_smmu_write_context_bank(smmu, cfg->cbndx);
 
-	if (cfg->irptndx != INVALID_IRPTNDX) {
+	if (cfg->irptndx != ARM_SMMU_INVALID_IRPTNDX) {
 		irq = smmu->irqs[smmu->num_global_irqs + cfg->irptndx];
 		devm_free_irq(smmu->dev, irq, domain);
 	}
@@ -931,23 +936,24 @@ static void arm_smmu_domain_free(struct iommu_domain *domain)
 static void arm_smmu_write_smr(struct arm_smmu_device *smmu, int idx)
 {
 	struct arm_smmu_smr *smr = smmu->smrs + idx;
-	u32 reg = FIELD_PREP(SMR_ID, smr->id) | FIELD_PREP(SMR_MASK, smr->mask);
+	u32 reg = FIELD_PREP(ARM_SMMU_SMR_ID, smr->id) |
+		  FIELD_PREP(ARM_SMMU_SMR_MASK, smr->mask);
 
 	if (!(smmu->features & ARM_SMMU_FEAT_EXIDS) && smr->valid)
-		reg |= SMR_VALID;
+		reg |= ARM_SMMU_SMR_VALID;
 	arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_SMR(idx), reg);
 }
 
 static void arm_smmu_write_s2cr(struct arm_smmu_device *smmu, int idx)
 {
 	struct arm_smmu_s2cr *s2cr = smmu->s2crs + idx;
-	u32 reg = FIELD_PREP(S2CR_TYPE, s2cr->type) |
-		  FIELD_PREP(S2CR_CBNDX, s2cr->cbndx) |
-		  FIELD_PREP(S2CR_PRIVCFG, s2cr->privcfg);
+	u32 reg = FIELD_PREP(ARM_SMMU_S2CR_TYPE, s2cr->type) |
+		  FIELD_PREP(ARM_SMMU_S2CR_CBNDX, s2cr->cbndx) |
+		  FIELD_PREP(ARM_SMMU_S2CR_PRIVCFG, s2cr->privcfg);
 
 	if (smmu->features & ARM_SMMU_FEAT_EXIDS && smmu->smrs &&
 	    smmu->smrs[idx].valid)
-		reg |= S2CR_EXIDVALID;
+		reg |= ARM_SMMU_S2CR_EXIDVALID;
 	arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_S2CR(idx), reg);
 }
 
@@ -965,24 +971,37 @@ static void arm_smmu_write_sme(struct arm_smmu_device *smmu, int idx)
 static void arm_smmu_test_smr_masks(struct arm_smmu_device *smmu)
 {
 	u32 smr;
+	int i;
 
 	if (!smmu->smrs)
 		return;
-
+	/*
+	 * If we've had to accommodate firmware memory regions, we may
+	 * have live SMRs by now; tread carefully...
+	 *
+	 * Somewhat perversely, not having a free SMR for this test implies we
+	 * can get away without it anyway, as we'll only be able to 'allocate'
+	 * these SMRs for the ID/mask values we're already trusting to be OK.
+	 */
+	for (i = 0; i < smmu->num_mapping_groups; i++)
+		if (!smmu->smrs[i].valid)
+			goto smr_ok;
+	return;
+smr_ok:
 	/*
 	 * SMR.ID bits may not be preserved if the corresponding MASK
 	 * bits are set, so check each one separately. We can reject
 	 * masters later if they try to claim IDs outside these masks.
 	 */
-	smr = FIELD_PREP(SMR_ID, smmu->streamid_mask);
-	arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_SMR(0), smr);
-	smr = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_SMR(0));
-	smmu->streamid_mask = FIELD_GET(SMR_ID, smr);
+	smr = FIELD_PREP(ARM_SMMU_SMR_ID, smmu->streamid_mask);
+	arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_SMR(i), smr);
+	smr = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_SMR(i));
+	smmu->streamid_mask = FIELD_GET(ARM_SMMU_SMR_ID, smr);
 
-	smr = FIELD_PREP(SMR_MASK, smmu->streamid_mask);
-	arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_SMR(0), smr);
-	smr = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_SMR(0));
-	smmu->smr_mask_mask = FIELD_GET(SMR_MASK, smr);
+	smr = FIELD_PREP(ARM_SMMU_SMR_MASK, smmu->streamid_mask);
+	arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_SMR(i), smr);
+	smr = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_SMR(i));
+	smmu->smr_mask_mask = FIELD_GET(ARM_SMMU_SMR_MASK, smr);
 }
 
 static int arm_smmu_find_sme(struct arm_smmu_device *smmu, u16 id, u16 mask)
@@ -1051,8 +1070,8 @@ static int arm_smmu_master_alloc_smes(struct device *dev)
 	mutex_lock(&smmu->stream_map_mutex);
 	/* Figure out a viable stream map entry allocation */
 	for_each_cfg_sme(fwspec, i, idx) {
-		u16 sid = FIELD_GET(SMR_ID, fwspec->ids[i]);
-		u16 mask = FIELD_GET(SMR_MASK, fwspec->ids[i]);
+		u16 sid = FIELD_GET(ARM_SMMU_SMR_ID, fwspec->ids[i]);
+		u16 mask = FIELD_GET(ARM_SMMU_SMR_MASK, fwspec->ids[i]);
 
 		if (idx != INVALID_SMENDX) {
 			ret = -EEXIST;
@@ -1296,7 +1315,8 @@ static phys_addr_t arm_smmu_iova_to_phys_hard(struct iommu_domain *domain,
 		arm_smmu_cb_write(smmu, idx, ARM_SMMU_CB_ATS1PR, va);
 
 	reg = arm_smmu_page(smmu, ARM_SMMU_CB(smmu, idx)) + ARM_SMMU_CB_ATSR;
-	if (readl_poll_timeout_atomic(reg, tmp, !(tmp & ATSR_ACTIVE), 5, 50)) {
+	if (readl_poll_timeout_atomic(reg, tmp, !(tmp & ARM_SMMU_ATSR_ACTIVE),
+				      5, 50)) {
 		spin_unlock_irqrestore(&smmu_domain->cb_lock, flags);
 		dev_err(dev,
 			"iova to phys timed out on %pad. Falling back to software table walk.\n",
@@ -1306,7 +1326,7 @@ static phys_addr_t arm_smmu_iova_to_phys_hard(struct iommu_domain *domain,
 
 	phys = arm_smmu_cb_readq(smmu, idx, ARM_SMMU_CB_PAR);
 	spin_unlock_irqrestore(&smmu_domain->cb_lock, flags);
-	if (phys & CB_PAR_F) {
+	if (phys & ARM_SMMU_CB_PAR_F) {
 		dev_err(dev, "translation fault!\n");
 		dev_err(dev, "PAR = 0x%llx\n", phys);
 		return 0;
@@ -1387,8 +1407,8 @@ static int arm_smmu_add_device(struct device *dev)
 
 	ret = -EINVAL;
 	for (i = 0; i < fwspec->num_ids; i++) {
-		u16 sid = FIELD_GET(SMR_ID, fwspec->ids[i]);
-		u16 mask = FIELD_GET(SMR_MASK, fwspec->ids[i]);
+		u16 sid = FIELD_GET(ARM_SMMU_SMR_ID, fwspec->ids[i]);
+		u16 mask = FIELD_GET(ARM_SMMU_SMR_MASK, fwspec->ids[i]);
 
 		if (sid & ~smmu->streamid_mask) {
 			dev_err(dev, "stream ID 0x%x out of range for SMMU (0x%x)\n",
@@ -1569,12 +1589,12 @@ static int arm_smmu_of_xlate(struct device *dev, struct of_phandle_args *args)
 	u32 mask, fwid = 0;
 
 	if (args->args_count > 0)
-		fwid |= FIELD_PREP(SMR_ID, args->args[0]);
+		fwid |= FIELD_PREP(ARM_SMMU_SMR_ID, args->args[0]);
 
 	if (args->args_count > 1)
-		fwid |= FIELD_PREP(SMR_MASK, args->args[1]);
+		fwid |= FIELD_PREP(ARM_SMMU_SMR_MASK, args->args[1]);
 	else if (!of_property_read_u32(args->np, "stream-match-mask", &mask))
-		fwid |= FIELD_PREP(SMR_MASK, mask);
+		fwid |= FIELD_PREP(ARM_SMMU_SMR_MASK, mask);
 
 	return iommu_fwspec_add_ids(dev, &fwid, 1);
 }
@@ -1623,7 +1643,6 @@ static struct iommu_ops arm_smmu_ops = {
 	.get_resv_regions	= arm_smmu_get_resv_regions,
 	.put_resv_regions	= arm_smmu_put_resv_regions,
 	.pgsize_bitmap		= -1UL, /* Restricted during device attach */
-	.owner			= THIS_MODULE,
 };
 
 static void arm_smmu_device_reset(struct arm_smmu_device *smmu)
@@ -1645,7 +1664,7 @@ static void arm_smmu_device_reset(struct arm_smmu_device *smmu)
 	/* Make sure all context banks are disabled and clear CB_FSR  */
 	for (i = 0; i < smmu->num_context_banks; ++i) {
 		arm_smmu_write_context_bank(smmu, i);
-		arm_smmu_cb_write(smmu, i, ARM_SMMU_CB_FSR, FSR_FAULT);
+		arm_smmu_cb_write(smmu, i, ARM_SMMU_CB_FSR, ARM_SMMU_FSR_FAULT);
 	}
 
 	/* Invalidate the TLB, just in case */
@@ -1655,29 +1674,30 @@ static void arm_smmu_device_reset(struct arm_smmu_device *smmu)
 	reg = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_sCR0);
 
 	/* Enable fault reporting */
-	reg |= (sCR0_GFRE | sCR0_GFIE | sCR0_GCFGFRE | sCR0_GCFGFIE);
+	reg |= (ARM_SMMU_sCR0_GFRE | ARM_SMMU_sCR0_GFIE |
+		ARM_SMMU_sCR0_GCFGFRE | ARM_SMMU_sCR0_GCFGFIE);
 
 	/* Disable TLB broadcasting. */
-	reg |= (sCR0_VMIDPNE | sCR0_PTM);
+	reg |= (ARM_SMMU_sCR0_VMIDPNE | ARM_SMMU_sCR0_PTM);
 
 	/* Enable client access, handling unmatched streams as appropriate */
-	reg &= ~sCR0_CLIENTPD;
+	reg &= ~ARM_SMMU_sCR0_CLIENTPD;
 	if (disable_bypass)
-		reg |= sCR0_USFCFG;
+		reg |= ARM_SMMU_sCR0_USFCFG;
 	else
-		reg &= ~sCR0_USFCFG;
+		reg &= ~ARM_SMMU_sCR0_USFCFG;
 
 	/* Disable forced broadcasting */
-	reg &= ~sCR0_FB;
+	reg &= ~ARM_SMMU_sCR0_FB;
 
 	/* Don't upgrade barriers */
-	reg &= ~(sCR0_BSU);
+	reg &= ~(ARM_SMMU_sCR0_BSU);
 
 	if (smmu->features & ARM_SMMU_FEAT_VMID16)
-		reg |= sCR0_VMID16EN;
+		reg |= ARM_SMMU_sCR0_VMID16EN;
 
 	if (smmu->features & ARM_SMMU_FEAT_EXIDS)
-		reg |= sCR0_EXIDENABLE;
+		reg |= ARM_SMMU_sCR0_EXIDENABLE;
 
 	if (smmu->impl && smmu->impl->reset)
 		smmu->impl->reset(smmu);
@@ -1722,21 +1742,21 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 
 	/* Restrict available stages based on module parameter */
 	if (force_stage == 1)
-		id &= ~(ID0_S2TS | ID0_NTS);
+		id &= ~(ARM_SMMU_ID0_S2TS | ARM_SMMU_ID0_NTS);
 	else if (force_stage == 2)
-		id &= ~(ID0_S1TS | ID0_NTS);
+		id &= ~(ARM_SMMU_ID0_S1TS | ARM_SMMU_ID0_NTS);
 
-	if (id & ID0_S1TS) {
+	if (id & ARM_SMMU_ID0_S1TS) {
 		smmu->features |= ARM_SMMU_FEAT_TRANS_S1;
 		dev_notice(smmu->dev, "\tstage 1 translation\n");
 	}
 
-	if (id & ID0_S2TS) {
+	if (id & ARM_SMMU_ID0_S2TS) {
 		smmu->features |= ARM_SMMU_FEAT_TRANS_S2;
 		dev_notice(smmu->dev, "\tstage 2 translation\n");
 	}
 
-	if (id & ID0_NTS) {
+	if (id & ARM_SMMU_ID0_NTS) {
 		smmu->features |= ARM_SMMU_FEAT_TRANS_NESTED;
 		dev_notice(smmu->dev, "\tnested translation\n");
 	}
@@ -1747,8 +1767,8 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 		return -ENODEV;
 	}
 
-	if ((id & ID0_S1TS) &&
-		((smmu->version < ARM_SMMU_V2) || !(id & ID0_ATOSNS))) {
+	if ((id & ARM_SMMU_ID0_S1TS) &&
+	    ((smmu->version < ARM_SMMU_V2) || !(id & ARM_SMMU_ID0_ATOSNS))) {
 		smmu->features |= ARM_SMMU_FEAT_TRANS_OPS;
 		dev_notice(smmu->dev, "\taddress translation ops\n");
 	}
@@ -1759,7 +1779,7 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 	 * Fortunately, this also opens up a workaround for systems where the
 	 * ID register value has ended up configured incorrectly.
 	 */
-	cttw_reg = !!(id & ID0_CTTW);
+	cttw_reg = !!(id & ARM_SMMU_ID0_CTTW);
 	if (cttw_fw || cttw_reg)
 		dev_notice(smmu->dev, "\t%scoherent table walk\n",
 			   cttw_fw ? "" : "non-");
@@ -1768,16 +1788,16 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 			   "\t(IDR0.CTTW overridden by FW configuration)\n");
 
 	/* Max. number of entries we have for stream matching/indexing */
-	if (smmu->version == ARM_SMMU_V2 && id & ID0_EXIDS) {
+	if (smmu->version == ARM_SMMU_V2 && id & ARM_SMMU_ID0_EXIDS) {
 		smmu->features |= ARM_SMMU_FEAT_EXIDS;
 		size = 1 << 16;
 	} else {
-		size = 1 << FIELD_GET(ID0_NUMSIDB, id);
+		size = 1 << FIELD_GET(ARM_SMMU_ID0_NUMSIDB, id);
 	}
 	smmu->streamid_mask = size - 1;
-	if (id & ID0_SMS) {
+	if (id & ARM_SMMU_ID0_SMS) {
 		smmu->features |= ARM_SMMU_FEAT_STREAM_MATCH;
-		size = FIELD_GET(ID0_NUMSMRG, id);
+		size = FIELD_GET(ARM_SMMU_ID0_NUMSMRG, id);
 		if (size == 0) {
 			dev_err(smmu->dev,
 				"stream-matching supported, but no SMRs present!\n");
@@ -1805,18 +1825,19 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 	mutex_init(&smmu->stream_map_mutex);
 	spin_lock_init(&smmu->global_sync_lock);
 
-	if (smmu->version < ARM_SMMU_V2 || !(id & ID0_PTFS_NO_AARCH32)) {
+	if (smmu->version < ARM_SMMU_V2 ||
+	    !(id & ARM_SMMU_ID0_PTFS_NO_AARCH32)) {
 		smmu->features |= ARM_SMMU_FEAT_FMT_AARCH32_L;
-		if (!(id & ID0_PTFS_NO_AARCH32S))
+		if (!(id & ARM_SMMU_ID0_PTFS_NO_AARCH32S))
 			smmu->features |= ARM_SMMU_FEAT_FMT_AARCH32_S;
 	}
 
 	/* ID1 */
 	id = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_ID1);
-	smmu->pgshift = (id & ID1_PAGESIZE) ? 16 : 12;
+	smmu->pgshift = (id & ARM_SMMU_ID1_PAGESIZE) ? 16 : 12;
 
 	/* Check for size mismatch of SMMU address space from mapped region */
-	size = 1 << (FIELD_GET(ID1_NUMPAGENDXB, id) + 1);
+	size = 1 << (FIELD_GET(ARM_SMMU_ID1_NUMPAGENDXB, id) + 1);
 	if (smmu->numpage != 2 * size << smmu->pgshift)
 		dev_warn(smmu->dev,
 			"SMMU address space size (0x%x) differs from mapped region size (0x%x)!\n",
@@ -1824,8 +1845,8 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 	/* Now properly encode NUMPAGE to subsequently derive SMMU_CB_BASE */
 	smmu->numpage = size;
 
-	smmu->num_s2_context_banks = FIELD_GET(ID1_NUMS2CB, id);
-	smmu->num_context_banks = FIELD_GET(ID1_NUMCB, id);
+	smmu->num_s2_context_banks = FIELD_GET(ARM_SMMU_ID1_NUMS2CB, id);
+	smmu->num_context_banks = FIELD_GET(ARM_SMMU_ID1_NUMCB, id);
 	if (smmu->num_s2_context_banks > smmu->num_context_banks) {
 		dev_err(smmu->dev, "impossible number of S2 context banks!\n");
 		return -ENODEV;
@@ -1839,14 +1860,14 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 
 	/* ID2 */
 	id = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_ID2);
-	size = arm_smmu_id_size_to_bits(FIELD_GET(ID2_IAS, id));
+	size = arm_smmu_id_size_to_bits(FIELD_GET(ARM_SMMU_ID2_IAS, id));
 	smmu->ipa_size = size;
 
 	/* The output mask is also applied for bypass */
-	size = arm_smmu_id_size_to_bits(FIELD_GET(ID2_OAS, id));
+	size = arm_smmu_id_size_to_bits(FIELD_GET(ARM_SMMU_ID2_OAS, id));
 	smmu->pa_size = size;
 
-	if (id & ID2_VMID16)
+	if (id & ARM_SMMU_ID2_VMID16)
 		smmu->features |= ARM_SMMU_FEAT_VMID16;
 
 	/*
@@ -1863,13 +1884,13 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 		if (smmu->version == ARM_SMMU_V1_64K)
 			smmu->features |= ARM_SMMU_FEAT_FMT_AARCH64_64K;
 	} else {
-		size = FIELD_GET(ID2_UBS, id);
+		size = FIELD_GET(ARM_SMMU_ID2_UBS, id);
 		smmu->va_size = arm_smmu_id_size_to_bits(size);
-		if (id & ID2_PTFS_4K)
+		if (id & ARM_SMMU_ID2_PTFS_4K)
 			smmu->features |= ARM_SMMU_FEAT_FMT_AARCH64_4K;
-		if (id & ID2_PTFS_16K)
+		if (id & ARM_SMMU_ID2_PTFS_16K)
 			smmu->features |= ARM_SMMU_FEAT_FMT_AARCH64_16K;
-		if (id & ID2_PTFS_64K)
+		if (id & ARM_SMMU_ID2_PTFS_64K)
 			smmu->features |= ARM_SMMU_FEAT_FMT_AARCH64_64K;
 	}
 
@@ -2246,7 +2267,7 @@ static int arm_smmu_device_remove(struct platform_device *pdev)
 
 	arm_smmu_rpm_get(smmu);
 	/* Turn the thing off */
-	arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_sCR0, sCR0_CLIENTPD);
+	arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_sCR0, ARM_SMMU_sCR0_CLIENTPD);
 	arm_smmu_rpm_put(smmu);
 
 	if (pm_runtime_enabled(smmu->dev))
@@ -2311,7 +2332,7 @@ static const struct dev_pm_ops arm_smmu_pm_ops = {
 static struct platform_driver arm_smmu_driver = {
 	.driver	= {
 		.name			= "arm-smmu",
-		.of_match_table		= of_match_ptr(arm_smmu_of_match),
+		.of_match_table		= arm_smmu_of_match,
 		.pm			= &arm_smmu_pm_ops,
 		.suppress_bind_attrs    = true,
 	},
diff --git a/drivers/iommu/arm-smmu.h b/drivers/iommu/arm-smmu.h
index 62b9f0cec49b..8d1cd54d82a6 100644
--- a/drivers/iommu/arm-smmu.h
+++ b/drivers/iommu/arm-smmu.h
@@ -11,6 +11,7 @@
 #define _ARM_SMMU_H
 
 #include <linux/atomic.h>
+#include <linux/bitfield.h>
 #include <linux/bits.h>
 #include <linux/clk.h>
 #include <linux/device.h>
@@ -23,51 +24,51 @@
 
 /* Configuration registers */
 #define ARM_SMMU_GR0_sCR0		0x0
-#define sCR0_VMID16EN			BIT(31)
-#define sCR0_BSU			GENMASK(15, 14)
-#define sCR0_FB				BIT(13)
-#define sCR0_PTM			BIT(12)
-#define sCR0_VMIDPNE			BIT(11)
-#define sCR0_USFCFG			BIT(10)
-#define sCR0_GCFGFIE			BIT(5)
-#define sCR0_GCFGFRE			BIT(4)
-#define sCR0_EXIDENABLE			BIT(3)
-#define sCR0_GFIE			BIT(2)
-#define sCR0_GFRE			BIT(1)
-#define sCR0_CLIENTPD			BIT(0)
+#define ARM_SMMU_sCR0_VMID16EN		BIT(31)
+#define ARM_SMMU_sCR0_BSU		GENMASK(15, 14)
+#define ARM_SMMU_sCR0_FB		BIT(13)
+#define ARM_SMMU_sCR0_PTM		BIT(12)
+#define ARM_SMMU_sCR0_VMIDPNE		BIT(11)
+#define ARM_SMMU_sCR0_USFCFG		BIT(10)
+#define ARM_SMMU_sCR0_GCFGFIE		BIT(5)
+#define ARM_SMMU_sCR0_GCFGFRE		BIT(4)
+#define ARM_SMMU_sCR0_EXIDENABLE	BIT(3)
+#define ARM_SMMU_sCR0_GFIE		BIT(2)
+#define ARM_SMMU_sCR0_GFRE		BIT(1)
+#define ARM_SMMU_sCR0_CLIENTPD		BIT(0)
 
 /* Auxiliary Configuration register */
 #define ARM_SMMU_GR0_sACR		0x10
 
 /* Identification registers */
 #define ARM_SMMU_GR0_ID0		0x20
-#define ID0_S1TS			BIT(30)
-#define ID0_S2TS			BIT(29)
-#define ID0_NTS				BIT(28)
-#define ID0_SMS				BIT(27)
-#define ID0_ATOSNS			BIT(26)
-#define ID0_PTFS_NO_AARCH32		BIT(25)
-#define ID0_PTFS_NO_AARCH32S		BIT(24)
-#define ID0_NUMIRPT			GENMASK(23, 16)
-#define ID0_CTTW			BIT(14)
-#define ID0_NUMSIDB			GENMASK(12, 9)
-#define ID0_EXIDS			BIT(8)
-#define ID0_NUMSMRG			GENMASK(7, 0)
+#define ARM_SMMU_ID0_S1TS		BIT(30)
+#define ARM_SMMU_ID0_S2TS		BIT(29)
+#define ARM_SMMU_ID0_NTS		BIT(28)
+#define ARM_SMMU_ID0_SMS		BIT(27)
+#define ARM_SMMU_ID0_ATOSNS		BIT(26)
+#define ARM_SMMU_ID0_PTFS_NO_AARCH32	BIT(25)
+#define ARM_SMMU_ID0_PTFS_NO_AARCH32S	BIT(24)
+#define ARM_SMMU_ID0_NUMIRPT		GENMASK(23, 16)
+#define ARM_SMMU_ID0_CTTW		BIT(14)
+#define ARM_SMMU_ID0_NUMSIDB		GENMASK(12, 9)
+#define ARM_SMMU_ID0_EXIDS		BIT(8)
+#define ARM_SMMU_ID0_NUMSMRG		GENMASK(7, 0)
 
 #define ARM_SMMU_GR0_ID1		0x24
-#define ID1_PAGESIZE			BIT(31)
-#define ID1_NUMPAGENDXB			GENMASK(30, 28)
-#define ID1_NUMS2CB			GENMASK(23, 16)
-#define ID1_NUMCB			GENMASK(7, 0)
+#define ARM_SMMU_ID1_PAGESIZE		BIT(31)
+#define ARM_SMMU_ID1_NUMPAGENDXB	GENMASK(30, 28)
+#define ARM_SMMU_ID1_NUMS2CB		GENMASK(23, 16)
+#define ARM_SMMU_ID1_NUMCB		GENMASK(7, 0)
 
 #define ARM_SMMU_GR0_ID2		0x28
-#define ID2_VMID16			BIT(15)
-#define ID2_PTFS_64K			BIT(14)
-#define ID2_PTFS_16K			BIT(13)
-#define ID2_PTFS_4K			BIT(12)
-#define ID2_UBS				GENMASK(11, 8)
-#define ID2_OAS				GENMASK(7, 4)
-#define ID2_IAS				GENMASK(3, 0)
+#define ARM_SMMU_ID2_VMID16		BIT(15)
+#define ARM_SMMU_ID2_PTFS_64K		BIT(14)
+#define ARM_SMMU_ID2_PTFS_16K		BIT(13)
+#define ARM_SMMU_ID2_PTFS_4K		BIT(12)
+#define ARM_SMMU_ID2_UBS		GENMASK(11, 8)
+#define ARM_SMMU_ID2_OAS		GENMASK(7, 4)
+#define ARM_SMMU_ID2_IAS		GENMASK(3, 0)
 
 #define ARM_SMMU_GR0_ID3		0x2c
 #define ARM_SMMU_GR0_ID4		0x30
@@ -75,11 +76,11 @@
 #define ARM_SMMU_GR0_ID6		0x38
 
 #define ARM_SMMU_GR0_ID7		0x3c
-#define ID7_MAJOR			GENMASK(7, 4)
-#define ID7_MINOR			GENMASK(3, 0)
+#define ARM_SMMU_ID7_MAJOR		GENMASK(7, 4)
+#define ARM_SMMU_ID7_MINOR		GENMASK(3, 0)
 
 #define ARM_SMMU_GR0_sGFSR		0x48
-#define sGFSR_USF			BIT(1)
+#define ARM_SMMU_sGFSR_USF		BIT(1)
 
 #define ARM_SMMU_GR0_sGFSYNR0		0x50
 #define ARM_SMMU_GR0_sGFSYNR1		0x54
@@ -92,106 +93,132 @@
 #define ARM_SMMU_GR0_sTLBGSYNC		0x70
 
 #define ARM_SMMU_GR0_sTLBGSTATUS	0x74
-#define sTLBGSTATUS_GSACTIVE		BIT(0)
+#define ARM_SMMU_sTLBGSTATUS_GSACTIVE	BIT(0)
 
 /* Stream mapping registers */
 #define ARM_SMMU_GR0_SMR(n)		(0x800 + ((n) << 2))
-#define SMR_VALID			BIT(31)
-#define SMR_MASK			GENMASK(31, 16)
-#define SMR_ID				GENMASK(15, 0)
+#define ARM_SMMU_SMR_VALID		BIT(31)
+#define ARM_SMMU_SMR_MASK		GENMASK(31, 16)
+#define ARM_SMMU_SMR_ID			GENMASK(15, 0)
 
 #define ARM_SMMU_GR0_S2CR(n)		(0xc00 + ((n) << 2))
-#define S2CR_PRIVCFG			GENMASK(25, 24)
+#define ARM_SMMU_S2CR_PRIVCFG		GENMASK(25, 24)
 enum arm_smmu_s2cr_privcfg {
 	S2CR_PRIVCFG_DEFAULT,
 	S2CR_PRIVCFG_DIPAN,
 	S2CR_PRIVCFG_UNPRIV,
 	S2CR_PRIVCFG_PRIV,
 };
-#define S2CR_TYPE			GENMASK(17, 16)
+#define ARM_SMMU_S2CR_TYPE		GENMASK(17, 16)
 enum arm_smmu_s2cr_type {
 	S2CR_TYPE_TRANS,
 	S2CR_TYPE_BYPASS,
 	S2CR_TYPE_FAULT,
 };
-#define S2CR_EXIDVALID			BIT(10)
-#define S2CR_CBNDX			GENMASK(7, 0)
+#define ARM_SMMU_S2CR_EXIDVALID		BIT(10)
+#define ARM_SMMU_S2CR_CBNDX		GENMASK(7, 0)
 
 /* Context bank attribute registers */
 #define ARM_SMMU_GR1_CBAR(n)		(0x0 + ((n) << 2))
-#define CBAR_IRPTNDX			GENMASK(31, 24)
-#define CBAR_TYPE			GENMASK(17, 16)
+#define ARM_SMMU_CBAR_IRPTNDX		GENMASK(31, 24)
+#define ARM_SMMU_CBAR_TYPE		GENMASK(17, 16)
 enum arm_smmu_cbar_type {
 	CBAR_TYPE_S2_TRANS,
 	CBAR_TYPE_S1_TRANS_S2_BYPASS,
 	CBAR_TYPE_S1_TRANS_S2_FAULT,
 	CBAR_TYPE_S1_TRANS_S2_TRANS,
 };
-#define CBAR_S1_MEMATTR			GENMASK(15, 12)
-#define CBAR_S1_MEMATTR_WB		0xf
-#define CBAR_S1_BPSHCFG			GENMASK(9, 8)
-#define CBAR_S1_BPSHCFG_NSH		3
-#define CBAR_VMID			GENMASK(7, 0)
+#define ARM_SMMU_CBAR_S1_MEMATTR	GENMASK(15, 12)
+#define ARM_SMMU_CBAR_S1_MEMATTR_WB	0xf
+#define ARM_SMMU_CBAR_S1_BPSHCFG	GENMASK(9, 8)
+#define ARM_SMMU_CBAR_S1_BPSHCFG_NSH	3
+#define ARM_SMMU_CBAR_VMID		GENMASK(7, 0)
 
 #define ARM_SMMU_GR1_CBFRSYNRA(n)	(0x400 + ((n) << 2))
 
 #define ARM_SMMU_GR1_CBA2R(n)		(0x800 + ((n) << 2))
-#define CBA2R_VMID16			GENMASK(31, 16)
-#define CBA2R_VA64			BIT(0)
+#define ARM_SMMU_CBA2R_VMID16		GENMASK(31, 16)
+#define ARM_SMMU_CBA2R_VA64		BIT(0)
 
 #define ARM_SMMU_CB_SCTLR		0x0
-#define SCTLR_S1_ASIDPNE		BIT(12)
-#define SCTLR_CFCFG			BIT(7)
-#define SCTLR_CFIE			BIT(6)
-#define SCTLR_CFRE			BIT(5)
-#define SCTLR_E				BIT(4)
-#define SCTLR_AFE			BIT(2)
-#define SCTLR_TRE			BIT(1)
-#define SCTLR_M				BIT(0)
+#define ARM_SMMU_SCTLR_S1_ASIDPNE	BIT(12)
+#define ARM_SMMU_SCTLR_CFCFG		BIT(7)
+#define ARM_SMMU_SCTLR_CFIE		BIT(6)
+#define ARM_SMMU_SCTLR_CFRE		BIT(5)
+#define ARM_SMMU_SCTLR_E		BIT(4)
+#define ARM_SMMU_SCTLR_AFE		BIT(2)
+#define ARM_SMMU_SCTLR_TRE		BIT(1)
+#define ARM_SMMU_SCTLR_M		BIT(0)
 
 #define ARM_SMMU_CB_ACTLR		0x4
 
 #define ARM_SMMU_CB_RESUME		0x8
-#define RESUME_TERMINATE		BIT(0)
+#define ARM_SMMU_RESUME_TERMINATE	BIT(0)
 
 #define ARM_SMMU_CB_TCR2		0x10
-#define TCR2_SEP			GENMASK(17, 15)
-#define TCR2_SEP_UPSTREAM		0x7
-#define TCR2_AS				BIT(4)
+#define ARM_SMMU_TCR2_SEP		GENMASK(17, 15)
+#define ARM_SMMU_TCR2_SEP_UPSTREAM	0x7
+#define ARM_SMMU_TCR2_AS		BIT(4)
+#define ARM_SMMU_TCR2_PASIZE		GENMASK(3, 0)
 
 #define ARM_SMMU_CB_TTBR0		0x20
 #define ARM_SMMU_CB_TTBR1		0x28
-#define TTBRn_ASID			GENMASK_ULL(63, 48)
+#define ARM_SMMU_TTBRn_ASID		GENMASK_ULL(63, 48)
 
 #define ARM_SMMU_CB_TCR			0x30
+#define ARM_SMMU_TCR_EAE		BIT(31)
+#define ARM_SMMU_TCR_EPD1		BIT(23)
+#define ARM_SMMU_TCR_TG0		GENMASK(15, 14)
+#define ARM_SMMU_TCR_SH0		GENMASK(13, 12)
+#define ARM_SMMU_TCR_ORGN0		GENMASK(11, 10)
+#define ARM_SMMU_TCR_IRGN0		GENMASK(9, 8)
+#define ARM_SMMU_TCR_T0SZ		GENMASK(5, 0)
+
+#define ARM_SMMU_VTCR_RES1		BIT(31)
+#define ARM_SMMU_VTCR_PS		GENMASK(18, 16)
+#define ARM_SMMU_VTCR_TG0		ARM_SMMU_TCR_TG0
+#define ARM_SMMU_VTCR_SH0		ARM_SMMU_TCR_SH0
+#define ARM_SMMU_VTCR_ORGN0		ARM_SMMU_TCR_ORGN0
+#define ARM_SMMU_VTCR_IRGN0		ARM_SMMU_TCR_IRGN0
+#define ARM_SMMU_VTCR_SL0		GENMASK(7, 6)
+#define ARM_SMMU_VTCR_T0SZ		ARM_SMMU_TCR_T0SZ
+
 #define ARM_SMMU_CB_CONTEXTIDR		0x34
 #define ARM_SMMU_CB_S1_MAIR0		0x38
 #define ARM_SMMU_CB_S1_MAIR1		0x3c
 
 #define ARM_SMMU_CB_PAR			0x50
-#define CB_PAR_F			BIT(0)
+#define ARM_SMMU_CB_PAR_F		BIT(0)
 
 #define ARM_SMMU_CB_FSR			0x58
-#define FSR_MULTI			BIT(31)
-#define FSR_SS				BIT(30)
-#define FSR_UUT				BIT(8)
-#define FSR_ASF				BIT(7)
-#define FSR_TLBLKF			BIT(6)
-#define FSR_TLBMCF			BIT(5)
-#define FSR_EF				BIT(4)
-#define FSR_PF				BIT(3)
-#define FSR_AFF				BIT(2)
-#define FSR_TF				BIT(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 ARM_SMMU_FSR_MULTI		BIT(31)
+#define ARM_SMMU_FSR_SS			BIT(30)
+#define ARM_SMMU_FSR_UUT		BIT(8)
+#define ARM_SMMU_FSR_ASF		BIT(7)
+#define ARM_SMMU_FSR_TLBLKF		BIT(6)
+#define ARM_SMMU_FSR_TLBMCF		BIT(5)
+#define ARM_SMMU_FSR_EF			BIT(4)
+#define ARM_SMMU_FSR_PF			BIT(3)
+#define ARM_SMMU_FSR_AFF		BIT(2)
+#define ARM_SMMU_FSR_TF			BIT(1)
+
+#define ARM_SMMU_FSR_IGN		(ARM_SMMU_FSR_AFF |		\
+					 ARM_SMMU_FSR_ASF |		\
+					 ARM_SMMU_FSR_TLBMCF |		\
+					 ARM_SMMU_FSR_TLBLKF)
+
+#define ARM_SMMU_FSR_FAULT		(ARM_SMMU_FSR_MULTI |		\
+					 ARM_SMMU_FSR_SS |		\
+					 ARM_SMMU_FSR_UUT |		\
+					 ARM_SMMU_FSR_EF |		\
+					 ARM_SMMU_FSR_PF |		\
+					 ARM_SMMU_FSR_TF |		\
+					 ARM_SMMU_FSR_IGN)
 
 #define ARM_SMMU_CB_FAR			0x60
 
 #define ARM_SMMU_CB_FSYNR0		0x68
-#define FSYNR0_WNR			BIT(4)
+#define ARM_SMMU_FSYNR0_WNR		BIT(4)
 
 #define ARM_SMMU_CB_S1_TLBIVA		0x600
 #define ARM_SMMU_CB_S1_TLBIASID		0x610
@@ -203,7 +230,7 @@ enum arm_smmu_cbar_type {
 #define ARM_SMMU_CB_ATS1PR		0x800
 
 #define ARM_SMMU_CB_ATSR		0x8f0
-#define ATSR_ACTIVE			BIT(0)
+#define ARM_SMMU_ATSR_ACTIVE		BIT(0)
 
 
 /* Maximum number of context banks per SMMU */
@@ -297,7 +324,7 @@ struct arm_smmu_cfg {
 	enum arm_smmu_cbar_type		cbar;
 	enum arm_smmu_context_fmt	fmt;
 };
-#define INVALID_IRPTNDX			0xff
+#define ARM_SMMU_INVALID_IRPTNDX	0xff
 
 enum arm_smmu_domain_stage {
 	ARM_SMMU_DOMAIN_S1 = 0,
@@ -318,6 +345,33 @@ struct arm_smmu_domain {
 	struct iommu_domain		domain;
 };
 
+static inline u32 arm_smmu_lpae_tcr(struct io_pgtable_cfg *cfg)
+{
+	return ARM_SMMU_TCR_EPD1 |
+	       FIELD_PREP(ARM_SMMU_TCR_TG0, cfg->arm_lpae_s1_cfg.tcr.tg) |
+	       FIELD_PREP(ARM_SMMU_TCR_SH0, cfg->arm_lpae_s1_cfg.tcr.sh) |
+	       FIELD_PREP(ARM_SMMU_TCR_ORGN0, cfg->arm_lpae_s1_cfg.tcr.orgn) |
+	       FIELD_PREP(ARM_SMMU_TCR_IRGN0, cfg->arm_lpae_s1_cfg.tcr.irgn) |
+	       FIELD_PREP(ARM_SMMU_TCR_T0SZ, cfg->arm_lpae_s1_cfg.tcr.tsz);
+}
+
+static inline u32 arm_smmu_lpae_tcr2(struct io_pgtable_cfg *cfg)
+{
+	return FIELD_PREP(ARM_SMMU_TCR2_PASIZE, cfg->arm_lpae_s1_cfg.tcr.ips) |
+	       FIELD_PREP(ARM_SMMU_TCR2_SEP, ARM_SMMU_TCR2_SEP_UPSTREAM);
+}
+
+static inline u32 arm_smmu_lpae_vtcr(struct io_pgtable_cfg *cfg)
+{
+	return ARM_SMMU_VTCR_RES1 |
+	       FIELD_PREP(ARM_SMMU_VTCR_PS, cfg->arm_lpae_s2_cfg.vtcr.ps) |
+	       FIELD_PREP(ARM_SMMU_VTCR_TG0, cfg->arm_lpae_s2_cfg.vtcr.tg) |
+	       FIELD_PREP(ARM_SMMU_VTCR_SH0, cfg->arm_lpae_s2_cfg.vtcr.sh) |
+	       FIELD_PREP(ARM_SMMU_VTCR_ORGN0, cfg->arm_lpae_s2_cfg.vtcr.orgn) |
+	       FIELD_PREP(ARM_SMMU_VTCR_IRGN0, cfg->arm_lpae_s2_cfg.vtcr.irgn) |
+	       FIELD_PREP(ARM_SMMU_VTCR_SL0, cfg->arm_lpae_s2_cfg.vtcr.sl) |
+	       FIELD_PREP(ARM_SMMU_VTCR_T0SZ, cfg->arm_lpae_s2_cfg.vtcr.tsz);
+}
 
 /* Implementation details, yay! */
 struct arm_smmu_impl {
diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
index 7c3bd2c3cdca..4272fe4e17f4 100644
--- a/drivers/iommu/io-pgtable-arm-v7s.c
+++ b/drivers/iommu/io-pgtable-arm-v7s.c
@@ -149,8 +149,6 @@
 #define ARM_V7S_TTBR_IRGN_ATTR(attr)					\
 	((((attr) & 0x1) << 6) | (((attr) & 0x2) >> 1))
 
-#define ARM_V7S_TCR_PD1			BIT(5)
-
 #ifdef CONFIG_ZONE_DMA32
 #define ARM_V7S_TABLE_GFP_DMA GFP_DMA32
 #define ARM_V7S_TABLE_SLAB_FLAGS SLAB_CACHE_DMA32
@@ -798,8 +796,8 @@ static struct io_pgtable *arm_v7s_alloc_pgtable(struct io_pgtable_cfg *cfg,
 	 */
 	cfg->pgsize_bitmap &= SZ_4K | SZ_64K | SZ_1M | SZ_16M;
 
-	/* TCR: T0SZ=0, disable TTBR1 */
-	cfg->arm_v7s_cfg.tcr = ARM_V7S_TCR_PD1;
+	/* TCR: T0SZ=0, EAE=0 (if applicable) */
+	cfg->arm_v7s_cfg.tcr = 0;
 
 	/*
 	 * TEX remap: the indices used map to the closest equivalent types
@@ -822,15 +820,13 @@ static struct io_pgtable *arm_v7s_alloc_pgtable(struct io_pgtable_cfg *cfg,
 	/* Ensure the empty pgd is visible before any actual TTBR write */
 	wmb();
 
-	/* TTBRs */
-	cfg->arm_v7s_cfg.ttbr[0] = virt_to_phys(data->pgd) |
-				   ARM_V7S_TTBR_S | ARM_V7S_TTBR_NOS |
-				   (cfg->coherent_walk ?
-				   (ARM_V7S_TTBR_IRGN_ATTR(ARM_V7S_RGN_WBWA) |
-				    ARM_V7S_TTBR_ORGN_ATTR(ARM_V7S_RGN_WBWA)) :
-				   (ARM_V7S_TTBR_IRGN_ATTR(ARM_V7S_RGN_NC) |
-				    ARM_V7S_TTBR_ORGN_ATTR(ARM_V7S_RGN_NC)));
-	cfg->arm_v7s_cfg.ttbr[1] = 0;
+	/* TTBR */
+	cfg->arm_v7s_cfg.ttbr = virt_to_phys(data->pgd) | ARM_V7S_TTBR_S |
+				(cfg->coherent_walk ? (ARM_V7S_TTBR_NOS |
+				 ARM_V7S_TTBR_IRGN_ATTR(ARM_V7S_RGN_WBWA) |
+				 ARM_V7S_TTBR_ORGN_ATTR(ARM_V7S_RGN_WBWA)) :
+				(ARM_V7S_TTBR_IRGN_ATTR(ARM_V7S_RGN_NC) |
+				 ARM_V7S_TTBR_ORGN_ATTR(ARM_V7S_RGN_NC)));
 	return &data->iop;
 
 out_free_data:
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index bdf47f745268..983b08477e64 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -100,40 +100,29 @@
 #define ARM_LPAE_PTE_MEMATTR_DEV	(((arm_lpae_iopte)0x1) << 2)
 
 /* Register bits */
-#define ARM_32_LPAE_TCR_EAE		(1 << 31)
-#define ARM_64_LPAE_S2_TCR_RES1		(1 << 31)
+#define ARM_LPAE_TCR_TG0_4K		0
+#define ARM_LPAE_TCR_TG0_64K		1
+#define ARM_LPAE_TCR_TG0_16K		2
 
-#define ARM_LPAE_TCR_EPD1		(1 << 23)
+#define ARM_LPAE_TCR_TG1_16K		1
+#define ARM_LPAE_TCR_TG1_4K		2
+#define ARM_LPAE_TCR_TG1_64K		3
 
-#define ARM_LPAE_TCR_TG0_4K		(0 << 14)
-#define ARM_LPAE_TCR_TG0_64K		(1 << 14)
-#define ARM_LPAE_TCR_TG0_16K		(2 << 14)
-
-#define ARM_LPAE_TCR_SH0_SHIFT		12
-#define ARM_LPAE_TCR_SH0_MASK		0x3
 #define ARM_LPAE_TCR_SH_NS		0
 #define ARM_LPAE_TCR_SH_OS		2
 #define ARM_LPAE_TCR_SH_IS		3
 
-#define ARM_LPAE_TCR_ORGN0_SHIFT	10
-#define ARM_LPAE_TCR_IRGN0_SHIFT	8
-#define ARM_LPAE_TCR_RGN_MASK		0x3
 #define ARM_LPAE_TCR_RGN_NC		0
 #define ARM_LPAE_TCR_RGN_WBWA		1
 #define ARM_LPAE_TCR_RGN_WT		2
 #define ARM_LPAE_TCR_RGN_WB		3
 
-#define ARM_LPAE_TCR_SL0_SHIFT		6
-#define ARM_LPAE_TCR_SL0_MASK		0x3
+#define ARM_LPAE_VTCR_SL0_MASK		0x3
 
 #define ARM_LPAE_TCR_T0SZ_SHIFT		0
-#define ARM_LPAE_TCR_SZ_MASK		0xf
-
-#define ARM_LPAE_TCR_PS_SHIFT		16
-#define ARM_LPAE_TCR_PS_MASK		0x7
 
-#define ARM_LPAE_TCR_IPS_SHIFT		32
-#define ARM_LPAE_TCR_IPS_MASK		0x7
+#define ARM_LPAE_VTCR_PS_SHIFT		16
+#define ARM_LPAE_VTCR_PS_MASK		0x7
 
 #define ARM_LPAE_TCR_PS_32_BIT		0x0ULL
 #define ARM_LPAE_TCR_PS_36_BIT		0x1ULL
@@ -293,17 +282,11 @@ static void __arm_lpae_init_pte(struct arm_lpae_io_pgtable *data,
 {
 	arm_lpae_iopte pte = prot;
 
-	if (data->iop.cfg.quirks & IO_PGTABLE_QUIRK_ARM_NS)
-		pte |= ARM_LPAE_PTE_NS;
-
 	if (data->iop.fmt != ARM_MALI_LPAE && lvl == ARM_LPAE_MAX_LEVELS - 1)
 		pte |= ARM_LPAE_PTE_TYPE_PAGE;
 	else
 		pte |= ARM_LPAE_PTE_TYPE_BLOCK;
 
-	if (data->iop.fmt != ARM_MALI_LPAE)
-		pte |= ARM_LPAE_PTE_AF;
-	pte |= ARM_LPAE_PTE_SH_IS;
 	pte |= paddr_to_iopte(paddr, data);
 
 	__arm_lpae_set_pte(ptep, pte, &data->iop.cfg);
@@ -460,9 +443,20 @@ static arm_lpae_iopte arm_lpae_prot_to_pte(struct arm_lpae_io_pgtable *data,
 				<< ARM_LPAE_PTE_ATTRINDX_SHIFT);
 	}
 
+	if (prot & IOMMU_CACHE)
+		pte |= ARM_LPAE_PTE_SH_IS;
+	else
+		pte |= ARM_LPAE_PTE_SH_OS;
+
 	if (prot & IOMMU_NOEXEC)
 		pte |= ARM_LPAE_PTE_XN;
 
+	if (data->iop.cfg.quirks & IO_PGTABLE_QUIRK_ARM_NS)
+		pte |= ARM_LPAE_PTE_NS;
+
+	if (data->iop.fmt != ARM_MALI_LPAE)
+		pte |= ARM_LPAE_PTE_AF;
+
 	return pte;
 }
 
@@ -474,6 +468,7 @@ static int arm_lpae_map(struct io_pgtable_ops *ops, unsigned long iova,
 	arm_lpae_iopte *ptep = data->pgd;
 	int ret, lvl = data->start_level;
 	arm_lpae_iopte prot;
+	long iaext = (long)iova >> cfg->ias;
 
 	/* If no access, then nothing to do */
 	if (!(iommu_prot & (IOMMU_READ | IOMMU_WRITE)))
@@ -482,7 +477,9 @@ static int arm_lpae_map(struct io_pgtable_ops *ops, unsigned long iova,
 	if (WARN_ON(!size || (size & cfg->pgsize_bitmap) != size))
 		return -EINVAL;
 
-	if (WARN_ON(iova >> data->iop.cfg.ias || paddr >> data->iop.cfg.oas))
+	if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_TTBR1)
+		iaext = ~iaext;
+	if (WARN_ON(iaext || paddr >> cfg->oas))
 		return -ERANGE;
 
 	prot = arm_lpae_prot_to_pte(data, iommu_prot);
@@ -648,11 +645,14 @@ static size_t arm_lpae_unmap(struct io_pgtable_ops *ops, unsigned long iova,
 	struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops);
 	struct io_pgtable_cfg *cfg = &data->iop.cfg;
 	arm_lpae_iopte *ptep = data->pgd;
+	long iaext = (long)iova >> cfg->ias;
 
 	if (WARN_ON(!size || (size & cfg->pgsize_bitmap) != size))
 		return 0;
 
-	if (WARN_ON(iova >> data->iop.cfg.ias))
+	if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_TTBR1)
+		iaext = ~iaext;
+	if (WARN_ON(iaext))
 		return 0;
 
 	return __arm_lpae_unmap(data, gather, iova, size, data->start_level, ptep);
@@ -787,9 +787,12 @@ arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
 {
 	u64 reg;
 	struct arm_lpae_io_pgtable *data;
+	typeof(&cfg->arm_lpae_s1_cfg.tcr) tcr = &cfg->arm_lpae_s1_cfg.tcr;
+	bool tg1;
 
 	if (cfg->quirks & ~(IO_PGTABLE_QUIRK_ARM_NS |
-			    IO_PGTABLE_QUIRK_NON_STRICT))
+			    IO_PGTABLE_QUIRK_NON_STRICT |
+			    IO_PGTABLE_QUIRK_ARM_TTBR1))
 		return NULL;
 
 	data = arm_lpae_alloc_pgtable(cfg);
@@ -798,58 +801,55 @@ arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
 
 	/* TCR */
 	if (cfg->coherent_walk) {
-		reg = (ARM_LPAE_TCR_SH_IS << ARM_LPAE_TCR_SH0_SHIFT) |
-		      (ARM_LPAE_TCR_RGN_WBWA << ARM_LPAE_TCR_IRGN0_SHIFT) |
-		      (ARM_LPAE_TCR_RGN_WBWA << ARM_LPAE_TCR_ORGN0_SHIFT);
+		tcr->sh = ARM_LPAE_TCR_SH_IS;
+		tcr->irgn = ARM_LPAE_TCR_RGN_WBWA;
+		tcr->orgn = ARM_LPAE_TCR_RGN_WBWA;
 	} else {
-		reg = (ARM_LPAE_TCR_SH_OS << ARM_LPAE_TCR_SH0_SHIFT) |
-		      (ARM_LPAE_TCR_RGN_NC << ARM_LPAE_TCR_IRGN0_SHIFT) |
-		      (ARM_LPAE_TCR_RGN_NC << ARM_LPAE_TCR_ORGN0_SHIFT);
+		tcr->sh = ARM_LPAE_TCR_SH_OS;
+		tcr->irgn = ARM_LPAE_TCR_RGN_NC;
+		tcr->orgn = ARM_LPAE_TCR_RGN_NC;
 	}
 
+	tg1 = cfg->quirks & IO_PGTABLE_QUIRK_ARM_TTBR1;
 	switch (ARM_LPAE_GRANULE(data)) {
 	case SZ_4K:
-		reg |= ARM_LPAE_TCR_TG0_4K;
+		tcr->tg = tg1 ? ARM_LPAE_TCR_TG1_4K : ARM_LPAE_TCR_TG0_4K;
 		break;
 	case SZ_16K:
-		reg |= ARM_LPAE_TCR_TG0_16K;
+		tcr->tg = tg1 ? ARM_LPAE_TCR_TG1_16K : ARM_LPAE_TCR_TG0_16K;
 		break;
 	case SZ_64K:
-		reg |= ARM_LPAE_TCR_TG0_64K;
+		tcr->tg = tg1 ? ARM_LPAE_TCR_TG1_64K : ARM_LPAE_TCR_TG0_64K;
 		break;
 	}
 
 	switch (cfg->oas) {
 	case 32:
-		reg |= (ARM_LPAE_TCR_PS_32_BIT << ARM_LPAE_TCR_IPS_SHIFT);
+		tcr->ips = ARM_LPAE_TCR_PS_32_BIT;
 		break;
 	case 36:
-		reg |= (ARM_LPAE_TCR_PS_36_BIT << ARM_LPAE_TCR_IPS_SHIFT);
+		tcr->ips = ARM_LPAE_TCR_PS_36_BIT;
 		break;
 	case 40:
-		reg |= (ARM_LPAE_TCR_PS_40_BIT << ARM_LPAE_TCR_IPS_SHIFT);
+		tcr->ips = ARM_LPAE_TCR_PS_40_BIT;
 		break;
 	case 42:
-		reg |= (ARM_LPAE_TCR_PS_42_BIT << ARM_LPAE_TCR_IPS_SHIFT);
+		tcr->ips = ARM_LPAE_TCR_PS_42_BIT;
 		break;
 	case 44:
-		reg |= (ARM_LPAE_TCR_PS_44_BIT << ARM_LPAE_TCR_IPS_SHIFT);
+		tcr->ips = ARM_LPAE_TCR_PS_44_BIT;
 		break;
 	case 48:
-		reg |= (ARM_LPAE_TCR_PS_48_BIT << ARM_LPAE_TCR_IPS_SHIFT);
+		tcr->ips = ARM_LPAE_TCR_PS_48_BIT;
 		break;
 	case 52:
-		reg |= (ARM_LPAE_TCR_PS_52_BIT << ARM_LPAE_TCR_IPS_SHIFT);
+		tcr->ips = ARM_LPAE_TCR_PS_52_BIT;
 		break;
 	default:
 		goto out_free_data;
 	}
 
-	reg |= (64ULL - cfg->ias) << ARM_LPAE_TCR_T0SZ_SHIFT;
-
-	/* Disable speculative walks through TTBR1 */
-	reg |= ARM_LPAE_TCR_EPD1;
-	cfg->arm_lpae_s1_cfg.tcr = reg;
+	tcr->tsz = 64ULL - cfg->ias;
 
 	/* MAIRs */
 	reg = (ARM_LPAE_MAIR_ATTR_NC
@@ -872,9 +872,8 @@ arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
 	/* Ensure the empty pgd is visible before any actual TTBR write */
 	wmb();
 
-	/* TTBRs */
-	cfg->arm_lpae_s1_cfg.ttbr[0] = virt_to_phys(data->pgd);
-	cfg->arm_lpae_s1_cfg.ttbr[1] = 0;
+	/* TTBR */
+	cfg->arm_lpae_s1_cfg.ttbr = virt_to_phys(data->pgd);
 	return &data->iop;
 
 out_free_data:
@@ -885,8 +884,9 @@ out_free_data:
 static struct io_pgtable *
 arm_64_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie)
 {
-	u64 reg, sl;
+	u64 sl;
 	struct arm_lpae_io_pgtable *data;
+	typeof(&cfg->arm_lpae_s2_cfg.vtcr) vtcr = &cfg->arm_lpae_s2_cfg.vtcr;
 
 	/* The NS quirk doesn't apply at stage 2 */
 	if (cfg->quirks & ~(IO_PGTABLE_QUIRK_NON_STRICT))
@@ -911,55 +911,59 @@ arm_64_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie)
 	}
 
 	/* VTCR */
-	reg = ARM_64_LPAE_S2_TCR_RES1 |
-	     (ARM_LPAE_TCR_SH_IS << ARM_LPAE_TCR_SH0_SHIFT) |
-	     (ARM_LPAE_TCR_RGN_WBWA << ARM_LPAE_TCR_IRGN0_SHIFT) |
-	     (ARM_LPAE_TCR_RGN_WBWA << ARM_LPAE_TCR_ORGN0_SHIFT);
+	if (cfg->coherent_walk) {
+		vtcr->sh = ARM_LPAE_TCR_SH_IS;
+		vtcr->irgn = ARM_LPAE_TCR_RGN_WBWA;
+		vtcr->orgn = ARM_LPAE_TCR_RGN_WBWA;
+	} else {
+		vtcr->sh = ARM_LPAE_TCR_SH_OS;
+		vtcr->irgn = ARM_LPAE_TCR_RGN_NC;
+		vtcr->orgn = ARM_LPAE_TCR_RGN_NC;
+	}
 
 	sl = data->start_level;
 
 	switch (ARM_LPAE_GRANULE(data)) {
 	case SZ_4K:
-		reg |= ARM_LPAE_TCR_TG0_4K;
+		vtcr->tg = ARM_LPAE_TCR_TG0_4K;
 		sl++; /* SL0 format is different for 4K granule size */
 		break;
 	case SZ_16K:
-		reg |= ARM_LPAE_TCR_TG0_16K;
+		vtcr->tg = ARM_LPAE_TCR_TG0_16K;
 		break;
 	case SZ_64K:
-		reg |= ARM_LPAE_TCR_TG0_64K;
+		vtcr->tg = ARM_LPAE_TCR_TG0_64K;
 		break;
 	}
 
 	switch (cfg->oas) {
 	case 32:
-		reg |= (ARM_LPAE_TCR_PS_32_BIT << ARM_LPAE_TCR_PS_SHIFT);
+		vtcr->ps = ARM_LPAE_TCR_PS_32_BIT;
 		break;
 	case 36:
-		reg |= (ARM_LPAE_TCR_PS_36_BIT << ARM_LPAE_TCR_PS_SHIFT);
+		vtcr->ps = ARM_LPAE_TCR_PS_36_BIT;
 		break;
 	case 40:
-		reg |= (ARM_LPAE_TCR_PS_40_BIT << ARM_LPAE_TCR_PS_SHIFT);
+		vtcr->ps = ARM_LPAE_TCR_PS_40_BIT;
 		break;
 	case 42:
-		reg |= (ARM_LPAE_TCR_PS_42_BIT << ARM_LPAE_TCR_PS_SHIFT);
+		vtcr->ps = ARM_LPAE_TCR_PS_42_BIT;
 		break;
 	case 44:
-		reg |= (ARM_LPAE_TCR_PS_44_BIT << ARM_LPAE_TCR_PS_SHIFT);
+		vtcr->ps = ARM_LPAE_TCR_PS_44_BIT;
 		break;
 	case 48:
-		reg |= (ARM_LPAE_TCR_PS_48_BIT << ARM_LPAE_TCR_PS_SHIFT);
+		vtcr->ps = ARM_LPAE_TCR_PS_48_BIT;
 		break;
 	case 52:
-		reg |= (ARM_LPAE_TCR_PS_52_BIT << ARM_LPAE_TCR_PS_SHIFT);
+		vtcr->ps = ARM_LPAE_TCR_PS_52_BIT;
 		break;
 	default:
 		goto out_free_data;
 	}
 
-	reg |= (64ULL - cfg->ias) << ARM_LPAE_TCR_T0SZ_SHIFT;
-	reg |= (~sl & ARM_LPAE_TCR_SL0_MASK) << ARM_LPAE_TCR_SL0_SHIFT;
-	cfg->arm_lpae_s2_cfg.vtcr = reg;
+	vtcr->tsz = 64ULL - cfg->ias;
+	vtcr->sl = ~sl & ARM_LPAE_VTCR_SL0_MASK;
 
 	/* Allocate pgd pages */
 	data->pgd = __arm_lpae_alloc_pages(ARM_LPAE_PGD_SIZE(data),
@@ -982,35 +986,21 @@ out_free_data:
 static struct io_pgtable *
 arm_32_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
 {
-	struct io_pgtable *iop;
-
 	if (cfg->ias > 32 || cfg->oas > 40)
 		return NULL;
 
 	cfg->pgsize_bitmap &= (SZ_4K | SZ_2M | SZ_1G);
-	iop = arm_64_lpae_alloc_pgtable_s1(cfg, cookie);
-	if (iop) {
-		cfg->arm_lpae_s1_cfg.tcr |= ARM_32_LPAE_TCR_EAE;
-		cfg->arm_lpae_s1_cfg.tcr &= 0xffffffff;
-	}
-
-	return iop;
+	return arm_64_lpae_alloc_pgtable_s1(cfg, cookie);
 }
 
 static struct io_pgtable *
 arm_32_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie)
 {
-	struct io_pgtable *iop;
-
 	if (cfg->ias > 40 || cfg->oas > 40)
 		return NULL;
 
 	cfg->pgsize_bitmap &= (SZ_4K | SZ_2M | SZ_1G);
-	iop = arm_64_lpae_alloc_pgtable_s2(cfg, cookie);
-	if (iop)
-		cfg->arm_lpae_s2_cfg.vtcr &= 0xffffffff;
-
-	return iop;
+	return arm_64_lpae_alloc_pgtable_s2(cfg, cookie);
 }
 
 static struct io_pgtable *
diff --git a/drivers/iommu/io-pgtable.c b/drivers/iommu/io-pgtable.c
index ced53e5b72b5..94394c81468f 100644
--- a/drivers/iommu/io-pgtable.c
+++ b/drivers/iommu/io-pgtable.c
@@ -63,7 +63,7 @@ void free_io_pgtable_ops(struct io_pgtable_ops *ops)
 	if (!ops)
 		return;
 
-	iop = container_of(ops, struct io_pgtable, ops);
+	iop = io_pgtable_ops_to_pgtable(ops);
 	io_pgtable_tlb_flush_all(iop);
 	io_pgtable_init_table[iop->fmt]->free(iop);
 }
diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c
index d02edd2751f3..ecb3f9464dd5 100644
--- a/drivers/iommu/ipmmu-vmsa.c
+++ b/drivers/iommu/ipmmu-vmsa.c
@@ -374,7 +374,7 @@ static void ipmmu_domain_setup_context(struct ipmmu_vmsa_domain *domain)
 	u32 tmp;
 
 	/* TTBR0 */
-	ttbr = domain->cfg.arm_lpae_s1_cfg.ttbr[0];
+	ttbr = domain->cfg.arm_lpae_s1_cfg.ttbr;
 	ipmmu_ctx_write_root(domain, IMTTLBR0, ttbr);
 	ipmmu_ctx_write_root(domain, IMTTUBR0, ttbr >> 32);
 
diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c
index 93f14bca26ee..94a6df1bddd6 100644
--- a/drivers/iommu/msm_iommu.c
+++ b/drivers/iommu/msm_iommu.c
@@ -279,8 +279,8 @@ static void __program_context(void __iomem *base, int ctx,
 	SET_V2PCFG(base, ctx, 0x3);
 
 	SET_TTBCR(base, ctx, priv->cfg.arm_v7s_cfg.tcr);
-	SET_TTBR0(base, ctx, priv->cfg.arm_v7s_cfg.ttbr[0]);
-	SET_TTBR1(base, ctx, priv->cfg.arm_v7s_cfg.ttbr[1]);
+	SET_TTBR0(base, ctx, priv->cfg.arm_v7s_cfg.ttbr);
+	SET_TTBR1(base, ctx, 0);
 
 	/* Set prrr and nmrr */
 	SET_PRRR(base, ctx, priv->cfg.arm_v7s_cfg.prrr);
diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index 6fc1f5ecf91e..95945f467c03 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -367,7 +367,7 @@ static int mtk_iommu_attach_device(struct iommu_domain *domain,
 	/* Update the pgtable base address register of the M4U HW */
 	if (!data->m4u_dom) {
 		data->m4u_dom = dom;
-		writel(dom->cfg.arm_v7s_cfg.ttbr[0] & MMU_PT_ADDR_MASK,
+		writel(dom->cfg.arm_v7s_cfg.ttbr & MMU_PT_ADDR_MASK,
 		       data->base + REG_MMU_PT_BASE_ADDR);
 	}
 
@@ -765,7 +765,7 @@ static int __maybe_unused mtk_iommu_resume(struct device *dev)
 	writel_relaxed(reg->ivrp_paddr, base + REG_MMU_IVRP_PADDR);
 	writel_relaxed(reg->vld_pa_rng, base + REG_MMU_VLD_PA_RNG);
 	if (m4u_dom)
-		writel(m4u_dom->cfg.arm_v7s_cfg.ttbr[0] & MMU_PT_ADDR_MASK,
+		writel(m4u_dom->cfg.arm_v7s_cfg.ttbr & MMU_PT_ADDR_MASK,
 		       base + REG_MMU_PT_BASE_ADDR);
 	return 0;
 }
diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c
index e7bc8b721947..20738aacac89 100644
--- a/drivers/iommu/of_iommu.c
+++ b/drivers/iommu/of_iommu.c
@@ -203,8 +203,12 @@ const struct iommu_ops *of_iommu_configure(struct device *dev,
 			if (err)
 				break;
 		}
-	}
 
+		fwspec = dev_iommu_fwspec_get(dev);
+		if (!err && fwspec)
+			of_property_read_u32(master_np, "pasid-num-bits",
+					     &fwspec->num_pasid_bits);
+	}
 
 	/*
 	 * Two success conditions can be represented by non-negative err here:
diff --git a/drivers/iommu/qcom_iommu.c b/drivers/iommu/qcom_iommu.c
index 52f38292df5b..39759db4f003 100644
--- a/drivers/iommu/qcom_iommu.c
+++ b/drivers/iommu/qcom_iommu.c
@@ -201,7 +201,7 @@ static irqreturn_t qcom_iommu_fault(int irq, void *dev)
 
 	fsr = iommu_readl(ctx, ARM_SMMU_CB_FSR);
 
-	if (!(fsr & FSR_FAULT))
+	if (!(fsr & ARM_SMMU_FSR_FAULT))
 		return IRQ_NONE;
 
 	fsynr = iommu_readl(ctx, ARM_SMMU_CB_FSYNR0);
@@ -215,7 +215,7 @@ static irqreturn_t qcom_iommu_fault(int irq, void *dev)
 	}
 
 	iommu_writel(ctx, ARM_SMMU_CB_FSR, fsr);
-	iommu_writel(ctx, ARM_SMMU_CB_RESUME, RESUME_TERMINATE);
+	iommu_writel(ctx, ARM_SMMU_CB_RESUME, ARM_SMMU_RESUME_TERMINATE);
 
 	return IRQ_HANDLED;
 }
@@ -269,18 +269,15 @@ static int qcom_iommu_init_domain(struct iommu_domain *domain,
 
 		/* TTBRs */
 		iommu_writeq(ctx, ARM_SMMU_CB_TTBR0,
-				pgtbl_cfg.arm_lpae_s1_cfg.ttbr[0] |
-				FIELD_PREP(TTBRn_ASID, ctx->asid));
-		iommu_writeq(ctx, ARM_SMMU_CB_TTBR1,
-				pgtbl_cfg.arm_lpae_s1_cfg.ttbr[1] |
-				FIELD_PREP(TTBRn_ASID, ctx->asid));
+				pgtbl_cfg.arm_lpae_s1_cfg.ttbr |
+				FIELD_PREP(ARM_SMMU_TTBRn_ASID, ctx->asid));
+		iommu_writeq(ctx, ARM_SMMU_CB_TTBR1, 0);
 
 		/* TCR */
 		iommu_writel(ctx, ARM_SMMU_CB_TCR2,
-				(pgtbl_cfg.arm_lpae_s1_cfg.tcr >> 32) |
-				FIELD_PREP(TCR2_SEP, TCR2_SEP_UPSTREAM));
+				arm_smmu_lpae_tcr2(&pgtbl_cfg));
 		iommu_writel(ctx, ARM_SMMU_CB_TCR,
-				pgtbl_cfg.arm_lpae_s1_cfg.tcr);
+			     arm_smmu_lpae_tcr(&pgtbl_cfg) | ARM_SMMU_TCR_EAE);
 
 		/* MAIRs (stage-1 only) */
 		iommu_writel(ctx, ARM_SMMU_CB_S1_MAIR0,
@@ -289,11 +286,13 @@ static int qcom_iommu_init_domain(struct iommu_domain *domain,
 				pgtbl_cfg.arm_lpae_s1_cfg.mair >> 32);
 
 		/* SCTLR */
-		reg = SCTLR_CFIE | SCTLR_CFRE | SCTLR_AFE | SCTLR_TRE |
-			SCTLR_M | SCTLR_S1_ASIDPNE | SCTLR_CFCFG;
+		reg = ARM_SMMU_SCTLR_CFIE | ARM_SMMU_SCTLR_CFRE |
+		      ARM_SMMU_SCTLR_AFE | ARM_SMMU_SCTLR_TRE |
+		      ARM_SMMU_SCTLR_M | ARM_SMMU_SCTLR_S1_ASIDPNE |
+		      ARM_SMMU_SCTLR_CFCFG;
 
 		if (IS_ENABLED(CONFIG_BIG_ENDIAN))
-			reg |= SCTLR_E;
+			reg |= ARM_SMMU_SCTLR_E;
 
 		iommu_writel(ctx, ARM_SMMU_CB_SCTLR, reg);