iommu/arm-smmu-v3: Add support for VHE

ARMv8.1 extensions added Virtualization Host Extensions (VHE), which allow
to run a host kernel at EL2. When using normal DMA, Device and CPU address
spaces are dissociated, and do not need to implement the same
capabilities, so VHE hasn't been used in the SMMU until now.

With shared address spaces however, ASIDs are shared between MMU and SMMU,
and broadcast TLB invalidations issued by a CPU are taken into account by
the SMMU. TLB entries on both sides need to have identical exception level
in order to be cleared with a single invalidation.

When the CPU is using VHE, enable VHE in the SMMU for all STEs. Normal DMA
mappings will need to use TLBI_EL2 commands instead of TLBI_NH, but
shouldn't be otherwise affected by this change.
Acked-by: NWill Deacon <will@kernel.org>
Reviewed-by: NJonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: NJean-Philippe Brucker <jean-philippe@linaro.org>
Link: https://lore.kernel.org/r/20210122151054.2833521-4-jean-philippe@linaro.orgSigned-off-by: NWill Deacon <will@kernel.org>

drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c

@@ -263,9 +263,11 @@ static int arm_smmu_cmdq_build_cmd(u64 *cmd, struct arm_smmu_cmdq_ent *ent)
 		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);
+		fallthrough;
+	case CMDQ_OP_TLBI_EL2_VA:
 		cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_NUM, ent->tlbi.num);
 		cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_SCALE, ent->tlbi.scale);
-		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] |= FIELD_PREP(CMDQ_TLBI_1_TTL, ent->tlbi.ttl);
@@ -287,6 +289,9 @@ static int arm_smmu_cmdq_build_cmd(u64 *cmd, struct arm_smmu_cmdq_ent *ent)
 	case CMDQ_OP_TLBI_S12_VMALL:
 		cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_VMID, ent->tlbi.vmid);
 		break;
+	case CMDQ_OP_TLBI_EL2_ASID:
+		cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_ASID, ent->tlbi.asid);
+		break;
 	case CMDQ_OP_ATC_INV:
 		cmd[0] |= FIELD_PREP(CMDQ_0_SSV, ent->substream_valid);
 		cmd[0] |= FIELD_PREP(CMDQ_ATC_0_GLOBAL, ent->atc.global);
@@ -877,7 +882,8 @@ static int arm_smmu_cmdq_batch_submit(struct arm_smmu_device *smmu,
 void arm_smmu_tlb_inv_asid(struct arm_smmu_device *smmu, u16 asid)
 {
 	struct arm_smmu_cmdq_ent cmd = {
-		.opcode = CMDQ_OP_TLBI_NH_ASID,
+		.opcode	= smmu->features & ARM_SMMU_FEAT_E2H ?
+			CMDQ_OP_TLBI_EL2_ASID : CMDQ_OP_TLBI_NH_ASID,
 		.tlbi.asid = asid,
 	};
 
@@ -1260,13 +1266,16 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 	}
 
 	if (s1_cfg) {
+		u64 strw = smmu->features & ARM_SMMU_FEAT_E2H ?
+			STRTAB_STE_1_STRW_EL2 : STRTAB_STE_1_STRW_NSEL1;
+
 		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) |
-			 FIELD_PREP(STRTAB_STE_1_STRW, STRTAB_STE_1_STRW_NSEL1));
+			 FIELD_PREP(STRTAB_STE_1_STRW, strw));
 
 		if (smmu->features & ARM_SMMU_FEAT_STALLS &&
 		   !(smmu->features & ARM_SMMU_FEAT_STALL_FORCE))
@@ -1728,7 +1737,8 @@ static void arm_smmu_tlb_inv_range_domain(unsigned long iova, size_t size,
 	};
 
 	if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) {
-		cmd.opcode	= CMDQ_OP_TLBI_NH_VA;
+		cmd.opcode	= smmu_domain->smmu->features & ARM_SMMU_FEAT_E2H ?
+				  CMDQ_OP_TLBI_EL2_VA : CMDQ_OP_TLBI_NH_VA;
 		cmd.tlbi.asid	= smmu_domain->s1_cfg.cd.asid;
 	} else {
 		cmd.opcode	= CMDQ_OP_TLBI_S2_IPA;
@@ -1748,7 +1758,8 @@ void arm_smmu_tlb_inv_range_asid(unsigned long iova, size_t size, int asid,
 				 struct arm_smmu_domain *smmu_domain)
 {
 	struct arm_smmu_cmdq_ent cmd = {
-		.opcode	= CMDQ_OP_TLBI_NH_VA,
+		.opcode	= smmu_domain->smmu->features & ARM_SMMU_FEAT_E2H ?
+			  CMDQ_OP_TLBI_EL2_VA : CMDQ_OP_TLBI_NH_VA,
 		.tlbi = {
 			.asid	= asid,
 			.leaf	= leaf,
@@ -3076,7 +3087,11 @@ static int arm_smmu_device_reset(struct arm_smmu_device *smmu, bool bypass)
 	writel_relaxed(reg, smmu->base + ARM_SMMU_CR1);
 
 	/* CR2 (random crap) */
-	reg = CR2_PTM | CR2_RECINVSID | CR2_E2H;
+	reg = CR2_PTM | CR2_RECINVSID;
+
+	if (smmu->features & ARM_SMMU_FEAT_E2H)
+		reg |= CR2_E2H;
+
 	writel_relaxed(reg, smmu->base + ARM_SMMU_CR2);
 
 	/* Stream table */
@@ -3235,8 +3250,11 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu)
 			smmu->options |= ARM_SMMU_OPT_MSIPOLL;
 	}
 
-	if (reg & IDR0_HYP)
+	if (reg & IDR0_HYP) {
 		smmu->features |= ARM_SMMU_FEAT_HYP;
+		if (cpus_have_cap(ARM64_HAS_VIRT_HOST_EXTN))
+			smmu->features |= ARM_SMMU_FEAT_E2H;
+	}
 
 	/*
 	 * The coherency feature as set by FW is used in preference to the ID

drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h

@@ -430,6 +430,8 @@ struct arm_smmu_cmdq_ent {
 		#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_EL2_ASID	0x21
+		#define CMDQ_OP_TLBI_EL2_VA	0x22
 		#define CMDQ_OP_TLBI_S12_VMALL	0x28
 		#define CMDQ_OP_TLBI_S2_IPA	0x2a
 		#define CMDQ_OP_TLBI_NSNH_ALL	0x30
@@ -604,6 +606,7 @@ struct arm_smmu_device {
 #define ARM_SMMU_FEAT_RANGE_INV		(1 << 15)
 #define ARM_SMMU_FEAT_BTM		(1 << 16)
 #define ARM_SMMU_FEAT_SVA		(1 << 17)
+#define ARM_SMMU_FEAT_E2H		(1 << 18)
 	u32				features;
 
 #define ARM_SMMU_OPT_SKIP_PREFETCH	(1 << 0)