3 files changed, 68 insertions, 5 deletions

diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
index 3fd83fb75722..9b0dc3505601 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -894,6 +894,12 @@ static void arm_smmu_cmdq_batch_add(struct arm_smmu_device *smmu,
 {
 	int index;
 
+	if (cmds->num == CMDQ_BATCH_ENTRIES - 1 &&
+	    (smmu->options & ARM_SMMU_OPT_CMDQ_FORCE_SYNC)) {
+		arm_smmu_cmdq_issue_cmdlist(smmu, cmds->cmds, cmds->num, true);
+		cmds->num = 0;
+	}
+
 	if (cmds->num == CMDQ_BATCH_ENTRIES) {
 		arm_smmu_cmdq_issue_cmdlist(smmu, cmds->cmds, cmds->num, false);
 		cmds->num = 0;
@@ -1892,8 +1898,13 @@ static void __arm_smmu_tlb_inv_range(struct arm_smmu_cmdq_ent *cmd,
 		/* Convert page size of 12,14,16 (log2) to 1,2,3 */
 		cmd->tlbi.tg = (tg - 10) / 2;
 
-		/* Determine what level the granule is at */
-		cmd->tlbi.ttl = 4 - ((ilog2(granule) - 3) / (tg - 3));
+		/*
+		 * Determine what level the granule is at. For non-leaf, io-pgtable
+		 * assumes .tlb_flush_walk can invalidate multiple levels at once,
+		 * so ignore the nominal last-level granule and leave TTL=0.
+		 */
+		if (cmd->tlbi.leaf)
+			cmd->tlbi.ttl = 4 - ((ilog2(granule) - 3) / (tg - 3));
 
 		num_pages = size >> tg;
 	}
@@ -2008,6 +2019,7 @@ static bool arm_smmu_capable(struct device *dev, enum iommu_cap cap)
 		/* Assume that a coherent TCU implies coherent TBUs */
 		return master->smmu->features & ARM_SMMU_FEAT_COHERENCY;
 	case IOMMU_CAP_NOEXEC:
+	case IOMMU_CAP_DEFERRED_FLUSH:
 		return true;
 	default:
 		return false;
@@ -2023,7 +2035,6 @@ static struct iommu_domain *arm_smmu_domain_alloc(unsigned type)
 
 	if (type != IOMMU_DOMAIN_UNMANAGED &&
 	    type != IOMMU_DOMAIN_DMA &&
-	    type != IOMMU_DOMAIN_DMA_FQ &&
 	    type != IOMMU_DOMAIN_IDENTITY)
 		return NULL;
 
@@ -3429,6 +3440,44 @@ static int arm_smmu_device_reset(struct arm_smmu_device *smmu, bool bypass)
 	return 0;
 }
 
+#define IIDR_IMPLEMENTER_ARM		0x43b
+#define IIDR_PRODUCTID_ARM_MMU_600	0x483
+#define IIDR_PRODUCTID_ARM_MMU_700	0x487
+
+static void arm_smmu_device_iidr_probe(struct arm_smmu_device *smmu)
+{
+	u32 reg;
+	unsigned int implementer, productid, variant, revision;
+
+	reg = readl_relaxed(smmu->base + ARM_SMMU_IIDR);
+	implementer = FIELD_GET(IIDR_IMPLEMENTER, reg);
+	productid = FIELD_GET(IIDR_PRODUCTID, reg);
+	variant = FIELD_GET(IIDR_VARIANT, reg);
+	revision = FIELD_GET(IIDR_REVISION, reg);
+
+	switch (implementer) {
+	case IIDR_IMPLEMENTER_ARM:
+		switch (productid) {
+		case IIDR_PRODUCTID_ARM_MMU_600:
+			/* Arm erratum 1076982 */
+			if (variant == 0 && revision <= 2)
+				smmu->features &= ~ARM_SMMU_FEAT_SEV;
+			/* Arm erratum 1209401 */
+			if (variant < 2)
+				smmu->features &= ~ARM_SMMU_FEAT_NESTING;
+			break;
+		case IIDR_PRODUCTID_ARM_MMU_700:
+			/* Arm erratum 2812531 */
+			smmu->features &= ~ARM_SMMU_FEAT_BTM;
+			smmu->options |= ARM_SMMU_OPT_CMDQ_FORCE_SYNC;
+			/* Arm errata 2268618, 2812531 */
+			smmu->features &= ~ARM_SMMU_FEAT_NESTING;
+			break;
+		}
+		break;
+	}
+}
+
 static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu)
 {
 	u32 reg;
@@ -3635,6 +3684,12 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu)
 
 	smmu->ias = max(smmu->ias, smmu->oas);
 
+	if ((smmu->features & ARM_SMMU_FEAT_TRANS_S1) &&
+	    (smmu->features & ARM_SMMU_FEAT_TRANS_S2))
+		smmu->features |= ARM_SMMU_FEAT_NESTING;
+
+	arm_smmu_device_iidr_probe(smmu);
+
 	if (arm_smmu_sva_supported(smmu))
 		smmu->features |= ARM_SMMU_FEAT_SVA;
 
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
index b574c58a3487..dcab85698a4e 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
@@ -69,6 +69,12 @@
 #define IDR5_VAX			GENMASK(11, 10)
 #define IDR5_VAX_52_BIT			1
 
+#define ARM_SMMU_IIDR			0x18
+#define IIDR_PRODUCTID			GENMASK(31, 20)
+#define IIDR_VARIANT			GENMASK(19, 16)
+#define IIDR_REVISION			GENMASK(15, 12)
+#define IIDR_IMPLEMENTER		GENMASK(11, 0)
+
 #define ARM_SMMU_CR0			0x20
 #define CR0_ATSCHK			(1 << 4)
 #define CR0_CMDQEN			(1 << 3)
@@ -639,11 +645,13 @@ struct arm_smmu_device {
 #define ARM_SMMU_FEAT_BTM		(1 << 16)
 #define ARM_SMMU_FEAT_SVA		(1 << 17)
 #define ARM_SMMU_FEAT_E2H		(1 << 18)
+#define ARM_SMMU_FEAT_NESTING		(1 << 19)
 	u32				features;
 
 #define ARM_SMMU_OPT_SKIP_PREFETCH	(1 << 0)
 #define ARM_SMMU_OPT_PAGE0_REGS_ONLY	(1 << 1)
 #define ARM_SMMU_OPT_MSIPOLL		(1 << 2)
+#define ARM_SMMU_OPT_CMDQ_FORCE_SYNC	(1 << 3)
 	u32				options;
 
 	struct arm_smmu_cmdq		cmdq;
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c
index 6e0813b26fb6..a86acd76c1df 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c
@@ -856,8 +856,7 @@ static struct iommu_domain *arm_smmu_domain_alloc(unsigned type)
 	struct arm_smmu_domain *smmu_domain;
 
 	if (type != IOMMU_DOMAIN_UNMANAGED && type != IOMMU_DOMAIN_IDENTITY) {
-		if (using_legacy_binding ||
-		    (type != IOMMU_DOMAIN_DMA && type != IOMMU_DOMAIN_DMA_FQ))
+		if (using_legacy_binding || type != IOMMU_DOMAIN_DMA)
 			return NULL;
 	}
 	/*
@@ -1325,6 +1324,7 @@ static bool arm_smmu_capable(struct device *dev, enum iommu_cap cap)
 		return cfg->smmu->features & ARM_SMMU_FEAT_COHERENT_WALK ||
 			device_get_dma_attr(dev) == DEV_DMA_COHERENT;
 	case IOMMU_CAP_NOEXEC:
+	case IOMMU_CAP_DEFERRED_FLUSH:
 		return true;
 	default:
 		return false;