3 files changed, 34 insertions, 24 deletions

diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
index 57c097e87613..573085349df3 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
@@ -367,6 +367,7 @@ static int qcom_adreno_smmu_init_context(struct arm_smmu_domain *smmu_domain,
 static const struct of_device_id qcom_smmu_client_of_match[] __maybe_unused = {
 	{ .compatible = "qcom,adreno" },
 	{ .compatible = "qcom,adreno-gmu" },
+	{ .compatible = "qcom,glymur-mdss" },
 	{ .compatible = "qcom,mdp4" },
 	{ .compatible = "qcom,mdss" },
 	{ .compatible = "qcom,qcm2290-mdss" },
@@ -431,17 +432,19 @@ static int qcom_smmu_cfg_probe(struct arm_smmu_device *smmu)
 
 	/*
 	 * Some platforms support more than the Arm SMMU architected maximum of
-	 * 128 stream matching groups. For unknown reasons, the additional
-	 * groups don't exhibit the same behavior as the architected registers,
-	 * so limit the groups to 128 until the behavior is fixed for the other
-	 * groups.
+	 * 128 stream matching groups. The additional registers appear to have
+	 * the same behavior as the architected registers in the hardware.
+	 * However, on some firmware versions, the hypervisor does not
+	 * correctly trap and emulate accesses to the additional registers,
+	 * resulting in unexpected behavior.
+	 *
+	 * If there are more than 128 groups, use the last reliable group to
+	 * detect if we need to apply the bypass quirk.
 	 */
-	if (smmu->num_mapping_groups > 128) {
-		dev_notice(smmu->dev, "\tLimiting the stream matching groups to 128\n");
-		smmu->num_mapping_groups = 128;
-	}
-
-	last_s2cr = ARM_SMMU_GR0_S2CR(smmu->num_mapping_groups - 1);
+	if (smmu->num_mapping_groups > 128)
+		last_s2cr = ARM_SMMU_GR0_S2CR(127);
+	else
+		last_s2cr = ARM_SMMU_GR0_S2CR(smmu->num_mapping_groups - 1);
 
 	/*
 	 * With some firmware versions writes to S2CR of type FAULT are
@@ -464,6 +467,11 @@ static int qcom_smmu_cfg_probe(struct arm_smmu_device *smmu)
 
 		reg = FIELD_PREP(ARM_SMMU_CBAR_TYPE, CBAR_TYPE_S1_TRANS_S2_BYPASS);
 		arm_smmu_gr1_write(smmu, ARM_SMMU_GR1_CBAR(qsmmu->bypass_cbndx), reg);
+
+		if (smmu->num_mapping_groups > 128) {
+			dev_notice(smmu->dev, "\tLimiting the stream matching groups to 128\n");
+			smmu->num_mapping_groups = 128;
+		}
 	}
 
 	for (i = 0; i < smmu->num_mapping_groups; i++) {
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c
index 4ced4b5bee4d..5e690cf85ec9 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c
@@ -1165,7 +1165,8 @@ static void arm_smmu_master_install_s2crs(struct arm_smmu_master_cfg *cfg,
 	}
 }
 
-static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
+static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev,
+			       struct iommu_domain *old)
 {
 	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
 	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
@@ -1234,7 +1235,8 @@ static int arm_smmu_attach_dev_type(struct device *dev,
 }
 
 static int arm_smmu_attach_dev_identity(struct iommu_domain *domain,
-					struct device *dev)
+					struct device *dev,
+					struct iommu_domain *old)
 {
 	return arm_smmu_attach_dev_type(dev, S2CR_TYPE_BYPASS);
 }
@@ -1249,7 +1251,8 @@ static struct iommu_domain arm_smmu_identity_domain = {
 };
 
 static int arm_smmu_attach_dev_blocked(struct iommu_domain *domain,
-				       struct device *dev)
+				       struct device *dev,
+				       struct iommu_domain *old)
 {
 	return arm_smmu_attach_dev_type(dev, S2CR_TYPE_FAULT);
 }
diff --git a/drivers/iommu/arm/arm-smmu/qcom_iommu.c b/drivers/iommu/arm/arm-smmu/qcom_iommu.c
index c5be95e56031..f69d9276dc55 100644
--- a/drivers/iommu/arm/arm-smmu/qcom_iommu.c
+++ b/drivers/iommu/arm/arm-smmu/qcom_iommu.c
@@ -359,7 +359,8 @@ static void qcom_iommu_domain_free(struct iommu_domain *domain)
 	kfree(qcom_domain);
 }
 
-static int qcom_iommu_attach_dev(struct iommu_domain *domain, struct device *dev)
+static int qcom_iommu_attach_dev(struct iommu_domain *domain,
+				 struct device *dev, struct iommu_domain *old)
 {
 	struct qcom_iommu_dev *qcom_iommu = dev_iommu_priv_get(dev);
 	struct qcom_iommu_domain *qcom_domain = to_qcom_iommu_domain(domain);
@@ -388,18 +389,18 @@ static int qcom_iommu_attach_dev(struct iommu_domain *domain, struct device *dev
 }
 
 static int qcom_iommu_identity_attach(struct iommu_domain *identity_domain,
-				      struct device *dev)
+				      struct device *dev,
+				      struct iommu_domain *old)
 {
-	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
 	struct qcom_iommu_domain *qcom_domain;
 	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
 	struct qcom_iommu_dev *qcom_iommu = dev_iommu_priv_get(dev);
 	unsigned int i;
 
-	if (domain == identity_domain || !domain)
+	if (old == identity_domain || !old)
 		return 0;
 
-	qcom_domain = to_qcom_iommu_domain(domain);
+	qcom_domain = to_qcom_iommu_domain(old);
 	if (WARN_ON(!qcom_domain->iommu))
 		return -EINVAL;
 
@@ -565,14 +566,14 @@ static int qcom_iommu_of_xlate(struct device *dev,
 
 	qcom_iommu = platform_get_drvdata(iommu_pdev);
 
+	put_device(&iommu_pdev->dev);
+
 	/* make sure the asid specified in dt is valid, so we don't have
 	 * to sanity check this elsewhere:
 	 */
 	if (WARN_ON(asid > qcom_iommu->max_asid) ||
-	    WARN_ON(qcom_iommu->ctxs[asid] == NULL)) {
-		put_device(&iommu_pdev->dev);
+	    WARN_ON(qcom_iommu->ctxs[asid] == NULL))
 		return -EINVAL;
-	}
 
 	if (!dev_iommu_priv_get(dev)) {
 		dev_iommu_priv_set(dev, qcom_iommu);
@@ -581,10 +582,8 @@ static int qcom_iommu_of_xlate(struct device *dev,
 		 * multiple different iommu devices.  Multiple context
 		 * banks are ok, but multiple devices are not:
 		 */
-		if (WARN_ON(qcom_iommu != dev_iommu_priv_get(dev))) {
-			put_device(&iommu_pdev->dev);
+		if (WARN_ON(qcom_iommu != dev_iommu_priv_get(dev)))
 			return -EINVAL;
-		}
 	}
 
 	return iommu_fwspec_add_ids(dev, &asid, 1);