Merge tag 'iommu-updates-v6.4' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull iommu updates from Joerg Roedel:

 - Convert to platform remove callback returning void

 - Extend changing default domain to normal group

 - Intel VT-d updates:
     - Remove VT-d virtual command interface and IOASID
     - Allow the VT-d driver to support non-PRI IOPF
     - Remove PASID supervisor request support
     - Various small and misc cleanups

 - ARM SMMU updates:
     - Device-tree binding updates:
         * Allow Qualcomm GPU SMMUs to accept relevant clock properties
         * Document Qualcomm 8550 SoC as implementing an MMU-500
         * Favour new "qcom,smmu-500" binding for Adreno SMMUs

     - Fix S2CR quirk detection on non-architectural Qualcomm SMMU
       implementations

     - Acknowledge SMMUv3 PRI queue overflow when consuming events

     - Document (in a comment) why ATS is disabled for bypass streams

 - AMD IOMMU updates:
     - 5-level page-table support
     - NUMA awareness for memory allocations

 - Unisoc driver: Support for reattaching an existing domain

 - Rockchip driver: Add missing set_platform_dma_ops callback

 - Mediatek driver: Adjust the dma-ranges

 - Various other small fixes and cleanups

* tag 'iommu-updates-v6.4' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (82 commits)
  iommu: Remove iommu_group_get_by_id()
  iommu: Make iommu_release_device() static
  iommu/vt-d: Remove BUG_ON in dmar_insert_dev_scope()
  iommu/vt-d: Remove a useless BUG_ON(dev->is_virtfn)
  iommu/vt-d: Remove BUG_ON in map/unmap()
  iommu/vt-d: Remove BUG_ON when domain->pgd is NULL
  iommu/vt-d: Remove BUG_ON in handling iotlb cache invalidation
  iommu/vt-d: Remove BUG_ON on checking valid pfn range
  iommu/vt-d: Make size of operands same in bitwise operations
  iommu/vt-d: Remove PASID supervisor request support
  iommu/vt-d: Use non-privileged mode for all PASIDs
  iommu/vt-d: Remove extern from function prototypes
  iommu/vt-d: Do not use GFP_ATOMIC when not needed
  iommu/vt-d: Remove unnecessary checks in iopf disabling path
  iommu/vt-d: Move PRI handling to IOPF feature path
  iommu/vt-d: Move pfsid and ats_qdep calculation to device probe path
  iommu/vt-d: Move iopf code from SVA to IOPF enabling path
  iommu/vt-d: Allow SVA with device-specific IOPF
  dmaengine: idxd: Add enable/disable device IOPF feature
  arm64: dts: mt8186: Add dma-ranges for the parent "soc" node
  ...

4 files changed, 45 insertions, 29 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 f2425b0f0cd6..3fd83fb75722 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -152,6 +152,18 @@ static void queue_inc_cons(struct arm_smmu_ll_queue *q)
 	q->cons = Q_OVF(q->cons) | Q_WRP(q, cons) | Q_IDX(q, cons);
 }
 
+static void queue_sync_cons_ovf(struct arm_smmu_queue *q)
+{
+	struct arm_smmu_ll_queue *llq = &q->llq;
+
+	if (likely(Q_OVF(llq->prod) == Q_OVF(llq->cons)))
+		return;
+
+	llq->cons = Q_OVF(llq->prod) | Q_WRP(llq, llq->cons) |
+		      Q_IDX(llq, llq->cons);
+	queue_sync_cons_out(q);
+}
+
 static int queue_sync_prod_in(struct arm_smmu_queue *q)
 {
 	u32 prod;
@@ -1577,8 +1589,7 @@ static irqreturn_t arm_smmu_evtq_thread(int irq, void *dev)
 	} while (!queue_empty(llq));
 
 	/* Sync our overflow flag, as we believe we're up to speed */
-	llq->cons = Q_OVF(llq->prod) | Q_WRP(llq, llq->cons) |
-		    Q_IDX(llq, llq->cons);
+	queue_sync_cons_ovf(q);
 	return IRQ_HANDLED;
 }
 
@@ -1636,9 +1647,7 @@ static irqreturn_t arm_smmu_priq_thread(int irq, void *dev)
 	} while (!queue_empty(llq));
 
 	/* Sync our overflow flag, as we believe we're up to speed */
-	llq->cons = Q_OVF(llq->prod) | Q_WRP(llq, llq->cons) |
-		      Q_IDX(llq, llq->cons);
-	queue_sync_cons_out(q);
+	queue_sync_cons_ovf(q);
 	return IRQ_HANDLED;
 }
 
@@ -2447,6 +2456,13 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 
 	master->domain = smmu_domain;
 
+	/*
+	 * The SMMU does not support enabling ATS with bypass. When the STE is
+	 * in bypass (STE.Config[2:0] == 0b100), ATS Translation Requests and
+	 * Translated transactions are denied as though ATS is disabled for the
+	 * stream (STE.EATS == 0b00), causing F_BAD_ATS_TREQ and
+	 * F_TRANSL_FORBIDDEN events (IHI0070Ea 5.2 Stream Table Entry).
+	 */
 	if (smmu_domain->stage != ARM_SMMU_DOMAIN_BYPASS)
 		master->ats_enabled = arm_smmu_ats_supported(master);
 
@@ -3844,7 +3860,7 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int arm_smmu_device_remove(struct platform_device *pdev)
+static void arm_smmu_device_remove(struct platform_device *pdev)
 {
 	struct arm_smmu_device *smmu = platform_get_drvdata(pdev);
 
@@ -3852,8 +3868,6 @@ static int arm_smmu_device_remove(struct platform_device *pdev)
 	iommu_device_sysfs_remove(&smmu->iommu);
 	arm_smmu_device_disable(smmu);
 	iopf_queue_free(smmu->evtq.iopf);
-
-	return 0;
 }
 
 static void arm_smmu_device_shutdown(struct platform_device *pdev)
@@ -3882,7 +3896,7 @@ static struct platform_driver arm_smmu_driver = {
 		.suppress_bind_attrs	= true,
 	},
 	.probe	= arm_smmu_device_probe,
-	.remove	= arm_smmu_device_remove,
+	.remove_new = arm_smmu_device_remove,
 	.shutdown = arm_smmu_device_shutdown,
 };
 module_driver(arm_smmu_driver, platform_driver_register,
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
index d1b296b95c86..ae09c627bc84 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
@@ -268,13 +268,27 @@ static int qcom_smmu_init_context(struct arm_smmu_domain *smmu_domain,
 
 static int qcom_smmu_cfg_probe(struct arm_smmu_device *smmu)
 {
-	unsigned int last_s2cr = ARM_SMMU_GR0_S2CR(smmu->num_mapping_groups - 1);
 	struct qcom_smmu *qsmmu = to_qcom_smmu(smmu);
+	unsigned int last_s2cr;
 	u32 reg;
 	u32 smr;
 	int i;
 
 	/*
+	 * 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.
+	 */
+	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);
+
+	/*
 	 * With some firmware versions writes to S2CR of type FAULT are
 	 * ignored, and writing BYPASS will end up written as FAULT in the
 	 * register. Perform a write to S2CR to detect if this is the case and
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c
index 2ff7a72cf377..6e0813b26fb6 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c
@@ -139,7 +139,7 @@ static int arm_smmu_register_legacy_master(struct device *dev,
 	int err;
 
 	np = dev_get_dev_node(dev);
-	if (!np || !of_find_property(np, "#stream-id-cells", NULL)) {
+	if (!np || !of_property_present(np, "#stream-id-cells")) {
 		of_node_put(np);
 		return -ENODEV;
 	}
@@ -2195,9 +2195,6 @@ static void arm_smmu_device_shutdown(struct platform_device *pdev)
 {
 	struct arm_smmu_device *smmu = platform_get_drvdata(pdev);
 
-	if (!smmu)
-		return;
-
 	if (!bitmap_empty(smmu->context_map, ARM_SMMU_MAX_CBS))
 		dev_notice(&pdev->dev, "disabling translation\n");
 
@@ -2214,19 +2211,14 @@ static void arm_smmu_device_shutdown(struct platform_device *pdev)
 	clk_bulk_unprepare(smmu->num_clks, smmu->clks);
 }
 
-static int arm_smmu_device_remove(struct platform_device *pdev)
+static void arm_smmu_device_remove(struct platform_device *pdev)
 {
 	struct arm_smmu_device *smmu = platform_get_drvdata(pdev);
 
-	if (!smmu)
-		return -ENODEV;
-
 	iommu_device_unregister(&smmu->iommu);
 	iommu_device_sysfs_remove(&smmu->iommu);
 
 	arm_smmu_device_shutdown(pdev);
-
-	return 0;
 }
 
 static int __maybe_unused arm_smmu_runtime_resume(struct device *dev)
@@ -2302,7 +2294,7 @@ static struct platform_driver arm_smmu_driver = {
 		.suppress_bind_attrs    = true,
 	},
 	.probe	= arm_smmu_device_probe,
-	.remove	= arm_smmu_device_remove,
+	.remove_new = arm_smmu_device_remove,
 	.shutdown = arm_smmu_device_shutdown,
 };
 module_platform_driver(arm_smmu_driver);
diff --git a/drivers/iommu/arm/arm-smmu/qcom_iommu.c b/drivers/iommu/arm/arm-smmu/qcom_iommu.c
index c8b70f476cd8..a503ed758ec3 100644
--- a/drivers/iommu/arm/arm-smmu/qcom_iommu.c
+++ b/drivers/iommu/arm/arm-smmu/qcom_iommu.c
@@ -682,7 +682,7 @@ static int qcom_iommu_ctx_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int qcom_iommu_ctx_remove(struct platform_device *pdev)
+static void qcom_iommu_ctx_remove(struct platform_device *pdev)
 {
 	struct qcom_iommu_dev *qcom_iommu = dev_get_drvdata(pdev->dev.parent);
 	struct qcom_iommu_ctx *ctx = platform_get_drvdata(pdev);
@@ -690,8 +690,6 @@ static int qcom_iommu_ctx_remove(struct platform_device *pdev)
 	platform_set_drvdata(pdev, NULL);
 
 	qcom_iommu->ctxs[ctx->asid - 1] = NULL;
-
-	return 0;
 }
 
 static const struct of_device_id ctx_of_match[] = {
@@ -706,7 +704,7 @@ static struct platform_driver qcom_iommu_ctx_driver = {
 		.of_match_table	= ctx_of_match,
 	},
 	.probe	= qcom_iommu_ctx_probe,
-	.remove = qcom_iommu_ctx_remove,
+	.remove_new = qcom_iommu_ctx_remove,
 };
 
 static bool qcom_iommu_has_secure_context(struct qcom_iommu_dev *qcom_iommu)
@@ -824,7 +822,7 @@ err_pm_disable:
 	return ret;
 }
 
-static int qcom_iommu_device_remove(struct platform_device *pdev)
+static void qcom_iommu_device_remove(struct platform_device *pdev)
 {
 	struct qcom_iommu_dev *qcom_iommu = platform_get_drvdata(pdev);
 
@@ -832,8 +830,6 @@ static int qcom_iommu_device_remove(struct platform_device *pdev)
 	platform_set_drvdata(pdev, NULL);
 	iommu_device_sysfs_remove(&qcom_iommu->iommu);
 	iommu_device_unregister(&qcom_iommu->iommu);
-
-	return 0;
 }
 
 static int __maybe_unused qcom_iommu_resume(struct device *dev)
@@ -870,7 +866,7 @@ static struct platform_driver qcom_iommu_driver = {
 		.pm		= &qcom_iommu_pm_ops,
 	},
 	.probe	= qcom_iommu_device_probe,
-	.remove	= qcom_iommu_device_remove,
+	.remove_new = qcom_iommu_device_remove,
 };
 
 static int __init qcom_iommu_init(void)