Merge tag 'iommu-updates-v5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull iommu updates from Joerg Roedel:

 - SMMU Updates from Will Deacon:

     - SMMUv3:
        - Support stalling faults for platform devices
        - Decrease defaults sizes for the event and PRI queues
     - SMMUv2:
        - Support for a new '->probe_finalize' hook, needed by Nvidia
        - Even more Qualcomm compatible strings
        - Avoid Adreno TTBR1 quirk for DB820C platform

 - Intel VT-d updates from Lu Baolu:

     - Convert Intel IOMMU to use sva_lib helpers in iommu core
     - ftrace and debugfs supports for page fault handling
     - Support asynchronous nested capabilities
     - Various misc cleanups

 - Support for new VIOT ACPI table to make the VirtIO IOMMU
   available on x86

 - Add the amd_iommu=force_enable command line option to enable
   the IOMMU on platforms where they are known to cause problems

 - Support for version 2 of the Rockchip IOMMU

 - Various smaller fixes, cleanups and refactorings

* tag 'iommu-updates-v5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (66 commits)
  iommu/virtio: Enable x86 support
  iommu/dma: Pass address limit rather than size to iommu_setup_dma_ops()
  ACPI: Add driver for the VIOT table
  ACPI: Move IOMMU setup code out of IORT
  ACPI: arm64: Move DMA setup operations out of IORT
  iommu/vt-d: Fix dereference of pointer info before it is null checked
  iommu: Update "iommu.strict" documentation
  iommu/arm-smmu: Check smmu->impl pointer before dereferencing
  iommu/arm-smmu-v3: Remove unnecessary oom message
  iommu/arm-smmu: Fix arm_smmu_device refcount leak in address translation
  iommu/arm-smmu: Fix arm_smmu_device refcount leak when arm_smmu_rpm_get fails
  iommu/vt-d: Fix linker error on 32-bit
  iommu/vt-d: No need to typecast
  iommu/vt-d: Define counter explicitly as unsigned int
  iommu/vt-d: Remove unnecessary braces
  iommu/vt-d: Removed unused iommu_count in dmar domain
  iommu/vt-d: Use bitfields for DMAR capabilities
  iommu/vt-d: Use DEVICE_ATTR_RO macro
  iommu/vt-d: Fix out-bounds-warning in intel/svm.c
  iommu/vt-d: Add PRQ handling latency sampling
  ...

4 files changed, 84 insertions, 13 deletions

diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
index 61fc645c1325..9b9d13ec5a88 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
@@ -3,6 +3,7 @@
  * Copyright (c) 2019, The Linux Foundation. All rights reserved.
  */
 
+#include <linux/acpi.h>
 #include <linux/adreno-smmu-priv.h>
 #include <linux/of_device.h>
 #include <linux/qcom_scm.h>
@@ -177,6 +178,16 @@ static int qcom_adreno_smmu_alloc_context_bank(struct arm_smmu_domain *smmu_doma
 	return __arm_smmu_alloc_bitmap(smmu->context_map, start, count);
 }
 
+static bool qcom_adreno_can_do_ttbr1(struct arm_smmu_device *smmu)
+{
+	const struct device_node *np = smmu->dev->of_node;
+
+	if (of_device_is_compatible(np, "qcom,msm8996-smmu-v2"))
+		return false;
+
+	return true;
+}
+
 static int qcom_adreno_smmu_init_context(struct arm_smmu_domain *smmu_domain,
 		struct io_pgtable_cfg *pgtbl_cfg, struct device *dev)
 {
@@ -191,7 +202,8 @@ static int qcom_adreno_smmu_init_context(struct arm_smmu_domain *smmu_domain,
 	 * be AARCH64 stage 1 but double check because the arm-smmu code assumes
 	 * that is the case when the TTBR1 quirk is enabled
 	 */
-	if ((smmu_domain->stage == ARM_SMMU_DOMAIN_S1) &&
+	if (qcom_adreno_can_do_ttbr1(smmu_domain->smmu) &&
+	    (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) &&
 	    (smmu_domain->cfg.fmt == ARM_SMMU_CTX_FMT_AARCH64))
 		pgtbl_cfg->quirks |= IO_PGTABLE_QUIRK_ARM_TTBR1;
 
@@ -216,6 +228,7 @@ static const struct of_device_id qcom_smmu_client_of_match[] __maybe_unused = {
 	{ .compatible = "qcom,mdss" },
 	{ .compatible = "qcom,sc7180-mdss" },
 	{ .compatible = "qcom,sc7180-mss-pil" },
+	{ .compatible = "qcom,sc7280-mdss" },
 	{ .compatible = "qcom,sc8180x-mdss" },
 	{ .compatible = "qcom,sdm845-mdss" },
 	{ .compatible = "qcom,sdm845-mss-pil" },
@@ -380,24 +393,48 @@ static struct arm_smmu_device *qcom_smmu_create(struct arm_smmu_device *smmu,
 static const struct of_device_id __maybe_unused qcom_smmu_impl_of_match[] = {
 	{ .compatible = "qcom,msm8998-smmu-v2" },
 	{ .compatible = "qcom,sc7180-smmu-500" },
+	{ .compatible = "qcom,sc7280-smmu-500" },
 	{ .compatible = "qcom,sc8180x-smmu-500" },
 	{ .compatible = "qcom,sdm630-smmu-v2" },
 	{ .compatible = "qcom,sdm845-smmu-500" },
+	{ .compatible = "qcom,sm6125-smmu-500" },
 	{ .compatible = "qcom,sm8150-smmu-500" },
 	{ .compatible = "qcom,sm8250-smmu-500" },
 	{ .compatible = "qcom,sm8350-smmu-500" },
 	{ }
 };
 
+#ifdef CONFIG_ACPI
+static struct acpi_platform_list qcom_acpi_platlist[] = {
+	{ "LENOVO", "CB-01   ", 0x8180, ACPI_SIG_IORT, equal, "QCOM SMMU" },
+	{ "QCOM  ", "QCOMEDK2", 0x8180, ACPI_SIG_IORT, equal, "QCOM SMMU" },
+	{ }
+};
+#endif
+
 struct arm_smmu_device *qcom_smmu_impl_init(struct arm_smmu_device *smmu)
 {
 	const struct device_node *np = smmu->dev->of_node;
 
-	if (of_match_node(qcom_smmu_impl_of_match, np))
-		return qcom_smmu_create(smmu, &qcom_smmu_impl);
+#ifdef CONFIG_ACPI
+	if (np == NULL) {
+		/* Match platform for ACPI boot */
+		if (acpi_match_platform_list(qcom_acpi_platlist) >= 0)
+			return qcom_smmu_create(smmu, &qcom_smmu_impl);
+	}
+#endif
 
+	/*
+	 * Do not change this order of implementation, i.e., first adreno
+	 * smmu impl and then apss smmu since we can have both implementing
+	 * arm,mmu-500 in which case we will miss setting adreno smmu specific
+	 * features if the order is changed.
+	 */
 	if (of_device_is_compatible(np, "qcom,adreno-smmu"))
 		return qcom_smmu_create(smmu, &qcom_adreno_smmu_impl);
 
+	if (of_match_node(qcom_smmu_impl_of_match, np))
+		return qcom_smmu_create(smmu, &qcom_smmu_impl);
+
 	return smmu;
 }
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c
index b4b32d31fc06..f22dbeb1e510 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c
@@ -31,7 +31,6 @@
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_device.h>
-#include <linux/of_iommu.h>
 #include <linux/pci.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
@@ -74,7 +73,7 @@ static bool using_legacy_binding, using_generic_binding;
 static inline int arm_smmu_rpm_get(struct arm_smmu_device *smmu)
 {
 	if (pm_runtime_enabled(smmu->dev))
-		return pm_runtime_get_sync(smmu->dev);
+		return pm_runtime_resume_and_get(smmu->dev);
 
 	return 0;
 }
@@ -1276,6 +1275,7 @@ static phys_addr_t arm_smmu_iova_to_phys_hard(struct iommu_domain *domain,
 	u64 phys;
 	unsigned long va, flags;
 	int ret, idx = cfg->cbndx;
+	phys_addr_t addr = 0;
 
 	ret = arm_smmu_rpm_get(smmu);
 	if (ret < 0)
@@ -1295,6 +1295,7 @@ static phys_addr_t arm_smmu_iova_to_phys_hard(struct iommu_domain *domain,
 		dev_err(dev,
 			"iova to phys timed out on %pad. Falling back to software table walk.\n",
 			&iova);
+		arm_smmu_rpm_put(smmu);
 		return ops->iova_to_phys(ops, iova);
 	}
 
@@ -1303,12 +1304,14 @@ static phys_addr_t arm_smmu_iova_to_phys_hard(struct iommu_domain *domain,
 	if (phys & ARM_SMMU_CB_PAR_F) {
 		dev_err(dev, "translation fault!\n");
 		dev_err(dev, "PAR = 0x%llx\n", phys);
-		return 0;
+		goto out;
 	}
 
+	addr = (phys & GENMASK_ULL(39, 12)) | (iova & 0xfff);
+out:
 	arm_smmu_rpm_put(smmu);
 
-	return (phys & GENMASK_ULL(39, 12)) | (iova & 0xfff);
+	return addr;
 }
 
 static phys_addr_t arm_smmu_iova_to_phys(struct iommu_domain *domain,
@@ -1455,6 +1458,18 @@ static void arm_smmu_release_device(struct device *dev)
 	iommu_fwspec_free(dev);
 }
 
+static void arm_smmu_probe_finalize(struct device *dev)
+{
+	struct arm_smmu_master_cfg *cfg;
+	struct arm_smmu_device *smmu;
+
+	cfg = dev_iommu_priv_get(dev);
+	smmu = cfg->smmu;
+
+	if (smmu->impl && smmu->impl->probe_finalize)
+		smmu->impl->probe_finalize(smmu, dev);
+}
+
 static struct iommu_group *arm_smmu_device_group(struct device *dev)
 {
 	struct arm_smmu_master_cfg *cfg = dev_iommu_priv_get(dev);
@@ -1574,6 +1589,7 @@ static struct iommu_ops arm_smmu_ops = {
 	.iova_to_phys		= arm_smmu_iova_to_phys,
 	.probe_device		= arm_smmu_probe_device,
 	.release_device		= arm_smmu_release_device,
+	.probe_finalize		= arm_smmu_probe_finalize,
 	.device_group		= arm_smmu_device_group,
 	.enable_nesting		= arm_smmu_enable_nesting,
 	.set_pgtable_quirks	= arm_smmu_set_pgtable_quirks,
@@ -2169,7 +2185,7 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
 	err = iommu_device_register(&smmu->iommu, &arm_smmu_ops, dev);
 	if (err) {
 		dev_err(dev, "Failed to register iommu\n");
-		return err;
+		goto err_sysfs_remove;
 	}
 
 	platform_set_drvdata(pdev, smmu);
@@ -2192,10 +2208,19 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
 	 * any device which might need it, so we want the bus ops in place
 	 * ready to handle default domain setup as soon as any SMMU exists.
 	 */
-	if (!using_legacy_binding)
-		return arm_smmu_bus_init(&arm_smmu_ops);
+	if (!using_legacy_binding) {
+		err = arm_smmu_bus_init(&arm_smmu_ops);
+		if (err)
+			goto err_unregister_device;
+	}
 
 	return 0;
+
+err_unregister_device:
+	iommu_device_unregister(&smmu->iommu);
+err_sysfs_remove:
+	iommu_device_sysfs_remove(&smmu->iommu);
+	return err;
 }
 
 static int arm_smmu_device_remove(struct platform_device *pdev)
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.h b/drivers/iommu/arm/arm-smmu/arm-smmu.h
index 84c21c4b0691..a50271595960 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu.h
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu.h
@@ -441,6 +441,7 @@ struct arm_smmu_impl {
 				  struct device *dev, int start);
 	void (*write_s2cr)(struct arm_smmu_device *smmu, int idx);
 	void (*write_sctlr)(struct arm_smmu_device *smmu, int idx, u32 reg);
+	void (*probe_finalize)(struct arm_smmu_device *smmu, struct device *dev);
 };
 
 #define INVALID_SMENDX			-1
diff --git a/drivers/iommu/arm/arm-smmu/qcom_iommu.c b/drivers/iommu/arm/arm-smmu/qcom_iommu.c
index 4294abe389b2..25ed444ff94d 100644
--- a/drivers/iommu/arm/arm-smmu/qcom_iommu.c
+++ b/drivers/iommu/arm/arm-smmu/qcom_iommu.c
@@ -25,7 +25,6 @@
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_device.h>
-#include <linux/of_iommu.h>
 #include <linux/platform_device.h>
 #include <linux/pm.h>
 #include <linux/pm_runtime.h>
@@ -850,10 +849,12 @@ static int qcom_iommu_device_probe(struct platform_device *pdev)
 	ret = iommu_device_register(&qcom_iommu->iommu, &qcom_iommu_ops, dev);
 	if (ret) {
 		dev_err(dev, "Failed to register iommu\n");
-		return ret;
+		goto err_sysfs_remove;
 	}
 
-	bus_set_iommu(&platform_bus_type, &qcom_iommu_ops);
+	ret = bus_set_iommu(&platform_bus_type, &qcom_iommu_ops);
+	if (ret)
+		goto err_unregister_device;
 
 	if (qcom_iommu->local_base) {
 		pm_runtime_get_sync(dev);
@@ -862,6 +863,13 @@ static int qcom_iommu_device_probe(struct platform_device *pdev)
 	}
 
 	return 0;
+
+err_unregister_device:
+	iommu_device_unregister(&qcom_iommu->iommu);
+
+err_sysfs_remove:
+	iommu_device_sysfs_remove(&qcom_iommu->iommu);
+	return ret;
 }
 
 static int qcom_iommu_device_remove(struct platform_device *pdev)