Merge tag 'iommu-fixes-v3.17-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull iommu fixes from Joerg Roedel:
 - two fixes for issues found by Coverity
 - various fixes for the ARM SMMU driver
 - a warning fix for the FSL PAMU driver

* tag 'iommu-fixes-v3.17-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu:
  iommu/fsl: Fix warning resulting from adding PCI device twice
  iommu/arm-smmu: fix corner cases in address size calculations
  iommu/arm-smmu: fix decimal printf format specifiers prefixed with 0x
  iommu/arm-smmu: Do not access non-existing S2CR registers
  iommu/arm-smmu: fix s2cr and smr teardown on device detach from domain
  iommu/arm-smmu: remove pgtable_page_{c,d}tor()
  iommu/arm-smmu: fix programming of SMMU_CBn_TCR for stage 1
  iommu/arm-smmu: avoid calling request_irq in atomic context
  iommu/vt-d: Check return value of acpi_bus_get_device()
  iommu/core: Make iommu_group_get_for_dev() more robust

drivers/iommu/arm-smmu.c

@@ -146,6 +146,8 @@
 #define ID0_CTTW			(1 << 14)
 #define ID0_NUMIRPT_SHIFT		16
 #define ID0_NUMIRPT_MASK		0xff
+#define ID0_NUMSIDB_SHIFT		9
+#define ID0_NUMSIDB_MASK		0xf
 #define ID0_NUMSMRG_SHIFT		0
 #define ID0_NUMSMRG_MASK		0xff
 
@@ -524,9 +526,18 @@ static int register_smmu_master(struct arm_smmu_device *smmu,
 	master->of_node			= masterspec->np;
 	master->cfg.num_streamids	= masterspec->args_count;
 
-	for (i = 0; i < master->cfg.num_streamids; ++i)
-		master->cfg.streamids[i] = masterspec->args[i];
+	for (i = 0; i < master->cfg.num_streamids; ++i) {
+		u16 streamid = masterspec->args[i];
 
+		if (!(smmu->features & ARM_SMMU_FEAT_STREAM_MATCH) &&
+		     (streamid >= smmu->num_mapping_groups)) {
+			dev_err(dev,
+				"stream ID for master device %s greater than maximum allowed (%d)\n",
+				masterspec->np->name, smmu->num_mapping_groups);
+			return -ERANGE;
+		}
+		master->cfg.streamids[i] = streamid;
+	}
 	return insert_smmu_master(smmu, master);
 }
 
@@ -623,7 +634,7 @@ static irqreturn_t arm_smmu_context_fault(int irq, void *dev)
 
 	if (fsr & FSR_IGN)
 		dev_err_ratelimited(smmu->dev,
-				    "Unexpected context fault (fsr 0x%u)\n",
+				    "Unexpected context fault (fsr 0x%x)\n",
 				    fsr);
 
 	fsynr = readl_relaxed(cb_base + ARM_SMMU_CB_FSYNR0);
@@ -752,6 +763,7 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain)
 			reg = (TTBCR2_ADDR_36 << TTBCR2_SEP_SHIFT);
 			break;
 		case 39:
+		case 40:
 			reg = (TTBCR2_ADDR_40 << TTBCR2_SEP_SHIFT);
 			break;
 		case 42:
@@ -773,6 +785,7 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain)
 			reg |= (TTBCR2_ADDR_36 << TTBCR2_PASIZE_SHIFT);
 			break;
 		case 39:
+		case 40:
 			reg |= (TTBCR2_ADDR_40 << TTBCR2_PASIZE_SHIFT);
 			break;
 		case 42:
@@ -843,8 +856,11 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain)
 	reg |= TTBCR_EAE |
 	      (TTBCR_SH_IS << TTBCR_SH0_SHIFT) |
 	      (TTBCR_RGN_WBWA << TTBCR_ORGN0_SHIFT) |
-	      (TTBCR_RGN_WBWA << TTBCR_IRGN0_SHIFT) |
-	      (TTBCR_SL0_LVL_1 << TTBCR_SL0_SHIFT);
+	      (TTBCR_RGN_WBWA << TTBCR_IRGN0_SHIFT);
+
+	if (!stage1)
+		reg |= (TTBCR_SL0_LVL_1 << TTBCR_SL0_SHIFT);
+
 	writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBCR);
 
 	/* MAIR0 (stage-1 only) */
@@ -868,10 +884,15 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain)
 static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 					struct arm_smmu_device *smmu)
 {
-	int irq, ret, start;
+	int irq, start, ret = 0;
+	unsigned long flags;
 	struct arm_smmu_domain *smmu_domain = domain->priv;
 	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
 
+	spin_lock_irqsave(&smmu_domain->lock, flags);
+	if (smmu_domain->smmu)
+		goto out_unlock;
+
 	if (smmu->features & ARM_SMMU_FEAT_TRANS_NESTED) {
 		/*
 		 * We will likely want to change this if/when KVM gets
@@ -890,7 +911,7 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 	ret = __arm_smmu_alloc_bitmap(smmu->context_map, start,
 				      smmu->num_context_banks);
 	if (IS_ERR_VALUE(ret))
-		return ret;
+		goto out_unlock;
 
 	cfg->cbndx = ret;
 	if (smmu->version == 1) {
@@ -900,6 +921,10 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 		cfg->irptndx = cfg->cbndx;
 	}
 
+	ACCESS_ONCE(smmu_domain->smmu) = smmu;
+	arm_smmu_init_context_bank(smmu_domain);
+	spin_unlock_irqrestore(&smmu_domain->lock, flags);
+
 	irq = smmu->irqs[smmu->num_global_irqs + cfg->irptndx];
 	ret = request_irq(irq, arm_smmu_context_fault, IRQF_SHARED,
 			  "arm-smmu-context-fault", domain);
@@ -907,15 +932,12 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 		dev_err(smmu->dev, "failed to request context IRQ %d (%u)\n",
 			cfg->irptndx, irq);
 		cfg->irptndx = INVALID_IRPTNDX;
-		goto out_free_context;
 	}
 
-	smmu_domain->smmu = smmu;
-	arm_smmu_init_context_bank(smmu_domain);
 	return 0;
 
-out_free_context:
-	__arm_smmu_free_bitmap(smmu->context_map, cfg->cbndx);
+out_unlock:
+	spin_unlock_irqrestore(&smmu_domain->lock, flags);
 	return ret;
 }
 
@@ -975,7 +997,6 @@ static void arm_smmu_free_ptes(pmd_t *pmd)
 {
 	pgtable_t table = pmd_pgtable(*pmd);
 
-	pgtable_page_dtor(table);
 	__free_page(table);
 }
 
@@ -1108,6 +1129,9 @@ static void arm_smmu_master_free_smrs(struct arm_smmu_device *smmu,
 	void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
 	struct arm_smmu_smr *smrs = cfg->smrs;
 
+	if (!smrs)
+		return;
+
 	/* Invalidate the SMRs before freeing back to the allocator */
 	for (i = 0; i < cfg->num_streamids; ++i) {
 		u8 idx = smrs[i].idx;
@@ -1120,20 +1144,6 @@ static void arm_smmu_master_free_smrs(struct arm_smmu_device *smmu,
 	kfree(smrs);
 }
 
-static void arm_smmu_bypass_stream_mapping(struct arm_smmu_device *smmu,
-					   struct arm_smmu_master_cfg *cfg)
-{
-	int i;
-	void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
-
-	for (i = 0; i < cfg->num_streamids; ++i) {
-		u16 sid = cfg->streamids[i];
-
-		writel_relaxed(S2CR_TYPE_BYPASS,
-			       gr0_base + ARM_SMMU_GR0_S2CR(sid));
-	}
-}
-
 static int arm_smmu_domain_add_master(struct arm_smmu_domain *smmu_domain,
 				      struct arm_smmu_master_cfg *cfg)
 {
@@ -1160,23 +1170,30 @@ static int arm_smmu_domain_add_master(struct arm_smmu_domain *smmu_domain,
 static void arm_smmu_domain_remove_master(struct arm_smmu_domain *smmu_domain,
 					  struct arm_smmu_master_cfg *cfg)
 {
+	int i;
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
 
 	/*
 	 * We *must* clear the S2CR first, because freeing the SMR means
 	 * that it can be re-allocated immediately.
 	 */
-	arm_smmu_bypass_stream_mapping(smmu, cfg);
+	for (i = 0; i < cfg->num_streamids; ++i) {
+		u32 idx = cfg->smrs ? cfg->smrs[i].idx : cfg->streamids[i];
+
+		writel_relaxed(S2CR_TYPE_BYPASS,
+			       gr0_base + ARM_SMMU_GR0_S2CR(idx));
+	}
+
 	arm_smmu_master_free_smrs(smmu, cfg);
 }
 
 static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 {
-	int ret = -EINVAL;
+	int ret;
 	struct arm_smmu_domain *smmu_domain = domain->priv;
-	struct arm_smmu_device *smmu;
+	struct arm_smmu_device *smmu, *dom_smmu;
 	struct arm_smmu_master_cfg *cfg;
-	unsigned long flags;
 
 	smmu = dev_get_master_dev(dev)->archdata.iommu;
 	if (!smmu) {
@@ -1188,20 +1205,22 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 	 * Sanity check the domain. We don't support domains across
 	 * different SMMUs.
 	 */
-	spin_lock_irqsave(&smmu_domain->lock, flags);
-	if (!smmu_domain->smmu) {
+	dom_smmu = ACCESS_ONCE(smmu_domain->smmu);
+	if (!dom_smmu) {
 		/* Now that we have a master, we can finalise the domain */
 		ret = arm_smmu_init_domain_context(domain, smmu);
 		if (IS_ERR_VALUE(ret))
-			goto err_unlock;
-	} else if (smmu_domain->smmu != smmu) {
+			return ret;
+
+		dom_smmu = smmu_domain->smmu;
+	}
+
+	if (dom_smmu != smmu) {
 		dev_err(dev,
 			"cannot attach to SMMU %s whilst already attached to domain on SMMU %s\n",
-			dev_name(smmu_domain->smmu->dev),
-			dev_name(smmu->dev));
-		goto err_unlock;
+			dev_name(smmu_domain->smmu->dev), dev_name(smmu->dev));
+		return -EINVAL;
 	}
-	spin_unlock_irqrestore(&smmu_domain->lock, flags);
 
 	/* Looks ok, so add the device to the domain */
 	cfg = find_smmu_master_cfg(smmu_domain->smmu, dev);
@@ -1209,10 +1228,6 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 		return -ENODEV;
 
 	return arm_smmu_domain_add_master(smmu_domain, cfg);
-
-err_unlock:
-	spin_unlock_irqrestore(&smmu_domain->lock, flags);
-	return ret;
 }
 
 static void arm_smmu_detach_dev(struct iommu_domain *domain, struct device *dev)
@@ -1247,10 +1262,6 @@ static int arm_smmu_alloc_init_pte(struct arm_smmu_device *smmu, pmd_t *pmd,
 			return -ENOMEM;
 
 		arm_smmu_flush_pgtable(smmu, page_address(table), PAGE_SIZE);
-		if (!pgtable_page_ctor(table)) {
-			__free_page(table);
-			return -ENOMEM;
-		}
 		pmd_populate(NULL, pmd, table);
 		arm_smmu_flush_pgtable(smmu, pmd, sizeof(*pmd));
 	}
@@ -1626,7 +1637,7 @@ static void arm_smmu_device_reset(struct arm_smmu_device *smmu)
 
 	/* Mark all SMRn as invalid and all S2CRn as bypass */
 	for (i = 0; i < smmu->num_mapping_groups; ++i) {
-		writel_relaxed(~SMR_VALID, gr0_base + ARM_SMMU_GR0_SMR(i));
+		writel_relaxed(0, gr0_base + ARM_SMMU_GR0_SMR(i));
 		writel_relaxed(S2CR_TYPE_BYPASS,
 			gr0_base + ARM_SMMU_GR0_S2CR(i));
 	}
@@ -1761,6 +1772,9 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 		dev_notice(smmu->dev,
 			   "\tstream matching with %u register groups, mask 0x%x",
 			   smmu->num_mapping_groups, mask);
+	} else {
+		smmu->num_mapping_groups = (id >> ID0_NUMSIDB_SHIFT) &
+					   ID0_NUMSIDB_MASK;
 	}
 
 	/* ID1 */
@@ -1794,11 +1808,16 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 	 * Stage-1 output limited by stage-2 input size due to pgd
 	 * allocation (PTRS_PER_PGD).
 	 */
+	if (smmu->features & ARM_SMMU_FEAT_TRANS_NESTED) {
 #ifdef CONFIG_64BIT
-	smmu->s1_output_size = min_t(unsigned long, VA_BITS, size);
+		smmu->s1_output_size = min_t(unsigned long, VA_BITS, size);
 #else
-	smmu->s1_output_size = min(32UL, size);
+		smmu->s1_output_size = min(32UL, size);
 #endif
+	} else {
+		smmu->s1_output_size = min_t(unsigned long, PHYS_MASK_SHIFT,
+					     size);
+	}
 
 	/* The stage-2 output mask is also applied for bypass */
 	size = arm_smmu_id_size_to_bits((id >> ID2_OAS_SHIFT) & ID2_OAS_MASK);
@@ -1889,6 +1908,10 @@ static int arm_smmu_device_dt_probe(struct platform_device *pdev)
 		smmu->irqs[i] = irq;
 	}
 
+	err = arm_smmu_device_cfg_probe(smmu);
+	if (err)
+		return err;
+
 	i = 0;
 	smmu->masters = RB_ROOT;
 	while (!of_parse_phandle_with_args(dev->of_node, "mmu-masters",
@@ -1905,10 +1928,6 @@ static int arm_smmu_device_dt_probe(struct platform_device *pdev)
 	}
 	dev_notice(dev, "registered %d master devices\n", i);
 
-	err = arm_smmu_device_cfg_probe(smmu);
-	if (err)
-		goto out_put_masters;
-
 	parse_driver_options(smmu);
 
 	if (smmu->version > 1 &&

drivers/iommu/dmar.c

@@ -678,8 +678,7 @@ static int __init dmar_acpi_dev_scope_init(void)
 				       andd->device_name);
 				continue;
 			}
-			acpi_bus_get_device(h, &adev);
-			if (!adev) {
+			if (acpi_bus_get_device(h, &adev)) {
 				pr_err("Failed to get device for ACPI object %s\n",
 				       andd->device_name);
 				continue;

drivers/iommu/fsl_pamu_domain.c

@@ -984,7 +984,7 @@ static int fsl_pamu_add_device(struct device *dev)
 	struct iommu_group *group = ERR_PTR(-ENODEV);
 	struct pci_dev *pdev;
 	const u32 *prop;
-	int ret, len;
+	int ret = 0, len;
 
 	/*
 	 * For platform devices we allocate a separate group for
@@ -1007,7 +1007,13 @@ static int fsl_pamu_add_device(struct device *dev)
 	if (IS_ERR(group))
 		return PTR_ERR(group);
 
-	ret = iommu_group_add_device(group, dev);
+	/*
+	 * Check if device has already been added to an iommu group.
+	 * Group could have already been created for a PCI device in
+	 * the iommu_group_get_for_dev path.
+	 */
+	if (!dev->iommu_group)
+		ret = iommu_group_add_device(group, dev);
 
 	iommu_group_put(group);
 	return ret;

drivers/iommu/iommu.c

@@ -678,15 +678,17 @@ static struct iommu_group *iommu_group_get_for_pci_dev(struct pci_dev *pdev)
  */
 struct iommu_group *iommu_group_get_for_dev(struct device *dev)
 {
-	struct iommu_group *group = ERR_PTR(-EIO);
+	struct iommu_group *group;
 	int ret;
 
 	group = iommu_group_get(dev);
 	if (group)
 		return group;
 
-	if (dev_is_pci(dev))
-		group = iommu_group_get_for_pci_dev(to_pci_dev(dev));
+	if (!dev_is_pci(dev))
+		return ERR_PTR(-EINVAL);
+
+	group = iommu_group_get_for_pci_dev(to_pci_dev(dev));
 
 	if (IS_ERR(group))
 		return group;