Merge tag 'iommu-updates-v4.16' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull IOMMU updates from Joerg Roedel:
 "This time there are not a lot of changes coming from the IOMMU side.

  That is partly because I returned from my parental leave late in the
  development process and probably partly because everyone was busy with
  Spectre and Meltdown mitigation work and didn't find the time for
  IOMMU work. So here are the few changes that queued up for this merge
  window:

   - 5-level page-table support for the Intel IOMMU.

   - error reporting improvements for the AMD IOMMU driver

   - additional DT bindings for ipmmu-vmsa (Renesas)

   - small fixes and cleanups"

* tag 'iommu-updates-v4.16' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu:
  iommu: Clean up of_iommu_init_fn
  iommu/ipmmu-vmsa: Remove redundant of_iommu_init_fn hook
  iommu/msm: Claim bus ops on probe
  iommu/vt-d: Enable 5-level paging mode in the PASID entry
  iommu/vt-d: Add a check for 5-level paging support
  iommu/vt-d: Add a check for 1GB page support
  iommu/vt-d: Enable upto 57 bits of domain address width
  iommu/vt-d: Use domain instead of cache fetching
  iommu/exynos: Don't unconditionally steal bus ops
  iommu/omap: Fix debugfs_create_*() usage
  iommu/vt-d: clean up pr_irq if request_threaded_irq fails
  iommu: Check the result of iommu_group_get() for NULL
  iommu/ipmmu-vmsa: Add r8a779(70|95) DT bindings
  iommu/ipmmu-vmsa: Add r8a7796 DT binding
  iommu/amd: Set the device table entry PPR bit for IOMMU V2 devices
  iommu/amd - Record more information about unknown events

Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.txt

@@ -16,6 +16,9 @@ Required Properties:
     - "renesas,ipmmu-r8a7793" for the R8A7793 (R-Car M2-N) IPMMU.
     - "renesas,ipmmu-r8a7794" for the R8A7794 (R-Car E2) IPMMU.
     - "renesas,ipmmu-r8a7795" for the R8A7795 (R-Car H3) IPMMU.
+    - "renesas,ipmmu-r8a7796" for the R8A7796 (R-Car M3-W) IPMMU.
+    - "renesas,ipmmu-r8a77970" for the R8A77970 (R-Car V3M) IPMMU.
+    - "renesas,ipmmu-r8a77995" for the R8A77995 (R-Car D3) IPMMU.
     - "renesas,ipmmu-vmsa" for generic R-Car Gen2 VMSA-compatible IPMMU.
 
   - reg: Base address and size of the IPMMU registers.

drivers/iommu/amd_iommu.c

@@ -617,7 +617,9 @@ static void iommu_print_event(struct amd_iommu *iommu, void *__evt)
 		       address, flags);
 		break;
 	default:
-		printk(KERN_ERR "UNKNOWN type=0x%02x]\n", type);
+		printk(KERN_ERR "UNKNOWN type=0x%02x event[0]=0x%08x "
+		       "event[1]=0x%08x event[2]=0x%08x event[3]=0x%08x\n",
+		       type, event[0], event[1], event[2], event[3]);
 	}
 
 	memset(__evt, 0, 4 * sizeof(u32));
@@ -1816,7 +1818,8 @@ static bool dma_ops_domain(struct protection_domain *domain)
 	return domain->flags & PD_DMA_OPS_MASK;
 }
 
-static void set_dte_entry(u16 devid, struct protection_domain *domain, bool ats)
+static void set_dte_entry(u16 devid, struct protection_domain *domain,
+			  bool ats, bool ppr)
 {
 	u64 pte_root = 0;
 	u64 flags = 0;
@@ -1833,6 +1836,13 @@ static void set_dte_entry(u16 devid, struct protection_domain *domain, bool ats)
 	if (ats)
 		flags |= DTE_FLAG_IOTLB;
 
+	if (ppr) {
+		struct amd_iommu *iommu = amd_iommu_rlookup_table[devid];
+
+		if (iommu_feature(iommu, FEATURE_EPHSUP))
+			pte_root |= 1ULL << DEV_ENTRY_PPR;
+	}
+
 	if (domain->flags & PD_IOMMUV2_MASK) {
 		u64 gcr3 = iommu_virt_to_phys(domain->gcr3_tbl);
 		u64 glx  = domain->glx;
@@ -1895,9 +1905,9 @@ static void do_attach(struct iommu_dev_data *dev_data,
 	domain->dev_cnt                 += 1;
 
 	/* Update device table */
-	set_dte_entry(dev_data->devid, domain, ats);
+	set_dte_entry(dev_data->devid, domain, ats, dev_data->iommu_v2);
 	if (alias != dev_data->devid)
-		set_dte_entry(alias, domain, ats);
+		set_dte_entry(alias, domain, ats, dev_data->iommu_v2);
 
 	device_flush_dte(dev_data);
 }
@@ -2276,13 +2286,15 @@ static void update_device_table(struct protection_domain *domain)
 	struct iommu_dev_data *dev_data;
 
 	list_for_each_entry(dev_data, &domain->dev_list, list) {
-		set_dte_entry(dev_data->devid, domain, dev_data->ats.enabled);
+		set_dte_entry(dev_data->devid, domain, dev_data->ats.enabled,
+			      dev_data->iommu_v2);
 
 		if (dev_data->devid == dev_data->alias)
 			continue;
 
 		/* There is an alias, update device table entry for it */
-		set_dte_entry(dev_data->alias, domain, dev_data->ats.enabled);
+		set_dte_entry(dev_data->alias, domain, dev_data->ats.enabled,
+			      dev_data->iommu_v2);
 	}
 }
 

drivers/iommu/amd_iommu_types.h

@@ -98,6 +98,7 @@
 #define FEATURE_HE		(1ULL<<8)
 #define FEATURE_PC		(1ULL<<9)
 #define FEATURE_GAM_VAPIC	(1ULL<<21)
+#define FEATURE_EPHSUP		(1ULL<<50)
 
 #define FEATURE_PASID_SHIFT	32
 #define FEATURE_PASID_MASK	(0x1fULL << FEATURE_PASID_SHIFT)
@@ -192,6 +193,7 @@
 /* macros and definitions for device table entries */
 #define DEV_ENTRY_VALID         0x00
 #define DEV_ENTRY_TRANSLATION   0x01
+#define DEV_ENTRY_PPR           0x34
 #define DEV_ENTRY_IR            0x3d
 #define DEV_ENTRY_IW            0x3e
 #define DEV_ENTRY_NO_PAGE_FAULT	0x62

drivers/iommu/arm-smmu-v3.c

@@ -2971,7 +2971,7 @@ static struct platform_driver arm_smmu_driver = {
 };
 module_platform_driver(arm_smmu_driver);
 
-IOMMU_OF_DECLARE(arm_smmuv3, "arm,smmu-v3", NULL);
+IOMMU_OF_DECLARE(arm_smmuv3, "arm,smmu-v3");
 
 MODULE_DESCRIPTION("IOMMU API for ARM architected SMMUv3 implementations");
 MODULE_AUTHOR("Will Deacon <will.deacon@arm.com>");

drivers/iommu/arm-smmu.c

@@ -2211,12 +2211,12 @@ static struct platform_driver arm_smmu_driver = {
 };
 module_platform_driver(arm_smmu_driver);
 
-IOMMU_OF_DECLARE(arm_smmuv1, "arm,smmu-v1", NULL);
-IOMMU_OF_DECLARE(arm_smmuv2, "arm,smmu-v2", NULL);
-IOMMU_OF_DECLARE(arm_mmu400, "arm,mmu-400", NULL);
-IOMMU_OF_DECLARE(arm_mmu401, "arm,mmu-401", NULL);
-IOMMU_OF_DECLARE(arm_mmu500, "arm,mmu-500", NULL);
-IOMMU_OF_DECLARE(cavium_smmuv2, "cavium,smmu-v2", NULL);
+IOMMU_OF_DECLARE(arm_smmuv1, "arm,smmu-v1");
+IOMMU_OF_DECLARE(arm_smmuv2, "arm,smmu-v2");
+IOMMU_OF_DECLARE(arm_mmu400, "arm,mmu-400");
+IOMMU_OF_DECLARE(arm_mmu401, "arm,mmu-401");
+IOMMU_OF_DECLARE(arm_mmu500, "arm,mmu-500");
+IOMMU_OF_DECLARE(cavium_smmuv2, "cavium,smmu-v2");
 
 MODULE_DESCRIPTION("IOMMU API for ARM architected SMMU implementations");
 MODULE_AUTHOR("Will Deacon <will.deacon@arm.com>");

drivers/iommu/exynos-iommu.c

@@ -1353,8 +1353,15 @@ static const struct iommu_ops exynos_iommu_ops = {
 
 static int __init exynos_iommu_init(void)
 {
+	struct device_node *np;
 	int ret;
 
+	np = of_find_matching_node(NULL, sysmmu_of_match);
+	if (!np)
+		return 0;
+
+	of_node_put(np);
+
 	lv2table_kmem_cache = kmem_cache_create("exynos-iommu-lv2table",
 				LV2TABLE_SIZE, LV2TABLE_SIZE, 0, NULL);
 	if (!lv2table_kmem_cache) {
@@ -1394,4 +1401,4 @@ static int __init exynos_iommu_init(void)
 }
 core_initcall(exynos_iommu_init);
 
-IOMMU_OF_DECLARE(exynos_iommu_of, "samsung,exynos-sysmmu", NULL);
+IOMMU_OF_DECLARE(exynos_iommu_of, "samsung,exynos-sysmmu");

drivers/iommu/intel-iommu.c

@@ -64,7 +64,7 @@
 #define IOAPIC_RANGE_END	(0xfeefffff)
 #define IOVA_START_ADDR		(0x1000)
 
-#define DEFAULT_DOMAIN_ADDRESS_WIDTH 48
+#define DEFAULT_DOMAIN_ADDRESS_WIDTH 57
 
 #define MAX_AGAW_WIDTH 64
 #define MAX_AGAW_PFN_WIDTH	(MAX_AGAW_WIDTH - VTD_PAGE_SHIFT)
@@ -1601,8 +1601,7 @@ static void iommu_flush_iotlb_psi(struct intel_iommu *iommu,
 	 * flush. However, device IOTLB doesn't need to be flushed in this case.
 	 */
 	if (!cap_caching_mode(iommu->cap) || !map)
-		iommu_flush_dev_iotlb(get_iommu_domain(iommu, did),
-				      addr, mask);
+		iommu_flush_dev_iotlb(domain, addr, mask);
 }
 
 static void iommu_flush_iova(struct iova_domain *iovad)

drivers/iommu/intel-svm.c

@@ -26,6 +26,10 @@
 #include <linux/interrupt.h>
 #include <asm/page.h>
 
+#define PASID_ENTRY_P		BIT_ULL(0)
+#define PASID_ENTRY_FLPM_5LP	BIT_ULL(9)
+#define PASID_ENTRY_SRE		BIT_ULL(11)
+
 static irqreturn_t prq_event_thread(int irq, void *d);
 
 struct pasid_entry {
@@ -41,6 +45,14 @@ int intel_svm_alloc_pasid_tables(struct intel_iommu *iommu)
 	struct page *pages;
 	int order;
 
+	if (cpu_feature_enabled(X86_FEATURE_GBPAGES) &&
+			!cap_fl1gp_support(iommu->cap))
+		return -EINVAL;
+
+	if (cpu_feature_enabled(X86_FEATURE_LA57) &&
+			!cap_5lp_support(iommu->cap))
+		return -EINVAL;
+
 	/* Start at 2 because it's defined as 2^(1+PSS) */
 	iommu->pasid_max = 2 << ecap_pss(iommu->ecap);
 
@@ -129,6 +141,7 @@ int intel_svm_enable_prq(struct intel_iommu *iommu)
 		pr_err("IOMMU: %s: Failed to request IRQ for page request queue\n",
 		       iommu->name);
 		dmar_free_hwirq(irq);
+		iommu->pr_irq = 0;
 		goto err;
 	}
 	dmar_writeq(iommu->reg + DMAR_PQH_REG, 0ULL);
@@ -144,9 +157,11 @@ int intel_svm_finish_prq(struct intel_iommu *iommu)
 	dmar_writeq(iommu->reg + DMAR_PQT_REG, 0ULL);
 	dmar_writeq(iommu->reg + DMAR_PQA_REG, 0ULL);
 
+	if (iommu->pr_irq) {
 		free_irq(iommu->pr_irq, iommu);
 		dmar_free_hwirq(iommu->pr_irq);
 		iommu->pr_irq = 0;
+	}
 
 	free_pages((unsigned long)iommu->prq, PRQ_ORDER);
 	iommu->prq = NULL;
@@ -290,6 +305,7 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_
 	struct intel_svm_dev *sdev;
 	struct intel_svm *svm = NULL;
 	struct mm_struct *mm = NULL;
+	u64 pasid_entry_val;
 	int pasid_max;
 	int ret;
 
@@ -396,9 +412,15 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_
 				kfree(sdev);
 				goto out;
 			}
-			iommu->pasid_table[svm->pasid].val = (u64)__pa(mm->pgd) | 1;
+			pasid_entry_val = (u64)__pa(mm->pgd) | PASID_ENTRY_P;
 		} else
-			iommu->pasid_table[svm->pasid].val = (u64)__pa(init_mm.pgd) | 1 | (1ULL << 11);
+			pasid_entry_val = (u64)__pa(init_mm.pgd) |
+					  PASID_ENTRY_P | PASID_ENTRY_SRE;
+		if (cpu_feature_enabled(X86_FEATURE_LA57))
+			pasid_entry_val |= PASID_ENTRY_FLPM_5LP;
+
+		iommu->pasid_table[svm->pasid].val = pasid_entry_val;
+
 		wmb();
 		/* In caching mode, we still have to flush with PASID 0 when
 		 * a PASID table entry becomes present. Not entirely clear

drivers/iommu/iommu.c

@@ -1303,6 +1303,9 @@ int iommu_attach_device(struct iommu_domain *domain, struct device *dev)
 	int ret;
 
 	group = iommu_group_get(dev);
+	if (!group)
+		return -ENODEV;
+
 	/*
 	 * Lock the group to make sure the device-count doesn't
 	 * change while we are attaching
@@ -1341,6 +1344,8 @@ void iommu_detach_device(struct iommu_domain *domain, struct device *dev)
 	struct iommu_group *group;
 
 	group = iommu_group_get(dev);
+	if (!group)
+		return;
 
 	mutex_lock(&group->mutex);
 	if (iommu_group_device_count(group) != 1) {

drivers/iommu/ipmmu-vmsa.c

@@ -1108,18 +1108,8 @@ static void __exit ipmmu_exit(void)
 subsys_initcall(ipmmu_init);
 module_exit(ipmmu_exit);
 
-#ifdef CONFIG_IOMMU_DMA
-static int __init ipmmu_vmsa_iommu_of_setup(struct device_node *np)
-{
-	ipmmu_init();
-	return 0;
-}
-
-IOMMU_OF_DECLARE(ipmmu_vmsa_iommu_of, "renesas,ipmmu-vmsa",
-		 ipmmu_vmsa_iommu_of_setup);
-IOMMU_OF_DECLARE(ipmmu_r8a7795_iommu_of, "renesas,ipmmu-r8a7795",
-		 ipmmu_vmsa_iommu_of_setup);
-#endif
+IOMMU_OF_DECLARE(ipmmu_vmsa_iommu_of, "renesas,ipmmu-vmsa");
+IOMMU_OF_DECLARE(ipmmu_r8a7795_iommu_of, "renesas,ipmmu-r8a7795");
 
 MODULE_DESCRIPTION("IOMMU API for Renesas VMSA-compatible IPMMU");
 MODULE_AUTHOR("Laurent Pinchart <laurent.pinchart@ideasonboard.com>");

drivers/iommu/msm_iommu.c

@@ -823,6 +823,8 @@ static int msm_iommu_probe(struct platform_device *pdev)
 		goto fail;
 	}
 
+	bus_set_iommu(&platform_bus_type, &msm_iommu_ops);
+
 	pr_info("device mapped at %p, irq %d with %d ctx banks\n",
 		iommu->base, iommu->irq, iommu->ncb);
 
@@ -875,19 +877,7 @@ static void __exit msm_iommu_driver_exit(void)
 subsys_initcall(msm_iommu_driver_init);
 module_exit(msm_iommu_driver_exit);
 
-static int __init msm_iommu_init(void)
-{
-	bus_set_iommu(&platform_bus_type, &msm_iommu_ops);
-	return 0;
-}
-
-static int __init msm_iommu_of_setup(struct device_node *np)
-{
-	msm_iommu_init();
-	return 0;
-}
-
-IOMMU_OF_DECLARE(msm_iommu_of, "qcom,apq8064-iommu", msm_iommu_of_setup);
+IOMMU_OF_DECLARE(msm_iommu_of, "qcom,apq8064-iommu");
 
 MODULE_LICENSE("GPL v2");
 MODULE_AUTHOR("Stepan Moskovchenko <stepanm@codeaurora.org>");

drivers/iommu/of_iommu.c

@@ -231,19 +231,3 @@ const struct iommu_ops *of_iommu_configure(struct device *dev,
 
 	return ops;
 }
-
-static int __init of_iommu_init(void)
-{
-	struct device_node *np;
-	const struct of_device_id *match, *matches = &__iommu_of_table;
-
-	for_each_matching_node_and_match(np, matches, &match) {
-		const of_iommu_init_fn init_fn = match->data;
-
-		if (init_fn && init_fn(np))
-			pr_err("Failed to initialise IOMMU %pOF\n", np);
-	}
-
-	return 0;
-}
-postcore_initcall_sync(of_iommu_init);

drivers/iommu/omap-iommu-debug.c

@@ -274,8 +274,8 @@ void omap_iommu_debugfs_add(struct omap_iommu *obj)
 	if (!obj->debug_dir)
 		return;
 
-	d = debugfs_create_u8("nr_tlb_entries", 0400, obj->debug_dir,
-			      (u8 *)&obj->nr_tlb_entries);
+	d = debugfs_create_u32("nr_tlb_entries", 0400, obj->debug_dir,
+			       &obj->nr_tlb_entries);
 	if (!d)
 		return;
 

drivers/iommu/qcom_iommu.c

@@ -947,7 +947,7 @@ static void __exit qcom_iommu_exit(void)
 module_init(qcom_iommu_init);
 module_exit(qcom_iommu_exit);
 
-IOMMU_OF_DECLARE(qcom_iommu_dev, "qcom,msm-iommu-v1", NULL);
+IOMMU_OF_DECLARE(qcom_iommu_dev, "qcom,msm-iommu-v1");
 
 MODULE_DESCRIPTION("IOMMU API for QCOM IOMMU v1 implementations");
 MODULE_LICENSE("GPL v2");

include/linux/intel-iommu.h

@@ -83,7 +83,9 @@
 /*
  * Decoding Capability Register
  */
+#define cap_5lp_support(c)	(((c) >> 60) & 1)
 #define cap_pi_support(c)	(((c) >> 59) & 1)
+#define cap_fl1gp_support(c)	(((c) >> 56) & 1)
 #define cap_read_drain(c)	(((c) >> 55) & 1)
 #define cap_write_drain(c)	(((c) >> 54) & 1)
 #define cap_max_amask_val(c)	(((c) >> 48) & 0x3f)

include/linux/of_iommu.h

@@ -34,9 +34,6 @@ static inline const struct iommu_ops *of_iommu_configure(struct device *dev,
 
 extern struct of_device_id __iommu_of_table;
 
-typedef int (*of_iommu_init_fn)(struct device_node *);
-
-#define IOMMU_OF_DECLARE(name, compat, fn) \
-	_OF_DECLARE(iommu, name, compat, fn, of_iommu_init_fn)
+#define IOMMU_OF_DECLARE(name, compat)	OF_DECLARE_1(iommu, name, compat, NULL)
 
 #endif /* __OF_IOMMU_H */