Merge branch 'for-next/iommu/fixes' into for-next/iommu/core

Merge in IOMMU fixes for 5.10 in order to resolve conflicts against the
queue for 5.11.

* for-next/iommu/fixes:
  iommu/amd: Set DTE[IntTabLen] to represent 512 IRTEs
  iommu/vt-d: Don't read VCCAP register unless it exists
  x86/tboot: Don't disable swiotlb when iommu is forced on
  iommu: Check return of __iommu_attach_device()
  arm-smmu-qcom: Ensure the qcom_scm driver has finished probing
  iommu/amd: Enforce 4k mapping for certain IOMMU data structures
  MAINTAINERS: Temporarily add myself to the IOMMU entry
  iommu/vt-d: Fix compile error with CONFIG_PCI_ATS not set
  iommu/vt-d: Avoid panic if iommu init fails in tboot system
  iommu/vt-d: Cure VF irqdomain hickup
  x86/platform/uv: Fix copied UV5 output archtype
  x86/platform/uv: Drop last traces of uv_flush_tlb_others

6 files changed, 60 insertions, 16 deletions

diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h
index 89647700bab2..494b42a31b7a 100644
--- a/drivers/iommu/amd/amd_iommu_types.h
+++ b/drivers/iommu/amd/amd_iommu_types.h
@@ -257,7 +257,7 @@
 #define DTE_IRQ_REMAP_INTCTL_MASK	(0x3ULL << 60)
 #define DTE_IRQ_TABLE_LEN_MASK	(0xfULL << 1)
 #define DTE_IRQ_REMAP_INTCTL    (2ULL << 60)
-#define DTE_IRQ_TABLE_LEN       (8ULL << 1)
+#define DTE_IRQ_TABLE_LEN       (9ULL << 1)
 #define DTE_IRQ_REMAP_ENABLE    1ULL
 
 #define PAGE_MODE_NONE    0x00
diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c
index 82e4af8f09bb..23a790f8f550 100644
--- a/drivers/iommu/amd/init.c
+++ b/drivers/iommu/amd/init.c
@@ -29,6 +29,7 @@
 #include <asm/iommu_table.h>
 #include <asm/io_apic.h>
 #include <asm/irq_remapping.h>
+#include <asm/set_memory.h>
 
 #include <linux/crash_dump.h>
 
@@ -672,11 +673,27 @@ static void __init free_command_buffer(struct amd_iommu *iommu)
 	free_pages((unsigned long)iommu->cmd_buf, get_order(CMD_BUFFER_SIZE));
 }
 
+static void *__init iommu_alloc_4k_pages(struct amd_iommu *iommu,
+					 gfp_t gfp, size_t size)
+{
+	int order = get_order(size);
+	void *buf = (void *)__get_free_pages(gfp, order);
+
+	if (buf &&
+	    iommu_feature(iommu, FEATURE_SNP) &&
+	    set_memory_4k((unsigned long)buf, (1 << order))) {
+		free_pages((unsigned long)buf, order);
+		buf = NULL;
+	}
+
+	return buf;
+}
+
 /* allocates the memory where the IOMMU will log its events to */
 static int __init alloc_event_buffer(struct amd_iommu *iommu)
 {
-	iommu->evt_buf = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
-						  get_order(EVT_BUFFER_SIZE));
+	iommu->evt_buf = iommu_alloc_4k_pages(iommu, GFP_KERNEL | __GFP_ZERO,
+					      EVT_BUFFER_SIZE);
 
 	return iommu->evt_buf ? 0 : -ENOMEM;
 }
@@ -715,8 +732,8 @@ static void __init free_event_buffer(struct amd_iommu *iommu)
 /* allocates the memory where the IOMMU will log its events to */
 static int __init alloc_ppr_log(struct amd_iommu *iommu)
 {
-	iommu->ppr_log = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
-						  get_order(PPR_LOG_SIZE));
+	iommu->ppr_log = iommu_alloc_4k_pages(iommu, GFP_KERNEL | __GFP_ZERO,
+					      PPR_LOG_SIZE);
 
 	return iommu->ppr_log ? 0 : -ENOMEM;
 }
@@ -838,7 +855,7 @@ static int iommu_init_ga(struct amd_iommu *iommu)
 
 static int __init alloc_cwwb_sem(struct amd_iommu *iommu)
 {
-	iommu->cmd_sem = (void *)get_zeroed_page(GFP_KERNEL);
+	iommu->cmd_sem = iommu_alloc_4k_pages(iommu, GFP_KERNEL | __GFP_ZERO, 1);
 
 	return iommu->cmd_sem ? 0 : -ENOMEM;
 }
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
index add1859b2899..5dff7ffbef11 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
@@ -309,6 +309,10 @@ static struct arm_smmu_device *qcom_smmu_create(struct arm_smmu_device *smmu,
 {
 	struct qcom_smmu *qsmmu;
 
+	/* Check to make sure qcom_scm has finished probing */
+	if (!qcom_scm_is_available())
+		return ERR_PTR(-EPROBE_DEFER);
+
 	qsmmu = devm_krealloc(smmu->dev, smmu, sizeof(*qsmmu), GFP_KERNEL);
 	if (!qsmmu)
 		return ERR_PTR(-ENOMEM);
diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c
index 404b40af31cb..b46dbfa6d0ed 100644
--- a/drivers/iommu/intel/dmar.c
+++ b/drivers/iommu/intel/dmar.c
@@ -333,6 +333,13 @@ static void  dmar_pci_bus_del_dev(struct dmar_pci_notify_info *info)
 	dmar_iommu_notify_scope_dev(info);
 }
 
+static inline void vf_inherit_msi_domain(struct pci_dev *pdev)
+{
+	struct pci_dev *physfn = pci_physfn(pdev);
+
+	dev_set_msi_domain(&pdev->dev, dev_get_msi_domain(&physfn->dev));
+}
+
 static int dmar_pci_bus_notifier(struct notifier_block *nb,
 				 unsigned long action, void *data)
 {
@@ -342,8 +349,20 @@ static int dmar_pci_bus_notifier(struct notifier_block *nb,
 	/* Only care about add/remove events for physical functions.
 	 * For VFs we actually do the lookup based on the corresponding
 	 * PF in device_to_iommu() anyway. */
-	if (pdev->is_virtfn)
+	if (pdev->is_virtfn) {
+		/*
+		 * Ensure that the VF device inherits the irq domain of the
+		 * PF device. Ideally the device would inherit the domain
+		 * from the bus, but DMAR can have multiple units per bus
+		 * which makes this impossible. The VF 'bus' could inherit
+		 * from the PF device, but that's yet another x86'sism to
+		 * inflict on everybody else.
+		 */
+		if (action == BUS_NOTIFY_ADD_DEVICE)
+			vf_inherit_msi_domain(pdev);
 		return NOTIFY_DONE;
+	}
+
 	if (action != BUS_NOTIFY_ADD_DEVICE &&
 	    action != BUS_NOTIFY_REMOVED_DEVICE)
 		return NOTIFY_DONE;
@@ -967,7 +986,8 @@ static int map_iommu(struct intel_iommu *iommu, u64 phys_addr)
 		warn_invalid_dmar(phys_addr, " returns all ones");
 		goto unmap;
 	}
-	iommu->vccap = dmar_readq(iommu->reg + DMAR_VCCAP_REG);
+	if (ecap_vcs(iommu->ecap))
+		iommu->vccap = dmar_readq(iommu->reg + DMAR_VCCAP_REG);
 
 	/* the registers might be more than one page */
 	map_size = max_t(int, ecap_max_iotlb_offset(iommu->ecap),
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 07f8b012e1b6..788119c5b021 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -179,7 +179,7 @@ static int rwbf_quirk;
  * (used when kernel is launched w/ TXT)
  */
 static int force_on = 0;
-int intel_iommu_tboot_noforce;
+static int intel_iommu_tboot_noforce;
 static int no_platform_optin;
 
 #define ROOT_ENTRY_NR (VTD_PAGE_SIZE/sizeof(struct root_entry))
@@ -1829,7 +1829,7 @@ static void free_dmar_iommu(struct intel_iommu *iommu)
 		if (ecap_prs(iommu->ecap))
 			intel_svm_finish_prq(iommu);
 	}
-	if (ecap_vcs(iommu->ecap) && vccap_pasid(iommu->vccap))
+	if (vccap_pasid(iommu->vccap))
 		ioasid_unregister_allocator(&iommu->pasid_allocator);
 
 #endif
@@ -3120,7 +3120,7 @@ static void register_pasid_allocator(struct intel_iommu *iommu)
 	 * is active. All vIOMMU allocators will eventually be calling the same
 	 * host allocator.
 	 */
-	if (!ecap_vcs(iommu->ecap) || !vccap_pasid(iommu->vccap))
+	if (!vccap_pasid(iommu->vccap))
 		return;
 
 	pr_info("Register custom PASID allocator\n");
@@ -4205,7 +4205,8 @@ int __init intel_iommu_init(void)
 	 * Intel IOMMU is required for a TXT/tboot launch or platform
 	 * opt in, so enforce that.
 	 */
-	force_on = tboot_force_iommu() || platform_optin_force_iommu();
+	force_on = (!intel_iommu_tboot_noforce && tboot_force_iommu()) ||
+		    platform_optin_force_iommu();
 
 	if (iommu_init_mempool()) {
 		if (force_on)
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index a606b7aef96b..ffeebda8d6de 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -268,16 +268,18 @@ int iommu_probe_device(struct device *dev)
 	 */
 	iommu_alloc_default_domain(group, dev);
 
-	if (group->default_domain)
+	if (group->default_domain) {
 		ret = __iommu_attach_device(group->default_domain, dev);
+		if (ret) {
+			iommu_group_put(group);
+			goto err_release;
+		}
+	}
 
 	iommu_create_device_direct_mappings(group, dev);
 
 	iommu_group_put(group);
 
-	if (ret)
-		goto err_release;
-
 	if (ops->probe_finalize)
 		ops->probe_finalize(dev);