iommu fixes for -rc6

- Fix intel iommu driver when running on devices without VCCAP_REG
 
 - Fix swiotlb and "iommu=pt" interaction under TXT (tboot)
 
 - Fix missing return value check during device probe()
 
 - Fix probe ordering for Qualcomm SMMU implementation
 
 - Ensure page-sized mappings are used for AMD IOMMU buffers with SNP RMP
 -----BEGIN PGP SIGNATURE-----
 
 iQFEBAABCgAuFiEEPxTL6PPUbjXGY88ct6xw3ITBYzQFAl/A3msQHHdpbGxAa2Vy
 bmVsLm9yZwAKCRC3rHDchMFjNAI6B/9/MLjurPmQrSusq9Y7dhnGR7aahtICLAwR
 UDZHebGTeVxNqtTklQVl/1qgcY7DxU40LAO1777MM7eHOW1FnlCAWrkTo6BBQsGx
 U1FKegOJ/0eVHFPtFDfM7IA2skeLwlZW+hywNLAksme5mtd6iZG9yQLlDFqAjxL7
 v8uXgfHFn6Z2MvMc2O+IeKTtflIwPek/6rYuaEf7UknA6ZYPAD3hnu9i1RTEuUAA
 h2PoVrrJ/KefEsCMUIq2jwMTsSvxohDH8ClGK9b6h74J2CLKKuhALSgABRAmsEL9
 7w5TVdtMQ85n3ccnXyT4RBQ+O/eVtmsKSdfeAbFI4nG9e9j7YE1L
 =BI1u
 -----END PGP SIGNATURE-----

Merge tag 'iommu-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull iommu fixes from Will Deacon:
 "Here's another round of IOMMU fixes for -rc6 consisting mainly of a
  bunch of independent driver fixes. Thomas agreed for me to take the
  x86 'tboot' fix here, as it fixes a regression introduced by a vt-d
  change.

   - Fix intel iommu driver when running on devices without VCCAP_REG

   - Fix swiotlb and "iommu=pt" interaction under TXT (tboot)

   - Fix missing return value check during device probe()

   - Fix probe ordering for Qualcomm SMMU implementation

   - Ensure page-sized mappings are used for AMD IOMMU buffers with SNP
     RMP"

* tag 'iommu-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux:
  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

arch/x86/kernel/tboot.c

@@ -514,13 +514,10 @@ int tboot_force_iommu(void)
 	if (!tboot_enabled())
 		return 0;
 
-	if (no_iommu || swiotlb || dmar_disabled)
+	if (no_iommu || dmar_disabled)
 		pr_warn("Forcing Intel-IOMMU to enabled\n");
 
 	dmar_disabled = 0;
-#ifdef CONFIG_SWIOTLB
-	swiotlb = 0;
-#endif
 	no_iommu = 0;
 
 	return 1;

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;
 }

drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c

@@ -69,6 +69,10 @@ struct arm_smmu_device *qcom_smmu_impl_init(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_kzalloc(smmu->dev, sizeof(*qsmmu), GFP_KERNEL);
 	if (!qsmmu)
 		return ERR_PTR(-ENOMEM);

drivers/iommu/intel/dmar.c

@@ -986,7 +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),

drivers/iommu/intel/iommu.c

@@ -1833,7 +1833,7 @@ 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
@@ -3212,7 +3212,7 @@ 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");

drivers/iommu/iommu.c

@@ -264,16 +264,18 @@ 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);