Merge: [AMDSERVER 10.2 Feature] [Kernel] Advertise Host (v1) Page Table NOT Supported (for QEMU AMD eIOMMU)

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-10/-/merge_requests/1384

JIRA: https://issues.redhat.com/browse/RHEL-107079

 * 7e5516e iommu/amd: Add HATDis feature support
 * 025d137 iommu/amd: Add efr[HATS] max v1 page table level

Signed-off-by: CKI Backport Bot <cki-ci-bot+cki-gitlab-backport-bot@redhat.com>

---

<small>Created 2025-08-29 15:43 UTC by backporter - [KWF FAQ](https://red.ht/kernel_workflow_doc) - [Slack #team-kernel-workflow](https://redhat-internal.slack.com/archives/C04LRUPMJQ5) - [Source](https://gitlab.com/cki-project/kernel-workflow/-/blob/main/webhook/utils/backporter.py) - [Documentation](https://gitlab.com/cki-project/kernel-workflow/-/blob/main/docs/README.backporter.md) - [Report an issue](https://issues.redhat.com/secure/CreateIssueDetails!init.jspa?pid=12334433&issuetype=1&priority=4&summary=backporter+webhook+issue&components=kernel-workflow+/+backporter)</small>

Approved-by: Eder Zulian <ezulian@redhat.com>
Approved-by: Jerry Snitselaar <jsnitsel@redhat.com>
Approved-by: CKI KWF Bot <cki-ci-bot+kwf-gitlab-com@redhat.com>

Merged-by: CKI GitLab Kmaint Pipeline Bot <26919896-cki-kmaint-pipeline-bot@users.noreply.gitlab.com>

Author: CKI KWF Bot

drivers/iommu/amd/amd_iommu.h

@@ -42,7 +42,9 @@ int amd_iommu_enable_faulting(unsigned int cpu);
 extern int amd_iommu_guest_ir;
 extern enum protection_domain_mode amd_iommu_pgtable;
 extern int amd_iommu_gpt_level;
+extern u8 amd_iommu_hpt_level;
 extern unsigned long amd_iommu_pgsize_bitmap;
+extern bool amd_iommu_hatdis;
 
 /* Protection domain ops */
 void amd_iommu_init_identity_domain(void);

drivers/iommu/amd/amd_iommu_types.h

@@ -96,6 +96,7 @@
 #define FEATURE_GA		BIT_ULL(7)
 #define FEATURE_HE		BIT_ULL(8)
 #define FEATURE_PC		BIT_ULL(9)
+#define FEATURE_HATS		GENMASK_ULL(11, 10)
 #define FEATURE_GATS		GENMASK_ULL(13, 12)
 #define FEATURE_GLX		GENMASK_ULL(15, 14)
 #define FEATURE_GAM_VAPIC	BIT_ULL(21)
@@ -460,6 +461,9 @@
 /* IOMMU Feature Reporting Field (for IVHD type 10h */
 #define IOMMU_FEAT_GASUP_SHIFT	6
 
+/* IOMMU HATDIS for IVHD type 11h and 40h */
+#define IOMMU_IVHD_ATTR_HATDIS_SHIFT	0
+
 /* IOMMU Extended Feature Register (EFR) */
 #define IOMMU_EFR_XTSUP_SHIFT	2
 #define IOMMU_EFR_GASUP_SHIFT	7
@@ -558,7 +562,8 @@ struct amd_io_pgtable {
 };
 
 enum protection_domain_mode {
-	PD_MODE_V1 = 1,
+	PD_MODE_NONE,
+	PD_MODE_V1,
 	PD_MODE_V2,
 };
 

drivers/iommu/amd/init.c

@@ -152,6 +152,8 @@ bool amd_iommu_dump;
 bool amd_iommu_irq_remap __read_mostly;
 
 enum protection_domain_mode amd_iommu_pgtable = PD_MODE_V1;
+/* Host page table level */
+u8 amd_iommu_hpt_level;
 /* Guest page table level */
 int amd_iommu_gpt_level = PAGE_MODE_4_LEVEL;
 
@@ -168,6 +170,9 @@ static int amd_iommu_target_ivhd_type;
 u64 amd_iommu_efr;
 u64 amd_iommu_efr2;
 
+/* Host (v1) page table is not supported*/
+bool amd_iommu_hatdis;
+
 /* SNP is enabled on the system? */
 bool amd_iommu_snp_en;
 EXPORT_SYMBOL(amd_iommu_snp_en);
@@ -1798,6 +1803,11 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h,
 		if (h->efr_reg & BIT(IOMMU_EFR_XTSUP_SHIFT))
 			amd_iommu_xt_mode = IRQ_REMAP_X2APIC_MODE;
 
+		if (h->efr_attr & BIT(IOMMU_IVHD_ATTR_HATDIS_SHIFT)) {
+			pr_warn_once("Host Address Translation is not supported.\n");
+			amd_iommu_hatdis = true;
+		}
+
 		early_iommu_features_init(iommu, h);
 
 		break;
@@ -2118,7 +2128,15 @@ static int __init iommu_init_pci(struct amd_iommu *iommu)
 			return ret;
 	}
 
-	iommu_device_register(&iommu->iommu, &amd_iommu_ops, NULL);
+	ret = iommu_device_register(&iommu->iommu, &amd_iommu_ops, NULL);
+	if (ret || amd_iommu_pgtable == PD_MODE_NONE) {
+		/*
+		 * Remove sysfs if DMA translation is not supported by the
+		 * IOMMU. Do not return an error to enable IRQ remapping
+		 * in state_next(), DTE[V, TV] must eventually be set to 0.
+		 */
+		iommu_device_sysfs_remove(&iommu->iommu);
+	}
 
 	return pci_enable_device(iommu->dev);
 }
@@ -2579,7 +2597,7 @@ static void init_device_table_dma(struct amd_iommu_pci_seg *pci_seg)
 	u32 devid;
 	struct dev_table_entry *dev_table = pci_seg->dev_table;
 
-	if (dev_table == NULL)
+	if (!dev_table || amd_iommu_pgtable == PD_MODE_NONE)
 		return;
 
 	for (devid = 0; devid <= pci_seg->last_bdf; ++devid) {
@@ -3041,6 +3059,7 @@ static int __init early_amd_iommu_init(void)
 	struct acpi_table_header *ivrs_base;
 	int ret;
 	acpi_status status;
+	u8 efr_hats;
 
 	if (!amd_iommu_detected)
 		return -ENODEV;
@@ -3085,13 +3104,37 @@ static int __init early_amd_iommu_init(void)
 	    FIELD_GET(FEATURE_GATS, amd_iommu_efr) == GUEST_PGTABLE_5_LEVEL)
 		amd_iommu_gpt_level = PAGE_MODE_5_LEVEL;
 
+	efr_hats = FIELD_GET(FEATURE_HATS, amd_iommu_efr);
+	if (efr_hats != 0x3) {
+		/*
+		 * efr[HATS] bits specify the maximum host translation level
+		 * supported, with LEVEL 4 being initial max level.
+		 */
+		amd_iommu_hpt_level = efr_hats + PAGE_MODE_4_LEVEL;
+	} else {
+		pr_warn_once(FW_BUG "Disable host address translation due to invalid translation level (%#x).\n",
+			     efr_hats);
+		amd_iommu_hatdis = true;
+	}
+
 	if (amd_iommu_pgtable == PD_MODE_V2) {
 		if (!amd_iommu_v2_pgtbl_supported()) {
 			pr_warn("Cannot enable v2 page table for DMA-API. Fallback to v1.\n");
 			amd_iommu_pgtable = PD_MODE_V1;
 		}
 	}
 
+	if (amd_iommu_hatdis) {
+		/*
+		 * Host (v1) page table is not available. Attempt to use
+		 * Guest (v2) page table.
+		 */
+		if (amd_iommu_v2_pgtbl_supported())
+			amd_iommu_pgtable = PD_MODE_V2;
+		else
+			amd_iommu_pgtable = PD_MODE_NONE;
+	}
+
 	/* Disable any previously enabled IOMMUs */
 	if (!is_kdump_kernel() || amd_iommu_disabled)
 		disable_iommus();

drivers/iommu/amd/io_pgtable.c

@@ -132,7 +132,7 @@ static bool increase_address_space(struct amd_io_pgtable *pgtable,
 		goto out;
 
 	ret = false;
-	if (WARN_ON_ONCE(pgtable->mode == PAGE_MODE_6_LEVEL))
+	if (WARN_ON_ONCE(pgtable->mode == amd_iommu_hpt_level))
 		goto out;
 
 	*pte = PM_LEVEL_PDE(pgtable->mode, iommu_virt_to_phys(pgtable->root));
@@ -531,7 +531,7 @@ static void v1_free_pgtable(struct io_pgtable *iop)
 
 	/* Page-table is not visible to IOMMU anymore, so free it */
 	BUG_ON(pgtable->mode < PAGE_MODE_NONE ||
-	       pgtable->mode > PAGE_MODE_6_LEVEL);
+	       pgtable->mode > amd_iommu_hpt_level);
 
 	free_sub_pt(pgtable->root, pgtable->mode, &freelist);
 	iommu_put_pages_list(&freelist);

drivers/iommu/amd/iommu.c

@@ -2416,6 +2416,13 @@ static struct iommu_device *amd_iommu_probe_device(struct device *dev)
 					     pci_max_pasids(to_pci_dev(dev)));
 	}
 
+	if (amd_iommu_pgtable == PD_MODE_NONE) {
+		pr_warn_once("%s: DMA translation not supported by iommu.\n",
+			     __func__);
+		iommu_dev = ERR_PTR(-ENODEV);
+		goto out_err;
+	}
+
 out_err:
 
 	iommu_completion_wait(iommu);
@@ -2503,6 +2510,9 @@ static int pdom_setup_pgtable(struct protection_domain *domain,
 	case PD_MODE_V2:
 		fmt = AMD_IOMMU_V2;
 		break;
+	case PD_MODE_NONE:
+		WARN_ON_ONCE(1);
+		return -EPERM;
 	}
 
 	domain->iop.pgtbl.cfg.amd.nid = dev_to_node(dev);
@@ -2516,14 +2526,17 @@ static int pdom_setup_pgtable(struct protection_domain *domain,
 static inline u64 dma_max_address(enum protection_domain_mode pgtable)
 {
 	if (pgtable == PD_MODE_V1)
-		return ~0ULL;
+		return PM_LEVEL_SIZE(amd_iommu_hpt_level);
 
 	/* V2 with 4/5 level page table */
 	return ((1ULL << PM_LEVEL_SHIFT(amd_iommu_gpt_level)) - 1);
 }
 
 static bool amd_iommu_hd_support(struct amd_iommu *iommu)
 {
+	if (amd_iommu_hatdis)
+		return false;
+
 	return iommu && (iommu->features & FEATURE_HDSUP);
 }