iommu/amd: Add support for nested domain allocation

The nested domain is allocated with IOMMU_DOMAIN_NESTED type to store
stage-1 translation (i.e. GVA->GPA). This includes the GCR3 root pointer
table along with guest page tables. The struct iommu_hwpt_amd_guest
contains this information, and is passed from user-space as a parameter
of the struct iommu_ops.domain_alloc_nested().

Reviewed-by: Nicolin Chen <nicolinc@nvidia.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>

drivers/iommu/amd/Makefile

@@ -1,4 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0-only
 obj-y += iommu.o init.o quirks.o ppr.o pasid.o
-obj-$(CONFIG_AMD_IOMMU_IOMMUFD) += iommufd.o
+obj-$(CONFIG_AMD_IOMMU_IOMMUFD) += iommufd.o nested.o
 obj-$(CONFIG_AMD_IOMMU_DEBUGFS) += debugfs.o

drivers/iommu/amd/amd_iommu.h

@@ -202,4 +202,8 @@ amd_iommu_make_clear_dte(struct iommu_dev_data *dev_data, struct dev_table_entry
 	new->data128[1] = 0;
 }
 
+/* NESTED */
+struct iommu_domain *
+amd_iommu_alloc_domain_nested(struct iommufd_viommu *viommu, u32 flags,
+			      const struct iommu_user_data *user_data);
 #endif /* AMD_IOMMU_H */

drivers/iommu/amd/amd_iommu_types.h

@@ -21,6 +21,8 @@
 #include <linux/irqreturn.h>
 #include <linux/generic_pt/iommu.h>
 
+#include <uapi/linux/iommufd.h>
+
 /*
  * Maximum number of IOMMUs supported
  */
@@ -353,6 +355,8 @@
 #define DTE_FLAG_V	BIT_ULL(0)
 #define DTE_FLAG_TV	BIT_ULL(1)
 #define DTE_FLAG_HAD	(3ULL << 7)
+#define DTE_MODE_MASK	GENMASK_ULL(11, 9)
+#define DTE_HOST_TRP	GENMASK_ULL(51, 12)
 #define DTE_FLAG_GIOV	BIT_ULL(54)
 #define DTE_FLAG_GV	BIT_ULL(55)
 #define DTE_GLX		GENMASK_ULL(57, 56)
@@ -501,6 +505,16 @@ struct amd_iommu_viommu {
 	struct protection_domain *parent; /* nest parent domain for this viommu */
 };
 
+/*
+ * Nested domain is specifically used for nested translation
+ */
+struct nested_domain {
+	struct iommu_domain domain; /* generic domain handle used by iommu core code */
+	u16 gdom_id;                /* domain ID from gDTE */
+	struct iommu_hwpt_amd_guest gdte; /* Guest vIOMMU DTE */
+	struct amd_iommu_viommu *viommu;  /* AMD hw-viommu this nested domain belong to */
+};
+
 /*
  * This structure contains generic data for  IOMMU protection domains
  * independent of their use.

drivers/iommu/amd/nested.c

@@ -0,0 +1,110 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2025 Advanced Micro Devices, Inc.
+ */
+
+#define dev_fmt(fmt)	"AMD-Vi: " fmt
+
+#include <linux/iommu.h>
+#include <uapi/linux/iommufd.h>
+
+#include "amd_iommu.h"
+
+static const struct iommu_domain_ops nested_domain_ops;
+
+static inline struct nested_domain *to_ndomain(struct iommu_domain *dom)
+{
+	return container_of(dom, struct nested_domain, domain);
+}
+
+/*
+ * Validate guest DTE to make sure that configuration for host (v1)
+ * and guest (v2) page tables are valid when allocating nested domain.
+ */
+static int validate_gdte_nested(struct iommu_hwpt_amd_guest *gdte)
+{
+	u32 gpt_level = FIELD_GET(DTE_GPT_LEVEL_MASK, gdte->dte[2]);
+
+	/* Must be zero: Mode, Host-TPR */
+	if (FIELD_GET(DTE_MODE_MASK, gdte->dte[0]) != 0 ||
+	    FIELD_GET(DTE_HOST_TRP, gdte->dte[0]) != 0)
+		return -EINVAL;
+
+	/* GCR3 TRP must be non-zero if V, GV is set */
+	if (FIELD_GET(DTE_FLAG_V, gdte->dte[0]) == 1 &&
+	    FIELD_GET(DTE_FLAG_GV, gdte->dte[0]) == 1 &&
+	    FIELD_GET(DTE_GCR3_14_12, gdte->dte[0]) == 0 &&
+	    FIELD_GET(DTE_GCR3_30_15, gdte->dte[1]) == 0 &&
+	    FIELD_GET(DTE_GCR3_51_31, gdte->dte[1]) == 0)
+		return -EINVAL;
+
+	/* Valid Guest Paging Mode values are 0 and 1 */
+	if (gpt_level != GUEST_PGTABLE_4_LEVEL &&
+	    gpt_level != GUEST_PGTABLE_5_LEVEL)
+		return -EINVAL;
+
+	/* GLX = 3 is reserved */
+	if (FIELD_GET(DTE_GLX, gdte->dte[0]) == 3)
+		return -EINVAL;
+
+	/*
+	 * We need to check host capability before setting
+	 * the Guest Paging Mode
+	 */
+	if (gpt_level == GUEST_PGTABLE_5_LEVEL &&
+	    amd_iommu_gpt_level < PAGE_MODE_5_LEVEL)
+		return -EOPNOTSUPP;
+
+	return 0;
+}
+
+/*
+ * This function is assigned to struct iommufd_viommu_ops.alloc_domain_nested()
+ * during the call to struct iommu_ops.viommu_init().
+ */
+struct iommu_domain *
+amd_iommu_alloc_domain_nested(struct iommufd_viommu *viommu, u32 flags,
+			      const struct iommu_user_data *user_data)
+{
+	int ret;
+	struct nested_domain *ndom;
+	struct amd_iommu_viommu *aviommu = container_of(viommu, struct amd_iommu_viommu, core);
+
+	if (user_data->type != IOMMU_HWPT_DATA_AMD_GUEST)
+		return ERR_PTR(-EOPNOTSUPP);
+
+	ndom = kzalloc(sizeof(*ndom), GFP_KERNEL);
+	if (!ndom)
+		return ERR_PTR(-ENOMEM);
+
+	ret = iommu_copy_struct_from_user(&ndom->gdte, user_data,
+					  IOMMU_HWPT_DATA_AMD_GUEST,
+					  dte);
+	if (ret)
+		goto out_err;
+
+	ret = validate_gdte_nested(&ndom->gdte);
+	if (ret)
+		goto out_err;
+
+	ndom->gdom_id = FIELD_GET(DTE_DOMID_MASK, ndom->gdte.dte[1]);
+	ndom->domain.ops = &nested_domain_ops;
+	ndom->domain.type = IOMMU_DOMAIN_NESTED;
+	ndom->viommu = aviommu;
+
+	return &ndom->domain;
+out_err:
+	kfree(ndom);
+	return ERR_PTR(ret);
+}
+
+static void nested_domain_free(struct iommu_domain *dom)
+{
+	struct nested_domain *ndom = to_ndomain(dom);
+
+	kfree(ndom);
+}
+
+static const struct iommu_domain_ops nested_domain_ops = {
+	.free = nested_domain_free,
+};