Merge branch 'kvm-6.11-sev-attestation' into HEAD

The GHCB 2.0 specification defines 2 GHCB request types to allow SNP guests
to send encrypted messages/requests to firmware: SNP Guest Requests and SNP
Extended Guest Requests. These encrypted messages are used for things like
servicing attestation requests issued by the guest. Implementing support for
these is required to be fully GHCB-compliant.

For the most part, KVM only needs to handle forwarding these requests to
firmware (to be issued via the SNP_GUEST_REQUEST firmware command defined
in the SEV-SNP Firmware ABI), and then forwarding the encrypted response to
the guest.

However, in the case of SNP Extended Guest Requests, the host is also
able to provide the certificate data corresponding to the endorsement key
used by firmware to sign attestation report requests. This certificate data
is provided by userspace because:

1) It allows for different keys/key types to be used for each particular
guest with requiring any sort of KVM API to configure the certificate
table in advance on a per-guest basis.

2) It provides additional flexibility with how attestation requests might
be handled during live migration where the certificate data for
source/dest might be different.

3) It allows all synchronization between certificates and firmware/signing
key updates to be handled purely by userspace rather than requiring
some in-kernel mechanism to facilitate it. [1]

To support fetching certificate data from userspace, a new KVM exit type will
be needed to handle fetching the certificate from userspace. An attempt to
define a new KVM_EXIT_COCO/KVM_EXIT_COCO_REQ_CERTS exit type to handle this
was introduced in v1 of this patchset, but is still being discussed by
community, so for now this patchset only implements a stub version of SNP
Extended Guest Requests that does not provide certificate data, but is still
enough to provide compliance with the GHCB 2.0 spec.

arch/x86/include/asm/sev.h

···
 	unsigned int data_npages;
 };
 
+#define MAX_AUTHTAG_LEN		32
+
+/* See SNP spec SNP_GUEST_REQUEST section for the structure */
+enum msg_type {
+	SNP_MSG_TYPE_INVALID = 0,
+	SNP_MSG_CPUID_REQ,
+	SNP_MSG_CPUID_RSP,
+	SNP_MSG_KEY_REQ,
+	SNP_MSG_KEY_RSP,
+	SNP_MSG_REPORT_REQ,
+	SNP_MSG_REPORT_RSP,
+	SNP_MSG_EXPORT_REQ,
+	SNP_MSG_EXPORT_RSP,
+	SNP_MSG_IMPORT_REQ,
+	SNP_MSG_IMPORT_RSP,
+	SNP_MSG_ABSORB_REQ,
+	SNP_MSG_ABSORB_RSP,
+	SNP_MSG_VMRK_REQ,
+	SNP_MSG_VMRK_RSP,
+
+	SNP_MSG_TYPE_MAX
+};
+
+enum aead_algo {
+	SNP_AEAD_INVALID,
+	SNP_AEAD_AES_256_GCM,
+};
+
+struct snp_guest_msg_hdr {
+	u8 authtag[MAX_AUTHTAG_LEN];
+	u64 msg_seqno;
+	u8 rsvd1[8];
+	u8 algo;
+	u8 hdr_version;
+	u16 hdr_sz;
+	u8 msg_type;
+	u8 msg_version;
+	u16 msg_sz;
+	u32 rsvd2;
+	u8 msg_vmpck;
+	u8 rsvd3[35];
+} __packed;
+
+struct snp_guest_msg {
+	struct snp_guest_msg_hdr hdr;
+	u8 payload[4000];
+} __packed;
+
 struct sev_guest_platform_data {
 	u64 secrets_gpa;
 };

arch/x86/kvm/svm/sev.c

···
 #include <linux/misc_cgroup.h>
 #include <linux/processor.h>
 #include <linux/trace_events.h>
+#include <uapi/linux/sev-guest.h>
 
 #include <asm/pkru.h>
 #include <asm/trapnr.h>
···
 	sev_decommission(handle);
 }
 
+/*
+ * This sets up bounce buffers/firmware pages to handle SNP Guest Request
+ * messages (e.g. attestation requests). See "SNP Guest Request" in the GHCB
+ * 2.0 specification for more details.
+ *
+ * Technically, when an SNP Guest Request is issued, the guest will provide its
+ * own request/response pages, which could in theory be passed along directly
+ * to firmware rather than using bounce pages. However, these pages would need
+ * special care:
+ *
+ *   - Both pages are from shared guest memory, so they need to be protected
+ *     from migration/etc. occurring while firmware reads/writes to them. At a
+ *     minimum, this requires elevating the ref counts and potentially needing
+ *     an explicit pinning of the memory. This places additional restrictions
+ *     on what type of memory backends userspace can use for shared guest
+ *     memory since there is some reliance on using refcounted pages.
+ *
+ *   - The response page needs to be switched to Firmware-owned[1] state
+ *     before the firmware can write to it, which can lead to potential
+ *     host RMP #PFs if the guest is misbehaved and hands the host a
+ *     guest page that KVM might write to for other reasons (e.g. virtio
+ *     buffers/etc.).
+ *
+ * Both of these issues can be avoided completely by using separately-allocated
+ * bounce pages for both the request/response pages and passing those to
+ * firmware instead. So that's what is being set up here.
+ *
+ * Guest requests rely on message sequence numbers to ensure requests are
+ * issued to firmware in the order the guest issues them, so concurrent guest
+ * requests generally shouldn't happen. But a misbehaved guest could issue
+ * concurrent guest requests in theory, so a mutex is used to serialize
+ * access to the bounce buffers.
+ *
+ * [1] See the "Page States" section of the SEV-SNP Firmware ABI for more
+ *     details on Firmware-owned pages, along with "RMP and VMPL Access Checks"
+ *     in the APM for details on the related RMP restrictions.
+ */
+static int snp_guest_req_init(struct kvm *kvm)
+{
+	struct kvm_sev_info *sev = to_kvm_sev_info(kvm);
+	struct page *req_page;
+
+	req_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
+	if (!req_page)
+		return -ENOMEM;
+
+	sev->guest_resp_buf = snp_alloc_firmware_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
+	if (!sev->guest_resp_buf) {
+		__free_page(req_page);
+		return -EIO;
+	}
+
+	sev->guest_req_buf = page_address(req_page);
+	mutex_init(&sev->guest_req_mutex);
+
+	return 0;
+}
+
+static void snp_guest_req_cleanup(struct kvm *kvm)
+{
+	struct kvm_sev_info *sev = to_kvm_sev_info(kvm);
+
+	if (sev->guest_resp_buf)
+		snp_free_firmware_page(sev->guest_resp_buf);
+
+	if (sev->guest_req_buf)
+		__free_page(virt_to_page(sev->guest_req_buf));
+
+	sev->guest_req_buf = NULL;
+	sev->guest_resp_buf = NULL;
+}
+
 static int __sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp,
 			    struct kvm_sev_init *data,
 			    unsigned long vm_type)
···
 	init_args.probe = false;
 	ret = sev_platform_init(&init_args);
 	if (ret)
+		goto e_free;
+
+	/* This needs to happen after SEV/SNP firmware initialization. */
+	if (vm_type == KVM_X86_SNP_VM && snp_guest_req_init(kvm))
 		goto e_free;
 
 	INIT_LIST_HEAD(&sev->regions_list);
···
 	}
 
 	if (sev_snp_guest(kvm)) {
+		snp_guest_req_cleanup(kvm);
+
 		/*
 		 * Decomission handles unbinding of the ASID. If it fails for
 		 * some unexpected reason, just leak the ASID.
···
 		break;
 	case SVM_VMGEXIT_PSC:
 		if (!sev_snp_guest(vcpu->kvm) || !kvm_ghcb_sw_scratch_is_valid(svm))
+			goto vmgexit_err;
+		break;
+	case SVM_VMGEXIT_GUEST_REQUEST:
+	case SVM_VMGEXIT_EXT_GUEST_REQUEST:
+		if (!sev_snp_guest(vcpu->kvm) ||
+		    !PAGE_ALIGNED(control->exit_info_1) ||
+		    !PAGE_ALIGNED(control->exit_info_2) ||
+		    control->exit_info_1 == control->exit_info_2)
 			goto vmgexit_err;
 		break;
 	default:
···
 	return ret;
 }
 
+static int snp_handle_guest_req(struct vcpu_svm *svm, gpa_t req_gpa, gpa_t resp_gpa)
+{
+	struct sev_data_snp_guest_request data = {0};
+	struct kvm *kvm = svm->vcpu.kvm;
+	struct kvm_sev_info *sev = to_kvm_sev_info(kvm);
+	sev_ret_code fw_err = 0;
+	int ret;
+
+	if (!sev_snp_guest(kvm))
+		return -EINVAL;
+
+	mutex_lock(&sev->guest_req_mutex);
+
+	if (kvm_read_guest(kvm, req_gpa, sev->guest_req_buf, PAGE_SIZE)) {
+		ret = -EIO;
+		goto out_unlock;
+	}
+
+	data.gctx_paddr = __psp_pa(sev->snp_context);
+	data.req_paddr = __psp_pa(sev->guest_req_buf);
+	data.res_paddr = __psp_pa(sev->guest_resp_buf);
+
+	/*
+	 * Firmware failures are propagated on to guest, but any other failure
+	 * condition along the way should be reported to userspace. E.g. if
+	 * the PSP is dead and commands are timing out.
+	 */
+	ret = sev_issue_cmd(kvm, SEV_CMD_SNP_GUEST_REQUEST, &data, &fw_err);
+	if (ret && !fw_err)
+		goto out_unlock;
+
+	if (kvm_write_guest(kvm, resp_gpa, sev->guest_resp_buf, PAGE_SIZE)) {
+		ret = -EIO;
+		goto out_unlock;
+	}
+
+	ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, SNP_GUEST_ERR(0, fw_err));
+
+	ret = 1; /* resume guest */
+
+out_unlock:
+	mutex_unlock(&sev->guest_req_mutex);
+	return ret;
+}
+
+static int snp_handle_ext_guest_req(struct vcpu_svm *svm, gpa_t req_gpa, gpa_t resp_gpa)
+{
+	struct kvm *kvm = svm->vcpu.kvm;
+	u8 msg_type;
+
+	if (!sev_snp_guest(kvm))
+		return -EINVAL;
+
+	if (kvm_read_guest(kvm, req_gpa + offsetof(struct snp_guest_msg_hdr, msg_type),
+			   &msg_type, 1))
+		return -EIO;
+
+	/*
+	 * As per GHCB spec, requests of type MSG_REPORT_REQ also allow for
+	 * additional certificate data to be provided alongside the attestation
+	 * report via the guest-provided data pages indicated by RAX/RBX. The
+	 * certificate data is optional and requires additional KVM enablement
+	 * to provide an interface for userspace to provide it, but KVM still
+	 * needs to be able to handle extended guest requests either way. So
+	 * provide a stub implementation that will always return an empty
+	 * certificate table in the guest-provided data pages.
+	 */
+	if (msg_type == SNP_MSG_REPORT_REQ) {
+		struct kvm_vcpu *vcpu = &svm->vcpu;
+		u64 data_npages;
+		gpa_t data_gpa;
+
+		if (!kvm_ghcb_rax_is_valid(svm) || !kvm_ghcb_rbx_is_valid(svm))
+			goto request_invalid;
+
+		data_gpa = vcpu->arch.regs[VCPU_REGS_RAX];
+		data_npages = vcpu->arch.regs[VCPU_REGS_RBX];
+
+		if (!PAGE_ALIGNED(data_gpa))
+			goto request_invalid;
+
+		/*
+		 * As per GHCB spec (see "SNP Extended Guest Request"), the
+		 * certificate table is terminated by 24-bytes of zeroes.
+		 */
+		if (data_npages && kvm_clear_guest(kvm, data_gpa, 24))
+			return -EIO;
+	}
+
+	return snp_handle_guest_req(svm, req_gpa, resp_gpa);
+
+request_invalid:
+	ghcb_set_sw_exit_info_1(svm->sev_es.ghcb, 2);
+	ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, GHCB_ERR_INVALID_INPUT);
+	return 1; /* resume guest */
+}
+
 static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm)
 {
 	struct vmcb_control_area *control = &svm->vmcb->control;
···
 		}
 
 		ret = 1;
+		break;
+	case SVM_VMGEXIT_GUEST_REQUEST:
+		ret = snp_handle_guest_req(svm, control->exit_info_1, control->exit_info_2);
+		break;
+	case SVM_VMGEXIT_EXT_GUEST_REQUEST:
+		ret = snp_handle_ext_guest_req(svm, control->exit_info_1, control->exit_info_2);
 		break;
 	case SVM_VMGEXIT_UNSUPPORTED_EVENT:
 		vcpu_unimpl(vcpu,

arch/x86/kvm/svm/svm.h

···
 	struct misc_cg *misc_cg; /* For misc cgroup accounting */
 	atomic_t migration_in_progress;
 	void *snp_context;      /* SNP guest context page */
+	void *guest_req_buf;    /* Bounce buffer for SNP Guest Request input */
+	void *guest_resp_buf;   /* Bounce buffer for SNP Guest Request output */
+	struct mutex guest_req_mutex; /* Must acquire before using bounce buffers */
 };
 
 struct kvm_svm {

drivers/virt/coco/sev-guest/sev-guest.c

···
 #include <asm/svm.h>
 #include <asm/sev.h>
 
-#include "sev-guest.h"
-
 #define DEVICE_NAME	"sev-guest"
 #define AAD_LEN		48
 #define MSG_HDR_VER	1

drivers/virt/coco/sev-guest/sev-guest.h

···
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (C) 2021 Advanced Micro Devices, Inc.
- *
- * Author: Brijesh Singh <[e-mail]>
- *
- * SEV-SNP API spec is available at https://developer.amd.com/sev
- */
-
-#ifndef __VIRT_SEVGUEST_H__
-#define __VIRT_SEVGUEST_H__
-
-#include <linux/types.h>
-
-#define MAX_AUTHTAG_LEN		32
-
-/* See SNP spec SNP_GUEST_REQUEST section for the structure */
-enum msg_type {
-	SNP_MSG_TYPE_INVALID = 0,
-	SNP_MSG_CPUID_REQ,
-	SNP_MSG_CPUID_RSP,
-	SNP_MSG_KEY_REQ,
-	SNP_MSG_KEY_RSP,
-	SNP_MSG_REPORT_REQ,
-	SNP_MSG_REPORT_RSP,
-	SNP_MSG_EXPORT_REQ,
-	SNP_MSG_EXPORT_RSP,
-	SNP_MSG_IMPORT_REQ,
-	SNP_MSG_IMPORT_RSP,
-	SNP_MSG_ABSORB_REQ,
-	SNP_MSG_ABSORB_RSP,
-	SNP_MSG_VMRK_REQ,
-	SNP_MSG_VMRK_RSP,
-
-	SNP_MSG_TYPE_MAX
-};
-
-enum aead_algo {
-	SNP_AEAD_INVALID,
-	SNP_AEAD_AES_256_GCM,
-};
-
-struct snp_guest_msg_hdr {
-	u8 authtag[MAX_AUTHTAG_LEN];
-	u64 msg_seqno;
-	u8 rsvd1[8];
-	u8 algo;
-	u8 hdr_version;
-	u16 hdr_sz;
-	u8 msg_type;
-	u8 msg_version;
-	u16 msg_sz;
-	u32 rsvd2;
-	u8 msg_vmpck;
-	u8 rsvd3[35];
-} __packed;
-
-struct snp_guest_msg {
-	struct snp_guest_msg_hdr hdr;
-	u8 payload[4000];
-} __packed;
-
-#endif /* __VIRT_SEVGUEST_H__ */

include/uapi/linux/sev-guest.h

···
 #define SNP_GUEST_FW_ERR_MASK		GENMASK_ULL(31, 0)
 #define SNP_GUEST_VMM_ERR_SHIFT		32
 #define SNP_GUEST_VMM_ERR(x)		(((u64)x) << SNP_GUEST_VMM_ERR_SHIFT)
+#define SNP_GUEST_FW_ERR(x)		((x) & SNP_GUEST_FW_ERR_MASK)
+#define SNP_GUEST_ERR(vmm_err, fw_err)	(SNP_GUEST_VMM_ERR(vmm_err) | \
+					 SNP_GUEST_FW_ERR(fw_err))
 
 #define SNP_GUEST_VMM_ERR_INVALID_LEN	1
 #define SNP_GUEST_VMM_ERR_BUSY		2