Received-SPF: pass (google.com: domain of linux-kernel+bounces-202813-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:40f1:3f00::1 as permitted sender) client-ip=2604:1380:40f1:3f00::1;
Received-SPF: Pass (protection.outlook.com: domain of amd.com designates
 165.204.84.17 as permitted sender) receiver=protection.outlook.com;
 client-ip=165.204.84.17; helo=SATLEXMB04.amd.com; pr=C
From: Tom Lendacky <thomas.lendacky@amd.com>
To: <linux-kernel@vger.kernel.org>, <x86@kernel.org>,
	<linux-coco@lists.linux.dev>, <svsm-devel@coconut-svsm.dev>
CC: Thomas Gleixner <tglx@linutronix.de>, Ingo Molnar <mingo@redhat.com>,
	Borislav Petkov <bp@alien8.de>, Dave Hansen <dave.hansen@linux.intel.com>,
	"H. Peter Anvin" <hpa@zytor.com>, Andy Lutomirski <luto@kernel.org>, "Peter
 Zijlstra" <peterz@infradead.org>, Dan Williams <dan.j.williams@intel.com>,
	Michael Roth <michael.roth@amd.com>, Ashish Kalra <ashish.kalra@amd.com>
Subject: [PATCH v5 05/13] x86/sev: Use the SVSM to create a vCPU when not in VMPL0
Date: Wed, 5 Jun 2024 10:18:48 -0500
Message-ID: <bcdd95ecabe9723673b9693c7f1533a2b8f17781.1717600736.git.thomas.lendacky@amd.com>
In-Reply-To: <cover.1717600736.git.thomas.lendacky@amd.com>
References: <cover.1717600736.git.thomas.lendacky@amd.com>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Content-Type: text/plain
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 05 Jun 2024 15:19:47.2849
 (UTC)
X-MS-Exchange-CrossTenant-Network-Message-Id: 7121651e-6a81-4792-1363-08dc8572efad
X-MS-Exchange-CrossTenant-Id: 3dd8961f-e488-4e60-8e11-a82d994e183d
X-MS-Exchange-CrossTenant-OriginalAttributedTenantConnectingIp: TenantId=3dd8961f-e488-4e60-8e11-a82d994e183d;Ip=[165.204.84.17];Helo=[SATLEXMB04.amd.com]
X-MS-Exchange-CrossTenant-AuthSource:
	BN3PEPF0000B36D.namprd21.prod.outlook.com
X-MS-Exchange-CrossTenant-AuthAs: Anonymous
X-MS-Exchange-CrossTenant-FromEntityHeader: HybridOnPrem
X-MS-Exchange-Transport-CrossTenantHeadersStamped: MW4PR12MB7358

Using the RMPADJUST instruction, the VSMA attribute can only be changed
at VMPL0. An SVSM will be present when running at VMPL1 or a lower
privilege level.

When an SVSM is present, use the SVSM_CORE_CREATE_VCPU call or the
SVSM_CORE_DESTROY_VCPU call to perform VMSA attribute changes. Use the
VMPL level supplied by the SVSM for the VMSA when starting the AP.

Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
---
 arch/x86/include/asm/sev.h |  2 +
 arch/x86/kernel/sev.c      | 75 ++++++++++++++++++++++++++++----------
 2 files changed, 57 insertions(+), 20 deletions(-)

diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h
index 01e3866c4d61..36cd7aebaa9b 100644
--- a/arch/x86/include/asm/sev.h
+++ b/arch/x86/include/asm/sev.h
@@ -233,6 +233,8 @@ struct svsm_call {
 #define SVSM_CORE_CALL(x)		((0ULL << 32) | (x))
 #define SVSM_CORE_REMAP_CA		0
 #define SVSM_CORE_PVALIDATE		1
+#define SVSM_CORE_CREATE_VCPU		2
+#define SVSM_CORE_DELETE_VCPU		3
 
 #ifdef CONFIG_AMD_MEM_ENCRYPT
 extern void __sev_es_ist_enter(struct pt_regs *regs);
diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c
index b5c18ed4c572..ea4677177396 100644
--- a/arch/x86/kernel/sev.c
+++ b/arch/x86/kernel/sev.c
@@ -1006,22 +1006,50 @@ void snp_accept_memory(phys_addr_t start, phys_addr_t end)
 	set_pages_state(vaddr, npages, SNP_PAGE_STATE_PRIVATE);
 }
 
-static int snp_set_vmsa(void *va, bool vmsa)
+static int snp_set_vmsa(void *va, void *caa, int apic_id, bool make_vmsa)
 {
-	u64 attrs;
+	int ret;
 
-	/*
-	 * Running at VMPL0 allows the kernel to change the VMSA bit for a page
-	 * using the RMPADJUST instruction. However, for the instruction to
-	 * succeed it must target the permissions of a lesser privileged
-	 * (higher numbered) VMPL level, so use VMPL1 (refer to the RMPADJUST
-	 * instruction in the AMD64 APM Volume 3).
-	 */
-	attrs = 1;
-	if (vmsa)
-		attrs |= RMPADJUST_VMSA_PAGE_BIT;
+	if (snp_vmpl) {
+		struct svsm_call call = {};
+		unsigned long flags;
 
-	return rmpadjust((unsigned long)va, RMP_PG_SIZE_4K, attrs);
+		local_irq_save(flags);
+
+		call.caa = this_cpu_read(svsm_caa);
+		call.rcx = __pa(va);
+
+		if (make_vmsa) {
+			/* Protocol 0, Call ID 2 */
+			call.rax = SVSM_CORE_CALL(SVSM_CORE_CREATE_VCPU);
+			call.rdx = __pa(caa);
+			call.r8  = apic_id;
+		} else {
+			/* Protocol 0, Call ID 3 */
+			call.rax = SVSM_CORE_CALL(SVSM_CORE_DELETE_VCPU);
+		}
+
+		ret = svsm_perform_call_protocol(&call);
+
+		local_irq_restore(flags);
+	} else {
+		u64 attrs;
+
+		/*
+		 * Running at VMPL0 allows the kernel to change the VMSA bit for a page
+		 * using the RMPADJUST instruction. However, for the instruction to
+		 * succeed it must target the permissions of a lesser privileged
+		 * (higher numbered) VMPL level, so use VMPL1 (refer to the RMPADJUST
+		 * instruction in the AMD64 APM Volume 3).
+		 */
+		attrs = 1;
+		if (make_vmsa)
+			attrs |= RMPADJUST_VMSA_PAGE_BIT;
+
+		ret = rmpadjust((unsigned long)va, RMP_PG_SIZE_4K, attrs);
+	}
+
+	return ret;
 }
 
 #define __ATTR_BASE		(SVM_SELECTOR_P_MASK | SVM_SELECTOR_S_MASK)
@@ -1055,11 +1083,11 @@ static void *snp_alloc_vmsa_page(int cpu)
 	return page_address(p + 1);
 }
 
-static void snp_cleanup_vmsa(struct sev_es_save_area *vmsa)
+static void snp_cleanup_vmsa(struct sev_es_save_area *vmsa, int apic_id)
 {
 	int err;
 
-	err = snp_set_vmsa(vmsa, false);
+	err = snp_set_vmsa(vmsa, NULL, apic_id, false);
 	if (err)
 		pr_err("clear VMSA page failed (%u), leaking page\n", err);
 	else
@@ -1070,6 +1098,7 @@ static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip)
 {
 	struct sev_es_save_area *cur_vmsa, *vmsa;
 	struct ghcb_state state;
+	struct svsm_ca *caa;
 	unsigned long flags;
 	struct ghcb *ghcb;
 	u8 sipi_vector;
@@ -1116,6 +1145,9 @@ static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip)
 	if (!vmsa)
 		return -ENOMEM;
 
+	/* If an SVSM is present, the SVSM per-CPU CAA will be !NULL */
+	caa = per_cpu(svsm_caa, cpu);
+
 	/* CR4 should maintain the MCE value */
 	cr4 = native_read_cr4() & X86_CR4_MCE;
 
@@ -1163,11 +1195,11 @@ static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip)
 	 *   VMPL level
 	 *   SEV_FEATURES (matches the SEV STATUS MSR right shifted 2 bits)
 	 */
-	vmsa->vmpl		= 0;
+	vmsa->vmpl		= snp_vmpl;
 	vmsa->sev_features	= sev_status >> 2;
 
 	/* Switch the page over to a VMSA page now that it is initialized */
-	ret = snp_set_vmsa(vmsa, true);
+	ret = snp_set_vmsa(vmsa, caa, apic_id, true);
 	if (ret) {
 		pr_err("set VMSA page failed (%u)\n", ret);
 		free_page((unsigned long)vmsa);
@@ -1183,7 +1215,10 @@ static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip)
 	vc_ghcb_invalidate(ghcb);
 	ghcb_set_rax(ghcb, vmsa->sev_features);
 	ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_AP_CREATION);
-	ghcb_set_sw_exit_info_1(ghcb, ((u64)apic_id << 32) | SVM_VMGEXIT_AP_CREATE);
+	ghcb_set_sw_exit_info_1(ghcb,
+				((u64)apic_id << 32)	|
+				((u64)snp_vmpl << 16)	|
+				SVM_VMGEXIT_AP_CREATE);
 	ghcb_set_sw_exit_info_2(ghcb, __pa(vmsa));
 
 	sev_es_wr_ghcb_msr(__pa(ghcb));
@@ -1201,13 +1236,13 @@ static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip)
 
 	/* Perform cleanup if there was an error */
 	if (ret) {
-		snp_cleanup_vmsa(vmsa);
+		snp_cleanup_vmsa(vmsa, apic_id);
 		vmsa = NULL;
 	}
 
 	/* Free up any previous VMSA page */
 	if (cur_vmsa)
-		snp_cleanup_vmsa(cur_vmsa);
+		snp_cleanup_vmsa(cur_vmsa, apic_id);
 
 	/* Record the current VMSA page */
 	per_cpu(sev_vmsa, cpu) = vmsa;
-- 
2.43.2