[PATCH v6 00/42] Add AMD Secure Nested Paging (SEV-SNP) Guest Support

@@ -481,8 +481,10 @@
 #define MSR_AMD64_SEV			0xc0010131
 #define MSR_AMD64_SEV_ENABLED_BIT	0
 #define MSR_AMD64_SEV_ES_ENABLED_BIT	1
+#define MSR_AMD64_SEV_SNP_ENABLED_BIT	2
 #define MSR_AMD64_SEV_ENABLED		BIT_ULL(MSR_AMD64_SEV_ENABLED_BIT)
 #define MSR_AMD64_SEV_ES_ENABLED	BIT_ULL(MSR_AMD64_SEV_ES_ENABLED_BIT)
+#define MSR_AMD64_SEV_SNP_ENABLED	BIT_ULL(MSR_AMD64_SEV_SNP_ENABLED_BIT)
 
 #define MSR_AMD64_VIRT_SPEC_CTRL	0xc001011f
 

@@ -50,6 +50,8 @@ static bool amd_cc_platform_has(enum cc_attr attr)
 	case CC_ATTR_GUEST_STATE_ENCRYPT:
 		return sev_status & MSR_AMD64_SEV_ES_ENABLED;
 
+	case CC_ATTR_SEV_SNP:
+		return sev_status & MSR_AMD64_SEV_SNP_ENABLED;
 	default:
 		return false;
 	}

@@ -433,6 +433,10 @@ static void print_mem_encrypt_feature_info(void)
 	if (cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT))
 		pr_cont(" SEV-ES");
 
+	/* Secure Nested Paging */
+	if (cc_platform_has(CC_ATTR_SEV_SNP))
+		pr_cont(" SEV-SNP");
+
 	pr_cont("\n");
 }
 

@@ -61,6 +61,14 @@ enum cc_attr {
 	 * Examples include SEV-ES.
 	 */
 	CC_ATTR_GUEST_STATE_ENCRYPT,
+
+	/**
+	 * @CC_ATTR_SEV_SNP: Guest SNP is active.
+	 *
+	 * The platform/OS is running as a guest/virtual machine and actively
+	 * using AMD SEV-SNP features.
+	 */
+	CC_ATTR_SEV_SNP = 0x100,
 };
 
 #ifdef CONFIG_ARCH_HAS_CC_PLATFORM

@@ -122,7 +122,7 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt,
 static bool early_setup_sev_es(void)
 {
 	if (!sev_es_negotiate_protocol())
-		sev_es_terminate(GHCB_SEV_ES_REASON_PROTOCOL_UNSUPPORTED);
+		sev_es_terminate(GHCB_SEV_ES_PROT_UNSUPPORTED);
 
 	if (set_page_decrypted((unsigned long)&boot_ghcb_page))
 		return false;

@@ -175,7 +175,7 @@ void do_boot_stage2_vc(struct pt_regs *regs, unsigned long exit_code)
 	enum es_result result;
 
 	if (!boot_ghcb && !early_setup_sev_es())
-		sev_es_terminate(GHCB_SEV_ES_REASON_GENERAL_REQUEST);
+		sev_es_terminate(GHCB_SEV_ES_GEN_REQ);
 
 	vc_ghcb_invalidate(boot_ghcb);
 	result = vc_init_em_ctxt(&ctxt, regs, exit_code);

@@ -202,5 +202,5 @@ void do_boot_stage2_vc(struct pt_regs *regs, unsigned long exit_code)
 	if (result == ES_OK)
 		vc_finish_insn(&ctxt);
 	else if (result != ES_RETRY)
-		sev_es_terminate(GHCB_SEV_ES_REASON_GENERAL_REQUEST);
+		sev_es_terminate(GHCB_SEV_ES_GEN_REQ);
 }

@@ -68,8 +68,8 @@
 	(((((u64)reason_set) &  GHCB_MSR_TERM_REASON_SET_MASK) << GHCB_MSR_TERM_REASON_SET_POS) | \
 	((((u64)reason_val) & GHCB_MSR_TERM_REASON_MASK) << GHCB_MSR_TERM_REASON_POS))
 
-#define GHCB_SEV_ES_REASON_GENERAL_REQUEST	0
-#define GHCB_SEV_ES_REASON_PROTOCOL_UNSUPPORTED	1
+#define GHCB_SEV_ES_GEN_REQ		0
+#define GHCB_SEV_ES_PROT_UNSUPPORTED	1
 
 #define GHCB_RESP_CODE(v)		((v) & GHCB_MSR_INFO_MASK)
 

@@ -210,7 +210,7 @@ void __init do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code)
 
 fail:
 	/* Terminate the guest */
-	sev_es_terminate(GHCB_SEV_ES_REASON_GENERAL_REQUEST);
+	sev_es_terminate(GHCB_SEV_ES_GEN_REQ);
 }
 
 static enum es_result vc_insn_string_read(struct es_em_ctxt *ctxt,

@@ -1397,7 +1397,7 @@ DEFINE_IDTENTRY_VC_KERNEL(exc_vmm_communication)
 		show_regs(regs);
 
 		/* Ask hypervisor to sev_es_terminate */
-		sev_es_terminate(GHCB_SEV_ES_REASON_GENERAL_REQUEST);
+		sev_es_terminate(GHCB_SEV_ES_GEN_REQ);
 
 		/* If that fails and we get here - just panic */
 		panic("Returned from Terminate-Request to Hypervisor\n");

@@ -1445,7 +1445,7 @@ bool __init handle_vc_boot_ghcb(struct pt_regs *regs)
 
 	/* Do initial setup or terminate the guest */
 	if (unlikely(boot_ghcb == NULL && !sev_es_setup_ghcb()))
-		sev_es_terminate(GHCB_SEV_ES_REASON_GENERAL_REQUEST);
+		sev_es_terminate(GHCB_SEV_ES_GEN_REQ);
 
 	vc_ghcb_invalidate(boot_ghcb);
 

@@ -18,20 +18,19 @@
 /* SEV Information Request/Response */
 #define GHCB_MSR_SEV_INFO_RESP		0x001
 #define GHCB_MSR_SEV_INFO_REQ		0x002
-#define GHCB_MSR_VER_MAX_POS		48
-#define GHCB_MSR_VER_MAX_MASK		0xffff
-#define GHCB_MSR_VER_MIN_POS		32
-#define GHCB_MSR_VER_MIN_MASK		0xffff
-#define GHCB_MSR_CBIT_POS		24
-#define GHCB_MSR_CBIT_MASK		0xff
-#define GHCB_MSR_SEV_INFO(_max, _min, _cbit)				\
-	((((_max) & GHCB_MSR_VER_MAX_MASK) << GHCB_MSR_VER_MAX_POS) |	\
-	 (((_min) & GHCB_MSR_VER_MIN_MASK) << GHCB_MSR_VER_MIN_POS) |	\
-	 (((_cbit) & GHCB_MSR_CBIT_MASK) << GHCB_MSR_CBIT_POS) |	\
+
+#define GHCB_MSR_SEV_INFO(_max, _min, _cbit)	\
+	/* GHCBData[63:48] */			\
+	((((_max) & 0xffff) << 48) |		\
+	 /* GHCBData[47:32] */			\
+	 (((_min) & 0xffff) << 32) |		\
+	 /* GHCBData[31:24] */			\
+	 (((_cbit) & 0xff)  << 24) |		\
 	 GHCB_MSR_SEV_INFO_RESP)
+
 #define GHCB_MSR_INFO(v)		((v) & 0xfffUL)
-#define GHCB_MSR_PROTO_MAX(v)		(((v) >> GHCB_MSR_VER_MAX_POS) & GHCB_MSR_VER_MAX_MASK)
-#define GHCB_MSR_PROTO_MIN(v)		(((v) >> GHCB_MSR_VER_MIN_POS) & GHCB_MSR_VER_MIN_MASK)
+#define GHCB_MSR_PROTO_MAX(v)		(((v) >> 48) & 0xffff)
+#define GHCB_MSR_PROTO_MIN(v)		(((v) >> 32) & 0xffff)
 
 /* CPUID Request/Response */
 #define GHCB_MSR_CPUID_REQ		0x004

@@ -46,27 +45,33 @@
 #define GHCB_CPUID_REQ_EBX		1
 #define GHCB_CPUID_REQ_ECX		2
 #define GHCB_CPUID_REQ_EDX		3
-#define GHCB_CPUID_REQ(fn, reg)		\
-		(GHCB_MSR_CPUID_REQ | \
-		(((unsigned long)reg & GHCB_MSR_CPUID_REG_MASK) << GHCB_MSR_CPUID_REG_POS) | \
-		(((unsigned long)fn) << GHCB_MSR_CPUID_FUNC_POS))
+#define GHCB_CPUID_REQ(fn, reg)				\
+	/* GHCBData[11:0] */				\
+	(GHCB_MSR_CPUID_REQ |				\
+	/* GHCBData[31:12] */				\
+	(((unsigned long)(reg) & 0x3) << 30) |		\
+	/* GHCBData[63:32] */				\
+	(((unsigned long)fn) << 32))
 
 /* AP Reset Hold */
-#define GHCB_MSR_AP_RESET_HOLD_REQ		0x006
-#define GHCB_MSR_AP_RESET_HOLD_RESP		0x007
+#define GHCB_MSR_AP_RESET_HOLD_REQ	0x006
+#define GHCB_MSR_AP_RESET_HOLD_RESP	0x007
 
 /* GHCB Hypervisor Feature Request/Response */
-#define GHCB_MSR_HV_FT_REQ			0x080
-#define GHCB_MSR_HV_FT_RESP			0x081
+#define GHCB_MSR_HV_FT_REQ		0x080
+#define GHCB_MSR_HV_FT_RESP		0x081
 
 #define GHCB_MSR_TERM_REQ		0x100
 #define GHCB_MSR_TERM_REASON_SET_POS	12
 #define GHCB_MSR_TERM_REASON_SET_MASK	0xf
 #define GHCB_MSR_TERM_REASON_POS	16
 #define GHCB_MSR_TERM_REASON_MASK	0xff
-#define GHCB_SEV_TERM_REASON(reason_set, reason_val)						  \
-	(((((u64)reason_set) &  GHCB_MSR_TERM_REASON_SET_MASK) << GHCB_MSR_TERM_REASON_SET_POS) | \
-	((((u64)reason_val) & GHCB_MSR_TERM_REASON_MASK) << GHCB_MSR_TERM_REASON_POS))
+
+#define GHCB_SEV_TERM_REASON(reason_set, reason_val)	\
+	/* GHCBData[15:12] */				\
+	(((((u64)reason_set) &  0xf) << 12) |		\
+	 /* GHCBData[23:16] */				\
+	((((u64)reason_val) & 0xff) << 16))
 
 #define GHCB_SEV_ES_GEN_REQ		0
 #define GHCB_SEV_ES_PROT_UNSUPPORTED	1

@@ -122,7 +122,7 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt,
 static bool early_setup_sev_es(void)
 {
 	if (!sev_es_negotiate_protocol())
-		sev_es_terminate(GHCB_SEV_ES_PROT_UNSUPPORTED);
+		sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_PROT_UNSUPPORTED);
 
 	if (set_page_decrypted((unsigned long)&boot_ghcb_page))
 		return false;

@@ -175,7 +175,7 @@ void do_boot_stage2_vc(struct pt_regs *regs, unsigned long exit_code)
 	enum es_result result;
 
 	if (!boot_ghcb && !early_setup_sev_es())
-		sev_es_terminate(GHCB_SEV_ES_GEN_REQ);
+		sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
 
 	vc_ghcb_invalidate(boot_ghcb);
 	result = vc_init_em_ctxt(&ctxt, regs, exit_code);

@@ -202,5 +202,5 @@ void do_boot_stage2_vc(struct pt_regs *regs, unsigned long exit_code)
 	if (result == ES_OK)
 		vc_finish_insn(&ctxt);
 	else if (result != ES_RETRY)
-		sev_es_terminate(GHCB_SEV_ES_GEN_REQ);
+		sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
 }

@@ -73,9 +73,17 @@
 	 /* GHCBData[23:16] */				\
 	((((u64)reason_val) & 0xff) << 16))
 
+/* Error codes from reason set 0 */
+#define SEV_TERM_SET_GEN		0
 #define GHCB_SEV_ES_GEN_REQ		0
 #define GHCB_SEV_ES_PROT_UNSUPPORTED	1
 
+/* Linux-specific reason codes (used with reason set 1) */
+#define SEV_TERM_SET_LINUX		1
+#define GHCB_TERM_REGISTER		0	/* GHCB GPA registration failure */
+#define GHCB_TERM_PSC			1	/* Page State Change failure */
+#define GHCB_TERM_PVALIDATE		2	/* Pvalidate failure */
+
 #define GHCB_RESP_CODE(v)		((v) & GHCB_MSR_INFO_MASK)
 
 #endif

@@ -24,15 +24,12 @@ static bool __init sev_es_check_cpu_features(void)
 	return true;
 }
 
-static void __noreturn sev_es_terminate(unsigned int reason)
+static void __noreturn sev_es_terminate(unsigned int set, unsigned int reason)
 {
 	u64 val = GHCB_MSR_TERM_REQ;
 
-	/*
-	 * Tell the hypervisor what went wrong - only reason-set 0 is
-	 * currently supported.
-	 */
-	val |= GHCB_SEV_TERM_REASON(0, reason);
+	/* Tell the hypervisor what went wrong. */
+	val |= GHCB_SEV_TERM_REASON(set, reason);
 
 	/* Request Guest Termination from Hypvervisor */
 	sev_es_wr_ghcb_msr(val);

@@ -210,7 +207,7 @@ void __init do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code)
 
 fail:
 	/* Terminate the guest */
-	sev_es_terminate(GHCB_SEV_ES_GEN_REQ);
+	sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
 }
 
 static enum es_result vc_insn_string_read(struct es_em_ctxt *ctxt,

@@ -1397,7 +1397,7 @@ DEFINE_IDTENTRY_VC_KERNEL(exc_vmm_communication)
 		show_regs(regs);
 
 		/* Ask hypervisor to sev_es_terminate */
-		sev_es_terminate(GHCB_SEV_ES_GEN_REQ);
+		sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
 
 		/* If that fails and we get here - just panic */
 		panic("Returned from Terminate-Request to Hypervisor\n");

@@ -1445,7 +1445,7 @@ bool __init handle_vc_boot_ghcb(struct pt_regs *regs)
 
 	/* Do initial setup or terminate the guest */
 	if (unlikely(boot_ghcb == NULL && !sev_es_setup_ghcb()))
-		sev_es_terminate(GHCB_SEV_ES_GEN_REQ);
+		sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
 
 	vc_ghcb_invalidate(boot_ghcb);
 

@@ -12,7 +12,7 @@
 #include <asm/insn.h>
 #include <asm/sev-common.h>
 
-#define GHCB_PROTO_OUR		0x0001UL
+#define GHCB_PROTOCOL_MIN	1ULL
 #define GHCB_PROTOCOL_MAX	1ULL
 #define GHCB_DEFAULT_USAGE	0ULL
 

@@ -14,6 +14,15 @@
 #define has_cpuflag(f)	boot_cpu_has(f)
 #endif
 
+/*
+ * Since feature negotiation related variables are set early in the boot
+ * process they must reside in the .data section so as not to be zeroed
+ * out when the .bss section is later cleared.
+ *
+ * GHCB protocol version negotiated with the hypervisor.
+ */
+static u16 __ro_after_init ghcb_version;
+
 static bool __init sev_es_check_cpu_features(void)
 {
 	if (!has_cpuflag(X86_FEATURE_RDRAND)) {

@@ -51,10 +60,12 @@ static bool sev_es_negotiate_protocol(void)
 	if (GHCB_MSR_INFO(val) != GHCB_MSR_SEV_INFO_RESP)
 		return false;
 
-	if (GHCB_MSR_PROTO_MAX(val) < GHCB_PROTO_OUR ||
-	    GHCB_MSR_PROTO_MIN(val) > GHCB_PROTO_OUR)
+	if (GHCB_MSR_PROTO_MAX(val) < GHCB_PROTOCOL_MIN ||
+	    GHCB_MSR_PROTO_MIN(val) > GHCB_PROTOCOL_MAX)
 		return false;
 
+	ghcb_version = min_t(size_t, GHCB_MSR_PROTO_MAX(val), GHCB_PROTOCOL_MAX);
+
 	return true;
 }
 

@@ -99,7 +110,7 @@ static enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb,
 	enum es_result ret;
 
 	/* Fill in protocol and format specifiers */
-	ghcb->protocol_version = GHCB_PROTOCOL_MAX;
+	ghcb->protocol_version = ghcb_version;
 	ghcb->ghcb_usage       = GHCB_DEFAULT_USAGE;
 
 	ghcb_set_sw_exit_code(ghcb, exit_code);

@@ -126,6 +126,36 @@ static bool __head check_la57_support(unsigned long physaddr)
 }
 #endif
 
+static unsigned long sme_postprocess_startup(struct boot_params *bp, pmdval_t *pmd)
+{
+	unsigned long vaddr, vaddr_end;
+	int i;
+
+	/* Encrypt the kernel and related (if SME is active) */
+	sme_encrypt_kernel(bp);
+
+	/*
+	 * Clear the memory encryption mask from the .bss..decrypted section.
+	 * The bss section will be memset to zero later in the initialization so
+	 * there is no need to zero it after changing the memory encryption
+	 * attribute.
+	 */
+	if (sme_get_me_mask()) {
+		vaddr = (unsigned long)__start_bss_decrypted;
+		vaddr_end = (unsigned long)__end_bss_decrypted;
+		for (; vaddr < vaddr_end; vaddr += PMD_SIZE) {
+			i = pmd_index(vaddr);
+			pmd[i] -= sme_get_me_mask();
+		}
+	}
+
+	/*
+	 * Return the SME encryption mask (if SME is active) to be used as a
+	 * modifier for the initial pgdir entry programmed into CR3.
+	 */
+	return sme_get_me_mask();
+}
+
 /* Code in __startup_64() can be relocated during execution, but the compiler
  * doesn't have to generate PC-relative relocations when accessing globals from
  * that function. Clang actually does not generate them, which leads to

@@ -135,7 +165,6 @@ static bool __head check_la57_support(unsigned long physaddr)
 unsigned long __head __startup_64(unsigned long physaddr,
 				  struct boot_params *bp)
 {
-	unsigned long vaddr, vaddr_end;
 	unsigned long load_delta, *p;
 	unsigned long pgtable_flags;
 	pgdval_t *pgd;

@@ -276,34 +305,7 @@ unsigned long __head __startup_64(unsigned long physaddr,
 	 */
 	*fixup_long(&phys_base, physaddr) += load_delta - sme_get_me_mask();
 
-	/* Encrypt the kernel and related (if SME is active) */
-	sme_encrypt_kernel(bp);
-
-	/*
-	 * Clear the memory encryption mask from the .bss..decrypted section.
-	 * The bss section will be memset to zero later in the initialization so
-	 * there is no need to zero it after changing the memory encryption
-	 * attribute.
-	 *
-	 * This is early code, use an open coded check for SME instead of
-	 * using cc_platform_has(). This eliminates worries about removing
-	 * instrumentation or checking boot_cpu_data in the cc_platform_has()
-	 * function.
-	 */
-	if (sme_get_me_mask()) {
-		vaddr = (unsigned long)__start_bss_decrypted;
-		vaddr_end = (unsigned long)__end_bss_decrypted;
-		for (; vaddr < vaddr_end; vaddr += PMD_SIZE) {
-			i = pmd_index(vaddr);
-			pmd[i] -= sme_get_me_mask();
-		}
-	}
-
-	/*
-	 * Return the SME encryption mask (if SME is active) to be used as a
-	 * modifier for the initial pgdir entry programmed into CR3.
-	 */
-	return sme_get_me_mask();
+	return sme_postprocess_startup(bp, pmd);
 }
 
 unsigned long __startup_secondary_64(void)

@@ -191,6 +191,20 @@ void __init do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code)
 	if (exit_code != SVM_EXIT_CPUID)
 		goto fail;
 
+	/*
+	 * A #VC implies that either SEV-ES or SEV-SNP are enabled, so the SEV
+	 * MSR is also available. Go ahead and initialize sev_status here to
+	 * allow SEV features to be checked without relying solely on the SEV
+	 * cpuid bit to indicate whether it is safe to do so.
+	 */
+	if (!sev_status) {
+		unsigned long lo, hi;
+
+		asm volatile("rdmsr" : "=a" (lo), "=d" (hi)
+				     : "c" (MSR_AMD64_SEV));
+		sev_status = (hi << 32) | lo;
+	}
+
 	sev_es_wr_ghcb_msr(GHCB_CPUID_REQ(fn, GHCB_CPUID_REQ_EAX));
 	VMGEXIT();
 	val = sev_es_rd_ghcb_msr();

@@ -60,6 +60,9 @@
 /* GHCB Hypervisor Feature Request/Response */
 #define GHCB_MSR_HV_FT_REQ		0x080
 #define GHCB_MSR_HV_FT_RESP		0x081
+#define GHCB_MSR_HV_FT_RESP_VAL(v)			\
+	/* GHCBData[63:12] */				\
+	(((u64)(v) & GENMASK_ULL(63, 12)) >> 12)
 
 #define GHCB_MSR_TERM_REQ		0x100
 #define GHCB_MSR_TERM_REASON_SET_POS	12

@@ -13,7 +13,7 @@
 #include <asm/sev-common.h>
 
 #define GHCB_PROTOCOL_MIN	1ULL
-#define GHCB_PROTOCOL_MAX	1ULL
+#define GHCB_PROTOCOL_MAX	2ULL
 #define GHCB_DEFAULT_USAGE	0ULL
 
 #define	VMGEXIT()			{ asm volatile("rep; vmmcall\n\r"); }

@@ -108,6 +108,7 @@
 #define SVM_VMGEXIT_AP_JUMP_TABLE		0x80000005
 #define SVM_VMGEXIT_SET_AP_JUMP_TABLE		0
 #define SVM_VMGEXIT_GET_AP_JUMP_TABLE		1
+#define SVM_VMGEXIT_HV_FEATURES			0x8000fffd
 #define SVM_VMGEXIT_UNSUPPORTED_EVENT		0x8000ffff
 
 /* Exit code reserved for hypervisor/software use */

@@ -218,6 +219,7 @@
 	{ SVM_VMGEXIT_NMI_COMPLETE,	"vmgexit_nmi_complete" }, \
 	{ SVM_VMGEXIT_AP_HLT_LOOP,	"vmgexit_ap_hlt_loop" }, \
 	{ SVM_VMGEXIT_AP_JUMP_TABLE,	"vmgexit_ap_jump_table" }, \
+	{ SVM_VMGEXIT_HV_FEATURES,	"vmgexit_hypervisor_feature" }, \
 	{ SVM_EXIT_ERR,         "invalid_guest_state" }
 
 

@@ -23,6 +23,9 @@
  */
 static u16 __ro_after_init ghcb_version;
 
+/* Bitmap of SEV features supported by the hypervisor */
+static u64 __ro_after_init sev_hv_features;
+
 static bool __init sev_es_check_cpu_features(void)
 {
 	if (!has_cpuflag(X86_FEATURE_RDRAND)) {

@@ -48,6 +51,30 @@ static void __noreturn sev_es_terminate(unsigned int set, unsigned int reason)
 		asm volatile("hlt\n" : : : "memory");
 }
 
+/*
+ * The hypervisor features are available from GHCB version 2 onward.
+ */
+static bool get_hv_features(void)
+{
+	u64 val;
+
+	sev_hv_features = 0;
+
+	if (ghcb_version < 2)
+		return false;
+
+	sev_es_wr_ghcb_msr(GHCB_MSR_HV_FT_REQ);
+	VMGEXIT();
+
+	val = sev_es_rd_ghcb_msr();
+	if (GHCB_RESP_CODE(val) != GHCB_MSR_HV_FT_RESP)
+		return false;
+
+	sev_hv_features = GHCB_MSR_HV_FT_RESP_VAL(val);
+
+	return true;
+}
+
 static bool sev_es_negotiate_protocol(void)
 {
 	u64 val;

@@ -66,6 +93,9 @@ static bool sev_es_negotiate_protocol(void)
 
 	ghcb_version = min_t(size_t, GHCB_MSR_PROTO_MAX(val), GHCB_PROTOCOL_MAX);
 
+	if (!get_hv_features())
+		return false;
+
 	return true;
 }
 

@@ -119,11 +119,23 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt,
 /* Include code for early handlers */
 #include "../../kernel/sev-shared.c"
 
-static bool early_setup_sev_es(void)
+static inline bool sev_snp_enabled(void)
+{
+	return sev_status & MSR_AMD64_SEV_SNP_ENABLED;
+}
+
+static bool do_early_sev_setup(void)
 {
 	if (!sev_es_negotiate_protocol())
 		sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_PROT_UNSUPPORTED);
 
+	/*
+	 * If SEV-SNP is enabled, then check if the hypervisor supports the SEV-SNP
+	 * features.
+	 */
+	if (sev_snp_enabled() && !(sev_hv_features & GHCB_HV_FT_SNP))
+		sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED);
+
 	if (set_page_decrypted((unsigned long)&boot_ghcb_page))
 		return false;
 

@@ -174,7 +186,7 @@ void do_boot_stage2_vc(struct pt_regs *regs, unsigned long exit_code)
 	struct es_em_ctxt ctxt;
 	enum es_result result;
 
-	if (!boot_ghcb && !early_setup_sev_es())
+	if (!boot_ghcb && !do_early_sev_setup())
 		sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
 
 	vc_ghcb_invalidate(boot_ghcb);

@@ -64,6 +64,8 @@
 	/* GHCBData[63:12] */				\
 	(((u64)(v) & GENMASK_ULL(63, 12)) >> 12)
 
+#define GHCB_HV_FT_SNP			BIT_ULL(0)
+
 #define GHCB_MSR_TERM_REQ		0x100
 #define GHCB_MSR_TERM_REASON_SET_POS	12
 #define GHCB_MSR_TERM_REASON_SET_MASK	0xf

@@ -80,6 +82,7 @@
 #define SEV_TERM_SET_GEN		0
 #define GHCB_SEV_ES_GEN_REQ		0
 #define GHCB_SEV_ES_PROT_UNSUPPORTED	1
+#define GHCB_SNP_UNSUPPORTED		2
 
 /* Linux-specific reason codes (used with reason set 1) */
 #define SEV_TERM_SET_LINUX		1

@@ -631,12 +631,16 @@ static enum es_result vc_handle_msr(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
  * This function runs on the first #VC exception after the kernel
  * switched to virtual addresses.
  */
-static bool __init sev_es_setup_ghcb(void)
+static bool __init setup_ghcb(void)
 {
 	/* First make sure the hypervisor talks a supported protocol. */
 	if (!sev_es_negotiate_protocol())
 		return false;
 
+	/* If SNP is active, make sure that hypervisor supports the feature. */
+	if (cc_platform_has(CC_ATTR_SEV_SNP) && !(sev_hv_features & GHCB_HV_FT_SNP))
+		sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED);
+
 	/*
 	 * Clear the boot_ghcb. The first exception comes in before the bss
 	 * section is cleared.

@@ -1444,7 +1448,7 @@ bool __init handle_vc_boot_ghcb(struct pt_regs *regs)
 	enum es_result result;
 
 	/* Do initial setup or terminate the guest */
-	if (unlikely(boot_ghcb == NULL && !sev_es_setup_ghcb()))
+	if (unlikely(!boot_ghcb && !setup_ghcb()))
 		sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
 
 	vc_ghcb_invalidate(boot_ghcb);

@@ -59,6 +59,9 @@ extern void vc_no_ghcb(void);
 extern void vc_boot_ghcb(void);
 extern bool handle_vc_boot_ghcb(struct pt_regs *regs);
 
+/* Software defined (when rFlags.CF = 1) */
+#define PVALIDATE_FAIL_NOUPDATE		255
+
 #ifdef CONFIG_AMD_MEM_ENCRYPT
 extern struct static_key_false sev_es_enable_key;
 extern void __sev_es_ist_enter(struct pt_regs *regs);

@@ -81,12 +84,30 @@ static __always_inline void sev_es_nmi_complete(void)
 		__sev_es_nmi_complete();
 }
 extern int __init sev_es_efi_map_ghcbs(pgd_t *pgd);
+static inline int pvalidate(unsigned long vaddr, bool rmp_psize, bool validate)
+{
+	bool no_rmpupdate;
+	int rc;
+
+	/* "pvalidate" mnemonic support in binutils 2.36 and newer */
+	asm volatile(".byte 0xF2, 0x0F, 0x01, 0xFF\n\t"
+		     CC_SET(c)
+		     : CC_OUT(c) (no_rmpupdate), "=a"(rc)
+		     : "a"(vaddr), "c"(rmp_psize), "d"(validate)
+		     : "memory", "cc");
+
+	if (no_rmpupdate)
+		return PVALIDATE_FAIL_NOUPDATE;
+
+	return rc;
+}
 #else
 static inline void sev_es_ist_enter(struct pt_regs *regs) { }
 static inline void sev_es_ist_exit(void) { }
 static inline int sev_es_setup_ap_jump_table(struct real_mode_header *rmh) { return 0; }
 static inline void sev_es_nmi_complete(void) { }
 static inline int sev_es_efi_map_ghcbs(pgd_t *pgd) { return 0; }
+static inline int pvalidate(unsigned long vaddr, bool rmp_psize, bool validate) { return 0; }
 #endif
 
 #endif

@@ -275,15 +275,31 @@ static int set_clr_page_flags(struct x86_mapping_info *info,
 	 * Changing encryption attributes of a page requires to flush it from
 	 * the caches.
 	 */
-	if ((set | clr) & _PAGE_ENC)
+	if ((set | clr) & _PAGE_ENC) {
 		clflush_page(address);
 
+		/*
+		 * If the encryption attribute is being cleared, then change
+		 * the page state to shared in the RMP table.
+		 */
+		if (clr)
+			snp_set_page_shared(pte_pfn(*ptep) << PAGE_SHIFT);
+	}
+
 	/* Update PTE */
 	pte = *ptep;
 	pte = pte_set_flags(pte, set);
 	pte = pte_clear_flags(pte, clr);
 	set_pte(ptep, pte);
 
+	/*
+	 * If the encryption attribute is being set, then change the page state to
+	 * private in the RMP entry. The page state must be done after the PTE
+	 * is updated.
+	 */
+	if (set & _PAGE_ENC)
+		snp_set_page_private(pte_pfn(*ptep) << PAGE_SHIFT);
+
 	/* Flush TLB after changing encryption attribute */
 	write_cr3(top_level_pgt);
 

@@ -121,12 +121,18 @@ void set_sev_encryption_mask(void);
 #ifdef CONFIG_AMD_MEM_ENCRYPT
 void sev_es_shutdown_ghcb(void);
 extern bool sev_es_check_ghcb_fault(unsigned long address);
+void snp_set_page_private(unsigned long paddr);
+void snp_set_page_shared(unsigned long paddr);
+
 #else
 static inline void sev_es_shutdown_ghcb(void) { }
 static inline bool sev_es_check_ghcb_fault(unsigned long address)
 {
 	return false;
 }
+static inline void snp_set_page_private(unsigned long paddr) { }
+static inline void snp_set_page_shared(unsigned long paddr) { }
+
 #endif
 
 /* acpi.c */

@@ -154,6 +154,47 @@ static bool is_vmpl0(void)
 	return true;
 }
 
+static void __page_state_change(unsigned long paddr, enum psc_op op)
+{
+	u64 val;
+
+	if (!sev_snp_enabled())
+		return;
+
+	/*
+	 * If private -> shared then invalidate the page before requesting the
+	 * state change in the RMP table.
+	 */
+	if (op == SNP_PAGE_STATE_SHARED && pvalidate(paddr, RMP_PG_SIZE_4K, 0))
+		sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PVALIDATE);
+
+	/* Issue VMGEXIT to change the page state in RMP table. */
+	sev_es_wr_ghcb_msr(GHCB_MSR_PSC_REQ_GFN(paddr >> PAGE_SHIFT, op));
+	VMGEXIT();
+
+	/* Read the response of the VMGEXIT. */
+	val = sev_es_rd_ghcb_msr();
+	if ((GHCB_RESP_CODE(val) != GHCB_MSR_PSC_RESP) || GHCB_MSR_PSC_RESP_VAL(val))
+		sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC);
+
+	/*
+	 * Now that page is added in the RMP table, validate it so that it is
+	 * consistent with the RMP entry.
+	 */
+	if (op == SNP_PAGE_STATE_PRIVATE && pvalidate(paddr, RMP_PG_SIZE_4K, 1))
+		sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PVALIDATE);
+}
+
+void snp_set_page_private(unsigned long paddr)
+{
+	__page_state_change(paddr, SNP_PAGE_STATE_PRIVATE);
+}
+
+void snp_set_page_shared(unsigned long paddr)
+{
+	__page_state_change(paddr, SNP_PAGE_STATE_SHARED);
+}
+
 static bool do_early_sev_setup(void)
 {
 	if (!sev_es_negotiate_protocol())

@@ -57,6 +57,32 @@
 #define GHCB_MSR_AP_RESET_HOLD_REQ	0x006
 #define GHCB_MSR_AP_RESET_HOLD_RESP	0x007
 
+/*
+ * SNP Page State Change Operation
+ *
+ * GHCBData[55:52] - Page operation:
+ *   0x0001 – Page assignment, Private
+ *   0x0002 – Page assignment, Shared
+ */
+enum psc_op {
+	SNP_PAGE_STATE_PRIVATE = 1,
+	SNP_PAGE_STATE_SHARED,
+};
+
+#define GHCB_MSR_PSC_REQ		0x014
+#define GHCB_MSR_PSC_REQ_GFN(gfn, op)			\
+	/* GHCBData[55:52] */				\
+	(((u64)((op) & 0xf) << 52) |			\
+	/* GHCBData[51:12] */				\
+	((u64)((gfn) & GENMASK_ULL(39, 0)) << 12) |	\
+	/* GHCBData[11:0] */				\
+	GHCB_MSR_PSC_REQ)
+
+#define GHCB_MSR_PSC_RESP		0x015
+#define GHCB_MSR_PSC_RESP_VAL(val)			\
+	/* GHCBData[63:32] */				\
+	(((u64)(val) & GENMASK_ULL(63, 32)) >> 32)
+
 /* GHCB Hypervisor Feature Request/Response */
 #define GHCB_MSR_HV_FT_REQ		0x080
 #define GHCB_MSR_HV_FT_RESP		0x081

@@ -223,6 +223,10 @@ static bool do_early_sev_setup(void)
 	/* Initialize lookup tables for the instruction decoder */
 	inat_init_tables();
 
+	/* SEV-SNP guest requires the GHCB GPA must be registered */
+	if (sev_snp_enabled())
+		snp_register_ghcb_early(__pa(&boot_ghcb_page));
+
 	return true;
 }
 

@@ -57,6 +57,19 @@
 #define GHCB_MSR_AP_RESET_HOLD_REQ	0x006
 #define GHCB_MSR_AP_RESET_HOLD_RESP	0x007
 
+/* GHCB GPA Register */
+#define GHCB_MSR_REG_GPA_REQ		0x012
+#define GHCB_MSR_REG_GPA_REQ_VAL(v)			\
+	/* GHCBData[63:12] */				\
+	(((u64)((v) & GENMASK_ULL(51, 0)) << 12) |	\
+	/* GHCBData[11:0] */				\
+	GHCB_MSR_REG_GPA_REQ)
+
+#define GHCB_MSR_REG_GPA_RESP		0x013
+#define GHCB_MSR_REG_GPA_RESP_VAL(v)			\
+	/* GHCBData[63:12] */				\
+	(((u64)(v) & GENMASK_ULL(63, 12)) >> 12)
+
 /*
  * SNP Page State Change Operation
  *

@@ -75,6 +75,22 @@ static bool get_hv_features(void)
 	return true;
 }
 
+static void snp_register_ghcb_early(unsigned long paddr)
+{
+	unsigned long pfn = paddr >> PAGE_SHIFT;
+	u64 val;
+
+	sev_es_wr_ghcb_msr(GHCB_MSR_REG_GPA_REQ_VAL(pfn));
+	VMGEXIT();
+
+	val = sev_es_rd_ghcb_msr();
+
+	/* If the response GPA is not ours then abort the guest */
+	if ((GHCB_RESP_CODE(val) != GHCB_MSR_REG_GPA_RESP) ||
+	    (GHCB_MSR_REG_GPA_RESP_VAL(val) != pfn))
+		sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_REGISTER);
+}
+
 static bool sev_es_negotiate_protocol(void)
 {
 	u64 val;

@@ -124,6 +124,36 @@ static inline bool sev_snp_enabled(void)
 	return sev_status & MSR_AMD64_SEV_SNP_ENABLED;
 }
 
+static bool is_vmpl0(void)
+{
+	u64 attrs, va;
+	int err;
+
+	/*
+	 * There is no straightforward way to query the current VMPL level. The
+	 * simplest method is to use the RMPADJUST instruction to change a page
+	 * permission to a VMPL level-1, and if the guest kernel is launched at
+	 * a level <= 1, then RMPADJUST instruction will return an error.
+	 */
+	attrs = 1;
+
+	/*
+	 * Any page aligned virtual address is sufficent to test the VMPL level.
+	 * The boot_ghcb_page is page aligned memory, so lets use for the test.
+	 */
+	va = (u64)&boot_ghcb_page;
+
+	/* Instruction mnemonic supported in binutils versions v2.36 and later */
+	asm volatile (".byte 0xf3,0x0f,0x01,0xfe\n\t"
+		      : "=a" (err)
+		      : "a" (va), "c" (RMP_PG_SIZE_4K), "d" (attrs)
+		      : "memory", "cc");
+	if (err)
+		return false;
+
+	return true;
+}
+
 static bool do_early_sev_setup(void)
 {
 	if (!sev_es_negotiate_protocol())

@@ -131,10 +161,15 @@ static bool do_early_sev_setup(void)
 
 	/*
 	 * If SEV-SNP is enabled, then check if the hypervisor supports the SEV-SNP
-	 * features.
+	 * features and is launched at VMPL-0 level.
 	 */
-	if (sev_snp_enabled() && !(sev_hv_features & GHCB_HV_FT_SNP))
-		sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED);
+	if (sev_snp_enabled()) {
+		if (!(sev_hv_features & GHCB_HV_FT_SNP))
+			sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED);
+
+		if (!is_vmpl0())
+			sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_NOT_VMPL0);
+	}
 
 	if (set_page_decrypted((unsigned long)&boot_ghcb_page))
 		return false;

@@ -89,6 +89,7 @@
 #define GHCB_TERM_REGISTER		0	/* GHCB GPA registration failure */
 #define GHCB_TERM_PSC			1	/* Page State Change failure */
 #define GHCB_TERM_PVALIDATE		2	/* Pvalidate failure */
+#define GHCB_TERM_NOT_VMPL0		3	/* SNP guest is not running at VMPL-0 */
 
 #define GHCB_RESP_CODE(v)		((v) & GHCB_MSR_INFO_MASK)
 

@@ -62,6 +62,9 @@ extern bool handle_vc_boot_ghcb(struct pt_regs *regs);
 /* Software defined (when rFlags.CF = 1) */
 #define PVALIDATE_FAIL_NOUPDATE		255
 
+/* RMP page size */
+#define RMP_PG_SIZE_4K			0
+
 #ifdef CONFIG_AMD_MEM_ENCRYPT
 extern struct static_key_false sev_es_enable_key;
 extern void __sev_es_ist_enter(struct pt_regs *regs);

@@ -143,7 +143,14 @@ static unsigned long sme_postprocess_startup(struct boot_params *bp, pmdval_t *p
 	if (sme_get_me_mask()) {
 		vaddr = (unsigned long)__start_bss_decrypted;
 		vaddr_end = (unsigned long)__end_bss_decrypted;
+
 		for (; vaddr < vaddr_end; vaddr += PMD_SIZE) {
+			/*
+			 * When SEV-SNP is active then transition the page to shared in the RMP
+			 * table so that it is consistent with the page table attribute change.
+			 */
+			early_snp_set_memory_shared(__pa(vaddr), __pa(vaddr), PTRS_PER_PMD);
+
 			i = pmd_index(vaddr);
 			pmd[i] -= sme_get_me_mask();
 		}

@@ -238,7 +238,8 @@ struct vmcb_save_area {
 	struct vmcb_seg ldtr;
 	struct vmcb_seg idtr;
 	struct vmcb_seg tr;
-	u8 reserved_1[43];
+	u8 reserved_1[42];
+	u8 vmpl;
 	u8 cpl;
 	u8 reserved_2[4];
 	u64 efer;

@@ -303,7 +304,8 @@ struct vmcb_save_area {
 	u64 sw_exit_info_1;
 	u64 sw_exit_info_2;
 	u64 sw_scratch;
-	u8 reserved_11[56];
+	u64 sev_features;
+	u8 reserved_11[48];
 	u64 xcr0;
 	u8 valid_bitmap[16];
 	u64 x87_state_gpa;

@@ -3210,8 +3210,8 @@ static void dump_vmcb(struct kvm_vcpu *vcpu)
 	       "tr:",
 	       save01->tr.selector, save01->tr.attrib,
 	       save01->tr.limit, save01->tr.base);
-	pr_err("cpl:            %d                efer:         %016llx\n",
-		save->cpl, save->efer);
+	pr_err("vmpl: %d   cpl:  %d               efer:          %016llx\n",
+	       save->vmpl, save->cpl, save->efer);
 	pr_err("%-15s %016llx %-13s %016llx\n",
 	       "cr0:", save->cr0, "cr2:", save->cr2);
 	pr_err("%-15s %016llx %-13s %016llx\n",

@@ -21,6 +21,7 @@
 #include <asm/sections.h>
 #include <asm/io.h>
 #include <asm/setup_arch.h>
+#include <asm/sev.h>
 
 static struct resource system_rom_resource = {
 	.name	= "System ROM",

@@ -197,11 +198,21 @@ static int __init romchecksum(const unsigned char *rom, unsigned long length)
 
 void __init probe_roms(void)
 {
-	const unsigned char *rom;
 	unsigned long start, length, upper;
+	const unsigned char *rom;
 	unsigned char c;
 	int i;
 
+	/*
+	 * The ROM memory is not part of the E820 system RAM and is not pre-validated
+	 * by the BIOS. The kernel page table maps the ROM region as encrypted memory,
+	 * the SEV-SNP requires the encrypted memory must be validated before the
+	 * access. Validate the ROM before accessing it.
+	 */
+	snp_prep_memory(video_rom_resource.start,
+			((system_rom_resource.end + 1) - video_rom_resource.start),
+			SNP_PAGE_STATE_PRIVATE);
+
 	/* video rom */
 	upper = adapter_rom_resources[0].start;
 	for (start = video_rom_resource.start; start < upper; start += 2048) {

@@ -105,6 +105,28 @@ enum psc_op {
 
 #define GHCB_HV_FT_SNP			BIT_ULL(0)
 
+/* SNP Page State Change NAE event */
+#define VMGEXIT_PSC_MAX_ENTRY		253
+
+struct psc_hdr {
+	u16 cur_entry;
+	u16 end_entry;
+	u32 reserved;
+} __packed;
+
+struct psc_entry {
+	u64	cur_page	: 12,
+		gfn		: 40,
+		operation	: 4,
+		pagesize	: 1,
+		reserved	: 7;
+} __packed;
+
+struct snp_psc_desc {
+	struct psc_hdr hdr;
+	struct psc_entry entries[VMGEXIT_PSC_MAX_ENTRY];
+} __packed;
+
 #define GHCB_MSR_TERM_REQ		0x100
 #define GHCB_MSR_TERM_REASON_SET_POS	12
 #define GHCB_MSR_TERM_REASON_SET_MASK	0xf

@@ -109,6 +109,8 @@ void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long padd
 void __init early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr,
 					unsigned int npages);
 void __init snp_prep_memory(unsigned long paddr, unsigned int sz, enum psc_op op);
+void snp_set_memory_shared(unsigned long vaddr, unsigned int npages);
+void snp_set_memory_private(unsigned long vaddr, unsigned int npages);
 #else
 static inline void sev_es_ist_enter(struct pt_regs *regs) { }
 static inline void sev_es_ist_exit(void) { }

@@ -121,6 +123,8 @@ early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr, unsigned
 static inline void __init
 early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr, unsigned int npages) { }
 static inline void __init snp_prep_memory(unsigned long paddr, unsigned int sz, enum psc_op op) { }
+static inline void snp_set_memory_shared(unsigned long vaddr, unsigned int npages) { }
+static inline void snp_set_memory_private(unsigned long vaddr, unsigned int npages) { }
 #endif
 
 #endif

@@ -108,6 +108,7 @@
 #define SVM_VMGEXIT_AP_JUMP_TABLE		0x80000005
 #define SVM_VMGEXIT_SET_AP_JUMP_TABLE		0
 #define SVM_VMGEXIT_GET_AP_JUMP_TABLE		1
+#define SVM_VMGEXIT_PSC				0x80000010
 #define SVM_VMGEXIT_HV_FEATURES			0x8000fffd
 #define SVM_VMGEXIT_UNSUPPORTED_EVENT		0x8000ffff