Merge tag 'x86_sev_for_v5.19_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull AMD SEV-SNP support from Borislav Petkov:
 "The third AMD confidential computing feature called Secure Nested
  Paging.

  Add to confidential guests the necessary memory integrity protection
  against malicious hypervisor-based attacks like data replay, memory
  remapping and others, thus achieving a stronger isolation from the
  hypervisor.

  At the core of the functionality is a new structure called a reverse
  map table (RMP) with which the guest has a say in which pages get
  assigned to it and gets notified when a page which it owns, gets
  accessed/modified under the covers so that the guest can take an
  appropriate action.

  In addition, add support for the whole machinery needed to launch a
  SNP guest, details of which is properly explained in each patch.

  And last but not least, the series refactors and improves parts of the
  previous SEV support so that the new code is accomodated properly and
  not just bolted on"

* tag 'x86_sev_for_v5.19_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (60 commits)
  x86/entry: Fixup objtool/ibt validation
  x86/sev: Mark the code returning to user space as syscall gap
  x86/sev: Annotate stack change in the #VC handler
  x86/sev: Remove duplicated assignment to variable info
  x86/sev: Fix address space sparse warning
  x86/sev: Get the AP jump table address from secrets page
  x86/sev: Add missing __init annotations to SEV init routines
  virt: sevguest: Rename the sevguest dir and files to sev-guest
  virt: sevguest: Change driver name to reflect generic SEV support
  x86/boot: Put globals that are accessed early into the .data section
  x86/boot: Add an efi.h header for the decompressor
  virt: sevguest: Fix bool function returning negative value
  virt: sevguest: Fix return value check in alloc_shared_pages()
  x86/sev-es: Replace open-coded hlt-loop with sev_es_terminate()
  virt: sevguest: Add documentation for SEV-SNP CPUID Enforcement
  virt: sevguest: Add support to get extended report
  virt: sevguest: Add support to derive key
  virt: Add SEV-SNP guest driver
  x86/sev: Register SEV-SNP guest request platform device
  x86/sev: Provide support for SNP guest request NAEs
  ...

8 files changed, 1404 insertions, 73 deletions

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index c41ef42adbe8..1a2dc328cb5e 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -46,8 +46,6 @@ endif
 # non-deterministic coverage.
 KCOV_INSTRUMENT		:= n
 
-CFLAGS_head$(BITS).o	+= -fno-stack-protector
-
 CFLAGS_irq.o := -I $(srctree)/$(src)/../include/asm/trace
 
 obj-y			:= process_$(BITS).o signal.o
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index e342ae4db3c4..f0baf1b7522e 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -60,6 +60,7 @@
 #include <asm/uv/uv.h>
 #include <asm/sigframe.h>
 #include <asm/traps.h>
+#include <asm/sev.h>
 
 #include "cpu.h"
 
@@ -2126,6 +2127,9 @@ void cpu_init_exception_handling(void)
 
 	load_TR_desc();
 
+	/* GHCB needs to be setup to handle #VC. */
+	setup_ghcb();
+
 	/* Finally load the IDT */
 	load_current_idt();
 }
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 4f5ecbbaae77..c185f4831498 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -143,7 +143,20 @@ static unsigned long __head sme_postprocess_startup(struct boot_params *bp, pmdv
 	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) {
+			/*
+			 * On SNP, transition the page to shared in the RMP table so that
+			 * it is consistent with the page table attribute change.
+			 *
+			 * __start_bss_decrypted has a virtual address in the high range
+			 * mapping (kernel .text). PVALIDATE, by way of
+			 * early_snp_set_memory_shared(), requires a valid virtual
+			 * address but the kernel is currently running off of the identity
+			 * mapping so use __pa() to get a *currently* valid virtual address.
+			 */
+			early_snp_set_memory_shared(__pa(vaddr), __pa(vaddr), PTRS_PER_PMD);
+
 			i = pmd_index(vaddr);
 			pmd[i] -= sme_get_me_mask();
 		}
@@ -192,9 +205,6 @@ unsigned long __head __startup_64(unsigned long physaddr,
 	if (load_delta & ~PMD_PAGE_MASK)
 		for (;;);
 
-	/* Activate Secure Memory Encryption (SME) if supported and enabled */
-	sme_enable(bp);
-
 	/* Include the SME encryption mask in the fixup value */
 	load_delta += sme_get_me_mask();
 
@@ -308,15 +318,6 @@ unsigned long __head __startup_64(unsigned long physaddr,
 	return sme_postprocess_startup(bp, pmd);
 }
 
-unsigned long __startup_secondary_64(void)
-{
-	/*
-	 * 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();
-}
-
 /* Wipe all early page tables except for the kernel symbol map */
 static void __init reset_early_page_tables(void)
 {
@@ -600,8 +601,10 @@ static void startup_64_load_idt(unsigned long physbase)
 void early_setup_idt(void)
 {
 	/* VMM Communication Exception */
-	if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT))
+	if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT)) {
+		setup_ghcb();
 		set_bringup_idt_handler(bringup_idt_table, X86_TRAP_VC, vc_boot_ghcb);
+	}
 
 	bringup_idt_descr.address = (unsigned long)bringup_idt_table;
 	native_load_idt(&bringup_idt_descr);
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index b8e3019547a5..7bac9a4bdf7c 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -65,10 +65,39 @@ SYM_CODE_START_NOALIGN(startup_64)
 	leaq	(__end_init_task - FRAME_SIZE)(%rip), %rsp
 
 	leaq	_text(%rip), %rdi
+
+	/*
+	 * initial_gs points to initial fixed_percpu_data struct with storage for
+	 * the stack protector canary. Global pointer fixups are needed at this
+	 * stage, so apply them as is done in fixup_pointer(), and initialize %gs
+	 * such that the canary can be accessed at %gs:40 for subsequent C calls.
+	 */
+	movl	$MSR_GS_BASE, %ecx
+	movq	initial_gs(%rip), %rax
+	movq	$_text, %rdx
+	subq	%rdx, %rax
+	addq	%rdi, %rax
+	movq	%rax, %rdx
+	shrq	$32,  %rdx
+	wrmsr
+
 	pushq	%rsi
 	call	startup_64_setup_env
 	popq	%rsi
 
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+	/*
+	 * Activate SEV/SME memory encryption if supported/enabled. This needs to
+	 * be done now, since this also includes setup of the SEV-SNP CPUID table,
+	 * which needs to be done before any CPUID instructions are executed in
+	 * subsequent code.
+	 */
+	movq	%rsi, %rdi
+	pushq	%rsi
+	call	sme_enable
+	popq	%rsi
+#endif
+
 	/* Now switch to __KERNEL_CS so IRET works reliably */
 	pushq	$__KERNEL_CS
 	leaq	.Lon_kernel_cs(%rip), %rax
@@ -134,9 +163,11 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
 	 * Retrieve the modifier (SME encryption mask if SME is active) to be
 	 * added to the initial pgdir entry that will be programmed into CR3.
 	 */
-	pushq	%rsi
-	call	__startup_secondary_64
-	popq	%rsi
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+	movq	sme_me_mask, %rax
+#else
+	xorq	%rax, %rax
+#endif
 
 	/* Form the CR3 value being sure to include the CR3 modifier */
 	addq	$(init_top_pgt - __START_KERNEL_map), %rax
diff --git a/arch/x86/kernel/probe_roms.c b/arch/x86/kernel/probe_roms.c
index 36e84d904260..319fef37d9dc 100644
--- a/arch/x86/kernel/probe_roms.c
+++ b/arch/x86/kernel/probe_roms.c
@@ -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 range is not part of the e820 table and is therefore not
+	 * pre-validated by BIOS. The kernel page table maps the ROM region as encrypted
+	 * memory, and SNP requires encrypted memory to be validated before access.
+	 * Do that here.
+	 */
+	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) {
diff --git a/arch/x86/kernel/sev-shared.c b/arch/x86/kernel/sev-shared.c
index ce987688bbc0..b478edf43bec 100644
--- a/arch/x86/kernel/sev-shared.c
+++ b/arch/x86/kernel/sev-shared.c
@@ -14,6 +14,68 @@
 #define has_cpuflag(f)	boot_cpu_has(f)
 #endif
 
+/* I/O parameters for CPUID-related helpers */
+struct cpuid_leaf {
+	u32 fn;
+	u32 subfn;
+	u32 eax;
+	u32 ebx;
+	u32 ecx;
+	u32 edx;
+};
+
+/*
+ * Individual entries of the SNP CPUID table, as defined by the SNP
+ * Firmware ABI, Revision 0.9, Section 7.1, Table 14.
+ */
+struct snp_cpuid_fn {
+	u32 eax_in;
+	u32 ecx_in;
+	u64 xcr0_in;
+	u64 xss_in;
+	u32 eax;
+	u32 ebx;
+	u32 ecx;
+	u32 edx;
+	u64 __reserved;
+} __packed;
+
+/*
+ * SNP CPUID table, as defined by the SNP Firmware ABI, Revision 0.9,
+ * Section 8.14.2.6. Also noted there is the SNP firmware-enforced limit
+ * of 64 entries per CPUID table.
+ */
+#define SNP_CPUID_COUNT_MAX 64
+
+struct snp_cpuid_table {
+	u32 count;
+	u32 __reserved1;
+	u64 __reserved2;
+	struct snp_cpuid_fn fn[SNP_CPUID_COUNT_MAX];
+} __packed;
+
+/*
+ * 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 ghcb_version __ro_after_init;
+
+/* Copy of the SNP firmware's CPUID page. */
+static struct snp_cpuid_table cpuid_table_copy __ro_after_init;
+
+/*
+ * These will be initialized based on CPUID table so that non-present
+ * all-zero leaves (for sparse tables) can be differentiated from
+ * invalid/out-of-range leaves. This is needed since all-zero leaves
+ * still need to be post-processed.
+ */
+static u32 cpuid_std_range_max __ro_after_init;
+static u32 cpuid_hyp_range_max __ro_after_init;
+static u32 cpuid_ext_range_max __ro_after_init;
+
 static bool __init sev_es_check_cpu_features(void)
 {
 	if (!has_cpuflag(X86_FEATURE_RDRAND)) {
@@ -24,15 +86,12 @@ 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);
@@ -42,6 +101,42 @@ static void __noreturn sev_es_terminate(unsigned int reason)
 		asm volatile("hlt\n" : : : "memory");
 }
 
+/*
+ * The hypervisor features are available from GHCB version 2 onward.
+ */
+static u64 get_hv_features(void)
+{
+	u64 val;
+
+	if (ghcb_version < 2)
+		return 0;
+
+	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 0;
+
+	return GHCB_MSR_HV_FT_RESP_VAL(val);
+}
+
+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;
@@ -54,10 +149,12 @@ 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;
 }
 
@@ -104,10 +201,7 @@ static enum es_result verify_exception_info(struct ghcb *ghcb, struct es_em_ctxt
 
 	if (ret == 1) {
 		u64 info = ghcb->save.sw_exit_info_2;
-		unsigned long v;
-
-		info = ghcb->save.sw_exit_info_2;
-		v = info & SVM_EVTINJ_VEC_MASK;
+		unsigned long v = info & SVM_EVTINJ_VEC_MASK;
 
 		/* Check if exception information from hypervisor is sane. */
 		if ((info & SVM_EVTINJ_VALID) &&
@@ -130,7 +224,7 @@ enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb, bool set_ghcb_msr,
 				   u64 exit_info_1, u64 exit_info_2)
 {
 	/* 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);
@@ -150,6 +244,290 @@ enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb, bool set_ghcb_msr,
 	return verify_exception_info(ghcb, ctxt);
 }
 
+static int __sev_cpuid_hv(u32 fn, int reg_idx, u32 *reg)
+{
+	u64 val;
+
+	sev_es_wr_ghcb_msr(GHCB_CPUID_REQ(fn, reg_idx));
+	VMGEXIT();
+	val = sev_es_rd_ghcb_msr();
+	if (GHCB_RESP_CODE(val) != GHCB_MSR_CPUID_RESP)
+		return -EIO;
+
+	*reg = (val >> 32);
+
+	return 0;
+}
+
+static int sev_cpuid_hv(struct cpuid_leaf *leaf)
+{
+	int ret;
+
+	/*
+	 * MSR protocol does not support fetching non-zero subfunctions, but is
+	 * sufficient to handle current early-boot cases. Should that change,
+	 * make sure to report an error rather than ignoring the index and
+	 * grabbing random values. If this issue arises in the future, handling
+	 * can be added here to use GHCB-page protocol for cases that occur late
+	 * enough in boot that GHCB page is available.
+	 */
+	if (cpuid_function_is_indexed(leaf->fn) && leaf->subfn)
+		return -EINVAL;
+
+	ret =         __sev_cpuid_hv(leaf->fn, GHCB_CPUID_REQ_EAX, &leaf->eax);
+	ret = ret ? : __sev_cpuid_hv(leaf->fn, GHCB_CPUID_REQ_EBX, &leaf->ebx);
+	ret = ret ? : __sev_cpuid_hv(leaf->fn, GHCB_CPUID_REQ_ECX, &leaf->ecx);
+	ret = ret ? : __sev_cpuid_hv(leaf->fn, GHCB_CPUID_REQ_EDX, &leaf->edx);
+
+	return ret;
+}
+
+/*
+ * This may be called early while still running on the initial identity
+ * mapping. Use RIP-relative addressing to obtain the correct address
+ * while running with the initial identity mapping as well as the
+ * switch-over to kernel virtual addresses later.
+ */
+static const struct snp_cpuid_table *snp_cpuid_get_table(void)
+{
+	void *ptr;
+
+	asm ("lea cpuid_table_copy(%%rip), %0"
+	     : "=r" (ptr)
+	     : "p" (&cpuid_table_copy));
+
+	return ptr;
+}
+
+/*
+ * The SNP Firmware ABI, Revision 0.9, Section 7.1, details the use of
+ * XCR0_IN and XSS_IN to encode multiple versions of 0xD subfunctions 0
+ * and 1 based on the corresponding features enabled by a particular
+ * combination of XCR0 and XSS registers so that a guest can look up the
+ * version corresponding to the features currently enabled in its XCR0/XSS
+ * registers. The only values that differ between these versions/table
+ * entries is the enabled XSAVE area size advertised via EBX.
+ *
+ * While hypervisors may choose to make use of this support, it is more
+ * robust/secure for a guest to simply find the entry corresponding to the
+ * base/legacy XSAVE area size (XCR0=1 or XCR0=3), and then calculate the
+ * XSAVE area size using subfunctions 2 through 64, as documented in APM
+ * Volume 3, Rev 3.31, Appendix E.3.8, which is what is done here.
+ *
+ * Since base/legacy XSAVE area size is documented as 0x240, use that value
+ * directly rather than relying on the base size in the CPUID table.
+ *
+ * Return: XSAVE area size on success, 0 otherwise.
+ */
+static u32 snp_cpuid_calc_xsave_size(u64 xfeatures_en, bool compacted)
+{
+	const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table();
+	u64 xfeatures_found = 0;
+	u32 xsave_size = 0x240;
+	int i;
+
+	for (i = 0; i < cpuid_table->count; i++) {
+		const struct snp_cpuid_fn *e = &cpuid_table->fn[i];
+
+		if (!(e->eax_in == 0xD && e->ecx_in > 1 && e->ecx_in < 64))
+			continue;
+		if (!(xfeatures_en & (BIT_ULL(e->ecx_in))))
+			continue;
+		if (xfeatures_found & (BIT_ULL(e->ecx_in)))
+			continue;
+
+		xfeatures_found |= (BIT_ULL(e->ecx_in));
+
+		if (compacted)
+			xsave_size += e->eax;
+		else
+			xsave_size = max(xsave_size, e->eax + e->ebx);
+	}
+
+	/*
+	 * Either the guest set unsupported XCR0/XSS bits, or the corresponding
+	 * entries in the CPUID table were not present. This is not a valid
+	 * state to be in.
+	 */
+	if (xfeatures_found != (xfeatures_en & GENMASK_ULL(63, 2)))
+		return 0;
+
+	return xsave_size;
+}
+
+static bool
+snp_cpuid_get_validated_func(struct cpuid_leaf *leaf)
+{
+	const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table();
+	int i;
+
+	for (i = 0; i < cpuid_table->count; i++) {
+		const struct snp_cpuid_fn *e = &cpuid_table->fn[i];
+
+		if (e->eax_in != leaf->fn)
+			continue;
+
+		if (cpuid_function_is_indexed(leaf->fn) && e->ecx_in != leaf->subfn)
+			continue;
+
+		/*
+		 * For 0xD subfunctions 0 and 1, only use the entry corresponding
+		 * to the base/legacy XSAVE area size (XCR0=1 or XCR0=3, XSS=0).
+		 * See the comments above snp_cpuid_calc_xsave_size() for more
+		 * details.
+		 */
+		if (e->eax_in == 0xD && (e->ecx_in == 0 || e->ecx_in == 1))
+			if (!(e->xcr0_in == 1 || e->xcr0_in == 3) || e->xss_in)
+				continue;
+
+		leaf->eax = e->eax;
+		leaf->ebx = e->ebx;
+		leaf->ecx = e->ecx;
+		leaf->edx = e->edx;
+
+		return true;
+	}
+
+	return false;
+}
+
+static void snp_cpuid_hv(struct cpuid_leaf *leaf)
+{
+	if (sev_cpuid_hv(leaf))
+		sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_CPUID_HV);
+}
+
+static int snp_cpuid_postprocess(struct cpuid_leaf *leaf)
+{
+	struct cpuid_leaf leaf_hv = *leaf;
+
+	switch (leaf->fn) {
+	case 0x1:
+		snp_cpuid_hv(&leaf_hv);
+
+		/* initial APIC ID */
+		leaf->ebx = (leaf_hv.ebx & GENMASK(31, 24)) | (leaf->ebx & GENMASK(23, 0));
+		/* APIC enabled bit */
+		leaf->edx = (leaf_hv.edx & BIT(9)) | (leaf->edx & ~BIT(9));
+
+		/* OSXSAVE enabled bit */
+		if (native_read_cr4() & X86_CR4_OSXSAVE)
+			leaf->ecx |= BIT(27);
+		break;
+	case 0x7:
+		/* OSPKE enabled bit */
+		leaf->ecx &= ~BIT(4);
+		if (native_read_cr4() & X86_CR4_PKE)
+			leaf->ecx |= BIT(4);
+		break;
+	case 0xB:
+		leaf_hv.subfn = 0;
+		snp_cpuid_hv(&leaf_hv);
+
+		/* extended APIC ID */
+		leaf->edx = leaf_hv.edx;
+		break;
+	case 0xD: {
+		bool compacted = false;
+		u64 xcr0 = 1, xss = 0;
+		u32 xsave_size;
+
+		if (leaf->subfn != 0 && leaf->subfn != 1)
+			return 0;
+
+		if (native_read_cr4() & X86_CR4_OSXSAVE)
+			xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
+		if (leaf->subfn == 1) {
+			/* Get XSS value if XSAVES is enabled. */
+			if (leaf->eax & BIT(3)) {
+				unsigned long lo, hi;
+
+				asm volatile("rdmsr" : "=a" (lo), "=d" (hi)
+						     : "c" (MSR_IA32_XSS));
+				xss = (hi << 32) | lo;
+			}
+
+			/*
+			 * The PPR and APM aren't clear on what size should be
+			 * encoded in 0xD:0x1:EBX when compaction is not enabled
+			 * by either XSAVEC (feature bit 1) or XSAVES (feature
+			 * bit 3) since SNP-capable hardware has these feature
+			 * bits fixed as 1. KVM sets it to 0 in this case, but
+			 * to avoid this becoming an issue it's safer to simply
+			 * treat this as unsupported for SNP guests.
+			 */
+			if (!(leaf->eax & (BIT(1) | BIT(3))))
+				return -EINVAL;
+
+			compacted = true;
+		}
+
+		xsave_size = snp_cpuid_calc_xsave_size(xcr0 | xss, compacted);
+		if (!xsave_size)
+			return -EINVAL;
+
+		leaf->ebx = xsave_size;
+		}
+		break;
+	case 0x8000001E:
+		snp_cpuid_hv(&leaf_hv);
+
+		/* extended APIC ID */
+		leaf->eax = leaf_hv.eax;
+		/* compute ID */
+		leaf->ebx = (leaf->ebx & GENMASK(31, 8)) | (leaf_hv.ebx & GENMASK(7, 0));
+		/* node ID */
+		leaf->ecx = (leaf->ecx & GENMASK(31, 8)) | (leaf_hv.ecx & GENMASK(7, 0));
+		break;
+	default:
+		/* No fix-ups needed, use values as-is. */
+		break;
+	}
+
+	return 0;
+}
+
+/*
+ * Returns -EOPNOTSUPP if feature not enabled. Any other non-zero return value
+ * should be treated as fatal by caller.
+ */
+static int snp_cpuid(struct cpuid_leaf *leaf)
+{
+	const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table();
+
+	if (!cpuid_table->count)
+		return -EOPNOTSUPP;
+
+	if (!snp_cpuid_get_validated_func(leaf)) {
+		/*
+		 * Some hypervisors will avoid keeping track of CPUID entries
+		 * where all values are zero, since they can be handled the
+		 * same as out-of-range values (all-zero). This is useful here
+		 * as well as it allows virtually all guest configurations to
+		 * work using a single SNP CPUID table.
+		 *
+		 * To allow for this, there is a need to distinguish between
+		 * out-of-range entries and in-range zero entries, since the
+		 * CPUID table entries are only a template that may need to be
+		 * augmented with additional values for things like
+		 * CPU-specific information during post-processing. So if it's
+		 * not in the table, set the values to zero. Then, if they are
+		 * within a valid CPUID range, proceed with post-processing
+		 * using zeros as the initial values. Otherwise, skip
+		 * post-processing and just return zeros immediately.
+		 */
+		leaf->eax = leaf->ebx = leaf->ecx = leaf->edx = 0;
+
+		/* Skip post-processing for out-of-range zero leafs. */
+		if (!(leaf->fn <= cpuid_std_range_max ||
+		      (leaf->fn >= 0x40000000 && leaf->fn <= cpuid_hyp_range_max) ||
+		      (leaf->fn >= 0x80000000 && leaf->fn <= cpuid_ext_range_max)))
+			return 0;
+	}
+
+	return snp_cpuid_postprocess(leaf);
+}
+
 /*
  * Boot VC Handler - This is the first VC handler during boot, there is no GHCB
  * page yet, so it only supports the MSR based communication with the
@@ -157,40 +535,33 @@ enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb, bool set_ghcb_msr,
  */
 void __init do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code)
 {
+	unsigned int subfn = lower_bits(regs->cx, 32);
 	unsigned int fn = lower_bits(regs->ax, 32);
-	unsigned long val;
+	struct cpuid_leaf leaf;
+	int ret;
 
 	/* Only CPUID is supported via MSR protocol */
 	if (exit_code != SVM_EXIT_CPUID)
 		goto fail;
 
-	sev_es_wr_ghcb_msr(GHCB_CPUID_REQ(fn, GHCB_CPUID_REQ_EAX));
-	VMGEXIT();
-	val = sev_es_rd_ghcb_msr();
-	if (GHCB_RESP_CODE(val) != GHCB_MSR_CPUID_RESP)
-		goto fail;
-	regs->ax = val >> 32;
+	leaf.fn = fn;
+	leaf.subfn = subfn;
 
-	sev_es_wr_ghcb_msr(GHCB_CPUID_REQ(fn, GHCB_CPUID_REQ_EBX));
-	VMGEXIT();
-	val = sev_es_rd_ghcb_msr();
-	if (GHCB_RESP_CODE(val) != GHCB_MSR_CPUID_RESP)
-		goto fail;
-	regs->bx = val >> 32;
+	ret = snp_cpuid(&leaf);
+	if (!ret)
+		goto cpuid_done;
 
-	sev_es_wr_ghcb_msr(GHCB_CPUID_REQ(fn, GHCB_CPUID_REQ_ECX));
-	VMGEXIT();
-	val = sev_es_rd_ghcb_msr();
-	if (GHCB_RESP_CODE(val) != GHCB_MSR_CPUID_RESP)
+	if (ret != -EOPNOTSUPP)
 		goto fail;
-	regs->cx = val >> 32;
 
-	sev_es_wr_ghcb_msr(GHCB_CPUID_REQ(fn, GHCB_CPUID_REQ_EDX));
-	VMGEXIT();
-	val = sev_es_rd_ghcb_msr();
-	if (GHCB_RESP_CODE(val) != GHCB_MSR_CPUID_RESP)
+	if (sev_cpuid_hv(&leaf))
 		goto fail;
-	regs->dx = val >> 32;
+
+cpuid_done:
+	regs->ax = leaf.eax;
+	regs->bx = leaf.ebx;
+	regs->cx = leaf.ecx;
+	regs->dx = leaf.edx;
 
 	/*
 	 * This is a VC handler and the #VC is only raised when SEV-ES is
@@ -221,7 +592,7 @@ 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,
@@ -481,12 +852,37 @@ static enum es_result vc_handle_ioio(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
 	return ret;
 }
 
+static int vc_handle_cpuid_snp(struct pt_regs *regs)
+{
+	struct cpuid_leaf leaf;
+	int ret;
+
+	leaf.fn = regs->ax;
+	leaf.subfn = regs->cx;
+	ret = snp_cpuid(&leaf);
+	if (!ret) {
+		regs->ax = leaf.eax;
+		regs->bx = leaf.ebx;
+		regs->cx = leaf.ecx;
+		regs->dx = leaf.edx;
+	}
+
+	return ret;
+}
+
 static enum es_result vc_handle_cpuid(struct ghcb *ghcb,
 				      struct es_em_ctxt *ctxt)
 {
 	struct pt_regs *regs = ctxt->regs;
 	u32 cr4 = native_read_cr4();
 	enum es_result ret;
+	int snp_cpuid_ret;
+
+	snp_cpuid_ret = vc_handle_cpuid_snp(regs);
+	if (!snp_cpuid_ret)
+		return ES_OK;
+	if (snp_cpuid_ret != -EOPNOTSUPP)
+		return ES_VMM_ERROR;
 
 	ghcb_set_rax(ghcb, regs->ax);
 	ghcb_set_rcx(ghcb, regs->cx);
@@ -538,3 +934,67 @@ static enum es_result vc_handle_rdtsc(struct ghcb *ghcb,
 
 	return ES_OK;
 }
+
+struct cc_setup_data {
+	struct setup_data header;
+	u32 cc_blob_address;
+};
+
+/*
+ * Search for a Confidential Computing blob passed in as a setup_data entry
+ * via the Linux Boot Protocol.
+ */
+static struct cc_blob_sev_info *find_cc_blob_setup_data(struct boot_params *bp)
+{
+	struct cc_setup_data *sd = NULL;
+	struct setup_data *hdr;
+
+	hdr = (struct setup_data *)bp->hdr.setup_data;
+
+	while (hdr) {
+		if (hdr->type == SETUP_CC_BLOB) {
+			sd = (struct cc_setup_data *)hdr;
+			return (struct cc_blob_sev_info *)(unsigned long)sd->cc_blob_address;
+		}
+		hdr = (struct setup_data *)hdr->next;
+	}
+
+	return NULL;
+}
+
+/*
+ * Initialize the kernel's copy of the SNP CPUID table, and set up the
+ * pointer that will be used to access it.
+ *
+ * Maintaining a direct mapping of the SNP CPUID table used by firmware would
+ * be possible as an alternative, but the approach is brittle since the
+ * mapping needs to be updated in sync with all the changes to virtual memory
+ * layout and related mapping facilities throughout the boot process.
+ */
+static void __init setup_cpuid_table(const struct cc_blob_sev_info *cc_info)
+{
+	const struct snp_cpuid_table *cpuid_table_fw, *cpuid_table;
+	int i;
+
+	if (!cc_info || !cc_info->cpuid_phys || cc_info->cpuid_len < PAGE_SIZE)
+		sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_CPUID);
+
+	cpuid_table_fw = (const struct snp_cpuid_table *)cc_info->cpuid_phys;
+	if (!cpuid_table_fw->count || cpuid_table_fw->count > SNP_CPUID_COUNT_MAX)
+		sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_CPUID);
+
+	cpuid_table = snp_cpuid_get_table();
+	memcpy((void *)cpuid_table, cpuid_table_fw, sizeof(*cpuid_table));
+
+	/* Initialize CPUID ranges for range-checking. */
+	for (i = 0; i < cpuid_table->count; i++) {
+		const struct snp_cpuid_fn *fn = &cpuid_table->fn[i];
+
+		if (fn->eax_in == 0x0)
+			cpuid_std_range_max = fn->eax;
+		else if (fn->eax_in == 0x40000000)
+			cpuid_hyp_range_max = fn->eax;
+		else if (fn->eax_in == 0x80000000)
+			cpuid_ext_range_max = fn->eax;
+	}
+}
diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c
index e6d316a01fdd..c05f0124c410 100644
--- a/arch/x86/kernel/sev.c
+++ b/arch/x86/kernel/sev.c
@@ -18,6 +18,10 @@
 #include <linux/memblock.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
+#include <linux/cpumask.h>
+#include <linux/efi.h>
+#include <linux/platform_device.h>
+#include <linux/io.h>
 
 #include <asm/cpu_entry_area.h>
 #include <asm/stacktrace.h>
@@ -31,9 +35,28 @@
 #include <asm/svm.h>
 #include <asm/smp.h>
 #include <asm/cpu.h>
+#include <asm/apic.h>
+#include <asm/cpuid.h>
+#include <asm/cmdline.h>
 
 #define DR7_RESET_VALUE        0x400
 
+/* AP INIT values as documented in the APM2  section "Processor Initialization State" */
+#define AP_INIT_CS_LIMIT		0xffff
+#define AP_INIT_DS_LIMIT		0xffff
+#define AP_INIT_LDTR_LIMIT		0xffff
+#define AP_INIT_GDTR_LIMIT		0xffff
+#define AP_INIT_IDTR_LIMIT		0xffff
+#define AP_INIT_TR_LIMIT		0xffff
+#define AP_INIT_RFLAGS_DEFAULT		0x2
+#define AP_INIT_DR6_DEFAULT		0xffff0ff0
+#define AP_INIT_GPAT_DEFAULT		0x0007040600070406ULL
+#define AP_INIT_XCR0_DEFAULT		0x1
+#define AP_INIT_X87_FTW_DEFAULT		0x5555
+#define AP_INIT_X87_FCW_DEFAULT		0x0040
+#define AP_INIT_CR0_DEFAULT		0x60000010
+#define AP_INIT_MXCSR_DEFAULT		0x1f80
+
 /* For early boot hypervisor communication in SEV-ES enabled guests */
 static struct ghcb boot_ghcb_page __bss_decrypted __aligned(PAGE_SIZE);
 
@@ -41,7 +64,10 @@ static struct ghcb boot_ghcb_page __bss_decrypted __aligned(PAGE_SIZE);
  * Needs to be in the .data section because we need it NULL before bss is
  * cleared
  */
-static struct ghcb __initdata *boot_ghcb;
+static struct ghcb *boot_ghcb __section(".data");
+
+/* Bitmap of SEV features supported by the hypervisor */
+static u64 sev_hv_features __ro_after_init;
 
 /* #VC handler runtime per-CPU data */
 struct sev_es_runtime_data {
@@ -87,6 +113,15 @@ struct ghcb_state {
 static DEFINE_PER_CPU(struct sev_es_runtime_data*, runtime_data);
 DEFINE_STATIC_KEY_FALSE(sev_es_enable_key);
 
+static DEFINE_PER_CPU(struct sev_es_save_area *, sev_vmsa);
+
+struct sev_config {
+	__u64 debug		: 1,
+	      __reserved	: 63;
+};
+
+static struct sev_config sev_cfg __read_mostly;
+
 static __always_inline bool on_vc_stack(struct pt_regs *regs)
 {
 	unsigned long sp = regs->sp;
@@ -523,13 +558,68 @@ void noinstr __sev_es_nmi_complete(void)
 	__sev_put_ghcb(&state);
 }
 
-static u64 get_jump_table_addr(void)
+static u64 __init get_secrets_page(void)
+{
+	u64 pa_data = boot_params.cc_blob_address;
+	struct cc_blob_sev_info info;
+	void *map;
+
+	/*
+	 * The CC blob contains the address of the secrets page, check if the
+	 * blob is present.
+	 */
+	if (!pa_data)
+		return 0;
+
+	map = early_memremap(pa_data, sizeof(info));
+	if (!map) {
+		pr_err("Unable to locate SNP secrets page: failed to map the Confidential Computing blob.\n");
+		return 0;
+	}
+	memcpy(&info, map, sizeof(info));
+	early_memunmap(map, sizeof(info));
+
+	/* smoke-test the secrets page passed */
+	if (!info.secrets_phys || info.secrets_len != PAGE_SIZE)
+		return 0;
+
+	return info.secrets_phys;
+}
+
+static u64 __init get_snp_jump_table_addr(void)
+{
+	struct snp_secrets_page_layout *layout;
+	void __iomem *mem;
+	u64 pa, addr;
+
+	pa = get_secrets_page();
+	if (!pa)
+		return 0;
+
+	mem = ioremap_encrypted(pa, PAGE_SIZE);
+	if (!mem) {
+		pr_err("Unable to locate AP jump table address: failed to map the SNP secrets page.\n");
+		return 0;
+	}
+
+	layout = (__force struct snp_secrets_page_layout *)mem;
+
+	addr = layout->os_area.ap_jump_table_pa;
+	iounmap(mem);
+
+	return addr;
+}
+
+static u64 __init get_jump_table_addr(void)
 {
 	struct ghcb_state state;
 	unsigned long flags;
 	struct ghcb *ghcb;
 	u64 ret = 0;
 
+	if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
+		return get_snp_jump_table_addr();
+
 	local_irq_save(flags);
 
 	ghcb = __sev_get_ghcb(&state);
@@ -553,7 +643,496 @@ static u64 get_jump_table_addr(void)
 	return ret;
 }