Merge tag 'x86_sev_for_v6.11_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 SEV updates from Borislav Petkov:

 - Add support for running the kernel in a SEV-SNP guest, over a Secure
   VM Service Module (SVSM).

   When running over a SVSM, different services can run at different
   protection levels, apart from the guest OS but still within the
   secure SNP environment. They can provide services to the guest, like
   a vTPM, for example.

   This series adds the required facilities to interface with such a
   SVSM module.

 - The usual fixlets, refactoring and cleanups

[ And as always: "SEV" is AMD's "Secure Encrypted Virtualization".

  I can't be the only one who gets all the newer x86 TLA's confused,
  can I?
              - Linus ]

* tag 'x86_sev_for_v6.11_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  Documentation/ABI/configfs-tsm: Fix an unexpected indentation silly
  x86/sev: Do RMP memory coverage check after max_pfn has been set
  x86/sev: Move SEV compilation units
  virt: sev-guest: Mark driver struct with __refdata to prevent section mismatch
  x86/sev: Allow non-VMPL0 execution when an SVSM is present
  x86/sev: Extend the config-fs attestation support for an SVSM
  x86/sev: Take advantage of configfs visibility support in TSM
  fs/configfs: Add a callback to determine attribute visibility
  sev-guest: configfs-tsm: Allow the privlevel_floor attribute to be updated
  virt: sev-guest: Choose the VMPCK key based on executing VMPL
  x86/sev: Provide guest VMPL level to userspace
  x86/sev: Provide SVSM discovery support
  x86/sev: Use the SVSM to create a vCPU when not in VMPL0
  x86/sev: Perform PVALIDATE using the SVSM when not at VMPL0
  x86/sev: Use kernel provided SVSM Calling Areas
  x86/sev: Check for the presence of an SVSM in the SNP secrets page
  x86/irqflags: Provide native versions of the local_irq_save()/restore()

14 files changed, 1118 insertions, 128 deletions

diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c
index 0457a9d7e515..cd44e120fe53 100644
--- a/arch/x86/boot/compressed/sev.c
+++ b/arch/x86/boot/compressed/sev.c
@@ -127,7 +127,35 @@ static bool fault_in_kernel_space(unsigned long address)
 #include "../../lib/insn.c"
 
 /* Include code for early handlers */
-#include "../../kernel/sev-shared.c"
+#include "../../coco/sev/shared.c"
+
+static struct svsm_ca *svsm_get_caa(void)
+{
+	return boot_svsm_caa;
+}
+
+static u64 svsm_get_caa_pa(void)
+{
+	return boot_svsm_caa_pa;
+}
+
+static int svsm_perform_call_protocol(struct svsm_call *call)
+{
+	struct ghcb *ghcb;
+	int ret;
+
+	if (boot_ghcb)
+		ghcb = boot_ghcb;
+	else
+		ghcb = NULL;
+
+	do {
+		ret = ghcb ? svsm_perform_ghcb_protocol(ghcb, call)
+			   : svsm_perform_msr_protocol(call);
+	} while (ret == -EAGAIN);
+
+	return ret;
+}
 
 bool sev_snp_enabled(void)
 {
@@ -145,8 +173,8 @@ static void __page_state_change(unsigned long paddr, enum psc_op op)
 	 * 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);
+	if (op == SNP_PAGE_STATE_SHARED)
+		pvalidate_4k_page(paddr, paddr, false);
 
 	/* Issue VMGEXIT to change the page state in RMP table. */
 	sev_es_wr_ghcb_msr(GHCB_MSR_PSC_REQ_GFN(paddr >> PAGE_SHIFT, op));
@@ -161,8 +189,8 @@ static void __page_state_change(unsigned long paddr, enum psc_op op)
 	 * Now that page state is changed 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);
+	if (op == SNP_PAGE_STATE_PRIVATE)
+		pvalidate_4k_page(paddr, paddr, true);
 }
 
 void snp_set_page_private(unsigned long paddr)
@@ -256,6 +284,16 @@ void sev_es_shutdown_ghcb(void)
 		error("SEV-ES CPU Features missing.");
 
 	/*
+	 * This denotes whether to use the GHCB MSR protocol or the GHCB
+	 * shared page to perform a GHCB request. Since the GHCB page is
+	 * being changed to encrypted, it can't be used to perform GHCB
+	 * requests. Clear the boot_ghcb variable so that the GHCB MSR
+	 * protocol is used to change the GHCB page over to an encrypted
+	 * page.
+	 */
+	boot_ghcb = NULL;
+
+	/*
 	 * GHCB Page must be flushed from the cache and mapped encrypted again.
 	 * Otherwise the running kernel will see strange cache effects when
 	 * trying to use that page.
@@ -463,6 +501,13 @@ static bool early_snp_init(struct boot_params *bp)
 	setup_cpuid_table(cc_info);
 
 	/*
+	 * Record the SVSM Calling Area (CA) address if the guest is not
+	 * running at VMPL0. The CA will be used to communicate with the
+	 * SVSM and request its services.
+	 */
+	svsm_setup_ca(cc_info);
+
+	/*
 	 * Pass run-time kernel a pointer to CC info via boot_params so EFI
 	 * config table doesn't need to be searched again during early startup
 	 * phase.
@@ -565,22 +610,31 @@ void sev_enable(struct boot_params *bp)
 	 * features.
 	 */
 	if (sev_status & MSR_AMD64_SEV_SNP_ENABLED) {
-		if (!(get_hv_features() & GHCB_HV_FT_SNP))
+		u64 hv_features;
+		int ret;
+
+		hv_features = get_hv_features();
+		if (!(hv_features & GHCB_HV_FT_SNP))
 			sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED);
 
 		/*
-		 * Enforce running at VMPL0.
-		 *
-		 * RMPADJUST modifies RMP permissions of a lesser-privileged (numerically
-		 * higher) privilege level. Here, clear the VMPL1 permission mask of the
-		 * GHCB page. If the guest is not running at VMPL0, this will fail.
+		 * Enforce running at VMPL0 or with an SVSM.
 		 *
-		 * If the guest is running at VMPL0, it will succeed. Even if that operation
-		 * modifies permission bits, it is still ok to do so currently because Linux
-		 * SNP guests running at VMPL0 only run at VMPL0, so VMPL1 or higher
-		 * permission mask changes are a don't-care.
+		 * Use RMPADJUST (see the rmpadjust() function for a description of
+		 * what the instruction does) to update the VMPL1 permissions of a
+		 * page. If the guest is running at VMPL0, this will succeed. If the
+		 * guest is running at any other VMPL, this will fail. Linux SNP guests
+		 * only ever run at a single VMPL level so permission mask changes of a
+		 * lesser-privileged VMPL are a don't-care.
+		 */
+		ret = rmpadjust((unsigned long)&boot_ghcb_page, RMP_PG_SIZE_4K, 1);
+
+		/*
+		 * Running at VMPL0 is not required if an SVSM is present and the hypervisor
+		 * supports the required SVSM GHCB events.
 		 */
-		if (rmpadjust((unsigned long)&boot_ghcb_page, RMP_PG_SIZE_4K, 1))
+		if (ret &&
+		    !(snp_vmpl && (hv_features & GHCB_HV_FT_SNP_MULTI_VMPL)))
 			sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_NOT_VMPL0);
 	}
 
diff --git a/arch/x86/coco/Makefile b/arch/x86/coco/Makefile
index c816acf78b6a..eabdc7486538 100644
--- a/arch/x86/coco/Makefile
+++ b/arch/x86/coco/Makefile
@@ -6,3 +6,4 @@ CFLAGS_core.o		+= -fno-stack-protector
 obj-y += core.o
 
 obj-$(CONFIG_INTEL_TDX_GUEST)	+= tdx/
+obj-$(CONFIG_AMD_MEM_ENCRYPT)   += sev/
diff --git a/arch/x86/coco/sev/Makefile b/arch/x86/coco/sev/Makefile
new file mode 100644
index 000000000000..4e375e7305ac
--- /dev/null
+++ b/arch/x86/coco/sev/Makefile
@@ -0,0 +1,15 @@
+# SPDX-License-Identifier: GPL-2.0
+
+obj-y += core.o
+
+ifdef CONFIG_FUNCTION_TRACER
+CFLAGS_REMOVE_core.o = -pg
+endif
+
+KASAN_SANITIZE_core.o	:= n
+KMSAN_SANITIZE_core.o	:= n
+KCOV_INSTRUMENT_core.o	:= n
+
+# With some compiler versions the generated code results in boot hangs, caused
+# by several compilation units. To be safe, disable all instrumentation.
+KCSAN_SANITIZE		:= n
diff --git a/arch/x86/kernel/sev.c b/arch/x86/coco/sev/core.c
index 3342ed58e168..082d61d85dfc 100644
--- a/arch/x86/kernel/sev.c
+++ b/arch/x86/coco/sev/core.c
@@ -133,16 +133,20 @@ struct ghcb_state {
 	struct ghcb *ghcb;
 };
 
+/* For early boot SVSM communication */
+static struct svsm_ca boot_svsm_ca_page __aligned(PAGE_SIZE);
+
 static DEFINE_PER_CPU(struct sev_es_runtime_data*, runtime_data);
 static DEFINE_PER_CPU(struct sev_es_save_area *, sev_vmsa);
+static DEFINE_PER_CPU(struct svsm_ca *, svsm_caa);
+static DEFINE_PER_CPU(u64, svsm_caa_pa);
 
 struct sev_config {
 	__u64 debug		: 1,
 
 	      /*
-	       * A flag used by __set_pages_state() that indicates when the
-	       * per-CPU GHCB has been created and registered and thus can be
-	       * used by the BSP instead of the early boot GHCB.
+	       * Indicates when the per-CPU GHCB has been created and registered
+	       * and thus can be used by the BSP instead of the early boot GHCB.
 	       *
 	       * For APs, the per-CPU GHCB is created before they are started
 	       * and registered upon startup, so this flag can be used globally
@@ -150,6 +154,15 @@ struct sev_config {
 	       */
 	      ghcbs_initialized	: 1,
 
+	      /*
+	       * Indicates when the per-CPU SVSM CA is to be used instead of the
+	       * boot SVSM CA.
+	       *
+	       * For APs, the per-CPU SVSM CA is created as part of the AP
+	       * bringup, so this flag can be used globally for the BSP and APs.
+	       */
+	      use_cas		: 1,
+
 	      __reserved	: 62;
 };
 
@@ -572,8 +585,61 @@ fault:
 	return ES_EXCEPTION;
 }
 
+static __always_inline void vc_forward_exception(struct es_em_ctxt *ctxt)
+{
+	long error_code = ctxt->fi.error_code;
+	int trapnr = ctxt->fi.vector;
+
+	ctxt->regs->orig_ax = ctxt->fi.error_code;
+
+	switch (trapnr) {
+	case X86_TRAP_GP:
+		exc_general_protection(ctxt->regs, error_code);
+		break;
+	case X86_TRAP_UD:
+		exc_invalid_op(ctxt->regs);
+		break;
+	case X86_TRAP_PF:
+		write_cr2(ctxt->fi.cr2);
+		exc_page_fault(ctxt->regs, error_code);
+		break;
+	case X86_TRAP_AC:
+		exc_alignment_check(ctxt->regs, error_code);
+		break;
+	default:
+		pr_emerg("Unsupported exception in #VC instruction emulation - can't continue\n");
+		BUG();
+	}
+}
+
 /* Include code shared with pre-decompression boot stage */
-#include "sev-shared.c"
+#include "shared.c"
+
+static inline struct svsm_ca *svsm_get_caa(void)
+{
+	/*
+	 * Use rIP-relative references when called early in the boot. If
+	 * ->use_cas is set, then it is late in the boot and no need
+	 * to worry about rIP-relative references.
+	 */
+	if (RIP_REL_REF(sev_cfg).use_cas)
+		return this_cpu_read(svsm_caa);
+	else
+		return RIP_REL_REF(boot_svsm_caa);
+}
+
+static u64 svsm_get_caa_pa(void)
+{
+	/*
+	 * Use rIP-relative references when called early in the boot. If
+	 * ->use_cas is set, then it is late in the boot and no need
+	 * to worry about rIP-relative references.
+	 */
+	if (RIP_REL_REF(sev_cfg).use_cas)
+		return this_cpu_read(svsm_caa_pa);
+	else
+		return RIP_REL_REF(boot_svsm_caa_pa);
+}
 
 static noinstr void __sev_put_ghcb(struct ghcb_state *state)
 {
@@ -600,6 +666,44 @@ static noinstr void __sev_put_ghcb(struct ghcb_state *state)
 	}
 }
 
+static int svsm_perform_call_protocol(struct svsm_call *call)
+{
+	struct ghcb_state state;
+	unsigned long flags;
+	struct ghcb *ghcb;
+	int ret;
+
+	/*
+	 * This can be called very early in the boot, use native functions in
+	 * order to avoid paravirt issues.
+	 */
+	flags = native_local_irq_save();
+
+	/*
+	 * Use rip-relative references when called early in the boot. If
+	 * ghcbs_initialized is set, then it is late in the boot and no need
+	 * to worry about rip-relative references in called functions.
+	 */
+	if (RIP_REL_REF(sev_cfg).ghcbs_initialized)
+		ghcb = __sev_get_ghcb(&state);
+	else if (RIP_REL_REF(boot_ghcb))
+		ghcb = RIP_REL_REF(boot_ghcb);
+	else
+		ghcb = NULL;
+
+	do {
+		ret = ghcb ? svsm_perform_ghcb_protocol(ghcb, call)
+			   : svsm_perform_msr_protocol(call);
+	} while (ret == -EAGAIN);
+
+	if (RIP_REL_REF(sev_cfg).ghcbs_initialized)
+		__sev_put_ghcb(&state);
+
+	native_local_irq_restore(flags);
+
+	return ret;
+}
+
 void noinstr __sev_es_nmi_complete(void)
 {
 	struct ghcb_state state;
@@ -709,7 +813,6 @@ early_set_pages_state(unsigned long vaddr, unsigned long paddr,
 {
 	unsigned long paddr_end;
 	u64 val;
-	int ret;
 
 	vaddr = vaddr & PAGE_MASK;
 
@@ -717,12 +820,9 @@ early_set_pages_state(unsigned long vaddr, unsigned long paddr,
 	paddr_end = paddr + (npages << PAGE_SHIFT);
 
 	while (paddr < paddr_end) {
-		if (op == SNP_PAGE_STATE_SHARED) {
-			/* Page validation must be rescinded before changing to shared */
-			ret = pvalidate(vaddr, RMP_PG_SIZE_4K, false);
-			if (WARN(ret, "Failed to validate address 0x%lx ret %d", paddr, ret))
-				goto e_term;
-		}
+		/* Page validation must be rescinded before changing to shared */
+		if (op == SNP_PAGE_STATE_SHARED)
+			pvalidate_4k_page(vaddr, paddr, false);
 
 		/*
 		 * Use the MSR protocol because this function can be called before
@@ -744,12 +844,9 @@ early_set_pages_state(unsigned long vaddr, unsigned long paddr,
 			 paddr, GHCB_MSR_PSC_RESP_VAL(val)))
 			goto e_term;
 
-		if (op == SNP_PAGE_STATE_PRIVATE) {
-			/* Page validation must be performed after changing to private */
-			ret = pvalidate(vaddr, RMP_PG_SIZE_4K, true);
-			if (WARN(ret, "Failed to validate address 0x%lx ret %d", paddr, ret))
-				goto e_term;
-		}
+		/* Page validation must be performed after changing to private */
+		if (op == SNP_PAGE_STATE_PRIVATE)
+			pvalidate_4k_page(vaddr, paddr, true);
 
 		vaddr += PAGE_SIZE;
 		paddr += PAGE_SIZE;
@@ -913,22 +1010,49 @@ 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;
+
+		local_irq_save(flags);
 
-	return rmpadjust((unsigned long)va, RMP_PG_SIZE_4K, attrs);
+		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 {
+		/*
+		 * If the kernel runs at VMPL0, it can 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.
+		 */
+		u64 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)
@@ -962,11 +1086,11 @@ 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
@@ -977,6 +1101,7 @@ 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;
@@ -1023,6 +1148,9 @@ 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;
 
@@ -1070,11 +1198,11 @@ 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);
@@ -1090,7 +1218,10 @@ 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));
@@ -1108,13 +1239,13 @@ 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;
@@ -1209,6 +1340,17 @@ static enum es_result vc_handle_msr(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
 	/* Is it a WRMSR? */
 	exit_info_1 = (ctxt->insn.opcode.bytes[1] == 0x30) ? 1 : 0;
 
+	if (regs->cx == MSR_SVSM_CAA) {
+		/* Writes to the SVSM CAA msr are ignored */
+		if (exit_info_1)
+			return ES_OK;
+
+		regs->ax = lower_32_bits(this_cpu_read(svsm_caa_pa));
+		regs->dx = upper_32_bits(this_cpu_read(svsm_caa_pa));
+
+		return ES_OK;
+	}
+
 	ghcb_set_rcx(ghcb, regs->cx);
 	if (exit_info_1) {
 		ghcb_set_rax(ghcb, regs->ax);
@@ -1346,6 +1488,18 @@ static void __init alloc_runtime_data(int cpu)
 		panic("Can't allocate SEV-ES runtime data");
 
 	per_cpu(runtime_data, cpu) = data;
+
+	if (snp_vmpl) {
+		struct svsm_ca *caa;
+
+		/* Allocate the SVSM CA page if an SVSM is present */
+		caa = memblock_alloc(sizeof(*caa), PAGE_SIZE);
+		if (!caa)
+			panic("Can't allocate SVSM CA page\n");
+
+		per_cpu(svsm_caa, cpu) = caa;
+		per_cpu(svsm_caa_pa, cpu) = __pa(caa);
+	}
 }
 
 static void __init init_ghcb(int cpu)
@@ -1395,6 +1549,32 @@ void __init sev_es_init_vc_handling(void)
 		init_ghcb(cpu);
 	}
 
+	/* If running under an SVSM, switch to the per-cpu CA */
+	if (snp_vmpl) {
+		struct svsm_call call = {};
+		unsigned long flags;
+		int ret;
+
+		local_irq_save(flags);
+
+		/*
+		 * SVSM_CORE_REMAP_CA call:
+		 *   RAX = 0 (Protocol=0, CallID=0)
+		 *   RCX = New CA GPA
+		 */
+		call.caa = svsm_get_caa();
+		call.rax = SVSM_CORE_CALL(SVSM_CORE_REMAP_CA);
+		call.rcx = this_cpu_read(svsm_caa_pa);
+		ret = svsm_perform_call_protocol(&call);
+		if (ret)
+			panic("Can't remap the SVSM CA, ret=%d, rax_out=0x%llx\n",
+			      ret, call.rax_out);
+
+		sev_cfg.use_cas = true;
+
+		local_irq_restore(flags);
+	}
+
 	sev_es_setup_play_dead();
 
 	/* Secondary CPUs use the runtime #VC handler */
@@ -1819,33 +1999,6 @@ static enum es_result vc_handle_exitcode(struct es_em_ctxt *ctxt,
 	return result;
 }
 
-static __always_inline void vc_forward_exception(struct es_em_ctxt *ctxt)
-{
-	long error_code = ctxt->fi.error_code;
-	int trapnr = ctxt->fi.vector;
-
-	ctxt->regs->orig_ax = ctxt->fi.error_code;
-
-	switch (trapnr) {
-	case X86_TRAP_GP:
-		exc_general_protection(ctxt->regs, error_code);
-		break;
-	case X86_TRAP_UD:
-		exc_invalid_op(ctxt->regs);
-		break;
-	case X86_TRAP_PF:
-		write_cr2(ctxt->fi.cr2);
-		exc_page_fault(ctxt->regs, error_code);
-		break;
-	case X86_TRAP_AC:
-		exc_alignment_check(ctxt->regs, error_code);
-		break;
-	default:
-		pr_emerg("Unsupported exception in #VC instruction emulation - can't continue\n");
-		BUG();
-	}
-}
-
 static __always_inline bool is_vc2_stack(unsigned long sp)
 {
 	return (sp >= __this_cpu_ist_bottom_va(VC2) && sp < __this_cpu_ist_top_va(VC2));
@@ -2095,6 +2248,47 @@ found_cc_info:
 	return cc_info;
 }
 
+static __head void svsm_setup(struct cc_blob_sev_info *cc_info)
+{
+	struct svsm_call call = {};
+	int ret;
+	u64 pa;
+
+	/*
+	 * Record the SVSM Calling Area address (CAA) if the guest is not
+	 * running at VMPL0. The CA will be used to communicate with the
+	 * SVSM to perform the SVSM services.
+	 */
+	if (!svsm_setup_ca(cc_info))
+		return;
+
+	/*
+	 * It is very early in the boot and the kernel is running identity
+	 * mapped but without having adjusted the pagetables to where the
+	 * kernel was loaded (physbase), so the get the CA address using
+	 * RIP-relative addressing.
+	 */
+	pa = (u64)&RIP_REL_REF(boot_svsm_ca_page);
+
+	/*
+	 * Switch over to the boot SVSM CA while the current CA is still
+	 * addressable. There is no GHCB at this point so use the MSR protocol.
+	 *
+	 * SVSM_CORE_REMAP_CA call:
+	 *   RAX = 0 (Protocol=0, CallID=0)
+	 *   RCX = New CA GPA
+	 */
+	call.caa = svsm_get_caa();
+	call.rax = SVSM_CORE_CALL(SVSM_CORE_REMAP_CA);
+	call.rcx = pa;
+	ret = svsm_perform_call_protocol(&call);
+	if (ret)
+		panic("Can't remap the SVSM CA, ret=%d, rax_out=0x%llx\n", ret, call.rax_out);
+
+	RIP_REL_REF(boot_svsm_caa) = (struct svsm_ca *)pa;
+	RIP_REL_REF(boot_svsm_caa_pa) = pa;
+}
+
 bool __head snp_init(struct boot_params *bp)
 {
 	struct cc_blob_sev_info *cc_info;
@@ -2108,6 +2302,8 @@ bool __head snp_init(struct boot_params *bp)
 
 	setup_cpuid_table(cc_info);
 
+	svsm_setup(cc_info);
+
 	/*
 	 * The CC blob will be used later to access the secrets page. Cache
 	 * it here like the boot kernel does.
@@ -2156,23 +2352,27 @@ static void dump_cpuid_table(void)
  * expected, but that initialization happens too early in boot to print any
  * sort of indicator, and there's not really any other good place to do it,
  * so do it here.
+ *
+ * If running as an SNP guest, report the current VM privilege level (VMPL).
  */
-static int __init report_cpuid_table(void)
+static int __init report_snp_info(void)
 {
 	const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table();
 
-	if (!cpuid_table->count)
-		return 0;
+	if (cpuid_table->count) {
+		pr_info("Using SNP CPUID table, %d entries present.\n",
+			cpuid_table->count);
 
-	pr_info("Using SNP CPUID table, %d entries present.\n",
-		cpuid_table->count);
+		if (sev_cfg.debug)
+			dump_cpuid_table();
+	}
 
-	if (sev_cfg.debug)
-		dump_cpuid_table();
+	if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
+		pr_info("SNP running at VMPL%u.\n", snp_vmpl);
 
 	return 0;
 }
-arch_initcall(report_cpuid_table);
+arch_initcall(report_snp_info);
 
 static int __init init_sev_config(char *str)
 {
@@ -2191,6 +2391,56 @@ static int __init init_sev_config(char *str)
 }
 __setup("sev=", init_sev_config);
 
+static void update_attest_input(struct svsm_call *call, struct svsm_attest_call *input)
+{
+	/* If (new) lengths have been returned, propagate them up */
+	if (call->rcx_out != call->rcx)
+		input->manifest_buf.len = call->rcx_out;
+
+	if (call->rdx_out != call->rdx)
+		input->certificates_buf.len = call->rdx_out;
+
+	if (call->r8_out != call->r8)
+		input->report_buf.len = call->r8_out;
+}
+
+int snp_issue_svsm_attest_req(u64 call_id, struct svsm_call *call,
+			      struct svsm_attest_call *input)
+{
+	struct svsm_attest_call *ac;
+	unsigned long flags;
+	u64 attest_call_pa;
+	int ret;
+
+	if (!snp_vmpl)
+		return -EINVAL;
+
+	local_irq_save(flags);
+
+	call->caa = svsm_get_caa();
+
+	ac = (struct svsm_attest_call *)call->caa->svsm_buffer;
+	attest_call_pa = svsm_get_caa_pa() + offsetof(struct svsm_ca, svsm_buffer);
+
+	*ac = *input;
+
+	/*
+	 * Set input registers for the request and set RDX and R8 to known
+	 * values in order to detect length values being returned in them.
+	 */
+	call->rax = call_id;
+	call->rcx = attest_call_pa;
+	call->rdx = -1;
+	call->r8 = -1;
+	ret = svsm_perform_call_protocol(call);
+	update_attest_input(call, input);
+
+	local_irq_restore(flags);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(snp_issue_svsm_attest_req);
+
 int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, struct snp_guest_request_ioctl *rio)
 {
 	struct ghcb_state state;
@@ -2299,3 +2549,58 @@ void sev_show_status(void)
 	}
 	pr_cont("\n");
 }
+
+void __init snp_update_svsm_ca(void)
+{
+	if (!snp_vmpl)
+		return;
+
+	/* Update the CAA to a proper kernel address */
+	boot_svsm_caa = &boot_svsm_ca_page;
+}
+
+#ifdef CONFIG_SYSFS
+static ssize_t vmpl_show(struct kobject *kobj,
+			 struct kobj_attribute *attr, char *buf)
+{
+	return sysfs_emit(buf, "%d\n", snp_vmpl);
+}
+
+static struct kobj_attribute vmpl_attr = __ATTR_RO(vmpl);
+
+static struct attribute *vmpl_attrs[] = {
+	&vmpl_attr.attr,
+	NULL
+};
+
+static struct attribute_group sev_attr_group = {
+	.attrs = vmpl_attrs,
+};
+
+static int __init sev_sysfs_init(void)
+{
+	struct kobject *sev_kobj;
+	struct device *dev_root;
+	int ret;
+
+	if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
+		return -ENODEV;
+
+	dev_root = bus_get_dev_root(&cpu_subsys);
+	if (!dev_root)
+		return -ENODEV;
+
+	sev_kobj = kobject_create_and_add("sev", &dev_root->kobj);
+	put_device(dev_root);
+
+	if (!sev_kobj)
+		return -ENOMEM;
+
+	ret = sysfs_create_group(sev_kobj, &sev_attr_group);
+	if (ret)
+		kobject_put(sev_kobj);
+
+	return ret;
+}
+arch_initcall(sev_sysfs_init);
+#endif // CONFIG_SYSFS
diff --git a/arch/x86/kernel/sev-shared.c b/arch/x86/coco/sev/shared.c
index b4f8fa0f722c..71de53194089 100644
--- a/arch/x86/kernel/sev-shared.c
+++ b/arch/x86/coco/sev/shared.c
@@ -21,8 +21,30 @@
 #define WARN(condition, format...) (!!(condition))
 #define sev_printk(fmt, ...)
 #define sev_printk_rtl(fmt, ...)
+#undef vc_forward_exception
+#define vc_forward_exception(c)		panic("SNP: Hypervisor requested exception\n")
 #endif
 
+/*
+ * SVSM related information:
+ *   When running under an SVSM, the VMPL that Linux is executing at must be
+ *   non-zero. The VMPL is therefore used to indicate the presence of an SVSM.
+ *
+ *   During boot, the page tables are set up as identity mapped and later
+ *   changed to use kernel virtual addresses. Maintain separate virtual and
+ *   physical addresses for the CAA to allow SVSM functions to be used during
+ *   early boot, both with identity mapped virtual addresses and proper kernel
+ *   virtual addresses.
+ */
+u8 snp_vmpl __ro_after_init;
+EXPORT_SYMBOL_GPL(snp_vmpl);
+static struct svsm_ca *boot_svsm_caa __ro_after_init;
+static u64 boot_svsm_caa_pa __ro_after_init;
+
+static struct svsm_ca *svsm_get_caa(void);
+static u64 svsm_get_caa_pa(void);
+static int svsm_perform_call_protocol(struct svsm_call *call);
+
 /* I/O parameters for CPUID-related helpers */
 struct cpuid_leaf {
 	u32 fn;
@@ -229,6 +251,126 @@ static enum es_result verify_exception_info(struct ghcb *ghcb, struct es_em_ctxt
 	return ES_VMM_ERROR;
 }
 
+static inline int svsm_process_result_codes(struct svsm_call *call)
+{
+	switch (call->rax_out) {
+	case SVSM_SUCCESS:
+		return 0;
+	case SVSM_ERR_INCOMPLETE:
+	case SVSM_ERR_BUSY:
+		return -EAGAIN;
+	default:
+		return -EINVAL;
+	}
+}
+
+/*
+ * Issue a VMGEXIT to call the SVSM:
+ *   - Load the SVSM register state (RAX, RCX, RDX, R8 and R9)
+ *   - Set the CA call pending field to 1
+ *   - Issue VMGEXIT
+ *   - Save the SVSM return register state (RAX, RCX, RDX, R8 and R9)
+ *   - Perform atomic exchange of the CA call pending field
+ *
+ *   - See the "Secure VM Service Module for SEV-SNP Guests" specification for
+ *     details on the calling convention.
+ *     - The calling convention loosely follows the Microsoft X64 calling
+ *       convention by putting arguments in RCX, RDX, R8 and R9.
+ *     - RAX specifies the SVSM protocol/callid as input and the return code
+ *       as output.
+ */
+static __always_inline void svsm_issue_call(struct svsm_call *call, u8 *pending)
+{
+	register unsigned long rax asm("rax") = call->rax;
+	register unsigned long rcx asm("rcx") = call->rcx;
+	register unsigned long rdx asm("rdx") = call->rdx;
+	register unsigned long r8  asm("r8")  = call->r8;
+	register unsigned long r9  asm("r9")  = call->r9;
+
+	call->caa->call_pending = 1;
+
+	asm volatile("rep; vmmcall\n\t"
+		     : "+r" (rax), "+r" (rcx), "+r" (rdx), "+r" (r8), "+r" (r9)
+		     : : "memory");
+
+	*pending = xchg(&call->caa->call_pending, *pending);
+
+	call->rax_out = rax;
+	call->rcx_out = rcx;
+	call->rdx_out = rdx;
+	call->r8_out  = r8;
+	call->r9_out  = r9;
+}
+
+static int svsm_perform_msr_protocol(struct svsm_call *call)
+{
+	u8 pending = 0;
+	u64 val, resp;
+
+	/*
+	 * When using the MSR protocol, be sure to save and restore
+	 * the current MSR value.
+	 */
+	val = sev_es_rd_ghcb_msr();
+
+	sev_es_wr_ghcb_msr(GHCB_MSR_VMPL_REQ_LEVEL(0));
+
+	svsm_issue_call(call, &pending);
+
+	resp = sev_es_rd_ghcb_msr();
+
+	sev_es_wr_ghcb_msr(val);
+
+	if (pending)
+		return -EINVAL;
+
+	if (GHCB_RESP_CODE(resp) != GHCB_MSR_VMPL_RESP)
+		return -EINVAL;
+
+	if (GHCB_MSR_VMPL_RESP_VAL(resp))
+		return -EINVAL;
+
+	return svsm_process_result_codes(call);
+}
+
+static int svsm_perform_ghcb_protocol(struct ghcb *ghcb, struct svsm_call *call)
+{
+	struct es_em_ctxt ctxt;
+	u8 pending = 0;
+
+	vc_ghcb_invalidate(ghcb);
+
+	/*
+	 * Fill in protocol and format specifiers. This can be called very early
+	 * in the boot, so use rip-relative references as needed.
+	 */
+	ghcb->protocol_version = RIP_REL_REF(ghcb_version);
+	ghcb->ghcb_usage       = GHCB_DEFAULT_USAGE;
+
+	ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_SNP_RUN_VMPL);
+	ghcb_set_sw_exit_info_1(ghcb, 0);
+	ghcb_set_sw_exit_info_2(ghcb, 0);
+
+	sev_es_wr_ghcb_msr(__pa(ghcb));
+
+	svsm_issue_call(call, &pending);
+
+	if (pending)
+		return -EINVAL;
+
+	switch (verify_exception_info(ghcb, &ctxt)) {
+	case ES_OK:
+		break;
+	case ES_EXCEPTION:
+		vc_forward_exception(&ctxt);
+		fallthrough;
+	default:
+		return -EINVAL;
+	}
+
+	return svsm_process_result_codes(call);
+}
+
 static enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb,
 					  struct es_em_ctxt *ctxt,
 					  u64 exit_code, u64 exit_info_1,
@@ -1079,38 +1221,268 @@ static void __head setup_cpuid_table(const struct cc_blob_sev_info *cc_info)
 	}
 }
 
-static void pvalidate_pages(struct snp_psc_desc *desc)
+static inline void __pval_terminate(u64 pfn, bool action, unsigned int page_size,
+				    int ret, u64 svsm_ret)
+{
+	WARN(1, "PVALIDATE failure: pfn: 0x%llx, action: %u, size: %u, ret: %d, svsm_ret: 0x%llx\n",
+	     pfn, action, page_size, ret, svsm_ret);
+
+	sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PVALIDATE);
+}
+
+static void svsm_pval_terminate(struct svsm_pvalidate_call *pc, int ret, u64 svsm_ret)
+{
+	unsigned int page_size;
+	bool action;
+	u64 pfn;
+
+	pfn = pc->entry[pc->cur_index].pfn;
+	action = pc->entry[pc->cur_index].action;
+	page_size = pc->entry[pc->cur_index].page_size;
+
+	__pval_terminate(pfn, action, page_size, ret, svsm_ret);
+}
+
+static void svsm_pval_4k_page(unsigned long paddr, bool validate)
+{
+	struct svsm_pvalidate_call *pc;
+	struct svsm_call call = {};
+	unsigned long flags;
+	u64 pc_pa;
+	int ret;
+
+	/*
+	 * This can be called very early in the boot, use native functions in
+	 * order to avoid paravirt issues.
+	 */
+	flags = native_local_irq_save();
+
+	call.caa = svsm_get_caa();
+
+	pc = (struct svsm_pvalidate_call *)call.caa->svsm_buffer;
+	pc_pa = svsm_get_caa_pa() + offsetof(struct svsm_ca, svsm_buffer);
+
+	pc->num_entries = 1;
+	pc->cur_index   = 0;
+	pc->entry[0].page_size = RMP_PG_SIZE_4K;
+	pc->entry[0].action    = validate;
+	pc->entry[0].ignore_cf = 0;
+	pc->entry[0].pfn       = paddr >> PAGE_SHIFT;
+
+	/* Protocol 0, Call ID 1 */
+	call.rax = SVSM_CORE_CALL(SVSM_CORE_PVALIDATE);
+	call.rcx = pc_pa;
+
+	ret = svsm_perform_call_protocol(&call);
+	if (ret)
+		svsm_pval_terminate(pc, ret, call.rax_out);
+
+	native_local_irq_restore(flags);
+}
+
+static void pvalidate_4k_page(unsigned long vaddr, unsigned long paddr, bool validate)
+{
+	int ret;
+
+	/*
+	 * This can be called very early during boot, so use rIP-relative
+	 * references as needed.
+	 */
+	if (RIP_REL_REF(snp_vmpl)) {
+		svsm_pval_4k_page(paddr, validate);
+	} else {
+		ret = pvalidate(vaddr, RMP_PG_SIZE_4K, validate);
+		if (ret)
+			__pval_terminate(PHYS_PFN(paddr), validate, RMP_PG_SIZE_4K, ret, 0);
+	}
+}
+
+static void pval_pages(struct snp_psc_desc *desc)
 {
 	struct psc_entry *e;
 	unsigned long vaddr;
 	unsigned int size;
 	unsigned int i;
 	bool validate;
+	u64 pfn;
 	int rc;
 
 	for (i = 0; i <= desc->hdr.end_entry; i++) {
 		e = &desc->entries[i];
 
-		vaddr = (unsigned long)pfn_to_kaddr(e->gfn);
+		pfn = e->gfn;
+		vaddr = (unsigned long)pfn_to_kaddr(pfn);
 		size = e->pagesize ? RMP_PG_SIZE_2M : RMP_PG_SIZE_4K;
 		validate = e->operation == SNP_PAGE_STATE_PRIVATE;
 
 		rc = pvalidate(vaddr, size, validate);
+		if (!rc)
+			continue;
+
 		if (rc == PVALIDATE_FAIL_SIZEMISMATCH && size == RMP_PG_SIZE_2M) {
 			unsigned long vaddr_end = vaddr + PMD_SIZE;
 
-			for (; vaddr < vaddr_end; vaddr += PAGE_SIZE) {
+			for (; vaddr < vaddr_end; vaddr += PAGE_SIZE, pfn++) {
 				rc = pvalidate(vaddr, RMP_PG_SIZE_4K, validate);
 				if (rc)
-					break;
+					__pval_terminate(pfn, validate, RMP_PG_SIZE_4K, rc, 0);
 			}
+		} else {
+			__pval_terminate(pfn, validate, size, rc, 0);
 		}
+	}
+}
+
+static u64 svsm_build_ca_from_pfn_range(u64 pfn, u64 pfn_end, bool action,
+					struct svsm_pvalidate_call *pc)
+{
+	struct svsm_pvalidate_entry *pe;
+
+	/* Nothing in the CA yet */
+	pc->num_entries = 0;
+	pc->cur_index   = 0;
+
+	pe = &pc->entry[0];
+
+	while (pfn < pfn_end) {
+		pe->page_size = RMP_PG_SIZE_4K;
+		pe->action    = action;
+		pe->ignore_cf = 0;
+		pe->pfn       = pfn;
+
+		pe++;
+		pfn++;
+
+		pc->num_entries++;
+		if (pc->num_entries == SVSM_PVALIDATE_MAX_COUNT)
+			break;
+	}
+
+	return pfn;
+}
+
+static int svsm_build_ca_from_psc_desc(struct snp_psc_desc *desc, unsigned int desc_entry,
+				       struct svsm_pvalidate_call *pc)
+{
+	struct svsm_pvalidate_entry *pe;
+	struct psc_entry *e;
+
+	/* Nothing in the CA yet */
+	pc->num_entries = 0;
+	pc->cur_index   = 0;
+
+	pe = &pc->entry[0];
+	e  = &desc->entries[desc_entry];
+
+	while (desc_entry <= desc->hdr.end_entry) {
+		pe->page_size = e->pagesize ? RMP_PG_SIZE_2M : RMP_PG_SIZE_4K;
+		pe->action    = e->operation == SNP_PAGE_STATE_PRIVATE;
+		pe->ignore_cf = 0;
+		pe->pfn       = e->gfn;
+
+		pe++;
+		e++;
+
+		desc_entry++;
+		pc->num_entries++;
+		if (pc->num_entries == SVSM_PVALIDATE_MAX_COUNT)
+			break;
+	}
+
+	return desc_entry;
+}
+
+static void svsm_pval_pages(struct snp_psc_desc *desc)
+{
+	struct svsm_pvalidate_entry pv_4k[VMGEXIT_PSC_MAX_ENTRY];
+	unsigned int i, pv_4k_count = 0;
+	struct svsm_pvalidate_call *pc;
+	struct svsm_call call = {};
+	unsigned long flags;
+	bool action;
+	u64 pc_pa;
+	int ret;
+
+	/*
+	 * This can be called very early in the boot, use native functions in
+	 * order to avoid paravirt issues.
+	 */
+	flags = native_local_irq_save();
+
+	/*
+	 * The SVSM calling area (CA) can support processing 510 entries at a
+	 * time. Loop through the Page State Change descriptor until the CA is
+	 * full or the last entry in the descriptor is reached, at which time
+	 * the SVSM is invoked. This repeats until all entries in the descriptor
+	 * are processed.
+	 */
+	call.caa = svsm_get_caa();
+
+	pc = (struct svsm_pvalidate_call *)call.caa->svsm_buffer;
+	pc_pa = svsm_get_caa_pa() + offsetof(struct svsm_ca, svsm_buffer);
+
+	/* Protocol 0, Call ID 1 */
+	call.rax = SVSM_CORE_CALL(SVSM_CORE_PVALIDATE);
+	call.rcx = pc_pa;
+
+	for (i = 0; i <= desc->hdr.end_entry;) {
+		i = svsm_build_ca_from_psc_desc(desc, i, pc);
+
+		do {
+			ret = svsm_perform_call_protocol(&call);
+			if (!ret)
+				continue;
+
+			/*
+			 * Check if the entry failed because of an RMP mismatch (a
+			 * PVALIDATE at 2M was requested, but the page is mapped in
+			 * the RMP as 4K).
+			 */
 
-		if (rc) {
-			WARN(1, "Failed to validate address 0x%lx ret %d", vaddr, rc);
-			sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PVALIDATE);
+			if (call.rax_out == SVSM_PVALIDATE_FAIL_SIZEMISMATCH &&
+			    pc->entry[pc->cur_index].page_size == RMP_PG_SIZE_2M) {
+				/* Save this entry for post-processing at 4K */
+				pv_4k[pv_4k_count++] = pc->entry[pc->cur_index];
+
+				/* Skip to the next one unless at the end of the list */
+				pc->cur_index++;
+				if (pc->cur_index < pc->num_entries)
+					ret = -EAGAIN;
+				else
+					ret = 0;
+			}
+		} while (ret == -EAGAIN);
+
+		if (ret)
+			svsm_pval_terminate(pc, ret, call.rax_out);
+	}
+
+	/* Process any entries that failed to be validated at 2M and validate them at 4K */
+	for (i = 0; i < pv_4k_count; i++) {
+		u64 pfn, pfn_end;
+
+		action  = pv_4k[i].action;
+		pfn     = pv_4k[i].pfn;
+		pfn_end = pfn + 512;
+
+		while (pfn < pfn_end) {
+			pfn = svsm_build_ca_from_pfn_range(pfn, pfn_end, action, pc);
+
+			ret = svsm_perform_call_protocol(&call);
+			if (ret)
+				svsm_pval_terminate(pc, ret, call.rax_out);
 		}
 	}
+
+	native_local_irq_restore(flags);
+}
+
+static void pvalidate_pages(struct snp_psc_desc *desc)
+{
+	if (snp_vmpl)
+		svsm_pval_pages(desc);
+	else
+		pval_pages(desc);
 }
 
 static int vmgexit_psc(struct ghcb *ghcb, struct snp_psc_desc *desc)
@@ -1269,3 +1641,77 @@ static enum es_result vc_check_opcode_bytes(struct es_em_ctxt *ctxt,
 
 	return ES_UNSUPPORTED;
 }
+
+/*
+ * Maintain the GPA of the SVSM Calling Area (CA) in order to utilize the SVSM
+ * services needed when not running in VMPL0.
+ */
+static bool __head svsm_setup_ca(const struct cc_blob_sev_info *cc_info)
+{
+	struct snp_secrets_page *secrets_page;
+	struct snp_cpuid_table *cpuid_table;
+	unsigned int i;
+	u64 caa;
+
+	BUILD_BUG_ON(sizeof(*secrets_page) != PAGE_SIZE);
+
+	/*
+	 * Check if running at VMPL0.
+	 *
+	 * Use RMPADJUST (see the rmpadjust() function for a description of what
+	 * the instruction does) to update the VMPL1 permissions of a page. If
+	 * the guest is running at VMPL0, this will succeed and implies there is
+	 * no SVSM. If the guest is running at any other VMPL, this will fail.
+	 * Linux SNP guests only ever run at a single VMPL level so permission mask
+	 * changes of a lesser-privileged VMPL are a don't-care.
+	 *
+	 * Use a rip-relative reference to obtain the proper address, since this
+	 * routine is running identity mapped when called, both by the decompressor
+	 * code and the early kernel code.
+	 */
+	if (!rmpadjust((unsigned long)&RIP_REL_REF(boot_ghcb_page), RMP_PG_SIZE_4K, 1))
+		return false;
+
+	/*
+	 * Not running at VMPL0, ensure everything has been properly supplied
+	 * for running under an SVSM.
+	 */
+	if (!cc_info || !cc_info->secrets_phys || cc_info->secrets_len != PAGE_SIZE)
+		sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_SECRETS_PAGE);
+
+	secrets_page = (struct snp_secrets_page *)cc_info->secrets_phys;
+	if (!secrets_page->svsm_size)
+		sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_NO_SVSM);
+
+	if (!secrets_page->svsm_guest_vmpl)
+		sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_SVSM_VMPL0);
+
+	RIP_REL_REF(snp_vmpl) = secrets_page->svsm_guest_vmpl;
+
+	caa = secrets_page->svsm_caa;
+
+	/*
+	 * An open-coded PAGE_ALIGNED() in order to avoid including
+	 * kernel-proper headers into the decompressor.
+	 */
+	if (caa & (PAGE_SIZE - 1))
+		sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_SVSM_CAA);
+
+	/*
+	 * The CA is identity mapped when this routine is called, both by the
+	 * decompressor code and the early kernel code.
+	 */
+	RIP_REL_REF(boot_svsm_caa) = (struct svsm_ca *)caa;
+	RIP_REL_REF(boot_svsm_caa_pa) = caa;
+
+	/* Advertise the SVSM presence via CPUID. */
+	cpuid_table = (struct snp_cpuid_table *)snp_cpuid_get_table();
+	for (i = 0; i < cpuid_table->count; i++) {
+		struct snp_cpuid_fn *fn = &cpuid_table->fn[i];
+
+		if (fn->eax_in == 0x8000001f)
+			fn->eax |= BIT(28);
+	}
+
+	return true;
+}
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index a1dd81027c2d..b51e88d01b21 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -446,6 +446,7 @@
 #define X86_FEATURE_V_TSC_AUX		(19*32+ 9) /* Virtual TSC_AUX */
 #define X86_FEATURE_SME_COHERENT	(19*32+10) /* AMD hardware-enforced cache coherency */
 #define X86_FEATURE_DEBUG_SWAP		(19*32+14) /* "debug_swap" AMD SEV-ES full debug state swap support */
+#define X86_FEATURE_SVSM		(19*32+28) /* "svsm" SVSM present */
 
 /* AMD-defined Extended Feature 2 EAX, CPUID level 0x80000021 (EAX), word 20 */
 #define X86_FEATURE_NO_NESTED_DATA_BP	(20*32+ 0) /* No Nested Data Breakpoints */
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index 8c5ae649d2df..cf7fc2b8e3ce 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -54,6 +54,26 @@ static __always_inline void native_halt(void)
 	asm volatile("hlt": : :"memory");
 }
 
+static __always_inline int native_irqs_disabled_flags(unsigned long flags)
+{
+	return !(flags & X86_EFLAGS_IF);
+}
+
+static __always_inline unsigned long native_local_irq_save(void)
+{
+	unsigned long flags = native_save_fl();
+
+	native_irq_disable();
+
+	return flags;
+}
+
+static __always_inline void native_local_irq_restore(unsigned long flags)
+{
+	if (!native_irqs_disabled_flags(flags))
+		native_irq_enable();
+}
+
 #endif
 
 #ifdef CONFIG_PARAVIRT_XXL
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 3cb8dd6311c3..01342963011e 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -660,6 +660,8 @@
 #define MSR_AMD64_RMP_BASE		0xc0010132
 #define MSR_AMD64_RMP_END		0xc0010133
 
+#define MSR_SVSM_CAA			0xc001f000
+
 /* AMD Collaborative Processor Performance Control MSRs */
 #define MSR_AMD_CPPC_CAP1		0xc00102b0
 #define MSR_AMD_CPPC_ENABLE		0xc00102b1
diff --git a/arch/x86/include/asm/sev-common.h b/arch/x86/include/asm/sev-common.h
index 5a8246dd532f..e90d403f2068 100644
--- a/arch/x86/include/asm/sev-common.h
+++ b/arch/x86/include/asm/sev-common.h
@@ -98,6 +98,19 @@ enum psc_op {
 	/* GHCBData[63:32] */				\
 	(((u64)(val) & GENMASK_ULL(63, 32)) >> 32)
 
+/* GHCB Run at VMPL Request/Response */
+#define GHCB_MSR_VMPL_REQ		0x016
+#define GHCB_MSR_VMPL_REQ_LEVEL(v)			\
+	/* GHCBData[39:32] */				\
+	(((u64)(v) & GENMASK_ULL(7, 0) << 32) |		\
+	/* GHCBDdata[11:0] */				\
+	GHCB_MSR_VMPL_REQ)
+
+#define GHCB_MSR_VMPL_RESP		0x017
+#define GHCB_MSR_VMPL_RESP_VAL(v)			\
+	/* GHCBData[63:32] */				\
+	(((u64)(v) & GENMASK_ULL(63, 32)) >> 32)
+
 /* GHCB Hypervisor Feature Request/Response */
 #define GHCB_MSR_HV_FT_REQ		0x080
 #define GHCB_MSR_HV_FT_RESP		0x081
@@ -109,6 +122,7 @@ enum psc_op {
 
 #define GHCB_HV_FT_SNP			BIT_ULL(0)
 #define GHCB_HV_FT_SNP_AP_CREATION	BIT_ULL(1)
+#define GHCB_HV_FT_SNP_MULTI_VMPL	BIT_ULL(5)
 
 /*
  * SNP Page State Change NAE event
@@ -163,6 +177,10 @@ struct snp_psc_desc {
 #define GHCB_TERM_NOT_VMPL0		3	/* SNP guest is not running at VMPL-0 */
 #define GHCB_TERM_CPUID			4	/* CPUID-validation failure */
 #define GHCB_TERM_CPUID_HV		5	/* CPUID failure during hypervisor fallback */
+#define GHCB_TERM_SECRETS_PAGE		6	/* Secrets page failure */
+#define GHCB_TERM_NO_SVSM		7	/* SVSM is not advertised in the secrets page */
+#define GHCB_TERM_SVSM_VMPL0		8	/* SVSM is present but has set VMPL to 0 */
+#define GHCB_TERM_SVSM_CAA		9	/* SVSM is present but CAA is not page aligned */
 
 #define GHCB_RESP_CODE(v)		((v) & GHCB_MSR_INFO_MASK)
 
diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h
index ca20cc4e5826..ac5886ce252e 100644
--- a/arch/x86/include/asm/sev.h
+++ b/arch/x86/include/asm/sev.h
@@ -152,10 +152,119 @@ struct snp_secrets_page {
 	u8 vmpck2[VMPCK_KEY_LEN];
 	u8 vmpck3[VMPCK_KEY_LEN];
 	struct secrets_os_area os_area;
-	u8 rsvd3[3840];
+
+	u8 vmsa_tweak_bitmap[64];
+
+	/* SVSM fields */
+	u64 svsm_base;
+	u64 svsm_size;
+	u64 svsm_caa;
+	u32 svsm_max_version;
+	u8 svsm_guest_vmpl;
+	u8 rsvd3[3];
+
+	/* Remainder of page */
+	u8 rsvd4[3744];
 } __packed;
 
+/*
+ * The SVSM Calling Area (CA) related structures.
+ */
+struct svsm_ca {
+	u8 call_pending;
+	u8 mem_available;
+	u8 rsvd1[6];
+
+	u8 svsm_buffer[PAGE_SIZE - 8];
+};
+
+#define SVSM_SUCCESS				0
+#define SVSM_ERR_INCOMPLETE			0x80000000
+#define SVSM_ERR_UNSUPPORTED_PROTOCOL		0x80000001
+#define SVSM_ERR_UNSUPPORTED_CALL		0x80000002
+#define SVSM_ERR_INVALID_ADDRESS		0x80000003
+#define SVSM_ERR_INVALID_FORMAT			0x80000004
+#define SVSM_ERR_INVALID_PARAMETER		0x80000005
+#define SVSM_ERR_INVALID_REQUEST		0x80000006
+#define SVSM_ERR_BUSY				0x80000007
+#define SVSM_PVALIDATE_FAIL_SIZEMISMATCH	0x80001006
+
+/*
+ * The SVSM PVALIDATE related structures
+ */
+struct svsm_pvalidate_entry {
+	u64 page_size		: 2,
+	    action		: 1,
+	    ignore_cf		: 1,
+	    rsvd		: 8,
+	    pfn			: 52;
+};
+
+struct svsm_pvalidate_call {
+	u16 num_entries;
+	u16 cur_index;
+
+	u8 rsvd1[4];
+
+	struct svsm_pvalidate_entry entry[];
+};
+
+#define SVSM_PVALIDATE_MAX_COUNT	((sizeof_field(struct svsm_ca, svsm_buffer) -		\
+					  offsetof(struct svsm_pvalidate_call, entry)) /	\
+					 sizeof(struct svsm_pvalidate_entry))
+
+/*
+ * The SVSM Attestation related structures
+ */
+struct svsm_loc_entry {
+	u64 pa;
+	u32 len;
+	u8 rsvd[4];
+};
+
+struct svsm_attest_call {
+	struct svsm_loc_entry report_buf;
+	struct svsm_loc_entry nonce;
+	struct svsm_loc_entry manifest_buf;
+	struct svsm_loc_entry certificates_buf;
+
+	/* For attesting a single service */
+	u8 service_guid[16];
+	u32 service_manifest_ver;
+	u8 rsvd[4];
+};
+
+/*
+ * SVSM protocol structure
+ */
+struct svsm_call {
+	struct svsm_ca *caa;
+	u64 rax;
+	u64 rcx;
+	u64 rdx;
+	u64 r8;
+	u64 r9;
+	u64 rax_out;
+	u64 rcx_out;
+	u64 rdx_out;
+	u64 r8_out;
+	u64 r9_out;
+};
+
+#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
+
+#define SVSM_ATTEST_CALL(x)		((1ULL << 32) | (x))
+#define SVSM_ATTEST_SERVICES		0
+#define SVSM_ATTEST_SINGLE_SERVICE	1
+
 #ifdef CONFIG_AMD_MEM_ENCRYPT
+
+extern u8 snp_vmpl;
+
 extern void __sev_es_ist_enter(struct pt_regs *regs);
 extern void __sev_es_ist_exit(void);
 static __always_inline void sev_es_ist_enter(struct pt_regs *regs)
@@ -181,6 +290,14 @@ static __always_inline void sev_es_nmi_complete(void)
 extern int __init sev_es_efi_map_ghcbs(pgd_t *pgd);
 extern void sev_enable(struct boot_params *bp);
 
+/*
+ * RMPADJUST modifies the RMP permissions of a page of a lesser-
+ * privileged (numerically higher) VMPL.
+ *
+ * If the guest is running at a higher-privilege than the privilege
+ * level the instruction is targeting, the instruction will succeed,
+ * otherwise, it will fail.
+ */
 static inline int rmpadjust(unsigned long vaddr, bool rmp_psize, unsigned long attrs)
 {
 	int rc;
@@ -225,11 +342,16 @@ bool snp_init(struct boot_params *bp);
 void __noreturn snp_abort(void);
 void snp_dmi_setup(void);
 int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, struct snp_guest_request_ioctl *rio);
+int snp_issue_svsm_attest_req(u64 call_id, struct svsm_call *call, struct svsm_attest_call *input);
 void snp_accept_memory(phys_addr_t start, phys_addr_t end);
 u64 snp_get_unsupported_features(u64 status);
 u64 sev_get_status(void);
 void sev_show_status(void);
-#else
+void snp_update_svsm_ca(void);
+
+#else	/* !CONFIG_AMD_MEM_ENCRYPT */
+
+#define snp_vmpl 0
 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; }
@@ -253,12 +375,17 @@ static inline int snp_issue_guest_request(u64 exit_code, struct snp_req_data *in
 {
 	return -ENOTTY;
 }
-
+static inline int snp_issue_svsm_attest_req(u64 call_id, struct svsm_call *call, struct svsm_attest_call *input)
+{
+	return -ENOTTY;
+}
 static inline void snp_accept_memory(phys_addr_t start, phys_addr_t end) { }
 static inline u64 snp_get_unsupported_features(u64 status) { return 0; }
 static inline u64 sev_get_status(void) { return 0; }
 static inline void sev_show_status(void) { }
-#endif
+static inline void snp_update_svsm_ca(void) { }
+
+#endif	/* CONFIG_AMD_MEM_ENCRYPT */
 
 #ifdef CONFIG_KVM_AMD_SEV
 bool snp_probe_rmptable_info(void);
diff --git a/arch/x86/include/uapi/asm/svm.h b/arch/x86/include/uapi/asm/svm.h
index 80e1df482337..1814b413fd57 100644
--- a/arch/x86/include/uapi/asm/svm.h
+++ b/arch/x86/include/uapi/asm/svm.h
@@ -115,6 +115,7 @@
 #define SVM_VMGEXIT_AP_CREATE_ON_INIT		0
 #define SVM_VMGEXIT_AP_CREATE			1
 #define SVM_VMGEXIT_AP_DESTROY			2
+#define SVM_VMGEXIT_SNP_RUN_VMPL		0x80000018
 #define SVM_VMGEXIT_HV_FEATURES			0x8000fffd
 #define SVM_VMGEXIT_TERM_REQUEST		0x8000fffe
 #define SVM_VMGEXIT_TERM_REASON(reason_set, reason_code)	\
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 20a0dd51700a..a847180836e4 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -17,7 +17,6 @@ CFLAGS_REMOVE_ftrace.o = -pg
 CFLAGS_REMOVE_early_printk.o = -pg
 CFLAGS_REMOVE_head64.o = -pg
 CFLAGS_REMOVE_head32.o = -pg
-CFLAGS_REMOVE_sev.o = -pg
 CFLAGS_REMOVE_rethook.o = -pg
 endif
 
@@ -26,19 +25,16 @@ KASAN_SANITIZE_dumpstack.o				:= n
 KASAN_SANITIZE_dumpstack_$(BITS).o			:= n
 KASAN_SANITIZE_stacktrace.o				:= n
 KASAN_SANITIZE_paravirt.o				:= n
-KASAN_SANITIZE_sev.o					:= n
 
 # With some compiler versions the generated code results in boot hangs, caused
 # by several compilation units. To be safe, disable all instrumentation.
 KCSAN_SANITIZE := n
 KMSAN_SANITIZE_head$(BITS).o				:= n
 KMSAN_SANITIZE_nmi.o					:= n
-KMSAN_SANITIZE_sev.o					:= n
 
 # If instrumentation of the following files is enabled, boot hangs during
 # first second.
 KCOV_INSTRUMENT_head$(BITS).o				:= n
-KCOV_INSTRUMENT_sev.o					:= n
 
 CFLAGS_irq.o := -I $(src)/../include/asm/trace
 
@@ -142,8 +138,6 @@ obj-$(CONFIG_UNWINDER_ORC)		+= unwind_orc.o
 obj-$(CONFIG_UNWINDER_FRAME_POINTER)	+= unwind_frame.o
 obj-$(CONFIG_UNWINDER_GUESS)		+= unwind_guess.o
 
-obj-$(CONFIG_AMD_MEM_ENCRYPT)		+= sev.o
-
 obj-$(CONFIG_CFI_CLANG)			+= cfi.o
 
 obj-$(CONFIG_CALL_THUNKS)		+= callthunks.o
diff --git a/arch/x86/mm/mem_encrypt_amd.c b/arch/x86/mm/mem_encrypt_amd.c
index e7b67519ddb5..86a476a426c2 100644
--- a/arch/x86/mm/mem_encrypt_amd.c
+++ b/arch/x86/mm/mem_encrypt_amd.c
@@ -2,7 +2,7 @@
 /*
  * AMD Memory Encryption Support
  *
- * Copyright (C) 2016 Advanced Micro Devices, Inc.
+ * Copyright (C) 2016-2024 Advanced Micro Devices, Inc.
  *
  * Author: Tom Lendacky <thomas.lendacky@amd.com>
  */
@@ -510,6 +510,12 @@ void __init sme_early_init(void)
 		 */
 		x86_init.resources.dmi_setup = snp_dmi_setup;
 	}
+
+	/*
+	 * Switch the SVSM CA mapping (if active) from identity mapped to
+	 * kernel mapped.
+	 */
+	snp_update_svsm_ca();
 }
 
 void __init mem_encrypt_free_decrypted_mem(void)
diff --git a/arch/x86/virt/svm/sev.c b/arch/x86/virt/svm/sev.c
index 0ae10535c699..0ce17766c0e5 100644
--- a/arch/x86/virt/svm/sev.c
+++ b/arch/x86/virt/svm/sev.c
@@ -120,7 +120,7 @@ static __init void snp_enable(void *arg)
 
 bool snp_probe_rmptable_info(void)
 {
-	u64 max_rmp_pfn, calc_rmp_sz, rmp_sz, rmp_base, rmp_end;
+	u64 rmp_sz, rmp_base, rmp_end;
 
 	rdmsrl(MSR_AMD64_RMP_BASE, rmp_base);
 	rdmsrl(MSR_AMD64_RMP_END, rmp_end);
@@ -137,28 +137,11 @@ bool snp_probe_rmptable_info(void)
 
 	rmp_sz = rmp_end - rmp_base + 1;
 
-	/*
-	 * Calculate the amount the memory that must be reserved by the BIOS to
-	 * address the whole RAM, including the bookkeeping area. The RMP itself
-	 * must also be covered.
-	 */
-	max_rmp_pfn = max_pfn;
-	if (PHYS_PFN(rmp_end) > max_pfn)
-		max_rmp_pfn = PHYS_PFN(rmp_end);
-
-	calc_rmp_sz = (max_rmp_pfn << 4) + RMPTABLE_CPU_BOOKKEEPING_SZ;
-
-	if (calc_rmp_sz > rmp_sz) {
-		pr_err("Memory reserved for the RMP table does not cover full system RAM (expected 0x%llx got 0x%llx)\n",
-		       calc_rmp_sz, rmp_sz);
-		return false;
-	}
-
 	probed_rmp_base = rmp_base;
 	probed_rmp_size = rmp_sz;
 
 	pr_info("RMP table physical range [0x%016llx - 0x%016llx]\n",
-		probed_rmp_base, probed_rmp_base + probed_rmp_size - 1);
+		rmp_base, rmp_end);
 
 	return true;
 }
@@ -206,9 +189,8 @@ void __init snp_fixup_e820_tables(void)
  */
 static int __init snp_rmptable_init(void)
 {
+	u64 max_rmp_pfn, calc_rmp_sz, rmptable_size, rmp_end, val;
 	void *rmptable_start;
-	u64 rmptable_size;
-	u64 val;
 
 	if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP))
 		return 0;
@@ -219,10 +201,28 @@ static int __init snp_rmptable_init(void)
 	if (!probed_rmp_size)
 		goto nosnp;
 
+	rmp_end = probed_rmp_base + probed_rmp_size - 1;
+
+	/*
+	 * Calculate the amount the memory that must be reserved by the BIOS to
+	 * address the whole RAM, including the bookkeeping area. The RMP itself
+	 * must also be covered.
+	 */
+	max_rmp_pfn = max_pfn;
+	if (PFN_UP(rmp_end) > max_pfn)
+		max_rmp_pfn = PFN_UP(rmp_end);
+
+	calc_rmp_sz = (max_rmp_pfn << 4) + RMPTABLE_CPU_BOOKKEEPING_SZ;
+	if (calc_rmp_sz > probed_rmp_size) {
+		pr_err("Memory reserved for the RMP table does not cover full system RAM (expected 0x%llx got 0x%llx)\n",
+		       calc_rmp_sz, probed_rmp_size);
+		goto nosnp;
+	}
+
 	rmptable_start = memremap(probed_rmp_base, probed_rmp_size, MEMREMAP_WB);
 	if (!rmptable_start) {
 		pr_err("Failed to map RMP table\n");
-		return 1;
+		goto nosnp;
 	}
 
 	/*