[PATCH v1 00/26] Add AMD Secure Nested Paging (SEV-SNP) Initialization Support

@@ -90,6 +90,7 @@ extern bool handle_vc_boot_ghcb(struct pt_regs *regs);
 /* RMP page size */
 #define RMP_PG_SIZE_4K			0
 #define RMP_PG_SIZE_2M			1
+#define RMP_TO_PG_LEVEL(level)		(((level) == RMP_PG_SIZE_4K) ? PG_LEVEL_4K : PG_LEVEL_2M)
 
 #define RMPADJUST_VMSA_PAGE_BIT		BIT(16)
 

@@ -245,8 +246,10 @@ static inline u64 sev_get_status(void) { return 0; }
 
 #ifdef CONFIG_KVM_AMD_SEV
 bool snp_probe_rmptable_info(void);
+int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level);
 #else
 static inline bool snp_probe_rmptable_info(void) { return false; }
+static inline int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level) { return -ENODEV; }
 #endif
 
 #endif

@@ -53,6 +53,9 @@ struct rmpentry {
  */
 #define RMPTABLE_CPU_BOOKKEEPING_SZ	0x4000
 
+/* Mask to apply to a PFN to get the first PFN of a 2MB page */
+#define PFN_PMD_MASK	GENMASK_ULL(63, PMD_SHIFT - PAGE_SHIFT)
+
 static u64 probed_rmp_base, probed_rmp_size;
 static struct rmpentry *rmptable __ro_after_init;
 static u64 rmptable_max_pfn __ro_after_init;

@@ -217,3 +220,49 @@ static int __init snp_rmptable_init(void)
  * This must be called after the IOMMU has been initialized.
  */
 device_initcall(snp_rmptable_init);
+
+static struct rmpentry *get_rmpentry(u64 pfn)
+{
+	if (WARN_ON_ONCE(pfn > rmptable_max_pfn))
+		return ERR_PTR(-EFAULT);
+
+	return &rmptable[pfn];
+}
+
+static struct rmpentry *__snp_lookup_rmpentry(u64 pfn, int *level)
+{
+	struct rmpentry *large_entry, *entry;
+
+	if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP))
+		return ERR_PTR(-ENODEV);
+
+	entry = get_rmpentry(pfn);
+	if (IS_ERR(entry))
+		return entry;
+
+	/*
+	 * Find the authoritative RMP entry for a PFN. This can be either a 4K
+	 * RMP entry or a special large RMP entry that is authoritative for a
+	 * whole 2M area.
+	 */
+	large_entry = get_rmpentry(pfn & PFN_PMD_MASK);
+	if (IS_ERR(large_entry))
+		return large_entry;
+
+	*level = RMP_TO_PG_LEVEL(large_entry->pagesize);
+
+	return entry;
+}
+
+int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level)
+{
+	struct rmpentry *e;
+
+	e = __snp_lookup_rmpentry(pfn, level);
+	if (IS_ERR(e))
+		return PTR_ERR(e);
+
+	*assigned = !!e->assigned;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(snp_lookup_rmpentry);

@@ -247,9 +247,11 @@ static inline u64 sev_get_status(void) { return 0; }
 #ifdef CONFIG_KVM_AMD_SEV
 bool snp_probe_rmptable_info(void);
 int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level);
+void snp_dump_hva_rmpentry(unsigned long address);
 #else
 static inline bool snp_probe_rmptable_info(void) { return false; }
 static inline int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level) { return -ENODEV; }
+static inline void snp_dump_hva_rmpentry(unsigned long address) {}
 #endif
 
 #endif

@@ -266,3 +266,80 @@ int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level)
 	return 0;
 }
 EXPORT_SYMBOL_GPL(snp_lookup_rmpentry);
+
+/*
+ * Dump the raw RMP entry for a particular PFN. These bits are documented in the
+ * PPR for a particular CPU model and provide useful information about how a
+ * particular PFN is being utilized by the kernel/firmware at the time certain
+ * unexpected events occur, such as RMP faults.
+ */
+static void dump_rmpentry(u64 pfn)
+{
+	u64 pfn_current, pfn_end;
+	struct rmpentry *e;
+	u64 *e_data;
+	int level;
+
+	e = __snp_lookup_rmpentry(pfn, &level);
+	if (IS_ERR(e)) {
+		pr_info("Failed to read RMP entry for PFN 0x%llx, error %ld\n",
+			pfn, PTR_ERR(e));
+		return;
+	}
+
+	e_data = (u64 *)e;
+	if (e->assigned) {
+		pr_info("RMP entry for PFN 0x%llx: [high=0x%016llx low=0x%016llx]\n",
+			pfn, e_data[1], e_data[0]);
+		return;
+	}
+
+	/*
+	 * If the RMP entry for a particular PFN is not in an assigned state,
+	 * then it is sometimes useful to get an idea of whether or not any RMP
+	 * entries for other PFNs within the same 2MB region are assigned, since
+	 * those too can affect the ability to access a particular PFN in
+	 * certain situations, such as when the PFN is being accessed via a 2MB
+	 * mapping in the host page table.
+	 */
+	pfn_current = ALIGN(pfn, PTRS_PER_PMD);
+	pfn_end = pfn_current + PTRS_PER_PMD;
+
+	while (pfn_current < pfn_end) {
+		e = __snp_lookup_rmpentry(pfn_current, &level);
+		if (IS_ERR(e)) {
+			pfn_current++;
+			continue;
+		}
+
+		e_data = (u64 *)e;
+		if (e_data[0] || e_data[1]) {
+			pr_info("No assigned RMP entry for PFN 0x%llx, but the 2MB region contains populated RMP entries, e.g.: PFN 0x%llx: [high=0x%016llx low=0x%016llx]\n",
+				pfn, pfn_current, e_data[1], e_data[0]);
+			return;
+		}
+		pfn_current++;
+	}
+
+	pr_info("No populated RMP entries in the 2MB region containing PFN 0x%llx\n",
+		pfn);
+}
+
+void snp_dump_hva_rmpentry(unsigned long hva)
+{
+	unsigned int level;
+	pgd_t *pgd;
+	pte_t *pte;
+
+	pgd = __va(read_cr3_pa());
+	pgd += pgd_index(hva);
+	pte = lookup_address_in_pgd(pgd, hva, &level);
+
+	if (!pte) {
+		pr_info("Can't dump RMP entry for HVA %lx: no PTE/PFN found\n", hva);
+		return;
+	}
+
+	dump_rmpentry(pte_pfn(*pte));
+}
+EXPORT_SYMBOL_GPL(snp_dump_hva_rmpentry);

@@ -2,6 +2,8 @@
 #ifndef _ASM_X86_TRAP_PF_H
 #define _ASM_X86_TRAP_PF_H
 
+#include <linux/bits.h>  /* BIT() macro */
+
 /*
  * Page fault error code bits:
  *

@@ -13,16 +15,18 @@
  *   bit 5 ==				1: protection keys block access
  *   bit 6 ==				1: shadow stack access fault
  *   bit 15 ==				1: SGX MMU page-fault
+ *   bit 31 ==				1: fault was due to RMP violation
  */
 enum x86_pf_error_code {
-	X86_PF_PROT	=		1 << 0,
-	X86_PF_WRITE	=		1 << 1,
-	X86_PF_USER	=		1 << 2,
-	X86_PF_RSVD	=		1 << 3,
-	X86_PF_INSTR	=		1 << 4,
-	X86_PF_PK	=		1 << 5,
-	X86_PF_SHSTK	=		1 << 6,
-	X86_PF_SGX	=		1 << 15,
+	X86_PF_PROT	=		BIT(0),
+	X86_PF_WRITE	=		BIT(1),
+	X86_PF_USER	=		BIT(2),
+	X86_PF_RSVD	=		BIT(3),
+	X86_PF_INSTR	=		BIT(4),
+	X86_PF_PK	=		BIT(5),
+	X86_PF_SHSTK	=		BIT(6),
+	X86_PF_SGX	=		BIT(15),
+	X86_PF_RMP	=		BIT(31),
 };
 
 #endif /* _ASM_X86_TRAP_PF_H */

@@ -547,6 +547,7 @@ show_fault_oops(struct pt_regs *regs, unsigned long error_code, unsigned long ad
 		 !(error_code & X86_PF_PROT) ? "not-present page" :
 		 (error_code & X86_PF_RSVD)  ? "reserved bit violation" :
 		 (error_code & X86_PF_PK)    ? "protection keys violation" :
+		 (error_code & X86_PF_RMP)   ? "RMP violation" :
 					       "permissions violation");
 
 	if (!(error_code & X86_PF_USER) && user_mode(regs)) {

@@ -34,6 +34,7 @@
 #include <asm/kvm_para.h>		/* kvm_handle_async_pf		*/
 #include <asm/vdso.h>			/* fixup_vdso_exception()	*/
 #include <asm/irq_stack.h>
+#include <asm/sev.h>			/* snp_dump_hva_rmpentry()	*/
 
 #define CREATE_TRACE_POINTS
 #include <asm/trace/exceptions.h>

@@ -580,6 +581,9 @@ show_fault_oops(struct pt_regs *regs, unsigned long error_code, unsigned long ad
 	}
 
 	dump_pagetable(address);
+
+	if (error_code & X86_PF_RMP)
+		snp_dump_hva_rmpentry(address);
 }
 
 static noinline void

@@ -87,10 +87,23 @@ extern bool handle_vc_boot_ghcb(struct pt_regs *regs);
 /* Software defined (when rFlags.CF = 1) */
 #define PVALIDATE_FAIL_NOUPDATE		255
 
+/* RMUPDATE detected 4K page and 2MB page overlap. */
+#define RMPUPDATE_FAIL_OVERLAP		4
+
 /* RMP page size */
 #define RMP_PG_SIZE_4K			0
 #define RMP_PG_SIZE_2M			1
 #define RMP_TO_PG_LEVEL(level)		(((level) == RMP_PG_SIZE_4K) ? PG_LEVEL_4K : PG_LEVEL_2M)
+#define PG_LEVEL_TO_RMP(level)		(((level) == PG_LEVEL_4K) ? RMP_PG_SIZE_4K : RMP_PG_SIZE_2M)
+
+struct rmp_state {
+	u64 gpa;
+	u8 assigned;
+	u8 pagesize;
+	u8 immutable;
+	u8 rsvd;
+	u32 asid;
+} __packed;
 
 #define RMPADJUST_VMSA_PAGE_BIT		BIT(16)
 

@@ -248,10 +261,20 @@ static inline u64 sev_get_status(void) { return 0; }
 bool snp_probe_rmptable_info(void);
 int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level);
 void snp_dump_hva_rmpentry(unsigned long address);
+int psmash(u64 pfn);
+int rmp_make_private(u64 pfn, u64 gpa, enum pg_level level, int asid, bool immutable);
+int rmp_make_shared(u64 pfn, enum pg_level level);
 #else
 static inline bool snp_probe_rmptable_info(void) { return false; }
 static inline int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level) { return -ENODEV; }
 static inline void snp_dump_hva_rmpentry(unsigned long address) {}
+static inline int psmash(u64 pfn) { return -ENODEV; }
+static inline int rmp_make_private(u64 pfn, u64 gpa, enum pg_level level, int asid,
+				   bool immutable)
+{
+	return -ENODEV;
+}
+static inline int rmp_make_shared(u64 pfn, enum pg_level level) { return -ENODEV; }
 #endif
 
 #endif

@@ -343,3 +343,82 @@ void snp_dump_hva_rmpentry(unsigned long hva)
 	dump_rmpentry(pte_pfn(*pte));
 }
 EXPORT_SYMBOL_GPL(snp_dump_hva_rmpentry);
+
+/*
+ * PSMASH a 2MB aligned page into 4K pages in the RMP table while preserving the
+ * Validated bit.
+ */
+int psmash(u64 pfn)
+{
+	unsigned long paddr = pfn << PAGE_SHIFT;
+	int ret;
+
+	if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP))
+		return -ENODEV;
+
+	if (!pfn_valid(pfn))
+		return -EINVAL;
+
+	/* Binutils version 2.36 supports the PSMASH mnemonic. */
+	asm volatile(".byte 0xF3, 0x0F, 0x01, 0xFF"
+		      : "=a" (ret)
+		      : "a" (paddr)
+		      : "memory", "cc");
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(psmash);
+
+static int rmpupdate(u64 pfn, struct rmp_state *state)
+{
+	unsigned long paddr = pfn << PAGE_SHIFT;
+	int ret;
+
+	if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP))
+		return -ENODEV;
+
+	do {
+		/* Binutils version 2.36 supports the RMPUPDATE mnemonic. */
+		asm volatile(".byte 0xF2, 0x0F, 0x01, 0xFE"
+			     : "=a" (ret)
+			     : "a" (paddr), "c" ((unsigned long)state)
+			     : "memory", "cc");
+	} while (ret == RMPUPDATE_FAIL_OVERLAP);
+
+	if (ret) {
+		pr_err("RMPUPDATE failed for PFN %llx, ret: %d\n", pfn, ret);
+		dump_rmpentry(pfn);
+		dump_stack();
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
+/* Transition a page to guest-owned/private state in the RMP table. */
+int rmp_make_private(u64 pfn, u64 gpa, enum pg_level level, int asid, bool immutable)
+{
+	struct rmp_state state;
+
+	memset(&state, 0, sizeof(state));
+	state.assigned = 1;
+	state.asid = asid;
+	state.immutable = immutable;
+	state.gpa = gpa;
+	state.pagesize = PG_LEVEL_TO_RMP(level);
+
+	return rmpupdate(pfn, &state);
+}
+EXPORT_SYMBOL_GPL(rmp_make_private);
+
+/* Transition a page to hypervisor-owned/shared state in the RMP table. */
+int rmp_make_shared(u64 pfn, enum pg_level level)
+{
+	struct rmp_state state;
+
+	memset(&state, 0, sizeof(state));
+	state.pagesize = PG_LEVEL_TO_RMP(level);
+
+	return rmpupdate(pfn, &state);
+}
+EXPORT_SYMBOL_GPL(rmp_make_shared);

@@ -369,14 +369,64 @@ int psmash(u64 pfn)
 }
 EXPORT_SYMBOL_GPL(psmash);
 
+static int restore_direct_map(u64 pfn, int npages)
+{
+	int i, ret = 0;
+
+	for (i = 0; i < npages; i++) {
+		ret = set_direct_map_default_noflush(pfn_to_page(pfn + i));
+		if (ret)
+			break;
+	}
+
+	if (ret)
+		pr_warn("Failed to restore direct map for pfn 0x%llx, ret: %d\n",
+			pfn + i, ret);
+
+	return ret;
+}
+
+static int invalidate_direct_map(u64 pfn, int npages)
+{
+	int i, ret = 0;
+
+	for (i = 0; i < npages; i++) {
+		ret = set_direct_map_invalid_noflush(pfn_to_page(pfn + i));
+		if (ret)
+			break;
+	}
+
+	if (ret) {
+		pr_warn("Failed to invalidate direct map for pfn 0x%llx, ret: %d\n",
+			pfn + i, ret);
+		restore_direct_map(pfn, i);
+	}
+
+	return ret;
+}
+
 static int rmpupdate(u64 pfn, struct rmp_state *state)
 {
 	unsigned long paddr = pfn << PAGE_SHIFT;
-	int ret;
+	int ret, level, npages;
 
 	if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP))
 		return -ENODEV;
 
+	level = RMP_TO_PG_LEVEL(state->pagesize);
+	npages = page_level_size(level) / PAGE_SIZE;
+
+	/*
+	 * If the kernel uses a 2MB directmap mapping to write to an address,
+	 * and that 2MB range happens to contain a 4KB page that set to private
+	 * in the RMP table, an RMP #PF will trigger and cause a host crash.
+	 *
+	 * Prevent this by removing pages from the directmap prior to setting
+	 * them as private in the RMP table.
+	 */
+	if (state->assigned && invalidate_direct_map(pfn, npages))
+		return -EFAULT;
+
 	do {
 		/* Binutils version 2.36 supports the RMPUPDATE mnemonic. */
 		asm volatile(".byte 0xF2, 0x0F, 0x01, 0xFE"

@@ -386,12 +436,16 @@ static int rmpupdate(u64 pfn, struct rmp_state *state)
 	} while (ret == RMPUPDATE_FAIL_OVERLAP);
 
 	if (ret) {
-		pr_err("RMPUPDATE failed for PFN %llx, ret: %d\n", pfn, ret);
+		pr_err("RMPUPDATE failed for PFN %llx, pg_level: %d, ret: %d\n",
+		       pfn, level, ret);
 		dump_rmpentry(pfn);
 		dump_stack();
 		return -EFAULT;
 	}
 
+	if (!state->assigned && restore_direct_map(pfn, npages))
+		return -EFAULT;
+
 	return 0;
 }
 

@@ -130,6 +130,8 @@ static int sev_cmd_buffer_len(int cmd)
 	switch (cmd) {
 	case SEV_CMD_INIT:			return sizeof(struct sev_data_init);
 	case SEV_CMD_INIT_EX:                   return sizeof(struct sev_data_init_ex);
+	case SEV_CMD_SNP_SHUTDOWN_EX:		return sizeof(struct sev_data_snp_shutdown_ex);
+	case SEV_CMD_SNP_INIT_EX:		return sizeof(struct sev_data_snp_init_ex);
 	case SEV_CMD_PLATFORM_STATUS:		return sizeof(struct sev_user_data_status);
 	case SEV_CMD_PEK_CSR:			return sizeof(struct sev_data_pek_csr);
 	case SEV_CMD_PEK_CERT_IMPORT:		return sizeof(struct sev_data_pek_cert_import);

@@ -158,6 +160,20 @@ static int sev_cmd_buffer_len(int cmd)
 	case SEV_CMD_GET_ID:			return sizeof(struct sev_data_get_id);
 	case SEV_CMD_ATTESTATION_REPORT:	return sizeof(struct sev_data_attestation_report);
 	case SEV_CMD_SEND_CANCEL:		return sizeof(struct sev_data_send_cancel);
+	case SEV_CMD_SNP_GCTX_CREATE:		return sizeof(struct sev_data_snp_addr);
+	case SEV_CMD_SNP_LAUNCH_START:		return sizeof(struct sev_data_snp_launch_start);
+	case SEV_CMD_SNP_LAUNCH_UPDATE:		return sizeof(struct sev_data_snp_launch_update);
+	case SEV_CMD_SNP_ACTIVATE:		return sizeof(struct sev_data_snp_activate);
+	case SEV_CMD_SNP_DECOMMISSION:		return sizeof(struct sev_data_snp_addr);
+	case SEV_CMD_SNP_PAGE_RECLAIM:		return sizeof(struct sev_data_snp_page_reclaim);
+	case SEV_CMD_SNP_GUEST_STATUS:		return sizeof(struct sev_data_snp_guest_status);
+	case SEV_CMD_SNP_LAUNCH_FINISH:		return sizeof(struct sev_data_snp_launch_finish);
+	case SEV_CMD_SNP_DBG_DECRYPT:		return sizeof(struct sev_data_snp_dbg);
+	case SEV_CMD_SNP_DBG_ENCRYPT:		return sizeof(struct sev_data_snp_dbg);
+	case SEV_CMD_SNP_PAGE_UNSMASH:		return sizeof(struct sev_data_snp_page_unsmash);
+	case SEV_CMD_SNP_PLATFORM_STATUS:	return sizeof(struct sev_data_snp_addr);
+	case SEV_CMD_SNP_GUEST_REQUEST:		return sizeof(struct sev_data_snp_guest_request);
+	case SEV_CMD_SNP_CONFIG:		return sizeof(struct sev_user_data_snp_config);
 	default:				return 0;
 	}
 

@@ -78,6 +78,36 @@ enum sev_cmd {
 	SEV_CMD_DBG_DECRYPT		= 0x060,
 	SEV_CMD_DBG_ENCRYPT		= 0x061,
 
+	/* SNP specific commands */
+	SEV_CMD_SNP_INIT		= 0x081,
+	SEV_CMD_SNP_SHUTDOWN		= 0x082,
+	SEV_CMD_SNP_PLATFORM_STATUS	= 0x083,
+	SEV_CMD_SNP_DF_FLUSH		= 0x084,
+	SEV_CMD_SNP_INIT_EX		= 0x085,
+	SEV_CMD_SNP_SHUTDOWN_EX		= 0x086,
+	SEV_CMD_SNP_DECOMMISSION	= 0x090,
+	SEV_CMD_SNP_ACTIVATE		= 0x091,
+	SEV_CMD_SNP_GUEST_STATUS	= 0x092,
+	SEV_CMD_SNP_GCTX_CREATE		= 0x093,
+	SEV_CMD_SNP_GUEST_REQUEST	= 0x094,
+	SEV_CMD_SNP_ACTIVATE_EX		= 0x095,
+	SEV_CMD_SNP_LAUNCH_START	= 0x0A0,
+	SEV_CMD_SNP_LAUNCH_UPDATE	= 0x0A1,
+	SEV_CMD_SNP_LAUNCH_FINISH	= 0x0A2,
+	SEV_CMD_SNP_DBG_DECRYPT		= 0x0B0,
+	SEV_CMD_SNP_DBG_ENCRYPT		= 0x0B1,
+	SEV_CMD_SNP_PAGE_SWAP_OUT	= 0x0C0,
+	SEV_CMD_SNP_PAGE_SWAP_IN	= 0x0C1,
+	SEV_CMD_SNP_PAGE_MOVE		= 0x0C2,
+	SEV_CMD_SNP_PAGE_MD_INIT	= 0x0C3,
+	SEV_CMD_SNP_PAGE_SET_STATE	= 0x0C6,
+	SEV_CMD_SNP_PAGE_RECLAIM	= 0x0C7,
+	SEV_CMD_SNP_PAGE_UNSMASH	= 0x0C8,
+	SEV_CMD_SNP_CONFIG		= 0x0C9,
+	SEV_CMD_SNP_DOWNLOAD_FIRMWARE_EX	= 0x0CA,
+	SEV_CMD_SNP_COMMIT		= 0x0CB,
+	SEV_CMD_SNP_VLEK_LOAD		= 0x0CD,
+
 	SEV_CMD_MAX,
 };
 

@@ -523,6 +553,240 @@ struct sev_data_attestation_report {
 	u32 len;				/* In/Out */
 } __packed;
 
+/**
+ * struct sev_data_snp_download_firmware - SNP_DOWNLOAD_FIRMWARE command params
+ *
+ * @address: physical address of firmware image
+ * @len: len of the firmware image
+ */
+struct sev_data_snp_download_firmware {
+	u64 address;				/* In */
+	u32 len;				/* In */
+} __packed;
+
+/**
+ * struct sev_data_snp_activate - SNP_ACTIVATE command params
+ *
+ * @gctx_paddr: system physical address guest context page
+ * @asid: ASID to bind to the guest
+ */
+struct sev_data_snp_activate {
+	u64 gctx_paddr;				/* In */
+	u32 asid;				/* In */
+} __packed;
+
+/**
+ * struct sev_data_snp_addr - generic SNP command params
+ *
+ * @gctx_paddr: system physical address guest context page
+ */
+struct sev_data_snp_addr {
+	u64 gctx_paddr;				/* In */
+} __packed;
+
+/**
+ * struct sev_data_snp_launch_start - SNP_LAUNCH_START command params
+ *
+ * @gctx_paddr: system physical address of guest context page
+ * @policy: guest policy
+ * @ma_gctx_paddr: system physical address of migration agent
+ * @ma_en: the guest is associated with a migration agent
+ * @imi_en: launch flow is launching an Incoming Migration Image for the
+ *	purpose of guest-assisted migration.
+ * @rsvd: reserved
+ * @gosvw: guest OS-visible workarounds, as defined by hypervisor
+ */
+struct sev_data_snp_launch_start {
+	u64 gctx_paddr;				/* In */
+	u64 policy;				/* In */
+	u64 ma_gctx_paddr;			/* In */
+	u32 ma_en:1;				/* In */
+	u32 imi_en:1;				/* In */
+	u32 rsvd:30;
+	u8 gosvw[16];				/* In */
+} __packed;
+
+/* SNP support page type */
+enum {
+	SNP_PAGE_TYPE_NORMAL		= 0x1,
+	SNP_PAGE_TYPE_VMSA		= 0x2,
+	SNP_PAGE_TYPE_ZERO		= 0x3,
+	SNP_PAGE_TYPE_UNMEASURED	= 0x4,
+	SNP_PAGE_TYPE_SECRET		= 0x5,
+	SNP_PAGE_TYPE_CPUID		= 0x6,
+
+	SNP_PAGE_TYPE_MAX
+};
+
+/**
+ * struct sev_data_snp_launch_update - SNP_LAUNCH_UPDATE command params
+ *
+ * @gctx_paddr: system physical address of guest context page
+ * @page_size: page size 0 indicates 4K and 1 indicates 2MB page
+ * @page_type: encoded page type
+ * @imi_page: indicates that this page is part of the IMI of the guest
+ * @rsvd: reserved
+ * @rsvd2: reserved
+ * @address: system physical address of destination page to encrypt
+ * @rsvd3: reserved
+ * @vmpl1_perms: VMPL permission mask for VMPL1
+ * @vmpl2_perms: VMPL permission mask for VMPL2
+ * @vmpl3_perms: VMPL permission mask for VMPL3
+ * @rsvd4: reserved
+ */
+struct sev_data_snp_launch_update {
+	u64 gctx_paddr;				/* In */
+	u32 page_size:1;			/* In */
+	u32 page_type:3;			/* In */
+	u32 imi_page:1;				/* In */
+	u32 rsvd:27;
+	u32 rsvd2;
+	u64 address;				/* In */
+	u32 rsvd3:8;
+	u32 vmpl1_perms:8;			/* In */
+	u32 vmpl2_perms:8;			/* In */
+	u32 vmpl3_perms:8;			/* In */
+	u32 rsvd4;
+} __packed;
+
+/**
+ * struct sev_data_snp_launch_finish - SNP_LAUNCH_FINISH command params
+ *
+ * @gctx_paddr: system physical address of guest context page
+ * @id_block_paddr: system physical address of ID block
+ * @id_auth_paddr: system physical address of ID block authentication structure
+ * @id_block_en: indicates whether ID block is present
+ * @auth_key_en: indicates whether author key is present in authentication structure
+ * @rsvd: reserved
+ * @host_data: host-supplied data for guest, not interpreted by firmware
+ */
+struct sev_data_snp_launch_finish {
+	u64 gctx_paddr;
+	u64 id_block_paddr;
+	u64 id_auth_paddr;
+	u8 id_block_en:1;
+	u8 auth_key_en:1;
+	u64 rsvd:62;
+	u8 host_data[32];
+} __packed;
+
+/**
+ * struct sev_data_snp_guest_status - SNP_GUEST_STATUS command params
+ *
+ * @gctx_paddr: system physical address of guest context page
+ * @address: system physical address of guest status page
+ */
+struct sev_data_snp_guest_status {
+	u64 gctx_paddr;
+	u64 address;
+} __packed;
+
+/**
+ * struct sev_data_snp_page_reclaim - SNP_PAGE_RECLAIM command params
+ *
+ * @paddr: system physical address of page to be claimed. The 0th bit
+ *	in the address indicates the page size. 0h indicates 4 kB and
+ *	1h indicates 2 MB page.
+ */
+struct sev_data_snp_page_reclaim {
+	u64 paddr;
+} __packed;
+
+/**
+ * struct sev_data_snp_page_unsmash - SNP_PAGE_UNSMASH command params
+ *
+ * @paddr: system physical address of page to be unsmashed. The 0th bit
+ *	in the address indicates the page size. 0h indicates 4 kB and
+ *	1h indicates 2 MB page.
+ */
+struct sev_data_snp_page_unsmash {
+	u64 paddr;
+} __packed;
+
+/**
+ * struct sev_data_snp_dbg - DBG_ENCRYPT/DBG_DECRYPT command parameters
+ *
+ * @gctx_paddr: system physical address of guest context page
+ * @src_addr: source address of data to operate on
+ * @dst_addr: destination address of data to operate on
+ */
+struct sev_data_snp_dbg {
+	u64 gctx_paddr;				/* In */
+	u64 src_addr;				/* In */
+	u64 dst_addr;				/* In */
+} __packed;
+
+/**
+ * struct sev_data_snp_guest_request - SNP_GUEST_REQUEST command params
+ *
+ * @gctx_paddr: system physical address of guest context page
+ * @req_paddr: system physical address of request page
+ * @res_paddr: system physical address of response page
+ */
+struct sev_data_snp_guest_request {
+	u64 gctx_paddr;				/* In */
+	u64 req_paddr;				/* In */
+	u64 res_paddr;				/* In */
+} __packed;
+
+/**
+ * struct sev_data_snp_init_ex - SNP_INIT_EX structure
+ *
+ * @init_rmp: indicate that the RMP should be initialized.
+ * @list_paddr_en: indicate that list_paddr is valid
+ * @rsvd: reserved
+ * @rsvd1: reserved
+ * @list_paddr: system physical address of range list
+ * @rsvd2: reserved
+ */
+struct sev_data_snp_init_ex {
+	u32 init_rmp:1;
+	u32 list_paddr_en:1;
+	u32 rsvd:30;
+	u32 rsvd1;
+	u64 list_paddr;
+	u8  rsvd2[48];
+} __packed;
+
+/**
+ * struct sev_data_range - RANGE structure
+ *
+ * @base: system physical address of first byte of range
+ * @page_count: number of 4KB pages in this range
+ * @rsvd: reserved
+ */
+struct sev_data_range {
+	u64 base;
+	u32 page_count;
+	u32 rsvd;
+} __packed;
+
+/**
+ * struct sev_data_range_list - RANGE_LIST structure
+ *
+ * @num_elements: number of elements in RANGE_ARRAY
+ * @rsvd: reserved
+ * @ranges: array of num_elements of type RANGE
+ */
+struct sev_data_range_list {
+	u32 num_elements;
+	u32 rsvd;
+	struct sev_data_range ranges[];
+} __packed;
+
+/**
+ * struct sev_data_snp_shutdown_ex - SNP_SHUTDOWN_EX structure
+ *
+ * @length: len of the command buffer read by the PSP
+ * @iommu_snp_shutdown: Disable enforcement of SNP in the IOMMU
+ * @rsvd1: reserved
+ */
+struct sev_data_snp_shutdown_ex {
+	u32 length;
+	u32 iommu_snp_shutdown:1;
+	u32 rsvd1:31;
+} __packed;
+
 #ifdef CONFIG_CRYPTO_DEV_SP_PSP
 
 /**

@@ -69,6 +69,12 @@ typedef enum {
 	SEV_RET_RESOURCE_LIMIT,
 	SEV_RET_SECURE_DATA_INVALID,
 	SEV_RET_INVALID_KEY = 0x27,
+	SEV_RET_INVALID_PAGE_SIZE,
+	SEV_RET_INVALID_PAGE_STATE,
+	SEV_RET_INVALID_MDATA_ENTRY,
+	SEV_RET_INVALID_PAGE_OWNER,
+	SEV_RET_INVALID_PAGE_AEAD_OFLOW,
+	SEV_RET_RMP_INIT_REQUIRED,
 	SEV_RET_MAX,
 } sev_ret_code;
 

@@ -155,6 +161,56 @@ struct sev_user_data_get_id2 {
 	__u32 length;				/* In/Out */
 } __packed;
 
+/**
+ * struct sev_user_data_snp_status - SNP status
+ *
+ * @api_major: API major version
+ * @api_minor: API minor version
+ * @state: current platform state
+ * @is_rmp_initialized: whether RMP is initialized or not
+ * @rsvd: reserved
+ * @build_id: firmware build id for the API version
+ * @mask_chip_id: whether chip id is present in attestation reports or not
+ * @mask_chip_key: whether attestation reports are signed or not
+ * @vlek_en: VLEK hashstick is loaded
+ * @rsvd1: reserved
+ * @guest_count: the number of guest currently managed by the firmware
+ * @current_tcb_version: current TCB version
+ * @reported_tcb_version: reported TCB version
+ */
+struct sev_user_data_snp_status {
+	__u8 api_major;			/* Out */
+	__u8 api_minor;			/* Out */
+	__u8 state;			/* Out */
+	__u8 is_rmp_initialized:1;	/* Out */
+	__u8 rsvd:7;
+	__u32 build_id;			/* Out */
+	__u32 mask_chip_id:1;		/* Out */
+	__u32 mask_chip_key:1;		/* Out */
+	__u32 vlek_en:1;		/* Out */
+	__u32 rsvd1:29;
+	__u32 guest_count;		/* Out */
+	__u64 current_tcb_version;	/* Out */
+	__u64 reported_tcb_version;	/* Out */
+} __packed;
+
+/**
+ * struct sev_user_data_snp_config - system wide configuration value for SNP.
+ *
+ * @reported_tcb: the TCB version to report in the guest attestation report.
+ * @mask_chip_id: whether chip id is present in attestation reports or not
+ * @mask_chip_key: whether attestation reports are signed or not
+ * @rsvd: reserved
+ * @rsvd1: reserved
+ */
+struct sev_user_data_snp_config {
+	__u64 reported_tcb  ;   /* In */
+	__u32 mask_chip_id:1;   /* In */
+	__u32 mask_chip_key:1;  /* In */
+	__u32 rsvd:30;          /* In */
+	__u8 rsvd1[52];
+} __packed;
+
 /**
  * struct sev_issue_cmd - SEV ioctl parameters
  *

@@ -246,6 +246,7 @@ static void sev_unbind_asid(struct kvm *kvm, unsigned int handle)
 static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp)
 {
 	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+	struct sev_platform_init_args init_args = {0};
 	int asid, ret;
 
 	if (kvm->created_vcpus)

@@ -262,7 +263,8 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp)
 		goto e_no_asid;
 	sev->asid = asid;
 
-	ret = sev_platform_init(&argp->error);
+	init_args.probe = false;
+	ret = sev_platform_init(&init_args);
 	if (ret)
 		goto e_free;
 

@@ -274,6 +276,7 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp)
 	return 0;
 
 e_free:
+	argp->error = init_args.error;
 	sev_asid_free(sev);
 	sev->asid = 0;
 e_no_asid:

@@ -29,6 +29,7 @@
 
 #include <asm/smp.h>
 #include <asm/cacheflush.h>
+#include <asm/e820/types.h>
 
 #include "psp-dev.h"
 #include "sev-dev.h"