9 files changed, 473 insertions, 121 deletions

diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c
index 0893436cc09f..1f2ae708b223 100644
--- a/tools/objtool/arch/x86/decode.c
+++ b/tools/objtool/arch/x86/decode.c
@@ -20,6 +20,7 @@
 #include <objtool/arch.h>
 #include <objtool/warn.h>
 #include <objtool/endianness.h>
+#include <objtool/builtin.h>
 #include <arch/elf.h>
 
 static int is_x86_64(const struct elf *elf)
@@ -102,12 +103,13 @@ unsigned long arch_jump_destination(struct instruction *insn)
 #define rm_is_mem(reg)	(mod_is_mem() && !is_RIP() && rm_is(reg))
 #define rm_is_reg(reg)	(mod_is_reg() && modrm_rm == (reg))
 
-int arch_decode_instruction(const struct elf *elf, const struct section *sec,
+int arch_decode_instruction(struct objtool_file *file, const struct section *sec,
 			    unsigned long offset, unsigned int maxlen,
 			    unsigned int *len, enum insn_type *type,
 			    unsigned long *immediate,
 			    struct list_head *ops_list)
 {
+	const struct elf *elf = file->elf;
 	struct insn insn;
 	int x86_64, ret;
 	unsigned char op1, op2,
@@ -544,6 +546,36 @@ int arch_decode_instruction(const struct elf *elf, const struct section *sec,
 		*type = INSN_RETURN;
 		break;
 
+	case 0xc7: /* mov imm, r/m */
+		if (!noinstr)
+			break;
+
+		if (insn.length == 3+4+4 && !strncmp(sec->name, ".init.text", 10)) {
+			struct reloc *immr, *disp;
+			struct symbol *func;
+			int idx;
+
+			immr = find_reloc_by_dest(elf, (void *)sec, offset+3);
+			disp = find_reloc_by_dest(elf, (void *)sec, offset+7);
+
+			if (!immr || strcmp(immr->sym->name, "pv_ops"))
+				break;
+
+			idx = (immr->addend + 8) / sizeof(void *);
+
+			func = disp->sym;
+			if (disp->sym->type == STT_SECTION)
+				func = find_symbol_by_offset(disp->sym->sec, disp->addend);
+			if (!func) {
+				WARN("no func for pv_ops[]");
+				return -1;
+			}
+
+			objtool_pv_add(file, idx, func);
+		}
+
+		break;
+
 	case 0xcf: /* iret */
 		/*
 		 * Handle sync_core(), which has an IRET to self.
@@ -659,6 +691,26 @@ const char *arch_nop_insn(int len)
 	return nops[len-1];
 }
 
+#define BYTE_RET	0xC3
+
+const char *arch_ret_insn(int len)
+{
+	static const char ret[5][5] = {
+		{ BYTE_RET },
+		{ BYTE_RET, BYTES_NOP1 },
+		{ BYTE_RET, BYTES_NOP2 },
+		{ BYTE_RET, BYTES_NOP3 },
+		{ BYTE_RET, BYTES_NOP4 },
+	};
+
+	if (len < 1 || len > 5) {
+		WARN("invalid RET size: %d\n", len);
+		return NULL;
+	}
+
+	return ret[len-1];
+}
+
 /* asm/alternative.h ? */
 
 #define ALTINSTR_FLAG_INV	(1 << 15)
@@ -779,34 +831,32 @@ int arch_rewrite_retpolines(struct objtool_file *file)
 	return 0;
 }
 
-int arch_decode_hint_reg(struct instruction *insn, u8 sp_reg)
+int arch_decode_hint_reg(u8 sp_reg, int *base)
 {
-	struct cfi_reg *cfa = &insn->cfi.cfa;
-
 	switch (sp_reg) {
 	case ORC_REG_UNDEFINED:
-		cfa->base = CFI_UNDEFINED;
+		*base = CFI_UNDEFINED;
 		break;
 	case ORC_REG_SP:
-		cfa->base = CFI_SP;
+		*base = CFI_SP;
 		break;
 	case ORC_REG_BP:
-		cfa->base = CFI_BP;
+		*base = CFI_BP;
 		break;
 	case ORC_REG_SP_INDIRECT:
-		cfa->base = CFI_SP_INDIRECT;
+		*base = CFI_SP_INDIRECT;
 		break;
 	case ORC_REG_R10:
-		cfa->base = CFI_R10;
+		*base = CFI_R10;
 		break;
 	case ORC_REG_R13:
-		cfa->base = CFI_R13;
+		*base = CFI_R13;
 		break;
 	case ORC_REG_DI:
-		cfa->base = CFI_DI;
+		*base = CFI_DI;
 		break;
 	case ORC_REG_DX:
-		cfa->base = CFI_DX;
+		*base = CFI_DX;
 		break;
 	default:
 		return -1;
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 06b5c164ae93..7c865a10372a 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -5,6 +5,7 @@
 
 #include <string.h>
 #include <stdlib.h>
+#include <sys/mman.h>
 
 #include <arch/elf.h>
 #include <objtool/builtin.h>
@@ -26,7 +27,11 @@ struct alternative {
 	bool skip_orig;
 };
 
-struct cfi_init_state initial_func_cfi;
+static unsigned long nr_cfi, nr_cfi_reused, nr_cfi_cache;
+
+static struct cfi_init_state initial_func_cfi;
+static struct cfi_state init_cfi;
+static struct cfi_state func_cfi;
 
 struct instruction *find_insn(struct objtool_file *file,
 			      struct section *sec, unsigned long offset)
@@ -173,6 +178,7 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func,
 		"rewind_stack_do_exit",
 		"kunit_try_catch_throw",
 		"xen_start_kernel",
+		"cpu_bringup_and_idle",
 	};
 
 	if (!func)
@@ -265,6 +271,78 @@ static void init_insn_state(struct insn_state *state, struct section *sec)
 		state->noinstr = sec->noinstr;
 }
 
+static struct cfi_state *cfi_alloc(void)
+{
+	struct cfi_state *cfi = calloc(sizeof(struct cfi_state), 1);
+	if (!cfi) {
+		WARN("calloc failed");
+		exit(1);
+	}
+	nr_cfi++;
+	return cfi;
+}
+
+static int cfi_bits;
+static struct hlist_head *cfi_hash;
+
+static inline bool cficmp(struct cfi_state *cfi1, struct cfi_state *cfi2)
+{
+	return memcmp((void *)cfi1 + sizeof(cfi1->hash),
+		      (void *)cfi2 + sizeof(cfi2->hash),
+		      sizeof(struct cfi_state) - sizeof(struct hlist_node));
+}
+
+static inline u32 cfi_key(struct cfi_state *cfi)
+{
+	return jhash((void *)cfi + sizeof(cfi->hash),
+		     sizeof(*cfi) - sizeof(cfi->hash), 0);
+}
+
+static struct cfi_state *cfi_hash_find_or_add(struct cfi_state *cfi)
+{
+	struct hlist_head *head = &cfi_hash[hash_min(cfi_key(cfi), cfi_bits)];
+	struct cfi_state *obj;
+
+	hlist_for_each_entry(obj, head, hash) {
+		if (!cficmp(cfi, obj)) {
+			nr_cfi_cache++;
+			return obj;
+		}
+	}
+
+	obj = cfi_alloc();
+	*obj = *cfi;
+	hlist_add_head(&obj->hash, head);
+
+	return obj;
+}
+
+static void cfi_hash_add(struct cfi_state *cfi)
+{
+	struct hlist_head *head = &cfi_hash[hash_min(cfi_key(cfi), cfi_bits)];
+
+	hlist_add_head(&cfi->hash, head);
+}
+
+static void *cfi_hash_alloc(unsigned long size)
+{
+	cfi_bits = max(10, ilog2(size));
+	cfi_hash = mmap(NULL, sizeof(struct hlist_head) << cfi_bits,
+			PROT_READ|PROT_WRITE,
+			MAP_PRIVATE|MAP_ANON, -1, 0);
+	if (cfi_hash == (void *)-1L) {
+		WARN("mmap fail cfi_hash");
+		cfi_hash = NULL;
+	}  else if (stats) {
+		printf("cfi_bits: %d\n", cfi_bits);
+	}
+
+	return cfi_hash;
+}
+
+static unsigned long nr_insns;
+static unsigned long nr_insns_visited;
+
 /*
  * Call the arch-specific instruction decoder for all the instructions and add
  * them to the global instruction list.
@@ -275,7 +353,6 @@ static int decode_instructions(struct objtool_file *file)
 	struct symbol *func;
 	unsigned long offset;
 	struct instruction *insn;
-	unsigned long nr_insns = 0;
 	int ret;
 
 	for_each_sec(file, sec) {
@@ -301,12 +378,11 @@ static int decode_instructions(struct objtool_file *file)
 			memset(insn, 0, sizeof(*insn));
 			INIT_LIST_HEAD(&insn->alts);
 			INIT_LIST_HEAD(&insn->stack_ops);
-			init_cfi_state(&insn->cfi);
 
 			insn->sec = sec;
 			insn->offset = offset;
 
-			ret = arch_decode_instruction(file->elf, sec, offset,
+			ret = arch_decode_instruction(file, sec, offset,
 						      sec->sh.sh_size - offset,
 						      &insn->len, &insn->type,
 						      &insn->immediate,
@@ -344,6 +420,82 @@ err:
 	return ret;
 }
 
+/*
+ * Read the pv_ops[] .data table to find the static initialized values.
+ */
+static int add_pv_ops(struct objtool_file *file, const char *symname)
+{
+	struct symbol *sym, *func;
+	unsigned long off, end;
+	struct reloc *rel;
+	int idx;
+
+	sym = find_symbol_by_name(file->elf, symname);
+	if (!sym)
+		return 0;
+
+	off = sym->offset;
+	end = off + sym->len;
+	for (;;) {
+		rel = find_reloc_by_dest_range(file->elf, sym->sec, off, end - off);
+		if (!rel)
+			break;
+
+		func = rel->sym;
+		if (func->type == STT_SECTION)
+			func = find_symbol_by_offset(rel->sym->sec, rel->addend);
+
+		idx = (rel->offset - sym->offset) / sizeof(unsigned long);
+
+		objtool_pv_add(file, idx, func);
+
+		off = rel->offset + 1;
+		if (off > end)
+			break;
+	}
+
+	return 0;
+}
+
+/*
+ * Allocate and initialize file->pv_ops[].
+ */
+static int init_pv_ops(struct objtool_file *file)
+{
+	static const char *pv_ops_tables[] = {
+		"pv_ops",
+		"xen_cpu_ops",
+		"xen_irq_ops",
+		"xen_mmu_ops",
+		NULL,
+	};
+	const char *pv_ops;
+	struct symbol *sym;
+	int idx, nr;
+
+	if (!noinstr)
+		return 0;
+
+	file->pv_ops = NULL;
+
+	sym = find_symbol_by_name(file->elf, "pv_ops");
+	if (!sym)
+		return 0;
+
+	nr = sym->len / sizeof(unsigned long);
+	file->pv_ops = calloc(sizeof(struct pv_state), nr);
+	if (!file->pv_ops)
+		return -1;
+
+	for (idx = 0; idx < nr; idx++)
+		INIT_LIST_HEAD(&file->pv_ops[idx].targets);
+
+	for (idx = 0; (pv_ops = pv_ops_tables[idx]); idx++)
+		add_pv_ops(file, pv_ops);
+
+	return 0;
+}
+
 static struct instruction *find_last_insn(struct objtool_file *file,
 					  struct section *sec)
 {
@@ -817,6 +969,9 @@ static struct reloc *insn_reloc(struct objtool_file *file, struct instruction *i
 		return NULL;
 
 	if (!insn->reloc) {
+		if (!file)
+			return NULL;
+
 		insn->reloc = find_reloc_by_dest_range(file->elf, insn->sec,
 						       insn->offset, insn->len);
 		if (!insn->reloc) {
@@ -828,6 +983,79 @@ static struct reloc *insn_reloc(struct objtool_file *file, struct instruction *i
 	return insn->reloc;
 }
 
+static void remove_insn_ops(struct instruction *insn)
+{
+	struct stack_op *op, *tmp;
+
+	list_for_each_entry_safe(op, tmp, &insn->stack_ops, list) {
+		list_del(&op->list);
+		free(op);
+	}
+}
+
+static void add_call_dest(struct objtool_file *file, struct instruction *insn,
+			  struct symbol *dest, bool sibling)
+{
+	struct reloc *reloc = insn_reloc(file, insn);
+
+	insn->call_dest = dest;
+	if (!dest)
+		return;
+
+	if (insn->call_dest->static_call_tramp) {
+		list_add_tail(&insn->call_node,
+			      &file->static_call_list);
+	}
+
+	/*
+	 * Many compilers cannot disable KCOV with a function attribute
+	 * so they need a little help, NOP out any KCOV calls from noinstr
+	 * text.
+	 */
+	if (insn->sec->noinstr &&
+	    !strncmp(insn->call_dest->name, "__sanitizer_cov_", 16)) {
+		if (reloc) {
+			reloc->type = R_NONE;
+			elf_write_reloc(file->elf, reloc);
+		}
+
+		elf_write_insn(file->elf, insn->sec,
+			       insn->offset, insn->len,
+			       sibling ? arch_ret_insn(insn->len)
+			               : arch_nop_insn(insn->len));
+
+		insn->type = sibling ? INSN_RETURN : INSN_NOP;
+	}
+
+	if (mcount && !strcmp(insn->call_dest->name, "__fentry__")) {
+		if (sibling)
+			WARN_FUNC("Tail call to __fentry__ !?!?", insn->sec, insn->offset);
+
+		if (reloc) {
+			reloc->type = R_NONE;
+			elf_write_reloc(file->elf, reloc);
+		}
+
+		elf_write_insn(file->elf, insn->sec,
+			       insn->offset, insn->len,
+			       arch_nop_insn(insn->len));
+
+		insn->type = INSN_NOP;
+
+		list_add_tail(&insn->mcount_loc_node,
+			      &file->mcount_loc_list);
+	}
+
+	/*
+	 * Whatever stack impact regular CALLs have, should be undone
+	 * by the RETURN of the called function.
+	 *
+	 * Annotated intra-function calls retain the stack_ops but
+	 * are converted to JUMP, see read_intra_function_calls().
+	 */
+	remove_insn_ops(insn);
+}
+
 /*
  * Find the destination instructions for all jumps.
  */
@@ -866,11 +1094,7 @@ static int add_jump_destinations(struct objtool_file *file)
 			continue;
 		} else if (insn->func) {
 			/* internal or external sibling call (with reloc) */
-			insn->call_dest = reloc->sym;
-			if (insn->call_dest->static_call_tramp) {
-				list_add_tail(&insn->call_node,
-					      &file->static_call_list);
-			}
+			add_call_dest(file, insn, reloc->sym, true);
 			continue;
 		} else if (reloc->sym->sec->idx) {
 			dest_sec = reloc->sym->sec;
@@ -926,13 +1150,8 @@ static int add_jump_destinations(struct objtool_file *file)
 
 			} else if (insn->jump_dest->func->pfunc != insn->func->pfunc &&
 				   insn->jump_dest->offset == insn->jump_dest->func->offset) {
-
 				/* internal sibling call (without reloc) */
-				insn->call_dest = insn->jump_dest->func;
-				if (insn->call_dest->static_call_tramp) {
-					list_add_tail(&insn->call_node,
-						      &file->static_call_list);
-				}
+				add_call_dest(file, insn, insn->jump_dest->func, true);
 			}
 		}
 	}
@@ -940,16 +1159,6 @@ static int add_jump_destinations(struct objtool_file *file)
 	return 0;
 }
 
-static void remove_insn_ops(struct instruction *insn)
-{
-	struct stack_op *op, *tmp;
-
-	list_for_each_entry_safe(op, tmp, &insn->stack_ops, list) {
-		list_del(&op->list);
-		free(op);
-	}
-}
-
 static struct symbol *find_call_destination(struct section *sec, unsigned long offset)
 {
 	struct symbol *call_dest;
@@ -968,6 +1177,7 @@ static int add_call_destinations(struct objtool_file *file)
 {
 	struct instruction *insn;
 	unsigned long dest_off;
+	struct symbol *dest;
 	struct reloc *reloc;
 
 	for_each_insn(file, insn) {
@@ -977,7 +1187,9 @@ static int add_call_destinations(struct objtool_file *file)
 		reloc = insn_reloc(file, insn);
 		if (!reloc) {
 			dest_off = arch_jump_destination(insn);
-			insn->call_dest = find_call_destination(insn->sec, dest_off);
+			dest = find_call_destination(insn->sec, dest_off);
+
+			add_call_dest(file, insn, dest, false);
 
 			if (insn->ignore)
 				continue;
@@ -995,9 +1207,8 @@ static int add_call_destinations(struct objtool_file *file)
 
 		} else if (reloc->sym->type == STT_SECTION) {
 			dest_off = arch_dest_reloc_offset(reloc->addend);
-			insn->call_dest = find_call_destination(reloc->sym->sec,
-								dest_off);
-			if (!insn->call_dest) {
+			dest = find_call_destination(reloc->sym->sec, dest_off);
+			if (!dest) {
 				WARN_FUNC("can't find call dest symbol at %s+0x%lx",
 					  insn->sec, insn->offset,
 					  reloc->sym->sec->name,
@@ -1005,6 +1216,8 @@ static int add_call_destinations(struct objtool_file *file)
 				return -1;
 			}
 
+			add_call_dest(file, insn, dest, false);
+
 		} else if (arch_is_retpoline(reloc->sym)) {
 			/*
 			 * Retpoline calls are really dynamic calls in
@@ -1020,55 +1233,7 @@ static int add_call_destinations(struct objtool_file *file)
 			continue;
 
 		} else
-			insn->call_dest = reloc->sym;
-
-		if (insn->call_dest && insn->call_dest->static_call_tramp) {
-			list_add_tail(&insn->call_node,
-				      &file->static_call_list);
-		}
-
-		/*
-		 * Many compilers cannot disable KCOV with a function attribute
-		 * so they need a little help, NOP out any KCOV calls from noinstr
-		 * text.
-		 */
-		if (insn->sec->noinstr &&
-		    !strncmp(insn->call_dest->name, "__sanitizer_cov_", 16)) {
-			if (reloc) {
-				reloc->type = R_NONE;
-				elf_write_reloc(file->elf, reloc);
-			}
-
-			elf_write_insn(file->elf, insn->sec,
-				       insn->offset, insn->len,
-				       arch_nop_insn(insn->len));
-			insn->type = INSN_NOP;
-		}
-
-		if (mcount && !strcmp(insn->call_dest->name, "__fentry__")) {
-			if (reloc) {
-				reloc->type = R_NONE;
-				elf_write_reloc(file->elf, reloc);
-			}
-
-			elf_write_insn(file->elf, insn->sec,
-				       insn->offset, insn->len,
-				       arch_nop_insn(insn->len));
-
-			insn->type = INSN_NOP;
-
-			list_add_tail(&insn->mcount_loc_node,
-				      &file->mcount_loc_list);
-		}
-
-		/*
-		 * Whatever stack impact regular CALLs have, should be undone
-		 * by the RETURN of the called function.
-		 *
-		 * Annotated intra-function calls retain the stack_ops but
-		 * are converted to JUMP, see read_intra_function_calls().
-		 */
-		remove_insn_ops(insn);
+			add_call_dest(file, insn, reloc->sym, false);
 	}
 
 	return 0;
@@ -1136,7 +1301,6 @@ static int handle_group_alt(struct objtool_file *file,
 		memset(nop, 0, sizeof(*nop));
 		INIT_LIST_HEAD(&nop->alts);
 		INIT_LIST_HEAD(&nop->stack_ops);
-		init_cfi_state(&nop->cfi);
 
 		nop->sec = special_alt->new_sec;
 		nop->offset = special_alt->new_off + special_alt->new_len;
@@ -1545,10 +1709,11 @@ static void set_func_state(struct cfi_state *state)
 
 static int read_unwind_hints(struct objtool_file *file)
 {
+	struct cfi_state cfi = init_cfi;
 	struct section *sec, *relocsec;
-	struct reloc *reloc;
 	struct unwind_hint *hint;
 	struct instruction *insn;
+	struct reloc *reloc;
 	int i;
 
 	sec = find_section_by_name(file->elf, ".discard.unwind_hints");
@@ -1586,19 +1751,24 @@ static int read_unwind_hints(struct objtool_file *file)
 		insn->hint = true;
 
 		if (hint->type == UNWIND_HINT_TYPE_FUNC) {
-			set_func_state(&insn->cfi);
+			insn->cfi = &func_cfi;
 			continue;
 		}
 
-		if (arch_decode_hint_reg(insn, hint->sp_reg)) {
+		if (insn->cfi)
+			cfi = *(insn->cfi);
+
+		if (arch_decode_hint_reg(hint->sp_reg, &cfi.cfa.base)) {
 			WARN_FUNC("unsupported unwind_hint sp base reg %d",
 				  insn->sec, insn->offset, hint->sp_reg);
 			return -1;
 		}
 
-		insn->cfi.cfa.offset = bswap_if_needed(hint->sp_offset);
-		insn->cfi.type = hint->type;
-		insn->cfi.end = hint->end;
+		cfi.cfa.offset = bswap_if_needed(hint->sp_offset);
+		cfi.type = hint->type;
+		cfi.end = hint->end;
+
+		insn->cfi = cfi_hash_find_or_add(&cfi);
 	}
 
 	return 0;
@@ -1791,6 +1961,10 @@ static int decode_sections(struct objtool_file *file)
 
 	mark_rodata(file);
 
+	ret = init_pv_ops(file);
+	if (ret)
+		return ret;
+
 	ret = decode_instructions(file);
 	if (ret)
 		return ret;
@@ -2452,13 +2626,18 @@ static int propagate_alt_cfi(struct objtool_file *file, struct instruction *insn
 	if (!insn->alt_group)
 		return 0;
 
+	if (!insn->cfi) {
+		WARN("CFI missing");
+		return -1;
+	}
+
 	alt_cfi = insn->alt_group->cfi;
 	group_off = insn->offset - insn->alt_group->first_insn->offset;
 
 	if (!alt_cfi[group_off]) {
-		alt_cfi[group_off] = &insn->cfi;
+		alt_cfi[group_off] = insn->cfi;
 	} else {
-		if (memcmp(alt_cfi[group_off], &insn->cfi, sizeof(struct cfi_state))) {
+		if (cficmp(alt_cfi[group_off], insn->cfi)) {
 			WARN_FUNC("stack layout conflict in alternatives",
 				  insn->sec, insn->offset);
 			return -1;
@@ -2509,9 +2688,14 @@ static int handle_insn_ops(struct instruction *insn,
 
 static bool insn_cfi_match(struct instruction *insn, struct cfi_state *cfi2)
 {
-	struct cfi_state *cfi1 = &insn->cfi;
+	struct cfi_state *cfi1 = insn->cfi;
 	int i;
 
+	if (!cfi1) {
+		WARN("CFI missing");
+		return false;
+	}
+
 	if (memcmp(&cfi1->cfa, &cfi2->cfa, sizeof(cfi1->cfa))) {
 
 		WARN_FUNC("stack state mismatch: cfa1=%d%+d cfa2=%d%+d",
@@ -2562,20 +2746,64 @@ static inline bool func_uaccess_safe(struct symbol *func)
 
 static inline const char *call_dest_name(struct instruction *insn)
 {
+	static char pvname[16];
+	struct reloc *rel;
+	int idx;
+
 	if (insn->call_dest)
 		return insn->call_dest->name;
 
+	rel = insn_reloc(NULL, insn);
+	if (rel && !strcmp(rel->sym->name, "pv_ops")) {
+		idx = (rel->addend / sizeof(void *));
+		snprintf(pvname, sizeof(pvname), "pv_ops[%d]", idx);
+		return pvname;
+	}
+
 	return "{dynamic}";
 }
 
-static inline bool noinstr_call_dest(struct symbol *func)
+static bool pv_call_dest(struct objtool_file *file, struct instruction *insn)
+{
+	struct symbol *target;
+	struct reloc *rel;
+	int idx;
+
+	rel = insn_reloc(file, insn);
+	if (!rel || strcmp(rel->sym->name, "pv_ops"))
+		return false;
+
+	idx = (arch_dest_reloc_offset(rel->addend) / sizeof(void *));
+
+	if (file->pv_ops[idx].clean)
+		return true;
+
+	file->pv_ops[idx].clean = true;
+
+	list_for_each_entry(target, &file->pv_ops[idx].targets, pv_target) {
+		if (!target->sec->noinstr) {
+			WARN("pv_ops[%d]: %s", idx, target->name);
+			file->pv_ops[idx].clean = false;
+		}
+	}
+
+	return file->pv_ops[idx].clean;
+}
+
+static inline bool noinstr_call_dest(struct objtool_file *file,
+				     struct instruction *insn,
+				     struct symbol *func)
 {
 	/*
 	 * We can't deal with indirect function calls at present;
 	 * assume they're instrumented.
 	 */
-	if (!func)
+	if (!func) {
+		if (file->pv_ops)
+			return pv_call_dest(file, insn);
+
 		return false;
+	}
 
 	/*
 	 * If the symbol is from a noinstr section; we good.
@@ -2594,10 +2822,12 @@ static inline bool noinstr_call_dest(struct symbol *func)
 	return false;
 }
 
-static int validate_call(struct instruction *insn, struct insn_state *state)
+static int validate_call(struct objtool_file *file,
+			 struct instruction *insn,
+			 struct insn_state *state)
 {
 	if (state->noinstr && state->instr <= 0 &&
-	    !noinstr_call_dest(insn->call_dest)) {
+	    !noinstr_call_dest(file, insn, insn->call_dest)) {
 		WARN_FUNC("call to %s() leaves .noinstr.text section",
 				insn->sec, insn->offset, call_dest_name(insn));
 		return 1;
@@ -2618,7 +2848,9 @@ static int validate_call(struct instruction *insn, struct insn_state *state)
 	return 0;
 }
 
-static int validate_sibling_call(struct instruction *insn, struct insn_state *state)
+static int validate_sibling_call(struct objtool_file *file,
+				 struct instruction *insn,
+				 struct insn_state *state)
 {
 	if (has_modified_stack_frame(insn, state)) {
 		WARN_FUNC("sibling call from callable instruction with modified stack frame",
@@ -2626,7 +2858,7 @@ static int validate_sibling_call(struct instruction *insn, struct insn_state *st
 		return 1;
 	}
 
-	return validate_call(insn, state);
+	return validate_call(file, insn, state);
 }
 
 static int validate_return(struct symbol *func, struct instruction *insn, struct insn_state *state)
@@ -2696,7 +2928,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func,
 			   struct instruction *insn, struct insn_state state)
 {
 	struct alternative *alt;
-	struct instruction *next_insn;
+	struct instruction *next_insn, *prev_insn = NULL;
 	struct section *sec;
 	u8 visited;
 	int ret;
@@ -2725,15 +2957,25 @@ static int validate_branch(struct objtool_file *file, struct symbol *func,
 
 			if (insn->visited & visited)
 				return 0;
+		} else {
+			nr_insns_visited++;
 		}
 
 		if (state.noinstr)
 			state.instr += insn->instr;
 
-		if (insn->hint)
-			state.cfi = insn->cfi;
-		else
-			insn->cfi = state.cfi;
+		if (insn->hint) {
+			state.cfi = *insn->cfi;
+		} else {
+			/* XXX track if we actually changed state.cfi */
+
+			if (prev_insn && !cficmp(prev_insn->cfi, &state.cfi)) {
+				insn->cfi = prev_insn->cfi;
+				nr_cfi_reused++;
+			} else {
+				insn->cfi = cfi_hash_find_or_add(&state.cfi);
+			}
+		}
 
 		insn->visited |= visited;
 
@@ -2769,7 +3011,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func,
 
 		case INSN_CALL:
 		case INSN_CALL_DYNAMIC:
-			ret = validate_call(insn, &state);
+			ret = validate_call(file, insn, &state);
 			if (ret)
 				return ret;
 
@@ -2788,7 +3030,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func,
 		case INSN_JUMP_CONDITIONAL:
 		case INSN_JUMP_UNCONDITIONAL:
 			if (is_sibling_call(insn)) {
-				ret = validate_sibling_call(insn, &state);
+				ret = validate_sibling_call(file, insn, &state);
 				if (ret)
 					return ret;
 
@@ -2810,7 +3052,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func,
 		case INSN_JUMP_DYNAMIC:
 		case INSN_JUMP_DYNAMIC_CONDITIONAL:
 			if (is_sibling_call(insn)) {
-				ret = validate_sibling_call(insn, &state);
+				ret = validate_sibling_call(file, insn, &state);
 				if (ret)
 					return ret;
 			}
@@ -2883,6 +3125,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func,
 			return 1;
 		}
 
+		prev_insn = insn;
 		insn = next_insn;
 	}
 
@@ -3138,10 +3381,20 @@ int check(struct objtool_file *file)
 	int ret, warnings = 0;
 
 	arch_initial_func_cfi_state(&initial_func_cfi);
+	init_cfi_state(&init_cfi);
+	init_cfi_state(&func_cfi);
+	set_func_state(&func_cfi);
+
+	if (!cfi_hash_alloc(1UL << (file->elf->symbol_bits - 3)))
+		goto out;
+
+	cfi_hash_add(&init_cfi);
+	cfi_hash_add(&func_cfi);
 
 	ret = decode_sections(file);
 	if (ret < 0)
 		goto out;
+
 	warnings += ret;
 
 	if (list_empty(&file->insn_list))
@@ -3192,6 +3445,13 @@ int check(struct objtool_file *file)
 		warnings += ret;
 	}
 
+	if (stats) {
+		printf("nr_insns_visited: %ld\n", nr_insns_visited);
+		printf("nr_cfi: %ld\n", nr_cfi);
+		printf("nr_cfi_reused: %ld\n", nr_cfi_reused);
+		printf("nr_cfi_cache: %ld\n", nr_cfi_cache);
+	}
+
 out:
 	/*
 	 *  For now, don't fail the kernel build on fatal warnings.  These
diff --git a/tools/objtool/include/objtool/arch.h b/tools/objtool/include/objtool/arch.h
index 062bb6e9b865..589ff58426ab 100644
--- a/tools/objtool/include/objtool/arch.h
+++ b/tools/objtool/include/objtool/arch.h
@@ -69,7 +69,7 @@ struct instruction;
 
 void arch_initial_func_cfi_state(struct cfi_init_state *state);
 
-int arch_decode_instruction(const struct elf *elf, const struct section *sec,
+int arch_decode_instruction(struct objtool_file *file, const struct section *sec,
 			    unsigned long offset, unsigned int maxlen,
 			    unsigned int *len, enum insn_type *type,
 			    unsigned long *immediate,
@@ -82,8 +82,9 @@ unsigned long arch_jump_destination(struct instruction *insn);
 unsigned long arch_dest_reloc_offset(int addend);
 
 const char *arch_nop_insn(int len);
+const char *arch_ret_insn(int len);
 
-int arch_decode_hint_reg(struct instruction *insn, u8 sp_reg);
+int arch_decode_hint_reg(u8 sp_reg, int *base);
 
 bool arch_is_retpoline(struct symbol *sym);
 
diff --git a/tools/objtool/include/objtool/cfi.h b/tools/objtool/include/objtool/cfi.h
index fd5cb0bed9bf..f11d1ac1dadf 100644
--- a/tools/objtool/include/objtool/cfi.h
+++ b/tools/objtool/include/objtool/cfi.h
@@ -7,6 +7,7 @@
 #define _OBJTOOL_CFI_H
 
 #include <arch/cfi_regs.h>
+#include <linux/list.h>
 
 #define CFI_UNDEFINED		-1
 #define CFI_CFA			-2
@@ -24,6 +25,7 @@ struct cfi_init_state {
 };
 
 struct cfi_state {
+	struct hlist_node hash; /* must be first, cficmp() */
 	struct cfi_reg regs[CFI_NUM_REGS];
 	struct cfi_reg vals[CFI_NUM_REGS];
 	struct cfi_reg cfa;
diff --git a/tools/objtool/include/objtool/check.h b/tools/objtool/include/objtool/check.h
index 56d50bc50c10..07e99c25c7ac 100644
--- a/tools/objtool/include/objtool/check.h
+++ b/tools/objtool/include/objtool/check.h
@@ -60,7 +60,7 @@ struct instruction {
 	struct list_head alts;
 	struct symbol *func;
 	struct list_head stack_ops;
-	struct cfi_state cfi;
+	struct cfi_state *cfi;
 };
 
 static inline bool is_static_jump(struct instruction *insn)
diff --git a/tools/objtool/include/objtool/elf.h b/tools/objtool/include/objtool/elf.h
index 075d8291b854..c48c1067797d 100644
--- a/tools/objtool/include/objtool/elf.h
+++ b/tools/objtool/include/objtool/elf.h
@@ -56,6 +56,7 @@ struct symbol {
 	struct symbol *pfunc, *cfunc, *alias;
 	bool uaccess_safe;
 	bool static_call_tramp;
+	struct list_head pv_target;
 };
 
 struct reloc {
diff --git a/tools/objtool/include/objtool/objtool.h b/tools/objtool/include/objtool/objtool.h
index 24fa83634de4..f99fbc6078d5 100644
--- a/tools/objtool/include/objtool/objtool.h
+++ b/tools/objtool/include/objtool/objtool.h
@@ -14,6 +14,11 @@
 
 #define __weak __attribute__((weak))
 
+struct pv_state {
+	bool clean;
+	struct list_head targets;
+};
+
 struct objtool_file {
 	struct elf *elf;
 	struct list_head insn_list;
@@ -25,10 +30,14 @@ struct objtool_file {
 
 	unsigned long jl_short, jl_long;
 	unsigned long jl_nop_short, jl_nop_long;
+
+	struct pv_state *pv_ops;
 };
 
 struct objtool_file *objtool_open_read(const char *_objname);
 
+void objtool_pv_add(struct objtool_file *file, int idx, struct symbol *func);
+
 int check(struct objtool_file *file);
 int orc_dump(const char *objname);
 int orc_create(struct objtool_file *file);
diff --git a/tools/objtool/objtool.c b/tools/objtool/objtool.c
index e21db8bce493..c90c7084e45a 100644
--- a/tools/objtool/objtool.c
+++ b/tools/objtool/objtool.c
@@ -135,6 +135,28 @@ struct objtool_file *objtool_open_read(const char *_objname)
 	return &file;
 }
 
+void objtool_pv_add(struct objtool_file *f, int idx, struct symbol *func)
+{
+	if (!noinstr)
+		return;
+
+	if (!f->pv_ops) {
+		WARN("paravirt confusion");
+		return;
+	}
+
+	/*
+	 * These functions will be patched into native code,
+	 * see paravirt_patch().
+	 */
+	if (!strcmp(func->name, "_paravirt_nop") ||
+	    !strcmp(func->name, "_paravirt_ident_64"))
+		return;
+
+	list_add(&func->pv_target, &f->pv_ops[idx].targets);
+	f->pv_ops[idx].clean = false;
+}
+
 static void cmd_usage(void)
 {
 	unsigned int i, longest = 0;
diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c
index b5865e2450cb..dd3c64af9db2 100644
--- a/tools/objtool/orc_gen.c
+++ b/tools/objtool/orc_gen.c
@@ -13,13 +13,19 @@
 #include <objtool/warn.h>
 #include <objtool/endianness.h>
 
-static int init_orc_entry(struct orc_entry *orc, struct cfi_state *cfi)
+static int init_orc_entry(struct orc_entry *orc, struct cfi_state *cfi,
+			  struct instruction *insn)
 {
-	struct instruction *insn = container_of(cfi, struct instruction, cfi);
 	struct cfi_reg *bp = &cfi->regs[CFI_BP];
 
 	memset(orc, 0, sizeof(*orc));
 
+	if (!cfi) {
+		orc->end = 0;
+		orc->sp_reg = ORC_REG_UNDEFINED;
+		return 0;
+	}
+
 	orc->end = cfi->end;
 
 	if (cfi->cfa.base == CFI_UNDEFINED) {
@@ -162,7 +168,7 @@ int orc_create(struct objtool_file *file)
 			int i;
 
 			if (!alt_group) {
-				if (init_orc_entry(&orc, &insn->cfi))
+				if (init_orc_entry(&orc, insn->cfi, insn))
 					return -1;
 				if (!memcmp(&prev_orc, &orc, sizeof(orc)))
 					continue;
@@ -186,7 +192,8 @@ int orc_create(struct objtool_file *file)
 				struct cfi_state *cfi = alt_group->cfi[i];
 				if (!cfi)
 					continue;
-				if (init_orc_entry(&orc, cfi))
+				/* errors are reported on the original insn */
+				if (init_orc_entry(&orc, cfi, insn))
 					return -1;
 				if (!memcmp(&prev_orc, &orc, sizeof(orc)))
 					continue;