Merge tag 'objtool-core-2021-02-23' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull objtool updates from Thomas Gleixner:

 - Make objtool work for big-endian cross compiles

 - Make stack tracking via stack pointer memory operations match
   push/pop semantics to prepare for architectures w/o PUSH/POP
   instructions.

 - Add support for analyzing alternatives

 - Improve retpoline detection and handling

 - Improve assembly code coverage on x86

 - Provide support for inlined stack switching

* tag 'objtool-core-2021-02-23' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (33 commits)
  objtool: Support stack-swizzle
  objtool,x86: Additionally decode: mov %rsp, (%reg)
  x86/unwind/orc: Change REG_SP_INDIRECT
  x86/power: Support objtool validation in hibernate_asm_64.S
  x86/power: Move restore_registers() to top of the file
  x86/power: Annotate indirect branches as safe
  x86/acpi: Support objtool validation in wakeup_64.S
  x86/acpi: Annotate indirect branch as safe
  x86/ftrace: Support objtool vmlinux.o validation in ftrace_64.S
  x86/xen/pvh: Annotate indirect branch as safe
  x86/xen: Support objtool vmlinux.o validation in xen-head.S
  x86/xen: Support objtool validation in xen-asm.S
  objtool: Add xen_start_kernel() to noreturn list
  objtool: Combine UNWIND_HINT_RET_OFFSET and UNWIND_HINT_FUNC
  objtool: Add asm version of STACK_FRAME_NON_STANDARD
  objtool: Assume only ELF functions do sibling calls
  x86/ftrace: Add UNWIND_HINT_FUNC annotation for ftrace_stub
  objtool: Support retpoline jump detection for vmlinux.o
  objtool: Fix ".cold" section suffix check for newer versions of GCC
  objtool: Fix retpoline detection in asm code
  ...

17 files changed, 206 insertions, 153 deletions

diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h
index a8c3d284fa46..95a448fbb44c 100644
--- a/arch/x86/include/asm/insn.h
+++ b/arch/x86/include/asm/insn.h
@@ -7,9 +7,12 @@
  * Copyright (C) IBM Corporation, 2009
  */
 
+#include <asm/byteorder.h>
 /* insn_attr_t is defined in inat.h */
 #include <asm/inat.h>
 
+#if defined(__BYTE_ORDER) ? __BYTE_ORDER == __LITTLE_ENDIAN : defined(__LITTLE_ENDIAN)
+
 struct insn_field {
 	union {
 		insn_value_t value;
@@ -20,6 +23,48 @@ struct insn_field {
 	unsigned char nbytes;
 };
 
+static inline void insn_field_set(struct insn_field *p, insn_value_t v,
+				  unsigned char n)
+{
+	p->value = v;
+	p->nbytes = n;
+}
+
+static inline void insn_set_byte(struct insn_field *p, unsigned char n,
+				 insn_byte_t v)
+{
+	p->bytes[n] = v;
+}
+
+#else
+
+struct insn_field {
+	insn_value_t value;
+	union {
+		insn_value_t little;
+		insn_byte_t bytes[4];
+	};
+	/* !0 if we've run insn_get_xxx() for this field */
+	unsigned char got;
+	unsigned char nbytes;
+};
+
+static inline void insn_field_set(struct insn_field *p, insn_value_t v,
+				  unsigned char n)
+{
+	p->value = v;
+	p->little = __cpu_to_le32(v);
+	p->nbytes = n;
+}
+
+static inline void insn_set_byte(struct insn_field *p, unsigned char n,
+				 insn_byte_t v)
+{
+	p->bytes[n] = v;
+	p->value = __le32_to_cpu(p->little);
+}
+#endif
+
 struct insn {
 	struct insn_field prefixes;	/*
 					 * Prefixes
diff --git a/arch/x86/include/asm/orc_types.h b/arch/x86/include/asm/orc_types.h
index fdbffec4cfde..5a2baf28a1dc 100644
--- a/arch/x86/include/asm/orc_types.h
+++ b/arch/x86/include/asm/orc_types.h
@@ -40,6 +40,8 @@
 #define ORC_REG_MAX			15
 
 #ifndef __ASSEMBLY__
+#include <asm/byteorder.h>
+
 /*
  * This struct is more or less a vastly simplified version of the DWARF Call
  * Frame Information standard.  It contains only the necessary parts of DWARF
@@ -51,10 +53,18 @@
 struct orc_entry {
 	s16		sp_offset;
 	s16		bp_offset;
+#if defined(__LITTLE_ENDIAN_BITFIELD)
 	unsigned	sp_reg:4;
 	unsigned	bp_reg:4;
 	unsigned	type:2;
 	unsigned	end:1;
+#elif defined(__BIG_ENDIAN_BITFIELD)
+	unsigned	bp_reg:4;
+	unsigned	sp_reg:4;
+	unsigned	unused:5;
+	unsigned	end:1;
+	unsigned	type:2;
+#endif
 } __packed;
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/x86/include/asm/unwind_hints.h b/arch/x86/include/asm/unwind_hints.h
index 664d4610d700..8e574c0afef8 100644
--- a/arch/x86/include/asm/unwind_hints.h
+++ b/arch/x86/include/asm/unwind_hints.h
@@ -48,17 +48,8 @@
 	UNWIND_HINT_REGS base=\base offset=\offset partial=1
 .endm
 
-.macro UNWIND_HINT_FUNC sp_offset=8
-	UNWIND_HINT sp_reg=ORC_REG_SP sp_offset=\sp_offset type=UNWIND_HINT_TYPE_CALL
-.endm
-
-/*
- * RET_OFFSET: Used on instructions that terminate a function; mostly RETURN
- * and sibling calls. On these, sp_offset denotes the expected offset from
- * initial_func_cfi.
- */
-.macro UNWIND_HINT_RET_OFFSET sp_offset=8
-	UNWIND_HINT sp_reg=ORC_REG_SP type=UNWIND_HINT_TYPE_RET_OFFSET sp_offset=\sp_offset
+.macro UNWIND_HINT_FUNC
+	UNWIND_HINT sp_reg=ORC_REG_SP sp_offset=8 type=UNWIND_HINT_TYPE_FUNC
 .endm
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/x86/kernel/acpi/Makefile b/arch/x86/kernel/acpi/Makefile
index f1bb57b0e41e..cf340d85946a 100644
--- a/arch/x86/kernel/acpi/Makefile
+++ b/arch/x86/kernel/acpi/Makefile
@@ -1,5 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
-OBJECT_FILES_NON_STANDARD_wakeup_$(BITS).o := y
 
 obj-$(CONFIG_ACPI)		+= boot.o
 obj-$(CONFIG_ACPI_SLEEP)	+= sleep.o wakeup_$(BITS).o
diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S
index 5d3a0b8fd379..56b6865afb2a 100644
--- a/arch/x86/kernel/acpi/wakeup_64.S
+++ b/arch/x86/kernel/acpi/wakeup_64.S
@@ -1,12 +1,14 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 .text
 #include <linux/linkage.h>
+#include <linux/objtool.h>
 #include <asm/segment.h>
 #include <asm/pgtable_types.h>
 #include <asm/page_types.h>
 #include <asm/msr.h>
 #include <asm/asm-offsets.h>
 #include <asm/frame.h>
+#include <asm/nospec-branch.h>
 
 # Copyright 2003 Pavel Machek <pavel@suse.cz
 
@@ -39,6 +41,7 @@ SYM_FUNC_START(wakeup_long64)
 	movq	saved_rbp, %rbp
 
 	movq	saved_rip, %rax
+	ANNOTATE_RETPOLINE_SAFE
 	jmp	*%rax
 SYM_FUNC_END(wakeup_long64)
 
@@ -126,6 +129,7 @@ SYM_FUNC_START(do_suspend_lowlevel)
 	FRAME_END
 	jmp	restore_processor_state
 SYM_FUNC_END(do_suspend_lowlevel)
+STACK_FRAME_NON_STANDARD do_suspend_lowlevel
 
 .data
 saved_rbp:		.quad	0
diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S
index 0d54099c2a3a..7c273846c687 100644
--- a/arch/x86/kernel/ftrace_64.S
+++ b/arch/x86/kernel/ftrace_64.S
@@ -184,6 +184,7 @@ SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL)
  * It is also used to copy the retq for trampolines.
  */
 SYM_INNER_LABEL_ALIGN(ftrace_stub, SYM_L_WEAK)
+	UNWIND_HINT_FUNC
 	retq
 SYM_FUNC_END(ftrace_epilogue)
 
@@ -276,7 +277,7 @@ SYM_INNER_LABEL(ftrace_regs_caller_end, SYM_L_GLOBAL)
 	restore_mcount_regs 8
 	/* Restore flags */
 	popfq
-	UNWIND_HINT_RET_OFFSET
+	UNWIND_HINT_FUNC
 	jmp	ftrace_epilogue
 
 SYM_FUNC_END(ftrace_regs_caller)
@@ -333,8 +334,7 @@ SYM_FUNC_START(ftrace_graph_caller)
 	retq
 SYM_FUNC_END(ftrace_graph_caller)
 
-SYM_CODE_START(return_to_handler)
-	UNWIND_HINT_EMPTY
+SYM_FUNC_START(return_to_handler)
 	subq  $24, %rsp
 
 	/* Save the return values */
@@ -349,5 +349,5 @@ SYM_CODE_START(return_to_handler)
 	movq (%rsp), %rax
 	addq $24, %rsp
 	JMP_NOSPEC rdi
-SYM_CODE_END(return_to_handler)
+SYM_FUNC_END(return_to_handler)
 #endif
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index 73f800100066..2a1d47f47eee 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -471,7 +471,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		break;
 
 	case ORC_REG_SP_INDIRECT:
-		sp = state->sp + orc->sp_offset;
+		sp = state->sp;
 		indirect = true;
 		break;
 
@@ -521,6 +521,9 @@ bool unwind_next_frame(struct unwind_state *state)
 	if (indirect) {
 		if (!deref_stack_reg(state, sp, &sp))
 			goto err;
+
+		if (orc->sp_reg == ORC_REG_SP_INDIRECT)
+			sp += orc->sp_offset;
 	}
 
 	/* Find IP, SP and possibly regs: */
diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c
index 404279563891..435630a6ec97 100644
--- a/arch/x86/lib/insn.c
+++ b/arch/x86/lib/insn.c
@@ -5,6 +5,7 @@
  * Copyright (C) IBM Corporation, 2002, 2004, 2009
  */
 
+#include <linux/kernel.h>
 #ifdef __KERNEL__
 #include <linux/string.h>
 #else
@@ -15,15 +16,28 @@
 
 #include <asm/emulate_prefix.h>
 
+#define leXX_to_cpu(t, r)						\
+({									\
+	__typeof__(t) v;						\
+	switch (sizeof(t)) {						\
+	case 4: v = le32_to_cpu(r); break;				\
+	case 2: v = le16_to_cpu(r); break;				\
+	case 1:	v = r; break;						\
+	default:							\
+		BUILD_BUG(); break;					\
+	}								\
+	v;								\
+})
+
 /* Verify next sizeof(t) bytes can be on the same instruction */
 #define validate_next(t, insn, n)	\
 	((insn)->next_byte + sizeof(t) + n <= (insn)->end_kaddr)
 
 #define __get_next(t, insn)	\
-	({ t r = *(t*)insn->next_byte; insn->next_byte += sizeof(t); r; })
+	({ t r = *(t*)insn->next_byte; insn->next_byte += sizeof(t); leXX_to_cpu(t, r); })
 
 #define __peek_nbyte_next(t, insn, n)	\
-	({ t r = *(t*)((insn)->next_byte + n); r; })
+	({ t r = *(t*)((insn)->next_byte + n); leXX_to_cpu(t, r); })
 
 #define get_next(t, insn)	\
 	({ if (unlikely(!validate_next(t, insn, 0))) goto err_out; __get_next(t, insn); })
@@ -147,9 +161,9 @@ found:
 			b = insn->prefixes.bytes[3];
 			for (i = 0; i < nb; i++)
 				if (prefixes->bytes[i] == lb)
-					prefixes->bytes[i] = b;
+					insn_set_byte(prefixes, i, b);
 		}
-		insn->prefixes.bytes[3] = lb;
+		insn_set_byte(&insn->prefixes, 3, lb);
 	}
 
 	/* Decode REX prefix */
@@ -157,8 +171,7 @@ found:
 		b = peek_next(insn_byte_t, insn);
 		attr = inat_get_opcode_attribute(b);
 		if (inat_is_rex_prefix(attr)) {
-			insn->rex_prefix.value = b;
-			insn->rex_prefix.nbytes = 1;
+			insn_field_set(&insn->rex_prefix, b, 1);
 			insn->next_byte++;
 			if (X86_REX_W(b))
 				/* REX.W overrides opnd_size */
@@ -181,13 +194,13 @@ found:
 			if (X86_MODRM_MOD(b2) != 3)
 				goto vex_end;
 		}
-		insn->vex_prefix.bytes[0] = b;
-		insn->vex_prefix.bytes[1] = b2;
+		insn_set_byte(&insn->vex_prefix, 0, b);
+		insn_set_byte(&insn->vex_prefix, 1, b2);
 		if (inat_is_evex_prefix(attr)) {
 			b2 = peek_nbyte_next(insn_byte_t, insn, 2);
-			insn->vex_prefix.bytes[2] = b2;
+			insn_set_byte(&insn->vex_prefix, 2, b2);
 			b2 = peek_nbyte_next(insn_byte_t, insn, 3);
-			insn->vex_prefix.bytes[3] = b2;
+			insn_set_byte(&insn->vex_prefix, 3, b2);
 			insn->vex_prefix.nbytes = 4;
 			insn->next_byte += 4;
 			if (insn->x86_64 && X86_VEX_W(b2))
@@ -195,7 +208,7 @@ found:
 				insn->opnd_bytes = 8;
 		} else if (inat_is_vex3_prefix(attr)) {
 			b2 = peek_nbyte_next(insn_byte_t, insn, 2);
-			insn->vex_prefix.bytes[2] = b2;
+			insn_set_byte(&insn->vex_prefix, 2, b2);
 			insn->vex_prefix.nbytes = 3;
 			insn->next_byte += 3;
 			if (insn->x86_64 && X86_VEX_W(b2))
@@ -207,7 +220,7 @@ found:
 			 * Makes it easier to decode vex.W, vex.vvvv,
 			 * vex.L and vex.pp. Masking with 0x7f sets vex.W == 0.
 			 */
-			insn->vex_prefix.bytes[2] = b2 & 0x7f;
+			insn_set_byte(&insn->vex_prefix, 2, b2 & 0x7f);
 			insn->vex_prefix.nbytes = 2;
 			insn->next_byte += 2;
 		}
@@ -243,7 +256,7 @@ void insn_get_opcode(struct insn *insn)
 
 	/* Get first opcode */
 	op = get_next(insn_byte_t, insn);
-	opcode->bytes[0] = op;
+	insn_set_byte(opcode, 0, op);
 	opcode->nbytes = 1;
 
 	/* Check if there is VEX prefix or not */
@@ -295,8 +308,7 @@ void insn_get_modrm(struct insn *insn)
 
 	if (inat_has_modrm(insn->attr)) {
 		mod = get_next(insn_byte_t, insn);
-		modrm->value = mod;
-		modrm->nbytes = 1;
+		insn_field_set(modrm, mod, 1);
 		if (inat_is_group(insn->attr)) {
 			pfx_id = insn_last_prefix_id(insn);
 			insn->attr = inat_get_group_attribute(mod, pfx_id,
@@ -334,7 +346,7 @@ int insn_rip_relative(struct insn *insn)
 	 * For rip-relative instructions, the mod field (top 2 bits)
 	 * is zero and the r/m field (bottom 3 bits) is 0x5.
 	 */
-	return (modrm->nbytes && (modrm->value & 0xc7) == 0x5);
+	return (modrm->nbytes && (modrm->bytes[0] & 0xc7) == 0x5);
 }
 
 /**
@@ -353,11 +365,11 @@ void insn_get_sib(struct insn *insn)
 	if (!insn->modrm.got)
 		insn_get_modrm(insn);
 	if (insn->modrm.nbytes) {
-		modrm = (insn_byte_t)insn->modrm.value;
+		modrm = insn->modrm.bytes[0];
 		if (insn->addr_bytes != 2 &&
 		    X86_MODRM_MOD(modrm) != 3 && X86_MODRM_RM(modrm) == 4) {
-			insn->sib.value = get_next(insn_byte_t, insn);
-			insn->sib.nbytes = 1;
+			insn_field_set(&insn->sib,
+				       get_next(insn_byte_t, insn), 1);
 		}
 	}
 	insn->sib.got = 1;
@@ -407,19 +419,18 @@ void insn_get_displacement(struct insn *insn)
 		if (mod == 3)
 			goto out;
 		if (mod == 1) {
-			insn->displacement.value = get_next(signed char, insn);
-			insn->displacement.nbytes = 1;
+			insn_field_set(&insn->displacement,
+				       get_next(signed char, insn), 1);
 		} else if (insn->addr_bytes == 2) {
 			if ((mod == 0 && rm == 6) || mod == 2) {
-				insn->displacement.value =
-					 get_next(short, insn);
-				insn->displacement.nbytes = 2;
+				insn_field_set(&insn->displacement,
+					       get_next(short, insn), 2);
 			}
 		} else {
 			if ((mod == 0 && rm == 5) || mod == 2 ||
 			    (mod == 0 && base == 5)) {
-				insn->displacement.value = get_next(int, insn);
-				insn->displacement.nbytes = 4;
+				insn_field_set(&insn->displacement,
+					       get_next(int, insn), 4);
 			}
 		}
 	}
@@ -435,18 +446,14 @@ static int __get_moffset(struct insn *insn)
 {
 	switch (insn->addr_bytes) {
 	case 2:
-		insn->moffset1.value = get_next(short, insn);
-		insn->moffset1.nbytes = 2;
+		insn_field_set(&insn->moffset1, get_next(short, insn), 2);
 		break;
 	case 4:
-		insn->moffset1.value = get_next(int, insn);
-		insn->moffset1.nbytes = 4;
+		insn_field_set(&insn->moffset1, get_next(int, insn), 4);
 		break;
 	case 8:
-		insn->moffset1.value = get_next(int, insn);
-		insn->moffset1.nbytes = 4;
-		insn->moffset2.value = get_next(int, insn);
-		insn->moffset2.nbytes = 4;
+		insn_field_set(&insn->moffset1, get_next(int, insn), 4);
+		insn_field_set(&insn->moffset2, get_next(int, insn), 4);
 		break;
 	default:	/* opnd_bytes must be modified manually */
 		goto err_out;
@@ -464,13 +471,11 @@ static int __get_immv32(struct insn *insn)
 {
 	switch (insn->opnd_bytes) {
 	case 2:
-		insn->immediate.value = get_next(short, insn);
-		insn->immediate.nbytes = 2;
+		insn_field_set(&insn->immediate, get_next(short, insn), 2);
 		break;
 	case 4:
 	case 8:
-		insn->immediate.value = get_next(int, insn);
-		insn->immediate.nbytes = 4;
+		insn_field_set(&insn->immediate, get_next(int, insn), 4);
 		break;
 	default:	/* opnd_bytes must be modified manually */
 		goto err_out;
@@ -487,18 +492,15 @@ static int __get_immv(struct insn *insn)
 {
 	switch (insn->opnd_bytes) {
 	case 2:
-		insn->immediate1.value = get_next(short, insn);
-		insn->immediate1.nbytes = 2;
+		insn_field_set(&insn->immediate1, get_next(short, insn), 2);
 		break;
 	case 4:
-		insn->immediate1.value = get_next(int, insn);
+		insn_field_set(&insn->immediate1, get_next(int, insn), 4);
 		insn->immediate1.nbytes = 4;
 		break;
 	case 8:
-		insn->immediate1.value = get_next(int, insn);
-		insn->immediate1.nbytes = 4;
-		insn->immediate2.value = get_next(int, insn);
-		insn->immediate2.nbytes = 4;
+		insn_field_set(&insn->immediate1, get_next(int, insn), 4);
+		insn_field_set(&insn->immediate2, get_next(int, insn), 4);
 		break;
 	default:	/* opnd_bytes must be modified manually */
 		goto err_out;
@@ -515,12 +517,10 @@ static int __get_immptr(struct insn *insn)
 {
 	switch (insn->opnd_bytes) {
 	case 2:
-		insn->immediate1.value = get_next(short, insn);
-		insn->immediate1.nbytes = 2;
+		insn_field_set(&insn->immediate1, get_next(short, insn), 2);
 		break;
 	case 4:
-		insn->immediate1.value = get_next(int, insn);
-		insn->immediate1.nbytes = 4;
+		insn_field_set(&insn->immediate1, get_next(int, insn), 4);
 		break;
 	case 8:
 		/* ptr16:64 is not exist (no segment) */
@@ -528,8 +528,7 @@ static int __get_immptr(struct insn *insn)
 	default:	/* opnd_bytes must be modified manually */
 		goto err_out;
 	}
-	insn->immediate2.value = get_next(unsigned short, insn);
-	insn->immediate2.nbytes = 2;
+	insn_field_set(&insn->immediate2, get_next(unsigned short, insn), 2);
 	insn->immediate1.got = insn->immediate2.got = 1;
 
 	return 1;
@@ -565,22 +564,17 @@ void insn_get_immediate(struct insn *insn)
 
 	switch (inat_immediate_size(insn->attr)) {
 	case INAT_IMM_BYTE:
-		insn->immediate.value = get_next(signed char, insn);
-		insn->immediate.nbytes = 1;
+		insn_field_set(&insn->immediate, get_next(signed char, insn), 1);
 		break;
 	case INAT_IMM_WORD:
-		insn->immediate.value = get_next(short, insn);
-		insn->immediate.nbytes = 2;
+		insn_field_set(&insn->immediate, get_next(short, insn), 2);
 		break;
 	case INAT_IMM_DWORD:
-		insn->immediate.value = get_next(int, insn);
-		insn->immediate.nbytes = 4;
+		insn_field_set(&insn->immediate, get_next(int, insn), 4);
 		break;
 	case INAT_IMM_QWORD:
-		insn->immediate1.value = get_next(int, insn);
-		insn->immediate1.nbytes = 4;
-		insn->immediate2.value = get_next(int, insn);
-		insn->immediate2.nbytes = 4;
+		insn_field_set(&insn->immediate1, get_next(int, insn), 4);
+		insn_field_set(&insn->immediate2, get_next(int, insn), 4);
 		break;
 	case INAT_IMM_PTR:
 		if (!__get_immptr(insn))
@@ -599,8 +593,7 @@ void insn_get_immediate(struct insn *insn)
 		goto err_out;
 	}
 	if (inat_has_second_immediate(insn->attr)) {
-		insn->immediate2.value = get_next(signed char, insn);
-		insn->immediate2.nbytes = 1;
+		insn_field_set(&insn->immediate2, get_next(signed char, insn), 1);
 	}
 done:
 	insn->immediate.got = 1;
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index b4c43a9b1483..f6fb1d218dcc 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -28,7 +28,7 @@ SYM_FUNC_START_NOALIGN(__x86_retpoline_\reg)
 	jmp	.Lspec_trap_\@
 .Ldo_rop_\@:
 	mov	%\reg, (%_ASM_SP)
-	UNWIND_HINT_RET_OFFSET
+	UNWIND_HINT_FUNC
 	ret
 SYM_FUNC_END(__x86_retpoline_\reg)
 
diff --git a/arch/x86/platform/pvh/head.S b/arch/x86/platform/pvh/head.S
index 43b4d864817e..d2ccadc247e6 100644
--- a/arch/x86/platform/pvh/head.S
+++ b/arch/x86/platform/pvh/head.S
@@ -16,6 +16,7 @@
 #include <asm/boot.h>
 #include <asm/processor-flags.h>
 #include <asm/msr.h>
+#include <asm/nospec-branch.h>
 #include <xen/interface/elfnote.h>
 
 	__HEAD
@@ -105,6 +106,7 @@ SYM_CODE_START_LOCAL(pvh_start_xen)
 	/* startup_64 expects boot_params in %rsi. */
 	mov $_pa(pvh_bootparams), %rsi
 	mov $_pa(startup_64), %rax
+	ANNOTATE_RETPOLINE_SAFE
 	jmp *%rax
 
 #else /* CONFIG_X86_64 */
diff --git a/arch/x86/power/Makefile b/arch/x86/power/Makefile
index 6907b523e856..3ff80156f21a 100644
--- a/arch/x86/power/Makefile
+++ b/arch/x86/power/Makefile
@@ -1,5 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
-OBJECT_FILES_NON_STANDARD_hibernate_asm_$(BITS).o := y
 
 # __restore_processor_state() restores %gs after S3 resume and so should not
 # itself be stack-protected
diff --git a/arch/x86/power/hibernate_asm_64.S b/arch/x86/power/hibernate_asm_64.S
index 7918b8415f13..d9bed596d849 100644
--- a/arch/x86/power/hibernate_asm_64.S
+++ b/arch/x86/power/hibernate_asm_64.S
@@ -21,6 +21,53 @@
 #include <asm/asm-offsets.h>
 #include <asm/processor-flags.h>
 #include <asm/frame.h>
+#include <asm/nospec-branch.h>
+
+	 /* code below belongs to the image kernel */
+	.align PAGE_SIZE
+SYM_FUNC_START(restore_registers)
+	/* go back to the original page tables */
+	movq    %r9, %cr3
+
+	/* Flush TLB, including "global" things (vmalloc) */
+	movq	mmu_cr4_features(%rip), %rax
+	movq	%rax, %rdx
+	andq	$~(X86_CR4_PGE), %rdx
+	movq	%rdx, %cr4;  # turn off PGE
+	movq	%cr3, %rcx;  # flush TLB
+	movq	%rcx, %cr3
+	movq	%rax, %cr4;  # turn PGE back on
+
+	/* We don't restore %rax, it must be 0 anyway */
+	movq	$saved_context, %rax
+	movq	pt_regs_sp(%rax), %rsp
+	movq	pt_regs_bp(%rax), %rbp
+	movq	pt_regs_si(%rax), %rsi
+	movq	pt_regs_di(%rax), %rdi
+	movq	pt_regs_bx(%rax), %rbx
+	movq	pt_regs_cx(%rax), %rcx
+	movq	pt_regs_dx(%rax), %rdx
+	movq	pt_regs_r8(%rax), %r8
+	movq	pt_regs_r9(%rax), %r9
+	movq	pt_regs_r10(%rax), %r10
+	movq	pt_regs_r11(%rax), %r11
+	movq	pt_regs_r12(%rax), %r12
+	movq	pt_regs_r13(%rax), %r13
+	movq	pt_regs_r14(%rax), %r14
+	movq	pt_regs_r15(%rax), %r15
+	pushq	pt_regs_flags(%rax)
+	popfq
+
+	/* Saved in save_processor_state. */
+	lgdt	saved_context_gdt_desc(%rax)
+
+	xorl	%eax, %eax
+
+	/* tell the hibernation core that we've just restored the memory */
+	movq	%rax, in_suspend(%rip)
+
+	ret
+SYM_FUNC_END(restore_registers)
 
 SYM_FUNC_START(swsusp_arch_suspend)
 	movq	$saved_context, %rax
@@ -52,7 +99,7 @@ SYM_FUNC_START(swsusp_arch_suspend)
 	ret
 SYM_FUNC_END(swsusp_arch_suspend)
 
-SYM_CODE_START(restore_image)
+SYM_FUNC_START(restore_image)
 	/* prepare to jump to the image kernel */
 	movq	restore_jump_address(%rip), %r8
 	movq	restore_cr3(%rip), %r9
@@ -66,11 +113,12 @@ SYM_CODE_START(restore_image)
 
 	/* jump to relocated restore code */
 	movq	relocated_restore_code(%rip), %rcx
+	ANNOTATE_RETPOLINE_SAFE
 	jmpq	*%rcx
-SYM_CODE_END(restore_image)
+SYM_FUNC_END(restore_image)
 
 	/* code below has been relocated to a safe page */
-SYM_CODE_START(core_restore_code)
+SYM_FUNC_START(core_restore_code)
 	/* switch to temporary page tables */
 	movq	%rax, %cr3
 	/* flush TLB */
@@ -97,51 +145,6 @@ SYM_CODE_START(core_restore_code)
 
 .Ldone:
 	/* jump to the restore_registers address from the image header */
+	ANNOTATE_RETPOLINE_SAFE
 	jmpq	*%r8
-SYM_CODE_END(core_restore_code)
-
-	 /* code below belongs to the image kernel */
-	.align PAGE_SIZE
-SYM_FUNC_START(restore_registers)
-	/* go back to the original page tables */
-	movq    %r9, %cr3
-
-	/* Flush TLB, including "global" things (vmalloc) */
-	movq	mmu_cr4_features(%rip), %rax
-	movq	%rax, %rdx
-	andq	$~(X86_CR4_PGE), %rdx
-	movq	%rdx, %cr4;  # turn off PGE
-	movq	%cr3, %rcx;  # flush TLB
-	movq	%rcx, %cr3
-	movq	%rax, %cr4;  # turn PGE back on
-
-	/* We don't restore %rax, it must be 0 anyway */
-	movq	$saved_context, %rax
-	movq	pt_regs_sp(%rax), %rsp
-	movq	pt_regs_bp(%rax), %rbp
-	movq	pt_regs_si(%rax), %rsi
-	movq	pt_regs_di(%rax), %rdi
-	movq	pt_regs_bx(%rax), %rbx
-	movq	pt_regs_cx(%rax), %rcx
-	movq	pt_regs_dx(%rax), %rdx
-	movq	pt_regs_r8(%rax), %r8
-	movq	pt_regs_r9(%rax), %r9
-	movq	pt_regs_r10(%rax), %r10
-	movq	pt_regs_r11(%rax), %r11
-	movq	pt_regs_r12(%rax), %r12
-	movq	pt_regs_r13(%rax), %r13
-	movq	pt_regs_r14(%rax), %r14
-	movq	pt_regs_r15(%rax), %r15
-	pushq	pt_regs_flags(%rax)
-	popfq
-
-	/* Saved in save_processor_state. */
-	lgdt	saved_context_gdt_desc(%rax)
-
-	xorl	%eax, %eax
-
-	/* tell the hibernation core that we've just restored the memory */
-	movq	%rax, in_suspend(%rip)
-
-	ret
-SYM_FUNC_END(restore_registers)
+SYM_FUNC_END(core_restore_code)
diff --git a/arch/x86/tools/Makefile b/arch/x86/tools/Makefile
index 55b1ab378974..bddfc9a46645 100644
--- a/arch/x86/tools/Makefile
+++ b/arch/x86/tools/Makefile
@@ -29,14 +29,14 @@ posttest: $(obj)/insn_decoder_test vmlinux $(obj)/insn_sanity
 hostprogs += insn_decoder_test insn_sanity
 
 # -I needed for generated C source and C source which in the kernel tree.
-HOSTCFLAGS_insn_decoder_test.o := -Wall -I$(objtree)/arch/x86/lib/ -I$(srctree)/arch/x86/include/uapi/ -I$(srctree)/arch/x86/include/ -I$(srctree)/arch/x86/lib/ -I$(srctree)/include/uapi/
+HOSTCFLAGS_insn_decoder_test.o := -Wall -I$(srctree)/tools/arch/x86/lib/ -I$(srctree)/tools/arch/x86/include/ -I$(objtree)/arch/x86/lib/
 
-HOSTCFLAGS_insn_sanity.o := -Wall -I$(objtree)/arch/x86/lib/ -I$(srctree)/arch/x86/include/ -I$(srctree)/arch/x86/lib/ -I$(srctree)/include/
+HOSTCFLAGS_insn_sanity.o := -Wall -I$(srctree)/tools/arch/x86/lib/ -I$(srctree)/tools/arch/x86/include/ -I$(objtree)/arch/x86/lib/
 
 # Dependencies are also needed.
-$(obj)/insn_decoder_test.o: $(srctree)/arch/x86/lib/insn.c $(srctree)/arch/x86/lib/inat.c $(srctree)/arch/x86/include/asm/inat_types.h $(srctree)/arch/x86/include/asm/inat.h $(srctree)/arch/x86/include/asm/insn.h $(objtree)/arch/x86/lib/inat-tables.c
+$(obj)/insn_decoder_test.o: $(srctree)/tools/arch/x86/lib/insn.c $(srctree)/tools/arch/x86/lib/inat.c $(srctree)/tools/arch/x86/include/asm/inat_types.h $(srctree)/tools/arch/x86/include/asm/inat.h $(srctree)/tools/arch/x86/include/asm/insn.h $(objtree)/arch/x86/lib/inat-tables.c
 
-$(obj)/insn_sanity.o: $(srctree)/arch/x86/lib/insn.c $(srctree)/arch/x86/lib/inat.c $(srctree)/arch/x86/include/asm/inat_types.h $(srctree)/arch/x86/include/asm/inat.h $(srctree)/arch/x86/include/asm/insn.h $(objtree)/arch/x86/lib/inat-tables.c
+$(obj)/insn_sanity.o: $(srctree)/tools/arch/x86/lib/insn.c $(srctree)/tools/arch/x86/lib/inat.c $(srctree)/tools/arch/x86/include/asm/inat_types.h $(srctree)/tools/arch/x86/include/asm/inat.h $(srctree)/tools/arch/x86/include/asm/insn.h $(objtree)/arch/x86/lib/inat-tables.c
 
 HOST_EXTRACFLAGS += -I$(srctree)/tools/include
 hostprogs	+= relocs
diff --git a/arch/x86/tools/insn_sanity.c b/arch/x86/tools/insn_sanity.c
index 185ceba9d289..c6a0000ae635 100644
--- a/arch/x86/tools/insn_sanity.c
+++ b/arch/x86/tools/insn_sanity.c
@@ -14,10 +14,6 @@
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <fcntl.h>
-
-#define unlikely(cond) (cond)
-#define ARRAY_SIZE(a)	(sizeof(a)/sizeof(a[0]))
-
 #include <asm/insn.h>
 #include <inat.c>
 #include <insn.c>
diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile
index fc5c5ba4aacb..40b5779fce21 100644
--- a/arch/x86/xen/Makefile
+++ b/arch/x86/xen/Makefile
@@ -1,5 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
-OBJECT_FILES_NON_STANDARD_xen-asm.o := y
 
 ifdef CONFIG_FUNCTION_TRACER
 # Do not profile debug and lowlevel utilities
diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S
index 02f31341e435..1e626444712b 100644
--- a/arch/x86/xen/xen-asm.S
+++ b/arch/x86/xen/xen-asm.S
@@ -14,6 +14,7 @@
 #include <asm/thread_info.h>
 #include <asm/asm.h>
 #include <asm/frame.h>
+#include <asm/unwind_hints.h>
 
 #include <xen/interface/xen.h>
 
@@ -118,6 +119,7 @@ SYM_FUNC_END(xen_read_cr2_direct);
 
 .macro xen_pv_trap name
 SYM_CODE_START(xen_\name)
+	UNWIND_HINT_EMPTY
 	pop %rcx
 	pop %r11
 	jmp  \name
@@ -157,6 +159,7 @@ xen_pv_trap asm_exc_xen_hypervisor_callback
 SYM_CODE_START(xen_early_idt_handler_array)
 	i = 0
 	.rept NUM_EXCEPTION_VECTORS
+	UNWIND_HINT_EMPTY
 	pop %rcx
 	pop %r11
 	jmp early_idt_handler_array + i*EARLY_IDT_HANDLER_SIZE
@@ -183,6 +186,7 @@ hypercall_iret = hypercall_page + __HYPERVISOR_iret * 32
  * rsp->rax		}
  */
 SYM_CODE_START(xen_iret)
+	UNWIND_HINT_EMPTY
 	pushq $0
 	jmp hypercall_iret
 SYM_CODE_END(xen_iret)
@@ -203,7 +207,8 @@ SYM_CODE_END(xen_iret)
  */
 
 /* Normal 64-bit system call target */
-SYM_FUNC_START(xen_syscall_target)
+SYM_CODE_START(xen_syscall_target)
+	UNWIND_HINT_EMPTY
 	popq %rcx
 	popq %r11
 
@@ -216,12 +221,13 @@ SYM_FUNC_START(xen_syscall_target)
 	movq $__USER_CS, 1*8(%rsp)
 
 	jmp entry_SYSCALL_64_after_hwframe
-SYM_FUNC_END(xen_syscall_target)
+SYM_CODE_END(xen_syscall_target)
 
 #ifdef CONFIG_IA32_EMULATION
 
 /* 32-bit compat syscall target */
-SYM_FUNC_START(xen_syscall32_target)
+SYM_CODE_START(xen_syscall32_target)
+	UNWIND_HINT_EMPTY
 	popq %rcx
 	popq %r11
 
@@ -234,10 +240,11 @@ SYM_FUNC_START(xen_syscall32_target)
 	movq $__USER32_CS, 1*8(%rsp)
 
 	jmp entry_SYSCALL_compat_after_hwframe
-SYM_FUNC_END(xen_syscall32_target)
+SYM_CODE_END(xen_syscall32_target)
 
 /* 32-bit compat sysenter target */
-SYM_FUNC_START(xen_sysenter_target)
+SYM_CODE_START(xen_sysenter_target)
+	UNWIND_HINT_EMPTY
 	/*
 	 * NB: Xen is polite and clears TF from EFLAGS for us.  This means
 	 * that we don't need to guard against single step exceptions here.
@@ -254,17 +261,18 @@ SYM_FUNC_START(xen_sysenter_target)
 	movq $__USER32_CS, 1*8(%rsp)
 
 	jmp entry_SYSENTER_compat_after_hwframe
-SYM_FUNC_END(xen_sysenter_target)
+SYM_CODE_END(xen_sysenter_target)
 
 #else /* !CONFIG_IA32_EMULATION */
 
-SYM_FUNC_START_ALIAS(xen_syscall32_target)
-SYM_FUNC_START(xen_sysenter_target)
+SYM_CODE_START(xen_syscall32_target)
+SYM_CODE_START(xen_sysenter_target)
+	UNWIND_HINT_EMPTY
 	lea 16(%rsp), %rsp	/* strip %rcx, %r11 */
 	mov $-ENOSYS, %rax
 	pushq $0
 	jmp hypercall_iret
-SYM_FUNC_END(xen_sysenter_target)
-SYM_FUNC_END_ALIAS(xen_syscall32_target)
+SYM_CODE_END(xen_sysenter_target)
+SYM_CODE_END(xen_syscall32_target)
 
 #endif	/* CONFIG_IA32_EMULATION */
diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index 2d7c8f34f56c..cb6538ae2fe0 100644
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -68,8 +68,9 @@ SYM_CODE_END(asm_cpu_bringup_and_idle)
 	.balign PAGE_SIZE
 SYM_CODE_START(hypercall_page)
 	.rept (PAGE_SIZE / 32)
-		UNWIND_HINT_EMPTY
-		.skip 32
+		UNWIND_HINT_FUNC
+		.skip 31, 0x90
+		ret
 	.endr
 
 #define HYPERCALL(n) \