Merge tag 'x86_core_for_v5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 updates from Borislav Petkov:

 - Turn the stack canary into a normal __percpu variable on 32-bit which
   gets rid of the LAZY_GS stuff and a lot of code.

 - Add an insn_decode() API which all users of the instruction decoder
   should preferrably use. Its goal is to keep the details of the
   instruction decoder away from its users and simplify and streamline
   how one decodes insns in the kernel. Convert its users to it.

 - kprobes improvements and fixes

 - Set the maximum DIE per package variable on Hygon

 - Rip out the dynamic NOP selection and simplify all the machinery
   around selecting NOPs. Use the simplified NOPs in objtool now too.

 - Add Xeon Sapphire Rapids to list of CPUs that support PPIN

 - Simplify the retpolines by folding the entire thing into an
   alternative now that objtool can handle alternatives with stack ops.
   Then, have objtool rewrite the call to the retpoline with the
   alternative which then will get patched at boot time.

 - Document Intel uarch per models in intel-family.h

 - Make Sub-NUMA Clustering topology the default and Cluster-on-Die the
   exception on Intel.

* tag 'x86_core_for_v5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (53 commits)
  x86, sched: Treat Intel SNC topology as default, COD as exception
  x86/cpu: Comment Skylake server stepping too
  x86/cpu: Resort and comment Intel models
  objtool/x86: Rewrite retpoline thunk calls
  objtool: Skip magical retpoline .altinstr_replacement
  objtool: Cache instruction relocs
  objtool: Keep track of retpoline call sites
  objtool: Add elf_create_undef_symbol()
  objtool: Extract elf_symbol_add()
  objtool: Extract elf_strtab_concat()
  objtool: Create reloc sections implicitly
  objtool: Add elf_create_reloc() helper
  objtool: Rework the elf_rebuild_reloc_section() logic
  objtool: Fix static_call list generation
  objtool: Handle per arch retpoline naming
  objtool: Correctly handle retpoline thunk calls
  x86/retpoline: Simplify retpolines
  x86/alternatives: Optimize optimize_nops()
  x86: Add insn_decode_kernel()
  x86/kprobes: Move 'inline' to the beginning of the kprobe_is_ss() declaration
  ...

22 files changed, 869 insertions, 318 deletions

diff --git a/tools/arch/x86/include/asm/inat.h b/tools/arch/x86/include/asm/inat.h
index 877827b7c2c3..a61051400311 100644
--- a/tools/arch/x86/include/asm/inat.h
+++ b/tools/arch/x86/include/asm/inat.h
@@ -6,7 +6,7 @@
  *
  * Written by Masami Hiramatsu <mhiramat@redhat.com>
  */
-#include "inat_types.h"
+#include "inat_types.h" /* __ignore_sync_check__ */
 
 /*
  * Internal bits. Don't use bitmasks directly, because these bits are
diff --git a/tools/arch/x86/include/asm/insn.h b/tools/arch/x86/include/asm/insn.h
index cc777c185212..dc632b41f135 100644
--- a/tools/arch/x86/include/asm/insn.h
+++ b/tools/arch/x86/include/asm/insn.h
@@ -9,7 +9,7 @@
 
 #include <asm/byteorder.h>
 /* insn_attr_t is defined in inat.h */
-#include "inat.h"
+#include "inat.h" /* __ignore_sync_check__ */
 
 #if defined(__BYTE_ORDER) ? __BYTE_ORDER == __LITTLE_ENDIAN : defined(__LITTLE_ENDIAN)
 
@@ -132,13 +132,25 @@ struct insn {
 #define X86_VEX_M_MAX	0x1f			/* VEX3.M Maximum value */
 
 extern void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64);
-extern void insn_get_prefixes(struct insn *insn);
-extern void insn_get_opcode(struct insn *insn);
-extern void insn_get_modrm(struct insn *insn);
-extern void insn_get_sib(struct insn *insn);
-extern void insn_get_displacement(struct insn *insn);
-extern void insn_get_immediate(struct insn *insn);
-extern void insn_get_length(struct insn *insn);
+extern int insn_get_prefixes(struct insn *insn);
+extern int insn_get_opcode(struct insn *insn);
+extern int insn_get_modrm(struct insn *insn);
+extern int insn_get_sib(struct insn *insn);
+extern int insn_get_displacement(struct insn *insn);
+extern int insn_get_immediate(struct insn *insn);
+extern int insn_get_length(struct insn *insn);
+
+enum insn_mode {
+	INSN_MODE_32,
+	INSN_MODE_64,
+	/* Mode is determined by the current kernel build. */
+	INSN_MODE_KERN,
+	INSN_NUM_MODES,
+};
+
+extern int insn_decode(struct insn *insn, const void *kaddr, int buf_len, enum insn_mode m);
+
+#define insn_decode_kernel(_insn, _ptr) insn_decode((_insn), (_ptr), MAX_INSN_SIZE, INSN_MODE_KERN)
 
 /* Attribute will be determined after getting ModRM (for opcode groups) */
 static inline void insn_get_attribute(struct insn *insn)
@@ -149,17 +161,6 @@ static inline void insn_get_attribute(struct insn *insn)
 /* Instruction uses RIP-relative addressing */
 extern int insn_rip_relative(struct insn *insn);
 
-/* Init insn for kernel text */
-static inline void kernel_insn_init(struct insn *insn,
-				    const void *kaddr, int buf_len)
-{
-#ifdef CONFIG_X86_64
-	insn_init(insn, kaddr, buf_len, 1);
-#else /* CONFIG_X86_32 */
-	insn_init(insn, kaddr, buf_len, 0);
-#endif
-}
-
 static inline int insn_is_avx(struct insn *insn)
 {
 	if (!insn->prefixes.got)
@@ -179,13 +180,6 @@ static inline int insn_has_emulate_prefix(struct insn *insn)
 	return !!insn->emulate_prefix_size;
 }
 
-/* Ensure this instruction is decoded completely */
-static inline int insn_complete(struct insn *insn)
-{
-	return insn->opcode.got && insn->modrm.got && insn->sib.got &&
-		insn->displacement.got && insn->immediate.got;
-}
-
 static inline insn_byte_t insn_vex_m_bits(struct insn *insn)
 {
 	if (insn->vex_prefix.nbytes == 2)	/* 2 bytes VEX */
diff --git a/tools/arch/x86/include/asm/nops.h b/tools/arch/x86/include/asm/nops.h
new file mode 100644
index 000000000000..c1e5e818ba16
--- /dev/null
+++ b/tools/arch/x86/include/asm/nops.h
@@ -0,0 +1,81 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_NOPS_H
+#define _ASM_X86_NOPS_H
+
+/*
+ * Define nops for use with alternative() and for tracing.
+ */
+
+#ifndef CONFIG_64BIT
+
+/*
+ * Generic 32bit nops from GAS:
+ *
+ * 1: nop
+ * 2: movl %esi,%esi
+ * 3: leal 0x0(%esi),%esi
+ * 4: leal 0x0(%esi,%eiz,1),%esi
+ * 5: leal %ds:0x0(%esi,%eiz,1),%esi
+ * 6: leal 0x0(%esi),%esi
+ * 7: leal 0x0(%esi,%eiz,1),%esi
+ * 8: leal %ds:0x0(%esi,%eiz,1),%esi
+ *
+ * Except 5 and 8, which are DS prefixed 4 and 7 resp, where GAS would emit 2
+ * nop instructions.
+ */
+#define BYTES_NOP1	0x90
+#define BYTES_NOP2	0x89,0xf6
+#define BYTES_NOP3	0x8d,0x76,0x00
+#define BYTES_NOP4	0x8d,0x74,0x26,0x00
+#define BYTES_NOP5	0x3e,BYTES_NOP4
+#define BYTES_NOP6	0x8d,0xb6,0x00,0x00,0x00,0x00
+#define BYTES_NOP7	0x8d,0xb4,0x26,0x00,0x00,0x00,0x00
+#define BYTES_NOP8	0x3e,BYTES_NOP7
+
+#else
+
+/*
+ * Generic 64bit nops from GAS:
+ *
+ * 1: nop
+ * 2: osp nop
+ * 3: nopl (%eax)
+ * 4: nopl 0x00(%eax)
+ * 5: nopl 0x00(%eax,%eax,1)
+ * 6: osp nopl 0x00(%eax,%eax,1)
+ * 7: nopl 0x00000000(%eax)
+ * 8: nopl 0x00000000(%eax,%eax,1)
+ */
+#define BYTES_NOP1	0x90
+#define BYTES_NOP2	0x66,BYTES_NOP1
+#define BYTES_NOP3	0x0f,0x1f,0x00
+#define BYTES_NOP4	0x0f,0x1f,0x40,0x00
+#define BYTES_NOP5	0x0f,0x1f,0x44,0x00,0x00
+#define BYTES_NOP6	0x66,BYTES_NOP5
+#define BYTES_NOP7	0x0f,0x1f,0x80,0x00,0x00,0x00,0x00
+#define BYTES_NOP8	0x0f,0x1f,0x84,0x00,0x00,0x00,0x00,0x00
+
+#endif /* CONFIG_64BIT */
+
+#ifdef __ASSEMBLY__
+#define _ASM_MK_NOP(x) .byte x
+#else
+#define _ASM_MK_NOP(x) ".byte " __stringify(x) "\n"
+#endif
+
+#define ASM_NOP1 _ASM_MK_NOP(BYTES_NOP1)
+#define ASM_NOP2 _ASM_MK_NOP(BYTES_NOP2)
+#define ASM_NOP3 _ASM_MK_NOP(BYTES_NOP3)
+#define ASM_NOP4 _ASM_MK_NOP(BYTES_NOP4)
+#define ASM_NOP5 _ASM_MK_NOP(BYTES_NOP5)
+#define ASM_NOP6 _ASM_MK_NOP(BYTES_NOP6)
+#define ASM_NOP7 _ASM_MK_NOP(BYTES_NOP7)
+#define ASM_NOP8 _ASM_MK_NOP(BYTES_NOP8)
+
+#define ASM_NOP_MAX 8
+
+#ifndef __ASSEMBLY__
+extern const unsigned char * const x86_nops[];
+#endif
+
+#endif /* _ASM_X86_NOPS_H */
diff --git a/tools/arch/x86/lib/inat.c b/tools/arch/x86/lib/inat.c
index 4f5ed49e1b4e..dfbcc6405941 100644
--- a/tools/arch/x86/lib/inat.c
+++ b/tools/arch/x86/lib/inat.c
@@ -4,7 +4,7 @@
  *
  * Written by Masami Hiramatsu <mhiramat@redhat.com>
  */
-#include "../include/asm/insn.h"
+#include "../include/asm/insn.h" /* __ignore_sync_check__ */
 
 /* Attribute tables are generated from opcode map */
 #include "inat-tables.c"
diff --git a/tools/arch/x86/lib/insn.c b/tools/arch/x86/lib/insn.c
index 3d9355ed1246..c41f95815480 100644
--- a/tools/arch/x86/lib/insn.c
+++ b/tools/arch/x86/lib/insn.c
@@ -11,10 +11,13 @@
 #else
 #include <string.h>
 #endif
-#include "../include/asm/inat.h"
-#include "../include/asm/insn.h"
+#include "../include/asm/inat.h" /* __ignore_sync_check__ */
+#include "../include/asm/insn.h" /* __ignore_sync_check__ */
 
-#include "../include/asm/emulate_prefix.h"
+#include <linux/errno.h>
+#include <linux/kconfig.h>
+
+#include "../include/asm/emulate_prefix.h" /* __ignore_sync_check__ */
 
 #define leXX_to_cpu(t, r)						\
 ({									\
@@ -51,6 +54,7 @@
  * insn_init() - initialize struct insn
  * @insn:	&struct insn to be initialized
  * @kaddr:	address (in kernel memory) of instruction (or copy thereof)
+ * @buf_len:	length of the insn buffer at @kaddr
  * @x86_64:	!0 for 64-bit kernel or 64-bit app
  */
 void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64)
@@ -111,8 +115,12 @@ static void insn_get_emulate_prefix(struct insn *insn)
  * Populates the @insn->prefixes bitmap, and updates @insn->next_byte
  * to point to the (first) opcode.  No effect if @insn->prefixes.got
  * is already set.
+ *
+ * * Returns:
+ * 0:  on success
+ * < 0: on error
  */
-void insn_get_prefixes(struct insn *insn)
+int insn_get_prefixes(struct insn *insn)
 {
 	struct insn_field *prefixes = &insn->prefixes;
 	insn_attr_t attr;
@@ -120,7 +128,7 @@ void insn_get_prefixes(struct insn *insn)
 	int i, nb;
 
 	if (prefixes->got)
-		return;
+		return 0;
 
 	insn_get_emulate_prefix(insn);
 
@@ -230,8 +238,10 @@ vex_end:
 
 	prefixes->got = 1;
 
+	return 0;
+
 err_out:
-	return;
+	return -ENODATA;
 }
 
 /**
@@ -243,16 +253,25 @@ err_out:
  * If necessary, first collects any preceding (prefix) bytes.
  * Sets @insn->opcode.value = opcode1.  No effect if @insn->opcode.got
  * is already 1.
+ *
+ * Returns:
+ * 0:  on success
+ * < 0: on error
  */
-void insn_get_opcode(struct insn *insn)
+int insn_get_opcode(struct insn *insn)
 {
 	struct insn_field *opcode = &insn->opcode;
+	int pfx_id, ret;
 	insn_byte_t op;
-	int pfx_id;
+
 	if (opcode->got)
-		return;
-	if (!insn->prefixes.got)
-		insn_get_prefixes(insn);
+		return 0;
+
+	if (!insn->prefixes.got) {
+		ret = insn_get_prefixes(insn);
+		if (ret)
+			return ret;
+	}
 
 	/* Get first opcode */
 	op = get_next(insn_byte_t, insn);
@@ -267,9 +286,13 @@ void insn_get_opcode(struct insn *insn)
 		insn->attr = inat_get_avx_attribute(op, m, p);
 		if ((inat_must_evex(insn->attr) && !insn_is_evex(insn)) ||
 		    (!inat_accept_vex(insn->attr) &&
-		     !inat_is_group(insn->attr)))
-			insn->attr = 0;	/* This instruction is bad */
-		goto end;	/* VEX has only 1 byte for opcode */
+		     !inat_is_group(insn->attr))) {
+			/* This instruction is bad */
+			insn->attr = 0;
+			return -EINVAL;
+		}
+		/* VEX has only 1 byte for opcode */
+		goto end;
 	}
 
 	insn->attr = inat_get_opcode_attribute(op);
@@ -280,13 +303,18 @@ void insn_get_opcode(struct insn *insn)
 		pfx_id = insn_last_prefix_id(insn);
 		insn->attr = inat_get_escape_attribute(op, pfx_id, insn->attr);
 	}
-	if (inat_must_vex(insn->attr))
-		insn->attr = 0;	/* This instruction is bad */
+
+	if (inat_must_vex(insn->attr)) {
+		/* This instruction is bad */
+		insn->attr = 0;
+		return -EINVAL;
+	}
 end:
 	opcode->got = 1;
+	return 0;
 
 err_out:
-	return;
+	return -ENODATA;
 }
 
 /**
@@ -296,15 +324,25 @@ err_out:
  * Populates @insn->modrm and updates @insn->next_byte to point past the
  * ModRM byte, if any.  If necessary, first collects the preceding bytes
  * (prefixes and opcode(s)).  No effect if @insn->modrm.got is already 1.
+ *
+ * Returns:
+ * 0:  on success
+ * < 0: on error
  */
-void insn_get_modrm(struct insn *insn)
+int insn_get_modrm(struct insn *insn)
 {
 	struct insn_field *modrm = &insn->modrm;
 	insn_byte_t pfx_id, mod;
+	int ret;
+
 	if (modrm->got)
-		return;
-	if (!insn->opcode.got)
-		insn_get_opcode(insn);
+		return 0;
+
+	if (!insn->opcode.got) {
+		ret = insn_get_opcode(insn);
+		if (ret)
+			return ret;
+	}
 
 	if (inat_has_modrm(insn->attr)) {
 		mod = get_next(insn_byte_t, insn);
@@ -313,17 +351,22 @@ void insn_get_modrm(struct insn *insn)
 			pfx_id = insn_last_prefix_id(insn);
 			insn->attr = inat_get_group_attribute(mod, pfx_id,
 							      insn->attr);
-			if (insn_is_avx(insn) && !inat_accept_vex(insn->attr))
-				insn->attr = 0;	/* This is bad */
+			if (insn_is_avx(insn) && !inat_accept_vex(insn->attr)) {
+				/* Bad insn */
+				insn->attr = 0;
+				return -EINVAL;
+			}
 		}
 	}
 
 	if (insn->x86_64 && inat_is_force64(insn->attr))
 		insn->opnd_bytes = 8;
+
 	modrm->got = 1;
+	return 0;
 
 err_out:
-	return;
+	return -ENODATA;
 }
 
 
@@ -337,11 +380,16 @@ err_out:
 int insn_rip_relative(struct insn *insn)
 {
 	struct insn_field *modrm = &insn->modrm;
+	int ret;
 
 	if (!insn->x86_64)
 		return 0;
-	if (!modrm->got)
-		insn_get_modrm(insn);
+
+	if (!modrm->got) {
+		ret = insn_get_modrm(insn);
+		if (ret)
+			return 0;
+	}
 	/*
 	 * For rip-relative instructions, the mod field (top 2 bits)
 	 * is zero and the r/m field (bottom 3 bits) is 0x5.
@@ -355,15 +403,25 @@ int insn_rip_relative(struct insn *insn)
  *
  * If necessary, first collects the instruction up to and including the
  * ModRM byte.
+ *
+ * Returns:
+ * 0: if decoding succeeded
+ * < 0: otherwise.
  */
-void insn_get_sib(struct insn *insn)
+int insn_get_sib(struct insn *insn)
 {
 	insn_byte_t modrm;
+	int ret;
 
 	if (insn->sib.got)
-		return;
-	if (!insn->modrm.got)
-		insn_get_modrm(insn);
+		return 0;
+
+	if (!insn->modrm.got) {
+		ret = insn_get_modrm(insn);
+		if (ret)
+			return ret;
+	}
+
 	if (insn->modrm.nbytes) {
 		modrm = insn->modrm.bytes[0];
 		if (insn->addr_bytes != 2 &&
@@ -374,8 +432,10 @@ void insn_get_sib(struct insn *insn)
 	}
 	insn->sib.got = 1;
 
+	return 0;
+
 err_out:
-	return;
+	return -ENODATA;
 }
 
 
@@ -386,15 +446,25 @@ err_out:
  * If necessary, first collects the instruction up to and including the
  * SIB byte.
  * Displacement value is sign-expanded.
+ *
+ * * Returns:
+ * 0: if decoding succeeded
+ * < 0: otherwise.
  */
-void insn_get_displacement(struct insn *insn)
+int insn_get_displacement(struct insn *insn)
 {
 	insn_byte_t mod, rm, base;
+	int ret;
 
 	if (insn->displacement.got)
-		return;
-	if (!insn->sib.got)
-		insn_get_sib(insn);
+		return 0;
+
+	if (!insn->sib.got) {
+		ret = insn_get_sib(insn);
+		if (ret)
+			return ret;
+	}
+
 	if (insn->modrm.nbytes) {
 		/*
 		 * Interpreting the modrm byte:
@@ -436,9 +506,10 @@ void insn_get_displacement(struct insn *insn)
 	}
 out:
 	insn->displacement.got = 1;
+	return 0;
 
 err_out:
-	return;
+	return -ENODATA;
 }
 
 /* Decode moffset16/32/64. Return 0 if failed */
@@ -537,20 +608,30 @@ err_out:
 }
 
 /**
- * insn_get_immediate() - Get the immediates of instruction
+ * insn_get_immediate() - Get the immediate in an instruction
  * @insn:	&struct insn containing instruction
  *
  * If necessary, first collects the instruction up to and including the
  * displacement bytes.
  * Basically, most of immediates are sign-expanded. Unsigned-value can be
- * get by bit masking with ((1 << (nbytes * 8)) - 1)
+ * computed by bit masking with ((1 << (nbytes * 8)) - 1)
+ *
+ * Returns:
+ * 0:  on success
+ * < 0: on error
  */
-void insn_get_immediate(struct insn *insn)
+int insn_get_immediate(struct insn *insn)
 {
+	int ret;
+
 	if (insn->immediate.got)
-		return;
-	if (!insn->displacement.got)
-		insn_get_displacement(insn);
+		return 0;
+
+	if (!insn->displacement.got) {
+		ret = insn_get_displacement(insn);
+		if (ret)
+			return ret;
+	}
 
 	if (inat_has_moffset(insn->attr)) {
 		if (!__get_moffset(insn))
@@ -597,9 +678,10 @@ void insn_get_immediate(struct insn *insn)
 	}
 done:
 	insn->immediate.got = 1;
+	return 0;
 
 err_out:
-	return;
+	return -ENODATA;
 }
 
 /**
@@ -608,13 +690,65 @@ err_out:
  *
  * If necessary, first collects the instruction up to and including the
  * immediates bytes.
- */
-void insn_get_length(struct insn *insn)
+ *
+ * Returns:
+ *  - 0 on success
+ *  - < 0 on error
+*/
+int insn_get_length(struct insn *insn)
 {
+	int ret;
+
 	if (insn->length)
-		return;
-	if (!insn->immediate.got)
-		insn_get_immediate(insn);
+		return 0;
+
+	if (!insn->immediate.got) {
+		ret = insn_get_immediate(insn);
+		if (ret)
+			return ret;
+	}
+
 	insn->length = (unsigned char)((unsigned long)insn->next_byte
 				     - (unsigned long)insn->kaddr);
+
+	return 0;
+}
+
+/* Ensure this instruction is decoded completely */
+static inline int insn_complete(struct insn *insn)
+{
+	return insn->opcode.got && insn->modrm.got && insn->sib.got &&
+		insn->displacement.got && insn->immediate.got;
+}
+
+/**
+ * insn_decode() - Decode an x86 instruction
+ * @insn:	&struct insn to be initialized
+ * @kaddr:	address (in kernel memory) of instruction (or copy thereof)
+ * @buf_len:	length of the insn buffer at @kaddr
+ * @m:		insn mode, see enum insn_mode
+ *
+ * Returns:
+ * 0: if decoding succeeded
+ * < 0: otherwise.
+ */
+int insn_decode(struct insn *insn, const void *kaddr, int buf_len, enum insn_mode m)
+{
+	int ret;
+
+#define INSN_MODE_KERN (enum insn_mode)-1 /* __ignore_sync_check__ mode is only valid in the kernel */
+
+	if (m == INSN_MODE_KERN)
+		insn_init(insn, kaddr, buf_len, IS_ENABLED(CONFIG_X86_64));
+	else
+		insn_init(insn, kaddr, buf_len, m == INSN_MODE_64);
+
+	ret = insn_get_length(insn);
+	if (ret)
+		return ret;
+
+	if (insn_complete(insn))
+		return 0;
+
+	return -EINVAL;
 }
diff --git a/tools/include/linux/kconfig.h b/tools/include/linux/kconfig.h
new file mode 100644
index 000000000000..1555a0c4f345
--- /dev/null
+++ b/tools/include/linux/kconfig.h
@@ -0,0 +1,73 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOOLS_LINUX_KCONFIG_H
+#define _TOOLS_LINUX_KCONFIG_H
+
+/* CONFIG_CC_VERSION_TEXT (Do not delete this comment. See help in Kconfig) */
+
+#ifdef CONFIG_CPU_BIG_ENDIAN
+#define __BIG_ENDIAN 4321
+#else
+#define __LITTLE_ENDIAN 1234
+#endif
+
+#define __ARG_PLACEHOLDER_1 0,
+#define __take_second_arg(__ignored, val, ...) val
+
+/*
+ * The use of "&&" / "||" is limited in certain expressions.
+ * The following enable to calculate "and" / "or" with macro expansion only.
+ */
+#define __and(x, y)			___and(x, y)
+#define ___and(x, y)			____and(__ARG_PLACEHOLDER_##x, y)
+#define ____and(arg1_or_junk, y)	__take_second_arg(arg1_or_junk y, 0)
+
+#define __or(x, y)			___or(x, y)
+#define ___or(x, y)			____or(__ARG_PLACEHOLDER_##x, y)
+#define ____or(arg1_or_junk, y)		__take_second_arg(arg1_or_junk 1, y)
+
+/*
+ * Helper macros to use CONFIG_ options in C/CPP expressions. Note that
+ * these only work with boolean and tristate options.
+ */
+
+/*
+ * Getting something that works in C and CPP for an arg that may or may
+ * not be defined is tricky.  Here, if we have "#define CONFIG_BOOGER 1"
+ * we match on the placeholder define, insert the "0," for arg1 and generate
+ * the triplet (0, 1, 0).  Then the last step cherry picks the 2nd arg (a one).
+ * When CONFIG_BOOGER is not defined, we generate a (... 1, 0) pair, and when
+ * the last step cherry picks the 2nd arg, we get a zero.
+ */
+#define __is_defined(x)			___is_defined(x)
+#define ___is_defined(val)		____is_defined(__ARG_PLACEHOLDER_##val)
+#define ____is_defined(arg1_or_junk)	__take_second_arg(arg1_or_junk 1, 0)
+
+/*
+ * IS_BUILTIN(CONFIG_FOO) evaluates to 1 if CONFIG_FOO is set to 'y', 0
+ * otherwise. For boolean options, this is equivalent to
+ * IS_ENABLED(CONFIG_FOO).
+ */
+#define IS_BUILTIN(option) __is_defined(option)
+
+/*
+ * IS_MODULE(CONFIG_FOO) evaluates to 1 if CONFIG_FOO is set to 'm', 0
+ * otherwise.
+ */
+#define IS_MODULE(option) __is_defined(option##_MODULE)
+
+/*
+ * IS_REACHABLE(CONFIG_FOO) evaluates to 1 if the currently compiled
+ * code can call a function defined in code compiled based on CONFIG_FOO.
+ * This is similar to IS_ENABLED(), but returns false when invoked from
+ * built-in code when CONFIG_FOO is set to 'm'.
+ */
+#define IS_REACHABLE(option) __or(IS_BUILTIN(option), \
+				__and(IS_MODULE(option), __is_defined(MODULE)))
+
+/*
+ * IS_ENABLED(CONFIG_FOO) evaluates to 1 if CONFIG_FOO is set to 'y' or 'm',
+ * 0 otherwise.
+ */
+#define IS_ENABLED(option) __or(IS_BUILTIN(option), IS_MODULE(option))
+
+#endif /* _TOOLS_LINUX_KCONFIG_H */
diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c
index 549813cff8ab..7e8b5bedd946 100644
--- a/tools/objtool/arch/x86/decode.c
+++ b/tools/objtool/arch/x86/decode.c
@@ -11,11 +11,15 @@
 #include "../../../arch/x86/lib/inat.c"
 #include "../../../arch/x86/lib/insn.c"
 
+#define CONFIG_64BIT 1
+#include <asm/nops.h>
+
 #include <asm/orc_types.h>
 #include <objtool/check.h>
 #include <objtool/elf.h>
 #include <objtool/arch.h>
 #include <objtool/warn.h>
+#include <arch/elf.h>
 
 static unsigned char op_to_cfi_reg[][2] = {
 	{CFI_AX, CFI_R8},
@@ -90,7 +94,7 @@ int arch_decode_instruction(const struct elf *elf, const struct section *sec,
 			    struct list_head *ops_list)
 {
 	struct insn insn;
-	int x86_64, sign;
+	int x86_64, sign, ret;
 	unsigned char op1, op2, rex = 0, rex_b = 0, rex_r = 0, rex_w = 0,
 		      rex_x = 0, modrm = 0, modrm_mod = 0, modrm_rm = 0,
 		      modrm_reg = 0, sib = 0;
@@ -101,10 +105,9 @@ int arch_decode_instruction(const struct elf *elf, const struct section *sec,
 	if (x86_64 == -1)
 		return -1;
 
-	insn_init(&insn, sec->data->d_buf + offset, maxlen, x86_64);
-	insn_get_length(&insn);
-
-	if (!insn_complete(&insn)) {
+	ret = insn_decode(&insn, sec->data->d_buf + offset, maxlen,
+			  x86_64 ? INSN_MODE_64 : INSN_MODE_32);
+	if (ret < 0) {
 		WARN("can't decode instruction at %s:0x%lx", sec->name, offset);
 		return -1;
 	}
@@ -596,11 +599,11 @@ void arch_initial_func_cfi_state(struct cfi_init_state *state)
 const char *arch_nop_insn(int len)
 {
 	static const char nops[5][5] = {
-		/* 1 */ { 0x90 },
-		/* 2 */ { 0x66, 0x90 },
-		/* 3 */ { 0x0f, 0x1f, 0x00 },
-		/* 4 */ { 0x0f, 0x1f, 0x40, 0x00 },
-		/* 5 */ { 0x0f, 0x1f, 0x44, 0x00, 0x00 },
+		{ BYTES_NOP1 },
+		{ BYTES_NOP2 },
+		{ BYTES_NOP3 },
+		{ BYTES_NOP4 },
+		{ BYTES_NOP5 },
 	};
 
 	if (len < 1 || len > 5) {
@@ -611,6 +614,122 @@ const char *arch_nop_insn(int len)
 	return nops[len-1];
 }
 
+/* asm/alternative.h ? */
+
+#define ALTINSTR_FLAG_INV	(1 << 15)
+#define ALT_NOT(feat)		((feat) | ALTINSTR_FLAG_INV)
+
+struct alt_instr {
+	s32 instr_offset;	/* original instruction */
+	s32 repl_offset;	/* offset to replacement instruction */
+	u16 cpuid;		/* cpuid bit set for replacement */
+	u8  instrlen;		/* length of original instruction */
+	u8  replacementlen;	/* length of new instruction */
+} __packed;
+
+static int elf_add_alternative(struct elf *elf,
+			       struct instruction *orig, struct symbol *sym,
+			       int cpuid, u8 orig_len, u8 repl_len)
+{
+	const int size = sizeof(struct alt_instr);
+	struct alt_instr *alt;
+	struct section *sec;
+	Elf_Scn *s;
+
+	sec = find_section_by_name(elf, ".altinstructions");
+	if (!sec) {
+		sec = elf_create_section(elf, ".altinstructions",
+					 SHF_WRITE, size, 0);
+
+		if (!sec) {
+			WARN_ELF("elf_create_section");
+			return -1;
+		}
+	}
+
+	s = elf_getscn(elf->elf, sec->idx);
+	if (!s) {
+		WARN_ELF("elf_getscn");
+		return -1;
+	}
+
+	sec->data = elf_newdata(s);
+	if (!sec->data) {
+		WARN_ELF("elf_newdata");
+		return -1;
+	}
+
+	sec->data->d_size = size;
+	sec->data->d_align = 1;
+
+	alt = sec->data->d_buf = malloc(size);
+	if (!sec->data->d_buf) {
+		perror("malloc");
+		return -1;
+	}
+	memset(sec->data->d_buf, 0, size);
+
+	if (elf_add_reloc_to_insn(elf, sec, sec->sh.sh_size,
+				  R_X86_64_PC32, orig->sec, orig->offset)) {
+		WARN("elf_create_reloc: alt_instr::instr_offset");
+		return -1;
+	}
+
+	if (elf_add_reloc(elf, sec, sec->sh.sh_size + 4,
+			  R_X86_64_PC32, sym, 0)) {
+		WARN("elf_create_reloc: alt_instr::repl_offset");
+		return -1;
+	}
+
+	alt->cpuid = cpuid;
+	alt->instrlen = orig_len;
+	alt->replacementlen = repl_len;
+
+	sec->sh.sh_size += size;
+	sec->changed = true;
+
+	return 0;
+}
+
+#define X86_FEATURE_RETPOLINE                ( 7*32+12)
+
+int arch_rewrite_retpolines(struct objtool_file *file)
+{
+	struct instruction *insn;
+	struct reloc *reloc;
+	struct symbol *sym;
+	char name[32] = "";
+
+	list_for_each_entry(insn, &file->retpoline_call_list, call_node) {
+
+		if (!strcmp(insn->sec->name, ".text.__x86.indirect_thunk"))
+			continue;
+
+		reloc = insn->reloc;
+
+		sprintf(name, "__x86_indirect_alt_%s_%s",
+			insn->type == INSN_JUMP_DYNAMIC ? "jmp" : "call",
+			reloc->sym->name + 21);
+
+		sym = find_symbol_by_name(file->elf, name);
+		if (!sym) {
+			sym = elf_create_undef_symbol(file->elf, name);
+			if (!sym) {
+				WARN("elf_create_undef_symbol");
+				return -1;
+			}
+		}
+
+		if (elf_add_alternative(file->elf, insn, sym,
+					ALT_NOT(X86_FEATURE_RETPOLINE), 5, 5)) {
+			WARN("elf_add_alternative");
+			return -1;
+		}
+	}
+
+	return 0;
+}
+
 int arch_decode_hint_reg(struct instruction *insn, u8 sp_reg)
 {
 	struct cfi_reg *cfa = &insn->cfi.cfa;
@@ -646,3 +765,8 @@ int arch_decode_hint_reg(struct instruction *insn, u8 sp_reg)
 
 	return 0;
 }
+
+bool arch_is_retpoline(struct symbol *sym)
+{
+	return !strncmp(sym->name, "__x86_indirect_", 15);
+}
diff --git a/tools/objtool/arch/x86/include/arch/special.h b/tools/objtool/arch/x86/include/arch/special.h
index d818b2bffa02..14271cca0c74 100644
--- a/tools/objtool/arch/x86/include/arch/special.h
+++ b/tools/objtool/arch/x86/include/arch/special.h
@@ -10,7 +10,7 @@
 #define JUMP_ORIG_OFFSET	0
 #define JUMP_NEW_OFFSET		4
 
-#define ALT_ENTRY_SIZE		13
+#define ALT_ENTRY_SIZE		12
 #define ALT_ORIG_OFFSET		0
 #define ALT_NEW_OFFSET		4
 #define ALT_FEATURE_OFFSET	8
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 5e5388a38e2a..1f4154f9b04b 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -433,8 +433,7 @@ reachable:
 
 static int create_static_call_sections(struct objtool_file *file)
 {
-	struct section *sec, *reloc_sec;
-	struct reloc *reloc;
+	struct section *sec;
 	struct static_call_site *site;
 	struct instruction *insn;
 	struct symbol *key_sym;
@@ -452,7 +451,7 @@ static int create_static_call_sections(struct objtool_file *file)
 		return 0;
 
 	idx = 0;
-	list_for_each_entry(insn, &file->static_call_list, static_call_node)
+	list_for_each_entry(insn, &file->static_call_list, call_node)
 		idx++;
 
 	sec = elf_create_section(file->elf, ".static_call_sites", SHF_WRITE,
@@ -460,36 +459,18 @@ static int create_static_call_sections(struct objtool_file *file)
 	if (!sec)
 		return -1;
 
-	reloc_sec = elf_create_reloc_section(file->elf, sec, SHT_RELA);
-	if (!reloc_sec)
-		return -1;
-
 	idx = 0;
-	list_for_each_entry(insn, &file->static_call_list, static_call_node) {
+	list_for_each_entry(insn, &file->static_call_list, call_node) {
 
 		site = (struct static_call_site *)sec->data->d_buf + idx;
 		memset(site, 0, sizeof(struct static_call_site));
 
 		/* populate reloc for 'addr' */
-		reloc = malloc(sizeof(*reloc));
-
-		if (!reloc) {
-			perror("malloc");
+		if (elf_add_reloc_to_insn(file->elf, sec,
+					  idx * sizeof(struct static_call_site),
+					  R_X86_64_PC32,
+					  insn->sec, insn->offset))
 			return -1;
-		}
-		memset(reloc, 0, sizeof(*reloc));
-
-		insn_to_reloc_sym_addend(insn->sec, insn->offset, reloc);
-		if (!reloc->sym) {
-			WARN_FUNC("static call tramp: missing containing symbol",
-				  insn->sec, insn->offset);
-			return -1;
-		}
-
-		reloc->type = R_X86_64_PC32;
-		reloc->offset = idx * sizeof(struct static_call_site);
-		reloc->sec = reloc_sec;
-		elf_add_reloc(file->elf, reloc);
 
 		/* find key symbol */
 		key_name = strdup(insn->call_dest->name);
@@ -526,32 +507,21 @@ static int create_static_call_sections(struct objtool_file *file)
 		free(key_name);
 
 		/* populate reloc for 'key' */
-		reloc = malloc(sizeof(*reloc));
-		if (!reloc) {
-			perror("malloc");
+		if (elf_add_reloc(file->elf, sec,
+				  idx * sizeof(struct static_call_site) + 4,
+				  R_X86_64_PC32, key_sym,
+				  is_sibling_call(insn) * STATIC_CALL_SITE_TAIL))
 			return -1;
-		}
-		memset(reloc, 0, sizeof(*reloc));
-		reloc->sym = key_sym;
-		reloc->addend = is_sibling_call(insn) ? STATIC_CALL_SITE_TAIL : 0;
-		reloc->type = R_X86_64_PC32;
-		reloc->offset = idx * sizeof(struct static_call_site) + 4;
-		reloc->sec = reloc_sec;
-		elf_add_reloc(file->elf, reloc);
 
 		idx++;
 	}
 
-	if (elf_rebuild_reloc_section(file->elf, reloc_sec))
-		return -1;
-
 	return 0;
 }
 
 static int create_mcount_loc_sections(struct objtool_file *file)
 {
-	struct section *sec, *reloc_sec;
-	struct reloc *reloc;
+	struct section *sec;
 	unsigned long *loc;
 	struct instruction *insn;
 	int idx;
@@ -574,49 +544,21 @@ static int create_mcount_loc_sections(struct objtool_file *file)
 	if (!sec)
 		return -1;
 
-	reloc_sec = elf_create_reloc_section(file->elf, sec, SHT_RELA);
-	if (!reloc_sec)
-		return -1;
-
 	idx = 0;
 	list_for_each_entry(insn, &file->mcount_loc_list, mcount_loc_node) {
 
 		loc = (unsigned long *)sec->data->d_buf + idx;
 		memset(loc, 0, sizeof(unsigned long));
 
-		reloc = malloc(sizeof(*reloc));
-		if (!reloc) {
-			perror("malloc");
+		if (elf_add_reloc_to_insn(file->elf, sec,
+					  idx * sizeof(unsigned long),
+					  R_X86_64_64,
+					  insn->sec, insn->offset))
 			return -1;
-		}
-		memset(reloc, 0, sizeof(*reloc));
-
-		if (insn->sec->sym) {
-			reloc->sym = insn->sec->sym;
-			reloc->addend = insn->offset;
-		} else {
-			reloc->sym = find_symbol_containing(insn->sec, insn->offset);
-
-			if (!reloc->sym) {
-				WARN("missing symbol for insn at offset 0x%lx\n",
-				     insn->offset);
-				return -1;
-			}
-
-			reloc->addend = insn->offset - reloc->sym->offset;
-		}
-
-		reloc->type = R_X86_64_64;
-		reloc->offset = idx * sizeof(unsigned long);
-		reloc->sec = reloc_sec;
-		elf_add_reloc(file->elf, reloc);
 
 		idx++;
 	}
 
-	if (elf_rebuild_reloc_section(file->elf, reloc_sec))
-		return -1;
-
 	return 0;
 }
 
@@ -850,6 +792,30 @@ static int add_ignore_alternatives(struct objtool_file *file)
 	return 0;
 }
 
+__weak bool arch_is_retpoline(struct symbol *sym)
+{
+	return false;
+}
+
+#define NEGATIVE_RELOC	((void *)-1L)
+
+static struct reloc *insn_reloc(struct objtool_file *file, struct instruction *insn)
+{
+	if (insn->reloc == NEGATIVE_RELOC)
+		return NULL;
+
+	if (!insn->reloc) {
+		insn->reloc = find_reloc_by_dest_range(file->elf, insn->sec,
+						       insn->offset, insn->len);
+		if (!insn->reloc) {
+			insn->reloc = NEGATIVE_RELOC;
+			return NULL;
+		}
+	}
+
+	return insn->reloc;
+}
+
 /*
  * Find the destination instructions for all jumps.
  */
@@ -864,16 +830,14 @@ static int add_jump_destinations(struct objtool_file *file)
 		if (!is_static_jump(insn))
 			continue;
 
-		reloc = find_reloc_by_dest_range(file->elf, insn->sec,
-						 insn->offset, insn->len);
+		reloc = insn_reloc(file, insn);
 		if (!reloc) {
 			dest_sec = insn->sec;
 			dest_off = arch_jump_destination(insn);
 		} else if (reloc->sym->type == STT_SECTION) {
 			dest_sec = reloc->sym->sec;
 			dest_off = arch_dest_reloc_offset(reloc->addend);
-		} else if (!strncmp(reloc->sym->name, "__x86_indirect_thunk_", 21) ||
-			   !strncmp(reloc->sym->name, "__x86_retpoline_", 16)) {
+		} else if (arch_is_retpoline(reloc->sym)) {
 			/*
 			 * Retpoline jumps are really dynamic jumps in
 			 * disguise, so convert them accordingly.
@@ -883,13 +847,16 @@ static int add_jump_destinations(struct objtool_file *file)
 			else
 				insn->type = INSN_JUMP_DYNAMIC_CONDITIONAL;
 
+			list_add_tail(&insn->call_node,
+				      &file->retpoline_call_list);
+
 			insn->retpoline_safe = true;
 			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->static_call_node,
+				list_add_tail(&insn->call_node,
 					      &file->static_call_list);
 			}
 			continue;
@@ -951,7 +918,7 @@ static int add_jump_destinations(struct objtool_file *file)
 				/* internal sibling call (without reloc) */
 				insn->call_dest = insn->jump_dest->func;
 				if (insn->call_dest->static_call_tramp) {
-					list_add_tail(&insn->static_call_node,
+					list_add_tail(&insn->call_node,
 						      &file->static_call_list);
 				}
 			}
@@ -995,8 +962,7 @@ static int add_call_destinations(struct objtool_file *file)
 		if (insn->type != INSN_CALL)
 			continue;
 
-		reloc = find_reloc_by_dest_range(file->elf, insn->sec,
-					       insn->offset, insn->len);
+		reloc = insn_reloc(file, insn);
 		if (!reloc) {
 			dest_off = arch_jump_destination(insn);
 			insn->call_dest = find_call_destination(insn->sec, dest_off);
@@ -1026,9 +992,29 @@ static int add_call_destinations(struct objtool_file *file)
 					  dest_off);
 				return -1;
 			}
+
+		} else if (arch_is_retpoline(reloc->sym)) {
+			/*
+			 * Retpoline calls are really dynamic calls in
+			 * disguise, so convert them accordingly.
+			 */
+			insn->type = INSN_CALL_DYNAMIC;
+			insn->retpoline_safe = true;
+
+			list_add_tail(&insn->call_node,
+				      &file->retpoline_call_list);
+
+			remove_insn_ops(insn);
+			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
@@ -1175,8 +1161,7 @@ static int handle_group_alt(struct objtool_file *file,
 		 * alternatives code can adjust the relative offsets
 		 * accordingly.
 		 */
-		alt_reloc = find_reloc_by_dest_range(file->elf, insn->sec,
-						   insn->offset, insn->len);
+		alt_reloc = insn_reloc(file, insn);
 		if (alt_reloc &&
 		    !arch_support_alt_relocation(special_alt, insn, alt_reloc)) {
 
@@ -1751,6 +1736,11 @@ static void mark_rodata(struct objtool_file *file)
 	file->rodata = found;
 }
 
+__weak int arch_rewrite_retpolines(struct objtool_file *file)
+{
+	return 0;
+}
+
 static int decode_sections(struct objtool_file *file)
 {
 	int ret;
@@ -1772,10 +1762,17 @@ static int decode_sections(struct objtool_file *file)
 	if (ret)
 		return ret;
 
+	/*
+	 * Must be before add_{jump_call}_destination.
+	 */
 	ret = read_static_call_tramps(file);
 	if (ret)
 		return ret;
 
+	/*
+	 * Must be before add_special_section_alts() as that depends on
+	 * jump_dest being set.
+	 */
 	ret = add_jump_destinations(file);
 	if (ret)
 		return ret;
@@ -1784,6 +1781,10 @@ static int decode_sections(struct objtool_file *file)
 	if (ret)
 		return ret;
 
+	/*
+	 * Must be before add_call_destination(); it changes INSN_CALL to
+	 * INSN_JUMP.
+	 */
 	ret = read_intra_function_calls(file);
 	if (ret)
 		return ret;
@@ -1808,6 +1809,15 @@ static int decode_sections(struct objtool_file *file)
 	if (ret)
 		return ret;
 
+	/*
+	 * Must be after add_special_section_alts(), since this will emit
+	 * alternatives. Must be after add_{jump,call}_destination(), since
+	 * those create the call insn lists.
+	 */
+	ret = arch_rewrite_retpolines(file);
+	if (ret)
+		return ret;
+
 	return 0;
 }
 
@@ -2746,11 +2756,6 @@ static int validate_branch(struct objtool_file *file, struct symbol *func,
 			if (dead_end_function(file, insn->call_dest))
 				return 0;
 
-			if (insn->type == INSN_CALL && insn->call_dest->static_call_tramp) {
-				list_add_tail(&insn->static_call_node,
-					      &file->static_call_list);
-			}
-
 			break;
 
 		case INSN_JUMP_CONDITIONAL:
diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index 93fa833a49a5..d08f5f3670f8 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -211,32 +211,6 @@ struct reloc *find_reloc_by_dest(const struct elf *elf, struct section *sec, uns
 	return find_reloc_by_dest_range(elf, sec, offset, 1);
 }
 
-void insn_to_reloc_sym_addend(struct section *sec, unsigned long offset,
-			      struct reloc *reloc)
-{
-	if (sec->sym) {
-		reloc->sym = sec->sym;
-		reloc->addend = offset;
-		return;
-	}
-
-	/*
-	 * The Clang assembler strips section symbols, so we have to reference
-	 * the function symbol instead:
-	 */
-	reloc->sym = find_symbol_containing(sec, offset);
-	if (!reloc->sym) {
-		/*
-		 * Hack alert.  This happens when we need to reference the NOP
-		 * pad insn immediately after the function.
-		 */
-		reloc->sym = find_symbol_containing(sec, offset - 1);
-	}
-
-	if (reloc->sym)
-		reloc->addend = offset - reloc->sym->offset;
-}
-
 static int read_sections(struct elf *elf)
 {
 	Elf_Scn *s = NULL;
@@ -316,12 +290,39 @@ static int read_sections(struct elf *elf)
 	return 0;
 }
 
+static void elf_add_symbol(struct elf *elf, struct symbol *sym)
+{
+	struct list_head *entry;
+	struct rb_node *pnode;
+
+	sym->type = GELF_ST_TYPE(sym->sym.st_info);
+	sym->bind = GELF_ST_BIND(sym->sym.st_info);
+
+	sym->offset = sym->sym.st_value;
+	sym->len = sym->sym.st_size;
+
+	rb_add(&sym->node, &sym->sec->symbol_tree, symbol_to_offset);
+	pnode = rb_prev(&sym->node);
+	if (pnode)
+		entry = &rb_entry(pnode, struct symbol, node)->list;
+	else
+		entry = &sym->sec->symbol_list;
+	list_add(&sym->list, entry);
+	elf_hash_add(elf->symbol_hash, &sym->hash, sym->idx);
+	elf_hash_add(elf->symbol_name_hash, &sym->name_hash, str_hash(sym->name));
+
+	/*
+	 * Don't store empty STT_NOTYPE symbols in the rbtree.  They
+	 * can exist within a function, confusing the sorting.
+	 */
+	if (!sym->len)
+		rb_erase(&sym->node, &sym->sec->symbol_tree);
+}
+
 static int read_symbols(struct elf *elf)
 {
 	struct section *symtab, *symtab_shndx, *sec;
 	struct symbol *sym, *pfunc;
-	struct list_head *entry;
-	struct rb_node *pnode;
 	int symbols_nr, i;
 	char *coldstr;
 	Elf_Data *shndx_data = NULL;
@@ -366,9 +367,6 @@ static int read_symbols(struct elf *elf)
 			goto err;
 		}
 
-		sym->type = GELF_ST_TYPE(sym->sym.st_info);
-		sym->bind = GELF_ST_BIND(sym->sym.st_info);
-
 		if ((sym->sym.st_shndx > SHN_UNDEF &&
 		     sym->sym.st_shndx < SHN_LORESERVE) ||
 		    (shndx_data && sym->sym.st_shndx == SHN_XINDEX)) {
@@ -381,32 +379,14 @@ static int read_symbols(struct elf *elf)
 				     sym->name);
 				goto err;
 			}
-			if (sym->type == STT_SECTION) {
+			if (GELF_ST_TYPE(sym->sym.st_info) == STT_SECTION) {
 				sym->name = sym->sec->name;
 				sym->sec->sym = sym;
 			}
 		} else
 			sym->sec = find_section_by_index(elf, 0);
 
-		sym->offset = sym->sym.st_value;
-		sym->len = sym->sym.st_size;
-
-		rb_add(&sym->node, &sym->sec->symbol_tree, symbol_to_offset);
-		pnode = rb_prev(&sym->node);
-		if (pnode)
-			entry = &rb_entry(pnode, struct symbol, node)->list;
-		else
-			entry = &sym->sec->symbol_list;
-		list_add(&sym->list, entry);
-		elf_hash_add(elf->symbol_hash, &sym->hash, sym->idx);
-		elf_hash_add(elf->symbol_name_hash, &sym->name_hash, str_hash(sym->name));
-
-		/*
-		 * Don't store empty STT_NOTYPE symbols in the rbtree.  They
-		 * can exist within a function, confusing the sorting.
-		 */
-		if (!sym->len)
-			rb_erase(&sym->node, &sym->sec->symbol_tree);
+		elf_add_symbol(elf, sym);
 	}
 
 	if (stats)
@@ -473,12 +453,73 @@ err:
 	return -1;
 }
 
-void elf_add_reloc(struct elf *elf, struct reloc *reloc)
+static struct section *elf_create_reloc_section(struct elf *elf,
+						struct section *base,
+						int reltype);
+
+int elf_add_reloc(struct elf *elf, struct section *sec, unsigned long offset,
+		  unsigned int type, struct symbol *sym, int addend)
 {
-	struct section *sec = reloc->sec;
+	struct reloc *reloc;
 
-	list_add_tail(&reloc->list, &sec->reloc_list);
+	if (!sec->reloc && !elf_create_reloc_section(elf, sec, SHT_RELA))
+		return -1;
+
+	reloc = malloc(sizeof(*reloc));
+	if (!reloc) {
+		perror("malloc");
+		return -1;
+	}
+	memset(reloc, 0, sizeof(*reloc));
+
+	reloc->sec = sec->reloc;
+	reloc->offset = offset;
+	reloc->type = type;
+	reloc->sym = sym;
+	reloc->addend = addend;
+
+	list_add_tail(&reloc->list, &sec->reloc->reloc_list);
 	elf_hash_add(elf->reloc_hash, &reloc->hash, reloc_hash(reloc));
+
+	sec->reloc->changed = true;
+
+	return 0;
+}
+
+int elf_add_reloc_to_insn(struct elf *elf, struct section *sec,
+			  unsigned long offset, unsigned int type,
+			  struct section *insn_sec, unsigned long insn_off)
+{
+	struct symbol *sym;
+	int addend;
+
+	if (insn_sec->sym) {
+		sym = insn_sec->sym;
+		addend = insn_off;
+
+	} else {
+		/*
+		 * The Clang assembler strips section symbols, so we have to
+		 * reference the function symbol instead:
+		 */
+		sym = find_symbol_containing(insn_sec, insn_off);
+		if (!sym) {
+			/*
+			 * Hack alert.  This happens when we need to reference
+			 * the NOP pad insn immediately after the function.
+			 */
+			sym = find_symbol_containing(insn_sec, insn_off - 1);
+		}
+
+		if (!sym) {
+			WARN("can't find symbol containing %s+0x%lx", insn_sec->name, insn_off);
+			return -1;
+		}
+
+		addend = insn_off - sym->offset;
+	}
+
+	return elf_add_reloc(elf, sec, offset, type, sym, addend);
 }
 
 static int read_rel_reloc(struct section *sec, int i, struct reloc *reloc, unsigned int *symndx)
@@ -558,7 +599,9 @@ static int read_relocs(struct elf *elf)
 				return -1;
 			}
 
-			elf_add_reloc(elf, reloc);
+			list_add_tail(&reloc->list, &sec->reloc_list);
+			elf_hash_add(elf->reloc_hash, &reloc->hash, reloc_hash(reloc));
+
 			nr_reloc++;
 		}
 		max_reloc = max(max_reloc, nr_reloc);
@@ -636,13 +679,108 @@ err:
 	return NULL;
 }
 
+static int elf_add_string(struct elf *elf, struct section *strtab, char *str)
+{
+	Elf_Data *data;
+	Elf_Scn *s;
+	int len;
+
+	if (!strtab)
+		strtab = find_section_by_name(elf, ".strtab");
+	if (!strtab) {
+		WARN("can't find .strtab section");
+		return -1;
+	}
+
+	s = elf_getscn(elf->elf, strtab->idx);
+	if (!s) {
+		WARN_ELF("elf_getscn");
+		return -1;
+	}
+
+	data = elf_newdata(s);
+	if (!data) {
+		WARN_ELF("elf_newdata");
+		return -1;
+	}
+
+	data->d_buf = str;
+	data->d_size = strlen(str) + 1;
+	data->d_align = 1;
+
+	len = strtab->len;
+	strtab->len += data->d_size;
+	strtab->changed = true;
+
+	return len;
+}
+
+struct symbol *elf_create_undef_symbol(struct elf *elf, const char *name)
+{
+	struct section *symtab;
+	struct symbol *sym;
+	Elf_Data *data;
+	Elf_Scn *s;
+
+	sym = malloc(sizeof(*sym));
+	if (!sym) {
+		perror("malloc");
+		return NULL;
+	}
+	memset(sym, 0, sizeof(*sym));
+
+	sym->name = strdup(name);
+
+	sym->sym.st_name = elf_add_string(elf, NULL, sym->name);
+	if (sym->sym.st_name == -1)
+		return NULL;
+
+	sym->sym.st_info = GELF_ST_INFO(STB_GLOBAL, STT_NOTYPE);
+	// st_other 0
+	// st_shndx 0
+	// st_value 0
+	// st_size 0
+
+	symtab = find_section_by_name(elf, ".symtab");
+	if (!symtab) {
+		WARN("can't find .symtab");
+		return NULL;
+	}
+
+	s = elf_getscn(elf->elf, symtab->idx);
+	if (!s) {
+		WARN_ELF("elf_getscn");
+		return NULL;
+	}
+
+	data = elf_newdata(s);
+	if (!data) {
+		WARN_ELF("elf_newdata");
+		return NULL;
+	}
+
+	data->d_buf = &sym->sym;
+	data->d_size = sizeof(sym->sym);
+	data->d_align = 1;
+
+	sym->idx = symtab->len / sizeof(sym->sym);
+
+	symtab->len += data->d_size;
+	symtab->changed = true;
+
+	sym->sec = find_section_by_index(elf, 0);
+
+	elf_add_symbol(elf, sym);
+
+	return sym;
+}
+
 struct section *elf_create_section(struct elf *elf, const char *name,
 				   unsigned int sh_flags, size_t entsize, int nr)
 {
 	struct section *sec, *shstrtab;
 	size_t size = entsize * nr;
 	Elf_Scn *s;
-	Elf_Data *data;
 
 	sec = malloc(sizeof(*sec));
 	if (!sec) {
@@ -699,7 +837,6 @@ struct section *elf_create_section(struct elf *elf, const char *name,
 	sec->sh.sh_addralign = 1;
 	sec->sh.sh_flags = SHF_ALLOC | sh_flags;
 
-
 	/* Add section name to .shstrtab (or .strtab for Clang) */
 	shstrtab = find_section_by_name(elf, ".shstrtab");
 	if (!shstrtab)
@@ -708,27 +845,9 @@ struct section *elf_create_section(struct elf *elf, const char *name,
 		WARN("can't find .shstrtab or .strtab section");
 		return NULL;
 	}
-
-	s = elf_getscn(elf->elf, shstrtab->idx);
-	if (!s) {
-		WARN_ELF("elf_getscn");
-		return NULL;
-	}
-
-	data = elf_newdata(s);
-	if (!data) {
-		WARN_ELF("elf_newdata");
+	sec->sh.sh_name = elf_add_string(elf, shstrtab, sec->name);
+	if (sec->sh.sh_name == -1)
 		return NULL;
-	}
-
-	data->d_buf = sec->name;
-	data->d_size = strlen(name) + 1;
-	data->d_align = 1;
-
-	sec->sh.sh_name = shstrtab->len;
-
-	shstrtab->len += strlen(name) + 1;
-	shstrtab->changed = true;
 
 	list_add_tail(&sec->list, &elf->sections);
 	elf_hash_add(elf->section_hash, &sec->hash, sec->idx);
@@ -799,7 +918,7 @@ static struct section *elf_create_rela_reloc_section(struct elf *elf, struct sec
 	return sec;
 }
 
-struct section *elf_create_reloc_section(struct elf *elf,
+static struct section *elf_create_reloc_section(struct elf *elf,
 					 struct section *base,
 					 int reltype)
 {
@@ -873,14 +992,11 @@ static int elf_rebuild_rela_reloc_section(struct section *sec, int nr)
 	return 0;
 }
 
-int elf_rebuild_reloc_section(struct elf *elf, struct section *sec)
+static int elf_rebuild_reloc_section(struct elf *elf, struct section *sec)
 {
 	struct reloc *reloc;
 	int nr;
 
-	sec->changed = true;
-	elf->changed = true;
-
 	nr = 0;
 	list_for_each_entry(reloc, &sec->reloc_list, list)
 		nr++;
@@ -944,9 +1060,15 @@ int elf_write(struct elf *elf)
 	struct section *sec;
 	Elf_Scn *s;
 
-	/* Update section headers for changed sections: */
+	/* Update changed relocation sections and section headers: */
 	list_for_each_entry(sec, &elf->sections, list) {
 		if (sec->changed) {
+			if (sec->base &&
+			    elf_rebuild_reloc_section(elf, sec)) {
+				WARN("elf_rebuild_reloc_section");
+				return -1;
+			}
+
 			s = elf_getscn(elf->elf, sec->idx);
 			if (!s) {
 				WARN_ELF("elf_getscn");
@@ -958,6 +1080,7 @@ int elf_write(struct elf *elf)
 			}
 
 			sec->changed = false;
+			elf->changed = true;
 		}
 	}
 
diff --git a/tools/objtool/include/objtool/arch.h b/tools/objtool/include/objtool/arch.h
index 6ff0685f5cc5..48b540a9d9e9 100644
--- a/tools/objtool/include/objtool/arch.h
+++ b/tools/objtool/include/objtool/arch.h
@@ -86,4 +86,8 @@ const char *arch_nop_insn(int len);
 
 int arch_decode_hint_reg(struct instruction *insn, u8 sp_reg);
 
+bool arch_is_retpoline(struct symbol *sym);
+
+int arch_rewrite_retpolines(struct objtool_file *file);
+
 #endif /* _ARCH_H */
diff --git a/tools/objtool/include/objtool/check.h b/tools/objtool/include/objtool/check.h
index f5be798107bc..56d50bc50c10 100644
--- a/tools/objtool/include/objtool/check.h
+++ b/tools/objtool/include/objtool/check.h
@@ -39,7 +39,7 @@ struct alt_group {
 struct instruction {
 	struct list_head list;
 	struct hlist_node hash;
-	struct list_head static_call_node;
+	struct list_head call_node;
 	struct list_head mcount_loc_node;
 	struct section *sec;
 	unsigned long offset;
@@ -56,6 +56,7 @@ struct instruction {
 	struct instruction *jump_dest;
 	struct instruction *first_jump_src;
 	struct reloc *jump_table;
+	struct reloc *reloc;
 	struct list_head alts;
 	struct symbol *func;
 	struct list_head stack_ops;
diff --git a/tools/objtool/include/objtool/elf.h b/tools/objtool/include/objtool/elf.h
index e6890cc70a25..45e5ede363b0 100644
--- a/tools/objtool/include/objtool/elf.h
+++ b/tools/objtool/include/objtool/elf.h
@@ -122,12 +122,18 @@ static inline u32 reloc_hash(struct reloc *reloc)
 
 struct elf *elf_open_read(const char *name, int flags);
 struct section *elf_create_section(struct elf *elf, const char *name, unsigned int sh_flags, size_t entsize, int nr);
-struct section *elf_create_reloc_section(struct elf *elf, struct section *base, int reltype);
-void elf_add_reloc(struct elf *elf, struct reloc *reloc);
+
+int elf_add_reloc(struct elf *elf, struct section *sec, unsigned long offset,
+		  unsigned int type, struct symbol *sym, int addend);
+int elf_add_reloc_to_insn(struct elf *elf, struct section *sec,
+			  unsigned long offset, unsigned int type,
+			  struct section *insn_sec, unsigned long insn_off);
+
 int elf_write_insn(struct elf *elf, struct section *sec,
 		   unsigned long offset, unsigned int len,
 		   const char *insn);
 int elf_write_reloc(struct elf *elf, struct reloc *reloc);
+struct symbol *elf_create_undef_symbol(struct elf *elf, const char *name);
 int elf_write(struct elf *elf);
 void elf_close(struct elf *elf);
 
@@ -140,9 +146,6 @@ struct reloc *find_reloc_by_dest(const struct elf *elf, struct section *sec, uns
 struct reloc *find_reloc_by_dest_range(const struct elf *elf, struct section *sec,
 				     unsigned long offset, unsigned int len);
 struct symbol *find_func_containing(struct section *sec, unsigned long offset);
-void insn_to_reloc_sym_addend(struct section *sec, unsigned long offset,
-			      struct reloc *reloc);
-int elf_rebuild_reloc_section(struct elf *elf, struct section *sec);
 
 #define for_each_sec(file, sec)						\
 	list_for_each_entry(sec, &file->elf->sections, list)
diff --git a/tools/objtool/include/objtool/objtool.h b/tools/objtool/include/objtool/objtool.h
index e68e37476c15..e4084afb2304 100644
--- a/tools/objtool/include/objtool/objtool.h
+++ b/tools/objtool/include/objtool/objtool.h
@@ -18,6 +18,7 @@ struct objtool_file {
 	struct elf *elf;
 	struct list_head insn_list;
 	DECLARE_HASHTABLE(insn_hash, 20);
+	struct list_head retpoline_call_list;
 	struct list_head static_call_list;
 	struct list_head mcount_loc_list;
 	bool ignore_unreachables, c_file, hints, rodata;
diff --git a/tools/objtool/objtool.c b/tools/objtool/objtool.c
index 7b97ce499405..3a3ea1b4e4da 100644
--- a/tools/objtool/objtool.c
+++ b/tools/objtool/objtool.c
@@ -61,6 +61,7 @@ struct objtool_file *objtool_open_read(const char *_objname)
 
 	INIT_LIST_HEAD(&file.insn_list);
 	hash_init(file.insn_hash);
+	INIT_LIST_HEAD(&file.retpoline_call_list);
 	INIT_LIST_HEAD(&file.static_call_list);
 	INIT_LIST_HEAD(&file.mcount_loc_list);
 	file.c_file = !vmlinux && find_section_by_name(file.elf, ".comment");
diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c
index 738aa5021bc4..dc9b7dd314b0 100644
--- a/tools/objtool/orc_gen.c
+++ b/tools/objtool/orc_gen.c
@@ -82,12 +82,11 @@ static int init_orc_entry(struct orc_entry *orc, struct cfi_state *cfi)
 }
 
 static int write_orc_entry(struct elf *elf, struct section *orc_sec,
-			   struct section *ip_rsec, unsigned int idx,
+			   struct section *ip_sec, unsigned int idx,
 			   struct section *insn_sec, unsigned long insn_off,
 			   struct orc_entry *o)
 {
 	struct orc_entry *orc;
-	struct reloc *reloc;
 
 	/* populate ORC data */
 	orc = (struct orc_entry *)orc_sec->data->d_buf + idx;
@@ -96,25 +95,9 @@ static int write_orc_entry(struct elf *elf, struct section *orc_sec,
 	orc->bp_offset = bswap_if_needed(orc->bp_offset);
 
 	/* populate reloc for ip */
-	reloc = malloc(sizeof(*reloc));
-	if (!reloc) {
-		perror("malloc");
+	if (elf_add_reloc_to_insn(elf, ip_sec, idx * sizeof(int), R_X86_64_PC32,
+				  insn_sec, insn_off))
 		return -1;
-	}
-	memset(reloc, 0, sizeof(*reloc));
-
-	insn_to_reloc_sym_addend(insn_sec, insn_off, reloc);
-	if (!reloc->sym) {
-		WARN("missing symbol for insn at offset 0x%lx",
-		     insn_off);
-		return -1;
-	}
-
-	reloc->type = R_X86_64_PC32;
-	reloc->offset = idx * sizeof(int);
-	reloc->sec = ip_rsec;
-
-	elf_add_reloc(elf, reloc);
 
 	return 0;
 }
@@ -153,7 +136,7 @@ static unsigned long alt_group_len(struct alt_group *alt_group)
 
 int orc_create(struct objtool_file *file)
 {
-	struct section *sec, *ip_rsec, *orc_sec;
+	struct section *sec, *orc_sec;
 	unsigned int nr = 0, idx = 0;
 	struct orc_list_entry *entry;
 	struct list_head orc_list;
@@ -242,20 +225,14 @@ int orc_create(struct objtool_file *file)
 	sec = elf_create_section(file->elf, ".orc_unwind_ip", 0, sizeof(int), nr);
 	if (!sec)
 		return -1;
-	ip_rsec = elf_create_reloc_section(file->elf, sec, SHT_RELA);
-	if (!ip_rsec)
-		return -1;
 
 	/* Write ORC entries to sections: */
 	list_for_each_entry(entry, &orc_list, list) {
-		if (write_orc_entry(file->elf, orc_sec, ip_rsec, idx++,
+		if (write_orc_entry(file->elf, orc_sec, sec, idx++,
 				    entry->insn_sec, entry->insn_off,
 				    &entry->orc))
 			return -1;
 	}
 
-	if (elf_rebuild_reloc_section(file->elf, ip_rsec))
-		return -1;
-
 	return 0;
 }
diff --git a/tools/objtool/special.c b/tools/objtool/special.c
index 2c7fbda7b055..07b21cfabf5c 100644
--- a/tools/objtool/special.c
+++ b/tools/objtool/special.c
@@ -106,6 +106,14 @@ static int get_alt_entry(struct elf *elf, struct special_entry *entry,
 			return -1;
 		}
 
+		/*
+		 * Skip retpoline .altinstr_replacement... we already rewrite the
+		 * instructions for retpolines anyway, see arch_is_retpoline()
+		 * usage in add_{call,jump}_destinations().
+		 */
+		if (arch_is_retpoline(new_reloc->sym))
+			return 1;
+
 		alt->new_sec = new_reloc->sym->sec;
 		alt->new_off = (unsigned int)new_reloc->addend;
 
@@ -154,7 +162,9 @@ int special_get_alts(struct elf *elf, struct list_head *alts)
 			memset(alt, 0, sizeof(*alt));
 
 			ret = get_alt_entry(elf, entry, sec, idx, alt);
-			if (ret)
+			if (ret > 0)
+				continue;
+			if (ret < 0)
 				return ret;
 
 			list_add_tail(&alt->list, alts);
diff --git a/tools/objtool/sync-check.sh b/tools/objtool/sync-check.sh
index 606a4b5e929f..105a291ff8e7 100755
--- a/tools/objtool/sync-check.sh
+++ b/tools/objtool/sync-check.sh
@@ -10,17 +10,21 @@ FILES="include/linux/objtool.h"
 
 if [ "$SRCARCH" = "x86" ]; then
 FILES="$FILES
+arch/x86/include/asm/nops.h
 arch/x86/include/asm/inat_types.h
 arch/x86/include/asm/orc_types.h
 arch/x86/include/asm/emulate_prefix.h
 arch/x86/lib/x86-opcode-map.txt
 arch/x86/tools/gen-insn-attr-x86.awk
 include/linux/static_call_types.h
-arch/x86/include/asm/inat.h     -I '^#include [\"<]\(asm/\)*inat_types.h[\">]'
-arch/x86/include/asm/insn.h     -I '^#include [\"<]\(asm/\)*inat.h[\">]'
-arch/x86/lib/inat.c             -I '^#include [\"<]\(../include/\)*asm/insn.h[\">]'
-arch/x86/lib/insn.c             -I '^#include [\"<]\(../include/\)*asm/in\(at\|sn\).h[\">]' -I '^#include [\"<]\(../include/\)*asm/emulate_prefix.h[\">]'
 "
+
+SYNC_CHECK_FILES='
+arch/x86/include/asm/inat.h
+arch/x86/include/asm/insn.h
+arch/x86/lib/inat.c
+arch/x86/lib/insn.c
+'
 fi
 
 check_2 () {
@@ -63,3 +67,9 @@ while read -r file_entry; do
 done <<EOF
 $FILES
 EOF
+
+if [ "$SRCARCH" = "x86" ]; then
+	for i in $SYNC_CHECK_FILES; do
+		check $i '-I "^.*\/\*.*__ignore_sync_check__.*\*\/.*$"'
+	done
+fi
diff --git a/tools/perf/arch/x86/tests/insn-x86.c b/tools/perf/arch/x86/tests/insn-x86.c
index 4f75ae990140..0262b0d8ccf5 100644
--- a/tools/perf/arch/x86/tests/insn-x86.c
+++ b/tools/perf/arch/x86/tests/insn-x86.c
@@ -96,13 +96,12 @@ static int get_branch(const char *branch_str)
 static int test_data_item(struct test_data *dat, int x86_64)
 {
 	struct intel_pt_insn intel_pt_insn;
+	int op, branch, ret;
 	struct insn insn;
-	int op, branch;
 
-	insn_init(&insn, dat->data, MAX_INSN_SIZE, x86_64);
-	insn_get_length(&insn);
-
-	if (!insn_complete(&insn)) {
+	ret = insn_decode(&insn, dat->data, MAX_INSN_SIZE,
+			  x86_64 ? INSN_MODE_64 : INSN_MODE_32);
+	if (ret < 0) {
 		pr_debug("Failed to decode: %s\n", dat->asm_rep);
 		return -1;
 	}
diff --git a/tools/perf/arch/x86/util/archinsn.c b/tools/perf/arch/x86/util/archinsn.c
index 34d600c51044..546feda08428 100644
--- a/tools/perf/arch/x86/util/archinsn.c
+++ b/tools/perf/arch/x86/util/archinsn.c
@@ -11,7 +11,7 @@ void arch_fetch_insn(struct perf_sample *sample,
 		     struct machine *machine)
 {
 	struct insn insn;
-	int len;
+	int len, ret;
 	bool is64bit = false;
 
 	if (!sample->ip)
@@ -19,8 +19,9 @@ void arch_fetch_insn(struct perf_sample *sample,
 	len = thread__memcpy(thread, machine, sample->insn, sample->ip, sizeof(sample->insn), &is64bit);
 	if (len <= 0)
 		return;
-	insn_init(&insn, sample->insn, len, is64bit);
-	insn_get_length(&insn);
-	if (insn_complete(&insn) && insn.length <= len)
+
+	ret = insn_decode(&insn, sample->insn, len,
+			  is64bit ? INSN_MODE_64 : INSN_MODE_32);
+	if (ret >= 0 && insn.length <= len)
 		sample->insn_len = insn.length;
 }
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index dded93a2bc89..07857dfb4d91 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -75,6 +75,13 @@ include/uapi/asm-generic/mman-common.h
 include/uapi/asm-generic/unistd.h
 '
 
+SYNC_CHECK_FILES='
+arch/x86/include/asm/inat.h
+arch/x86/include/asm/insn.h
+arch/x86/lib/inat.c
+arch/x86/lib/insn.c
+'
+
 # These copies are under tools/perf/trace/beauty/ as they are not used to in
 # building object files only by scripts in tools/perf/trace/beauty/ to generate
 # tables that then gets included in .c files for things like id->string syscall
@@ -129,6 +136,10 @@ for i in $FILES; do
   check $i -B
 done
 
+for i in $SYNC_CHECK_FILES; do
+  check $i '-I "^.*\/\*.*__ignore_sync_check__.*\*\/.*$"'
+done
+
 # diff with extra ignore lines
 check arch/x86/lib/memcpy_64.S        '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" -I"^SYM_FUNC_START\(_LOCAL\)*(memcpy_\(erms\|orig\))"'
 check arch/x86/lib/memset_64.S        '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" -I"^SYM_FUNC_START\(_LOCAL\)*(memset_\(erms\|orig\))"'
@@ -137,10 +148,6 @@ check include/uapi/linux/mman.h       '-I "^#include <\(uapi/\)*asm/mman.h>"'
 check include/linux/build_bug.h       '-I "^#\(ifndef\|endif\)\( \/\/\)* static_assert$"'
 check include/linux/ctype.h	      '-I "isdigit("'
 check lib/ctype.c		      '-I "^EXPORT_SYMBOL" -I "^#include <linux/export.h>" -B'
-check arch/x86/include/asm/inat.h     '-I "^#include [\"<]\(asm/\)*inat_types.h[\">]"'
-check arch/x86/include/asm/insn.h     '-I "^#include [\"<]\(asm/\)*inat.h[\">]"'
-check arch/x86/lib/inat.c	      '-I "^#include [\"<]\(../include/\)*asm/insn.h[\">]"'
-check arch/x86/lib/insn.c             '-I "^#include [\"<]\(../include/\)*asm/in\(at\|sn\).h[\">]" -I "^#include [\"<]\(../include/\)*asm/emulate_prefix.h[\">]"'
 
 # diff non-symmetric files
 check_2 tools/perf/arch/x86/entry/syscalls/syscall_64.tbl arch/x86/entry/syscalls/syscall_64.tbl
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c
index 2f6cc7eea251..593f20e9774c 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c
@@ -169,11 +169,13 @@ int intel_pt_get_insn(const unsigned char *buf, size_t len, int x86_64,
 		      struct intel_pt_insn *intel_pt_insn)
 {
 	struct insn insn;
+	int ret;
 
-	insn_init(&insn, buf, len, x86_64);
-	insn_get_length(&insn);
-	if (!insn_complete(&insn) || insn.length > len)
+	ret = insn_decode(&insn, buf, len,
+			  x86_64 ? INSN_MODE_64 : INSN_MODE_32);
+	if (ret < 0 || insn.length > len)
 		return -1;
+
 	intel_pt_insn_decoder(&insn, intel_pt_insn);
 	if (insn.length < INTEL_PT_INSN_BUF_SZ)
 		memcpy(intel_pt_insn->buf, buf, insn.length);
@@ -194,12 +196,13 @@ const char *dump_insn(struct perf_insn *x, uint64_t ip __maybe_unused,
 		      u8 *inbuf, int inlen, int *lenp)
 {
 	struct insn insn;
-	int n, i;
+	int n, i, ret;
 	int left;
 
-	insn_init(&insn, inbuf, inlen, x->is64bit);
-	insn_get_length(&insn);
-	if (!insn_complete(&insn) || insn.length > inlen)
+	ret = insn_decode(&insn, inbuf, inlen,
+			  x->is64bit ? INSN_MODE_64 : INSN_MODE_32);
+
+	if (ret < 0 || insn.length > inlen)
 		return "<bad>";
 	if (lenp)
 		*lenp = insn.length;