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
...

arch/x86/Kconfig

···
 	def_bool y
 	depends on X86_64 && SMP
 
-config X86_32_LAZY_GS
-	def_bool y
-	depends on X86_32 && !STACKPROTECTOR
-
 config ARCH_SUPPORTS_UPROBES
 	def_bool y
 
···
 	default $(success,$(srctree)/scripts/gcc-x86_32-has-stack-protector.sh $(CC))
 	help
 	   We have to make sure stack protector is unconditionally disabled if
-	   the compiler produces broken code.
+	   the compiler produces broken code or if it does not let us control
+	   the segment on 32-bit kernels.
 
 menu "Processor type and features"
 

arch/x86/Makefile

···
 
         # temporary until string.h is fixed
         KBUILD_CFLAGS += -ffreestanding
+
+	ifeq ($(CONFIG_STACKPROTECTOR),y)
+		ifeq ($(CONFIG_SMP),y)
+			KBUILD_CFLAGS += -mstack-protector-guard-reg=fs -mstack-protector-guard-symbol=__stack_chk_guard
+		else
+			KBUILD_CFLAGS += -mstack-protector-guard=global
+		endif
+	endif
 else
         BITS := 64
         UTS_MACHINE := x86_64

arch/x86/boot/compressed/sev-es.c

···
 static enum es_result vc_decode_insn(struct es_em_ctxt *ctxt)
 {
 	char buffer[MAX_INSN_SIZE];
-	enum es_result ret;
+	int ret;
 
 	memcpy(buffer, (unsigned char *)ctxt->regs->ip, MAX_INSN_SIZE);
 
-	insn_init(&ctxt->insn, buffer, MAX_INSN_SIZE, 1);
-	insn_get_length(&ctxt->insn);
+	ret = insn_decode(&ctxt->insn, buffer, MAX_INSN_SIZE, INSN_MODE_64);
+	if (ret < 0)
+		return ES_DECODE_FAILED;
 
-	ret = ctxt->insn.immediate.got ? ES_OK : ES_DECODE_FAILED;
-
-	return ret;
+	return ES_OK;
 }
 
 static enum es_result vc_write_mem(struct es_em_ctxt *ctxt,

arch/x86/entry/entry_32.S

···
  *	1C(%esp) - %ds
  *	20(%esp) - %es
  *	24(%esp) - %fs
- *	28(%esp) - %gs		saved iff !CONFIG_X86_32_LAZY_GS
+ *	28(%esp) - unused -- was %gs on old stackprotector kernels
  *	2C(%esp) - orig_eax
  *	30(%esp) - %eip
  *	34(%esp) - %cs
···
 	.section .entry.text, "ax"
 
 #define PTI_SWITCH_MASK         (1 << PAGE_SHIFT)
-
-/*
- * User gs save/restore
- *
- * %gs is used for userland TLS and kernel only uses it for stack
- * canary which is required to be at %gs:20 by gcc.  Read the comment
- * at the top of stackprotector.h for more info.
- *
- * Local labels 98 and 99 are used.
- */
-#ifdef CONFIG_X86_32_LAZY_GS
-
- /* unfortunately push/pop can't be no-op */
-.macro PUSH_GS
-	pushl	$0
-.endm
-.macro POP_GS pop=0
-	addl	$(4 + \pop), %esp
-.endm
-.macro POP_GS_EX
-.endm
-
- /* all the rest are no-op */
-.macro PTGS_TO_GS
-.endm
-.macro PTGS_TO_GS_EX
-.endm
-.macro GS_TO_REG reg
-.endm
-.macro REG_TO_PTGS reg
-.endm
-.macro SET_KERNEL_GS reg
-.endm
-
-#else	/* CONFIG_X86_32_LAZY_GS */
-
-.macro PUSH_GS
-	pushl	%gs
-.endm
-
-.macro POP_GS pop=0
-98:	popl	%gs
-  .if \pop <> 0
-	add	$\pop, %esp
-  .endif
-.endm
-.macro POP_GS_EX
-.pushsection .fixup, "ax"
-99:	movl	$0, (%esp)
-	jmp	98b
-.popsection
-	_ASM_EXTABLE(98b, 99b)
-.endm
-
-.macro PTGS_TO_GS
-98:	mov	PT_GS(%esp), %gs
-.endm
-.macro PTGS_TO_GS_EX
-.pushsection .fixup, "ax"
-99:	movl	$0, PT_GS(%esp)
-	jmp	98b
-.popsection
-	_ASM_EXTABLE(98b, 99b)
-.endm
-
-.macro GS_TO_REG reg
-	movl	%gs, \reg
-.endm
-.macro REG_TO_PTGS reg
-	movl	\reg, PT_GS(%esp)
-.endm
-.macro SET_KERNEL_GS reg
-	movl	$(__KERNEL_STACK_CANARY), \reg
-	movl	\reg, %gs
-.endm
-
-#endif /* CONFIG_X86_32_LAZY_GS */
 
 /* Unconditionally switch to user cr3 */
 .macro SWITCH_TO_USER_CR3 scratch_reg:req
···
 .macro SAVE_ALL pt_regs_ax=%eax switch_stacks=0 skip_gs=0 unwind_espfix=0
 	cld
 .if \skip_gs == 0
-	PUSH_GS
+	pushl	$0
 .endif
 	pushl	%fs
 
···
 	movl	$(__USER_DS), %edx
 	movl	%edx, %ds
 	movl	%edx, %es
-.if \skip_gs == 0
-	SET_KERNEL_GS %edx
-.endif
 	/* Switch to kernel stack if necessary */
 .if \switch_stacks > 0
 	SWITCH_TO_KERNEL_STACK
···
 1:	popl	%ds
 2:	popl	%es
 3:	popl	%fs
-	POP_GS \pop
+	addl	$(4 + \pop), %esp	/* pop the unused "gs" slot */
 	IRET_FRAME
 .pushsection .fixup, "ax"
 4:	movl	$0, (%esp)
···
 	_ASM_EXTABLE(1b, 4b)
 	_ASM_EXTABLE(2b, 5b)
 	_ASM_EXTABLE(3b, 6b)
-	POP_GS_EX
 .endm
 
 .macro RESTORE_ALL_NMI cr3_reg:req pop=0
···
 
 #ifdef CONFIG_STACKPROTECTOR
 	movl	TASK_stack_canary(%edx), %ebx
-	movl	%ebx, PER_CPU_VAR(stack_canary)+stack_canary_offset
+	movl	%ebx, PER_CPU_VAR(__stack_chk_guard)
 #endif
 
 #ifdef CONFIG_RETPOLINE
···
 	movl	PT_EIP(%esp), %edx	/* pt_regs->ip */
 	movl	PT_OLDESP(%esp), %ecx	/* pt_regs->sp */
 1:	mov	PT_FS(%esp), %fs
-	PTGS_TO_GS
 
 	popl	%ebx			/* pt_regs->bx */
 	addl	$2*4, %esp		/* skip pt_regs->cx and pt_regs->dx */
···
 	jmp	1b
 .popsection
 	_ASM_EXTABLE(1b, 2b)
-	PTGS_TO_GS_EX
 
 .Lsysenter_fix_flags:
 	pushl	$X86_EFLAGS_FIXED
···
 	SAVE_ALL switch_stacks=1 skip_gs=1 unwind_espfix=1
 	ENCODE_FRAME_POINTER
 
-	/* fixup %gs */
-	GS_TO_REG %ecx
 	movl	PT_GS(%esp), %edi		# get the function address
-	REG_TO_PTGS %ecx
-	SET_KERNEL_GS %ecx
 
 	/* fixup orig %eax */
 	movl	PT_ORIG_EAX(%esp), %edx		# get the error code

arch/x86/events/intel/ds.c

···
 		is_64bit = kernel_ip(to) || any_64bit_mode(regs);
 #endif
 		insn_init(&insn, kaddr, size, is_64bit);
-		insn_get_length(&insn);
+
 		/*
-		 * Make sure there was not a problem decoding the
-		 * instruction and getting the length.  This is
-		 * doubly important because we have an infinite
-		 * loop if insn.length=0.
+		 * Make sure there was not a problem decoding the instruction.
+		 * This is doubly important because we have an infinite loop if
+		 * insn.length=0.
 		 */
-		if (!insn.length)
+		if (insn_get_length(&insn))
 			break;
 
 		to += insn.length;

arch/x86/events/intel/lbr.c

···
 	is64 = kernel_ip((unsigned long)addr) || any_64bit_mode(current_pt_regs());
 #endif
 	insn_init(&insn, addr, bytes_read, is64);
-	insn_get_opcode(&insn);
-	if (!insn.opcode.got)
+	if (insn_get_opcode(&insn))
 		return X86_BR_ABORT;
 
 	switch (insn.opcode.bytes[0]) {
···
 		ret = X86_BR_INT;
 		break;
 	case 0xe8: /* call near rel */
-		insn_get_immediate(&insn);
-		if (insn.immediate1.value == 0) {
+		if (insn_get_immediate(&insn) || insn.immediate1.value == 0) {
 			/* zero length call */
 			ret = X86_BR_ZERO_CALL;
 			break;
···
 		ret = X86_BR_JMP;
 		break;
 	case 0xff: /* call near absolute, call far absolute ind */
-		insn_get_modrm(&insn);
+		if (insn_get_modrm(&insn))
+			return X86_BR_ABORT;
+
 		ext = (insn.modrm.bytes[0] >> 3) & 0x7;
 		switch (ext) {
 		case 2: /* near ind call */

arch/x86/include/asm/alternative.h

···
 	u16 cpuid;		/* cpuid bit set for replacement */
 	u8  instrlen;		/* length of original instruction */
 	u8  replacementlen;	/* length of new instruction */
-	u8  padlen;		/* length of build-time padding */
 } __packed;
 
 /*
···
 
 #define alt_end_marker		"663"
 #define alt_slen		"662b-661b"
-#define alt_pad_len		alt_end_marker"b-662b"
 #define alt_total_slen		alt_end_marker"b-661b"
 #define alt_rlen(num)		e_replacement(num)"f-"b_replacement(num)"f"
 
···
 	" .long " b_replacement(num)"f - .\n"		/* new instruction */ \
 	" .word " __stringify(feature) "\n"		/* feature bit     */ \
 	" .byte " alt_total_slen "\n"			/* source len      */ \
-	" .byte " alt_rlen(num) "\n"			/* replacement len */ \
-	" .byte " alt_pad_len "\n"			/* pad len */
+	" .byte " alt_rlen(num) "\n"			/* replacement len */
 
 #define ALTINSTR_REPLACEMENT(newinstr, num)		/* replacement */	\
 	"# ALT: replacement " #num "\n"						\
···
  * Peculiarities:
  * No memory clobber here.
  * Argument numbers start with 1.
- * Best is to use constraints that are fixed size (like (%1) ... "r")
- * If you use variable sized constraints like "m" or "g" in the
- * replacement make sure to pad to the worst case length.
  * Leaving an unused argument 0 to keep API compatibility.
  */
 #define alternative_input(oldinstr, newinstr, feature, input...)	\
···
  * enough information for the alternatives patching code to patch an
  * instruction. See apply_alternatives().
  */
-.macro altinstruction_entry orig alt feature orig_len alt_len pad_len
+.macro altinstruction_entry orig alt feature orig_len alt_len
 	.long \orig - .
 	.long \alt - .
 	.word \feature
 	.byte \orig_len
 	.byte \alt_len
-	.byte \pad_len
 .endm
 
 /*
···
 142:
 
 	.pushsection .altinstructions,"a"
-	altinstruction_entry 140b,143f,\feature,142b-140b,144f-143f,142b-141b
+	altinstruction_entry 140b,143f,\feature,142b-140b,144f-143f
 	.popsection
 
 	.pushsection .altinstr_replacement,"ax"
···
 142:
 
 	.pushsection .altinstructions,"a"
-	altinstruction_entry 140b,143f,\feature1,142b-140b,144f-143f,142b-141b
-	altinstruction_entry 140b,144f,\feature2,142b-140b,145f-144f,142b-141b
+	altinstruction_entry 140b,143f,\feature1,142b-140b,144f-143f
+	altinstruction_entry 140b,144f,\feature2,142b-140b,145f-144f
 	.popsection
 
 	.pushsection .altinstr_replacement,"ax"

arch/x86/include/asm/asm-prototypes.h

···
 
 #ifdef CONFIG_RETPOLINE
 
-#define DECL_INDIRECT_THUNK(reg) \
-	extern asmlinkage void __x86_indirect_thunk_ ## reg (void);
-
-#define DECL_RETPOLINE(reg) \
-	extern asmlinkage void __x86_retpoline_ ## reg (void);
-
 #undef GEN
-#define GEN(reg) DECL_INDIRECT_THUNK(reg)
+#define GEN(reg) \
+	extern asmlinkage void __x86_indirect_thunk_ ## reg (void);
 #include <asm/GEN-for-each-reg.h>
 
 #undef GEN
-#define GEN(reg) DECL_RETPOLINE(reg)
+#define GEN(reg) \
+	extern asmlinkage void __x86_indirect_alt_call_ ## reg (void);
+#include <asm/GEN-for-each-reg.h>
+
+#undef GEN
+#define GEN(reg) \
+	extern asmlinkage void __x86_indirect_alt_jmp_ ## reg (void);
 #include <asm/GEN-for-each-reg.h>
 
 #endif /* CONFIG_RETPOLINE */

arch/x86/include/asm/cpufeatures.h

···
 
 /* CPU types for specific tunings: */
 #define X86_FEATURE_K8			( 3*32+ 4) /* "" Opteron, Athlon64 */
-#define X86_FEATURE_K7			( 3*32+ 5) /* "" Athlon */
+/* FREE, was #define X86_FEATURE_K7			( 3*32+ 5) "" Athlon */
 #define X86_FEATURE_P3			( 3*32+ 6) /* "" P3 */
 #define X86_FEATURE_P4			( 3*32+ 7) /* "" P4 */
 #define X86_FEATURE_CONSTANT_TSC	( 3*32+ 8) /* TSC ticks at a constant rate */

arch/x86/include/asm/inat.h

···
  *
  * Written by Masami Hiramatsu <[e-mail]>
  */
-#include <asm/inat_types.h>
+#include <asm/inat_types.h> /* __ignore_sync_check__ */
 
 /*
  * Internal bits. Don't use bitmasks directly, because these bits are

arch/x86/include/asm/insn-eval.h

···
 			 unsigned char buf[MAX_INSN_SIZE]);
 int insn_fetch_from_user_inatomic(struct pt_regs *regs,
 				  unsigned char buf[MAX_INSN_SIZE]);
-bool insn_decode(struct insn *insn, struct pt_regs *regs,
-		 unsigned char buf[MAX_INSN_SIZE], int buf_size);
+bool insn_decode_from_regs(struct insn *insn, struct pt_regs *regs,
+			   unsigned char buf[MAX_INSN_SIZE], int buf_size);
 
 #endif /* _ASM_X86_INSN_EVAL_H */

arch/x86/include/asm/insn.h

···
 
 #include <asm/byteorder.h>
 /* insn_attr_t is defined in inat.h */
-#include <asm/inat.h>
+#include <asm/inat.h> /* __ignore_sync_check__ */
 
 #if defined(__BYTE_ORDER) ? __BYTE_ORDER == __LITTLE_ENDIAN : defined(__LITTLE_ENDIAN)
 
···
 #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)
···
 
 /* 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)
 {
···
 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)

arch/x86/include/asm/intel-family.h

···
  *		_EP	- 2 socket server parts
  *		_EX	- 4+ socket server parts
  *
- * The #define line may optionally include a comment including platform names.
+ * The #define line may optionally include a comment including platform or core
+ * names. An exception is made for skylake/kabylake where steppings seem to have gotten
+ * their own names :-(
  */
 
 /* Wildcard match for FAM6 so X86_MATCH_INTEL_FAM6_MODEL(ANY) works */
···
 #define INTEL_FAM6_BROADWELL_X		0x4F
 #define INTEL_FAM6_BROADWELL_D		0x56
 
-#define INTEL_FAM6_SKYLAKE_L		0x4E
-#define INTEL_FAM6_SKYLAKE		0x5E
-#define INTEL_FAM6_SKYLAKE_X		0x55
-#define INTEL_FAM6_KABYLAKE_L		0x8E
-#define INTEL_FAM6_KABYLAKE		0x9E
+#define INTEL_FAM6_SKYLAKE_L		0x4E	/* Sky Lake             */
+#define INTEL_FAM6_SKYLAKE		0x5E	/* Sky Lake             */
+#define INTEL_FAM6_SKYLAKE_X		0x55	/* Sky Lake             */
+/*                 CASCADELAKE_X	0x55	   Sky Lake -- s: 7     */
+/*                 COOPERLAKE_X		0x55	   Sky Lake -- s: 11    */
 
-#define INTEL_FAM6_CANNONLAKE_L		0x66
+#define INTEL_FAM6_KABYLAKE_L		0x8E	/* Sky Lake             */
+/*                 AMBERLAKE_L		0x8E	   Sky Lake -- s: 9     */
+/*                 COFFEELAKE_L		0x8E	   Sky Lake -- s: 10    */
+/*                 WHISKEYLAKE_L	0x8E       Sky Lake -- s: 11,12 */
 
-#define INTEL_FAM6_ICELAKE_X		0x6A
-#define INTEL_FAM6_ICELAKE_D		0x6C
-#define INTEL_FAM6_ICELAKE		0x7D
-#define INTEL_FAM6_ICELAKE_L		0x7E
-#define INTEL_FAM6_ICELAKE_NNPI		0x9D
+#define INTEL_FAM6_KABYLAKE		0x9E	/* Sky Lake             */
+/*                 COFFEELAKE		0x9E	   Sky Lake -- s: 10-13 */
 
-#define INTEL_FAM6_TIGERLAKE_L		0x8C
-#define INTEL_FAM6_TIGERLAKE		0x8D
+#define INTEL_FAM6_COMETLAKE		0xA5	/* Sky Lake             */
+#define INTEL_FAM6_COMETLAKE_L		0xA6	/* Sky Lake             */
 
-#define INTEL_FAM6_COMETLAKE		0xA5
-#define INTEL_FAM6_COMETLAKE_L		0xA6
+#define INTEL_FAM6_CANNONLAKE_L		0x66	/* Palm Cove */
 
-#define INTEL_FAM6_ROCKETLAKE		0xA7
+#define INTEL_FAM6_ICELAKE_X		0x6A	/* Sunny Cove */
+#define INTEL_FAM6_ICELAKE_D		0x6C	/* Sunny Cove */
+#define INTEL_FAM6_ICELAKE		0x7D	/* Sunny Cove */
+#define INTEL_FAM6_ICELAKE_L		0x7E	/* Sunny Cove */
+#define INTEL_FAM6_ICELAKE_NNPI		0x9D	/* Sunny Cove */
 
-#define INTEL_FAM6_SAPPHIRERAPIDS_X	0x8F
+#define INTEL_FAM6_LAKEFIELD		0x8A	/* Sunny Cove / Tremont */
 
-/* Hybrid Core/Atom Processors */
+#define INTEL_FAM6_ROCKETLAKE		0xA7	/* Cypress Cove */
 
-#define	INTEL_FAM6_LAKEFIELD		0x8A
-#define INTEL_FAM6_ALDERLAKE		0x97
-#define INTEL_FAM6_ALDERLAKE_L		0x9A
+#define INTEL_FAM6_TIGERLAKE_L		0x8C	/* Willow Cove */
+#define INTEL_FAM6_TIGERLAKE		0x8D	/* Willow Cove */
+#define INTEL_FAM6_SAPPHIRERAPIDS_X	0x8F	/* Willow Cove */
+
+#define INTEL_FAM6_ALDERLAKE		0x97	/* Golden Cove / Gracemont */
+#define INTEL_FAM6_ALDERLAKE_L		0x9A	/* Golden Cove / Gracemont */
 
 /* "Small Core" Processors (Atom) */
 

arch/x86/include/asm/jump_label.h

···
 
 #define JUMP_LABEL_NOP_SIZE 5
 
-#ifdef CONFIG_X86_64
-# define STATIC_KEY_INIT_NOP P6_NOP5_ATOMIC
-#else
-# define STATIC_KEY_INIT_NOP GENERIC_NOP5_ATOMIC
-#endif
-
 #include <asm/asm.h>
 #include <asm/nops.h>
 
···
 static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
 	asm_volatile_goto("1:"
-		".byte " __stringify(STATIC_KEY_INIT_NOP) "\n\t"
+		".byte " __stringify(BYTES_NOP5) "\n\t"
 		".pushsection __jump_table,  \"aw\" \n\t"
 		_ASM_ALIGN "\n\t"
 		".long 1b - ., %l[l_yes] - . \n\t"
···
 	.long		\target - .Lstatic_jump_after_\@
 .Lstatic_jump_after_\@:
 	.else
-	.byte		STATIC_KEY_INIT_NOP
+	.byte		BYTES_NOP5
 	.endif
 	.pushsection __jump_table, "aw"
 	_ASM_ALIGN
···
 .macro STATIC_JUMP_IF_FALSE target, key, def
 .Lstatic_jump_\@:
 	.if \def
-	.byte		STATIC_KEY_INIT_NOP
+	.byte		BYTES_NOP5
 	.else
 	/* Equivalent to "jmp.d32 \target" */
 	.byte		0xe9

arch/x86/include/asm/kprobes.h

···
 	 * a post_handler).
 	 */
 	unsigned boostable:1;
-	unsigned if_modifier:1;
-	unsigned is_call:1;
-	unsigned is_pushf:1;
-	unsigned is_abs_ip:1;
+	unsigned char size;	/* The size of insn */
+	union {
+		unsigned char opcode;
+		struct {
+			unsigned char type;
+		} jcc;
+		struct {
+			unsigned char type;
+			unsigned char asize;
+		} loop;
+		struct {
+			unsigned char reg;
+		} indirect;
+	};
+	s32 rel32;	/* relative offset must be s32, s16, or s8 */
+	void (*emulate_op)(struct kprobe *p, struct pt_regs *regs);
 	/* Number of bytes of text poked */
 	int tp_len;
 };
···
 extern int kprobe_exceptions_notify(struct notifier_block *self,
 				    unsigned long val, void *data);
 extern int kprobe_int3_handler(struct pt_regs *regs);
-extern int kprobe_debug_handler(struct pt_regs *regs);
 
 #else
 

arch/x86/include/asm/nops.h

···
 
 /*
  * Define nops for use with alternative() and for tracing.
- *
- * *_NOP5_ATOMIC must be a single instruction.
  */
 
-#define NOP_DS_PREFIX 0x3e
+#ifndef CONFIG_64BIT
 
-/* generic versions from gas
-   1: nop
-   the following instructions are NOT nops in 64-bit mode,
-   for 64-bit mode use K8 or P6 nops instead
-   2: movl %esi,%esi
-   3: leal 0x00(%esi),%esi
-   4: leal 0x00(,%esi,1),%esi
-   6: leal 0x00000000(%esi),%esi
-   7: leal 0x00000000(,%esi,1),%esi
-*/
-#define GENERIC_NOP1 0x90
-#define GENERIC_NOP2 0x89,0xf6
-#define GENERIC_NOP3 0x8d,0x76,0x00
-#define GENERIC_NOP4 0x8d,0x74,0x26,0x00
-#define GENERIC_NOP5 GENERIC_NOP1,GENERIC_NOP4
-#define GENERIC_NOP6 0x8d,0xb6,0x00,0x00,0x00,0x00
-#define GENERIC_NOP7 0x8d,0xb4,0x26,0x00,0x00,0x00,0x00
-#define GENERIC_NOP8 GENERIC_NOP1,GENERIC_NOP7
-#define GENERIC_NOP5_ATOMIC NOP_DS_PREFIX,GENERIC_NOP4
+/*
+ * 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
 
-/* Opteron 64bit nops
-   1: nop
-   2: osp nop
-   3: osp osp nop
-   4: osp osp osp nop
-*/
-#define K8_NOP1 GENERIC_NOP1
-#define K8_NOP2	0x66,K8_NOP1
-#define K8_NOP3	0x66,K8_NOP2
-#define K8_NOP4	0x66,K8_NOP3
-#define K8_NOP5	K8_NOP3,K8_NOP2
-#define K8_NOP6	K8_NOP3,K8_NOP3
-#define K8_NOP7	K8_NOP4,K8_NOP3
-#define K8_NOP8	K8_NOP4,K8_NOP4
-#define K8_NOP5_ATOMIC 0x66,K8_NOP4
+#else
 
-/* K7 nops
-   uses eax dependencies (arbitrary choice)
-   1: nop
-   2: movl %eax,%eax
-   3: leal (,%eax,1),%eax
-   4: leal 0x00(,%eax,1),%eax
-   6: leal 0x00000000(%eax),%eax
-   7: leal 0x00000000(,%eax,1),%eax
-*/
-#define K7_NOP1	GENERIC_NOP1
-#define K7_NOP2	0x8b,0xc0
-#define K7_NOP3	0x8d,0x04,0x20
-#define K7_NOP4	0x8d,0x44,0x20,0x00
-#define K7_NOP5	K7_NOP4,K7_NOP1
-#define K7_NOP6	0x8d,0x80,0,0,0,0
-#define K7_NOP7	0x8D,0x04,0x05,0,0,0,0
-#define K7_NOP8	K7_NOP7,K7_NOP1
-#define K7_NOP5_ATOMIC NOP_DS_PREFIX,K7_NOP4
+/*
+ * 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
 
-/* P6 nops
-   uses eax dependencies (Intel-recommended choice)
-   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)
-   Note: All the above are assumed to be a single instruction.
-	There is kernel code that depends on this.
-*/
-#define P6_NOP1	GENERIC_NOP1
-#define P6_NOP2	0x66,0x90
-#define P6_NOP3	0x0f,0x1f,0x00
-#define P6_NOP4	0x0f,0x1f,0x40,0
-#define P6_NOP5	0x0f,0x1f,0x44,0x00,0
-#define P6_NOP6	0x66,0x0f,0x1f,0x44,0x00,0
-#define P6_NOP7	0x0f,0x1f,0x80,0,0,0,0
-#define P6_NOP8	0x0f,0x1f,0x84,0x00,0,0,0,0
-#define P6_NOP5_ATOMIC P6_NOP5
+#endif /* CONFIG_64BIT */
 
 #ifdef __ASSEMBLY__
 #define _ASM_MK_NOP(x) .byte x
···
 #define _ASM_MK_NOP(x) ".byte " __stringify(x) "\n"
 #endif
 
-#if defined(CONFIG_MK7)
-#define ASM_NOP1 _ASM_MK_NOP(K7_NOP1)
-#define ASM_NOP2 _ASM_MK_NOP(K7_NOP2)
-#define ASM_NOP3 _ASM_MK_NOP(K7_NOP3)
-#define ASM_NOP4 _ASM_MK_NOP(K7_NOP4)
-#define ASM_NOP5 _ASM_MK_NOP(K7_NOP5)
-#define ASM_NOP6 _ASM_MK_NOP(K7_NOP6)
-#define ASM_NOP7 _ASM_MK_NOP(K7_NOP7)
-#define ASM_NOP8 _ASM_MK_NOP(K7_NOP8)
-#define ASM_NOP5_ATOMIC _ASM_MK_NOP(K7_NOP5_ATOMIC)
-#elif defined(CONFIG_X86_P6_NOP)
-#define ASM_NOP1 _ASM_MK_NOP(P6_NOP1)
-#define ASM_NOP2 _ASM_MK_NOP(P6_NOP2)
-#define ASM_NOP3 _ASM_MK_NOP(P6_NOP3)
-#define ASM_NOP4 _ASM_MK_NOP(P6_NOP4)
-#define ASM_NOP5 _ASM_MK_NOP(P6_NOP5)
-#define ASM_NOP6 _ASM_MK_NOP(P6_NOP6)
-#define ASM_NOP7 _ASM_MK_NOP(P6_NOP7)
-#define ASM_NOP8 _ASM_MK_NOP(P6_NOP8)
-#define ASM_NOP5_ATOMIC _ASM_MK_NOP(P6_NOP5_ATOMIC)
-#elif defined(CONFIG_X86_64)
-#define ASM_NOP1 _ASM_MK_NOP(K8_NOP1)
-#define ASM_NOP2 _ASM_MK_NOP(K8_NOP2)
-#define ASM_NOP3 _ASM_MK_NOP(K8_NOP3)
-#define ASM_NOP4 _ASM_MK_NOP(K8_NOP4)
-#define ASM_NOP5 _ASM_MK_NOP(K8_NOP5)
-#define ASM_NOP6 _ASM_MK_NOP(K8_NOP6)
-#define ASM_NOP7 _ASM_MK_NOP(K8_NOP7)
-#define ASM_NOP8 _ASM_MK_NOP(K8_NOP8)
-#define ASM_NOP5_ATOMIC _ASM_MK_NOP(K8_NOP5_ATOMIC)
-#else
-#define ASM_NOP1 _ASM_MK_NOP(GENERIC_NOP1)
-#define ASM_NOP2 _ASM_MK_NOP(GENERIC_NOP2)
-#define ASM_NOP3 _ASM_MK_NOP(GENERIC_NOP3)
-#define ASM_NOP4 _ASM_MK_NOP(GENERIC_NOP4)
-#define ASM_NOP5 _ASM_MK_NOP(GENERIC_NOP5)
-#define ASM_NOP6 _ASM_MK_NOP(GENERIC_NOP6)
-#define ASM_NOP7 _ASM_MK_NOP(GENERIC_NOP7)
-#define ASM_NOP8 _ASM_MK_NOP(GENERIC_NOP8)
-#define ASM_NOP5_ATOMIC _ASM_MK_NOP(GENERIC_NOP5_ATOMIC)
-#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
-#define NOP_ATOMIC5 (ASM_NOP_MAX+1)	/* Entry for the 5-byte atomic NOP */
 
 #ifndef __ASSEMBLY__
-extern const unsigned char * const *ideal_nops;
-extern void arch_init_ideal_nops(void);
+extern const unsigned char * const x86_nops[];
 #endif
 
 #endif /* _ASM_X86_NOPS_H */

arch/x86/include/asm/nospec-branch.h

···
 .macro JMP_NOSPEC reg:req
 #ifdef CONFIG_RETPOLINE
 	ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), \
-		      __stringify(jmp __x86_retpoline_\reg), X86_FEATURE_RETPOLINE, \
+		      __stringify(jmp __x86_indirect_thunk_\reg), X86_FEATURE_RETPOLINE, \
 		      __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), X86_FEATURE_RETPOLINE_AMD
 #else
 	jmp	*%\reg
···
 .macro CALL_NOSPEC reg:req
 #ifdef CONFIG_RETPOLINE
 	ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; call *%\reg), \
-		      __stringify(call __x86_retpoline_\reg), X86_FEATURE_RETPOLINE, \
+		      __stringify(call __x86_indirect_thunk_\reg), X86_FEATURE_RETPOLINE, \
 		      __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; call *%\reg), X86_FEATURE_RETPOLINE_AMD
 #else
 	call	*%\reg
···
 	ALTERNATIVE_2(						\
 	ANNOTATE_RETPOLINE_SAFE					\
 	"call *%[thunk_target]\n",				\
-	"call __x86_retpoline_%V[thunk_target]\n",		\
+	"call __x86_indirect_thunk_%V[thunk_target]\n",		\
 	X86_FEATURE_RETPOLINE,					\
 	"lfence;\n"						\
 	ANNOTATE_RETPOLINE_SAFE					\

arch/x86/include/asm/processor.h

···
 	 * GCC hardcodes the stack canary as %gs:40.  Since the
 	 * irq_stack is the object at %gs:0, we reserve the bottom
 	 * 48 bytes of the irq stack for the canary.
+	 *
+	 * Once we are willing to require -mstack-protector-guard-symbol=
+	 * support for x86_64 stackprotector, we can get rid of this.
 	 */
 	char		gs_base[40];
 	unsigned long	stack_canary;
···
 void current_save_fsgs(void);
 #else	/* X86_64 */
 #ifdef CONFIG_STACKPROTECTOR
-/*
- * Make sure stack canary segment base is cached-aligned:
- *   "For Intel Atom processors, avoid non zero segment base address
- *    that is not aligned to cache line boundary at all cost."
- * (Optim Ref Manual Assembly/Compiler Coding Rule 15.)
- */
-struct stack_canary {
-	char __pad[20];		/* canary at %gs:20 */
-	unsigned long canary;
-};
-DECLARE_PER_CPU_ALIGNED(struct stack_canary, stack_canary);
+DECLARE_PER_CPU(unsigned long, __stack_chk_guard);
 #endif
 DECLARE_PER_CPU(struct irq_stack *, hardirq_stack_ptr);
 DECLARE_PER_CPU(struct irq_stack *, softirq_stack_ptr);

arch/x86/include/asm/ptrace.h

···
 	unsigned short __esh;
 	unsigned short fs;
 	unsigned short __fsh;
-	/* On interrupt, gs and __gsh store the vector number. */
+	/*
+	 * On interrupt, gs and __gsh store the vector number.  They never
+	 * store gs any more.
+	 */
 	unsigned short gs;
 	unsigned short __gsh;
 	/* On interrupt, this is the error code. */

arch/x86/include/asm/segment.h

···
  *
  *  26 - ESPFIX small SS
  *  27 - per-cpu			[ offset to per-cpu data area ]
- *  28 - stack_canary-20		[ for stack protector ]		<=== cacheline #8
+ *  28 - unused
  *  29 - unused
  *  30 - unused
  *  31 - TSS for double fault handler
···
 
 #define GDT_ENTRY_ESPFIX_SS		26
 #define GDT_ENTRY_PERCPU		27
-#define GDT_ENTRY_STACK_CANARY		28
 
 #define GDT_ENTRY_DOUBLEFAULT_TSS	31
 
···
 # define __KERNEL_PERCPU		(GDT_ENTRY_PERCPU*8)
 #else
 # define __KERNEL_PERCPU		0
-#endif
-
-#ifdef CONFIG_STACKPROTECTOR
-# define __KERNEL_STACK_CANARY		(GDT_ENTRY_STACK_CANARY*8)
-#else
-# define __KERNEL_STACK_CANARY		0
 #endif
 
 #else /* 64-bit: */
···
 	asm("mov %%" #seg ",%0":"=r" (value) : : "memory")
 
 /*
- * x86-32 user GS accessors:
+ * x86-32 user GS accessors.  This is ugly and could do with some cleaning up.
  */
 #ifdef CONFIG_X86_32
-# ifdef CONFIG_X86_32_LAZY_GS
-#  define get_user_gs(regs)		(u16)({ unsigned long v; savesegment(gs, v); v; })
-#  define set_user_gs(regs, v)		loadsegment(gs, (unsigned long)(v))
-#  define task_user_gs(tsk)		((tsk)->thread.gs)
-#  define lazy_save_gs(v)		savesegment(gs, (v))
-#  define lazy_load_gs(v)		loadsegment(gs, (v))
-# else	/* X86_32_LAZY_GS */
-#  define get_user_gs(regs)		(u16)((regs)->gs)
-#  define set_user_gs(regs, v)		do { (regs)->gs = (v); } while (0)
-#  define task_user_gs(tsk)		(task_pt_regs(tsk)->gs)
-#  define lazy_save_gs(v)		do { } while (0)
-#  define lazy_load_gs(v)		do { } while (0)
-# endif	/* X86_32_LAZY_GS */
+# define get_user_gs(regs)		(u16)({ unsigned long v; savesegment(gs, v); v; })
+# define set_user_gs(regs, v)		loadsegment(gs, (unsigned long)(v))
+# define task_user_gs(tsk)		((tsk)->thread.gs)
+# define lazy_save_gs(v)		savesegment(gs, (v))
+# define lazy_load_gs(v)		loadsegment(gs, (v))
+# define load_gs_index(v)		loadsegment(gs, (v))
 #endif	/* X86_32 */
 
 #endif /* !__ASSEMBLY__ */

arch/x86/include/asm/special_insns.h

···
 
 static inline void clflushopt(volatile void *__p)
 {
-	alternative_io(".byte " __stringify(NOP_DS_PREFIX) "; clflush %P0",
+	alternative_io(".byte 0x3e; clflush %P0",
 		       ".byte 0x66; clflush %P0",
 		       X86_FEATURE_CLFLUSHOPT,
 		       "+m" (*(volatile char __force *)__p));
···
 	volatile struct { char x[64]; } *p = __p;
 
 	asm volatile(ALTERNATIVE_2(
-		".byte " __stringify(NOP_DS_PREFIX) "; clflush (%[pax])",
+		".byte 0x3e; clflush (%[pax])",
 		".byte 0x66; clflush (%[pax])", /* clflushopt (%%rax) */
 		X86_FEATURE_CLFLUSHOPT,
 		".byte 0x66, 0x0f, 0xae, 0x30",  /* clwb (%%rax) */

arch/x86/include/asm/stackprotector.h

···
  * Stack protector works by putting predefined pattern at the start of
  * the stack frame and verifying that it hasn't been overwritten when
  * returning from the function.  The pattern is called stack canary
- * and unfortunately gcc requires it to be at a fixed offset from %gs.
- * On x86_64, the offset is 40 bytes and on x86_32 20 bytes.  x86_64
- * and x86_32 use segment registers differently and thus handles this
- * requirement differently.
+ * and unfortunately gcc historically required it to be at a fixed offset
+ * from the percpu segment base.  On x86_64, the offset is 40 bytes.
  *
- * On x86_64, %gs is shared by percpu area and stack canary.  All
- * percpu symbols are zero based and %gs points to the base of percpu
- * area.  The first occupant of the percpu area is always
- * fixed_percpu_data which contains stack_canary at offset 40.  Userland
- * %gs is always saved and restored on kernel entry and exit using
- * swapgs, so stack protector doesn't add any complexity there.
+ * The same segment is shared by percpu area and stack canary.  On
+ * x86_64, percpu symbols are zero based and %gs (64-bit) points to the
+ * base of percpu area.  The first occupant of the percpu area is always
+ * fixed_percpu_data which contains stack_canary at the approproate
+ * offset.  On x86_32, the stack canary is just a regular percpu
+ * variable.
  *
- * On x86_32, it's slightly more complicated.  As in x86_64, %gs is
- * used for userland TLS.  Unfortunately, some processors are much
- * slower at loading segment registers with different value when
- * entering and leaving the kernel, so the kernel uses %fs for percpu
- * area and manages %gs lazily so that %gs is switched only when
- * necessary, usually during task switch.
+ * Putting percpu data in %fs on 32-bit is a minor optimization compared to
+ * using %gs.  Since 32-bit userspace normally has %fs == 0, we are likely
+ * to load 0 into %fs on exit to usermode, whereas with percpu data in
+ * %gs, we are likely to load a non-null %gs on return to user mode.
  *
- * As gcc requires the stack canary at %gs:20, %gs can't be managed
- * lazily if stack protector is enabled, so the kernel saves and
- * restores userland %gs on kernel entry and exit.  This behavior is
- * controlled by CONFIG_X86_32_LAZY_GS and accessors are defined in
- * system.h to hide the details.
+ * Once we are willing to require GCC 8.1 or better for 64-bit stackprotector
+ * support, we can remove some of this complexity.
  */
 
 #ifndef _ASM_STACKPROTECTOR_H
···
 
 #include <linux/random.h>
 #include <linux/sched.h>
-
-/*
- * 24 byte read-only segment initializer for stack canary.  Linker
- * can't handle the address bit shifting.  Address will be set in
- * head_32 for boot CPU and setup_per_cpu_areas() for others.
- */
-#define GDT_STACK_CANARY_INIT						\
-	[GDT_ENTRY_STACK_CANARY] = GDT_ENTRY_INIT(0x4090, 0, 0x18),
 
 /*
  * Initialize the stackprotector canary value.
···
 #ifdef CONFIG_X86_64
 	this_cpu_write(fixed_percpu_data.stack_canary, canary);
 #else
-	this_cpu_write(stack_canary.canary, canary);
+	this_cpu_write(__stack_chk_guard, canary);
 #endif
 }
 
···
 #ifdef CONFIG_X86_64
 	per_cpu(fixed_percpu_data.stack_canary, cpu) = idle->stack_canary;
 #else
-	per_cpu(stack_canary.canary, cpu) = idle->stack_canary;
-#endif
-}
-
-static inline void setup_stack_canary_segment(int cpu)
-{
-#ifdef CONFIG_X86_32
-	unsigned long canary = (unsigned long)&per_cpu(stack_canary, cpu);
-	struct desc_struct *gdt_table = get_cpu_gdt_rw(cpu);
-	struct desc_struct desc;
-
-	desc = gdt_table[GDT_ENTRY_STACK_CANARY];
-	set_desc_base(&desc, canary);
-	write_gdt_entry(gdt_table, GDT_ENTRY_STACK_CANARY, &desc, DESCTYPE_S);
-#endif
-}
-
-static inline void load_stack_canary_segment(void)
-{
-#ifdef CONFIG_X86_32
-	asm("mov %0, %%gs" : : "r" (__KERNEL_STACK_CANARY) : "memory");
+	per_cpu(__stack_chk_guard, cpu) = idle->stack_canary;
 #endif
 }
 
 #else	/* STACKPROTECTOR */
 
-#define GDT_STACK_CANARY_INIT
-
 /* dummy boot_init_stack_canary() is defined in linux/stackprotector.h */
-
-static inline void setup_stack_canary_segment(int cpu)
-{ }
 
 static inline void cpu_init_stack_canary(int cpu, struct task_struct *idle)
 { }
-
-static inline void load_stack_canary_segment(void)
-{
-#ifdef CONFIG_X86_32
-	asm volatile ("mov %0, %%gs" : : "r" (0));
-#endif
-}
 
 #endif	/* STACKPROTECTOR */
 #endif	/* _ASM_STACKPROTECTOR_H */

arch/x86/include/asm/suspend_32.h

···
 /* image of the saved processor state */
 struct saved_context {
 	/*
-	 * On x86_32, all segment registers, with the possible exception of
-	 * gs, are saved at kernel entry in pt_regs.
+	 * On x86_32, all segment registers except gs are saved at kernel
+	 * entry in pt_regs.
 	 */
-#ifdef CONFIG_X86_32_LAZY_GS
 	u16 gs;
-#endif
 	unsigned long cr0, cr2, cr3, cr4;
 	u64 misc_enable;
 	bool misc_enable_saved;

arch/x86/kernel/alternative.c

···
 	}								\
 } while (0)
 
-/*
- * Each GENERIC_NOPX is of X bytes, and defined as an array of bytes
- * that correspond to that nop. Getting from one nop to the next, we
- * add to the array the offset that is equal to the sum of all sizes of
- * nops preceding the one we are after.
- *
- * Note: The GENERIC_NOP5_ATOMIC is at the end, as it breaks the
- * nice symmetry of sizes of the previous nops.
- */
-#if defined(GENERIC_NOP1) && !defined(CONFIG_X86_64)
-static const unsigned char intelnops[] =
+const unsigned char x86nops[] =
 {
-	GENERIC_NOP1,
-	GENERIC_NOP2,
-	GENERIC_NOP3,
-	GENERIC_NOP4,
-	GENERIC_NOP5,
-	GENERIC_NOP6,
-	GENERIC_NOP7,
-	GENERIC_NOP8,
-	GENERIC_NOP5_ATOMIC
+	BYTES_NOP1,
+	BYTES_NOP2,
+	BYTES_NOP3,
+	BYTES_NOP4,
+	BYTES_NOP5,
+	BYTES_NOP6,
+	BYTES_NOP7,
+	BYTES_NOP8,
 };
-static const unsigned char * const intel_nops[ASM_NOP_MAX+2] =
+
+const unsigned char * const x86_nops[ASM_NOP_MAX+1] =
 {
 	NULL,
-	intelnops,
-	intelnops + 1,
-	intelnops + 1 + 2,
-	intelnops + 1 + 2 + 3,
-	intelnops + 1 + 2 + 3 + 4,
-	intelnops + 1 + 2 + 3 + 4 + 5,
-	intelnops + 1 + 2 + 3 + 4 + 5 + 6,
-	intelnops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
-	intelnops + 1 + 2 + 3 + 4 + 5 + 6 + 7 + 8,
+	x86nops,
+	x86nops + 1,
+	x86nops + 1 + 2,
+	x86nops + 1 + 2 + 3,
+	x86nops + 1 + 2 + 3 + 4,
+	x86nops + 1 + 2 + 3 + 4 + 5,
+	x86nops + 1 + 2 + 3 + 4 + 5 + 6,
+	x86nops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
 };
-#endif
-
-#ifdef K8_NOP1
-static const unsigned char k8nops[] =
-{
-	K8_NOP1,
-	K8_NOP2,
-	K8_NOP3,
-	K8_NOP4,
-	K8_NOP5,
-	K8_NOP6,
-	K8_NOP7,
-	K8_NOP8,
-	K8_NOP5_ATOMIC
-};
-static const unsigned char * const k8_nops[ASM_NOP_MAX+2] =
-{
-	NULL,
-	k8nops,
-	k8nops + 1,
-	k8nops + 1 + 2,
-	k8nops + 1 + 2 + 3,
-	k8nops + 1 + 2 + 3 + 4,
-	k8nops + 1 + 2 + 3 + 4 + 5,
-	k8nops + 1 + 2 + 3 + 4 + 5 + 6,
-	k8nops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
-	k8nops + 1 + 2 + 3 + 4 + 5 + 6 + 7 + 8,
-};
-#endif
-
-#if defined(K7_NOP1) && !defined(CONFIG_X86_64)
-static const unsigned char k7nops[] =
-{
-	K7_NOP1,
-	K7_NOP2,
-	K7_NOP3,
-	K7_NOP4,
-	K7_NOP5,
-	K7_NOP6,
-	K7_NOP7,
-	K7_NOP8,
-	K7_NOP5_ATOMIC
-};
-static const unsigned char * const k7_nops[ASM_NOP_MAX+2] =
-{
-	NULL,
-	k7nops,
-	k7nops + 1,
-	k7nops + 1 + 2,
-	k7nops + 1 + 2 + 3,
-	k7nops + 1 + 2 + 3 + 4,
-	k7nops + 1 + 2 + 3 + 4 + 5,
-	k7nops + 1 + 2 + 3 + 4 + 5 + 6,
-	k7nops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
-	k7nops + 1 + 2 + 3 + 4 + 5 + 6 + 7 + 8,
-};
-#endif
-
-#ifdef P6_NOP1
-static const unsigned char p6nops[] =
-{
-	P6_NOP1,
-	P6_NOP2,
-	P6_NOP3,
-	P6_NOP4,
-	P6_NOP5,
-	P6_NOP6,
-	P6_NOP7,
-	P6_NOP8,
-	P6_NOP5_ATOMIC
-};
-static const unsigned char * const p6_nops[ASM_NOP_MAX+2] =
-{
-	NULL,
-	p6nops,
-	p6nops + 1,
-	p6nops + 1 + 2,
-	p6nops + 1 + 2 + 3,
-	p6nops + 1 + 2 + 3 + 4,
-	p6nops + 1 + 2 + 3 + 4 + 5,
-	p6nops + 1 + 2 + 3 + 4 + 5 + 6,
-	p6nops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
-	p6nops + 1 + 2 + 3 + 4 + 5 + 6 + 7 + 8,
-};
-#endif
-
-/* Initialize these to a safe default */
-#ifdef CONFIG_X86_64
-const unsigned char * const *ideal_nops = p6_nops;
-#else
-const unsigned char * const *ideal_nops = intel_nops;
-#endif
-
-void __init arch_init_ideal_nops(void)
-{
-	switch (boot_cpu_data.x86_vendor) {
-	case X86_VENDOR_INTEL:
-		/*
-		 * Due to a decoder implementation quirk, some
-		 * specific Intel CPUs actually perform better with
-		 * the "k8_nops" than with the SDM-recommended NOPs.
-		 */
-		if (boot_cpu_data.x86 == 6 &&
-		    boot_cpu_data.x86_model >= 0x0f &&
-		    boot_cpu_data.x86_model != 0x1c &&
-		    boot_cpu_data.x86_model != 0x26 &&
-		    boot_cpu_data.x86_model != 0x27 &&
-		    boot_cpu_data.x86_model < 0x30) {
-			ideal_nops = k8_nops;
-		} else if (boot_cpu_has(X86_FEATURE_NOPL)) {
-			   ideal_nops = p6_nops;
-		} else {
-#ifdef CONFIG_X86_64
-			ideal_nops = k8_nops;
-#else
-			ideal_nops = intel_nops;
-#endif
-		}
-		break;
-
-	case X86_VENDOR_HYGON:
-		ideal_nops = p6_nops;
-		return;
-
-	case X86_VENDOR_AMD:
-		if (boot_cpu_data.x86 > 0xf) {
-			ideal_nops = p6_nops;
-			return;
-		}
-
-		fallthrough;
-
-	default:
-#ifdef CONFIG_X86_64
-		ideal_nops = k8_nops;
-#else
-		if (boot_cpu_has(X86_FEATURE_K8))
-			ideal_nops = k8_nops;
-		else if (boot_cpu_has(X86_FEATURE_K7))
-			ideal_nops = k7_nops;
-		else
-			ideal_nops = intel_nops;
-#endif
-	}
-}
 
 /* Use this to add nops to a buffer, then text_poke the whole buffer. */
 static void __init_or_module add_nops(void *insns, unsigned int len)
···
 		unsigned int noplen = len;
 		if (noplen > ASM_NOP_MAX)
 			noplen = ASM_NOP_MAX;
-		memcpy(insns, ideal_nops[noplen], noplen);
+		memcpy(insns, x86_nops[noplen], noplen);
 		insns += noplen;
 		len -= noplen;
 	}
···
 static void __init_or_module noinline optimize_nops(struct alt_instr *a, u8 *instr)
 {
 	unsigned long flags;
-	int i;
+	struct insn insn;
+	int nop, i = 0;
 
-	for (i = 0; i < a->padlen; i++) {
-		if (instr[i] != 0x90)
+	/*
+	 * Jump over the non-NOP insns, the remaining bytes must be single-byte
+	 * NOPs, optimize them.
+	 */
+	for (;;) {
+		if (insn_decode_kernel(&insn, &instr[i]))
+			return;
+
+		if (insn.length == 1 && insn.opcode.bytes[0] == 0x90)
+			break;
+
+		if ((i += insn.length) >= a->instrlen)
+			return;
+	}
+
+	for (nop = i; i < a->instrlen; i++) {
+		if (WARN_ONCE(instr[i] != 0x90, "Not a NOP at 0x%px\n", &instr[i]))
 			return;
 	}
 
 	local_irq_save(flags);
-	add_nops(instr + (a->instrlen - a->padlen), a->padlen);
+	add_nops(instr + nop, i - nop);
 	local_irq_restore(flags);
 
 	DUMP_BYTES(instr, a->instrlen, "%px: [%d:%d) optimized NOPs: ",
-		   instr, a->instrlen - a->padlen, a->padlen);
+		   instr, nop, a->instrlen);
 }
 
 /*
···
 		 * - feature not present but ALTINSTR_FLAG_INV is set to mean,
 		 *   patch if feature is *NOT* present.
 		 */
-		if (!boot_cpu_has(feature) == !(a->cpuid & ALTINSTR_FLAG_INV)) {
-			if (a->padlen > 1)
-				optimize_nops(a, instr);
+		if (!boot_cpu_has(feature) == !(a->cpuid & ALTINSTR_FLAG_INV))
+			goto next;
 
-			continue;
-		}
-
-		DPRINTK("feat: %s%d*32+%d, old: (%pS (%px) len: %d), repl: (%px, len: %d), pad: %d",
+		DPRINTK("feat: %s%d*32+%d, old: (%pS (%px) len: %d), repl: (%px, len: %d)",
 			(a->cpuid & ALTINSTR_FLAG_INV) ? "!" : "",
 			feature >> 5,
 			feature & 0x1f,
 			instr, instr, a->instrlen,
-			replacement, a->replacementlen, a->padlen);
+			replacement, a->replacementlen);
 
 		DUMP_BYTES(instr, a->instrlen, "%px: old_insn: ", instr);
 		DUMP_BYTES(replacement, a->replacementlen, "%px: rpl_insn: ", replacement);
···
 		if (a->replacementlen && is_jmp(replacement[0]))
 			recompute_jump(a, instr, replacement, insn_buff);
 
-		if (a->instrlen > a->replacementlen) {
-			add_nops(insn_buff + a->replacementlen,
-				 a->instrlen - a->replacementlen);
-			insn_buff_sz += a->instrlen - a->replacementlen;
-		}
+		for (; insn_buff_sz < a->instrlen; insn_buff_sz++)
+			insn_buff[insn_buff_sz] = 0x90;
+
 		DUMP_BYTES(insn_buff, insn_buff_sz, "%px: final_insn: ", instr);
 
 		text_poke_early(instr, insn_buff, insn_buff_sz);
+
+next:
+		optimize_nops(a, instr);
 	}
 }
 
···
 			       const void *opcode, size_t len, const void *emulate)
 {
 	struct insn insn;
+	int ret;
 
 	memcpy((void *)tp->text, opcode, len);
 	if (!emulate)
 		emulate = opcode;
 
-	kernel_insn_init(&insn, emulate, MAX_INSN_SIZE);
-	insn_get_length(&insn);
+	ret = insn_decode_kernel(&insn, emulate);
 
-	BUG_ON(!insn_complete(&insn));
+	BUG_ON(ret < 0);
 	BUG_ON(len != insn.length);
 
 	tp->rel_addr = addr - (void *)_stext;
···
 	default: /* assume NOP */
 		switch (len) {
 		case 2: /* NOP2 -- emulate as JMP8+0 */
-			BUG_ON(memcmp(emulate, ideal_nops[len], len));
+			BUG_ON(memcmp(emulate, x86_nops[len], len));
 			tp->opcode = JMP8_INSN_OPCODE;
 			tp->rel32 = 0;
 			break;
 
 		case 5: /* NOP5 -- emulate as JMP32+0 */
-			BUG_ON(memcmp(emulate, ideal_nops[NOP_ATOMIC5], len));
+			BUG_ON(memcmp(emulate, x86_nops[len], len));
 			tp->opcode = JMP32_INSN_OPCODE;
 			tp->rel32 = 0;
 			break;

arch/x86/kernel/asm-offsets_32.c

···
 	       offsetof(struct cpu_entry_area, tss.x86_tss.sp1) -
 	       offsetofend(struct cpu_entry_area, entry_stack_page.stack));
 
-#ifdef CONFIG_STACKPROTECTOR
-	BLANK();
-	OFFSET(stack_canary_offset, stack_canary, canary);
-#endif
-
 	BLANK();
 	DEFINE(EFI_svam, offsetof(efi_runtime_services_t, set_virtual_address_map));
 }

arch/x86/kernel/cpu/amd.c

···
 
 	early_init_amd_mc(c);
 
-#ifdef CONFIG_X86_32
-	if (c->x86 == 6)
-		set_cpu_cap(c, X86_FEATURE_K7);
-#endif
-
 	if (c->x86 >= 0xf)
 		set_cpu_cap(c, X86_FEATURE_K8);
 

arch/x86/kernel/cpu/common.c

···
 
 	[GDT_ENTRY_ESPFIX_SS]		= GDT_ENTRY_INIT(0xc092, 0, 0xfffff),
 	[GDT_ENTRY_PERCPU]		= GDT_ENTRY_INIT(0xc092, 0, 0xfffff),
-	GDT_STACK_CANARY_INIT
 #endif
 } };
 EXPORT_PER_CPU_SYMBOL_GPL(gdt_page);
···
 	__loadsegment_simple(gs, 0);
 	wrmsrl(MSR_GS_BASE, cpu_kernelmode_gs_base(cpu));
 #endif
-	load_stack_canary_segment();
 }
 
 #ifdef CONFIG_X86_32
···
 EXPORT_PER_CPU_SYMBOL(cpu_current_top_of_stack);
 
 #ifdef CONFIG_STACKPROTECTOR
-DEFINE_PER_CPU_ALIGNED(struct stack_canary, stack_canary);
+DEFINE_PER_CPU(unsigned long, __stack_chk_guard);
+EXPORT_PER_CPU_SYMBOL(__stack_chk_guard);
 #endif
 
 #endif	/* CONFIG_X86_64 */

arch/x86/kernel/cpu/hygon.c

···
 		u32 ecx;
 
 		ecx = cpuid_ecx(0x8000001e);
-		nodes_per_socket = ((ecx >> 8) & 7) + 1;
+		__max_die_per_package = nodes_per_socket = ((ecx >> 8) & 7) + 1;
 	} else if (boot_cpu_has(X86_FEATURE_NODEID_MSR)) {
 		u64 value;
 
 		rdmsrl(MSR_FAM10H_NODE_ID, value);
-		nodes_per_socket = ((value >> 3) & 7) + 1;
+		__max_die_per_package = nodes_per_socket = ((value >> 3) & 7) + 1;
 	}
 
 	if (!boot_cpu_has(X86_FEATURE_AMD_SSBD) &&

arch/x86/kernel/cpu/mce/intel.c

···
 	case INTEL_FAM6_BROADWELL_X:
 	case INTEL_FAM6_SKYLAKE_X:
 	case INTEL_FAM6_ICELAKE_X:
+	case INTEL_FAM6_SAPPHIRERAPIDS_X:
 	case INTEL_FAM6_XEON_PHI_KNL:
 	case INTEL_FAM6_XEON_PHI_KNM:
 

arch/x86/kernel/cpu/mce/severity.c

···
 static bool is_copy_from_user(struct pt_regs *regs)
 {
 	u8 insn_buf[MAX_INSN_SIZE];
-	struct insn insn;
 	unsigned long addr;
+	struct insn insn;
+	int ret;
 
 	if (copy_from_kernel_nofault(insn_buf, (void *)regs->ip, MAX_INSN_SIZE))
 		return false;
 
-	kernel_insn_init(&insn, insn_buf, MAX_INSN_SIZE);
-	insn_get_opcode(&insn);
-	if (!insn.opcode.got)
+	ret = insn_decode_kernel(&insn, insn_buf);
+	if (ret < 0)
 		return false;
 
 	switch (insn.opcode.value) {
···
 	case 0x8A: case 0x8B:
 	/* MOVZ mem,reg */
 	case 0xB60F: case 0xB70F:
-		insn_get_modrm(&insn);
-		insn_get_sib(&insn);
-		if (!insn.modrm.got || !insn.sib.got)
-			return false;
 		addr = (unsigned long)insn_get_addr_ref(&insn, regs);
 		break;
 	/* REP MOVS */

arch/x86/kernel/doublefault_32.c

···
 		.ss		= __KERNEL_DS,
 		.ds		= __USER_DS,
 		.fs		= __KERNEL_PERCPU,
-#ifndef CONFIG_X86_32_LAZY_GS
-		.gs		= __KERNEL_STACK_CANARY,
-#endif
+		.gs		= 0,
 
 		.__cr3		= __pa_nodebug(swapper_pg_dir),
 	},

arch/x86/kernel/ftrace.c

···
 
 static const char *ftrace_nop_replace(void)
 {
-	return ideal_nops[NOP_ATOMIC5];
+	return x86_nops[5];
 }
 
 static const char *ftrace_call_replace(unsigned long ip, unsigned long addr)
···
 		ip = trampoline + (jmp_offset - start_offset);
 		if (WARN_ON(*(char *)ip != 0x75))
 			goto fail;
-		ret = copy_from_kernel_nofault(ip, ideal_nops[2], 2);
+		ret = copy_from_kernel_nofault(ip, x86_nops[2], 2);
 		if (ret < 0)
 			goto fail;
 	}

arch/x86/kernel/head_32.S

···
 	movl $(__KERNEL_PERCPU), %eax
 	movl %eax,%fs			# set this cpu's percpu
 
-	movl $(__KERNEL_STACK_CANARY),%eax
-	movl %eax,%gs
+	xorl %eax,%eax
+	movl %eax,%gs			# clear possible garbage in %gs
 
 	xorl %eax,%eax			# Clear LDT
 	lldt %ax
···
  */
 __INIT
 setup_once:
-#ifdef CONFIG_STACKPROTECTOR
-	/*
-	 * Configure the stack canary. The linker can't handle this by
-	 * relocation.  Manually set base address in stack canary
-	 * segment descriptor.
-	 */
-	movl $gdt_page,%eax
-	movl $stack_canary,%ecx
-	movw %cx, 8 * GDT_ENTRY_STACK_CANARY + 2(%eax)
-	shrl $16, %ecx
-	movb %cl, 8 * GDT_ENTRY_STACK_CANARY + 4(%eax)
-	movb %ch, 8 * GDT_ENTRY_STACK_CANARY + 7(%eax)
-#endif
-
 	andl $0,setup_once_ref	/* Once is enough, thanks */
 	ret
 

arch/x86/kernel/jump_label.c

···
 }
 
 static const void *
-__jump_label_set_jump_code(struct jump_entry *entry, enum jump_label_type type, int init)
+__jump_label_set_jump_code(struct jump_entry *entry, enum jump_label_type type)
 {
-	const unsigned char default_nop[] = { STATIC_KEY_INIT_NOP };
-	const unsigned char *ideal_nop = ideal_nops[NOP_ATOMIC5];
 	const void *expect, *code;
 	const void *addr, *dest;
 	int line;
···
 
 	code = text_gen_insn(JMP32_INSN_OPCODE, addr, dest);
 
-	if (init) {
-		expect = default_nop; line = __LINE__;
-	} else if (type == JUMP_LABEL_JMP) {
-		expect = ideal_nop; line = __LINE__;
+	if (type == JUMP_LABEL_JMP) {
+		expect = x86_nops[5]; line = __LINE__;
 	} else {
 		expect = code; line = __LINE__;
 	}
···
 		bug_at(addr, line);
 
 	if (type == JUMP_LABEL_NOP)
-		code = ideal_nop;
+		code = x86_nops[5];
 
 	return code;
 }
···
 					  enum jump_label_type type,
 					  int init)
 {
-	const void *opcode = __jump_label_set_jump_code(entry, type, init);
+	const void *opcode = __jump_label_set_jump_code(entry, type);
 
 	/*
 	 * As long as only a single processor is running and the code is still
···
 	}
 
 	mutex_lock(&text_mutex);
-	opcode = __jump_label_set_jump_code(entry, type, 0);
+	opcode = __jump_label_set_jump_code(entry, type);
 	text_poke_queue((void *)jump_entry_code(entry),
 			opcode, JUMP_LABEL_NOP_SIZE, NULL);
 	mutex_unlock(&text_mutex);
···
 __init_or_module void arch_jump_label_transform_static(struct jump_entry *entry,
 				      enum jump_label_type type)
 {
-	/*
-	 * This function is called at boot up and when modules are
-	 * first loaded. Check if the default nop, the one that is
-	 * inserted at compile time, is the ideal nop. If it is, then
-	 * we do not need to update the nop, and we can leave it as is.
-	 * If it is not, then we need to update the nop to the ideal nop.
-	 */
-	if (jlstate == JL_STATE_START) {
-		const unsigned char default_nop[] = { STATIC_KEY_INIT_NOP };
-		const unsigned char *ideal_nop = ideal_nops[NOP_ATOMIC5];
-
-		if (memcmp(ideal_nop, default_nop, 5) != 0)
-			jlstate = JL_STATE_UPDATE;
-		else
-			jlstate = JL_STATE_NO_UPDATE;
-	}
 	if (jlstate == JL_STATE_UPDATE)
 		jump_label_transform(entry, type, 1);
 }

arch/x86/kernel/kprobes/core.c

···
 int can_boost(struct insn *insn, void *addr)
 {
 	kprobe_opcode_t opcode;
+	insn_byte_t prefix;
+	int i;
 
 	if (search_exception_tables((unsigned long)addr))
 		return 0;	/* Page fault may occur on this address. */
···
 	if (insn->opcode.nbytes != 1)
 		return 0;
 
-	/* Can't boost Address-size override prefix */
-	if (unlikely(inat_is_address_size_prefix(insn->attr)))
-		return 0;
+	for_each_insn_prefix(insn, i, prefix) {
+		insn_attr_t attr;
+
+		attr = inat_get_opcode_attribute(prefix);
+		/* Can't boost Address-size override prefix and CS override prefix */
+		if (prefix == 0x2e || inat_is_address_size_prefix(attr))
+			return 0;
+	}
 
 	opcode = insn->opcode.bytes[0];
 
-	switch (opcode & 0xf0) {
-	case 0x60:
-		/* can't boost "bound" */
-		return (opcode != 0x62);
-	case 0x70:
-		return 0; /* can't boost conditional jump */
-	case 0x90:
-		return opcode != 0x9a;	/* can't boost call far */
-	case 0xc0:
-		/* can't boost software-interruptions */
-		return (0xc1 < opcode && opcode < 0xcc) || opcode == 0xcf;
-	case 0xd0:
-		/* can boost AA* and XLAT */
-		return (opcode == 0xd4 || opcode == 0xd5 || opcode == 0xd7);
-	case 0xe0:
-		/* can boost in/out and absolute jmps */
-		return ((opcode & 0x04) || opcode == 0xea);
-	case 0xf0:
-		/* clear and set flags are boostable */
-		return (opcode == 0xf5 || (0xf7 < opcode && opcode < 0xfe));
+	switch (opcode) {
+	case 0x62:		/* bound */
+	case 0x70 ... 0x7f:	/* Conditional jumps */
+	case 0x9a:		/* Call far */
+	case 0xc0 ... 0xc1:	/* Grp2 */
+	case 0xcc ... 0xce:	/* software exceptions */
+	case 0xd0 ... 0xd3:	/* Grp2 */
+	case 0xd6:		/* (UD) */
+	case 0xd8 ... 0xdf:	/* ESC */
+	case 0xe0 ... 0xe3:	/* LOOP*, JCXZ */
+	case 0xe8 ... 0xe9:	/* near Call, JMP */
+	case 0xeb:		/* Short JMP */
+	case 0xf0 ... 0xf4:	/* LOCK/REP, HLT */
+	case 0xf6 ... 0xf7:	/* Grp3 */
+	case 0xfe:		/* Grp4 */
+		/* ... are not boostable */
+		return 0;
+	case 0xff:		/* Grp5 */
+		/* Only indirect jmp is boostable */
+		return X86_MODRM_REG(insn->modrm.bytes[0]) == 4;
 	default:
-		/* CS override prefix and call are not boostable */
-		return (opcode != 0x2e && opcode != 0x9a);
+		return 1;
 	}
 }
 
···
 		return 0UL;
 
 	if (faddr)
-		memcpy(buf, ideal_nops[NOP_ATOMIC5], 5);
+		memcpy(buf, x86_nops[5], 5);
 	else
 		buf[0] = kp->opcode;
 	return (unsigned long)buf;
···
 	/* Decode instructions */
 	addr = paddr - offset;
 	while (addr < paddr) {
+		int ret;
+
 		/*
 		 * Check if the instruction has been modified by another
 		 * kprobe, in which case we replace the breakpoint by the
···
 		__addr = recover_probed_instruction(buf, addr);
 		if (!__addr)
 			return 0;
-		kernel_insn_init(&insn, (void *)__addr, MAX_INSN_SIZE);
-		insn_get_length(&insn);
+
+		ret = insn_decode_kernel(&insn, (void *)__addr);
+		if (ret < 0)
+			return 0;
 
 		/*
 		 * Another debugging subsystem might insert this breakpoint.
···
 int __copy_instruction(u8 *dest, u8 *src, u8 *real, struct insn *insn)
 {
 	kprobe_opcode_t buf[MAX_INSN_SIZE];
-	unsigned long recovered_insn =
-		recover_probed_instruction(buf, (unsigned long)src);
+	unsigned long recovered_insn = recover_probed_instruction(buf, (unsigned long)src);
+	int ret;
 
 	if (!recovered_insn || !insn)
 		return 0;
···
 			MAX_INSN_SIZE))
 		return 0;
 
-	kernel_insn_init(insn, dest, MAX_INSN_SIZE);
-	insn_get_length(insn);
+	ret = insn_decode_kernel(insn, dest);
+	if (ret < 0)
+		return 0;
 
 	/* We can not probe force emulate prefixed instruction */
 	if (insn_has_emulate_prefix(insn))
···
 	return insn->length;
 }
 
-/* Prepare reljump right after instruction to boost */
-static int prepare_boost(kprobe_opcode_t *buf, struct kprobe *p,
-			  struct insn *insn)
+/* Prepare reljump or int3 right after instruction */
+static int prepare_singlestep(kprobe_opcode_t *buf, struct kprobe *p,
+			      struct insn *insn)
 {
 	int len = insn->length;
 
-	if (can_boost(insn, p->addr) &&
+	if (!IS_ENABLED(CONFIG_PREEMPTION) &&
+	    !p->post_handler && can_boost(insn, p->addr) &&
 	    MAX_INSN_SIZE - len >= JMP32_INSN_SIZE) {
 		/*
 		 * These instructions can be executed directly if it
···
 		len += JMP32_INSN_SIZE;
 		p->ainsn.boostable = 1;
 	} else {
-		p->ainsn.boostable = 0;
+		/* Otherwise, put an int3 for trapping singlestep */
+		if (MAX_INSN_SIZE - len < INT3_INSN_SIZE)
+			return -ENOSPC;
+
+		buf[len] = INT3_INSN_OPCODE;
+		len += INT3_INSN_SIZE;
 	}
 
 	return len;
···
 	module_memfree(page);
 }
 
-static void set_resume_flags(struct kprobe *p, struct insn *insn)
+/* Kprobe x86 instruction emulation - only regs->ip or IF flag modifiers */
+
+static void kprobe_emulate_ifmodifiers(struct kprobe *p, struct pt_regs *regs)
+{
+	switch (p->ainsn.opcode) {
+	case 0xfa:	/* cli */
+		regs->flags &= ~(X86_EFLAGS_IF);
+		break;
+	case 0xfb:	/* sti */
+		regs->flags |= X86_EFLAGS_IF;
+		break;
+	case 0x9c:	/* pushf */
+		int3_emulate_push(regs, regs->flags);
+		break;
+	case 0x9d:	/* popf */
+		regs->flags = int3_emulate_pop(regs);
+		break;
+	}
+	regs->ip = regs->ip - INT3_INSN_SIZE + p->ainsn.size;
+}
+NOKPROBE_SYMBOL(kprobe_emulate_ifmodifiers);
+
+static void kprobe_emulate_ret(struct kprobe *p, struct pt_regs *regs)
+{
+	int3_emulate_ret(regs);
+}
+NOKPROBE_SYMBOL(kprobe_emulate_ret);
+
+static void kprobe_emulate_call(struct kprobe *p, struct pt_regs *regs)
+{
+	unsigned long func = regs->ip - INT3_INSN_SIZE + p->ainsn.size;
+
+	func += p->ainsn.rel32;
+	int3_emulate_call(regs, func);
+}
+NOKPROBE_SYMBOL(kprobe_emulate_call);
+
+static nokprobe_inline
+void __kprobe_emulate_jmp(struct kprobe *p, struct pt_regs *regs, bool cond)
+{
+	unsigned long ip = regs->ip - INT3_INSN_SIZE + p->ainsn.size;
+
+	if (cond)
+		ip += p->ainsn.rel32;
+	int3_emulate_jmp(regs, ip);
+}
+
+static void kprobe_emulate_jmp(struct kprobe *p, struct pt_regs *regs)
+{
+	__kprobe_emulate_jmp(p, regs, true);
+}
+NOKPROBE_SYMBOL(kprobe_emulate_jmp);
+
+static const unsigned long jcc_mask[6] = {
+	[0] = X86_EFLAGS_OF,
+	[1] = X86_EFLAGS_CF,
+	[2] = X86_EFLAGS_ZF,
+	[3] = X86_EFLAGS_CF | X86_EFLAGS_ZF,
+	[4] = X86_EFLAGS_SF,
+	[5] = X86_EFLAGS_PF,
+};
+
+static void kprobe_emulate_jcc(struct kprobe *p, struct pt_regs *regs)
+{
+	bool invert = p->ainsn.jcc.type & 1;
+	bool match;
+
+	if (p->ainsn.jcc.type < 0xc) {
+		match = regs->flags & jcc_mask[p->ainsn.jcc.type >> 1];
+	} else {
+		match = ((regs->flags & X86_EFLAGS_SF) >> X86_EFLAGS_SF_BIT) ^
+			((regs->flags & X86_EFLAGS_OF) >> X86_EFLAGS_OF_BIT);
+		if (p->ainsn.jcc.type >= 0xe)
+			match = match && (regs->flags & X86_EFLAGS_ZF);
+	}
+	__kprobe_emulate_jmp(p, regs, (match && !invert) || (!match && invert));
+}
+NOKPROBE_SYMBOL(kprobe_emulate_jcc);
+
+static void kprobe_emulate_loop(struct kprobe *p, struct pt_regs *regs)
+{
+	bool match;
+
+	if (p->ainsn.loop.type != 3) {	/* LOOP* */
+		if (p->ainsn.loop.asize == 32)
+			match = ((*(u32 *)&regs->cx)--) != 0;
+#ifdef CONFIG_X86_64
+		else if (p->ainsn.loop.asize == 64)
+			match = ((*(u64 *)&regs->cx)--) != 0;
+#endif
+		else
+			match = ((*(u16 *)&regs->cx)--) != 0;
+	} else {			/* JCXZ */
+		if (p->ainsn.loop.asize == 32)
+			match = *(u32 *)(&regs->cx) == 0;
+#ifdef CONFIG_X86_64
+		else if (p->ainsn.loop.asize == 64)
+			match = *(u64 *)(&regs->cx) == 0;
+#endif
+		else
+			match = *(u16 *)(&regs->cx) == 0;
+	}
+
+	if (p->ainsn.loop.type == 0)	/* LOOPNE */
+		match = match && !(regs->flags & X86_EFLAGS_ZF);
+	else if (p->ainsn.loop.type == 1)	/* LOOPE */
+		match = match && (regs->flags & X86_EFLAGS_ZF);
+
+	__kprobe_emulate_jmp(p, regs, match);
+}
+NOKPROBE_SYMBOL(kprobe_emulate_loop);
+
+static const int addrmode_regoffs[] = {
+	offsetof(struct pt_regs, ax),
+	offsetof(struct pt_regs, cx),
+	offsetof(struct pt_regs, dx),
+	offsetof(struct pt_regs, bx),
+	offsetof(struct pt_regs, sp),
+	offsetof(struct pt_regs, bp),
+	offsetof(struct pt_regs, si),
+	offsetof(struct pt_regs, di),
+#ifdef CONFIG_X86_64
+	offsetof(struct pt_regs, r8),
+	offsetof(struct pt_regs, r9),
+	offsetof(struct pt_regs, r10),
+	offsetof(struct pt_regs, r11),
+	offsetof(struct pt_regs, r12),
+	offsetof(struct pt_regs, r13),
+	offsetof(struct pt_regs, r14),
+	offsetof(struct pt_regs, r15),
+#endif
+};
+
+static void kprobe_emulate_call_indirect(struct kprobe *p, struct pt_regs *regs)
+{
+	unsigned long offs = addrmode_regoffs[p->ainsn.indirect.reg];
+
+	int3_emulate_call(regs, regs_get_register(regs, offs));
+}
+NOKPROBE_SYMBOL(kprobe_emulate_call_indirect);
+
+static void kprobe_emulate_jmp_indirect(struct kprobe *p, struct pt_regs *regs)
+{
+	unsigned long offs = addrmode_regoffs[p->ainsn.indirect.reg];
+
+	int3_emulate_jmp(regs, regs_get_register(regs, offs));
+}
+NOKPROBE_SYMBOL(kprobe_emulate_jmp_indirect);
+
+static int prepare_emulation(struct kprobe *p, struct insn *insn)
 {
 	insn_byte_t opcode = insn->opcode.bytes[0];
 
 	switch (opcode) {
 	case 0xfa:		/* cli */
 	case 0xfb:		/* sti */
+	case 0x9c:		/* pushfl */
 	case 0x9d:		/* popf/popfd */
-		/* Check whether the instruction modifies Interrupt Flag or not */
-		p->ainsn.if_modifier = 1;
+		/*
+		 * IF modifiers must be emulated since it will enable interrupt while
+		 * int3 single stepping.
+		 */
+		p->ainsn.emulate_op = kprobe_emulate_ifmodifiers;
+		p->ainsn.opcode = opcode;
 		break;
-	case 0x9c:	/* pushfl */
-		p->ainsn.is_pushf = 1;
-		break;
-	case 0xcf:	/* iret */
-		p->ainsn.if_modifier = 1;
-		fallthrough;
 	case 0xc2:	/* ret/lret */
 	case 0xc3:
 	case 0xca:
 	case 0xcb:
-	case 0xea:	/* jmp absolute -- ip is correct */
-		/* ip is already adjusted, no more changes required */
-		p->ainsn.is_abs_ip = 1;
-		/* Without resume jump, this is boostable */
-		p->ainsn.boostable = 1;
+		p->ainsn.emulate_op = kprobe_emulate_ret;
 		break;
-	case 0xe8:	/* call relative - Fix return addr */
-		p->ainsn.is_call = 1;
+	case 0x9a:	/* far call absolute -- segment is not supported */
+	case 0xea:	/* far jmp absolute -- segment is not supported */
+	case 0xcc:	/* int3 */
+	case 0xcf:	/* iret -- in-kernel IRET is not supported */
+		return -EOPNOTSUPP;
 		break;
-#ifdef CONFIG_X86_32
-	case 0x9a:	/* call absolute -- same as call absolute, indirect */
-		p->ainsn.is_call = 1;
-		p->ainsn.is_abs_ip = 1;
+	case 0xe8:	/* near call relative */
+		p->ainsn.emulate_op = kprobe_emulate_call;
+		if (insn->immediate.nbytes == 2)
+			p->ainsn.rel32 = *(s16 *)&insn->immediate.value;
+		else
+			p->ainsn.rel32 = *(s32 *)&insn->immediate.value;
 		break;
-#endif
-	case 0xff:
+	case 0xeb:	/* short jump relative */
+	case 0xe9:	/* near jump relative */
+		p->ainsn.emulate_op = kprobe_emulate_jmp;
+		if (insn->immediate.nbytes == 1)
+			p->ainsn.rel32 = *(s8 *)&insn->immediate.value;
+		else if (insn->immediate.nbytes == 2)
+			p->ainsn.rel32 = *(s16 *)&insn->immediate.value;
+		else
+			p->ainsn.rel32 = *(s32 *)&insn->immediate.value;
+		break;
+	case 0x70 ... 0x7f:
+		/* 1 byte conditional jump */
+		p->ainsn.emulate_op = kprobe_emulate_jcc;
+		p->ainsn.jcc.type = opcode & 0xf;
+		p->ainsn.rel32 = *(char *)insn->immediate.bytes;
+		break;
+	case 0x0f:
 		opcode = insn->opcode.bytes[1];
-		if ((opcode & 0x30) == 0x10) {
-			/*
-			 * call absolute, indirect
-			 * Fix return addr; ip is correct.
-			 * But this is not boostable
-			 */
-			p->ainsn.is_call = 1;
-			p->ainsn.is_abs_ip = 1;
-			break;
-		} else if (((opcode & 0x31) == 0x20) ||
-			   ((opcode & 0x31) == 0x21)) {
-			/*
-			 * jmp near and far, absolute indirect
-			 * ip is correct.
-			 */
-			p->ainsn.is_abs_ip = 1;
-			/* Without resume jump, this is boostable */
-			p->ainsn.boostable = 1;
+		if ((opcode & 0xf0) == 0x80) {
+			/* 2 bytes Conditional Jump */
+			p->ainsn.emulate_op = kprobe_emulate_jcc;
+			p->ainsn.jcc.type = opcode & 0xf;
+			if (insn->immediate.nbytes == 2)
+				p->ainsn.rel32 = *(s16 *)&insn->immediate.value;
+			else
+				p->ainsn.rel32 = *(s32 *)&insn->immediate.value;
+		} else if (opcode == 0x01 &&
+			   X86_MODRM_REG(insn->modrm.bytes[0]) == 0 &&
+			   X86_MODRM_MOD(insn->modrm.bytes[0]) == 3) {
+			/* VM extensions - not supported */
+			return -EOPNOTSUPP;
 		}
 		break;
+	case 0xe0:	/* Loop NZ */
+	case 0xe1:	/* Loop */
+	case 0xe2:	/* Loop */
+	case 0xe3:	/* J*CXZ */
+		p->ainsn.emulate_op = kprobe_emulate_loop;
+		p->ainsn.loop.type = opcode & 0x3;
+		p->ainsn.loop.asize = insn->addr_bytes * 8;
+		p->ainsn.rel32 = *(s8 *)&insn->immediate.value;
+		break;
+	case 0xff:
+		/*
+		 * Since the 0xff is an extended group opcode, the instruction
+		 * is determined by the MOD/RM byte.
+		 */
+		opcode = insn->modrm.bytes[0];
+		if ((opcode & 0x30) == 0x10) {
+			if ((opcode & 0x8) == 0x8)
+				return -EOPNOTSUPP;	/* far call */
+			/* call absolute, indirect */
+			p->ainsn.emulate_op = kprobe_emulate_call_indirect;
+		} else if ((opcode & 0x30) == 0x20) {
+			if ((opcode & 0x8) == 0x8)
+				return -EOPNOTSUPP;	/* far jmp */
+			/* jmp near absolute indirect */
+			p->ainsn.emulate_op = kprobe_emulate_jmp_indirect;
+		} else
+			break;
+
+		if (insn->addr_bytes != sizeof(unsigned long))
+			return -EOPNOTSUPP;	/* Don't support differnt size */
+		if (X86_MODRM_MOD(opcode) != 3)
+			return -EOPNOTSUPP;	/* TODO: support memory addressing */
+
+		p->ainsn.indirect.reg = X86_MODRM_RM(opcode);
+#ifdef CONFIG_X86_64
+		if (X86_REX_B(insn->rex_prefix.value))
+			p->ainsn.indirect.reg += 8;
+#endif
+		break;
+	default:
+		break;
 	}
+	p->ainsn.size = insn->length;
+
+	return 0;
 }
 
 static int arch_copy_kprobe(struct kprobe *p)
 {
 	struct insn insn;
 	kprobe_opcode_t buf[MAX_INSN_SIZE];
-	int len;
+	int ret, len;
 
 	/* Copy an instruction with recovering if other optprobe modifies it.*/
 	len = __copy_instruction(buf, p->addr, p->ainsn.insn, &insn);
 	if (!len)
 		return -EINVAL;
 
-	/*
-	 * __copy_instruction can modify the displacement of the instruction,
-	 * but it doesn't affect boostable check.
-	 */
-	len = prepare_boost(buf, p, &insn);
+	/* Analyze the opcode and setup emulate functions */
+	ret = prepare_emulation(p, &insn);
+	if (ret < 0)
+		return ret;
 
-	/* Analyze the opcode and set resume flags */
-	set_resume_flags(p, &insn);
+	/* Add int3 for single-step or booster jmp */
+	len = prepare_singlestep(buf, p, &insn);
+	if (len < 0)
+		return len;
 
 	/* Also, displacement change doesn't affect the first byte */
 	p->opcode = buf[0];
···
 {
 	__this_cpu_write(current_kprobe, p);
 	kcb->kprobe_saved_flags = kcb->kprobe_old_flags
-		= (regs->flags & (X86_EFLAGS_TF | X86_EFLAGS_IF));
-	if (p->ainsn.if_modifier)
-		kcb->kprobe_saved_flags &= ~X86_EFLAGS_IF;
-}
-
-static nokprobe_inline void clear_btf(void)
-{
-	if (test_thread_flag(TIF_BLOCKSTEP)) {
-		unsigned long debugctl = get_debugctlmsr();
-
-		debugctl &= ~DEBUGCTLMSR_BTF;
-		update_debugctlmsr(debugctl);
-	}
-}
-
-static nokprobe_inline void restore_btf(void)
-{
-	if (test_thread_flag(TIF_BLOCKSTEP)) {
-		unsigned long debugctl = get_debugctlmsr();
-
-		debugctl |= DEBUGCTLMSR_BTF;
-		update_debugctlmsr(debugctl);
-	}
+		= (regs->flags & X86_EFLAGS_IF);
 }
 
 void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs)
···
 }
 NOKPROBE_SYMBOL(arch_prepare_kretprobe);
 
+static void kprobe_post_process(struct kprobe *cur, struct pt_regs *regs,
+			       struct kprobe_ctlblk *kcb)
+{
+	if ((kcb->kprobe_status != KPROBE_REENTER) && cur->post_handler) {
+		kcb->kprobe_status = KPROBE_HIT_SSDONE;
+		cur->post_handler(cur, regs, 0);
+	}
+
+	/* Restore back the original saved kprobes variables and continue. */
+	if (kcb->kprobe_status == KPROBE_REENTER)
+		restore_previous_kprobe(kcb);
+	else
+		reset_current_kprobe();
+}
+NOKPROBE_SYMBOL(kprobe_post_process);
+
 static void setup_singlestep(struct kprobe *p, struct pt_regs *regs,
 			     struct kprobe_ctlblk *kcb, int reenter)
 {
···
 		return;
 
 #if !defined(CONFIG_PREEMPTION)
-	if (p->ainsn.boostable && !p->post_handler) {
+	if (p->ainsn.boostable) {
 		/* Boost up -- we can execute copied instructions directly */
 		if (!reenter)
 			reset_current_kprobe();
···
 		kcb->kprobe_status = KPROBE_REENTER;
 	} else
 		kcb->kprobe_status = KPROBE_HIT_SS;
-	/* Prepare real single stepping */
-	clear_btf();
-	regs->flags |= X86_EFLAGS_TF;
+
+	if (p->ainsn.emulate_op) {
+		p->ainsn.emulate_op(p, regs);
+		kprobe_post_process(p, regs, kcb);
+		return;
+	}
+
+	/* Disable interrupt, and set ip register on trampoline */
 	regs->flags &= ~X86_EFLAGS_IF;
-	/* single step inline if the instruction is an int3 */
-	if (p->opcode == INT3_INSN_OPCODE)
-		regs->ip = (unsigned long)p->addr;
-	else
-		regs->ip = (unsigned long)p->ainsn.insn;
+	regs->ip = (unsigned long)p->ainsn.insn;
 }
 NOKPROBE_SYMBOL(setup_singlestep);
+
+/*
+ * Called after single-stepping.  p->addr is the address of the
+ * instruction whose first byte has been replaced by the "int3"
+ * instruction.  To avoid the SMP problems that can occur when we
+ * temporarily put back the original opcode to single-step, we
+ * single-stepped a copy of the instruction.  The address of this
+ * copy is p->ainsn.insn. We also doesn't use trap, but "int3" again
+ * right after the copied instruction.
+ * Different from the trap single-step, "int3" single-step can not
+ * handle the instruction which changes the ip register, e.g. jmp,
+ * call, conditional jmp, and the instructions which changes the IF
+ * flags because interrupt must be disabled around the single-stepping.
+ * Such instructions are software emulated, but others are single-stepped
+ * using "int3".
+ *
+ * When the 2nd "int3" handled, the regs->ip and regs->flags needs to
+ * be adjusted, so that we can resume execution on correct code.
+ */
+static void resume_singlestep(struct kprobe *p, struct pt_regs *regs,
+			      struct kprobe_ctlblk *kcb)
+{
+	unsigned long copy_ip = (unsigned long)p->ainsn.insn;
+	unsigned long orig_ip = (unsigned long)p->addr;
+
+	/* Restore saved interrupt flag and ip register */
+	regs->flags |= kcb->kprobe_saved_flags;
+	/* Note that regs->ip is executed int3 so must be a step back */
+	regs->ip += (orig_ip - copy_ip) - INT3_INSN_SIZE;
+}
+NOKPROBE_SYMBOL(resume_singlestep);
 
 /*
  * We have reentered the kprobe_handler(), since another probe was hit while
···
 	return 1;
 }
 NOKPROBE_SYMBOL(reenter_kprobe);
+
+static nokprobe_inline int kprobe_is_ss(struct kprobe_ctlblk *kcb)
+{
+	return (kcb->kprobe_status == KPROBE_HIT_SS ||
+		kcb->kprobe_status == KPROBE_REENTER);
+}
 
 /*
  * Interrupts are disabled on entry as trap3 is an interrupt gate and they
···
 				reset_current_kprobe();
 			return 1;
 		}
-	} else if (*addr != INT3_INSN_OPCODE) {
+	} else if (kprobe_is_ss(kcb)) {
+		p = kprobe_running();
+		if ((unsigned long)p->ainsn.insn < regs->ip &&
+		    (unsigned long)p->ainsn.insn + MAX_INSN_SIZE > regs->ip) {
+			/* Most provably this is the second int3 for singlestep */
+			resume_singlestep(p, regs, kcb);
+			kprobe_post_process(p, regs, kcb);
+			return 1;
+		}
+	}
+
+	if (*addr != INT3_INSN_OPCODE) {
 		/*
 		 * The breakpoint instruction was removed right
 		 * after we hit it.  Another cpu has removed
···
 }
 NOKPROBE_SYMBOL(trampoline_handler);
 
-/*
- * Called after single-stepping.  p->addr is the address of the
- * instruction whose first byte has been replaced by the "int 3"
- * instruction.  To avoid the SMP problems that can occur when we
- * temporarily put back the original opcode to single-step, we
- * single-stepped a copy of the instruction.  The address of this
- * copy is p->ainsn.insn.
- *
- * This function prepares to return from the post-single-step
- * interrupt.  We have to fix up the stack as follows:
- *
- * 0) Except in the case of absolute or indirect jump or call instructions,
- * the new ip is relative to the copied instruction.  We need to make
- * it relative to the original instruction.
- *
- * 1) If the single-stepped instruction was pushfl, then the TF and IF
- * flags are set in the just-pushed flags, and may need to be cleared.
- *
- * 2) If the single-stepped instruction was a call, the return address
- * that is atop the stack is the address following the copied instruction.
- * We need to make it the address following the original instruction.
- */
-static void resume_execution(struct kprobe *p, struct pt_regs *regs,
-			     struct kprobe_ctlblk *kcb)
-{
-	unsigned long *tos = stack_addr(regs);
-	unsigned long copy_ip = (unsigned long)p->ainsn.insn;
-	unsigned long orig_ip = (unsigned long)p->addr;
-
-	regs->flags &= ~X86_EFLAGS_TF;
-
-	/* Fixup the contents of top of stack */
-	if (p->ainsn.is_pushf) {
-		*tos &= ~(X86_EFLAGS_TF | X86_EFLAGS_IF);
-		*tos |= kcb->kprobe_old_flags;
-	} else if (p->ainsn.is_call) {
-		*tos = orig_ip + (*tos - copy_ip);
-	}
-
-	if (!p->ainsn.is_abs_ip)
-		regs->ip += orig_ip - copy_ip;
-
-	restore_btf();
-}
-NOKPROBE_SYMBOL(resume_execution);
-
-/*
- * Interrupts are disabled on entry as trap1 is an interrupt gate and they
- * remain disabled throughout this function.
- */
-int kprobe_debug_handler(struct pt_regs *regs)
-{
-	struct kprobe *cur = kprobe_running();
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
-	if (!cur)
-		return 0;
-
-	resume_execution(cur, regs, kcb);
-	regs->flags |= kcb->kprobe_saved_flags;
-
-	if ((kcb->kprobe_status != KPROBE_REENTER) && cur->post_handler) {
-		kcb->kprobe_status = KPROBE_HIT_SSDONE;
-		cur->post_handler(cur, regs, 0);
-	}
-
-	/* Restore back the original saved kprobes variables and continue. */
-	if (kcb->kprobe_status == KPROBE_REENTER) {
-		restore_previous_kprobe(kcb);
-		goto out;
-	}
-	reset_current_kprobe();
-out:
-	/*
-	 * if somebody else is singlestepping across a probe point, flags
-	 * will have TF set, in which case, continue the remaining processing
-	 * of do_debug, as if this is not a probe hit.
-	 */
-	if (regs->flags & X86_EFLAGS_TF)
-		return 0;
-
-	return 1;
-}
-NOKPROBE_SYMBOL(kprobe_debug_handler);
-
 int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
 {
 	struct kprobe *cur = kprobe_running();
···
 		 * normal page fault.
 		 */
 		regs->ip = (unsigned long)cur->addr;
-		/*
-		 * Trap flag (TF) has been set here because this fault
-		 * happened where the single stepping will be done.
-		 * So clear it by resetting the current kprobe:
-		 */
-		regs->flags &= ~X86_EFLAGS_TF;
-		/*
-		 * Since the single step (trap) has been cancelled,
-		 * we need to restore BTF here.
-		 */
-		restore_btf();
 
 		/*
-		 * If the TF flag was set before the kprobe hit,
+		 * If the IF flag was set before the kprobe hit,
 		 * don't touch it:
 		 */
 		regs->flags |= kcb->kprobe_old_flags;

arch/x86/kernel/kprobes/opt.c

···
 	addr = paddr - offset;
 	while (addr < paddr - offset + size) { /* Decode until function end */
 		unsigned long recovered_insn;
+		int ret;
+
 		if (search_exception_tables(addr))
 			/*
 			 * Since some fixup code will jumps into this function,
···
 		recovered_insn = recover_probed_instruction(buf, addr);
 		if (!recovered_insn)
 			return 0;
-		kernel_insn_init(&insn, (void *)recovered_insn, MAX_INSN_SIZE);
-		insn_get_length(&insn);
+
+		ret = insn_decode_kernel(&insn, (void *)recovered_insn);
+		if (ret < 0)
+			return 0;
+
 		/*
 		 * In the case of detecting unknown breakpoint, this could be
 		 * a padding INT3 between functions. Let's check that all the

arch/x86/kernel/setup.c

···
 
 	idt_setup_early_traps();
 	early_cpu_init();
-	arch_init_ideal_nops();
 	jump_label_init();
 	static_call_init();
 	early_ioremap_init();

arch/x86/kernel/setup_percpu.c

···
 		per_cpu(this_cpu_off, cpu) = per_cpu_offset(cpu);
 		per_cpu(cpu_number, cpu) = cpu;
 		setup_percpu_segment(cpu);
-		setup_stack_canary_segment(cpu);
 		/*
 		 * Copy data used in early init routines from the
 		 * initial arrays to the per cpu data areas.  These

arch/x86/kernel/sev-es.c

···
 	return copy_from_kernel_nofault(buffer, (unsigned char *)ctxt->regs->ip, MAX_INSN_SIZE);
 }
 
-static enum es_result vc_decode_insn(struct es_em_ctxt *ctxt)
+static enum es_result __vc_decode_user_insn(struct es_em_ctxt *ctxt)
 {
 	char buffer[MAX_INSN_SIZE];
-	enum es_result ret;
 	int res;
 
-	if (user_mode(ctxt->regs)) {
-		res = insn_fetch_from_user_inatomic(ctxt->regs, buffer);
-		if (!res) {
-			ctxt->fi.vector     = X86_TRAP_PF;
-			ctxt->fi.error_code = X86_PF_INSTR | X86_PF_USER;
-			ctxt->fi.cr2        = ctxt->regs->ip;
-			return ES_EXCEPTION;
-		}
-
-		if (!insn_decode(&ctxt->insn, ctxt->regs, buffer, res))
-			return ES_DECODE_FAILED;
-	} else {
-		res = vc_fetch_insn_kernel(ctxt, buffer);
-		if (res) {
-			ctxt->fi.vector     = X86_TRAP_PF;
-			ctxt->fi.error_code = X86_PF_INSTR;
-			ctxt->fi.cr2        = ctxt->regs->ip;
-			return ES_EXCEPTION;
-		}
-
-		insn_init(&ctxt->insn, buffer, MAX_INSN_SIZE, 1);
-		insn_get_length(&ctxt->insn);
+	res = insn_fetch_from_user_inatomic(ctxt->regs, buffer);
+	if (!res) {
+		ctxt->fi.vector     = X86_TRAP_PF;
+		ctxt->fi.error_code = X86_PF_INSTR | X86_PF_USER;
+		ctxt->fi.cr2        = ctxt->regs->ip;
+		return ES_EXCEPTION;
 	}
 
-	ret = ctxt->insn.immediate.got ? ES_OK : ES_DECODE_FAILED;
+	if (!insn_decode_from_regs(&ctxt->insn, ctxt->regs, buffer, res))
+		return ES_DECODE_FAILED;
 
-	return ret;
+	if (ctxt->insn.immediate.got)
+		return ES_OK;
+	else
+		return ES_DECODE_FAILED;
+}
+
+static enum es_result __vc_decode_kern_insn(struct es_em_ctxt *ctxt)
+{
+	char buffer[MAX_INSN_SIZE];
+	int res, ret;
+
+	res = vc_fetch_insn_kernel(ctxt, buffer);
+	if (res) {
+		ctxt->fi.vector     = X86_TRAP_PF;
+		ctxt->fi.error_code = X86_PF_INSTR;
+		ctxt->fi.cr2        = ctxt->regs->ip;
+		return ES_EXCEPTION;
+	}
+
+	ret = insn_decode(&ctxt->insn, buffer, MAX_INSN_SIZE, INSN_MODE_64);
+	if (ret < 0)
+		return ES_DECODE_FAILED;
+	else
+		return ES_OK;
+}
+
+static enum es_result vc_decode_insn(struct es_em_ctxt *ctxt)
+{
+	if (user_mode(ctxt->regs))
+		return __vc_decode_user_insn(ctxt);
+	else
+		return __vc_decode_kern_insn(ctxt);
 }
 
 static enum es_result vc_write_mem(struct es_em_ctxt *ctxt,

arch/x86/kernel/smpboot.c

···
 	return false;
 }
 
-/*
- * Define snc_cpu[] for SNC (Sub-NUMA Cluster) CPUs.
- *
- * These are Intel CPUs that enumerate an LLC that is shared by
- * multiple NUMA nodes. The LLC on these systems is shared for
- * off-package data access but private to the NUMA node (half
- * of the package) for on-package access.
- *
- * CPUID (the source of the information about the LLC) can only
- * enumerate the cache as being shared *or* unshared, but not
- * this particular configuration. The CPU in this case enumerates
- * the cache to be shared across the entire package (spanning both
- * NUMA nodes).
- */
-
-static const struct x86_cpu_id snc_cpu[] = {
-	X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_X, NULL),
-	{}
-};
-
-static bool match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
+static bool match_die(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 {
-	int cpu1 = c->cpu_index, cpu2 = o->cpu_index;
-
-	/* Do not match if we do not have a valid APICID for cpu: */
-	if (per_cpu(cpu_llc_id, cpu1) == BAD_APICID)
-		return false;
-
-	/* Do not match if LLC id does not match: */
-	if (per_cpu(cpu_llc_id, cpu1) != per_cpu(cpu_llc_id, cpu2))
-		return false;
-
-	/*
-	 * Allow the SNC topology without warning. Return of false
-	 * means 'c' does not share the LLC of 'o'. This will be
-	 * reflected to userspace.
-	 */
-	if (!topology_same_node(c, o) && x86_match_cpu(snc_cpu))
-		return false;
-
-	return topology_sane(c, o, "llc");
+	if (c->phys_proc_id == o->phys_proc_id &&
+	    c->cpu_die_id == o->cpu_die_id)
+		return true;
+	return false;
 }
 
 /*
···
 	return false;
 }
 
-static bool match_die(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
+/*
+ * Define intel_cod_cpu[] for Intel COD (Cluster-on-Die) CPUs.
+ *
+ * Any Intel CPU that has multiple nodes per package and does not
+ * match intel_cod_cpu[] has the SNC (Sub-NUMA Cluster) topology.
+ *
+ * When in SNC mode, these CPUs enumerate an LLC that is shared
+ * by multiple NUMA nodes. The LLC is shared for off-package data
+ * access but private to the NUMA node (half of the package) for
+ * on-package access. CPUID (the source of the information about
+ * the LLC) can only enumerate the cache as shared or unshared,
+ * but not this particular configuration.
+ */
+
+static const struct x86_cpu_id intel_cod_cpu[] = {
+	X86_MATCH_INTEL_FAM6_MODEL(HASWELL_X, 0),	/* COD */
+	X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_X, 0),	/* COD */
+	X86_MATCH_INTEL_FAM6_MODEL(ANY, 1),		/* SNC */
+	{}
+};
+
+static bool match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 {
-	if ((c->phys_proc_id == o->phys_proc_id) &&
-		(c->cpu_die_id == o->cpu_die_id))
-		return true;
-	return false;
+	const struct x86_cpu_id *id = x86_match_cpu(intel_cod_cpu);
+	int cpu1 = c->cpu_index, cpu2 = o->cpu_index;
+	bool intel_snc = id && id->driver_data;
+
+	/* Do not match if we do not have a valid APICID for cpu: */
+	if (per_cpu(cpu_llc_id, cpu1) == BAD_APICID)
+		return false;
+
+	/* Do not match if LLC id does not match: */
+	if (per_cpu(cpu_llc_id, cpu1) != per_cpu(cpu_llc_id, cpu2))
+		return false;
+
+	/*
+	 * Allow the SNC topology without warning. Return of false
+	 * means 'c' does not share the LLC of 'o'. This will be
+	 * reflected to userspace.
+	 */
+	if (match_pkg(c, o) && !topology_same_node(c, o) && intel_snc)
+		return false;
+
+	return topology_sane(c, o, "llc");
 }
 
 
···
 	for_each_cpu(i, cpu_sibling_setup_mask) {
 		o = &cpu_data(i);
 
+		if (match_pkg(c, o) && !topology_same_node(c, o))
+			x86_has_numa_in_package = true;
+
 		if ((i == cpu) || (has_smt && match_smt(c, o)))
 			link_mask(topology_sibling_cpumask, cpu, i);
 
 		if ((i == cpu) || (has_mp && match_llc(c, o)))
 			link_mask(cpu_llc_shared_mask, cpu, i);
 
+		if ((i == cpu) || (has_mp && match_die(c, o)))
+			link_mask(topology_die_cpumask, cpu, i);
 	}
+
+	threads = cpumask_weight(topology_sibling_cpumask(cpu));
+	if (threads > __max_smt_threads)
+		__max_smt_threads = threads;
 
 	/*
 	 * This needs a separate iteration over the cpus because we rely on all
···
 			/*
 			 *  Does this new cpu bringup a new core?
 			 */
-			if (cpumask_weight(
-			    topology_sibling_cpumask(cpu)) == 1) {
+			if (threads == 1) {
 				/*
 				 * for each core in package, increment
 				 * the booted_cores for this new cpu
···
 			} else if (i != cpu && !c->booted_cores)
 				c->booted_cores = cpu_data(i).booted_cores;
 		}
-		if (match_pkg(c, o) && !topology_same_node(c, o))
-			x86_has_numa_in_package = true;
-
-		if ((i == cpu) || (has_mp && match_die(c, o)))
-			link_mask(topology_die_cpumask, cpu, i);
 	}
-
-	threads = cpumask_weight(topology_sibling_cpumask(cpu));
-	if (threads > __max_smt_threads)
-		__max_smt_threads = threads;
 }
 
 /* maps the cpu to the sched domain representing multi-core */

arch/x86/kernel/static_call.c

···
 		break;
 
 	case NOP:
-		code = ideal_nops[NOP_ATOMIC5];
+		code = x86_nops[5];
 		break;
 
 	case JMP:
···
 			return;
 	} else {
 		if (opcode == CALL_INSN_OPCODE ||
-		    !memcmp(insn, ideal_nops[NOP_ATOMIC5], 5) ||
+		    !memcmp(insn, x86_nops[5], 5) ||
 		    !memcmp(insn, xor5rax, 5))
 			return;
 	}

arch/x86/kernel/tls.c

···
 		savesegment(fs, sel);
 		if (sel == modified_sel)
 			loadsegment(fs, sel);
+#endif
 
 		savesegment(gs, sel);
 		if (sel == modified_sel)
 			load_gs_index(sel);
-#endif
-
-#ifdef CONFIG_X86_32_LAZY_GS
-		savesegment(gs, sel);
-		if (sel == modified_sel)
-			loadsegment(gs, sel);
-#endif
 	} else {
 #ifdef CONFIG_X86_64
 		if (p->thread.fsindex == modified_sel)

arch/x86/kernel/traps.c

···
 {
 	u8 insn_buf[MAX_INSN_SIZE];
 	struct insn insn;
+	int ret;
 
 	if (copy_from_kernel_nofault(insn_buf, (void *)regs->ip,
 			MAX_INSN_SIZE))
 		return GP_NO_HINT;
 
-	kernel_insn_init(&insn, insn_buf, MAX_INSN_SIZE);
-	insn_get_modrm(&insn);
-	insn_get_sib(&insn);
+	ret = insn_decode_kernel(&insn, insn_buf);
+	if (ret < 0)
+		return GP_NO_HINT;
 
 	*addr = (unsigned long)insn_get_addr_ref(&insn, regs);
 	if (*addr == -1UL)
···
 	 */
 	if ((dr6 & DR_STEP) && is_sysenter_singlestep(regs))
 		dr6 &= ~DR_STEP;
-
-	if (kprobe_debug_handler(regs))
-		goto out;
 
 	/*
 	 * The kernel doesn't use INT1

arch/x86/kernel/umip.c

···
 	if (!nr_copied)
 		return false;
 
-	if (!insn_decode(&insn, regs, buf, nr_copied))
+	if (!insn_decode_from_regs(&insn, regs, buf, nr_copied))
 		return false;
 
 	umip_inst = identify_insn(&insn);

arch/x86/kernel/uprobes.c

···
 
 static int uprobe_init_insn(struct arch_uprobe *auprobe, struct insn *insn, bool x86_64)
 {
+	enum insn_mode m = x86_64 ? INSN_MODE_64 : INSN_MODE_32;
 	u32 volatile *good_insns;
+	int ret;
 
-	insn_init(insn, auprobe->insn, sizeof(auprobe->insn), x86_64);
-	/* has the side-effect of processing the entire instruction */
-	insn_get_length(insn);
-	if (!insn_complete(insn))
+	ret = insn_decode(insn, auprobe->insn, sizeof(auprobe->insn), m);
+	if (ret < 0)
 		return -ENOEXEC;
 
 	if (is_prefix_bad(insn))

arch/x86/lib/inat.c

···
  *
  * Written by Masami Hiramatsu <[e-mail]>
  */
-#include <asm/insn.h>
+#include <asm/insn.h> /* __ignore_sync_check__ */
 
 /* Attribute tables are generated from opcode map */
 #include "inat-tables.c"

arch/x86/lib/insn-eval.c

···
 	case INAT_SEG_REG_FS:
 		return (unsigned short)(regs->fs & 0xffff);
 	case INAT_SEG_REG_GS:
-		/*
-		 * GS may or may not be in regs as per CONFIG_X86_32_LAZY_GS.
-		 * The macro below takes care of both cases.
-		 */
 		return get_user_gs(regs);
 	case INAT_SEG_REG_IGNORE:
 	default:
···
 static int get_eff_addr_reg(struct insn *insn, struct pt_regs *regs,
 			    int *regoff, long *eff_addr)
 {
-	insn_get_modrm(insn);
+	int ret;
 
-	if (!insn->modrm.nbytes)
-		return -EINVAL;
+	ret = insn_get_modrm(insn);
+	if (ret)
+		return ret;
 
 	if (X86_MODRM_MOD(insn->modrm.value) != 3)
 		return -EINVAL;
···
 			      int *regoff, long *eff_addr)
 {
 	long tmp;
+	int ret;
 
 	if (insn->addr_bytes != 8 && insn->addr_bytes != 4)
 		return -EINVAL;
 
-	insn_get_modrm(insn);
-
-	if (!insn->modrm.nbytes)
-		return -EINVAL;
+	ret = insn_get_modrm(insn);
+	if (ret)
+		return ret;
 
 	if (X86_MODRM_MOD(insn->modrm.value) > 2)
 		return -EINVAL;
···
  * @base_offset will have a register, as an offset from the base of pt_regs,
  * that can be used to resolve the associated segment.
  *
- * -EINVAL on error.
+ * Negative value on error.
  */
 static int get_eff_addr_sib(struct insn *insn, struct pt_regs *regs,
 			    int *base_offset, long *eff_addr)
 {
 	long base, indx;
 	int indx_offset;
+	int ret;
 
 	if (insn->addr_bytes != 8 && insn->addr_bytes != 4)
 		return -EINVAL;
 
-	insn_get_modrm(insn);
+	ret = insn_get_modrm(insn);
+	if (ret)
+		return ret;
 
 	if (!insn->modrm.nbytes)
 		return -EINVAL;
···
 	if (X86_MODRM_MOD(insn->modrm.value) > 2)
 		return -EINVAL;
 
-	insn_get_sib(insn);
+	ret = insn_get_sib(insn);
+	if (ret)
+		return ret;
 
 	if (!insn->sib.nbytes)
 		return -EINVAL;
···
 	short eff_addr;
 	long tmp;
 
-	insn_get_modrm(insn);
-	insn_get_displacement(insn);
+	if (insn_get_displacement(insn))
+		goto out;
 
 	if (insn->addr_bytes != 2)
 		goto out;
···
 }
 
 /**
- * insn_decode() - Decode an instruction
+ * insn_decode_from_regs() - Decode an instruction
  * @insn:	Structure to store decoded instruction
  * @regs:	Structure with register values as seen when entering kernel mode
  * @buf:	Buffer containing the instruction bytes
···
  *
  * True if instruction was decoded, False otherwise.
  */
-bool insn_decode(struct insn *insn, struct pt_regs *regs,
-		 unsigned char buf[MAX_INSN_SIZE], int buf_size)
+bool insn_decode_from_regs(struct insn *insn, struct pt_regs *regs,
+			   unsigned char buf[MAX_INSN_SIZE], int buf_size)
 {
 	int seg_defs;
 
···
 	insn->addr_bytes = INSN_CODE_SEG_ADDR_SZ(seg_defs);
 	insn->opnd_bytes = INSN_CODE_SEG_OPND_SZ(seg_defs);
 
-	insn_get_length(insn);
+	if (insn_get_length(insn))
+		return false;
+
 	if (buf_size < insn->length)
 		return false;
 

arch/x86/lib/insn.c

···
 #else
 #include <string.h>
 #endif
-#include <asm/inat.h>
-#include <asm/insn.h>
+#include <asm/inat.h> /*__ignore_sync_check__ */
+#include <asm/insn.h> /* __ignore_sync_check__ */
 
-#include <asm/emulate_prefix.h>
+#include <linux/errno.h>
+#include <linux/kconfig.h>
+
+#include <asm/emulate_prefix.h> /* __ignore_sync_check__ */
 
 #define leXX_to_cpu(t, r)						\
 ({									\
···
  * 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)
···
  * 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;
···
 	int i, nb;
 
 	if (prefixes->got)
-		return;
+		return 0;
 
 	insn_get_emulate_prefix(insn);
 
···
 
 	prefixes->got = 1;
 
+	return 0;
+
 err_out:
-	return;
+	return -ENODATA;
 }
 
 /**
···
  * 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);
···
 		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);
···
 		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;
 }
 
 /**
···
  * 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);
···
 			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;
 }
 
 
···
 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.
···
  *
  * 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 &&
···
 	}
 	insn->sib.got = 1;
 
+	return 0;
+
 err_out:
-	return;
+	return -ENODATA;
 }
 
 
···
  * 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:
···
 	}
 out:
 	insn->displacement.got = 1;
+	return 0;
 
 err_out:
-	return;
+	return -ENODATA;
 }
 
 /* Decode moffset16/32/64. Return 0 if failed */
···
 }
 
 /**
- * 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))
···
 	}
 done:
 	insn->immediate.got = 1;
+	return 0;
 
 err_out:
-	return;
+	return -ENODATA;
 }
 
 /**
···
  *
  * 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	-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;
 }

arch/x86/lib/retpoline.S

···
 #include <asm/unwind_hints.h>
 #include <asm/frame.h>
 
-.macro THUNK reg
 	.section .text.__x86.indirect_thunk
 
-	.align 32
-SYM_FUNC_START(__x86_indirect_thunk_\reg)
-	JMP_NOSPEC \reg
-SYM_FUNC_END(__x86_indirect_thunk_\reg)
-
-SYM_FUNC_START_NOALIGN(__x86_retpoline_\reg)
+.macro RETPOLINE reg
 	ANNOTATE_INTRA_FUNCTION_CALL
-	call	.Ldo_rop_\@
+	call    .Ldo_rop_\@
 .Lspec_trap_\@:
 	UNWIND_HINT_EMPTY
 	pause
 	lfence
-	jmp	.Lspec_trap_\@
+	jmp .Lspec_trap_\@
 .Ldo_rop_\@:
-	mov	%\reg, (%_ASM_SP)
+	mov     %\reg, (%_ASM_SP)
 	UNWIND_HINT_FUNC
 	ret
-SYM_FUNC_END(__x86_retpoline_\reg)
+.endm
+
+.macro THUNK reg
+
+	.align 32
+
+SYM_FUNC_START(__x86_indirect_thunk_\reg)
+
+	ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), \
+		      __stringify(RETPOLINE \reg), X86_FEATURE_RETPOLINE, \
+		      __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), X86_FEATURE_RETPOLINE_AMD
+
+SYM_FUNC_END(__x86_indirect_thunk_\reg)
+
+.endm
+
+/*
+ * This generates .altinstr_replacement symbols for use by objtool. They,
+ * however, must not actually live in .altinstr_replacement since that will be
+ * discarded after init, but module alternatives will also reference these
+ * symbols.
+ *
+ * Their names matches the "__x86_indirect_" prefix to mark them as retpolines.
+ */
+.macro ALT_THUNK reg
+
+	.align 1
+
+SYM_FUNC_START_NOALIGN(__x86_indirect_alt_call_\reg)
+	ANNOTATE_RETPOLINE_SAFE
+1:	call	*%\reg
+2:	.skip	5-(2b-1b), 0x90
+SYM_FUNC_END(__x86_indirect_alt_call_\reg)
+
+SYM_FUNC_START_NOALIGN(__x86_indirect_alt_jmp_\reg)
+	ANNOTATE_RETPOLINE_SAFE
+1:	jmp	*%\reg
+2:	.skip	5-(2b-1b), 0x90
+SYM_FUNC_END(__x86_indirect_alt_jmp_\reg)
 
 .endm
 
···
 
 #define __EXPORT_THUNK(sym)	_ASM_NOKPROBE(sym); EXPORT_SYMBOL(sym)
 #define EXPORT_THUNK(reg)	__EXPORT_THUNK(__x86_indirect_thunk_ ## reg)
-#define EXPORT_RETPOLINE(reg)  __EXPORT_THUNK(__x86_retpoline_ ## reg)
 
 #undef GEN
 #define GEN(reg) THUNK reg
···
 #include <asm/GEN-for-each-reg.h>
 
 #undef GEN
-#define GEN(reg) EXPORT_RETPOLINE(reg)
+#define GEN(reg) ALT_THUNK reg
+#include <asm/GEN-for-each-reg.h>
+
+#undef GEN
+#define GEN(reg) __EXPORT_THUNK(__x86_indirect_alt_call_ ## reg)
+#include <asm/GEN-for-each-reg.h>
+
+#undef GEN
+#define GEN(reg) __EXPORT_THUNK(__x86_indirect_alt_jmp_ ## reg)
 #include <asm/GEN-for-each-reg.h>

arch/x86/net/bpf_jit_comp.c

···
 	/* BPF trampoline can be made to work without these nops,
 	 * but let's waste 5 bytes for now and optimize later
 	 */
-	memcpy(prog, ideal_nops[NOP_ATOMIC5], cnt);
+	memcpy(prog, x86_nops[5], cnt);
 	prog += cnt;
 	if (!ebpf_from_cbpf) {
 		if (tail_call_reachable && !is_subprog)
···
 				void *old_addr, void *new_addr,
 				const bool text_live)
 {
-	const u8 *nop_insn = ideal_nops[NOP_ATOMIC5];
+	const u8 *nop_insn = x86_nops[5];
 	u8 old_insn[X86_PATCH_SIZE];
 	u8 new_insn[X86_PATCH_SIZE];
 	u8 *prog;
···
 	if (stack_depth)
 		EMIT3_off32(0x48, 0x81, 0xC4, round_up(stack_depth, 8));
 
-	memcpy(prog, ideal_nops[NOP_ATOMIC5], X86_PATCH_SIZE);
+	memcpy(prog, x86_nops[5], X86_PATCH_SIZE);
 	prog += X86_PATCH_SIZE;
 	/* out: */
 
···
 			noplen = ASM_NOP_MAX;
 
 		for (i = 0; i < noplen; i++)
-			EMIT1(ideal_nops[noplen][i]);
+			EMIT1(x86_nops[noplen][i]);
 		len -= noplen;
 	}
 
···
 		/* remember return value in a stack for bpf prog to access */
 		emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8);
 		im->ip_after_call = prog;
-		memcpy(prog, ideal_nops[NOP_ATOMIC5], X86_PATCH_SIZE);
+		memcpy(prog, x86_nops[5], X86_PATCH_SIZE);
 		prog += X86_PATCH_SIZE;
 	}
 

arch/x86/platform/pvh/head.S

···
 
 #define PVH_GDT_ENTRY_CS	1
 #define PVH_GDT_ENTRY_DS	2
-#define PVH_GDT_ENTRY_CANARY	3
 #define PVH_CS_SEL		(PVH_GDT_ENTRY_CS * 8)
 #define PVH_DS_SEL		(PVH_GDT_ENTRY_DS * 8)
-#define PVH_CANARY_SEL		(PVH_GDT_ENTRY_CANARY * 8)
 
 SYM_CODE_START_LOCAL(pvh_start_xen)
 	cld
···
 
 #else /* CONFIG_X86_64 */
 
-	/* Set base address in stack canary descriptor. */
-	movl $_pa(gdt_start),%eax
-	movl $_pa(canary),%ecx
-	movw %cx, (PVH_GDT_ENTRY_CANARY * 8) + 2(%eax)
-	shrl $16, %ecx
-	movb %cl, (PVH_GDT_ENTRY_CANARY * 8) + 4(%eax)
-	movb %ch, (PVH_GDT_ENTRY_CANARY * 8) + 7(%eax)
-
-	mov $PVH_CANARY_SEL,%eax
-	mov %eax,%gs
-
 	call mk_early_pgtbl_32
 
 	mov $_pa(initial_page_table), %eax
···
 	.quad GDT_ENTRY(0xc09a, 0, 0xfffff) /* PVH_CS_SEL */
 #endif
 	.quad GDT_ENTRY(0xc092, 0, 0xfffff) /* PVH_DS_SEL */
-	.quad GDT_ENTRY(0x4090, 0, 0x18)    /* PVH_CANARY_SEL */
 SYM_DATA_END_LABEL(gdt_start, SYM_L_LOCAL, gdt_end)
 
 	.balign 16

arch/x86/power/cpu.c

···
 	/*
 	 * segment registers
 	 */
-#ifdef CONFIG_X86_32_LAZY_GS
 	savesegment(gs, ctxt->gs);
-#endif
 #ifdef CONFIG_X86_64
-	savesegment(gs, ctxt->gs);
 	savesegment(fs, ctxt->fs);
 	savesegment(ds, ctxt->ds);
 	savesegment(es, ctxt->es);
···
 	wrmsrl(MSR_GS_BASE, ctxt->kernelmode_gs_base);
 #else
 	loadsegment(fs, __KERNEL_PERCPU);
-	loadsegment(gs, __KERNEL_STACK_CANARY);
 #endif
 
 	/* Restore the TSS, RO GDT, LDT, and usermode-relevant MSRs. */
···
 	 */
 	wrmsrl(MSR_FS_BASE, ctxt->fs_base);
 	wrmsrl(MSR_KERNEL_GS_BASE, ctxt->usermode_gs_base);
-#elif defined(CONFIG_X86_32_LAZY_GS)
+#else
 	loadsegment(gs, ctxt->gs);
 #endif
 

arch/x86/tools/insn_decoder_test.c

···
 
 	while (fgets(line, BUFSIZE, stdin)) {
 		char copy[BUFSIZE], *s, *tab1, *tab2;
-		int nb = 0;
+		int nb = 0, ret;
 		unsigned int b;
 
 		if (line[0] == '<') {
···
 			} else
 				break;
 		}
+
 		/* Decode an instruction */
-		insn_init(&insn, insn_buff, sizeof(insn_buff), x86_64);
-		insn_get_length(&insn);
-		if (insn.length != nb) {
+		ret = insn_decode(&insn, insn_buff, sizeof(insn_buff),
+				  x86_64 ? INSN_MODE_64 : INSN_MODE_32);
+
+		if (ret < 0 || insn.length != nb) {
 			warnings++;
 			pr_warn("Found an x86 instruction decoder bug, "
 				"please report this.\n", sym);

arch/x86/tools/insn_sanity.c

···
 
 int main(int argc, char **argv)
 {
+	int insns = 0, ret;
 	struct insn insn;
-	int insns = 0;
 	int errors = 0;
 	unsigned long i;
 	unsigned char insn_buff[MAX_INSN_SIZE * 2];
···
 			continue;
 
 		/* Decode an instruction */
-		insn_init(&insn, insn_buff, sizeof(insn_buff), x86_64);
-		insn_get_length(&insn);
+		ret = insn_decode(&insn, insn_buff, sizeof(insn_buff),
+				  x86_64 ? INSN_MODE_64 : INSN_MODE_32);
 
 		if (insn.next_byte <= insn.kaddr ||
 		    insn.kaddr + MAX_INSN_SIZE < insn.next_byte) {
 			/* Access out-of-range memory */
 			dump_stream(stderr, "Error: Found an access violation", i, insn_buff, &insn);
 			errors++;
-		} else if (verbose && !insn_complete(&insn))
+		} else if (verbose && ret < 0)
 			dump_stream(stdout, "Info: Found an undecodable input", i, insn_buff, &insn);
 		else if (verbose >= 2)
 			dump_insn(stdout, &insn);

arch/x86/xen/enlighten_pv.c

···
 	pv_ops.cpu.write_gdt_entry = xen_write_gdt_entry_boot;
 	pv_ops.cpu.load_gdt = xen_load_gdt_boot;
 
-	setup_stack_canary_segment(cpu);
 	switch_to_new_gdt(cpu);
 
 	pv_ops.cpu.write_gdt_entry = xen_write_gdt_entry;

scripts/gcc-x86_32-has-stack-protector.sh

···
 #!/bin/sh
 # SPDX-License-Identifier: GPL-2.0
 
-echo "int foo(void) { char X[200]; return 3; }" | $* -S -x c -c -m32 -O0 -fstack-protector - -o - 2> /dev/null | grep -q "%gs"
+# This requires GCC 8.1 or better.  Specifically, we require
+# -mstack-protector-guard-reg, added by
+# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81708
+
+echo "int foo(void) { char X[200]; return 3; }" | $* -S -x c -c -m32 -O0 -fstack-protector -mstack-protector-guard-reg=fs -mstack-protector-guard-symbol=__stack_chk_guard - -o - 2> /dev/null | grep -q "%fs"

tools/arch/x86/include/asm/inat.h

···
  *
  * Written by Masami Hiramatsu <[e-mail]>
  */
-#include "inat_types.h"
+#include "inat_types.h" /* __ignore_sync_check__ */
 
 /*
  * Internal bits. Don't use bitmasks directly, because these bits are

tools/arch/x86/include/asm/insn.h

···
 
 #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)
 
···
 #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)
···
 
 /* 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)
 {
···
 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)

tools/arch/x86/include/asm/nops.h

···
+/* 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 */

tools/arch/x86/lib/inat.c

···
  *
  * Written by Masami Hiramatsu <[e-mail]>
  */
-#include "../include/asm/insn.h"
+#include "../include/asm/insn.h" /* __ignore_sync_check__ */
 
 /* Attribute tables are generated from opcode map */
 #include "inat-tables.c"

tools/arch/x86/lib/insn.c

···
 #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)						\
 ({									\
···
  * 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)
···
  * 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;
···
 	int i, nb;
 
 	if (prefixes->got)
-		return;
+		return 0;
 
 	insn_get_emulate_prefix(insn);
 
···
 
 	prefixes->got = 1;
 
+	return 0;
+
 err_out:
-	return;
+	return -ENODATA;
 }
 
 /**
···
  * 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);
···
 		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);
···
 		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;
 }
 
 /**
···
  * 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);
···
 			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;
 }
 
 
···
 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.
···
  *
  * 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 &&
···
 	}
 	insn->sib.got = 1;
 
+	return 0;
+
 err_out:
-	return;
+	return -ENODATA;
 }
 
 
···
  * 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:
···
 	}
 out:
 	insn->displacement.got = 1;
+	return 0;
 
 err_out:
-	return;
+	return -ENODATA;
 }
 
 /* Decode moffset16/32/64. Return 0 if failed */
···
 }
 
 /**
- * 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))
···
 	}
 done:
 	insn->immediate.got = 1;
+	return 0;
 
 err_out:
-	return;
+	return -ENODATA;
 }
 
 /**
···
  *
  * 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;
 }

tools/include/linux/kconfig.h

···
+/* 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 */

tools/objtool/arch/x86/decode.c

···
 #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},
···
 			    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;
···
 	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;
 	}
···
 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) {
···
 	}
 
 	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)
···
 	}
 
 	return 0;
+}
+
+bool arch_is_retpoline(struct symbol *sym)
+{
+	return !strncmp(sym->name, "__x86_indirect_", 15);
 }

tools/objtool/arch/x86/include/arch/special.h

···
 #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

tools/objtool/check.c

···
 
 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;
···
 		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,
···
 	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);
···
 		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;
···
 	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;
 }
···
 	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.
  */
···
 		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.
···
 			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;
···
 				/* 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);
 				}
 			}
···
 		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);
···
 					  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
···
 		 * 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)) {
 
···
 	file->rodata = found;
 }
 
+__weak int arch_rewrite_retpolines(struct objtool_file *file)
+{
+	return 0;
+}
+
 static int decode_sections(struct objtool_file *file)
 {
 	int ret;
···
 	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;
···
 	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;
···
 		return ret;
 
 	ret = read_instr_hints(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;
 
···
 
 			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;
 

tools/objtool/elf.c

···
 	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;
···
 	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;
···
 			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)) {
···
 				     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)
···
 	return -1;
 }
 
-void elf_add_reloc(struct elf *elf, struct reloc *reloc)
-{
-	struct section *sec = reloc->sec;
+static struct section *elf_create_reloc_section(struct elf *elf,
+						struct section *base,
+						int reltype);
 
-	list_add_tail(&reloc->list, &sec->reloc_list);
+int elf_add_reloc(struct elf *elf, struct section *sec, unsigned long offset,
+		  unsigned int type, struct symbol *sym, int addend)
+{
+	struct reloc *reloc;
+
+	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)
···
 				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);
···
 	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) {
···
 	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)
···
 		WARN("can't find .shstrtab or .strtab section");
 		return NULL;
 	}
-
-	s = elf_getscn(elf->elf, shstrtab->idx);
-	if (!s) {
-		WARN_ELF("elf_getscn");
+	sec->sh.sh_name = elf_add_string(elf, shstrtab, sec->name);
+	if (sec->sh.sh_name == -1)
 		return NULL;
-	}
-
-	data = elf_newdata(s);
-	if (!data) {
-		WARN_ELF("elf_newdata");
-		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);
···
 	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)
 {
···
 	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)
···
 	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");
···
 			}
 
 			sec->changed = false;
+			elf->changed = true;
 		}
 	}
 

tools/objtool/include/objtool/arch.h

···
 
 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 */

tools/objtool/include/objtool/check.h

···
 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;
···
 	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;

tools/objtool/include/objtool/elf.h

···
 
 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);
 
···
 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)

tools/objtool/include/objtool/objtool.h

···
 	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;

tools/objtool/objtool.c

···
 
 	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");

tools/objtool/orc_gen.c

···
 }
 
 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;
···
 	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;
 }
···
 
 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;
···
 	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;
 }

tools/objtool/special.c

···
 			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;
 
···
 			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);

tools/objtool/sync-check.sh

···
 
 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 () {
···
 done <<EOF
 $FILES
 EOF
+
+if [ "$SRCARCH" = "x86" ]; then
+	for i in $SYNC_CHECK_FILES; do
+		check $i '-I "^.*\/\*.*__ignore_sync_check__.*\*\/.*$"'
+	done
+fi

tools/perf/arch/x86/tests/insn-x86.c

···
 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;
 	}

tools/perf/arch/x86/util/archinsn.c

···
 		     struct machine *machine)
 {
 	struct insn insn;
-	int len;
+	int len, ret;
 	bool is64bit = false;
 
 	if (!sample->ip)
···
 	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;
 }

tools/perf/check-headers.sh

···
 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
···
   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_\(erms\|orig\))"'
···
 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

tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c

···
 		      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);
···
 		      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;