Merge tag 'objtool-core-2020-06-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull objtool updates from Ingo Molnar:
 "There are a lot of objtool changes in this cycle, all across the map:

   - Speed up objtool significantly, especially when there are large
     number of sections

   - Improve objtool's understanding of special instructions such as
     IRET, to reduce the number of annotations required

   - Implement 'noinstr' validation

   - Do baby steps for non-x86 objtool use

   - Simplify/fix retpoline decoding

   - Add vmlinux validation

   - Improve documentation

   - Fix various bugs and apply smaller cleanups"

* tag 'objtool-core-2020-06-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (54 commits)
  objtool: Enable compilation of objtool for all architectures
  objtool: Move struct objtool_file into arch-independent header
  objtool: Exit successfully when requesting help
  objtool: Add check_kcov_mode() to the uaccess safelist
  samples/ftrace: Fix asm function ELF annotations
  objtool: optimize add_dead_ends for split sections
  objtool: use gelf_getsymshndx to handle >64k sections
  objtool: Allow no-op CFI ops in alternatives
  x86/retpoline: Fix retpoline unwind
  x86: Change {JMP,CALL}_NOSPEC argument
  x86: Simplify retpoline declaration
  x86/speculation: Change FILL_RETURN_BUFFER to work with objtool
  objtool: Add support for intra-function calls
  objtool: Move the IRET hack into the arch decoder
  objtool: Remove INSN_STACK
  objtool: Make handle_insn_ops() unconditional
  objtool: Rework allocating stack_ops on decode
  objtool: UNWIND_HINT_RET_OFFSET should not check registers
  objtool: is_fentry_call() crashes if call has no destination
  x86,smap: Fix smap_{save,restore}() alternatives
  ...

19 files changed, 172 insertions, 182 deletions

diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S
index cad6e1bfa7d5..54e7d15dbd0d 100644
--- a/arch/x86/crypto/aesni-intel_asm.S
+++ b/arch/x86/crypto/aesni-intel_asm.S
@@ -2758,7 +2758,7 @@ SYM_FUNC_START(aesni_xts_crypt8)
 	pxor INC, STATE4
 	movdqu IV, 0x30(OUTP)
 
-	CALL_NOSPEC %r11
+	CALL_NOSPEC r11
 
 	movdqu 0x00(OUTP), INC
 	pxor INC, STATE1
@@ -2803,7 +2803,7 @@ SYM_FUNC_START(aesni_xts_crypt8)
 	_aesni_gf128mul_x_ble()
 	movups IV, (IVP)
 
-	CALL_NOSPEC %r11
+	CALL_NOSPEC r11
 
 	movdqu 0x40(OUTP), INC
 	pxor INC, STATE1
diff --git a/arch/x86/crypto/camellia-aesni-avx-asm_64.S b/arch/x86/crypto/camellia-aesni-avx-asm_64.S
index d01ddd73de65..ecc0a9a905c4 100644
--- a/arch/x86/crypto/camellia-aesni-avx-asm_64.S
+++ b/arch/x86/crypto/camellia-aesni-avx-asm_64.S
@@ -1228,7 +1228,7 @@ SYM_FUNC_START_LOCAL(camellia_xts_crypt_16way)
 	vpxor 14 * 16(%rax), %xmm15, %xmm14;
 	vpxor 15 * 16(%rax), %xmm15, %xmm15;
 
-	CALL_NOSPEC %r9;
+	CALL_NOSPEC r9;
 
 	addq $(16 * 16), %rsp;
 
diff --git a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
index 563ef6e83cdd..0907243c501c 100644
--- a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
+++ b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
@@ -1339,7 +1339,7 @@ SYM_FUNC_START_LOCAL(camellia_xts_crypt_32way)
 	vpxor 14 * 32(%rax), %ymm15, %ymm14;
 	vpxor 15 * 32(%rax), %ymm15, %ymm15;
 
-	CALL_NOSPEC %r9;
+	CALL_NOSPEC r9;
 
 	addq $(16 * 32), %rsp;
 
diff --git a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
index 0e6690e3618c..8501ec4532f4 100644
--- a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
+++ b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
@@ -75,7 +75,7 @@
 
 .text
 SYM_FUNC_START(crc_pcl)
-#define    bufp		%rdi
+#define    bufp		rdi
 #define    bufp_dw	%edi
 #define    bufp_w	%di
 #define    bufp_b	%dil
@@ -105,9 +105,9 @@ SYM_FUNC_START(crc_pcl)
 	## 1) ALIGN:
 	################################################################
 
-	mov     bufp, bufptmp		# rdi = *buf
-	neg     bufp
-	and     $7, bufp		# calculate the unalignment amount of
+	mov     %bufp, bufptmp		# rdi = *buf
+	neg     %bufp
+	and     $7, %bufp		# calculate the unalignment amount of
 					# the address
 	je      proc_block		# Skip if aligned
 
@@ -123,13 +123,13 @@ SYM_FUNC_START(crc_pcl)
 do_align:
 	#### Calculate CRC of unaligned bytes of the buffer (if any)
 	movq    (bufptmp), tmp		# load a quadward from the buffer
-	add     bufp, bufptmp		# align buffer pointer for quadword
+	add     %bufp, bufptmp		# align buffer pointer for quadword
 					# processing
-	sub     bufp, len		# update buffer length
+	sub     %bufp, len		# update buffer length
 align_loop:
 	crc32b  %bl, crc_init_dw 	# compute crc32 of 1-byte
 	shr     $8, tmp			# get next byte
-	dec     bufp
+	dec     %bufp
 	jne     align_loop
 
 proc_block:
@@ -169,10 +169,10 @@ continue_block:
 	xor     crc2, crc2
 
 	## branch into array
-	lea	jump_table(%rip), bufp
-	movzxw  (bufp, %rax, 2), len
-	lea	crc_array(%rip), bufp
-	lea     (bufp, len, 1), bufp
+	lea	jump_table(%rip), %bufp
+	movzxw  (%bufp, %rax, 2), len
+	lea	crc_array(%rip), %bufp
+	lea     (%bufp, len, 1), %bufp
 	JMP_NOSPEC bufp
 
 	################################################################
@@ -218,9 +218,9 @@ LABEL crc_ %i
 	## 4) Combine three results:
 	################################################################
 
-	lea	(K_table-8)(%rip), bufp		# first entry is for idx 1
+	lea	(K_table-8)(%rip), %bufp		# first entry is for idx 1
 	shlq    $3, %rax			# rax *= 8
-	pmovzxdq (bufp,%rax), %xmm0		# 2 consts: K1:K2
+	pmovzxdq (%bufp,%rax), %xmm0		# 2 consts: K1:K2
 	leal	(%eax,%eax,2), %eax		# rax *= 3 (total *24)
 	subq    %rax, tmp			# tmp -= rax*24
 
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index b67bae7091d7..7e7ffb7a5147 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -816,7 +816,7 @@ SYM_CODE_START(ret_from_fork)
 
 	/* kernel thread */
 1:	movl	%edi, %eax
-	CALL_NOSPEC %ebx
+	CALL_NOSPEC ebx
 	/*
 	 * A kernel thread is allowed to return here after successfully
 	 * calling do_execve().  Exit to userspace to complete the execve()
@@ -1501,7 +1501,7 @@ SYM_CODE_START_LOCAL_NOALIGN(common_exception_read_cr2)
 
 	TRACE_IRQS_OFF
 	movl	%esp, %eax			# pt_regs pointer
-	CALL_NOSPEC %edi
+	CALL_NOSPEC edi
 	jmp	ret_from_exception
 SYM_CODE_END(common_exception_read_cr2)
 
@@ -1522,7 +1522,7 @@ SYM_CODE_START_LOCAL_NOALIGN(common_exception)
 
 	TRACE_IRQS_OFF
 	movl	%esp, %eax			# pt_regs pointer
-	CALL_NOSPEC %edi
+	CALL_NOSPEC edi
 	jmp	ret_from_exception
 SYM_CODE_END(common_exception)
 
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 3063aa9090f9..64fe3d82157e 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -348,7 +348,7 @@ SYM_CODE_START(ret_from_fork)
 	/* kernel thread */
 	UNWIND_HINT_EMPTY
 	movq	%r12, %rdi
-	CALL_NOSPEC %rbx
+	CALL_NOSPEC rbx
 	/*
 	 * A kernel thread is allowed to return here after successfully
 	 * calling do_execve().  Exit to userspace to complete the execve()
diff --git a/arch/x86/include/asm/GEN-for-each-reg.h b/arch/x86/include/asm/GEN-for-each-reg.h
new file mode 100644
index 000000000000..1b07fb102c4e
--- /dev/null
+++ b/arch/x86/include/asm/GEN-for-each-reg.h
@@ -0,0 +1,25 @@
+#ifdef CONFIG_64BIT
+GEN(rax)
+GEN(rbx)
+GEN(rcx)
+GEN(rdx)
+GEN(rsi)
+GEN(rdi)
+GEN(rbp)
+GEN(r8)
+GEN(r9)
+GEN(r10)
+GEN(r11)
+GEN(r12)
+GEN(r13)
+GEN(r14)
+GEN(r15)
+#else
+GEN(eax)
+GEN(ebx)
+GEN(ecx)
+GEN(edx)
+GEN(esi)
+GEN(edi)
+GEN(ebp)
+#endif
diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h
index ce92c4acc913..9bf2620ce817 100644
--- a/arch/x86/include/asm/asm-prototypes.h
+++ b/arch/x86/include/asm/asm-prototypes.h
@@ -17,24 +17,19 @@ extern void cmpxchg8b_emu(void);
 #endif
 
 #ifdef CONFIG_RETPOLINE
-#ifdef CONFIG_X86_32
-#define INDIRECT_THUNK(reg) extern asmlinkage void __x86_indirect_thunk_e ## reg(void);
-#else
-#define INDIRECT_THUNK(reg) extern asmlinkage void __x86_indirect_thunk_r ## reg(void);
-INDIRECT_THUNK(8)
-INDIRECT_THUNK(9)
-INDIRECT_THUNK(10)
-INDIRECT_THUNK(11)
-INDIRECT_THUNK(12)
-INDIRECT_THUNK(13)
-INDIRECT_THUNK(14)
-INDIRECT_THUNK(15)
-#endif
-INDIRECT_THUNK(ax)
-INDIRECT_THUNK(bx)
-INDIRECT_THUNK(cx)
-INDIRECT_THUNK(dx)
-INDIRECT_THUNK(si)
-INDIRECT_THUNK(di)
-INDIRECT_THUNK(bp)
+
+#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)
+#include <asm/GEN-for-each-reg.h>
+
+#undef GEN
+#define GEN(reg) DECL_RETPOLINE(reg)
+#include <asm/GEN-for-each-reg.h>
+
 #endif /* CONFIG_RETPOLINE */
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 7e9a281e2660..d52d1aacdd97 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -4,20 +4,13 @@
 #define _ASM_X86_NOSPEC_BRANCH_H_
 
 #include <linux/static_key.h>
+#include <linux/frame.h>
 
 #include <asm/alternative.h>
 #include <asm/alternative-asm.h>
 #include <asm/cpufeatures.h>
 #include <asm/msr-index.h>
-
-/*
- * This should be used immediately before a retpoline alternative. It tells
- * objtool where the retpolines are so that it can make sense of the control
- * flow by just reading the original instruction(s) and ignoring the
- * alternatives.
- */
-#define ANNOTATE_NOSPEC_ALTERNATIVE \
-	ANNOTATE_IGNORE_ALTERNATIVE
+#include <asm/unwind_hints.h>
 
 /*
  * Fill the CPU return stack buffer.
@@ -46,21 +39,25 @@
 #define __FILL_RETURN_BUFFER(reg, nr, sp)	\
 	mov	$(nr/2), reg;			\
 771:						\
+	ANNOTATE_INTRA_FUNCTION_CALL;		\
 	call	772f;				\
 773:	/* speculation trap */			\
+	UNWIND_HINT_EMPTY;			\
 	pause;					\
 	lfence;					\
 	jmp	773b;				\
 772:						\
+	ANNOTATE_INTRA_FUNCTION_CALL;		\
 	call	774f;				\
 775:	/* speculation trap */			\
+	UNWIND_HINT_EMPTY;			\
 	pause;					\
 	lfence;					\
 	jmp	775b;				\
 774:						\
+	add	$(BITS_PER_LONG/8) * 2, sp;	\
 	dec	reg;				\
-	jnz	771b;				\
-	add	$(BITS_PER_LONG/8) * nr, sp;
+	jnz	771b;
 
 #ifdef __ASSEMBLY__
 
@@ -77,57 +74,27 @@
 .endm
 
 /*
- * These are the bare retpoline primitives for indirect jmp and call.
- * Do not use these directly; they only exist to make the ALTERNATIVE
- * invocation below less ugly.
- */
-.macro RETPOLINE_JMP reg:req
-	call	.Ldo_rop_\@
-.Lspec_trap_\@:
-	pause
-	lfence
-	jmp	.Lspec_trap_\@
-.Ldo_rop_\@:
-	mov	\reg, (%_ASM_SP)
-	ret
-.endm
-
-/*
- * This is a wrapper around RETPOLINE_JMP so the called function in reg
- * returns to the instruction after the macro.
- */
-.macro RETPOLINE_CALL reg:req
-	jmp	.Ldo_call_\@
-.Ldo_retpoline_jmp_\@:
-	RETPOLINE_JMP \reg
-.Ldo_call_\@:
-	call	.Ldo_retpoline_jmp_\@
-.endm
-
-/*
  * JMP_NOSPEC and CALL_NOSPEC macros can be used instead of a simple
  * indirect jmp/call which may be susceptible to the Spectre variant 2
  * attack.
  */
 .macro JMP_NOSPEC reg:req
 #ifdef CONFIG_RETPOLINE
-	ANNOTATE_NOSPEC_ALTERNATIVE
-	ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *\reg),	\
-		__stringify(RETPOLINE_JMP \reg), X86_FEATURE_RETPOLINE,	\
-		__stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *\reg), X86_FEATURE_RETPOLINE_AMD
+	ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), \
+		      __stringify(jmp __x86_retpoline_\reg), X86_FEATURE_RETPOLINE, \
+		      __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), X86_FEATURE_RETPOLINE_AMD
 #else
-	jmp	*\reg
+	jmp	*%\reg
 #endif
 .endm
 
 .macro CALL_NOSPEC reg:req
 #ifdef CONFIG_RETPOLINE
-	ANNOTATE_NOSPEC_ALTERNATIVE
-	ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; call *\reg),	\
-		__stringify(RETPOLINE_CALL \reg), X86_FEATURE_RETPOLINE,\
-		__stringify(lfence; ANNOTATE_RETPOLINE_SAFE; call *\reg), X86_FEATURE_RETPOLINE_AMD
+	ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; call *%\reg), \
+		      __stringify(call __x86_retpoline_\reg), X86_FEATURE_RETPOLINE, \
+		      __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; call *%\reg), X86_FEATURE_RETPOLINE_AMD
 #else
-	call	*\reg
+	call	*%\reg
 #endif
 .endm
 
@@ -137,10 +104,8 @@
   */
 .macro FILL_RETURN_BUFFER reg:req nr:req ftr:req
 #ifdef CONFIG_RETPOLINE
-	ANNOTATE_NOSPEC_ALTERNATIVE
-	ALTERNATIVE "jmp .Lskip_rsb_\@",				\
-		__stringify(__FILL_RETURN_BUFFER(\reg,\nr,%_ASM_SP))	\
-		\ftr
+	ALTERNATIVE "jmp .Lskip_rsb_\@", "", \ftr
+	__FILL_RETURN_BUFFER(\reg,\nr,%_ASM_SP)
 .Lskip_rsb_\@:
 #endif
 .endm
@@ -161,16 +126,16 @@
  * which is ensured when CONFIG_RETPOLINE is defined.
  */
 # define CALL_NOSPEC						\
-	ANNOTATE_NOSPEC_ALTERNATIVE				\
 	ALTERNATIVE_2(						\
 	ANNOTATE_RETPOLINE_SAFE					\
 	"call *%[thunk_target]\n",				\
-	"call __x86_indirect_thunk_%V[thunk_target]\n",		\
+	"call __x86_retpoline_%V[thunk_target]\n",		\
 	X86_FEATURE_RETPOLINE,					\
 	"lfence;\n"						\
 	ANNOTATE_RETPOLINE_SAFE					\
 	"call *%[thunk_target]\n",				\
 	X86_FEATURE_RETPOLINE_AMD)
+
 # define THUNK_TARGET(addr) [thunk_target] "r" (addr)
 
 #else /* CONFIG_X86_32 */
@@ -180,7 +145,6 @@
  * here, anyway.
  */
 # define CALL_NOSPEC						\
-	ANNOTATE_NOSPEC_ALTERNATIVE				\
 	ALTERNATIVE_2(						\
 	ANNOTATE_RETPOLINE_SAFE					\
 	"call *%[thunk_target]\n",				\
diff --git a/arch/x86/include/asm/orc_types.h b/arch/x86/include/asm/orc_types.h
index 6e060907c163..d25534940bde 100644
--- a/arch/x86/include/asm/orc_types.h
+++ b/arch/x86/include/asm/orc_types.h
@@ -58,8 +58,7 @@
 #define ORC_TYPE_CALL			0
 #define ORC_TYPE_REGS			1
 #define ORC_TYPE_REGS_IRET		2
-#define UNWIND_HINT_TYPE_SAVE		3
-#define UNWIND_HINT_TYPE_RESTORE	4
+#define UNWIND_HINT_TYPE_RET_OFFSET	3
 
 #ifndef __ASSEMBLY__
 /*
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index c4e8fd709cf6..29ee0c088009 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -728,7 +728,6 @@ static inline void sync_core(void)
 	unsigned int tmp;
 
 	asm volatile (
-		UNWIND_HINT_SAVE
 		"mov %%ss, %0\n\t"
 		"pushq %q0\n\t"
 		"pushq %%rsp\n\t"
@@ -738,7 +737,6 @@ static inline void sync_core(void)
 		"pushq %q0\n\t"
 		"pushq $1f\n\t"
 		"iretq\n\t"
-		UNWIND_HINT_RESTORE
 		"1:"
 		: "=&r" (tmp), ASM_CALL_CONSTRAINT : : "cc", "memory");
 #endif
diff --git a/arch/x86/include/asm/smap.h b/arch/x86/include/asm/smap.h
index 27c47d183f4b..8b58d6975d5d 100644
--- a/arch/x86/include/asm/smap.h
+++ b/arch/x86/include/asm/smap.h
@@ -57,8 +57,10 @@ static __always_inline unsigned long smap_save(void)
 {
 	unsigned long flags;
 
-	asm volatile (ALTERNATIVE("", "pushf; pop %0; " __ASM_CLAC,
-				  X86_FEATURE_SMAP)
+	asm volatile ("# smap_save\n\t"
+		      ALTERNATIVE("jmp 1f", "", X86_FEATURE_SMAP)
+		      "pushf; pop %0; " __ASM_CLAC "\n\t"
+		      "1:"
 		      : "=rm" (flags) : : "memory", "cc");
 
 	return flags;
@@ -66,7 +68,10 @@ static __always_inline unsigned long smap_save(void)
 
 static __always_inline void smap_restore(unsigned long flags)
 {
-	asm volatile (ALTERNATIVE("", "push %0; popf", X86_FEATURE_SMAP)
+	asm volatile ("# smap_restore\n\t"
+		      ALTERNATIVE("jmp 1f", "", X86_FEATURE_SMAP)
+		      "push %0; popf\n\t"
+		      "1:"
 		      : : "g" (flags) : "memory", "cc");
 }
 
diff --git a/arch/x86/include/asm/unwind_hints.h b/arch/x86/include/asm/unwind_hints.h
index f5e2eb12cb71..7d903fdb3f43 100644
--- a/arch/x86/include/asm/unwind_hints.h
+++ b/arch/x86/include/asm/unwind_hints.h
@@ -86,32 +86,15 @@
 	UNWIND_HINT sp_offset=\sp_offset
 .endm
 
-.macro UNWIND_HINT_SAVE
-	UNWIND_HINT type=UNWIND_HINT_TYPE_SAVE
-.endm
-
-.macro UNWIND_HINT_RESTORE
-	UNWIND_HINT type=UNWIND_HINT_TYPE_RESTORE
+/*
+ * RET_OFFSET: Used on instructions that terminate a function; mostly RETURN
+ * and sibling calls. On these, sp_offset denotes the expected offset from
+ * initial_func_cfi.
+ */
+.macro UNWIND_HINT_RET_OFFSET sp_offset=8
+	UNWIND_HINT type=UNWIND_HINT_TYPE_RET_OFFSET sp_offset=\sp_offset
 .endm
 
-#else /* !__ASSEMBLY__ */
-
-#define UNWIND_HINT(sp_reg, sp_offset, type, end)		\
-	"987: \n\t"						\
-	".pushsection .discard.unwind_hints\n\t"		\
-	/* struct unwind_hint */				\
-	".long 987b - .\n\t"					\
-	".short " __stringify(sp_offset) "\n\t"			\
-	".byte " __stringify(sp_reg) "\n\t"			\
-	".byte " __stringify(type) "\n\t"			\
-	".byte " __stringify(end) "\n\t"			\
-	".balign 4 \n\t"					\
-	".popsection\n\t"
-
-#define UNWIND_HINT_SAVE UNWIND_HINT(0, 0, UNWIND_HINT_TYPE_SAVE, 0)
-
-#define UNWIND_HINT_RESTORE UNWIND_HINT(0, 0, UNWIND_HINT_TYPE_RESTORE, 0)
-
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_X86_UNWIND_HINTS_H */
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index b0e641793be4..c84d28e90a58 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -282,7 +282,8 @@ static inline void tramp_free(void *tramp) { }
 
 /* Defined as markers to the end of the ftrace default trampolines */
 extern void ftrace_regs_caller_end(void);
-extern void ftrace_epilogue(void);
+extern void ftrace_regs_caller_ret(void);
+extern void ftrace_caller_end(void);
 extern void ftrace_caller_op_ptr(void);
 extern void ftrace_regs_caller_op_ptr(void);
 
@@ -334,7 +335,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 		call_offset = (unsigned long)ftrace_regs_call;
 	} else {
 		start_offset = (unsigned long)ftrace_caller;
-		end_offset = (unsigned long)ftrace_epilogue;
+		end_offset = (unsigned long)ftrace_caller_end;
 		op_offset = (unsigned long)ftrace_caller_op_ptr;
 		call_offset = (unsigned long)ftrace_call;
 	}
@@ -366,6 +367,13 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 	if (WARN_ON(ret < 0))
 		goto fail;
 
+	if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) {
+		ip = trampoline + (ftrace_regs_caller_ret - ftrace_regs_caller);
+		ret = probe_kernel_read(ip, (void *)retq, RET_SIZE);
+		if (WARN_ON(ret < 0))
+			goto fail;
+	}
+
 	/*
 	 * The address of the ftrace_ops that is used for this trampoline
 	 * is stored at the end of the trampoline. This will be used to
@@ -433,7 +441,7 @@ void set_ftrace_ops_ro(void)
 			end_offset = (unsigned long)ftrace_regs_caller_end;
 		} else {
 			start_offset = (unsigned long)ftrace_caller;
-			end_offset = (unsigned long)ftrace_epilogue;
+			end_offset = (unsigned long)ftrace_caller_end;
 		}
 		size = end_offset - start_offset;
 		size = size + RET_SIZE + sizeof(void *);
diff --git a/arch/x86/kernel/ftrace_32.S b/arch/x86/kernel/ftrace_32.S
index e8a9f8370112..e405fe1a8bf4 100644
--- a/arch/x86/kernel/ftrace_32.S
+++ b/arch/x86/kernel/ftrace_32.S
@@ -189,5 +189,5 @@ return_to_handler:
 	movl	%eax, %ecx
 	popl	%edx
 	popl	%eax
-	JMP_NOSPEC %ecx
+	JMP_NOSPEC ecx
 #endif
diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S
index 369e61faacfe..aa5d28aeb31e 100644
--- a/arch/x86/kernel/ftrace_64.S
+++ b/arch/x86/kernel/ftrace_64.S
@@ -23,7 +23,7 @@
 #endif /* CONFIG_FRAME_POINTER */
 
 /* Size of stack used to save mcount regs in save_mcount_regs */
-#define MCOUNT_REG_SIZE		(SS+8 + MCOUNT_FRAME_SIZE)
+#define MCOUNT_REG_SIZE		(FRAME_SIZE + MCOUNT_FRAME_SIZE)
 
 /*
  * gcc -pg option adds a call to 'mcount' in most functions.
@@ -77,7 +77,7 @@
 	/*
 	 * We add enough stack to save all regs.
 	 */
-	subq $(MCOUNT_REG_SIZE - MCOUNT_FRAME_SIZE), %rsp
+	subq $(FRAME_SIZE), %rsp
 	movq %rax, RAX(%rsp)
 	movq %rcx, RCX(%rsp)
 	movq %rdx, RDX(%rsp)
@@ -157,8 +157,12 @@ SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL)
 	 * think twice before adding any new code or changing the
 	 * layout here.
 	 */
-SYM_INNER_LABEL(ftrace_epilogue, SYM_L_GLOBAL)
+SYM_INNER_LABEL(ftrace_caller_end, SYM_L_GLOBAL)
 
+	jmp ftrace_epilogue
+SYM_FUNC_END(ftrace_caller);
+
+SYM_FUNC_START(ftrace_epilogue)
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL)
 	jmp ftrace_stub
@@ -170,14 +174,12 @@ SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL)
  */
 SYM_INNER_LABEL_ALIGN(ftrace_stub, SYM_L_WEAK)
 	retq
-SYM_FUNC_END(ftrace_caller)
+SYM_FUNC_END(ftrace_epilogue)
 
 SYM_FUNC_START(ftrace_regs_caller)
 	/* Save the current flags before any operations that can change them */
 	pushfq
 
-	UNWIND_HINT_SAVE
-
 	/* added 8 bytes to save flags */
 	save_mcount_regs 8
 	/* save_mcount_regs fills in first two parameters */
@@ -233,10 +235,13 @@ SYM_INNER_LABEL(ftrace_regs_call, SYM_L_GLOBAL)
 	movq ORIG_RAX(%rsp), %rax
 	movq %rax, MCOUNT_REG_SIZE-8(%rsp)
 
-	/* If ORIG_RAX is anything but zero, make this a call to that */
+	/*
+	 * If ORIG_RAX is anything but zero, make this a call to that.
+	 * See arch_ftrace_set_direct_caller().
+	 */
 	movq ORIG_RAX(%rsp), %rax
-	cmpq	$0, %rax
-	je	1f
+	testq	%rax, %rax
+	jz	1f
 
 	/* Swap the flags with orig_rax */
 	movq MCOUNT_REG_SIZE(%rsp), %rdi
@@ -244,20 +249,14 @@ SYM_INNER_LABEL(ftrace_regs_call, SYM_L_GLOBAL)
 	movq %rax, MCOUNT_REG_SIZE(%rsp)
 
 	restore_mcount_regs 8
+	/* Restore flags */
+	popfq
 
-	jmp	2f
+SYM_INNER_LABEL(ftrace_regs_caller_ret, SYM_L_GLOBAL);
+	UNWIND_HINT_RET_OFFSET
+	jmp	ftrace_epilogue
 
 1:	restore_mcount_regs
-
-
-2:
-	/*
-	 * The stack layout is nondetermistic here, depending on which path was
-	 * taken.  This confuses objtool and ORC, rightfully so.  For now,
-	 * pretend the stack always looks like the non-direct case.
-	 */
-	UNWIND_HINT_RESTORE
-
 	/* Restore flags */
 	popfq
 
@@ -268,7 +267,6 @@ SYM_INNER_LABEL(ftrace_regs_call, SYM_L_GLOBAL)
 	 * to the return.
 	 */
 SYM_INNER_LABEL(ftrace_regs_caller_end, SYM_L_GLOBAL)
-
 	jmp ftrace_epilogue
 
 SYM_FUNC_END(ftrace_regs_caller)
@@ -303,7 +301,7 @@ trace:
 	 * function tracing is enabled.
 	 */
 	movq ftrace_trace_function, %r8
-	CALL_NOSPEC %r8
+	CALL_NOSPEC r8
 	restore_mcount_regs
 
 	jmp fgraph_trace
@@ -340,6 +338,6 @@ SYM_CODE_START(return_to_handler)
 	movq 8(%rsp), %rdx
 	movq (%rsp), %rax
 	addq $24, %rsp
-	JMP_NOSPEC %rdi
+	JMP_NOSPEC rdi
 SYM_CODE_END(return_to_handler)
 #endif
diff --git a/arch/x86/lib/checksum_32.S b/arch/x86/lib/checksum_32.S
index 4742e8fa7ee7..d1d768912368 100644
--- a/arch/x86/lib/checksum_32.S
+++ b/arch/x86/lib/checksum_32.S
@@ -153,7 +153,7 @@ SYM_FUNC_START(csum_partial)
 	negl %ebx
 	lea 45f(%ebx,%ebx,2), %ebx
 	testl %esi, %esi
-	JMP_NOSPEC %ebx
+	JMP_NOSPEC ebx
 
 	# Handle 2-byte-aligned regions
 20:	addw (%esi), %ax
@@ -436,7 +436,7 @@ SYM_FUNC_START(csum_partial_copy_generic)
 	andl $-32,%edx
 	lea 3f(%ebx,%ebx), %ebx
 	testl %esi, %esi 
-	JMP_NOSPEC %ebx
+	JMP_NOSPEC ebx
 1:	addl $64,%esi
 	addl $64,%edi 
 	SRC(movb -32(%edx),%bl)	; SRC(movb (%edx),%bl)
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index 363ec132df7e..b4c43a9b1483 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -7,15 +7,31 @@
 #include <asm/alternative-asm.h>
 #include <asm/export.h>
 #include <asm/nospec-branch.h>
+#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)
-	CFI_STARTPROC
-	JMP_NOSPEC %\reg
-	CFI_ENDPROC
+	JMP_NOSPEC \reg
 SYM_FUNC_END(__x86_indirect_thunk_\reg)
+
+SYM_FUNC_START_NOALIGN(__x86_retpoline_\reg)
+	ANNOTATE_INTRA_FUNCTION_CALL
+	call	.Ldo_rop_\@
+.Lspec_trap_\@:
+	UNWIND_HINT_EMPTY
+	pause
+	lfence
+	jmp	.Lspec_trap_\@
+.Ldo_rop_\@:
+	mov	%\reg, (%_ASM_SP)
+	UNWIND_HINT_RET_OFFSET
+	ret
+SYM_FUNC_END(__x86_retpoline_\reg)
+
 .endm
 
 /*
@@ -24,25 +40,24 @@ SYM_FUNC_END(__x86_indirect_thunk_\reg)
  * only see one instance of "__x86_indirect_thunk_\reg" rather
  * than one per register with the correct names. So we do it
  * the simple and nasty way...
+ *
+ * Worse, you can only have a single EXPORT_SYMBOL per line,
+ * and CPP can't insert newlines, so we have to repeat everything
+ * at least twice.
  */
-#define __EXPORT_THUNK(sym) _ASM_NOKPROBE(sym); EXPORT_SYMBOL(sym)
-#define EXPORT_THUNK(reg) __EXPORT_THUNK(__x86_indirect_thunk_ ## reg)
-#define GENERATE_THUNK(reg) THUNK reg ; EXPORT_THUNK(reg)
-
-GENERATE_THUNK(_ASM_AX)
-GENERATE_THUNK(_ASM_BX)
-GENERATE_THUNK(_ASM_CX)
-GENERATE_THUNK(_ASM_DX)
-GENERATE_THUNK(_ASM_SI)
-GENERATE_THUNK(_ASM_DI)
-GENERATE_THUNK(_ASM_BP)
-#ifdef CONFIG_64BIT
-GENERATE_THUNK(r8)
-GENERATE_THUNK(r9)
-GENERATE_THUNK(r10)
-GENERATE_THUNK(r11)
-GENERATE_THUNK(r12)
-GENERATE_THUNK(r13)
-GENERATE_THUNK(r14)
-GENERATE_THUNK(r15)
-#endif
+
+#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_THUNK(reg)
+#include <asm/GEN-for-each-reg.h>
+
+#undef GEN
+#define GEN(reg) EXPORT_RETPOLINE(reg)
+#include <asm/GEN-for-each-reg.h>
diff --git a/arch/x86/platform/efi/efi_stub_64.S b/arch/x86/platform/efi/efi_stub_64.S
index 15da118f04f0..90380a17ab23 100644
--- a/arch/x86/platform/efi/efi_stub_64.S
+++ b/arch/x86/platform/efi/efi_stub_64.S
@@ -21,7 +21,7 @@ SYM_FUNC_START(__efi_call)
 	mov %r8, %r9
 	mov %rcx, %r8
 	mov %rsi, %rcx
-	CALL_NOSPEC %rdi
+	CALL_NOSPEC rdi
 	leave
 	ret
 SYM_FUNC_END(__efi_call)