Merge tag 'x86_alternatives_for_v6.11_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 alternatives updates from Borislav Petkov:
 "This is basically PeterZ's idea to nest the alternative macros to
  avoid the need to "spell out" the number of alternates in an
  ALTERNATIVE_n() macro and thus have an ever-increasing complexity in
  those definitions.

  For ease of bisection, the old macros are converted to the new, nested
  variants in a step-by-step manner so that in case an issue is
  encountered during testing, one can pinpoint the place where it fails
  easier.

  Because debugging alternatives is a serious pain"

* tag 'x86_alternatives_for_v6.11_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/alternatives, kvm: Fix a couple of CALLs without a frame pointer
  x86/alternative: Replace the old macros
  x86/alternative: Convert the asm ALTERNATIVE_3() macro
  x86/alternative: Convert the asm ALTERNATIVE_2() macro
  x86/alternative: Convert the asm ALTERNATIVE() macro
  x86/alternative: Convert ALTERNATIVE_3()
  x86/alternative: Convert ALTERNATIVE_TERNARY()
  x86/alternative: Convert alternative_call_2()
  x86/alternative: Convert alternative_call()
  x86/alternative: Convert alternative_io()
  x86/alternative: Convert alternative_input()
  x86/alternative: Convert alternative_2()
  x86/alternative: Convert alternative()
  x86/alternatives: Add nested alternatives macros
  x86/alternative: Zap alternative_ternary()

8 files changed, 152 insertions, 187 deletions

diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index ba99ef75f56c..ca9ae606aab9 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -156,102 +156,50 @@ static inline int alternatives_text_reserved(void *start, void *end)
 
 #define ALT_CALL_INSTR		"call BUG_func"
 
-#define b_replacement(num)	"664"#num
-#define e_replacement(num)	"665"#num
+#define alt_slen		"772b-771b"
+#define alt_total_slen		"773b-771b"
+#define alt_rlen		"775f-774f"
 
-#define alt_end_marker		"663"
-#define alt_slen		"662b-661b"
-#define alt_total_slen		alt_end_marker"b-661b"
-#define alt_rlen(num)		e_replacement(num)"f-"b_replacement(num)"f"
-
-#define OLDINSTR(oldinstr, num)						\
-	"# ALT: oldnstr\n"						\
-	"661:\n\t" oldinstr "\n662:\n"					\
+#define OLDINSTR(oldinstr)						\
+	"# ALT: oldinstr\n"						\
+	"771:\n\t" oldinstr "\n772:\n"					\
 	"# ALT: padding\n"						\
-	".skip -(((" alt_rlen(num) ")-(" alt_slen ")) > 0) * "		\
-		"((" alt_rlen(num) ")-(" alt_slen ")),0x90\n"		\
-	alt_end_marker ":\n"
-
-/*
- * gas compatible max based on the idea from:
- * http://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax
- *
- * The additional "-" is needed because gas uses a "true" value of -1.
- */
-#define alt_max_short(a, b)	"((" a ") ^ (((" a ") ^ (" b ")) & -(-((" a ") < (" b ")))))"
-
-/*
- * Pad the second replacement alternative with additional NOPs if it is
- * additionally longer than the first replacement alternative.
- */
-#define OLDINSTR_2(oldinstr, num1, num2) \
-	"# ALT: oldinstr2\n"									\
-	"661:\n\t" oldinstr "\n662:\n"								\
-	"# ALT: padding2\n"									\
-	".skip -((" alt_max_short(alt_rlen(num1), alt_rlen(num2)) " - (" alt_slen ")) > 0) * "	\
-		"(" alt_max_short(alt_rlen(num1), alt_rlen(num2)) " - (" alt_slen ")), 0x90\n"	\
-	alt_end_marker ":\n"
-
-#define OLDINSTR_3(oldinsn, n1, n2, n3)								\
-	"# ALT: oldinstr3\n"									\
-	"661:\n\t" oldinsn "\n662:\n"								\
-	"# ALT: padding3\n"									\
-	".skip -((" alt_max_short(alt_max_short(alt_rlen(n1), alt_rlen(n2)), alt_rlen(n3))	\
-		" - (" alt_slen ")) > 0) * "							\
-		"(" alt_max_short(alt_max_short(alt_rlen(n1), alt_rlen(n2)), alt_rlen(n3))	\
-		" - (" alt_slen ")), 0x90\n"							\
-	alt_end_marker ":\n"
-
-#define ALTINSTR_ENTRY(ft_flags, num)					      \
-	" .long 661b - .\n"				/* label           */ \
-	" .long " b_replacement(num)"f - .\n"		/* new instruction */ \
+	".skip -(((" alt_rlen ")-(" alt_slen ")) > 0) * "		\
+		"((" alt_rlen ")-(" alt_slen ")),0x90\n"		\
+	"773:\n"
+
+#define ALTINSTR_ENTRY(ft_flags)					      \
+	".pushsection .altinstructions,\"a\"\n"				      \
+	" .long 771b - .\n"				/* label           */ \
+	" .long 774f - .\n"				/* new instruction */ \
 	" .4byte " __stringify(ft_flags) "\n"		/* feature + flags */ \
 	" .byte " alt_total_slen "\n"			/* source len      */ \
-	" .byte " alt_rlen(num) "\n"			/* replacement len */
+	" .byte " alt_rlen "\n"				/* replacement len */ \
+	".popsection\n"
 
-#define ALTINSTR_REPLACEMENT(newinstr, num)		/* replacement */	\
-	"# ALT: replacement " #num "\n"						\
-	b_replacement(num)":\n\t" newinstr "\n" e_replacement(num) ":\n"
+#define ALTINSTR_REPLACEMENT(newinstr)		/* replacement */	\
+	".pushsection .altinstr_replacement, \"ax\"\n"			\
+	"# ALT: replacement\n"						\
+	"774:\n\t" newinstr "\n775:\n"					\
+	".popsection\n"
 
 /* alternative assembly primitive: */
 #define ALTERNATIVE(oldinstr, newinstr, ft_flags)			\
-	OLDINSTR(oldinstr, 1)						\
-	".pushsection .altinstructions,\"a\"\n"				\
-	ALTINSTR_ENTRY(ft_flags, 1)					\
-	".popsection\n"							\
-	".pushsection .altinstr_replacement, \"ax\"\n"			\
-	ALTINSTR_REPLACEMENT(newinstr, 1)				\
-	".popsection\n"
+	OLDINSTR(oldinstr)						\
+	ALTINSTR_ENTRY(ft_flags)					\
+	ALTINSTR_REPLACEMENT(newinstr)
 
 #define ALTERNATIVE_2(oldinstr, newinstr1, ft_flags1, newinstr2, ft_flags2) \
-	OLDINSTR_2(oldinstr, 1, 2)					\
-	".pushsection .altinstructions,\"a\"\n"				\
-	ALTINSTR_ENTRY(ft_flags1, 1)					\
-	ALTINSTR_ENTRY(ft_flags2, 2)					\
-	".popsection\n"							\
-	".pushsection .altinstr_replacement, \"ax\"\n"			\
-	ALTINSTR_REPLACEMENT(newinstr1, 1)				\
-	ALTINSTR_REPLACEMENT(newinstr2, 2)				\
-	".popsection\n"
+	ALTERNATIVE(ALTERNATIVE(oldinstr, newinstr1, ft_flags1), newinstr2, ft_flags2)
 
 /* If @feature is set, patch in @newinstr_yes, otherwise @newinstr_no. */
 #define ALTERNATIVE_TERNARY(oldinstr, ft_flags, newinstr_yes, newinstr_no) \
-	ALTERNATIVE_2(oldinstr, newinstr_no, X86_FEATURE_ALWAYS,	\
-		      newinstr_yes, ft_flags)
-
-#define ALTERNATIVE_3(oldinsn, newinsn1, ft_flags1, newinsn2, ft_flags2, \
-			newinsn3, ft_flags3)				\
-	OLDINSTR_3(oldinsn, 1, 2, 3)					\
-	".pushsection .altinstructions,\"a\"\n"				\
-	ALTINSTR_ENTRY(ft_flags1, 1)					\
-	ALTINSTR_ENTRY(ft_flags2, 2)					\
-	ALTINSTR_ENTRY(ft_flags3, 3)					\
-	".popsection\n"							\
-	".pushsection .altinstr_replacement, \"ax\"\n"			\
-	ALTINSTR_REPLACEMENT(newinsn1, 1)				\
-	ALTINSTR_REPLACEMENT(newinsn2, 2)				\
-	ALTINSTR_REPLACEMENT(newinsn3, 3)				\
-	".popsection\n"
+	ALTERNATIVE_2(oldinstr, newinstr_no, X86_FEATURE_ALWAYS, newinstr_yes, ft_flags)
+
+#define ALTERNATIVE_3(oldinstr, newinstr1, ft_flags1, newinstr2, ft_flags2, \
+			newinstr3, ft_flags3)				\
+	ALTERNATIVE(ALTERNATIVE_2(oldinstr, newinstr1, ft_flags1, newinstr2, ft_flags2), \
+		      newinstr3, ft_flags3)
 
 /*
  * Alternative instructions for different CPU types or capabilities.
@@ -266,14 +214,11 @@ static inline int alternatives_text_reserved(void *start, void *end)
  * without volatile and memory clobber.
  */
 #define alternative(oldinstr, newinstr, ft_flags)			\
-	asm_inline volatile (ALTERNATIVE(oldinstr, newinstr, ft_flags) : : : "memory")
+	asm_inline volatile(ALTERNATIVE(oldinstr, newinstr, ft_flags) : : : "memory")
 
 #define alternative_2(oldinstr, newinstr1, ft_flags1, newinstr2, ft_flags2) \
 	asm_inline volatile(ALTERNATIVE_2(oldinstr, newinstr1, ft_flags1, newinstr2, ft_flags2) ::: "memory")
 
-#define alternative_ternary(oldinstr, ft_flags, newinstr_yes, newinstr_no) \
-	asm_inline volatile(ALTERNATIVE_TERNARY(oldinstr, ft_flags, newinstr_yes, newinstr_no) ::: "memory")
-
 /*
  * Alternative inline assembly with input.
  *
@@ -283,18 +228,28 @@ static inline int alternatives_text_reserved(void *start, void *end)
  * Leaving an unused argument 0 to keep API compatibility.
  */
 #define alternative_input(oldinstr, newinstr, ft_flags, input...)	\
-	asm_inline volatile (ALTERNATIVE(oldinstr, newinstr, ft_flags)	\
+	asm_inline volatile(ALTERNATIVE(oldinstr, newinstr, ft_flags) \
 		: : "i" (0), ## input)
 
 /* Like alternative_input, but with a single output argument */
 #define alternative_io(oldinstr, newinstr, ft_flags, output, input...)	\
-	asm_inline volatile (ALTERNATIVE(oldinstr, newinstr, ft_flags)	\
+	asm_inline volatile(ALTERNATIVE(oldinstr, newinstr, ft_flags)	\
 		: output : "i" (0), ## input)
 
-/* Like alternative_io, but for replacing a direct call with another one. */
-#define alternative_call(oldfunc, newfunc, ft_flags, output, input...)	\
-	asm_inline volatile (ALTERNATIVE("call %c[old]", "call %c[new]", ft_flags) \
-		: output : [old] "i" (oldfunc), [new] "i" (newfunc), ## input)
+/*
+ * Like alternative_io, but for replacing a direct call with another one.
+ *
+ * Use the %c operand modifier which is the generic way to print a bare
+ * constant expression with all syntax-specific punctuation omitted. %P
+ * is the x86-specific variant which can handle constants too, for
+ * historical reasons, but it should be used primarily for PIC
+ * references: i.e., if used for a function, it would add the PLT
+ * suffix.
+ */
+#define alternative_call(oldfunc, newfunc, ft_flags, output, input...)			\
+	asm_inline volatile(ALTERNATIVE("call %c[old]", "call %c[new]", ft_flags)	\
+		: ALT_OUTPUT_SP(output)							\
+		: [old] "i" (oldfunc), [new] "i" (newfunc), ## input)
 
 /*
  * Like alternative_call, but there are two features and respective functions.
@@ -302,12 +257,12 @@ static inline int alternatives_text_reserved(void *start, void *end)
  * Otherwise, if CPU has feature1, function1 is used.
  * Otherwise, old function is used.
  */
-#define alternative_call_2(oldfunc, newfunc1, ft_flags1, newfunc2, ft_flags2, \
-			   output, input...)				\
-	asm_inline volatile (ALTERNATIVE_2("call %c[old]", "call %c[new1]", ft_flags1, \
-		"call %c[new2]", ft_flags2)				\
-		: output, ASM_CALL_CONSTRAINT				\
-		: [old] "i" (oldfunc), [new1] "i" (newfunc1),		\
+#define alternative_call_2(oldfunc, newfunc1, ft_flags1, newfunc2, ft_flags2,		\
+			   output, input...)						\
+	asm_inline volatile(ALTERNATIVE_2("call %c[old]", "call %c[new1]", ft_flags1,	\
+		"call %c[new2]", ft_flags2)						\
+		: ALT_OUTPUT_SP(output)							\
+		: [old] "i" (oldfunc), [new1] "i" (newfunc1),				\
 		  [new2] "i" (newfunc2), ## input)
 
 /*
@@ -322,6 +277,8 @@ static inline int alternatives_text_reserved(void *start, void *end)
  */
 #define ASM_NO_INPUT_CLOBBER(clbr...) "i" (0) : clbr
 
+#define ALT_OUTPUT_SP(...) ASM_CALL_CONSTRAINT, ## __VA_ARGS__
+
 /* Macro for creating assembler functions avoiding any C magic. */
 #define DEFINE_ASM_FUNC(func, instr, sec)		\
 	asm (".pushsection " #sec ", \"ax\"\n"		\
@@ -388,22 +345,23 @@ void nop_func(void);
  * @newinstr. ".skip" directive takes care of proper instruction padding
  * in case @newinstr is longer than @oldinstr.
  */
-.macro ALTERNATIVE oldinstr, newinstr, ft_flags
-140:
-	\oldinstr
-141:
-	.skip -(((144f-143f)-(141b-140b)) > 0) * ((144f-143f)-(141b-140b)),0x90
-142:
-
-	.pushsection .altinstructions,"a"
-	altinstr_entry 140b,143f,\ft_flags,142b-140b,144f-143f
-	.popsection
+#define __ALTERNATIVE(oldinst, newinst, flag)				\
+740:									\
+	oldinst	;							\
+741:									\
+	.skip -(((744f-743f)-(741b-740b)) > 0) * ((744f-743f)-(741b-740b)),0x90	;\
+742:									\
+	.pushsection .altinstructions,"a" ;				\
+	altinstr_entry 740b,743f,flag,742b-740b,744f-743f ;		\
+	.popsection ;							\
+	.pushsection .altinstr_replacement,"ax"	;			\
+743:									\
+	newinst	;							\
+744:									\
+	.popsection ;
 
-	.pushsection .altinstr_replacement,"ax"
-143:
-	\newinstr
-144:
-	.popsection
+.macro ALTERNATIVE oldinstr, newinstr, ft_flags
+	__ALTERNATIVE(\oldinstr, \newinstr, \ft_flags)
 .endm
 
 #define old_len			141b-140b
@@ -412,65 +370,18 @@ void nop_func(void);
 #define new_len3		146f-145f
 
 /*
- * gas compatible max based on the idea from:
- * http://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax
- *
- * The additional "-" is needed because gas uses a "true" value of -1.
- */
-#define alt_max_2(a, b)		((a) ^ (((a) ^ (b)) & -(-((a) < (b)))))
-#define alt_max_3(a, b, c)	(alt_max_2(alt_max_2(a, b), c))
-
-
-/*
  * Same as ALTERNATIVE macro above but for two alternatives. If CPU
  * has @feature1, it replaces @oldinstr with @newinstr1. If CPU has
  * @feature2, it replaces @oldinstr with @feature2.
  */
 .macro ALTERNATIVE_2 oldinstr, newinstr1, ft_flags1, newinstr2, ft_flags2
-140:
-	\oldinstr
-141:
-	.skip -((alt_max_2(new_len1, new_len2) - (old_len)) > 0) * \
-		(alt_max_2(new_len1, new_len2) - (old_len)),0x90
-142:
-
-	.pushsection .altinstructions,"a"
-	altinstr_entry 140b,143f,\ft_flags1,142b-140b,144f-143f
-	altinstr_entry 140b,144f,\ft_flags2,142b-140b,145f-144f
-	.popsection
-
-	.pushsection .altinstr_replacement,"ax"
-143:
-	\newinstr1
-144:
-	\newinstr2
-145:
-	.popsection
+	__ALTERNATIVE(__ALTERNATIVE(\oldinstr, \newinstr1, \ft_flags1),
+		      \newinstr2, \ft_flags2)
 .endm
 
 .macro ALTERNATIVE_3 oldinstr, newinstr1, ft_flags1, newinstr2, ft_flags2, newinstr3, ft_flags3
-140:
-	\oldinstr
-141:
-	.skip -((alt_max_3(new_len1, new_len2, new_len3) - (old_len)) > 0) * \
-		(alt_max_3(new_len1, new_len2, new_len3) - (old_len)),0x90
-142:
-
-	.pushsection .altinstructions,"a"
-	altinstr_entry 140b,143f,\ft_flags1,142b-140b,144f-143f
-	altinstr_entry 140b,144f,\ft_flags2,142b-140b,145f-144f
-	altinstr_entry 140b,145f,\ft_flags3,142b-140b,146f-145f
-	.popsection
-
-	.pushsection .altinstr_replacement,"ax"
-143:
-	\newinstr1
-144:
-	\newinstr2
-145:
-	\newinstr3
-146:
-	.popsection
+	__ALTERNATIVE(ALTERNATIVE_2(\oldinstr, \newinstr1, \ft_flags1, \newinstr2, \ft_flags2),
+		      \newinstr3, \ft_flags3)
 .endm
 
 /* If @feature is set, patch in @newinstr_yes, otherwise @newinstr_no. */
diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h
index cc6b8e087192..af4302d79b59 100644
--- a/arch/x86/include/asm/page_64.h
+++ b/arch/x86/include/asm/page_64.h
@@ -54,7 +54,7 @@ static inline void clear_page(void *page)
 			   clear_page_rep, X86_FEATURE_REP_GOOD,
 			   clear_page_erms, X86_FEATURE_ERMS,
 			   "=D" (page),
-			   "0" (page)
+			   "D" (page)
 			   : "cc", "memory", "rax", "rcx");
 }
 
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 89de61243272..333b16181357 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -432,6 +432,11 @@ static int alt_replace_call(u8 *instr, u8 *insn_buff, struct alt_instr *a)
 	return 5;
 }
 
+static inline u8 * instr_va(struct alt_instr *i)
+{
+	return (u8 *)&i->instr_offset + i->instr_offset;
+}
+
 /*
  * Replace instructions with better alternatives for this CPU type. This runs
  * before SMP is initialized to avoid SMP problems with self modifying code.
@@ -447,7 +452,7 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
 {
 	u8 insn_buff[MAX_PATCH_LEN];
 	u8 *instr, *replacement;
-	struct alt_instr *a;
+	struct alt_instr *a, *b;
 
 	DPRINTK(ALT, "alt table %px, -> %px", start, end);
 
@@ -473,7 +478,18 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
 	for (a = start; a < end; a++) {
 		int insn_buff_sz = 0;
 
-		instr = (u8 *)&a->instr_offset + a->instr_offset;
+		/*
+		 * In case of nested ALTERNATIVE()s the outer alternative might
+		 * add more padding. To ensure consistent patching find the max
+		 * padding for all alt_instr entries for this site (nested
+		 * alternatives result in consecutive entries).
+		 */
+		for (b = a+1; b < end && instr_va(b) == instr_va(a); b++) {
+			u8 len = max(a->instrlen, b->instrlen);
+			a->instrlen = b->instrlen = len;
+		}
+
+		instr = instr_va(a);
 		replacement = (u8 *)&a->repl_offset + a->repl_offset;
 		BUG_ON(a->instrlen > sizeof(insn_buff));
 		BUG_ON(a->cpuid >= (NCAPINTS + NBUGINTS) * 32);
@@ -1641,7 +1657,7 @@ static noinline void __init alt_reloc_selftest(void)
 	 */
 	asm_inline volatile (
 		ALTERNATIVE("", "lea %[mem], %%" _ASM_ARG1 "; call __alt_reloc_selftest;", X86_FEATURE_ALWAYS)
-		: /* output */
+		: ASM_CALL_CONSTRAINT
 		: [mem] "m" (__alt_reloc_selftest_addr)
 		: _ASM_ARG1
 	);
diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h
index 05df04f39628..2ee0b9c53dcc 100644
--- a/arch/x86/kernel/fpu/xstate.h
+++ b/arch/x86/kernel/fpu/xstate.h
@@ -106,21 +106,17 @@ static inline u64 xfeatures_mask_independent(void)
  * Otherwise, if XSAVEOPT is enabled, XSAVEOPT replaces XSAVE because XSAVEOPT
  * supports modified optimization which is not supported by XSAVE.
  *
- * We use XSAVE as a fallback.
- *
- * The 661 label is defined in the ALTERNATIVE* macros as the address of the
- * original instruction which gets replaced. We need to use it here as the
- * address of the instruction where we might get an exception at.
+ * Use XSAVE as a fallback.
  */
 #define XSTATE_XSAVE(st, lmask, hmask, err)				\
-	asm volatile(ALTERNATIVE_3(XSAVE,				\
+	asm volatile("1: " ALTERNATIVE_3(XSAVE,				\
 				   XSAVEOPT, X86_FEATURE_XSAVEOPT,	\
 				   XSAVEC,   X86_FEATURE_XSAVEC,	\
 				   XSAVES,   X86_FEATURE_XSAVES)	\
 		     "\n"						\
 		     "xor %[err], %[err]\n"				\
 		     "3:\n"						\
-		     _ASM_EXTABLE_TYPE_REG(661b, 3b, EX_TYPE_EFAULT_REG, %[err]) \
+		     _ASM_EXTABLE_TYPE_REG(1b, 3b, EX_TYPE_EFAULT_REG, %[err]) \
 		     : [err] "=r" (err)					\
 		     : "D" (st), "m" (*st), "a" (lmask), "d" (hmask)	\
 		     : "memory")
@@ -130,11 +126,11 @@ static inline u64 xfeatures_mask_independent(void)
  * XSAVE area format.
  */
 #define XSTATE_XRESTORE(st, lmask, hmask)				\
-	asm volatile(ALTERNATIVE(XRSTOR,				\
+	asm volatile("1: " ALTERNATIVE(XRSTOR,				\
 				 XRSTORS, X86_FEATURE_XSAVES)		\
 		     "\n"						\
 		     "3:\n"						\
-		     _ASM_EXTABLE_TYPE(661b, 3b, EX_TYPE_FPU_RESTORE)	\
+		     _ASM_EXTABLE_TYPE(1b, 3b, EX_TYPE_FPU_RESTORE)	\
 		     :							\
 		     : "D" (st), "m" (*st), "a" (lmask), "d" (hmask)	\
 		     : "memory")
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 5d4c86133453..c8cc578646d0 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -1069,7 +1069,7 @@ static __always_inline u8 test_cc(unsigned int condition, unsigned long flags)
 
 	flags = (flags & EFLAGS_MASK) | X86_EFLAGS_IF;
 	asm("push %[flags]; popf; " CALL_NOSPEC
-	    : "=a"(rc) : [thunk_target]"r"(fop), [flags]"r"(flags));
+	    : "=a"(rc), ASM_CALL_CONSTRAINT : [thunk_target]"r"(fop), [flags]"r"(flags));
 	return rc;
 }
 
diff --git a/tools/objtool/Documentation/objtool.txt b/tools/objtool/Documentation/objtool.txt
index fe39c2a8ef0d..7c3ee959b63c 100644
--- a/tools/objtool/Documentation/objtool.txt
+++ b/tools/objtool/Documentation/objtool.txt
@@ -284,6 +284,25 @@ the objtool maintainers.
 
    Otherwise the stack frame may not get created before the call.
 
+   objtool can help with pinpointing the exact function where it happens:
+
+   $ OBJTOOL_ARGS="--verbose" make arch/x86/kvm/
+
+   arch/x86/kvm/kvm.o: warning: objtool: .altinstr_replacement+0xc5: call without frame pointer save/setup
+   arch/x86/kvm/kvm.o: warning: objtool:   em_loop.part.0+0x29: (alt)
+   arch/x86/kvm/kvm.o: warning: objtool:   em_loop.part.0+0x0: <=== (sym)
+    LD [M]  arch/x86/kvm/kvm-intel.o
+   0000 0000000000028220 <em_loop.part.0>:
+   0000    28220:  0f b6 47 61             movzbl 0x61(%rdi),%eax
+   0004    28224:  3c e2                   cmp    $0xe2,%al
+   0006    28226:  74 2c                   je     28254 <em_loop.part.0+0x34>
+   0008    28228:  48 8b 57 10             mov    0x10(%rdi),%rdx
+   000c    2822c:  83 f0 05                xor    $0x5,%eax
+   000f    2822f:  48 c1 e0 04             shl    $0x4,%rax
+   0013    28233:  25 f0 00 00 00          and    $0xf0,%eax
+   0018    28238:  81 e2 d5 08 00 00       and    $0x8d5,%edx
+   001e    2823e:  80 ce 02                or     $0x2,%dh
+   ...
 
 2. file.o: warning: objtool: .text+0x53: unreachable instruction
 
diff --git a/tools/objtool/arch/x86/special.c b/tools/objtool/arch/x86/special.c
index 4134d27c696b..4ea0f9815fda 100644
--- a/tools/objtool/arch/x86/special.c
+++ b/tools/objtool/arch/x86/special.c
@@ -9,6 +9,29 @@
 
 void arch_handle_alternative(unsigned short feature, struct special_alt *alt)
 {
+	static struct special_alt *group, *prev;
+
+	/*
+	 * Recompute orig_len for nested ALTERNATIVE()s.
+	 */
+	if (group && group->orig_sec == alt->orig_sec &&
+	             group->orig_off == alt->orig_off) {
+
+		struct special_alt *iter = group;
+		for (;;) {
+			unsigned int len = max(iter->orig_len, alt->orig_len);
+			iter->orig_len = alt->orig_len = len;
+
+			if (iter == prev)
+				break;
+
+			iter = list_next_entry(iter, list);
+		}
+
+	} else group = alt;
+
+	prev = alt;
+
 	switch (feature) {
 	case X86_FEATURE_SMAP:
 		/*
diff --git a/tools/objtool/special.c b/tools/objtool/special.c
index 91b1950f5bd8..097a69db82a0 100644
--- a/tools/objtool/special.c
+++ b/tools/objtool/special.c
@@ -84,6 +84,14 @@ static int get_alt_entry(struct elf *elf, const struct special_entry *entry,
 						  entry->new_len);
 	}
 
+	orig_reloc = find_reloc_by_dest(elf, sec, offset + entry->orig);
+	if (!orig_reloc) {
+		WARN_FUNC("can't find orig reloc", sec, offset + entry->orig);
+		return -1;
+	}
+
+	reloc_to_sec_off(orig_reloc, &alt->orig_sec, &alt->orig_off);
+
 	if (entry->feature) {
 		unsigned short feature;
 
@@ -94,14 +102,6 @@ static int get_alt_entry(struct elf *elf, const struct special_entry *entry,
 		arch_handle_alternative(feature, alt);
 	}
 
-	orig_reloc = find_reloc_by_dest(elf, sec, offset + entry->orig);
-	if (!orig_reloc) {
-		WARN_FUNC("can't find orig reloc", sec, offset + entry->orig);
-		return -1;
-	}
-
-	reloc_to_sec_off(orig_reloc, &alt->orig_sec, &alt->orig_off);
-
 	if (!entry->group || alt->new_len) {
 		new_reloc = find_reloc_by_dest(elf, sec, offset + entry->new);
 		if (!new_reloc) {