x86/alternatives: Add instruction padding

Up until now we have always paid attention to make sure the length of
the new instruction replacing the old one is at least less or equal to
the length of the old instruction. If the new instruction is longer, at
the time it replaces the old instruction it will overwrite the beginning
of the next instruction in the kernel image and cause your pants to
catch fire.

So instead of having to pay attention, teach the alternatives framework
to pad shorter old instructions with NOPs at buildtime - but only in the
case when

  len(old instruction(s)) < len(new instruction(s))

and add nothing in the >= case. (In that case we do add_nops() when
patching).

This way the alternatives user shouldn't have to care about instruction
sizes and simply use the macros.

Add asm ALTERNATIVE* flavor macros too, while at it.

Also, we need to save the pad length in a separate struct alt_instr
member for NOP optimization and the way to do that reliably is to carry
the pad length instead of trying to detect whether we're looking at
single-byte NOPs or at pathological instruction offsets like e9 90 90 90
90, for example, which is a valid instruction.

Thanks to Michael Matz for the great help with toolchain questions.

Signed-off-by: Borislav Petkov <bp@suse.de>

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

@@ -18,12 +18,53 @@
 	.endm
 #endif
 
-.macro altinstruction_entry orig alt feature orig_len alt_len
+.macro altinstruction_entry orig alt feature orig_len alt_len pad_len
 	.long \orig - .
 	.long \alt - .
 	.word \feature
 	.byte \orig_len
 	.byte \alt_len
+	.byte \pad_len
+.endm
+
+.macro ALTERNATIVE oldinstr, newinstr, feature
+140:
+	\oldinstr
+141:
+	.skip -(((144f-143f)-(141b-140b)) > 0) * ((144f-143f)-(141b-140b)),0x90
+142:
+
+	.pushsection .altinstructions,"a"
+	altinstruction_entry 140b,143f,\feature,142b-140b,144f-143f,142b-141b
+	.popsection
+
+	.pushsection .altinstr_replacement,"ax"
+143:
+	\newinstr
+144:
+	.popsection
+.endm
+
+.macro ALTERNATIVE_2 oldinstr, newinstr1, feature1, newinstr2, feature2
+140:
+	\oldinstr
+141:
+	.skip -(((144f-143f)-(141b-140b)) > 0) * ((144f-143f)-(141b-140b)),0x90
+	.skip -(((145f-144f)-(144f-143f)-(141b-140b)) > 0) * ((145f-144f)-(144f-143f)-(141b-140b)),0x90
+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
+	.popsection
+
+	.pushsection .altinstr_replacement,"ax"
+143:
+	\newinstr1
+144:
+	\newinstr2
+145:
+	.popsection
 .endm
 
 #endif  /*  __ASSEMBLY__  */

arch/x86/include/asm/alternative.h

@@ -48,8 +48,9 @@ struct alt_instr {
 	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, <= instrlen */
-};
+	u8  replacementlen;	/* length of new instruction */
+	u8  padlen;		/* length of build-time padding */
+} __packed;
 
 extern void alternative_instructions(void);
 extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end);
@@ -76,50 +77,61 @@ static inline int alternatives_text_reserved(void *start, void *end)
 }
 #endif	/* CONFIG_SMP */
 
-#define OLDINSTR(oldinstr)	"661:\n\t" oldinstr "\n662:\n"
+#define b_replacement(num)	"664"#num
+#define e_replacement(num)	"665"#num
 
-#define b_replacement(number)	"663"#number
-#define e_replacement(number)	"664"#number
+#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"
 
-#define alt_slen "662b-661b"
-#define alt_rlen(number) e_replacement(number)"f-"b_replacement(number)"f"
+#define __OLDINSTR(oldinstr, num)					\
+	"661:\n\t" oldinstr "\n662:\n"					\
+	".skip -(((" alt_rlen(num) ")-(" alt_slen ")) > 0) * "		\
+		"((" alt_rlen(num) ")-(" alt_slen ")),0x90\n"
 
-#define ALTINSTR_ENTRY(feature, number)					      \
+#define OLDINSTR(oldinstr, num)						\
+	__OLDINSTR(oldinstr, num)					\
+	alt_end_marker ":\n"
+
+/*
+ * Pad the second replacement alternative with additional NOPs if it is
+ * additionally longer than the first replacement alternative.
+ */
+#define OLDINSTR_2(oldinstr, num1, num2)					\
+	__OLDINSTR(oldinstr, num1)						\
+	".skip -(((" alt_rlen(num2) ")-(" alt_rlen(num1) ")-(662b-661b)) > 0) * " \
+		"((" alt_rlen(num2) ")-(" alt_rlen(num1) ")-(662b-661b)),0x90\n"  \
+	alt_end_marker ":\n"
+
+#define ALTINSTR_ENTRY(feature, num)					      \
 	" .long 661b - .\n"				/* label           */ \
-	" .long " b_replacement(number)"f - .\n"	/* new instruction */ \
+	" .long " b_replacement(num)"f - .\n"		/* new instruction */ \
 	" .word " __stringify(feature) "\n"		/* feature bit     */ \
-	" .byte " alt_slen "\n"				/* source len      */ \
-	" .byte " alt_rlen(number) "\n"			/* replacement len */
+	" .byte " alt_total_slen "\n"			/* source len      */ \
+	" .byte " alt_rlen(num) "\n"			/* replacement len */ \
+	" .byte " alt_pad_len "\n"			/* pad len */
 
-#define DISCARD_ENTRY(number)				/* rlen <= slen */    \
-	" .byte 0xff + (" alt_rlen(number) ") - (" alt_slen ")\n"
-
-#define ALTINSTR_REPLACEMENT(newinstr, feature, number)	/* replacement */     \
-	b_replacement(number)":\n\t" newinstr "\n" e_replacement(number) ":\n\t"
+#define ALTINSTR_REPLACEMENT(newinstr, feature, num)	/* replacement */     \
+	b_replacement(num)":\n\t" newinstr "\n" e_replacement(num) ":\n\t"
 
 /* alternative assembly primitive: */
 #define ALTERNATIVE(oldinstr, newinstr, feature)			\
-	OLDINSTR(oldinstr)						\
+	OLDINSTR(oldinstr, 1)						\
 	".pushsection .altinstructions,\"a\"\n"				\
 	ALTINSTR_ENTRY(feature, 1)					\
 	".popsection\n"							\
-	".pushsection .discard,\"aw\",@progbits\n"			\
-	DISCARD_ENTRY(1)						\
-	".popsection\n"							\
 	".pushsection .altinstr_replacement, \"ax\"\n"			\
 	ALTINSTR_REPLACEMENT(newinstr, feature, 1)			\
 	".popsection"
 
 #define ALTERNATIVE_2(oldinstr, newinstr1, feature1, newinstr2, feature2)\
-	OLDINSTR(oldinstr)						\
+	OLDINSTR_2(oldinstr, 1, 2)					\
 	".pushsection .altinstructions,\"a\"\n"				\
 	ALTINSTR_ENTRY(feature1, 1)					\
 	ALTINSTR_ENTRY(feature2, 2)					\
 	".popsection\n"							\
-	".pushsection .discard,\"aw\",@progbits\n"			\
-	DISCARD_ENTRY(1)						\
-	DISCARD_ENTRY(2)						\
-	".popsection\n"							\
 	".pushsection .altinstr_replacement, \"ax\"\n"			\
 	ALTINSTR_REPLACEMENT(newinstr1, feature1, 1)			\
 	ALTINSTR_REPLACEMENT(newinstr2, feature2, 2)			\
@@ -146,6 +158,9 @@ static inline int alternatives_text_reserved(void *start, void *end)
 #define alternative(oldinstr, newinstr, feature)			\
 	asm volatile (ALTERNATIVE(oldinstr, newinstr, feature) : : : "memory")
 
+#define alternative_2(oldinstr, newinstr1, feature1, newinstr2, feature2) \
+	asm volatile(ALTERNATIVE_2(oldinstr, newinstr1, feature1, newinstr2, feature2) ::: "memory")
+
 /*
  * Alternative inline assembly with input.
  *

arch/x86/include/asm/cpufeature.h

@@ -418,6 +418,7 @@ static __always_inline __pure bool __static_cpu_has(u16 bit)
 			 " .word %P0\n"		/* 1: do replace */
 			 " .byte 2b - 1b\n"	/* source len */
 			 " .byte 0\n"		/* replacement len */
+			 " .byte 0\n"		/* pad len */
 			 ".previous\n"
 			 /* skipping size check since replacement size = 0 */
 			 : : "i" (X86_FEATURE_ALWAYS) : : t_warn);
@@ -432,6 +433,7 @@ static __always_inline __pure bool __static_cpu_has(u16 bit)
 			 " .word %P0\n"		/* feature bit */
 			 " .byte 2b - 1b\n"	/* source len */
 			 " .byte 0\n"		/* replacement len */
+			 " .byte 0\n"		/* pad len */
 			 ".previous\n"
 			 /* skipping size check since replacement size = 0 */
 			 : : "i" (bit) : : t_no);
@@ -457,6 +459,7 @@ static __always_inline __pure bool __static_cpu_has(u16 bit)
 			     " .word %P1\n"		/* feature bit */
 			     " .byte 2b - 1b\n"		/* source len */
 			     " .byte 4f - 3f\n"		/* replacement len */
+			     " .byte 0\n"		/* pad len */
 			     ".previous\n"
 			     ".section .discard,\"aw\",@progbits\n"
 			     " .byte 0xff + (4f-3f) - (2b-1b)\n" /* size check */
@@ -491,23 +494,28 @@ static __always_inline __pure bool _static_cpu_has_safe(u16 bit)
  */
 		asm_volatile_goto("1: .byte 0xe9\n .long %l[t_dynamic] - 2f\n"
 			 "2:\n"
+			 ".skip -(((5f-4f) - (2b-1b)) > 0) * "
+			         "((5f-4f) - (2b-1b)),0x90\n"
+			 "3:\n"
 			 ".section .altinstructions,\"a\"\n"
 			 " .long 1b - .\n"		/* src offset */
-			 " .long 3f - .\n"		/* repl offset */
+			 " .long 4f - .\n"		/* repl offset */
 			 " .word %P1\n"			/* always replace */
-			 " .byte 2b - 1b\n"		/* src len */
-			 " .byte 4f - 3f\n"		/* repl len */
+			 " .byte 3b - 1b\n"		/* src len */
+			 " .byte 5f - 4f\n"		/* repl len */
+			 " .byte 3b - 2b\n"		/* pad len */
 			 ".previous\n"
 			 ".section .altinstr_replacement,\"ax\"\n"
-			 "3: .byte 0xe9\n .long %l[t_no] - 2b\n"
-			 "4:\n"
+			 "4: .byte 0xe9\n .long %l[t_no] - 2b\n"
+			 "5:\n"
 			 ".previous\n"
 			 ".section .altinstructions,\"a\"\n"
 			 " .long 1b - .\n"		/* src offset */
 			 " .long 0\n"			/* no replacement */
 			 " .word %P0\n"			/* feature bit */
-			 " .byte 2b - 1b\n"		/* src len */
+			 " .byte 3b - 1b\n"		/* src len */
 			 " .byte 0\n"			/* repl len */
+			 " .byte 0\n"			/* pad len */
 			 ".previous\n"
 			 : : "i" (bit), "i" (X86_FEATURE_ALWAYS)
 			 : : t_dynamic, t_no);
@@ -527,6 +535,7 @@ static __always_inline __pure bool _static_cpu_has_safe(u16 bit)
 			     " .word %P2\n"		/* always replace */
 			     " .byte 2b - 1b\n"		/* source len */
 			     " .byte 4f - 3f\n"		/* replacement len */
+			     " .byte 0\n"		/* pad len */
 			     ".previous\n"
 			     ".section .discard,\"aw\",@progbits\n"
 			     " .byte 0xff + (4f-3f) - (2b-1b)\n" /* size check */
@@ -541,6 +550,7 @@ static __always_inline __pure bool _static_cpu_has_safe(u16 bit)
 			     " .word %P1\n"		/* feature bit */
 			     " .byte 4b - 3b\n"		/* src len */
 			     " .byte 6f - 5f\n"		/* repl len */
+			     " .byte 0\n"		/* pad len */
 			     ".previous\n"
 			     ".section .discard,\"aw\",@progbits\n"
 			     " .byte 0xff + (6f-5f) - (4b-3b)\n" /* size check */

arch/x86/include/asm/smap.h

@@ -33,7 +33,7 @@
 	662: __ASM_CLAC ;						\
 	.popsection ;							\
 	.pushsection .altinstructions, "a" ;				\
-	altinstruction_entry 661b, 662b, X86_FEATURE_SMAP, 3, 3 ;	\
+	altinstruction_entry 661b, 662b, X86_FEATURE_SMAP, 3, 3, 0 ;	\
 	.popsection
 
 #define ASM_STAC							\
@@ -42,7 +42,7 @@
 	662: __ASM_STAC ;						\
 	.popsection ;							\
 	.pushsection .altinstructions, "a" ;				\
-	altinstruction_entry 661b, 662b, X86_FEATURE_SMAP, 3, 3 ;	\
+	altinstruction_entry 661b, 662b, X86_FEATURE_SMAP, 3, 3, 0 ;	\
 	.popsection
 
 #else /* CONFIG_X86_SMAP */

arch/x86/kernel/alternative.c

@@ -270,7 +270,6 @@ void __init_or_module apply_alternatives(struct alt_instr *start,
 	for (a = start; a < end; a++) {
 		instr = (u8 *)&a->instr_offset + a->instr_offset;
 		replacement = (u8 *)&a->repl_offset + a->repl_offset;
-		BUG_ON(a->replacementlen > a->instrlen);
 		BUG_ON(a->instrlen > sizeof(insnbuf));
 		BUG_ON(a->cpuid >= (NCAPINTS + NBUGINTS) * 32);
 		if (!boot_cpu_has(a->cpuid))
@@ -290,8 +289,9 @@ void __init_or_module apply_alternatives(struct alt_instr *start,
 			DPRINTK("Fix CALL offset: 0x%x", *(s32 *)(insnbuf + 1));
 		}
 
-		add_nops(insnbuf + a->replacementlen,
-			 a->instrlen - a->replacementlen);
+		if (a->instrlen > a->replacementlen)
+			add_nops(insnbuf + a->replacementlen,
+				 a->instrlen - a->replacementlen);
 
 		text_poke_early(instr, insnbuf, a->instrlen);
 	}

arch/x86/kernel/entry_32.S

@@ -819,7 +819,7 @@ ENTRY(simd_coprocessor_error)
 661:	pushl_cfi $do_general_protection
 662:
 .section .altinstructions,"a"
-	altinstruction_entry 661b, 663f, X86_FEATURE_XMM, 662b-661b, 664f-663f
+	altinstruction_entry 661b, 663f, X86_FEATURE_XMM, 662b-661b, 664f-663f, 0
 .previous
 .section .altinstr_replacement,"ax"
 663:	pushl $do_simd_coprocessor_error

arch/x86/lib/clear_page_64.S

@@ -67,7 +67,7 @@ ENDPROC(clear_page)
 	.previous
 	.section .altinstructions,"a"
 	altinstruction_entry clear_page,1b,X86_FEATURE_REP_GOOD,\
-			     .Lclear_page_end-clear_page, 2b-1b
+			     .Lclear_page_end-clear_page, 2b-1b, 0
 	altinstruction_entry clear_page,2b,X86_FEATURE_ERMS,   \
-			     .Lclear_page_end-clear_page,3b-2b
+			     .Lclear_page_end-clear_page,3b-2b, 0
 	.previous

arch/x86/lib/copy_page_64.S

@@ -106,5 +106,5 @@ ENDPROC(copy_page)
 	.previous
 	.section .altinstructions,"a"
 	altinstruction_entry copy_page, 1b, X86_FEATURE_REP_GOOD,	\
-		.Lcopy_page_end-copy_page, 2b-1b
+		.Lcopy_page_end-copy_page, 2b-1b, 0
 	.previous

arch/x86/lib/copy_user_64.S

@@ -36,8 +36,8 @@
 	.previous
 
 	.section .altinstructions,"a"
-	altinstruction_entry 0b,2b,\feature1,5,5
-	altinstruction_entry 0b,3b,\feature2,5,5
+	altinstruction_entry 0b,2b,\feature1,5,5,0
+	altinstruction_entry 0b,3b,\feature2,5,5,0
 	.previous
 	.endm
 

arch/x86/lib/memcpy_64.S

@@ -202,7 +202,7 @@ ENDPROC(__memcpy)
 	 */
 	.section .altinstructions, "a"
 	altinstruction_entry __memcpy,.Lmemcpy_c,X86_FEATURE_REP_GOOD,\
-			     .Lmemcpy_e-.Lmemcpy_c,.Lmemcpy_e-.Lmemcpy_c
+			     .Lmemcpy_e-.Lmemcpy_c,.Lmemcpy_e-.Lmemcpy_c,0
 	altinstruction_entry __memcpy,.Lmemcpy_c_e,X86_FEATURE_ERMS, \
-			     .Lmemcpy_e_e-.Lmemcpy_c_e,.Lmemcpy_e_e-.Lmemcpy_c_e
+			     .Lmemcpy_e_e-.Lmemcpy_c_e,.Lmemcpy_e_e-.Lmemcpy_c_e,0
 	.previous

arch/x86/lib/memmove_64.S

@@ -221,7 +221,7 @@ ENTRY(__memmove)
 	altinstruction_entry .Lmemmove_begin_forward,		\
 		.Lmemmove_begin_forward_efs,X86_FEATURE_ERMS,	\
 		.Lmemmove_end_forward-.Lmemmove_begin_forward,	\
-		.Lmemmove_end_forward_efs-.Lmemmove_begin_forward_efs
+		.Lmemmove_end_forward_efs-.Lmemmove_begin_forward_efs,0
 	.previous
 ENDPROC(__memmove)
 ENDPROC(memmove)

arch/x86/lib/memset_64.S

@@ -150,7 +150,7 @@ ENDPROC(__memset)
 	 */
 	.section .altinstructions,"a"
 	altinstruction_entry __memset,.Lmemset_c,X86_FEATURE_REP_GOOD,\
-			     .Lfinal-__memset,.Lmemset_e-.Lmemset_c
+			     .Lfinal-__memset,.Lmemset_e-.Lmemset_c,0
 	altinstruction_entry __memset,.Lmemset_c_e,X86_FEATURE_ERMS, \
-			     .Lfinal-__memset,.Lmemset_e_e-.Lmemset_c_e
+			     .Lfinal-__memset,.Lmemset_e_e-.Lmemset_c_e,0
 	.previous