perf bench: Update the copies of x86's mem{cpy,set}_64.S

And update linux/linkage.h, which requires in turn that we make these
files switch from ENTRY()/ENDPROC() to SYM_FUNC_START()/SYM_FUNC_END():

tools/perf/arch/arm64/tests/regs_load.S
tools/perf/arch/arm/tests/regs_load.S
tools/perf/arch/powerpc/tests/regs_load.S
tools/perf/arch/x86/tests/regs_load.S

We also need to switch SYM_FUNC_START_LOCAL() to SYM_FUNC_START() for
the functions used directly by 'perf bench', and update
tools/perf/check_headers.sh to ignore those changes when checking if the
kernel original files drifted from the copies we carry.

This is to get the changes from:

6dcc5627f6ae ("x86/asm: Change all ENTRY+ENDPROC to SYM_FUNC_*")
ef1e03152cb0 ("x86/asm: Make some functions local")
e9b9d020c487 ("x86/asm: Annotate aliases")

And address these tools/perf build warnings:

Warning: Kernel ABI header at 'tools/arch/x86/lib/memcpy_64.S' differs from latest version at 'arch/x86/lib/memcpy_64.S'
diff -u tools/arch/x86/lib/memcpy_64.S arch/x86/lib/memcpy_64.S
Warning: Kernel ABI header at 'tools/arch/x86/lib/memset_64.S' differs from latest version at 'arch/x86/lib/memset_64.S'
diff -u tools/arch/x86/lib/memset_64.S arch/x86/lib/memset_64.S

Cc: Adrian Hunter <[e-mail]>
Cc: Borislav Petkov <[e-mail]>
Cc: Jiri Olsa <[e-mail]>
Cc: Jiri Slaby <[e-mail]>
Cc: Namhyung Kim <[e-mail]>
Link: https://lkml.kernel.org/n/[e-mail]
Signed-off-by: Arnaldo Carvalho de Melo <[e-mail]>

tools/arch/x86/lib/memcpy_64.S

···
  * Output:
  * rax original destination
  */
-ENTRY(__memcpy)
-ENTRY(memcpy)
+SYM_FUNC_START_ALIAS(__memcpy)
+SYM_FUNC_START_LOCAL(memcpy)
 	ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \
 		      "jmp memcpy_erms", X86_FEATURE_ERMS
 
···
 	movl %edx, %ecx
 	rep movsb
 	ret
-ENDPROC(memcpy)
-ENDPROC(__memcpy)
+SYM_FUNC_END(memcpy)
+SYM_FUNC_END_ALIAS(__memcpy)
 EXPORT_SYMBOL(memcpy)
 EXPORT_SYMBOL(__memcpy)
 
···
  * memcpy_erms() - enhanced fast string memcpy. This is faster and
  * simpler than memcpy. Use memcpy_erms when possible.
  */
-ENTRY(memcpy_erms)
+SYM_FUNC_START(memcpy_erms)
 	movq %rdi, %rax
 	movq %rdx, %rcx
 	rep movsb
 	ret
-ENDPROC(memcpy_erms)
+SYM_FUNC_END(memcpy_erms)
 
-ENTRY(memcpy_orig)
+SYM_FUNC_START(memcpy_orig)
 	movq %rdi, %rax
 
 	cmpq $0x20, %rdx
···
 
 .Lend:
 	retq
-ENDPROC(memcpy_orig)
+SYM_FUNC_END(memcpy_orig)
 
 #ifndef CONFIG_UML
 
···
  * Note that we only catch machine checks when reading the source addresses.
  * Writes to target are posted and don't generate machine checks.
  */
-ENTRY(__memcpy_mcsafe)
+SYM_FUNC_START(__memcpy_mcsafe)
 	cmpl $8, %edx
 	/* Less than 8 bytes? Go to byte copy loop */
 	jb .L_no_whole_words
···
 	xorl %eax, %eax
 .L_done:
 	ret
-ENDPROC(__memcpy_mcsafe)
+SYM_FUNC_END(__memcpy_mcsafe)
 EXPORT_SYMBOL_GPL(__memcpy_mcsafe)
 
 	.section .fixup, "ax"

tools/arch/x86/lib/memset_64.S

···
  *
  * rax   original destination
  */
-ENTRY(memset)
-ENTRY(__memset)
+SYM_FUNC_START_ALIAS(memset)
+SYM_FUNC_START(__memset)
 	/*
 	 * Some CPUs support enhanced REP MOVSB/STOSB feature. It is recommended
 	 * to use it when possible. If not available, use fast string instructions.
···
 	rep stosb
 	movq %r9,%rax
 	ret
-ENDPROC(memset)
-ENDPROC(__memset)
+SYM_FUNC_END(__memset)
+SYM_FUNC_END_ALIAS(memset)
 
 /*
  * ISO C memset - set a memory block to a byte value. This function uses
···
  *
  * rax   original destination
  */
-ENTRY(memset_erms)
+SYM_FUNC_START(memset_erms)
 	movq %rdi,%r9
 	movb %sil,%al
 	movq %rdx,%rcx
 	rep stosb
 	movq %r9,%rax
 	ret
-ENDPROC(memset_erms)
+SYM_FUNC_END(memset_erms)
 
-ENTRY(memset_orig)
+SYM_FUNC_START(memset_orig)
 	movq %rdi,%r10
 
 	/* expand byte value  */
···
 	subq %r8,%rdx
 	jmp .Lafter_bad_alignment
 .Lfinal:
-ENDPROC(memset_orig)
+SYM_FUNC_END(memset_orig)

tools/perf/arch/arm/tests/regs_load.S

···
 
 .text
 .type perf_regs_load,%function
-ENTRY(perf_regs_load)
+SYM_FUNC_START(perf_regs_load)
 	str r0, [r0, #R0]
 	str r1, [r0, #R1]
 	str r2, [r0, #R2]
···
 	str lr, [r0, #PC]	// store pc as lr in order to skip the call
 	                        //  to this function
 	mov pc, lr
-ENDPROC(perf_regs_load)
+SYM_FUNC_END(perf_regs_load)

tools/perf/arch/arm64/tests/regs_load.S

···
 #define LDR_REG(r)	ldr x##r, [x0, 8 * r]
 #define SP	(8 * 31)
 #define PC	(8 * 32)
-ENTRY(perf_regs_load)
+SYM_FUNC_START(perf_regs_load)
 	STR_REG(0)
 	STR_REG(1)
 	STR_REG(2)
···
 	str x30, [x0, #PC]
 	LDR_REG(1)
 	ret
-ENDPROC(perf_regs_load)
+SYM_FUNC_END(perf_regs_load)

tools/perf/arch/x86/tests/regs_load.S

···
 
 .text
 #ifdef HAVE_ARCH_X86_64_SUPPORT
-ENTRY(perf_regs_load)
+SYM_FUNC_START(perf_regs_load)
 	movq %rax, AX(%rdi)
 	movq %rbx, BX(%rdi)
 	movq %rcx, CX(%rdi)
···
 	movq %r14, R14(%rdi)
 	movq %r15, R15(%rdi)
 	ret
-ENDPROC(perf_regs_load)
+SYM_FUNC_END(perf_regs_load)
 #else
-ENTRY(perf_regs_load)
+SYM_FUNC_START(perf_regs_load)
 	push %edi
 	movl 8(%esp), %edi
 	movl %eax, AX(%edi)
···
 	movl $0, FS(%edi)
 	movl $0, GS(%edi)
 	ret
-ENDPROC(perf_regs_load)
+SYM_FUNC_END(perf_regs_load)
 #endif
 
 /*

tools/perf/check-headers.sh

···
 done
 
 # diff with extra ignore lines
-check arch/x86/lib/memcpy_64.S        '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"'
-check arch/x86/lib/memset_64.S        '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"'
+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/uapi/asm-generic/mman.h '-I "^#include <\(uapi/\)*asm-generic/mman-common\(-tools\)*.h>"'
 check include/uapi/linux/mman.h       '-I "^#include <\(uapi/\)*asm/mman.h>"'
 check include/linux/ctype.h	      '-I "isdigit("'

tools/perf/util/include/linux/linkage.h

···
 
 /* linkage.h ... for including arch/x86/lib/memcpy_64.S */
 
-#define ENTRY(name)				\
-	.globl name;				\
-	name:
+/* Some toolchains use other characters (e.g. '`') to mark new line in macro */
+#ifndef ASM_NL
+#define ASM_NL		 ;
+#endif
 
-#define ENDPROC(name)
+#ifndef __ALIGN
+#define __ALIGN		.align 4,0x90
+#define __ALIGN_STR	".align 4,0x90"
+#endif
+
+/* SYM_T_FUNC -- type used by assembler to mark functions */
+#ifndef SYM_T_FUNC
+#define SYM_T_FUNC				STT_FUNC
+#endif
+
+/* SYM_A_* -- align the symbol? */
+#define SYM_A_ALIGN				ALIGN
+
+/* SYM_L_* -- linkage of symbols */
+#define SYM_L_GLOBAL(name)			.globl name
+#define SYM_L_LOCAL(name)			/* nothing */
+
+#define ALIGN __ALIGN
+
+/* === generic annotations === */
+
+/* SYM_ENTRY -- use only if you have to for non-paired symbols */
+#ifndef SYM_ENTRY
+#define SYM_ENTRY(name, linkage, align...)		\
+	linkage(name) ASM_NL				\
+	align ASM_NL					\
+	name:
+#endif
+
+/* SYM_START -- use only if you have to */
+#ifndef SYM_START
+#define SYM_START(name, linkage, align...)		\
+	SYM_ENTRY(name, linkage, align)
+#endif
+
+/* SYM_END -- use only if you have to */
+#ifndef SYM_END
+#define SYM_END(name, sym_type)				\
+	.type name sym_type ASM_NL			\
+	.size name, .-name
+#endif
+
+/*
+ * SYM_FUNC_START_ALIAS -- use where there are two global names for one
+ * function
+ */
+#ifndef SYM_FUNC_START_ALIAS
+#define SYM_FUNC_START_ALIAS(name)			\
+	SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN)
+#endif
+
+/* SYM_FUNC_START -- use for global functions */
+#ifndef SYM_FUNC_START
+/*
+ * The same as SYM_FUNC_START_ALIAS, but we will need to distinguish these two
+ * later.
+ */
+#define SYM_FUNC_START(name)				\
+	SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN)
+#endif
+
+/* SYM_FUNC_START_LOCAL -- use for local functions */
+#ifndef SYM_FUNC_START_LOCAL
+/* the same as SYM_FUNC_START_LOCAL_ALIAS, see comment near SYM_FUNC_START */
+#define SYM_FUNC_START_LOCAL(name)			\
+	SYM_START(name, SYM_L_LOCAL, SYM_A_ALIGN)
+#endif
+
+/* SYM_FUNC_END_ALIAS -- the end of LOCAL_ALIASed or ALIASed function */
+#ifndef SYM_FUNC_END_ALIAS
+#define SYM_FUNC_END_ALIAS(name)			\
+	SYM_END(name, SYM_T_FUNC)
+#endif
+
+/*
+ * SYM_FUNC_END -- the end of SYM_FUNC_START_LOCAL, SYM_FUNC_START,
+ * SYM_FUNC_START_WEAK, ...
+ */
+#ifndef SYM_FUNC_END
+/* the same as SYM_FUNC_END_ALIAS, see comment near SYM_FUNC_START */
+#define SYM_FUNC_END(name)				\
+	SYM_END(name, SYM_T_FUNC)
+#endif
 
 #endif	/* PERF_LINUX_LINKAGE_H_ */