x86/lib/copy_page_64.S: Use generic ALTERNATIVE macro

... instead of the semi-version with the spelled out sections.

What is more, make the REP_GOOD version be the default copy_page()
version as the majority of the relevant x86 CPUs do set
X86_FEATURE_REP_GOOD. Thus, copy_page gets compiled to:

ffffffff8130af80 <copy_page>:
ffffffff8130af80: e9 0b 00 00 00 jmpq ffffffff8130af90 <copy_page_regs>
ffffffff8130af85: b9 00 02 00 00 mov $0x200,%ecx
ffffffff8130af8a: f3 48 a5 rep movsq %ds:(%rsi),%es:(%rdi)
ffffffff8130af8d: c3 retq
ffffffff8130af8e: 66 90 xchg %ax,%ax

ffffffff8130af90 <copy_page_regs>:
...

and after the alternatives have run, the JMP to the old, unrolled
version gets NOPed out:

ffffffff8130af80 <copy_page>:
ffffffff8130af80: 66 66 90 xchg %ax,%ax
ffffffff8130af83: 66 90 xchg %ax,%ax
ffffffff8130af85: b9 00 02 00 00 mov $0x200,%ecx
ffffffff8130af8a: f3 48 a5 rep movsq %ds:(%rsi),%es:(%rdi)
ffffffff8130af8d: c3 retq

On modern uarches, those NOPs are cheaper than the unconditional JMP
previously.

Signed-off-by: Borislav Petkov <[e-mail]>

arch/x86/lib/copy_page_64.S

···
 
 #include <linux/linkage.h>
 #include <asm/dwarf2.h>
+#include <asm/cpufeature.h>
 #include <asm/alternative-asm.h>
 
+/*
+ * Some CPUs run faster using the string copy instructions (sane microcode).
+ * It is also a lot simpler. Use this when possible. But, don't use streaming
+ * copy unless the CPU indicates X86_FEATURE_REP_GOOD. Could vary the
+ * prefetch distance based on SMP/UP.
+ */
 	ALIGN
-copy_page_rep:
+ENTRY(copy_page)
 	CFI_STARTPROC
+	ALTERNATIVE "jmp copy_page_regs", "", X86_FEATURE_REP_GOOD
 	movl	$4096/8, %ecx
 	rep	movsq
 	ret
 	CFI_ENDPROC
-ENDPROC(copy_page_rep)
+ENDPROC(copy_page)
 
-/*
- *  Don't use streaming copy unless the CPU indicates X86_FEATURE_REP_GOOD.
- *  Could vary the prefetch distance based on SMP/UP.
-*/
-
-ENTRY(copy_page)
+ENTRY(copy_page_regs)
 	CFI_STARTPROC
 	subq	$2*8,	%rsp
 	CFI_ADJUST_CFA_OFFSET 2*8
···
 	addq	$2*8, %rsp
 	CFI_ADJUST_CFA_OFFSET -2*8
 	ret
-.Lcopy_page_end:
 	CFI_ENDPROC
-ENDPROC(copy_page)
-
-	/* Some CPUs run faster using the string copy instructions.
-	   It is also a lot simpler. Use this when possible */
-
-#include <asm/cpufeature.h>
-
-	.section .altinstr_replacement,"ax"
-1:	.byte 0xeb					/* jmp <disp8> */
-	.byte (copy_page_rep - copy_page) - (2f - 1b)	/* offset */
-2:
-	.previous
-	.section .altinstructions,"a"
-	altinstruction_entry copy_page, 1b, X86_FEATURE_REP_GOOD,	\
-		.Lcopy_page_end-copy_page, 2b-1b, 0
-	.previous
+ENDPROC(copy_page_regs)