x86/lib/memset_64.S: Convert to ALTERNATIVE_2 macro

Make alternatives replace single JMPs instead of whole memset functions,
thus decreasing the amount of instructions copied during patching time
at boot.

While at it, make it use the REP_GOOD version by default which means
alternatives NOP out the JMP to the other versions, as REP_GOOD is set
by default on the majority of relevant x86 processors.

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

diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S
index f6153c1cdddc497728a598abf7e665c2623a05e9..93118fb239762ba78efd754d20a756aed0221411 100644 (file)
--- a/arch/x86/lib/memset_64.S
+++ b/arch/x86/lib/memset_64.S
@@ -5,19 +5,30 @@
 #include <asm/cpufeature.h>
 #include <asm/alternative-asm.h>
 
+.weak memset
+
 /*
  * ISO C memset - set a memory block to a byte value. This function uses fast
  * string to get better performance than the original function. The code is
  * simpler and shorter than the orignal function as well.
- *     
+ *
  * rdi   destination
- * rsi   value (char) 
- * rdx   count (bytes) 
- * 
+ * rsi   value (char)
+ * rdx   count (bytes)
+ *
  * rax   original destination
- */    
-       .section .altinstr_replacement, "ax", @progbits
-.Lmemset_c:
+ */
+ENTRY(memset)
+ENTRY(__memset)
+       /*
+        * Some CPUs support enhanced REP MOVSB/STOSB feature. It is recommended
+        * to use it when possible. If not available, use fast string instructions.
+        *
+        * Otherwise, use original memset function.
+        */
+       ALTERNATIVE_2 "jmp memset_orig", "", X86_FEATURE_REP_GOOD, \
+                     "jmp memset_erms", X86_FEATURE_ERMS
+
        movq %rdi,%r9
        movq %rdx,%rcx
        andl $7,%edx
@@ -31,8 +42,8 @@
        rep stosb
        movq %r9,%rax
        ret
-.Lmemset_e:
-       .previous
+ENDPROC(memset)
+ENDPROC(__memset)
 
 /*
  * ISO C memset - set a memory block to a byte value. This function uses
@@ -45,21 +56,16 @@
  *
  * rax   original destination
  */
-       .section .altinstr_replacement, "ax", @progbits
-.Lmemset_c_e:
+ENTRY(memset_erms)
        movq %rdi,%r9
        movb %sil,%al
        movq %rdx,%rcx
        rep stosb
        movq %r9,%rax
        ret
-.Lmemset_e_e:
-       .previous
-
-.weak memset
+ENDPROC(memset_erms)
 
-ENTRY(memset)
-ENTRY(__memset)
+ENTRY(memset_orig)
        CFI_STARTPROC
        movq %rdi,%r10
 
@@ -134,23 +140,4 @@ ENTRY(__memset)
        jmp .Lafter_bad_alignment
 .Lfinal:
        CFI_ENDPROC
-ENDPROC(memset)
-ENDPROC(__memset)
-
-       /* Some CPUs support enhanced REP MOVSB/STOSB feature.
-        * It is recommended to use this when possible.
-        *
-        * If enhanced REP MOVSB/STOSB feature is not available, use fast string
-        * instructions.
-        *
-        * Otherwise, use original memset function.
-        *
-        * In .altinstructions section, ERMS feature is placed after REG_GOOD
-         * feature to implement the right patch order.
-        */
-       .section .altinstructions,"a"
-       altinstruction_entry __memset,.Lmemset_c,X86_FEATURE_REP_GOOD,\
-                            .Lfinal-__memset,.Lmemset_e-.Lmemset_c,0
-       altinstruction_entry __memset,.Lmemset_c_e,X86_FEATURE_ERMS, \
-                            .Lfinal-__memset,.Lmemset_e_e-.Lmemset_c_e,0
-       .previous
+ENDPROC(memset_orig)