x86/lib/clear_page_64.S: Convert to ALTERNATIVE_2 macro

Move clear_page() up so that we can get 2-byte forward JMPs when
patching:

  apply_alternatives: feat: 3*32+16, old: (ffffffff8130adb0, len: 5), repl: (ffffffff81d0b859, len: 5)
  ffffffff8130adb0: alt_insn: 90 90 90 90 90
  recompute_jump: new_displ: 0x0000003e
  ffffffff81d0b859: rpl_insn: eb 3e 66 66 90

even though the compiler generated 5-byte JMPs which we padded with 5
NOPs.

Also, make the REP_GOOD version be the default as the majority of
machines set REP_GOOD. This way we get to save ourselves the JMP:

  old insn VA: 0xffffffff813038b0, CPU feat: X86_FEATURE_REP_GOOD, size: 5, padlen: 0
  clear_page:

  ffffffff813038b0 <clear_page>:
  ffffffff813038b0:       e9 0b 00 00 00          jmpq ffffffff813038c0
  repl insn: 0xffffffff81cf0e92, size: 0

  old insn VA: 0xffffffff813038b0, CPU feat: X86_FEATURE_ERMS, size: 5, padlen: 0
  clear_page:

  ffffffff813038b0 <clear_page>:
  ffffffff813038b0:       e9 0b 00 00 00          jmpq ffffffff813038c0
  repl insn: 0xffffffff81cf0e92, size: 5
   ffffffff81cf0e92:      e9 69 2a 61 ff          jmpq ffffffff81303900

  ffffffff813038b0 <clear_page>:
  ffffffff813038b0:       e9 69 2a 61 ff          jmpq ffffffff8091631e

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

1 files changed, 27 insertions, 39 deletions

diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S
index 38e57faefd71..e67e579c93bd 100644
--- a/arch/x86/lib/clear_page_64.S
+++ b/arch/x86/lib/clear_page_64.S
@@ -1,31 +1,35 @@
 #include <linux/linkage.h>
 #include <asm/dwarf2.h>
+#include <asm/cpufeature.h>
 #include <asm/alternative-asm.h>
 
 /*
- * Zero a page.         
- * rdi  page
- */                     
-ENTRY(clear_page_c)
+ * Most CPUs support enhanced REP MOVSB/STOSB instructions. It is
+ * recommended to use this when possible and we do use them by default.
+ * If enhanced REP MOVSB/STOSB is not available, try to use fast string.
+ * Otherwise, use original.
+ */
+
+/*
+ * Zero a page.
+ * %rdi - page
+ */
+ENTRY(clear_page)
         CFI_STARTPROC
+
+        ALTERNATIVE_2 "jmp clear_page_orig", "", X86_FEATURE_REP_GOOD, \
+                      "jmp clear_page_c_e", X86_FEATURE_ERMS
+
         movl $4096/8,%ecx
         xorl %eax,%eax
         rep stosq
         ret
         CFI_ENDPROC
-ENDPROC(clear_page_c)
+ENDPROC(clear_page)
 
-ENTRY(clear_page_c_e)
+ENTRY(clear_page_orig)
         CFI_STARTPROC
-        movl $4096,%ecx
-        xorl %eax,%eax
-        rep stosb
-        ret
-        CFI_ENDPROC
-ENDPROC(clear_page_c_e)
 
-ENTRY(clear_page)
-        CFI_STARTPROC
         xorl   %eax,%eax
         movl   $4096/64,%ecx
         .p2align 4
@@ -45,29 +49,13 @@ ENTRY(clear_page)
         nop
         ret
         CFI_ENDPROC
-.Lclear_page_end:
-ENDPROC(clear_page)
-
-        /*
-         * Some CPUs support enhanced REP MOVSB/STOSB instructions.
-         * It is recommended to use this when possible.
-         * If enhanced REP MOVSB/STOSB is not available, try to use fast string.
-         * Otherwise, use original function.
-         *
-         */
+ENDPROC(clear_page_orig)
 
-#include <asm/cpufeature.h>
-
-        .section .altinstr_replacement,"ax"
-1:      .byte 0xeb                                      /* jmp <disp8> */
-        .byte (clear_page_c - clear_page) - (2f - 1b)   /* offset */
-2:      .byte 0xeb                                      /* jmp <disp8> */
-        .byte (clear_page_c_e - clear_page) - (3f - 2b) /* offset */
-3:
-        .previous
-        .section .altinstructions,"a"
-        altinstruction_entry clear_page,1b,X86_FEATURE_REP_GOOD,\
-                             .Lclear_page_end-clear_page, 2b-1b, 0
-        altinstruction_entry clear_page,2b,X86_FEATURE_ERMS,   \
-                             .Lclear_page_end-clear_page,3b-2b, 0
-        .previous
+ENTRY(clear_page_c_e)
+        CFI_STARTPROC
+        movl $4096,%ecx
+        xorl %eax,%eax
+        rep stosb
+        ret
+        CFI_ENDPROC
+ENDPROC(clear_page_c_e)