From: Oliver O'Halloran <oohall@gmail.com>
Date: Thu, 6 Jul 2017 08:47:10 +0000 (+1000)
Subject: arch/ppc: Fix get_cpu_clock asm clobber list
X-Git-Tag: fio-3.1~31^2
X-Git-Url: https://git.kernel.dk/?a=commitdiff_plain;h=e8bf784a034fe73aeed99a3360e803af38728126;p=fio.git

arch/ppc: Fix get_cpu_clock asm clobber list

Mark condition register 0 (cr0) as being clobbered by the inline asm in
get_cpu_clock(). Not doing this results in strange behaviour due to GCC
optimising away some checking. For example e.g:

  $ ./fio examples/null.fio --output-format=json
  time     5500  cycles_start=8085227422910      <--- bad!
  {
    "fio version" : "fio-2.21-89-gb034",
    <snip>

The extra output is due to the flag checking in dprint being removed
at higher optimisation levels.

Signed-off-by: Oliver O'Halloran <oohall@gmail.com>
---

diff --git a/arch/arch-ppc.h b/arch/arch-ppc.h
index ba452b15..804d596a 100644
--- a/arch/arch-ppc.h
+++ b/arch/arch-ppc.h
@@ -62,7 +62,8 @@ static inline unsigned long long get_cpu_clock(void)
 		"	cmpwi %0,0;\n"
 		"	beq-  90b;\n"
 	: "=r" (rval)
-	: "i" (SPRN_TBRL));
+	: "i" (SPRN_TBRL)
+	: "cr0");
 
 	return rval;
 }