On Fri, Feb 24, 2017 at 10:21:50AM +0100, Jonas Bonn wrote: > On 02/24/2017 05:32 AM, Stafford Horne wrote: > > Originally openrisc spec 0 specified that r0 would be wired to ground. > > This is no longer the case. r0 is not guaranteed to be 0 at init, so we > > need to initialize it to 0 before using it. > > > > Also, if we are clearing r0 we cant use r0 to clear itself. Change the > > the CLEAR_GPR macro to use movhi for clearing. > > Use the Reported-by: tag here since you are taking the time to mention him > in the summary mail.
Right, added. Thanks. > Reported-by: Jakob... > > Signed-off-by: Stafford Horne <sho...@gmail.com> > > --- > > arch/openrisc/kernel/head.S | 5 ++++- > > 1 file changed, 4 insertions(+), 1 deletion(-) > > > > diff --git a/arch/openrisc/kernel/head.S b/arch/openrisc/kernel/head.S > > index 573e131..e8a1784 100644 > > --- a/arch/openrisc/kernel/head.S > > +++ b/arch/openrisc/kernel/head.S > > @@ -35,7 +35,7 @@ > > l.add rd,rd,rs > > #define CLEAR_GPR(gpr) \ > > - l.or gpr,r0,r0 > > + l.movhi gpr,0x0 > > #define LOAD_SYMBOL_2_GPR(gpr,symbol) \ > > l.movhi gpr,hi(symbol) ;\ > > @@ -443,6 +443,9 @@ _dispatch_do_ipage_fault: > > __HEAD > > .global _start > > _start: > > + /* Init r0 to zero as per spec */ > > + CLEAR_GPR(r0) > > + > > /* save kernel parameters */ > > l.or r25,r0,r3 /* pointer to fdt */ > >
