On Fri, Feb 27, 2015 at 03:29:38PM -0500, Pranith Kumar wrote:

On Fri, Feb 27, 2015 at 3:17 PM, Pranith Kumar [off-list ref] wrote:

quoted

On Fri, Feb 27, 2015 at 3:15 PM, Will Deacon [off-list ref] wrote:

quoted

quoted

@@ -166,11 +166,11 @@ static inline int __cmpxchg_double(volatile void *ptr1, volatile void *ptr2,
              VM_BUG_ON((unsigned long *)ptr2 - (unsigned long *)ptr1 != 1);
              do {
                      asm volatile("// __cmpxchg_double8\n"
+                     "       mov     %w0, #0\n"
                      "       ldxp    %0, %1, %2\n"

Seriously, you might want to test this before you mindlessly make changes to
low-level synchronisation code. Not only is the change completely unnecessary
but it is actively harmful.

Oops, I apologize for this. I should have looked more closely. It is
wrong to do this in cmpxchg_double(). What about the other cases?

I tried looking closely on what might be the problem here. I am
waiting on a HiKey arm64 board and I agree I should not send in
changes without running/testing them first.

Could you please explain (for educational purposes) why you think this
change is harmful?

Do you mean the cmpxchg_double() change? Becuase %w0 and %0 is the same
physical register. You set it to 0 and immediately override it with
ldxp.

-- 
Catalin