Messages in this thread | | | Date | Fri, 31 Jan 2003 01:57:47 +0100 | From | Andrea Arcangeli <> | Subject | Re: frlock and barrier discussion |
| |
On Thu, Jan 30, 2003 at 04:41:20PM -0800, Richard Henderson wrote: > On Thu, Jan 30, 2003 at 02:52:19AM +0100, Andrea Arcangeli wrote: > > you're missing xtimensec is a write. > > Eh? xtimensec is a register.
then it's fine, the register will be flushed to ram eventually and it will be within the two wmb(), just write in the example also the line where the xtimensec ""register"" is flushed to ram and it will be in the right place
if the register isn't flushed to ram eventually, it will be discared and the whole critical section is a noop from the point of view of the other cpus and no wmb() or rmb() or mb() would be needed in the first place
Andrea - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
| |