On Tue, 2011-05-17 at 23:42 +0200, Jiri Slaby wrote: > On 05/17/2011 10:47 PM, John Stultz wrote: > > +static noinline_for_stack > > I still fail to see why this should be slowed down by noinlining it. > Care to explain? Just that I was hesitant to change it without consensus and it follows the convention of other similarly called functions. > With my setup, the code below inlined will use 32 bytes of stack. The > same as %pK case. Uninlined it obviously eats "only" 8 bytes for IP. Maybe could we defer that discussion into a following patch, which maybe does a similar analysis on the other noinline_for_stack usage in that case? (And I may be dropping the whole series here in a bit, so more debate on it might be moot) thanks -john -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@xxxxxxxxxx For more info on Linux MM, see: http://www.linux-mm.org/ . Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/ Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>