On Mon, 2014-01-20 at 13:07 +0100, Peter Zijlstra wrote: > On Thu, Jan 16, 2014 at 04:08:16PM -0800, Tim Chen wrote: > > +/* > > + * We don't inline mcs_spin_lock() so that perf can correctly account for the > > + * time spent in this lock function. > > + */ > > +static noinline > > +void mcs_spin_lock(struct mcs_spinlock **lock, struct mcs_spinlock *node) > > But given a vmlinux with sufficient DWARFs in, the IP will resolve to a > .ista. symbol, no? I'm actually only renaming the mspin_lock code to mcs_spin_lock here and moving the code to header file. The noinline logic was in the original code. Later on when we move mcs_spin_lock to its own file and exporting the symbol, then I think this issue will be resolved. Tim -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@xxxxxxxxx. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>