On Mon, 9 Oct 2017 09:33:50 -0600 Jonathan Corbet <cor...@lwn.net> wrote:
> > Using ftrace to hook to functions > > ================================= > > > > Copyright 2017 VMware Inc. > > Author: Steven Rostedt <srost...@goodmis.org> > > License: The GNU Free Documentation License, Version 1.2 > > (dual licensed under the GPL v2) > > > > Written for: 4.14 > > Experience says that strings like this go obsolete in a hurry, so they > don't really reflect the state of the document. The git history tends to > be rather more reliable. And this document is about to become stale by 4.15 ;-) > > The ftrace FLAGS > > ================ > > > > The ftrace_ops flags are all defined and documented in > > include/linux/ftrace.h. > > Some of the flags are used for internal infrastructure of ftrace, but the > > ones that users should be aware of are the following: > > > > (All of these are prefixed with FTRACE_OPS_FL_) > > I hate to say it, but you'll reduce the cognitive load on the reader if you > just spell the flags out. > > > PER_CPU - When set, the callback can be enabled or disabled per cpu with the > > following functions: > > > > void ftrace_function_local_enable(struct ftrace_ops *ops); > > void ftrace_function_local_disable(struct ftrace_ops *ops); > > > > These two functions must be called with preemption disabled. > > s/per cpu/per-CPU/ > > More importantly, though, what does this actually mean? Presumably that > the callback is only called if the function is hit on an enabled CPU? It > seems you can only enable/disable the local CPU? Is the default state > enabled or disabled? Inquiring minds want to know. This may be removed by 4.15. Link: http://lkml.kernel.org/r/20171010130448.4goubbka7e4bg...@hirez.programming.kicks-ass.net -- Steve
