Re: [RFC PATCH] riscv: Implement HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS

From: Steven Rostedt
Date: Thu Mar 21 2024 - 10:47:26 EST


On Tue, 12 Mar 2024 13:42:28 +0000
Mark Rutland <mark.rutland@xxxxxxx> wrote:

> > It would be interesting to see how the per-call performance would
> > improve on x86 with CALL_OPS! ;-)
>
> Heh. ;)

But this would require adding -fpatchable-function-entry on x86, which
would increase the size of text, which could possibly have a performance
regression when tracing is disabled.

I'd have no problem if someone were to implement it, but there's a strict
requirement that it does not slow down the system when tracing is disabled.
As tracing is a second class citizen compared to the rest of the kernel.

-- Steve