From mboxrd@z Thu Jan 1 00:00:00 1970 From: daniel.lezcano@linaro.org (Daniel Lezcano) Date: Mon, 16 Jun 2014 10:52:12 +0200 Subject: [PATCH 1/3] clocksource: exynos_mct: Fix ftrace In-Reply-To: References: <1401903034-20074-1-git-send-email-dianders@chromium.org> <539E0D8E.9080706@linaro.org> Message-ID: <539EB03C.5080100@linaro.org> To: linux-arm-kernel@lists.infradead.org List-Id: linux-arm-kernel.lists.infradead.org On 06/16/2014 06:40 AM, Doug Anderson wrote: > Daniel, > > On Sun, Jun 15, 2014 at 2:18 PM, Daniel Lezcano > wrote: >> On 06/04/2014 07:30 PM, Doug Anderson wrote: >>> >>> In (93bfb76 clocksource: exynos_mct: register sched_clock callback) we >>> supported using the MCT as a scheduler clock. We properly marked >>> exynos4_read_sched_clock() as notrace. However, we then went and >>> called another function that _wasn't_ notrace. That means if you do: >>> >>> cd /sys/kernel/debug/tracing/ >>> echo function_graph > current_tracer >>> >>> You'll get a crash. >>> >>> Fix this (but still let other readers of the MCT be trace-enabled) by >>> adding an extra function. It's important to keep other users of MCT >>> traceable because the MCT is actually quite slow. >> >> >> >> Hi Doug, >> >> could you elaborate ? I don't get the 'because the MCT ... slow' > > Sorry, I was trying to avoid duplication in the series and it's more > obvious when you look at parts 2 and 3 of the series. ;) > > Doing the math (please correct any miscalculations) using the numbers > from the other patches: You can see that the existing code takes > 1323852 us for 1000000 gettimeofday in userspace. The fastest > implementation (just shaving to a 32-bit timer) gets us as fast as > ~1000000 us for 1000000 gettimeofday in userspace. > > From profiling, I believe that gettimeofday from userspace is about > 50% overhead (system call, multiplication, copies, etc) and about 50% > MCT read. That means that the fastest you can possibly do an MCT read > is in .5us or 500ns. > > I believe an A15 has something like 1 or 2 cycles per instruction. If > it were 2 cycles per instruction, it can execute a normal instruction > on a 2GHz machine in .5ns. That means we can execute 1000 normal > instructions in the time it takes to do a since MCT access. > > ...so I guess that's what I'd call slow. ;) What do you think? I > know that the MCT read shows up in whole system profiles of > gettimeofday. Hi Dough, thanks for the explanation. I still don't get why it is important to keep others users of mct traceable because it is quite slow ? May be it is what you explained here, but I miss the connection between 'the other users' <-> 'traceable' <-> 'because slow'. -- Linaro.org ? Open source software for ARM SoCs Follow Linaro: Facebook | Twitter | Blog