Messages in this thread Patch in this message | | | Date | Fri, 04 Oct 2013 21:31:22 +0300 | From | Adrian Hunter <> | Subject | Re: [tip:perf/core] perf/x86: Clean up cap_user_time* setting |
| |
On 4/10/2013 8:31 p.m., tip-bot for Peter Zijlstra wrote: > Commit-ID: d8b11a0cbd1c66ce283eb9dabe0498dfa6483f32 > Gitweb: http://git.kernel.org/tip/d8b11a0cbd1c66ce283eb9dabe0498dfa6483f32 > Author: Peter Zijlstra <peterz@infradead.org> > AuthorDate: Thu, 3 Oct 2013 16:00:14 +0200 > Committer: Ingo Molnar <mingo@kernel.org> > CommitDate: Fri, 4 Oct 2013 09:58:55 +0200 > > perf/x86: Clean up cap_user_time* setting > > Currently the cap_user_time_zero capability has different tests than > cap_user_time; even though they expose the exact same data. > > Switch from CONSTANT && NONSTOP to sched_clock_stable to also deal > with multi cabinet machines and drop the tsc_disabled() check.. non of > this will work sanely without tsc anyway.
Unfortunately in the case that TSC is disabled, sched_clock is still reported as stable, which means removing the tsc_disabled() check breaks the capability bit. e.g.
$ dmesg | grep -i TSC [ 0.000000] Command line: BOOT_IMAGE=/boot/vmlinuz-3.11.0+ root=UUID=f1b4c71a-15aa-41a6-8898-cdde49966bce ro ignore_loglevel earlyprintk=ttyS0 console=ttyS0,115200n8 no_console_suspend notsc=1 sched_debug=1 [ 0.000000] Kernel command line: BOOT_IMAGE=/boot/vmlinuz-3.11.0+ root=UUID=f1b4c71a-15aa-41a6-8898-cdde49966bce ro ignore_loglevel earlyprintk=ttyS0 console=ttyS0,115200n8 no_console_suspend notsc=1 sched_debug=1 [ 0.000000] tsc: Kernel compiled with CONFIG_X86_TSC, cannot disable TSC completely [ 0.000000] tsc: Fast TSC calibration using PIT [ 0.004000] tsc: Detected 2594.166 MHz processor [ 0.224000] TSC deadline timer enabled $ cat /proc/sched_debug | grep sched_clock_stable sched_clock_stable : 1
> > Signed-off-by: Peter Zijlstra <peterz@infradead.org> > Link: http://lkml.kernel.org/n/tip-nmgn0j0muo1r4c94vlfh23xy@git.kernel.org > Signed-off-by: Ingo Molnar <mingo@kernel.org> > --- > arch/x86/kernel/cpu/perf_event.c | 11 +++-------- > 1 file changed, 3 insertions(+), 8 deletions(-) > > diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c > index 897783b..9d84491 100644 > --- a/arch/x86/kernel/cpu/perf_event.c > +++ b/arch/x86/kernel/cpu/perf_event.c > @@ -1888,10 +1888,7 @@ void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now) > userpg->cap_user_rdpmc = x86_pmu.attr_rdpmc; > userpg->pmc_width = x86_pmu.cntval_bits; > > - if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) > - return; > - > - if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC)) > + if (!sched_clock_stable) > return; > > userpg->cap_user_time = 1; > @@ -1899,10 +1896,8 @@ void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now) > userpg->time_shift = CYC2NS_SCALE_FACTOR; > userpg->time_offset = this_cpu_read(cyc2ns_offset) - now; > > - if (sched_clock_stable && !check_tsc_disabled()) { > - userpg->cap_user_time_zero = 1; > - userpg->time_zero = this_cpu_read(cyc2ns_offset); > - } > + userpg->cap_user_time_zero = 1; > + userpg->time_zero = this_cpu_read(cyc2ns_offset); > } > > /* >
| |