linux/arch
Kan Liang d31fc13fdc perf/x86/intel: Fix event update for auto-reload
There is a bug when reading event->count with large PEBS enabled.

Here is an example:

  # ./read_count
  0x71f0
  0x122c0
  0x1000000001c54
  0x100000001257d
  0x200000000bdc5

In fixed period mode, the auto-reload mechanism could be enabled for
PEBS events, but the calculation of event->count does not take the
auto-reload values into account.

Anyone who reads event->count will get the wrong result, e.g x86_pmu_read().

This bug was introduced with the auto-reload mechanism enabled since
commit:

  851559e35f ("perf/x86/intel: Use the PEBS auto reload mechanism when possible")

Introduce intel_pmu_save_and_restart_reload() to calculate the
event->count only for auto-reload.

Since the counter increments a negative counter value and overflows on
the sign switch, giving the interval:

        [-period, 0]

the difference between two consequtive reads is:

 A) value2 - value1;
    when no overflows have happened in between,
 B) (0 - value1) + (value2 - (-period));
    when one overflow happened in between,
 C) (0 - value1) + (n - 1) * (period) + (value2 - (-period));
    when @n overflows happened in between.

Here A) is the obvious difference, B) is the extension to the discrete
interval, where the first term is to the top of the interval and the
second term is from the bottom of the next interval and C) the extension
to multiple intervals, where the middle term is the whole intervals
covered.

The equation for all cases is:

    value2 - value1 + n * period

Previously the event->count is updated right before the sample output.
But for case A, there is no PEBS record ready. It needs to be specially
handled.

Remove the auto-reload code from x86_perf_event_set_period() since
we'll not longer call that function in this case.

Based-on-code-from: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: acme@kernel.org
Fixes: 851559e35f ("perf/x86/intel: Use the PEBS auto reload mechanism when possible")
Link: http://lkml.kernel.org/r/1518474035-21006-2-git-send-email-kan.liang@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2018-03-09 08:22:19 +01:00
..
alpha locking/xchg/alpha: Fix xchg() and cmpxchg() memory ordering bugs 2018-02-23 08:38:16 +01:00
arc ARC fixes for 4.16-rc4 2018-03-01 14:32:23 -08:00
arm ARM: SoC fixes for 4.16 2018-02-28 16:11:04 -08:00
arm64 ARM: SoC fixes for 4.16 2018-02-28 16:11:04 -08:00
blackfin unify {de,}mangle_poll(), get rid of kernel-side POLL... 2018-02-11 14:37:22 -08:00
c6x The core framework has a handful of patches this time around, mostly due 2018-02-01 16:56:07 -08:00
cris bug.h: work around GCC PR82365 in BUG() 2018-02-21 15:35:43 -08:00
frv unify {de,}mangle_poll(), get rid of kernel-side POLL... 2018-02-11 14:37:22 -08:00
h8300 The core framework has a handful of patches this time around, mostly due 2018-02-01 16:56:07 -08:00
hexagon The core framework has a handful of patches this time around, mostly due 2018-02-01 16:56:07 -08:00
ia64 bug.h: work around GCC PR82365 in BUG() 2018-02-21 15:35:43 -08:00
m32r The core framework has a handful of patches this time around, mostly due 2018-02-01 16:56:07 -08:00
m68k bug.h: work around GCC PR82365 in BUG() 2018-02-21 15:35:43 -08:00
metag The core framework has a handful of patches this time around, mostly due 2018-02-01 16:56:07 -08:00
microblaze Microblaze patches for 4.16-rc1 2018-02-02 09:48:36 -08:00
mips MIPS fixes for 4.16-rc3 2018-02-23 14:59:29 -08:00
mn10300 The core framework has a handful of patches this time around, mostly due 2018-02-01 16:56:07 -08:00
nios2 nios2 update for v4.16-rc1 2018-02-11 13:52:32 -08:00
openrisc The core framework has a handful of patches this time around, mostly due 2018-02-01 16:56:07 -08:00
parisc Merge branch 'parisc-4.16-1' of git://git.kernel.org/pub/scm/linux/kernel/git/deller/parisc-linux 2018-03-02 13:05:20 -08:00
powerpc Merge branch 'core-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 2018-02-25 16:27:51 -08:00
riscv riscv/barrier: Define __smp_{mb,rmb,wmb} 2018-02-26 08:44:50 -08:00
s390 KVM: s390: provide only a single function for setting the tod (fix SCK) 2018-02-20 20:51:28 +00:00
score arch/score/kernel/setup.c: combine two seq_printf() calls into one call in show_cpuinfo() 2018-02-06 18:32:47 -08:00
sh sh: fix build error for empty CONFIG_BUILTIN_DTB_SOURCE 2018-03-02 09:20:55 +09:00
sparc bug.h: work around GCC PR82365 in BUG() 2018-02-21 15:35:43 -08:00
tile The core framework has a handful of patches this time around, mostly due 2018-02-01 16:56:07 -08:00
um mconsole_proc(): don't mess with file->f_pos 2018-02-09 19:28:01 -08:00
unicore32 lib: optimize cpumask_next_and() 2018-02-06 18:32:44 -08:00
x86 perf/x86/intel: Fix event update for auto-reload 2018-03-09 08:22:19 +01:00
xtensa xtensa: support DMA buffers in high memory 2018-02-16 19:19:54 -08:00
.gitignore
Kconfig Makefile: introduce CONFIG_CC_STACKPROTECTOR_AUTO 2018-02-06 18:32:44 -08:00