Adds the set-2038 test which sets the time to near-edge cases
like the start and end of the 32 bit epoch and checks that
time behaves properly. There is also a dangerous mode, which
lets the clock roll over past 2038 on 32bit systems, which
on some older kernels will cause system hangs.

Cc: Shuah Khan <shuahkh@osg.samsung.com>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: NJohn Stultz <john.stultz@linaro.org>
Tested-by: NPrarit Bhargava <prarit@redhat.com>
Signed-off-by: NShuah Khan <shuahkh@osg.samsung.com>

This patch adds the set-tai test which ensures the tai offset
can be set properly from adjtimex.

Cc: Shuah Khan <shuahkh@osg.samsung.com>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: NJohn Stultz <john.stultz@linaro.org>
Tested-by: NPrarit Bhargava <prarit@redhat.com>
Signed-off-by: NShuah Khan <shuahkh@osg.samsung.com>

This change adds the leapcrash test which tests to see if a
leapsecond deadlock which was observed from 2.6.26 to 3.3
is present on this system.

Cc: Shuah Khan <shuahkh@osg.samsung.com>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: NJohn Stultz <john.stultz@linaro.org>
Tested-by: NPrarit Bhargava <prarit@redhat.com>
Signed-off-by: NShuah Khan <shuahkh@osg.samsung.com>

This change adds the leap-a-day test which sets STA_INS and
STA_DEL each day to trigger leapseconds each day. It also
has a mode to jump the time to right before the end of the
day each iteration.

Cc: Shuah Khan <shuahkh@osg.samsung.com>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: NJohn Stultz <john.stultz@linaro.org>
Tested-by: NPrarit Bhargava <prarit@redhat.com>
Signed-off-by: NShuah Khan <shuahkh@osg.samsung.com>

Adds the clocksource-switch tests which continually switches the
current clocksource between all the available ones, watching for
any timekeeping inconsistencies.

Cc: Shuah Khan <shuahkh@osg.samsung.com>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: NJohn Stultz <john.stultz@linaro.org>
Tested-by: NPrarit Bhargava <prarit@redhat.com>
Signed-off-by: NShuah Khan <shuahkh@osg.samsung.com>

This change adds the skew_consistency test, which twists the
ADJ_FREQUENCY knob back and forth and watches for timekeeping
inconsistencies.

Cc: Shuah Khan <shuahkh@osg.samsung.com>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: NJohn Stultz <john.stultz@linaro.org>
Tested-by: NPrarit Bhargava <prarit@redhat.com>
Signed-off-by: NShuah Khan <shuahkh@osg.samsung.com>

This patch adds the change_skew test which validates the
adjtimex freq can be set to various values and then using
the inconsistency-check, raw_skew, and nanosleep tests
ensures time behaves properly.

Cc: Shuah Khan <shuahkh@osg.samsung.com>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: NJohn Stultz <john.stultz@linaro.org>
Tested-by: NPrarit Bhargava <prarit@redhat.com>
Signed-off-by: NShuah Khan <shuahkh@osg.samsung.com>

This adds the alarmtimer-suspend test from the timetests suite,
which tests that the alarmtimers wake the system up from suspend
shortly after the time they were set to fire.

Cc: Shuah Khan <shuahkh@osg.samsung.com>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: NJohn Stultz <john.stultz@linaro.org>
Tested-by: NPrarit Bhargava <prarit@redhat.com>
Signed-off-by: NShuah Khan <shuahkh@osg.samsung.com>

This adds a adjtimex validation test which checks the behavior
for a set of valida and invalid inputs. So far this only tests
ADJ_FREQUENCY, but hopefully will grow.

Cc: Shuah Khan <shuahkh@osg.samsung.com>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: NJohn Stultz <john.stultz@linaro.org>
Tested-by: NPrarit Bhargava <prarit@redhat.com>
Signed-off-by: NShuah Khan <shuahkh@osg.samsung.com>

Add test to validate mqueue timeout latency from the timetest suite

Cc: Shuah Khan <shuahkh@osg.samsung.com>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: NJohn Stultz <john.stultz@linaro.org>
Tested-by: NPrarit Bhargava <prarit@redhat.com>
Signed-off-by: NShuah Khan <shuahkh@osg.samsung.com>

Add the threaded time inconsistency test from the timetest suite.
This checks for time inconsistencies between cpus, usually associated
with clock skew as sometimes found w/ TSCs.

Cc: Shuah Khan <shuahkh@osg.samsung.com>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: NJohn Stultz <john.stultz@linaro.org>
Tested-by: NPrarit Bhargava <prarit@redhat.com>
Signed-off-by: NShuah Khan <shuahkh@osg.samsung.com>

Add my set-timer-lat test from the timetest suite. This
test checks the latency from set_timer and reports if
any are unreasonable (>40ms).

Cc: Shuah Khan <shuahkh@osg.samsung.com>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: NJohn Stultz <john.stultz@linaro.org>
Tested-by: NPrarit Bhargava <prarit@redhat.com>
Signed-off-by: NShuah Khan <shuahkh@osg.samsung.com>

This adds my clock skew estimation test from the timetest suite.
It measures the drift between CLOCK_MONOTONIC and CLOCK_MONOTONIC_RAW
and compares it with the current frequency value from adjtimex.

It sometimes can trigger false failures when ntpd isn't in a
steady state, but its a useful too when doing adjtimex testing.

Cc: Shuah Khan <shuahkh@osg.samsung.com>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: NJohn Stultz <john.stultz@linaro.org>
Tested-by: NPrarit Bhargava <prarit@redhat.com>
Signed-off-by: NShuah Khan <shuahkh@osg.samsung.com>

Adds my nanosleep latency test from the timetest suite.
This checks to make sure we don't see "unreasonable"
latencies (> 40ms) when calling nanosleep.

Cc: Shuah Khan <shuahkh@osg.samsung.com>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: NJohn Stultz <john.stultz@linaro.org>
Tested-by: NPrarit Bhargava <prarit@redhat.com>
Signed-off-by: NShuah Khan <shuahkh@osg.samsung.com>

This adds my inconsistency-test from my timetests suite,
which checks for (single threaded) time inconsistencies
across the various clockids.

Cc: Shuah Khan <shuahkh@osg.samsung.com>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: NJohn Stultz <john.stultz@linaro.org>
Tested-by: NPrarit Bhargava <prarit@redhat.com>
Signed-off-by: NShuah Khan <shuahkh@osg.samsung.com>

Add my basic nanosleep test from my timetest suite.
This test validates that nanosleep doesn't return early
against a number of clockids.

Cc: Shuah Khan <shuahkh@osg.samsung.com>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: NJohn Stultz <john.stultz@linaro.org>
Tested-by: NPrarit Bhargava <prarit@redhat.com>
Signed-off-by: NShuah Khan <shuahkh@osg.samsung.com>

The posix_timers.c test has a loop that tries to keep it in
kernel space, repeatedly calling brk(). However, it doesn't
check the return value, which causes warnings.

This patch adds a err value which captures the return value
and modifies the test so it will quit if a failure occurs.

Cc: Shuah Khan <shuahkh@osg.samsung.com>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: NJohn Stultz <john.stultz@linaro.org>
Tested-by: NPrarit Bhargava <prarit@redhat.com>
Signed-off-by: NShuah Khan <shuahkh@osg.samsung.com>

Try to streamline the makefile so its easier to add timer/timekeeping
tests.

Also adds support for the CROSS_COMPILE variable.

Cc: Shuah Khan <shuahkh@osg.samsung.com>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: NJohn Stultz <john.stultz@linaro.org>
Tested-by: NPrarit Bhargava <prarit@redhat.com>
Signed-off-by: NShuah Khan <shuahkh@osg.samsung.com>

gcc complains about the 'cols' variable being unused. This is
unavoidable, given the ncurses getmaxyx() macro-based API, which wants
to assign to a variable directly, even when we're not going to use it.

Warning:

    gcc -O1 -Wall -Wshadow -W -Wformat -Wimplicit-function-declaration -Wimplicit-int -fstack-protector -D VERSION=\"1.0\"   -c -o tui.o tui.c
    tui.c: In function ‘show_dialogue’:
    tui.c:288:12: warning: variable ‘cols’ set but not used [-Wunused-but-set-variable]
      int rows, cols;
                ^

So, add a hack to get rid of that warning.
Signed-off-by: NBrian Norris <computersforpeace@gmail.com>
Acked-by: NJacob Pan <jacob.jun.pan@linux.intel.com>
Reviewed-by: NFlorian Fainelli <f.fainelli@gmail.com>
Signed-off-by: NZhang Rui <rui.zhang@intel.com>

Some distros (e.g., Arch Linux) don't package the tinfo library
separately from ncurses, so don't unconditionally include it. Instead,
use pkg-config.

The $(STATIC) ugliness is to handle the reported build case from commit
6b533269 ("tools/thermal: tmon: fix compilation errors when building
statically"), where a developer wants to be able to build with:

  make LDFLAGS=-static

which requires an additional pkg-config flag.

Finally, support a lowest common denominator fallback (-lpanel
-lncurses) for build systems that don't have pkg-config entries for
ncurses.
Signed-off-by: NBrian Norris <computersforpeace@gmail.com>
Acked-by: NJacob Pan <jacob.jun.pan@linux.intel.com>
Reviewed-by: NFlorian Fainelli <f.fainelli@gmail.com>
Signed-off-by: NZhang Rui <rui.zhang@intel.com>

We might want to prepare CFLAGS outside of this Makefile, so don't
overwrite its initial value.

Then, support $(CROSS_COMPILE), so we can use a cross-compile toolchain.
Signed-off-by: NBrian Norris <computersforpeace@gmail.com>
Acked-by: NJacob Pan <jacob.jun.pan@linux.intel.com>
Reviewed-by: NFlorian Fainelli <f.fainelli@gmail.com>
Signed-off-by: NZhang Rui <rui.zhang@intel.com>

Signed-off-by: NBrian Norris <computersforpeace@gmail.com>
Acked-by: NJacob Pan <jacob.jun.pan@linux.intel.com>
Reviewed-by: NFlorian Fainelli <f.fainelli@gmail.com>
Signed-off-by: NZhang Rui <rui.zhang@intel.com>

The number of rows in the dialog vary according to the number of cooling
devices. However, some of the windowing computations were assuming a
fixed number of rows. This computation is OK when we have between 4 and
9 cooling devices (and they wrap to the next column), but with fewer
devices, we end up printing off the end of the window.

This unifies the row computation into a single function and uses that
throughout the TUI code. This also accounts for increasing the number of
rows when there are more than 9 total cooling devices.
Signed-off-by: NBrian Norris <computersforpeace@gmail.com>
Acked-by: NJacob Pan <jacob.jun.pan@linux.intel.com>
Reviewed-by: NFlorian Fainelli <f.fainelli@gmail.com>
Signed-off-by: NZhang Rui <rui.zhang@intel.com>

We can use the ncurses API to get the number of rows.
Signed-off-by: NBrian Norris <computersforpeace@gmail.com>
Acked-by: NJacob Pan <jacob.jun.pan@linux.intel.com>
Reviewed-by: NFlorian Fainelli <f.fainelli@gmail.com>
Signed-off-by: NZhang Rui <rui.zhang@intel.com>

Signed-off-by: NBrian Norris <computersforpeace@gmail.com>
Acked-by: NJacob Pan <jacob.jun.pan@linux.intel.com>
Reviewed-by: NFlorian Fainelli <f.fainelli@gmail.com>
Signed-off-by: NZhang Rui <rui.zhang@intel.com>

If we launch in daemon mode (--daemon), we don't have the ncurses UI,
but we might want to set the target temperature still. For example,
someone might stick the following in their boot script:

  tmon --control intel_powerclamp --target-temp 90 --log --daemon

This would turn on CPU idle injection when we're around 90 degrees
celsius, and would log temperature and throttling info to
/var/tmp/tmon.log.
Signed-off-by: NBrian Norris <computersforpeace@gmail.com>
Acked-by: NJacob Pan <jacob.jun.pan@linux.intel.com>
Reviewed-by: NFlorian Fainelli <f.fainelli@gmail.com>
Signed-off-by: NZhang Rui <rui.zhang@intel.com>

The recent build changes cause perf to not compile for sparc64 since the
arch/sparc64/Build file does not exist:

/home/dahern/kernels/linux.git/tools/build/Makefile.build:40: arch/sparc64/Build: No such file or directory

Fix by converting the sparc64 RAW_ARCH to sparc ARCH -- similar to what
is done for x86_64.
Signed-off-by: NDavid Ahern <david.ahern@oracle.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/1424306222-96843-1-git-send-email-david.ahern@oracle.comSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>

4886f2ca added an arm-64 check, but the EM_AARCH64 macro is not
defined in older releases (e.g., RHEL6). Define if it is not defined.
Signed-off-by: NDavid Ahern <david.ahern@oracle.com>
Cc: Victor Kamensky <victor.kamensky@linaro.org>
Link: http://lkml.kernel.org/r/1424306017-96797-1-git-send-email-david.ahern@oracle.comSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>

perf-top is terminating due to SIGBUS on sparc64. git bisect points to:

    commit 82396986
    Author: Arnaldo Carvalho de Melo <acme@redhat.com>
    Date:   Mon Sep 8 13:26:35 2014 -0300

        perf evlist: Refcount mmaps

        We need to know how many fds are using a perf mmap via
        PERF_EVENT_IOC_SET_OUTPUT, so that we can know when to ditch an mmap,
        refcount it.

This commit added 'int refcnt' to struct perf_mmap and the addition makes the
event_copy element no longer 8-byte aligned.

Fix by adding __attribute__((aligned(8))) to the event_copy struct
member.
Signed-off-by: NDavid Ahern <david.ahern@oracle.com>
Link: http://lkml.kernel.org/r/1424304198-92028-1-git-send-email-david.ahern@oracle.com
[ Switched from 'int pad;' to using __attribute__, David tested/acked that ]
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>

Commit f6edb53c converted the probe to
a CPU wide event first (pid == -1). For kernels that do not support
the PERF_FLAG_FD_CLOEXEC flag the probe fails with EINVAL. Since this
errno is not handled pid is not reset to 0 and the subsequent use of
pid = -1 as an argument brings in an additional failure path if
perf_event_paranoid > 0:

$ perf record -- sleep 1
perf_event_open(..., 0) failed unexpectedly with error 13 (Permission denied)
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.007 MB /tmp/perf.data (11 samples) ]

Also, ensure the fd of the confirmation check is closed and comment why
pid = -1 is used.

Needs to go to 3.18 stable tree as well.
Signed-off-by: NAdrian Hunter <adrian.hunter@intel.com>
Based-on-patch-by: NDavid Ahern <david.ahern@oracle.com>
Acked-by: NDavid Ahern <david.ahern@oracle.com>
Cc: David Ahern <dsahern@gmail.com>
Link: http://lkml.kernel.org/r/54EC610C.8000403@intel.com
Cc: stable@vger.kernel.org  # v3.18+
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>

Feature detection for pthread_attr_setaffinity_np was failing, producing
this error:

  In file included from bench/futex-hash.c:17:0:
  bench/futex.h:73:19: error: conflicting types for ‘pthread_attr_setaffinity_np’
   static inline int pthread_attr_setaffinity_np(pthread_attr_t *attr,
                   ^
  In file included from bench/futex.h:72:0,
                   from bench/futex-hash.c:17:
  /usr/include/pthread.h:407:12: note: previous declaration of ‘pthread_attr_setaffinity_np’ was here
   extern int pthread_attr_setaffinity_np (pthread_attr_t *__attr,
            ^
  make[3]: *** [bench/futex-hash.o] Error 1
  make[2]: *** [bench] Error 2
  make[2]: *** Waiting for unfinished jobs....

  This was because compiling test-pthread-attr-setaffinity-np.c
  failed due to the function arguments:

  test-pthread-attr-setaffinity-np.c: In function ‘main’:
  test-pthread-attr-setaffinity-np.c:11:2: warning: null argument where non-null required (argument 3) [-Wnonnull]
    ret = pthread_attr_setaffinity_np(&thread_attr, 0, NULL);
    ^
  So fix the arguments.
Signed-off-by: NAdrian Hunter <adrian.hunter@intel.com>
Tested-by: NStephane Eranian <eranian@google.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/1424774766-24194-1-git-send-email-adrian.hunter@intel.comSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>

The man page for pthread_attr_set_affinity_np states that _GNU_SOURCE
must be defined before pthread.h is included in order to get the proper
function declaration.  Define this in the Makefile.

Without this defined, the feature check fails on a Fedora system with
gcc5 and then the perf build later fails with conflicting prototypes for
the function.
Signed-off-by: NJosh Boyer <jwboyer@fedoraproject.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Vineet Gupta <Vineet.Gupta1@synopsys.com>
Link: http://lkml.kernel.org/r/20150211162404.GA15522@hansolo.redhat.comSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>

This was causing the destination instead of the source to be filled.  As
a result, the source was typically all mapped to one zero page, and
hence very cacheable.
Signed-off-by: NBruce Merry <bmerry@ska.ac.za>
Acked-by: NIngo Molnar <mingo@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20150115092022.GA11292@krytonSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>

Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>

Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>

Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>

This is from all the non-PCI parts of the spec.
Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>

We were activating them with the virtqueues, and that's not allowed.
Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>

Linux doesn't generate these, but it's perfectly valid according to
a close reading of the spec.  I opened virtio spec bug VIRTIO-134 to
make this clearer there, too.
Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>

As a demonstration, the lguest launcher is pretty strict, trying to
catch badly behaved drivers.  Document this precisely.

A good implementation would *NOT* crash the guest when these happened!
Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>