Cyrill Gorcunov [Fri, 14 May 2010 19:08:15 +0000 (23:08 +0400)]
x86, perf: P4 PMU - fix counters management logic
Jaswinder reported this #GP:
|
| Message from syslogd@ht at May 14 09:39:32 ...
| kernel:[ 314.908612] EIP: [<c100ccca>]
| x86_perf_event_set_period+0x19d/0x1b2 SS:ESP 0068:edac3d70
|
Ming has narrowed it down to a comparision issue
between arguments with different sizes and
signs. As result event index reached a wrong
value which in turn led to a GP fault.
At the same time it was found that p4_next_cntr
has broken logic and should return the counter
index only if it was not yet borrowed for
another event.
Reported-by: Jaswinder Singh Rajput <jaswinderlinux@gmail.com> Reported-by: Lin Ming <ming.m.lin@intel.com> Bisected-by: Lin Ming <ming.m.lin@intel.com> Tested-by: Jaswinder Singh Rajput <jaswinderlinux@gmail.com> Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org> CC: Peter Zijlstra <a.p.zijlstra@chello.nl> CC: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <20100514190815.GG13509@lenovo> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Steven Rostedt [Fri, 14 May 2010 14:19:13 +0000 (10:19 -0400)]
tracing: Comment the use of event_mutex with trace event flags
The flags variable is protected by the event_mutex when modifying,
but the event_mutex is not held when reading the variable.
This is due to the fact that the reads occur in critical sections where
taking a mutex (or even a spinlock) is not wanted.
But the two flags that exist (enable and filter_active) have the code
written as such to handle the reads to not need a lock.
The enable flag is used just to know if the event is enabled or not
and its use is always under the event_mutex. Whether or not the event
is actually enabled is really determined by the tracepoint being
registered. The flag is just a way to let the code know if the tracepoint
is registered.
The filter_active is different. It is read without the lock. If it
is set, then the event probes jump to the filter code. There can be a
slight mismatch between filters available and filter_active. If the flag is
set but no filters are available, the code safely jumps to a filter nop.
If the flag is not set and the filters are available, then the filters
are skipped. This is acceptable since filters are usually set before
tracing or they are set by humans, which would not notice the slight
delay that this causes.
v2: Fixed typo: "cacheing" -> "caching"
Reported-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Tom Zanussi <tzanussi@gmail.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
After we use the filters to zoom into DSOs or threads, we can use <-
(left arrow) to zoom out from the last filter applied.
It is still possible to zoom out of order by using the popup menu.
With this we now have the zoom out operation on the browsing fast path,
by allowing fast navigation using just the four arrors and the enter key
to expand collapse callchains.
Suggested-by: Ingo Molnar <mingo@elte.hu> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Tom Zanussi <tzanussi@gmail.com>
LKML-Reference: <new-submission> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Li Zefan [Mon, 10 May 2010 03:23:00 +0000 (11:23 +0800)]
tracing: Fix function declarations if !CONFIG_STACKTRACE
ftrace_trace_stack() and frace_trace_userstacke() take a
struct ring_buffer argument, not struct trace_array. Commit e77405ad("tracing: pass around ring buffer instead of tracer")
made this change.
Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>
LKML-Reference: <4BE77C14.5010806@cn.fujitsu.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Steven Rostedt [Fri, 23 Apr 2010 15:12:36 +0000 (11:12 -0400)]
tracing: Combine event filter_active and enable into single flags field
The filter_active and enable both use an int (4 bytes each) to
set a single flag. We can save 4 bytes per event by combining the
two into a single integer.
The modification of both the enable and filter fields are done
under the event_mutex, so it is still safe to combine the two.
Note: Although Mathieu gave his Acked-by, he would like it documented
that the reads of flags are not protected by the mutex. The way the
code works, these reads will not break anything, but will have a
residual effect. Since this behavior is the same even before this
patch, describing this situation is left to another patch, as this
patch does not change the behavior, but just brought it to Mathieu's
attention.
v2: Updated the event trace self test to for this change.
Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Acked-by: Masami Hiramatsu <mhiramat@redhat.com> Acked-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Tom Zanussi <tzanussi@gmail.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Steven Rostedt [Fri, 23 Apr 2010 14:38:03 +0000 (10:38 -0400)]
tracing: Remove duplicate id information in event structure
Now that the trace_event structure is embedded in the ftrace_event_call
structure, there is no need for the ftrace_event_call id field.
The id field is the same as the trace_event type field.
Removing the id and re-arranging the structure brings down the tracepoint
footprint by another 5K.
Steven Rostedt [Fri, 23 Apr 2010 14:00:22 +0000 (10:00 -0400)]
tracing: Move print functions into event class
Currently, every event has its own trace_event structure. This is
fine since the structure is needed anyway. But the print function
structure (trace_event_functions) is now separate. Since the output
of the trace event is done by the class (with the exception of events
defined by DEFINE_EVENT_PRINT), it makes sense to have the class
define the print functions that all events in the class can use.
This makes a bigger deal with the syscall events since all syscall events
use the same class. The savings here is another 30K.
To accomplish this, and to let the class know what event is being
printed, the event structure is embedded in the ftrace_event_call
structure. This should not be an issues since the event structure
was created for each event anyway.
Steven Rostedt [Thu, 22 Apr 2010 22:46:14 +0000 (18:46 -0400)]
tracing: Allow events to share their print functions
Multiple events may use the same method to print their data.
Instead of having all events have a pointer to their print funtions,
the trace_event structure now points to a trace_event_functions structure
that will hold the way to print ouf the event.
The event itself is now passed to the print function to let the print
function know what kind of event it should print.
This opens the door to consolidating the way several events print
their output.
Steven Rostedt [Thu, 22 Apr 2010 15:46:44 +0000 (11:46 -0400)]
tracing: Move raw_init from events to class
The raw_init function pointer in the event is used to initialize
various kinds of events. The type of initialization needed is usually
classed to the kind of event it is.
Two events with the same class will always have the same initialization
function, so it makes sense to move this to the class structure.
Perhaps even making a special system structure would work since
the initialization is the same for all events within a system.
But since there's no system structure (yet), this will just move it
to the class.
The text grew very slightly, but this is a constant growth that happened
with the changing of the C files that call the init code.
The bigger savings is the data which will be saved the more events share
a class.
Steven Rostedt [Thu, 22 Apr 2010 14:35:55 +0000 (10:35 -0400)]
tracing: Move fields from event to class structure
Move the defined fields from the event to the class structure.
Since the fields of the event are defined by the class they belong
to, it makes sense to have the class hold the information instead
of the individual events. The events of the same class would just
hold duplicate information.
After this change the size of the kernel dropped another 3K:
Although the text increased, this was mainly due to the C files
having to adapt to the change. This is a constant increase, where
new tracepoints will not increase the Text. But the big drop is
in the data size (as well as needed allocations to hold the fields).
This will give even more savings as more tracepoints are created.
Note, if just TRACE_EVENT()s are used and not DECLARE_EVENT_CLASS()
with several DEFINE_EVENT()s, then the savings will be lost. But
we are pushing developers to consolidate events with DEFINE_EVENT()
so this should not be an issue.
The kprobes define a unique class to every new event, but are dynamic
so it should not be a issue.
The syscalls however have a single class but the fields for the individual
events are different. The syscalls use a metadata to define the
fields. I moved the fields list from the event to the metadata and
added a "get_fields()" function to the class. This function is used
to find the fields. For normal events and kprobes, get_fields() just
returns a pointer to the fields list_head in the class. For syscall
events, it returns the fields list_head in the metadata for the event.
v2: Fixed the syscall fields. The syscall metadata needs a list
of fields for both enter and exit.
Acked-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Acked-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Steven Rostedt [Wed, 21 Apr 2010 16:27:06 +0000 (12:27 -0400)]
tracing: Remove per event trace registering
This patch removes the register functions of TRACE_EVENT() to enable
and disable tracepoints. The registering of a event is now down
directly in the trace_events.c file. The tracepoint_probe_register()
is now called directly.
The prototypes are no longer type checked, but this should not be
an issue since the tracepoints are created automatically by the
macros. If a prototype is incorrect in the TRACE_EVENT() macro, then
other macros will catch it.
The trace_event_class structure now holds the probes to be called
by the callbacks. This removes needing to have each event have
a separate pointer for the probe.
To handle kprobes and syscalls, since they register probes in a
different manner, a "reg" field is added to the ftrace_event_class
structure. If the "reg" field is assigned, then it will be called for
enabling and disabling of the probe for either ftrace or perf. To let
the reg function know what is happening, a new enum (trace_reg) is
created that has the type of control that is needed.
With this new rework, the 82 kernel events and 618 syscall events
has their footprint dramatically lowered:
The size went from 6863829 to 6819176, that's a total of 44K
in savings. With tracepoints being continuously added, this is
critical that the footprint becomes minimal.
v5: Added #ifdef CONFIG_PERF_EVENTS around a reference to perf
specific structure in trace_events.c.
v4: Fixed trace self tests to check probe because regfunc no longer
exists.
v3: Updated to handle void *data in beginning of probe parameters.
Also added the tracepoint: check_trace_callback_type_##call().
v2: Changed the callback probes to pass void * and typecast the
value within the function.
Number of samples is meaningless after we switched to auto-freq, so
report the number of events, i.e. not the sum of the different periods,
but the number PERF_RECORD_SAMPLE emitted by the kernel.
While doing this I noticed that naming "count" to the sum of all the
event periods can be confusing, so rename it to .period, just like in
struct sample.data, so that we become more consistent.
This helps with the next step, that was to record in struct hist_entry
the number of sample events for each instance, we need that because we
use it to generate the number of events when applying filters to the
tree of hist entries like it is being done in the TUI report browser.
Suggested-by: Ingo Molnar <mingo@elte.hu> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Tom Zanussi <tzanussi@gmail.com>
LKML-Reference: <new-submission> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The events_stats.total field is too generic, rename it to .total_period,
and also add a comment explaining that it is the sum of all the .period
fields in samples, that is needed because we use auto-freq to avoid
sampling artifacts.
Ditto for events_stats.lost, that is the sum of all lost_event.lost
fields, i.e. the number of events the kernel dropped.
Looking at the users, builtin-sched.c can make use of these fields and
stop doing it again.
Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Tom Zanussi <tzanussi@gmail.com>
LKML-Reference: <new-submission> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The same callback can also be registered to the same tracepoint as long
as the data registered is different. Note, the data must also be used
to unregister the callback:
Again, this patch also increases the size of the kernel, but
lays the ground work for decreasing it.
v5: Fixed net/core/drop_monitor.c to handle these updates.
v4: Moved the DECLARE_TRACE() DECLARE_TRACE_NOARGS out of the
#ifdef CONFIG_TRACE_POINTS, since the two are the same in both
cases. The __DECLARE_TRACE() is what changes.
Thanks to Frederic Weisbecker for pointing this out.
v3: Made all register_* functions require data to be passed and
all callbacks to take a void * parameter as its first argument.
This makes the calling functions comply with C standards.
Also added more comments to the modifications of DECLARE_TRACE().
v2: Made the DECLARE_TRACE() have the ability to pass arguments
and added a new DECLARE_TRACE_NOARGS() for tracepoints that
do not need any arguments.
Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Acked-by: Masami Hiramatsu <mhiramat@redhat.com> Acked-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Neil Horman <nhorman@tuxdriver.com> Cc: David S. Miller <davem@davemloft.net> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
This check is meant to be used by tracepoint users which do a direct cast of
callbacks to (void *) for direct registration, thus bypassing the
register_trace_##name and unregister_trace_##name checks.
This permits to ensure that the callback type matches the function type at the
call site, but without generating any code.
Acked-by: Masami Hiramatsu <mhiramat@redhat.com> Acked-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
LKML-Reference: <20100430165959.GA25605@Krystal> CC: Ingo Molnar <mingo@elte.hu> CC: Andrew Morton <akpm@linux-foundation.org> CC: Thomas Gleixner <tglx@linutronix.de> CC: Peter Zijlstra <peterz@infradead.org> CC: Arnaldo Carvalho de Melo <acme@redhat.com> CC: Lai Jiangshan <laijs@cn.fujitsu.com> CC: Li Zefan <lizf@cn.fujitsu.com> CC: Christoph Hellwig <hch@lst.de> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Steven Rostedt [Tue, 20 Apr 2010 14:47:33 +0000 (10:47 -0400)]
tracing: Create class struct for events
This patch creates a ftrace_event_class struct that event structs point to.
This class struct will be made to hold information to modify the
events. Currently the class struct only holds the events system name.
This patch slightly increases the size, but this change lays the ground work
of other changes to make the footprint of tracepoints smaller.
With 82 standard tracepoints, and 618 system call tracepoints
(two tracepoints per syscall: enter and exit):
Stephane Eranian [Wed, 12 May 2010 08:40:01 +0000 (10:40 +0200)]
perf tools: change event inheritance logic in stat and record
By default, event inheritance across fork and pthread_create was on but the -i
option of stat and record, which enabled inheritance, led to believe it was off
by default.
This patch fixes this logic by inverting the meaning of the -i option. By
default inheritance is on whether you attach to a process (-p), a thread (-t)
or start a process. If you pass -i, then you turn off inheritance. Turning off
inheritance if you don't need it, helps limit perf resource usage as well.
The patch also fixes perf stat -t xxxx and perf record -t xxxx which did not
start the counters.
Acked-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: David S. Miller <davem@davemloft.net> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org>
LKML-Reference: <4bea9d2f.d60ce30a.0b5b.08e1@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
hist.c needs to include util.h so that it gets stdio.h
inclusion with __GNU_SOURCE defined.
Fixes:
util/hist.c: In function ‘hist_entry__parse_objdump_line’:
util/hist.c:931: erreur: implicit declaration of function ‘getline’
util/hist.c:931: erreur: nested extern declaration of ‘getline’
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <1273772836-11533-1-git-send-regression-fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cyrill Gorcunov [Wed, 12 May 2010 17:42:42 +0000 (21:42 +0400)]
x86, perf: P4 PMU -- use hash for p4_get_escr_idx()
Linear search over all p4 MSRs should be fine if only
we would not use it in events scheduling routine which
is pretty time critical. Lets use hashes. It should speed
scheduling up significantly.
v2: Steven proposed to use more gentle approach than issue
BUG on error, so we use WARN_ONCE now
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Lin Ming <ming.m.lin@intel.com>
LKML-Reference: <20100512174242.GA5190@lenovo> Signed-off-by: Ingo Molnar <mingo@elte.hu>
perf report: Librarize the annotation code and use it in the newt browser
Now we don't anymore use popen to run 'perf annotate' for the selected
symbol, instead we collect per address samplings when processing samples
in 'perf report' if we're using the newt browser, then we use this data
directly to do annotation.
Done this way we can actually traverse the objdump_line objects
directly, matching the addresses to the collected samples and colouring
them appropriately using lower level slang routines.
The new ui_browser class will be reused for the main, callchain aware,
histogram browser, when it will be made generic and don't assume that
the objects are always instances of the objdump_line class maintained
using list_heads.
Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Tom Zanussi <tzanussi@gmail.com>
LKML-Reference: <new-submission> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Initially this was just to be able to have a printf like method to
prepare the formatted string and then pass to newtPushHelpLine, but as
we already have for ui_progress, etc, its a step in identifying a
restricted, highlevel set of widgets we can then have implementations
for multiple widget sets (GTK, etc).
Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Tom Zanussi <tzanussi@gmail.com>
LKML-Reference: <new-submission> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Changli Gao [Fri, 7 May 2010 06:33:26 +0000 (14:33 +0800)]
sched, wait: Use wrapper functions
epoll should not touch flags in wait_queue_t. This patch introduces a new
function __add_wait_queue_exclusive(), for the users, who use wait queue as a
LIFO queue.
__add_wait_queue_tail_exclusive() is introduced too instead of
add_wait_queue_exclusive_locked(). remove_wait_queue_locked() is removed, as
it is a duplicate of __remove_wait_queue(), disliked by users, and with less
users.
Signed-off-by: Changli Gao <xiaosuo@gmail.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Paul Menage <menage@google.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Davide Libenzi <davidel@xmailserver.org> Cc: <containers@lists.linux-foundation.org>
LKML-Reference: <1273214006-2979-1-git-send-email-xiaosuo@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Kyle McMartin [Mon, 10 May 2010 20:43:35 +0000 (16:43 -0400)]
perf symbols: allow forcing use of cplus_demangle
For Fedora, I want to force perf to link against libiberty.a for
cplus_demangle, rather than libbfd.a for bfd_demangle due to licensing insanity
on binutils. (libiberty is LGPL2, libbfd is GPL3.)
If we just rely on autodetection, we'll end up with libbfd linked against us,
since they're both in binutils-static in the buildroot.
Masami Hiramatsu [Tue, 11 May 2010 04:59:53 +0000 (00:59 -0400)]
perf probe: Check older elfutils and set NO_DWARF
Check whether elfutils is older than 0.138 (from which version checking
routine has been introduced). And if so, set NO_DWARF because it is hard
to check the API dependency without version checking.
Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Reported-by: Robert Richter <robert.richter@amd.com> Cc: Robert Richter <robert.richter@amd.com> Cc: Ingo Molnar <mingo@elte.hu>
LKML-Reference: <20100511045953.9913.19485.stgit@localhost6.localdomain6> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Lin Ming [Sat, 8 May 2010 10:28:41 +0000 (20:28 +1000)]
perf, powerpc: Implement group scheduling transactional APIs
[paulus@samba.org: Set cpuhw->event[i]->hw.config in
power_pmu_commit_txn.]
Signed-off-by: Lin Ming <ming.m.lin@intel.com> Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <20100508102841.GA10650@brick.ozlabs.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Peter Zijlstra [Tue, 11 May 2010 09:51:53 +0000 (11:51 +0200)]
perf: Fix exit() vs PERF_FORMAT_GROUP
Both Stephane and Corey reported that PERF_FORMAT_GROUP didn't
work as expected if the task the counters were attached to quit
before the read() call.
The cause is that we unconditionally destroy the grouping when
we remove counters from their context. Fix this by splitting off
the group destroy from the list removal such that
perf_event_remove_from_context() does not do this and change
perf_event_release() to do so.
Tom Zanussi [Mon, 10 May 2010 04:46:54 +0000 (23:46 -0500)]
perf/trace/scripting: rwtop script cleanup
A couple of fixes for the rwtop script:
- printing the totals and clearing the hashes in the signal handler
eventually leads to various random and serious problems when running
the rwtop script continuously. Moving the print_totals() calls to
the event handlers solves that problem, and the event handlers are
invoked frequently enough that it doesn't affect the timeliness of
the output.
- Fix nuisance 'use of uninitialized value' warnings
Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu>
Message-Id: <1273466820-9330-4-git-send-email-tzanussi@gmail.com> Signed-off-by: Tom Zanussi <tzanussi@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
perf hist: Introduce hists class and move lots of methods to it
In cbbc79a we introduced support for multiple events by introducing a
new "event_stat_id" struct and then made several perf_session methods
receive a point to it instead of a pointer to perf_session, and kept the
event_stats and hists rb_tree in perf_session.
While working on the new newt based browser, I realised that it would be
better to introduce a new class, "hists" (short for "histograms"),
renaming the "event_stat_id" struct and the perf_session methods that
were really "hists" methods, as they manipulate only struct hists
members, not touching anything in the other perf_session members.
Other optimizations, such as calculating the maximum lenght of a symbol
name present in an hists instance will be possible as we add them,
avoiding a re-traversal just for finding that information.
The rationale for the name "hists" to replace "event_stat_id" is that we
may have multiple sets of hists for the same event_stat id, as, for
instance, the 'perf diff' tool has, so event stat id is not what
characterizes what this struct and the functions that manipulate it do.
Cc: Eric B Munson <ebmunson@us.ibm.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Tom Zanussi <tzanussi@gmail.com>
LKML-Reference: <new-submission> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
perf session: create_kernel_maps should use ->host_machine
Using machines__create_kernel_maps(..., HOST_KERNEL_ID) it would create
another machine instance for the host machine, and since 1f626bc we have
it out of the machines rb_tree.
Fix it by using machine__create_kernel_maps(&self->host_machine)
directly.
Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Tom Zanussi <tzanussi@gmail.com>
LKML-Reference: <new-submission> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Will show only the first two symbols where at least 0.5% of the samples
took place.
All the other symbols that don't fall outside these constraints will be
put together in the last entry, prefixed with "[...]" and the total
percentage for them.
Suggested-by: Arjan van de Ven <arjan@linux.intel.com> Acked-by: Arjan van de Ven <arjan@linux.intel.com> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Tom Zanussi <tzanussi@gmail.com>
LKML-Reference: <new-submission> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
perf session: Embed the host machine data on perf_session
We have just one host on a given session, and that is the most common
setup right now, so embed a ->host_machine struct machine instance
directly in the perf_session class, check if we're looking for it before
going to the rb_tree.
This also fixes a problem found when we try to process old perf.data
files where we didn't have MMAP events for the kernel and modules and
thus don't create the kernel maps, do it in event__preprocess_sample if
it wasn't already.
Reported-by: Ingo Molnar <mingo@elte.hu> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Zhang, Yanmin <yanmin_zhang@linux.intel.com>
LKML-Reference: <new-submission> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
perf symbols: Check if a struct machine instance was found
Which can happen when processing old files that had no fake kernel MMAP,
events.
That shouldn't result in perf_session__create_kernel_maps not being
called, this will be fixed in a followup patch, for now do these checks
to avoid segfaulting.
Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Tom Zanussi <tzanussi@gmail.com>
LKML-Reference: <new-submission> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Hitoshi Mitake [Sat, 8 May 2010 08:10:29 +0000 (17:10 +0900)]
perf lock: Drop "-a" option from cmd_record() default arguments set
This patch drops "-a" from the default arguments passed to
perf record by perf lock.
If a user wants to do a system wide record of lock events,
perf lock record -a <program> <argument> ...
is enough for this purpose.
This can reduce the size of the perf.data file.
% sudo ./perf lock record whoami
root
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.439 MB perf.data (~19170 samples) ]
% sudo ./perf lock record -a whoami # with -a option
root
[ perf record: Woken up 0 times to write data ]
[ perf record: Captured and wrote 48.962 MB perf.data (~2139197 samples) ]
ondemand: Make the iowait-is-busy time a sysfs tunable
Pavel Machek pointed out that not all CPUs have an efficient
idle at high frequency. Specifically, older Intel and various
AMD cpus would get a higher powerusage when copying files from
USB.
Mike Chan pointed out that the same is true for various ARM
chips as well.
Thomas Renninger suggested to make this a sysfs tunable with a
reasonable default.
This patch adds a sysfs tunable for the new behavior, and uses
a very simple function to determine a reasonable default,
depending on the CPU vendor/type.
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: Pavel Machek <pavel@ucw.cz> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: davej@redhat.com
LKML-Reference: <20100509082651.46914d04@infradead.org>
[ minor tidyup ] Signed-off-by: Ingo Molnar <mingo@elte.hu>
ondemand: Solve a big performance issue by counting IOWAIT time as busy
The ondemand cpufreq governor uses CPU busy time (e.g. not-idle
time) as a measure for scaling the CPU frequency up or down.
If the CPU is busy, the CPU frequency scales up, if it's idle,
the CPU frequency scales down. Effectively, it uses the CPU busy
time as proxy variable for the more nebulous "how critical is
performance right now" question.
This algorithm falls flat on its face in the light of workloads
where you're alternatingly disk and CPU bound, such as the ever
popular "git grep", but also things like startup of programs and
maildir using email clients... much to the chagarin of Andrew
Morton.
This patch changes the ondemand algorithm to count iowait time
as busy, not idle, time. As shown in the breakdown cases above,
iowait is performance critical often, and by counting iowait,
the proxy variable becomes a more accurate representation of the
"how critical is performance" question.
The problem and fix are both verified with the "perf timechar"
tool.
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Dave Jones <davej@redhat.com> Reviewed-by: Rik van Riel <riel@redhat.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <20100509082606.3d9f00d0@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Now that the only user of ts->idle_lastupdate is
update_ts_time_stats(), the entire field can be eliminated.
In update_ts_time_stats(), idle_lastupdate is first set to
"now", and a few lines later, the only user is an if() statement
that assigns a variable either to "now" or to
ts->idle_lastupdate, which has the value of "now" at that point.
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Rik van Riel <riel@redhat.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: davej@redhat.com
LKML-Reference: <20100509082439.2fab0b4f@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
sched: Fold updating of the last_update_time_info into update_ts_time_stats()
This patch folds the updating of the last_update_time into the
update_ts_time_stats() function, and updates the callers.
This allows for further cleanups that are done in the next
patch.
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Rik van Riel <riel@redhat.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: davej@redhat.com
LKML-Reference: <20100509082403.60072967@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
sched: Update the idle statistics in get_cpu_idle_time_us()
Right now, get_cpu_idle_time_us() only reports the idle
statistics upto the point the CPU entered last idle; not what is
valid right now.
This patch adds an update of the idle statistics to
get_cpu_idle_time_us(), so that calling this function always
returns statistics that are accurate at the point of the call.
This includes resetting the start of the idle time for
accounting purposes to avoid double accounting.
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Rik van Riel <riel@redhat.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: davej@redhat.com
LKML-Reference: <20100509082323.2d2f1945@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
sched: Introduce a function to update the idle statistics
Currently, two places update the idle statistics (and more to
come later in this series).
This patch creates a helper function for updating these
statistics.
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Rik van Riel <riel@redhat.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: davej@redhat.com
LKML-Reference: <20100509082245.163e67ed@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
The exported function get_cpu_idle_time_us() has no comment
describing it; add a kerneldoc comment
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Rik van Riel <riel@redhat.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: davej@redhat.com
LKML-Reference: <20100509082208.7cb721f0@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
perf hist: Simplify the insertion of new hist_entry instances
And with that fix at least one bug:
The first hit for an entry, the one that calls malloc to create a new
instance in __perf_session__add_hist_entry, wasn't adding the count to
the per cpumode (PERF_RECORD_MISC_USER, etc) total variable.
Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Tom Zanussi <tzanussi@gmail.com>
LKML-Reference: <new-submission> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tom Zanussi [Wed, 5 May 2010 05:27:40 +0000 (00:27 -0500)]
perf/live-mode: Handle payload-less events
Some events, such as the PERF_RECORD_FINISHED_ROUND event consist of
only an event header and no data. In this case, a 0-length payload
will be read, and the 0 return value will be wrongly interpreted as an
'unexpected end of event stream'.
This patch allows for proper handling of data-less events by skipping
0-length reads.
Signed-off-by: Tom Zanussi <tzanussi@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Masami Hiramatsu <mhiramat@redhat.com>
LKML-Reference: <1273038527.6383.51.camel@tropicana> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Drop the waittime field from the lock_acquired event, we can
calculate it by substracting the lock_acquired event timestamp
with the matching lock_acquire one.
It is not needed and takes useless space in the traces.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp> Cc: Steven Rostedt <rostedt@goodmis.org>
When a lock is acquired after beeing contended, we update the
wait time statistics for the given lock.
But if the min wait time is updated, we don't check the max wait
time. This is wrong because the first time we update the wait time,
we want to update both min and max wait time.
Before:
Name acquired contended total wait (ns) max wait (ns) min wait (ns)
key 8 1 21656 0 21656
After:
Name acquired contended total wait (ns) max wait (ns) min wait (ns)
key 8 1 21656 21656 21656
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp>
Fix the cast made to get the bad rate. It is made in the result
instead of the operands. We need the operands to be cast in double,
otherwise the result will always be zero.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp>
Hitoshi Mitake [Mon, 3 May 2010 05:12:00 +0000 (14:12 +0900)]
perf lock: Add "info" subcommand for dumping misc information
This adds the "info" subcommand to perf lock which can be used
to dump metadata like threads or addresses of lock instances.
"map" was removed because info should do the work for it.
This will be useful not only for debugging but also for ordinary
analyzing.
v2: adding example of usage
% sudo ./perf lock info -t
| Thread ID: comm
| 0: swapper
| 1: init
| 18: migration/5
| 29: events/2
| 32: events/5
| 33: events/6
...
perf: Provide a new deterministic events reordering algorithm
The current events reordering algorithm is based on a heuristic that
gets broken once we deal with a very fast flow of events.
Indeed the time period based flushing is not suitable anymore
in the following case, assuming we have a flush period of two
seconds.
CPU 0 | CPU 1
|
cnt1 timestamps | cnt1 timestamps
|
0 | 0
1 | 1
2 | 2
3 | 3
[...] | [...]
4 seconds later
If we spend too much time to read the buffers (case of a lot of
events to record in each buffers or when we have a lot of CPU buffers
to read), in the next pass the CPU 0 buffer could contain a slice
of several seconds of events. We'll read them all and notice we've
reached the period to flush. In the above example we flush the first
half of the CPU 0 buffer, then we read the CPU 1 buffer where we
have events that were on the flush slice and then the reordering
fails.
It's simple to reproduce with:
perf lock record perf bench sched messaging
To solve this, we use a new solution that doesn't rely on an
heuristical time slice period anymore but on a deterministic basis
based on how perf record does its job.
perf record saves the buffers through passes. A pass is a tour
on every buffers from every CPUs. This is made in order: for
each CPU we read the buffers of every counters. So the more
buffers we visit, the later will be the timstamps of their events.
When perf record finishes a pass it records a
PERF_RECORD_FINISHED_ROUND pseudo event.
We record the max timestamp t found in the pass n. Assuming these
timestamps are monotonic across cpus, we know that if a buffer
still has events with timestamps below t, they will be all available
and then read in the pass n + 1.
Hence when we start to read the pass n + 2, we can safely flush every
events with timestamps below t.
============ PASS n =================
CPU 0 | CPU 1
|
cnt1 timestamps | cnt2 timestamps
1 | 2
2 | 3
- | 4 <--- max recorded
============ PASS n + 1 ==============
CPU 0 | CPU 1
|
cnt1 timestamps | cnt2 timestamps
3 | 5
4 | 6
5 | 7 <---- max recorded
Flush every events below timestamp 4
============ PASS n + 2 ==============
CPU 0 | CPU 1
|
cnt1 timestamps | cnt2 timestamps
6 | 8
7 | 9
- | 10
Flush every events below timestamp 7
etc...
It also works on perf.data versions that don't have
PERF_RECORD_FINISHED_ROUND pseudo events. The difference is that
the events will be only flushed in the end of the perf.data
processing. It will then consume more memory and scale less with
large perf.data files.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Masami Hiramatsu <mhiramat@redhat.com>
perf: Introduce a new "round of buffers read" pseudo event
In order to provide a more rubust and deterministic reordering
algorithm, we need to know when we reach a point where we just
did a pass through over every counter buffers to read every thing
they had.
This patch introduces a new PERF_RECORD_FINISHED_ROUND pseudo event
that only consist in an event header and doesn't need to contain
anything.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Masami Hiramatsu <mhiramat@redhat.com>
Tejun Heo [Sat, 8 May 2010 14:20:53 +0000 (16:20 +0200)]
cpu_stop: add dummy implementation for UP
When !CONFIG_SMP, cpu_stop functions weren't defined at all which
could lead to build failures if UP code uses cpu_stop facility. Add
dummy cpu_stop implementation for UP. The waiting variants execute
the work function directly with preempt disabled and
stop_one_cpu_nowait() schedules a workqueue work.
Makefile and ifdefs around stop_machine implementation are updated to
accomodate CONFIG_SMP && !CONFIG_STOP_MACHINE case.
Due to the fact that p4 counters are shared between HT threads
we synthetically divide the whole set of counters into two
non-intersected subsets. And while we're "borrowing" counters
from these subsets we should not be preempted (well, strictly
speaking in p4_hw_config we just pre-set reference to the
subset which allow to save some cycles in schedule routine
if it happens on the same cpu). So use get_cpu/put_cpu pair.
Also p4_pmu_schedule_events should use smp_processor_id rather
than raw_ version. This allow us to catch up preemption issue
(if there will ever be).
Reported-by: Steven Rostedt <rostedt@goodmis.org> Tested-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Lin Ming <ming.m.lin@intel.com>
LKML-Reference: <20100508112716.963478928@openvz.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Paul Mackerras [Sat, 8 May 2010 10:58:00 +0000 (20:58 +1000)]
perf_event: Make software events work again
Commit 6bde9b6ce0127e2a56228a2071536d422be31336 ("perf: Add
group scheduling transactional APIs") added code to allow a
group to be scheduled in a single transaction. However, it
introduced a bug in handling events whose pmu does not implement
transactions -- at the end of scheduling in the events in the
group, in the non-transactional case the code now falls through
to the group_error label, and proceeds to unschedule all the
events in the group and return failure.
This fixes it by returning 0 (success) in the non-transactional
case.
Signed-off-by: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Lin Ming <ming.m.lin@intel.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: eranian@gmail.com
LKML-Reference: <20100508105800.GB10650@brick.ozlabs.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
perf list: Improve the raw hw event descriptor documentation
It was x86 specific and imcomplete at that, improve the situation by
making it clear where the example provided applies and by adding the
URLs for the Intel and AMD manuals where this is discussed in depth.
Acked-by: Robert Richter <robert.richter@amd.com> Cc: Cyrill Gorcunov <gorcunov@gmail.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Robert Richter <robert.richter@amd.com> Reported-by: Robert Richter <robert.richter@amd.com
LKML-Reference: <new-submission> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Lin Ming [Fri, 23 Apr 2010 05:56:12 +0000 (13:56 +0800)]
perf, x86: implement group scheduling transactional APIs
Convert to the transactional PMU API and remove the duplication of
group_sched_in().
Reviewed-by: Stephane Eranian <eranian@google.com> Signed-off-by: Lin Ming <ming.m.lin@intel.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: David Miller <davem@davemloft.net> Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <1272002172.5707.61.camel@minggr.sh.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Lin Ming [Fri, 23 Apr 2010 05:56:00 +0000 (13:56 +0800)]
perf: Add group scheduling transactional APIs
Add group scheduling transactional APIs to struct pmu.
These APIs will be implemented in arch code, based on Peter's idea as
below.
> the idea behind hw_perf_group_sched_in() is to not perform
> schedulability tests on each event in the group, but to add the group
> as a whole and then perform one test.
>
> Of course, when that test fails, you'll have to roll-back the whole
> group again.
>
> So start_txn (or a better name) would simply toggle a flag in the pmu
> implementation that will make pmu::enable() not perform the
> schedulablilty test.
>
> Then commit_txn() will perform the schedulability test (so note the
> method has to have a !void return value.
>
> This will allow us to use the regular
> kernel/perf_event.c::group_sched_in() and all the rollback code.
> Currently each hw_perf_group_sched_in() implementation duplicates all
> the rolllback code (with various bugs).
->start_txn:
Start group events scheduling transaction, set a flag to make
pmu::enable() not perform the schedulability test, it will be performed
at commit time.
->commit_txn:
Commit group events scheduling transaction, perform the group
schedulability as a whole
->cancel_txn:
Stop group events scheduling transaction, clear the flag so
pmu::enable() will perform the schedulability test.
Reviewed-by: Stephane Eranian <eranian@google.com> Reviewed-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Lin Ming <ming.m.lin@intel.com> Cc: David Miller <davem@davemloft.net> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1272002160.5707.60.camel@minggr.sh.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Peter Zijlstra [Thu, 8 Apr 2010 21:03:20 +0000 (23:03 +0200)]
perf, x86: Improve the PEBS ABI
Rename perf_event_attr::precise to perf_event_attr::precise_ip and
widen it to 2 bits. This new field describes the required precision of
the PERF_SAMPLE_IP field:
0 - SAMPLE_IP can have arbitrary skid
1 - SAMPLE_IP must have constant skid
2 - SAMPLE_IP requested to have 0 skid
3 - SAMPLE_IP must have 0 skid
And modify the Intel PEBS code accordingly. The PEBS implementation
now supports up to precise_ip == 2, where we perform the IP fixup.
Also s/PERF_RECORD_MISC_EXACT/&_IP/ to clarify its meaning, this bit
should be set for each PERF_SAMPLE_IP field known to match the actual
instruction triggering the event.
This new scheme allows for a PEBS mode that uses the buffer for more
than a single event.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Stephane Eranian <eranian@google.com>
LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Robert Richter [Tue, 13 Apr 2010 20:23:15 +0000 (22:23 +0200)]
perf, x86: Use weight instead of cmask in for_each_event_constraint()
There may exist constraints with a cmask set to zero. In this case
for_each_event_constraint() will not work properly. Now weight is used
instead of the cmask for loop exit detection. Weight is always a value
other than zero since the default contains the HWEIGHT from the
counter mask and in other cases a value of zero does not fit too.
This is in preparation of ibs event constraints that wont have a
cmask.
Signed-off-by: Robert Richter <robert.richter@amd.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1271190201-25705-7-git-send-email-robert.richter@amd.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>