We are taking a wrong regs snapshot when a trace event triggers.
Either we use get_irq_regs(), which gives us the interrupted
registers if we are in an interrupt, or we use task_pt_regs()
which gives us the state before we entered the kernel, assuming
we are lucky enough to be no kernel thread, in which case
task_pt_regs() returns the initial set of regs when the kernel
thread was started.

What we want is different. We need a hot snapshot of the regs,
so that we can get the instruction pointer to record in the
sample, the frame pointer for the callchain, and some other
things.

Let's use the new perf_fetch_caller_regs() for that.

Comparison with perf record -e lock: -R -a -f -g
Before:

        perf  [kernel]                   [k] __do_softirq
               |
               --- __do_softirq
                  |
                  |--55.16%-- __open
                  |
                   --44.84%-- __write_nocancel

After:

            perf  [kernel]           [k] perf_tp_event
               |
               --- perf_tp_event
                  |
                  |--41.07%-- lock_acquire
                  |          |
                  |          |--39.36%-- _raw_spin_lock
                  |          |          |
                  |          |          |--7.81%-- hrtimer_interrupt
                  |          |          |          smp_apic_timer_interrupt
                  |          |          |          apic_timer_interrupt

The old case was producing unreliable callchains. Now having
right frame and instruction pointers, we have the trace we
want.

Also syscalls and kprobe events already have the right regs,
let's use them instead of wasting a retrieval.

v2: Follow the rename perf_save_regs() -> perf_fetch_caller_regs()
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Jason Baron <jbaron@redhat.com>
Cc: Archs <linux-arch@vger.kernel.org>

Introduce ftrace_perf_buf_prepare() and ftrace_perf_buf_submit() to
gather the common code that operates on raw events sampling buffer.
This cleans up redundant code between regular trace events, syscall
events and kprobe events.

Changelog v1->v2:
- Rename function name as per Masami and Frederic's suggestion
- Add __kprobes for ftrace_perf_buf_prepare() and make
  ftrace_perf_buf_submit() inline as per Masami's suggestion
- Export ftrace_perf_buf_prepare since modules will use it
Signed-off-by: NXiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Acked-by: NMasami Hiramatsu <mhiramat@redhat.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Jason Baron <jbaron@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
LKML-Reference: <4B60E92D.9000808@cn.fujitsu.com>
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>

The previous patches added the use of print_fmt string and changes
the trace_define_field() function to also create the fields and
format output for the event format files.

   text	   data	    bss	    dec	    hex	filename
5857201	1355780	9336808	16549789	 fc879d	vmlinux
5884589	1351684	9337896	16574169	 fce6d9	vmlinux-orig

The above shows the size of the vmlinux after this patch set
compared to the vmlinux-orig which is before the patch set.

This saves us 27k on text, 1k on bss and adds just 4k of data.

The total savings of 24k in size.
Signed-off-by: NLai Jiangshan <laijs@cn.fujitsu.com>
LKML-Reference: <4B273D4D.40604@cn.fujitsu.com>
Acked-by: NMasami Hiramatsu <mhiramat@redhat.com>
Signed-off-by: NSteven Rostedt <rostedt@goodmis.org>

This is part of a patch set that removes the show_format method
in the ftrace event macros.

The print_fmt field is added to hold the string that shows
the print_fmt in the event format files. This patch only adds
the field but it is currently not used. Later patches will use
this field to enable us to remove the show_format field
and function.
Signed-off-by: NLai Jiangshan <laijs@cn.fujitsu.com>
LKML-Reference: <4B273D3E.2000704@cn.fujitsu.com>
Signed-off-by: NSteven Rostedt <rostedt@goodmis.org>

Quoted from Ingo:

| This reminds me - i think we should eliminate CONFIG_EVENT_PROFILE -
| it's an unnecessary Kconfig complication. If both PERF_EVENTS and
| EVENT_TRACING is enabled we should expose generic tracepoints.
|
| Nor is it limited to event 'profiling', so it has become a misnomer as
| well.
Signed-off-by: NLi Zefan <lizf@cn.fujitsu.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <4B2F1557.2050705@cn.fujitsu.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Like total_profile_count, struct ftrace_event_call::profile_count
is protected by event_mutex, so it doesn't need to be atomic_t.
Signed-off-by: NLi Zefan <lizf@cn.fujitsu.com>
Acked-by: NSteven Rostedt <rostedt@goodmis.org>
Cc: Jason Baron <jbaron@redhat.com>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
LKML-Reference: <4B1DC549.5010705@cn.fujitsu.com>
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>

Call trace_define_common_fields() in event_create_dir() only.
This avoids trace events to handle it from their define_fields
callbacks and shrinks the kernel code size:

   text    data     bss     dec     hex filename
5346802 1961864 7103260 14411926         dbe896 vmlinux.o.old
5345151 1961864 7103260 14410275         dbe223 vmlinux.o
Signed-off-by: NLi Zefan <lizf@cn.fujitsu.com>
Acked-by: NSteven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jason Baron <jbaron@redhat.com>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
LKML-Reference: <4B1DC49C.8000107@cn.fujitsu.com>
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>

Use a generic trace_event_raw_init() function for all event's raw_init
callbacks (but kprobes) instead of defining the same version for each
of these.
This shrinks the kernel code:

   text    data     bss     dec     hex filename
5355293 1961928 7103260 14420481         dc0a01 vmlinux.o.old
5346802 1961864 7103260 14411926         dbe896 vmlinux.o

raw_init can't be removed, because ftrace events and kprobe events
use different raw_init callbacks. Though it's possible to totally
remove raw_init, I choose to leave it as it is for now.
Signed-off-by: NLi Zefan <lizf@cn.fujitsu.com>
Acked-by: NSteven Rostedt <rostedt@goodmis.org>
Cc: Jason Baron <jbaron@redhat.com>
Cc: Ingo Molnar <mingo@elte.hu>
LKML-Reference: <4B1DC48C.7080603@cn.fujitsu.com>
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>

If the seq_read fills the buffer it will call s_start again on the next
itertation with the same position. This causes a problem with the
function_graph tracer because it consumes the iteration in order to
determine leaf functions.

What happens is that the iterator stores the entry, and the function
graph plugin will look at the next entry. If that next entry is a return
of the same function and task, then the function is a leaf and the
function_graph plugin calls ring_buffer_read which moves the ring buffer
iterator forward (the trace iterator still points to the function start
entry).

The copying of the trace_seq to the seq_file buffer will fail if the
seq_file buffer is full. The seq_read will not show this entry.
The next read by userspace will cause seq_read to again call s_start
which will reuse the trace iterator entry (the function start entry).
But the function return entry was already consumed. The function graph
plugin will think that this entry is a nested function and not a leaf.

To solve this, the trace code now checks the return status of the
seq_printf (trace_print_seq). If the writing to the seq_file buffer
fails, we set a flag in the iterator (leftover) and we do not reset
the trace_seq buffer. On the next call to s_start, we check the leftover
flag, and if it is set, we just reuse the trace_seq buffer and do not
call into the plugin print functions.

Before this patch:

 2)               |      fput() {
 2)               |        __fput() {
 2)   0.550 us    |          inotify_inode_queue_event();
 2)               |          __fsnotify_parent() {
 2)   0.540 us    |          inotify_dentry_parent_queue_event();

After the patch:

 2)               |      fput() {
 2)               |        __fput() {
 2)   0.550 us    |          inotify_inode_queue_event();
 2)   0.548 us    |          __fsnotify_parent();
 2)   0.540 us    |          inotify_dentry_parent_queue_event();

[
  Updated the patch to fix a missing return 0 from the trace_print_seq()
  stub when CONFIG_TRACING is disabled.
Reported-by: NIngo Molnar <mingo@elte.hu>
]
Reported-by: NJiri Olsa <jolsa@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: NSteven Rostedt <rostedt@goodmis.org>

When we commit a trace to perf, we first check if we are
recursing in the same buffer so that we don't mess-up the buffer
with a recursing trace. But later on, we do the same check from
perf to avoid commit recursion. The recursion check is desired
early before we touch the buffer but we want to do this check
only once.

Then export the recursion protection from perf and use it from
the trace events before submitting a trace.

v2: Put appropriate Reported-by tag
Reported-by: NPeter Zijlstra <peterz@infradead.org>
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Jason Baron <jbaron@redhat.com>
LKML-Reference: <1258864015-10579-1-git-send-email-fweisbec@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

While tracing using events with perf, if one enables the
lockdep:lock_acquire event, it will infect every other perf
trace events.

Basically, you can enable whatever set of trace events through
perf but if this event is part of the set, the only result we
can get is a long list of lock_acquire events of rcu read lock,
and only that.

This is because of a recursion inside perf.

1) When a trace event is triggered, it will fill a per cpu
   buffer and submit it to perf.

2) Perf will commit this event but will also protect some data
   using rcu_read_lock

3) A recursion appears: rcu_read_lock triggers a lock_acquire
   event that will fill the per cpu event and then submit the
   buffer to perf.

4) Perf detects a recursion and ignores it

5) Perf continues its work on the previous event, but its buffer
   has been overwritten by the lock_acquire event, it has then
   been turned into a lock_acquire event of rcu read lock

Such scenario also happens with lock_release with
rcu_read_unlock().

We could turn the rcu_read_lock() into __rcu_read_lock() to drop
the lock debugging from perf fast path, but that would make us
lose the rcu debugging and that doesn't prevent from other
possible kind of recursion from perf in the future.

This patch adds a recursion protection based on a counter on the
perf trace per cpu buffers to solve the problem.

-v2: Fixed lost whitespace, added reviewed-by tag
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
Reviewed-by: NMasami Hiramatsu <mhiramat@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Jason Baron <jbaron@redhat.com>
LKML-Reference: <1257477185-7838-1-git-send-email-fweisbec@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

- Add an ioctl to allocate a filter for a perf event.

- Free the filter when the associated perf event is to be freed.

- Do the filtering in perf_swevent_match().
Signed-off-by: NLi Zefan <lizf@cn.fujitsu.com>
Acked-by: NPeter Zijlstra <peterz@infradead.org>
Acked-by: NFrederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Tom Zanussi <tzanussi@gmail.com>
LKML-Reference: <4AD69546.8050401@cn.fujitsu.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Currently the trace event profile buffer is allocated in the stack. But
this may be too much for the stack, as the events can have large
statically defined field size and can also grow with dynamic arrays.

Allocate two per cpu buffer for all profiled events. The first cpu
buffer is used to host every non-nmi context traces. It is protected
by disabling the interrupts while writing and committing the trace.

The second buffer is reserved for nmi. So that there is no race between
them and the first buffer.

The whole write/commit section is rcu protected because we release
these buffers while deactivating the last profiling trace event.

v2: Move the buffers from trace_event to be global, as pointed by
    Steven Rostedt.

v3: Fix the syscall events to handle the profiling buffer races
    by disabling interrupts, now that the buffers are globals.
Suggested-by: NSteven Rostedt <rostedt@goodmis.org>
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Jason Baron <jbaron@redhat.com>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Ingo Molnar <mingo@elte.hu>

Factorize the events enabling accounting in a common tracing core
helper. This reduces the size of the profile_enable() and
profile_disable() callbacks for each trace events.
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
Acked-by: NSteven Rostedt <rostedt@goodmis.org>
Acked-by: NLi Zefan <lizf@cn.fujitsu.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Jason Baron <jbaron@redhat.com>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Ingo Molnar <mingo@elte.hu>

This patch increases the max string used by predicates to
handle KSYM_SYMBOL_LEN.

Also moves an include to look nicer.
Signed-off-by: NSteven Rostedt <rostedt@goodmis.org>

This patch adds the lock depth of the big kernel lock to the generic
entry header. This way we can see the depth of the lock and help
in removing the BKL.

Example:

 #                  _------=> CPU#
 #                 / _-----=> irqs-off
 #                | / _----=> need-resched
 #                || / _---=> hardirq/softirq
 #                ||| / _--=> preempt-depth
 #                |||| /_--=> lock-depth
 #                |||||/     delay
 #  cmd     pid   |||||| time  |   caller
 #     \   /      ||||||   \   |   /
   <idle>-0       2.N..3 5902255250us+: lock_acquire: read rcu_read_lock
   <idle>-0       2.N..3 5902255253us+: lock_release: rcu_read_lock
   <idle>-0       2dN..3 5902255257us+: lock_acquire: xtime_lock
   <idle>-0       2dN..4 5902255259us : lock_acquire: clocksource_lock
   <idle>-0       2dN..4 5902255261us+: lock_release: clocksource_lock
Signed-off-by: NSteven Rostedt <rostedt@goodmis.org>

The userstack trace required the recording of the tgid entry.
Unfortunately, it was added to the generic entry where it wasted
4 bytes of every entry and was only used by one entry.

This patch moves it out of the generic field and moves it into the
only user (userstack_entry).
Signed-off-by: NSteven Rostedt <rostedt@goodmis.org>

The latency tracers (irqsoff and wakeup) can swap trace buffers
on the fly. If an event is happening and has reserved data on one of
the buffers, and the latency tracer swaps the global buffer with the
max buffer, the result is that the event may commit the data to the
wrong buffer.

This patch changes the API to the trace recording to be recieve the
buffer that was used to reserve a commit. Then this buffer can be passed
in to the commit.
Signed-off-by: NSteven Rostedt <rostedt@goodmis.org>

init_preds() allocates about 5392 bytes of memory (on x86_32) for
a TRACE_EVENT. With my config, at system boot total memory occupied
is:

	5392 * (642 + 15) == 3459KB

642 == cat available_events | wc -l
15 == number of dirs in events/ftrace

That's quite a lot, so we'd better defer memory allocation util
it's needed, that's when filter is used.
Signed-off-by: NLi Zefan <lizf@cn.fujitsu.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
LKML-Reference: <4A9B8EA5.6020700@cn.fujitsu.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Restore the const qualifier in field's name and type parameters of
trace_define_field that was lost while solving a conflict.

Fields names and types are defined as builtin constant strings in
static TRACE_EVENTs. But kprobes allocates these dynamically.

That said, we still want to always pass these strings as const char *
in trace_define_fields() to avoid any further accidental writes on
the pointed strings.
Reported-by: NLi Zefan <lizf@cn.fujitsu.com>
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>

Add dynamic ftrace_event_call support to ftrace. Trace engines can add
new ftrace_event_call to ftrace on the fly. Each operator function of
the call takes an ftrace_event_call data structure as an argument,
because these functions may be shared among several ftrace_event_calls.

Changes from v13:
 - Define remove_subsystem_dir() always (revirt a2ca5e03), because
   trace_remove_event_call() uses it.
 - Modify syscall tracer because of ftrace_event_call change.

[fweisbec@gmail.com: Fixed conflict against latest tracing/core]
Signed-off-by: NMasami Hiramatsu <mhiramat@redhat.com>
Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Frank Ch. Eigler <fche@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jason Baron <jbaron@redhat.com>
Cc: Jim Keniston <jkenisto@us.ibm.com>
Cc: K.Prasad <prasad@linux.vnet.ibm.com>
Cc: Lai Jiangshan <laijs@cn.fujitsu.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Przemysław Pawełczyk <przemyslaw@pawelczyk.it>
Cc: Roland McGrath <roland@redhat.com>
Cc: Sam Ravnborg <sam@ravnborg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Tom Zanussi <tzanussi@gmail.com>
Cc: Vegard Nossum <vegard.nossum@gmail.com>
LKML-Reference: <20090813203453.31965.71901.stgit@localhost.localdomain>
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>

Usually, char * entries are dangerous in traces because the string
can be released whereas a pointer to it can still wait to be read from
the ring buffer.

But sometimes we can assume it's safe, like in case of RO data
(eg: __file__ or __line__, used in bkl trace event). If these RO data
are in a module and so is the call to the trace event, then it's safe,
because the ring buffer will be flushed once this module get unloaded.

To allow char * to be treated as a string:

	TRACE_EVENT(...,

		TP_STRUCT__entry(
			__field_ext(const char *, name, FILTER_PTR_STRING)
			...
		)

		...
	);

The filtering will not dereference "char *" unless the developer
explicitly sets FILTER_PTR_STR in __field_ext.
Signed-off-by: NLi Zefan <lizf@cn.fujitsu.com>
LKML-Reference: <4A7B9287.90205@cn.fujitsu.com>
Signed-off-by: NSteven Rostedt <rostedt@goodmis.org>

Add __field_ext(), so a field can be assigned to a specific
filter_type, which matches a corresponding filter function.

For example, a later patch will allow this:
	__field_ext(const char *, str, FILTER_PTR_STR);
Signed-off-by: NLi Zefan <lizf@cn.fujitsu.com>
LKML-Reference: <4A7B9272.60507095@cn.fujitsu.com>

[
  Fixed a -1 to FILTER_OTHER
  Forward ported to latest kernel.
]
Signed-off-by: NSteven Rostedt <rostedt@goodmis.org>

Add filtering support for syscall events:

 # echo 'mode == 0666' > events/syscalls/sys_enter_open
 # echo 'ret == 0' > events/syscalls/sys_exit_open
 # echo 1 > events/syscalls/sys_enter_open
 # echo 1 > events/syscalls/sys_exit_open
 # cat trace
 ...
   modprobe-3084 [001] 117.463140: sys_open(filename: 917d3e8, flags: 0, mode: 1b6)
   modprobe-3084 [001] 117.463176: sys_open -> 0x0
       less-3086 [001] 117.510455: sys_open(filename: 9c6bdb8, flags: 8000, mode: 1b6)
   sendmail-2574 [001] 122.145840: sys_open(filename: b807a365, flags: 0, mode: 1b6)
 ...
Signed-off-by: NLi Zefan <lizf@cn.fujitsu.com>
Cc: Jason Baron <jbaron@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <4A8BAFCB.1040006@cn.fujitsu.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Extract duplicate code. Also prepare for the later patch.
Signed-off-by: NLi Zefan <lizf@cn.fujitsu.com>
Cc: Jason Baron <jbaron@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <4A8BAFB8.1010304@cn.fujitsu.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

This parameter is needed by syscall events to add define_fields()
handler.
Signed-off-by: NLi Zefan <lizf@cn.fujitsu.com>
Cc: Jason Baron <jbaron@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <4A8BAF90.6060801@cn.fujitsu.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Add the struct ftrace_event_call as a parameter of its show_format()
callback. This way we can use it from the syscall trace events to
retrieve the syscall name from the ftrace event call parameter and
describe its fields using the syscalls metadata.
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
Cc: Lai Jiangshan <laijs@cn.fujitsu.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Cc: Jiaying Zhang <jiayingz@google.com>
Cc: Martin Bligh <mbligh@google.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Jason Baron <jbaron@redhat.com>

add an optional void * pointer to 'ftrace_event_call' that is
passed in for regfunc and unregfunc.

This prepares for syscall tracepoints creation by passing the name of
the syscall we want to trace and then retrieve its number through our
arch syscall table.
Signed-off-by: NJason Baron <jbaron@redhat.com>
Cc: Lai Jiangshan <laijs@cn.fujitsu.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Cc: Jiaying Zhang <jiayingz@google.com>
Cc: Martin Bligh <mbligh@google.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>

This patch implements the kernel side support for ftrace event
record sampling.

A new counter sampling attribute is added:

   PERF_SAMPLE_TP_RECORD

which requests ftrace events record sampling. In this case
if a PERF_TYPE_TRACEPOINT counter is active and a tracepoint
fires, we emit the tracepoint binary record to the
perfcounter event buffer, as a sample.

Result, after setting PERF_SAMPLE_TP_RECORD attribute from perf
record:

 perf record -f -F 1 -a -e workqueue:workqueue_execution
 perf report -D

 0x21e18 [0x48]: event: 9
 .
 . ... raw event: size 72 bytes
 .  0000:  09 00 00 00 01 00 48 00 d0 c7 00 81 ff ff ff ff  ......H........
 .  0010:  0a 00 00 00 0a 00 00 00 21 00 00 00 00 00 00 00  ........!......
 .  0020:  2b 00 01 02 0a 00 00 00 0a 00 00 00 65 76 65 6e  +...........eve
 .  0030:  74 73 2f 31 00 00 00 00 00 00 00 00 0a 00 00 00  ts/1...........
 .  0040:  e0 b1 31 81 ff ff ff ff                          .......
.
0x21e18 [0x48]: PERF_EVENT_SAMPLE (IP, 1): 10: 0xffffffff8100c7d0 period: 33

The raw ftrace binary record starts at offset 0020.

Translation:

 struct trace_entry {
	type		= 0x2b = 43;
	flags		= 1;
	preempt_count	= 2;
	pid		= 0xa = 10;
	tgid		= 0xa = 10;
 }

 thread_comm = "events/1"
 thread_pid  = 0xa = 10;
 func	    = 0xffffffff8131b1e0 = flush_to_ldisc()

What will come next?

 - Userspace support ('perf trace'), 'flight data recorder' mode
   for perf trace, etc.

 - The unconditional copy from the profiling callback brings
   some costs however if someone wants no such sampling to
   occur, and needs to be fixed in the future. For that we need
   to have an instant access to the perf counter attribute.
   This is a matter of a flag to add in the struct ftrace_event.

 - Take care of the events recursivity! Don't ever try to record
   a lock event for example, it seems some locking is used in
   the profiling fast path and lead to a tracing recursivity.
   That will be fixed using raw spinlock or recursivity
   protection.

 - [...]

 - Profit! :-)
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Gabriel Munteanu <eduard.munteanu@linux360.ro>
Cc: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Not all tracepoints are created equal, in specific the ftrace
tracepoints are created with TRACE_EVENT_FORMAT() which does
not generate the needed bits to tie them into perf counters.

For those events, don't create the 'id' file and fail
->profile_enable when their ID is specified through other
means.
Reported-by: NChris Mason <chris.mason@oracle.com>
Signed-off-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
LKML-Reference: <1249497664.5890.4.camel@laptop>
[ v2: fix build error in the !CONFIG_EVENT_PROFILE case ]
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Currently a subsystem filter should be applicable to all events
under the subsystem, and if it failed, all the event filters
will be cleared. Those behaviors make subsys filter much less
useful:

  # echo 'vec == 1' > irq/softirq_entry/filter
  # echo 'irq == 5' > irq/filter
  bash: echo: write error: Invalid argument
  # cat irq/softirq_entry/filter
  none

I'd expect it set the filter for irq_handler_entry/exit, and
not touch softirq_entry/exit.

The basic idea is, try to see if the filter can be applied
to which events, and then just apply to the those events:

  # echo 'vec == 1' > softirq_entry/filter
  # echo 'irq == 5' > filter
  # cat irq_handler_entry/filter
  irq == 5
  # cat softirq_entry/filter
  vec == 1

Changelog for v2:
- do some cleanups to address Frederic's comments.
Inspired-by: NSteven Rostedt <srostedt@redhat.com>
Signed-off-by: NLi Zefan <lizf@cn.fujitsu.com>
Acked-by: NFrederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <4A63D485.7030703@cn.fujitsu.com>
Signed-off-by: NSteven Rostedt <rostedt@goodmis.org>

The trace_pipe did not recognize the latency format flag and would produce
different output than the trace file. The problem was partly due that
the trace flags in the iterator was not set as well as the trace_pipe
zeros out part of the iterator (including the flags) to be able to use
the same routines as the trace file. trace_flags of the iterator should
not cause any problems when not zeroed out by for trace_pipe.
Reported-by: NJohannes Berg <johannes@sipsolutions.net>
Signed-off-by: NSteven Rostedt <rostedt@goodmis.org>

This patch adds __print_symbolic which is similar to __print_flags but
works for an enumeration type instead. That is, there is only a one to one
mapping between the values and the symbols. When a match is made, then
it is printed, otherwise the hex value is outputed.

[ Impact: add interface for showing symbol names in events ]
Signed-off-by: NSteven Rostedt <rostedt@goodmis.org>
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>

Developers have been asking for the ability in the ftrace event tracer
to display names of bits in a flags variable.

Instead of printing out c2, it would be easier to read FOO|BAR|GOO,
assuming that FOO is bit 1, BAR is bit 6 and GOO is bit 7.

Some examples where this would be useful are the state flags in a context
switch, kmalloc flags, and even permision flags in accessing files.

[
  v2 changes include:

  Frederic Weisbecker's idea of using a mask instead of bits,
  thus we can output GFP_KERNEL instead of GPF_WAIT|GFP_IO|GFP_FS.

  Li Zefan's idea of allowing the caller of __print_flags to add their
  own delimiter (or no delimiter) where we can get for file permissions
  rwx instead of r|w|x.
]

[
  v3 changes:

   Christoph Hellwig's idea of using an array instead of va_args.
]

[ Impact: better displaying of flags in trace output ]
Signed-off-by: NSteven Rostedt <rostedt@goodmis.org>
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>

Other parts of the kernel may need to be able to enable or disable
specific events. Especially parts that create trace events.

[ Impact: allow enabling of trace events by those that create the event ]
Signed-off-by: NSteven Rostedt <rostedt@goodmis.org>

When unloading a module, memory allocated by init_preds() and
trace_define_field() is not freed.

[ Impact: fix memory leak ]
Signed-off-by: NLi Zefan <lizf@cn.fujitsu.com>
Acked-by: NFrederic Weisbecker <fweisbec@gmail.com>
Acked-by: NSteven Rostedt <rostedt@goodmis.org>
Cc: Tom Zanussi <tzanussi@gmail.com>
LKML-Reference: <4A00F6E0.3040503@cn.fujitsu.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Replace the current event parser hack with a better one.  Filters are
no longer specified predicate by predicate, but all at once and can
use parens and any of the following operators:

numeric fields:

==, !=, <, <=, >, >=

string fields:

==, !=

predicates can be combined with the logical operators:

&&, ||

examples:

"common_preempt_count > 4" > filter

"((sig >= 10 && sig < 15) || sig == 17) && comm != bash" > filter

If there was an error, the erroneous string along with an error
message can be seen by looking at the filter e.g.:

((sig >= 10 && sig < 15) || dsig == 17) && comm != bash
^
parse_error: Field not found

Currently the caret for an error always appears at the beginning of
the filter; a real position should be used, but the error message
should be useful even without it.

To clear a filter, '0' can be written to the filter file.

Filters can also be set or cleared for a complete subsystem by writing
the same filter as would be written to an individual event to the
filter file at the root of the subsytem.  Note however, that if any
event in the subsystem lacks a field specified in the filter being
set, the set will fail and all filters in the subsytem are
automatically cleared.  This change from the previous version was made
because using only the fields that happen to exist for a given event
would most likely result in a meaningless filter.

Because the logical operators are now implemented as predicates, the
maximum number of predicates in a filter was increased from 8 to 16.

[ Impact: add new, extended trace-filter implementation ]
Signed-off-by: NTom Zanussi <tzanussi@gmail.com>
Acked-by: NSteven Rostedt <rostedt@goodmis.org>
Cc: fweisbec@gmail.com
Cc: Li Zefan <lizf@cn.fujitsu.com>
LKML-Reference: <1240905899.6416.121.camel@tropicana>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

The new filter comparison ops need to be able to distinguish between
signed and unsigned field types, so add an is_signed flag/param to the
event field struct/trace_define_fields().  Also define a simple macro,
is_signed_type() to determine the signedness at compile time, used in the
trace macros.  If the is_signed_type() macro won't work with a specific
type, a new slightly modified version of TRACE_FIELD() called
TRACE_FIELD_SIGN(), allows the signedness to be set explicitly.

[ Impact: extend trace-filter code for new feature ]
Signed-off-by: NTom Zanussi <tzanussi@gmail.com>
Acked-by: NSteven Rostedt <rostedt@goodmis.org>
Cc: fweisbec@gmail.com
Cc: Li Zefan <lizf@cn.fujitsu.com>
LKML-Reference: <1240905893.6416.120.camel@tropicana>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Create a new event_filter object, and move the pred-related members
out of the call and subsystem objects and into the filter object - the
details of the filter implementation don't need to be exposed in the
call and subsystem in any case, and it will also help make the new
parser implementation a little cleaner.

[ Impact: refactor trace-filter code to prepare for new features ]
Signed-off-by: NTom Zanussi <tzanussi@gmail.com>
Acked-by: NSteven Rostedt <rostedt@goodmis.org>
Cc: fweisbec@gmail.com
Cc: Li Zefan <lizf@cn.fujitsu.com>
LKML-Reference: <1240905887.6416.119.camel@tropicana>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

With modules being able to add trace events, and the max trace event
counter is 16 bits (65536) we can overflow the counter easily
with a simple while loop adding and removing modules that contain
trace events.

This patch links together the registered trace events and on overflow
searches for available trace event ids. It will still fail if
over 65536 events are registered, but considering that a typical
kernel only has 22000 functions, 65000 events should be sufficient.
Reported-by: NLi Zefan <lizf@cn.fujitsu.com>
Signed-off-by: NSteven Rostedt <rostedt@goodmis.org>