[3.8] tracing: Updated patches

Ingo,

This includes the updates to the formating issues to the patches that were in the original patch set, and which I had dropped from my last pull request. I added this on top of my last git pull request.

I also included Shan's dead comment removal.

Please pull the latest tip/perf/core tree, which can be found at:

git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace.git
tip/perf/core

Head SHA1: 1c7d66732458dc187008e3f5b2f71e019e320fc2

David Sharp (2):
tracing,x86: Add a TSC trace_clock
tracing: Format non-nanosec times from tsc clock without a decimal point.

Shan Wei (1):
tracing: Kill unused and puzzled sample code in ftrace.h

Yoshihiro YUNOMAE (1):
tracing: Show raw time stamp on stats per cpu using counter or tsc mode for trace_clock

----

 arch/alpha/include/asm/Kbuild      |    1 +
 arch/arm/include/asm/Kbuild        |    1 +
 arch/arm64/include/asm/Kbuild      |    1 +
 arch/avr32/include/asm/Kbuild      |    1 +
 arch/blackfin/include/asm/Kbuild   |    1 +
 arch/c6x/include/asm/Kbuild        |    1 +
 arch/cris/include/asm/Kbuild       |    1 +
 arch/frv/include/asm/Kbuild        |    1 +
 arch/h8300/include/asm/Kbuild      |    1 +
 arch/hexagon/include/asm/Kbuild    |    1 +
 arch/ia64/include/asm/Kbuild       |    1 +
 arch/m32r/include/asm/Kbuild       |    1 +
 arch/m68k/include/asm/Kbuild       |    1 +
 arch/microblaze/include/asm/Kbuild |    1 +
 arch/mips/include/asm/Kbuild       |    1 +
 arch/mn10300/include/asm/Kbuild    |    1 +
 arch/openrisc/include/asm/Kbuild   |    1 +
 arch/parisc/include/asm/Kbuild     |    1 +
 arch/powerpc/include/asm/Kbuild    |    1 +
 arch/s390/include/asm/Kbuild       |    1 +
 arch/score/include/asm/Kbuild      |    1 +
 arch/sh/include/asm/Kbuild         |    1 +
 arch/sparc/include/asm/Kbuild      |    1 +
 arch/tile/include/asm/Kbuild       |    1 +
 arch/um/include/asm/Kbuild         |    1 +
 arch/unicore32/include/asm/Kbuild  |    1 +
 arch/x86/include/asm/trace_clock.h |   20 +++++++++
 arch/x86/kernel/Makefile           |    1 +
 arch/x86/kernel/trace_clock.c      |   21 ++++++++++
 arch/xtensa/include/asm/Kbuild     |    1 +
 include/asm-generic/trace_clock.h  |   16 ++++++++
 include/linux/ftrace_event.h       |    6 +++
 include/linux/trace_clock.h        |    2 +
 include/trace/ftrace.h             |   73 ---------------------------------
 kernel/trace/trace.c               |   39 +++++++++++++-----
 kernel/trace/trace.h               |    4 --
 kernel/trace/trace_output.c        |   78 ++++++++++++++++++++++++------------
 37 files changed, 176 insertions(+), 111 deletions(-)

From: David Sharp <[email protected]>

In order to promote interoperability between userspace tracers and ftrace, add a trace_clock that reports raw TSC values which will then be recorded in the ring buffer. Userspace tracers that also record TSCs are then on exactly the same time base as the kernel and events can be unambiguously interlaced.

Tested: Enabled a tracepoint and the "tsc" trace_clock and saw very large timestamp values.

v2:
Move arch-specific bits out of generic code.
v3:
Rename "x86-tsc", cleanups
v7:
Generic arch bits in Kbuild.

Google-Bug-Id: 6980623

---
 arch/alpha/include/asm/Kbuild      |    1 +
 arch/arm/include/asm/Kbuild        |    1 +
 arch/arm64/include/asm/Kbuild      |    1 +
 arch/avr32/include/asm/Kbuild      |    1 +
 arch/blackfin/include/asm/Kbuild   |    1 +
 arch/c6x/include/asm/Kbuild        |    1 +
 arch/cris/include/asm/Kbuild       |    1 +
 arch/frv/include/asm/Kbuild        |    1 +
 arch/h8300/include/asm/Kbuild      |    1 +
 arch/hexagon/include/asm/Kbuild    |    1 +
 arch/ia64/include/asm/Kbuild       |    1 +
 arch/m32r/include/asm/Kbuild       |    1 +
 arch/m68k/include/asm/Kbuild       |    1 +
 arch/microblaze/include/asm/Kbuild |    1 +
 arch/mips/include/asm/Kbuild       |    1 +
 arch/mn10300/include/asm/Kbuild    |    1 +
 arch/openrisc/include/asm/Kbuild   |    1 +
 arch/parisc/include/asm/Kbuild     |    1 +
 arch/powerpc/include/asm/Kbuild    |    1 +
 arch/s390/include/asm/Kbuild       |    1 +
 arch/score/include/asm/Kbuild      |    1 +
 arch/sh/include/asm/Kbuild         |    1 +
 arch/sparc/include/asm/Kbuild      |    1 +
 arch/tile/include/asm/Kbuild       |    1 +
 arch/um/include/asm/Kbuild         |    1 +
 arch/unicore32/include/asm/Kbuild  |    1 +
 arch/x86/include/asm/trace_clock.h |   20 ++++++++++++++++++++
 arch/x86/kernel/Makefile           |    1 +
 arch/x86/kernel/trace_clock.c      |   21 +++++++++++++++++++++
 arch/xtensa/include/asm/Kbuild     |    1 +
 include/asm-generic/trace_clock.h  |   16 ++++++++++++++++
 include/linux/trace_clock.h        |    2 ++
 kernel/trace/trace.c               |    1 +
 33 files changed, 88 insertions(+)
 create mode 100644 arch/x86/include/asm/trace_clock.h
 create mode 100644 arch/x86/kernel/trace_clock.c
 create mode 100644 include/asm-generic/trace_clock.h

index 64ffc9e..dcfabb9 100644
@@ -11,3 +11,4 @@ header-y += reg.h
 header-y += regdef.h
 header-y += sysinfo.h
 generic-y += exec.h
+generic-y += trace_clock.h

index f70ae17..514e398 100644
@@ -31,5 +31,6 @@ generic-y += sockios.h
 generic-y += termbits.h
 generic-y += termios.h
 generic-y += timex.h
+generic-y += trace_clock.h
 generic-y += types.h
 generic-y += unaligned.h

index a581a22..6e9ca46 100644
@@ -43,6 +43,7 @@ generic-y += swab.h
 generic-y += termbits.h
 generic-y += termios.h
 generic-y += topology.h
+generic-y += trace_clock.h
 generic-y += types.h
 generic-y += unaligned.h
 generic-y += user.h

index 4807ded..4dd4f78 100644
@@ -1,3 +1,4 @@
 
 generic-y	+= clkdev.h
 generic-y	+= exec.h
+generic-y	+= trace_clock.h

index 5a0625a..27d7075 100644
@@ -38,6 +38,7 @@ generic-y += statfs.h
 generic-y += termbits.h
 generic-y += termios.h
 generic-y += topology.h
+generic-y += trace_clock.h
 generic-y += types.h
 generic-y += ucontext.h
 generic-y += unaligned.h

index 112a496..eae7b59 100644
@@ -49,6 +49,7 @@ generic-y += termbits.h
 generic-y += termios.h
 generic-y += tlbflush.h
 generic-y += topology.h
+generic-y += trace_clock.h
 generic-y += types.h
 generic-y += ucontext.h
 generic-y += user.h

index 6d43a95..15a122c 100644
@@ -11,3 +11,4 @@ header-y += sync_serial.h
 generic-y += clkdev.h
 generic-y += exec.h
 generic-y += module.h
+generic-y += trace_clock.h

index 4a159da..c5d7670 100644
@@ -1,3 +1,4 @@
 
 generic-y += clkdev.h
 generic-y += exec.h
+generic-y += trace_clock.h

index 50bbf38..4bc8ae7 100644
@@ -3,3 +3,4 @@ include include/asm-generic/Kbuild.asm
 generic-y += clkdev.h
 generic-y += exec.h
 generic-y += module.h
+generic-y += trace_clock.h

index 3bfa9b3..bdb54ce 100644
@@ -48,6 +48,7 @@ generic-y += stat.h
 generic-y += termbits.h
 generic-y += termios.h
 generic-y += topology.h
+generic-y += trace_clock.h
 generic-y += types.h
 generic-y += ucontext.h
 generic-y += unaligned.h

index dd02f09..05b03ec 100644
@@ -2,3 +2,4 @@
 generic-y += clkdev.h
 generic-y += exec.h
 generic-y += kvm_para.h
+generic-y += trace_clock.h

index 50bbf38..4bc8ae7 100644
@@ -3,3 +3,4 @@ include include/asm-generic/Kbuild.asm
 generic-y += clkdev.h
 generic-y += exec.h
 generic-y += module.h
+generic-y += trace_clock.h

index 88fa3ac..7f1949c 100644
@@ -24,6 +24,7 @@ generic-y += sections.h
 generic-y += siginfo.h
 generic-y += statfs.h
 generic-y += topology.h
+generic-y += trace_clock.h
 generic-y += types.h
 generic-y += word-at-a-time.h
 generic-y += xor.h

index 8653072..2957fcc 100644
@@ -3,3 +3,4 @@ include include/asm-generic/Kbuild.asm
 header-y  += elf.h
 generic-y += clkdev.h
 generic-y += exec.h
+generic-y += trace_clock.h

index 533053d..9b54b7a 100644
@@ -1 +1,2 @@
 # MIPS headers
+generic-y += trace_clock.h

index 4a159da..c5d7670 100644
@@ -1,3 +1,4 @@
 
 generic-y += clkdev.h
 generic-y += exec.h
+generic-y += trace_clock.h

index 78de680..8971026 100644
@@ -60,6 +60,7 @@ generic-y += swab.h
 generic-y += termbits.h
 generic-y += termios.h
 generic-y += topology.h
+generic-y += trace_clock.h
 generic-y += types.h
 generic-y += ucontext.h
 generic-y += user.h

index bac8deb..ff4c9fa 100644
@@ -3,3 +3,4 @@ generic-y += word-at-a-time.h auxvec.h user.h cputime.h emergency-restart.h \
 	  segment.h topology.h vga.h device.h percpu.h hw_irq.h mutex.h \
 	  div64.h irq_regs.h kdebug.h kvm_para.h local64.h local.h param.h \
 	  poll.h xor.h clkdev.h exec.h
+generic-y += trace_clock.h

index a4fe15e..2d62b48 100644
@@ -2,3 +2,4 @@
 
 generic-y += clkdev.h
 generic-y += rwsem.h
+generic-y += trace_clock.h

index 0633dc6..f313f9c 100644
@@ -1,3 +1,4 @@
 
 
 generic-y += clkdev.h
+generic-y += trace_clock.h

index ec697ae..16e41fe 100644
@@ -3,3 +3,4 @@ include include/asm-generic/Kbuild.asm
 header-y +=
 
 generic-y += clkdev.h
+generic-y += trace_clock.h

index 29f83be..280bea9 100644
@@ -31,5 +31,6 @@ generic-y += socket.h
 generic-y += statfs.h
 generic-y += termbits.h
 generic-y += termios.h
+generic-y += trace_clock.h
 generic-y += ucontext.h
 generic-y += xor.h

index 645a58d..e26d430 100644
@@ -8,4 +8,5 @@ generic-y += local64.h
 generic-y += irq_regs.h
 generic-y += local.h
 generic-y += module.h
+generic-y += trace_clock.h
 generic-y += word-at-a-time.h

index 6948015..b17b9b8 100644
@@ -34,5 +34,6 @@ generic-y += sockios.h
 generic-y += statfs.h
 generic-y += termbits.h
 generic-y += termios.h
+generic-y += trace_clock.h
 generic-y += types.h
 generic-y += xor.h

index 0f6e7b3..b30f34a 100644
@@ -2,3 +2,4 @@ generic-y += bug.h cputime.h device.h emergency-restart.h futex.h hardirq.h
 generic-y += hw_irq.h irq_regs.h kdebug.h percpu.h sections.h topology.h xor.h
 generic-y += ftrace.h pci.h io.h param.h delay.h mutex.h current.h exec.h
 generic-y += switch_to.h clkdev.h
+generic-y += trace_clock.h

index c910c98..7be503e 100644
@@ -54,6 +54,7 @@ generic-y += syscalls.h
 generic-y += termbits.h
 generic-y += termios.h
 generic-y += topology.h
+generic-y += trace_clock.h
 generic-y += types.h
 generic-y += ucontext.h
 generic-y += unaligned.h

new file mode 100644
index 0000000..5c16527
@@ -0,0 +1,20 @@
+#ifndef _ASM_X86_TRACE_CLOCK_H
+#define _ASM_X86_TRACE_CLOCK_H
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+
+#ifdef CONFIG_X86_TSC
+
+extern u64 notrace trace_clock_x86_tsc(void);
+
+# define ARCH_TRACE_CLOCKS \
+	{ trace_clock_x86_tsc,	"x86-tsc" },
+
+#else /* !CONFIG_X86_TSC */
+
+#define ARCH_TRACE_CLOCKS
+
+#endif
+
+#endif  /* _ASM_X86_TRACE_CLOCK_H */

index 9fd5eed..34e923a 100644
@@ -61,6 +61,7 @@ obj-$(CONFIG_X86_REBOOTFIXUPS)	+= reboot_fixups_32.o
 obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
 obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o
 obj-$(CONFIG_FTRACE_SYSCALLS)	+= ftrace.o
+obj-$(CONFIG_X86_TSC)		+= trace_clock.o
 obj-$(CONFIG_KEXEC)		+= machine_kexec_$(BITS).o
 obj-$(CONFIG_KEXEC)		+= relocate_kernel_$(BITS).o crash.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump_$(BITS).o

new file mode 100644
index 0000000..25b9937
@@ -0,0 +1,21 @@
+/*
+ * X86 trace clocks
+ */
+#include <asm/trace_clock.h>
+#include <asm/barrier.h>
+#include <asm/msr.h>
+
+/*
+ * trace_clock_x86_tsc(): A clock that is just the cycle counter.
+ *
+ * Unlike the other clocks, this is not in nanoseconds.
+ */
+u64 notrace trace_clock_x86_tsc(void)
+{
+	u64 ret;
+
+	rdtsc_barrier();
+	rdtscll(ret);
+
+	return ret;
+}

index 6d13027..095f0a2 100644
@@ -25,4 +25,5 @@ generic-y += siginfo.h
 generic-y += statfs.h
 generic-y += termios.h
 generic-y += topology.h
+generic-y += trace_clock.h
 generic-y += xor.h

new file mode 100644
index 0000000..6726f1b
@@ -0,0 +1,16 @@
+#ifndef _ASM_GENERIC_TRACE_CLOCK_H
+#define _ASM_GENERIC_TRACE_CLOCK_H
+/*
+ * Arch-specific trace clocks.
+ */
+
+/*
+ * Additional trace clocks added to the trace_clocks
+ * array in kernel/trace/trace.c
+ * None if the architecture has not defined it.
+ */
+#ifndef ARCH_TRACE_CLOCKS
+# define ARCH_TRACE_CLOCKS
+#endif
+
+#endif  /* _ASM_GENERIC_TRACE_CLOCK_H */

index 4eb4902..d563f37 100644
@@ -12,6 +12,8 @@
 #include <linux/compiler.h>
 #include <linux/types.h>
 
+#include <asm/trace_clock.h>
+
 extern u64 notrace trace_clock_local(void);
 extern u64 notrace trace_clock(void);
 extern u64 notrace trace_clock_global(void);

index c1434b5..0d20620 100644
@@ -488,6 +488,7 @@ static struct {
 	{ trace_clock_local,	"local" },
 	{ trace_clock_global,	"global" },
 	{ trace_clock_counter,	"counter" },
+	ARCH_TRACE_CLOCKS
 };
 
 int trace_clock_id;

1.7.10.4

From: David Sharp <[email protected]>

With the addition of the "tsc" clock, formatting timestamps to look like fractional seconds is misleading. Mark clocks as either in nanoseconds or not, and format non-nanosecond timestamps as decimal integers.

Tested:

$ cd /sys/kernel/debug/tracing/
$ cat trace_clock
[local] global tsc
$ echo sched_switch > set_event
$ echo 1 > tracing_on ; sleep 0.0005 ; echo 0 > tracing_on
$ cat trace
          <idle>-0     [000]  6330.555552: sched_switch: prev_comm=swapper prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=bash next_pid=29964 next_prio=120
           sleep-29964 [000]  6330.555628: sched_switch: prev_comm=bash prev_pid=29964 prev_prio=120 prev_state=S ==> next_comm=swapper next_pid=0 next_prio=120
  ...
$ echo 1 > options/latency-format
$ cat trace
  <idle>-0       0 4104553247us+: sched_switch: prev_comm=swapper prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=bash next_pid=29964 next_prio=120
   sleep-29964   0 4104553322us+: sched_switch: prev_comm=bash prev_pid=29964 prev_prio=120 prev_state=S ==> next_comm=swapper next_pid=0 next_prio=120
  ...
$ echo tsc > trace_clock
$ cat trace
$ echo 1 > tracing_on ; sleep 0.0005 ; echo 0 > tracing_on
$ echo 0 > options/latency-format
$ cat trace
          <idle>-0     [000] 16490053398357: sched_switch: prev_comm=swapper prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=bash next_pid=31128 next_prio=120
           sleep-31128 [000] 16490053588518: sched_switch: prev_comm=bash prev_pid=31128 prev_prio=120 prev_state=S ==> next_comm=swapper next_pid=0 next_prio=120
  ...
echo 1 > options/latency-format
$ cat trace
  <idle>-0       0 91557653238+: sched_switch: prev_comm=swapper prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=bash next_pid=31128 next_prio=120
   sleep-31128   0 91557843399+: sched_switch: prev_comm=bash prev_pid=31128 prev_prio=120 prev_state=S ==> next_comm=swapper next_pid=0 next_prio=120
  ...

v2:
Move arch-specific bits out of generic code.
v4:
Fix x86_32 build due to 64-bit division.

Google-Bug-Id: 6980623

---
 arch/x86/include/asm/trace_clock.h |    2 +-
 include/linux/ftrace_event.h       |    6 +++
 kernel/trace/trace.c               |   15 +++++--
 kernel/trace/trace.h               |    4 --
 kernel/trace/trace_output.c        |   78 ++++++++++++++++++++++++------------
 5 files changed, 72 insertions(+), 33 deletions(-)

index 5c16527..beab86c 100644
@@ -9,7 +9,7 @@
 extern u64 notrace trace_clock_x86_tsc(void);
 
 # define ARCH_TRACE_CLOCKS \
-	{ trace_clock_x86_tsc,	"x86-tsc" },
+	{ trace_clock_x86_tsc,	"x86-tsc",	.in_ns = 0 },
 
 #else /* !CONFIG_X86_TSC */
 

index b80c8dd..a3d4895 100644
@@ -86,6 +86,12 @@ struct trace_iterator {
 	cpumask_var_t		started;
 };
 
+enum trace_iter_flags {
+	TRACE_FILE_LAT_FMT	= 1,
+	TRACE_FILE_ANNOTATE	= 2,
+	TRACE_FILE_TIME_IN_NS	= 4,
+};
+
 
 struct trace_event;
 

index 0d20620..d943e69 100644
@@ -484,10 +484,11 @@ static const char *trace_options[] = {
 static struct {
 	u64 (*func)(void);
 	const char *name;
+	int in_ns;		/* is this clock in nanoseconds? */
 } trace_clocks[] = {
-	{ trace_clock_local,	"local" },
-	{ trace_clock_global,	"global" },
-	{ trace_clock_counter,	"counter" },
+	{ trace_clock_local,	"local",	1 },
+	{ trace_clock_global,	"global",	1 },
+	{ trace_clock_counter,	"counter",	0 },
 	ARCH_TRACE_CLOCKS
 };
 

@@ -2478,6 +2479,10 @@ __tracing_open(struct inode *inode, struct file *file)
 	if (ring_buffer_overruns(iter->tr->buffer))
 		iter->iter_flags |= TRACE_FILE_ANNOTATE;
 
+	/* Output in nanoseconds only if we are using a clock in nanoseconds. */
+	if (trace_clocks[trace_clock_id].in_ns)
+		iter->iter_flags |= TRACE_FILE_TIME_IN_NS;
+
 	/* stop the trace while dumping */
 	tracing_stop();
 

@@ -3339,6 +3344,10 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
 	if (trace_flags & TRACE_ITER_LATENCY_FMT)
 		iter->iter_flags |= TRACE_FILE_LAT_FMT;
 
+	/* Output in nanoseconds only if we are using a clock in nanoseconds. */
+	if (trace_clocks[trace_clock_id].in_ns)
+		iter->iter_flags |= TRACE_FILE_TIME_IN_NS;
+
 	iter->cpu_file = cpu_file;
 	iter->tr = &global_trace;
 	mutex_init(&iter->mutex);

index 55010ed..c75d798 100644
@@ -406,10 +406,6 @@ void tracing_stop_sched_switch_record(void);
 void tracing_start_sched_switch_record(void);
 int register_tracer(struct tracer *type);
 int is_tracing_stopped(void);
-enum trace_file_type {
-	TRACE_FILE_LAT_FMT	= 1,
-	TRACE_FILE_ANNOTATE	= 2,
-};
 
 extern cpumask_var_t __read_mostly tracing_buffer_mask;
 

1.7.10.4

From: Yoshihiro YUNOMAE <[email protected]>

Show raw time stamp values for stats per cpu if you choose counter or tsc mode for trace_clock. Although a unit of tracing time stamp is nsec in local or global mode, the units in counter and TSC mode are tracing counter and cycles respectively.

---
 kernel/trace/trace.c |   23 +++++++++++++++++------
 1 file changed, 17 insertions(+), 6 deletions(-)

index d943e69..b69cc38 100644
@@ -4388,13 +4388,24 @@ tracing_stats_read(struct file *filp, char __user *ubuf,
 	cnt = ring_buffer_bytes_cpu(tr->buffer, cpu);
 	trace_seq_printf(s, "bytes: %ld\n", cnt);
 
-	t = ns2usecs(ring_buffer_oldest_event_ts(tr->buffer, cpu));
-	usec_rem = do_div(t, USEC_PER_SEC);
-	trace_seq_printf(s, "oldest event ts: %5llu.%06lu\n", t, usec_rem);
+	if (trace_clocks[trace_clock_id].in_ns) {
+		/* local or global for trace_clock */
+		t = ns2usecs(ring_buffer_oldest_event_ts(tr->buffer, cpu));
+		usec_rem = do_div(t, USEC_PER_SEC);
+		trace_seq_printf(s, "oldest event ts: %5llu.%06lu\n",
+								t, usec_rem);
+
+		t = ns2usecs(ring_buffer_time_stamp(tr->buffer, cpu));
+		usec_rem = do_div(t, USEC_PER_SEC);
+		trace_seq_printf(s, "now ts: %5llu.%06lu\n", t, usec_rem);
+	} else {
+		/* counter or tsc mode for trace_clock */
+		trace_seq_printf(s, "oldest event ts: %llu\n",
+				ring_buffer_oldest_event_ts(tr->buffer, cpu));
 
-	t = ns2usecs(ring_buffer_time_stamp(tr->buffer, cpu));
-	usec_rem = do_div(t, USEC_PER_SEC);
-	trace_seq_printf(s, "now ts: %5llu.%06lu\n", t, usec_rem);
+		trace_seq_printf(s, "now ts: %llu\n",
+				ring_buffer_time_stamp(tr->buffer, cpu));
+	}
 
 	cnt = ring_buffer_dropped_events_cpu(tr->buffer, cpu);
 	trace_seq_printf(s, "dropped events: %ld\n", cnt);

1.7.10.4

From: Shan Wei <[email protected]>

When doing per-cpu helper optimizing work, find that this code is so puzzled.
1. It's mark as comment text, maybe a sample function for guidelines or a todo work.
2. But, this sample code is odd where struct perf_trace_buf is nonexistent. commit ce71b9 delete struct perf_trace_buf definition.

Author: Frederic Weisbecker <[email protected]>
Date: Sun Nov 22 05:26:55 2009 +0100

tracing: Use the perf recursion protection from trace event

Is it necessary to keep there?
just compile test.

---
 include/trace/ftrace.h |   73 ------------------------------------------------
 1 file changed, 73 deletions(-)

index 698f2a8..40dc5e8 100644
@@ -619,79 +619,6 @@ __attribute__((section("_ftrace_events"))) *__event_##call = &event_##call
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
-/*
- * Define the insertion callback to perf events
- *
- * The job is very similar to ftrace_raw_event_<call> except that we don't
- * insert in the ring buffer but in a perf counter.
- *
- * static void ftrace_perf_<call>(proto)
- * {
- *	struct ftrace_data_offsets_<call> __maybe_unused __data_offsets;
- *	struct ftrace_event_call *event_call = &event_<call>;
- *	extern void perf_tp_event(int, u64, u64, void *, int);
- *	struct ftrace_raw_##call *entry;
- *	struct perf_trace_buf *trace_buf;
- *	u64 __addr = 0, __count = 1;
- *	unsigned long irq_flags;
- *	struct trace_entry *ent;
- *	int __entry_size;
- *	int __data_size;
- *	int __cpu
- *	int pc;
- *
- *	pc = preempt_count();
- *
- *	__data_size = ftrace_get_offsets_<call>(&__data_offsets, args);
- *
- *	// Below we want to get the aligned size by taking into account
- *	// the u32 field that will later store the buffer size
- *	__entry_size = ALIGN(__data_size + sizeof(*entry) + sizeof(u32),
- *			     sizeof(u64));
- *	__entry_size -= sizeof(u32);
- *
- *	// Protect the non nmi buffer
- *	// This also protects the rcu read side
- *	local_irq_save(irq_flags);
- *	__cpu = smp_processor_id();
- *
- *	if (in_nmi())
- *		trace_buf = rcu_dereference_sched(perf_trace_buf_nmi);
- *	else
- *		trace_buf = rcu_dereference_sched(perf_trace_buf);
- *
- *	if (!trace_buf)
- *		goto end;
- *
- *	trace_buf = per_cpu_ptr(trace_buf, __cpu);
- *
- * 	// Avoid recursion from perf that could mess up the buffer
- * 	if (trace_buf->recursion++)
- *		goto end_recursion;
- *
- * 	raw_data = trace_buf->buf;
- *
- *	// Make recursion update visible before entering perf_tp_event
- *	// so that we protect from perf recursions.
- *
- *	barrier();
- *
- *	//zero dead bytes from alignment to avoid stack leak to userspace:
- *	*(u64 *)(&raw_data[__entry_size - sizeof(u64)]) = 0ULL;
- *	entry = (struct ftrace_raw_<call> *)raw_data;
- *	ent = &entry->ent;
- *	tracing_generic_entry_update(ent, irq_flags, pc);
- *	ent->type = event_call->id;
- *
- *	<tstruct> <- do some jobs with dynamic arrays
- *
- *	<assign>  <- affect our values
- *
- *	perf_tp_event(event_call->id, __addr, __count, entry,
- *		     __entry_size);  <- submit them to perf counter
- *
- * }
- */
 
 #ifdef CONFIG_PERF_EVENTS
 

1.7.10.4

Ping

-- Steve

Pulled, thanks Steve!

Ingo