Merge branch 'tip/perf/core' of...

Merge branch 'tip/perf/core' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace into perf/core

Pull ftrace updates from Steve Rostedt.
Signed-off-by: NIngo Molnar <mingo@kernel.org>

arch/alpha/include/asm/Kbuild

@@ -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

arch/arm/include/asm/Kbuild

@@ -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

arch/arm64/include/asm/Kbuild

@@ -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

arch/avr32/include/asm/Kbuild

 
 generic-y	+= clkdev.h
 generic-y	+= exec.h
+generic-y	+= trace_clock.h

arch/blackfin/include/asm/Kbuild

@@ -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

arch/c6x/include/asm/Kbuild

@@ -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

arch/cris/include/asm/Kbuild

@@ -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

arch/frv/include/asm/Kbuild

 
 generic-y += clkdev.h
 generic-y += exec.h
+generic-y += trace_clock.h

arch/h8300/include/asm/Kbuild

@@ -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

arch/hexagon/include/asm/Kbuild

@@ -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

arch/ia64/include/asm/Kbuild

@@ -2,3 +2,4 @@
 generic-y += clkdev.h
 generic-y += exec.h
 generic-y += kvm_para.h
+generic-y += trace_clock.h

arch/m32r/include/asm/Kbuild

@@ -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

arch/m68k/include/asm/Kbuild

@@ -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

arch/microblaze/include/asm/Kbuild

@@ -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

arch/mips/include/asm/Kbuild

 # MIPS headers
+generic-y += trace_clock.h

arch/mn10300/include/asm/Kbuild

 
 generic-y += clkdev.h
 generic-y += exec.h
+generic-y += trace_clock.h

arch/openrisc/include/asm/Kbuild

@@ -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

arch/parisc/include/asm/Kbuild

@@ -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

arch/powerpc/include/asm/Kbuild

@@ -2,3 +2,4 @@
 
 generic-y += clkdev.h
 generic-y += rwsem.h
+generic-y += trace_clock.h

arch/s390/include/asm/Kbuild

 
 
 generic-y += clkdev.h
+generic-y += trace_clock.h

arch/score/include/asm/Kbuild

@@ -3,3 +3,4 @@ include include/asm-generic/Kbuild.asm
 header-y +=
 
 generic-y += clkdev.h
+generic-y += trace_clock.h

arch/sh/include/asm/Kbuild

@@ -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

arch/sparc/include/asm/Kbuild

@@ -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

arch/tile/include/asm/Kbuild

@@ -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

arch/um/include/asm/Kbuild

@@ -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

arch/unicore32/include/asm/Kbuild

@@ -53,6 +53,7 @@ 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

arch/x86/include/asm/trace_clock.h

+#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",	.in_ns = 0 },
+
+#else /* !CONFIG_X86_TSC */
+
+#define ARCH_TRACE_CLOCKS
+
+#endif
+
+#endif  /* _ASM_X86_TRACE_CLOCK_H */

arch/x86/kernel/Makefile

@@ -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

arch/x86/kernel/trace_clock.c

+/*
+ * 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;
+}

arch/xtensa/include/asm/Kbuild

@@ -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

include/asm-generic/trace_clock.h

+#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 */

include/linux/ftrace_event.h

@@ -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;
 

include/linux/trace_clock.h

@@ -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);

include/trace/ftrace.h

@@ -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
 

kernel/trace/trace.c

@@ -484,10 +484,12 @@ 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
 };
 
 int trace_clock_id;
@@ -2477,6 +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();
 
@@ -3338,6 +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);
@@ -4378,13 +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);
+		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));
+
+		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);

kernel/trace/trace.h

@@ -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;
 

kernel/trace/trace_output.c

@@ -610,24 +610,54 @@ lat_print_generic(struct trace_seq *s, struct trace_entry *entry, int cpu)
 	return trace_print_lat_fmt(s, entry);
 }
 
-static unsigned long preempt_mark_thresh = 100;
+static unsigned long preempt_mark_thresh_us = 100;
 
 static int
-lat_print_timestamp(struct trace_seq *s, u64 abs_usecs,
-		    unsigned long rel_usecs)
+lat_print_timestamp(struct trace_iterator *iter, u64 next_ts)
 {
-	return trace_seq_printf(s, " %4lldus%c: ", abs_usecs,
-				rel_usecs > preempt_mark_thresh ? '!' :
-				  rel_usecs > 1 ? '+' : ' ');
+	unsigned long verbose = trace_flags & TRACE_ITER_VERBOSE;
+	unsigned long in_ns = iter->iter_flags & TRACE_FILE_TIME_IN_NS;
+	unsigned long long abs_ts = iter->ts - iter->tr->time_start;
+	unsigned long long rel_ts = next_ts - iter->ts;
+	struct trace_seq *s = &iter->seq;
+
+	if (in_ns) {
+		abs_ts = ns2usecs(abs_ts);
+		rel_ts = ns2usecs(rel_ts);
+	}
+
+	if (verbose && in_ns) {
+		unsigned long abs_usec = do_div(abs_ts, USEC_PER_MSEC);
+		unsigned long abs_msec = (unsigned long)abs_ts;
+		unsigned long rel_usec = do_div(rel_ts, USEC_PER_MSEC);
+		unsigned long rel_msec = (unsigned long)rel_ts;
+
+		return trace_seq_printf(
+				s, "[%08llx] %ld.%03ldms (+%ld.%03ldms): ",
+				ns2usecs(iter->ts),
+				abs_msec, abs_usec,
+				rel_msec, rel_usec);
+	} else if (verbose && !in_ns) {
+		return trace_seq_printf(
+				s, "[%016llx] %lld (+%lld): ",
+				iter->ts, abs_ts, rel_ts);
+	} else if (!verbose && in_ns) {
+		return trace_seq_printf(
+				s, " %4lldus%c: ",
+				abs_ts,
+				rel_ts > preempt_mark_thresh_us ? '!' :
+				  rel_ts > 1 ? '+' : ' ');
+	} else { /* !verbose && !in_ns */
+		return trace_seq_printf(s, " %4lld: ", abs_ts);
+	}
 }
 
 int trace_print_context(struct trace_iterator *iter)
 {
 	struct trace_seq *s = &iter->seq;
 	struct trace_entry *entry = iter->ent;
-	unsigned long long t = ns2usecs(iter->ts);
-	unsigned long usec_rem = do_div(t, USEC_PER_SEC);
-	unsigned long secs = (unsigned long)t;
+	unsigned long long t;
+	unsigned long secs, usec_rem;
 	char comm[TASK_COMM_LEN];
 	int ret;
 
@@ -644,8 +674,13 @@ int trace_print_context(struct trace_iterator *iter)
 			return 0;
 	}
 
-	return trace_seq_printf(s, " %5lu.%06lu: ",
-				secs, usec_rem);
+	if (iter->iter_flags & TRACE_FILE_TIME_IN_NS) {
+		t = ns2usecs(iter->ts);
+		usec_rem = do_div(t, USEC_PER_SEC);
+		secs = (unsigned long)t;
+		return trace_seq_printf(s, " %5lu.%06lu: ", secs, usec_rem);
+	} else
+		return trace_seq_printf(s, " %12llu: ", iter->ts);
 }
 
 int trace_print_lat_context(struct trace_iterator *iter)
@@ -659,36 +694,29 @@ int trace_print_lat_context(struct trace_iterator *iter)
 			   *next_entry = trace_find_next_entry(iter, NULL,
 							       &next_ts);
 	unsigned long verbose = (trace_flags & TRACE_ITER_VERBOSE);
-	unsigned long abs_usecs = ns2usecs(iter->ts - iter->tr->time_start);
-	unsigned long rel_usecs;
 
 	/* Restore the original ent_size */
 	iter->ent_size = ent_size;
 
 	if (!next_entry)
 		next_ts = iter->ts;
-	rel_usecs = ns2usecs(next_ts - iter->ts);
 
 	if (verbose) {
 		char comm[TASK_COMM_LEN];
 
 		trace_find_cmdline(entry->pid, comm);
 
-		ret = trace_seq_printf(s, "%16s %5d %3d %d %08x %08lx [%08llx]"
-				       " %ld.%03ldms (+%ld.%03ldms): ", comm,
-				       entry->pid, iter->cpu, entry->flags,
-				       entry->preempt_count, iter->idx,
-				       ns2usecs(iter->ts),
-				       abs_usecs / USEC_PER_MSEC,
-				       abs_usecs % USEC_PER_MSEC,
-				       rel_usecs / USEC_PER_MSEC,
-				       rel_usecs % USEC_PER_MSEC);
+		ret = trace_seq_printf(
+				s, "%16s %5d %3d %d %08x %08lx ",
+				comm, entry->pid, iter->cpu, entry->flags,
+				entry->preempt_count, iter->idx);
 	} else {
 		ret = lat_print_generic(s, entry, iter->cpu);
-		if (ret)
-			ret = lat_print_timestamp(s, abs_usecs, rel_usecs);
 	}
 
+	if (ret)
+		ret = lat_print_timestamp(iter, next_ts);
+
 	return ret;
 }