Merge branch 'tracing-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'tracing-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (413 commits) tracing, net: fix net tree and tracing tree merge interaction tracing, powerpc: fix powerpc tree and tracing tree interaction ring-buffer: do not remove reader page from list on ring buffer free function-graph: allow unregistering twice trace: make argument 'mem' of trace_seq_putmem() const tracing: add missing 'extern' keywords to trace_output.h tracing: provide trace_seq_reserve() blktrace: print out BLK_TN_MESSAGE properly blktrace: extract duplidate code blktrace: fix memory leak when freeing struct blk_io_trace blktrace: fix blk_probes_ref chaos blktrace: make classic output more classic blktrace: fix off-by-one bug blktrace: fix the original blktrace blktrace: fix a race when creating blk_tree_root in debugfs blktrace: fix timestamp in binary output tracing, Text Edit Lock: cleanup tracing: filter fix for TRACE_EVENT_FORMAT events ftrace: Using FTRACE_WARN_ON() to check "freed record" in ftrace_release() x86: kretprobe-booster interrupt emulation code fix ... Fix up trivial conflicts in arch/parisc/include/asm/ftrace.h include/linux/memory.h kernel/extable.c kernel/module.c
2026-05-01 15:00:59 -07:00 · 2009-04-05 11:04:19 -07:00
parent 8901e7ffc2 645dae969c
commit 714f83d5d9
145 changed files with 13836 additions and 3480 deletions
@@ -15,11 +15,22 @@
    along with this program; if not, write to the Free Software
    Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 */
-#include <linux/module.h>
-#include <linux/init.h>
 #include <linux/ftrace.h>
-#include <asm/uaccess.h>
+#include <linux/memory.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/init.h>
+
 #include <asm/sections.h>
+#include <asm/uaccess.h>
+
+/*
+ * mutex protecting text section modification (dynamic code patching).
+ * some users need to sleep (allocating memory...) while they hold this lock.
+ *
+ * NOT exported to modules - patching kernel text is a really delicate matter.
+ */
+DEFINE_MUTEX(text_mutex);

 extern struct exception_table_entry __start___ex_table[];
 extern struct exception_table_entry __stop___ex_table[];
@@ -49,7 +60,7 @@ static inline int init_kernel_text(unsigned long addr)
 	return 0;
 }

-__notrace_funcgraph int core_kernel_text(unsigned long addr)
+int core_kernel_text(unsigned long addr)
 {
 	if (addr >= (unsigned long)_stext &&
 	    addr <= (unsigned long)_etext)
@@ -61,7 +72,7 @@ __notrace_funcgraph int core_kernel_text(unsigned long addr)
 	return 0;
 }

-__notrace_funcgraph int __kernel_text_address(unsigned long addr)
+int __kernel_text_address(unsigned long addr)
 {
 	if (core_kernel_text(addr))
 		return 1;
@@ -17,6 +17,7 @@
 #include <linux/kernel_stat.h>
 #include <linux/rculist.h>
 #include <linux/hash.h>
+#include <trace/irq.h>
 #include <linux/bootmem.h>

 #include "internals.h"
@@ -338,6 +339,9 @@ irqreturn_t no_action(int cpl, void *dev_id)
 	return IRQ_NONE;
 }

+DEFINE_TRACE(irq_handler_entry);
+DEFINE_TRACE(irq_handler_exit);
+
 /**
 * handle_IRQ_event - irq action chain handler
 * @irq:	the interrupt number
@@ -356,7 +360,9 @@ irqreturn_t handle_IRQ_event(unsigned int irq, struct irqaction *action)
 		local_irq_enable_in_hardirq();

 	do {
+		trace_irq_handler_entry(irq, action);
 		ret = action->handler(irq, action->dev_id);
+		trace_irq_handler_exit(irq, action, ret);
 		if (ret == IRQ_HANDLED)
 			status |= action->flags;
 		retval |= ret;
@@ -43,6 +43,7 @@
 #include <linux/seq_file.h>
 #include <linux/debugfs.h>
 #include <linux/kdebug.h>
+#include <linux/memory.h>

 #include <asm-generic/sections.h>
 #include <asm/cacheflush.h>
@@ -699,9 +700,10 @@ int __kprobes register_kprobe(struct kprobe *p)
 		goto out;
 	}

+	mutex_lock(&text_mutex);
 	ret = arch_prepare_kprobe(p);
 	if (ret)
-		goto out;
+		goto out_unlock_text;

 	INIT_HLIST_NODE(&p->hlist);
 	hlist_add_head_rcu(&p->hlist,
@@ -710,6 +712,8 @@ int __kprobes register_kprobe(struct kprobe *p)
 	if (kprobe_enabled)
 		arch_arm_kprobe(p);

+out_unlock_text:
+	mutex_unlock(&text_mutex);
 out:
 	mutex_unlock(&kprobe_mutex);

@@ -746,8 +750,11 @@ valid_p:
 		 * enabled and not gone - otherwise, the breakpoint would
 		 * already have been removed. We save on flushing icache.
 		 */
-		if (kprobe_enabled && !kprobe_gone(old_p))
+		if (kprobe_enabled && !kprobe_gone(old_p)) {
+			mutex_lock(&text_mutex);
 			arch_disarm_kprobe(p);
+			mutex_unlock(&text_mutex);
+		}
 		hlist_del_rcu(&old_p->hlist);
 	} else {
 		if (p->break_handler && !kprobe_gone(p))
@@ -912,10 +919,8 @@ static int __kprobes pre_handler_kretprobe(struct kprobe *p,
 		ri->rp = rp;
 		ri->task = current;

-		if (rp->entry_handler && rp->entry_handler(ri, regs)) {
-			spin_unlock_irqrestore(&rp->lock, flags);
+		if (rp->entry_handler && rp->entry_handler(ri, regs))
 			return 0;
-		}

 		arch_prepare_kretprobe(ri, regs);

@@ -1280,12 +1285,14 @@ static void __kprobes enable_all_kprobes(void)
 	if (kprobe_enabled)
 		goto already_enabled;

+	mutex_lock(&text_mutex);
 	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
 		head = &kprobe_table[i];
 		hlist_for_each_entry_rcu(p, node, head, hlist)
 			if (!kprobe_gone(p))
 				arch_arm_kprobe(p);
 	}
+	mutex_unlock(&text_mutex);

 	kprobe_enabled = true;
 	printk(KERN_INFO "Kprobes globally enabled\n");
@@ -1310,6 +1317,7 @@ static void __kprobes disable_all_kprobes(void)

 	kprobe_enabled = false;
 	printk(KERN_INFO "Kprobes globally disabled\n");
+	mutex_lock(&text_mutex);
 	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
 		head = &kprobe_table[i];
 		hlist_for_each_entry_rcu(p, node, head, hlist) {
@@ -1318,6 +1326,7 @@ static void __kprobes disable_all_kprobes(void)
 		}
 	}

+	mutex_unlock(&text_mutex);
 	mutex_unlock(&kprobe_mutex);
 	/* Allow all currently running kprobes to complete */
 	synchronize_sched();
@@ -42,6 +42,7 @@
 #include <linux/hash.h>
 #include <linux/ftrace.h>
 #include <linux/stringify.h>
+#include <trace/lockdep.h>

 #include <asm/sections.h>

@@ -2923,6 +2924,8 @@ void lock_set_class(struct lockdep_map *lock, const char *name,
 }
 EXPORT_SYMBOL_GPL(lock_set_class);

+DEFINE_TRACE(lock_acquire);
+
 /*
 * We are not always called with irqs disabled - do that here,
 * and also avoid lockdep recursion:
@@ -2933,6 +2936,8 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 {
 	unsigned long flags;

+	trace_lock_acquire(lock, subclass, trylock, read, check, nest_lock, ip);
+
 	if (unlikely(current->lockdep_recursion))
 		return;

@@ -2947,11 +2952,15 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 }
 EXPORT_SYMBOL_GPL(lock_acquire);

+DEFINE_TRACE(lock_release);
+
 void lock_release(struct lockdep_map *lock, int nested,
 			  unsigned long ip)
 {
 	unsigned long flags;

+	trace_lock_release(lock, nested, ip);
+
 	if (unlikely(current->lockdep_recursion))
 		return;

@@ -3100,10 +3109,14 @@ found_it:
 	lock->ip = ip;
 }

+DEFINE_TRACE(lock_contended);
+
 void lock_contended(struct lockdep_map *lock, unsigned long ip)
 {
 	unsigned long flags;

+	trace_lock_contended(lock, ip);
+
 	if (unlikely(!lock_stat))
 		return;

@@ -3119,10 +3132,14 @@ void lock_contended(struct lockdep_map *lock, unsigned long ip)
 }
 EXPORT_SYMBOL_GPL(lock_contended);

+DEFINE_TRACE(lock_acquired);
+
 void lock_acquired(struct lockdep_map *lock, unsigned long ip)
 {
 	unsigned long flags;

+	trace_lock_acquired(lock, ip);
+
 	if (unlikely(!lock_stat))
 		return;

@@ -2777,7 +2777,7 @@ bool is_module_address(unsigned long addr)
 * Must be called with preempt disabled or module mutex held so that
 * module doesn't get freed during this.
 */
-__notrace_funcgraph struct module *__module_address(unsigned long addr)
+struct module *__module_address(unsigned long addr)
 {
 	struct module *mod;

@@ -677,9 +677,7 @@ int relay_late_setup_files(struct rchan *chan,
 	 */
 	for_each_online_cpu(i) {
 		if (unlikely(!chan->buf[i])) {
-			printk(KERN_ERR "relay_late_setup_files: CPU %u "
-					"has no buffer, it must have!\n", i);
-			BUG();
+			WARN_ONCE(1, KERN_ERR "CPU has no buffer!\n");
 			err = -EINVAL;
 			break;
 		}
@@ -4773,10 +4773,7 @@ void scheduler_tick(void)
 #endif
 }

-#if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \
-				defined(CONFIG_PREEMPT_TRACER))
-
-static inline unsigned long get_parent_ip(unsigned long addr)
+unsigned long get_parent_ip(unsigned long addr)
 {
 	if (in_lock_functions(addr)) {
 		addr = CALLER_ADDR2;
@@ -4786,6 +4783,9 @@ static inline unsigned long get_parent_ip(unsigned long addr)
 	return addr;
 }

+#if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \
+				defined(CONFIG_PREEMPT_TRACER))
+
 void __kprobes add_preempt_count(int val)
 {
 #ifdef CONFIG_DEBUG_PREEMPT
@@ -25,6 +25,7 @@
 * consistent between cpus (never more than 2 jiffies difference).
 */
 #include <linux/spinlock.h>
+#include <linux/hardirq.h>
 #include <linux/module.h>
 #include <linux/percpu.h>
 #include <linux/ktime.h>
@@ -154,6 +155,17 @@ u64 sched_clock_cpu(int cpu)
 		return sched_clock();

 	scd = cpu_sdc(cpu);
+
+	/*
+	 * Normally this is not called in NMI context - but if it is,
+	 * trying to do any locking here is totally lethal.
+	 */
+	if (unlikely(in_nmi()))
+		return scd->clock;
+
+	if (unlikely(!sched_clock_running))
+		return 0ull;
+
 	WARN_ON_ONCE(!irqs_disabled());
 	now = sched_clock();

@@ -21,8 +21,10 @@
 #include <linux/freezer.h>
 #include <linux/kthread.h>
 #include <linux/rcupdate.h>
+#include <linux/ftrace.h>
 #include <linux/smp.h>
 #include <linux/tick.h>
+#include <trace/irq.h>

 #include <asm/irq.h>
 /*
@@ -52,6 +54,11 @@ static struct softirq_action softirq_vec[NR_SOFTIRQS] __cacheline_aligned_in_smp

 static DEFINE_PER_CPU(struct task_struct *, ksoftirqd);

+char *softirq_to_name[NR_SOFTIRQS] = {
+	"HI", "TIMER", "NET_TX", "NET_RX", "BLOCK",
+	"TASKLET", "SCHED", "HRTIMER",	"RCU"
+};
+
 /*
 * we cannot loop indefinitely here to avoid userspace starvation,
 * but we also don't want to introduce a worst case 1/HZ latency
@@ -79,13 +86,23 @@ static void __local_bh_disable(unsigned long ip)
 	WARN_ON_ONCE(in_irq());

 	raw_local_irq_save(flags);
-	add_preempt_count(SOFTIRQ_OFFSET);
+	/*
+	 * The preempt tracer hooks into add_preempt_count and will break
+	 * lockdep because it calls back into lockdep after SOFTIRQ_OFFSET
+	 * is set and before current->softirq_enabled is cleared.
+	 * We must manually increment preempt_count here and manually
+	 * call the trace_preempt_off later.
+	 */
+	preempt_count() += SOFTIRQ_OFFSET;
 	/*
 	 * Were softirqs turned off above:
 	 */
 	if (softirq_count() == SOFTIRQ_OFFSET)
 		trace_softirqs_off(ip);
 	raw_local_irq_restore(flags);
+
+	if (preempt_count() == SOFTIRQ_OFFSET)
+		trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
 }
 #else /* !CONFIG_TRACE_IRQFLAGS */
 static inline void __local_bh_disable(unsigned long ip)
@@ -169,6 +186,9 @@ EXPORT_SYMBOL(local_bh_enable_ip);
 */
 #define MAX_SOFTIRQ_RESTART 10

+DEFINE_TRACE(softirq_entry);
+DEFINE_TRACE(softirq_exit);
+
 asmlinkage void __do_softirq(void)
 {
 	struct softirq_action *h;
@@ -195,12 +215,14 @@ restart:
 		if (pending & 1) {
 			int prev_count = preempt_count();

+			trace_softirq_entry(h, softirq_vec);
 			h->action(h);
-
+			trace_softirq_exit(h, softirq_vec);
 			if (unlikely(prev_count != preempt_count())) {
-				printk(KERN_ERR "huh, entered softirq %td %p"
+				printk(KERN_ERR "huh, entered softirq %td %s %p"
 				       "with preempt_count %08x,"
 				       " exited with %08x?\n", h - softirq_vec,
+				       softirq_to_name[h - softirq_vec],
 				       h->action, prev_count, preempt_count());
 				preempt_count() = prev_count;
 			}
@@ -9,6 +9,9 @@ config USER_STACKTRACE_SUPPORT
 config NOP_TRACER
 	bool

+config HAVE_FTRACE_NMI_ENTER
+	bool
+
 config HAVE_FUNCTION_TRACER
 	bool

@@ -31,12 +34,20 @@ config HAVE_FTRACE_MCOUNT_RECORD
 config HAVE_HW_BRANCH_TRACER
 	bool

+config HAVE_FTRACE_SYSCALLS
+	bool
+
 config TRACER_MAX_TRACE
 	bool

 config RING_BUFFER
 	bool

+config FTRACE_NMI_ENTER
+       bool
+       depends on HAVE_FTRACE_NMI_ENTER
+       default y
+
 config TRACING
 	bool
 	select DEBUG_FS
@@ -44,13 +55,29 @@ config TRACING
 	select STACKTRACE if STACKTRACE_SUPPORT
 	select TRACEPOINTS
 	select NOP_TRACER
+	select BINARY_PRINTF
+
+#
+# Minimum requirements an architecture has to meet for us to
+# be able to offer generic tracing facilities:
+#
+config TRACING_SUPPORT
+	bool
+	# PPC32 has no irqflags tracing support, but it can use most of the
+	# tracers anyway, they were tested to build and work. Note that new
+	# exceptions to this list aren't welcomed, better implement the
+	# irqflags tracing for your architecture.
+	depends on TRACE_IRQFLAGS_SUPPORT || PPC32
+	depends on STACKTRACE_SUPPORT
+	default y
+
+if TRACING_SUPPORT

 menu "Tracers"

 config FUNCTION_TRACER
 	bool "Kernel Function Tracer"
 	depends on HAVE_FUNCTION_TRACER
-	depends on DEBUG_KERNEL
 	select FRAME_POINTER
 	select KALLSYMS
 	select TRACING
@@ -82,7 +109,6 @@ config IRQSOFF_TRACER
 	default n
 	depends on TRACE_IRQFLAGS_SUPPORT
 	depends on GENERIC_TIME
-	depends on DEBUG_KERNEL
 	select TRACE_IRQFLAGS
 	select TRACING
 	select TRACER_MAX_TRACE
@@ -105,7 +131,6 @@ config PREEMPT_TRACER
 	default n
 	depends on GENERIC_TIME
 	depends on PREEMPT
-	depends on DEBUG_KERNEL
 	select TRACING
 	select TRACER_MAX_TRACE
 	help
@@ -126,13 +151,13 @@ config SYSPROF_TRACER
 	bool "Sysprof Tracer"
 	depends on X86
 	select TRACING
+	select CONTEXT_SWITCH_TRACER
 	help
 	  This tracer provides the trace needed by the 'Sysprof' userspace
 	  tool.

 config SCHED_TRACER
 	bool "Scheduling Latency Tracer"
-	depends on DEBUG_KERNEL
 	select TRACING
 	select CONTEXT_SWITCH_TRACER
 	select TRACER_MAX_TRACE
@@ -142,16 +167,30 @@ config SCHED_TRACER

 config CONTEXT_SWITCH_TRACER
 	bool "Trace process context switches"
-	depends on DEBUG_KERNEL
 	select TRACING
 	select MARKERS
 	help
 	  This tracer gets called from the context switch and records
 	  all switching of tasks.

+config EVENT_TRACER
+	bool "Trace various events in the kernel"
+	select TRACING
+	help
+	  This tracer hooks to various trace points in the kernel
+	  allowing the user to pick and choose which trace point they
+	  want to trace.
+
+config FTRACE_SYSCALLS
+	bool "Trace syscalls"
+	depends on HAVE_FTRACE_SYSCALLS
+	select TRACING
+	select KALLSYMS
+	help
+	  Basic tracer to catch the syscall entry and exit events.
+
 config BOOT_TRACER
 	bool "Trace boot initcalls"
-	depends on DEBUG_KERNEL
 	select TRACING
 	select CONTEXT_SWITCH_TRACER
 	help
@@ -164,13 +203,11 @@ config BOOT_TRACER
 	  representation of the delays during initcalls - but the raw
 	  /debug/tracing/trace text output is readable too.

-	  ( Note that tracing self tests can't be enabled if this tracer is
-	    selected, because the self-tests are an initcall as well and that
-	    would invalidate the boot trace. )
+	  You must pass in ftrace=initcall to the kernel command line
+	  to enable this on bootup.

 config TRACE_BRANCH_PROFILING
 	bool "Trace likely/unlikely profiler"
-	depends on DEBUG_KERNEL
 	select TRACING
 	help
 	  This tracer profiles all the the likely and unlikely macros
@@ -223,7 +260,6 @@ config BRANCH_TRACER

 config POWER_TRACER
 	bool "Trace power consumption behavior"
-	depends on DEBUG_KERNEL
 	depends on X86
 	select TRACING
 	help
@@ -235,7 +271,6 @@ config POWER_TRACER
 config STACK_TRACER
 	bool "Trace max stack"
 	depends on HAVE_FUNCTION_TRACER
-	depends on DEBUG_KERNEL
 	select FUNCTION_TRACER
 	select STACKTRACE
 	select KALLSYMS
@@ -265,11 +300,66 @@ config HW_BRANCH_TRACER
 	  This tracer records all branches on the system in a circular
 	  buffer giving access to the last N branches for each cpu.

+config KMEMTRACE
+	bool "Trace SLAB allocations"
+	select TRACING
+	help
+	  kmemtrace provides tracing for slab allocator functions, such as
+	  kmalloc, kfree, kmem_cache_alloc, kmem_cache_free etc.. Collected
+	  data is then fed to the userspace application in order to analyse
+	  allocation hotspots, internal fragmentation and so on, making it
+	  possible to see how well an allocator performs, as well as debug
+	  and profile kernel code.
+
+	  This requires an userspace application to use. See
+	  Documentation/vm/kmemtrace.txt for more information.
+
+	  Saying Y will make the kernel somewhat larger and slower. However,
+	  if you disable kmemtrace at run-time or boot-time, the performance
+	  impact is minimal (depending on the arch the kernel is built for).
+
+	  If unsure, say N.
+
+config WORKQUEUE_TRACER
+	bool "Trace workqueues"
+	select TRACING
+	help
+	  The workqueue tracer provides some statistical informations
+          about each cpu workqueue thread such as the number of the
+          works inserted and executed since their creation. It can help
+          to evaluate the amount of work each of them have to perform.
+          For example it can help a developer to decide whether he should
+          choose a per cpu workqueue instead of a singlethreaded one.
+
+config BLK_DEV_IO_TRACE
+	bool "Support for tracing block io actions"
+	depends on SYSFS
+	depends on BLOCK
+	select RELAY
+	select DEBUG_FS
+	select TRACEPOINTS
+	select TRACING
+	select STACKTRACE
+	help
+	  Say Y here if you want to be able to trace the block layer actions
+	  on a given queue. Tracing allows you to see any traffic happening
+	  on a block device queue. For more information (and the userspace
+	  support tools needed), fetch the blktrace tools from:
+
+	  git://git.kernel.dk/blktrace.git
+
+	  Tracing also is possible using the ftrace interface, e.g.:
+
+	    echo 1 > /sys/block/sda/sda1/trace/enable
+	    echo blk > /sys/kernel/debug/tracing/current_tracer
+	    cat /sys/kernel/debug/tracing/trace_pipe
+
+	  If unsure, say N.
+
 config DYNAMIC_FTRACE
 	bool "enable/disable ftrace tracepoints dynamically"
 	depends on FUNCTION_TRACER
 	depends on HAVE_DYNAMIC_FTRACE
-	depends on DEBUG_KERNEL
 	default y
 	help
         This option will modify all the calls to ftrace dynamically
@@ -295,7 +385,7 @@ config FTRACE_SELFTEST

 config FTRACE_STARTUP_TEST
 	bool "Perform a startup test on ftrace"
-	depends on TRACING && DEBUG_KERNEL && !BOOT_TRACER
+	depends on TRACING
 	select FTRACE_SELFTEST
 	help
 	  This option performs a series of startup tests on ftrace. On bootup
@@ -305,7 +395,7 @@ config FTRACE_STARTUP_TEST

 config MMIOTRACE
 	bool "Memory mapped IO tracing"
-	depends on HAVE_MMIOTRACE_SUPPORT && DEBUG_KERNEL && PCI
+	depends on HAVE_MMIOTRACE_SUPPORT && PCI
 	select TRACING
 	help
 	  Mmiotrace traces Memory Mapped I/O access and is meant for
@@ -327,3 +417,6 @@ config MMIOTRACE_TEST
 	  Say N, unless you absolutely know what you are doing.

 endmenu
+
+endif # TRACING_SUPPORT
+
@@ -19,6 +19,10 @@ obj-$(CONFIG_FUNCTION_TRACER) += libftrace.o
 obj-$(CONFIG_RING_BUFFER) += ring_buffer.o

 obj-$(CONFIG_TRACING) += trace.o
+obj-$(CONFIG_TRACING) += trace_clock.o
+obj-$(CONFIG_TRACING) += trace_output.o
+obj-$(CONFIG_TRACING) += trace_stat.o
+obj-$(CONFIG_TRACING) += trace_printk.o
 obj-$(CONFIG_CONTEXT_SWITCH_TRACER) += trace_sched_switch.o
 obj-$(CONFIG_SYSPROF_TRACER) += trace_sysprof.o
 obj-$(CONFIG_FUNCTION_TRACER) += trace_functions.o
@@ -33,5 +37,14 @@ obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += trace_functions_graph.o
 obj-$(CONFIG_TRACE_BRANCH_PROFILING) += trace_branch.o
 obj-$(CONFIG_HW_BRANCH_TRACER) += trace_hw_branches.o
 obj-$(CONFIG_POWER_TRACER) += trace_power.o
+obj-$(CONFIG_KMEMTRACE) += kmemtrace.o
+obj-$(CONFIG_WORKQUEUE_TRACER) += trace_workqueue.o
+obj-$(CONFIG_BLK_DEV_IO_TRACE)	+= blktrace.o
+obj-$(CONFIG_EVENT_TRACER) += trace_events.o
+obj-$(CONFIG_EVENT_TRACER) += events.o
+obj-$(CONFIG_EVENT_TRACER) += trace_export.o
+obj-$(CONFIG_FTRACE_SYSCALLS) += trace_syscalls.o
+obj-$(CONFIG_EVENT_PROFILE) += trace_event_profile.o
+obj-$(CONFIG_EVENT_TRACER) += trace_events_filter.o

 libftrace-y := ftrace.o
@@ -0,0 +1,14 @@
+/*
+ * This is the place to register all trace points as events.
+ */
+
+#include <linux/stringify.h>
+
+#include <trace/trace_events.h>
+
+#include "trace_output.h"
+
+#include "trace_events_stage_1.h"
+#include "trace_events_stage_2.h"
+#include "trace_events_stage_3.h"
+
@@ -0,0 +1,339 @@
+/*
+ * Memory allocator tracing
+ *
+ * Copyright (C) 2008 Eduard - Gabriel Munteanu
+ * Copyright (C) 2008 Pekka Enberg <penberg@cs.helsinki.fi>
+ * Copyright (C) 2008 Frederic Weisbecker <fweisbec@gmail.com>
+ */
+
+#include <linux/dcache.h>
+#include <linux/debugfs.h>
+#include <linux/fs.h>
+#include <linux/seq_file.h>
+#include <trace/kmemtrace.h>
+
+#include "trace.h"
+#include "trace_output.h"
+
+/* Select an alternative, minimalistic output than the original one */
+#define TRACE_KMEM_OPT_MINIMAL	0x1
+
+static struct tracer_opt kmem_opts[] = {
+	/* Default disable the minimalistic output */
+	{ TRACER_OPT(kmem_minimalistic, TRACE_KMEM_OPT_MINIMAL) },
+	{ }
+};
+
+static struct tracer_flags kmem_tracer_flags = {
+	.val = 0,
+	.opts = kmem_opts
+};
+
+
+static bool kmem_tracing_enabled __read_mostly;
+static struct trace_array *kmemtrace_array;
+
+static int kmem_trace_init(struct trace_array *tr)
+{
+	int cpu;
+	kmemtrace_array = tr;
+
+	for_each_cpu_mask(cpu, cpu_possible_map)
+		tracing_reset(tr, cpu);
+
+	kmem_tracing_enabled = true;
+
+	return 0;
+}
+
+static void kmem_trace_reset(struct trace_array *tr)
+{
+	kmem_tracing_enabled = false;
+}
+
+static void kmemtrace_headers(struct seq_file *s)
+{
+	/* Don't need headers for the original kmemtrace output */
+	if (!(kmem_tracer_flags.val & TRACE_KMEM_OPT_MINIMAL))
+		return;
+
+	seq_printf(s, "#\n");
+	seq_printf(s, "# ALLOC  TYPE  REQ   GIVEN  FLAGS     "
+			"      POINTER         NODE    CALLER\n");
+	seq_printf(s, "# FREE   |      |     |       |       "
+			"       |   |            |        |\n");
+	seq_printf(s, "# |\n\n");
+}
+
+/*
+ * The two following functions give the original output from kmemtrace,
+ * or something close to....perhaps they need some missing things
+ */
+static enum print_line_t
+kmemtrace_print_alloc_original(struct trace_iterator *iter,
+				struct kmemtrace_alloc_entry *entry)
+{
+	struct trace_seq *s = &iter->seq;
+	int ret;
+
+	/* Taken from the old linux/kmemtrace.h */
+	ret = trace_seq_printf(s, "type_id %d call_site %lu ptr %lu "
+	  "bytes_req %lu bytes_alloc %lu gfp_flags %lu node %d\n",
+	   entry->type_id, entry->call_site, (unsigned long) entry->ptr,
+	   (unsigned long) entry->bytes_req, (unsigned long) entry->bytes_alloc,
+	   (unsigned long) entry->gfp_flags, entry->node);
+
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t
+kmemtrace_print_free_original(struct trace_iterator *iter,
+				struct kmemtrace_free_entry *entry)
+{
+	struct trace_seq *s = &iter->seq;
+	int ret;
+
+	/* Taken from the old linux/kmemtrace.h */
+	ret = trace_seq_printf(s, "type_id %d call_site %lu ptr %lu\n",
+	   entry->type_id, entry->call_site, (unsigned long) entry->ptr);
+
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	return TRACE_TYPE_HANDLED;
+}
+
+
+/* The two other following provide a more minimalistic output */
+static enum print_line_t
+kmemtrace_print_alloc_compress(struct trace_iterator *iter,
+					struct kmemtrace_alloc_entry *entry)
+{
+	struct trace_seq *s = &iter->seq;
+	int ret;
+
+	/* Alloc entry */
+	ret = trace_seq_printf(s, "  +      ");
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	/* Type */
+	switch (entry->type_id) {
+	case KMEMTRACE_TYPE_KMALLOC:
+		ret = trace_seq_printf(s, "K   ");
+		break;
+	case KMEMTRACE_TYPE_CACHE:
+		ret = trace_seq_printf(s, "C   ");
+		break;
+	case KMEMTRACE_TYPE_PAGES:
+		ret = trace_seq_printf(s, "P   ");
+		break;
+	default:
+		ret = trace_seq_printf(s, "?   ");
+	}
+
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	/* Requested */
+	ret = trace_seq_printf(s, "%4zu   ", entry->bytes_req);
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	/* Allocated */
+	ret = trace_seq_printf(s, "%4zu   ", entry->bytes_alloc);
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	/* Flags
+	 * TODO: would be better to see the name of the GFP flag names
+	 */
+	ret = trace_seq_printf(s, "%08x   ", entry->gfp_flags);
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	/* Pointer to allocated */
+	ret = trace_seq_printf(s, "0x%tx   ", (ptrdiff_t)entry->ptr);
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	/* Node */
+	ret = trace_seq_printf(s, "%4d   ", entry->node);
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	/* Call site */
+	ret = seq_print_ip_sym(s, entry->call_site, 0);
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	if (!trace_seq_printf(s, "\n"))
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t
+kmemtrace_print_free_compress(struct trace_iterator *iter,
+				struct kmemtrace_free_entry *entry)
+{
+	struct trace_seq *s = &iter->seq;
+	int ret;
+
+	/* Free entry */
+	ret = trace_seq_printf(s, "  -      ");
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	/* Type */
+	switch (entry->type_id) {
+	case KMEMTRACE_TYPE_KMALLOC:
+		ret = trace_seq_printf(s, "K     ");
+		break;
+	case KMEMTRACE_TYPE_CACHE:
+		ret = trace_seq_printf(s, "C     ");
+		break;
+	case KMEMTRACE_TYPE_PAGES:
+		ret = trace_seq_printf(s, "P     ");
+		break;
+	default:
+		ret = trace_seq_printf(s, "?     ");
+	}
+
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	/* Skip requested/allocated/flags */
+	ret = trace_seq_printf(s, "                       ");
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	/* Pointer to allocated */
+	ret = trace_seq_printf(s, "0x%tx   ", (ptrdiff_t)entry->ptr);
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	/* Skip node */
+	ret = trace_seq_printf(s, "       ");
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	/* Call site */
+	ret = seq_print_ip_sym(s, entry->call_site, 0);
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	if (!trace_seq_printf(s, "\n"))
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t kmemtrace_print_line(struct trace_iterator *iter)
+{
+	struct trace_entry *entry = iter->ent;
+
+	switch (entry->type) {
+	case TRACE_KMEM_ALLOC: {
+		struct kmemtrace_alloc_entry *field;
+		trace_assign_type(field, entry);
+		if (kmem_tracer_flags.val & TRACE_KMEM_OPT_MINIMAL)
+			return kmemtrace_print_alloc_compress(iter, field);
+		else
+			return kmemtrace_print_alloc_original(iter, field);
+	}
+
+	case TRACE_KMEM_FREE: {
+		struct kmemtrace_free_entry *field;
+		trace_assign_type(field, entry);
+		if (kmem_tracer_flags.val & TRACE_KMEM_OPT_MINIMAL)
+			return kmemtrace_print_free_compress(iter, field);
+		else
+			return kmemtrace_print_free_original(iter, field);
+	}
+
+	default:
+		return TRACE_TYPE_UNHANDLED;
+	}
+}
+
+/* Trace allocations */
+void kmemtrace_mark_alloc_node(enum kmemtrace_type_id type_id,
+			     unsigned long call_site,
+			     const void *ptr,
+			     size_t bytes_req,
+			     size_t bytes_alloc,
+			     gfp_t gfp_flags,
+			     int node)
+{
+	struct ring_buffer_event *event;
+	struct kmemtrace_alloc_entry *entry;
+	struct trace_array *tr = kmemtrace_array;
+
+	if (!kmem_tracing_enabled)
+		return;
+
+	event = trace_buffer_lock_reserve(tr, TRACE_KMEM_ALLOC,
+					  sizeof(*entry), 0, 0);
+	if (!event)
+		return;
+	entry	= ring_buffer_event_data(event);
+
+	entry->call_site = call_site;
+	entry->ptr = ptr;
+	entry->bytes_req = bytes_req;
+	entry->bytes_alloc = bytes_alloc;
+	entry->gfp_flags = gfp_flags;
+	entry->node	=	node;
+
+	trace_buffer_unlock_commit(tr, event, 0, 0);
+}
+EXPORT_SYMBOL(kmemtrace_mark_alloc_node);
+
+void kmemtrace_mark_free(enum kmemtrace_type_id type_id,
+		       unsigned long call_site,
+		       const void *ptr)
+{
+	struct ring_buffer_event *event;
+	struct kmemtrace_free_entry *entry;
+	struct trace_array *tr = kmemtrace_array;
+
+	if (!kmem_tracing_enabled)
+		return;
+
+	event = trace_buffer_lock_reserve(tr, TRACE_KMEM_FREE,
+					  sizeof(*entry), 0, 0);
+	if (!event)
+		return;
+	entry	= ring_buffer_event_data(event);
+	entry->type_id	= type_id;
+	entry->call_site = call_site;
+	entry->ptr = ptr;
+
+	trace_buffer_unlock_commit(tr, event, 0, 0);
+}
+EXPORT_SYMBOL(kmemtrace_mark_free);
+
+static struct tracer kmem_tracer __read_mostly = {
+	.name		= "kmemtrace",
+	.init		= kmem_trace_init,
+	.reset		= kmem_trace_reset,
+	.print_line	= kmemtrace_print_line,
+	.print_header = kmemtrace_headers,
+	.flags		= &kmem_tracer_flags
+};
+
+void kmemtrace_init(void)
+{
+	/* earliest opportunity to start kmem tracing */
+}
+
+static int __init init_kmem_tracer(void)
+{
+	return register_tracer(&kmem_tracer);
+}
+
+device_initcall(init_kmem_tracer);
@@ -11,6 +11,7 @@
 #include <linux/kallsyms.h>

 #include "trace.h"
+#include "trace_output.h"

 static struct trace_array *boot_trace;
 static bool pre_initcalls_finished;
@@ -27,13 +28,13 @@ void start_boot_trace(void)

 void enable_boot_trace(void)
 {
-	if (pre_initcalls_finished)
+	if (boot_trace && pre_initcalls_finished)
 		tracing_start_sched_switch_record();
 }

 void disable_boot_trace(void)
 {
-	if (pre_initcalls_finished)
+	if (boot_trace && pre_initcalls_finished)
 		tracing_stop_sched_switch_record();
 }

@@ -42,6 +43,9 @@ static int boot_trace_init(struct trace_array *tr)
 	int cpu;
 	boot_trace = tr;

+	if (!tr)
+		return 0;
+
 	for_each_cpu(cpu, cpu_possible_mask)
 		tracing_reset(tr, cpu);

@@ -128,10 +132,9 @@ void trace_boot_call(struct boot_trace_call *bt, initcall_t fn)
 {
 	struct ring_buffer_event *event;
 	struct trace_boot_call *entry;
-	unsigned long irq_flags;
 	struct trace_array *tr = boot_trace;

-	if (!pre_initcalls_finished)
+	if (!tr || !pre_initcalls_finished)
 		return;

 	/* Get its name now since this function could
@@ -140,18 +143,13 @@ void trace_boot_call(struct boot_trace_call *bt, initcall_t fn)
 	sprint_symbol(bt->func, (unsigned long)fn);
 	preempt_disable();

-	event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
-					 &irq_flags);
+	event = trace_buffer_lock_reserve(tr, TRACE_BOOT_CALL,
+					  sizeof(*entry), 0, 0);
 	if (!event)
 		goto out;
 	entry	= ring_buffer_event_data(event);
-	tracing_generic_entry_update(&entry->ent, 0, 0);
-	entry->ent.type = TRACE_BOOT_CALL;
 	entry->boot_call = *bt;
-	ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
-
-	trace_wake_up();
-
+	trace_buffer_unlock_commit(tr, event, 0, 0);
 out:
 	preempt_enable();
 }
@@ -160,27 +158,21 @@ void trace_boot_ret(struct boot_trace_ret *bt, initcall_t fn)
 {
 	struct ring_buffer_event *event;
 	struct trace_boot_ret *entry;
-	unsigned long irq_flags;
 	struct trace_array *tr = boot_trace;

-	if (!pre_initcalls_finished)
+	if (!tr || !pre_initcalls_finished)
 		return;

 	sprint_symbol(bt->func, (unsigned long)fn);
 	preempt_disable();

-	event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
-					 &irq_flags);
+	event = trace_buffer_lock_reserve(tr, TRACE_BOOT_RET,
+					  sizeof(*entry), 0, 0);
 	if (!event)
 		goto out;
 	entry	= ring_buffer_event_data(event);
-	tracing_generic_entry_update(&entry->ent, 0, 0);
-	entry->ent.type = TRACE_BOOT_RET;
 	entry->boot_ret = *bt;
-	ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
-
-	trace_wake_up();
-
+	trace_buffer_unlock_commit(tr, event, 0, 0);
 out:
 	preempt_enable();
 }
@@ -14,12 +14,17 @@
 #include <linux/hash.h>
 #include <linux/fs.h>
 #include <asm/local.h>
+
 #include "trace.h"
+#include "trace_stat.h"
+#include "trace_output.h"

 #ifdef CONFIG_BRANCH_TRACER

+static struct tracer branch_trace;
 static int branch_tracing_enabled __read_mostly;
 static DEFINE_MUTEX(branch_tracing_mutex);
+
 static struct trace_array *branch_tracer;

 static void
@@ -28,7 +33,7 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect)
 	struct trace_array *tr = branch_tracer;
 	struct ring_buffer_event *event;
 	struct trace_branch *entry;
-	unsigned long flags, irq_flags;
+	unsigned long flags;
 	int cpu, pc;
 	const char *p;

@@ -47,15 +52,13 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect)
 	if (atomic_inc_return(&tr->data[cpu]->disabled) != 1)
 		goto out;

-	event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
-					 &irq_flags);
+	pc = preempt_count();
+	event = trace_buffer_lock_reserve(tr, TRACE_BRANCH,
+					  sizeof(*entry), flags, pc);
 	if (!event)
 		goto out;

-	pc = preempt_count();
 	entry	= ring_buffer_event_data(event);
-	tracing_generic_entry_update(&entry->ent, flags, pc);
-	entry->ent.type		= TRACE_BRANCH;

 	/* Strip off the path, only save the file */
 	p = f->file + strlen(f->file);
@@ -70,7 +73,7 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect)
 	entry->line = f->line;
 	entry->correct = val == expect;

-	ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
+	ring_buffer_unlock_commit(tr->buffer, event);

 out:
 	atomic_dec(&tr->data[cpu]->disabled);
@@ -88,8 +91,6 @@ void trace_likely_condition(struct ftrace_branch_data *f, int val, int expect)

 int enable_branch_tracing(struct trace_array *tr)
 {
-	int ret = 0;
-
 	mutex_lock(&branch_tracing_mutex);
 	branch_tracer = tr;
 	/*
@@ -100,7 +101,7 @@ int enable_branch_tracing(struct trace_array *tr)
 	branch_tracing_enabled++;
 	mutex_unlock(&branch_tracing_mutex);

-	return ret;
+	return 0;
 }

 void disable_branch_tracing(void)
@@ -128,11 +129,6 @@ static void stop_branch_trace(struct trace_array *tr)

 static int branch_trace_init(struct trace_array *tr)
 {
-	int cpu;
-
-	for_each_online_cpu(cpu)
-		tracing_reset(tr, cpu);
-
 	start_branch_trace(tr);
 	return 0;
 }
@@ -142,22 +138,53 @@ static void branch_trace_reset(struct trace_array *tr)
 	stop_branch_trace(tr);
 }

-struct tracer branch_trace __read_mostly =
+static enum print_line_t trace_branch_print(struct trace_iterator *iter,
+					    int flags)
+{
+	struct trace_branch *field;
+
+	trace_assign_type(field, iter->ent);
+
+	if (trace_seq_printf(&iter->seq, "[%s] %s:%s:%d\n",
+			     field->correct ? "  ok  " : " MISS ",
+			     field->func,
+			     field->file,
+			     field->line))
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	return TRACE_TYPE_HANDLED;
+}
+
+
+static struct trace_event trace_branch_event = {
+	.type		= TRACE_BRANCH,
+	.trace		= trace_branch_print,
+};
+
+static struct tracer branch_trace __read_mostly =
 {
 	.name		= "branch",
 	.init		= branch_trace_init,
 	.reset		= branch_trace_reset,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest	= trace_selftest_startup_branch,
-#endif
+#endif /* CONFIG_FTRACE_SELFTEST */
 };

-__init static int init_branch_trace(void)
+__init static int init_branch_tracer(void)
 {
+	int ret;
+
+	ret = register_ftrace_event(&trace_branch_event);
+	if (!ret) {
+		printk(KERN_WARNING "Warning: could not register "
+				    "branch events\n");
+		return 1;
+	}
 	return register_tracer(&branch_trace);
 }
+device_initcall(init_branch_tracer);

-device_initcall(init_branch_trace);
 #else
 static inline
 void trace_likely_condition(struct ftrace_branch_data *f, int val, int expect)
@@ -183,65 +210,38 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect)
 }
 EXPORT_SYMBOL(ftrace_likely_update);

-struct ftrace_pointer {
-	void		*start;
-	void		*stop;
-	int		hit;
-};
+extern unsigned long __start_annotated_branch_profile[];
+extern unsigned long __stop_annotated_branch_profile[];

-static void *
-t_next(struct seq_file *m, void *v, loff_t *pos)
+static int annotated_branch_stat_headers(struct seq_file *m)
 {
-	const struct ftrace_pointer *f = m->private;
-	struct ftrace_branch_data *p = v;
-
-	(*pos)++;
-
-	if (v == (void *)1)
-		return f->start;
-
-	++p;
-
-	if ((void *)p >= (void *)f->stop)
-		return NULL;
-
-	return p;
-}
-
-static void *t_start(struct seq_file *m, loff_t *pos)
-{
-	void *t = (void *)1;
-	loff_t l = 0;
-
-	for (; t && l < *pos; t = t_next(m, t, &l))
-		;
-
-	return t;
-}
-
-static void t_stop(struct seq_file *m, void *p)
-{
-}
-
-static int t_show(struct seq_file *m, void *v)
-{
-	const struct ftrace_pointer *fp = m->private;
-	struct ftrace_branch_data *p = v;
-	const char *f;
-	long percent;
-
-	if (v == (void *)1) {
-		if (fp->hit)
-			seq_printf(m, "   miss      hit    %% ");
-		else
-			seq_printf(m, " correct incorrect  %% ");
-		seq_printf(m, "       Function                "
+	seq_printf(m, " correct incorrect  %% ");
+	seq_printf(m, "       Function                "
 			      "  File              Line\n"
 			      " ------- ---------  - "
 			      "       --------                "
 			      "  ----              ----\n");
-		return 0;
-	}
+	return 0;
+}
+
+static inline long get_incorrect_percent(struct ftrace_branch_data *p)
+{
+	long percent;
+
+	if (p->correct) {
+		percent = p->incorrect * 100;
+		percent /= p->correct + p->incorrect;
+	} else
+		percent = p->incorrect ? 100 : -1;
+
+	return percent;
+}
+
+static int branch_stat_show(struct seq_file *m, void *v)
+{
+	struct ftrace_branch_data *p = v;
+	const char *f;
+	long percent;

 	/* Only print the file, not the path */
 	f = p->file + strlen(p->file);
@@ -252,11 +252,7 @@ static int t_show(struct seq_file *m, void *v)
 	/*
 	 * The miss is overlayed on correct, and hit on incorrect.
 	 */
-	if (p->correct) {
-		percent = p->incorrect * 100;
-		percent /= p->correct + p->incorrect;
-	} else
-		percent = p->incorrect ? 100 : -1;
+	percent = get_incorrect_percent(p);

 	seq_printf(m, "%8lu %8lu ",  p->correct, p->incorrect);
 	if (percent < 0)
@@ -267,76 +263,118 @@ static int t_show(struct seq_file *m, void *v)
 	return 0;
 }

-static struct seq_operations tracing_likely_seq_ops = {
-	.start		= t_start,
-	.next		= t_next,
-	.stop		= t_stop,
-	.show		= t_show,
+static void *annotated_branch_stat_start(void)
+{
+	return __start_annotated_branch_profile;
+}
+
+static void *
+annotated_branch_stat_next(void *v, int idx)
+{
+	struct ftrace_branch_data *p = v;
+
+	++p;
+
+	if ((void *)p >= (void *)__stop_annotated_branch_profile)
+		return NULL;
+
+	return p;
+}
+
+static int annotated_branch_stat_cmp(void *p1, void *p2)
+{
+	struct ftrace_branch_data *a = p1;
+	struct ftrace_branch_data *b = p2;
+
+	long percent_a, percent_b;
+
+	percent_a = get_incorrect_percent(a);
+	percent_b = get_incorrect_percent(b);
+
+	if (percent_a < percent_b)
+		return -1;
+	if (percent_a > percent_b)
+		return 1;
+	else
+		return 0;
+}
+
+static struct tracer_stat annotated_branch_stats = {
+	.name = "branch_annotated",
+	.stat_start = annotated_branch_stat_start,
+	.stat_next = annotated_branch_stat_next,
+	.stat_cmp = annotated_branch_stat_cmp,
+	.stat_headers = annotated_branch_stat_headers,
+	.stat_show = branch_stat_show
 };

-static int tracing_branch_open(struct inode *inode, struct file *file)
+__init static int init_annotated_branch_stats(void)
 {
 	int ret;

-	ret = seq_open(file, &tracing_likely_seq_ops);
+	ret = register_stat_tracer(&annotated_branch_stats);
 	if (!ret) {
-		struct seq_file *m = file->private_data;
-		m->private = (void *)inode->i_private;
+		printk(KERN_WARNING "Warning: could not register "
+				    "annotated branches stats\n");
+		return 1;
 	}
-
-	return ret;
+	return 0;
 }
-
-static const struct file_operations tracing_branch_fops = {
-	.open		= tracing_branch_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-};
+fs_initcall(init_annotated_branch_stats);

 #ifdef CONFIG_PROFILE_ALL_BRANCHES
+
 extern unsigned long __start_branch_profile[];
 extern unsigned long __stop_branch_profile[];

-static const struct ftrace_pointer ftrace_branch_pos = {
-	.start			= __start_branch_profile,
-	.stop			= __stop_branch_profile,
-	.hit			= 1,
-};
-
-#endif /* CONFIG_PROFILE_ALL_BRANCHES */
-
-extern unsigned long __start_annotated_branch_profile[];
-extern unsigned long __stop_annotated_branch_profile[];
-
-static const struct ftrace_pointer ftrace_annotated_branch_pos = {
-	.start			= __start_annotated_branch_profile,
-	.stop			= __stop_annotated_branch_profile,
-};
-
-static __init int ftrace_branch_init(void)
+static int all_branch_stat_headers(struct seq_file *m)
 {
-	struct dentry *d_tracer;
-	struct dentry *entry;
-
-	d_tracer = tracing_init_dentry();
-
-	entry = debugfs_create_file("profile_annotated_branch", 0444, d_tracer,
-				    (void *)&ftrace_annotated_branch_pos,
-				    &tracing_branch_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs "
-			   "'profile_annotatet_branch' entry\n");
-
-#ifdef CONFIG_PROFILE_ALL_BRANCHES
-	entry = debugfs_create_file("profile_branch", 0444, d_tracer,
-				    (void *)&ftrace_branch_pos,
-				    &tracing_branch_fops);
-	if (!entry)
-		pr_warning("Could not create debugfs"
-			   " 'profile_branch' entry\n");
-#endif
-
+	seq_printf(m, "   miss      hit    %% ");
+	seq_printf(m, "       Function                "
+			      "  File              Line\n"
+			      " ------- ---------  - "
+			      "       --------                "
+			      "  ----              ----\n");
 	return 0;
 }

-device_initcall(ftrace_branch_init);
+static void *all_branch_stat_start(void)
+{
+	return __start_branch_profile;
+}
+
+static void *
+all_branch_stat_next(void *v, int idx)
+{
+	struct ftrace_branch_data *p = v;
+
+	++p;
+
+	if ((void *)p >= (void *)__stop_branch_profile)
+		return NULL;
+
+	return p;
+}
+
+static struct tracer_stat all_branch_stats = {
+	.name = "branch_all",
+	.stat_start = all_branch_stat_start,
+	.stat_next = all_branch_stat_next,
+	.stat_headers = all_branch_stat_headers,
+	.stat_show = branch_stat_show
+};
+
+__init static int all_annotated_branch_stats(void)
+{
+	int ret;
+
+	ret = register_stat_tracer(&all_branch_stats);
+	if (!ret) {
+		printk(KERN_WARNING "Warning: could not register "
+				    "all branches stats\n");
+		return 1;
+	}
+	return 0;
+}
+fs_initcall(all_annotated_branch_stats);
+#endif /* CONFIG_PROFILE_ALL_BRANCHES */
--- a/Show More
+++ b/Show More