Merge branches 'tracing/docs', 'tracing/filters', 'tracing/ftrace', 'tracing/kprobes', 'tracing/blktrace-v2' and 'tracing/textedit' into tracing/core-v2

arch/x86/kernel/ftrace.c

@@ -410,7 +410,6 @@ int ftrace_disable_ftrace_graph_caller(void)
 void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
 {
 	unsigned long old;
-	unsigned long long calltime;
 	int faulted;
 	struct ftrace_graph_ent trace;
 	unsigned long return_hooker = (unsigned long)
@@ -453,10 +452,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
 		return;
 	}
 
-	calltime = trace_clock_local();
-
-	if (ftrace_push_return_trace(old, calltime,
-				self_addr, &trace.depth) == -EBUSY) {
+	if (ftrace_push_return_trace(old, self_addr, &trace.depth) == -EBUSY) {
 		*parent = old;
 		return;
 	}

arch/x86/kernel/kprobes.c

@@ -638,13 +638,13 @@ static void __used __kprobes kretprobe_trampoline_holder(void)
 #else
 			"	pushf\n"
 			/*
-			 * Skip cs, ip, orig_ax.
+			 * Skip cs, ip, orig_ax and gs.
 			 * trampoline_handler() will plug in these values
 			 */
-			"	subl $12, %esp\n"
+			"	subl $16, %esp\n"
 			"	pushl %fs\n"
-			"	pushl %ds\n"
 			"	pushl %es\n"
+			"	pushl %ds\n"
 			"	pushl %eax\n"
 			"	pushl %ebp\n"
 			"	pushl %edi\n"
@@ -655,10 +655,10 @@ static void __used __kprobes kretprobe_trampoline_holder(void)
 			"	movl %esp, %eax\n"
 			"	call trampoline_handler\n"
 			/* Move flags to cs */
-			"	movl 52(%esp), %edx\n"
-			"	movl %edx, 48(%esp)\n"
+			"	movl 56(%esp), %edx\n"
+			"	movl %edx, 52(%esp)\n"
 			/* Replace saved flags with true return address. */
-			"	movl %eax, 52(%esp)\n"
+			"	movl %eax, 56(%esp)\n"
 			"	popl %ebx\n"
 			"	popl %ecx\n"
 			"	popl %edx\n"
@@ -666,8 +666,8 @@ static void __used __kprobes kretprobe_trampoline_holder(void)
 			"	popl %edi\n"
 			"	popl %ebp\n"
 			"	popl %eax\n"
-			/* Skip ip, orig_ax, es, ds, fs */
-			"	addl $20, %esp\n"
+			/* Skip ds, es, fs, gs, orig_ax and ip */
+			"	addl $24, %esp\n"
 			"	popf\n"
 #endif
 			"	ret\n");
@@ -691,6 +691,7 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
 	regs->cs = __KERNEL_CS;
 #else
 	regs->cs = __KERNEL_CS | get_kernel_rpl();
+	regs->gs = 0;
 #endif
 	regs->ip = trampoline_address;
 	regs->orig_ax = ~0UL;

fs/debugfs/inode.c

@@ -30,6 +30,7 @@
 
 static struct vfsmount *debugfs_mount;
 static int debugfs_mount_count;
+static bool debugfs_registered;
 
 static struct inode *debugfs_get_inode(struct super_block *sb, int mode, dev_t dev)
 {
@@ -496,6 +497,16 @@ exit:
 }
 EXPORT_SYMBOL_GPL(debugfs_rename);
 
+/**
+ * debugfs_initialized - Tells whether debugfs has been registered
+ */
+bool debugfs_initialized(void)
+{
+	return debugfs_registered;
+}
+EXPORT_SYMBOL_GPL(debugfs_initialized);
+
+
 static struct kobject *debug_kobj;
 
 static int __init debugfs_init(void)
@@ -509,11 +520,16 @@ static int __init debugfs_init(void)
 	retval = register_filesystem(&debug_fs_type);
 	if (retval)
 		kobject_put(debug_kobj);
+	else
+		debugfs_registered = true;
+
 	return retval;
 }
 
 static void __exit debugfs_exit(void)
 {
+	debugfs_registered = false;
+
 	simple_release_fs(&debugfs_mount, &debugfs_mount_count);
 	unregister_filesystem(&debug_fs_type);
 	kobject_put(debug_kobj);

include/linux/debugfs.h

@@ -71,6 +71,9 @@ struct dentry *debugfs_create_bool(const char *name, mode_t mode,
 struct dentry *debugfs_create_blob(const char *name, mode_t mode,
 				  struct dentry *parent,
 				  struct debugfs_blob_wrapper *blob);
+
+bool debugfs_initialized(void);
+
 #else
 
 #include <linux/err.h>
@@ -183,6 +186,11 @@ static inline struct dentry *debugfs_create_blob(const char *name, mode_t mode,
 	return ERR_PTR(-ENODEV);
 }
 
+static inline bool debugfs_initialized(void)
+{
+	return false;
+}
+
 #endif
 
 #endif

include/linux/ftrace.h

@@ -145,9 +145,15 @@ enum {
 };
 
 struct dyn_ftrace {
-	unsigned long		ip; /* address of mcount call-site */
-	unsigned long		flags;
-	struct dyn_arch_ftrace	arch;
+	union {
+		unsigned long		ip; /* address of mcount call-site */
+		struct dyn_ftrace	*freelist;
+	};
+	union {
+		unsigned long		flags;
+		struct dyn_ftrace	*newlist;
+	};
+	struct dyn_arch_ftrace		arch;
 };
 
 int ftrace_force_update(void);
@@ -369,8 +375,7 @@ struct ftrace_ret_stack {
 extern void return_to_handler(void);
 
 extern int
-ftrace_push_return_trace(unsigned long ret, unsigned long long time,
-			 unsigned long func, int *depth);
+ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth);
 extern void
 ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret);
 

include/linux/ring_buffer.h

@@ -18,10 +18,13 @@ struct ring_buffer_event {
 /**
  * enum ring_buffer_type - internal ring buffer types
  *
- * @RINGBUF_TYPE_PADDING:	Left over page padding
- *				 array is ignored
- *				 size is variable depending on how much
+ * @RINGBUF_TYPE_PADDING:	Left over page padding or discarded event
+ *				 If time_delta is 0:
+ *				  array is ignored
+ *				  size is variable depending on how much
  *				  padding is needed
+ *				 If time_delta is non zero:
+ *				  everything else same as RINGBUF_TYPE_DATA
  *
  * @RINGBUF_TYPE_TIME_EXTEND:	Extend the time delta
  *				 array[0] = time delta (28 .. 59)
@@ -65,6 +68,8 @@ ring_buffer_event_time_delta(struct ring_buffer_event *event)
 	return event->time_delta;
 }
 
+void ring_buffer_event_discard(struct ring_buffer_event *event);
+
 /*
  * size is in bytes for each per CPU buffer.
  */

include/linux/sched.h

@@ -1409,6 +1409,8 @@ struct task_struct {
 	int curr_ret_stack;
 	/* Stack of return addresses for return function tracing */
 	struct ftrace_ret_stack	*ret_stack;
+	/* time stamp for last schedule */
+	unsigned long long ftrace_timestamp;
 	/*
 	 * Number of functions that haven't been traced
 	 * because of depth overrun.

init/main.c

@@ -772,6 +772,7 @@ static void __init do_basic_setup(void)
 {
 	rcu_init_sched(); /* needed by module_init stage. */
 	init_workqueues();
+	cpuset_init_smp();
 	usermodehelper_init();
 	driver_init();
 	init_irq_proc();
@@ -865,8 +866,6 @@ static int __init kernel_init(void * unused)
 	smp_init();
 	sched_init_smp();
 
-	cpuset_init_smp();
-
 	do_basic_setup();
 
 	/*

kernel/extable.c

@@ -16,6 +16,7 @@
     Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 */
 #include <linux/ftrace.h>
+#include <linux/memory.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/init.h>

kernel/trace/Kconfig

@@ -63,7 +63,11 @@ config TRACING
 #
 config TRACING_SUPPORT
 	bool
-	depends on TRACE_IRQFLAGS_SUPPORT
+	# 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
 

kernel/trace/Makefile

@@ -45,5 +45,6 @@ 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

kernel/trace/blktrace.c

@@ -30,7 +30,7 @@
 static unsigned int blktrace_seq __read_mostly = 1;
 
 static struct trace_array *blk_tr;
-static int __read_mostly  blk_tracer_enabled;
+static bool blk_tracer_enabled __read_mostly;
 
 /* Select an alternative, minimalistic output than the original one */
 #define TRACE_BLK_OPT_CLASSIC	0x1
@@ -47,10 +47,9 @@ static struct tracer_flags blk_tracer_flags = {
 };
 
 /* Global reference count of probes */
-static DEFINE_MUTEX(blk_probe_mutex);
 static atomic_t blk_probes_ref = ATOMIC_INIT(0);
 
-static int blk_register_tracepoints(void);
+static void blk_register_tracepoints(void);
 static void blk_unregister_tracepoints(void);
 
 /*
@@ -60,22 +59,39 @@ static void trace_note(struct blk_trace *bt, pid_t pid, int action,
 		       const void *data, size_t len)
 {
 	struct blk_io_trace *t;
+	struct ring_buffer_event *event = NULL;
+	int pc = 0;
+	int cpu = smp_processor_id();
+	bool blk_tracer = blk_tracer_enabled;
+
+	if (blk_tracer) {
+		pc = preempt_count();
+		event = trace_buffer_lock_reserve(blk_tr, TRACE_BLK,
+						  sizeof(*t) + len,
+						  0, pc);
+		if (!event)
+			return;
+		t = ring_buffer_event_data(event);
+		goto record_it;
+	}
 
 	if (!bt->rchan)
 		return;
 
 	t = relay_reserve(bt->rchan, sizeof(*t) + len);
 	if (t) {
-		const int cpu = smp_processor_id();
-
 		t->magic = BLK_IO_TRACE_MAGIC | BLK_IO_TRACE_VERSION;
 		t->time = ktime_to_ns(ktime_get());
+record_it:
 		t->device = bt->dev;
 		t->action = action;
 		t->pid = pid;
 		t->cpu = cpu;
 		t->pdu_len = len;
 		memcpy((void *) t + sizeof(*t), data, len);
+
+		if (blk_tracer)
+			trace_buffer_unlock_commit(blk_tr, event, 0, pc);
 	}
 }
 
@@ -111,14 +127,8 @@ void __trace_note_message(struct blk_trace *bt, const char *fmt, ...)
 	unsigned long flags;
 	char *buf;
 
-	if (blk_tr) {
-		va_start(args, fmt);
-		ftrace_vprintk(fmt, args);
-		va_end(args);
-		return;
-	}
-
-	if (!bt->msg_data)
+	if (unlikely(bt->trace_state != Blktrace_running &&
+		     !blk_tracer_enabled))
 		return;
 
 	local_irq_save(flags);
@@ -148,8 +158,8 @@ static int act_log_check(struct blk_trace *bt, u32 what, sector_t sector,
 /*
  * Data direction bit lookup
  */
-static u32 ddir_act[2] __read_mostly = { BLK_TC_ACT(BLK_TC_READ),
-					 BLK_TC_ACT(BLK_TC_WRITE) };
+static const u32 ddir_act[2] = { BLK_TC_ACT(BLK_TC_READ),
+				 BLK_TC_ACT(BLK_TC_WRITE) };
 
 /* The ilog2() calls fall out because they're constant */
 #define MASK_TC_BIT(rw, __name) ((rw & (1 << BIO_RW_ ## __name)) << \
@@ -169,9 +179,9 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 	unsigned long *sequence;
 	pid_t pid;
 	int cpu, pc = 0;
+	bool blk_tracer = blk_tracer_enabled;
 
-	if (unlikely(bt->trace_state != Blktrace_running ||
-		     !blk_tracer_enabled))
+	if (unlikely(bt->trace_state != Blktrace_running && !blk_tracer))
 		return;
 
 	what |= ddir_act[rw & WRITE];
@@ -186,7 +196,7 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 		return;
 	cpu = raw_smp_processor_id();
 
-	if (blk_tr) {
+	if (blk_tracer) {
 		tracing_record_cmdline(current);
 
 		pc = preempt_count();
@@ -236,7 +246,7 @@ record_it:
 		if (pdu_len)
 			memcpy((void *) t + sizeof(*t), pdu_data, pdu_len);
 
-		if (blk_tr) {
+		if (blk_tracer) {
 			trace_buffer_unlock_commit(blk_tr, event, 0, pc);
 			return;
 		}
@@ -248,7 +258,7 @@ record_it:
 static struct dentry *blk_tree_root;
 static DEFINE_MUTEX(blk_tree_mutex);
 
-static void blk_trace_cleanup(struct blk_trace *bt)
+static void blk_trace_free(struct blk_trace *bt)
 {
 	debugfs_remove(bt->msg_file);
 	debugfs_remove(bt->dropped_file);
@@ -256,10 +266,13 @@ static void blk_trace_cleanup(struct blk_trace *bt)
 	free_percpu(bt->sequence);
 	free_percpu(bt->msg_data);
 	kfree(bt);
-	mutex_lock(&blk_probe_mutex);
+}
+
+static void blk_trace_cleanup(struct blk_trace *bt)
+{
+	blk_trace_free(bt);
 	if (atomic_dec_and_test(&blk_probes_ref))
 		blk_unregister_tracepoints();
-	mutex_unlock(&blk_probe_mutex);
 }
 
 int blk_trace_remove(struct request_queue *q)
@@ -270,8 +283,7 @@ int blk_trace_remove(struct request_queue *q)
 	if (!bt)
 		return -EINVAL;
 
-	if (bt->trace_state == Blktrace_setup ||
-	    bt->trace_state == Blktrace_stopped)
+	if (bt->trace_state != Blktrace_running)
 		blk_trace_cleanup(bt);
 
 	return 0;
@@ -414,11 +426,11 @@ int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 		if (buts->name[i] == '/')
 			buts->name[i] = '_';
 
-	ret = -ENOMEM;
 	bt = kzalloc(sizeof(*bt), GFP_KERNEL);
 	if (!bt)
-		goto err;
+		return -ENOMEM;
 
+	ret = -ENOMEM;
 	bt->sequence = alloc_percpu(unsigned long);
 	if (!bt->sequence)
 		goto err;
@@ -429,11 +441,15 @@ int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 
 	ret = -ENOENT;
 
+	mutex_lock(&blk_tree_mutex);
 	if (!blk_tree_root) {
 		blk_tree_root = debugfs_create_dir("block", NULL);
-		if (!blk_tree_root)
-			return -ENOMEM;
+		if (!blk_tree_root) {
+			mutex_unlock(&blk_tree_mutex);
+			goto err;
+		}
 	}
+	mutex_unlock(&blk_tree_mutex);
 
 	dir = debugfs_create_dir(buts->name, blk_tree_root);
 
@@ -471,14 +487,6 @@ int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	bt->pid = buts->pid;
 	bt->trace_state = Blktrace_setup;
 
-	mutex_lock(&blk_probe_mutex);
-	if (atomic_add_return(1, &blk_probes_ref) == 1) {
-		ret = blk_register_tracepoints();
-		if (ret)
-			goto probe_err;
-	}
-	mutex_unlock(&blk_probe_mutex);
-
 	ret = -EBUSY;
 	old_bt = xchg(&q->blk_trace, bt);
 	if (old_bt) {
@@ -486,22 +494,12 @@ int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 		goto err;
 	}
 
+	if (atomic_inc_return(&blk_probes_ref) == 1)
+		blk_register_tracepoints();
+
 	return 0;
-probe_err:
-	atomic_dec(&blk_probes_ref);
-	mutex_unlock(&blk_probe_mutex);
 err:
-	if (bt) {
-		if (bt->msg_file)
-			debugfs_remove(bt->msg_file);
-		if (bt->dropped_file)
-			debugfs_remove(bt->dropped_file);
-		free_percpu(bt->sequence);
-		free_percpu(bt->msg_data);
-		if (bt->rchan)
-			relay_close(bt->rchan);
-		kfree(bt);
-	}
+	blk_trace_free(bt);
 	return ret;
 }
 
@@ -863,7 +861,7 @@ void blk_add_driver_data(struct request_queue *q,
 }
 EXPORT_SYMBOL_GPL(blk_add_driver_data);
 
-static int blk_register_tracepoints(void)
+static void blk_register_tracepoints(void)
 {
 	int ret;
 
@@ -901,7 +899,6 @@ static int blk_register_tracepoints(void)
 	WARN_ON(ret);
 	ret = register_trace_block_remap(blk_add_trace_remap);
 	WARN_ON(ret);
-	return 0;
 }
 
 static void blk_unregister_tracepoints(void)
@@ -934,25 +931,31 @@ static void blk_unregister_tracepoints(void)
 static void fill_rwbs(char *rwbs, const struct blk_io_trace *t)
 {
 	int i = 0;
+	int tc = t->action >> BLK_TC_SHIFT;
+
+	if (t->action == BLK_TN_MESSAGE) {
+		rwbs[i++] = 'N';
+		goto out;
+	}
 
-	if (t->action & BLK_TC_DISCARD)
+	if (tc & BLK_TC_DISCARD)
 		rwbs[i++] = 'D';
-	else if (t->action & BLK_TC_WRITE)
+	else if (tc & BLK_TC_WRITE)
 		rwbs[i++] = 'W';
 	else if (t->bytes)
 		rwbs[i++] = 'R';
 	else
 		rwbs[i++] = 'N';
 
-	if (t->action & BLK_TC_AHEAD)
+	if (tc & BLK_TC_AHEAD)
 		rwbs[i++] = 'A';
-	if (t->action & BLK_TC_BARRIER)
+	if (tc & BLK_TC_BARRIER)
 		rwbs[i++] = 'B';
-	if (t->action & BLK_TC_SYNC)
+	if (tc & BLK_TC_SYNC)
 		rwbs[i++] = 'S';
-	if (t->action & BLK_TC_META)
+	if (tc & BLK_TC_META)
 		rwbs[i++] = 'M';
-
+out:
 	rwbs[i] = '\0';
 }
 
@@ -979,7 +982,7 @@ static inline unsigned long long t_sector(const struct trace_entry *ent)
 
 static inline __u16 t_error(const struct trace_entry *ent)
 {
-	return te_blk_io_trace(ent)->sector;
+	return te_blk_io_trace(ent)->error;
 }
 
 static __u64 get_pdu_int(const struct trace_entry *ent)
@@ -999,29 +1002,31 @@ static void get_pdu_remap(const struct trace_entry *ent,
 	r->sector = be64_to_cpu(sector);
 }
 
-static int blk_log_action_iter(struct trace_iterator *iter, const char *act)
+typedef int (blk_log_action_t) (struct trace_iterator *iter, const char *act);
+
+static int blk_log_action_classic(struct trace_iterator *iter, const char *act)
 {
 	char rwbs[6];
-	unsigned long long ts  = ns2usecs(iter->ts);
-	unsigned long usec_rem = do_div(ts, USEC_PER_SEC);
+	unsigned long long ts  = iter->ts;
+	unsigned long nsec_rem = do_div(ts, NSEC_PER_SEC);
 	unsigned secs	       = (unsigned long)ts;
-	const struct trace_entry *ent = iter->ent;
-	const struct blk_io_trace *t = (const struct blk_io_trace *)ent;
+	const struct blk_io_trace *t = te_blk_io_trace(iter->ent);
 
 	fill_rwbs(rwbs, t);
 
 	return trace_seq_printf(&iter->seq,
-				"%3d,%-3d %2d %5d.%06lu %5u %2s %3s ",
+				"%3d,%-3d %2d %5d.%09lu %5u %2s %3s ",
 				MAJOR(t->device), MINOR(t->device), iter->cpu,
-				secs, usec_rem, ent->pid, act, rwbs);
+				secs, nsec_rem, iter->ent->pid, act, rwbs);
 }
 
-static int blk_log_action_seq(struct trace_seq *s, const struct blk_io_trace *t,
-			      const char *act)
+static int blk_log_action(struct trace_iterator *iter, const char *act)
 {
 	char rwbs[6];
+	const struct blk_io_trace *t = te_blk_io_trace(iter->ent);
+
 	fill_rwbs(rwbs, t);
-	return trace_seq_printf(s, "%3d,%-3d %2s %3s ",
+	return trace_seq_printf(&iter->seq, "%3d,%-3d %2s %3s ",
 				MAJOR(t->device), MINOR(t->device), act, rwbs);
 }
 
@@ -1085,6 +1090,17 @@ static int blk_log_split(struct trace_seq *s, const struct trace_entry *ent)
 				get_pdu_int(ent), cmd);
 }
 
+static int blk_log_msg(struct trace_seq *s, const struct trace_entry *ent)
+{
+	int ret;
+	const struct blk_io_trace *t = te_blk_io_trace(ent);
+
+	ret = trace_seq_putmem(s, t + 1, t->pdu_len);
+	if (ret)
+		return trace_seq_putc(s, '\n');
+	return ret;
+}
+
 /*
  * struct tracer operations
  */
@@ -1099,11 +1115,7 @@ static void blk_tracer_print_header(struct seq_file *m)
 
 static void blk_tracer_start(struct trace_array *tr)
 {
-	mutex_lock(&blk_probe_mutex);
-	if (atomic_add_return(1, &blk_probes_ref) == 1)
-		if (blk_register_tracepoints())
-			atomic_dec(&blk_probes_ref);
-	mutex_unlock(&blk_probe_mutex);
+	blk_tracer_enabled = true;
 	trace_flags &= ~TRACE_ITER_CONTEXT_INFO;
 }
 
@@ -1111,38 +1123,24 @@ static int blk_tracer_init(struct trace_array *tr)
 {
 	blk_tr = tr;
 	blk_tracer_start(tr);
-	mutex_lock(&blk_probe_mutex);
-	blk_tracer_enabled++;
-	mutex_unlock(&blk_probe_mutex);
 	return 0;
 }
 
 static void blk_tracer_stop(struct trace_array *tr)
 {
+	blk_tracer_enabled = false;
 	trace_flags |= TRACE_ITER_CONTEXT_INFO;
-	mutex_lock(&blk_probe_mutex);
-	if (atomic_dec_and_test(&blk_probes_ref))
-		blk_unregister_tracepoints();
-	mutex_unlock(&blk_probe_mutex);
 }
 
 static void blk_tracer_reset(struct trace_array *tr)
 {
-	if (!atomic_read(&blk_probes_ref))
-		return;
-
-	mutex_lock(&blk_probe_mutex);
-	blk_tracer_enabled--;
-	WARN_ON(blk_tracer_enabled < 0);
-	mutex_unlock(&blk_probe_mutex);
-
 	blk_tracer_stop(tr);
 }
 
-static struct {
+static const struct {
 	const char *act[2];
 	int	   (*print)(struct trace_seq *s, const struct trace_entry *ent);
-} what2act[] __read_mostly = {
+} what2act[] = {
 	[__BLK_TA_QUEUE]	= {{  "Q", "queue" },	   blk_log_generic },
 	[__BLK_TA_BACKMERGE]	= {{  "M", "backmerge" },  blk_log_generic },
 	[__BLK_TA_FRONTMERGE]	= {{  "F", "frontmerge" }, blk_log_generic },
@@ -1160,29 +1158,48 @@ static struct {
 	[__BLK_TA_REMAP]	= {{  "A", "remap" },	   blk_log_remap },
 };
 
-static enum print_line_t blk_trace_event_print(struct trace_iterator *iter,
-					       int flags)
+static enum print_line_t print_one_line(struct trace_iterator *iter,
+					bool classic)
 {
 	struct trace_seq *s = &iter->seq;
-	const struct blk_io_trace *t = (struct blk_io_trace *)iter->ent;
-	const u16 what = t->action & ((1 << BLK_TC_SHIFT) - 1);
+	const struct blk_io_trace *t;
+	u16 what;
 	int ret;
+	bool long_act;
+	blk_log_action_t *log_action;
 
-	if (!trace_print_context(iter))
-		return TRACE_TYPE_PARTIAL_LINE;
+	t	   = te_blk_io_trace(iter->ent);
+	what	   = t->action & ((1 << BLK_TC_SHIFT) - 1);
+	long_act   = !!(trace_flags & TRACE_ITER_VERBOSE);
+	log_action = classic ? &blk_log_action_classic : &blk_log_action;
 
-	if (unlikely(what == 0 || what > ARRAY_SIZE(what2act)))
+	if (t->action == BLK_TN_MESSAGE) {
+		ret = log_action(iter, long_act ? "message" : "m");
+		if (ret)
+			ret = blk_log_msg(s, iter->ent);
+		goto out;
+	}
+
+	if (unlikely(what == 0 || what >= ARRAY_SIZE(what2act)))
 		ret = trace_seq_printf(s, "Bad pc action %x\n", what);
 	else {
-		const bool long_act = !!(trace_flags & TRACE_ITER_VERBOSE);
-		ret = blk_log_action_seq(s, t, what2act[what].act[long_act]);
+		ret = log_action(iter, what2act[what].act[long_act]);
 		if (ret)
 			ret = what2act[what].print(s, iter->ent);
 	}
-
+out:
 	return ret ? TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE;
 }
 
+static enum print_line_t blk_trace_event_print(struct trace_iterator *iter,
+					       int flags)
+{
+	if (!trace_print_context(iter))
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	return print_one_line(iter, false);
+}
+
 static int blk_trace_synthesize_old_trace(struct trace_iterator *iter)
 {
 	struct trace_seq *s = &iter->seq;
@@ -1190,7 +1207,7 @@ static int blk_trace_synthesize_old_trace(struct trace_iterator *iter)
 	const int offset = offsetof(struct blk_io_trace, sector);
 	struct blk_io_trace old = {
 		.magic	  = BLK_IO_TRACE_MAGIC | BLK_IO_TRACE_VERSION,
-		.time     = ns2usecs(iter->ts),
+		.time     = iter->ts,
 	};
 
 	if (!trace_seq_putmem(s, &old, offset))
@@ -1208,26 +1225,10 @@ blk_trace_event_print_binary(struct trace_iterator *iter, int flags)
 
 static enum print_line_t blk_tracer_print_line(struct trace_iterator *iter)
 {
-	const struct blk_io_trace *t;
-	u16 what;
-	int ret;
-
 	if (!(blk_tracer_flags.val & TRACE_BLK_OPT_CLASSIC))
 		return TRACE_TYPE_UNHANDLED;
 
-	t = (const struct blk_io_trace *)iter->ent;
-	what = t->action & ((1 << BLK_TC_SHIFT) - 1);
-
-	if (unlikely(what == 0 || what > ARRAY_SIZE(what2act)))
-		ret = trace_seq_printf(&iter->seq, "Bad pc action %x\n", what);
-	else {
-		const bool long_act = !!(trace_flags & TRACE_ITER_VERBOSE);
-		ret = blk_log_action_iter(iter, what2act[what].act[long_act]);
-		if (ret)
-			ret = what2act[what].print(&iter->seq, iter->ent);
-	}
-
-	return ret ? TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE;
+	return print_one_line(iter, true);
 }
 
 static struct tracer blk_tracer __read_mostly = {
@@ -1273,7 +1274,10 @@ static int blk_trace_remove_queue(struct request_queue *q)
 	if (bt == NULL)
 		return -EINVAL;
 
-	kfree(bt);
+	if (atomic_dec_and_test(&blk_probes_ref))
+		blk_unregister_tracepoints();
+
+	blk_trace_free(bt);
 	return 0;
 }
 
@@ -1283,26 +1287,33 @@ static int blk_trace_remove_queue(struct request_queue *q)
 static int blk_trace_setup_queue(struct request_queue *q, dev_t dev)
 {
 	struct blk_trace *old_bt, *bt = NULL;
-	int ret;
+	int ret = -ENOMEM;
 
-	ret = -ENOMEM;
 	bt = kzalloc(sizeof(*bt), GFP_KERNEL);
 	if (!bt)
-		goto err;
+		return -ENOMEM;
+
+	bt->msg_data = __alloc_percpu(BLK_TN_MAX_MSG, __alignof__(char));
+	if (!bt->msg_data)
+		goto free_bt;
 
 	bt->dev = dev;
 	bt->act_mask = (u16)-1;
 	bt->end_lba = -1ULL;
-	bt->trace_state = Blktrace_running;
 
 	old_bt = xchg(&q->blk_trace, bt);
 	if (old_bt != NULL) {
 		(void)xchg(&q->blk_trace, old_bt);
-		kfree(bt);
 		ret = -EBUSY;
+		goto free_bt;
 	}
+
+	if (atomic_inc_return(&blk_probes_ref) == 1)
+		blk_register_tracepoints();
 	return 0;
-err:
+
+free_bt:
+	blk_trace_free(bt);
 	return ret;
 }
 
@@ -1310,72 +1321,6 @@ err:
  * sysfs interface to enable and configure tracing
  */
 
-static ssize_t sysfs_blk_trace_enable_show(struct device *dev,
-					   struct device_attribute *attr,
-					   char *buf)
-{
-	struct hd_struct *p = dev_to_part(dev);
-	struct block_device *bdev;
-	ssize_t ret = -ENXIO;
-
-	lock_kernel();
-	bdev = bdget(part_devt(p));
-	if (bdev != NULL) {
-		struct request_queue *q = bdev_get_queue(bdev);
-
-		if (q != NULL) {
-			mutex_lock(&bdev->bd_mutex);
-			ret = sprintf(buf, "%u\n", !!q->blk_trace);
-			mutex_unlock(&bdev->bd_mutex);
-		}
-
-		bdput(bdev);
-	}
-
-	unlock_kernel();
-	return ret;
-}
-
-static ssize_t sysfs_blk_trace_enable_store(struct device *dev,
-					    struct device_attribute *attr,
-					    const char *buf, size_t count)
-{
-	struct block_device *bdev;
-	struct request_queue *q;
-	struct hd_struct *p;
-	int value;
-	ssize_t ret = -ENXIO;
-
-	if (count == 0 || sscanf(buf, "%d", &value) != 1)
-		goto out;
-
-	lock_kernel();
-	p = dev_to_part(dev);
-	bdev = bdget(part_devt(p));
-	if (bdev == NULL)
-		goto out_unlock_kernel;
-
-	q = bdev_get_queue(bdev);
-	if (q == NULL)
-		goto out_bdput;
-
-	mutex_lock(&bdev->bd_mutex);
-	if (value)
-		ret = blk_trace_setup_queue(q, bdev->bd_dev);
-	else
-		ret = blk_trace_remove_queue(q);
-	mutex_unlock(&bdev->bd_mutex);
-
-	if (ret == 0)
-		ret = count;
-out_bdput:
-	bdput(bdev);
-out_unlock_kernel:
-	unlock_kernel();
-out:
-	return ret;
-}
-
 static ssize_t sysfs_blk_trace_attr_show(struct device *dev,
 					 struct device_attribute *attr,
 					 char *buf);
@@ -1387,8 +1332,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
 		    sysfs_blk_trace_attr_show, \
 		    sysfs_blk_trace_attr_store)
 
-static DEVICE_ATTR(enable, S_IRUGO | S_IWUSR,
-		   sysfs_blk_trace_enable_show, sysfs_blk_trace_enable_store);
+static BLK_TRACE_DEVICE_ATTR(enable);
 static BLK_TRACE_DEVICE_ATTR(act_mask);
 static BLK_TRACE_DEVICE_ATTR(pid);
 static BLK_TRACE_DEVICE_ATTR(start_lba);
@@ -1408,53 +1352,85 @@ struct attribute_group blk_trace_attr_group = {
 	.attrs = blk_trace_attrs,
 };
 
-static int blk_str2act_mask(const char *str)
+static const struct {
+	int mask;
+	const char *str;
+} mask_maps[] = {
+	{ BLK_TC_READ,		"read"		},
+	{ BLK_TC_WRITE,		"write"		},
+	{ BLK_TC_BARRIER,	"barrier"	},
+	{ BLK_TC_SYNC,		"sync"		},
+	{ BLK_TC_QUEUE,		"queue"		},
+	{ BLK_TC_REQUEUE,	"requeue"	},
+	{ BLK_TC_ISSUE,		"issue"		},
+	{ BLK_TC_COMPLETE,	"complete"	},
+	{ BLK_TC_FS,		"fs"		},
+	{ BLK_TC_PC,		"pc"		},
+	{ BLK_TC_AHEAD,		"ahead"		},
+	{ BLK_TC_META,		"meta"		},
+	{ BLK_TC_DISCARD,	"discard"	},
+	{ BLK_TC_DRV_DATA,	"drv_data"	},
+};
+
+static int blk_trace_str2mask(const char *str)
 {
+	int i;
 	int mask = 0;
-	char *copy = kstrdup(str, GFP_KERNEL), *s;
+	char *s, *token;
 
-	if (copy == NULL)
+	s = kstrdup(str, GFP_KERNEL);
+	if (s == NULL)
 		return -ENOMEM;
-
-	s = strstrip(copy);
+	s = strstrip(s);
 
 	while (1) {
-		char *sep = strchr(s, ',');
-
-		if (sep != NULL)
-			*sep = '\0';
-
-		if (strcasecmp(s, "barrier") == 0)
-			mask |= BLK_TC_BARRIER;
-		else if (strcasecmp(s, "complete") == 0)
-			mask |= BLK_TC_COMPLETE;
-		else if (strcasecmp(s, "fs") == 0)
-			mask |= BLK_TC_FS;
-		else if (strcasecmp(s, "issue") == 0)
-			mask |= BLK_TC_ISSUE;
-		else if (strcasecmp(s, "pc") == 0)
-			mask |= BLK_TC_PC;
-		else if (strcasecmp(s, "queue") == 0)
-			mask |= BLK_TC_QUEUE;
-		else if (strcasecmp(s, "read") == 0)
-			mask |= BLK_TC_READ;
-		else if (strcasecmp(s, "requeue") == 0)
-			mask |= BLK_TC_REQUEUE;
-		else if (strcasecmp(s, "sync") == 0)
-			mask |= BLK_TC_SYNC;
-		else if (strcasecmp(s, "write") == 0)
-			mask |= BLK_TC_WRITE;
-
-		if (sep == NULL)
+		token = strsep(&s, ",");
+		if (token == NULL)
 			break;
 
-		s = sep + 1;
+		if (*token == '\0')
+			continue;
+
+		for (i = 0; i < ARRAY_SIZE(mask_maps); i++) {
+			if (strcasecmp(token, mask_maps[i].str) == 0) {
+				mask |= mask_maps[i].mask;
+				break;
+			}
+		}
+		if (i == ARRAY_SIZE(mask_maps)) {
+			mask = -EINVAL;
+			break;
+		}
 	}
-	kfree(copy);
+	kfree(s);
 
 	return mask;
 }
 
+static ssize_t blk_trace_mask2str(char *buf, int mask)
+{
+	int i;
+	char *p = buf;
+
+	for (i = 0; i < ARRAY_SIZE(mask_maps); i++) {
+		if (mask & mask_maps[i].mask) {
+			p += sprintf(p, "%s%s",
+				    (p == buf) ? "" : ",", mask_maps[i].str);
+		}
+	}
+	*p++ = '\n';
+
+	return p - buf;
+}
+
+static struct request_queue *blk_trace_get_queue(struct block_device *bdev)
+{
+	if (bdev->bd_disk == NULL)
+		return NULL;
+
+	return bdev_get_queue(bdev);
+}
+
 static ssize_t sysfs_blk_trace_attr_show(struct device *dev,
 					 struct device_attribute *attr,
 					 char *buf)
@@ -1469,20 +1445,29 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev,
 	if (bdev == NULL)
 		goto out_unlock_kernel;
 
-	q = bdev_get_queue(bdev);
+	q = blk_trace_get_queue(bdev);
 	if (q == NULL)
 		goto out_bdput;
+
 	mutex_lock(&bdev->bd_mutex);
+
+	if (attr == &dev_attr_enable) {
+		ret = sprintf(buf, "%u\n", !!q->blk_trace);
+		goto out_unlock_bdev;
+	}
+
 	if (q->blk_trace == NULL)
 		ret = sprintf(buf, "disabled\n");
 	else if (attr == &dev_attr_act_mask)
-		ret = sprintf(buf, "%#x\n", q->blk_trace->act_mask);
+		ret = blk_trace_mask2str(buf, q->blk_trace->act_mask);
 	else if (attr == &dev_attr_pid)
 		ret = sprintf(buf, "%u\n", q->blk_trace->pid);
 	else if (attr == &dev_attr_start_lba)
 		ret = sprintf(buf, "%llu\n", q->blk_trace->start_lba);
 	else if (attr == &dev_attr_end_lba)
 		ret = sprintf(buf, "%llu\n", q->blk_trace->end_lba);
+
+out_unlock_bdev:
 	mutex_unlock(&bdev->bd_mutex);
 out_bdput:
 	bdput(bdev);
@@ -1499,7 +1484,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
 	struct request_queue *q;
 	struct hd_struct *p;
 	u64 value;
-	ssize_t ret = -ENXIO;
+	ssize_t ret = -EINVAL;
 
 	if (count == 0)
 		goto out;
@@ -1507,24 +1492,36 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
 	if (attr == &dev_attr_act_mask) {
 		if (sscanf(buf, "%llx", &value) != 1) {
 			/* Assume it is a list of trace category names */
-			value = blk_str2act_mask(buf);
-			if (value < 0)
+			ret = blk_trace_str2mask(buf);
+			if (ret < 0)
 				goto out;
+			value = ret;
 		}
 	} else if (sscanf(buf, "%llu", &value) != 1)
 		goto out;
 
+	ret = -ENXIO;
+
 	lock_kernel();
 	p = dev_to_part(dev);
 	bdev = bdget(part_devt(p));
 	if (bdev == NULL)
 		goto out_unlock_kernel;
 
-	q = bdev_get_queue(bdev);
+	q = blk_trace_get_queue(bdev);
 	if (q == NULL)
 		goto out_bdput;
 
 	mutex_lock(&bdev->bd_mutex);
+
+	if (attr == &dev_attr_enable) {
+		if (value)
+			ret = blk_trace_setup_queue(q, bdev->bd_dev);
+		else
+			ret = blk_trace_remove_queue(q);
+		goto out_unlock_bdev;
+	}
+
 	ret = 0;
 	if (q->blk_trace == NULL)
 		ret = blk_trace_setup_queue(q, bdev->bd_dev);
@@ -1538,13 +1535,15 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
 			q->blk_trace->start_lba = value;
 		else if (attr == &dev_attr_end_lba)
 			q->blk_trace->end_lba = value;
-		ret = count;
 	}
+
+out_unlock_bdev:
 	mutex_unlock(&bdev->bd_mutex);
 out_bdput:
 	bdput(bdev);
 out_unlock_kernel:
 	unlock_kernel();
 out:
-	return ret;
+	return ret ? ret : count;
 }
+

kernel/trace/ftrace.c

@@ -29,6 +29,8 @@
 #include <linux/list.h>
 #include <linux/hash.h>
 
+#include <trace/sched.h>
+
 #include <asm/ftrace.h>
 
 #include "trace.h"
@@ -339,7 +341,7 @@ static inline int record_frozen(struct dyn_ftrace *rec)
 
 static void ftrace_free_rec(struct dyn_ftrace *rec)
 {
-	rec->ip = (unsigned long)ftrace_free_records;
+	rec->freelist = ftrace_free_records;
 	ftrace_free_records = rec;
 	rec->flags |= FTRACE_FL_FREE;
 }
@@ -356,9 +358,14 @@ void ftrace_release(void *start, unsigned long size)
 
 	mutex_lock(&ftrace_lock);
 	do_for_each_ftrace_rec(pg, rec) {
-		if ((rec->ip >= s) && (rec->ip < e) &&
-		    !(rec->flags & FTRACE_FL_FREE))
+		if ((rec->ip >= s) && (rec->ip < e)) {
+			/*
+			 * rec->ip is changed in ftrace_free_rec()
+			 * It should not between s and e if record was freed.
+			 */
+			FTRACE_WARN_ON(rec->flags & FTRACE_FL_FREE);
 			ftrace_free_rec(rec);
+		}
 	} while_for_each_ftrace_rec();
 	mutex_unlock(&ftrace_lock);
 }
@@ -377,7 +384,7 @@ static struct dyn_ftrace *ftrace_alloc_dyn_node(unsigned long ip)
 			return NULL;
 		}
 
-		ftrace_free_records = (void *)rec->ip;
+		ftrace_free_records = rec->freelist;
 		memset(rec, 0, sizeof(*rec));
 		return rec;
 	}
@@ -409,7 +416,7 @@ ftrace_record_ip(unsigned long ip)
 		return NULL;
 
 	rec->ip = ip;
-	rec->flags = (unsigned long)ftrace_new_addrs;
+	rec->newlist = ftrace_new_addrs;
 	ftrace_new_addrs = rec;
 
 	return rec;
@@ -729,7 +736,7 @@ static int ftrace_update_code(struct module *mod)
 			return -1;
 
 		p = ftrace_new_addrs;
-		ftrace_new_addrs = (struct dyn_ftrace *)p->flags;
+		ftrace_new_addrs = p->newlist;
 		p->flags = 0L;
 
 		/* convert record (i.e, patch mcount-call with NOP) */
@@ -2262,7 +2269,7 @@ ftrace_pid_read(struct file *file, char __user *ubuf,
 	if (ftrace_pid_trace == ftrace_swapper_pid)
 		r = sprintf(buf, "swapper tasks\n");
 	else if (ftrace_pid_trace)
-		r = sprintf(buf, "%u\n", pid_nr(ftrace_pid_trace));
+		r = sprintf(buf, "%u\n", pid_vnr(ftrace_pid_trace));
 	else
 		r = sprintf(buf, "no pid\n");
 
@@ -2590,6 +2597,38 @@ free:
 	return ret;
 }
 
+static void
+ftrace_graph_probe_sched_switch(struct rq *__rq, struct task_struct *prev,
+				struct task_struct *next)
+{
+	unsigned long long timestamp;
+	int index;
+
+	/*
+	 * Does the user want to count the time a function was asleep.
+	 * If so, do not update the time stamps.
+	 */
+	if (trace_flags & TRACE_ITER_SLEEP_TIME)
+		return;
+
+	timestamp = trace_clock_local();
+
+	prev->ftrace_timestamp = timestamp;
+
+	/* only process tasks that we timestamped */
+	if (!next->ftrace_timestamp)
+		return;
+
+	/*
+	 * Update all the counters in next to make up for the
+	 * time next was sleeping.
+	 */
+	timestamp -= next->ftrace_timestamp;
+
+	for (index = next->curr_ret_stack; index >= 0; index--)
+		next->ret_stack[index].calltime += timestamp;
+}
+
 /* Allocate a return stack for each task */
 static int start_graph_tracing(void)
 {
@@ -2611,6 +2650,13 @@ static int start_graph_tracing(void)
 		ret = alloc_retstack_tasklist(ret_stack_list);
 	} while (ret == -EAGAIN);
 
+	if (!ret) {
+		ret = register_trace_sched_switch(ftrace_graph_probe_sched_switch);
+		if (ret)
+			pr_info("ftrace_graph: Couldn't activate tracepoint"
+				" probe to kernel_sched_switch\n");
+	}
+
 	kfree(ret_stack_list);
 	return ret;
 }
@@ -2643,6 +2689,12 @@ int register_ftrace_graph(trace_func_graph_ret_t retfunc,
 
 	mutex_lock(&ftrace_lock);
 
+	/* we currently allow only one tracer registered at a time */
+	if (atomic_read(&ftrace_graph_active)) {
+		ret = -EBUSY;
+		goto out;
+	}
+
 	ftrace_suspend_notifier.notifier_call = ftrace_suspend_notifier_call;
 	register_pm_notifier(&ftrace_suspend_notifier);
 
@@ -2668,6 +2720,7 @@ void unregister_ftrace_graph(void)
 	mutex_lock(&ftrace_lock);
 
 	atomic_dec(&ftrace_graph_active);
+	unregister_trace_sched_switch(ftrace_graph_probe_sched_switch);
 	ftrace_graph_return = (trace_func_graph_ret_t)ftrace_stub;
 	ftrace_graph_entry = ftrace_graph_entry_stub;
 	ftrace_shutdown(FTRACE_STOP_FUNC_RET);
@@ -2688,6 +2741,7 @@ void ftrace_graph_init_task(struct task_struct *t)
 		t->curr_ret_stack = -1;
 		atomic_set(&t->tracing_graph_pause, 0);
 		atomic_set(&t->trace_overrun, 0);
+		t->ftrace_timestamp = 0;
 	} else
 		t->ret_stack = NULL;
 }

kernel/trace/ring_buffer.c

@@ -189,16 +189,65 @@ enum {
 	RB_LEN_TIME_STAMP = 16,
 };
 
-/* inline for ring buffer fast paths */
+static inline int rb_null_event(struct ring_buffer_event *event)
+{
+	return event->type == RINGBUF_TYPE_PADDING && event->time_delta == 0;
+}
+
+static inline int rb_discarded_event(struct ring_buffer_event *event)
+{
+	return event->type == RINGBUF_TYPE_PADDING && event->time_delta;
+}
+
+static void rb_event_set_padding(struct ring_buffer_event *event)
+{
+	event->type = RINGBUF_TYPE_PADDING;
+	event->time_delta = 0;
+}
+
+/**
+ * ring_buffer_event_discard - discard an event in the ring buffer
+ * @buffer: the ring buffer
+ * @event: the event to discard
+ *
+ * Sometimes a event that is in the ring buffer needs to be ignored.
+ * This function lets the user discard an event in the ring buffer
+ * and then that event will not be read later.
+ *
+ * Note, it is up to the user to be careful with this, and protect
+ * against races. If the user discards an event that has been consumed
+ * it is possible that it could corrupt the ring buffer.
+ */
+void ring_buffer_event_discard(struct ring_buffer_event *event)
+{
+	event->type = RINGBUF_TYPE_PADDING;
+	/* time delta must be non zero */
+	if (!event->time_delta)
+		event->time_delta = 1;
+}
+
 static unsigned
-rb_event_length(struct ring_buffer_event *event)
+rb_event_data_length(struct ring_buffer_event *event)
 {
 	unsigned length;
 
+	if (event->len)
+		length = event->len * RB_ALIGNMENT;
+	else
+		length = event->array[0];
+	return length + RB_EVNT_HDR_SIZE;
+}
+
+/* inline for ring buffer fast paths */
+static unsigned
+rb_event_length(struct ring_buffer_event *event)
+{
 	switch (event->type) {
 	case RINGBUF_TYPE_PADDING:
-		/* undefined */
-		return -1;
+		if (rb_null_event(event))
+			/* undefined */
+			return -1;
+		return rb_event_data_length(event);
 
 	case RINGBUF_TYPE_TIME_EXTEND:
 		return RB_LEN_TIME_EXTEND;
@@ -207,11 +256,7 @@ rb_event_length(struct ring_buffer_event *event)
 		return RB_LEN_TIME_STAMP;
 
 	case RINGBUF_TYPE_DATA:
-		if (event->len)
-			length = event->len * RB_ALIGNMENT;
-		else
-			length = event->array[0];
-		return length + RB_EVNT_HDR_SIZE;
+		return rb_event_data_length(event);
 	default:
 		BUG();
 	}
@@ -845,11 +890,6 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
 }
 EXPORT_SYMBOL_GPL(ring_buffer_resize);
 
-static inline int rb_null_event(struct ring_buffer_event *event)
-{
-	return event->type == RINGBUF_TYPE_PADDING;
-}
-
 static inline void *
 __rb_data_page_index(struct buffer_data_page *bpage, unsigned index)
 {
@@ -1219,7 +1259,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 		if (tail < BUF_PAGE_SIZE) {
 			/* Mark the rest of the page with padding */
 			event = __rb_page_index(tail_page, tail);
-			event->type = RINGBUF_TYPE_PADDING;
+			rb_event_set_padding(event);
 		}
 
 		if (tail <= BUF_PAGE_SIZE)
@@ -1969,7 +2009,7 @@ static void rb_advance_reader(struct ring_buffer_per_cpu *cpu_buffer)
 
 	event = rb_reader_event(cpu_buffer);
 
-	if (event->type == RINGBUF_TYPE_DATA)
+	if (event->type == RINGBUF_TYPE_DATA || rb_discarded_event(event))
 		cpu_buffer->entries--;
 
 	rb_update_read_stamp(cpu_buffer, event);
@@ -2052,9 +2092,18 @@ rb_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
 
 	switch (event->type) {
 	case RINGBUF_TYPE_PADDING:
-		RB_WARN_ON(cpu_buffer, 1);
+		if (rb_null_event(event))
+			RB_WARN_ON(cpu_buffer, 1);
+		/*
+		 * Because the writer could be discarding every
+		 * event it creates (which would probably be bad)
+		 * if we were to go back to "again" then we may never
+		 * catch up, and will trigger the warn on, or lock
+		 * the box. Return the padding, and we will release
+		 * the current locks, and try again.
+		 */
 		rb_advance_reader(cpu_buffer);
-		return NULL;
+		return event;
 
 	case RINGBUF_TYPE_TIME_EXTEND:
 		/* Internal data, OK to advance */
@@ -2115,8 +2164,12 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 
 	switch (event->type) {
 	case RINGBUF_TYPE_PADDING:
-		rb_inc_iter(iter);
-		goto again;
+		if (rb_null_event(event)) {
+			rb_inc_iter(iter);
+			goto again;
+		}
+		rb_advance_iter(iter);
+		return event;
 
 	case RINGBUF_TYPE_TIME_EXTEND:
 		/* Internal data, OK to advance */
@@ -2163,10 +2216,16 @@ ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
 	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		return NULL;
 
+ again:
 	spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
 	event = rb_buffer_peek(buffer, cpu, ts);
 	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
+	if (event && event->type == RINGBUF_TYPE_PADDING) {
+		cpu_relax();
+		goto again;
+	}
+
 	return event;
 }
 
@@ -2185,10 +2244,16 @@ ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 	struct ring_buffer_event *event;
 	unsigned long flags;
 
+ again:
 	spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
 	event = rb_iter_peek(iter, ts);
 	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
+	if (event && event->type == RINGBUF_TYPE_PADDING) {
+		cpu_relax();
+		goto again;
+	}
+
 	return event;
 }
 
@@ -2207,6 +2272,7 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
 	struct ring_buffer_event *event = NULL;
 	unsigned long flags;
 
+ again:
 	/* might be called in atomic */
 	preempt_disable();
 
@@ -2228,6 +2294,11 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
  out:
 	preempt_enable();
 
+	if (event && event->type == RINGBUF_TYPE_PADDING) {
+		cpu_relax();
+		goto again;
+	}
+
 	return event;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_consume);
@@ -2306,6 +2377,7 @@ ring_buffer_read(struct ring_buffer_iter *iter, u64 *ts)
 	struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
 	unsigned long flags;
 
+ again:
 	spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
 	event = rb_iter_peek(iter, ts);
 	if (!event)
@@ -2315,6 +2387,11 @@ ring_buffer_read(struct ring_buffer_iter *iter, u64 *ts)
  out:
 	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
+	if (event && event->type == RINGBUF_TYPE_PADDING) {
+		cpu_relax();
+		goto again;
+	}
+
 	return event;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_read);

kernel/trace/trace.c

@@ -255,7 +255,7 @@ static DECLARE_WAIT_QUEUE_HEAD(trace_wait);
 
 /* trace_flags holds trace_options default values */
 unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK |
-	TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO;
+	TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO | TRACE_ITER_SLEEP_TIME;
 
 /**
  * trace_wake_up - wake up tasks waiting for trace input
@@ -316,6 +316,7 @@ static const char *trace_options[] = {
 	"context-info",
 	"latency-format",
 	"global-clock",
+	"sleep-time",
 	NULL
 };
 
@@ -382,7 +383,7 @@ ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf, size_t cnt)
 	return cnt;
 }
 
-ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt)
+static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt)
 {
 	int len;
 	void *ret;
@@ -860,15 +861,25 @@ static void ftrace_trace_stack(struct trace_array *tr,
 static void ftrace_trace_userstack(struct trace_array *tr,
 				   unsigned long flags, int pc);
 
-void trace_buffer_unlock_commit(struct trace_array *tr,
-				struct ring_buffer_event *event,
-				unsigned long flags, int pc)
+static inline void __trace_buffer_unlock_commit(struct trace_array *tr,
+					struct ring_buffer_event *event,
+					unsigned long flags, int pc,
+					int wake)
 {
 	ring_buffer_unlock_commit(tr->buffer, event);
 
 	ftrace_trace_stack(tr, flags, 6, pc);
 	ftrace_trace_userstack(tr, flags, pc);
-	trace_wake_up();
+
+	if (wake)
+		trace_wake_up();
+}
+
+void trace_buffer_unlock_commit(struct trace_array *tr,
+					struct ring_buffer_event *event,
+					unsigned long flags, int pc)
+{
+	__trace_buffer_unlock_commit(tr, event, flags, pc, 1);
 }
 
 struct ring_buffer_event *
@@ -882,7 +893,13 @@ trace_current_buffer_lock_reserve(unsigned char type, unsigned long len,
 void trace_current_buffer_unlock_commit(struct ring_buffer_event *event,
 					unsigned long flags, int pc)
 {
-	return trace_buffer_unlock_commit(&global_trace, event, flags, pc);
+	return __trace_buffer_unlock_commit(&global_trace, event, flags, pc, 1);
+}
+
+void trace_nowake_buffer_unlock_commit(struct ring_buffer_event *event,
+					unsigned long flags, int pc)
+{
+	return __trace_buffer_unlock_commit(&global_trace, event, flags, pc, 0);
 }
 
 void
@@ -908,7 +925,7 @@ trace_function(struct trace_array *tr,
 }
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-static void __trace_graph_entry(struct trace_array *tr,
+static int __trace_graph_entry(struct trace_array *tr,
 				struct ftrace_graph_ent *trace,
 				unsigned long flags,
 				int pc)
@@ -917,15 +934,17 @@ static void __trace_graph_entry(struct trace_array *tr,
 	struct ftrace_graph_ent_entry *entry;
 
 	if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
-		return;
+		return 0;
 
 	event = trace_buffer_lock_reserve(&global_trace, TRACE_GRAPH_ENT,
 					  sizeof(*entry), flags, pc);
 	if (!event)
-		return;
+		return 0;
 	entry	= ring_buffer_event_data(event);
 	entry->graph_ent			= *trace;
 	ring_buffer_unlock_commit(global_trace.buffer, event);
+
+	return 1;
 }
 
 static void __trace_graph_return(struct trace_array *tr,
@@ -1146,6 +1165,7 @@ int trace_graph_entry(struct ftrace_graph_ent *trace)
 	struct trace_array_cpu *data;
 	unsigned long flags;
 	long disabled;
+	int ret;
 	int cpu;
 	int pc;
 
@@ -1161,15 +1181,18 @@ int trace_graph_entry(struct ftrace_graph_ent *trace)
 	disabled = atomic_inc_return(&data->disabled);
 	if (likely(disabled == 1)) {
 		pc = preempt_count();
-		__trace_graph_entry(tr, trace, flags, pc);
+		ret = __trace_graph_entry(tr, trace, flags, pc);
+	} else {
+		ret = 0;
 	}
 	/* Only do the atomic if it is not already set */
 	if (!test_tsk_trace_graph(current))
 		set_tsk_trace_graph(current);
+
 	atomic_dec(&data->disabled);
 	local_irq_restore(flags);
 
-	return 1;
+	return ret;
 }
 
 void trace_graph_return(struct ftrace_graph_ret *trace)
@@ -3513,6 +3536,9 @@ struct dentry *tracing_init_dentry(void)
 	if (d_tracer)
 		return d_tracer;
 
+	if (!debugfs_initialized())
+		return NULL;
+
 	d_tracer = debugfs_create_dir("tracing", NULL);
 
 	if (!d_tracer && !once) {

kernel/trace/trace.h

@@ -483,6 +483,8 @@ trace_current_buffer_lock_reserve(unsigned char type, unsigned long len,
 				  unsigned long flags, int pc);
 void trace_current_buffer_unlock_commit(struct ring_buffer_event *event,
 					unsigned long flags, int pc);
+void trace_nowake_buffer_unlock_commit(struct ring_buffer_event *event,
+					unsigned long flags, int pc);
 
 struct trace_entry *tracing_get_trace_entry(struct trace_array *tr,
 						struct trace_array_cpu *data);
@@ -683,6 +685,7 @@ enum trace_iterator_flags {
 	TRACE_ITER_CONTEXT_INFO		= 0x20000, /* Print pid/cpu/time */
 	TRACE_ITER_LATENCY_FMT		= 0x40000,
 	TRACE_ITER_GLOBAL_CLK		= 0x80000,
+	TRACE_ITER_SLEEP_TIME		= 0x100000,
 };
 
 /*
@@ -775,16 +778,27 @@ enum {
 	TRACE_EVENT_TYPE_RAW		= 2,
 };
 
+struct ftrace_event_field {
+	struct list_head	link;
+	char			*name;
+	char			*type;
+	int			offset;
+	int			size;
+};
+
 struct ftrace_event_call {
-	char		*name;
-	char		*system;
-	struct dentry	*dir;
-	int		enabled;
-	int		(*regfunc)(void);
-	void		(*unregfunc)(void);
-	int		id;
-	int		(*raw_init)(void);
-	int		(*show_format)(struct trace_seq *s);
+	char			*name;
+	char			*system;
+	struct dentry		*dir;
+	int			enabled;
+	int			(*regfunc)(void);
+	void			(*unregfunc)(void);
+	int			id;
+	int			(*raw_init)(void);
+	int			(*show_format)(struct trace_seq *s);
+	int			(*define_fields)(void);
+	struct list_head	fields;
+	struct filter_pred	**preds;
 
 #ifdef CONFIG_EVENT_PROFILE
 	atomic_t	profile_count;
@@ -793,6 +807,51 @@ struct ftrace_event_call {
 #endif
 };
 
+struct event_subsystem {
+	struct list_head	list;
+	const char		*name;
+	struct dentry		*entry;
+	struct filter_pred	**preds;
+};
+
+#define events_for_each(event)						\
+	for (event = __start_ftrace_events;				\
+	     (unsigned long)event < (unsigned long)__stop_ftrace_events; \
+	     event++)
+
+#define MAX_FILTER_PRED 8
+
+struct filter_pred;
+
+typedef int (*filter_pred_fn_t) (struct filter_pred *pred, void *event);
+
+struct filter_pred {
+	filter_pred_fn_t fn;
+	u64 val;
+	char *str_val;
+	int str_len;
+	char *field_name;
+	int offset;
+	int not;
+	int or;
+	int compound;
+	int clear;
+};
+
+int trace_define_field(struct ftrace_event_call *call, char *type,
+		       char *name, int offset, int size);
+extern void filter_free_pred(struct filter_pred *pred);
+extern void filter_print_preds(struct filter_pred **preds,
+			       struct trace_seq *s);
+extern int filter_parse(char **pbuf, struct filter_pred *pred);
+extern int filter_add_pred(struct ftrace_event_call *call,
+			   struct filter_pred *pred);
+extern void filter_free_preds(struct ftrace_event_call *call);
+extern int filter_match_preds(struct ftrace_event_call *call, void *rec);
+extern void filter_free_subsystem_preds(struct event_subsystem *system);
+extern int filter_add_subsystem_pred(struct event_subsystem *system,
+				     struct filter_pred *pred);
+
 void event_trace_printk(unsigned long ip, const char *fmt, ...);
 extern struct ftrace_event_call __start_ftrace_events[];
 extern struct ftrace_event_call __stop_ftrace_events[];

kernel/trace/trace_clock.c

@@ -18,6 +18,7 @@
 #include <linux/percpu.h>
 #include <linux/sched.h>
 #include <linux/ktime.h>
+#include <linux/trace_clock.h>
 
 /*
  * trace_clock_local(): the simplest and least coherent tracing clock.

kernel/trace/trace_events.c

@@ -19,6 +19,39 @@
 
 static DEFINE_MUTEX(event_mutex);
 
+int trace_define_field(struct ftrace_event_call *call, char *type,
+		       char *name, int offset, int size)
+{
+	struct ftrace_event_field *field;
+
+	field = kzalloc(sizeof(*field), GFP_KERNEL);
+	if (!field)
+		goto err;
+
+	field->name = kstrdup(name, GFP_KERNEL);
+	if (!field->name)
+		goto err;
+
+	field->type = kstrdup(type, GFP_KERNEL);
+	if (!field->type)
+		goto err;
+
+	field->offset = offset;
+	field->size = size;
+	list_add(&field->link, &call->fields);
+
+	return 0;
+
+err:
+	if (field) {
+		kfree(field->name);
+		kfree(field->type);
+	}
+	kfree(field);
+
+	return -ENOMEM;
+}
+
 static void ftrace_clear_events(void)
 {
 	struct ftrace_event_call *call = (void *)__start_ftrace_events;
@@ -343,7 +376,8 @@ event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
 
 #undef FIELD
 #define FIELD(type, name)						\
-	#type, #name, offsetof(typeof(field), name), sizeof(field.name)
+	#type, "common_" #name, offsetof(typeof(field), name),		\
+		sizeof(field.name)
 
 static int trace_write_header(struct trace_seq *s)
 {
@@ -430,6 +464,139 @@ event_id_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
 	return r;
 }
 
+static ssize_t
+event_filter_read(struct file *filp, char __user *ubuf, size_t cnt,
+		  loff_t *ppos)
+{
+	struct ftrace_event_call *call = filp->private_data;
+	struct trace_seq *s;
+	int r;
+
+	if (*ppos)
+		return 0;
+
+	s = kmalloc(sizeof(*s), GFP_KERNEL);
+	if (!s)
+		return -ENOMEM;
+
+	trace_seq_init(s);
+
+	filter_print_preds(call->preds, s);
+	r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->len);
+
+	kfree(s);
+
+	return r;
+}
+
+static ssize_t
+event_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
+		   loff_t *ppos)
+{
+	struct ftrace_event_call *call = filp->private_data;
+	char buf[64], *pbuf = buf;
+	struct filter_pred *pred;
+	int err;
+
+	if (cnt >= sizeof(buf))
+		return -EINVAL;
+
+	if (copy_from_user(&buf, ubuf, cnt))
+		return -EFAULT;
+
+	pred = kzalloc(sizeof(*pred), GFP_KERNEL);
+	if (!pred)
+		return -ENOMEM;
+
+	err = filter_parse(&pbuf, pred);
+	if (err < 0) {
+		filter_free_pred(pred);
+		return err;
+	}
+
+	if (pred->clear) {
+		filter_free_preds(call);
+		filter_free_pred(pred);
+		return cnt;
+	}
+
+	if (filter_add_pred(call, pred)) {
+		filter_free_pred(pred);
+		return -EINVAL;
+	}
+
+	*ppos += cnt;
+
+	return cnt;
+}
+
+static ssize_t
+subsystem_filter_read(struct file *filp, char __user *ubuf, size_t cnt,
+		      loff_t *ppos)
+{
+	struct event_subsystem *system = filp->private_data;
+	struct trace_seq *s;
+	int r;
+
+	if (*ppos)
+		return 0;
+
+	s = kmalloc(sizeof(*s), GFP_KERNEL);
+	if (!s)
+		return -ENOMEM;
+
+	trace_seq_init(s);
+
+	filter_print_preds(system->preds, s);
+	r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->len);
+
+	kfree(s);
+
+	return r;
+}
+
+static ssize_t
+subsystem_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
+		       loff_t *ppos)
+{
+	struct event_subsystem *system = filp->private_data;
+	char buf[64], *pbuf = buf;
+	struct filter_pred *pred;
+	int err;
+
+	if (cnt >= sizeof(buf))
+		return -EINVAL;
+
+	if (copy_from_user(&buf, ubuf, cnt))
+		return -EFAULT;
+
+	pred = kzalloc(sizeof(*pred), GFP_KERNEL);
+	if (!pred)
+		return -ENOMEM;
+
+	err = filter_parse(&pbuf, pred);
+	if (err < 0) {
+		filter_free_pred(pred);
+		return err;
+	}
+
+	if (pred->clear) {
+		filter_free_subsystem_preds(system);
+		filter_free_pred(pred);
+		return cnt;
+	}
+
+	if (filter_add_subsystem_pred(system, pred)) {
+		filter_free_subsystem_preds(system);
+		filter_free_pred(pred);
+		return -EINVAL;
+	}
+
+	*ppos += cnt;
+
+	return cnt;
+}
+
 static const struct seq_operations show_event_seq_ops = {
 	.start = t_start,
 	.next = t_next,
@@ -475,6 +642,18 @@ static const struct file_operations ftrace_event_id_fops = {
 	.read = event_id_read,
 };
 
+static const struct file_operations ftrace_event_filter_fops = {
+	.open = tracing_open_generic,
+	.read = event_filter_read,
+	.write = event_filter_write,
+};
+
+static const struct file_operations ftrace_subsystem_filter_fops = {
+	.open = tracing_open_generic,
+	.read = subsystem_filter_read,
+	.write = subsystem_filter_write,
+};
+
 static struct dentry *event_trace_events_dir(void)
 {
 	static struct dentry *d_tracer;
@@ -495,12 +674,6 @@ static struct dentry *event_trace_events_dir(void)
 	return d_events;
 }
 
-struct event_subsystem {
-	struct list_head	list;
-	const char		*name;
-	struct dentry		*entry;
-};
-
 static LIST_HEAD(event_subsystems);
 
 static struct dentry *
@@ -533,6 +706,8 @@ event_subsystem_dir(const char *name, struct dentry *d_events)
 	system->name = name;
 	list_add(&system->list, &event_subsystems);
 
+	system->preds = NULL;
+
 	return system->entry;
 }
 
@@ -581,6 +756,20 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events)
 					call->name);
 	}
 
+	if (call->define_fields) {
+		ret = call->define_fields();
+		if (ret < 0) {
+			pr_warning("Could not initialize trace point"
+				   " events/%s\n", call->name);
+			return ret;
+		}
+		entry = debugfs_create_file("filter", 0644, call->dir, call,
+					    &ftrace_event_filter_fops);
+		if (!entry)
+			pr_warning("Could not create debugfs "
+				   "'%s/filter' entry\n", call->name);
+	}
+
 	/* A trace may not want to export its format */
 	if (!call->show_format)
 		return 0;

kernel/trace/trace_events_filter.c

@@ -0,0 +1,427 @@
+/*
+ * trace_events_filter - generic event filtering
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) 2009 Tom Zanussi <tzanussi@gmail.com>
+ */
+
+#include <linux/debugfs.h>
+#include <linux/uaccess.h>
+#include <linux/module.h>
+#include <linux/ctype.h>
+
+#include "trace.h"
+#include "trace_output.h"
+
+static int filter_pred_64(struct filter_pred *pred, void *event)
+{
+	u64 *addr = (u64 *)(event + pred->offset);
+	u64 val = (u64)pred->val;
+	int match;
+
+	match = (val == *addr) ^ pred->not;
+
+	return match;
+}
+
+static int filter_pred_32(struct filter_pred *pred, void *event)
+{
+	u32 *addr = (u32 *)(event + pred->offset);
+	u32 val = (u32)pred->val;
+	int match;
+
+	match = (val == *addr) ^ pred->not;
+
+	return match;
+}
+
+static int filter_pred_16(struct filter_pred *pred, void *event)
+{
+	u16 *addr = (u16 *)(event + pred->offset);
+	u16 val = (u16)pred->val;
+	int match;
+
+	match = (val == *addr) ^ pred->not;
+
+	return match;
+}
+
+static int filter_pred_8(struct filter_pred *pred, void *event)
+{
+	u8 *addr = (u8 *)(event + pred->offset);
+	u8 val = (u8)pred->val;
+	int match;
+
+	match = (val == *addr) ^ pred->not;
+
+	return match;
+}
+
+static int filter_pred_string(struct filter_pred *pred, void *event)
+{
+	char *addr = (char *)(event + pred->offset);
+	int cmp, match;
+
+	cmp = strncmp(addr, pred->str_val, pred->str_len);
+
+	match = (!cmp) ^ pred->not;
+
+	return match;
+}
+
+/* return 1 if event matches, 0 otherwise (discard) */
+int filter_match_preds(struct ftrace_event_call *call, void *rec)
+{
+	int i, matched, and_failed = 0;
+	struct filter_pred *pred;
+
+	for (i = 0; i < MAX_FILTER_PRED; i++) {
+		if (call->preds[i]) {
+			pred = call->preds[i];
+			if (and_failed && !pred->or)
+				continue;
+			matched = pred->fn(pred, rec);
+			if (!matched && !pred->or) {
+				and_failed = 1;
+				continue;
+			} else if (matched && pred->or)
+				return 1;
+		} else
+			break;
+	}
+
+	if (and_failed)
+		return 0;
+
+	return 1;
+}
+
+void filter_print_preds(struct filter_pred **preds, struct trace_seq *s)
+{
+	char *field_name;
+	struct filter_pred *pred;
+	int i;
+
+	if (!preds) {
+		trace_seq_printf(s, "none\n");
+		return;
+	}
+
+	for (i = 0; i < MAX_FILTER_PRED; i++) {
+		if (preds[i]) {
+			pred = preds[i];
+			field_name = pred->field_name;
+			if (i)
+				trace_seq_printf(s, pred->or ? "|| " : "&& ");
+			trace_seq_printf(s, "%s ", field_name);
+			trace_seq_printf(s, pred->not ? "!= " : "== ");
+			if (pred->str_val)
+				trace_seq_printf(s, "%s\n", pred->str_val);
+			else
+				trace_seq_printf(s, "%llu\n", pred->val);
+		} else
+			break;
+	}
+}
+
+static struct ftrace_event_field *
+find_event_field(struct ftrace_event_call *call, char *name)
+{
+	struct ftrace_event_field *field;
+
+	list_for_each_entry(field, &call->fields, link) {
+		if (!strcmp(field->name, name))
+			return field;
+	}
+
+	return NULL;
+}
+
+void filter_free_pred(struct filter_pred *pred)
+{
+	if (!pred)
+		return;
+
+	kfree(pred->field_name);
+	kfree(pred->str_val);
+	kfree(pred);
+}
+
+void filter_free_preds(struct ftrace_event_call *call)
+{
+	int i;
+
+	if (call->preds) {
+		for (i = 0; i < MAX_FILTER_PRED; i++)
+			filter_free_pred(call->preds[i]);
+		kfree(call->preds);
+		call->preds = NULL;
+	}
+}
+
+void filter_free_subsystem_preds(struct event_subsystem *system)
+{
+	struct ftrace_event_call *call = __start_ftrace_events;
+	int i;
+
+	if (system->preds) {
+		for (i = 0; i < MAX_FILTER_PRED; i++)
+			filter_free_pred(system->preds[i]);
+		kfree(system->preds);
+		system->preds = NULL;
+	}
+
+	events_for_each(call) {
+		if (!call->name || !call->regfunc)
+			continue;
+
+		if (!strcmp(call->system, system->name))
+			filter_free_preds(call);
+	}
+}
+
+static int __filter_add_pred(struct ftrace_event_call *call,
+			     struct filter_pred *pred)
+{
+	int i;
+
+	if (call->preds && !pred->compound)
+		filter_free_preds(call);
+
+	if (!call->preds) {
+		call->preds = kzalloc(MAX_FILTER_PRED * sizeof(pred),
+				      GFP_KERNEL);
+		if (!call->preds)
+			return -ENOMEM;
+	}
+
+	for (i = 0; i < MAX_FILTER_PRED; i++) {
+		if (!call->preds[i]) {
+			call->preds[i] = pred;
+			return 0;
+		}
+	}
+
+	return -ENOMEM;
+}
+
+static int is_string_field(const char *type)
+{
+	if (strchr(type, '[') && strstr(type, "char"))
+		return 1;
+
+	return 0;
+}
+
+int filter_add_pred(struct ftrace_event_call *call, struct filter_pred *pred)
+{
+	struct ftrace_event_field *field;
+
+	field = find_event_field(call, pred->field_name);
+	if (!field)
+		return -EINVAL;
+
+	pred->offset = field->offset;
+
+	if (is_string_field(field->type)) {
+		if (!pred->str_val)
+			return -EINVAL;
+		pred->fn = filter_pred_string;
+		pred->str_len = field->size;
+		return __filter_add_pred(call, pred);
+	} else {
+		if (pred->str_val)
+			return -EINVAL;
+	}
+
+	switch (field->size) {
+	case 8:
+		pred->fn = filter_pred_64;
+		break;
+	case 4:
+		pred->fn = filter_pred_32;
+		break;
+	case 2:
+		pred->fn = filter_pred_16;
+		break;
+	case 1:
+		pred->fn = filter_pred_8;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return __filter_add_pred(call, pred);
+}
+
+static struct filter_pred *copy_pred(struct filter_pred *pred)
+{
+	struct filter_pred *new_pred = kmalloc(sizeof(*pred), GFP_KERNEL);
+	if (!new_pred)
+		return NULL;
+
+	memcpy(new_pred, pred, sizeof(*pred));
+
+	if (pred->field_name) {
+		new_pred->field_name = kstrdup(pred->field_name, GFP_KERNEL);
+		if (!new_pred->field_name) {
+			kfree(new_pred);
+			return NULL;
+		}
+	}
+
+	if (pred->str_val) {
+		new_pred->str_val = kstrdup(pred->str_val, GFP_KERNEL);
+		if (!new_pred->str_val) {
+			filter_free_pred(new_pred);
+			return NULL;
+		}
+	}
+
+	return new_pred;
+}
+
+int filter_add_subsystem_pred(struct event_subsystem *system,
+			      struct filter_pred *pred)
+{
+	struct ftrace_event_call *call = __start_ftrace_events;
+	struct filter_pred *event_pred;
+	int i;
+
+	if (system->preds && !pred->compound)
+		filter_free_subsystem_preds(system);
+
+	if (!system->preds) {
+		system->preds = kzalloc(MAX_FILTER_PRED * sizeof(pred),
+					GFP_KERNEL);
+		if (!system->preds)
+			return -ENOMEM;
+	}
+
+	for (i = 0; i < MAX_FILTER_PRED; i++) {
+		if (!system->preds[i]) {
+			system->preds[i] = pred;
+			break;
+		}
+	}
+
+	if (i == MAX_FILTER_PRED)
+		return -EINVAL;
+
+	events_for_each(call) {
+		int err;
+
+		if (!call->name || !call->regfunc)
+			continue;
+
+		if (strcmp(call->system, system->name))
+			continue;
+
+		if (!find_event_field(call, pred->field_name))
+			continue;
+
+		event_pred = copy_pred(pred);
+		if (!event_pred)
+			goto oom;
+
+		err = filter_add_pred(call, event_pred);
+		if (err)
+			filter_free_pred(event_pred);
+		if (err == -ENOMEM)
+			goto oom;
+	}
+
+	return 0;
+
+oom:
+	system->preds[i] = NULL;
+	return -ENOMEM;
+}
+
+int filter_parse(char **pbuf, struct filter_pred *pred)
+{
+	char *tmp, *tok, *val_str = NULL;
+	int tok_n = 0;
+
+	/* field ==/!= number, or/and field ==/!= number, number */
+	while ((tok = strsep(pbuf, " \n"))) {
+		if (tok_n == 0) {
+			if (!strcmp(tok, "0")) {
+				pred->clear = 1;
+				return 0;
+			} else if (!strcmp(tok, "&&")) {
+				pred->or = 0;
+				pred->compound = 1;
+			} else if (!strcmp(tok, "||")) {
+				pred->or = 1;
+				pred->compound = 1;
+			} else
+				pred->field_name = tok;
+			tok_n = 1;
+			continue;
+		}
+		if (tok_n == 1) {
+			if (!pred->field_name)
+				pred->field_name = tok;
+			else if (!strcmp(tok, "!="))
+				pred->not = 1;
+			else if (!strcmp(tok, "=="))
+				pred->not = 0;
+			else {
+				pred->field_name = NULL;
+				return -EINVAL;
+			}
+			tok_n = 2;
+			continue;
+		}
+		if (tok_n == 2) {
+			if (pred->compound) {
+				if (!strcmp(tok, "!="))
+					pred->not = 1;
+				else if (!strcmp(tok, "=="))
+					pred->not = 0;
+				else {
+					pred->field_name = NULL;
+					return -EINVAL;
+				}
+			} else {
+				val_str = tok;
+				break; /* done */
+			}
+			tok_n = 3;
+			continue;
+		}
+		if (tok_n == 3) {
+			val_str = tok;
+			break; /* done */
+		}
+	}
+
+	pred->field_name = kstrdup(pred->field_name, GFP_KERNEL);
+	if (!pred->field_name)
+		return -ENOMEM;
+
+	pred->val = simple_strtoull(val_str, &tmp, 10);
+	if (tmp == val_str) {
+		pred->str_val = kstrdup(val_str, GFP_KERNEL);
+		if (!pred->str_val)
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
+

kernel/trace/trace_events_stage_2.h

@@ -129,3 +129,48 @@ ftrace_format_##call(struct trace_seq *s)				\
 }
 
 #include <trace/trace_event_types.h>
+
+#undef __field
+#define __field(type, item)						\
+	ret = trace_define_field(event_call, #type, #item,		\
+				 offsetof(typeof(field), item),		\
+				 sizeof(field.item));			\
+	if (ret)							\
+		return ret;
+
+#undef __array
+#define __array(type, item, len)					\
+	ret = trace_define_field(event_call, #type "[" #len "]", #item,	\
+				 offsetof(typeof(field), item),		\
+				 sizeof(field.item));			\
+	if (ret)							\
+		return ret;
+
+#define __common_field(type, item)					\
+	ret = trace_define_field(event_call, #type, "common_" #item,	\
+				 offsetof(typeof(field.ent), item),	\
+				 sizeof(field.ent.item));		\
+	if (ret)							\
+		return ret;
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(call, proto, args, tstruct, func, print)		\
+int									\
+ftrace_define_fields_##call(void)					\
+{									\
+	struct ftrace_raw_##call field;					\
+	struct ftrace_event_call *event_call = &event_##call;		\
+	int ret;							\
+									\
+	__common_field(unsigned char, type);				\
+	__common_field(unsigned char, flags);				\
+	__common_field(unsigned char, preempt_count);			\
+	__common_field(int, pid);					\
+	__common_field(int, tgid);					\
+									\
+	tstruct;							\
+									\
+	return ret;							\
+}
+
+#include <trace/trace_event_types.h>

kernel/trace/trace_events_stage_3.h

@@ -204,6 +204,7 @@ static struct ftrace_event_call event_##call;				\
 									\
 static void ftrace_raw_event_##call(proto)				\
 {									\
+	struct ftrace_event_call *call = &event_##call;			\
 	struct ring_buffer_event *event;				\
 	struct ftrace_raw_##call *entry;				\
 	unsigned long irq_flags;					\
@@ -221,7 +222,11 @@ static void ftrace_raw_event_##call(proto)				\
 									\
 	assign;								\
 									\
-	trace_current_buffer_unlock_commit(event, irq_flags, pc);	\
+	if (call->preds && !filter_match_preds(call, entry))		\
+		ring_buffer_event_discard(event);			\
+									\
+	trace_nowake_buffer_unlock_commit(event, irq_flags, pc);	\
+									\
 }									\
 									\
 static int ftrace_raw_reg_event_##call(void)				\
@@ -252,6 +257,7 @@ static int ftrace_raw_init_event_##call(void)				\
 	if (!id)							\
 		return -ENODEV;						\
 	event_##call.id = id;						\
+	INIT_LIST_HEAD(&event_##call.fields);				\
 	return 0;							\
 }									\
 									\
@@ -264,6 +270,7 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
 	.regfunc		= ftrace_raw_reg_event_##call,		\
 	.unregfunc		= ftrace_raw_unreg_event_##call,	\
 	.show_format		= ftrace_format_##call,			\
+	.define_fields		= ftrace_define_fields_##call,		\
 	_TRACE_PROFILE_INIT(call)					\
 }
 

kernel/trace/trace_functions_graph.c

@@ -57,9 +57,9 @@ static struct tracer_flags tracer_flags = {
 
 /* Add a function return address to the trace stack on thread info.*/
 int
-ftrace_push_return_trace(unsigned long ret, unsigned long long time,
-			 unsigned long func, int *depth)
+ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth)
 {
+	unsigned long long calltime;
 	int index;
 
 	if (!current->ret_stack)
@@ -71,11 +71,13 @@ ftrace_push_return_trace(unsigned long ret, unsigned long long time,
 		return -EBUSY;
 	}
 
+	calltime = trace_clock_local();
+
 	index = ++current->curr_ret_stack;
 	barrier();
 	current->ret_stack[index].ret = ret;
 	current->ret_stack[index].func = func;
-	current->ret_stack[index].calltime = time;
+	current->ret_stack[index].calltime = calltime;
 	*depth = index;
 
 	return 0;

kernel/trace/trace_nop.c

@@ -91,6 +91,7 @@ struct tracer nop_trace __read_mostly =
 	.name		= "nop",
 	.init		= nop_trace_init,
 	.reset		= nop_trace_reset,
+	.wait_pipe	= poll_wait_pipe,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest	= trace_selftest_startup_nop,
 #endif

kernel/trace/trace_output.c

@@ -137,7 +137,7 @@ int trace_seq_putc(struct trace_seq *s, unsigned char c)
 	return 1;
 }
 
-int trace_seq_putmem(struct trace_seq *s, void *mem, size_t len)
+int trace_seq_putmem(struct trace_seq *s, const void *mem, size_t len)
 {
 	if (len > ((PAGE_SIZE - 1) - s->len))
 		return 0;
@@ -148,10 +148,10 @@ int trace_seq_putmem(struct trace_seq *s, void *mem, size_t len)
 	return len;
 }
 
-int trace_seq_putmem_hex(struct trace_seq *s, void *mem, size_t len)
+int trace_seq_putmem_hex(struct trace_seq *s, const void *mem, size_t len)
 {
 	unsigned char hex[HEX_CHARS];
-	unsigned char *data = mem;
+	const unsigned char *data = mem;
 	int i, j;
 
 #ifdef __BIG_ENDIAN
@@ -167,6 +167,19 @@ int trace_seq_putmem_hex(struct trace_seq *s, void *mem, size_t len)
 	return trace_seq_putmem(s, hex, j);
 }
 
+void *trace_seq_reserve(struct trace_seq *s, size_t len)
+{
+	void *ret;
+
+	if (len > ((PAGE_SIZE - 1) - s->len))
+		return NULL;
+
+	ret = s->buffer + s->len;
+	s->len += len;
+
+	return ret;
+}
+
 int trace_seq_path(struct trace_seq *s, struct path *path)
 {
 	unsigned char *p;

kernel/trace/trace_output.h

@@ -29,24 +29,27 @@ seq_print_ip_sym(struct trace_seq *s, unsigned long ip,
 		unsigned long sym_flags);
 extern ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf,
 				 size_t cnt);
-int trace_seq_puts(struct trace_seq *s, const char *str);
-int trace_seq_putc(struct trace_seq *s, unsigned char c);
-int trace_seq_putmem(struct trace_seq *s, void *mem, size_t len);
-int trace_seq_putmem_hex(struct trace_seq *s, void *mem, size_t len);
-int trace_seq_path(struct trace_seq *s, struct path *path);
-int seq_print_userip_objs(const struct userstack_entry *entry,
-			  struct trace_seq *s, unsigned long sym_flags);
-int seq_print_user_ip(struct trace_seq *s, struct mm_struct *mm,
-		      unsigned long ip, unsigned long sym_flags);
+extern int trace_seq_puts(struct trace_seq *s, const char *str);
+extern int trace_seq_putc(struct trace_seq *s, unsigned char c);
+extern int trace_seq_putmem(struct trace_seq *s, const void *mem, size_t len);
+extern int trace_seq_putmem_hex(struct trace_seq *s, const void *mem,
+				size_t len);
+extern void *trace_seq_reserve(struct trace_seq *s, size_t len);
+extern int trace_seq_path(struct trace_seq *s, struct path *path);
+extern int seq_print_userip_objs(const struct userstack_entry *entry,
+				 struct trace_seq *s, unsigned long sym_flags);
+extern int seq_print_user_ip(struct trace_seq *s, struct mm_struct *mm,
+			     unsigned long ip, unsigned long sym_flags);
 
-int trace_print_context(struct trace_iterator *iter);
-int trace_print_lat_context(struct trace_iterator *iter);
+extern int trace_print_context(struct trace_iterator *iter);
+extern int trace_print_lat_context(struct trace_iterator *iter);
 
-struct trace_event *ftrace_find_event(int type);
-int register_ftrace_event(struct trace_event *event);
-int unregister_ftrace_event(struct trace_event *event);
+extern struct trace_event *ftrace_find_event(int type);
+extern int register_ftrace_event(struct trace_event *event);
+extern int unregister_ftrace_event(struct trace_event *event);
 
-enum print_line_t trace_nop_print(struct trace_iterator *iter, int flags);
+extern enum print_line_t trace_nop_print(struct trace_iterator *iter,
+					 int flags);
 
 #define MAX_MEMHEX_BYTES	8
 #define HEX_CHARS		(MAX_MEMHEX_BYTES*2 + 1)

kernel/trace/trace_stat.c

@@ -75,7 +75,7 @@ static int stat_seq_init(struct tracer_stat_session *session)
 {
 	struct trace_stat_list *iter_entry, *new_entry;
 	struct tracer_stat *ts = session->ts;
-	void *prev_stat;
+	void *stat;
 	int ret = 0;
 	int i;
 
@@ -85,6 +85,10 @@ static int stat_seq_init(struct tracer_stat_session *session)
 	if (!ts->stat_cmp)
 		ts->stat_cmp = dummy_cmp;
 
+	stat = ts->stat_start();
+	if (!stat)
+		goto exit;
+
 	/*
 	 * The first entry. Actually this is the second, but the first
 	 * one (the stat_list head) is pointless.
@@ -99,14 +103,19 @@ static int stat_seq_init(struct tracer_stat_session *session)
 
 	list_add(&new_entry->list, &session->stat_list);
 
-	new_entry->stat = ts->stat_start();
-	prev_stat = new_entry->stat;
+	new_entry->stat = stat;
 
 	/*
 	 * Iterate over the tracer stat entries and store them in a sorted
 	 * list.
 	 */
 	for (i = 1; ; i++) {
+		stat = ts->stat_next(stat, i);
+
+		/* End of insertion */
+		if (!stat)
+			break;
+
 		new_entry = kmalloc(sizeof(struct trace_stat_list), GFP_KERNEL);
 		if (!new_entry) {
 			ret = -ENOMEM;
@@ -114,31 +123,23 @@ static int stat_seq_init(struct tracer_stat_session *session)
 		}
 
 		INIT_LIST_HEAD(&new_entry->list);
-		new_entry->stat = ts->stat_next(prev_stat, i);
+		new_entry->stat = stat;
 
-		/* End of insertion */
-		if (!new_entry->stat)
-			break;
-
-		list_for_each_entry(iter_entry, &session->stat_list, list) {
+		list_for_each_entry_reverse(iter_entry, &session->stat_list,
+				list) {
 
 			/* Insertion with a descendent sorting */
-			if (ts->stat_cmp(new_entry->stat,
-						iter_entry->stat) > 0) {
-
-				list_add_tail(&new_entry->list,
-						&iter_entry->list);
-				break;
+			if (ts->stat_cmp(iter_entry->stat,
+					new_entry->stat) >= 0) {
 
-			/* The current smaller value */
-			} else if (list_is_last(&iter_entry->list,
-						&session->stat_list)) {
 				list_add(&new_entry->list, &iter_entry->list);
 				break;
 			}
 		}
 
-		prev_stat = new_entry->stat;
+		/* The current larger value */
+		if (list_empty(&new_entry->list))
+			list_add(&new_entry->list, &session->stat_list);
 	}
 exit:
 	mutex_unlock(&session->stat_mutex);
@@ -160,7 +161,7 @@ static void *stat_seq_start(struct seq_file *s, loff_t *pos)
 
 	/* If we are in the beginning of the file, print the headers */
 	if (!*pos && session->ts->stat_headers)
-		session->ts->stat_headers(s);
+		return SEQ_START_TOKEN;
 
 	return seq_list_start(&session->stat_list, *pos);
 }
@@ -169,6 +170,9 @@ static void *stat_seq_next(struct seq_file *s, void *p, loff_t *pos)
 {
 	struct tracer_stat_session *session = s->private;
 
+	if (p == SEQ_START_TOKEN)
+		return seq_list_start(&session->stat_list, *pos);
+
 	return seq_list_next(p, &session->stat_list, pos);
 }
 
@@ -183,6 +187,9 @@ static int stat_seq_show(struct seq_file *s, void *v)
 	struct tracer_stat_session *session = s->private;
 	struct trace_stat_list *l = list_entry(v, struct trace_stat_list, list);
 
+	if (v == SEQ_START_TOKEN)
+		return session->ts->stat_headers(s);
+
 	return session->ts->stat_show(s, l->stat);
 }
 

kernel/trace/trace_workqueue.c

@@ -196,6 +196,11 @@ static int workqueue_stat_show(struct seq_file *s, void *p)
 	struct pid *pid;
 	struct task_struct *tsk;
 
+	spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags);
+	if (&cws->list == workqueue_cpu_stat(cpu)->list.next)
+		seq_printf(s, "\n");
+	spin_unlock_irqrestore(&workqueue_cpu_stat(cpu)->lock, flags);
+
 	pid = find_get_pid(cws->pid);
 	if (pid) {
 		tsk = get_pid_task(pid, PIDTYPE_PID);
@@ -208,18 +213,13 @@ static int workqueue_stat_show(struct seq_file *s, void *p)
 		put_pid(pid);
 	}
 
-	spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags);
-	if (&cws->list == workqueue_cpu_stat(cpu)->list.next)
-		seq_printf(s, "\n");
-	spin_unlock_irqrestore(&workqueue_cpu_stat(cpu)->lock, flags);
-
 	return 0;
 }
 
 static int workqueue_stat_headers(struct seq_file *s)
 {
 	seq_printf(s, "# CPU  INSERTED  EXECUTED   NAME\n");
-	seq_printf(s, "# |      |         |          |\n\n");
+	seq_printf(s, "# |      |         |          |\n");
 	return 0;
 }
 

mm/memory.c

@@ -48,8 +48,6 @@
 #include <linux/rmap.h>
 #include <linux/module.h>
 #include <linux/delayacct.h>
-#include <linux/kprobes.h>
-#include <linux/mutex.h>
 #include <linux/init.h>
 #include <linux/writeback.h>
 #include <linux/memcontrol.h>