1 files changed, 443 insertions, 193 deletions

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 24c1f238255..16f7038d1f4 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -73,7 +73,8 @@ static struct tracer_flags dummy_tracer_flags = {
 	.opts = dummy_tracer_opt
 };
 
-static int dummy_set_flag(u32 old_flags, u32 bit, int set)
+static int
+dummy_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
 {
 	return 0;
 }
@@ -118,7 +119,7 @@ enum ftrace_dump_mode ftrace_dump_on_oops;
 /* When set, tracing will stop when a WARN*() is hit */
 int __disable_trace_on_warning;
 
-static int tracing_set_tracer(const char *buf);
+static int tracing_set_tracer(struct trace_array *tr, const char *buf);
 
 #define MAX_TRACER_SIZE		100
 static char bootup_tracer_buf[MAX_TRACER_SIZE] __initdata;
@@ -180,6 +181,17 @@ static int __init set_trace_boot_options(char *str)
 }
 __setup("trace_options=", set_trace_boot_options);
 
+static char trace_boot_clock_buf[MAX_TRACER_SIZE] __initdata;
+static char *trace_boot_clock __initdata;
+
+static int __init set_trace_boot_clock(char *str)
+{
+	strlcpy(trace_boot_clock_buf, str, MAX_TRACER_SIZE);
+	trace_boot_clock = trace_boot_clock_buf;
+	return 0;
+}
+__setup("trace_clock=", set_trace_boot_clock);
+
 
 unsigned long long ns2usecs(cycle_t nsec)
 {
@@ -263,7 +275,7 @@ int call_filter_check_discard(struct ftrace_event_call *call, void *rec,
 }
 EXPORT_SYMBOL_GPL(call_filter_check_discard);
 
-cycle_t buffer_ftrace_now(struct trace_buffer *buf, int cpu)
+static cycle_t buffer_ftrace_now(struct trace_buffer *buf, int cpu)
 {
 	u64 ts;
 
@@ -587,7 +599,7 @@ static int alloc_snapshot(struct trace_array *tr)
 	return 0;
 }
 
-void free_snapshot(struct trace_array *tr)
+static void free_snapshot(struct trace_array *tr)
 {
 	/*
 	 * We don't free the ring buffer. instead, resize it because
@@ -951,27 +963,9 @@ static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt)
 	return cnt;
 }
 
-/*
- * ftrace_max_lock is used to protect the swapping of buffers
- * when taking a max snapshot. The buffers themselves are
- * protected by per_cpu spinlocks. But the action of the swap
- * needs its own lock.
- *
- * This is defined as a arch_spinlock_t in order to help
- * with performance when lockdep debugging is enabled.
- *
- * It is also used in other places outside the update_max_tr
- * so it needs to be defined outside of the
- * CONFIG_TRACER_MAX_TRACE.
- */
-static arch_spinlock_t ftrace_max_lock =
-	(arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
-
 unsigned long __read_mostly	tracing_thresh;
 
 #ifdef CONFIG_TRACER_MAX_TRACE
-unsigned long __read_mostly	tracing_max_latency;
-
 /*
  * Copy the new maximum trace into the separate maximum-trace
  * structure. (this way the maximum trace is permanently saved,
@@ -988,7 +982,7 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 	max_buf->cpu = cpu;
 	max_buf->time_start = data->preempt_timestamp;
 
-	max_data->saved_latency = tracing_max_latency;
+	max_data->saved_latency = tr->max_latency;
 	max_data->critical_start = data->critical_start;
 	max_data->critical_end = data->critical_end;
 
@@ -1036,14 +1030,14 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 		return;
 	}
 
-	arch_spin_lock(&ftrace_max_lock);
+	arch_spin_lock(&tr->max_lock);
 
 	buf = tr->trace_buffer.buffer;
 	tr->trace_buffer.buffer = tr->max_buffer.buffer;
 	tr->max_buffer.buffer = buf;
 
 	__update_max_tr(tr, tsk, cpu);
-	arch_spin_unlock(&ftrace_max_lock);
+	arch_spin_unlock(&tr->max_lock);
 }
 
 /**
@@ -1069,7 +1063,7 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
 		return;
 	}
 
-	arch_spin_lock(&ftrace_max_lock);
+	arch_spin_lock(&tr->max_lock);
 
 	ret = ring_buffer_swap_cpu(tr->max_buffer.buffer, tr->trace_buffer.buffer, cpu);
 
@@ -1087,11 +1081,11 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
 	WARN_ON_ONCE(ret && ret != -EAGAIN && ret != -EBUSY);
 
 	__update_max_tr(tr, tsk, cpu);
-	arch_spin_unlock(&ftrace_max_lock);
+	arch_spin_unlock(&tr->max_lock);
 }
 #endif /* CONFIG_TRACER_MAX_TRACE */
 
-static void default_wait_pipe(struct trace_iterator *iter)
+static void wait_on_pipe(struct trace_iterator *iter)
 {
 	/* Iterators are static, they should be filled or empty */
 	if (trace_buffer_iter(iter, iter->cpu_file))
@@ -1208,8 +1202,6 @@ int register_tracer(struct tracer *type)
 	else
 		if (!type->flags->opts)
 			type->flags->opts = dummy_tracer_opt;
-	if (!type->wait_pipe)
-		type->wait_pipe = default_wait_pipe;
 
 	ret = run_tracer_selftest(type);
 	if (ret < 0)
@@ -1230,7 +1222,7 @@ int register_tracer(struct tracer *type)
 
 	printk(KERN_INFO "Starting tracer '%s'\n", type->name);
 	/* Do we want this tracer to start on bootup? */
-	tracing_set_tracer(type->name);
+	tracing_set_tracer(&global_trace, type->name);
 	default_bootup_tracer = NULL;
 	/* disable other selftests, since this will break it. */
 	tracing_selftest_disabled = true;
@@ -1293,22 +1285,71 @@ void tracing_reset_all_online_cpus(void)
 	}
 }
 
-#define SAVED_CMDLINES 128
+#define SAVED_CMDLINES_DEFAULT 128
 #define NO_CMDLINE_MAP UINT_MAX
-static unsigned map_pid_to_cmdline[PID_MAX_DEFAULT+1];
-static unsigned map_cmdline_to_pid[SAVED_CMDLINES];
-static char saved_cmdlines[SAVED_CMDLINES][TASK_COMM_LEN];
-static int cmdline_idx;
 static arch_spinlock_t trace_cmdline_lock = __ARCH_SPIN_LOCK_UNLOCKED;
+struct saved_cmdlines_buffer {
+	unsigned map_pid_to_cmdline[PID_MAX_DEFAULT+1];
+	unsigned *map_cmdline_to_pid;
+	unsigned cmdline_num;
+	int cmdline_idx;
+	char *saved_cmdlines;
+};
+static struct saved_cmdlines_buffer *savedcmd;
 
 /* temporary disable recording */
 static atomic_t trace_record_cmdline_disabled __read_mostly;
 
-static void trace_init_cmdlines(void)
+static inline char *get_saved_cmdlines(int idx)
+{
+	return &savedcmd->saved_cmdlines[idx * TASK_COMM_LEN];
+}
+
+static inline void set_cmdline(int idx, const char *cmdline)
+{
+	memcpy(get_saved_cmdlines(idx), cmdline, TASK_COMM_LEN);
+}
+
+static int allocate_cmdlines_buffer(unsigned int val,
+				    struct saved_cmdlines_buffer *s)
 {
-	memset(&map_pid_to_cmdline, NO_CMDLINE_MAP, sizeof(map_pid_to_cmdline));
-	memset(&map_cmdline_to_pid, NO_CMDLINE_MAP, sizeof(map_cmdline_to_pid));
-	cmdline_idx = 0;
+	s->map_cmdline_to_pid = kmalloc(val * sizeof(*s->map_cmdline_to_pid),
+					GFP_KERNEL);
+	if (!s->map_cmdline_to_pid)
+		return -ENOMEM;
+
+	s->saved_cmdlines = kmalloc(val * TASK_COMM_LEN, GFP_KERNEL);
+	if (!s->saved_cmdlines) {
+		kfree(s->map_cmdline_to_pid);
+		return -ENOMEM;
+	}
+
+	s->cmdline_idx = 0;
+	s->cmdline_num = val;
+	memset(&s->map_pid_to_cmdline, NO_CMDLINE_MAP,
+	       sizeof(s->map_pid_to_cmdline));
+	memset(s->map_cmdline_to_pid, NO_CMDLINE_MAP,
+	       val * sizeof(*s->map_cmdline_to_pid));
+
+	return 0;
+}
+
+static int trace_create_savedcmd(void)
+{
+	int ret;
+
+	savedcmd = kmalloc(sizeof(struct saved_cmdlines_buffer), GFP_KERNEL);
+	if (!savedcmd)
+		return -ENOMEM;
+
+	ret = allocate_cmdlines_buffer(SAVED_CMDLINES_DEFAULT, savedcmd);
+	if (ret < 0) {
+		kfree(savedcmd);
+		savedcmd = NULL;
+		return -ENOMEM;
+	}
+
+	return 0;
 }
 
 int is_tracing_stopped(void)
@@ -1341,7 +1382,7 @@ void tracing_start(void)
 	}
 
 	/* Prevent the buffers from switching */
-	arch_spin_lock(&ftrace_max_lock);
+	arch_spin_lock(&global_trace.max_lock);
 
 	buffer = global_trace.trace_buffer.buffer;
 	if (buffer)
@@ -1353,7 +1394,7 @@ void tracing_start(void)
 		ring_buffer_record_enable(buffer);
 #endif
 
-	arch_spin_unlock(&ftrace_max_lock);
+	arch_spin_unlock(&global_trace.max_lock);
 
 	ftrace_start();
  out:
@@ -1408,7 +1449,7 @@ void tracing_stop(void)
 		goto out;
 
 	/* Prevent the buffers from switching */
-	arch_spin_lock(&ftrace_max_lock);
+	arch_spin_lock(&global_trace.max_lock);
 
 	buffer = global_trace.trace_buffer.buffer;
 	if (buffer)
@@ -1420,7 +1461,7 @@ void tracing_stop(void)
 		ring_buffer_record_disable(buffer);
 #endif
 
-	arch_spin_unlock(&ftrace_max_lock);
+	arch_spin_unlock(&global_trace.max_lock);
 
  out:
 	raw_spin_unlock_irqrestore(&global_trace.start_lock, flags);
@@ -1449,12 +1490,12 @@ static void tracing_stop_tr(struct trace_array *tr)
 
 void trace_stop_cmdline_recording(void);
 
-static void trace_save_cmdline(struct task_struct *tsk)
+static int trace_save_cmdline(struct task_struct *tsk)
 {
 	unsigned pid, idx;
 
 	if (!tsk->pid || unlikely(tsk->pid > PID_MAX_DEFAULT))
-		return;
+		return 0;
 
 	/*
 	 * It's not the end of the world if we don't get
@@ -1463,11 +1504,11 @@ static void trace_save_cmdline(struct task_struct *tsk)
 	 * so if we miss here, then better luck next time.
 	 */
 	if (!arch_spin_trylock(&trace_cmdline_lock))
-		return;
+		return 0;
 
-	idx = map_pid_to_cmdline[tsk->pid];
+	idx = savedcmd->map_pid_to_cmdline[tsk->pid];
 	if (idx == NO_CMDLINE_MAP) {
-		idx = (cmdline_idx + 1) % SAVED_CMDLINES;
+		idx = (savedcmd->cmdline_idx + 1) % savedcmd->cmdline_num;
 
 		/*
 		 * Check whether the cmdline buffer at idx has a pid
@@ -1475,22 +1516,24 @@ static void trace_save_cmdline(struct task_struct *tsk)
 		 * need to clear the map_pid_to_cmdline. Otherwise we
 		 * would read the new comm for the old pid.
 		 */
-		pid = map_cmdline_to_pid[idx];
+		pid = savedcmd->map_cmdline_to_pid[idx];
 		if (pid != NO_CMDLINE_MAP)
-			map_pid_to_cmdline[pid] = NO_CMDLINE_MAP;
+			savedcmd->map_pid_to_cmdline[pid] = NO_CMDLINE_MAP;
 
-		map_cmdline_to_pid[idx] = tsk->pid;
-		map_pid_to_cmdline[tsk->pid] = idx;
+		savedcmd->map_cmdline_to_pid[idx] = tsk->pid;
+		savedcmd->map_pid_to_cmdline[tsk->pid] = idx;
 
-		cmdline_idx = idx;
+		savedcmd->cmdline_idx = idx;
 	}
 
-	memcpy(&saved_cmdlines[idx], tsk->comm, TASK_COMM_LEN);
+	set_cmdline(idx, tsk->comm);
 
 	arch_spin_unlock(&trace_cmdline_lock);
+
+	return 1;
 }
 
-void trace_find_cmdline(int pid, char comm[])
+static void __trace_find_cmdline(int pid, char comm[])
 {
 	unsigned map;
 
@@ -1509,13 +1552,19 @@ void trace_find_cmdline(int pid, char comm[])
 		return;
 	}
 
-	preempt_disable();
-	arch_spin_lock(&trace_cmdline_lock);
-	map = map_pid_to_cmdline[pid];
+	map = savedcmd->map_pid_to_cmdline[pid];
 	if (map != NO_CMDLINE_MAP)
-		strcpy(comm, saved_cmdlines[map]);
+		strcpy(comm, get_saved_cmdlines(map));
 	else
 		strcpy(comm, "<...>");
+}
+
+void trace_find_cmdline(int pid, char comm[])
+{
+	preempt_disable();
+	arch_spin_lock(&trace_cmdline_lock);
+
+	__trace_find_cmdline(pid, comm);
 
 	arch_spin_unlock(&trace_cmdline_lock);
 	preempt_enable();
@@ -1529,9 +1578,8 @@ void tracing_record_cmdline(struct task_struct *tsk)
 	if (!__this_cpu_read(trace_cmdline_save))
 		return;
 
-	__this_cpu_write(trace_cmdline_save, false);
-
-	trace_save_cmdline(tsk);
+	if (trace_save_cmdline(tsk))
+		__this_cpu_write(trace_cmdline_save, false);
 }
 
 void
@@ -1734,7 +1782,7 @@ static void __ftrace_trace_stack(struct ring_buffer *buffer,
 	 */
 	barrier();
 	if (use_stack == 1) {
-		trace.entries		= &__get_cpu_var(ftrace_stack).calls[0];
+		trace.entries		= this_cpu_ptr(ftrace_stack.calls);
 		trace.max_entries	= FTRACE_STACK_MAX_ENTRIES;
 
 		if (regs)
@@ -1983,7 +2031,21 @@ void trace_printk_init_buffers(void)
 	if (alloc_percpu_trace_buffer())
 		return;
 
-	pr_info("ftrace: Allocated trace_printk buffers\n");
+	/* trace_printk() is for debug use only. Don't use it in production. */
+
+	pr_warning("\n**********************************************************\n");
+	pr_warning("**   NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE   **\n");
+	pr_warning("**                                                      **\n");
+	pr_warning("** trace_printk() being used. Allocating extra memory.  **\n");
+	pr_warning("**                                                      **\n");
+	pr_warning("** This means that this is a DEBUG kernel and it is     **\n");
+	pr_warning("** unsafe for produciton use.                           **\n");
+	pr_warning("**                                                      **\n");
+	pr_warning("** If you see this message and you are not debugging    **\n");
+	pr_warning("** the kernel, report this immediately to your vendor!  **\n");
+	pr_warning("**                                                      **\n");
+	pr_warning("**   NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE   **\n");
+	pr_warning("**********************************************************\n");
 
 	/* Expand the buffers to set size */
 	tracing_update_buffers();
@@ -3137,27 +3199,52 @@ static int tracing_open(struct inode *inode, struct file *file)
 	return ret;
 }
 
+/*
+ * Some tracers are not suitable for instance buffers.
+ * A tracer is always available for the global array (toplevel)
+ * or if it explicitly states that it is.
+ */
+static bool
+trace_ok_for_array(struct tracer *t, struct trace_array *tr)
+{
+	return (tr->flags & TRACE_ARRAY_FL_GLOBAL) || t->allow_instances;
+}
+
+/* Find the next tracer that this trace array may use */
+static struct tracer *
+get_tracer_for_array(struct trace_array *tr, struct tracer *t)
+{
+	while (t && !trace_ok_for_array(t, tr))
+		t = t->next;
+
+	return t;
+}
+
 static void *
 t_next(struct seq_file *m, void *v, loff_t *pos)
 {
+	struct trace_array *tr = m->private;
 	struct tracer *t = v;
 
 	(*pos)++;
 
 	if (t)
-		t = t->next;
+		t = get_tracer_for_array(tr, t->next);
 
 	return t;
 }
 
 static void *t_start(struct seq_file *m, loff_t *pos)
 {
+	struct trace_array *tr = m->private;
 	struct tracer *t;
 	loff_t l = 0;
 
 	mutex_lock(&trace_types_lock);
-	for (t = trace_types; t && l < *pos; t = t_next(m, t, &l))
-		;
+
+	t = get_tracer_for_array(tr, trace_types);
+	for (; t && l < *pos; t = t_next(m, t, &l))
+			;
 
 	return t;
 }
@@ -3192,10 +3279,21 @@ static const struct seq_operations show_traces_seq_ops = {
 
 static int show_traces_open(struct inode *inode, struct file *file)
 {
+	struct trace_array *tr = inode->i_private;
+	struct seq_file *m;
+	int ret;
+
 	if (tracing_disabled)
 		return -ENODEV;
 
-	return seq_open(file, &show_traces_seq_ops);
+	ret = seq_open(file, &show_traces_seq_ops);
+	if (ret)
+		return ret;
+
+	m = file->private_data;
+	m->private = tr;
+
+	return 0;
 }
 
 static ssize_t
@@ -3285,7 +3383,7 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
 	mutex_lock(&tracing_cpumask_update_lock);
 
 	local_irq_disable();
-	arch_spin_lock(&ftrace_max_lock);
+	arch_spin_lock(&tr->max_lock);
 	for_each_tracing_cpu(cpu) {
 		/*
 		 * Increase/decrease the disabled counter if we are
@@ -3302,7 +3400,7 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
 			ring_buffer_record_enable_cpu(tr->trace_buffer.buffer, cpu);
 		}
 	}
-	arch_spin_unlock(&ftrace_max_lock);
+	arch_spin_unlock(&tr->max_lock);
 	local_irq_enable();
 
 	cpumask_copy(tr->tracing_cpumask, tracing_cpumask_new);
@@ -3355,13 +3453,14 @@ static int tracing_trace_options_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int __set_tracer_option(struct tracer *trace,
+static int __set_tracer_option(struct trace_array *tr,
 			       struct tracer_flags *tracer_flags,
 			       struct tracer_opt *opts, int neg)
 {
+	struct tracer *trace = tr->current_trace;
 	int ret;
 
-	ret = trace->set_flag(tracer_flags->val, opts->bit, !neg);
+	ret = trace->set_flag(tr, tracer_flags->val, opts->bit, !neg);
 	if (ret)
 		return ret;
 
@@ -3373,8 +3472,9 @@ static int __set_tracer_option(struct tracer *trace,
 }
 
 /* Try to assign a tracer specific option */
-static int set_tracer_option(struct tracer *trace, char *cmp, int neg)
+static int set_tracer_option(struct trace_array *tr, char *cmp, int neg)
 {
+	struct tracer *trace = tr->current_trace;
 	struct tracer_flags *tracer_flags = trace->flags;
 	struct tracer_opt *opts = NULL;
 	int i;
@@ -3383,8 +3483,7 @@ static int set_tracer_option(struct tracer *trace, char *cmp, int neg)
 		opts = &tracer_flags->opts[i];
 
 		if (strcmp(cmp, opts->name) == 0)
-			return __set_tracer_option(trace, trace->flags,
-						   opts, neg);
+			return __set_tracer_option(tr, trace->flags, opts, neg);
 	}
 
 	return -EINVAL;
@@ -3407,7 +3506,7 @@ int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled)
 
 	/* Give the tracer a chance to approve the change */
 	if (tr->current_trace->flag_changed)
-		if (tr->current_trace->flag_changed(tr->current_trace, mask, !!enabled))
+		if (tr->current_trace->flag_changed(tr, mask, !!enabled))
 			return -EINVAL;
 
 	if (enabled)
@@ -3456,7 +3555,7 @@ static int trace_set_options(struct trace_array *tr, char *option)
 
 	/* If no option could be set, test the specific tracer options */
 	if (!trace_options[i])
-		ret = set_tracer_option(tr->current_trace, cmp, neg);
+		ret = set_tracer_option(tr, cmp, neg);
 
 	mutex_unlock(&trace_types_lock);
 
@@ -3543,6 +3642,7 @@ static const char readme_msg[] =
 	"  trace_options\t\t- Set format or modify how tracing happens\n"
 	"\t\t\t  Disable an option by adding a suffix 'no' to the\n"
 	"\t\t\t  option name\n"
+	"  saved_cmdlines_size\t- echo command number in here to store comm-pid list\n"
 #ifdef CONFIG_DYNAMIC_FTRACE
 	"\n  available_filter_functions - list of functions that can be filtered on\n"
 	"  set_ftrace_filter\t- echo function name in here to only trace these\n"
@@ -3562,6 +3662,8 @@ static const char readme_msg[] =
 #ifdef CONFIG_TRACER_SNAPSHOT
 	"\t\t      snapshot\n"
 #endif
+	"\t\t      dump\n"
+	"\t\t      cpudump\n"
 	"\t     example: echo do_fault:traceoff > set_ftrace_filter\n"
 	"\t              echo do_trap:traceoff:3 > set_ftrace_filter\n"
 	"\t     The first one will disable tracing every time do_fault is hit\n"
@@ -3654,55 +3756,153 @@ static const struct file_operations tracing_readme_fops = {
 	.llseek		= generic_file_llseek,
 };
 
+static void *saved_cmdlines_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	unsigned int *ptr = v;
+
+	if (*pos || m->count)
+		ptr++;
+
+	(*pos)++;
+
+	for (; ptr < &savedcmd->map_cmdline_to_pid[savedcmd->cmdline_num];
+	     ptr++) {
+		if (*ptr == -1 || *ptr == NO_CMDLINE_MAP)
+			continue;
+
+		return ptr;
+	}
+
+	return NULL;
+}
+
+static void *saved_cmdlines_start(struct seq_file *m, loff_t *pos)
+{
+	void *v;
+	loff_t l = 0;
+
+	preempt_disable();
+	arch_spin_lock(&trace_cmdline_lock);
+
+	v = &savedcmd->map_cmdline_to_pid[0];
+	while (l <= *pos) {
+		v = saved_cmdlines_next(m, v, &l);
+		if (!v)
+			return NULL;
+	}
+
+	return v;
+}
+
+static void saved_cmdlines_stop(struct seq_file *m, void *v)
+{
+	arch_spin_unlock(&trace_cmdline_lock);
+	preempt_enable();
+}
+
+static int saved_cmdlines_show(struct seq_file *m, void *v)
+{
+	char buf[TASK_COMM_LEN];
+	unsigned int *pid = v;
+
+	__trace_find_cmdline(*pid, buf);
+	seq_printf(m, "%d %s\n", *pid, buf);
+	return 0;
+}
+
+static const struct seq_operations tracing_saved_cmdlines_seq_ops = {
+	.start		= saved_cmdlines_start,
+	.next		= saved_cmdlines_next,
+	.stop		= saved_cmdlines_stop,
+	.show		= saved_cmdlines_show,
+};
+
+static int tracing_saved_cmdlines_open(struct inode *inode, struct file *filp)
+{
+	if (tracing_disabled)
+		return -ENODEV;
+
+	return seq_open(filp, &tracing_saved_cmdlines_seq_ops);
+}
+
+static const struct file_operations tracing_saved_cmdlines_fops = {
+	.open		= tracing_saved_cmdlines_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
 static ssize_t
-tracing_saved_cmdlines_read(struct file *file, char __user *ubuf,
-				size_t cnt, loff_t *ppos)
+tracing_saved_cmdlines_size_read(struct file *filp, char __user *ubuf,
+				 size_t cnt, loff_t *ppos)
 {
-	char *buf_comm;
-	char *file_buf;
-	char *buf;
-	int len = 0;
-	int pid;
-	int i;
+	char buf[64];
+	int r;
+
+	arch_spin_lock(&trace_cmdline_lock);
+	r = sprintf(buf, "%u\n", savedcmd->cmdline_num);
+	arch_spin_unlock(&trace_cmdline_lock);
+
+	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+}
 
-	file_buf = kmalloc(SAVED_CMDLINES*(16+TASK_COMM_LEN), GFP_KERNEL);
-	if (!file_buf)
+static void free_saved_cmdlines_buffer(struct saved_cmdlines_buffer *s)
+{
+	kfree(s->saved_cmdlines);
+	kfree(s->map_cmdline_to_pid);
+	kfree(s);
+}
+
+static int tracing_resize_saved_cmdlines(unsigned int val)
+{
+	struct saved_cmdlines_buffer *s, *savedcmd_temp;
+
+	s = kmalloc(sizeof(struct saved_cmdlines_buffer), GFP_KERNEL);
+	if (!s)
 		return -ENOMEM;
 
-	buf_comm = kmalloc(TASK_COMM_LEN, GFP_KERNEL);
-	if (!buf_comm) {
-		kfree(file_buf);
+	if (allocate_cmdlines_buffer(val, s) < 0) {
+		kfree(s);
 		return -ENOMEM;
 	}
 
-	buf = file_buf;
+	arch_spin_lock(&trace_cmdline_lock);
+	savedcmd_temp = savedcmd;
+	savedcmd = s;
+	arch_spin_unlock(&trace_cmdline_lock);
+	free_saved_cmdlines_buffer(savedcmd_temp);
 
-	for (i = 0; i < SAVED_CMDLINES; i++) {
-		int r;
+	return 0;
+}
 
-		pid = map_cmdline_to_pid[i];
-		if (pid == -1 || pid == NO_CMDLINE_MAP)
-			continue;
+static ssize_t
+tracing_saved_cmdlines_size_write(struct file *filp, const char __user *ubuf,
+				  size_t cnt, loff_t *ppos)
+{
+	unsigned long val;
+	int ret;
 
-		trace_find_cmdline(pid, buf_comm);
-		r = sprintf(buf, "%d %s\n", pid, buf_comm);
-		buf += r;
-		len += r;
-	}
+	ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
+	if (ret)
+		return ret;
 
-	len = simple_read_from_buffer(ubuf, cnt, ppos,
-				      file_buf, len);
+	/* must have at least 1 entry or less than PID_MAX_DEFAULT */
+	if (!val || val > PID_MAX_DEFAULT)
+		return -EINVAL;
 
-	kfree(file_buf);
-	kfree(buf_comm);
+	ret = tracing_resize_saved_cmdlines((unsigned int)val);
+	if (ret < 0)
+		return ret;
 
-	return len;
+	*ppos += cnt;
+
+	return cnt;
 }
 
-static const struct file_operations tracing_saved_cmdlines_fops = {
-    .open       = tracing_open_generic,
-    .read       = tracing_saved_cmdlines_read,
-    .llseek	= generic_file_llseek,
+static const struct file_operations tracing_saved_cmdlines_size_fops = {
+	.open		= tracing_open_generic,
+	.read		= tracing_saved_cmdlines_size_read,
+	.write		= tracing_saved_cmdlines_size_write,
 };
 
 static ssize_t
@@ -3885,10 +4085,26 @@ create_trace_option_files(struct trace_array *tr, struct tracer *tracer);
 static void
 destroy_trace_option_files(struct trace_option_dentry *topts);
 
-static int tracing_set_tracer(const char *buf)
+/*
+ * Used to clear out the tracer before deletion of an instance.
+ * Must have trace_types_lock held.
+ */
+static void tracing_set_nop(struct trace_array *tr)
+{
+	if (tr->current_trace == &nop_trace)
+		return;
+	
+	tr->current_trace->enabled--;
+
+	if (tr->current_trace->reset)
+		tr->current_trace->reset(tr);
+
+	tr->current_trace = &nop_trace;
+}
+
+static int tracing_set_tracer(struct trace_array *tr, const char *buf)
 {
 	static struct trace_option_dentry *topts;
-	struct trace_array *tr = &global_trace;
 	struct tracer *t;
 #ifdef CONFIG_TRACER_MAX_TRACE
 	bool had_max_tr;
@@ -3916,9 +4132,15 @@ static int tracing_set_tracer(const char *buf)
 	if (t == tr->current_trace)
 		goto out;
 
+	/* Some tracers are only allowed for the top level buffer */
+	if (!trace_ok_for_array(t, tr)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
 	trace_branch_disable();
 
-	tr->current_trace->enabled = false;
+	tr->current_trace->enabled--;
 
 	if (tr->current_trace->reset)
 		tr->current_trace->reset(tr);
@@ -3941,9 +4163,11 @@ static int tracing_set_tracer(const char *buf)
 		free_snapshot(tr);
 	}
 #endif
-	destroy_trace_option_files(topts);
-
-	topts = create_trace_option_files(tr, t);
+	/* Currently, only the top instance has options */
+	if (tr->flags & TRACE_ARRAY_FL_GLOBAL) {
+		destroy_trace_option_files(topts);
+		topts = create_trace_option_files(tr, t);
+	}
 
 #ifdef CONFIG_TRACER_MAX_TRACE
 	if (t->use_max_tr && !had_max_tr) {
@@ -3960,7 +4184,7 @@ static int tracing_set_tracer(const char *buf)
 	}
 
 	tr->current_trace = t;
-	tr->current_trace->enabled = true;
+	tr->current_trace->enabled++;
 	trace_branch_enable(tr);
  out:
 	mutex_unlock(&trace_types_lock);
@@ -3972,6 +4196,7 @@ static ssize_t
 tracing_set_trace_write(struct file *filp, const char __user *ubuf,
 			size_t cnt, loff_t *ppos)
 {
+	struct trace_array *tr = filp->private_data;
 	char buf[MAX_TRACER_SIZE+1];
 	int i;
 	size_t ret;
@@ -3991,7 +4216,7 @@ tracing_set_trace_write(struct file *filp, const char __user *ubuf,
 	for (i = cnt - 1; i > 0 && isspace(buf[i]); i--)
 		buf[i] = 0;
 
-	err = tracing_set_tracer(buf);
+	err = tracing_set_tracer(tr, buf);
 	if (err)
 		return err;
 
@@ -4149,25 +4374,6 @@ tracing_poll_pipe(struct file *filp, poll_table *poll_table)
 	return trace_poll(iter, filp, poll_table);
 }
 
-/*
- * This is a make-shift waitqueue.
- * A tracer might use this callback on some rare cases:
- *
- *  1) the current tracer might hold the runqueue lock when it wakes up
- *     a reader, hence a deadlock (sched, function, and function graph tracers)
- *  2) the function tracers, trace all functions, we don't want
- *     the overhead of calling wake_up and friends
- *     (and tracing them too)
- *
- *     Anyway, this is really very primitive wakeup.
- */
-void poll_wait_pipe(struct trace_iterator *iter)
-{
-	set_current_state(TASK_INTERRUPTIBLE);
-	/* sleep for 100 msecs, and try again. */
-	schedule_timeout(HZ / 10);
-}
-
 /* Must be called with trace_types_lock mutex held. */
 static int tracing_wait_pipe(struct file *filp)
 {
@@ -4179,15 +4385,6 @@ static int tracing_wait_pipe(struct file *filp)
 			return -EAGAIN;
 		}
 
-		mutex_unlock(&iter->mutex);
-
-		iter->trace->wait_pipe(iter);
-
-		mutex_lock(&iter->mutex);
-
-		if (signal_pending(current))
-			return -EINTR;
-
 		/*
 		 * We block until we read something and tracing is disabled.
 		 * We still block if tracing is disabled, but we have never
@@ -4199,6 +4396,15 @@ static int tracing_wait_pipe(struct file *filp)
 		 */
 		if (!tracing_is_on() && iter->pos)
 			break;
+
+		mutex_unlock(&iter->mutex);
+
+		wait_on_pipe(iter);
+
+		mutex_lock(&iter->mutex);
+
+		if (signal_pending(current))
+			return -EINTR;
 	}
 
 	return 1;
@@ -4316,8 +4522,6 @@ static void tracing_spd_release_pipe(struct splice_pipe_desc *spd,
 
 static const struct pipe_buf_operations tracing_pipe_buf_ops = {
 	.can_merge		= 0,
-	.map			= generic_pipe_buf_map,
-	.unmap			= generic_pipe_buf_unmap,
 	.confirm		= generic_pipe_buf_confirm,
 	.release		= generic_pipe_buf_release,
 	.steal			= generic_pipe_buf_steal,
@@ -4412,7 +4616,7 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
 	trace_access_lock(iter->cpu_file);
 
 	/* Fill as many pages as possible. */
-	for (i = 0, rem = len; i < pipe->buffers && rem; i++) {
+	for (i = 0, rem = len; i < spd.nr_pages_max && rem; i++) {
 		spd.pages[i] = alloc_page(GFP_KERNEL);
 		if (!spd.pages[i])
 			break;
@@ -4699,25 +4903,10 @@ static int tracing_clock_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static ssize_t tracing_clock_write(struct file *filp, const char __user *ubuf,
-				   size_t cnt, loff_t *fpos)
+static int tracing_set_clock(struct trace_array *tr, const char *clockstr)
 {
-	struct seq_file *m = filp->private_data;
-	struct trace_array *tr = m->private;
-	char buf[64];
-	const char *clockstr;
 	int i;
 
-	if (cnt >= sizeof(buf))
-		return -EINVAL;
-
-	if (copy_from_user(&buf, ubuf, cnt))
-		return -EFAULT;
-
-	buf[cnt] = 0;
-
-	clockstr = strstrip(buf);
-
 	for (i = 0; i < ARRAY_SIZE(trace_clocks); i++) {
 		if (strcmp(trace_clocks[i].name, clockstr) == 0)
 			break;
@@ -4745,6 +4934,32 @@ static ssize_t tracing_clock_write(struct file *filp, const char __user *ubuf,
 
 	mutex_unlock(&trace_types_lock);
 
+	return 0;
+}
+
+static ssize_t tracing_clock_write(struct file *filp, const char __user *ubuf,
+				   size_t cnt, loff_t *fpos)
+{
+	struct seq_file *m = filp->private_data;
+	struct trace_array *tr = m->private;
+	char buf[64];
+	const char *clockstr;
+	int ret;
+
+	if (cnt >= sizeof(buf))
+		return -EINVAL;
+
+	if (copy_from_user(&buf, ubuf, cnt))
+		return -EFAULT;
+
+	buf[cnt] = 0;
+
+	clockstr = strstrip(buf);
+
+	ret = tracing_set_clock(tr, clockstr);
+	if (ret)
+		return ret;
+
 	*fpos += cnt;
 
 	return cnt;
@@ -5112,7 +5327,7 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 				goto out_unlock;
 			}
 			mutex_unlock(&trace_types_lock);
-			iter->trace->wait_pipe(iter);
+			wait_on_pipe(iter);
 			mutex_lock(&trace_types_lock);
 			if (signal_pending(current)) {
 				size = -EINTR;
@@ -5194,8 +5409,6 @@ static void buffer_pipe_buf_get(struct pipe_inode_info *pipe,
 /* Pipe buffer operations for a buffer. */
 static const struct pipe_buf_operations buffer_pipe_buf_ops = {
 	.can_merge		= 0,
-	.map			= generic_pipe_buf_map,
-	.unmap			= generic_pipe_buf_unmap,
 	.confirm		= generic_pipe_buf_confirm,
 	.release		= buffer_pipe_buf_release,
 	.steal			= generic_pipe_buf_steal,
@@ -5271,7 +5484,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 	trace_access_lock(iter->cpu_file);
 	entries = ring_buffer_entries_cpu(iter->trace_buffer->buffer, iter->cpu_file);
 
-	for (i = 0; i < pipe->buffers && len && entries; i++, len -= PAGE_SIZE) {
+	for (i = 0; i < spd.nr_pages_max && len && entries; i++, len -= PAGE_SIZE) {
 		struct page *page;
 		int r;
 
@@ -5325,7 +5538,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 			goto out;
 		}
 		mutex_unlock(&trace_types_lock);
-		iter->trace->wait_pipe(iter);
+		wait_on_pipe(iter);
 		mutex_lock(&trace_types_lock);
 		if (signal_pending(current)) {
 			ret = -EINTR;
@@ -5705,7 +5918,7 @@ trace_options_write(struct file *filp, const char __user *ubuf, size_t cnt,
 
 	if (!!(topt->flags->val & topt->opt->bit) != val) {
 		mutex_lock(&trace_types_lock);
-		ret = __set_tracer_option(topt->tr->current_trace, topt->flags,
+		ret = __set_tracer_option(topt->tr, topt->flags,
 					  topt->opt, !val);
 		mutex_unlock(&trace_types_lock);
 		if (ret)
@@ -6019,6 +6232,25 @@ static int allocate_trace_buffers(struct trace_array *tr, int size)
 	return 0;
 }
 
+static void free_trace_buffers(struct trace_array *tr)
+{
+	if (!tr)
+		return;
+
+	if (tr->trace_buffer.buffer) {
+		ring_buffer_free(tr->trace_buffer.buffer);
+		tr->trace_buffer.buffer = NULL;
+		free_percpu(tr->trace_buffer.data);
+	}
+
+#ifdef CONFIG_TRACER_MAX_TRACE
+	if (tr->max_buffer.buffer) {
+		ring_buffer_free(tr->max_buffer.buffer);
+		tr->max_buffer.buffer = NULL;
+	}
+#endif
+}
+
 static int new_instance_create(const char *name)
 {
 	struct trace_array *tr;
@@ -6048,6 +6280,8 @@ static int new_instance_create(const char *name)
 
 	raw_spin_lock_init(&tr->start_lock);
 
+	tr->max_lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
+
 	tr->current_trace = &nop_trace;
 
 	INIT_LIST_HEAD(&tr->systems);
@@ -6075,8 +6309,7 @@ static int new_instance_create(const char *name)
 	return 0;
 
  out_free_tr:
-	if (tr->trace_buffer.buffer)
-		ring_buffer_free(tr->trace_buffer.buffer);
+	free_trace_buffers(tr);
 	free_cpumask_var(tr->tracing_cpumask);
 	kfree(tr->name);
 	kfree(tr);
@@ -6112,10 +6345,11 @@ static int instance_delete(const char *name)
 
 	list_del(&tr->list);
 
+	tracing_set_nop(tr);
 	event_trace_del_tracer(tr);
+	ftrace_destroy_function_files(tr);
 	debugfs_remove_recursive(tr->dir);
-	free_percpu(tr->trace_buffer.data);
-	ring_buffer_free(tr->trace_buffer.buffer);
+	free_trace_buffers(tr);
 
 	kfree(tr->name);
 	kfree(tr);
@@ -6207,6 +6441,12 @@ init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer)
 {
 	int cpu;
 
+	trace_create_file("available_tracers", 0444, d_tracer,
+			tr, &show_traces_fops);
+
+	trace_create_file("current_tracer", 0644, d_tracer,
+			tr, &set_tracer_fops);
+
 	trace_create_file("tracing_cpumask", 0644, d_tracer,
 			  tr, &tracing_cpumask_fops);
 
@@ -6237,6 +6477,14 @@ init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer)
 	trace_create_file("tracing_on", 0644, d_tracer,
 			  tr, &rb_simple_fops);
 
+#ifdef CONFIG_TRACER_MAX_TRACE
+	trace_create_file("tracing_max_latency", 0644, d_tracer,
+			&tr->max_latency, &tracing_max_lat_fops);
+#endif
+
+	if (ftrace_create_function_files(tr, d_tracer))
+		WARN(1, "Could not allocate function filter files");
+
 #ifdef CONFIG_TRACER_SNAPSHOT
 	trace_create_file("snapshot", 0644, d_tracer,
 			  tr, &snapshot_fops);
@@ -6259,17 +6507,6 @@ static __init int tracer_init_debugfs(void)
 
 	init_tracer_debugfs(&global_trace, d_tracer);
 
-	trace_create_file("available_tracers", 0444, d_tracer,
-			&global_trace, &show_traces_fops);
-
-	trace_create_file("current_tracer", 0644, d_tracer,
-			&global_trace, &set_tracer_fops);
-
-#ifdef CONFIG_TRACER_MAX_TRACE
-	trace_create_file("tracing_max_latency", 0644, d_tracer,
-			&tracing_max_latency, &tracing_max_lat_fops);
-#endif
-
 	trace_create_file("tracing_thresh", 0644, d_tracer,
 			&tracing_thresh, &tracing_max_lat_fops);
 
@@ -6279,6 +6516,9 @@ static __init int tracer_init_debugfs(void)
 	trace_create_file("saved_cmdlines", 0444, d_tracer,
 			NULL, &tracing_saved_cmdlines_fops);
 
+	trace_create_file("saved_cmdlines_size", 0644, d_tracer,
+			  NULL, &tracing_saved_cmdlines_size_fops);
+
 #ifdef CONFIG_DYNAMIC_FTRACE
 	trace_create_file("dyn_ftrace_total_info", 0444, d_tracer,
 			&ftrace_update_tot_cnt, &tracing_dyn_info_fops);
@@ -6515,17 +6755,25 @@ __init static int tracer_alloc_buffers(void)
 	if (!temp_buffer)
 		goto out_free_cpumask;
 
+	if (trace_create_savedcmd() < 0)
+		goto out_free_temp_buffer;
+
 	/* TODO: make the number of buffers hot pluggable with CPUS */
 	if (allocate_trace_buffers(&global_trace, ring_buf_size) < 0) {
 		printk(KERN_ERR "tracer: failed to allocate ring buffer!\n");
 		WARN_ON(1);
-		goto out_free_temp_buffer;
+		goto out_free_savedcmd;
 	}
 
 	if (global_trace.buffer_disabled)
 		tracing_off();
 
-	trace_init_cmdlines();
+	if (trace_boot_clock) {
+		ret = tracing_set_clock(&global_trace, trace_boot_clock);
+		if (ret < 0)
+			pr_warning("Trace clock %s not defined, going back to default\n",
+				   trace_boot_clock);
+	}
 
 	/*
 	 * register_tracer() might reference current_trace, so it
@@ -6534,6 +6782,10 @@ __init static int tracer_alloc_buffers(void)
 	 */
 	global_trace.current_trace = &nop_trace;
 
+	global_trace.max_lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
+
+	ftrace_init_global_array_ops(&global_trace);
+
 	register_tracer(&nop_trace);
 
 	/* All seems OK, enable tracing */
@@ -6561,13 +6813,11 @@ __init static int tracer_alloc_buffers(void)
 
 	return 0;
 
+out_free_savedcmd:
+	free_saved_cmdlines_buffer(savedcmd);
 out_free_temp_buffer:
 	ring_buffer_free(temp_buffer);
 out_free_cpumask:
-	free_percpu(global_trace.trace_buffer.data);
-#ifdef CONFIG_TRACER_MAX_TRACE
-	free_percpu(global_trace.max_buffer.data);
-#endif
 	free_cpumask_var(global_trace.tracing_cpumask);
 out_free_buffer_mask:
 	free_cpumask_var(tracing_buffer_mask);