X-Git-Url: https://err.no/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=kernel%2Ftrace%2Ftrace.c;h=ca0d6ff74c114a8f5a0a4a5b2751d9a6f0b7cee9;hb=9fe068e92f6290e89e19adc521441661a1229f00;hp=9022c357032ac87db2e867ae51f2a1608db0f047;hpb=6fb44b717c10ecf37beaaebd312f3afa93fed714;p=linux-2.6

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 9022c35703..ca0d6ff74c 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -28,14 +28,30 @@
 #include <linux/gfp.h>
 #include <linux/fs.h>
 
+#include <linux/stacktrace.h>
+
 #include "trace.h"
 
 unsigned long __read_mostly	tracing_max_latency = (cycle_t)ULONG_MAX;
 unsigned long __read_mostly	tracing_thresh;
 
+static unsigned long __read_mostly	tracing_nr_buffers;
+static cpumask_t __read_mostly		tracing_buffer_mask;
+
+#define for_each_tracing_cpu(cpu)	\
+	for_each_cpu_mask(cpu, tracing_buffer_mask)
+
+/* dummy trace to disable tracing */
+static struct tracer no_tracer __read_mostly = {
+	.name		= "none",
+};
+
+static int trace_alloc_page(void);
+static int trace_free_page(void);
+
 static int tracing_disabled = 1;
 
-static long notrace
+long
 ns2usecs(cycle_t nsec)
 {
 	nsec += 500;
@@ -43,36 +59,108 @@ ns2usecs(cycle_t nsec)
 	return nsec;
 }
 
-notrace cycle_t ftrace_now(int cpu)
+cycle_t ftrace_now(int cpu)
 {
 	return cpu_clock(cpu);
 }
 
+/*
+ * The global_trace is the descriptor that holds the tracing
+ * buffers for the live tracing. For each CPU, it contains
+ * a link list of pages that will store trace entries. The
+ * page descriptor of the pages in the memory is used to hold
+ * the link list by linking the lru item in the page descriptor
+ * to each of the pages in the buffer per CPU.
+ *
+ * For each active CPU there is a data field that holds the
+ * pages for the buffer for that CPU. Each CPU has the same number
+ * of pages allocated for its buffer.
+ */
 static struct trace_array	global_trace;
 
 static DEFINE_PER_CPU(struct trace_array_cpu, global_trace_cpu);
 
+/*
+ * The max_tr is used to snapshot the global_trace when a maximum
+ * latency is reached. Some tracers will use this to store a maximum
+ * trace while it continues examining live traces.
+ *
+ * The buffers for the max_tr are set up the same as the global_trace.
+ * When a snapshot is taken, the link list of the max_tr is swapped
+ * with the link list of the global_trace and the buffers are reset for
+ * the global_trace so the tracing can continue.
+ */
 static struct trace_array	max_tr;
 
 static DEFINE_PER_CPU(struct trace_array_cpu, max_data);
 
+/* tracer_enabled is used to toggle activation of a tracer */
 static int			tracer_enabled = 1;
-static unsigned long		trace_nr_entries = 16384UL;
 
+/*
+ * trace_nr_entries is the number of entries that is allocated
+ * for a buffer. Note, the number of entries is always rounded
+ * to ENTRIES_PER_PAGE.
+ */
+static unsigned long		trace_nr_entries = 65536UL;
+
+/* trace_types holds a link list of available tracers. */
 static struct tracer		*trace_types __read_mostly;
+
+/* current_trace points to the tracer that is currently active */
 static struct tracer		*current_trace __read_mostly;
+
+/*
+ * max_tracer_type_len is used to simplify the allocating of
+ * buffers to read userspace tracer names. We keep track of
+ * the longest tracer name registered.
+ */
 static int			max_tracer_type_len;
 
+/*
+ * trace_types_lock is used to protect the trace_types list.
+ * This lock is also used to keep user access serialized.
+ * Accesses from userspace will grab this lock while userspace
+ * activities happen inside the kernel.
+ */
 static DEFINE_MUTEX(trace_types_lock);
-static DECLARE_WAIT_QUEUE_HEAD (trace_wait);
+
+/* trace_wait is a waitqueue for tasks blocked on trace_poll */
+static DECLARE_WAIT_QUEUE_HEAD(trace_wait);
+
+/* trace_flags holds iter_ctrl options */
+unsigned long trace_flags = TRACE_ITER_PRINT_PARENT;
+
+/**
+ * trace_wake_up - wake up tasks waiting for trace input
+ *
+ * Simply wakes up any task that is blocked on the trace_wait
+ * queue. These is used with trace_poll for tasks polling the trace.
+ */
+void trace_wake_up(void)
+{
+	/*
+	 * The runqueue_is_locked() can fail, but this is the best we
+	 * have for now:
+	 */
+	if (!(trace_flags & TRACE_ITER_BLOCK) && !runqueue_is_locked())
+		wake_up(&trace_wait);
+}
 
 #define ENTRIES_PER_PAGE (PAGE_SIZE / sizeof(struct trace_entry))
 
 static int __init set_nr_entries(char *str)
 {
+	unsigned long nr_entries;
+	int ret;
+
 	if (!str)
 		return 0;
-	trace_nr_entries = simple_strtoul(str, &str, 0);
+	ret = strict_strtoul(str, 0, &nr_entries);
+	/* nr_entries can not be zero */
+	if (ret < 0 || nr_entries == 0)
+		return 0;
+	trace_nr_entries = nr_entries;
 	return 1;
 }
 __setup("trace_entries=", set_nr_entries);
@@ -82,16 +170,14 @@ unsigned long nsecs_to_usecs(unsigned long nsecs)
 	return nsecs / 1000;
 }
 
-enum trace_type {
-	__TRACE_FIRST_TYPE = 0,
-
-	TRACE_FN,
-	TRACE_CTX,
-	TRACE_SPECIAL,
-
-	__TRACE_LAST_TYPE
-};
-
+/*
+ * trace_flag_type is an enumeration that holds different
+ * states when a trace occurs. These are:
+ *  IRQS_OFF	- interrupts were disabled
+ *  NEED_RESCED - reschedule is requested
+ *  HARDIRQ	- inside an interrupt handler
+ *  SOFTIRQ	- inside a softirq handler
+ */
 enum trace_flag_type {
 	TRACE_FLAG_IRQS_OFF		= 0x01,
 	TRACE_FLAG_NEED_RESCHED		= 0x02,
@@ -99,21 +185,14 @@ enum trace_flag_type {
 	TRACE_FLAG_SOFTIRQ		= 0x08,
 };
 
-enum trace_iterator_flags {
-	TRACE_ITER_PRINT_PARENT		= 0x01,
-	TRACE_ITER_SYM_OFFSET		= 0x02,
-	TRACE_ITER_SYM_ADDR		= 0x04,
-	TRACE_ITER_VERBOSE		= 0x08,
-	TRACE_ITER_RAW			= 0x10,
-	TRACE_ITER_HEX			= 0x20,
-	TRACE_ITER_BIN			= 0x40,
-	TRACE_ITER_BLOCK		= 0x80,
-};
-
+/*
+ * TRACE_ITER_SYM_MASK masks the options in trace_flags that
+ * control the output of kernel symbols.
+ */
 #define TRACE_ITER_SYM_MASK \
 	(TRACE_ITER_PRINT_PARENT|TRACE_ITER_SYM_OFFSET|TRACE_ITER_SYM_ADDR)
 
-/* These must match the bit postions above */
+/* These must match the bit postions in trace_iterator_flags */
 static const char *trace_options[] = {
 	"print-parent",
 	"sym-offset",
@@ -123,19 +202,29 @@ static const char *trace_options[] = {
 	"hex",
 	"bin",
 	"block",
+	"stacktrace",
+	"sched-tree",
 	NULL
 };
 
-static unsigned trace_flags;
-
-static DEFINE_SPINLOCK(ftrace_max_lock);
+/*
+ * 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 raw_spinlock_t in order to help
+ * with performance when lockdep debugging is enabled.
+ */
+static raw_spinlock_t ftrace_max_lock =
+	(raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
 
 /*
  * Copy the new maximum trace into the separate maximum-trace
  * structure. (this way the maximum trace is permanently saved,
  * for later retrieval via /debugfs/tracing/latency_trace)
  */
-static notrace void
+static void
 __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 {
 	struct trace_array_cpu *data = tr->data[cpu];
@@ -157,6 +246,13 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 	tracing_record_cmdline(current);
 }
 
+/**
+ * check_pages - integrity check of trace buffers
+ *
+ * As a safty measure we check to make sure the data pages have not
+ * been corrupted. TODO: configure to disable this because it adds
+ * a bit of overhead.
+ */
 void check_pages(struct trace_array_cpu *data)
 {
 	struct page *page, *tmp;
@@ -170,6 +266,13 @@ void check_pages(struct trace_array_cpu *data)
 	}
 }
 
+/**
+ * head_page - page address of the first page in per_cpu buffer.
+ *
+ * head_page returns the page address of the first page in
+ * a per_cpu buffer. This also preforms various consistency
+ * checks to make sure the buffer has not been corrupted.
+ */
 void *head_page(struct trace_array_cpu *data)
 {
 	struct page *page;
@@ -184,7 +287,18 @@ void *head_page(struct trace_array_cpu *data)
 	return page_address(page);
 }
 
-static notrace int
+/**
+ * trace_seq_printf - sequence printing of trace information
+ * @s: trace sequence descriptor
+ * @fmt: printf format string
+ *
+ * The tracer may use either sequence operations or its own
+ * copy to user routines. To simplify formating of a trace
+ * trace_seq_printf is used to store strings into a special
+ * buffer (@s). Then the output may be either used by
+ * the sequencer or pulled into another buffer.
+ */
+int
 trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
 {
 	int len = (PAGE_SIZE - 1) - s->len;
@@ -199,7 +313,7 @@ trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
 	va_end(ap);
 
 	/* If we can't write it all, don't bother writing anything */
-	if (ret > len)
+	if (ret >= len)
 		return 0;
 
 	s->len += ret;
@@ -207,7 +321,17 @@ trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
 	return len;
 }
 
-static notrace int
+/**
+ * trace_seq_puts - trace sequence printing of simple string
+ * @s: trace sequence descriptor
+ * @str: simple string to record
+ *
+ * The tracer may use either the sequence operations or its own
+ * copy to user routines. This function records a simple string
+ * into a special buffer (@s) for later retrieval by a sequencer
+ * or other mechanism.
+ */
+static int
 trace_seq_puts(struct trace_seq *s, const char *str)
 {
 	int len = strlen(str);
@@ -221,7 +345,7 @@ trace_seq_puts(struct trace_seq *s, const char *str)
 	return len;
 }
 
-static notrace int
+static int
 trace_seq_putc(struct trace_seq *s, unsigned char c)
 {
 	if (s->len >= (PAGE_SIZE - 1))
@@ -232,7 +356,7 @@ trace_seq_putc(struct trace_seq *s, unsigned char c)
 	return 1;
 }
 
-static notrace int
+static int
 trace_seq_putmem(struct trace_seq *s, void *mem, size_t len)
 {
 	if (len > ((PAGE_SIZE - 1) - s->len))
@@ -245,19 +369,18 @@ trace_seq_putmem(struct trace_seq *s, void *mem, size_t len)
 }
 
 #define HEX_CHARS 17
+static const char hex2asc[] = "0123456789abcdef";
 
-static notrace int
+static int
 trace_seq_putmem_hex(struct trace_seq *s, void *mem, size_t len)
 {
 	unsigned char hex[HEX_CHARS];
-	unsigned char *data;
+	unsigned char *data = mem;
 	unsigned char byte;
 	int i, j;
 
 	BUG_ON(len >= HEX_CHARS);
 
-	data = mem;
-
 #ifdef __BIG_ENDIAN
 	for (i = 0, j = 0; i < len; i++) {
 #else
@@ -265,33 +388,21 @@ trace_seq_putmem_hex(struct trace_seq *s, void *mem, size_t len)
 #endif
 		byte = data[i];
 
-		hex[j]   = byte & 0x0f;
-		if (hex[j] >= 10)
-			hex[j] += 'a' - 10;
-		else
-			hex[j] += '0';
-		j++;
-
-		hex[j] = byte >> 4;
-		if (hex[j] >= 10)
-			hex[j] += 'a' - 10;
-		else
-			hex[j] += '0';
-		j++;
+		hex[j++] = hex2asc[byte & 0x0f];
+		hex[j++] = hex2asc[byte >> 4];
 	}
-	hex[j] = ' ';
-	j++;
+	hex[j++] = ' ';
 
 	return trace_seq_putmem(s, hex, j);
 }
 
-static notrace void
+static void
 trace_seq_reset(struct trace_seq *s)
 {
 	s->len = 0;
 }
 
-static notrace void
+static void
 trace_print_seq(struct seq_file *m, struct trace_seq *s)
 {
 	int len = s->len >= PAGE_SIZE ? PAGE_SIZE - 1 : s->len;
@@ -302,7 +413,14 @@ trace_print_seq(struct seq_file *m, struct trace_seq *s)
 	trace_seq_reset(s);
 }
 
-notrace static void
+/*
+ * flip the trace buffers between two trace descriptors.
+ * This usually is the buffers between the global_trace and
+ * the max_tr to record a snapshot of a current trace.
+ *
+ * The ftrace_max_lock must be held.
+ */
+static void
 flip_trace(struct trace_array_cpu *tr1, struct trace_array_cpu *tr2)
 {
 	struct list_head flip_pages;
@@ -323,23 +441,32 @@ flip_trace(struct trace_array_cpu *tr1, struct trace_array_cpu *tr2)
 	check_pages(tr2);
 }
 
-notrace void
+/**
+ * update_max_tr - snapshot all trace buffers from global_trace to max_tr
+ * @tr: tracer
+ * @tsk: the task with the latency
+ * @cpu: The cpu that initiated the trace.
+ *
+ * Flip the buffers between the @tr and the max_tr and record information
+ * about which task was the cause of this latency.
+ */
+void
 update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 {
 	struct trace_array_cpu *data;
 	int i;
 
 	WARN_ON_ONCE(!irqs_disabled());
-	spin_lock(&ftrace_max_lock);
+	__raw_spin_lock(&ftrace_max_lock);
 	/* clear out all the previous traces */
-	for_each_possible_cpu(i) {
+	for_each_tracing_cpu(i) {
 		data = tr->data[i];
 		flip_trace(max_tr.data[i], data);
 		tracing_reset(data);
 	}
 
 	__update_max_tr(tr, tsk, cpu);
-	spin_unlock(&ftrace_max_lock);
+	__raw_spin_unlock(&ftrace_max_lock);
 }
 
 /**
@@ -347,25 +474,33 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
  * @tr - tracer
  * @tsk - task with the latency
  * @cpu - the cpu of the buffer to copy.
+ *
+ * Flip the trace of a single CPU buffer between the @tr and the max_tr.
  */
-notrace void
+void
 update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
 {
 	struct trace_array_cpu *data = tr->data[cpu];
 	int i;
 
 	WARN_ON_ONCE(!irqs_disabled());
-	spin_lock(&ftrace_max_lock);
-	for_each_possible_cpu(i)
+	__raw_spin_lock(&ftrace_max_lock);
+	for_each_tracing_cpu(i)
 		tracing_reset(max_tr.data[i]);
 
 	flip_trace(max_tr.data[cpu], data);
 	tracing_reset(data);
 
 	__update_max_tr(tr, tsk, cpu);
-	spin_unlock(&ftrace_max_lock);
+	__raw_spin_unlock(&ftrace_max_lock);
 }
 
+/**
+ * register_tracer - register a tracer with the ftrace system.
+ * @type - the plugin for the tracer
+ *
+ * Register a new plugin tracer.
+ */
 int register_tracer(struct tracer *type)
 {
 	struct tracer *t;
@@ -402,7 +537,7 @@ int register_tracer(struct tracer *type)
 		 * internal tracing to verify that everything is in order.
 		 * If we fail, we do not register this tracer.
 		 */
-		for_each_possible_cpu(i) {
+		for_each_tracing_cpu(i) {
 			data = tr->data[i];
 			if (!head_page(data))
 				continue;
@@ -421,7 +556,7 @@ int register_tracer(struct tracer *type)
 			goto out;
 		}
 		/* Only reset on passing, to avoid touching corrupted buffers */
-		for_each_possible_cpu(i) {
+		for_each_tracing_cpu(i) {
 			data = tr->data[i];
 			if (!head_page(data))
 				continue;
@@ -471,9 +606,10 @@ void unregister_tracer(struct tracer *type)
 	mutex_unlock(&trace_types_lock);
 }
 
-notrace void tracing_reset(struct trace_array_cpu *data)
+void tracing_reset(struct trace_array_cpu *data)
 {
 	data->trace_idx = 0;
+	data->overrun = 0;
 	data->trace_head = data->trace_tail = head_page(data);
 	data->trace_head_idx = 0;
 	data->trace_tail_idx = 0;
@@ -485,7 +621,12 @@ static unsigned map_cmdline_to_pid[SAVED_CMDLINES];
 static char saved_cmdlines[SAVED_CMDLINES][TASK_COMM_LEN];
 static int cmdline_idx;
 static DEFINE_SPINLOCK(trace_cmdline_lock);
-atomic_t trace_record_cmdline_disabled;
+
+/* trace in all context switches */
+atomic_t trace_record_cmdline_enabled __read_mostly;
+
+/* temporary disable recording */
+atomic_t trace_record_cmdline_disabled __read_mostly;
 
 static void trace_init_cmdlines(void)
 {
@@ -494,9 +635,9 @@ static void trace_init_cmdlines(void)
 	cmdline_idx = 0;
 }
 
-notrace void trace_stop_cmdline_recording(void);
+void trace_stop_cmdline_recording(void);
 
-static notrace void trace_save_cmdline(struct task_struct *tsk)
+static void trace_save_cmdline(struct task_struct *tsk)
 {
 	unsigned map;
 	unsigned idx;
@@ -531,7 +672,7 @@ static notrace void trace_save_cmdline(struct task_struct *tsk)
 	spin_unlock(&trace_cmdline_lock);
 }
 
-static notrace char *trace_find_cmdline(int pid)
+static char *trace_find_cmdline(int pid)
 {
 	char *cmdline = "<...>";
 	unsigned map;
@@ -552,7 +693,7 @@ static notrace char *trace_find_cmdline(int pid)
 	return cmdline;
 }
 
-notrace void tracing_record_cmdline(struct task_struct *tsk)
+void tracing_record_cmdline(struct task_struct *tsk)
 {
 	if (atomic_read(&trace_record_cmdline_disabled))
 		return;
@@ -560,7 +701,7 @@ notrace void tracing_record_cmdline(struct task_struct *tsk)
 	trace_save_cmdline(tsk);
 }
 
-static inline notrace struct list_head *
+static inline struct list_head *
 trace_next_list(struct trace_array_cpu *data, struct list_head *next)
 {
 	/*
@@ -574,7 +715,7 @@ trace_next_list(struct trace_array_cpu *data, struct list_head *next)
 	return next;
 }
 
-static inline notrace void *
+static inline void *
 trace_next_page(struct trace_array_cpu *data, void *addr)
 {
 	struct list_head *next;
@@ -588,7 +729,7 @@ trace_next_page(struct trace_array_cpu *data, void *addr)
 	return page_address(page);
 }
 
-static inline notrace struct trace_entry *
+static inline struct trace_entry *
 tracing_get_trace_entry(struct trace_array *tr, struct trace_array_cpu *data)
 {
 	unsigned long idx, idx_next;
@@ -610,6 +751,7 @@ tracing_get_trace_entry(struct trace_array *tr, struct trace_array_cpu *data)
 	if (data->trace_head == data->trace_tail &&
 	    idx_next == data->trace_tail_idx) {
 		/* overrun */
+		data->overrun++;
 		data->trace_tail_idx++;
 		if (data->trace_tail_idx >= ENTRIES_PER_PAGE) {
 			data->trace_tail =
@@ -623,7 +765,7 @@ tracing_get_trace_entry(struct trace_array *tr, struct trace_array_cpu *data)
 	return entry;
 }
 
-static inline notrace void
+static inline void
 tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags)
 {
 	struct task_struct *tsk = current;
@@ -632,7 +774,7 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags)
 	pc = preempt_count();
 
 	entry->preempt_count	= pc & 0xff;
-	entry->pid		= tsk->pid;
+	entry->pid		= (tsk) ? tsk->pid : 0;
 	entry->t		= ftrace_now(raw_smp_processor_id());
 	entry->flags = (irqs_disabled_flags(flags) ? TRACE_FLAG_IRQS_OFF : 0) |
 		((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) |
@@ -640,26 +782,25 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags)
 		(need_resched() ? TRACE_FLAG_NEED_RESCHED : 0);
 }
 
-notrace void
+void
 trace_function(struct trace_array *tr, struct trace_array_cpu *data,
 	       unsigned long ip, unsigned long parent_ip, unsigned long flags)
 {
 	struct trace_entry *entry;
 	unsigned long irq_flags;
 
-	spin_lock_irqsave(&data->lock, irq_flags);
+	raw_local_irq_save(irq_flags);
+	__raw_spin_lock(&data->lock);
 	entry			= tracing_get_trace_entry(tr, data);
 	tracing_generic_entry_update(entry, flags);
 	entry->type		= TRACE_FN;
 	entry->fn.ip		= ip;
 	entry->fn.parent_ip	= parent_ip;
-	spin_unlock_irqrestore(&data->lock, irq_flags);
-
-	if (!(trace_flags & TRACE_ITER_BLOCK))
-		wake_up (&trace_wait);
+	__raw_spin_unlock(&data->lock);
+	raw_local_irq_restore(irq_flags);
 }
 
-notrace void
+void
 ftrace(struct trace_array *tr, struct trace_array_cpu *data,
        unsigned long ip, unsigned long parent_ip, unsigned long flags)
 {
@@ -667,36 +808,66 @@ ftrace(struct trace_array *tr, struct trace_array_cpu *data,
 		trace_function(tr, data, ip, parent_ip, flags);
 }
 
-notrace void
-trace_special(struct trace_array *tr, struct trace_array_cpu *data,
-	      unsigned long arg1, unsigned long arg2, unsigned long arg3)
+void
+__trace_special(void *__tr, void *__data,
+		unsigned long arg1, unsigned long arg2, unsigned long arg3)
 {
+	struct trace_array_cpu *data = __data;
+	struct trace_array *tr = __tr;
 	struct trace_entry *entry;
 	unsigned long irq_flags;
 
-	spin_lock_irqsave(&data->lock, irq_flags);
+	raw_local_irq_save(irq_flags);
+	__raw_spin_lock(&data->lock);
 	entry			= tracing_get_trace_entry(tr, data);
 	tracing_generic_entry_update(entry, 0);
 	entry->type		= TRACE_SPECIAL;
 	entry->special.arg1	= arg1;
 	entry->special.arg2	= arg2;
 	entry->special.arg3	= arg3;
-	spin_unlock_irqrestore(&data->lock, irq_flags);
+	__raw_spin_unlock(&data->lock);
+	raw_local_irq_restore(irq_flags);
 
-	if (!(trace_flags & TRACE_ITER_BLOCK))
-		wake_up (&trace_wait);
+	trace_wake_up();
 }
 
-notrace void
+void __trace_stack(struct trace_array *tr,
+		   struct trace_array_cpu *data,
+		   unsigned long flags,
+		   int skip)
+{
+	struct trace_entry *entry;
+	struct stack_trace trace;
+
+	if (!(trace_flags & TRACE_ITER_STACKTRACE))
+		return;
+
+	entry			= tracing_get_trace_entry(tr, data);
+	tracing_generic_entry_update(entry, flags);
+	entry->type		= TRACE_STACK;
+
+	memset(&entry->stack, 0, sizeof(entry->stack));
+
+	trace.nr_entries	= 0;
+	trace.max_entries	= FTRACE_STACK_ENTRIES;
+	trace.skip		= skip;
+	trace.entries		= entry->stack.caller;
+
+	save_stack_trace(&trace);
+}
+
+void
 tracing_sched_switch_trace(struct trace_array *tr,
 			   struct trace_array_cpu *data,
-			   struct task_struct *prev, struct task_struct *next,
+			   struct task_struct *prev,
+			   struct task_struct *next,
 			   unsigned long flags)
 {
 	struct trace_entry *entry;
 	unsigned long irq_flags;
 
-	spin_lock_irqsave(&data->lock, irq_flags);
+	raw_local_irq_save(irq_flags);
+	__raw_spin_lock(&data->lock);
 	entry			= tracing_get_trace_entry(tr, data);
 	tracing_generic_entry_update(entry, flags);
 	entry->type		= TRACE_CTX;
@@ -705,14 +876,42 @@ tracing_sched_switch_trace(struct trace_array *tr,
 	entry->ctx.prev_state	= prev->state;
 	entry->ctx.next_pid	= next->pid;
 	entry->ctx.next_prio	= next->prio;
-	spin_unlock_irqrestore(&data->lock, irq_flags);
+	entry->ctx.next_state	= next->state;
+	__trace_stack(tr, data, flags, 4);
+	__raw_spin_unlock(&data->lock);
+	raw_local_irq_restore(irq_flags);
+}
+
+void
+tracing_sched_wakeup_trace(struct trace_array *tr,
+			   struct trace_array_cpu *data,
+			   struct task_struct *wakee,
+			   struct task_struct *curr,
+			   unsigned long flags)
+{
+	struct trace_entry *entry;
+	unsigned long irq_flags;
+
+	raw_local_irq_save(irq_flags);
+	__raw_spin_lock(&data->lock);
+	entry			= tracing_get_trace_entry(tr, data);
+	tracing_generic_entry_update(entry, flags);
+	entry->type		= TRACE_WAKE;
+	entry->ctx.prev_pid	= curr->pid;
+	entry->ctx.prev_prio	= curr->prio;
+	entry->ctx.prev_state	= curr->state;
+	entry->ctx.next_pid	= wakee->pid;
+	entry->ctx.next_prio	= wakee->prio;
+	entry->ctx.next_state	= wakee->state;
+	__trace_stack(tr, data, flags, 5);
+	__raw_spin_unlock(&data->lock);
+	raw_local_irq_restore(irq_flags);
 
-	if (!(trace_flags & TRACE_ITER_BLOCK))
-		wake_up (&trace_wait);
+	trace_wake_up();
 }
 
 #ifdef CONFIG_FTRACE
-static notrace void
+static void
 function_trace_call(unsigned long ip, unsigned long parent_ip)
 {
 	struct trace_array *tr = &global_trace;
@@ -741,12 +940,12 @@ static struct ftrace_ops trace_ops __read_mostly =
 	.func = function_trace_call,
 };
 
-notrace void tracing_start_function_trace(void)
+void tracing_start_function_trace(void)
 {
 	register_ftrace_function(&trace_ops);
 }
 
-notrace void tracing_stop_function_trace(void)
+void tracing_stop_function_trace(void)
 {
 	unregister_ftrace_function(&trace_ops);
 }
@@ -786,7 +985,7 @@ trace_entry_idx(struct trace_array *tr, struct trace_array_cpu *data,
 	return &array[iter->next_page_idx[cpu]];
 }
 
-static struct trace_entry * notrace
+static struct trace_entry *
 find_next_entry(struct trace_iterator *iter, int *ent_cpu)
 {
 	struct trace_array *tr = iter->tr;
@@ -794,7 +993,7 @@ find_next_entry(struct trace_iterator *iter, int *ent_cpu)
 	int next_cpu = -1;
 	int cpu;
 
-	for_each_possible_cpu(cpu) {
+	for_each_tracing_cpu(cpu) {
 		if (!head_page(tr->data[cpu]))
 			continue;
 		ent = trace_entry_idx(tr, tr->data[cpu], iter, cpu);
@@ -813,7 +1012,7 @@ find_next_entry(struct trace_iterator *iter, int *ent_cpu)
 	return next;
 }
 
-static notrace void trace_iterator_increment(struct trace_iterator *iter)
+static void trace_iterator_increment(struct trace_iterator *iter)
 {
 	iter->idx++;
 	iter->next_idx[iter->cpu]++;
@@ -828,7 +1027,7 @@ static notrace void trace_iterator_increment(struct trace_iterator *iter)
 	}
 }
 
-static notrace void trace_consume(struct trace_iterator *iter)
+static void trace_consume(struct trace_iterator *iter)
 {
 	struct trace_array_cpu *data = iter->tr->data[iter->cpu];
 
@@ -844,7 +1043,7 @@ static notrace void trace_consume(struct trace_iterator *iter)
 		data->trace_idx = 0;
 }
 
-static notrace void *find_next_entry_inc(struct trace_iterator *iter)
+static void *find_next_entry_inc(struct trace_iterator *iter)
 {
 	struct trace_entry *next;
 	int next_cpu = -1;
@@ -863,7 +1062,7 @@ static notrace void *find_next_entry_inc(struct trace_iterator *iter)
 	return next ? iter : NULL;
 }
 
-static notrace void *s_next(struct seq_file *m, void *v, loff_t *pos)
+static void *s_next(struct seq_file *m, void *v, loff_t *pos)
 {
 	struct trace_iterator *iter = m->private;
 	void *last_ent = iter->ent;
@@ -901,8 +1100,10 @@ static void *s_start(struct seq_file *m, loff_t *pos)
 
 	mutex_lock(&trace_types_lock);
 
-	if (!current_trace || current_trace != iter->trace)
+	if (!current_trace || current_trace != iter->trace) {
+		mutex_unlock(&trace_types_lock);
 		return NULL;
+	}
 
 	atomic_inc(&trace_record_cmdline_disabled);
 
@@ -917,7 +1118,7 @@ static void *s_start(struct seq_file *m, loff_t *pos)
 		iter->prev_ent = NULL;
 		iter->prev_cpu = -1;
 
-		for_each_possible_cpu(i) {
+		for_each_tracing_cpu(i) {
 			iter->next_idx[i] = 0;
 			iter->next_page[i] = NULL;
 		}
@@ -978,7 +1179,7 @@ seq_print_sym_offset(struct trace_seq *s, const char *fmt,
 # define IP_FMT "%016lx"
 #endif
 
-static notrace int
+static int
 seq_print_ip_sym(struct trace_seq *s, unsigned long ip, unsigned long sym_flags)
 {
 	int ret;
@@ -999,7 +1200,7 @@ seq_print_ip_sym(struct trace_seq *s, unsigned long ip, unsigned long sym_flags)
 	return ret;
 }
 
-static notrace void print_lat_help_header(struct seq_file *m)
+static void print_lat_help_header(struct seq_file *m)
 {
 	seq_puts(m, "#                _------=> CPU#            \n");
 	seq_puts(m, "#               / _-----=> irqs-off        \n");
@@ -1012,14 +1213,14 @@ static notrace void print_lat_help_header(struct seq_file *m)
 	seq_puts(m, "#     \\   /    |||||   \\   |   /           \n");
 }
 
-static notrace void print_func_help_header(struct seq_file *m)
+static void print_func_help_header(struct seq_file *m)
 {
 	seq_puts(m, "#           TASK-PID   CPU#    TIMESTAMP  FUNCTION\n");
 	seq_puts(m, "#              | |      |          |         |\n");
 }
 
 
-static notrace void
+static void
 print_trace_header(struct seq_file *m, struct trace_iterator *iter)
 {
 	unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK);
@@ -1034,7 +1235,7 @@ print_trace_header(struct seq_file *m, struct trace_iterator *iter)
 	if (type)
 		name = type->name;
 
-	for_each_possible_cpu(cpu) {
+	for_each_tracing_cpu(cpu) {
 		if (head_page(tr->data[cpu])) {
 			total += tr->data[cpu]->trace_idx;
 			if (tr->data[cpu]->trace_idx > tr->entries)
@@ -1090,7 +1291,7 @@ print_trace_header(struct seq_file *m, struct trace_iterator *iter)
 	seq_puts(m, "\n");
 }
 
-static notrace void
+static void
 lat_print_generic(struct trace_seq *s, struct trace_entry *entry, int cpu)
 {
 	int hardirq, softirq;
@@ -1106,12 +1307,12 @@ lat_print_generic(struct trace_seq *s, struct trace_entry *entry, int cpu)
 
 	hardirq = entry->flags & TRACE_FLAG_HARDIRQ;
 	softirq = entry->flags & TRACE_FLAG_SOFTIRQ;
-	if (hardirq && softirq)
+	if (hardirq && softirq) {
 		trace_seq_putc(s, 'H');
-	else {
-		if (hardirq)
+	} else {
+		if (hardirq) {
 			trace_seq_putc(s, 'h');
-		else {
+		} else {
 			if (softirq)
 				trace_seq_putc(s, 's');
 			else
@@ -1127,7 +1328,7 @@ lat_print_generic(struct trace_seq *s, struct trace_entry *entry, int cpu)
 
 unsigned long preempt_mark_thresh = 100;
 
-static notrace void
+static void
 lat_print_timestamp(struct trace_seq *s, unsigned long long abs_usecs,
 		    unsigned long rel_usecs)
 {
@@ -1142,7 +1343,7 @@ lat_print_timestamp(struct trace_seq *s, unsigned long long abs_usecs,
 
 static const char state_to_char[] = TASK_STATE_TO_CHAR_STR;
 
-static notrace int
+static int
 print_lat_fmt(struct trace_iterator *iter, unsigned int trace_idx, int cpu)
 {
 	struct trace_seq *s = &iter->seq;
@@ -1153,7 +1354,9 @@ print_lat_fmt(struct trace_iterator *iter, unsigned int trace_idx, int cpu)
 	unsigned long abs_usecs;
 	unsigned long rel_usecs;
 	char *comm;
-	int S;
+	int S, T;
+	int i;
+	unsigned state;
 
 	if (!next_entry)
 		next_entry = entry;
@@ -1183,30 +1386,42 @@ print_lat_fmt(struct trace_iterator *iter, unsigned int trace_idx, int cpu)
 		trace_seq_puts(s, ")\n");
 		break;
 	case TRACE_CTX:
-		S = entry->ctx.prev_state < sizeof(state_to_char) ?
-			state_to_char[entry->ctx.prev_state] : 'X';
+	case TRACE_WAKE:
+		T = entry->ctx.next_state < sizeof(state_to_char) ?
+			state_to_char[entry->ctx.next_state] : 'X';
+
+		state = entry->ctx.prev_state ? __ffs(entry->ctx.prev_state) + 1 : 0;
+		S = state < sizeof(state_to_char) - 1 ? state_to_char[state] : 'X';
 		comm = trace_find_cmdline(entry->ctx.next_pid);
-		trace_seq_printf(s, " %d:%d:%c --> %d:%d %s\n",
+		trace_seq_printf(s, " %5d:%3d:%c %s %5d:%3d:%c %s\n",
 				 entry->ctx.prev_pid,
 				 entry->ctx.prev_prio,
-				 S,
+				 S, entry->type == TRACE_CTX ? "==>" : "  +",
 				 entry->ctx.next_pid,
 				 entry->ctx.next_prio,
-				 comm);
+				 T, comm);
 		break;
 	case TRACE_SPECIAL:
-		trace_seq_printf(s, " %lx %lx %lx\n",
+		trace_seq_printf(s, "# %ld %ld %ld\n",
 				 entry->special.arg1,
 				 entry->special.arg2,
 				 entry->special.arg3);
 		break;
+	case TRACE_STACK:
+		for (i = 0; i < FTRACE_STACK_ENTRIES; i++) {
+			if (i)
+				trace_seq_puts(s, " <= ");
+			seq_print_ip_sym(s, entry->stack.caller[i], sym_flags);
+		}
+		trace_seq_puts(s, "\n");
+		break;
 	default:
 		trace_seq_printf(s, "Unknown type %d\n", entry->type);
 	}
 	return 1;
 }
 
-static notrace int print_trace_fmt(struct trace_iterator *iter)
+static int print_trace_fmt(struct trace_iterator *iter)
 {
 	struct trace_seq *s = &iter->seq;
 	unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK);
@@ -1215,8 +1430,9 @@ static notrace int print_trace_fmt(struct trace_iterator *iter)
 	unsigned long long t;
 	unsigned long secs;
 	char *comm;
-	int S;
 	int ret;
+	int S, T;
+	int i;
 
 	entry = iter->ent;
 
@@ -1256,35 +1472,56 @@ static notrace int print_trace_fmt(struct trace_iterator *iter)
 			return 0;
 		break;
 	case TRACE_CTX:
+	case TRACE_WAKE:
 		S = entry->ctx.prev_state < sizeof(state_to_char) ?
 			state_to_char[entry->ctx.prev_state] : 'X';
-		ret = trace_seq_printf(s, " %d:%d:%c ==> %d:%d\n",
+		T = entry->ctx.next_state < sizeof(state_to_char) ?
+			state_to_char[entry->ctx.next_state] : 'X';
+		ret = trace_seq_printf(s, " %5d:%3d:%c %s %5d:%3d:%c\n",
 				       entry->ctx.prev_pid,
 				       entry->ctx.prev_prio,
 				       S,
+				       entry->type == TRACE_CTX ? "==>" : "  +",
 				       entry->ctx.next_pid,
-				       entry->ctx.next_prio);
+				       entry->ctx.next_prio,
+				       T);
 		if (!ret)
 			return 0;
 		break;
 	case TRACE_SPECIAL:
-		ret = trace_seq_printf(s, " %lx %lx %lx\n",
+		ret = trace_seq_printf(s, "# %ld %ld %ld\n",
 				 entry->special.arg1,
 				 entry->special.arg2,
 				 entry->special.arg3);
 		if (!ret)
 			return 0;
 		break;
+	case TRACE_STACK:
+		for (i = 0; i < FTRACE_STACK_ENTRIES; i++) {
+			if (i) {
+				ret = trace_seq_puts(s, " <= ");
+				if (!ret)
+					return 0;
+			}
+			ret = seq_print_ip_sym(s, entry->stack.caller[i],
+					       sym_flags);
+			if (!ret)
+				return 0;
+		}
+		ret = trace_seq_puts(s, "\n");
+		if (!ret)
+			return 0;
+		break;
 	}
 	return 1;
 }
 
-static notrace int print_raw_fmt(struct trace_iterator *iter)
+static int print_raw_fmt(struct trace_iterator *iter)
 {
 	struct trace_seq *s = &iter->seq;
 	struct trace_entry *entry;
 	int ret;
-	int S;
+	int S, T;
 
 	entry = iter->ent;
 
@@ -1301,19 +1538,26 @@ static notrace int print_raw_fmt(struct trace_iterator *iter)
 			return 0;
 		break;
 	case TRACE_CTX:
+	case TRACE_WAKE:
 		S = entry->ctx.prev_state < sizeof(state_to_char) ?
 			state_to_char[entry->ctx.prev_state] : 'X';
-		ret = trace_seq_printf(s, "%d %d %c %d %d\n",
+		T = entry->ctx.next_state < sizeof(state_to_char) ?
+			state_to_char[entry->ctx.next_state] : 'X';
+		if (entry->type == TRACE_WAKE)
+			S = '+';
+		ret = trace_seq_printf(s, "%d %d %c %d %d %c\n",
 				       entry->ctx.prev_pid,
 				       entry->ctx.prev_prio,
 				       S,
 				       entry->ctx.next_pid,
-				       entry->ctx.next_prio);
+				       entry->ctx.next_prio,
+				       T);
 		if (!ret)
 			return 0;
 		break;
 	case TRACE_SPECIAL:
-		ret = trace_seq_printf(s, " %lx %lx %lx\n",
+	case TRACE_STACK:
+		ret = trace_seq_printf(s, "# %ld %ld %ld\n",
 				 entry->special.arg1,
 				 entry->special.arg2,
 				 entry->special.arg3);
@@ -1336,12 +1580,12 @@ do {							\
 		return 0;				\
 } while (0)
 
-static notrace int print_hex_fmt(struct trace_iterator *iter)
+static int print_hex_fmt(struct trace_iterator *iter)
 {
 	struct trace_seq *s = &iter->seq;
 	unsigned char newline = '\n';
 	struct trace_entry *entry;
-	int S;
+	int S, T;
 
 	entry = iter->ent;
 
@@ -1355,16 +1599,23 @@ static notrace int print_hex_fmt(struct trace_iterator *iter)
 		SEQ_PUT_HEX_FIELD_RET(s, entry->fn.parent_ip);
 		break;
 	case TRACE_CTX:
+	case TRACE_WAKE:
 		S = entry->ctx.prev_state < sizeof(state_to_char) ?
 			state_to_char[entry->ctx.prev_state] : 'X';
+		T = entry->ctx.next_state < sizeof(state_to_char) ?
+			state_to_char[entry->ctx.next_state] : 'X';
+		if (entry->type == TRACE_WAKE)
+			S = '+';
 		SEQ_PUT_HEX_FIELD_RET(s, entry->ctx.prev_pid);
 		SEQ_PUT_HEX_FIELD_RET(s, entry->ctx.prev_prio);
 		SEQ_PUT_HEX_FIELD_RET(s, S);
 		SEQ_PUT_HEX_FIELD_RET(s, entry->ctx.next_pid);
 		SEQ_PUT_HEX_FIELD_RET(s, entry->ctx.next_prio);
 		SEQ_PUT_HEX_FIELD_RET(s, entry->fn.parent_ip);
+		SEQ_PUT_HEX_FIELD_RET(s, T);
 		break;
 	case TRACE_SPECIAL:
+	case TRACE_STACK:
 		SEQ_PUT_HEX_FIELD_RET(s, entry->special.arg1);
 		SEQ_PUT_HEX_FIELD_RET(s, entry->special.arg2);
 		SEQ_PUT_HEX_FIELD_RET(s, entry->special.arg3);
@@ -1375,7 +1626,7 @@ static notrace int print_hex_fmt(struct trace_iterator *iter)
 	return 1;
 }
 
-static notrace int print_bin_fmt(struct trace_iterator *iter)
+static int print_bin_fmt(struct trace_iterator *iter)
 {
 	struct trace_seq *s = &iter->seq;
 	struct trace_entry *entry;
@@ -1397,8 +1648,10 @@ static notrace int print_bin_fmt(struct trace_iterator *iter)
 		SEQ_PUT_FIELD_RET(s, entry->ctx.prev_state);
 		SEQ_PUT_FIELD_RET(s, entry->ctx.next_pid);
 		SEQ_PUT_FIELD_RET(s, entry->ctx.next_prio);
+		SEQ_PUT_FIELD_RET(s, entry->ctx.next_state);
 		break;
 	case TRACE_SPECIAL:
+	case TRACE_STACK:
 		SEQ_PUT_FIELD_RET(s, entry->special.arg1);
 		SEQ_PUT_FIELD_RET(s, entry->special.arg2);
 		SEQ_PUT_FIELD_RET(s, entry->special.arg3);
@@ -1412,7 +1665,7 @@ static int trace_empty(struct trace_iterator *iter)
 	struct trace_array_cpu *data;
 	int cpu;
 
-	for_each_possible_cpu(cpu) {
+	for_each_tracing_cpu(cpu) {
 		data = iter->tr->data[cpu];
 
 		if (head_page(data) && data->trace_idx &&
@@ -1425,6 +1678,9 @@ static int trace_empty(struct trace_iterator *iter)
 
 static int print_trace_line(struct trace_iterator *iter)
 {
+	if (iter->trace && iter->trace->print_line)
+		return iter->trace->print_line(iter);
+
 	if (trace_flags & TRACE_ITER_BIN)
 		return print_bin_fmt(iter);
 
@@ -1475,7 +1731,7 @@ static struct seq_operations tracer_seq_ops = {
 	.show		= s_show,
 };
 
-static struct trace_iterator notrace *
+static struct trace_iterator *
 __tracing_open(struct inode *inode, struct file *file, int *ret)
 {
 	struct trace_iterator *iter;
@@ -1572,7 +1828,7 @@ static int tracing_lt_open(struct inode *inode, struct file *file)
 }
 
 
-static notrace void *
+static void *
 t_next(struct seq_file *m, void *v, loff_t *pos)
 {
 	struct tracer *t = m->private;
@@ -1658,9 +1914,102 @@ static struct file_operations tracing_lt_fops = {
 };
 
 static struct file_operations show_traces_fops = {
-	.open = show_traces_open,
-	.read = seq_read,
-	.release = seq_release,
+	.open		= show_traces_open,
+	.read		= seq_read,
+	.release	= seq_release,
+};
+
+/*
+ * Only trace on a CPU if the bitmask is set:
+ */
+static cpumask_t tracing_cpumask = CPU_MASK_ALL;
+
+/*
+ * When tracing/tracing_cpu_mask is modified then this holds
+ * the new bitmask we are about to install:
+ */
+static cpumask_t tracing_cpumask_new;
+
+/*
+ * The tracer itself will not take this lock, but still we want
+ * to provide a consistent cpumask to user-space:
+ */
+static DEFINE_MUTEX(tracing_cpumask_update_lock);
+
+/*
+ * Temporary storage for the character representation of the
+ * CPU bitmask (and one more byte for the newline):
+ */
+static char mask_str[NR_CPUS + 1];
+
+static ssize_t
+tracing_cpumask_read(struct file *filp, char __user *ubuf,
+		     size_t count, loff_t *ppos)
+{
+	int len;
+
+	mutex_lock(&tracing_cpumask_update_lock);
+
+	len = cpumask_scnprintf(mask_str, count, tracing_cpumask);
+	if (count - len < 2) {
+		count = -EINVAL;
+		goto out_err;
+	}
+	len += sprintf(mask_str + len, "\n");
+	count = simple_read_from_buffer(ubuf, count, ppos, mask_str, NR_CPUS+1);
+
+out_err:
+	mutex_unlock(&tracing_cpumask_update_lock);
+
+	return count;
+}
+
+static ssize_t
+tracing_cpumask_write(struct file *filp, const char __user *ubuf,
+		      size_t count, loff_t *ppos)
+{
+	int err, cpu;
+
+	mutex_lock(&tracing_cpumask_update_lock);
+	err = cpumask_parse_user(ubuf, count, tracing_cpumask_new);
+	if (err)
+		goto err_unlock;
+
+	raw_local_irq_disable();
+	__raw_spin_lock(&ftrace_max_lock);
+	for_each_tracing_cpu(cpu) {
+		/*
+		 * Increase/decrease the disabled counter if we are
+		 * about to flip a bit in the cpumask:
+		 */
+		if (cpu_isset(cpu, tracing_cpumask) &&
+				!cpu_isset(cpu, tracing_cpumask_new)) {
+			atomic_inc(&global_trace.data[cpu]->disabled);
+		}
+		if (!cpu_isset(cpu, tracing_cpumask) &&
+				cpu_isset(cpu, tracing_cpumask_new)) {
+			atomic_dec(&global_trace.data[cpu]->disabled);
+		}
+	}
+	__raw_spin_unlock(&ftrace_max_lock);
+	raw_local_irq_enable();
+
+	tracing_cpumask = tracing_cpumask_new;
+
+	mutex_unlock(&tracing_cpumask_update_lock);
+
+	return count;
+
+err_unlock:
+	mutex_unlock(&tracing_cpumask_update_lock);
+
+	return err;
+}
+
+static struct file_operations tracing_cpumask_fops = {
+	.open		= tracing_open_generic,
+	.read		= tracing_cpumask_read,
+	.write		= tracing_cpumask_write,
 };
 
 static ssize_t
@@ -1693,8 +2042,7 @@ tracing_iter_ctrl_read(struct file *filp, char __user *ubuf,
 	r += sprintf(buf + r, "\n");
 	WARN_ON(r >= len + 2);
 
-	r = simple_read_from_buffer(ubuf, cnt, ppos,
-				    buf, r);
+	r = simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
 
 	kfree(buf);
 
@@ -1710,8 +2058,8 @@ tracing_iter_ctrl_write(struct file *filp, const char __user *ubuf,
 	int neg = 0;
 	int i;
 
-	if (cnt > 63)
-		cnt = 63;
+	if (cnt >= sizeof(buf))
+		return -EINVAL;
 
 	if (copy_from_user(&buf, ubuf, cnt))
 		return -EFAULT;
@@ -1734,6 +2082,11 @@ tracing_iter_ctrl_write(struct file *filp, const char __user *ubuf,
 			break;
 		}
 	}
+	/*
+	 * If no option could be set, return an error:
+	 */
+	if (!trace_options[i])
+		return -EINVAL;
 
 	filp->f_pos += cnt;
 
@@ -1741,9 +2094,9 @@ tracing_iter_ctrl_write(struct file *filp, const char __user *ubuf,
 }
 
 static struct file_operations tracing_iter_fops = {
-	.open = tracing_open_generic,
-	.read = tracing_iter_ctrl_read,
-	.write = tracing_iter_ctrl_write,
+	.open		= tracing_open_generic,
+	.read		= tracing_iter_ctrl_read,
+	.write		= tracing_iter_ctrl_write,
 };
 
 static const char readme_msg[] =
@@ -1774,8 +2127,8 @@ tracing_readme_read(struct file *filp, char __user *ubuf,
 }
 
 static struct file_operations tracing_readme_fops = {
-	.open = tracing_open_generic,
-	.read = tracing_readme_read,
+	.open		= tracing_open_generic,
+	.read		= tracing_readme_read,
 };
 
 static ssize_t
@@ -1795,18 +2148,21 @@ tracing_ctrl_write(struct file *filp, const char __user *ubuf,
 		   size_t cnt, loff_t *ppos)
 {
 	struct trace_array *tr = filp->private_data;
-	long val;
 	char buf[64];
+	long val;
+	int ret;
 
-	if (cnt > 63)
-		cnt = 63;
+	if (cnt >= sizeof(buf))
+		return -EINVAL;
 
 	if (copy_from_user(&buf, ubuf, cnt))
 		return -EFAULT;
 
 	buf[cnt] = 0;
 
-	val = simple_strtoul(buf, NULL, 10);
+	ret = strict_strtoul(buf, 10, &val);
+	if (ret < 0)
+		return ret;
 
 	val = !!val;
 
@@ -1898,10 +2254,10 @@ tracing_max_lat_read(struct file *filp, char __user *ubuf,
 	char buf[64];
 	int r;
 
-	r = snprintf(buf, 64, "%ld\n",
+	r = snprintf(buf, sizeof(buf), "%ld\n",
 		     *ptr == (unsigned long)-1 ? -1 : nsecs_to_usecs(*ptr));
-	if (r > 64)
-		r = 64;
+	if (r > sizeof(buf))
+		r = sizeof(buf);
 	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
 }
 
@@ -1910,18 +2266,21 @@ tracing_max_lat_write(struct file *filp, const char __user *ubuf,
 		      size_t cnt, loff_t *ppos)
 {
 	long *ptr = filp->private_data;
-	long val;
 	char buf[64];
+	long val;
+	int ret;
 
-	if (cnt > 63)
-		cnt = 63;
+	if (cnt >= sizeof(buf))
+		return -EINVAL;
 
 	if (copy_from_user(&buf, ubuf, cnt))
 		return -EFAULT;
 
 	buf[cnt] = 0;
 
-	val = simple_strtoul(buf, NULL, 10);
+	ret = strict_strtoul(buf, 10, &val);
+	if (ret < 0)
+		return ret;
 
 	*ptr = val * 1000;
 
@@ -1948,10 +2307,15 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
 	if (!iter)
 		return -ENOMEM;
 
+	mutex_lock(&trace_types_lock);
 	iter->tr = &global_trace;
-
+	iter->trace = current_trace;
 	filp->private_data = iter;
 
+	if (iter->trace->pipe_open)
+		iter->trace->pipe_open(iter);
+	mutex_unlock(&trace_types_lock);
+
 	return 0;
 }
 
@@ -1975,8 +2339,7 @@ tracing_poll_pipe(struct file *filp, poll_table *poll_table)
 		 * Always select as readable when in blocking mode
 		 */
 		return POLLIN | POLLRDNORM;
-	}
-	else {
+	} else {
 		if (!trace_empty(iter))
 			return POLLIN | POLLRDNORM;
 		poll_wait(filp, &trace_wait, poll_table);
@@ -2021,12 +2384,25 @@ tracing_read_pipe(struct file *filp, char __user *ubuf,
 		return cnt;
 	}
 
+	mutex_lock(&trace_types_lock);
+	if (iter->trace->read) {
+		ret = iter->trace->read(iter, filp, ubuf, cnt, ppos);
+		if (ret) {
+			read = ret;
+			goto out;
+		}
+	}
+
 	trace_seq_reset(&iter->seq);
 	start = 0;
 
 	while (trace_empty(iter)) {
-		if (!(trace_flags & TRACE_ITER_BLOCK))
-			return -EWOULDBLOCK;
+
+		if ((filp->f_flags & O_NONBLOCK)) {
+			read = -EAGAIN;
+			goto out;
+		}
+
 		/*
 		 * This is a make-shift waitqueue. The reason we don't use
 		 * an actual wait queue is because:
@@ -2039,13 +2415,22 @@ tracing_read_pipe(struct file *filp, char __user *ubuf,
 		set_current_state(TASK_INTERRUPTIBLE);
 		iter->tr->waiter = current;
 
-		/* sleep for one second, and try again. */
-		schedule_timeout(HZ);
+		mutex_unlock(&trace_types_lock);
+
+		/* sleep for 100 msecs, and try again. */
+		schedule_timeout(HZ/10);
+
+		mutex_lock(&trace_types_lock);
 
 		iter->tr->waiter = NULL;
 
-		if (signal_pending(current))
-			return -EINTR;
+		if (signal_pending(current)) {
+			read = -EINTR;
+			goto out;
+		}
+
+		if (iter->trace != current_trace)
+			goto out;
 
 		/*
 		 * We block until we read something and tracing is disabled.
@@ -2064,13 +2449,15 @@ tracing_read_pipe(struct file *filp, char __user *ubuf,
 
 	/* stop when tracing is finished */
 	if (trace_empty(iter))
-		return 0;
+		goto out;
 
 	if (cnt >= PAGE_SIZE)
 		cnt = PAGE_SIZE - 1;
 
-	memset(iter, 0, sizeof(*iter));
-	iter->tr = &global_trace;
+	/* reset all but tr, trace, and overruns */
+	memset(&iter->seq, 0,
+	       sizeof(struct trace_iterator) -
+	       offsetof(struct trace_iterator, seq));
 	iter->pos = -1;
 
 	/*
@@ -2087,7 +2474,7 @@ tracing_read_pipe(struct file *filp, char __user *ubuf,
 	ftrace_enabled = 0;
 #endif
 	smp_wmb();
-	for_each_possible_cpu(cpu) {
+	for_each_tracing_cpu(cpu) {
 		data = iter->tr->data[cpu];
 
 		if (!head_page(data) || !data->trace_idx)
@@ -2099,7 +2486,12 @@ tracing_read_pipe(struct file *filp, char __user *ubuf,
 
 	for_each_cpu_mask(cpu, mask) {
 		data = iter->tr->data[cpu];
-		spin_lock(&data->lock);
+		__raw_spin_lock(&data->lock);
+
+		if (data->overrun > iter->last_overrun[cpu])
+			iter->overrun[cpu] +=
+				data->overrun - iter->last_overrun[cpu];
+		iter->last_overrun[cpu] = data->overrun;
 	}
 
 	while (find_next_entry_inc(iter) != NULL) {
@@ -2120,7 +2512,7 @@ tracing_read_pipe(struct file *filp, char __user *ubuf,
 
 	for_each_cpu_mask(cpu, mask) {
 		data = iter->tr->data[cpu];
-		spin_unlock(&data->lock);
+		__raw_spin_unlock(&data->lock);
 	}
 
 	for_each_cpu_mask(cpu, mask) {
@@ -2147,9 +2539,79 @@ tracing_read_pipe(struct file *filp, char __user *ubuf,
 	if (ret)
 		read = -EFAULT;
 
+out:
+	mutex_unlock(&trace_types_lock);
+
 	return read;
 }
 
+static ssize_t
+tracing_entries_read(struct file *filp, char __user *ubuf,
+		     size_t cnt, loff_t *ppos)
+{
+	struct trace_array *tr = filp->private_data;
+	char buf[64];
+	int r;
+
+	r = sprintf(buf, "%lu\n", tr->entries);
+	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+}
+
+static ssize_t
+tracing_entries_write(struct file *filp, const char __user *ubuf,
+		      size_t cnt, loff_t *ppos)
+{
+	unsigned long val;
+	char buf[64];
+	int ret;
+
+	if (cnt >= sizeof(buf))
+		return -EINVAL;
+
+	if (copy_from_user(&buf, ubuf, cnt))
+		return -EFAULT;
+
+	buf[cnt] = 0;
+
+	ret = strict_strtoul(buf, 10, &val);
+	if (ret < 0)
+		return ret;
+
+	/* must have at least 1 entry */
+	if (!val)
+		return -EINVAL;
+
+	mutex_lock(&trace_types_lock);
+
+	if (current_trace != &no_tracer) {
+		cnt = -EBUSY;
+		pr_info("ftrace: set current_tracer to none"
+			" before modifying buffer size\n");
+		goto out;
+	}
+
+	if (val > global_trace.entries) {
+		while (global_trace.entries < val) {
+			if (trace_alloc_page()) {
+				cnt = -ENOMEM;
+				goto out;
+			}
+		}
+	} else {
+		/* include the number of entries in val (inc of page entries) */
+		while (global_trace.entries > val + (ENTRIES_PER_PAGE - 1))
+			trace_free_page();
+	}
+
+	filp->f_pos += cnt;
+
+ out:
+	max_tr.entries = global_trace.entries;
+	mutex_unlock(&trace_types_lock);
+
+	return cnt;
+}
+
 static struct file_operations tracing_max_lat_fops = {
 	.open		= tracing_open_generic,
 	.read		= tracing_max_lat_read,
@@ -2175,6 +2637,12 @@ static struct file_operations tracing_pipe_fops = {
 	.release	= tracing_release_pipe,
 };
 
+static struct file_operations tracing_entries_fops = {
+	.open		= tracing_open_generic,
+	.read		= tracing_entries_read,
+	.write		= tracing_entries_write,
+};
+
 #ifdef CONFIG_DYNAMIC_FTRACE
 
 static ssize_t
@@ -2238,6 +2706,11 @@ static __init void tracer_init_debugfs(void)
 	if (!entry)
 		pr_warning("Could not create debugfs 'iter_ctrl' entry\n");
 
+	entry = debugfs_create_file("tracing_cpumask", 0644, d_tracer,
+				    NULL, &tracing_cpumask_fops);
+	if (!entry)
+		pr_warning("Could not create debugfs 'tracing_cpumask' entry\n");
+
 	entry = debugfs_create_file("latency_trace", 0444, d_tracer,
 				    &global_trace, &tracing_lt_fops);
 	if (!entry)
@@ -2281,6 +2754,12 @@ static __init void tracer_init_debugfs(void)
 		pr_warning("Could not create debugfs "
 			   "'tracing_threash' entry\n");
 
+	entry = debugfs_create_file("trace_entries", 0644, d_tracer,
+				    &global_trace, &tracing_entries_fops);
+	if (!entry)
+		pr_warning("Could not create debugfs "
+			   "'tracing_threash' entry\n");
+
 #ifdef CONFIG_DYNAMIC_FTRACE
 	entry = debugfs_create_file("dyn_ftrace_total_info", 0444, d_tracer,
 				    &ftrace_update_tot_cnt,
@@ -2291,12 +2770,6 @@ static __init void tracer_init_debugfs(void)
 #endif
 }
 
-/* dummy trace to disable tracing */
-static struct tracer no_tracer __read_mostly =
-{
-	.name		= "none",
-};
-
 static int trace_alloc_page(void)
 {
 	struct trace_array_cpu *data;
@@ -2306,7 +2779,7 @@ static int trace_alloc_page(void)
 	int i;
 
 	/* first allocate a page for each CPU */
-	for_each_possible_cpu(i) {
+	for_each_tracing_cpu(i) {
 		array = (void *)__get_free_page(GFP_KERNEL);
 		if (array == NULL) {
 			printk(KERN_ERR "tracer: failed to allocate page"
@@ -2331,10 +2804,8 @@ static int trace_alloc_page(void)
 	}
 
 	/* Now that we successfully allocate a page per CPU, add them */
-	for_each_possible_cpu(i) {
+	for_each_tracing_cpu(i) {
 		data = global_trace.data[i];
-		spin_lock_init(&data->lock);
-		lockdep_set_class(&data->lock, &data->lock_key);
 		page = list_entry(pages.next, struct page, lru);
 		list_del_init(&page->lru);
 		list_add_tail(&page->lru, &data->trace_pages);
@@ -2342,8 +2813,6 @@ static int trace_alloc_page(void)
 
 #ifdef CONFIG_TRACER_MAX_TRACE
 		data = max_tr.data[i];
-		spin_lock_init(&data->lock);
-		lockdep_set_class(&data->lock, &data->lock_key);
 		page = list_entry(pages.next, struct page, lru);
 		list_del_init(&page->lru);
 		list_add_tail(&page->lru, &data->trace_pages);
@@ -2362,6 +2831,55 @@ static int trace_alloc_page(void)
 	return -ENOMEM;
 }
 
+static int trace_free_page(void)
+{
+	struct trace_array_cpu *data;
+	struct page *page;
+	struct list_head *p;
+	int i;
+	int ret = 0;
+
+	/* free one page from each buffer */
+	for_each_tracing_cpu(i) {
+		data = global_trace.data[i];
+		p = data->trace_pages.next;
+		if (p == &data->trace_pages) {
+			/* should never happen */
+			WARN_ON(1);
+			tracing_disabled = 1;
+			ret = -1;
+			break;
+		}
+		page = list_entry(p, struct page, lru);
+		ClearPageLRU(page);
+		list_del(&page->lru);
+		__free_page(page);
+
+		tracing_reset(data);
+
+#ifdef CONFIG_TRACER_MAX_TRACE
+		data = max_tr.data[i];
+		p = data->trace_pages.next;
+		if (p == &data->trace_pages) {
+			/* should never happen */
+			WARN_ON(1);
+			tracing_disabled = 1;
+			ret = -1;
+			break;
+		}
+		page = list_entry(p, struct page, lru);
+		ClearPageLRU(page);
+		list_del(&page->lru);
+		__free_page(page);
+
+		tracing_reset(data);
+#endif
+	}
+	global_trace.entries -= ENTRIES_PER_PAGE;
+
+	return ret;
+}
+
 __init static int tracer_alloc_buffers(void)
 {
 	struct trace_array_cpu *data;
@@ -2373,8 +2891,12 @@ __init static int tracer_alloc_buffers(void)
 
 	global_trace.ctrl = tracer_enabled;
 
+	/* TODO: make the number of buffers hot pluggable with CPUS */
+	tracing_nr_buffers = num_possible_cpus();
+	tracing_buffer_mask = cpu_possible_map;
+
 	/* Allocate the first page for all buffers */
-	for_each_possible_cpu(i) {
+	for_each_tracing_cpu(i) {
 		data = global_trace.data[i] = &per_cpu(global_trace_cpu, i);
 		max_tr.data[i] = &per_cpu(max_data, i);
 
@@ -2392,6 +2914,9 @@ __init static int tracer_alloc_buffers(void)
 		/* use the LRU flag to differentiate the two buffers */
 		ClearPageLRU(page);
 
+		data->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
+		max_tr.data[i]->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
+
 /* Only allocate if we are actually using the max trace */
 #ifdef CONFIG_TRACER_MAX_TRACE
 		array = (void *)__get_free_page(GFP_KERNEL);