Merge branch 'tip/tracing/ftrace' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace into tracing/ftrace

include/linux/interrupt.h

@@ -258,6 +258,11 @@ enum
 	NR_SOFTIRQS
 };
 
+/* map softirq index to softirq name. update 'softirq_to_name' in
+ * kernel/softirq.c when adding a new softirq.
+ */
+extern char *softirq_to_name[NR_SOFTIRQS];
+
 /* softirq mask and active fields moved to irq_cpustat_t in
  * asm/hardirq.h to get better cache usage.  KAO
  */

include/linux/kernel.h

@@ -452,31 +452,45 @@ do {									\
 
 #define trace_printk(fmt, args...)					\
 do {									\
-	static const char *trace_printk_fmt				\
-	__attribute__((section("__trace_printk_fmt")));			\
-									\
-	if (!trace_printk_fmt)						\
-		trace_printk_fmt = fmt;					\
-									\
 	__trace_printk_check_format(fmt, ##args);			\
-	__trace_printk(_THIS_IP_, trace_printk_fmt, ##args);		\
+	if (__builtin_constant_p(fmt)) {				\
+		static const char *trace_printk_fmt			\
+		  __attribute__((section("__trace_printk_fmt"))) =	\
+			__builtin_constant_p(fmt) ? fmt : NULL;		\
+									\
+		__trace_bprintk(_THIS_IP_, trace_printk_fmt, ##args);	\
+	} else								\
+		__trace_printk(_THIS_IP_, fmt, ##args);		\
 } while (0)
 
+extern int
+__trace_bprintk(unsigned long ip, const char *fmt, ...)
+	__attribute__ ((format (printf, 2, 3)));
+
 extern int
 __trace_printk(unsigned long ip, const char *fmt, ...)
 	__attribute__ ((format (printf, 2, 3)));
 
+/*
+ * The double __builtin_constant_p is because gcc will give us an error
+ * if we try to allocate the static variable to fmt if it is not a
+ * constant. Even with the outer if statement.
+ */
 #define ftrace_vprintk(fmt, vargs)					\
 do {									\
-	static const char *trace_printk_fmt				\
-	__attribute__((section("__trace_printk_fmt")));			\
-									\
-	if (!trace_printk_fmt)						\
-		trace_printk_fmt = fmt;					\
+	if (__builtin_constant_p(fmt)) {				\
+		static const char *trace_printk_fmt			\
+		  __attribute__((section("__trace_printk_fmt"))) =	\
+			__builtin_constant_p(fmt) ? fmt : NULL;		\
 									\
-	__ftrace_vprintk(_THIS_IP_, trace_printk_fmt, vargs);		\
+		__ftrace_vbprintk(_THIS_IP_, trace_printk_fmt, vargs);	\
+	} else								\
+		__ftrace_vprintk(_THIS_IP_, fmt, vargs);		\
 } while (0)
 
+extern int
+__ftrace_vbprintk(unsigned long ip, const char *fmt, va_list ap);
+
 extern int
 __ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap);
 

include/trace/irq_event_types.h

@@ -40,4 +40,16 @@ TRACE_EVENT(irq_handler_exit,
 		  __entry->irq, __entry->ret ? "handled" : "unhandled")
 );
 
+TRACE_FORMAT(softirq_entry,
+	TP_PROTO(struct softirq_action *h, struct softirq_action *vec),
+	TP_ARGS(h, vec),
+	TP_FMT("softirq=%d action=%s", (int)(h - vec), softirq_to_name[h-vec])
+	);
+
+TRACE_FORMAT(softirq_exit,
+	TP_PROTO(struct softirq_action *h, struct softirq_action *vec),
+	TP_ARGS(h, vec),
+	TP_FMT("softirq=%d action=%s", (int)(h - vec), softirq_to_name[h-vec])
+	);
+
 #undef TRACE_SYSTEM

kernel/softirq.c

@@ -24,6 +24,7 @@
 #include <linux/ftrace.h>
 #include <linux/smp.h>
 #include <linux/tick.h>
+#include <trace/irq.h>
 
 #include <asm/irq.h>
 /*
@@ -53,6 +54,12 @@ static struct softirq_action softirq_vec[NR_SOFTIRQS] __cacheline_aligned_in_smp
 
 static DEFINE_PER_CPU(struct task_struct *, ksoftirqd);
 
+char *softirq_to_name[NR_SOFTIRQS] = {
+	"HI_SOFTIRQ", "TIMER_SOFTIRQ", "NET_TX_SOFTIRQ", "NET_RX_SOFTIRQ",
+	"BLOCK_SOFTIRQ", "TASKLET_SOFTIRQ", "SCHED_SOFTIRQ", "HRTIMER_SOFTIRQ",
+	"RCU_SOFTIRQ"
+};
+
 /*
  * we cannot loop indefinitely here to avoid userspace starvation,
  * but we also don't want to introduce a worst case 1/HZ latency
@@ -180,6 +187,9 @@ EXPORT_SYMBOL(local_bh_enable_ip);
  */
 #define MAX_SOFTIRQ_RESTART 10
 
+DEFINE_TRACE(softirq_entry);
+DEFINE_TRACE(softirq_exit);
+
 asmlinkage void __do_softirq(void)
 {
 	struct softirq_action *h;
@@ -206,12 +216,14 @@ restart:
 		if (pending & 1) {
 			int prev_count = preempt_count();
 
+			trace_softirq_entry(h, softirq_vec);
 			h->action(h);
-
+			trace_softirq_exit(h, softirq_vec);
 			if (unlikely(prev_count != preempt_count())) {
-				printk(KERN_ERR "huh, entered softirq %td %p"
+				printk(KERN_ERR "huh, entered softirq %td %s %p"
 				       "with preempt_count %08x,"
 				       " exited with %08x?\n", h - softirq_vec,
+				       softirq_to_name[h - softirq_vec],
 				       h->action, prev_count, preempt_count());
 				preempt_count() = prev_count;
 			}

kernel/trace/ring_buffer.c

@@ -16,10 +16,79 @@
 #include <linux/init.h>
 #include <linux/hash.h>
 #include <linux/list.h>
+#include <linux/cpu.h>
 #include <linux/fs.h>
 
 #include "trace.h"
 
+/*
+ * The ring buffer is made up of a list of pages. A separate list of pages is
+ * allocated for each CPU. A writer may only write to a buffer that is
+ * associated with the CPU it is currently executing on.  A reader may read
+ * from any per cpu buffer.
+ *
+ * The reader is special. For each per cpu buffer, the reader has its own
+ * reader page. When a reader has read the entire reader page, this reader
+ * page is swapped with another page in the ring buffer.
+ *
+ * Now, as long as the writer is off the reader page, the reader can do what
+ * ever it wants with that page. The writer will never write to that page
+ * again (as long as it is out of the ring buffer).
+ *
+ * Here's some silly ASCII art.
+ *
+ *   +------+
+ *   |reader|          RING BUFFER
+ *   |page  |
+ *   +------+        +---+   +---+   +---+
+ *                   |   |-->|   |-->|   |
+ *                   +---+   +---+   +---+
+ *                     ^               |
+ *                     |               |
+ *                     +---------------+
+ *
+ *
+ *   +------+
+ *   |reader|          RING BUFFER
+ *   |page  |------------------v
+ *   +------+        +---+   +---+   +---+
+ *                   |   |-->|   |-->|   |
+ *                   +---+   +---+   +---+
+ *                     ^               |
+ *                     |               |
+ *                     +---------------+
+ *
+ *
+ *   +------+
+ *   |reader|          RING BUFFER
+ *   |page  |------------------v
+ *   +------+        +---+   +---+   +---+
+ *      ^            |   |-->|   |-->|   |
+ *      |            +---+   +---+   +---+
+ *      |                              |
+ *      |                              |
+ *      +------------------------------+
+ *
+ *
+ *   +------+
+ *   |buffer|          RING BUFFER
+ *   |page  |------------------v
+ *   +------+        +---+   +---+   +---+
+ *      ^            |   |   |   |-->|   |
+ *      |   New      +---+   +---+   +---+
+ *      |  Reader------^               |
+ *      |   page                       |
+ *      +------------------------------+
+ *
+ *
+ * After we make this swap, the reader can hand this page off to the splice
+ * code and be done with it. It can even allocate a new page if it needs to
+ * and swap that into the ring buffer.
+ *
+ * We will be using cmpxchg soon to make all this lockless.
+ *
+ */
+
 /*
  * A fast way to enable or disable all ring buffers is to
  * call tracing_on or tracing_off. Turning off the ring buffers
@@ -301,6 +370,10 @@ struct ring_buffer {
 	struct mutex			mutex;
 
 	struct ring_buffer_per_cpu	**buffers;
+
+#ifdef CONFIG_HOTPLUG_CPU
+	struct notifier_block		cpu_notify;
+#endif
 };
 
 struct ring_buffer_iter {
@@ -459,6 +532,11 @@ static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer)
  */
 extern int ring_buffer_page_too_big(void);
 
+#ifdef CONFIG_HOTPLUG_CPU
+static int __cpuinit rb_cpu_notify(struct notifier_block *self,
+				   unsigned long action, void *hcpu);
+#endif
+
 /**
  * ring_buffer_alloc - allocate a new ring_buffer
  * @size: the size in bytes per cpu that is needed.
@@ -496,7 +574,8 @@ struct ring_buffer *ring_buffer_alloc(unsigned long size, unsigned flags)
 	if (buffer->pages == 1)
 		buffer->pages++;
 
-	cpumask_copy(buffer->cpumask, cpu_possible_mask);
+	get_online_cpus();
+	cpumask_copy(buffer->cpumask, cpu_online_mask);
 	buffer->cpus = nr_cpu_ids;
 
 	bsize = sizeof(void *) * nr_cpu_ids;
@@ -512,6 +591,13 @@ struct ring_buffer *ring_buffer_alloc(unsigned long size, unsigned flags)
 			goto fail_free_buffers;
 	}
 
+#ifdef CONFIG_HOTPLUG_CPU
+	buffer->cpu_notify.notifier_call = rb_cpu_notify;
+	buffer->cpu_notify.priority = 0;
+	register_cpu_notifier(&buffer->cpu_notify);
+#endif
+
+	put_online_cpus();
 	mutex_init(&buffer->mutex);
 
 	return buffer;
@@ -525,6 +611,7 @@ struct ring_buffer *ring_buffer_alloc(unsigned long size, unsigned flags)
 
  fail_free_cpumask:
 	free_cpumask_var(buffer->cpumask);
+	put_online_cpus();
 
  fail_free_buffer:
 	kfree(buffer);
@@ -541,9 +628,17 @@ ring_buffer_free(struct ring_buffer *buffer)
 {
 	int cpu;
 
+	get_online_cpus();
+
+#ifdef CONFIG_HOTPLUG_CPU
+	unregister_cpu_notifier(&buffer->cpu_notify);
+#endif
+
 	for_each_buffer_cpu(buffer, cpu)
 		rb_free_cpu_buffer(buffer->buffers[cpu]);
 
+	put_online_cpus();
+
 	free_cpumask_var(buffer->cpumask);
 
 	kfree(buffer);
@@ -649,16 +744,15 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
 		return size;
 
 	mutex_lock(&buffer->mutex);
+	get_online_cpus();
 
 	nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
 
 	if (size < buffer_size) {
 
 		/* easy case, just free pages */
-		if (RB_WARN_ON(buffer, nr_pages >= buffer->pages)) {
-			mutex_unlock(&buffer->mutex);
-			return -1;
-		}
+		if (RB_WARN_ON(buffer, nr_pages >= buffer->pages))
+			goto out_fail;
 
 		rm_pages = buffer->pages - nr_pages;
 
@@ -677,10 +771,8 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
 	 * add these pages to the cpu_buffers. Otherwise we just free
 	 * them all and return -ENOMEM;
 	 */
-	if (RB_WARN_ON(buffer, nr_pages <= buffer->pages)) {
-		mutex_unlock(&buffer->mutex);
-		return -1;
-	}
+	if (RB_WARN_ON(buffer, nr_pages <= buffer->pages))
+		goto out_fail;
 
 	new_pages = nr_pages - buffer->pages;
 
@@ -705,13 +797,12 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
 		rb_insert_pages(cpu_buffer, &pages, new_pages);
 	}
 
-	if (RB_WARN_ON(buffer, !list_empty(&pages))) {
-		mutex_unlock(&buffer->mutex);
-		return -1;
-	}
+	if (RB_WARN_ON(buffer, !list_empty(&pages)))
+		goto out_fail;
 
  out:
 	buffer->pages = nr_pages;
+	put_online_cpus();
 	mutex_unlock(&buffer->mutex);
 
 	return size;
@@ -721,8 +812,18 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
 		list_del_init(&bpage->list);
 		free_buffer_page(bpage);
 	}
+	put_online_cpus();
 	mutex_unlock(&buffer->mutex);
 	return -ENOMEM;
+
+	/*
+	 * Something went totally wrong, and we are too paranoid
+	 * to even clean up the mess.
+	 */
+ out_fail:
+	put_online_cpus();
+	mutex_unlock(&buffer->mutex);
+	return -1;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_resize);
 
@@ -1564,12 +1665,15 @@ EXPORT_SYMBOL_GPL(ring_buffer_record_enable_cpu);
 unsigned long ring_buffer_entries_cpu(struct ring_buffer *buffer, int cpu)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
+	unsigned long ret;
 
 	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		return 0;
 
 	cpu_buffer = buffer->buffers[cpu];
-	return cpu_buffer->entries;
+	ret = cpu_buffer->entries;
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_entries_cpu);
 
@@ -1581,12 +1685,15 @@ EXPORT_SYMBOL_GPL(ring_buffer_entries_cpu);
 unsigned long ring_buffer_overrun_cpu(struct ring_buffer *buffer, int cpu)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
+	unsigned long ret;
 
 	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		return 0;
 
 	cpu_buffer = buffer->buffers[cpu];
-	return cpu_buffer->overrun;
+	ret = cpu_buffer->overrun;
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_overrun_cpu);
 
@@ -1663,9 +1770,14 @@ static void rb_iter_reset(struct ring_buffer_iter *iter)
  */
 void ring_buffer_iter_reset(struct ring_buffer_iter *iter)
 {
-	struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
+	struct ring_buffer_per_cpu *cpu_buffer;
 	unsigned long flags;
 
+	if (!iter)
+		return;
+
+	cpu_buffer = iter->cpu_buffer;
+
 	spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
 	rb_iter_reset(iter);
 	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
@@ -1900,9 +2012,6 @@ rb_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
 	struct buffer_page *reader;
 	int nr_loops = 0;
 
-	if (!cpumask_test_cpu(cpu, buffer->cpumask))
-		return NULL;
-
 	cpu_buffer = buffer->buffers[cpu];
 
  again:
@@ -2031,6 +2140,9 @@ ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
 	struct ring_buffer_event *event;
 	unsigned long flags;
 
+	if (!cpumask_test_cpu(cpu, buffer->cpumask))
+		return NULL;
+
 	spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
 	event = rb_buffer_peek(buffer, cpu, ts);
 	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
@@ -2071,24 +2183,31 @@ ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 struct ring_buffer_event *
 ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
 {
-	struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
-	struct ring_buffer_event *event;
+	struct ring_buffer_per_cpu *cpu_buffer;
+	struct ring_buffer_event *event = NULL;
 	unsigned long flags;
 
+	/* might be called in atomic */
+	preempt_disable();
+
 	if (!cpumask_test_cpu(cpu, buffer->cpumask))
-		return NULL;
+		goto out;
 
+	cpu_buffer = buffer->buffers[cpu];
 	spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
 
 	event = rb_buffer_peek(buffer, cpu, ts);
 	if (!event)
-		goto out;
+		goto out_unlock;
 
 	rb_advance_reader(cpu_buffer);
 
- out:
+ out_unlock:
 	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
+ out:
+	preempt_enable();
+
 	return event;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_consume);
@@ -2268,6 +2387,7 @@ int ring_buffer_empty(struct ring_buffer *buffer)
 		if (!rb_per_cpu_empty(cpu_buffer))
 			return 0;
 	}
+
 	return 1;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_empty);
@@ -2280,12 +2400,16 @@ EXPORT_SYMBOL_GPL(ring_buffer_empty);
 int ring_buffer_empty_cpu(struct ring_buffer *buffer, int cpu)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
+	int ret;
 
 	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		return 1;
 
 	cpu_buffer = buffer->buffers[cpu];
-	return rb_per_cpu_empty(cpu_buffer);
+	ret = rb_per_cpu_empty(cpu_buffer);
+
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_empty_cpu);
 
@@ -2304,32 +2428,35 @@ int ring_buffer_swap_cpu(struct ring_buffer *buffer_a,
 {
 	struct ring_buffer_per_cpu *cpu_buffer_a;
 	struct ring_buffer_per_cpu *cpu_buffer_b;
+	int ret = -EINVAL;
 
 	if (!cpumask_test_cpu(cpu, buffer_a->cpumask) ||
 	    !cpumask_test_cpu(cpu, buffer_b->cpumask))
-		return -EINVAL;
+		goto out;
 
 	/* At least make sure the two buffers are somewhat the same */
 	if (buffer_a->pages != buffer_b->pages)
-		return -EINVAL;
+		goto out;
+
+	ret = -EAGAIN;
 
 	if (ring_buffer_flags != RB_BUFFERS_ON)
-		return -EAGAIN;
+		goto out;
 
 	if (atomic_read(&buffer_a->record_disabled))
-		return -EAGAIN;
+		goto out;
 
 	if (atomic_read(&buffer_b->record_disabled))
-		return -EAGAIN;
+		goto out;
 
 	cpu_buffer_a = buffer_a->buffers[cpu];
 	cpu_buffer_b = buffer_b->buffers[cpu];
 
 	if (atomic_read(&cpu_buffer_a->record_disabled))
-		return -EAGAIN;
+		goto out;
 
 	if (atomic_read(&cpu_buffer_b->record_disabled))
-		return -EAGAIN;
+		goto out;
 
 	/*
 	 * We can't do a synchronize_sched here because this
@@ -2349,7 +2476,9 @@ int ring_buffer_swap_cpu(struct ring_buffer *buffer_a,
 	atomic_dec(&cpu_buffer_a->record_disabled);
 	atomic_dec(&cpu_buffer_b->record_disabled);
 
-	return 0;
+	ret = 0;
+out:
+	return ret;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_swap_cpu);
 
@@ -2464,27 +2593,30 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
 	u64 save_timestamp;
 	int ret = -1;
 
+	if (!cpumask_test_cpu(cpu, buffer->cpumask))
+		goto out;
+
 	/*
 	 * If len is not big enough to hold the page header, then
 	 * we can not copy anything.
 	 */
 	if (len <= BUF_PAGE_HDR_SIZE)
-		return -1;
+		goto out;
 
 	len -= BUF_PAGE_HDR_SIZE;
 
 	if (!data_page)
-		return -1;
+		goto out;
 
 	bpage = *data_page;
 	if (!bpage)
-		return -1;
+		goto out;
 
 	spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
 
 	reader = rb_get_reader_page(cpu_buffer);
 	if (!reader)
-		goto out;
+		goto out_unlock;
 
 	event = rb_reader_event(cpu_buffer);
 
@@ -2506,7 +2638,7 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
 		unsigned int size;
 
 		if (full)
-			goto out;
+			goto out_unlock;
 
 		if (len > (commit - read))
 			len = (commit - read);
@@ -2514,7 +2646,7 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
 		size = rb_event_length(event);
 
 		if (len < size)
-			goto out;
+			goto out_unlock;
 
 		/* save the current timestamp, since the user will need it */
 		save_timestamp = cpu_buffer->read_stamp;
@@ -2553,9 +2685,10 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
 	}
 	ret = read;
 
- out:
+ out_unlock:
 	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
+ out:
 	return ret;
 }
 
@@ -2629,3 +2762,42 @@ static __init int rb_init_debugfs(void)
 }
 
 fs_initcall(rb_init_debugfs);
+
+#ifdef CONFIG_HOTPLUG_CPU
+static int __cpuinit rb_cpu_notify(struct notifier_block *self,
+				   unsigned long action, void *hcpu)
+{
+	struct ring_buffer *buffer =
+		container_of(self, struct ring_buffer, cpu_notify);
+	long cpu = (long)hcpu;
+
+	switch (action) {
+	case CPU_UP_PREPARE:
+	case CPU_UP_PREPARE_FROZEN:
+		if (cpu_isset(cpu, *buffer->cpumask))
+			return NOTIFY_OK;
+
+		buffer->buffers[cpu] =
+			rb_allocate_cpu_buffer(buffer, cpu);
+		if (!buffer->buffers[cpu]) {
+			WARN(1, "failed to allocate ring buffer on CPU %ld\n",
+			     cpu);
+			return NOTIFY_OK;
+		}
+		smp_wmb();
+		cpu_set(cpu, *buffer->cpumask);
+		break;
+	case CPU_DOWN_PREPARE:
+	case CPU_DOWN_PREPARE_FROZEN:
+		/*
+		 * Do nothing.
+		 *  If we were to free the buffer, then the user would
+		 *  lose any trace that was in the buffer.
+		 */
+		break;
+	default:
+		break;
+	}
+	return NOTIFY_OK;
+}
+#endif

kernel/trace/trace.c

@@ -44,6 +44,12 @@
 unsigned long __read_mostly	tracing_max_latency;
 unsigned long __read_mostly	tracing_thresh;
 
+/*
+ * On boot up, the ring buffer is set to the minimum size, so that
+ * we do not waste memory on systems that are not using tracing.
+ */
+static int ring_buffer_expanded;
+
 /*
  * We need to change this state when a selftest is running.
  * A selftest will lurk into the ring-buffer to count the
@@ -128,6 +134,8 @@ static int __init set_ftrace(char *str)
 {
 	strncpy(bootup_tracer_buf, str, BOOTUP_TRACER_SIZE);
 	default_bootup_tracer = bootup_tracer_buf;
+	/* We are using ftrace early, expand it */
+	ring_buffer_expanded = 1;
 	return 1;
 }
 __setup("ftrace=", set_ftrace);
@@ -1171,10 +1179,10 @@ void trace_graph_return(struct ftrace_graph_ret *trace)
 
 
 /**
- * trace_vprintk - write binary msg to tracing buffer
+ * trace_vbprintk - write binary msg to tracing buffer
  *
  */
-int trace_vprintk(unsigned long ip, int depth, const char *fmt, va_list args)
+int trace_vbprintk(unsigned long ip, int depth, const char *fmt, va_list args)
 {
 	static raw_spinlock_t trace_buf_lock =
 		(raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
@@ -1183,7 +1191,7 @@ int trace_vprintk(unsigned long ip, int depth, const char *fmt, va_list args)
 	struct ring_buffer_event *event;
 	struct trace_array *tr = &global_trace;
 	struct trace_array_cpu *data;
-	struct print_entry *entry;
+	struct bprint_entry *entry;
 	unsigned long flags;
 	int resched;
 	int cpu, len = 0, size, pc;
@@ -1211,7 +1219,7 @@ int trace_vprintk(unsigned long ip, int depth, const char *fmt, va_list args)
 		goto out_unlock;
 
 	size = sizeof(*entry) + sizeof(u32) * len;
-	event = trace_buffer_lock_reserve(tr, TRACE_PRINT, size, flags, pc);
+	event = trace_buffer_lock_reserve(tr, TRACE_BPRINT, size, flags, pc);
 	if (!event)
 		goto out_unlock;
 	entry = ring_buffer_event_data(event);
@@ -1232,6 +1240,60 @@ out:
 
 	return len;
 }
+EXPORT_SYMBOL_GPL(trace_vbprintk);
+
+int trace_vprintk(unsigned long ip, int depth, const char *fmt, va_list args)
+{
+	static raw_spinlock_t trace_buf_lock = __RAW_SPIN_LOCK_UNLOCKED;
+	static char trace_buf[TRACE_BUF_SIZE];
+
+	struct ring_buffer_event *event;
+	struct trace_array *tr = &global_trace;
+	struct trace_array_cpu *data;
+	int cpu, len = 0, size, pc;
+	struct print_entry *entry;
+	unsigned long irq_flags;
+
+	if (tracing_disabled || tracing_selftest_running)
+		return 0;
+
+	pc = preempt_count();
+	preempt_disable_notrace();
+	cpu = raw_smp_processor_id();
+	data = tr->data[cpu];
+
+	if (unlikely(atomic_read(&data->disabled)))
+		goto out;
+
+	pause_graph_tracing();
+	raw_local_irq_save(irq_flags);
+	__raw_spin_lock(&trace_buf_lock);
+	len = vsnprintf(trace_buf, TRACE_BUF_SIZE, fmt, args);
+
+	len = min(len, TRACE_BUF_SIZE-1);
+	trace_buf[len] = 0;
+
+	size = sizeof(*entry) + len + 1;
+	event = trace_buffer_lock_reserve(tr, TRACE_PRINT, size, irq_flags, pc);
+	if (!event)
+		goto out_unlock;
+	entry = ring_buffer_event_data(event);
+	entry->ip			= ip;
+	entry->depth			= depth;
+
+	memcpy(&entry->buf, trace_buf, len);
+	entry->buf[len] = 0;
+	ring_buffer_unlock_commit(tr->buffer, event);
+
+ out_unlock:
+	__raw_spin_unlock(&trace_buf_lock);
+	raw_local_irq_restore(irq_flags);
+	unpause_graph_tracing();
+ out:
+	preempt_enable_notrace();
+
+	return len;
+}
 EXPORT_SYMBOL_GPL(trace_vprintk);
 
 enum trace_file_type {
@@ -1620,6 +1682,22 @@ static enum print_line_t print_hex_fmt(struct trace_iterator *iter)
 	return TRACE_TYPE_HANDLED;
 }
 
+static enum print_line_t print_bprintk_msg_only(struct trace_iterator *iter)
+{
+	struct trace_seq *s = &iter->seq;
+	struct trace_entry *entry = iter->ent;
+	struct bprint_entry *field;
+	int ret;
+
+	trace_assign_type(field, entry);
+
+	ret = trace_seq_bprintf(s, field->fmt, field->buf);
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	return TRACE_TYPE_HANDLED;
+}
+
 static enum print_line_t print_printk_msg_only(struct trace_iterator *iter)
 {
 	struct trace_seq *s = &iter->seq;
@@ -1629,7 +1707,7 @@ static enum print_line_t print_printk_msg_only(struct trace_iterator *iter)
 
 	trace_assign_type(field, entry);
 
-	ret = trace_seq_bprintf(s, field->fmt, field->buf);
+	ret = trace_seq_printf(s, "%s", field->buf);
 	if (!ret)
 		return TRACE_TYPE_PARTIAL_LINE;
 
@@ -1658,6 +1736,19 @@ static int trace_empty(struct trace_iterator *iter)
 {
 	int cpu;
 
+	/* If we are looking at one CPU buffer, only check that one */
+	if (iter->cpu_file != TRACE_PIPE_ALL_CPU) {
+		cpu = iter->cpu_file;
+		if (iter->buffer_iter[cpu]) {
+			if (!ring_buffer_iter_empty(iter->buffer_iter[cpu]))
+				return 0;
+		} else {
+			if (!ring_buffer_empty_cpu(iter->tr->buffer, cpu))
+				return 0;
+		}
+		return 1;
+	}
+
 	for_each_tracing_cpu(cpu) {
 		if (iter->buffer_iter[cpu]) {
 			if (!ring_buffer_iter_empty(iter->buffer_iter[cpu]))
@@ -1681,6 +1772,11 @@ static enum print_line_t print_trace_line(struct trace_iterator *iter)
 			return ret;
 	}
 
+	if (iter->ent->type == TRACE_BPRINT &&
+			trace_flags & TRACE_ITER_PRINTK &&
+			trace_flags & TRACE_ITER_PRINTK_MSGONLY)
+		return print_bprintk_msg_only(iter);
+
 	if (iter->ent->type == TRACE_PRINT &&
 			trace_flags & TRACE_ITER_PRINTK &&
 			trace_flags & TRACE_ITER_PRINTK_MSGONLY)
@@ -1784,17 +1880,11 @@ __tracing_open(struct inode *inode, struct file *file)
 
 			iter->buffer_iter[cpu] =
 				ring_buffer_read_start(iter->tr->buffer, cpu);
-
-			if (!iter->buffer_iter[cpu])
-				goto fail_buffer;
 		}
 	} else {
 		cpu = iter->cpu_file;
 		iter->buffer_iter[cpu] =
 				ring_buffer_read_start(iter->tr->buffer, cpu);
-
-		if (!iter->buffer_iter[cpu])
-			goto fail;
 	}
 
 	/* TODO stop tracer */
@@ -2315,6 +2405,75 @@ int tracer_init(struct tracer *t, struct trace_array *tr)
 	return t->init(tr);
 }
 
+static int tracing_resize_ring_buffer(unsigned long size)
+{
+	int ret;
+
+	/*
+	 * If kernel or user changes the size of the ring buffer
+	 * we use the size that was given, and we can forget about
+	 * expanding it later.
+	 */
+	ring_buffer_expanded = 1;
+
+	ret = ring_buffer_resize(global_trace.buffer, size);
+	if (ret < 0)
+		return ret;
+
+	ret = ring_buffer_resize(max_tr.buffer, size);
+	if (ret < 0) {
+		int r;
+
+		r = ring_buffer_resize(global_trace.buffer,
+				       global_trace.entries);
+		if (r < 0) {
+			/*
+			 * AARGH! We are left with different
+			 * size max buffer!!!!
+			 * The max buffer is our "snapshot" buffer.
+			 * When a tracer needs a snapshot (one of the
+			 * latency tracers), it swaps the max buffer
+			 * with the saved snap shot. We succeeded to
+			 * update the size of the main buffer, but failed to
+			 * update the size of the max buffer. But when we tried
+			 * to reset the main buffer to the original size, we
+			 * failed there too. This is very unlikely to
+			 * happen, but if it does, warn and kill all
+			 * tracing.
+			 */
+			WARN_ON(1);
+			tracing_disabled = 1;
+		}
+		return ret;
+	}
+
+	global_trace.entries = size;
+
+	return ret;
+}
+
+/**
+ * tracing_update_buffers - used by tracing facility to expand ring buffers
+ *
+ * To save on memory when the tracing is never used on a system with it
+ * configured in. The ring buffers are set to a minimum size. But once
+ * a user starts to use the tracing facility, then they need to grow
+ * to their default size.
+ *
+ * This function is to be called when a tracer is about to be used.
+ */
+int tracing_update_buffers(void)
+{
+	int ret = 0;
+
+	mutex_lock(&trace_types_lock);
+	if (!ring_buffer_expanded)
+		ret = tracing_resize_ring_buffer(trace_buf_size);
+	mutex_unlock(&trace_types_lock);
+
+	return ret;
+}
+
 struct trace_option_dentry;
 
 static struct trace_option_dentry *
@@ -2331,6 +2490,14 @@ static int tracing_set_tracer(const char *buf)
 	int ret = 0;
 
 	mutex_lock(&trace_types_lock);
+
+	if (!ring_buffer_expanded) {
+		ret = tracing_resize_ring_buffer(trace_buf_size);
+		if (ret < 0)
+			return ret;
+		ret = 0;
+	}
+
 	for (t = trace_types; t; t = t->next) {
 		if (strcmp(t->name, buf) == 0)
 			break;
@@ -2856,10 +3023,18 @@ 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];
+	char buf[96];
 	int r;
 
-	r = sprintf(buf, "%lu\n", tr->entries >> 10);
+	mutex_lock(&trace_types_lock);
+	if (!ring_buffer_expanded)
+		r = sprintf(buf, "%lu (expanded: %lu)\n",
+			    tr->entries >> 10,
+			    trace_buf_size >> 10);
+	else
+		r = sprintf(buf, "%lu\n", tr->entries >> 10);
+	mutex_unlock(&trace_types_lock);
+
 	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
 }
 
@@ -2903,28 +3078,11 @@ tracing_entries_write(struct file *filp, const char __user *ubuf,
 	val <<= 10;
 
 	if (val != global_trace.entries) {
-		ret = ring_buffer_resize(global_trace.buffer, val);
+		ret = tracing_resize_ring_buffer(val);
 		if (ret < 0) {
 			cnt = ret;
 			goto out;
 		}
-
-		ret = ring_buffer_resize(max_tr.buffer, val);
-		if (ret < 0) {
-			int r;
-			cnt = ret;
-			r = ring_buffer_resize(global_trace.buffer,
-					       global_trace.entries);
-			if (r < 0) {
-				/* AARGH! We are left with different
-				 * size max buffer!!!! */
-				WARN_ON(1);
-				tracing_disabled = 1;
-			}
-			goto out;
-		}
-
-		global_trace.entries = val;
 	}
 
 	filp->f_pos += cnt;
@@ -3916,6 +4074,7 @@ void ftrace_dump(void)
 __init static int tracer_alloc_buffers(void)
 {
 	struct trace_array_cpu *data;
+	int ring_buf_size;
 	int i;
 	int ret = -ENOMEM;
 
@@ -3928,12 +4087,18 @@ __init static int tracer_alloc_buffers(void)
 	if (!alloc_cpumask_var(&tracing_reader_cpumask, GFP_KERNEL))
 		goto out_free_tracing_cpumask;
 
+	/* To save memory, keep the ring buffer size to its minimum */
+	if (ring_buffer_expanded)
+		ring_buf_size = trace_buf_size;
+	else
+		ring_buf_size = 1;
+
 	cpumask_copy(tracing_buffer_mask, cpu_possible_mask);
 	cpumask_copy(tracing_cpumask, cpu_all_mask);
 	cpumask_clear(tracing_reader_cpumask);
 
 	/* TODO: make the number of buffers hot pluggable with CPUS */
-	global_trace.buffer = ring_buffer_alloc(trace_buf_size,
+	global_trace.buffer = ring_buffer_alloc(ring_buf_size,
 						   TRACE_BUFFER_FLAGS);
 	if (!global_trace.buffer) {
 		printk(KERN_ERR "tracer: failed to allocate ring buffer!\n");
@@ -3944,7 +4109,7 @@ __init static int tracer_alloc_buffers(void)
 
 
 #ifdef CONFIG_TRACER_MAX_TRACE
-	max_tr.buffer = ring_buffer_alloc(trace_buf_size,
+	max_tr.buffer = ring_buffer_alloc(ring_buf_size,
 					     TRACE_BUFFER_FLAGS);
 	if (!max_tr.buffer) {
 		printk(KERN_ERR "tracer: failed to allocate max ring buffer!\n");

kernel/trace/trace.h

@@ -20,6 +20,7 @@ enum trace_type {
 	TRACE_WAKE,
 	TRACE_STACK,
 	TRACE_PRINT,
+	TRACE_BPRINT,
 	TRACE_SPECIAL,
 	TRACE_MMIO_RW,
 	TRACE_MMIO_MAP,
@@ -117,7 +118,7 @@ struct userstack_entry {
 /*
  * trace_printk entry:
  */
-struct print_entry {
+struct bprint_entry {
 	struct trace_entry	ent;
 	unsigned long		ip;
 	int			depth;
@@ -125,6 +126,13 @@ struct print_entry {
 	u32			buf[];
 };
 
+struct print_entry {
+	struct trace_entry	ent;
+	unsigned long		ip;
+	int			depth;
+	char			buf[];
+};
+
 #define TRACE_OLD_SIZE		88
 
 struct trace_field_cont {
@@ -286,6 +294,7 @@ extern void __ftrace_bad_type(void);
 		IF_ASSIGN(var, ent, struct stack_entry, TRACE_STACK);	\
 		IF_ASSIGN(var, ent, struct userstack_entry, TRACE_USER_STACK);\
 		IF_ASSIGN(var, ent, struct print_entry, TRACE_PRINT);	\
+		IF_ASSIGN(var, ent, struct bprint_entry, TRACE_BPRINT);	\
 		IF_ASSIGN(var, ent, struct special_entry, 0);		\
 		IF_ASSIGN(var, ent, struct trace_mmiotrace_rw,		\
 			  TRACE_MMIO_RW);				\
@@ -570,6 +579,8 @@ extern int trace_selftest_startup_branch(struct tracer *trace,
 extern void *head_page(struct trace_array_cpu *data);
 extern long ns2usecs(cycle_t nsec);
 extern int
+trace_vbprintk(unsigned long ip, int depth, const char *fmt, va_list args);
+extern int
 trace_vprintk(unsigned long ip, int depth, const char *fmt, va_list args);
 
 extern unsigned long trace_flags;
@@ -737,6 +748,9 @@ static inline void trace_branch_disable(void)
 }
 #endif /* CONFIG_BRANCH_TRACER */
 
+/* set ring buffers to default size if not already done so */
+int tracing_update_buffers(void);
+
 /* trace event type bit fields, not numeric */
 enum {
 	TRACE_EVENT_TYPE_PRINTF		= 1,
@@ -759,4 +773,21 @@ 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[];
 
+extern const char *__start___trace_bprintk_fmt[];
+extern const char *__stop___trace_bprintk_fmt[];
+
+#define event_trace_printk(ip, fmt, args...)				\
+do {									\
+	__trace_printk_check_format(fmt, ##args);			\
+	tracing_record_cmdline(current);				\
+	if (__builtin_constant_p(fmt)) {				\
+		static const char *trace_printk_fmt			\
+		  __attribute__((section("__trace_printk_fmt"))) =	\
+			__builtin_constant_p(fmt) ? fmt : NULL;		\
+									\
+		__trace_bprintk(ip, trace_printk_fmt, ##args);		\
+	} else								\
+		__trace_printk(ip, fmt, ##args);			\
+} while (0)
+
 #endif /* _LINUX_KERNEL_TRACE_H */

kernel/trace/trace_event_types.h

@@ -102,7 +102,7 @@ TRACE_EVENT_FORMAT(user_stack, TRACE_USER_STACK, userstack_entry, ignore,
 		 "\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n")
 );
 
-TRACE_EVENT_FORMAT(print, TRACE_PRINT, print_entry, ignore,
+TRACE_EVENT_FORMAT(bprint, TRACE_BPRINT, bprint_entry, ignore,
 	TRACE_STRUCT(
 		TRACE_FIELD(unsigned long, ip, ip)
 		TRACE_FIELD(unsigned int, depth, depth)
@@ -112,6 +112,15 @@ TRACE_EVENT_FORMAT(print, TRACE_PRINT, print_entry, ignore,
 	TP_RAW_FMT("%08lx (%d) fmt:%p %s")
 );
 
+TRACE_EVENT_FORMAT(print, TRACE_PRINT, print_entry, ignore,
+	TRACE_STRUCT(
+		TRACE_FIELD(unsigned long, ip, ip)
+		TRACE_FIELD(unsigned int, depth, depth)
+		TRACE_FIELD_ZERO_CHAR(buf)
+	),
+	TP_RAW_FMT("%08lx (%d) fmt:%p %s")
+);
+
 TRACE_EVENT_FORMAT(branch, TRACE_BRANCH, trace_branch, ignore,
 	TRACE_STRUCT(
 		TRACE_FIELD(unsigned int, line, line)

kernel/trace/trace_events.c

@@ -24,16 +24,6 @@ static DEFINE_MUTEX(event_mutex);
 	     (unsigned long)event < (unsigned long)__stop_ftrace_events; \
 	     event++)
 
-void event_trace_printk(unsigned long ip, const char *fmt, ...)
-{
-	va_list ap;
-
-	va_start(ap, fmt);
-	tracing_record_cmdline(current);
-	trace_vprintk(ip, task_curr_ret_stack(current), fmt, ap);
-	va_end(ap);
-}
-
 static void ftrace_clear_events(void)
 {
 	struct ftrace_event_call *call = (void *)__start_ftrace_events;
@@ -141,6 +131,10 @@ ftrace_event_write(struct file *file, const char __user *ubuf,
 	if (!cnt || cnt < 0)
 		return 0;
 
+	ret = tracing_update_buffers();
+	if (ret < 0)
+		return ret;
+
 	ret = get_user(ch, ubuf++);
 	if (ret)
 		return ret;
@@ -331,6 +325,10 @@ event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
 	if (ret < 0)
 		return ret;
 
+	ret = tracing_update_buffers();
+	if (ret < 0)
+		return ret;
+
 	switch (val) {
 	case 0:
 	case 1:

kernel/trace/trace_events_stage_2.h

@@ -57,7 +57,7 @@ ftrace_raw_output_##call(struct trace_iterator *iter, int flags)	\
 									\
 	field = (typeof(field))entry;					\
 									\
-	ret = trace_seq_printf(s, print);				\
+	ret = trace_seq_printf(s, #call ": " print);			\
 	if (!ret)							\
 		return TRACE_TYPE_PARTIAL_LINE;				\
 									\

kernel/trace/trace_functions_graph.c

@@ -684,7 +684,7 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
 }
 
 static enum print_line_t
-print_graph_comment(struct print_entry *trace, struct trace_seq *s,
+print_graph_comment(struct bprint_entry *trace, struct trace_seq *s,
 		   struct trace_entry *ent, struct trace_iterator *iter)
 {
 	int i;
@@ -781,8 +781,8 @@ print_graph_function(struct trace_iterator *iter)
 		trace_assign_type(field, entry);
 		return print_graph_return(&field->ret, s, entry, iter);
 	}
-	case TRACE_PRINT: {
-		struct print_entry *field;
+	case TRACE_BPRINT: {
+		struct bprint_entry *field;
 		trace_assign_type(field, entry);
 		return print_graph_comment(field, s, entry, iter);
 	}

kernel/trace/trace_mmiotrace.c

@@ -254,6 +254,7 @@ static enum print_line_t mmio_print_mark(struct trace_iterator *iter)
 {
 	struct trace_entry *entry = iter->ent;
 	struct print_entry *print = (struct print_entry *)entry;
+	const char *msg		= print->buf;
 	struct trace_seq *s	= &iter->seq;
 	unsigned long long t	= ns2usecs(iter->ts);
 	unsigned long usec_rem	= do_div(t, USEC_PER_SEC);
@@ -261,11 +262,7 @@ static enum print_line_t mmio_print_mark(struct trace_iterator *iter)
 	int ret;
 
 	/* The trailing newline must be in the message. */
-	ret = trace_seq_printf(s, "MARK %u.%06lu ", secs, usec_rem);
-	if (!ret)
-		return TRACE_TYPE_PARTIAL_LINE;
-
-	ret = trace_seq_bprintf(s, print->fmt, print->buf);
+	ret = trace_seq_printf(s, "MARK %u.%06lu %s", secs, usec_rem, msg);
 	if (!ret)
 		return TRACE_TYPE_PARTIAL_LINE;
 

kernel/trace/trace_output.c

@@ -832,13 +832,13 @@ static struct trace_event trace_user_stack_event = {
 	.binary		= trace_special_bin,
 };
 
-/* TRACE_PRINT */
+/* TRACE_BPRINT */
 static enum print_line_t
-trace_print_print(struct trace_iterator *iter, int flags)
+trace_bprint_print(struct trace_iterator *iter, int flags)
 {
 	struct trace_entry *entry = iter->ent;
 	struct trace_seq *s = &iter->seq;
-	struct print_entry *field;
+	struct bprint_entry *field;
 
 	trace_assign_type(field, entry);
 
@@ -858,9 +858,10 @@ trace_print_print(struct trace_iterator *iter, int flags)
 }
 
 
-static enum print_line_t trace_print_raw(struct trace_iterator *iter, int flags)
+static enum print_line_t
+trace_bprint_raw(struct trace_iterator *iter, int flags)
 {
-	struct print_entry *field;
+	struct bprint_entry *field;
 	struct trace_seq *s = &iter->seq;
 
 	trace_assign_type(field, iter->ent);
@@ -878,12 +879,55 @@ static enum print_line_t trace_print_raw(struct trace_iterator *iter, int flags)
 }
 
 
+static struct trace_event trace_bprint_event = {
+	.type		= TRACE_BPRINT,
+	.trace		= trace_bprint_print,
+	.raw		= trace_bprint_raw,
+};
+
+/* TRACE_PRINT */
+static enum print_line_t trace_print_print(struct trace_iterator *iter,
+					   int flags)
+{
+	struct print_entry *field;
+	struct trace_seq *s = &iter->seq;
+
+	trace_assign_type(field, iter->ent);
+
+	if (!seq_print_ip_sym(s, field->ip, flags))
+		goto partial;
+
+	if (!trace_seq_printf(s, ": %s", field->buf))
+		goto partial;
+
+	return TRACE_TYPE_HANDLED;
+
+ partial:
+	return TRACE_TYPE_PARTIAL_LINE;
+}
+
+static enum print_line_t trace_print_raw(struct trace_iterator *iter, int flags)
+{
+	struct print_entry *field;
+
+	trace_assign_type(field, iter->ent);
+
+	if (!trace_seq_printf(&iter->seq, "# %lx %s", field->ip, field->buf))
+		goto partial;
+
+	return TRACE_TYPE_HANDLED;
+
+ partial:
+	return TRACE_TYPE_PARTIAL_LINE;
+}
+
 static struct trace_event trace_print_event = {
-	.type		= TRACE_PRINT,
+	.type	 	= TRACE_PRINT,
 	.trace		= trace_print_print,
 	.raw		= trace_print_raw,
 };
 
+
 static struct trace_event *events[] __initdata = {
 	&trace_fn_event,
 	&trace_ctx_event,
@@ -891,6 +935,7 @@ static struct trace_event *events[] __initdata = {
 	&trace_special_event,
 	&trace_stack_event,
 	&trace_user_stack_event,
+	&trace_bprint_event,
 	&trace_print_event,
 	NULL
 };

kernel/trace/trace_printk.c

@@ -4,18 +4,19 @@
  * Copyright (C) 2008 Lai Jiangshan <laijs@cn.fujitsu.com>
  *
  */
+#include <linux/seq_file.h>
+#include <linux/debugfs.h>
+#include <linux/uaccess.h>
 #include <linux/kernel.h>
 #include <linux/ftrace.h>
 #include <linux/string.h>
+#include <linux/module.h>
+#include <linux/marker.h>
+#include <linux/mutex.h>
 #include <linux/ctype.h>
 #include <linux/list.h>
-#include <linux/mutex.h>
 #include <linux/slab.h>
-#include <linux/module.h>
-#include <linux/seq_file.h>
 #include <linux/fs.h>
-#include <linux/marker.h>
-#include <linux/uaccess.h>
 
 #include "trace.h"
 
@@ -99,7 +100,7 @@ struct notifier_block module_trace_bprintk_format_nb = {
 	.notifier_call = module_trace_bprintk_format_notify,
 };
 
-int __trace_printk(unsigned long ip, const char *fmt, ...)
+int __trace_bprintk(unsigned long ip, const char *fmt, ...)
  {
 	int ret;
 	va_list ap;
@@ -111,13 +112,13 @@ int __trace_printk(unsigned long ip, const char *fmt, ...)
 		return 0;
 
 	va_start(ap, fmt);
-	ret = trace_vprintk(ip, task_curr_ret_stack(current), fmt, ap);
+	ret = trace_vbprintk(ip, task_curr_ret_stack(current), fmt, ap);
 	va_end(ap);
 	return ret;
 }
-EXPORT_SYMBOL_GPL(__trace_printk);
+EXPORT_SYMBOL_GPL(__trace_bprintk);
 
-int __ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap)
+int __ftrace_vbprintk(unsigned long ip, const char *fmt, va_list ap)
  {
 	if (unlikely(!fmt))
 		return 0;
@@ -125,10 +126,141 @@ int __ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap)
 	if (!(trace_flags & TRACE_ITER_PRINTK))
 		return 0;
 
+	return trace_vbprintk(ip, task_curr_ret_stack(current), fmt, ap);
+}
+EXPORT_SYMBOL_GPL(__ftrace_vbprintk);
+
+int __trace_printk(unsigned long ip, const char *fmt, ...)
+{
+	int ret;
+	va_list ap;
+
+	if (!(trace_flags & TRACE_ITER_PRINTK))
+		return 0;
+
+	va_start(ap, fmt);
+	ret = trace_vprintk(ip, task_curr_ret_stack(current), fmt, ap);
+	va_end(ap);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(__trace_printk);
+
+int __ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap)
+{
+	if (!(trace_flags & TRACE_ITER_PRINTK))
+		return 0;
+
 	return trace_vprintk(ip, task_curr_ret_stack(current), fmt, ap);
 }
 EXPORT_SYMBOL_GPL(__ftrace_vprintk);
 
+static void *
+t_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	const char **fmt = m->private;
+	const char **next = fmt;
+
+	(*pos)++;
+
+	if ((unsigned long)fmt >= (unsigned long)__stop___trace_bprintk_fmt)
+		return NULL;
+
+	next = fmt;
+	m->private = ++next;
+
+	return fmt;
+}
+
+static void *t_start(struct seq_file *m, loff_t *pos)
+{
+	return t_next(m, NULL, pos);
+}
+
+static int t_show(struct seq_file *m, void *v)
+{
+	const char **fmt = v;
+	const char *str = *fmt;
+	int i;
+
+	seq_printf(m, "0x%lx : \"", (unsigned long)fmt);
+
+	/*
+	 * Tabs and new lines need to be converted.
+	 */
+	for (i = 0; str[i]; i++) {
+		switch (str[i]) {
+		case '\n':
+			seq_puts(m, "\\n");
+			break;
+		case '\t':
+			seq_puts(m, "\\t");
+			break;
+		case '\\':
+			seq_puts(m, "\\");
+			break;
+		case '"':
+			seq_puts(m, "\\\"");
+			break;
+		default:
+			seq_putc(m, str[i]);
+		}
+	}
+	seq_puts(m, "\"\n");
+
+	return 0;
+}
+
+static void t_stop(struct seq_file *m, void *p)
+{
+}
+
+static const struct seq_operations show_format_seq_ops = {
+	.start = t_start,
+	.next = t_next,
+	.show = t_show,
+	.stop = t_stop,
+};
+
+static int
+ftrace_formats_open(struct inode *inode, struct file *file)
+{
+	int ret;
+
+	ret = seq_open(file, &show_format_seq_ops);
+	if (!ret) {
+		struct seq_file *m = file->private_data;
+
+		m->private = __start___trace_bprintk_fmt;
+	}
+	return ret;
+}
+
+static const struct file_operations ftrace_formats_fops = {
+	.open = ftrace_formats_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = seq_release,
+};
+
+static __init int init_trace_printk_function_export(void)
+{
+	struct dentry *d_tracer;
+	struct dentry *entry;
+
+	d_tracer = tracing_init_dentry();
+	if (!d_tracer)
+		return 0;
+
+	entry = debugfs_create_file("printk_formats", 0444, d_tracer,
+				    NULL, &ftrace_formats_fops);
+	if (!entry)
+		pr_warning("Could not create debugfs "
+			   "'printk_formats' entry\n");
+
+	return 0;
+}
+
+fs_initcall(init_trace_printk_function_export);
 
 static __init int init_trace_printk(void)
 {

kernel/trace/trace_stack.c

@@ -245,16 +245,31 @@ static int trace_lookup_stack(struct seq_file *m, long i)
 #endif
 }
 
+static void print_disabled(struct seq_file *m)
+{
+	seq_puts(m, "#\n"
+		 "#  Stack tracer disabled\n"
+		 "#\n"
+		 "# To enable the stack tracer, either add 'stacktrace' to the\n"
+		 "# kernel command line\n"
+		 "# or 'echo 1 > /proc/sys/kernel/stack_tracer_enabled'\n"
+		 "#\n");
+}
+
 static int t_show(struct seq_file *m, void *v)
 {
 	long i;
 	int size;
 
 	if (v == SEQ_START_TOKEN) {
-		seq_printf(m, "        Depth   Size      Location"
+		seq_printf(m, "        Depth    Size      Location"
 			   "    (%d entries)\n"
-			   "        -----   ----      --------\n",
+			   "        -----    ----      --------\n",
 			   max_stack_trace.nr_entries);
+
+		if (!stack_tracer_enabled && !max_stack_size)
+			print_disabled(m);
+
 		return 0;
 	}
 

kernel/trace/trace_workqueue.c

@@ -193,12 +193,20 @@ static int workqueue_stat_show(struct seq_file *s, void *p)
 	struct cpu_workqueue_stats *cws = p;
 	unsigned long flags;
 	int cpu = cws->cpu;
-	struct task_struct *tsk = find_task_by_vpid(cws->pid);
-
-	seq_printf(s, "%3d %6d     %6u       %s\n", cws->cpu,
-		   atomic_read(&cws->inserted),
-		   cws->executed,
-		   tsk ? tsk->comm : "<...>");
+	struct pid *pid;
+	struct task_struct *tsk;
+
+	pid = find_get_pid(cws->pid);
+	if (pid) {
+		tsk = get_pid_task(pid, PIDTYPE_PID);
+		if (tsk) {
+			seq_printf(s, "%3d %6d     %6u       %s\n", cws->cpu,
+				   atomic_read(&cws->inserted), cws->executed,
+				   tsk->comm);
+			put_task_struct(tsk);
+		}
+		put_pid(pid);
+	}
 
 	spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags);
 	if (&cws->list == workqueue_cpu_stat(cpu)->list.next)