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

2 files changed, 78 insertions, 41 deletions

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index ed35599..589b3ee 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -620,12 +620,6 @@ static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer)
 	kfree(cpu_buffer);
 }
 
-/*
- * Causes compile errors if the struct buffer_page gets bigger
- * than the struct page.
- */
-extern int ring_buffer_page_too_big(void);
-
 #ifdef CONFIG_HOTPLUG_CPU
 static int rb_cpu_notify(struct notifier_block *self,
 			 unsigned long action, void *hcpu);
@@ -648,11 +642,6 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
 	int bsize;
 	int cpu;
 
-	/* Paranoid! Optimizes out when all is well */
-	if (sizeof(struct buffer_page) > sizeof(struct page))
-		ring_buffer_page_too_big();
-
-
 	/* keep it in its own cache line */
 	buffer = kzalloc(ALIGN(sizeof(*buffer), cache_line_size()),
 			 GFP_KERNEL);
@@ -668,8 +657,8 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
 	buffer->reader_lock_key = key;
 
 	/* need at least two pages */
-	if (buffer->pages == 1)
-		buffer->pages++;
+	if (buffer->pages < 2)
+		buffer->pages = 2;
 
 	/*
 	 * In case of non-hotplug cpu, if the ring-buffer is allocated
@@ -1013,7 +1002,7 @@ rb_event_index(struct ring_buffer_event *event)
 {
 	unsigned long addr = (unsigned long)event;
 
-	return (addr & ~PAGE_MASK) - (PAGE_SIZE - BUF_PAGE_SIZE);
+	return (addr & ~PAGE_MASK) - BUF_PAGE_HDR_SIZE;
 }
 
 static inline int
@@ -1334,9 +1323,6 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 
 	/* We reserved something on the buffer */
 
-	if (RB_WARN_ON(cpu_buffer, write > BUF_PAGE_SIZE))
-		return NULL;
-
 	event = __rb_page_index(tail_page, tail);
 	rb_update_event(event, type, length);
 
@@ -2480,6 +2466,21 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 }
 EXPORT_SYMBOL_GPL(ring_buffer_iter_peek);
 
+static inline int rb_ok_to_lock(void)
+{
+	/*
+	 * If an NMI die dumps out the content of the ring buffer
+	 * do not grab locks. We also permanently disable the ring
+	 * buffer too. A one time deal is all you get from reading
+	 * the ring buffer from an NMI.
+	 */
+	if (likely(!in_nmi() && !oops_in_progress))
+		return 1;
+
+	tracing_off_permanent();
+	return 0;
+}
+
 /**
  * ring_buffer_peek - peek at the next event to be read
  * @buffer: The ring buffer to read
@@ -2495,14 +2496,20 @@ ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
 	struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
 	struct ring_buffer_event *event;
 	unsigned long flags;
+	int dolock;
 
 	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		return NULL;
 
+	dolock = rb_ok_to_lock();
  again:
-	spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+	local_irq_save(flags);
+	if (dolock)
+		spin_lock(&cpu_buffer->reader_lock);
 	event = rb_buffer_peek(buffer, cpu, ts);
-	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+	if (dolock)
+		spin_unlock(&cpu_buffer->reader_lock);
+	local_irq_restore(flags);
 
 	if (event && event->type_len == RINGBUF_TYPE_PADDING) {
 		cpu_relax();
@@ -2554,6 +2561,9 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
 	struct ring_buffer_per_cpu *cpu_buffer;
 	struct ring_buffer_event *event = NULL;
 	unsigned long flags;
+	int dolock;
+
+	dolock = rb_ok_to_lock();
 
  again:
 	/* might be called in atomic */
@@ -2563,7 +2573,9 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
 		goto out;
 
 	cpu_buffer = buffer->buffers[cpu];
-	spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+	local_irq_save(flags);
+	if (dolock)
+		spin_lock(&cpu_buffer->reader_lock);
 
 	event = rb_buffer_peek(buffer, cpu, ts);
 	if (!event)
@@ -2572,7 +2584,9 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
 	rb_advance_reader(cpu_buffer);
 
  out_unlock:
-	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+	if (dolock)
+		spin_unlock(&cpu_buffer->reader_lock);
+	local_irq_restore(flags);
 
  out:
 	preempt_enable();
@@ -2770,12 +2784,25 @@ EXPORT_SYMBOL_GPL(ring_buffer_reset);
 int ring_buffer_empty(struct ring_buffer *buffer)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
+	unsigned long flags;
+	int dolock;
 	int cpu;
+	int ret;
+
+	dolock = rb_ok_to_lock();
 
 	/* yes this is racy, but if you don't like the race, lock the buffer */
 	for_each_buffer_cpu(buffer, cpu) {
 		cpu_buffer = buffer->buffers[cpu];
-		if (!rb_per_cpu_empty(cpu_buffer))
+		local_irq_save(flags);
+		if (dolock)
+			spin_lock(&cpu_buffer->reader_lock);
+		ret = rb_per_cpu_empty(cpu_buffer);
+		if (dolock)
+			spin_unlock(&cpu_buffer->reader_lock);
+		local_irq_restore(flags);
+
+		if (!ret)
 			return 0;
 	}
 
@@ -2791,14 +2818,23 @@ EXPORT_SYMBOL_GPL(ring_buffer_empty);
 int ring_buffer_empty_cpu(struct ring_buffer *buffer, int cpu)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
+	unsigned long flags;
+	int dolock;
 	int ret;
 
 	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		return 1;
 
+	dolock = rb_ok_to_lock();
+
 	cpu_buffer = buffer->buffers[cpu];
+	local_irq_save(flags);
+	if (dolock)
+		spin_lock(&cpu_buffer->reader_lock);
 	ret = rb_per_cpu_empty(cpu_buffer);
-
+	if (dolock)
+		spin_unlock(&cpu_buffer->reader_lock);
+	local_irq_restore(flags);
 
 	return ret;
 }
diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c
index cf6b0f5..573d3cc 100644
--- a/kernel/trace/ring_buffer_benchmark.c
+++ b/kernel/trace/ring_buffer_benchmark.c
@@ -203,7 +203,7 @@ static void ring_buffer_producer(void)
 	 * Hammer the buffer for 10 secs (this may
 	 * make the system stall)
 	 */
-	pr_info("Starting ring buffer hammer\n");
+	trace_printk("Starting ring buffer hammer\n");
 	do_gettimeofday(&start_tv);
 	do {
 		struct ring_buffer_event *event;
@@ -239,7 +239,7 @@ static void ring_buffer_producer(void)
 #endif
 
 	} while (end_tv.tv_sec < (start_tv.tv_sec + RUN_TIME) && !kill_test);
-	pr_info("End ring buffer hammer\n");
+	trace_printk("End ring buffer hammer\n");
 
 	if (consumer) {
 		/* Init both completions here to avoid races */
@@ -262,49 +262,50 @@ static void ring_buffer_producer(void)
 	overruns = ring_buffer_overruns(buffer);
 
 	if (kill_test)
-		pr_info("ERROR!\n");
-	pr_info("Time:     %lld (usecs)\n", time);
-	pr_info("Overruns: %lld\n", overruns);
+		trace_printk("ERROR!\n");
+	trace_printk("Time:     %lld (usecs)\n", time);
+	trace_printk("Overruns: %lld\n", overruns);
 	if (disable_reader)
-		pr_info("Read:     (reader disabled)\n");
+		trace_printk("Read:     (reader disabled)\n");
 	else
-		pr_info("Read:     %ld  (by %s)\n", read,
+		trace_printk("Read:     %ld  (by %s)\n", read,
 			read_events ? "events" : "pages");
-	pr_info("Entries:  %lld\n", entries);
-	pr_info("Total:    %lld\n", entries + overruns + read);
-	pr_info("Missed:   %ld\n", missed);
-	pr_info("Hit:      %ld\n", hit);
+	trace_printk("Entries:  %lld\n", entries);
+	trace_printk("Total:    %lld\n", entries + overruns + read);
+	trace_printk("Missed:   %ld\n", missed);
+	trace_printk("Hit:      %ld\n", hit);
 
 	/* Convert time from usecs to millisecs */
 	do_div(time, USEC_PER_MSEC);
 	if (time)
 		hit /= (long)time;
 	else
-		pr_info("TIME IS ZERO??\n");
+		trace_printk("TIME IS ZERO??\n");
 
-	pr_info("Entries per millisec: %ld\n", hit);
+	trace_printk("Entries per millisec: %ld\n", hit);
 
 	if (hit) {
 		/* Calculate the average time in nanosecs */
 		avg = NSEC_PER_MSEC / hit;
-		pr_info("%ld ns per entry\n", avg);
+		trace_printk("%ld ns per entry\n", avg);
 	}
 
 	if (missed) {
 		if (time)
 			missed /= (long)time;
 
-		pr_info("Total iterations per millisec: %ld\n", hit + missed);
+		trace_printk("Total iterations per millisec: %ld\n",
+			     hit + missed);
 
 		/* it is possible that hit + missed will overflow and be zero */
 		if (!(hit + missed)) {
-			pr_info("hit + missed overflowed and totalled zero!\n");
+			trace_printk("hit + missed overflowed and totalled zero!\n");
 			hit--; /* make it non zero */
 		}
 
 		/* Caculate the average time in nanosecs */
 		avg = NSEC_PER_MSEC / (hit + missed);
-		pr_info("%ld ns per entry\n", avg);
+		trace_printk("%ld ns per entry\n", avg);
 	}
 }
 
@@ -355,7 +356,7 @@ static int ring_buffer_producer_thread(void *arg)
 
 		ring_buffer_producer();
 
-		pr_info("Sleeping for 10 secs\n");
+		trace_printk("Sleeping for 10 secs\n");
 		set_current_state(TASK_INTERRUPTIBLE);
 		schedule_timeout(HZ * SLEEP_TIME);
 		__set_current_state(TASK_RUNNING);