1 files changed, 76 insertions, 30 deletions

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 3c7834c24e54..13950d9027cb 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -3,8 +3,10 @@
  *
  * Copyright (C) 2008 Steven Rostedt <srostedt@redhat.com>
  */
+#include <linux/ftrace_event.h>
 #include <linux/ring_buffer.h>
 #include <linux/trace_clock.h>
+#include <linux/trace_seq.h>
 #include <linux/spinlock.h>
 #include <linux/debugfs.h>
 #include <linux/uaccess.h>
@@ -21,7 +23,6 @@
 #include <linux/fs.h>
 
 #include <asm/local.h>
-#include "trace.h"
 
 static void update_pages_handler(struct work_struct *work);
 
@@ -1397,6 +1398,8 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer)
 		struct list_head *head_page_with_bit;
 
 		head_page = &rb_set_head_page(cpu_buffer)->list;
+		if (!head_page)
+			break;
 		prev_page = head_page->prev;
 
 		first_page = pages->next;
@@ -2430,41 +2433,76 @@ rb_reserve_next_event(struct ring_buffer *buffer,
 
 #ifdef CONFIG_TRACING
 
-#define TRACE_RECURSIVE_DEPTH 16
+/*
+ * The lock and unlock are done within a preempt disable section.
+ * The current_context per_cpu variable can only be modified
+ * by the current task between lock and unlock. But it can
+ * be modified more than once via an interrupt. To pass this
+ * information from the lock to the unlock without having to
+ * access the 'in_interrupt()' functions again (which do show
+ * a bit of overhead in something as critical as function tracing,
+ * we use a bitmask trick.
+ *
+ *  bit 0 =  NMI context
+ *  bit 1 =  IRQ context
+ *  bit 2 =  SoftIRQ context
+ *  bit 3 =  normal context.
+ *
+ * This works because this is the order of contexts that can
+ * preempt other contexts. A SoftIRQ never preempts an IRQ
+ * context.
+ *
+ * When the context is determined, the corresponding bit is
+ * checked and set (if it was set, then a recursion of that context
+ * happened).
+ *
+ * On unlock, we need to clear this bit. To do so, just subtract
+ * 1 from the current_context and AND it to itself.
+ *
+ * (binary)
+ *  101 - 1 = 100
+ *  101 & 100 = 100 (clearing bit zero)
+ *
+ *  1010 - 1 = 1001
+ *  1010 & 1001 = 1000 (clearing bit 1)
+ *
+ * The least significant bit can be cleared this way, and it
+ * just so happens that it is the same bit corresponding to
+ * the current context.
+ */
+static DEFINE_PER_CPU(unsigned int, current_context);
 
-/* Keep this code out of the fast path cache */
-static noinline void trace_recursive_fail(void)
+static __always_inline int trace_recursive_lock(void)
 {
-	/* Disable all tracing before we do anything else */
-	tracing_off_permanent();
-
-	printk_once(KERN_WARNING "Tracing recursion: depth[%ld]:"
-		    "HC[%lu]:SC[%lu]:NMI[%lu]\n",
-		    trace_recursion_buffer(),
-		    hardirq_count() >> HARDIRQ_SHIFT,
-		    softirq_count() >> SOFTIRQ_SHIFT,
-		    in_nmi());
-
-	WARN_ON_ONCE(1);
-}
+	unsigned int val = this_cpu_read(current_context);
+	int bit;
 
-static inline int trace_recursive_lock(void)
-{
-	trace_recursion_inc();
+	if (in_interrupt()) {
+		if (in_nmi())
+			bit = 0;
+		else if (in_irq())
+			bit = 1;
+		else
+			bit = 2;
+	} else
+		bit = 3;
 
-	if (likely(trace_recursion_buffer() < TRACE_RECURSIVE_DEPTH))
-		return 0;
+	if (unlikely(val & (1 << bit)))
+		return 1;
 
-	trace_recursive_fail();
+	val |= (1 << bit);
+	this_cpu_write(current_context, val);
 
-	return -1;
+	return 0;
 }
 
-static inline void trace_recursive_unlock(void)
+static __always_inline void trace_recursive_unlock(void)
 {
-	WARN_ON_ONCE(!trace_recursion_buffer());
+	unsigned int val = this_cpu_read(current_context);
 
-	trace_recursion_dec();
+	val--;
+	val &= this_cpu_read(current_context);
+	this_cpu_write(current_context, val);
 }
 
 #else
@@ -2937,7 +2975,7 @@ u64 ring_buffer_oldest_event_ts(struct ring_buffer *buffer, int cpu)
 	unsigned long flags;
 	struct ring_buffer_per_cpu *cpu_buffer;
 	struct buffer_page *bpage;
-	u64 ret;
+	u64 ret = 0;
 
 	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		return 0;
@@ -2952,7 +2990,8 @@ u64 ring_buffer_oldest_event_ts(struct ring_buffer *buffer, int cpu)
 		bpage = cpu_buffer->reader_page;
 	else
 		bpage = rb_set_head_page(cpu_buffer);
-	ret = bpage->page->time_stamp;
+	if (bpage)
+		ret = bpage->page->time_stamp;
 	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
 	return ret;
@@ -3288,6 +3327,8 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 	 * Splice the empty reader page into the list around the head.
 	 */
 	reader = rb_set_head_page(cpu_buffer);
+	if (!reader)
+		goto out;
 	cpu_buffer->reader_page->list.next = rb_list_head(reader->list.next);
 	cpu_buffer->reader_page->list.prev = reader->list.prev;
 
@@ -3420,7 +3461,7 @@ static void rb_advance_iter(struct ring_buffer_iter *iter)
 	/* check for end of page padding */
 	if ((iter->head >= rb_page_size(iter->head_page)) &&
 	    (iter->head_page != cpu_buffer->commit_page))
-		rb_advance_iter(iter);
+		rb_inc_iter(iter);
 }
 
 static int rb_lost_events(struct ring_buffer_per_cpu *cpu_buffer)
@@ -3806,12 +3847,17 @@ void
 ring_buffer_read_finish(struct ring_buffer_iter *iter)
 {
 	struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
+	unsigned long flags;
 
 	/*
 	 * Ring buffer is disabled from recording, here's a good place
-	 * to check the integrity of the ring buffer. 
+	 * to check the integrity of the ring buffer.
+	 * Must prevent readers from trying to read, as the check
+	 * clears the HEAD page and readers require it.
 	 */
+	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
 	rb_check_pages(cpu_buffer);
+	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
 	atomic_dec(&cpu_buffer->record_disabled);
 	atomic_dec(&cpu_buffer->buffer->resize_disabled);