1 files changed, 529 insertions, 164 deletions

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index bd38c5cfd8a..960cbf44c84 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -4,21 +4,92 @@
  * Copyright (C) 2008 Steven Rostedt <srostedt@redhat.com>
  */
 #include <linux/ring_buffer.h>
+#include <linux/trace_clock.h>
+#include <linux/ftrace_irq.h>
 #include <linux/spinlock.h>
 #include <linux/debugfs.h>
 #include <linux/uaccess.h>
+#include <linux/hardirq.h>
 #include <linux/module.h>
 #include <linux/percpu.h>
 #include <linux/mutex.h>
-#include <linux/sched.h>        /* used for sched_clock() (for now) */
 #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
  * prevents all ring buffers from being recorded to.
@@ -57,7 +128,9 @@ enum {
         RB_BUFFERS_DISABLED     = 1 << RB_BUFFERS_DISABLED_BIT,
 };
 
-static long ring_buffer_flags __read_mostly = RB_BUFFERS_ON;
+static unsigned long ring_buffer_flags __read_mostly = RB_BUFFERS_ON;
+
+#define BUF_PAGE_HDR_SIZE offsetof(struct buffer_data_page, data)
 
 /**
  * tracing_on - enable all tracing buffers
@@ -89,59 +162,92 @@ EXPORT_SYMBOL_GPL(tracing_off);
  * tracing_off_permanent - permanently disable ring buffers
  *
  * This function, once called, will disable all ring buffers
- * permanenty.
+ * permanently.
  */
 void tracing_off_permanent(void)
 {
         set_bit(RB_BUFFERS_DISABLED_BIT, &ring_buffer_flags);
 }
 
+/**
+ * tracing_is_on - show state of ring buffers enabled
+ */
+int tracing_is_on(void)
+{
+        return ring_buffer_flags == RB_BUFFERS_ON;
+}
+EXPORT_SYMBOL_GPL(tracing_is_on);
+
 #include "trace.h"
 
-/* Up this if you want to test the TIME_EXTENTS and normalization */
-#define DEBUG_SHIFT 0
+#define RB_EVNT_HDR_SIZE (offsetof(struct ring_buffer_event, array))
+#define RB_ALIGNMENT            4U
+#define RB_MAX_SMALL_DATA       28
+
+enum {
+        RB_LEN_TIME_EXTEND = 8,
+        RB_LEN_TIME_STAMP = 16,
+};
 
-/* FIXME!!! */
-u64 ring_buffer_time_stamp(int cpu)
+static inline int rb_null_event(struct ring_buffer_event *event)
 {
-        u64 time;
+        return event->type == RINGBUF_TYPE_PADDING && event->time_delta == 0;
+}
 
-        preempt_disable_notrace();
-        /* shift to debug/test normalization and TIME_EXTENTS */
-        time = sched_clock() << DEBUG_SHIFT;
-        preempt_enable_no_resched_notrace();
+static inline int rb_discarded_event(struct ring_buffer_event *event)
+{
+        return event->type == RINGBUF_TYPE_PADDING && event->time_delta;
+}
 
-        return time;
+static void rb_event_set_padding(struct ring_buffer_event *event)
+{
+        event->type = RINGBUF_TYPE_PADDING;
+        event->time_delta = 0;
 }
-EXPORT_SYMBOL_GPL(ring_buffer_time_stamp);
 
-void ring_buffer_normalize_time_stamp(int cpu, u64 *ts)
+/**
+ * ring_buffer_event_discard - discard an event in the ring buffer
+ * @buffer: the ring buffer
+ * @event: the event to discard
+ *
+ * Sometimes a event that is in the ring buffer needs to be ignored.
+ * This function lets the user discard an event in the ring buffer
+ * and then that event will not be read later.
+ *
+ * Note, it is up to the user to be careful with this, and protect
+ * against races. If the user discards an event that has been consumed
+ * it is possible that it could corrupt the ring buffer.
+ */
+void ring_buffer_event_discard(struct ring_buffer_event *event)
 {
-        /* Just stupid testing the normalize function and deltas */
-        *ts >>= DEBUG_SHIFT;
+        event->type = RINGBUF_TYPE_PADDING;
+        /* time delta must be non zero */
+        if (!event->time_delta)
+                event->time_delta = 1;
 }
-EXPORT_SYMBOL_GPL(ring_buffer_normalize_time_stamp);
 
-#define RB_EVNT_HDR_SIZE (sizeof(struct ring_buffer_event))
+static unsigned