Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6

[linux-2.6-omap-h63xx.git] / kernel / trace / ring_buffer.c

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 94af1fe56bb4ef2dec0610a6a4c50e61a65979ec..3f338063864628a3ae42f0269018388062132a1a 100644 (file)
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -130,7 +130,7 @@ struct buffer_page {
 static inline void free_buffer_page(struct buffer_page *bpage)
 {
        if (bpage->page)
-               __free_page(bpage->page);
+               free_page((unsigned long)bpage->page);
        kfree(bpage);
 }
 
@@ -966,7 +966,9 @@ rb_add_time_stamp(struct ring_buffer_per_cpu *cpu_buffer,
        if (unlikely(*delta > (1ULL << 59) && !once++)) {
                printk(KERN_WARNING "Delta way too big! %llu"
                       " ts=%llu write stamp = %llu\n",
-                      *delta, *ts, cpu_buffer->write_stamp);
+                      (unsigned long long)*delta,
+                      (unsigned long long)*ts,
+                      (unsigned long long)cpu_buffer->write_stamp);
                WARN_ON(1);
        }
 
@@ -1020,8 +1022,23 @@ rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer,
        struct ring_buffer_event *event;
        u64 ts, delta;
        int commit = 0;
+       int nr_loops = 0;
 
  again:
+       /*
+        * We allow for interrupts to reenter here and do a trace.
+        * If one does, it will cause this original code to loop
+        * back here. Even with heavy interrupts happening, this
+        * should only happen a few times in a row. If this happens
+        * 1000 times in a row, there must be either an interrupt
+        * storm or we have something buggy.
+        * Bail!
+        */
+       if (unlikely(++nr_loops > 1000)) {
+               RB_WARN_ON(cpu_buffer, 1);
+               return NULL;
+       }
+
        ts = ring_buffer_time_stamp(cpu_buffer->cpu);
 
        /*
@@ -1530,10 +1547,23 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 {
        struct buffer_page *reader = NULL;
        unsigned long flags;
+       int nr_loops = 0;
 
        spin_lock_irqsave(&cpu_buffer->lock, flags);
 
  again:
+       /*
+        * This should normally only loop twice. But because the
+        * start of the reader inserts an empty page, it causes
+        * a case where we will loop three times. There should be no
+        * reason to loop four times (that I know of).
+        */
+       if (unlikely(++nr_loops > 3)) {
+               RB_WARN_ON(cpu_buffer, 1);
+               reader = NULL;
+               goto out;
+       }
+
        reader = cpu_buffer->reader_page;
 
        /* If there's more to read, return this page */
@@ -1663,6 +1693,7 @@ ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
        struct ring_buffer_per_cpu *cpu_buffer;
        struct ring_buffer_event *event;
        struct buffer_page *reader;
+       int nr_loops = 0;
 
        if (!cpu_isset(cpu, buffer->cpumask))
                return NULL;
@@ -1670,6 +1701,19 @@ ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
        cpu_buffer = buffer->buffers[cpu];
 
  again:
+       /*
+        * We repeat when a timestamp is encountered. It is possible
+        * to get multiple timestamps from an interrupt entering just
+        * as one timestamp is about to be written. The max times
+        * that this can happen is the number of nested interrupts we
+        * can have.  Nesting 10 deep of interrupts is clearly
+        * an anomaly.
+        */
+       if (unlikely(++nr_loops > 10)) {
+               RB_WARN_ON(cpu_buffer, 1);
+               return NULL;
+       }
+
        reader = rb_get_reader_page(cpu_buffer);
        if (!reader)
                return NULL;
@@ -1720,6 +1764,7 @@ ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
        struct ring_buffer *buffer;
        struct ring_buffer_per_cpu *cpu_buffer;
        struct ring_buffer_event *event;
+       int nr_loops = 0;
 
        if (ring_buffer_iter_empty(iter))
                return NULL;
@@ -1728,6 +1773,19 @@ ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
        buffer = cpu_buffer->buffer;
 
  again:
+       /*
+        * We repeat when a timestamp is encountered. It is possible
+        * to get multiple timestamps from an interrupt entering just
+        * as one timestamp is about to be written. The max times
+        * that this can happen is the number of nested interrupts we
+        * can have. Nesting 10 deep of interrupts is clearly
+        * an anomaly.
+        */
+       if (unlikely(++nr_loops > 10)) {
+               RB_WARN_ON(cpu_buffer, 1);
+               return NULL;
+       }
+
        if (rb_per_cpu_empty(cpu_buffer))
                return NULL;