ring-buffer: convert cpu buffer entries to local_t

The entries counter in cpu buffer is not atomic. It can be updated by
other interrupts or from another CPU (readers).

But making entries into "atomic_t" causes an atomic operation that can
hurt performance. Instead we convert it to a local_t that will increment
a counter with a local CPU atomic operation (if the arch supports it).

Instead of fighting with readers and overwrites that decrement the counter,
I added a "read" counter. Every time a reader reads an entry it is
incremented.

We already have a overrun counter and with that, the entries counter and
the read counter, we can calculate the total number of entries in the
buffer with:

  (entries - overrun) - read

As long as the total number of entries in the ring buffer is less than
the word size, this will work. But since the entries counter was previously
a long, this is no different than what we had before.

Thanks to Andrew Morton for pointing out in the first version that
atomic_t does not replace unsigned long. I switched to atomic_long_t
even though it is signed. A negative count is most likely a bug.

[ Impact: keep accurate count of cpu buffer entries ]

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 26e1359..c792ea8 100644 (file)
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -405,7 +405,8 @@ struct ring_buffer_per_cpu {
        unsigned long                   nmi_dropped;
        unsigned long                   commit_overrun;
        unsigned long                   overrun;
-       unsigned long                   entries;
+       unsigned long                   read;
+       local_t                         entries;
        u64                             write_stamp;
        u64                             read_stamp;
        atomic_t                        record_disabled;
@@ -997,7 +998,6 @@ static void rb_update_overflow(struct ring_buffer_per_cpu *cpu_buffer)
                if (event->type_len > RINGBUF_TYPE_DATA_TYPE_LEN_MAX)
                        continue;
                cpu_buffer->overrun++;
-               cpu_buffer->entries--;
        }
 }
 
@@ -1588,7 +1588,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_lock_reserve);
 static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer,
                      struct ring_buffer_event *event)
 {
-       cpu_buffer->entries++;
+       local_inc(&cpu_buffer->entries);
 
        /* Only process further if we own the commit */
        if (!rb_is_commit(cpu_buffer, event))
@@ -1722,7 +1722,7 @@ void ring_buffer_discard_commit(struct ring_buffer *buffer,
         * The commit is still visible by the reader, so we
         * must increment entries.
         */
-       cpu_buffer->entries++;
+       local_inc(&cpu_buffer->entries);
  out:
        /*
         * If a write came in and pushed the tail page
@@ -1902,7 +1902,8 @@ unsigned long ring_buffer_entries_cpu(struct ring_buffer *buffer, int cpu)
                return 0;
 
        cpu_buffer = buffer->buffers[cpu];
-       ret = cpu_buffer->entries;
+       ret = (local_read(&cpu_buffer->entries) - cpu_buffer->overrun)
+               - cpu_buffer->read;
 
        return ret;
 }
@@ -1985,7 +1986,8 @@ unsigned long ring_buffer_entries(struct ring_buffer *buffer)
        /* if you care about this being correct, lock the buffer */
        for_each_buffer_cpu(buffer, cpu) {
                cpu_buffer = buffer->buffers[cpu];
-               entries += cpu_buffer->entries;
+               entries += (local_read(&cpu_buffer->entries) -
+                           cpu_buffer->overrun) - cpu_buffer->read;
        }
 
        return entries;
@@ -2225,7 +2227,7 @@ static void rb_advance_reader(struct ring_buffer_per_cpu *cpu_buffer)
 
        if (event->type_len <= RINGBUF_TYPE_DATA_TYPE_LEN_MAX
                        || rb_discarded_event(event))
-               cpu_buffer->entries--;
+               cpu_buffer->read++;
 
        rb_update_read_stamp(cpu_buffer, event);
 
@@ -2642,7 +2644,8 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
        cpu_buffer->nmi_dropped = 0;
        cpu_buffer->commit_overrun = 0;
        cpu_buffer->overrun = 0;
-       cpu_buffer->entries = 0;
+       cpu_buffer->read = 0;
+       local_set(&cpu_buffer->entries, 0);
 
        cpu_buffer->write_stamp = 0;
        cpu_buffer->read_stamp = 0;
@@ -2813,7 +2816,7 @@ static void rb_remove_entries(struct ring_buffer_per_cpu *cpu_buffer,
                /* Only count data entries */
                if (event->type_len > RINGBUF_TYPE_DATA_TYPE_LEN_MAX)
                        continue;
-               cpu_buffer->entries--;
+               cpu_buffer->read++;
        }
        __raw_spin_unlock(&cpu_buffer->lock);
 }