+
+struct spu_buffer spu_buff[MAX_NUMNODES * SPUS_PER_NODE];
+struct delayed_work spu_work;
+static unsigned max_spu_buff;
+
+static void spu_buff_add(unsigned long int value, int spu)
+{
+ /* spu buff is a circular buffer. Add entries to the
+ * head. Head is the index to store the next value.
+ * The buffer is full when there is one available entry
+ * in the queue, i.e. head and tail can't be equal.
+ * That way we can tell the difference between the
+ * buffer being full versus empty.
+ *
+ * ASSUPTION: the buffer_lock is held when this function
+ * is called to lock the buffer, head and tail.
+ */
+ int full = 1;
+
+ if (spu_buff[spu].head >= spu_buff[spu].tail) {
+ if ((spu_buff[spu].head - spu_buff[spu].tail)
+ < (max_spu_buff - 1))
+ full = 0;
+
+ } else if (spu_buff[spu].tail > spu_buff[spu].head) {
+ if ((spu_buff[spu].tail - spu_buff[spu].head)
+ > 1)
+ full = 0;
+ }
+
+ if (!full) {
+ spu_buff[spu].buff[spu_buff[spu].head] = value;
+ spu_buff[spu].head++;
+
+ if (spu_buff[spu].head >= max_spu_buff)
+ spu_buff[spu].head = 0;
+ } else {
+ /* From the user's perspective make the SPU buffer
+ * size management/overflow look like we are using
+ * per cpu buffers. The user uses the same
+ * per cpu parameter to adjust the SPU buffer size.
+ * Increment the sample_lost_overflow to inform
+ * the user the buffer size needs to be increased.
+ */
+ oprofile_cpu_buffer_inc_smpl_lost();
+ }
+}
+
+/* This function copies the per SPU buffers to the
+ * OProfile kernel buffer.
+ */
+void sync_spu_buff(void)
+{
+ int spu;
+ unsigned long flags;
+ int curr_head;
+
+ for (spu = 0; spu < num_spu_nodes; spu++) {
+ /* In case there was an issue and the buffer didn't
+ * get created skip it.
+ */
+ if (spu_buff[spu].buff == NULL)
+ continue;
+
+ /* Hold the lock to make sure the head/tail
+ * doesn't change while spu_buff_add() is
+ * deciding if the buffer is full or not.
+ * Being a little paranoid.
+ */
+ spin_lock_irqsave(&buffer_lock, flags);
+ curr_head = spu_buff[spu].head;
+ spin_unlock_irqrestore(&buffer_lock, flags);
+
+ /* Transfer the current contents to the kernel buffer.
+ * data can still be added to the head of the buffer.
+ */
+ oprofile_put_buff(spu_buff[spu].buff,
+ spu_buff[spu].tail,
+ curr_head, max_spu_buff);
+
+ spin_lock_irqsave(&buffer_lock, flags);
+ spu_buff[spu].tail = curr_head;
+ spin_unlock_irqrestore(&buffer_lock, flags);
+ }
+
+}
+
+static void wq_sync_spu_buff(struct work_struct *work)
+{
+ /* move data from spu buffers to kernel buffer */
+ sync_spu_buff();
+
+ /* only reschedule if profiling is not done */
+ if (spu_prof_running)
+ schedule_delayed_work(&spu_work, DEFAULT_TIMER_EXPIRE);
+}