perf: Fix perf ring buffer memory ordering

	/*

	 * Control data for the mmap() data buffer.

	 *

	 * User-space reading the @data_head value should issue an rmb(), on

	 * SMP capable platforms, after reading this value -- see

	 * perf_event_wakeup().

	 * User-space reading the @data_head value should issue an smp_rmb(),

	 * after reading this value.

	 *

	 * When the mapping is PROT_WRITE the @data_tail value should be

	 * written by userspace to reflect the last read data. In this case

	 * the kernel will not over-write unread data.

	 * written by userspace to reflect the last read data, after issueing

	 * an smp_mb() to separate the data read from the ->data_tail store.

	 * In this case the kernel will not over-write unread data.

	 *

	 * See perf_output_put_handle() for the data ordering.

	 */

	__u64   data_head;		/* head in the data section */

	__u64	data_tail;		/* user-space written tail */

		goto out;

	/*

	 * Publish the known good head. Rely on the full barrier implied

	 * by atomic_dec_and_test() order the rb->head read and this

	 * write.

	 * Since the mmap() consumer (userspace) can run on a different CPU:

	 *

	 *   kernel				user

	 *

	 *   READ ->data_tail			READ ->data_head

	 *   smp_mb()	(A)			smp_rmb()	(C)

	 *   WRITE $data			READ $data

	 *   smp_wmb()	(B)			smp_mb()	(D)

	 *   STORE ->data_head			WRITE ->data_tail

	 *

	 * Where A pairs with D, and B pairs with C.

	 *

	 * I don't think A needs to be a full barrier because we won't in fact

	 * write data until we see the store from userspace. So we simply don't

	 * issue the data WRITE until we observe it. Be conservative for now.

	 *

	 * OTOH, D needs to be a full barrier since it separates the data READ

	 * from the tail WRITE.

	 *

	 * For B a WMB is sufficient since it separates two WRITEs, and for C

	 * an RMB is sufficient since it separates two READs.

	 *

	 * See perf_output_begin().

	 */

	smp_wmb();

	rb->user_page->data_head = head;

	/*

		 * Userspace could choose to issue a mb() before updating the

		 * tail pointer. So that all reads will be completed before the

		 * write is issued.

		 *

		 * See perf_output_put_handle().

		 */

		tail = ACCESS_ONCE(rb->user_page->data_tail);

		smp_rmb();

		smp_mb();

		offset = head = local_read(&rb->head);

		head += size;

		if (unlikely(!perf_output_space(rb, tail, offset, head)))