s390/qdio: fine-tune SLSB update

xchg() for a single-byte location assembles to a 4-byte Compare&Swap,
wrapped into a non-trivial amount of retry code that deals with
concurrent modifications to the unaffected bytes.

Change it to a simple byte-store, but preserve the memory ordering
semantics that the CS provided.
This simplifies the generated code for a hot path, and in theory also
allows us to amortize the memory barriers over multiple SLSB updates.

CC: Andreas Krebbel <krebbel@linux.ibm.com>
Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>

diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c
index 610c05f595890746a900fc0a4318fd4b7f1655f7..bb137f962c3f90f9f2a315ce4be90cf8c045559b 100644 (file)
--- a/drivers/s390/cio/qdio_main.c
+++ b/drivers/s390/cio/qdio_main.c
@@ -254,10 +254,17 @@ static inline int set_buf_states(struct qdio_q *q, int bufnr,
        if (is_qebsm(q))
                return qdio_do_sqbs(q, state, bufnr, count);
 
+       /* Ensure that all preceding changes to the SBALs are visible: */
+       mb();
+
        for (i = 0; i < count; i++) {
-               xchg(&q->slsb.val[bufnr], state);
+               WRITE_ONCE(q->slsb.val[bufnr], state);
                bufnr = next_buf(bufnr);
        }
+
+       /* Make our SLSB changes visible: */
+       mb();
+
        return count;
 }