IB/ipath: Performance optimization for CPU differences

Different processors have different ordering restrictions for write
combining.  By taking advantage of this, we can eliminate some write
barriers when writing to the send buffers.

Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

1 files changed, 12 insertions, 10 deletions

diff --git a/drivers/infiniband/hw/ipath/ipath_diag.c b/drivers/infiniband/hw/ipath/ipath_diag.c
index cf25cdab02f9..4137c7770f1b 100644
--- a/drivers/infiniband/hw/ipath/ipath_diag.c
+++ b/drivers/infiniband/hw/ipath/ipath_diag.c
@@ -446,19 +446,21 @@ static ssize_t ipath_diagpkt_write(struct file *fp,
 			   dd->ipath_unit, plen - 1, pbufn);
 
 	if (dp.pbc_wd == 0)
-		/* Legacy operation, use computed pbc_wd */
 		dp.pbc_wd = plen;
-
-	/* we have to flush after the PBC for correctness on some cpus
-	 * or WC buffer can be written out of order */
 	writeq(dp.pbc_wd, piobuf);
-	ipath_flush_wc();
-	/* copy all by the trigger word, then flush, so it's written
+	/*
+	 * Copy all by the trigger word, then flush, so it's written
 	 * to chip before trigger word, then write trigger word, then
-	 * flush again, so packet is sent. */
-	__iowrite32_copy(piobuf + 2, tmpbuf, clen - 1);
-	ipath_flush_wc();
-	__raw_writel(tmpbuf[clen - 1], piobuf + clen + 1);
+	 * flush again, so packet is sent.
+	 */
+	if (dd->ipath_flags & IPATH_PIO_FLUSH_WC) {
+		ipath_flush_wc();
+		__iowrite32_copy(piobuf + 2, tmpbuf, clen - 1);
+		ipath_flush_wc();
+		__raw_writel(tmpbuf[clen - 1], piobuf + clen + 1);
+	} else
+		__iowrite32_copy(piobuf + 2, tmpbuf, clen);
+
 	ipath_flush_wc();
 
 	ret = sizeof(dp);