[PATCH v6 7/7] ixgbevf: eliminate duplicate barriers on weakly-ordered archs

[Sinan Kaya]

Code includes wmb() followed by writel() in multiple places. writel()
already has a barrier on some architectures like arm64.

This ends up CPU observing two barriers back to back before executing the
register write.

Since code already has an explicit barrier call, changing writel() to
writel_relaxed().

Signed-off-by: Sinan Kaya <okaya at codeaurora.org>
---
 drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 21 ++++++++++++++++++---
 1 file changed, 18 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 815cb1a..9e684b1 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -725,7 +725,12 @@ static void ixgbevf_alloc_rx_buffers(struct ixgbevf_ring *rx_ring,
 		 * such as IA-64).
 		 */
 		wmb();
-		writel(i, rx_ring->tail);
+		writel_relaxed(i, rx_ring->tail);
+
+		/* We need this if more than one processor can write to our tail
+		 * at a time, it synchronizes IO on IA64/Altix systems
+		 */
+		mmiowb();
 	}
 }
 
@@ -1232,7 +1237,12 @@ static int ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector,
 		 * know there are new descriptors to fetch.
 		 */
 		wmb();
-		writel(xdp_ring->next_to_use, xdp_ring->tail);
+		writel_relaxed(xdp_ring->next_to_use, xdp_ring->tail);
+
+		/* We need this if more than one processor can write to our tail
+		 * at a time, it synchronizes IO on IA64/Altix systems
+		 */
+		mmiowb();
 	}
 
 	u64_stats_update_begin(&rx_ring->syncp);
@@ -4004,7 +4014,12 @@ static void ixgbevf_tx_map(struct ixgbevf_ring *tx_ring,
 	tx_ring->next_to_use = i;
 
 	/* notify HW of packet */
-	writel(i, tx_ring->tail);
+	writel_relaxed(i, tx_ring->tail);
+
+	/* We need this if more than one processor can write to our tail
+	 * at a time, it synchronizes IO on IA64/Altix systems
+	 */
+	mmiowb();
 
 	return;
 dma_error:
-- 
2.7.4