Thread (46 messages) 46 messages, 7 authors, 2018-03-23

[PATCH v4 4/6] infiniband: cxgb4: Eliminate duplicate barriers on weakly-ordered archs

From: Steve Wise <hidden>
Date: 2018-03-20 15:38:36
Also in: linux-arm-msm, linux-rdma, lkml

quoted
On Mon, Mar 19, 2018 at 10:47:46PM -0400, Sinan Kaya wrote:
quoted
Code includes wmb() followed by writel(). writel() already has a
barrier
on
quoted
quoted
some architectures like arm64.

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

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

Signed-off-by: Sinan Kaya <redacted>
 drivers/infiniband/hw/cxgb4/t4.h | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)
diff --git a/drivers/infiniband/hw/cxgb4/t4.h
b/drivers/infiniband/hw/cxgb4/t4.h
quoted
index 8369c7c..6e5658a 100644
+++ b/drivers/infiniband/hw/cxgb4/t4.h
@@ -457,7 +457,7 @@ static inline void pio_copy(u64 __iomem *dst,
u64
quoted
*src)
quoted
 	int count = 8;

 	while (count) {
-		writeq(*src, dst);
+		writeq_relaxed(*src, dst);
 		src++;
 		dst++;
 		count--;
This is another case where writes can be re-ordered.. IIRC dst is WC
BAR memory, so the NIC should tolerate re-ordering, but Steve will
have to ack this.
Yes, this is WC BAR memory.  The goal is that pio_copy() will enable
write-
combining this into a single 64B pci-e transaction.

I'd like to see the PPC issue resolved...but

Acked-by: Steve Wise <redacted>
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help