-----Original Message-----
From: Lance Richardson <redacted>
Sent: Thursday, July 8, 2021 9:51 PM
To: Zhang, Qi Z <redacted>
Cc: Joyce Kong <redacted>; Xing, Beilei <redacted>;
ruifeng.wang@arm.com; honnappa.nagarahalli@arm.com; Richardson, Bruce
[off-list ref]; Zhang, Helin [off-list ref];
dev@dpdk.org; stable@dpdk.org; nd@arm.com
Subject: Re: [dpdk-dev] [PATCH v3 2/2] net/i40e: replace SMP barrier with
thread fence

On Thu, Jul 8, 2021 at 8:09 AM Zhang, Qi Z [off-list ref] wrote:

quoted

quoted

-----Original Message-----
From: Joyce Kong <redacted>
Sent: Tuesday, July 6, 2021 2:54 PM
To: Xing, Beilei <redacted>; Zhang, Qi Z

[off-list ref];

quoted

quoted

ruifeng.wang@arm.com; honnappa.nagarahalli@arm.com; Richardson,

Bruce

quoted

quoted

[off-list ref]; Zhang, Helin [off-list ref]
Cc: dev@dpdk.org; stable@dpdk.org; nd@arm.com
Subject: [PATCH v3 2/2] net/i40e: replace SMP barrier with thread fence

Simply replace the SMP barrier with atomic thread fence for i40e hw ring

sacn,

quoted

quoted

if there is no synchronization point.

Signed-off-by: Joyce Kong <redacted>
Reviewed-by: Ruifeng Wang <redacted>
---
 drivers/net/i40e/i40e_rxtx.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/i40e/i40e_rxtx.c b/drivers/net/i40e/i40e_rxtx.c index

9aaabfd92..86e2f083e 100644

--- a/drivers/net/i40e/i40e_rxtx.c
+++ b/drivers/net/i40e/i40e_rxtx.c

@@ -482,7 +482,8 @@ i40e_rx_scan_hw_ring(struct i40e_rx_queue *rxq)

I40E_RXD_QW1_STATUS_SHIFT;

quoted

quoted

              }

-             rte_smp_rmb();
+             /* This barrier is to order loads of different words in the

descriptor */

quoted

quoted

+             rte_atomic_thread_fence(__ATOMIC_ACQUIRE);

Now for x86, you actually replace a compiler barrier with a memory fence,

this may have potential performance impact which need additional resource to
investigate

No memory fence instruction is generated for
__ATOMIC_ACQUIRE on x86 for any version of gcc
or clang that I've tried, based on experiments here:

    https://godbolt.org/z/Yxr1vGhKP

Nice tool!
I try to write some dummy code combined with or without __atomic_thread_fence(__ATOMIC_ACQUIRE)
but I didn't see any difference of the generated assembly code, does that means __atomic_thread_fence(__ATOMIC_ACQUIRE) just does nothing on x86?