[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20210517210815.3751286-5-awogbemila@google.com>
Date: Mon, 17 May 2021 14:08:14 -0700
From: David Awogbemila <awogbemila@...gle.com>
To: netdev@...r.kernel.org
Cc: Catherine Sullivan <csully@...gle.com>,
David Awogbemila <awogbemila@...gle.com>,
Willem de Brujin <willemb@...gle.com>
Subject: [PATCH net 4/5] gve: Upgrade memory barrier in poll routine
From: Catherine Sullivan <csully@...gle.com>
As currently written, if the driver checks for more work (via
gve_tx_poll or gve_rx_poll) before the device posts work and the
irq doorbell is not unmasked
(via iowrite32be(GVE_IRQ_ACK | GVE_IRQ_EVENT, ...)) before the device
attempts to raise an interrupt, an interrupt is lost and this could
potentially lead to the traffic being completely halted. For
example, if a tx queue has already been stopped, the driver won't get
the chance to complete work and egress will be halted.
We need a full memory barrier in the poll
routine to ensure that the irq doorbell is unmasked before the driver
checks for more work.
Fixes: f5cedc84a30d ("gve: Add transmit and receive support")
Signed-off-by: Catherine Sullivan <csully@...gle.com>
Signed-off-by: David Awogbemila <awogbemila@...gle.com>
Acked-by: Willem de Brujin <willemb@...gle.com>
---
drivers/net/ethernet/google/gve/gve_main.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c
index 21a5d058dab4..bbc423e93122 100644
--- a/drivers/net/ethernet/google/gve/gve_main.c
+++ b/drivers/net/ethernet/google/gve/gve_main.c
@@ -180,7 +180,7 @@ static int gve_napi_poll(struct napi_struct *napi, int budget)
/* Double check we have no extra work.
* Ensure unmask synchronizes with checking for work.
*/
- dma_rmb();
+ mb();
if (block->tx)
reschedule |= gve_tx_poll(block, -1);
if (block->rx)
--
2.31.1.751.gd2f1c929bd-goog
Powered by blists - more mailing lists