netdev - [PATCH net] qede: Fix Tx timeout due to xmit

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Date:	Tue, 16 Aug 2016 18:40:18 +0300
From:	Yuval Mintz <Yuval.Mintz@...gic.com>
To:	<davem@...emloft.net>, <netdev@...r.kernel.org>
CC:	Yuval Mintz <Yuval.Mintz@...gic.com>
Subject: [PATCH net] qede: Fix Tx timeout due to xmit_more

Driver uses netif_tx_queue_stopped() to make sure the xmit_more
indication will be honored, but that only checks for DRV_XOFF.

At the same time, it's possible that during transmission the DQL will
close the transmission queue with STACK_XOFF indication.
In re-configuration flows, when the threshold is relatively low, it's
possible that the device has no pending tranmissions, and during
tranmission the driver would miss doorbelling the HW.
Since there are no pending transmission, there will never be a Tx
completion [and thus the DQL would not remove the STACK_XOFF indication],
eventually causing the Tx queue to timeout.

While we're at it - also doorbell in case driver has to close the
transmission queue on its own [although this one is less important -
if the ring is full, we're bound to receive completion eventually,
which means the doorbell would only be postponed and not indefinetly
blocked].

Fixes: 312e06761c99 ("qede: Utilize xmit_more")
Signed-off-by: Yuval Mintz <Yuval.Mintz@...gic.com>
---
Hi Dave,

Please consider applying this to 'net'.

Do notice that we have pending patch intended for 'net-next'
("qede: Add support for per-queue stats") that might cause a merge
conflict with this one - although it should be trivial to resolve.

Thanks,
Yuval
---
 drivers/net/ethernet/qlogic/qede/qede_main.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index e4bd02e..a6eb6af 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -722,11 +722,14 @@ netdev_tx_t qede_start_xmit(struct sk_buff *skb,
 	txq->tx_db.data.bd_prod =
 		cpu_to_le16(qed_chain_get_prod_idx(&txq->tx_pbl));

-	if (!skb->xmit_more || netif_tx_queue_stopped(netdev_txq))
+	if (!skb->xmit_more || netif_xmit_stopped(netdev_txq))
 		qede_update_tx_producer(txq);

 	if (unlikely(qed_chain_get_elem_left(&txq->tx_pbl)
 		      < (MAX_SKB_FRAGS + 1))) {
+		if (skb->xmit_more)
+			qede_update_tx_producer(txq);
+
 		netif_tx_stop_queue(netdev_txq);
 		DP_VERBOSE(edev, NETIF_MSG_TX_QUEUED,
 			   "Stop queue was called\n");
-- 
1.9.3