public inbox for netdev@vger.kernel.org 
 help / color / mirror / Atom feed
From: Stephen Hemminger <stephen@networkplumber•org>
To: kys@microsoft•com, haiyangz@microsoft•com, sthemmin@microsoft•com
Cc: devel@linuxdriverproject•org, netdev@vger•kernel.org
Subject: [PATCH net 5/9] hv_netvsc: fix race in napi poll when rescheduling
Date: Thu,  1 Mar 2018 10:27:52 -0800	[thread overview]
Message-ID: <20180301182756.23027-6-sthemmin@microsoft.com> (raw)
In-Reply-To: <20180301182756.23027-1-sthemmin@microsoft.com>

There is a race between napi_reschedule and re-enabling interrupts
which could lead to missed host interrrupts.  This occurs when
interrupts are re-enabled (hv_end_read) and vmbus irq callback
(netvsc_channel_cb) has already scheduled NAPI.

Signed-off-by: Stephen Hemminger <sthemmin@microsoft•com>
---
 drivers/net/hyperv/netvsc.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index ff97a85b2e9d..4237cedc4f08 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -1207,9 +1207,10 @@ int netvsc_poll(struct napi_struct *napi, int budget)
 	if (send_recv_completions(ndev, net_device, nvchan) == 0 &&
 	    work_done < budget &&
 	    napi_complete_done(napi, work_done) &&
-	    hv_end_read(&channel->inbound)) {
+	    hv_end_read(&channel->inbound) &&
+	    napi_schedule_prep(napi)) {
 		hv_begin_read(&channel->inbound);
-		napi_reschedule(napi);
+		__napi_schedule(napi);
 	}
 
 	/* Driver may overshoot since multiple packets per descriptor */
-- 
2.16.1

  parent reply	other threads:[~2018-03-01 18:27 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-03-01 18:27 [PATCH net 0/9] hv_netvsc: minor bug fixes Stephen Hemminger
2018-03-01 18:27 ` [PATCH net 1/9] hv_netvsc: avoid retry on send during shutdown Stephen Hemminger
2018-03-01 18:27 ` [PATCH net 2/9] hv_netvsc: only wake transmit queue if link is up Stephen Hemminger
2018-03-01 18:27 ` [PATCH net 3/9] hv_netvsc: fix error unwind handling if vmbus_open fails Stephen Hemminger
2018-03-01 18:27 ` [PATCH net 4/9] hv_netvsc: cancel subchannel setup before halting device Stephen Hemminger
2018-03-01 18:27 ` Stephen Hemminger [this message]
2018-03-01 18:27 ` [PATCH net 6/9] hv_netvsc: use napi_schedule_irqoff Stephen Hemminger
2018-03-01 18:27 ` [PATCH net 7/9] hv_netvsc: don't need full irqsave for request_lock Stephen Hemminger
2018-03-01 18:27 ` [PATCH net 8/9] hv_netvsc: propagate rx filters to VF Stephen Hemminger
2018-03-01 21:56   ` Jakub Kicinski
2018-03-01 23:46   ` Stephen Hemminger
2018-03-01 18:27 ` [PATCH net 9/9] hv_netvsc: defer queue selection " Stephen Hemminger

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20180301182756.23027-6-sthemmin@microsoft.com \
    --to=stephen@networkplumber$(echo .)org \
    --cc=devel@linuxdriverproject$(echo .)org \
    --cc=haiyangz@microsoft$(echo .)com \
    --cc=kys@microsoft$(echo .)com \
    --cc=netdev@vger$(echo .)kernel.org \
    --cc=sthemmin@microsoft$(echo .)com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox