patches for DPDK stable branches
 help / color / Atom feed
* [dpdk-stable] [PATCH] net/ice: fix unexpected link down
@ 2019-10-29  5:16 Qi Zhang
  2019-10-29  5:35 ` [dpdk-stable] [dpdk-dev] " Ye Xiaolong
  0 siblings, 1 reply; 3+ messages in thread
From: Qi Zhang @ 2019-10-29  5:16 UTC (permalink / raw)
  To: Qiming.Yang; +Cc: dev, Qi Zhang, stable

Not to turn down link during dev_stop, it will cause the device
can't be bind by kernel driver after DPDK driver quit.

Fixes: e6161345d8a9 ("net/ice: support link status change")
Cc: stable@dpdk.org

Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
---
 drivers/net/ice/ice_ethdev.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/ice/ice_ethdev.c b/drivers/net/ice/ice_ethdev.c
index d74675842..ae6eba63e 100644
--- a/drivers/net/ice/ice_ethdev.c
+++ b/drivers/net/ice/ice_ethdev.c
@@ -2277,8 +2277,6 @@ ice_dev_stop(struct rte_eth_dev *dev)
 	/* Clear all queues and release mbufs */
 	ice_clear_queues(dev);
 
-	ice_dev_set_link_down(dev);
-
 	/* Clean datapath event and queue/vec mapping */
 	rte_intr_efd_disable(intr_handle);
 	if (intr_handle->intr_vec) {
-- 
2.13.6


^ permalink raw reply	[flat|nested] 3+ messages in thread

* Re: [dpdk-stable] [dpdk-dev] [PATCH] net/ice: fix unexpected link down
  2019-10-29  5:16 [dpdk-stable] [PATCH] net/ice: fix unexpected link down Qi Zhang
@ 2019-10-29  5:35 ` " Ye Xiaolong
  2019-10-31 21:52   ` Stillwell Jr, Paul M
  0 siblings, 1 reply; 3+ messages in thread
From: Ye Xiaolong @ 2019-10-29  5:35 UTC (permalink / raw)
  To: Qi Zhang; +Cc: Qiming.Yang, dev, stable

Hi, Qi

On 10/29, Qi Zhang wrote:
>Not to turn down link during dev_stop, it will cause the device
>can't be bind by kernel driver after DPDK driver quit.
>
>Fixes: e6161345d8a9 ("net/ice: support link status change")
>Cc: stable@dpdk.org
>
>Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
>---
> drivers/net/ice/ice_ethdev.c | 2 --
> 1 file changed, 2 deletions(-)
>
>diff --git a/drivers/net/ice/ice_ethdev.c b/drivers/net/ice/ice_ethdev.c
>index d74675842..ae6eba63e 100644
>--- a/drivers/net/ice/ice_ethdev.c
>+++ b/drivers/net/ice/ice_ethdev.c
>@@ -2277,8 +2277,6 @@ ice_dev_stop(struct rte_eth_dev *dev)
> 	/* Clear all queues and release mbufs */
> 	ice_clear_queues(dev);
> 
>-	ice_dev_set_link_down(dev);
>-

Is this ice specific issue? Calling set_link_down seems correct thing to do in stop
ops, as we can see in other PMDs like i40e, mvneta, ... 

Thanks,
Xiaolong


> 	/* Clean datapath event and queue/vec mapping */
> 	rte_intr_efd_disable(intr_handle);
> 	if (intr_handle->intr_vec) {
>-- 
>2.13.6
>

^ permalink raw reply	[flat|nested] 3+ messages in thread

* Re: [dpdk-stable] [dpdk-dev] [PATCH] net/ice: fix unexpected link down
  2019-10-29  5:35 ` [dpdk-stable] [dpdk-dev] " Ye Xiaolong
@ 2019-10-31 21:52   ` Stillwell Jr, Paul M
  0 siblings, 0 replies; 3+ messages in thread
From: Stillwell Jr, Paul M @ 2019-10-31 21:52 UTC (permalink / raw)
  To: Ye, Xiaolong, Zhang, Qi Z; +Cc: Yang, Qiming, dev, stable

Hi Xiaolong,

> -----Original Message-----
> From: dev <dev-bounces@dpdk.org> On Behalf Of Ye Xiaolong
> Sent: Monday, October 28, 2019 10:35 PM
> To: Zhang, Qi Z <qi.z.zhang@intel.com>
> Cc: Yang, Qiming <qiming.yang@intel.com>; dev@dpdk.org;
> stable@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH] net/ice: fix unexpected link down
> 
> Hi, Qi
> 
> On 10/29, Qi Zhang wrote:
> >Not to turn down link during dev_stop, it will cause the device can't
> >be bind by kernel driver after DPDK driver quit.
> >
> >Fixes: e6161345d8a9 ("net/ice: support link status change")
> >Cc: stable@dpdk.org
> >
> >Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
> >---
> > drivers/net/ice/ice_ethdev.c | 2 --
> > 1 file changed, 2 deletions(-)
> >
> >diff --git a/drivers/net/ice/ice_ethdev.c
> >b/drivers/net/ice/ice_ethdev.c index d74675842..ae6eba63e 100644
> >--- a/drivers/net/ice/ice_ethdev.c
> >+++ b/drivers/net/ice/ice_ethdev.c
> >@@ -2277,8 +2277,6 @@ ice_dev_stop(struct rte_eth_dev *dev)
> > 	/* Clear all queues and release mbufs */
> > 	ice_clear_queues(dev);
> >
> >-	ice_dev_set_link_down(dev);
> >-
> 
> Is this ice specific issue? Calling set_link_down seems correct thing to do in
> stop ops, as we can see in other PMDs like i40e, mvneta, ...
> 

Technically, this issue also existed in i40e. The i40e kernel driver added a workaround to fix this when the DPDK driver would force the link down when it closed. The FW handles the link status and the driver shouldn't mess with it unless the user indicates they want it in some other state. I think the best idea is to return the link state into whatever the link state was when DPDK started (probably up) instead of setting it to down when the PMD exits.

> Thanks,
> Xiaolong
> 
> 
> > 	/* Clean datapath event and queue/vec mapping */
> > 	rte_intr_efd_disable(intr_handle);
> > 	if (intr_handle->intr_vec) {
> >--
> >2.13.6
> >

^ permalink raw reply	[flat|nested] 3+ messages in thread

end of thread, back to index

Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2019-10-29  5:16 [dpdk-stable] [PATCH] net/ice: fix unexpected link down Qi Zhang
2019-10-29  5:35 ` [dpdk-stable] [dpdk-dev] " Ye Xiaolong
2019-10-31 21:52   ` Stillwell Jr, Paul M

patches for DPDK stable branches

Archives are clonable:
	git clone --mirror http://inbox.dpdk.org/stable/0 stable/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 stable stable/ http://inbox.dpdk.org/stable \
		stable@dpdk.org
	public-inbox-index stable


Newsgroup available over NNTP:
	nntp://inbox.dpdk.org/inbox.dpdk.stable


AGPL code for this site: git clone https://public-inbox.org/ public-inbox