[dpdk-dev] [PATCH] igb_uio: revert open and release operations

Thomas Monjalon thomas at monjalon.net
Fri Oct 13 23:11:54 CEST 2017


13/10/2017 23:05, Ferruh Yigit:
> On 10/13/2017 3:51 PM, Thomas Monjalon wrote:
> > Some VF drivers cannot work with igb_uio because of the
> > reset done in these functions.
> > 
> > First bug report:
> > 	http://dpdk.org/ml/archives/dev/2017-September/075236.html
> > 
> > A partial reset was tried:
> > 	http://dpdk.org/patch/28940
> > 
> > Second bug report after a partial revert trial:
> > 	http://dpdk.org/ml/archives/dev/2017-September/076998.html
> > 
> > The patch author agreed to revert his patch:
> > 	http://dpdk.org/ml/archives/dev/2017-October/077158.html
> > 
> > There are also some patches available to fix issues with i40e:
> > 	http://dpdk.org/patch/30021
> > 	http://dpdk.org/patch/30022
> > 
> > This patch takes the simple option of reverting the initial patch
> > and gives more time to properly improve igb_uio and PMDs.
> > 
> > Fixes: b58eedfc7dd5 ("igb_uio: issue FLR during open and release of device file")
> > 
> > Reported-by: Qiming Yang <qiming.yang at intel.com>
> > Reported-by: Jingjing Wu <jingjing.wu at intel.com>
> > Signed-off-by: Thomas Monjalon <thomas at monjalon.net>
> 
> Hi Thomas,
> 
> I put already some comment into other fix patch [1].
> 
> Mainly taking into account of current time for release, this patch make
> sense, but I suggest giving a chance to the fix mentioned above.
> 
> Because the original patch is for safer igb_uio, and fixing a few times
> reported issue.
> 
> Since this is rc1, we have time for testing, and many parties will be
> doing tests. Lets get the fix for rc1, and if we find any issue revert
> the patch?

OK, please check it works for every VF drivers.
There was an issue reported with bnxt.




More information about the dev mailing list