[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <Y2JqX3vC1mG/JDex@ziepe.ca>
Date: Wed, 2 Nov 2022 10:02:23 -0300
From: Jason Gunthorpe <jgg@...pe.ca>
To: Steven Rostedt <rostedt@...dmis.org>
Cc: Leonid Ravich <leonid.ravich@...anetworks.com>,
"linux-trace-kernel@...r.kernel.org"
<IMCEAMAILTO-linux-trace-kernel+40vger+2Ekernel+2Eorg@...prd02.prod.outlook.com>,
"mingo@...hat.com" <mingo@...hat.com>,
"linux-rdma@...r.kernel.org" <linux-rdma@...r.kernel.org>,
"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
Yigal Korman <yigal.korman@...anetworks.com>
Subject: Re: BUG: ib_mad ftrace event unsupported migration
On Wed, Nov 02, 2022 at 07:44:57AM -0400, Steven Rostedt wrote:
> > before starting throwing some patch into the the air I would like to align with you the approach we should take here.
> >
> > my suggestion here :
> > - ftrace infra should verify no migration happen (end and start happens on same CPU) in case not we will throw warning for the issue .
>
> The scheduler should have. On entering the ring buffer code
> ring_buffer_lock_reserver() it disables preemption and does not
> re-enable it until ring_buffer_unlock_commit().
>
> The only way to migrate is if you re-enable preemption. WHICH IS A
> BUG!
So what on earth did that?
I'm guessing some driver's query_pkey op, but AFAIK we don't have any
explicit pre-emption reenablements in the code - unless it is sneaky..
Leonid what driver are you testing?
Jason
Powered by blists - more mailing lists