lkml.org 
[lkml]   [2019]   [Aug]   [5]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [PATCH v2 6/6] firmware: arm_scmi: Check if platform has released shmem before using
On Mon, Aug 05, 2019 at 02:33:53PM +0200, Etienne Carriere wrote:
> Hello Sudeep,
>
> On Fri, 26 Jul 2019 at 15:46, Sudeep Holla <sudeep.holla@arm.com> wrote:
> >
> > Sometimes platfom may take too long to respond to the command and OS
> > might timeout before platform transfer the ownership of the shared
> > memory region to the OS with the response.
> >
> > Since the mailbox channel associated with the channel is freed and new
> > commands are dispatch on the same channel, OS needs to wait until it
> > gets back the ownership. If not, either OS may end up overwriting the
> > platform response for the last command(which is fine as OS timed out
> > that command) or platform might overwrite the payload for the next
> > command with the response for the old.
> >
> > The latter is problematic as platform may end up interpretting the
> > response as the payload. In order to avoid such race, let's wait until
> > the OS gets back the ownership before we prepare the shared memory with
> > the payload for the next command.
> >
> > Reported-by: Jim Quinlan <james.quinlan@broadcom.com>
> > Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
> > ---
> > drivers/firmware/arm_scmi/driver.c | 8 ++++++++
> > 1 file changed, 8 insertions(+)
> >
> > diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c
> > index 69bf85fea967..765573756987 100644
> > --- a/drivers/firmware/arm_scmi/driver.c
> > +++ b/drivers/firmware/arm_scmi/driver.c
> > @@ -265,6 +265,14 @@ static void scmi_tx_prepare(struct mbox_client *cl, void *m)
> > struct scmi_chan_info *cinfo = client_to_scmi_chan_info(cl);
> > struct scmi_shared_mem __iomem *mem = cinfo->payload;
> >
> > + /*
> > + * Ideally channel must be free by now unless OS timeout last
> > + * request and platform continued to process the same, wait
> > + * until it releases the shared memory, otherwise we may endup
> > + * overwriting it's response with new command payload or vice-versa
>
> minor typo: s/it's/its/
> maybe also s/command/message/
>

Thanks for taking a look at this, both are fixed locally now.

--
Regards,
Sudeep

\
 
 \ /
  Last update: 2019-08-05 14:53    [W:0.032 / U:3.364 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site