Re: [PATCH V7 6/7] remoteproc: imx_rproc: request mbox channel later

[Mathieu Poirier]

On Mon, Oct 17, 2022 at 03:13:16AM +0000, Peng Fan wrote:
> Hi Mathieu,
> 
> > Subject: Re: [PATCH V7 6/7] remoteproc: imx_rproc: request mbox channel
> > later
> > 
> > On Fri, Oct 14, 2022 at 11:10:36AM +0800, Peng Fan (OSS) wrote:
> > > From: Peng Fan <peng.fan@xxxxxxx>
> > >
> > > It is possible that when remote processor crash, the communication
> > > channel will be broken with garbage value in mailbox, such as when
> > > Linux is issuing a message through mailbox, remote processor crashes,
> > > we need free & rebuild the mailbox channels to make sure no garbage
> > > value in mailbox channels.
> > >
> > > So move the request/free to start/stop for managing remote procesosr
> > > in Linux, move to attach/detach for remote processor is out of control
> > > of Linux.
> > >
> > > Previous, we just request mbox when attach for CM4 boot early before
> > > Linux, but if mbox defer probe, remoteproc core will do resource
> > > cleanup and corrupt resource table for later probe.
> > >
> > > So move request mbox ealier and still keep mbox request when attach
> > > for self recovery case, but keep a check when request/free mbox.
> > >
> > > Signed-off-by: Peng Fan <peng.fan@xxxxxxx>
> > > ---
> > >  drivers/remoteproc/imx_rproc.c | 39
> > > ++++++++++++++++++++++++++++++++--
> > >  1 file changed, 37 insertions(+), 2 deletions(-)
> > >
> > > diff --git a/drivers/remoteproc/imx_rproc.c
> > > b/drivers/remoteproc/imx_rproc.c index 917e6db39572..1183de84a4c0
> > > 100644
> > > --- a/drivers/remoteproc/imx_rproc.c
> > > +++ b/drivers/remoteproc/imx_rproc.c
> > > @@ -84,6 +84,8 @@ struct imx_rproc_mem {
> > >  #define ATT_CORE_MASK   0xffff
> > >  #define ATT_CORE(I)     BIT((I))
> > >
> > > +static int imx_rproc_xtr_mbox_init(struct rproc *rproc); static void
> > > +imx_rproc_free_mbox(struct rproc *rproc);
> > >  static int imx_rproc_detach_pd(struct rproc *rproc);
> > >
> > >  struct imx_rproc {
> > > @@ -357,6 +359,10 @@ static int imx_rproc_start(struct rproc *rproc)
> > >  	struct arm_smccc_res res;
> > >  	int ret;
> > >
> > > +	ret = imx_rproc_xtr_mbox_init(rproc);
> > > +	if (ret)
> > > +		return ret;
> > > +
> > >  	switch (dcfg->method) {
> > >  	case IMX_RPROC_MMIO:
> > >  		ret = regmap_update_bits(priv->regmap, dcfg->src_reg,
> > > dcfg->src_mask, @@ -407,6 +413,8 @@ static int imx_rproc_stop(struct
> > > rproc *rproc)
> > >
> > >  	if (ret)
> > >  		dev_err(dev, "Failed to stop remote core\n");
> > > +	else
> > > +		imx_rproc_free_mbox(rproc);
> > >
> > >  	return ret;
> > >  }
> > > @@ -592,6 +600,22 @@ static void imx_rproc_kick(struct rproc *rproc,
> > > int vqid)
> > >
> > >  static int imx_rproc_attach(struct rproc *rproc)  {
> > > +	return imx_rproc_xtr_mbox_init(rproc); }
> > > +
> > > +static int imx_rproc_detach(struct rproc *rproc) {
> > > +	struct imx_rproc *priv = rproc->priv;
> > > +	const struct imx_rproc_dcfg *dcfg = priv->dcfg;
> > > +
> > > +	if (dcfg->method != IMX_RPROC_SCU_API)
> > > +		return -EOPNOTSUPP;
> > > +
> > > +	if (imx_sc_rm_is_resource_owned(priv->ipc_handle, priv->rsrc_id))
> > > +		return -EOPNOTSUPP;
> > > +
> > > +	imx_rproc_free_mbox(rproc);
> > > +
> > >  	return 0;
> > >  }
> > >
> > > @@ -610,6 +634,7 @@ static struct resource_table
> > > *imx_rproc_get_loaded_rsc_table(struct rproc *rproc  static const struct
> > rproc_ops imx_rproc_ops = {
> > >  	.prepare	= imx_rproc_prepare,
> > >  	.attach		= imx_rproc_attach,
> > > +	.detach		= imx_rproc_detach,
> > >  	.start		= imx_rproc_start,
> > >  	.stop		= imx_rproc_stop,
> > >  	.kick		= imx_rproc_kick,
> > > @@ -720,6 +745,9 @@ static int imx_rproc_xtr_mbox_init(struct rproc
> > *rproc)
> > >  	struct device *dev = priv->dev;
> > >  	struct mbox_client *cl;
> > >
> > > +	if (priv->tx_ch && priv->rx_ch)
> > > +		return 0;
> > > +
> > 
> > You did exactly the same things as in V6.  I asked you why this is needed and
> > all you did is point me to the code in _probe(), which I can read on my own.
> > 
> 
> Sorry for not wrote down clear.
> 
> > Again - why is this needed when we know it will be done in start() and
> > attach()?
> 
> start() and attach() not able to handle mbox defer probe. So I add

We are finally at the heart of the problem.  I had to go look at the
implementation of imx_rproc_xtr_mbox_init() to understand that it can return
-EPROBE_DEFER.  Had there been a comment in the code to highlight _why_ the if()
condition is needed, I would have understood right away and all this waste of
time avoided.

> the mbox requesting in probe to handle mbox defer probe, and add
> a check when requesting mbox channel in start/attach. During first
> time attach/start remote core, the imx_rproc_xtr_mbox_init just
> return, because channel requested in probe flow. 
> 
> Since mbox requested in probe, why still add it in start() and attach()?
> It is to support runtime stop and start(M4 is under control of Linux),
> to support runtime detach(only for i.MX8QM/QXP attach recovery,
> m4 out of control from linux) and attach.
> 
> Thanks,
> Peng.
> > 
> > 
> > >  	if (!of_get_property(dev->of_node, "mbox-names", NULL))
> > >  		return 0;
> > >
> > > @@ -749,8 +777,15 @@ static void imx_rproc_free_mbox(struct rproc
> > > *rproc)  {
> > >  	struct imx_rproc *priv = rproc->priv;
> > >
> > > -	mbox_free_channel(priv->tx_ch);
> > > -	mbox_free_channel(priv->rx_ch);
> > > +	if (priv->tx_ch) {
> > > +		mbox_free_channel(priv->tx_ch);
> > > +		priv->tx_ch = NULL;
> > > +	}
> > > +
> > > +	if (priv->rx_ch) {
> > > +		mbox_free_channel(priv->rx_ch);
> > > +		priv->rx_ch = NULL;
> > > +	}
> > >  }
> > >
> > >  static void imx_rproc_put_scu(struct rproc *rproc)
> > > --
> > > 2.37.1
> > >