| Message ID | 20220323034405.976643-3-peng.fan@oss.nxp.com (mailing list archive) |
|---|---|
| State | Superseded |
| Headers | show |
| Series | remoteproc: support self recovery | expand |
On Wed, Mar 23, 2022 at 11:44:05AM +0800, Peng Fan (OSS) wrote: > From: Peng Fan <peng.fan@nxp.com> > > Current logic only support main processor to stop/start the remote > processor after rproc crash. However to SoC, such as i.MX8QM/QXP, the > remote processor could do attach recovery after crash and trigger watchdog > reboot. It does not need main processor to load image, or stop/start M4 > core. > > Introduce two functions: rproc_attach_recovery, rproc_firmware_recovery > for the two cases. Firmware recovery is as before, let main processor to > help recovery, while attach recovery is recover itself withou help. > To attach recovery, we only do detach and attach. > > Signed-off-by: Peng Fan <peng.fan@nxp.com> > --- > drivers/remoteproc/remoteproc_core.c | 67 ++++++++++++++++++++-------- > 1 file changed, 48 insertions(+), 19 deletions(-) > > diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c > index c510125769b9..ad04515750ef 100644 > --- a/drivers/remoteproc/remoteproc_core.c > +++ b/drivers/remoteproc/remoteproc_core.c > @@ -1887,6 +1887,50 @@ static int __rproc_detach(struct rproc *rproc) > return 0; > } > > +static int rproc_attach_recovery(struct rproc *rproc) > +{ > + int ret; > + > + mutex_unlock(&rproc->lock); > + ret = rproc_detach(rproc); > + mutex_lock(&rproc->lock); > + if (ret) > + return ret; > + > + if (atomic_inc_return(&rproc->power) > 1) > + return 0; > + > + return rproc_attach(rproc); The correct functions to call here are __rproc_detach() and __rproc_attach() - they are similar to rproc_stop() and rproc_start() without the parts related to the firmware image. And you should not be dealing with rproc->power at this stage, which leaves the remote processor's state machine in the same way as the start/stop scenario. That being said, now that we actually count how many instances are requesting the remote processor to be powered, we might have a problem with rproc->power when the system is recovered after a crash. But we can address that when we get there. Thanks, Mathieu > +} > + > +static int rproc_firmware_recovery(struct rproc *rproc) > +{ > + const struct firmware *firmware_p; > + struct device *dev = &rproc->dev; > + int ret; > + > + ret = rproc_stop(rproc, true); > + if (ret) > + return ret; > + > + /* generate coredump */ > + rproc->ops->coredump(rproc); > + > + /* load firmware */ > + ret = request_firmware(&firmware_p, rproc->firmware, dev); > + if (ret < 0) { > + dev_err(dev, "request_firmware failed: %d\n", ret); > + return ret; > + } > + > + /* boot the remote processor up again */ > + ret = rproc_start(rproc, firmware_p); > + > + release_firmware(firmware_p); > + > + return ret; > +} > + > /** > * rproc_trigger_recovery() - recover a remoteproc > * @rproc: the remote processor > @@ -1901,7 +1945,6 @@ static int __rproc_detach(struct rproc *rproc) > */ > int rproc_trigger_recovery(struct rproc *rproc) > { > - const struct firmware *firmware_p; > struct device *dev = &rproc->dev; > int ret; > > @@ -1915,24 +1958,10 @@ int rproc_trigger_recovery(struct rproc *rproc) > > dev_err(dev, "recovering %s\n", rproc->name); > > - ret = rproc_stop(rproc, true); > - if (ret) > - goto unlock_mutex; > - > - /* generate coredump */ > - rproc->ops->coredump(rproc); > - > - /* load firmware */ > - ret = request_firmware(&firmware_p, rproc->firmware, dev); > - if (ret < 0) { > - dev_err(dev, "request_firmware failed: %d\n", ret); > - goto unlock_mutex; > - } > - > - /* boot the remote processor up again */ > - ret = rproc_start(rproc, firmware_p); > - > - release_firmware(firmware_p); > + if (rproc_has_feature(rproc, RPROC_FEAT_ATTACH_RECOVERY)) > + ret = rproc_attach_recovery(rproc); > + else > + ret = rproc_firmware_recovery(rproc); > > unlock_mutex: > mutex_unlock(&rproc->lock); > -- > 2.25.1 >
diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c index c510125769b9..ad04515750ef 100644 --- a/drivers/remoteproc/remoteproc_core.c +++ b/drivers/remoteproc/remoteproc_core.c @@ -1887,6 +1887,50 @@ static int __rproc_detach(struct rproc *rproc) return 0; } +static int rproc_attach_recovery(struct rproc *rproc) +{ + int ret; + + mutex_unlock(&rproc->lock); + ret = rproc_detach(rproc); + mutex_lock(&rproc->lock); + if (ret) + return ret; + + if (atomic_inc_return(&rproc->power) > 1) + return 0; + + return rproc_attach(rproc); +} + +static int rproc_firmware_recovery(struct rproc *rproc) +{ + const struct firmware *firmware_p; + struct device *dev = &rproc->dev; + int ret; + + ret = rproc_stop(rproc, true); + if (ret) + return ret; + + /* generate coredump */ + rproc->ops->coredump(rproc); + + /* load firmware */ + ret = request_firmware(&firmware_p, rproc->firmware, dev); + if (ret < 0) { + dev_err(dev, "request_firmware failed: %d\n", ret); + return ret; + } + + /* boot the remote processor up again */ + ret = rproc_start(rproc, firmware_p); + + release_firmware(firmware_p); + + return ret; +} + /** * rproc_trigger_recovery() - recover a remoteproc * @rproc: the remote processor @@ -1901,7 +1945,6 @@ static int __rproc_detach(struct rproc *rproc) */ int rproc_trigger_recovery(struct rproc *rproc) { - const struct firmware *firmware_p; struct device *dev = &rproc->dev; int ret; @@ -1915,24 +1958,10 @@ int rproc_trigger_recovery(struct rproc *rproc) dev_err(dev, "recovering %s\n", rproc->name); - ret = rproc_stop(rproc, true); - if (ret) - goto unlock_mutex; - - /* generate coredump */ - rproc->ops->coredump(rproc); - - /* load firmware */ - ret = request_firmware(&firmware_p, rproc->firmware, dev); - if (ret < 0) { - dev_err(dev, "request_firmware failed: %d\n", ret); - goto unlock_mutex; - } - - /* boot the remote processor up again */ - ret = rproc_start(rproc, firmware_p); - - release_firmware(firmware_p); + if (rproc_has_feature(rproc, RPROC_FEAT_ATTACH_RECOVERY)) + ret = rproc_attach_recovery(rproc); + else + ret = rproc_firmware_recovery(rproc); unlock_mutex: mutex_unlock(&rproc->lock);