[PATCHv2 2/3] remoteproc: recover a remoteproc when it has crashed

From: Fernando Guzman Lugo <fernando.lugo@ti.com>
To: <ohad@wizery.com>, <linux-omap@vger.kernel.org>,
	<linux-arm-kernel@lists.infradead.org>,
	<linux-kernel@vger.kernel.org>
Cc: Fernando Guzman Lugo <fernando.lugo@ti.com>
Subject: [PATCHv2 2/3] remoteproc: recover a remoteproc when it has crashed
Date: Thu, 30 Aug 2012 13:26:13 -0500	[thread overview]
Message-ID: <1346351174-28441-3-git-send-email-fernando.lugo@ti.com> (raw)
In-Reply-To: <1346351174-28441-1-git-send-email-fernando.lugo@ti.com>

This patch is introducing rproc_trigger_recover function which is in
charge of recovering the rproc. One way to recover the rproc after a crash
is resetting all its virtio devices. Doing that, all rpmsg drivers are
restored along with the rpmsg devices and that also causes the reset of
the remoteproc making the rpmsg communication with the remoteproc
functional again. So far, rproc_trigger_recover function is only resetting
all virtio devices, if in the future other rproc features are introduced
and need to be reset too, rproc_trigger_recover function should take care
of that.

Signed-off-by: Fernando Guzman Lugo <fernando.lugo@ti.com>
---
 drivers/remoteproc/remoteproc_core.c     |   37 +++++++++++++++++++++++++++++-
 drivers/remoteproc/remoteproc_internal.h |    1 +
 include/linux/remoteproc.h               |    2 +
 3 files changed, 39 insertions(+), 1 deletions(-)

diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c
index 3a6f1a1..9fbd364 100644
--- a/drivers/remoteproc/remoteproc_core.c
+++ b/drivers/remoteproc/remoteproc_core.c
@@ -882,6 +882,36 @@ out:
 }
 
 /**
+ * rproc_trigger_recover() - recover a remoteproc
+ * @rproc: the remote processor
+ *
+ * The recovery is done by reseting all the virtio devices, that way all the
+ * rpmsg drivers will be reseted along with the remote processor making the
+ * remoteproc functional again.
+ *
+ * This function can sleep, so that it cannot be called from atomic context.
+ */
+int rproc_trigger_recover(struct rproc *rproc)
+{
+	struct rproc_vdev *rvdev, *rvtmp;
+
+	dev_err(&rproc->dev, "recovering %s\n", rproc->name);
+
+	init_completion(&rproc->crash_comp);
+	/* clean up remote vdev entries */
+	list_for_each_entry_safe(rvdev, rvtmp, &rproc->rvdevs, node)
+		rproc_remove_virtio_dev(rvdev);
+
+	/* wait until there is no more rproc users */
+	wait_for_completion(&rproc->crash_comp);
+
+	/* run rproc_fw_config_virtio to create vdevs again */
+	return request_firmware_nowait(THIS_MODULE, FW_ACTION_HOTPLUG,
+			rproc->firmware, &rproc->dev, GFP_KERNEL,
+			rproc, rproc_fw_config_virtio);
+}
+
+/**
  * rproc_crash_handler_work() - handle a crash
  *
  * This function needs to handle everything related to a crash, like cpu
@@ -906,7 +936,7 @@ static void rproc_crash_handler_work(struct work_struct *work)
 		++rproc->crash_cnt, rproc->name);
 	mutex_unlock(&rproc->lock);
 
-	/* TODO: handle crash */
+	rproc_trigger_recover(rproc);
 }
 
 /**
@@ -1030,6 +1060,10 @@ void rproc_shutdown(struct rproc *rproc)
 
 	rproc_disable_iommu(rproc);
 
+	/* if in crash state, unlock crash handler */
+	if (rproc->state == RPROC_CRASHED)
+		complete_all(&rproc->crash_comp);
+
 	rproc->state = RPROC_OFFLINE;
 
 	dev_info(dev, "stopped remote processor %s\n", rproc->name);
@@ -1204,6 +1238,7 @@ struct rproc *rproc_alloc(struct device *dev, const char *name,
 	INIT_LIST_HEAD(&rproc->rvdevs);
 
 	INIT_WORK(&rproc->crash_handler, rproc_crash_handler_work);
+	init_completion(&rproc->crash_comp);
 
 	rproc->state = RPROC_OFFLINE;
 
diff --git a/drivers/remoteproc/remoteproc_internal.h b/drivers/remoteproc/remoteproc_internal.h
index a690ebe..d9c0730 100644
--- a/drivers/remoteproc/remoteproc_internal.h
+++ b/drivers/remoteproc/remoteproc_internal.h
@@ -63,6 +63,7 @@ void rproc_free_vring(struct rproc_vring *rvring);
 int rproc_alloc_vring(struct rproc_vdev *rvdev, int i);
 
 void *rproc_da_to_va(struct rproc *rproc, u64 da, int len);
+int rproc_trigger_recover(struct rproc *rproc);
 
 static inline
 int rproc_fw_sanity_check(struct rproc *rproc, const struct firmware *fw)
diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h
index a46ed27..0c1a2f9 100644
--- a/include/linux/remoteproc.h
+++ b/include/linux/remoteproc.h
@@ -398,6 +398,7 @@ enum rproc_crash_type {
  * @index: index of this rproc device
  * @crash_handler: workqueue for handling a crash
  * @crash_cnt: crash counter
+ * @crash_comp: completion used to sync crash handler and the rproc reload
  */
 struct rproc {
 	struct klist_node node;
@@ -423,6 +424,7 @@ struct rproc {
 	int index;
 	struct work_struct crash_handler;
 	unsigned crash_cnt;
+	struct completion crash_comp;
 };
 
 /* we currently support only two vrings per rvdev */
-- 
1.7.1

