Since commit 9bf19fbf0c8b ("media: v4l: async: Rework internal lists"), aka
v6.6-rc1~97^2~198, probing the tegra-video VI driver causes infinite
recursion due tegra_vi_graph_parse_one() calling itself until:
[ 1.571168] Insufficient stack space to handle exception!
...
[ 1.591416] Internal error: kernel stack overflow: 0 [#1] PREEMPT SMP ARM
...
[ 3.861013] of_phandle_iterator_init from __of_parse_phandle_with_args+0x40/0xf0
[ 3.868497] __of_parse_phandle_with_args from of_fwnode_graph_get_remote_endpoint+0x68/0xa8
[ 3.876938] of_fwnode_graph_get_remote_endpoint from fwnode_graph_get_remote_port_parent+0x30/0x7c
[ 3.885984] fwnode_graph_get_remote_port_parent from tegra_vi_graph_parse_one+0x7c/0x224
[ 3.894158] tegra_vi_graph_parse_one from tegra_vi_graph_parse_one+0x144/0x224
[ 3.901459] tegra_vi_graph_parse_one from tegra_vi_graph_parse_one+0x144/0x224
[ 3.908760] tegra_vi_graph_parse_one from tegra_vi_graph_parse_one+0x144/0x224
[ 3.916061] tegra_vi_graph_parse_one from tegra_vi_graph_parse_one+0x144/0x224
...
[ 4.857892] tegra_vi_graph_parse_one from tegra_vi_graph_parse_one+0x144/0x224
[ 4.865193] tegra_vi_graph_parse_one from tegra_vi_graph_parse_one+0x144/0x224
[ 4.872494] tegra_vi_graph_parse_one from tegra_vi_init+0x574/0x6d4
[ 4.878842] tegra_vi_init from host1x_device_init+0x84/0x15c
[ 4.884594] host1x_device_init from host1x_video_probe+0xa0/0x114
[ 4.890770] host1x_video_probe from really_probe+0xe0/0x400
The reason is the mentioned commit changed tegra_vi_graph_find_entity() to
search for an entity in the done notifier list:
> @@ -1464,7 +1464,7 @@ tegra_vi_graph_find_entity(struct tegra_vi_channel *chan,
> struct tegra_vi_graph_entity *entity;
> struct v4l2_async_connection *asd;
>
> - list_for_each_entry(asd, &chan->notifier.asc_list, asc_entry) {
> + list_for_each_entry(asd, &chan->notifier.done_list, asc_entry) {
> entity = to_tegra_vi_graph_entity(asd);
> if (entity->asd.match.fwnode == fwnode)
> return entity;
This is not always correct, being tegra_vi_graph_find_entity() called in
three locations, in this order:
1. tegra_vi_graph_parse_one() -- called while probing
2. tegra_vi_graph_notify_bound() -- the .bound notifier op
3. tegra_vi_graph_build() -- called in the .complete notifier op
Locations 1 and 2 are called before moving the entity from waiting_list to
done_list, thus they won't find what they are looking for in
done_list. Location 3 happens afterwards and thus it is not broken, however
it means tegra_vi_graph_find_entity() should not search in the same list
every time.
The error appears at step 1: tegra_vi_graph_parse_one() iterates
recursively until it finds the entity already notified, which now never
happens.
Fix by passing the specific notifier list pointer to
tegra_vi_graph_find_entity() instead of the channel, so each caller can
search in whatever list is correct.
Also improve the tegra_vi_graph_find_entity() comment.
Fixes: 9bf19fbf0c8b ("media: v4l: async: Rework internal lists")
Cc: Thierry Reding <thierry.reding@xxxxxxxxx>
Cc: Jonathan Hunter <jonathanh@xxxxxxxxxx>
Cc: Sowjanya Komatineni <skomatineni@xxxxxxxxxx>
Signed-off-by: Luca Ceresoli <luca.ceresoli@xxxxxxxxxxx>
---
drivers/staging/media/tegra-video/vi.c | 13 +++++++------
1 file changed, 7 insertions(+), 6 deletions(-)
diff --git a/drivers/staging/media/tegra-video/vi.c b/drivers/staging/media/tegra-video/vi.c
index e98b3010520e..d9a6d5b2aa84 100644
--- a/drivers/staging/media/tegra-video/vi.c
+++ b/drivers/staging/media/tegra-video/vi.c
@@ -1455,17 +1455,18 @@ static int __maybe_unused vi_runtime_suspend(struct device *dev)
}
/*
- * Graph Management
+ * Find the entity matching a given fwnode in an v4l2_async_notifier list
*/
static struct tegra_vi_graph_entity *
-tegra_vi_graph_find_entity(struct tegra_vi_channel *chan,
+tegra_vi_graph_find_entity(struct list_head *list,
const struct fwnode_handle *fwnode)
{
struct tegra_vi_graph_entity *entity;
struct v4l2_async_connection *asd;
- list_for_each_entry(asd, &chan->notifier.done_list, asc_entry) {
+ list_for_each_entry(asd, list, asc_entry) {
entity = to_tegra_vi_graph_entity(asd);
+
if (entity->asd.match.fwnode == fwnode)
return entity;
}
@@ -1532,7 +1533,7 @@ static int tegra_vi_graph_build(struct tegra_vi_channel *chan,
}
/* find the remote entity from notifier list */
- ent = tegra_vi_graph_find_entity(chan, link.remote_node);
+ ent = tegra_vi_graph_find_entity(&chan->notifier.done_list, link.remote_node);
if (!ent) {
dev_err(vi->dev, "no entity found for %pOF\n",
to_of_node(link.remote_node));
@@ -1664,7 +1665,7 @@ static int tegra_vi_graph_notify_bound(struct v4l2_async_notifier *notifier,
* Locate the entity corresponding to the bound subdev and store the
* subdev pointer.
*/
- entity = tegra_vi_graph_find_entity(chan, subdev->fwnode);
+ entity = tegra_vi_graph_find_entity(&chan->notifier.waiting_list, subdev->fwnode);
if (!entity) {
dev_err(vi->dev, "no entity for subdev %s\n", subdev->name);
return -EINVAL;
@@ -1713,7 +1714,7 @@ static int tegra_vi_graph_parse_one(struct tegra_vi_channel *chan,
/* skip entities that are already processed */
if (device_match_fwnode(vi->dev, remote) ||
- tegra_vi_graph_find_entity(chan, remote)) {
+ tegra_vi_graph_find_entity(&chan->notifier.waiting_list, remote)) {
fwnode_handle_put(remote);
continue;
}
--
2.34.1
