[PATCH 12/12] drm/panthor: Fix unplug in the reset path

Boris Brezillon <[email protected]>
Newsgroups gmane.linux.kernel,gmane.comp.video.dri.devel
Message-ID <[email protected]>
We can't use disable_work_sync() if panthor_device_unplug() is called
from the reset work or we'll deadlock. Pass a from_reset_work bool to
the panthor_device_unplug() function and lower the disable_work_sync()
to a disable_work() in that case.

We also add debugfs knobs to simulate this situation.

Maybe we should use a separate work and call device_release_driver()
instead of calling panthor_device_unplug() directly. This would allow
us to actually detach the device from panthor so it can later be
re-attached without an explicit unbind/bind or rmmod/modprobe sequence.
The problem is, this gets racy if the device is manually
unbound/rebound, and it's hard to fix that race, so let's keep this
for later.

Signed-off-by: Boris Brezillon <[email protected]>
---
 drivers/gpu/drm/panthor/panthor_device.c | 54 +++++++++++++++++++++++++++++---
 drivers/gpu/drm/panthor/panthor_device.h | 10 +++++-
 drivers/gpu/drm/panthor/panthor_drv.c    |  2 +-
 3 files changed, 60 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/panthor/panthor_device.c b/drivers/gpu/drm/panthor/panthor_device.c
index 425990369b99..d350bda58bb3 100644
--- a/drivers/gpu/drm/panthor/panthor_device.c
+++ b/drivers/gpu/drm/panthor/panthor_device.c
@@ -93,7 +93,7 @@ static int panthor_device_stop_before_unplug(struct panthor_device *ptdev)
 	return ret;
 }
 
-void panthor_device_unplug(struct panthor_device *ptdev)
+void panthor_device_unplug(struct panthor_device *ptdev, bool from_reset_work)
 {
 	int ret;
 
@@ -121,7 +121,10 @@ void panthor_device_unplug(struct panthor_device *ptdev)
 	drm_dev_unplug(&ptdev->base);
 
 	/* Make sure we're not interrupted by resets while we're unplugging. */
-	disable_work_sync(&ptdev->reset.work);
+	if (!from_reset_work)
+		disable_work_sync(&ptdev->reset.work);
+	else
+		disable_work(&ptdev->reset.work);
 
 	/* Do anything we can to stop the HW. If we can't guarantee that the HW
 	 * is fully stopped, we also can't guarantee the resources it had access
@@ -189,13 +192,16 @@ static void panthor_device_reset_work(struct work_struct *work)
 	panthor_hw_soft_reset(ptdev);
 	panthor_hw_l2_power_on(ptdev);
 	panthor_mmu_post_reset(ptdev);
-	ret = panthor_fw_post_reset(ptdev);
+	if (ptdev->reset.fake_failure)
+		ret = -EIO;
+	else
+		ret = panthor_fw_post_reset(ptdev);
 	atomic_set(&ptdev->reset.pending, 0);
 	panthor_sched_post_reset(ptdev, ret != 0);
 	drm_dev_exit(cookie);
 
 	if (ret) {
-		panthor_device_unplug(ptdev);
+		panthor_device_unplug(ptdev, true);
 		drm_err(&ptdev->base, "Failed to boot MCU after reset, making device unusable.");
 	}
 }
@@ -694,6 +700,40 @@ DEFINE_DEBUGFS_ATTRIBUTE(panthor_device_fake_unplug_failure_fops,
 			 panthor_device_fake_unplug_failure_get,
 			 panthor_device_fake_unplug_failure_set, "%llu\n");
 
+static int panthor_device_fake_fw_reset_failure_get(void *data, u64 *val)
+{
+	struct panthor_device *ptdev = data;
+
+	*val = ptdev->reset.fake_failure ? 1 : 0;
+	return 0;
+}
+
+static int panthor_device_fake_fw_reset_failure_set(void *data, u64 val)
+{
+	struct panthor_device *ptdev = data;
+
+	ptdev->reset.fake_failure = val ? true : false;
+	return 0;
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(panthor_device_fake_fw_reset_failure_fops,
+			 panthor_device_fake_fw_reset_failure_get,
+			 panthor_device_fake_fw_reset_failure_set, "%llu\n");
+
+static ssize_t panthor_device_reset_file_write(struct file *file,
+					       const char __user *, size_t size,
+					       loff_t *)
+{
+	struct panthor_device *ptdev = file_inode(file)->i_private;
+
+	panthor_device_schedule_reset(ptdev);
+	return size;
+}
+
+static const struct debugfs_short_fops panthor_device_reset_fops = {
+	.write = panthor_device_reset_file_write,
+};
+
 void panthor_device_debugfs_init(struct drm_minor *minor)
 {
 	struct panthor_device *ptdev = container_of(minor->dev, struct panthor_device, base);
@@ -701,6 +741,12 @@ void panthor_device_debugfs_init(struct drm_minor *minor)
 	debugfs_create_file("fake_unplug_failure", 0644,
 			    minor->debugfs_root, ptdev,
 			    &panthor_device_fake_unplug_failure_fops);
+	debugfs_create_file("fake_fw_reset_failure", 0644,
+			    minor->debugfs_root, ptdev,
+			    &panthor_device_fake_fw_reset_failure_fops);
+	debugfs_create_file("reset", 0200,
+			    minor->debugfs_root, ptdev,
+			    &panthor_device_reset_fops);
 	panthor_mmu_debugfs_init(minor);
 	panthor_gem_debugfs_init(minor);
 }
diff --git a/drivers/gpu/drm/panthor/panthor_device.h b/drivers/gpu/drm/panthor/panthor_device.h
index f960109f4b5b..7d3db80fdfb6 100644
--- a/drivers/gpu/drm/panthor/panthor_device.h
+++ b/drivers/gpu/drm/panthor/panthor_device.h
@@ -310,6 +310,14 @@ struct panthor_device {
 		 * all FW sections to make sure we start from a fresh state.
 		 */
 		bool fast;
+
+		/**
+		 * @fake_failure: When true, pretend the FW boot in the reset path failed.
+		 *
+		 * This is important to check that we're doing the right thing in this very
+		 * unlikely case.
+		 */
+		bool fake_failure;
 	} reset;
 
 	/** @pm: Power management related data. */
@@ -398,7 +406,7 @@ struct panthor_file {
 };
 
 int panthor_device_init(struct panthor_device *ptdev);
-void panthor_device_unplug(struct panthor_device *ptdev);
+void panthor_device_unplug(struct panthor_device *ptdev, bool from_reset_work);
 
 /**
  * panthor_device_schedule_reset() - Schedules a reset operation
diff --git a/drivers/gpu/drm/panthor/panthor_drv.c b/drivers/gpu/drm/panthor/panthor_drv.c
index 924a7ecd3733..730f7996985c 100644
--- a/drivers/gpu/drm/panthor/panthor_drv.c
+++ b/drivers/gpu/drm/panthor/panthor_drv.c
@@ -1827,7 +1827,7 @@ static void panthor_remove(struct platform_device *pdev)
 {
 	struct panthor_device *ptdev = platform_get_drvdata(pdev);
 
-	panthor_device_unplug(ptdev);
+	panthor_device_unplug(ptdev, false);
 }
 
 static ssize_t profiling_show(struct device *dev,

-- 
2.55.0
lmpx.com only provides a reader for public news (NNTP) servers. It is not affiliated with the servers or forums shown here and is not responsible for the content of articles, which is written by their respective authors.