[PATCH v4 08/31] accel: ethosu: Serialize job completion

[Rob Herring (Arm)]

The timeout worker and threaded IRQ handler can both clear
in_flight_job. If a new job is scheduled in between those,
in_flight_job could be overwritten when the IRQ thread resumes.
Serialize these updates so a late completion cannot clear the next job's
tracking pointer.

Fixes: 5a5e9c0228e6 ("accel: Add Arm Ethos-U NPU driver")
Cc: stable@xxxxxxxxxxxxxxx
Signed-off-by: Rob Herring (Arm) <robh@xxxxxxxxxx>
---
v4:
 - New patch
---
 drivers/accel/ethosu/ethosu_device.h |  1 +
 drivers/accel/ethosu/ethosu_job.c    | 43 +++++++++++++++++++++++++++++-------
 2 files changed, 36 insertions(+), 8 deletions(-)

diff --git a/drivers/accel/ethosu/ethosu_device.h b/drivers/accel/ethosu/ethosu_device.h
index 1eca8590e68d..51d5bc5d6137 100644
--- a/drivers/accel/ethosu/ethosu_device.h
+++ b/drivers/accel/ethosu/ethosu_device.h
@@ -7,6 +7,7 @@
 #include <linux/bitfield.h>
 #include <linux/bits.h>
 #include <linux/mutex.h>
+#include <linux/spinlock.h>
 #include <linux/types.h>
 
 #include <drm/drm_device.h>
diff --git a/drivers/accel/ethosu/ethosu_job.c b/drivers/accel/ethosu/ethosu_job.c
index d418ae7961cf..f22cacb19e3d 100644
--- a/drivers/accel/ethosu/ethosu_job.c
+++ b/drivers/accel/ethosu/ethosu_job.c
@@ -42,6 +42,25 @@ static const struct dma_fence_ops ethosu_fence_ops = {
 	.get_timeline_name = ethosu_fence_get_timeline_name,
 };
 
+static void ethosu_job_set_in_flight(struct ethosu_device *dev,
+				     struct ethosu_job *job)
+{
+	guard(spinlock)(&dev->job_lock);
+	dev->in_flight_job = job;
+}
+
+static struct ethosu_job *
+ethosu_job_clear_in_flight(struct ethosu_device *dev)
+{
+	struct ethosu_job *job;
+
+	guard(spinlock)(&dev->job_lock);
+	job = dev->in_flight_job;
+	dev->in_flight_job = NULL;
+
+	return job;
+}
+
 static void ethosu_job_hw_submit(struct ethosu_device *dev, struct ethosu_job *job)
 {
 	struct drm_gem_dma_object *cmd_bo = to_drm_gem_dma_obj(job->cmd_bo);
@@ -235,7 +254,7 @@ static struct dma_fence *ethosu_job_run(struct drm_sched_job *sched_job)
 
 	ethosu_switch_perfmon(dev, job);
 
-	WRITE_ONCE(dev->in_flight_job, job);
+	ethosu_job_set_in_flight(dev, job);
 	ethosu_job_hw_submit(dev, job);
 
 	return fence;
@@ -252,11 +271,9 @@ static void ethosu_job_handle_irq(struct ethosu_device *dev)
 		return;
 	}
 
-	job = READ_ONCE(dev->in_flight_job);
-	if (job) {
-		WRITE_ONCE(dev->in_flight_job, NULL);
+	job = ethosu_job_clear_in_flight(dev);
+	if (job)
 		dma_fence_signal(job->done_fence);
-	}
 }
 
 static irqreturn_t ethosu_job_irq_handler_thread(int irq, void *data)
@@ -285,6 +302,7 @@ static enum drm_gpu_sched_stat ethosu_job_timedout(struct drm_sched_job *bad)
 	struct ethosu_job *job = to_ethosu_job(bad);
 	struct ethosu_device *dev = job->dev;
 	bool running;
+	int ret;
 	u32 *bocmds = to_drm_gem_dma_obj(job->cmd_bo)->vaddr;
 	u32 cmdaddr;
 
@@ -311,11 +329,19 @@ static enum drm_gpu_sched_stat ethosu_job_timedout(struct drm_sched_job *bad)
 
 	drm_sched_stop(&dev->sched, bad);
 
-	WRITE_ONCE(dev->in_flight_job, NULL);
+	ethosu_job_clear_in_flight(dev);
 
 	/* Proceed with reset now. */
-	pm_runtime_force_suspend(dev->base.dev);
-	pm_runtime_force_resume(dev->base.dev);
+	ret = pm_runtime_force_suspend(dev->base.dev);
+	if (!ret)
+		ret = pm_runtime_force_resume(dev->base.dev);
+	if (ret) {
+		dev_err(dev->base.dev, "Failed to recover NPU: %d\n", ret);
+		return DRM_GPU_SCHED_STAT_ENODEV;
+	}
+
+	/* Drain a pending completion IRQ before a replacement job can run. */
+	synchronize_irq(dev->irq);
 
 	/* Restart the scheduler */
 	drm_sched_start(&dev->sched, 0);
@@ -344,6 +370,7 @@ int ethosu_job_init(struct ethosu_device *edev)
 	int ret;
 
 	spin_lock_init(&edev->fence_lock);
+	spin_lock_init(&edev->job_lock);
 	ret = devm_mutex_init(dev, &edev->sched_lock);
 	if (ret)
 		return ret;

-- 
2.53.0