[PATCH v1 26/27] drm/panthor: Prevent missed post-yield cleanup due to reset

[Karunika Choo]

With v15 GPUs, FW can yield GPU access at any point. This includes when
panthor has scheduled a reset. If a WINDOW_CLOSED event is received
after reset work is scheduled but before the actual RESET_SOFT command
is sent, panthor_aw can end up assuming that the WINDOW_CLOSED is a
result of the reset and fail to schedule the post-yield cleanup.

Introduce pre_reset and post_reset helpers for panthor_aw which marks a
granted AW as reset-active so reset-originated WINDOW_CLOSED handling
does not suppress post-yield cleanup when FW yield wins the race.

Signed-off-by: Karunika Choo <karunika.choo@xxxxxxx>
---
 drivers/gpu/drm/panthor/panthor_aw.c     | 54 +++++++++++++++++++++---
 drivers/gpu/drm/panthor/panthor_aw.h     |  7 +++
 drivers/gpu/drm/panthor/panthor_device.c | 13 +++++-
 3 files changed, 65 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/panthor/panthor_aw.c b/drivers/gpu/drm/panthor/panthor_aw.c
index 9ebb23eadfec5..7ef13db4acf50 100644
--- a/drivers/gpu/drm/panthor/panthor_aw.c
+++ b/drivers/gpu/drm/panthor/panthor_aw.c
@@ -248,7 +248,7 @@ static void panthor_aw_handle_window_closed(struct panthor_aw *aw)
 	struct panthor_device *ptdev = aw->ptdev;
 
 	/* Ignore this WINDOW_CLOSED as part of reset operation. */
-	if (panthor_device_reset_is_pending(ptdev))
+	if (atomic_read(&aw->state) == PANTHOR_AW_STATE_RESET_ACTIVE)
 		return;
 
 	if (atomic_read(&aw->state) == PANTHOR_AW_STATE_GPU_STOPPED ||
@@ -260,14 +260,14 @@ static void panthor_aw_handle_window_closed(struct panthor_aw *aw)
 
 	/*
 	 * Window may have been closed immediately after opening.
-	 * Setting state back to READY will prevent WINDOW_OPENDED from
+	 * Setting state back to READY will prevent WINDOW_OPENED from
 	 * mistakenly transitioning the state to GRANTED.
 	 */
 	if (panthor_aw_state_try_set(aw, PANTHOR_AW_STATE_GPU_REQUEST,
 				     PANTHOR_AW_STATE_READY))
 		return;
 
-	/* Triggerred from messaged-based yield. Unblock its wait */
+	/* Triggered from messaged-based yield. Unblock its wait */
 	if (panthor_aw_state_try_set(aw, PANTHOR_AW_STATE_STOPPED_IDLE,
 				     PANTHOR_AW_STATE_READY))
 		return;
@@ -275,6 +275,17 @@ static void panthor_aw_handle_window_closed(struct panthor_aw *aw)
 	panthor_aw_schedule_post_yield_work(aw);
 }
 
+static void panthor_aw_handle_window_opened(struct panthor_aw *aw)
+{
+	/* Ignore this WINDOW_OPENED as part of reset operation. */
+	if (atomic_read(&aw->state) == PANTHOR_AW_STATE_RESET_ACTIVE)
+		return;
+
+	/* Window opened due to GPU_REQUEST */
+	panthor_aw_state_try_set(aw, PANTHOR_AW_STATE_GPU_REQUEST,
+				     PANTHOR_AW_STATE_GPU_GRANTED);
+}
+
 static irqreturn_t panthor_aw_irq_raw_hander(int irq, void *data)
 {
 	struct panthor_irq *pirq = data;
@@ -297,10 +308,8 @@ static irqreturn_t panthor_aw_irq_raw_hander(int irq, void *data)
 	if (status & WINDOW_IRQ_WINDOW_CLOSED)
 		panthor_aw_handle_window_closed(aw);
 
-
 	if ((status & WINDOW_IRQ_WINDOW_OPENED) && panthor_aw_is_open(aw))
-		panthor_aw_state_try_set(aw, PANTHOR_AW_STATE_GPU_REQUEST,
-					 PANTHOR_AW_STATE_GPU_GRANTED);
+		panthor_aw_handle_window_opened(aw);
 
 	gpu_write(pirq->iomem, INT_CLEAR, status);
 
@@ -579,5 +588,36 @@ bool panthor_aw_has_gpu_access(struct panthor_device *ptdev)
 	if (!ptdev->aw)
 		return true;
 
-	return (atomic_read(&ptdev->aw->state) == PANTHOR_AW_STATE_GPU_GRANTED);
+	switch (atomic_read(&ptdev->aw->state)) {
+	case PANTHOR_AW_STATE_GPU_GRANTED:
+	case PANTHOR_AW_STATE_RESET_ACTIVE:
+		return true;
+	}
+
+	return false;
+}
+
+void panthor_aw_pre_reset(struct panthor_device *ptdev)
+{
+	struct panthor_aw *aw = ptdev->aw;
+
+	if (!aw)
+		return;
+
+	panthor_aw_state_try_set(ptdev->aw, PANTHOR_AW_STATE_GPU_GRANTED,
+				 PANTHOR_AW_STATE_RESET_ACTIVE);
+}
+
+void panthor_aw_post_reset(struct panthor_device *ptdev)
+{
+	struct panthor_aw *aw = ptdev->aw;
+
+	if (!aw)
+		return;
+
+	panthor_aw_state_try_set(aw, PANTHOR_AW_STATE_RESET_ACTIVE,
+				 PANTHOR_AW_STATE_GPU_GRANTED);
+
+	if (!panthor_aw_is_open(aw))
+		panthor_aw_schedule_post_yield_work(aw);
 }
diff --git a/drivers/gpu/drm/panthor/panthor_aw.h b/drivers/gpu/drm/panthor/panthor_aw.h
index 1da613fa330a0..0269bbbbdc165 100644
--- a/drivers/gpu/drm/panthor/panthor_aw.h
+++ b/drivers/gpu/drm/panthor/panthor_aw.h
@@ -24,6 +24,9 @@ enum aw_states {
 	/** @PANTHOR_AW_STATE_GPU_GRANTED: AW is granted GPU access. */
 	PANTHOR_AW_STATE_GPU_GRANTED,
 
+	/** @PANTHOR_AW_STATE_RESET_ACTIVE: AW is being reset. */
+	PANTHOR_AW_STATE_RESET_ACTIVE,
+
 	/** @PANTHOR_AW_STATE_STOPPED_IDLE: AW has stopped GPU access. */
 	PANTHOR_AW_STATE_STOPPED_IDLE,
 
@@ -43,4 +46,8 @@ int panthor_aw_ensure_gpu_access(struct panthor_device *ptdev);
 
 bool panthor_aw_has_gpu_access(struct panthor_device *ptdev);
 
+void panthor_aw_pre_reset(struct panthor_device *ptdev);
+
+void panthor_aw_post_reset(struct panthor_device *ptdev);
+
 #endif
diff --git a/drivers/gpu/drm/panthor/panthor_device.c b/drivers/gpu/drm/panthor/panthor_device.c
index ea35c5e1d87b4..86eb4e9a61789 100644
--- a/drivers/gpu/drm/panthor/panthor_device.c
+++ b/drivers/gpu/drm/panthor/panthor_device.c
@@ -138,18 +138,27 @@ static void panthor_device_reset_work(struct work_struct *work)
 	if (!drm_dev_enter(&ptdev->base, &cookie))
 		return;
 
+	if (!panthor_aw_has_gpu_access(ptdev))
+		goto out_clear_pending;
+
 	panthor_sched_pre_reset(ptdev);
+	panthor_aw_pre_reset(ptdev);
 	panthor_fw_pre_reset(ptdev, true);
 	panthor_mmu_pre_reset(ptdev);
+
 	panthor_hw_soft_reset(ptdev);
+
 	panthor_hw_l2_power_on(ptdev);
 	panthor_mmu_post_reset(ptdev);
 	ret = panthor_fw_post_reset(ptdev);
-	atomic_set(&ptdev->reset.pending, 0);
+	panthor_aw_post_reset(ptdev);
 	panthor_sched_post_reset(ptdev, ret != 0);
+
+out_clear_pending:
+	atomic_set(&ptdev->reset.pending, 0);
 	drm_dev_exit(cookie);
 
-	if (ret) {
+	if (ret && panthor_aw_has_gpu_access(ptdev)) {
 		panthor_device_unplug(ptdev);
 		drm_err(&ptdev->base, "Failed to boot MCU after reset, making device unusable.");
 	}
-- 
2.43.0