From: Jakub Pawlak <[email protected]>
Use separate flag to mark a job timeout as a reason
of starting context_abort_work. This allows to distinguish
engine reset reason and clearly adjust reset procedure flow.
The flag is cleared in ivpu_prepare_for_reset(), which every
recovery and suspend path already funnels through, so that the
state is clean after recovery.
Fixes: ade00a6c903f ("accel/ivpu: Perform engine reset instead of device
recovery on TDR")
Signed-off-by: Jakub Pawlak <[email protected]>
Signed-off-by: Karol Wachowski <[email protected]>
---
drivers/accel/ivpu/ivpu_drv.c | 3 ++-
drivers/accel/ivpu/ivpu_drv.h | 2 +-
drivers/accel/ivpu/ivpu_job.c | 7 +++----
drivers/accel/ivpu/ivpu_mmu.c | 1 -
drivers/accel/ivpu/ivpu_pm.c | 1 +
5 files changed, 7 insertions(+), 7 deletions(-)
diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c
index 0f215392d42d..647684219e9d 100644
--- a/drivers/accel/ivpu/ivpu_drv.c
+++ b/drivers/accel/ivpu/ivpu_drv.c
@@ -528,6 +528,7 @@ void ivpu_prepare_for_reset(struct ivpu_device *vdev)
{
ivpu_hw_irq_disable(vdev);
disable_irq(vdev->irq);
+ atomic_set(&vdev->job_timeout_detected, 0);
flush_work(&vdev->irq_dct_work);
flush_work(&vdev->context_abort_work);
flush_work(&vdev->job_destroy_work);
@@ -723,7 +724,7 @@ static int ivpu_dev_init(struct ivpu_device *vdev)
vdev->context_xa_limit.max = IVPU_USER_CONTEXT_MAX_SSID;
atomic64_set(&vdev->unique_id_counter, 0);
atomic_set(&vdev->job_timeout_counter, 0);
- atomic_set(&vdev->faults_detected, 0);
+ atomic_set(&vdev->job_timeout_detected, 0);
xa_init_flags(&vdev->context_xa, XA_FLAGS_ALLOC | XA_FLAGS_LOCK_IRQ);
xa_init_flags(&vdev->submitted_jobs_xa, XA_FLAGS_ALLOC1);
xa_init_flags(&vdev->db_xa, XA_FLAGS_ALLOC1);
diff --git a/drivers/accel/ivpu/ivpu_drv.h b/drivers/accel/ivpu/ivpu_drv.h
index 8f29f1dc52b9..37d5a6ac55f8 100644
--- a/drivers/accel/ivpu/ivpu_drv.h
+++ b/drivers/accel/ivpu/ivpu_drv.h
@@ -171,7 +171,7 @@ struct ivpu_device {
struct xarray submitted_jobs_xa;
struct ivpu_ipc_consumer job_done_consumer;
atomic_t job_timeout_counter;
- atomic_t faults_detected;
+ atomic_t job_timeout_detected;
atomic64_t unique_id_counter;
diff --git a/drivers/accel/ivpu/ivpu_job.c b/drivers/accel/ivpu/ivpu_job.c
index b3de5dd29d1e..084d825f744d 100644
--- a/drivers/accel/ivpu/ivpu_job.c
+++ b/drivers/accel/ivpu/ivpu_job.c
@@ -626,7 +626,6 @@ bool ivpu_job_handle_engine_error(struct ivpu_device *vdev,
u32 job_id, u32 job_
* status and ensure both are handled in the same way
*/
job->file_priv->has_mmu_faults = true;
- atomic_set(&vdev->faults_detected, 1);
queue_work(system_percpu_wq, &vdev->context_abort_work);
return true;
}
@@ -1260,10 +1259,10 @@ static int reset_engine_and_mark_faulty_contexts(struct
ivpu_device *vdev)
return ret;
/*
- * If faults are detected, ignore guilty contexts from engine reset as
NPU may not be stuck
- * and could return currently running good context and faulty contexts
are already marked
+ * If job timeout is detected, read guilty context from engine reset,
for other reasons
+ * faulty context is already known
*/
- if (atomic_cmpxchg(&vdev->faults_detected, 1, 0) == 1)
+ if (atomic_cmpxchg(&vdev->job_timeout_detected, 1, 0) == 0)
return 0;
num_impacted_contexts =
resp.payload.engine_reset_done.num_impacted_contexts;
diff --git a/drivers/accel/ivpu/ivpu_mmu.c b/drivers/accel/ivpu/ivpu_mmu.c
index 41efd8985fa6..b2025274f91d 100644
--- a/drivers/accel/ivpu/ivpu_mmu.c
+++ b/drivers/accel/ivpu/ivpu_mmu.c
@@ -964,7 +964,6 @@ void ivpu_mmu_irq_evtq_handler(struct ivpu_device *vdev)
file_priv = xa_load(&vdev->context_xa, ssid);
if (file_priv) {
if (!READ_ONCE(file_priv->has_mmu_faults)) {
- atomic_set(&vdev->faults_detected, 1);
ivpu_mmu_dump_event(vdev, event);
WRITE_ONCE(file_priv->has_mmu_faults, true);
}
diff --git a/drivers/accel/ivpu/ivpu_pm.c b/drivers/accel/ivpu/ivpu_pm.c
index c1ce8329790e..de0becbfdffb 100644
--- a/drivers/accel/ivpu/ivpu_pm.c
+++ b/drivers/accel/ivpu/ivpu_pm.c
@@ -229,6 +229,7 @@ static void ivpu_job_timeout_work(struct work_struct *work)
ivpu_jsm_state_dump(vdev);
ivpu_dev_coredump(vdev);
+ atomic_set(&vdev->job_timeout_detected, 1);
queue_work(system_percpu_wq, &vdev->context_abort_work);
}
--
2.43.0
