On 19/12/2025 09:35, Ketil Johnsen wrote:
> Ensure all related groups are evicted and suspended before VM
> destruction takes place.
>
> This fixes an issue where panthor_vm_destroy() destroys and unmaps the
> heap context while there are still on slot groups using this.
> The FW will do a write out to the heap context when a CSG (group) is
> suspended, so a premature unmap of the heap context will cause a
> GPU page fault.
> This page fault is quite harmless, and do not affect the continued
> operation of the GPU.
>
> Fixes: 647810ec2476 ("drm/panthor: Add the MMU/VM logical block")
> Reviewed-by: Boris Brezillon <[email protected]>
> Co-developed-by: Boris Brezillon <[email protected]>
> Signed-off-by: Ketil Johnsen <[email protected]>
Reviewed-by: Steven Price <[email protected]>
> ---
> Changes in v2:
> - Removed check for ptdev->scheduler
> - R-b from Boris
> - Link to v1:
> https://lore.kernel.org/all/[email protected]/
> ---
> drivers/gpu/drm/panthor/panthor_mmu.c | 4 ++++
> drivers/gpu/drm/panthor/panthor_sched.c | 14 ++++++++++++++
> drivers/gpu/drm/panthor/panthor_sched.h | 1 +
> 3 files changed, 19 insertions(+)
>
> diff --git a/drivers/gpu/drm/panthor/panthor_mmu.c
> b/drivers/gpu/drm/panthor/panthor_mmu.c
> index 74230f7199121..0e4b301a9c70e 100644
> --- a/drivers/gpu/drm/panthor/panthor_mmu.c
> +++ b/drivers/gpu/drm/panthor/panthor_mmu.c
> @@ -1537,6 +1537,10 @@ static void panthor_vm_destroy(struct panthor_vm *vm)
>
> vm->destroyed = true;
>
> + /* Tell scheduler to stop all GPU work related to this VM */
> + if (refcount_read(&vm->as.active_cnt) > 0)
> + panthor_sched_prepare_for_vm_destruction(vm->ptdev);
> +
> mutex_lock(&vm->heaps.lock);
> panthor_heap_pool_destroy(vm->heaps.pool);
> vm->heaps.pool = NULL;
> diff --git a/drivers/gpu/drm/panthor/panthor_sched.c
> b/drivers/gpu/drm/panthor/panthor_sched.c
> index f680edcd40aad..a40ac94e5e989 100644
> --- a/drivers/gpu/drm/panthor/panthor_sched.c
> +++ b/drivers/gpu/drm/panthor/panthor_sched.c
> @@ -2930,6 +2930,20 @@ void panthor_sched_report_mmu_fault(struct
> panthor_device *ptdev)
> sched_queue_delayed_work(ptdev->scheduler, tick, 0);
> }
>
> +void panthor_sched_prepare_for_vm_destruction(struct panthor_device *ptdev)
> +{
> + /* FW can write out internal state, like the heap context, during CSG
> + * suspend. It is therefore important that the scheduler has fully
> + * evicted any pending and related groups before VM destruction can
> + * safely continue. Failure to do so can lead to GPU page faults.
> + * A controlled termination of a Panthor instance involves destroying
> + * the group(s) before the VM. This means any relevant group eviction
> + * has already been initiated by this point, and we just need to
> + * ensure that any pending tick_work() has been completed.
> + */
> + flush_work(&ptdev->scheduler->tick_work.work);
> +}
> +
> void panthor_sched_resume(struct panthor_device *ptdev)
> {
> /* Force a tick to re-evaluate after a resume. */
> diff --git a/drivers/gpu/drm/panthor/panthor_sched.h
> b/drivers/gpu/drm/panthor/panthor_sched.h
> index f4a475aa34c0a..9a8692de8aded 100644
> --- a/drivers/gpu/drm/panthor/panthor_sched.h
> +++ b/drivers/gpu/drm/panthor/panthor_sched.h
> @@ -50,6 +50,7 @@ void panthor_sched_suspend(struct panthor_device *ptdev);
> void panthor_sched_resume(struct panthor_device *ptdev);
>
> void panthor_sched_report_mmu_fault(struct panthor_device *ptdev);
> +void panthor_sched_prepare_for_vm_destruction(struct panthor_device *ptdev);
> void panthor_sched_report_fw_events(struct panthor_device *ptdev, u32
> events);
>
> void panthor_fdinfo_gather_group_samples(struct panthor_file *pfile);
