[Intel-xe] [PATCH v2 02/27] drm/xe: Allow num_batch_buffer == 0 in exec IOCTL

[Thomas Hellström]

On Mon, 2023-11-06 at 21:25 -0800, Matthew Brost wrote:
> The idea being out-syncs can signal indicating all previous
> operations
> on the exec queue are complete. An example use case of this would be
> support for implementing vkQueueWaitForIdle easily.
> 
> v2: Don't add last_fence for VM's that do not support dma fences
> 
> Signed-off-by: Matthew Brost <matthew.brost at intel.com>
> ---
>  drivers/gpu/drm/xe/xe_exec.c             | 22 +++++++++++++++++++---
>  drivers/gpu/drm/xe/xe_exec_queue.c       |  5 ++++-
>  drivers/gpu/drm/xe/xe_exec_queue_types.h |  5 +++--
>  drivers/gpu/drm/xe/xe_sync.c             |  5 ++++-
>  drivers/gpu/drm/xe/xe_sync.h             |  2 +-
>  drivers/gpu/drm/xe/xe_vm.c               |  2 +-
>  6 files changed, 32 insertions(+), 9 deletions(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_exec.c
> b/drivers/gpu/drm/xe/xe_exec.c
> index 28e84a0bbeb0..4666f5b145f7 100644
> --- a/drivers/gpu/drm/xe/xe_exec.c
> +++ b/drivers/gpu/drm/xe/xe_exec.c
> @@ -161,7 +161,8 @@ int xe_exec_ioctl(struct drm_device *dev, void
> *data, struct drm_file *file)
>         if (XE_IOCTL_DBG(xe, q->flags & EXEC_QUEUE_FLAG_VM))
>                 return -EINVAL;
>  
> -       if (XE_IOCTL_DBG(xe, q->width != args->num_batch_buffer))
> +       if (XE_IOCTL_DBG(xe, args->num_batch_buffer &&
> +                        q->width != args->num_batch_buffer))
>                 return -EINVAL;
>  
>         if (XE_IOCTL_DBG(xe, q->flags & EXEC_QUEUE_FLAG_BANNED)) {
> @@ -182,12 +183,13 @@ int xe_exec_ioctl(struct drm_device *dev, void
> *data, struct drm_file *file)
>         for (i = 0; i < args->num_syncs; i++) {
>                 err = xe_sync_entry_parse(xe, xef,
> &syncs[num_syncs++],
>                                           &syncs_user[i], true,
> -                                         xe_vm_no_dma_fences(vm));
> +                                         xe_vm_no_dma_fences(vm),
> +                                         !args->num_batch_buffer);
>                 if (err)
>                         goto err_syncs;
>         }
>  
> -       if (xe_exec_queue_is_parallel(q)) {
> +       if (args->num_batch_buffer && xe_exec_queue_is_parallel(q)) {
>                 err = __copy_from_user(addresses, addresses_user,
> sizeof(u64) *
>                                        q->width);
>                 if (err) {
> @@ -234,6 +236,18 @@ int xe_exec_ioctl(struct drm_device *dev, void
> *data, struct drm_file *file)
>                 goto err_exec;
>         }
>  
> +       if (!args->num_batch_buffer) {
> +               if (!xe_vm_no_dma_fences(vm)) {
> +                       struct dma_fence *fence =
> +                               xe_exec_queue_last_fence_get(q, vm);
> +
> +                       for (i = 0; i < num_syncs; i++)
> +                               xe_sync_entry_signal(&syncs[i], NULL,
> fence);
> +               }
> +
> +               goto err_exec;
> +       }
> +
>         if (xe_exec_queue_is_lr(q) && xe_exec_queue_ring_full(q)) {
>                 err = -EWOULDBLOCK;
>                 goto err_exec;
> @@ -327,6 +341,8 @@ int xe_exec_ioctl(struct drm_device *dev, void
> *data, struct drm_file *file)
>  
>         if (xe_exec_queue_is_lr(q))
>                 q->ring_ops->emit_job(job);
> +       if (!xe_vm_no_dma_fences(vm))
> +               xe_exec_queue_last_fence_set(q, vm, &job-
> >drm.s_fence->finished);
>         xe_sched_job_push(job);
>         xe_vm_reactivate_rebind(vm);
>  
> diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c
> b/drivers/gpu/drm/xe/xe_exec_queue.c
> index 4fd44a9203e4..35710b66e5de 100644
> --- a/drivers/gpu/drm/xe/xe_exec_queue.c
> +++ b/drivers/gpu/drm/xe/xe_exec_queue.c
> @@ -924,7 +924,10 @@ int xe_exec_queue_set_property_ioctl(struct
> drm_device *dev, void *data,
>  static void xe_exec_queue_last_fence_lockdep_assert(struct
> xe_exec_queue *q,
>                                                     struct xe_vm *vm)
>  {
> -       lockdep_assert_held_write(&vm->lock);
> +       if (q->flags & EXEC_QUEUE_FLAG_VM)
> +               lockdep_assert_held_write(&vm->lock);
> +       else
> +               xe_vm_assert_held(vm);
>  }
>  
>  /**
> diff --git a/drivers/gpu/drm/xe/xe_exec_queue_types.h
> b/drivers/gpu/drm/xe/xe_exec_queue_types.h
> index ecd761177567..35ffe7c55f25 100644
> --- a/drivers/gpu/drm/xe/xe_exec_queue_types.h
> +++ b/drivers/gpu/drm/xe/xe_exec_queue_types.h
> @@ -53,8 +53,9 @@ struct xe_exec_queue {
>         struct xe_hw_fence_irq *fence_irq;
>  
>         /**
> -        * @last_fence: last fence on engine, protected by vm->lock
> in write
> -        * mode if bind engine
> +        * @last_fence: last fence on exec queue, protected by vm-
> >lock in write
> +        * mode if bind exec queue, protected by dma resv lock if
> non-bind exec
> +        * queue
>          */
>         struct dma_fence *last_fence;
>  
> diff --git a/drivers/gpu/drm/xe/xe_sync.c
> b/drivers/gpu/drm/xe/xe_sync.c
> index 73ef259aa387..2461e7d4814c 100644
> --- a/drivers/gpu/drm/xe/xe_sync.c
> +++ b/drivers/gpu/drm/xe/xe_sync.c
> @@ -100,7 +100,7 @@ static void user_fence_cb(struct dma_fence
> *fence, struct dma_fence_cb *cb)
>  int xe_sync_entry_parse(struct xe_device *xe, struct xe_file *xef,
>                         struct xe_sync_entry *sync,
>                         struct drm_xe_sync __user *sync_user,
> -                       bool exec, bool no_dma_fences)
> +                       bool exec, bool no_dma_fences, bool exec_nop)

Here we have a number of bools indicating the context of a potential
caller. That makes the code hard to read. When reading the caller code
you'd both need to remember what each argument position means and
exactly what xe_sync_entry_parse does for a certain caller, for example
exec_nop.
One would have a set of flags instead
exec_nop becomes FLAG_DISALLOW_USER_FENCE

Otherwise LGTM.