Re: [Intel-xe] [PATCH v2 1/1] drm/xe/uapi: Use LR abbrev for long-running vms

[Rodrigo Vivi <rodrigo.vivi@intel.com>]

On Mon, Nov 27, 2023 at 04:03:30PM +0100, Thomas Hellström wrote:
> Currently we're using "compute mode" for long running VMs using
> preempt-fences for memory management, and "fault mode" for long
> running VMs using page faults.
> 
> Change this to use the terminology "long-running" abbreviated as LR for
> long-running VMs. These VMs can then either be in preempt-fence mode or
> fault mode. The user can force fault mode at creation time, but otherwise
> the driver can choose to use fault- or preempt-fence mode for long-running
> vms depending on the device capabilities. Initially unless fault-mode is
> specified, the driver uses preempt-fence mode.
> 
> v2:
> - Fix commit message wording and the documentation around
>   CREATE_FLAG_LR_MODE and CREATE_FLAG_FAULT_MODE
> 
> Cc: Matthew Brost <matthew.brost@intel.com>
> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
> Cc: Francois Dugast <francois.dugast@intel.com>
> Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
> ---
>  drivers/gpu/drm/xe/xe_vm.c |  8 ++++----
>  include/uapi/drm/xe_drm.h  | 23 ++++++++++++++++++++++-
>  2 files changed, 26 insertions(+), 5 deletions(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
> index aa965e90ce12..6d35067ed8bc 100644
> --- a/drivers/gpu/drm/xe/xe_vm.c
> +++ b/drivers/gpu/drm/xe/xe_vm.c
> @@ -1919,7 +1919,7 @@ static int xe_vm_unbind(struct xe_vm *vm, struct xe_vma *vma,
>  }
>  
>  #define ALL_DRM_XE_VM_CREATE_FLAGS (DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE | \
> -				    DRM_XE_VM_CREATE_FLAG_COMPUTE_MODE | \
> +				    DRM_XE_VM_CREATE_FLAG_LR_MODE | \
>  				    DRM_XE_VM_CREATE_FLAG_ASYNC_DEFAULT | \
>  				    DRM_XE_VM_CREATE_FLAG_FAULT_MODE)
>  
> @@ -1955,7 +1955,7 @@ int xe_vm_create_ioctl(struct drm_device *dev, void *data,
>  			 args->flags & DRM_XE_VM_CREATE_FLAG_FAULT_MODE))
>  		return -EINVAL;
>  
> -	if (XE_IOCTL_DBG(xe, args->flags & DRM_XE_VM_CREATE_FLAG_COMPUTE_MODE &&
> +	if (XE_IOCTL_DBG(xe, !(args->flags & DRM_XE_VM_CREATE_FLAG_LR_MODE) &&
>  			 args->flags & DRM_XE_VM_CREATE_FLAG_FAULT_MODE))
>  		return -EINVAL;
>  
> @@ -1972,12 +1972,12 @@ int xe_vm_create_ioctl(struct drm_device *dev, void *data,
>  
>  	if (args->flags & DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE)
>  		flags |= XE_VM_FLAG_SCRATCH_PAGE;
> -	if (args->flags & DRM_XE_VM_CREATE_FLAG_COMPUTE_MODE)
> +	if (args->flags & DRM_XE_VM_CREATE_FLAG_LR_MODE)
>  		flags |= XE_VM_FLAG_LR_MODE;
>  	if (args->flags & DRM_XE_VM_CREATE_FLAG_ASYNC_DEFAULT)
>  		flags |= XE_VM_FLAG_ASYNC_DEFAULT;
>  	if (args->flags & DRM_XE_VM_CREATE_FLAG_FAULT_MODE)
> -		flags |= XE_VM_FLAG_LR_MODE | XE_VM_FLAG_FAULT_MODE;
> +		flags |= XE_VM_FLAG_FAULT_MODE;
>  
>  	vm = xe_vm_create(xe, flags);
>  	if (IS_ERR(vm))
> diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h
> index 88f3aca02b08..2810997a6db4 100644
> --- a/include/uapi/drm/xe_drm.h
> +++ b/include/uapi/drm/xe_drm.h
> @@ -589,8 +589,29 @@ struct drm_xe_vm_create {
>  	__u64 extensions;
>  
>  #define DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE	(1 << 0)
> -#define DRM_XE_VM_CREATE_FLAG_COMPUTE_MODE	(1 << 1)
> +	/*
> +	 * An LR, or Long Running VM accepts exec submissions
> +	 * to its exec_queues that don't have an upper time limit on
> +	 * the job execution time. But exec submissions to these
> +	 * don't allow any of the flags DRM_XE_SYNC_FLAG_SYNCOBJ,
> +	 * DRM_XE_SYNC_FLAG_TIMELINE_SYNCOBJ, DRM_XE_SYNC_FLAG_DMA_BUF,
> +	 * used as out-syncobjs, that is, together with DRM_XE_SYNC_FLAG_SIGNAL.
> +	 * LR VMs can be created in recoverable page-fault mode using
> +	 * DRM_XE_VM_CREATE_FLAG_FAULT_MODE, if the device supports it.
> +	 * If that flag is omitted, the UMD can not rely on the slightly
> +	 * different per-VM overcommit semantics that are enabled by
> +	 * DRM_XE_VM_CREATE_FLAG_FAULT_MODE (see below), but KMD may
> +	 * still enable recoverable pagefaults if supported by the device.
> +	 */
> +#define DRM_XE_VM_CREATE_FLAG_LR_MODE	        (1 << 1)
>  #define DRM_XE_VM_CREATE_FLAG_ASYNC_DEFAULT	(1 << 2)
> +	/*
> +	 * DRM_XE_VM_CREATE_FLAG_FAULT_MODE requires also
> +	 * DRM_XE_VM_CREATE_FLAG_LR_MODE. It allows memory to be allocated
> +	 * on demand when accessed, and also allows per-VM overcommit of memory.
> +	 * The xe driver internally uses recoverable pagefaults to implement
> +	 * this.

what happens if user selects this flag in a hardware that doesn't support
recoverable pagefaults?

> +	 */
>  #define DRM_XE_VM_CREATE_FLAG_FAULT_MODE	(1 << 3)
>  	/** @flags: Flags */
>  	__u32 flags;
> -- 
> 2.41.0
>