Re: [RFC v3 1/8] drm/xe/uapi: Add UAPI support for purgeable buffer objects

["Thomas Hellström" <thomas.hellstrom@linux.intel.com>]

On Wed, 2025-12-10 at 12:46 +0530, Yadav, Arvind wrote:
> 
> On 10-12-2025 11:03, Matthew Brost wrote:
> > On Wed, Dec 10, 2025 at 10:00:45AM +0530, Arvind Yadav wrote:
> > > From: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
> > > 
> > > Extend the DRM_XE_MADVISE ioctl to support purgeable buffer
> > > object
> > > management by adding DRM_XE_VMA_ATTR_PURGEABLE_STATE attribute
> > > type.
> > > 
> > > This allows userspace applications to provide memory usage hints
> > > to
> > > the kernel for better memory management under pressure:
> > > 
> > > This allows userspace applications to provide memory usage hints
> > > to
> > > the kernel for better memory management under pressure:
> > > 
> > > - WILLNEED: Buffer is needed and should not be purged. If the BO
> > > was
> > >    previously purged, retained field returns 0 indicating backing
> > > store
> > >    was lost (once purged, always purged semantics matching i915).
> > > 
> > > - DONTNEED: Buffer is not currently needed and may be purged by
> > > the
> > >    kernel under memory pressure to free resources. Only applies
> > > to
> > >    non-shared BOs.
> > > 
> > > The implementation includes a 'retained' output field (matching
> > > i915's
> > > drm_i915_gem_madvise.retained) that indicates whether the BO's
> > > backing
> > > store still exists (1) or has been purged (0).
> > > 
> > > v2:
> > >    - Add PURGED state for read-only status, change ioctl to
> > > DRM_IOWR,
> > >      add retained field for i915 compatibility
> > > 
> > > v3:
> > >    - UAPI rule should not be changed (Matthew Brost)
> > >    - Make 'retained' a userptr (Matthew Brost)
> > > 
> > > Cc: Matthew Brost <matthew.brost@intel.com>
> > > Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
> > > Signed-off-by: Himal Prasad Ghimiray
> > > <himal.prasad.ghimiray@intel.com>
> > > Signed-off-by: Arvind Yadav <arvind.yadav@intel.com>
> > > ---
> > >   include/uapi/drm/xe_drm.h | 39
> > > +++++++++++++++++++++++++++++++++++++++
> > >   1 file changed, 39 insertions(+)
> > > 
> > > diff --git a/include/uapi/drm/xe_drm.h
> > > b/include/uapi/drm/xe_drm.h
> > > index 876a076fa6c0..fc0dada62dd0 100644
> > > --- a/include/uapi/drm/xe_drm.h
> > > +++ b/include/uapi/drm/xe_drm.h
> > > @@ -2079,6 +2079,7 @@ struct drm_xe_madvise {
> > >   #define DRM_XE_MEM_RANGE_ATTR_PREFERRED_LOC	0
> > >   #define DRM_XE_MEM_RANGE_ATTR_ATOMIC		1
> > >   #define DRM_XE_MEM_RANGE_ATTR_PAT		2
> > > +#define DRM_XE_VMA_ATTR_PURGEABLE_STATE		3
> > >   	/** @type: type of attribute */
> > >   	__u32 type;
> > >   
> > > @@ -2157,6 +2158,44 @@ struct drm_xe_madvise {
> > >   			/** @pat_index.reserved: Reserved */
> > >   			__u64 reserved;
> > >   		} pat_index;
> > > +
> > > +		/**
> > > +		 * @purge_state_val: Purgeable state
> > > configuration
> > > +		 *
> > > +		 * Used when @type ==
> > > DRM_XE_VMA_ATTR_PURGEABLE_STATE.
> > > +		 *
> > > +		 * Configures the purgeable state of buffer
> > > objects in the specified
> > > +		 * virtual address range. This allows
> > > applications to hint to the kernel
> > > +		 * about bo's usage patterns for better memory
> > > management.
> > > +		 *
> > > +		 * Supported values for @purge_state_val.val:
> > > +		 *  - DRM_XE_VMA_PURGEABLE_STATE_WILLNEED (0):
> > > Marks BO as needed.
> > > +		 *    If BO was purged, returns retained=0
> > > (backing store lost).
> > > +		 *
> > > +		 *  - DRM_XE_VMA_PURGEABLE_STATE_DONTNEED (1):
> > > Hints that BO is not
> > > +		 *    currently needed. Kernel may purge it
> > > under memory pressure.
> > > +		 *    Only applies to non-shared BOs. Returns
> > > retained=1 if not purged.
> > > +		 */
> > > +		struct {
> > > +#define DRM_XE_VMA_PURGEABLE_STATE_WILLNEED	0
> > > +#define DRM_XE_VMA_PURGEABLE_STATE_DONTNEED	1
> > > +			/** @purge_state_val.val: value for
> > > DRM_XE_VMA_ATTR_PURGEABLE_STATE */
> > > +			__u32 val;
> > > +
> > > +			/* @purge_state_val.pad */
> > > +			__u32 pad;
> > > +			/**
> > > +			 * @purge_state_val.retained: Pointer to
> > > output field for backing
> > > +			 * store status.
> > > +			 *
> > > +			 * Userspace provides a pointer to u32.
> > > Kernel writes to it:
> > > +			 * 1 if backing store exists, 0 if
> > > purged.
> > > +			 * Similar to i915's
> > > drm_i915_gem_madvise.retained field.
> > > +			 */
> > > +			__u64 retained;
> > > +			/** @purge_state_val.reserved: Reserved
> > > */
> > > +			__u64 reserved;
> > You cannot make this part of the union (purge_state_val) larger
> > than the
> > existing union (16 bytes) or the bit layout of the IOCTL changes
> > and the
> > uAPI breaks.
> > 
> > So just drop the '__u64 reserved' field.
> Noted.
> > 
> > I'll also follow up if we can change an IOCTL from DRM_IOW to
> > DRM_IOWR
> > too. I honestly don't know if that is allowed or not.
> 
> 
> Noted. Please update us once you have clarity on whether changing
> from 
> DRM_IOW to DRM_IOWR is allowed, for future reference.

I think it is allowed, since AFAICT changing DRM_IOW to DRM_IOWR does
not change KMD code, only UMD code. So problem might occur only if a
UMD assumes one or the other.

/Thomas

> 
> ~Arvind
> 
> > 
> > Matt
> > 
> > > +		} purge_state_val;
> > >   	};
> > >   
> > >   	/** @reserved: Reserved */
> > > -- 
> > > 2.43.0
> > >