-----Original Message-----
From: Zhang, Jianxun <jianxun.zhang@xxxxxxxxx>
Sent: Wednesday, March 12, 2025 9:28 AM
To: Cavitt, Jonathan <jonathan.cavitt@xxxxxxxxx>; Brost, Matthew <matthew.brost@xxxxxxxxx>
Cc: intel-xe@xxxxxxxxxxxxxxxxxxxxx; Gupta, saurabhg <saurabhg.gupta@xxxxxxxxx>; Zuo, Alex <alex.zuo@xxxxxxxxx>; joonas.lahtinen@xxxxxxxxxxxxxxx; Lin, Shuicheng <shuicheng.lin@xxxxxxxxx>; dri-devel@xxxxxxxxxxxxxxxxxxxxx
Subject: Re: [PATCH v7 4/6] drm/xe/uapi: Define drm_xe_vm_get_faults
>
> Sorry if my reply is still in a wrong format. I have set plain text in the web-based outlook this time but don't know if it really works.
>
> Refer to my inline comment, thanks.
> ________________________________________
> From: Cavitt, Jonathan <jonathan.cavitt@xxxxxxxxx>
> Sent: Tuesday, March 11, 2025 7:11 AM
> To: Brost, Matthew; Zhang, Jianxun
> Cc: intel-xe@xxxxxxxxxxxxxxxxxxxxx; Gupta, saurabhg; Zuo, Alex; joonas.lahtinen@xxxxxxxxxxxxxxx; Lin, Shuicheng; dri-devel@xxxxxxxxxxxxxxxxxxxxx; Cavitt, Jonathan
> Subject: RE: [PATCH v7 4/6] drm/xe/uapi: Define drm_xe_vm_get_faults
>
> -----Original Message-----
> From: Brost, Matthew <matthew.brost@xxxxxxxxx>
> Sent: Monday, March 10, 2025 9:51 PM
> To: Cavitt, Jonathan <jonathan.cavitt@xxxxxxxxx>
> Cc: intel-xe@xxxxxxxxxxxxxxxxxxxxx; Gupta, saurabhg <saurabhg.gupta@xxxxxxxxx>; Zuo, Alex <alex.zuo@xxxxxxxxx>; joonas.lahtinen@xxxxxxxxxxxxxxx; Zhang, Jianxun <jianxun.zhang@xxxxxxxxx>; Lin, Shuicheng <shuicheng.lin@xxxxxxxxx>; dri-devel@xxxxxxxxxxxxxxxxxxxxx
> Subject: Re: [PATCH v7 4/6] drm/xe/uapi: Define drm_xe_vm_get_faults
> >
> > On Mon, Mar 10, 2025 at 05:18:32PM +0000, Jonathan Cavitt wrote:
> > > Add initial declarations for the drm_xe_vm_get_faults ioctl.
> > >
> > > Signed-off-by: Jonathan Cavitt <jonathan.cavitt@xxxxxxxxx>
> > > ---
> > > include/uapi/drm/xe_drm.h | 49 +++++++++++++++++++++++++++++++++++++++
> > > 1 file changed, 49 insertions(+)
> > >
> > > diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h
> > > index 616916985e3f..90c2fcdbd5c1 100644
> > > --- a/include/uapi/drm/xe_drm.h
> > > +++ b/include/uapi/drm/xe_drm.h
> > > @@ -81,6 +81,7 @@ extern "C" {
> > > * - &DRM_IOCTL_XE_EXEC
> > > * - &DRM_IOCTL_XE_WAIT_USER_FENCE
> > > * - &DRM_IOCTL_XE_OBSERVATION
> > > + * - %DRM_IOCTL_XE_VM_GET_FAULTS
> >
> > This should be a generic "get VM property" IOCTL, not a specific IOCTL
> > that only retrieves faults. This allows for future expansion of the
> > uAPI.
>
> Question from @Zhang, Jianxun :
> """
> But first of all, should we regard faults as a property?
> """
> -Jonathan Cavitt
>
> Thanks for Jonathan relaying my question here. I just feel it is a little strange to treat "faults" as "property". Perhaps it is just a naming thing. But I get KMD wants to take an extensible and consolidated approach. Either/any way works for me in UMD.
I got in touch with Matt Brost, and this was his explanation:
"""
I can see that PoV, kinda a bikeshed but in general for query things we make them generic
and extensible to avoid having a ton of IOCTLs for very specific things
"""
I guess I'll prioritize reverting it back into a property get ioctl.
-Jonathan Cavitt
>
> Thanks!
>
> >
> > > */
> > >
> > > /*
> > > @@ -102,6 +103,7 @@ extern "C" {
> > > #define DRM_XE_EXEC 0x09
> > > #define DRM_XE_WAIT_USER_FENCE 0x0a
> > > #define DRM_XE_OBSERVATION 0x0b
> > > +#define DRM_XE_VM_GET_FAULTS 0x0c
> > >
> > > /* Must be kept compact -- no holes */
> > >
> > > @@ -117,6 +119,7 @@ extern "C" {
> > > #define DRM_IOCTL_XE_EXEC DRM_IOW(DRM_COMMAND_BASE + DRM_XE_EXEC, struct drm_xe_exec)
> > > #define DRM_IOCTL_XE_WAIT_USER_FENCE DRM_IOWR(DRM_COMMAND_BASE + DRM_XE_WAIT_USER_FENCE, struct drm_xe_wait_user_fence)
> > > #define DRM_IOCTL_XE_OBSERVATION DRM_IOW(DRM_COMMAND_BASE + DRM_XE_OBSERVATION, struct drm_xe_observation_param)
> > > +#define DRM_IOCTL_XE_VM_GET_FAULTS DRM_IOWR(DRM_COMMAND_BASE + DRM_XE_VM_GET_FAULTS, struct drm_xe_vm_get_faults)
> > >
> > > /**
> > > * DOC: Xe IOCTL Extensions
> > > @@ -1189,6 +1192,52 @@ struct drm_xe_vm_bind {
> > > __u64 reserved[2];
> > > };
> > >
> > > +struct xe_vm_fault {
> > > + /** @address: Address of the fault, if relevant */
> > > + __u64 address;
> > > +#define DRM_XE_FAULT_ADDRESS_TYPE_NONE_EXT 0
> > > +#define DRM_XE_FAULT_ADDRESS_TYPE_READ_INVALID_EXT 1
> > > +#define DRM_XE_FAULT_ADDRESS_TYPE_WRITE_INVALID_EXT 2
> > > + /** @address_type: , if relevant */
> > > + __u32 address_type;
> > > + /**
> > > + * @address_precision: Precision of faulted address, if relevant.
> > > + * Currently only SZ_4K.
> > > + */
> > > + __u32 address_precision;
> > > + /** @reserved: MBZ */
> > > + __u64 reserved[3];
> > > +};
> > > +
> > > +/**
> > > + * struct drm_xe_vm_get_faults - Input of &DRM_IOCTL_XE_VM_GET_FAULTS
> > > + *
> > > + * The user provides a VM ID, and the ioctl will
> > > + *
> > > + */
> > > +struct drm_xe_vm_get_faults {
> > > + /** @extensions: Pointer to the first extension struct, if any */
> > > + __u64 extensions;
> > > +
> > > + /** @vm_id: The ID of the VM to query the properties of */
> > > + __u32 vm_id;
> > > +
> > > + /** @size: Size to allocate for @ptr */
> > > + __u32 size;
> > > +
> > > + /** @fault_count: Number of faults to be returned */
> > > + __u32 fault_count;
> > > +
> >
> > fault_count is implied by size.
> >
> > Matt
> >
> > > + /** @pad: MBZ */
> > > + __u32 pad;
> > > +
> > > + /** @reserved: MBZ */
> > > + __u64 reserved[2];
> > > +
> > > + /** @faults: Pointer to user-defined array of xe_vm_fault of flexible size */
> > > + __u64 faults;
> > > +};
> > > +
> > > /**
> > > * struct drm_xe_exec_queue_create - Input of &DRM_IOCTL_XE_EXEC_QUEUE_CREATE
> > > *
> > > --
> > > 2.43.0
> > >
> >
>
