Re: [PATCH v7 22/24] drm/xe: Enter ULLS for migration jobs upon page fault or SVM prefetch

[Matthew Brost <matthew.brost@intel.com>]

On Fri, Sep 25, 2026 at 07:49:43PM +0200, Maarten Lankhorst wrote:
> Hey,
> 
> I know this has been reviewed, but can it be changed to have xe_migrate_ulls_enter + xe_migrate_ulls_leave?
> It decreases the amount of pingponging with debugging enabled.
> 
> I kept below patch in my tree that did just that, feel free to merge with this patch.
> 

Ok, I see the potential races where before we get to a copy job in
either prefetch or a pagefault before the exit period ULLS will disarm
itself - I'd hope within the default of 5ms that would never happen in
practice as 5ms is a *really* long time in hot paths (prefetch, SVM).

Is this the issue you are seeing in debug builds, I personally have
never noticed this but generally run with perf builds.

Are you using ULLS somewhere else where 5ms can be hit more easier?

Want to get a full picture before commiting to something.

Matt

> Kind regards,
> ~Maarten Lankhorst
> 
> commit 6beeb2f7ff909bdaf9f8b1eeaa014cd15a65c78b
> Author: Maarten Lankhorst <dev@lankhorst.se>
> Date:   Mon Jun 8 19:05:46 2026 +0200
> 
>     drm/xe: Keep ulls alive while servicing ops.
>     
>     Instead of bumping at the start, when performing a lot of work ulls may
>     run longer, so keep track using a refcount to keep the full benefit of
>     ulls.
>     
>     Signed-off-by: Maarten Lankhorst <dev@lankhorst.se>
> 
> diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
> index d28da51d71452..f0b6641dd9815 100644
> --- a/drivers/gpu/drm/xe/xe_migrate.c
> +++ b/drivers/gpu/drm/xe/xe_migrate.c
> @@ -58,6 +58,8 @@ struct xe_migrate {
>      struct xe_tile *tile;
>      /** @job_mutex: Timeline mutex for @eng. */
>      struct mutex job_mutex;
> +    /** @ulls_used: How many outstanding ulls operations there are */
> +    atomic_t ulls_used;
>      /** @pt_bo: Page-table buffer object. */
>      struct xe_bo *pt_bo;
>      /** @batch_base_ofs: VM offset of the migration batch buffer */
> @@ -475,6 +477,8 @@ static int xe_migrate_lock_prepare_vm(struct xe_tile *tile, struct xe_migrate *m
>   *
>   * If DGFX and not a VF, enter ULLS mode bypassing GuC / HW context
>   * switches by utilizing semaphore and continuously running batches.
> + *
> + * Pairs with xe_migrate_ulls_leave().
>   */
>  void xe_migrate_ulls_enter(struct xe_migrate *m)
>  {
> @@ -488,6 +492,12 @@ void xe_migrate_ulls_enter(struct xe_migrate *m)
>      if (!IS_DGFX(xe) || IS_SRIOV_VF(xe) || !xe->info.ulls_enable)
>          return;
>  
> +    /* Bump */
> +    if (atomic_inc_return(&m->ulls_used) > 1)
> +        return;
> +
> +    cancel_delayed_work_sync(&m->ulls.exit_work);
> +
>  job_alloc:
>      if (alloc) {
>          /*
> @@ -534,10 +544,30 @@ void xe_migrate_ulls_enter(struct xe_migrate *m)
>      }
>      if (job)
>          xe_sched_job_put(job);
> +    mutex_unlock(&m->job_mutex);
> +}
> +
> +/**
> + * xe_migrate_ulls_leave() - Leave ULLS mode
> + * @m: The migration context.
> + *
> + * Leaves the critical part of the migration context, it may continue to be enabled.
> + * Pairs with xe_migrate_ulls_enter().
> + */
> +void xe_migrate_ulls_leave(struct xe_migrate *m)
> +{
> +    struct xe_device *xe = tile_to_xe(m->tile);
> +
> +    if (!IS_DGFX(xe) || IS_SRIOV_VF(xe) || !xe->info.ulls_enable)
> +        return;
> +
> +    if (atomic_dec_return(&m->ulls_used))
> +        return;
> +
> +    guard(mutex)(&m->job_mutex);
>      if (m->ulls.enabled)
>          mod_delayed_work(system_percpu_wq, &m->ulls.exit_work,
>                   ULLS_EXIT_JIFFIES);
> -    mutex_unlock(&m->job_mutex);
>  }
>  
>  static void xe_migrate_ulls_exit(struct work_struct *work)
> @@ -599,8 +629,8 @@ static void xe_migrate_ulls_exit(struct work_struct *work)
>                   ULLS_EXIT_JIFFIES);
>      }
>  
> -    drm_dev_exit(idx);
>      mutex_unlock(&m->job_mutex);
> +    drm_dev_exit(idx);
>  }
>  
>  /**
> diff --git a/drivers/gpu/drm/xe/xe_migrate.h b/drivers/gpu/drm/xe/xe_migrate.h
> index 2e8be10fdb71f..c909e1afb476e 100644
> --- a/drivers/gpu/drm/xe/xe_migrate.h
> +++ b/drivers/gpu/drm/xe/xe_migrate.h
> @@ -98,5 +98,6 @@ int xe_migrate_debug_ccs_overlap(struct xe_migrate *m,
>  #endif
>  
>  void xe_migrate_ulls_enter(struct xe_migrate *m);
> +void xe_migrate_ulls_leave(struct xe_migrate *m);
>  
>  #endif
> diff --git a/drivers/gpu/drm/xe/xe_pagefault.c b/drivers/gpu/drm/xe/xe_pagefault.c
> index 782ed50a2a43e..51b2cb8fdcf1c 100644
> --- a/drivers/gpu/drm/xe/xe_pagefault.c
> +++ b/drivers/gpu/drm/xe/xe_pagefault.c
> @@ -315,6 +315,7 @@ static int xe_pagefault_service(struct xe_pagefault *pf)
>  
>  unlock_vm:
>      up_read(&vm->lock);
> +    xe_migrate_ulls_leave(gt_to_tile(gt)->migrate);
>      xe_vm_put(vm);
>  
>      return err;
> diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
> index a1eca4871175b..fc9f587a35905 100644
> --- a/drivers/gpu/drm/xe/xe_vm.c
> +++ b/drivers/gpu/drm/xe/xe_vm.c
> @@ -2557,7 +2557,7 @@ vm_bind_ioctl_ops_create(struct xe_vm *vm, struct xe_vma_ops *vops,
>                  if (addr)
>                      goto alloc_next_range;
>                  else
> -                    goto print_op_label;
> +                    goto ulls_leave;
>              }
>  
>              if (IS_ERR(svm_range)) {
> @@ -2598,8 +2598,10 @@ vm_bind_ioctl_ops_create(struct xe_vm *vm, struct xe_vma_ops *vops,
>              if (need_put)
>                  xe_svm_range_put(svm_range);
>  
> +ulls_leave:
> +            for_each_tile(tile, vm->xe, id)
> +                xe_migrate_ulls_leave(tile->migrate);
>          }
> -print_op_label:
>          print_op(vm->xe, __op);
>      }
>  
> 
> 
> 
> On 9/25/26 06:53, Matthew Brost wrote:
> > Call xe_migrate_ulls_enter upon page fault or SVM prefetch in an
> > effort speed up these critical paths.
> >
> > Signed-off-by: Matthew Brost <matthew.brost@intel.com>
> > Reviewed-by: Shuicheng Lin <shuicheng.lin@intel.com>
> > Reviewed-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
> >
> > ---
> > v7:
> >  - s/migration/migrate (Shuicheng)
> > ---
> >  drivers/gpu/drm/xe/xe_pagefault.c | 3 +++
> >  drivers/gpu/drm/xe/xe_vm.c        | 4 +++-
> >  2 files changed, 6 insertions(+), 1 deletion(-)
> >
> > diff --git a/drivers/gpu/drm/xe/xe_pagefault.c b/drivers/gpu/drm/xe/xe_pagefault.c
> > index f9e5bd41cfd1..f219e9e3b73e 100644
> > --- a/drivers/gpu/drm/xe/xe_pagefault.c
> > +++ b/drivers/gpu/drm/xe/xe_pagefault.c
> > @@ -15,6 +15,7 @@
> >  #include "xe_gt_stats.h"
> >  #include "xe_hw_engine.h"
> >  #include "xe_log.h"
> > +#include "xe_migrate.h"
> >  #include "xe_pagefault.h"
> >  #include "xe_pagefault_types.h"
> >  #include "xe_pm.h"
> > @@ -281,6 +282,8 @@ static int xe_pagefault_service(struct xe_pagefault *pf)
> >  	if (IS_ERR(vm))
> >  		return PTR_ERR(vm);
> >  
> > +	xe_migrate_ulls_enter(gt_to_tile(gt)->migrate);
> > +
> >  	down_read(&vm->lock);
> >  
> >  	if (xe_vm_is_closed(vm)) {
> > diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
> > index f66bd1de2b70..425c678f4480 100644
> > --- a/drivers/gpu/drm/xe/xe_vm.c
> > +++ b/drivers/gpu/drm/xe/xe_vm.c
> > @@ -2528,8 +2528,10 @@ vm_bind_ioctl_ops_create(struct xe_vm *vm, struct xe_vma_ops *vops,
> >  			ctx.devmem_possible = IS_DGFX(vm->xe) &&
> >  					      IS_ENABLED(CONFIG_DRM_XE_PAGEMAP);
> >  
> > -			for_each_tile(tile, vm->xe, id)
> > +			for_each_tile(tile, vm->xe, id) {
> > +				xe_migrate_ulls_enter(tile->migrate);
> >  				tile_mask |= 0x1 << id;
> > +			}
> >  
> >  			if (prefetch_region == DRM_XE_CONSULT_MEM_ADVISE_PREF_LOC) {
> >  				dpagemap = xe_vma_resolve_pagemap(vma,
>