public inbox for intel-xe@lists.freedesktop.org
 help / color / mirror / Atom feed
From: Matthew Brost <matthew.brost@intel.com>
To: "Summers, Stuart" <stuart.summers@intel.com>
Cc: "intel-xe@lists.freedesktop.org" <intel-xe@lists.freedesktop.org>
Subject: Re: [PATCH v3 04/11] drm/xe: Add vm to exec queues association
Date: Mon, 12 Jan 2026 17:30:14 -0800	[thread overview]
Message-ID: <aWWgJnJ0OCz36WeO@lstrano-desk.jf.intel.com> (raw)
In-Reply-To: <840197fff028c4de7c80d62e64b963dbef425979.camel@intel.com>

On Mon, Jan 12, 2026 at 06:04:53PM -0700, Summers, Stuart wrote:
> On Mon, 2026-01-12 at 15:27 -0800, Matthew Brost wrote:
> > Maintain a list of exec queues per vm which will be used by TLB
> > invalidation code to do context-ID based tlb invalidations.
> > 
> > Signed-off-by: Nirmoy Das <nirmoy.das@intel.com>
> > Signed-off-by: Matthew Brost <matthew.brost@intel.com>
> > Reviewed-by: Stuart Summers <stuart.summers@intel.com>
> > ---
> >  drivers/gpu/drm/xe/xe_device.h           |  7 ----
> >  drivers/gpu/drm/xe/xe_device_types.h     |  7 ++++
> >  drivers/gpu/drm/xe/xe_exec_queue.c       |  7 +++-
> >  drivers/gpu/drm/xe/xe_exec_queue_types.h |  3 ++
> >  drivers/gpu/drm/xe/xe_vm.c               | 46
> > ++++++++++++++++++++++++
> >  drivers/gpu/drm/xe/xe_vm.h               |  3 ++
> >  drivers/gpu/drm/xe/xe_vm_types.h         | 13 +++++++
> >  7 files changed, 78 insertions(+), 8 deletions(-)
> > 
> > diff --git a/drivers/gpu/drm/xe/xe_device.h
> > b/drivers/gpu/drm/xe/xe_device.h
> > index 10d04c324257..db939fc82f71 100644
> > --- a/drivers/gpu/drm/xe/xe_device.h
> > +++ b/drivers/gpu/drm/xe/xe_device.h
> > @@ -62,13 +62,6 @@ static inline struct xe_tile
> > *xe_device_get_root_tile(struct xe_device *xe)
> >         return &xe->tiles[0];
> >  }
> >  
> > -/*
> > - * Highest GT/tile count for any platform.  Used only for memory
> > allocation
> > - * sizing.  Any logic looping over GTs or mapping userspace GT IDs
> > into GT
> > - * structures should use the per-platform xe->info.max_gt_per_tile
> > instead.
> > - */
> > -#define XE_MAX_GT_PER_TILE 2
> > -
> >  static inline struct xe_gt *xe_device_get_gt(struct xe_device *xe,
> > u8 gt_id)
> >  {
> >         struct xe_tile *tile;
> > diff --git a/drivers/gpu/drm/xe/xe_device_types.h
> > b/drivers/gpu/drm/xe/xe_device_types.h
> > index 4dab3057f58d..8db870aaa382 100644
> > --- a/drivers/gpu/drm/xe/xe_device_types.h
> > +++ b/drivers/gpu/drm/xe/xe_device_types.h
> > @@ -79,6 +79,13 @@ enum xe_wedged_mode {
> >  #define XE_GT1         1
> >  #define XE_MAX_TILES_PER_DEVICE        (XE_GT1 + 1)
> >  
> > +/*
> > + * Highest GT/tile count for any platform.  Used only for memory
> > allocation
> > + * sizing.  Any logic looping over GTs or mapping userspace GT IDs
> > into GT
> > + * structures should use the per-platform xe->info.max_gt_per_tile
> > instead.
> > + */
> > +#define XE_MAX_GT_PER_TILE 2
> > +
> >  #define XE_MAX_ASID    (BIT(20))
> >  
> >  #define IS_PLATFORM_STEP(_xe, _platform, min_step, max_step)   \
> > diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c
> > b/drivers/gpu/drm/xe/xe_exec_queue.c
> > index b5737563ee14..ce309d848916 100644
> > --- a/drivers/gpu/drm/xe/xe_exec_queue.c
> > +++ b/drivers/gpu/drm/xe/xe_exec_queue.c
> > @@ -154,8 +154,10 @@ static void __xe_exec_queue_free(struct
> > xe_exec_queue *q)
> >         if (xe_exec_queue_is_multi_queue(q))
> >                 xe_exec_queue_group_cleanup(q);
> >  
> > -       if (q->vm)
> > +       if (q->vm) {
> > +               xe_vm_remove_exec_queue(q->vm, q);
> >                 xe_vm_put(q->vm);
> > +       }
> >  
> >         if (q->xef)
> >                 xe_file_put(q->xef);
> > @@ -226,6 +228,7 @@ static struct xe_exec_queue
> > *__xe_exec_queue_alloc(struct xe_device *xe,
> >         q->ring_ops = gt->ring_ops[hwe->class];
> >         q->ops = gt->exec_queue_ops;
> >         INIT_LIST_HEAD(&q->lr.link);
> > +       INIT_LIST_HEAD(&q->vm_exec_queue_link);
> >         INIT_LIST_HEAD(&q->multi_gt_link);
> >         INIT_LIST_HEAD(&q->hw_engine_group_link);
> >         INIT_LIST_HEAD(&q->pxp.link);
> > @@ -1205,6 +1208,8 @@ int xe_exec_queue_create_ioctl(struct
> > drm_device *dev, void *data,
> >         }
> >  
> >         q->xef = xe_file_get(xef);
> > +       if (eci[0].engine_class != DRM_XE_ENGINE_CLASS_VM_BIND)
> > +               xe_vm_add_exec_queue(vm, q);
> 
> This still will hit an issue if we're sending a TLB invalidation before
> we register the context with GuC, just to reiterate... of course we
> agreed to move forward here.
> 

Ah, no. The active vfunc called in last patch prevents against this.

> >  
> >         /* user id alloc must always be last in ioctl to prevent UAF
> > */
> >         err = xa_alloc(&xef->exec_queue.xa, &id, q, xa_limit_32b,
> > GFP_KERNEL);
> > diff --git a/drivers/gpu/drm/xe/xe_exec_queue_types.h
> > b/drivers/gpu/drm/xe/xe_exec_queue_types.h
> > index 5fc516b0bb77..d3e2789cf5bc 100644
> > --- a/drivers/gpu/drm/xe/xe_exec_queue_types.h
> > +++ b/drivers/gpu/drm/xe/xe_exec_queue_types.h
> > @@ -205,6 +205,9 @@ struct xe_exec_queue {
> >                 struct dma_fence *last_fence;
> >         } tlb_inval[XE_EXEC_QUEUE_TLB_INVAL_COUNT];
> >  
> > +       /** @vm_exec_queue_link: Link to track exec queue within a
> > VM's list of exec queues. */
> > +       struct list_head vm_exec_queue_link;
> > +
> >         /** @pxp: PXP info tracking */
> >         struct {
> >                 /** @pxp.type: PXP session type used by this queue */
> > diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
> > index bdb04d6bf39c..3a1a1bd74d8d 100644
> > --- a/drivers/gpu/drm/xe/xe_vm.c
> > +++ b/drivers/gpu/drm/xe/xe_vm.c
> > @@ -1530,11 +1530,23 @@ struct xe_vm *xe_vm_create(struct xe_device
> > *xe, u32 flags, struct xe_file *xef)
> >         INIT_WORK(&vm->destroy_work, vm_destroy_work_func);
> >  
> >         INIT_LIST_HEAD(&vm->preempt.exec_queues);
> > +       INIT_LIST_HEAD(&vm->exec_queues.list);
> >         if (flags & XE_VM_FLAG_FAULT_MODE)
> >                 vm->preempt.min_run_period_ms = xe-
> > >min_run_period_pf_ms;
> >         else
> >                 vm->preempt.min_run_period_ms = xe-
> > >min_run_period_lr_ms;
> >  
> > +       init_rwsem(&vm->exec_queues.lock);
> > +       if (IS_ENABLED(CONFIG_PROVE_LOCKING)) {
> > +               fs_reclaim_acquire(GFP_KERNEL);
> > +               might_lock(&vm->exec_queues.lock);
> > +               fs_reclaim_release(GFP_KERNEL);
> > +
> > +               down_read(&vm->exec_queues.lock);
> > +               might_lock(&xe_root_mmio_gt(xe)->uc.guc.ct.lock);
> > +               up_read(&vm->exec_queues.lock);
> > +       }
> > +
> >         for_each_tile(tile, xe, id)
> >                 xe_range_fence_tree_init(&vm->rftree[id]);
> >  
> > @@ -4570,3 +4582,37 @@ int xe_vm_alloc_cpu_addr_mirror_vma(struct
> > xe_vm *vm, uint64_t start, uint64_t r
> >         return xe_vm_alloc_vma(vm, &map_req, false);
> >  }
> >  
> > +/**
> > + * xe_vm_add_exec_queue() - Add exec queue to VM
> > + * @vm: The VM.
> > + * @q: The exec_queue
> > + */
> > +void xe_vm_add_exec_queue(struct xe_vm *vm, struct xe_exec_queue *q)
> > +{
> > +       /* User VMs and queues only */
> > +       xe_assert(vm->xe, !(q->flags & EXEC_QUEUE_FLAG_KERNEL));
> > +       xe_assert(vm->xe, !(q->flags & EXEC_QUEUE_FLAG_PERMANENT));
> > +       xe_assert(vm->xe, !(q->flags & EXEC_QUEUE_FLAG_VM));
> > +       xe_assert(vm->xe, !(q->flags & EXEC_QUEUE_FLAG_MIGRATE));
> > +       xe_assert(vm->xe, vm->xef);
> 
> Can you add a check here against has_ctx_tlb_inval? No need to maintain
> this list if the platform doesn't support this invalidation.
> 

Yes, I do that.

> Can we also assert that the q->vm is the same as the vm being passed
> above? We want to make sure we aren't adding a queue from another VM
> here.
> 

Yes, I can also do that.

Matt

> Thanks,
> Stuart
> 
> > +
> > +       down_write(&vm->exec_queues.lock);
> > +       list_add(&q->vm_exec_queue_link, &vm->exec_queues.list);
> > +       ++vm->exec_queues.count[q->gt->info.id];
> > +       up_write(&vm->exec_queues.lock);
> > +}
> > +
> > +/**
> > + * xe_vm_remove_exec_queue() - Remove exec queue from VM
> > + * @vm: The VM.
> > + * @q: The exec_queue
> > + */
> > +void xe_vm_remove_exec_queue(struct xe_vm *vm, struct xe_exec_queue
> > *q)
> > +{
> > +       down_write(&vm->exec_queues.lock);
> > +       if (!list_empty(&q->vm_exec_queue_link)) {
> > +               list_del(&q->vm_exec_queue_link);
> > +               --vm->exec_queues.count[q->gt->info.id];
> > +       }
> > +       up_write(&vm->exec_queues.lock);
> > +}
> > diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h
> > index 6cc98df47291..288115c7844a 100644
> > --- a/drivers/gpu/drm/xe/xe_vm.h
> > +++ b/drivers/gpu/drm/xe/xe_vm.h
> > @@ -287,6 +287,9 @@ static inline struct dma_resv *xe_vm_resv(struct
> > xe_vm *vm)
> >  
> >  void xe_vm_kill(struct xe_vm *vm, bool unlocked);
> >  
> > +void xe_vm_add_exec_queue(struct xe_vm *vm, struct xe_exec_queue
> > *q);
> > +void xe_vm_remove_exec_queue(struct xe_vm *vm, struct xe_exec_queue
> > *q);
> > +
> >  /**
> >   * xe_vm_assert_held(vm) - Assert that the vm's reservation object
> > is held.
> >   * @vm: The vm
> > diff --git a/drivers/gpu/drm/xe/xe_vm_types.h
> > b/drivers/gpu/drm/xe/xe_vm_types.h
> > index 437f64202f3b..87318a4f5b08 100644
> > --- a/drivers/gpu/drm/xe/xe_vm_types.h
> > +++ b/drivers/gpu/drm/xe/xe_vm_types.h
> > @@ -298,6 +298,19 @@ struct xe_vm {
> >                 struct list_head pm_activate_link;
> >         } preempt;
> >  
> > +       /** @exec_queues: Manages list of exec queues attached to
> > this VM, protected by lock. */
> > +       struct {
> > +               /** @exec_queues.list: list of exec queues attached
> > to this VM */
> > +               struct list_head list;
> > +               /**
> > +                * @exec_queues.count: count of exec queues attached
> > to this VM,
> > +                * per GT
> > +                */
> > +               int count[XE_MAX_TILES_PER_DEVICE *
> > XE_MAX_GT_PER_TILE];
> > +               /** @exec_queues.lock: lock to protect exec_queues
> > list */
> > +               struct rw_semaphore lock;
> > +       } exec_queues;
> > +
> >         /** @um: unified memory state */
> >         struct {
> >                 /** @asid: address space ID, unique to each VM */
> 

  reply	other threads:[~2026-01-13  1:30 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-01-12 23:27 [PATCH v3 00/11] Context based TLB invalidations Matthew Brost
2026-01-12 23:27 ` [PATCH v3 01/11] drm/xe: Add normalize_invalidation_range Matthew Brost
2026-01-12 23:27 ` [PATCH v3 02/11] drm/xe: Make usm.asid_to_vm allocation use GFP_NOWAIT Matthew Brost
2026-01-12 23:27 ` [PATCH v3 03/11] drm/xe: Add xe_device_asid_to_vm helper Matthew Brost
2026-01-13  1:01   ` Summers, Stuart
2026-01-13  1:36     ` Matthew Brost
2026-01-12 23:27 ` [PATCH v3 04/11] drm/xe: Add vm to exec queues association Matthew Brost
2026-01-13  1:04   ` Summers, Stuart
2026-01-13  1:30     ` Matthew Brost [this message]
2026-01-13 21:55       ` Summers, Stuart
2026-01-12 23:27 ` [PATCH v3 05/11] drm/xe: Taint TLB invalidation seqno lock with GFP_KERNEL Matthew Brost
2026-01-12 23:27 ` [PATCH v3 06/11] drm/xe: Rename send_tlb_inval_ppgtt to send_tlb_inval_asid_ppgtt Matthew Brost
2026-01-12 23:27 ` [PATCH v3 07/11] drm/xe: Add send_tlb_inval_ppgtt helper Matthew Brost
2026-01-12 23:27 ` [PATCH v3 08/11] drm/xe: Add xe_tlb_inval_idle helper Matthew Brost
2026-01-12 23:27 ` [PATCH v3 09/11] drm/xe: Add exec queue active vfunc Matthew Brost
2026-01-12 23:27 ` [PATCH v3 10/11] drm/xe: Add context-based invalidation to GuC TLB invalidation backend Matthew Brost
2026-01-13  1:28   ` Summers, Stuart
2026-01-13  1:34     ` Matthew Brost
2026-01-13 22:36       ` Summers, Stuart
2026-01-14 16:09         ` Matthew Brost
2026-01-14 23:45           ` Summers, Stuart
2026-01-12 23:27 ` [PATCH v3 11/11] drm/xe: Enable context TLB invalidations for CI Matthew Brost
2026-01-12 23:37 ` ✓ CI.KUnit: success for Context based TLB invalidations (rev3) Patchwork
2026-01-13  0:17 ` ✗ Xe.CI.BAT: failure " Patchwork

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=aWWgJnJ0OCz36WeO@lstrano-desk.jf.intel.com \
    --to=matthew.brost@intel.com \
    --cc=intel-xe@lists.freedesktop.org \
    --cc=stuart.summers@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox