From: Matthew Brost <matthew.brost@intel.com>
To: intel-xe@lists.freedesktop.org
Cc: stuart.summers@intel.com, arvind.yadav@intel.com,
himal.prasad.ghimiray@intel.com,
thomas.hellstrom@linux.intel.com, francois.dugast@intel.com
Subject: [PATCH v3 17/25] drm/xe: Add device flag to enable PT mirroring across tiles
Date: Fri, 27 Feb 2026 17:34:53 -0800 [thread overview]
Message-ID: <20260228013501.106680-18-matthew.brost@intel.com> (raw)
In-Reply-To: <20260228013501.106680-1-matthew.brost@intel.com>
Some multi-tile devices may want to mirror page tables across tiles for
memory-bandwidth reasons, while others may not. Add a device flag that
allows enabling or disabling page-table mirroring across tiles.
Setting the flag to true (the existing behavior) on PVC, but both modes
have been tested and are working on PVC.
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
---
drivers/gpu/drm/xe/xe_device_types.h | 2 ++
drivers/gpu/drm/xe/xe_migrate.c | 5 ++--
drivers/gpu/drm/xe/xe_pci.c | 2 ++
drivers/gpu/drm/xe/xe_pci_types.h | 1 +
drivers/gpu/drm/xe/xe_pt.c | 38 ++++++++++++++++++++++++++--
drivers/gpu/drm/xe/xe_vm.c | 37 ++++++++++++++++++++++++---
drivers/gpu/drm/xe/xe_vm.h | 3 +++
7 files changed, 80 insertions(+), 8 deletions(-)
diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h
index 776e9e190320..b3737dfcc45c 100644
--- a/drivers/gpu/drm/xe/xe_device_types.h
+++ b/drivers/gpu/drm/xe/xe_device_types.h
@@ -208,6 +208,8 @@ struct xe_device {
u8 has_usm:1;
/** @info.has_64bit_timestamp: Device supports 64-bit timestamps */
u8 has_64bit_timestamp:1;
+ /** @info.has_pt_mirror: Device has PT mirroring across tiles */
+ u8 has_pt_mirror:1;
/** @info.is_dgfx: is discrete device */
u8 is_dgfx:1;
/** @info.needs_scratch: needs scratch page for oob prefetch to work */
diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index b5d4fc4d4c62..c9ee6325ec9d 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -183,7 +183,8 @@ static int xe_migrate_prepare_vm(struct xe_tile *tile, struct xe_migrate *m,
struct xe_device *xe = tile_to_xe(tile);
u16 pat_index = xe->pat.idx[XE_CACHE_WB];
u8 id = tile->id;
- u32 num_entries = NUM_PT_SLOTS, num_level = vm->pt_root[id]->level;
+ u32 num_entries = NUM_PT_SLOTS, num_level =
+ xe_vm_pt_root(vm, id)->level;
#define VRAM_IDENTITY_MAP_COUNT 2
u32 num_setup = num_level + VRAM_IDENTITY_MAP_COUNT;
#undef VRAM_IDENTITY_MAP_COUNT
@@ -210,7 +211,7 @@ static int xe_migrate_prepare_vm(struct xe_tile *tile, struct xe_migrate *m,
/* PT30 & PT31 reserved for 2M identity map */
pt29_ofs = xe_bo_size(bo) - 3 * XE_PAGE_SIZE;
entry = vm->pt_ops->pde_encode_bo(bo, pt29_ofs);
- xe_pt_write(xe, &vm->pt_root[id]->bo->vmap, 0, entry);
+ xe_pt_write(xe, &xe_vm_pt_root(vm, id)->bo->vmap, 0, entry);
map_ofs = (num_entries - num_setup) * XE_PAGE_SIZE;
diff --git a/drivers/gpu/drm/xe/xe_pci.c b/drivers/gpu/drm/xe/xe_pci.c
index 3ac99472d6dd..b8c8953833a5 100644
--- a/drivers/gpu/drm/xe/xe_pci.c
+++ b/drivers/gpu/drm/xe/xe_pci.c
@@ -352,6 +352,7 @@ static const __maybe_unused struct xe_device_desc pvc_desc = {
.dma_mask_size = 52,
.has_display = false,
.has_gsc_nvm = 1,
+ .has_pt_mirror = 1,
.has_heci_gscfi = 1,
.max_gt_per_tile = 1,
.max_remote_tiles = 1,
@@ -761,6 +762,7 @@ static int xe_info_init_early(struct xe_device *xe,
xe->info.has_soc_remapper_telem = desc->has_soc_remapper_telem;
xe->info.has_sriov = xe_configfs_primary_gt_allowed(to_pci_dev(xe->drm.dev)) &&
desc->has_sriov;
+ xe->info.has_pt_mirror = desc->has_pt_mirror;
xe->info.skip_guc_pc = desc->skip_guc_pc;
xe->info.skip_mtcfg = desc->skip_mtcfg;
xe->info.skip_pcode = desc->skip_pcode;
diff --git a/drivers/gpu/drm/xe/xe_pci_types.h b/drivers/gpu/drm/xe/xe_pci_types.h
index 47e8a1552c2b..14b688fbb4c1 100644
--- a/drivers/gpu/drm/xe/xe_pci_types.h
+++ b/drivers/gpu/drm/xe/xe_pci_types.h
@@ -57,6 +57,7 @@ struct xe_device_desc {
u8 has_soc_remapper_sysctrl:1;
u8 has_soc_remapper_telem:1;
u8 has_sriov:1;
+ u8 has_pt_mirror:1;
u8 needs_scratch:1;
u8 skip_guc_pc:1;
u8 skip_mtcfg:1;
diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c
index d91d80c92957..ef34fbfc14f0 100644
--- a/drivers/gpu/drm/xe/xe_pt.c
+++ b/drivers/gpu/drm/xe/xe_pt.c
@@ -734,7 +734,7 @@ xe_pt_stage_bind(struct xe_tile *tile, struct xe_vma *vma,
.wupd.entries = entries,
.clear_pt = clear_pt,
};
- struct xe_pt *pt = vm->pt_root[tile->id];
+ struct xe_pt *pt = xe_vm_pt_root(vm, tile->id);
int ret;
if (range) {
@@ -895,6 +895,11 @@ static int xe_pt_zap_ptes_entry(struct xe_ptw *parent, pgoff_t offset,
return 0;
}
+static bool pt_mirroring_disabled_for_tile(struct xe_vm *vm, u8 tile_id)
+{
+ return xe_vm_pt_root(vm, tile_id) != vm->pt_root[tile_id];
+}
+
static const struct xe_pt_walk_ops xe_pt_zap_ptes_ops = {
.pt_entry = xe_pt_zap_ptes_entry,
};
@@ -936,6 +941,9 @@ bool xe_pt_zap_ptes(struct xe_tile *tile, struct xe_vma *vma)
if (!(pt_mask & BIT(tile->id)))
return false;
+ if (pt_mirroring_disabled_for_tile(xe_vma_vm(vma), tile->id))
+ return true;
+
(void)xe_pt_walk_shared(&pt->base, pt->level, xe_vma_start(vma),
xe_vma_end(vma), &xe_walk.base);
@@ -988,6 +996,9 @@ bool xe_pt_zap_ptes_range(struct xe_tile *tile, struct xe_vm *vm,
if (!(pt_mask & BIT(tile->id)))
return false;
+ if (pt_mirroring_disabled_for_tile(vm, tile->id))
+ return true;
+
(void)xe_pt_walk_shared(&pt->base, pt->level, xe_svm_range_start(range),
xe_svm_range_end(range), &xe_walk.base);
@@ -1803,7 +1814,7 @@ static unsigned int xe_pt_stage_unbind(struct xe_tile *tile,
.wupd.entries = entries,
.prl = pt_update_op->prl,
};
- struct xe_pt *pt = vm->pt_root[tile->id];
+ struct xe_pt *pt = xe_vm_pt_root(vm, tile->id);
(void)xe_pt_walk_shared(&pt->base, pt->level, start, end,
&xe_walk.base);
@@ -2341,9 +2352,20 @@ int xe_pt_update_ops_prepare(struct xe_device *xe, struct xe_vma_ops *vops)
int id, err;
for_each_tile(tile, xe, id) {
+ struct xe_vm_pgtable_update_ops *pt_update_ops =
+ &vops->pt_update_ops[id];
+
if (!vops->pt_update_ops[id].num_ops)
continue;
+ if (pt_mirroring_disabled_for_tile(vops->vm, id)) {
+ struct xe_page_reclaim_list *prl = &pt_update_ops->prl;
+
+ /* Transfer root PT update ops PRL to current */
+ *prl = vops->pt_update_ops[0].prl;
+ continue;
+ }
+
err = __xe_pt_update_ops_prepare(tile, vops);
if (err)
return err;
@@ -2635,6 +2657,12 @@ xe_pt_update_ops_run(struct xe_device *xe, struct xe_vma_ops *vops)
struct xe_vm_pgtable_update_ops *pt_update_ops =
&vops->pt_update_ops[j];
+ if (pt_mirroring_disabled_for_tile(vm, j)) {
+ xe_tile_assert(tile, !get_current_op(pt_update_ops));
+ tile_mask |= BIT(tile->id);
+ continue;
+ }
+
for (i = 0; i < get_current_op(pt_update_ops); ++i) {
struct xe_vm_pgtable_update_op *pt_op =
to_pt_op(pt_update_ops, i);
@@ -2724,6 +2752,9 @@ void xe_pt_update_ops_fini(struct xe_device *xe, struct xe_vma_ops *vops)
if (!pt_update_ops->num_ops)
continue;
+ if (pt_mirroring_disabled_for_tile(vops->vm, id))
+ continue;
+
xe_page_reclaim_entries_put(pt_update_ops->prl.entries);
}
}
@@ -2748,6 +2779,9 @@ void xe_pt_update_ops_abort(struct xe_device *xe, struct xe_vma_ops *vops)
&vops->pt_update_ops[id];
int i;
+ if (pt_mirroring_disabled_for_tile(vops->vm, id))
+ continue;
+
for (i = pt_update_ops->num_ops - 1; i >= 0; --i) {
struct xe_vm_pgtable_update_op *pt_op =
to_pt_op(pt_update_ops, i);
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index b3928e05b70a..d4629e953b01 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -738,6 +738,14 @@ int xe_vm_rebind(struct xe_vm *vm, bool rebind_worker)
return err;
}
+static u8 adjust_rebind_tile_mask(struct xe_vm *vm, u8 tile_mask)
+{
+ if (vm->xe->info.has_pt_mirror)
+ return tile_mask;
+
+ return (0x1 << vm->xe->info.max_gt_per_tile) - 1;
+}
+
struct dma_fence *xe_vma_rebind(struct xe_vm *vm, struct xe_vma *vma, u8 tile_mask)
{
struct dma_fence *fence = NULL;
@@ -754,7 +762,8 @@ struct dma_fence *xe_vma_rebind(struct xe_vm *vm, struct xe_vma *vma, u8 tile_ma
vops.flags |= XE_VMA_OPS_FLAG_SKIP_TLB_WAIT |
XE_VMA_OPS_FLAG_WAIT_VM_BOOKKEEP;
- err = xe_vm_ops_add_rebind(&vops, vma, tile_mask);
+ err = xe_vm_ops_add_rebind(&vops, vma,
+ adjust_rebind_tile_mask(vm, tile_mask));
if (err)
return ERR_PTR(err);
@@ -840,7 +849,8 @@ struct dma_fence *xe_vm_range_rebind(struct xe_vm *vm,
vops.flags |= XE_VMA_OPS_FLAG_SKIP_TLB_WAIT |
XE_VMA_OPS_FLAG_WAIT_VM_BOOKKEEP;
- err = xe_vm_ops_add_range_rebind(&vops, vma, range, tile_mask);
+ err = xe_vm_ops_add_range_rebind(&vops, vma, range,
+ adjust_rebind_tile_mask(vm, tile_mask));
if (err)
return ERR_PTR(err);
@@ -1578,7 +1588,8 @@ struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags, struct xe_file *xef)
for_each_tile(tile, xe, id) {
if (flags & XE_VM_FLAG_MIGRATION &&
- tile->id != XE_VM_FLAG_TILE_ID(flags))
+ tile->id != XE_VM_FLAG_TILE_ID(flags) &&
+ (vm->xe->info.has_pt_mirror || id))
continue;
vm->pt_root[id] = xe_pt_create(vm, tile, xe->info.vm_max_level,
@@ -1887,7 +1898,7 @@ struct xe_vm *xe_vm_lookup(struct xe_file *xef, u32 id)
u64 xe_vm_pdp4_descriptor(struct xe_vm *vm, struct xe_tile *tile)
{
- return vm->pt_ops->pde_encode_bo(vm->pt_root[tile->id]->bo, 0);
+ return vm->pt_ops->pde_encode_bo(xe_vm_pt_root(vm, tile->id)->bo, 0);
}
static struct xe_exec_queue *
@@ -4583,3 +4594,21 @@ void xe_vm_remove_exec_queue(struct xe_vm *vm, struct xe_exec_queue *q)
}
up_write(&vm->exec_queues.lock);
}
+
+/**
+ * xe_vm_pt_root() - Retrieve VM page-table root
+ * @vm: The VM.
+ * @tile_id: Tile ID
+ *
+ * Retrieve VM page-table root for a tile ID, used to abstract if PT mirroring is
+ * enabled across tiles.
+ *
+ * Return: VM page-table root for a tile ID
+ */
+struct xe_pt *xe_vm_pt_root(struct xe_vm *vm, u8 tile_id)
+{
+ if (vm->xe->info.has_pt_mirror)
+ return vm->pt_root[tile_id];
+
+ return vm->pt_root[0];
+}
diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h
index f849e369432b..5a22f74ff332 100644
--- a/drivers/gpu/drm/xe/xe_vm.h
+++ b/drivers/gpu/drm/xe/xe_vm.h
@@ -425,4 +425,7 @@ static inline struct drm_exec *xe_vm_validation_exec(struct xe_vm *vm)
((READ_ONCE(tile_present) & ~READ_ONCE(tile_invalidated)) & BIT((tile)->id))
void xe_vma_mem_attr_copy(struct xe_vma_mem_attr *to, struct xe_vma_mem_attr *from);
+
+struct xe_pt *xe_vm_pt_root(struct xe_vm *vm, u8 tile_id);
+
#endif
--
2.34.1
next prev parent reply other threads:[~2026-02-28 1:35 UTC|newest]
Thread overview: 63+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-02-28 1:34 [PATCH v3 00/25] CPU binds and ULLS on migration queue Matthew Brost
2026-02-28 1:34 ` [PATCH v3 01/25] drm/xe: Drop struct xe_migrate_pt_update argument from populate/clear vfuns Matthew Brost
2026-03-05 14:17 ` Francois Dugast
2026-02-28 1:34 ` [PATCH v3 02/25] drm/xe: Add xe_migrate_update_pgtables_cpu_execute helper Matthew Brost
2026-03-05 14:39 ` Francois Dugast
2026-02-28 1:34 ` [PATCH v3 03/25] drm/xe: Decouple exec queue idle check from LRC Matthew Brost
2026-03-02 20:50 ` Summers, Stuart
2026-03-02 21:02 ` Matthew Brost
2026-03-03 21:26 ` Summers, Stuart
2026-03-03 22:42 ` Matthew Brost
2026-03-03 22:54 ` Summers, Stuart
2026-02-28 1:34 ` [PATCH v3 04/25] drm/xe: Add job count to GuC exec queue snapshot Matthew Brost
2026-03-02 20:50 ` Summers, Stuart
2026-02-28 1:34 ` [PATCH v3 05/25] drm/xe: Update xe_bo_put_deferred arguments to include writeback flag Matthew Brost
2026-04-01 12:20 ` Francois Dugast
2026-04-01 22:39 ` Matthew Brost
2026-02-28 1:34 ` [PATCH v3 06/25] drm/xe: Add XE_BO_FLAG_PUT_VM_ASYNC Matthew Brost
2026-04-01 12:22 ` Francois Dugast
2026-04-01 22:38 ` Matthew Brost
2026-02-28 1:34 ` [PATCH v3 07/25] drm/xe: Update scheduler job layer to support PT jobs Matthew Brost
2026-03-03 22:50 ` Summers, Stuart
2026-03-03 23:00 ` Matthew Brost
2026-02-28 1:34 ` [PATCH v3 08/25] drm/xe: Add helpers to access PT ops Matthew Brost
2026-04-07 15:22 ` Francois Dugast
2026-02-28 1:34 ` [PATCH v3 09/25] drm/xe: Add struct xe_pt_job_ops Matthew Brost
2026-03-03 23:26 ` Summers, Stuart
2026-03-03 23:28 ` Matthew Brost
2026-02-28 1:34 ` [PATCH v3 10/25] drm/xe: Update GuC submission backend to run PT jobs Matthew Brost
2026-03-03 23:28 ` Summers, Stuart
2026-03-04 0:26 ` Matthew Brost
2026-03-04 20:43 ` Summers, Stuart
2026-03-04 21:53 ` Matthew Brost
2026-03-05 20:24 ` Summers, Stuart
2026-02-28 1:34 ` [PATCH v3 11/25] drm/xe: Store level in struct xe_vm_pgtable_update Matthew Brost
2026-03-03 23:44 ` Summers, Stuart
2026-02-28 1:34 ` [PATCH v3 12/25] drm/xe: Don't use migrate exec queue for page fault binds Matthew Brost
2026-02-28 1:34 ` [PATCH v3 13/25] drm/xe: Enable CPU binds for jobs Matthew Brost
2026-02-28 1:34 ` [PATCH v3 14/25] drm/xe: Remove unused arguments from xe_migrate_pt_update_ops Matthew Brost
2026-02-28 1:34 ` [PATCH v3 15/25] drm/xe: Make bind queues operate cross-tile Matthew Brost
2026-02-28 1:34 ` [PATCH v3 16/25] drm/xe: Add CPU bind layer Matthew Brost
2026-02-28 1:34 ` Matthew Brost [this message]
2026-02-28 1:34 ` [PATCH v3 18/25] drm/xe: Add xe_hw_engine_write_ring_tail Matthew Brost
2026-02-28 1:34 ` [PATCH v3 19/25] drm/xe: Add ULLS support to LRC Matthew Brost
2026-03-05 20:21 ` Francois Dugast
2026-02-28 1:34 ` [PATCH v3 20/25] drm/xe: Add ULLS migration job support to migration layer Matthew Brost
2026-03-05 23:34 ` Summers, Stuart
2026-03-09 23:11 ` Matthew Brost
2026-02-28 1:34 ` [PATCH v3 21/25] drm/xe: Add MI_SEMAPHORE_WAIT instruction defs Matthew Brost
2026-02-28 1:34 ` [PATCH v3 22/25] drm/xe: Add ULLS migration job support to ring ops Matthew Brost
2026-02-28 1:34 ` [PATCH v3 23/25] drm/xe: Add ULLS migration job support to GuC submission Matthew Brost
2026-02-28 1:35 ` [PATCH v3 24/25] drm/xe: Enter ULLS for migration jobs upon page fault or SVM prefetch Matthew Brost
2026-02-28 1:35 ` [PATCH v3 25/25] drm/xe: Add modparam to enable / disable ULLS on migrate queue Matthew Brost
2026-03-05 22:59 ` Summers, Stuart
2026-04-01 22:44 ` Matthew Brost
2026-02-28 1:43 ` ✗ CI.checkpatch: warning for CPU binds and ULLS on migration queue (rev3) Patchwork
2026-02-28 1:44 ` ✓ CI.KUnit: success " Patchwork
2026-02-28 2:32 ` ✓ Xe.CI.BAT: " Patchwork
2026-02-28 13:59 ` ✗ Xe.CI.FULL: failure " Patchwork
2026-03-02 17:54 ` Summers, Stuart
2026-03-02 18:13 ` Matthew Brost
2026-03-05 22:56 ` [PATCH v3 00/25] CPU binds and ULLS on migration queue Summers, Stuart
2026-03-10 22:17 ` Matthew Brost
2026-03-20 15:31 ` Thomas Hellström
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=20260228013501.106680-18-matthew.brost@intel.com \
--to=matthew.brost@intel.com \
--cc=arvind.yadav@intel.com \
--cc=francois.dugast@intel.com \
--cc=himal.prasad.ghimiray@intel.com \
--cc=intel-xe@lists.freedesktop.org \
--cc=stuart.summers@intel.com \
--cc=thomas.hellstrom@linux.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.