From: Matt Roper <matthew.d.roper@intel.com>
To: intel-xe@lists.freedesktop.org
Cc: matthew.d.roper@intel.com,
Ravi Kumar Vodapalli <ravi.kumar.vodapalli@intel.com>
Subject: [PATCH v4 5/7] drm/xe: Assign GT IDs properly on multi-tile + multi-GT platforms
Date: Tue, 1 Jul 2025 13:13:26 -0700 [thread overview]
Message-ID: <20250701201320.2514369-14-matthew.d.roper@intel.com> (raw)
In-Reply-To: <20250701201320.2514369-9-matthew.d.roper@intel.com>
Although "multi-tile" and "multiple GTs per tile" are mutually-exclusive
characteristics on all of our platforms today, this may not always be
true. Assign GT IDs according to xe->info.max_gt_per_tile in a way that
should work even if future platforms have different configurations.
This patch should not change the behavior of current platforms; it only
future-proofs for potential future designs.
v2:
- Re-calculate gt_count if tile count gets reduced by MTCFG. (PVC CI)
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: Ravi Kumar Vodapalli<ravi.kumar.vodapalli@intel.com>
---
drivers/gpu/drm/xe/xe_mmio.c | 16 ++++++++++------
drivers/gpu/drm/xe/xe_pci.c | 14 ++++----------
2 files changed, 14 insertions(+), 16 deletions(-)
diff --git a/drivers/gpu/drm/xe/xe_mmio.c b/drivers/gpu/drm/xe/xe_mmio.c
index 7357458bc0d2..751586d6806a 100644
--- a/drivers/gpu/drm/xe/xe_mmio.c
+++ b/drivers/gpu/drm/xe/xe_mmio.c
@@ -55,6 +55,7 @@ static void tiles_fini(void *arg)
static void mmio_multi_tile_setup(struct xe_device *xe, size_t tile_mmio_size)
{
struct xe_tile *tile;
+ struct xe_gt *gt;
u8 id;
/*
@@ -67,7 +68,7 @@ static void mmio_multi_tile_setup(struct xe_device *xe, size_t tile_mmio_size)
/* Possibly override number of tile based on configuration register */
if (!xe->info.skip_mtcfg) {
struct xe_mmio *mmio = xe_root_tile_mmio(xe);
- u8 tile_count;
+ u8 tile_count, gt_count;
u32 mtcfg;
/*
@@ -84,12 +85,15 @@ static void mmio_multi_tile_setup(struct xe_device *xe, size_t tile_mmio_size)
xe->info.tile_count = tile_count;
/*
- * FIXME: Needs some work for standalone media, but
- * should be impossible with multi-tile for now:
- * multi-tile platform with standalone media doesn't
- * exist
+ * We've already setup gt_count according to the full
+ * tile count. Re-calculate it to only include the GTs
+ * that belong to the remaining tile(s).
*/
- xe->info.gt_count = xe->info.tile_count;
+ gt_count = 0;
+ for_each_gt(gt, xe, id)
+ if (gt->info.id < tile_count * xe->info.max_gt_per_tile)
+ gt_count++;
+ xe->info.gt_count = gt_count;
}
}
diff --git a/drivers/gpu/drm/xe/xe_pci.c b/drivers/gpu/drm/xe/xe_pci.c
index 658bfbddf9a8..bccd81e19bb0 100644
--- a/drivers/gpu/drm/xe/xe_pci.c
+++ b/drivers/gpu/drm/xe/xe_pci.c
@@ -694,10 +694,11 @@ static int xe_info_init(struct xe_device *xe,
*/
for_each_tile(tile, xe, id) {
gt = tile->primary_gt;
- gt->info.id = xe->info.gt_count++;
gt->info.type = XE_GT_TYPE_MAIN;
+ gt->info.id = tile->id * xe->info.max_gt_per_tile;
gt->info.has_indirect_ring_state = graphics_desc->has_indirect_ring_state;
gt->info.engine_mask = graphics_desc->hw_engine_mask;
+ xe->info.gt_count++;
if (MEDIA_VER(xe) < 13 && media_desc)
gt->info.engine_mask |= media_desc->hw_engine_mask;
@@ -715,17 +716,10 @@ static int xe_info_init(struct xe_device *xe,
gt = tile->media_gt;
gt->info.type = XE_GT_TYPE_MEDIA;
+ gt->info.id = tile->id * xe->info.max_gt_per_tile + 1;
gt->info.has_indirect_ring_state = media_desc->has_indirect_ring_state;
gt->info.engine_mask = media_desc->hw_engine_mask;
-
- /*
- * FIXME: At the moment multi-tile and standalone media are
- * mutually exclusive on current platforms. We'll need to
- * come up with a better way to number GTs if we ever wind
- * up with platforms that support both together.
- */
- drm_WARN_ON(&xe->drm, id != 0);
- gt->info.id = xe->info.gt_count++;
+ xe->info.gt_count++;
}
return 0;
--
2.49.0
next prev parent reply other threads:[~2025-07-01 20:13 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-07-01 20:13 [PATCH v4 0/7] Future-proof for multi-tile + multi-GT cases Matt Roper
2025-07-01 20:13 ` [PATCH v4 1/7] drm/xe/pmu: Fix GT sanity check in event_supported() Matt Roper
2025-07-01 20:13 ` [PATCH v4 2/7] drm/xe: Export xe_step_name for kunit tests Matt Roper
2025-07-01 20:13 ` [PATCH v4 3/7] drm/xe: Track maximum GTs per tile on a per-platform basis Matt Roper
2025-07-01 20:13 ` [PATCH v4 4/7] drm/xe/tests/pci: Ensure all platforms have a valid GT/tile count Matt Roper
2025-07-01 20:13 ` Matt Roper [this message]
2025-07-01 20:13 ` [PATCH v4 6/7] drm/xe: Don't compare GT ID to GT count when determining valid GTs Matt Roper
2025-07-01 20:13 ` [PATCH v4 7/7] drm/xe/xe_query: Use separate iterator while filling GT list Matt Roper
2025-07-01 20:18 ` ✗ CI.checkpatch: warning for Future-proof for multi-tile + multi-GT cases (rev6) Patchwork
2025-07-01 20:19 ` ✓ CI.KUnit: success " Patchwork
2025-07-02 5:09 ` ✗ CI.checkpatch: warning for Future-proof for multi-tile + multi-GT cases (rev7) Patchwork
2025-07-02 5:10 ` ✓ CI.KUnit: success " Patchwork
2025-07-02 6:01 ` ✓ Xe.CI.BAT: " Patchwork
2025-07-03 12:47 ` ✗ Xe.CI.Full: failure for Future-proof for multi-tile + multi-GT cases (rev6) Patchwork
2025-07-03 18:27 ` ✗ Xe.CI.Full: failure for Future-proof for multi-tile + multi-GT cases (rev7) 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=20250701201320.2514369-14-matthew.d.roper@intel.com \
--to=matthew.d.roper@intel.com \
--cc=intel-xe@lists.freedesktop.org \
--cc=ravi.kumar.vodapalli@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