[Intel-xe] [PATCH v3 01/31] drm/xe/mtl: Disable media GT

[Matt Roper]

On Wed, May 31, 2023 at 10:45:39AM -0300, Gustavo Sousa wrote:
> Quoting Matt Roper (2023-05-30 18:15:19-03:00)
> >Xe incorrectly conflates the concept of 'tile' and 'GT.'  Since MTL's
> >media support is not yet functioning properly, let's just disable it
> >completely for now while we fix the fundamental driver design.  Support
> >for media GTs on platforms like MTL will be re-added later.
> >
> >v2:
> > - Drop some unrelated code cleanup that didn't belong in this patch.
> >   (Lucas)
> >
> >Cc: Lucas De Marchi <lucas.demarchi at intel.com>
> >Reviewed-by: Matt Atwood <matthew.s.atwood at intel.com>
> >Reviewed-by: Lucas De Marchi <lucas.demarchi at intel.com>
> >Signed-off-by: Matt Roper <matthew.d.roper at intel.com>
> >---
> > drivers/gpu/drm/xe/xe_mmio.c |  2 --
> > drivers/gpu/drm/xe/xe_pci.c  | 13 +------------
> > 2 files changed, 1 insertion(+), 14 deletions(-)
> >
> >diff --git a/drivers/gpu/drm/xe/xe_mmio.c b/drivers/gpu/drm/xe/xe_mmio.c
> >index d3b57669c9a7..ef2353eef6fe 100644
> >--- a/drivers/gpu/drm/xe/xe_mmio.c
> >+++ b/drivers/gpu/drm/xe/xe_mmio.c
> >@@ -340,8 +340,6 @@ static void xe_mmio_probe_tiles(struct xe_device *xe)
> >         mtcfg = xe_mmio_read64(gt, XEHP_MTCFG_ADDR);
> >         adj_tile_count = xe->info.tile_count =
> >                 REG_FIELD_GET(TILE_COUNT, mtcfg) + 1;
> >-        if (xe->info.media_verx100 >= 1300)
> >-                xe->info.tile_count *= 2;
> > 
> >         drm_info(&xe->drm, "tile_count: %d, adj_tile_count %d\n",
> >                  xe->info.tile_count, adj_tile_count);
> >diff --git a/drivers/gpu/drm/xe/xe_pci.c b/drivers/gpu/drm/xe/xe_pci.c
> >index d8f1213ae1d6..be860f6d0a4f 100644
> >--- a/drivers/gpu/drm/xe/xe_pci.c
> >+++ b/drivers/gpu/drm/xe/xe_pci.c
> >@@ -19,6 +19,7 @@
> > #include "xe_device.h"
> > #include "xe_display.h"
> > #include "xe_drv.h"
> >+#include "xe_gt.h"
> 
> I'm not sure why we are adding this include here.

Yeah, it looks like this is leftover from earlier restructuring.  The
#include does eventually become necessary in patch #18 ("drm/xe:
Allocate GT dynamically") but we should add the include there rather
than here.


Matt

> 
> --
> Gustavo Sousa
> 
> > #include "xe_macros.h"
> > #include "xe_module.h"
> > #include "xe_pci_types.h"
> >@@ -290,21 +291,11 @@ static const struct xe_device_desc pvc_desc = {
> >         .extra_gts = pvc_gts,
> > };
> > 
> >-static const struct xe_gt_desc xelpmp_gts[] = {
> >-        {
> >-                .type = XE_GT_TYPE_MEDIA,
> >-                .vram_id = 0,
> >-                .mmio_adj_limit = 0x40000,
> >-                .mmio_adj_offset = 0x380000,
> >-        },
> >-};
> >-
> > static const struct xe_device_desc mtl_desc = {
> >         /* .graphics and .media determined via GMD_ID */
> >         .require_force_probe = true,
> >         PLATFORM(XE_METEORLAKE),
> >         .has_display = true,
> >-        .extra_gts = xelpmp_gts,
> > };
> > 
> > #undef PLATFORM
> >@@ -566,8 +557,6 @@ static int xe_info_init(struct xe_device *xe,
> >          * treats it as the number of GTs rather than just the number of tiles.
> >          */
> >         xe->info.tile_count = 1 + graphics_desc->max_remote_tiles;
> >-        if (MEDIA_VER(xe) >= 13)
> >-                xe->info.tile_count++;
> > 
> >         for (id = 0; id < xe->info.tile_count; ++id) {
> >                 gt = xe->gt + id;
> >-- 
> >2.40.1
> >

-- 
Matt Roper
Graphics Software Engineer
Linux GPU Platform Enablement
Intel Corporation