drm/xe/ptl: L3bank mask is not available on the media GT

On PTL platforms with media version 30.00, the fuse registers for
reporting L3 bank availability to the GT just read out as ~0 and do not
provide proper values. Xe does not use the L3 bank mask for anything
internally; it only passes the mask through to userspace via the GT
topology query.

Since we don't have any way to get the real L3 bank mask, we don't want
to pass garbage to userspace. Passing a zeroed mask or a copy of the
primary GT's L3 bank mask would also be inaccurate and likely to cause
confusion for userspace. The best approach is to simply not include L3
in the list of masks returned by the topology query in cases where we
aren't able to provide a meaningful value. This won't change the
behavior for any existing platforms (where we can always obtain L3 masks
successfully for all GTs), it will only prevent us from mis-reporting
bad information on upcoming platform(s).

There's a good chance this will become a formal workaround in the
future, but for now we don't have a lineage number so "no_media_l3" is
used in place of a lineage as the OOB workaround descriptor.

v2:
- Re-calculate query size to properly match data returned. (Gustavo)
- Update kerneldoc to clarify that the L3bank mask may not be included
in the query results if the hardware doesn't make it available.
(Gustavo)

Cc: Matt Atwood <[e-mail]>
Cc: Gustavo Sousa <[e-mail]>
Signed-off-by: Shekhar Chauhan <[e-mail]>
Co-developed-by: Matt Roper <[e-mail]>
Signed-off-by: Matt Roper <[e-mail]>
Reviewed-by: Jonathan Cavitt <[e-mail]>
Reviewed-by: Gustavo Sousa <[e-mail]>
Acked-by: Francois Dugast <[e-mail]>
Link: https://patchwork.freedesktop.org/patch/msgid/[e-mail]

drivers/gpu/drm/xe/xe_gt_topology.c

···
 
 #include "xe_gt_topology.h"
 
+#include <generated/xe_wa_oob.h>
 #include <linux/bitmap.h>
 #include <linux/compiler.h>
 
···
 #include "xe_assert.h"
 #include "xe_gt.h"
 #include "xe_mmio.h"
+#include "xe_wa.h"
 
 static void
 load_dss_mask(struct xe_gt *gt, xe_dss_mask_t mask, int numregs, ...)
···
 {
 	struct xe_device *xe = gt_to_xe(gt);
 	u32 fuse3 = xe_mmio_read32(&gt->mmio, MIRROR_FUSE3);
+
+	/*
+	 * PTL platforms with media version 30.00 do not provide proper values
+	 * for the media GT's L3 bank registers.  Skip the readout since we
+	 * don't have any way to obtain real values.
+	 *
+	 * This may get re-described as an official workaround in the future,
+	 * but there's no tracking number assigned yet so we use a custom
+	 * OOB workaround descriptor.
+	 */
+	if (XE_WA(gt, no_media_l3))
+		return;
 
 	if (GRAPHICS_VER(xe) >= 20) {
 		xe_l3_bank_mask_t per_node = {};

drivers/gpu/drm/xe/xe_query.c

···
 #include <linux/sched/clock.h>
 
 #include <drm/ttm/ttm_placement.h>
+#include <generated/xe_wa_oob.h>
 #include <uapi/drm/xe_drm.h>
 
 #include "regs/xe_engine_regs.h"
···
 #include "xe_macros.h"
 #include "xe_mmio.h"
 #include "xe_ttm_vram_mgr.h"
+#include "xe_wa.h"
 
 static const u16 xe_to_user_engine_class[] = {
 	[XE_ENGINE_CLASS_RENDER] = DRM_XE_ENGINE_CLASS_RENDER,
···
 
 static size_t calc_topo_query_size(struct xe_device *xe)
 {
-	return xe->info.gt_count *
-		(4 * sizeof(struct drm_xe_query_topology_mask) +
-		 sizeof_field(struct xe_gt, fuse_topo.g_dss_mask) +
-		 sizeof_field(struct xe_gt, fuse_topo.c_dss_mask) +
-		 sizeof_field(struct xe_gt, fuse_topo.l3_bank_mask) +
-		 sizeof_field(struct xe_gt, fuse_topo.eu_mask_per_dss));
+	struct xe_gt *gt;
+	size_t query_size = 0;
+	int id;
+
+	for_each_gt(gt, xe, id) {
+		query_size += 3 * sizeof(struct drm_xe_query_topology_mask) +
+			sizeof_field(struct xe_gt, fuse_topo.g_dss_mask) +
+			sizeof_field(struct xe_gt, fuse_topo.c_dss_mask) +
+			sizeof_field(struct xe_gt, fuse_topo.eu_mask_per_dss);
+
+		/* L3bank mask may not be available for some GTs */
+		if (!XE_WA(gt, no_media_l3))
+			query_size += sizeof(struct drm_xe_query_topology_mask) +
+				sizeof_field(struct xe_gt, fuse_topo.l3_bank_mask);
+	}
+
+	return query_size;
 }
 
 static int copy_mask(void __user **ptr,
···
 		if (err)
 			return err;
 
-		topo.type = DRM_XE_TOPO_L3_BANK;
-		err = copy_mask(&query_ptr, &topo, gt->fuse_topo.l3_bank_mask,
-				sizeof(gt->fuse_topo.l3_bank_mask));
-		if (err)
-			return err;
+		/*
+		 * If the kernel doesn't have a way to obtain a correct L3bank
+		 * mask, then it's better to omit L3 from the query rather than
+		 * reporting bogus or zeroed information to userspace.
+		 */
+		if (!XE_WA(gt, no_media_l3)) {
+			topo.type = DRM_XE_TOPO_L3_BANK;
+			err = copy_mask(&query_ptr, &topo, gt->fuse_topo.l3_bank_mask,
+					sizeof(gt->fuse_topo.l3_bank_mask));
+			if (err)
+				return err;
+		}
 
 		topo.type = gt->fuse_topo.eu_type == XE_GT_EU_TYPE_SIMD16 ?
 			DRM_XE_TOPO_SIMD16_EU_PER_DSS :

drivers/gpu/drm/xe/xe_wa_oob.rules

···
 16023588340	GRAPHICS_VERSION(2001)
 14019789679	GRAPHICS_VERSION(1255)
 		GRAPHICS_VERSION_RANGE(1270, 2004)
+no_media_l3	MEDIA_VERSION(3000)

include/uapi/drm/xe_drm.h

···
  *    containing the following in mask:
  *    ``DSS_COMPUTE    ff ff ff ff 00 00 00 00``
  *    means 32 DSS are available for compute.
- *  - %DRM_XE_TOPO_L3_BANK - To query the mask of enabled L3 banks
+ *  - %DRM_XE_TOPO_L3_BANK - To query the mask of enabled L3 banks.  This type
+ *    may be omitted if the driver is unable to query the mask from the
+ *    hardware.
  *  - %DRM_XE_TOPO_EU_PER_DSS - To query the mask of Execution Units (EU)
  *    available per Dual Sub Slices (DSS). For example a query response
  *    containing the following in mask: