It turned out that during early probe phase, VFs use detached from
the xe_device, temporary xe_gt objects, which when used as location
in xe_log() macros, will be treated by the dmesg decoration code as
bogus, possibly triggering a WARN, and the output will look like:

 [drm] *ERROR* SIGID=104 (-ETIMEDOUT) LOC3.0? GUC: MMIO request ...

instead of expected:

 [drm] *ERROR* SIGID=104 (-ETIMEDOUT) Tile0: GT0: GUC: MMIO request ...

Relax the tile/GT id validation and instead of looking for the real
objects, only check if encoded id is within the range of possible
tiles or GTs on the current xe device, using data from the device
descriptor rather then the object list.

nit: 'rather than'

Please mention invalid id case, how it's going to render like 

Warn + Tile3?  GT9? now.

Fixes: 1151b9f6f465 ("drm/xe/log: Add component/location decorations to dmesg")
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
---
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Mallesh Koujalagi <mallesh.koujalagi@intel.com>
---
 drivers/gpu/drm/xe/xe_log.c | 40 ++++++++++++++++++++++++-------------
 1 file changed, 26 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_log.c b/drivers/gpu/drm/xe/xe_log.c
index 5549ef6966fd..29eb16db3320 100644
--- a/drivers/gpu/drm/xe/xe_log.c
+++ b/drivers/gpu/drm/xe/xe_log.c
@@ -10,6 +10,7 @@
 
 #include "xe_device.h"
 #include "xe_log.h"
+#include "xe_pci_types.h"
 #include "xe_printk.h"
 
 static void log_emit_cper(struct pci_dev *pdev, int cper_sev, enum xe_sigid sigid,
@@ -52,18 +53,24 @@ static const char *log_component_prefix(u32 component)
 	return component ? log_unknown_component_prefix(component) : "";
 }
 
-static struct xe_gt *get_gt_safe(struct pci_dev *pdev, u8 id)
+static bool allowed_tile_id(struct xe_device *xe, u8 tile_id)
 {
-	struct xe_device *xe = pdev_to_xe_device(pdev);
+	return tile_id < 1 + xe->desc->max_remote_tiles;
+}
 
-	return xe ? xe_device_get_gt(xe, id) : NULL;
+static bool allowed_gt_id(struct xe_device *xe, u8 gt_id)
+{
+	return gt_id < (1 + xe->desc->max_remote_tiles) * xe->desc->max_gt_per_tile;
 }
 
-static struct xe_tile *get_tile_safe(struct pci_dev *pdev, u8 id)
+static u8 gt_id_to_tile_id(struct xe_device *xe, u8 gt_id)
 {
-	struct xe_device *xe = pdev_to_xe_device(pdev);
+	return gt_id / xe->desc->max_gt_per_tile;

hmm, we need to check max_gt_per_tile should not be zero to avoid hard Oops. I know in real scenario, max_gt_per_tile

value is greater than 0 and less than equal to XE_MAX_GT_PER_TILE, however rogue user can write kunit test case and manipulate it, to avoid such scenario, we need to handle it.

Thanks,

-/Mallesh

+}
 
-	return xe && id < xe->info.tile_count ? &xe->tiles[id] : NULL;
+static const char *location_suffix(bool valid)
+{
+	return valid ? ":" : "?";
 }
 
 static const char *log_location_prefix(struct pci_dev *pdev, u32 location, char *buf, size_t size)
@@ -76,17 +83,22 @@ static const char *log_location_prefix(struct pci_dev *pdev, u32 location, char
 			goto unrecognized;
 		strscpy(buf, "", size);
 	} else if (type == XE_LOG_LOCATION_TYPE_TILE) {
-		struct xe_tile *tile = get_tile_safe(pdev, id);
+		struct xe_device *xe = xe_any_to_xe(pdev);
+		bool valid = xe ? allowed_tile_id(xe, id) : false;
+		const char *pad = location_suffix(valid);
 
-		if (!tile)
-			goto unrecognized;
-		snprintf(buf, size, "Tile%u: ", id);
+		pci_WARN(pdev, !valid && IS_ENABLED(CONFIG_DRM_XE_DEBUG),
+			 "LOG: invalid tile identifier: %u\n", id);
+		snprintf(buf, size, "Tile%u%s ", id, pad);
 	} else if (type == XE_LOG_LOCATION_TYPE_GT) {
-		struct xe_gt *gt = get_gt_safe(pdev, id);
+		struct xe_device *xe = xe_any_to_xe(pdev);
+		bool valid = xe ? allowed_gt_id(xe, id) : false;
+		const char *pad = location_suffix(valid);
+		u8 tile_id = xe ? gt_id_to_tile_id(xe, id) : 0;
 
-		if (!gt)
-			goto unrecognized;
-		snprintf(buf, size, "Tile%u: GT%u: ", gt->tile->id, id);
+		pci_WARN(pdev, !valid && IS_ENABLED(CONFIG_DRM_XE_DEBUG),
+			 "LOG: invalid GT identifier: %u\n", id);
+		snprintf(buf, size, "Tile%u%s GT%u%s ", tile_id, pad, id, pad);
 	} else {
 		goto unrecognized;
 	}