drm/xe/xe3p: Add xe3p EU stall data format

Starting with Xe3p, IP address in EU stall data increases to 61 bits.
While at it, re-order the if-else ladder so the officially supported
platforms come before PVC.

Cc: Ashutosh Dixit <ashutosh.dixit@intel.com>
Signed-off-by: Harish Chegondi <harish.chegondi@intel.com>
Reviewed-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Link: https://lore.kernel.org/r/20251016-xe3p-v3-24-3dd173a3097a@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>

Author: harishchegondi

drivers/gpu/drm/xe/xe_eu_stall.c

@@ -124,6 +124,27 @@ struct xe_eu_stall_data_xe2 {
 	__u64 unused[6];
 } __packed;
 
+/*
+ * EU stall data format for Xe3p arch GPUs.
+ */
+struct xe_eu_stall_data_xe3p {
+	__u64 ip_addr:61;	  /* Bits 0  to 60  */
+	__u64 tdr_count:8;	  /* Bits 61 to 68  */
+	__u64 other_count:8;	  /* Bits 69 to 76  */
+	__u64 control_count:8;	  /* Bits 77 to 84  */
+	__u64 pipestall_count:8;  /* Bits 85 to 92  */
+	__u64 send_count:8;	  /* Bits 93 to 100 */
+	__u64 dist_acc_count:8;   /* Bits 101 to 108 */
+	__u64 sbid_count:8;	  /* Bits 109 to 116 */
+	__u64 sync_count:8;	  /* Bits 117 to 124 */
+	__u64 inst_fetch_count:8; /* Bits 125 to 132 */
+	__u64 active_count:8;	  /* Bits 133 to 140 */
+	__u64 ex_id:3;		  /* Bits 141 to 143 */
+	__u64 end_flag:1;	  /* Bit  144 */
+	__u64 unused_bits:47;
+	__u64 unused[5];
+} __packed;
+
 const u64 eu_stall_sampling_rates[] = {251, 251 * 2, 251 * 3, 251 * 4, 251 * 5, 251 * 6, 251 * 7};
 
 /**
@@ -167,10 +188,13 @@ size_t xe_eu_stall_data_record_size(struct xe_device *xe)
 {
 	size_t record_size = 0;
 
-	if (xe->info.platform == XE_PVC)
-		record_size = sizeof(struct xe_eu_stall_data_pvc);
+	if (GRAPHICS_VER(xe) >= 35)
+		record_size = sizeof(struct xe_eu_stall_data_xe3p);
 	else if (GRAPHICS_VER(xe) >= 20)
 		record_size = sizeof(struct xe_eu_stall_data_xe2);
+	else if (xe->info.platform == XE_PVC)
+		record_size = sizeof(struct xe_eu_stall_data_pvc);
+
 
 	xe_assert(xe, is_power_of_2(record_size));