drm/xe: Add command MI_LOAD_REGISTER_MEM

We will need this shortly during context state preparation.

Cc: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://lore.kernel.org/r/20231214185955.1791-2-michal.wajdeczko@intel.comSigned-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>

drivers/gpu/drm/xe/instructions/xe_mi_commands.h

@@ -56,6 +56,9 @@
 #define   MI_FLUSH_IMM_QW		REG_FIELD_PREP(MI_FLUSH_DW_LEN_DW, 5 - 2)
 #define   MI_FLUSH_DW_USE_GTT		REG_BIT(2)
 
+#define MI_LOAD_REGISTER_MEM		(__MI_INSTR(0x29) | XE_INSTR_NUM_DW(4))
+#define   MI_LRM_USE_GGTT		REG_BIT(22)
+
 #define MI_BATCH_BUFFER_START		__MI_INSTR(0x31)
 
 #endif

drivers/gpu/drm/xe/xe_lrc.c

@@ -964,6 +964,20 @@ static int dump_mi_command(struct drm_printer *p,
 			drm_printf(p, " - %#6x = %#010x\n", dw[i], dw[i + 1]);
 		return numdw;
 
+	case MI_LOAD_REGISTER_MEM & MI_OPCODE:
+		drm_printf(p, "[%#010x] MI_LOAD_REGISTER_MEM: %s%s\n",
+			   inst_header,
+			   dw[0] & MI_LRI_LRM_CS_MMIO ? "CS_MMIO " : "",
+			   dw[0] & MI_LRM_USE_GGTT ? "USE_GGTT " : "");
+		if (numdw == 4)
+			drm_printf(p, " - %#6x = %#010llx\n",
+				   dw[1], ((u64)(dw[3]) << 32 | (u64)(dw[2])));
+		else
+			drm_printf(p, " - %*ph (%s)\n",
+				   (int)sizeof(u32) * (numdw - 1), dw + 1,
+				   numdw < 4 ? "truncated" : "malformed");
+		return numdw;
+
 	case MI_FORCE_WAKEUP:
 		drm_printf(p, "[%#010x] MI_FORCE_WAKEUP\n", inst_header);
 		return numdw;