drm/xe: Set default MOCS value for cs instructions

CS instructions that dont have a explicit MOCS field will use this
default MOCS value.

To do this, it was necessary to initialize part of the mocs earlier
and add new function that loads another array of rtp entries set
during run-time.

This is still missing to handle of mocs read for platforms with
HAS_L3_CCS_READ(aka PVC).

v2:
- move to xe_hw_engine.c
- remove CMD_CCTL auxiliary macros

v3:
- rebased

Bspec: 45826
Cc: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>

drivers/gpu/drm/xe/regs/xe_engine_regs.h

@@ -44,6 +44,18 @@
 #define RING_EIR(base)				XE_REG((base) + 0xb0)
 #define RING_EMR(base)				XE_REG((base) + 0xb4)
 #define RING_ESR(base)				XE_REG((base) + 0xb8)
+
+#define RING_CMD_CCTL(base)			XE_REG((base) + 0xc4, XE_REG_OPTION_MASKED)
+/*
+ * CMD_CCTL read/write fields take a MOCS value and _not_ a table index.
+ * The lsb of each can be considered a separate enabling bit for encryption.
+ * 6:0 == default MOCS value for reads  =>  6:1 == table index for reads.
+ * 13:7 == default MOCS value for writes => 13:8 == table index for writes.
+ * 15:14 == Reserved => 31:30 are set to 0.
+ */
+#define   CMD_CCTL_WRITE_OVERRIDE_MASK		REG_GENMASK(13, 8)
+#define   CMD_CCTL_READ_OVERRIDE_MASK		REG_GENMASK(6, 1)
+
 #define RING_BBADDR(base)			XE_REG((base) + 0x140)
 #define RING_BBADDR_UDW(base)			XE_REG((base) + 0x168)
 #define RING_EXECLIST_STATUS_LO(base)		XE_REG((base) + 0x234)

drivers/gpu/drm/xe/xe_gt.c

@@ -390,6 +390,8 @@ static int gt_fw_domain_init(struct xe_gt *gt)
 	/* Rerun MCR init as we now have hw engine list */
 	xe_gt_mcr_init(gt);
 
+	xe_mocs_init_early(gt);
+
 	err = xe_hw_engines_init_early(gt);
 	if (err)
 		goto err_force_wake;

drivers/gpu/drm/xe/xe_hw_engine.c

@@ -21,6 +21,7 @@
 #include "xe_macros.h"
 #include "xe_mmio.h"
 #include "xe_reg_sr.h"
+#include "xe_rtp.h"
 #include "xe_sched_job.h"
 #include "xe_wa.h"
 
@@ -267,6 +268,39 @@ void xe_hw_engine_enable_ring(struct xe_hw_engine *hwe)
 	hw_engine_mmio_read32(hwe, RING_MI_MODE(0).reg);
 }
 
+static void
+hw_engine_setup_default_state(struct xe_hw_engine *hwe)
+{
+	struct xe_gt *gt = hwe->gt;
+	const u8 mocs_write_idx = gt->mocs.uc_index;
+	/* TODO: missing handling of HAS_L3_CCS_READ platforms */
+	const u8 mocs_read_idx = gt->mocs.uc_index;
+	u32 ring_cmd_cctl_val = REG_FIELD_PREP(CMD_CCTL_WRITE_OVERRIDE_MASK, mocs_write_idx) |
+			        REG_FIELD_PREP(CMD_CCTL_READ_OVERRIDE_MASK, mocs_read_idx);
+	const struct xe_rtp_entry engine_was[] = {
+		/*
+		 * RING_CMD_CCTL specifies the default MOCS entry that will be
+		 * used by the command streamer when executing commands that
+		 * don't have a way to explicitly specify a MOCS setting.
+		 * The default should usually reference whichever MOCS entry
+		 * corresponds to uncached behavior, although use of a WB cached
+		 * entry is recommended by the spec in certain circumstances on
+		 * specific platforms.
+		 */
+		{ XE_RTP_NAME("RING_CMD_CCTL_default_MOCS"),
+		  XE_RTP_RULES(GRAPHICS_VERSION_RANGE(1200, XE_RTP_END_VERSION_UNDEFINED)),
+		  XE_RTP_ACTIONS(FIELD_SET(RING_CMD_CCTL(0),
+					   CMD_CCTL_WRITE_OVERRIDE_MASK |
+					   CMD_CCTL_READ_OVERRIDE_MASK,
+					   ring_cmd_cctl_val,
+					   XE_RTP_ACTION_FLAG(ENGINE_BASE)))
+		},
+		{}
+	};
+
+	xe_rtp_process(engine_was, &hwe->reg_sr, gt, hwe);
+}
+
 static void hw_engine_init_early(struct xe_gt *gt, struct xe_hw_engine *hwe,
 				 enum xe_hw_engine_id id)
 {
@@ -293,6 +327,7 @@ static void hw_engine_init_early(struct xe_gt *gt, struct xe_hw_engine *hwe,
 
 	xe_reg_sr_init(&hwe->reg_sr, hwe->name, gt_to_xe(gt));
 	xe_wa_process_engine(hwe);
+	hw_engine_setup_default_state(hwe);
 
 	xe_reg_sr_init(&hwe->reg_whitelist, hwe->name, gt_to_xe(gt));
 	xe_reg_whitelist_process_engine(hwe);

drivers/gpu/drm/xe/xe_mocs.c

@@ -518,6 +518,15 @@ static void init_l3cc_table(struct xe_gt *gt,
 	}
 }
 
+void xe_mocs_init_early(struct xe_gt *gt)
+{
+	struct xe_mocs_info table;
+
+	get_mocs_settings(gt->xe, &table);
+	gt->mocs.uc_index = table.uc_index;
+	gt->mocs.wb_index = table.wb_index;
+}
+
 void xe_mocs_init(struct xe_gt *gt)
 {
 	struct xe_mocs_info table;
@@ -528,8 +537,6 @@ void xe_mocs_init(struct xe_gt *gt)
 	 */
 	flags = get_mocs_settings(gt->xe, &table);
 	mocs_dbg(&gt->xe->drm, "flag:0x%x\n", flags);
-	gt->mocs.uc_index = table.uc_index;
-	gt->mocs.wb_index = table.wb_index;
 
 	if (flags & HAS_GLOBAL_MOCS)
 		__init_mocs_table(gt, &table, GLOBAL_MOCS(0).reg);

drivers/gpu/drm/xe/xe_mocs.h

@@ -11,6 +11,7 @@
 struct xe_engine;
 struct xe_gt;
 
+void xe_mocs_init_early(struct xe_gt *gt);
 void xe_mocs_init(struct xe_gt *gt);
 
 /**