drm/xe: Raise GT frequency before GuC/HuC load

Starting GT freq is usually RPn. Raising freq to RP0 will
help speed up GuC load times. As an example, this data was
collected on DG2-

GuC Load time @RPn ~ 41 ms
GuC Load time @RP0 ~ 11 ms

v2: Raise GT freq before hwconfig init. This will speed up
both HuC and GuC loads. Address review comments (Rodrigo).
Also add a small usleep after requesting frequency which gives
pcode some time to react.

v3: Address checkpatch issue

Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Vinay Belgaumkar <vinay.belgaumkar@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>

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

@@ -263,6 +263,11 @@
 
 #define RPNSWREQ				XE_REG(0xa008)
 #define   REQ_RATIO_MASK			REG_GENMASK(31, 23)
+
+#define RP_CONTROL				XE_REG(0xa024)
+#define   RPSWCTL_MASK				REG_GENMASK(10, 9)
+#define   RPSWCTL_ENABLE			REG_FIELD_PREP(RPSWCTL_MASK, 2)
+#define   RPSWCTL_DISABLE			REG_FIELD_PREP(RPSWCTL_MASK, 0)
 #define RC_CONTROL				XE_REG(0xa090)
 #define RC_STATE				XE_REG(0xa094)
 

drivers/gpu/drm/xe/xe_gt.c

@@ -30,6 +30,7 @@
 #include "xe_gt_tlb_invalidation.h"
 #include "xe_gt_topology.h"
 #include "xe_guc_exec_queue_types.h"
+#include "xe_guc_pc.h"
 #include "xe_hw_fence.h"
 #include "xe_hw_engine_class_sysfs.h"
 #include "xe_irq.h"
@@ -349,6 +350,9 @@ static int gt_fw_domain_init(struct xe_gt *gt)
 	if (err)
 		goto err_force_wake;
 
+	/* Raise GT freq to speed up HuC/GuC load */
+	xe_guc_pc_init_early(&gt->uc.guc.pc);
+
 	err = xe_uc_init_hwconfig(&gt->uc);
 	if (err)
 		goto err_force_wake;

drivers/gpu/drm/xe/xe_guc_pc.c

@@ -247,6 +247,12 @@ static u32 decode_freq(u32 raw)
 				 GEN9_FREQ_SCALER);
 }
 
+static u32 encode_freq(u32 freq)
+{
+	return DIV_ROUND_CLOSEST(freq * GEN9_FREQ_SCALER,
+				 GT_FREQUENCY_MULTIPLIER);
+}
+
 static u32 pc_get_min_freq(struct xe_guc_pc *pc)
 {
 	u32 freq;
@@ -257,6 +263,32 @@ static u32 pc_get_min_freq(struct xe_guc_pc *pc)
 	return decode_freq(freq);
 }
 
+static void pc_set_manual_rp_ctrl(struct xe_guc_pc *pc, bool enable)
+{
+	struct xe_gt *gt = pc_to_gt(pc);
+	u32 state = enable ? RPSWCTL_ENABLE : RPSWCTL_DISABLE;
+
+	/* Allow/Disallow punit to process software freq requests */
+	xe_mmio_write32(gt, RP_CONTROL, state);
+}
+
+static void pc_set_cur_freq(struct xe_guc_pc *pc, u32 freq)
+{
+	struct xe_gt *gt = pc_to_gt(pc);
+	u32 rpnswreq;
+
+	pc_set_manual_rp_ctrl(pc, true);
+
+	/* Req freq is in units of 16.66 Mhz */
+	rpnswreq = REG_FIELD_PREP(REQ_RATIO_MASK, encode_freq(freq));
+	xe_mmio_write32(gt, RPNSWREQ, rpnswreq);
+
+	/* Sleep for a small time to allow pcode to respond */
+	usleep_range(100, 300);
+
+	pc_set_manual_rp_ctrl(pc, false);
+}
+
 static int pc_set_min_freq(struct xe_guc_pc *pc, u32 freq)
 {
 	/*
@@ -685,6 +717,21 @@ static void pc_init_fused_rp_values(struct xe_guc_pc *pc)
 	else
 		tgl_init_fused_rp_values(pc);
 }
+
+/**
+ * xe_guc_pc_init_early - Initialize RPx values and request a higher GT
+ * frequency to allow faster GuC load times
+ * @pc: Xe_GuC_PC instance
+ */
+void xe_guc_pc_init_early(struct xe_guc_pc *pc)
+{
+	struct xe_gt *gt = pc_to_gt(pc);
+
+	xe_force_wake_assert_held(gt_to_fw(gt), XE_FW_GT);
+	pc_init_fused_rp_values(pc);
+	pc_set_cur_freq(pc, pc->rp0_freq);
+}
+
 static int pc_adjust_freq_bounds(struct xe_guc_pc *pc)
 {
 	int ret;
@@ -918,8 +965,6 @@ int xe_guc_pc_init(struct xe_guc_pc *pc)
 
 	pc->bo = bo;
 
-	pc_init_fused_rp_values(pc);
-
 	err = sysfs_create_files(gt->sysfs, pc_attrs);
 	if (err)
 		return err;

drivers/gpu/drm/xe/xe_guc_pc.h

@@ -17,4 +17,5 @@ int xe_guc_pc_gucrc_disable(struct xe_guc_pc *pc);
 enum xe_gt_idle_state xe_guc_pc_c_status(struct xe_guc_pc *pc);
 u64 xe_guc_pc_rc6_residency(struct xe_guc_pc *pc);
 u64 xe_guc_pc_mc6_residency(struct xe_guc_pc *pc);
+void xe_guc_pc_init_early(struct xe_guc_pc *pc);
 #endif /* _XE_GUC_PC_H_ */