drm/i915/guc: Request RP0 before loading firmware

By default, GT (and GuC) run at RPn. Requesting for RP0
before firmware load can speed up DMA and HuC auth as well.
In addition to writing to 0xA008, we also need to enable
swreq in 0xA024 so that Punit will pay heed to our request.

SLPC will restore the frequency back to RPn after initialization,
but we need to manually do that for the non-SLPC path.

We don't need a manual override in the SLPC disabled case, just
use the intel_rps_set function to ensure consistent RPS state.
Signed-off-by: Vinay Belgaumkar <vinay.belgaumkar@intel.com>
Reviewed-by: Sujaritha Sundaresan <sujaritha.sundaresan@intel.com>
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211216233022.21351-1-vinay.belgaumkar@intel.com

drivers/gpu/drm/i915/gt/intel_rps.c

@@ -2226,6 +2226,65 @@ u32 intel_rps_read_state_cap(struct intel_rps *rps)
 		return intel_uncore_read(uncore, GEN6_RP_STATE_CAP);
 }
 
+static void intel_rps_set_manual(struct intel_rps *rps, bool enable)
+{
+	struct intel_uncore *uncore = rps_to_uncore(rps);
+	u32 state = enable ? GEN9_RPSWCTL_ENABLE : GEN9_RPSWCTL_DISABLE;
+
+	/* Allow punit to process software requests */
+	intel_uncore_write(uncore, GEN6_RP_CONTROL, state);
+}
+
+void intel_rps_raise_unslice(struct intel_rps *rps)
+{
+	struct intel_uncore *uncore = rps_to_uncore(rps);
+	u32 rp0_unslice_req;
+
+	mutex_lock(&rps->lock);
+
+	if (rps_uses_slpc(rps)) {
+		/* RP limits have not been initialized yet for SLPC path */
+		rp0_unslice_req = ((intel_rps_read_state_cap(rps) >> 0)
+				   & 0xff) * GEN9_FREQ_SCALER;
+
+		intel_rps_set_manual(rps, true);
+		intel_uncore_write(uncore, GEN6_RPNSWREQ,
+				   ((rp0_unslice_req <<
+				   GEN9_SW_REQ_UNSLICE_RATIO_SHIFT) |
+				   GEN9_IGNORE_SLICE_RATIO));
+		intel_rps_set_manual(rps, false);
+	} else {
+		intel_rps_set(rps, rps->rp0_freq);
+	}
+
+	mutex_unlock(&rps->lock);
+}
+
+void intel_rps_lower_unslice(struct intel_rps *rps)
+{
+	struct intel_uncore *uncore = rps_to_uncore(rps);
+	u32 rpn_unslice_req;
+
+	mutex_lock(&rps->lock);
+
+	if (rps_uses_slpc(rps)) {
+		/* RP limits have not been initialized yet for SLPC path */
+		rpn_unslice_req = ((intel_rps_read_state_cap(rps) >> 16)
+				   & 0xff) * GEN9_FREQ_SCALER;
+
+		intel_rps_set_manual(rps, true);
+		intel_uncore_write(uncore, GEN6_RPNSWREQ,
+				   ((rpn_unslice_req <<
+				   GEN9_SW_REQ_UNSLICE_RATIO_SHIFT) |
+				   GEN9_IGNORE_SLICE_RATIO));
+		intel_rps_set_manual(rps, false);
+	} else {
+		intel_rps_set(rps, rps->min_freq);
+	}
+
+	mutex_unlock(&rps->lock);
+}
+
 /* External interface for intel_ips.ko */
 
 static struct drm_i915_private __rcu *ips_mchdev;

drivers/gpu/drm/i915/gt/intel_rps.h

@@ -45,6 +45,8 @@ u32 intel_rps_get_rpn_frequency(struct intel_rps *rps);
 u32 intel_rps_read_punit_req(struct intel_rps *rps);
 u32 intel_rps_read_punit_req_frequency(struct intel_rps *rps);
 u32 intel_rps_read_state_cap(struct intel_rps *rps);
+void intel_rps_raise_unslice(struct intel_rps *rps);
+void intel_rps_lower_unslice(struct intel_rps *rps);
 
 void gen5_rps_irq_handler(struct intel_rps *rps);
 void gen6_rps_irq_handler(struct intel_rps *rps, u32 pm_iir);

drivers/gpu/drm/i915/gt/uc/intel_uc.c

@@ -8,6 +8,7 @@
 #include "intel_guc.h"
 #include "intel_guc_ads.h"
 #include "intel_guc_submission.h"
+#include "gt/intel_rps.h"
 #include "intel_uc.h"
 
 #include "i915_drv.h"
@@ -462,6 +463,8 @@ static int __uc_init_hw(struct intel_uc *uc)
 	else
 		attempts = 1;
 
+	intel_rps_raise_unslice(&uc_to_gt(uc)->rps);
+
 	while (attempts--) {
 		/*
 		 * Always reset the GuC just before (re)loading, so
@@ -499,6 +502,9 @@ static int __uc_init_hw(struct intel_uc *uc)
 		ret = intel_guc_slpc_enable(&guc->slpc);
 		if (ret)
 			goto err_submission;
+	} else {
+		/* Restore GT back to RPn for non-SLPC path */
+		intel_rps_lower_unslice(&uc_to_gt(uc)->rps);
 	}
 
 	drm_info(&i915->drm, "%s firmware %s version %u.%u %s:%s\n",
@@ -529,6 +535,9 @@ static int __uc_init_hw(struct intel_uc *uc)
 err_log_capture:
 	__uc_capture_load_err_log(uc);
 err_out:
+	/* Return GT back to RPn */
+	intel_rps_lower_unslice(&uc_to_gt(uc)->rps);
+
 	__uc_sanitize(uc);
 
 	if (!ret) {

drivers/gpu/drm/i915/i915_reg.h

@@ -9399,6 +9399,7 @@ enum {
 #define   GEN6_OFFSET(x)			((x) << 19)
 #define   GEN6_AGGRESSIVE_TURBO			(0 << 15)
 #define   GEN9_SW_REQ_UNSLICE_RATIO_SHIFT	23
+#define   GEN9_IGNORE_SLICE_RATIO		(0 << 0)
 
 #define GEN6_RC_VIDEO_FREQ			_MMIO(0xA00C)
 #define GEN6_RC_CONTROL				_MMIO(0xA090)
@@ -9434,6 +9435,9 @@ enum {
 #define   GEN6_RP_UP_BUSY_CONT			(0x4 << 3)
 #define   GEN6_RP_DOWN_IDLE_AVG			(0x2 << 0)
 #define   GEN6_RP_DOWN_IDLE_CONT		(0x1 << 0)
+#define   GEN6_RPSWCTL_SHIFT			9
+#define   GEN9_RPSWCTL_ENABLE			(0x2 << GEN6_RPSWCTL_SHIFT)
+#define   GEN9_RPSWCTL_DISABLE			(0x0 << GEN6_RPSWCTL_SHIFT)
 #define GEN6_RP_UP_THRESHOLD			_MMIO(0xA02C)
 #define GEN6_RP_DOWN_THRESHOLD			_MMIO(0xA030)
 #define GEN6_RP_CUR_UP_EI			_MMIO(0xA050)