drm/i915/perf: Enable bytes per clock reporting in OA

XEHPSDV and DG2 provide a way to configure bytes per clock vs commands
per clock reporting. Enable bytes per clock setting on enabling OA.

Bspec: 51762
Bspec: 52201

v2:
- Fix commit msg (Ashutosh)
- Fix checkpatch issues

v3:
- s/commands/bytes/ in code comment and commmit msg
Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Reviewed-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221026222102.5526-6-umesh.nerlige.ramappa@intel.com

drivers/gpu/drm/i915/i915_drv.h

@@ -901,6 +901,9 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
 #define HAS_RUNTIME_PM(dev_priv) (INTEL_INFO(dev_priv)->has_runtime_pm)
 #define HAS_64BIT_RELOC(dev_priv) (INTEL_INFO(dev_priv)->has_64bit_reloc)
 
+#define HAS_OA_BPC_REPORTING(dev_priv) \
+	(INTEL_INFO(dev_priv)->has_oa_bpc_reporting)
+
 /*
  * Set this flag, when platform requires 64K GTT page sizes or larger for
  * device local memory access.

drivers/gpu/drm/i915/i915_pci.c

@@ -1023,6 +1023,7 @@ static const struct intel_device_info adl_p_info = {
 	.has_logical_ring_contexts = 1, \
 	.has_logical_ring_elsq = 1, \
 	.has_mslice_steering = 1, \
+	.has_oa_bpc_reporting = 1, \
 	.has_rc6 = 1, \
 	.has_reset_engine = 1, \
 	.has_rps = 1, \

drivers/gpu/drm/i915/i915_perf.c

@@ -2748,10 +2748,12 @@ static int
 gen12_enable_metric_set(struct i915_perf_stream *stream,
 			struct i915_active *active)
 {
+	struct drm_i915_private *i915 = stream->perf->i915;
 	struct intel_uncore *uncore = stream->uncore;
 	struct i915_oa_config *oa_config = stream->oa_config;
 	bool periodic = stream->periodic;
 	u32 period_exponent = stream->period_exponent;
+	u32 sqcnt1;
 	int ret;
 
 	intel_uncore_write(uncore, GEN12_OAG_OA_DEBUG,
@@ -2770,6 +2772,16 @@ gen12_enable_metric_set(struct i915_perf_stream *stream,
 			    (period_exponent << GEN12_OAG_OAGLBCTXCTRL_TIMER_PERIOD_SHIFT))
 			    : 0);
 
+	/*
+	 * Initialize Super Queue Internal Cnt Register
+	 * Set PMON Enable in order to collect valid metrics.
+	 * Enable byets per clock reporting in OA for XEHPSDV onward.
+	 */
+	sqcnt1 = GEN12_SQCNT1_PMON_ENABLE |
+		 (HAS_OA_BPC_REPORTING(i915) ? GEN12_SQCNT1_OABPC : 0);
+
+	intel_uncore_rmw(uncore, GEN12_SQCNT1, 0, sqcnt1);
+
 	/*
 	 * Update all contexts prior writing the mux configurations as we need
 	 * to make sure all slices/subslices are ON before writing to NOA
@@ -2819,6 +2831,8 @@ static void gen11_disable_metric_set(struct i915_perf_stream *stream)
 static void gen12_disable_metric_set(struct i915_perf_stream *stream)
 {
 	struct intel_uncore *uncore = stream->uncore;
+	struct drm_i915_private *i915 = stream->perf->i915;
+	u32 sqcnt1;
 
 	/* Reset all contexts' slices/subslices configurations. */
 	gen12_configure_all_contexts(stream, NULL, NULL);
@@ -2829,6 +2843,12 @@ static void gen12_disable_metric_set(struct i915_perf_stream *stream)
 
 	/* Make sure we disable noa to save power. */
 	intel_uncore_rmw(uncore, RPM_CONFIG1, GEN10_GT_NOA_ENABLE, 0);
+
+	sqcnt1 = GEN12_SQCNT1_PMON_ENABLE |
+		 (HAS_OA_BPC_REPORTING(i915) ? GEN12_SQCNT1_OABPC : 0);
+
+	/* Reset PMON Enable to save power. */
+	intel_uncore_rmw(uncore, GEN12_SQCNT1, sqcnt1, 0);
 }
 
 static void gen7_oa_enable(struct i915_perf_stream *stream)

drivers/gpu/drm/i915/i915_perf_oa_regs.h

@@ -134,4 +134,8 @@
 #define GDT_CHICKEN_BITS    _MMIO(0x9840)
 #define   GT_NOA_ENABLE	    0x00000080
 
+#define GEN12_SQCNT1				_MMIO(0x8718)
+#define   GEN12_SQCNT1_PMON_ENABLE		REG_BIT(30)
+#define   GEN12_SQCNT1_OABPC			REG_BIT(29)
+
 #endif /* __INTEL_PERF_OA_REGS__ */

drivers/gpu/drm/i915/intel_device_info.h

@@ -163,6 +163,7 @@ enum intel_ppgtt_type {
 	func(has_logical_ring_elsq); \
 	func(has_media_ratio_mode); \
 	func(has_mslice_steering); \
+	func(has_oa_bpc_reporting); \
 	func(has_one_eu_per_fuse_bit); \
 	func(has_pxp); \
 	func(has_rc6); \