drm/i915/ats-m: Add thread execution tuning setting

On client DG2 platforms, optimal performance is achieved with the
hardware's default "age based" thread execution setting.  However on
ATS-M, switching this to "round robin after dependencies" provides
better performance.  We'll add a new "tuning" feature flag to the ATS-M
device info to enable/disable this setting.

Bspec: 68331
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: Matt Atwood <matthew.s.atwood@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220826212718.409948-1-matthew.d.roper@intel.com

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

@@ -1110,6 +1110,8 @@
 #define   GEN12_DISABLE_TDL_PUSH		REG_BIT(9)
 #define   GEN11_DIS_PICK_2ND_EU			REG_BIT(7)
 #define   GEN12_DISABLE_HDR_PAST_PAYLOAD_HOLD_FIX	REG_BIT(4)
+#define   THREAD_EX_ARB_MODE			REG_GENMASK(3, 2)
+#define   THREAD_EX_ARB_MODE_RR_AFTER_DEP	REG_FIELD_PREP(THREAD_EX_ARB_MODE, 0x2)
 
 #define HSW_ROW_CHICKEN3			_MMIO(0xe49c)
 #define   HSW_ROW_CHICKEN3_L3_GLOBAL_ATOMICS_DISABLE	(1 << 6)

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

@@ -2700,6 +2700,15 @@ add_render_compute_tuning_settings(struct drm_i915_private *i915,
 		       0 /* write-only, so skip validation */,
 		       true);
 	}
+
+	/*
+	 * This tuning setting proves beneficial only on ATS-M designs; the
+	 * default "age based" setting is optimal on regular DG2 and other
+	 * platforms.
+	 */
+	if (INTEL_INFO(i915)->tuning_thread_rr_after_dep)
+		wa_masked_field_set(wal, GEN9_ROW_CHICKEN4, THREAD_EX_ARB_MODE,
+				    THREAD_EX_ARB_MODE_RR_AFTER_DEP);
 }
 
 /*

drivers/gpu/drm/i915/i915_pci.c

@@ -1083,6 +1083,7 @@ static const struct intel_device_info ats_m_info = {
 	DG2_FEATURES,
 	.display = { 0 },
 	.require_force_probe = 1,
+	.tuning_thread_rr_after_dep = 1,
 };
 
 #define XE_HPC_FEATURES \

drivers/gpu/drm/i915/intel_device_info.h

@@ -172,6 +172,7 @@ enum intel_ppgtt_type {
 	func(has_runtime_pm); \
 	func(has_snoop); \
 	func(has_coherent_ggtt); \
+	func(tuning_thread_rr_after_dep); \
 	func(unfenced_needs_alignment); \
 	func(hws_needs_physical);