drm/i915/gen8+: Add RC6 CTX corruption WA

commit 7e34f4e4 upstream.

In some circumstances the RC6 context can get corrupted. We can detect
this and take the required action, that is disable RC6 and runtime PM.
The HW recovers from the corrupted state after a system suspend/resume
cycle, so detect the recovery and re-enable RC6 and runtime PM.

v2: rebase (Mika)
v3:
- Move intel_suspend_gt_powersave() to the end of the GEM suspend
  sequence.
- Add commit message.
v4:
- Rebased on intel_uncore_forcewake_put(i915->uncore, ...) API
  change.
v5: rebased on gem/gt split (Mika)
Signed-off-by: Imre Deak <imre.deak@intel.com>
Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

drivers/gpu/drm/i915/i915_drv.c

@@ -1627,6 +1627,7 @@ static int i915_drm_suspend_late(struct drm_device *dev, bool hibernation)
 	i915_gem_suspend_late(dev_priv);
 
 	intel_display_set_init_power(dev_priv, false);
+	i915_rc6_ctx_wa_suspend(dev_priv);
 	intel_uncore_suspend(dev_priv);
 
 	/*
@@ -1853,6 +1854,8 @@ static int i915_drm_resume_early(struct drm_device *dev)
 	else
 		intel_display_set_init_power(dev_priv, true);
 
+	i915_rc6_ctx_wa_resume(dev_priv);
+
 	intel_engines_sanitize(dev_priv);
 
 	enable_rpm_wakeref_asserts(dev_priv);

drivers/gpu/drm/i915/i915_drv.h

@@ -801,6 +801,7 @@ struct intel_rps {
 
 struct intel_rc6 {
 	bool enabled;
+	bool ctx_corrupted;
 	u64 prev_hw_residency[4];
 	u64 cur_residency[4];
 };
@@ -2557,10 +2558,12 @@ intel_info(const struct drm_i915_private *dev_priv)
 /* Early gen2 have a totally busted CS tlb and require pinned batches. */
 #define HAS_BROKEN_CS_TLB(dev_priv)	(IS_I830(dev_priv) || IS_I845G(dev_priv))
 
+#define NEEDS_RC6_CTX_CORRUPTION_WA(dev_priv)	\
+	(IS_BROADWELL(dev_priv) || INTEL_GEN(dev_priv) == 9)
+
 /* WaRsDisableCoarsePowerGating:skl,cnl */
 #define NEEDS_WaRsDisableCoarsePowerGating(dev_priv) \
-	(IS_CANNONLAKE(dev_priv) || \
-	 IS_SKL_GT3(dev_priv) || IS_SKL_GT4(dev_priv))
+	(IS_CANNONLAKE(dev_priv) || INTEL_GEN(dev_priv) == 9)
 
 #define HAS_GMBUS_IRQ(dev_priv) (INTEL_GEN(dev_priv) >= 4)
 #define HAS_GMBUS_BURST_READ(dev_priv) (INTEL_GEN(dev_priv) >= 10 || \

drivers/gpu/drm/i915/i915_gem.c

@@ -174,6 +174,11 @@ static u32 __i915_gem_park(struct drm_i915_private *i915)
 	if (INTEL_GEN(i915) >= 6)
 		gen6_rps_idle(i915);
 
+	if (NEEDS_RC6_CTX_CORRUPTION_WA(i915)) {
+		i915_rc6_ctx_wa_check(i915);
+		intel_uncore_forcewake_put(i915, FORCEWAKE_ALL);
+	}
+
 	intel_display_power_put(i915, POWER_DOMAIN_GT_IRQ);
 
 	intel_runtime_pm_put(i915);
@@ -220,6 +225,9 @@ void i915_gem_unpark(struct drm_i915_private *i915)
 	 */
 	intel_display_power_get(i915, POWER_DOMAIN_GT_IRQ);
 
+	if (NEEDS_RC6_CTX_CORRUPTION_WA(i915))
+		intel_uncore_forcewake_get(i915, FORCEWAKE_ALL);
+
 	i915->gt.awake = true;
 	if (unlikely(++i915->gt.epoch == 0)) /* keep 0 as invalid */
 		i915->gt.epoch = 1;

drivers/gpu/drm/i915/i915_reg.h

@@ -387,6 +387,8 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define   ECOCHK_PPGTT_WT_HSW		(0x2 << 3)
 #define   ECOCHK_PPGTT_WB_HSW		(0x3 << 3)
 
+#define GEN8_RC6_CTX_INFO		_MMIO(0x8504)
+
 #define GAC_ECO_BITS			_MMIO(0x14090)
 #define   ECOBITS_SNB_BIT		(1 << 13)
 #define   ECOBITS_PPGTT_CACHE64B	(3 << 8)

drivers/gpu/drm/i915/intel_drv.h

@@ -2064,6 +2064,9 @@ void intel_sanitize_gt_powersave(struct drm_i915_private *dev_priv);
 void intel_enable_gt_powersave(struct drm_i915_private *dev_priv);
 void intel_disable_gt_powersave(struct drm_i915_private *dev_priv);
 void intel_suspend_gt_powersave(struct drm_i915_private *dev_priv);
+bool i915_rc6_ctx_wa_check(struct drm_i915_private *i915);
+void i915_rc6_ctx_wa_suspend(struct drm_i915_private *i915);
+void i915_rc6_ctx_wa_resume(struct drm_i915_private *i915);
 void gen6_rps_busy(struct drm_i915_private *dev_priv);
 void gen6_rps_reset_ei(struct drm_i915_private *dev_priv);
 void gen6_rps_idle(struct drm_i915_private *dev_priv);

drivers/gpu/drm/i915/intel_pm.c

@@ -8196,6 +8196,95 @@ static void intel_init_emon(struct drm_i915_private *dev_priv)
 	dev_priv->ips.corr = (lcfuse & LCFUSE_HIV_MASK);
 }
 
+static bool i915_rc6_ctx_corrupted(struct drm_i915_private *dev_priv)
+{
+	return !I915_READ(GEN8_RC6_CTX_INFO);
+}
+
+static void i915_rc6_ctx_wa_init(struct drm_i915_private *i915)
+{
+	if (!NEEDS_RC6_CTX_CORRUPTION_WA(i915))
+		return;
+
+	if (i915_rc6_ctx_corrupted(i915)) {
+		DRM_INFO("RC6 context corrupted, disabling runtime power management\n");
+		i915->gt_pm.rc6.ctx_corrupted = true;
+		intel_runtime_pm_get(i915);
+	}
+}
+
+static void i915_rc6_ctx_wa_cleanup(struct drm_i915_private *i915)
+{
+	if (i915->gt_pm.rc6.ctx_corrupted) {
+		intel_runtime_pm_put(i915);
+		i915->gt_pm.rc6.ctx_corrupted = false;
+	}
+}
+
+/**
+ * i915_rc6_ctx_wa_suspend - system suspend sequence for the RC6 CTX WA
+ * @i915: i915 device
+ *
+ * Perform any steps needed to clean up the RC6 CTX WA before system suspend.
+ */
+void i915_rc6_ctx_wa_suspend(struct drm_i915_private *i915)
+{
+	if (i915->gt_pm.rc6.ctx_corrupted)
+		intel_runtime_pm_put(i915);
+}
+
+/**
+ * i915_rc6_ctx_wa_resume - system resume sequence for the RC6 CTX WA
+ * @i915: i915 device
+ *
+ * Perform any steps needed to re-init the RC6 CTX WA after system resume.
+ */
+void i915_rc6_ctx_wa_resume(struct drm_i915_private *i915)
+{
+	if (!i915->gt_pm.rc6.ctx_corrupted)
+		return;
+
+	if (i915_rc6_ctx_corrupted(i915)) {
+		intel_runtime_pm_get(i915);
+		return;
+	}
+
+	DRM_INFO("RC6 context restored, re-enabling runtime power management\n");
+	i915->gt_pm.rc6.ctx_corrupted = false;
+}
+
+static void intel_disable_rc6(struct drm_i915_private *dev_priv);
+
+/**
+ * i915_rc6_ctx_wa_check - check for a new RC6 CTX corruption
+ * @i915: i915 device
+ *
+ * Check if an RC6 CTX corruption has happened since the last check and if so
+ * disable RC6 and runtime power management.
+ *
+ * Return false if no context corruption has happened since the last call of
+ * this function, true otherwise.
+*/
+bool i915_rc6_ctx_wa_check(struct drm_i915_private *i915)
+{
+	if (!NEEDS_RC6_CTX_CORRUPTION_WA(i915))
+		return false;
+
+	if (i915->gt_pm.rc6.ctx_corrupted)
+		return false;
+
+	if (!i915_rc6_ctx_corrupted(i915))
+		return false;
+
+	DRM_NOTE("RC6 context corruption, disabling runtime power management\n");
+
+	intel_disable_rc6(i915);
+	i915->gt_pm.rc6.ctx_corrupted = true;
+	intel_runtime_pm_get_noresume(i915);
+
+	return true;
+}
+
 void intel_init_gt_powersave(struct drm_i915_private *dev_priv)
 {
 	struct intel_rps *rps = &dev_priv->gt_pm.rps;
@@ -8211,6 +8300,8 @@ void intel_init_gt_powersave(struct drm_i915_private *dev_priv)
 
 	mutex_lock(&dev_priv->pcu_lock);
 
+	i915_rc6_ctx_wa_init(dev_priv);
+
 	/* Initialize RPS limits (for userspace) */
 	if (IS_CHERRYVIEW(dev_priv))
 		cherryview_init_gt_powersave(dev_priv);
@@ -8257,6 +8348,8 @@ void intel_cleanup_gt_powersave(struct drm_i915_private *dev_priv)
 	if (IS_VALLEYVIEW(dev_priv))
 		valleyview_cleanup_gt_powersave(dev_priv);
 
+	i915_rc6_ctx_wa_cleanup(dev_priv);
+
 	if (!HAS_RC6(dev_priv))
 		intel_runtime_pm_put(dev_priv);
 }
@@ -8301,7 +8394,7 @@ static inline void intel_disable_llc_pstate(struct drm_i915_private *i915)
 	i915->gt_pm.llc_pstate.enabled = false;
 }
 
-static void intel_disable_rc6(struct drm_i915_private *dev_priv)
+static void __intel_disable_rc6(struct drm_i915_private *dev_priv)
 {
 	lockdep_assert_held(&dev_priv->pcu_lock);
 
@@ -8320,6 +8413,13 @@ static void intel_disable_rc6(struct drm_i915_private *dev_priv)
 	dev_priv->gt_pm.rc6.enabled = false;
 }
 
+static void intel_disable_rc6(struct drm_i915_private *dev_priv)
+{
+	mutex_lock(&dev_priv->pcu_lock);
+	__intel_disable_rc6(dev_priv);
+	mutex_unlock(&dev_priv->pcu_lock);
+}
+
 static void intel_disable_rps(struct drm_i915_private *dev_priv)
 {
 	lockdep_assert_held(&dev_priv->pcu_lock);
@@ -8345,7 +8445,7 @@ void intel_disable_gt_powersave(struct drm_i915_private *dev_priv)
 {
 	mutex_lock(&dev_priv->pcu_lock);
 
-	intel_disable_rc6(dev_priv);
+	__intel_disable_rc6(dev_priv);
 	intel_disable_rps(dev_priv);
 	if (HAS_LLC(dev_priv))
 		intel_disable_llc_pstate(dev_priv);
@@ -8372,6 +8472,9 @@ static void intel_enable_rc6(struct drm_i915_private *dev_priv)
 	if (dev_priv->gt_pm.rc6.enabled)
 		return;
 
+	if (dev_priv->gt_pm.rc6.ctx_corrupted)
+		return;
+
 	if (IS_CHERRYVIEW(dev_priv))
 		cherryview_enable_rc6(dev_priv);
 	else if (IS_VALLEYVIEW(dev_priv))