From 59d02a1f45beb1b6f4ef83a47feb264cb3577725 Mon Sep 17 00:00:00 2001 From: Imre Deak Date: Fri, 19 Dec 2014 19:33:26 +0200 Subject: [PATCH] drm/i915: fix HW lockup due to missing RPS IRQ workaround on GEN6 In commit dbea3cea69508e9d548ed4a6be13de35492e5d15 Author: Imre Deak Date: Mon Dec 15 18:59:28 2014 +0200 drm/i915: sanitize RPS resetting during GPU reset we disable RPS interrupts during GPU resetting, but don't apply the necessary GEN6 HW workaround. This leads to a HW lockup during a subsequent "looping batchbuffer" workload. This is triggered by the testcase that submits exactly this kind of workload after a simulated GPU reset. I'm not sure how likely the bug would have triggered otherwise, since we would have applied the workaround anyway shortly after the GPU reset, when enabling GT powersaving from the deferred work. This may also fix unrelated issues, since during driver loading / suspending we also disable RPS interrupts and so we also had a short window during the rest of the loading / resuming where a similar workload could run without the workaround applied. v2: - separate the fix to route RPS interrupts to the CPU on GEN9 too to a separate patch (Daniel) Bisected-by: Ander Conselvan de Oliveira Testcase: igt/gem_reset_stats/ban-ctx-render Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=87429 Signed-off-by: Imre Deak Reviewed-by: Daniel Vetter Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/i915_irq.c | 18 ++++++++++++++++-- drivers/gpu/drm/i915/intel_drv.h | 1 + drivers/gpu/drm/i915/intel_pm.c | 11 +---------- 3 files changed, 18 insertions(+), 12 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index d0d3dfbe6d2a..ba86dc330547 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -292,6 +292,21 @@ void gen6_enable_rps_interrupts(struct drm_device *dev) spin_unlock_irq(&dev_priv->irq_lock); } +u32 gen6_sanitize_rps_pm_mask(struct drm_i915_private *dev_priv, u32 mask) +{ + /* + * IVB and SNB hard hangs on looping batchbuffer + * if GEN6_PM_UP_EI_EXPIRED is masked. + */ + if (INTEL_INFO(dev_priv)->gen <= 7 && !IS_HASWELL(dev_priv)) + mask &= ~GEN6_PM_RP_UP_EI_EXPIRED; + + if (INTEL_INFO(dev_priv)->gen >= 8) + mask &= ~GEN8_PMINTR_REDIRECT_TO_NON_DISP; + + return mask; +} + void gen6_disable_rps_interrupts(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -304,8 +319,7 @@ void gen6_disable_rps_interrupts(struct drm_device *dev) spin_lock_irq(&dev_priv->irq_lock); - I915_WRITE(GEN6_PMINTRMSK, INTEL_INFO(dev_priv)->gen >= 8 ? - ~GEN8_PMINTR_REDIRECT_TO_NON_DISP : ~0); + I915_WRITE(GEN6_PMINTRMSK, gen6_sanitize_rps_pm_mask(dev_priv, ~0)); __gen6_disable_pm_irq(dev_priv, dev_priv->pm_rps_events); I915_WRITE(gen6_pm_ier(dev_priv), I915_READ(gen6_pm_ier(dev_priv)) & diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index 25fdbb16d4e0..3b40a17b8852 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -794,6 +794,7 @@ void gen6_disable_pm_irq(struct drm_i915_private *dev_priv, uint32_t mask); void gen6_reset_rps_interrupts(struct drm_device *dev); void gen6_enable_rps_interrupts(struct drm_device *dev); void gen6_disable_rps_interrupts(struct drm_device *dev); +u32 gen6_sanitize_rps_pm_mask(struct drm_i915_private *dev_priv, u32 mask); void intel_runtime_pm_disable_interrupts(struct drm_i915_private *dev_priv); void intel_runtime_pm_enable_interrupts(struct drm_i915_private *dev_priv); static inline bool intel_irqs_enabled(struct drm_i915_private *dev_priv) diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 78e308bebac9..3801ff59595f 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -4363,16 +4363,7 @@ static u32 gen6_rps_pm_mask(struct drm_i915_private *dev_priv, u8 val) mask |= dev_priv->pm_rps_events & (GEN6_PM_RP_DOWN_EI_EXPIRED | GEN6_PM_RP_UP_EI_EXPIRED); mask &= dev_priv->pm_rps_events; - /* IVB and SNB hard hangs on looping batchbuffer - * if GEN6_PM_UP_EI_EXPIRED is masked. - */ - if (INTEL_INFO(dev_priv->dev)->gen <= 7 && !IS_HASWELL(dev_priv->dev)) - mask |= GEN6_PM_RP_UP_EI_EXPIRED; - - if (INTEL_INFO(dev_priv)->gen >= 8) - mask |= GEN8_PMINTR_REDIRECT_TO_NON_DISP; - - return ~mask; + return gen6_sanitize_rps_pm_mask(dev_priv, ~mask); } /* gen6_set_rps is called to update the frequency request, but should also be -- 2.20.1