From 3b30197a63f93c0c315b46d73120cca0d55e4973 Mon Sep 17 00:00:00 2001 From: =?utf8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Mon, 23 May 2016 17:42:48 +0300 Subject: [PATCH] drm/i915: Never fully mask the the EI up rps interrupt on SNB/IVB MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit commit a7b4667a00025ac28300737c868bd4818b6d8c4d upstream. SNB (and IVB too I suppose) starts to misbehave if the GPU gets stuck in an infinite batch buffer loop. The GPU apparently hogs something critical and CPUs start to lose interrupts and whatnot. We can keep the system limping along by unmasking some interrupts in GEN6_PMINTRMSK. The EI up interrupt has been previously chosen for that task, so let's never mask it. v2: s/gen6_rps_pm_mask/gen6_sanitize_rps_pm_mask/ (Chris) Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=93122 Signed-off-by: Ville Syrjälä Reviewed-by: Chris Wilson Signed-off-by: Chris Wilson Link: http://patchwork.freedesktop.org/patch/msgid/1464014568-4529-1-git-send-email-ville.syrjala@linux.intel.com (cherry picked from commit 12c100bfa5d9103b6c4d43636fee09c31e75605a) Signed-off-by: Daniel Vetter Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/intel_pm.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index eb434881ddbc..1e851e037c29 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -4526,7 +4526,8 @@ void gen6_rps_idle(struct drm_i915_private *dev_priv) else gen6_set_rps(dev_priv->dev, dev_priv->rps.idle_freq); dev_priv->rps.last_adj = 0; - I915_WRITE(GEN6_PMINTRMSK, 0xffffffff); + I915_WRITE(GEN6_PMINTRMSK, + gen6_sanitize_rps_pm_mask(dev_priv, ~0)); } mutex_unlock(&dev_priv->rps.hw_lock); -- 2.20.1