Partially revert "drm/i915: unconditionally use mt forcewake on hsw/ivb"
Subsystems (2)
PATCH v2 1/1 Partially revert "drm/i915: unconditionally use mt forcewake on hsw/ivb"
This patch partially reverts commit 36ec8f877481449bdfa072e6adf2060869e2b970 for IvyBridge CPUs.
The original commit results in repeated 'Timed out waiting for forcewake old ack to clear' messages on a Supermicro C7H61 board (BIOS version 2.00 and 2.00b) with i7-3770K CPU. It ultimately results in a hangup if the system is highly loaded. Reverting the commit for IvyBridge CPUs fixes the issue.
Issue a warning if the CPU is IvyBridge and mt forcewake is disabled, since this condition can result in secondary issues.
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=60541
---
v2: Only revert patch for Ivybridge CPUs
Issue info message if mt forcewake is disabled on Ivybridge
drivers/gpu/drm/i915/intel_pm.c | 31 ++++++++++++++++++++++++++++++- 1 file changed, 30 insertions(+), 1 deletion(-)
drivers/gpu/drm/i915/intel_pm.c +30 -1
@@ -4510,9 +4510,38 @@ void intel_gt_init(struct drm_device *dev)if (IS_VALLEYVIEW (dev)) { dev_priv->gt.force_wake_get = vlv_force_wake_get; dev_priv->gt.force_wake_put = vlv_force_wake_put; - }else if (IS_IVYBRIDGE (dev) ||IS_HASWELL (dev)) { + }else if (IS_HASWELL (dev)) { dev_priv->gt.force_wake_get = __gen6_gt_force_wake_mt_get; dev_priv->gt.force_wake_put = __gen6_gt_force_wake_mt_put; + }else if (IS_IVYBRIDGE (dev)) { +u32 ecobus; + +/* IVB configs may use multi-threaded forcewake */ + +/* A small trick here - if the bios hasn't configured +* MT forcewake, and if the device is in RC6, then +* force_wake_mt_get will not wake the device and the +* ECOBUS read will return zero. Which will be +* (correctly) interpreted by the test below as MT +* forcewake being disabled. +*/ +mutex_lock (&dev->struct_mutex); +__gen6_gt_force_wake_mt_get (dev_priv); + ecobus =I915_READ_NOTRACE (ECOBUS ); +__gen6_gt_force_wake_mt_put (dev_priv); +mutex_unlock (&dev->struct_mutex); + +if (ecobus &FORCEWAKE_MT_ENABLE ) { + dev_priv->gt.force_wake_get = + __gen6_gt_force_wake_mt_get; + dev_priv->gt.force_wake_put = + __gen6_gt_force_wake_mt_put; + }else { +DRM_INFO ("No MT forcewake available on Ivybridge, this can result in issues\n" ); +DRM_INFO ("when using vblank-synced partial screen updates.\n" ); + dev_priv->gt.force_wake_get = __gen6_gt_force_wake_get; + dev_priv->gt.force_wake_put = __gen6_gt_force_wake_put; + } }else if (IS_GEN6 (dev)) { dev_priv->gt.force_wake_get = __gen6_gt_force_wake_get; dev_priv->gt.force_wake_put = __gen6_gt_force_wake_put;
Signature · 1 line
1.7.9.7
Daniel Vetter
AppliedQuoted 8 lines · Guenter Roeck
This patch partially reverts commit
36ec8f877481449bdfa072e6adf2060869e2b970for IvyBridge CPUs.The original commit results in repeated 'Timed out waiting for forcewake old ack to clear' messages on a Supermicro C7H61 board (BIOS version 2.00 and 2.00b) with i7-3770K CPU. It ultimately results in a hangup if the system is highly loaded. Reverting the commit for IvyBridge CPUs fixes the issue.
Quoted 8 lines
Issue a warning if the CPU is IvyBridge and mt forcewake is disabled, since this condition can result in secondary issues.
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=60541
Cc Jesse Barnes <[email protected]>Cc Daniel Vetter <[email protected]>Cc Mika Kuoppala <[email protected]>Signed-off-by Guenter Roeck <[email protected]>
Picked up for -fixes, thanks for the patch.
-Daniel
Signature · 3 lines
Daniel Vetter Software Engineer, Intel Corporation +41 (0) 79 365 57 48 - http://blog.ffwll.ch