[Intel-gfx] [PATCH] drm/i915: Wait one vblank before sending hotplug event to userspace

[Ville Syrjälä]

On Tue, Dec 04, 2018 at 11:46:39AM +0200, Mika Kahola wrote:
> Occasionally, we get the following error in our CI runs
> 
> [853.132830] Workqueue: events i915_hotplug_work_func [i915]
> [853.132844] RIP: 0010:drm_wait_one_vblank+0x19b/0x1b0
> [853.132852] Code: fe ff ff e8 b7 4e a6 ff 48 89 e6 4c 89 ff e8 6c 5f ab ff 45 85 ed 0f 85
> 15 ff ff ff 89 ee 48 c7 c7 e8 03 10 82 e8 b5 4b a6 ff <0f> 0b e9 00 ff ff ff 0f 1f 40 00 66
> 2e 0f 1f 84 00 00 00 00 00 8b
> [853.132859] RSP: 0018:ffffc9000146bca0 EFLAGS: 00010286
> [853.132866] RAX: 0000000000000000 RBX: ffff88849ef00000 RCX: 0000000000000000
> [853.132873] RDX: 0000000000000007 RSI: ffffffff820c6f58 RDI: 00000000ffffffff
> [853.132879] RBP: 0000000000000000 R08: 000000007ffc637a R09: 0000000000000000
> [853.132884] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000
> [853.132890] R13: 0000000000000000 R14: 000000000000d0c2 R15: ffff8884a491e680
> [853.132897] FS:  0000000000000000(0000) GS:ffff8884afe80000(0000) knlGS:0000000000000000
> [853.132904] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> [853.132910] CR2: 00007f63bf0df000 CR3: 0000000005210006 CR4: 0000000000760ee0
> [853.132916] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
> [853.132922] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
> [853.132927] PKRU: 55555554
> [853.132932] Call Trace:
> [853.132949]  ? wait_woken+0xa0/0xa0
> [853.133068]  intel_dp_retrain_link+0x130/0x190 [i915]
> [853.133176]  intel_ddi_hotplug+0x54/0x2e0 [i915]
> [853.133298]  i915_hotplug_work_func+0x1a9/0x240 [i915]
> [853.133324]  process_one_work+0x262/0x630
> [853.133349]  worker_thread+0x37/0x380
> [853.133365]  ? process_one_work+0x630/0x630
> [853.133373]  kthread+0x119/0x130
> [853.133383]  ? kthread_park+0x80/0x80
> [853.133400]  ret_from_fork+0x3a/0x50
> [853.133433] irq event stamp: 1426928
> 
> I suspect that this is caused by a racy condition when retraining the
> DisplayPort link. My proposal is to wait for one additional vblank
> event before we send out a hotplug event to userspace for reprobing.
> 
> Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=108835

The first problem in the log is 
<3> [853.020316] [drm:intel_ddi_prepare_link_retrain [i915]] *ERROR* Timeout waiting for DDI BUF A idle bit
That's where one should start.

Some suspects:
- icl_enable/disable_phy_clock_gating()
- intel_ddi_enable/disable_pipe_clock()

> 
> Cc: Manasi Navare <manasi.d.navare at intel.com>
> Signed-off-by: Mika Kahola <mika.kahola at intel.com>
> ---
>  drivers/gpu/drm/i915/intel_dp.c | 27 +++++++++++++++++++++++++++
>  1 file changed, 27 insertions(+)
> 
> diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
> index a6907a1761ab..6ce7d54e49af 100644
> --- a/drivers/gpu/drm/i915/intel_dp.c
> +++ b/drivers/gpu/drm/i915/intel_dp.c
> @@ -6746,6 +6746,10 @@ static void intel_dp_modeset_retry_work_fn(struct work_struct *work)
>  {
>  	struct intel_connector *intel_connector;
>  	struct drm_connector *connector;
> +	struct drm_connector_state *conn_state;
> +	struct drm_i915_private *dev_priv;
> +	struct intel_crtc *crtc;
> +	struct intel_crtc_state *crtc_state;
>  
>  	intel_connector = container_of(work, typeof(*intel_connector),
>  				       modeset_retry_work);
> @@ -6753,6 +6757,14 @@ static void intel_dp_modeset_retry_work_fn(struct work_struct *work)
>  	DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n", connector->base.id,
>  		      connector->name);
>  
> +	dev_priv = to_i915(connector->dev);
> +	conn_state = intel_connector->base.state;
> +
> +	crtc = to_intel_crtc(conn_state->crtc);
> +	crtc_state = to_intel_crtc_state(crtc->base.state);
> +
> +	WARN_ON(!intel_crtc_has_dp_encoder(crtc_state));
> +
>  	/* Grab the locks before changing connector property*/
>  	mutex_lock(&connector->dev->mode_config.mutex);
>  	/* Set connector link status to BAD and send a Uevent to notify
> @@ -6761,6 +6773,21 @@ static void intel_dp_modeset_retry_work_fn(struct work_struct *work)
>  	drm_connector_set_link_status_property(connector,
>  					       DRM_MODE_LINK_STATUS_BAD);
>  	mutex_unlock(&connector->dev->mode_config.mutex);
> +
> +	/* Suppress underruns caused by re-training */
> +	intel_set_cpu_fifo_underrun_reporting(dev_priv, crtc->pipe, false);
> +	if (crtc_state->has_pch_encoder)
> +		intel_set_pch_fifo_underrun_reporting(dev_priv,
> +						      intel_crtc_pch_transcoder(crtc), false);
> +
> +	/* Keep underrun reporting disabled until things are stable */
> +	intel_wait_for_vblank(dev_priv, crtc->pipe);
> +
> +	intel_set_cpu_fifo_underrun_reporting(dev_priv, crtc->pipe, true);
> +	if (crtc_state->has_pch_encoder)
> +		intel_set_pch_fifo_underrun_reporting(dev_priv,
> +						      intel_crtc_pch_transcoder(crtc), true);
> +
>  	/* Send Hotplug uevent so userspace can reprobe */
>  	drm_kms_helper_hotplug_event(connector->dev);
>  }
> -- 
> 2.17.1
> 
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx at lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/intel-gfx

-- 
Ville Syrjälä
Intel