[Intel-gfx] [PATCH 1/3] drm/i915: Remove livelock from "do_idle_maps" vtd w/a

[Intel-gfx] [PATCH 1/3] drm/i915: Remove livelock from "do_idle_maps" vtd w/a

[Chris Wilson]

A call to wait for the GT to idle from inside the put_pages fallback is
prone to cause an uninterruptible livelock. As it does not provide
adequate serialisation with new requests, simply fallback to a trial
sleep.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_gem_gtt.c | 25 ++++++++++---------------
 1 file changed, 10 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index c5ee1567f3d1..d2350a4c6606 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -55,22 +55,17 @@ int i915_gem_gtt_prepare_pages(struct drm_i915_gem_object *obj,
 void i915_gem_gtt_finish_pages(struct drm_i915_gem_object *obj,
 			       struct sg_table *pages)
 {
-	struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
-	struct device *kdev = &dev_priv->drm.pdev->dev;
-	struct i915_ggtt *ggtt = &dev_priv->ggtt;
-
-	if (unlikely(ggtt->do_idle_maps)) {
-		/* XXX This does not prevent more requests being submitted! */
-		if (intel_gt_retire_requests_timeout(ggtt->vm.gt,
-						     -MAX_SCHEDULE_TIMEOUT)) {
-			drm_err(&dev_priv->drm,
-				"Failed to wait for idle; VT'd may hang.\n");
-			/* Wait a bit, in hopes it avoids the hang */
-			udelay(10);
-		}
-	}
+	struct drm_i915_private *i915 = to_i915(obj->base.dev);
+	struct i915_ggtt *ggtt = &i915->ggtt;
+
+	/* XXX This does not prevent more requests being submitted! */
+	if (unlikely(ggtt->do_idle_maps))
+		/* Wait a bit, in hope it avoids the hang */
+		usleep_range(100, 250);
 
-	dma_unmap_sg(kdev, pages->sgl, pages->nents, PCI_DMA_BIDIRECTIONAL);
+	dma_unmap_sg(&i915->drm.pdev->dev,
+		     pages->sgl, pages->nents,
+		     PCI_DMA_BIDIRECTIONAL);
 }
 
 /**
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 2/3] drm/i915: Sleep around performing iommu unmaps on Tigerlake

[Chris Wilson]

Tigerlake is plagued by spontaneous DMAR faults [reason 7, next page
table ptr is invalid] which lead to GPU hangs. These faults occur when
an iommu map is immediately reused. Adding further clflushes and
barriers around either the GTT PTE or iommu PTE updates do not prevent
the faults. So far the only effect has been from inducing a delay
between reuse of the iommu on the GPU.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
---
 drivers/gpu/drm/i915/gt/intel_ggtt.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c
index cf94525be2c1..f5b981443117 100644
--- a/drivers/gpu/drm/i915/gt/intel_ggtt.c
+++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c
@@ -101,7 +101,16 @@ static bool needs_idle_maps(struct drm_i915_private *i915)
 	 * Query intel_iommu to see if we need the workaround. Presumably that
 	 * was loaded first.
 	 */
-	return IS_GEN(i915, 5) && IS_MOBILE(i915) && intel_vtd_active();
+	if (!intel_vtd_active())
+		return false;
+
+	if (IS_GEN(i915, 5) && IS_MOBILE(i915))
+		return true;
+
+	if (IS_GEN(i915, 12))
+		return true; /* XXX DMAR fault reason 7 */
+
+	return false;
 }
 
 void i915_ggtt_suspend(struct i915_ggtt *ggtt)
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [Intel-gfx] [PATCH 2/3] drm/i915: Sleep around performing iommu unmaps on Tigerlake

[Mika Kuoppala]

Chris Wilson <chris@chris-wilson.co.uk> writes:

> Tigerlake is plagued by spontaneous DMAR faults [reason 7, next page
> table ptr is invalid] which lead to GPU hangs. These faults occur when
> an iommu map is immediately reused. Adding further clflushes and
> barriers around either the GTT PTE or iommu PTE updates do not prevent
> the faults. So far the only effect has been from inducing a delay
> between reuse of the iommu on the GPU.
>
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>

Acked-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>

> ---
>  drivers/gpu/drm/i915/gt/intel_ggtt.c | 11 ++++++++++-
>  1 file changed, 10 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c
> index cf94525be2c1..f5b981443117 100644
> --- a/drivers/gpu/drm/i915/gt/intel_ggtt.c
> +++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c
> @@ -101,7 +101,16 @@ static bool needs_idle_maps(struct drm_i915_private *i915)
>  	 * Query intel_iommu to see if we need the workaround. Presumably that
>  	 * was loaded first.
>  	 */
> -	return IS_GEN(i915, 5) && IS_MOBILE(i915) && intel_vtd_active();
> +	if (!intel_vtd_active())
> +		return false;
> +
> +	if (IS_GEN(i915, 5) && IS_MOBILE(i915))
> +		return true;
> +
> +	if (IS_GEN(i915, 12))
> +		return true; /* XXX DMAR fault reason 7 */
> +
> +	return false;
>  }
>  
>  void i915_ggtt_suspend(struct i915_ggtt *ggtt)
> -- 
> 2.20.1
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH 3/3] drm/i915/gt: Remove uninterruptible parameter from intel_gt_wait_for_idle

[Chris Wilson]

Now that the only user of the uninterruptible wait was eliminated,
remove the support.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/gt/intel_gt_requests.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_gt_requests.c b/drivers/gpu/drm/i915/gt/intel_gt_requests.c
index 66fcbf9d0fdd..dc06c78c9eeb 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_requests.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_requests.c
@@ -135,13 +135,8 @@ long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout)
 	struct intel_gt_timelines *timelines = &gt->timelines;
 	struct intel_timeline *tl, *tn;
 	unsigned long active_count = 0;
-	bool interruptible;
 	LIST_HEAD(free);
 
-	interruptible = true;
-	if (unlikely(timeout < 0))
-		timeout = -timeout, interruptible = false;
-
 	flush_submission(gt, timeout); /* kick the ksoftirqd tasklets */
 	spin_lock(&timelines->lock);
 	list_for_each_entry_safe(tl, tn, &timelines->active_list, link) {
@@ -163,7 +158,7 @@ long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout)
 				mutex_unlock(&tl->mutex);
 
 				timeout = dma_fence_wait_timeout(fence,
-								 interruptible,
+								 true,
 								 timeout);
 				dma_fence_put(fence);
 
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [Intel-gfx] [PATCH 3/3] drm/i915/gt: Remove uninterruptible parameter from intel_gt_wait_for_idle

[Mika Kuoppala]

Chris Wilson <chris@chris-wilson.co.uk> writes:

> Now that the only user of the uninterruptible wait was eliminated,
> remove the support.
>
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>

Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>

> ---
>  drivers/gpu/drm/i915/gt/intel_gt_requests.c | 7 +------
>  1 file changed, 1 insertion(+), 6 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/gt/intel_gt_requests.c b/drivers/gpu/drm/i915/gt/intel_gt_requests.c
> index 66fcbf9d0fdd..dc06c78c9eeb 100644
> --- a/drivers/gpu/drm/i915/gt/intel_gt_requests.c
> +++ b/drivers/gpu/drm/i915/gt/intel_gt_requests.c
> @@ -135,13 +135,8 @@ long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout)
>  	struct intel_gt_timelines *timelines = &gt->timelines;
>  	struct intel_timeline *tl, *tn;
>  	unsigned long active_count = 0;
> -	bool interruptible;
>  	LIST_HEAD(free);
>  
> -	interruptible = true;
> -	if (unlikely(timeout < 0))
> -		timeout = -timeout, interruptible = false;
> -
>  	flush_submission(gt, timeout); /* kick the ksoftirqd tasklets */
>  	spin_lock(&timelines->lock);
>  	list_for_each_entry_safe(tl, tn, &timelines->active_list, link) {
> @@ -163,7 +158,7 @@ long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout)
>  				mutex_unlock(&tl->mutex);
>  
>  				timeout = dma_fence_wait_timeout(fence,
> -								 interruptible,
> +								 true,
>  								 timeout);
>  				dma_fence_put(fence);
>  
> -- 
> 2.20.1
>
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx@lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/intel-gfx
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] ✗ Fi.CI.BAT: failure for series starting with [1/3] drm/i915: Remove livelock from "do_idle_maps" vtd w/a

[Patchwork]

[-- Attachment #1.1: Type: text/plain, Size: 5428 bytes --]

== Series Details ==

Series: series starting with [1/3] drm/i915: Remove livelock from "do_idle_maps" vtd w/a
URL   : https://patchwork.freedesktop.org/series/84706/
State : failure

== Summary ==

CI Bug Log - changes from CI_DRM_9463 -> Patchwork_19083
====================================================

Summary
-------

  **FAILURE**

  Serious unknown changes coming with Patchwork_19083 absolutely need to be
  verified manually.
  
  If you think the reported changes have nothing to do with the changes
  introduced in Patchwork_19083, please notify your bug team to allow them
  to document this new failure mode, which will reduce false positives in CI.

  External URL: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19083/index.html

Possible new issues
-------------------

  Here are the unknown changes that may have been introduced in Patchwork_19083:

### IGT changes ###

#### Possible regressions ####

  * igt@i915_selftest@live@gem_contexts:
    - fi-apl-guc:         [PASS][1] -> [INCOMPLETE][2]
   [1]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9463/fi-apl-guc/igt@i915_selftest@live@gem_contexts.html
   [2]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19083/fi-apl-guc/igt@i915_selftest@live@gem_contexts.html

  * igt@i915_selftest@live@requests:
    - fi-apl-guc:         [PASS][3] -> [DMESG-WARN][4]
   [3]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9463/fi-apl-guc/igt@i915_selftest@live@requests.html
   [4]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19083/fi-apl-guc/igt@i915_selftest@live@requests.html

  
New tests
---------

  New tests have been introduced between CI_DRM_9463 and Patchwork_19083:

### New CI tests (1) ###

  * boot:
    - Statuses : 1 fail(s) 39 pass(s)
    - Exec time: [0.0] s

  

Known issues
------------

  Here are the changes found in Patchwork_19083 that come from known issues:

### IGT changes ###

#### Issues hit ####

  * igt@amdgpu/amd_basic@semaphore:
    - fi-icl-y:           NOTRUN -> [SKIP][5] ([fdo#109315]) +17 similar issues
   [5]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19083/fi-icl-y/igt@amdgpu/amd_basic@semaphore.html

  * igt@i915_pm_rpm@module-reload:
    - fi-byt-j1900:       [PASS][6] -> [INCOMPLETE][7] ([i915#142] / [i915#2405])
   [6]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9463/fi-byt-j1900/igt@i915_pm_rpm@module-reload.html
   [7]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19083/fi-byt-j1900/igt@i915_pm_rpm@module-reload.html

  * igt@runner@aborted:
    - fi-apl-guc:         NOTRUN -> [FAIL][8] ([i915#2426] / [i915#2722])
   [8]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19083/fi-apl-guc/igt@runner@aborted.html
    - fi-byt-j1900:       NOTRUN -> [FAIL][9] ([i915#1814])
   [9]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19083/fi-byt-j1900/igt@runner@aborted.html

  * igt@vgem_basic@dmabuf-fence-before:
    - fi-tgl-y:           [PASS][10] -> [DMESG-WARN][11] ([i915#402]) +2 similar issues
   [10]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9463/fi-tgl-y/igt@vgem_basic@dmabuf-fence-before.html
   [11]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19083/fi-tgl-y/igt@vgem_basic@dmabuf-fence-before.html

  
#### Possible fixes ####

  * igt@gem_flink_basic@double-flink:
    - fi-tgl-y:           [DMESG-WARN][12] ([i915#402]) -> [PASS][13] +1 similar issue
   [12]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9463/fi-tgl-y/igt@gem_flink_basic@double-flink.html
   [13]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19083/fi-tgl-y/igt@gem_flink_basic@double-flink.html

  * igt@i915_selftest@live@execlists:
    - fi-icl-y:           [INCOMPLETE][14] ([i915#1037] / [i915#2276]) -> [PASS][15]
   [14]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_9463/fi-icl-y/igt@i915_selftest@live@execlists.html
   [15]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19083/fi-icl-y/igt@i915_selftest@live@execlists.html

  
  [fdo#109315]: https://bugs.freedesktop.org/show_bug.cgi?id=109315
  [i915#1037]: https://gitlab.freedesktop.org/drm/intel/issues/1037
  [i915#142]: https://gitlab.freedesktop.org/drm/intel/issues/142
  [i915#1814]: https://gitlab.freedesktop.org/drm/intel/issues/1814
  [i915#2276]: https://gitlab.freedesktop.org/drm/intel/issues/2276
  [i915#2405]: https://gitlab.freedesktop.org/drm/intel/issues/2405
  [i915#2426]: https://gitlab.freedesktop.org/drm/intel/issues/2426
  [i915#2722]: https://gitlab.freedesktop.org/drm/intel/issues/2722
  [i915#402]: https://gitlab.freedesktop.org/drm/intel/issues/402


Participating hosts (43 -> 40)
------------------------------

  Missing    (3): fi-ilk-m540 fi-bdw-samus fi-hsw-4200u 


Build changes
-------------

  * Linux: CI_DRM_9463 -> Patchwork_19083

  CI-20190529: 20190529
  CI_DRM_9463: 1c64d5d72bcd4e6ccf2d0ba6e6ab3644497846b5 @ git://anongit.freedesktop.org/gfx-ci/linux
  IGT_5885: d99f644b1868b9c92435b05ebfafa230721cd677 @ git://anongit.freedesktop.org/xorg/app/intel-gpu-tools
  Patchwork_19083: c73b1388041d8bc867aeff9b59f39b24c6a5176c @ git://anongit.freedesktop.org/gfx-ci/linux


== Linux commits ==

c73b1388041d drm/i915/gt: Remove uninterruptible parameter from intel_gt_wait_for_idle
5e69d96f8d69 drm/i915: Sleep around performing iommu unmaps on Tigerlake
ae5a735df1bb drm/i915: Remove livelock from "do_idle_maps" vtd w/a

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_19083/index.html

[-- Attachment #1.2: Type: text/html, Size: 6381 bytes --]

[-- Attachment #2: Type: text/plain, Size: 160 bytes --]

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [Intel-gfx] [PATCH 1/3] drm/i915: Remove livelock from "do_idle_maps" vtd w/a

[Mika Kuoppala]

Chris Wilson <chris@chris-wilson.co.uk> writes:

> A call to wait for the GT to idle from inside the put_pages fallback is
> prone to cause an uninterruptible livelock. As it does not provide
> adequate serialisation with new requests, simply fallback to a trial

s/trial/trivial
> sleep.
>
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>

Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>

> ---
>  drivers/gpu/drm/i915/i915_gem_gtt.c | 25 ++++++++++---------------
>  1 file changed, 10 insertions(+), 15 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
> index c5ee1567f3d1..d2350a4c6606 100644
> --- a/drivers/gpu/drm/i915/i915_gem_gtt.c
> +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
> @@ -55,22 +55,17 @@ int i915_gem_gtt_prepare_pages(struct drm_i915_gem_object *obj,
>  void i915_gem_gtt_finish_pages(struct drm_i915_gem_object *obj,
>  			       struct sg_table *pages)
>  {
> -	struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
> -	struct device *kdev = &dev_priv->drm.pdev->dev;
> -	struct i915_ggtt *ggtt = &dev_priv->ggtt;
> -
> -	if (unlikely(ggtt->do_idle_maps)) {
> -		/* XXX This does not prevent more requests being submitted! */
> -		if (intel_gt_retire_requests_timeout(ggtt->vm.gt,
> -						     -MAX_SCHEDULE_TIMEOUT)) {
> -			drm_err(&dev_priv->drm,
> -				"Failed to wait for idle; VT'd may hang.\n");
> -			/* Wait a bit, in hopes it avoids the hang */
> -			udelay(10);
> -		}
> -	}
> +	struct drm_i915_private *i915 = to_i915(obj->base.dev);
> +	struct i915_ggtt *ggtt = &i915->ggtt;
> +
> +	/* XXX This does not prevent more requests being submitted! */
> +	if (unlikely(ggtt->do_idle_maps))
> +		/* Wait a bit, in hope it avoids the hang */
> +		usleep_range(100, 250);
>  
> -	dma_unmap_sg(kdev, pages->sgl, pages->nents, PCI_DMA_BIDIRECTIONAL);
> +	dma_unmap_sg(&i915->drm.pdev->dev,
> +		     pages->sgl, pages->nents,
> +		     PCI_DMA_BIDIRECTIONAL);
>  }
>  
>  /**
> -- 
> 2.20.1
>
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx@lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/intel-gfx
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx