drm/i915/bdw: Clean up execlist queue items in retire_work

PATCH In review Thomas Daniel 4 participants 12 messages Oct 20, 2014 – Oct 24, 2014

Subsystems (2)

DRM drivers Intel i915

lore

Share & tools

lore

Thomas Daniel

author

2014-10-20 12:52 UTC #0 lore raw

PATCH 1/1 drm/i915/bdw: Clean up execlist queue items in retire_work

No longer create a work item to clean each execlist queue item. Instead, move retired execlist requests to a queue and clean up the items during retire_requests.

Issue: VIZ-4274

Signed-off-by Thomas Daniel <[email protected]>

---
 drivers/gpu/drm/i915/i915_gem.c         |    1 +
 drivers/gpu/drm/i915/intel_lrc.c        |   52 ++++++++++++++++++-------------
 drivers/gpu/drm/i915/intel_lrc.h        |    2 +-
 drivers/gpu/drm/i915/intel_ringbuffer.h |    1 +
 4 files changed, 33 insertions(+), 23 deletions(-)

drivers/gpu/drm/i915/i915_gem.c +1 -0

index 895f988..6a3e0ea 100644
@@ -2718,6 +2718,7 @@ i915_gem_retire_requests(struct drm_device *dev)
 	for_each_ring(ring, dev_priv, i) {
 		i915_gem_retire_requests_ring(ring);
 		idle &= list_empty(&ring->request_list);
+			intel_execlists_retire_requests(ring);
 	}
 
 	if (idle)

drivers/gpu/drm/i915/intel_lrc.c +30 ~~-22~~

106 lines not on this page · raw message

drivers/gpu/drm/i915/intel_lrc.h +1 -1

index 33c3b4b..84bbf19 100644
@@ -104,11 +104,11 @@ struct intel_ctx_submit_request {
 	u32 tail;
 
 	struct list_head execlist_link;
-	struct work_struct work;
 
 	int elsp_submitted;
 };
 
 void intel_execlists_handle_ctx_events(struct intel_engine_cs *ring);
+void intel_execlists_retire_requests(struct intel_engine_cs *ring);
 
 #endif /* _INTEL_LRC_H_ */

drivers/gpu/drm/i915/intel_ringbuffer.h +1 -0

index 96479c8..8c002d2 100644
@@ -235,6 +235,7 @@ struct  intel_engine_cs {
 	/* Execlists */
 	spinlock_t execlist_lock;
 	struct list_head execlist_queue;
+	struct list_head execlist_retired_req_list;
 	u8 next_context_status_buffer;
 	u32             irq_keep_mask; /* bitmask for interrupts that should not be masked */
 	int		(*emit_request)(struct intel_ringbuffer *ringbuf);

Signature · 1 line

1.7.9.5

Thomas Daniel

author

2014-10-20 13:06 UTC #1 lore raw

PATCH 1/1 drm/i915/bdw: Clean up execlist queue items in retire_work

No longer create a work item to clean each execlist queue item. Instead, move retired execlist requests to a queue and clean up the items during retire_requests.

v2: Fix legacy ring path broken during overzealous cleanup

Issue: VIZ-4274

Signed-off-by Thomas Daniel <[email protected]>

---
 drivers/gpu/drm/i915/i915_gem.c         |    2 ++
 drivers/gpu/drm/i915/intel_lrc.c        |   52 ++++++++++++++++++-------------
 drivers/gpu/drm/i915/intel_lrc.h        |    2 +-
 drivers/gpu/drm/i915/intel_ringbuffer.h |    1 +
 4 files changed, 34 insertions(+), 23 deletions(-)

drivers/gpu/drm/i915/i915_gem.c +2 -0

index 895f988..65cfe9a 100644
@@ -2718,6 +2718,8 @@ i915_gem_retire_requests(struct drm_device *dev)
 	for_each_ring(ring, dev_priv, i) {
 		i915_gem_retire_requests_ring(ring);
 		idle &= list_empty(&ring->request_list);
+		if (i915.enable_execlists)
+			intel_execlists_retire_requests(ring);
 	}
 
 	if (idle)

drivers/gpu/drm/i915/intel_lrc.c +30 ~~-22~~

106 lines not on this page · raw message

drivers/gpu/drm/i915/intel_lrc.h +1 -1

index 33c3b4b..84bbf19 100644
@@ -104,11 +104,11 @@ struct intel_ctx_submit_request {
 	u32 tail;
 
 	struct list_head execlist_link;
-	struct work_struct work;
 
 	int elsp_submitted;
 };
 
 void intel_execlists_handle_ctx_events(struct intel_engine_cs *ring);
+void intel_execlists_retire_requests(struct intel_engine_cs *ring);
 
 #endif /* _INTEL_LRC_H_ */

drivers/gpu/drm/i915/intel_ringbuffer.h +1 -0

index 96479c8..8c002d2 100644
@@ -235,6 +235,7 @@ struct  intel_engine_cs {
 	/* Execlists */
 	spinlock_t execlist_lock;
 	struct list_head execlist_queue;
+	struct list_head execlist_retired_req_list;
 	u8 next_context_status_buffer;
 	u32             irq_keep_mask; /* bitmask for interrupts that should not be masked */
 	int		(*emit_request)(struct intel_ringbuffer *ringbuf);

Signature · 1 line

1.7.9.5

Chris Wilson

2014-10-20 13:11 UTC #2 lore raw

Quoted 5 lines · Thomas Daniel

No longer create a work item to clean each execlist queue item. Instead, move retired execlist requests to a queue and clean up the items during retire_requests.
v2: Fix legacy ring path broken during overzealous cleanup

At some point I presume you noticed that you broke the idle detection... Please do read http://patchwork.freedesktop.org/patch/33175/ and reconsider.
-Chris

Signature · 1 line

Chris Wilson, Intel Open Source Technology Centre

Daniel, Thomas

author

2014-10-20 13:31 UTC #3 lore raw

Quoted 8 lines

-----Original Message-----
From: Chris Wilson [mailto:[email protected]]
Sent: Monday, October 20, 2014 2:11 PM
To: Daniel, Thomas
Cc: [email protected]; [email protected]
Subject: Re: [Intel-gfx] [PATCH] drm/i915/bdw: Clean up execlist queue items in retire_work

Quoted 8 lines

Quoted 5 lines · Thomas Daniel
No longer create a work item to clean each execlist queue item. Instead, move retired execlist requests to a queue and clean up the items during retire_requests.
v2: Fix legacy ring path broken during overzealous cleanup
At some point I presume you noticed that you broke the idle detection...

This patch doesn't change the idle detection. Did you want the idle flag to now take into account the state of the execlists requests as well?

Quoted 2 lines

Please do read http://patchwork.freedesktop.org/patch/33175/ and reconsider.

Are you saying that my patch is not required because that patch reworks the code?

Cheers,
Thomas.

Quoted 4 lines

-Chris
--
Chris Wilson, Intel Open Source Technology Centre

Daniel Vetter

2014-10-24 08:18 UTC #4 lore raw

Quoted 13 lines · Thomas

Quoted 13 lines
-----Original Message-----
From: Chris Wilson [mailto:[email protected]]
Sent: Monday, October 20, 2014 2:11 PM
To: Daniel, Thomas
Cc: [email protected]; [email protected]
Subject: Re: [Intel-gfx] [PATCH] drm/i915/bdw: Clean up execlist queue items in retire_work
Quoted 4 lines · Thomas Daniel
No longer create a work item to clean each execlist queue item. Instead, move retired execlist requests to a queue and clean up the items during retire_requests.

Quoted 5 lines

Quoted 3 lines
Quoted 1 line
v2: Fix legacy ring path broken during overzealous cleanup
At some point I presume you noticed that you broke the idle detection...
This patch doesn't change the idle detection. Did you want the idle flag to now take into account the state of the execlists requests as well?

I guess what Chris means is that execlist broke idle detection (by retiring in a separate work item, but not integrating with the idle handling in the existing one). This patch gets us half-way there but still doesn't really integrate things back fully.

We probably need (again) the s/execlist_item/request/ refactor to make this happen for real. Since that's what Chris' patch does he featured the link to it as an endpoint guideline I think.

Or am I completely missing the point again?

Cheers, Daniel

Signature · 3 lines

Daniel Vetter
Software Engineer, Intel Corporation
+41 (0) 79 365 57 48 - http://blog.ffwll.ch

[email protected]

Tested-by on v1 1/1

2014-10-20 16:56 UTC #5 lore raw

Re: [PATCH] drm/i915/bdw: Clean up execlist queue items in

In reply to Thomas Daniel

Tested-by PRC QA PRTS (Patch Regression Test System Contact: [email protected])

[email protected]

Tested-by on v1 1/1

2014-10-20 13:54 UTC #6 lore raw

Re: [PATCH] drm/i915/bdw: Clean up execlist queue items in

In reply to Thomas Daniel

Tested-by PRC QA PRTS (Patch Regression Test System Contact: [email protected])

He, Shuang

2014-10-20 14:21 UTC #7 lore raw

Re: [PATCH] drm/i915/bdw: Clean up execlist queue items in

Quoted 8 lines

-----Original Message-----
From: He, Shuang
Sent: Monday, October 20, 2014 9:47 PM
To: He, Shuang; [email protected]; Daniel, Thomas
Subject: RE: [Intel-gfx] [PATCH] drm/i915/bdw: Clean up execlist queue items in
Tested-By: PRC QA PRTS (Patch Regression Test System Contact:
[email protected])

[He, Shuang] Hello, there's definitely something wrong with this test result, I will check what happened

Thanks
--Shuang

Quoted 12 lines

-------------------------------------Summary-------------------------------------
Platform: baseline_drm_intel_nightly_pass_rate->patch_applied_pass_rate
BYT: pass/total=1/1->1/1
PNV: pass/total=1/1->1/1
ILK: pass/total=1/1->1/1
IVB: pass/total=1/1->1/1
SNB: pass/total=1/1->1/1
HSW: pass/total=1/1->1/1
BDW: pass/total=1/1->1/1 -------------------------------------Detailed-------------------------------------
test_platform: test_suite, test_case, result_with_drm_intel_nightly->result_with_patch_applied

[email protected]

Tested-by on v1 1/1

2014-10-21 08:40 UTC #8 lore raw

Re: [PATCH] drm/i915/bdw: Clean up execlist queue items in

In reply to Thomas Daniel

Tested-by PRC QA PRTS (Patch Regression Test System Contact: [email protected])

-------------------------------------Summary-------------------------------------
Platform: baseline_drm_intel_nightly_pass_rate->patch_applied_pass_rate
BYT: pass/total=19/19->3/19
PNV: pass/total=2/2->1/2
ILK: pass/total=15/15->3/15
IVB: pass/total=2/2->1/2
SNB: pass/total=16/16->3/16
HSW: pass/total=2/2->1/2
BDW: pass/total=17/17->3/17 -------------------------------------Detailed-------------------------------------
test_platform: test_suite, test_case, result_with_drm_intel_nightly->result_with_patch_applied
BYT: Intel_gpu_tools, igt_core_getclient, PASS->TIMEOUT
BYT: Intel_gpu_tools, igt_core_get_client_auth_master-drop, PASS->TIMEOUT
BYT: Intel_gpu_tools, igt_core_get_client_auth_simple, PASS->TIMEOUT
BYT: Intel_gpu_tools, igt_core_getstats, PASS->TIMEOUT
BYT: Intel_gpu_tools, igt_core_getversion, PASS->TIMEOUT
BYT: Intel_gpu_tools, igt_debugfs_emon_crash, PASS->TIMEOUT
BYT: Intel_gpu_tools, igt_drm_vma_limiter, PASS->TIMEOUT
BYT: Intel_gpu_tools, igt_drm_vma_limiter_cached, PASS->TIMEOUT
BYT: Intel_gpu_tools, igt_drv_debugfs_reader, PASS->TIMEOUT
BYT: Intel_gpu_tools, igt_drv_hangman_error-state-basic, PASS->TIMEOUT
BYT: Intel_gpu_tools, igt_drv_hangman_error-state-capture-render, PASS->TIMEOUT
BYT: Intel_gpu_tools, igt_drv_hangman_error-state-debugfs-entry, PASS->TIMEOUT
BYT: Intel_gpu_tools, igt_drv_hangman_error-state-sysfs-entry, PASS->TIMEOUT
BYT: Intel_gpu_tools, igt_drv_hangman_ring-stop-sysfs-entry, PASS->TIMEOUT
BYT: Intel_gpu_tools, igt_drv_missed_irq_hang, PASS->TIMEOUT
BYT: Intel_gpu_tools, igt_gem_bad_length, PASS->TIMEOUT
PNV: Sanity, boot, PASS->FAIL
ILK: Intel_gpu_tools, igt_core_getclient, PASS->TIMEOUT
ILK: Intel_gpu_tools, igt_core_get_client_auth_master-drop, PASS->TIMEOUT
ILK: Intel_gpu_tools, igt_core_get_client_auth_simple, PASS->TIMEOUT
ILK: Intel_gpu_tools, igt_core_getstats, PASS->TIMEOUT
ILK: Intel_gpu_tools, igt_core_getversion, PASS->TIMEOUT
ILK: Intel_gpu_tools, igt_debugfs_emon_crash, PASS->TIMEOUT
ILK: Intel_gpu_tools, igt_drm_vma_limiter, PASS->TIMEOUT
ILK: Intel_gpu_tools, igt_drm_vma_limiter_cached, PASS->TIMEOUT
ILK: Intel_gpu_tools, igt_drv_debugfs_reader, PASS->TIMEOUT
ILK: Intel_gpu_tools, igt_drv_hangman_error-state-basic, PASS->TIMEOUT
ILK: Intel_gpu_tools, igt_drv_hangman_error-state-capture-render, PASS->TIMEOUT
ILK: Intel_gpu_tools, igt_drv_hangman_error-state-debugfs-entry, PASS->TIMEOUT
IVB: Sanity, boot, PASS->FAIL
SNB: Intel_gpu_tools, igt_core_getclient, PASS->TIMEOUT
SNB: Intel_gpu_tools, igt_core_get_client_auth_master-drop, PASS->TIMEOUT
SNB: Intel_gpu_tools, igt_core_get_client_auth_simple, PASS->TIMEOUT
SNB: Intel_gpu_tools, igt_core_getstats, PASS->TIMEOUT
SNB: Intel_gpu_tools, igt_core_getversion, PASS->TIMEOUT
SNB: Intel_gpu_tools, igt_debugfs_emon_crash, PASS->TIMEOUT
SNB: Intel_gpu_tools, igt_drm_vma_limiter, PASS->TIMEOUT
SNB: Intel_gpu_tools, igt_drm_vma_limiter_cached, PASS->TIMEOUT
SNB: Intel_gpu_tools, igt_drv_debugfs_reader, PASS->TIMEOUT
SNB: Intel_gpu_tools, igt_drv_hangman_error-state-basic, PASS->TIMEOUT
SNB: Intel_gpu_tools, igt_drv_hangman_error-state-capture-render, PASS->TIMEOUT
SNB: Intel_gpu_tools, igt_drv_hangman_error-state-debugfs-entry, PASS->TIMEOUT
SNB: Intel_gpu_tools, igt_drv_hangman_error-state-sysfs-entry, PASS->TIMEOUT
HSW: Sanity, boot, PASS->FAIL
BDW: Intel_gpu_tools, igt_core_getclient, PASS->TIMEOUT
BDW: Intel_gpu_tools, igt_core_get_client_auth_master-drop, PASS->TIMEOUT
BDW: Intel_gpu_tools, igt_core_get_client_auth_simple, PASS->TIMEOUT
BDW: Intel_gpu_tools, igt_core_getstats, PASS->TIMEOUT
BDW: Intel_gpu_tools, igt_core_getversion, PASS->TIMEOUT
BDW: Intel_gpu_tools, igt_debugfs_emon_crash, PASS->TIMEOUT
BDW: Intel_gpu_tools, igt_drm_vma_limiter, PASS->TIMEOUT
BDW: Intel_gpu_tools, igt_drm_vma_limiter_cached, PASS->TIMEOUT
BDW: Intel_gpu_tools, igt_drv_debugfs_reader, PASS->TIMEOUT
BDW: Intel_gpu_tools, igt_drv_hangman_error-state-basic, PASS->TIMEOUT
BDW: Intel_gpu_tools, igt_drv_hangman_error-state-capture-render, PASS->TIMEOUT
BDW: Intel_gpu_tools, igt_drv_hangman_error-state-debugfs-entry, PASS->TIMEOUT
BDW: Intel_gpu_tools, igt_drv_hangman_error-state-sysfs-entry, PASS->TIMEOUT
BDW: Intel_gpu_tools, igt_drv_hangman_ring-stop-sysfs-entry, PASS->TIMEOUT

Daniel Vetter

2014-10-21 12:13 UTC #9 lore raw

Re: [PATCH] drm/i915/bdw: Clean up execlist queue items in

Quoted 62 lines · On Tue, Oct 21, 2014 at 01:32:44AM -0700, [email protected] wrote:

Tested-by PRC QA PRTS (Patch Regression Test System Contact: [email protected])
-------------------------------------Summary-------------------------------------
Platform: baseline_drm_intel_nightly_pass_rate->patch_applied_pass_rate
BYT: pass/total=19/19->3/19
PNV: pass/total=2/2->1/2
ILK: pass/total=15/15->3/15
IVB: pass/total=2/2->1/2
SNB: pass/total=16/16->3/16
HSW: pass/total=2/2->1/2
BDW: pass/total=17/17->3/17 -------------------------------------Detailed-------------------------------------
test_platform: test_suite, test_case, result_with_drm_intel_nightly->result_with_patch_applied
BYT: Intel_gpu_tools, igt_core_getclient, PASS->TIMEOUT
BYT: Intel_gpu_tools, igt_core_get_client_auth_master-drop, PASS->TIMEOUT
BYT: Intel_gpu_tools, igt_core_get_client_auth_simple, PASS->TIMEOUT
BYT: Intel_gpu_tools, igt_core_getstats, PASS->TIMEOUT
BYT: Intel_gpu_tools, igt_core_getversion, PASS->TIMEOUT
BYT: Intel_gpu_tools, igt_debugfs_emon_crash, PASS->TIMEOUT
BYT: Intel_gpu_tools, igt_drm_vma_limiter, PASS->TIMEOUT
BYT: Intel_gpu_tools, igt_drm_vma_limiter_cached, PASS->TIMEOUT
BYT: Intel_gpu_tools, igt_drv_debugfs_reader, PASS->TIMEOUT
BYT: Intel_gpu_tools, igt_drv_hangman_error-state-basic, PASS->TIMEOUT
BYT: Intel_gpu_tools, igt_drv_hangman_error-state-capture-render, PASS->TIMEOUT
BYT: Intel_gpu_tools, igt_drv_hangman_error-state-debugfs-entry, PASS->TIMEOUT
BYT: Intel_gpu_tools, igt_drv_hangman_error-state-sysfs-entry, PASS->TIMEOUT
BYT: Intel_gpu_tools, igt_drv_hangman_ring-stop-sysfs-entry, PASS->TIMEOUT
BYT: Intel_gpu_tools, igt_drv_missed_irq_hang, PASS->TIMEOUT
BYT: Intel_gpu_tools, igt_gem_bad_length, PASS->TIMEOUT
PNV: Sanity, boot, PASS->FAIL
ILK: Intel_gpu_tools, igt_core_getclient, PASS->TIMEOUT
ILK: Intel_gpu_tools, igt_core_get_client_auth_master-drop, PASS->TIMEOUT
ILK: Intel_gpu_tools, igt_core_get_client_auth_simple, PASS->TIMEOUT
ILK: Intel_gpu_tools, igt_core_getstats, PASS->TIMEOUT
ILK: Intel_gpu_tools, igt_core_getversion, PASS->TIMEOUT
ILK: Intel_gpu_tools, igt_debugfs_emon_crash, PASS->TIMEOUT
ILK: Intel_gpu_tools, igt_drm_vma_limiter, PASS->TIMEOUT
ILK: Intel_gpu_tools, igt_drm_vma_limiter_cached, PASS->TIMEOUT
ILK: Intel_gpu_tools, igt_drv_debugfs_reader, PASS->TIMEOUT
ILK: Intel_gpu_tools, igt_drv_hangman_error-state-basic, PASS->TIMEOUT
ILK: Intel_gpu_tools, igt_drv_hangman_error-state-capture-render, PASS->TIMEOUT
ILK: Intel_gpu_tools, igt_drv_hangman_error-state-debugfs-entry, PASS->TIMEOUT
IVB: Sanity, boot, PASS->FAIL
SNB: Intel_gpu_tools, igt_core_getclient, PASS->TIMEOUT
SNB: Intel_gpu_tools, igt_core_get_client_auth_master-drop, PASS->TIMEOUT
SNB: Intel_gpu_tools, igt_core_get_client_auth_simple, PASS->TIMEOUT
SNB: Intel_gpu_tools, igt_core_getstats, PASS->TIMEOUT
SNB: Intel_gpu_tools, igt_core_getversion, PASS->TIMEOUT
SNB: Intel_gpu_tools, igt_debugfs_emon_crash, PASS->TIMEOUT
SNB: Intel_gpu_tools, igt_drm_vma_limiter, PASS->TIMEOUT
SNB: Intel_gpu_tools, igt_drm_vma_limiter_cached, PASS->TIMEOUT
SNB: Intel_gpu_tools, igt_drv_debugfs_reader, PASS->TIMEOUT
SNB: Intel_gpu_tools, igt_drv_hangman_error-state-basic, PASS->TIMEOUT
SNB: Intel_gpu_tools, igt_drv_hangman_error-state-capture-render, PASS->TIMEOUT
SNB: Intel_gpu_tools, igt_drv_hangman_error-state-debugfs-entry, PASS->TIMEOUT
SNB: Intel_gpu_tools, igt_drv_hangman_error-state-sysfs-entry, PASS->TIMEOUT
HSW: Sanity, boot, PASS->FAIL
BDW: Intel_gpu_tools, igt_core_getclient, PASS->TIMEOUT
BDW: Intel_gpu_tools, igt_core_get_client_auth_master-drop, PASS->TIMEOUT
BDW: Intel_gpu_tools, igt_core_get_client_auth_simple, PASS->TIMEOUT
BDW: Intel_gpu_tools, igt_core_getstats, PASS->TIMEOUT
BDW: Intel_gpu_tools, igt_core_getversion, PASS->TIMEOUT
BDW: Intel_gpu_tools, igt_debugfs_emon_crash, PASS->TIMEOUT

Quoted 8 lines

BDW: Intel_gpu_tools, igt_drm_vma_limiter, PASS->TIMEOUT
BDW: Intel_gpu_tools, igt_drm_vma_limiter_cached, PASS->TIMEOUT
BDW: Intel_gpu_tools, igt_drv_debugfs_reader, PASS->TIMEOUT
BDW: Intel_gpu_tools, igt_drv_hangman_error-state-basic, PASS->TIMEOUT
BDW: Intel_gpu_tools, igt_drv_hangman_error-state-capture-render, PASS->TIMEOUT
BDW: Intel_gpu_tools, igt_drv_hangman_error-state-debugfs-entry, PASS->TIMEOUT
BDW: Intel_gpu_tools, igt_drv_hangman_error-state-sysfs-entry, PASS->TIMEOUT
BDW: Intel_gpu_tools, igt_drv_hangman_ring-stop-sysfs-entry, PASS->TIMEOUT

That's an awful lot of timeouts, especially since the code should only touch bdw+. Has something gone south with prts hang recovery? -Daniel

Signature · 3 lines

Daniel Vetter
Software Engineer, Intel Corporation
+41 (0) 79 365 57 48 - http://blog.ffwll.ch

Daniel, Thomas

author

2014-10-21 12:46 UTC #10 lore raw

Re: [PATCH] drm/i915/bdw: Clean up execlist queue items in

Quoted 18 lines

-----Original Message-----
From: Daniel Vetter [mailto:[email protected]] On Behalf Of Daniel Vetter
Sent: Tuesday, October 21, 2014 1:14 PM
To: He, Shuang
Cc: [email protected]; Daniel, Thomas
Subject: Re: [Intel-gfx] [PATCH] drm/i915/bdw: Clean up execlist queue items in
Quoted 5 lines · On Tue, Oct 21, 2014 at 01:32:44AM -0700, [email protected] wrote:
Tested-By: PRC QA PRTS (Patch Regression Test System Contact:
[email protected]) -------------------------------------Summary--------------------------
-----------
PASS->TIMEOUT

Quoted 3 lines

That's an awful lot of timeouts, especially since the code should only touch bdw+. Has something gone south with prts hang recovery?
-Daniel

Those results do look funky.
The v1 patch won't boot without execlists anyway. V2 results are better.

Thomas.

Quoted 4 lines

--
Daniel Vetter
Software Engineer, Intel Corporation
+41 (0) 79 365 57 48 - http://blog.ffwll.ch

He, Shuang

2014-10-22 01:01 UTC #11 lore raw

Re: [PATCH] drm/i915/bdw: Clean up execlist queue items in

Quoted 25 lines

-----Original Message-----
From: Daniel, Thomas
Sent: Tuesday, October 21, 2014 8:46 PM
To: Daniel Vetter; He, Shuang
Cc: [email protected]
Subject: RE: [Intel-gfx] [PATCH] drm/i915/bdw: Clean up execlist queue items in
Quoted 16 lines
-----Original Message-----
From: Daniel Vetter [mailto:[email protected]] On Behalf Of Daniel Vetter
Sent: Tuesday, October 21, 2014 1:14 PM
To: He, Shuang
Cc: [email protected]; Daniel, Thomas
Subject: Re: [Intel-gfx] [PATCH] drm/i915/bdw: Clean up execlist queue items in
Quoted 5 lines · On Tue, Oct 21, 2014 at 01:32:44AM -0700, [email protected] wrote:
Tested-By: PRC QA PRTS (Patch Regression Test System Contact:
[email protected]) -------------------------------------Summary--------------------------
-----------
PASS->TIMEOUT

Quoted 5 lines

Quoted 3 lines
That's an awful lot of timeouts, especially since the code should only touch bdw+. Has something gone south with prts hang recovery?
-Daniel
Those results do look funky.
The v1 patch won't boot without execlists anyway. V2 results are better.

[He, Shuang] PRTS hang recovery is working as expected here

Thanks
--Shuang

Quoted 7 lines

Thomas.
Quoted 4 lines
--
Daniel Vetter
Software Engineer, Intel Corporation
+41 (0) 79 365 57 48 - http://blog.ffwll.ch