* [Intel-gfx] [PATCH] drm/i915/gt: Retry RING_HEAD reset until it sticks
@ 2022-12-23 12:18 ` Andi Shyti
0 siblings, 0 replies; 6+ messages in thread
From: Andi Shyti @ 2022-12-23 12:18 UTC (permalink / raw)
To: intel-gfx, dri-devel; +Cc: Andrzej Hajda, Chris Wilson
From: Chris Wilson <chris@chris-wilson.co.uk>
On Haswell, in particular, we see an issue where resets fails because
the engine resumes from an incorrect RING_HEAD. Since the RING_HEAD
doesn't point to the remaining requests to re-run, but may instead point
into the uninitialised portion of the ring, the GPU may be then fed
invalid instructions from a privileged context, often pushing the GPU
into an unrecoverable hang.
If at first the write doesn't succeed, try, try again.
References: https://gitlab.freedesktop.org/drm/intel/-/issues/5432
References: https://gitlab.freedesktop.org/drm/intel/-/issues/3303
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Andrzej Hajda <andrzej.hajda@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
---
.../gpu/drm/i915/gt/intel_ring_submission.c | 44 +++++++++++++------
drivers/gpu/drm/i915/i915_utils.h | 8 ++++
2 files changed, 38 insertions(+), 14 deletions(-)
diff --git a/drivers/gpu/drm/i915/gt/intel_ring_submission.c b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
index 827adb0cfaea6..cdf283f5b1427 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
@@ -192,6 +192,7 @@ static bool stop_ring(struct intel_engine_cs *engine)
static int xcs_resume(struct intel_engine_cs *engine)
{
struct intel_ring *ring = engine->legacy.ring;
+ ktime_t kt;
ENGINE_TRACE(engine, "ring:{HEAD:%04x, TAIL:%04x}\n",
ring->head, ring->tail);
@@ -230,9 +231,20 @@ static int xcs_resume(struct intel_engine_cs *engine)
set_pp_dir(engine);
/* First wake the ring up to an empty/idle ring */
- ENGINE_WRITE_FW(engine, RING_HEAD, ring->head);
+ until_timeout_ns(kt, 2 * NSEC_PER_MSEC) {
+ ENGINE_WRITE_FW(engine, RING_HEAD, ring->head);
+ if (ENGINE_READ_FW(engine, RING_HEAD) == ring->head)
+ break;
+ }
+
ENGINE_WRITE_FW(engine, RING_TAIL, ring->head);
- ENGINE_POSTING_READ(engine, RING_TAIL);
+ if (ENGINE_READ_FW(engine, RING_HEAD) != ENGINE_READ_FW(engine, RING_TAIL)) {
+ ENGINE_TRACE(engine, "failed to reset empty ring: [%x, %x]: %x\n",
+ ENGINE_READ_FW(engine, RING_HEAD),
+ ENGINE_READ_FW(engine, RING_TAIL),
+ ring->head);
+ goto err;
+ }
ENGINE_WRITE_FW(engine, RING_CTL,
RING_CTL_SIZE(ring->size) | RING_VALID);
@@ -241,12 +253,16 @@ static int xcs_resume(struct intel_engine_cs *engine)
if (__intel_wait_for_register_fw(engine->uncore,
RING_CTL(engine->mmio_base),
RING_VALID, RING_VALID,
- 5000, 0, NULL))
+ 5000, 0, NULL)) {
+ ENGINE_TRACE(engine, "failed to restart\n");
goto err;
+ }
- if (GRAPHICS_VER(engine->i915) > 2)
+ if (GRAPHICS_VER(engine->i915) > 2) {
ENGINE_WRITE_FW(engine,
RING_MI_MODE, _MASKED_BIT_DISABLE(STOP_RING));
+ ENGINE_POSTING_READ(engine, RING_MI_MODE);
+ }
/* Now awake, let it get started */
if (ring->tail != ring->head) {
@@ -259,16 +275,16 @@ static int xcs_resume(struct intel_engine_cs *engine)
return 0;
err:
- drm_err(&engine->i915->drm,
- "%s initialization failed; "
- "ctl %08x (valid? %d) head %08x [%08x] tail %08x [%08x] start %08x [expected %08x]\n",
- engine->name,
- ENGINE_READ(engine, RING_CTL),
- ENGINE_READ(engine, RING_CTL) & RING_VALID,
- ENGINE_READ(engine, RING_HEAD), ring->head,
- ENGINE_READ(engine, RING_TAIL), ring->tail,
- ENGINE_READ(engine, RING_START),
- i915_ggtt_offset(ring->vma));
+ ENGINE_TRACE(engine,
+ "initialization failed; "
+ "ctl %08x (valid? %d) head %08x [%08x] tail %08x [%08x] start %08x [expected %08x]\n",
+ ENGINE_READ(engine, RING_CTL),
+ ENGINE_READ(engine, RING_CTL) & RING_VALID,
+ ENGINE_READ(engine, RING_HEAD), ring->head,
+ ENGINE_READ(engine, RING_TAIL), ring->tail,
+ ENGINE_READ(engine, RING_START),
+ i915_ggtt_offset(ring->vma));
+ GEM_TRACE_DUMP();
return -EIO;
}
diff --git a/drivers/gpu/drm/i915/i915_utils.h b/drivers/gpu/drm/i915/i915_utils.h
index b64192d9c7daa..f24a25c0685e1 100644
--- a/drivers/gpu/drm/i915/i915_utils.h
+++ b/drivers/gpu/drm/i915/i915_utils.h
@@ -254,6 +254,14 @@ wait_remaining_ms_from_jiffies(unsigned long timestamp_jiffies, int to_wait_ms)
}
}
+/**
+ * until_timeout_ns - Keep retrying (busy spin) until the duration has passed
+ */
+#define until_timeout_ns(end, timeout_ns) \
+ for ((end) = ktime_get() + (timeout_ns); \
+ ktime_before(ktime_get(), (end)); \
+ cpu_relax())
+
/**
* __wait_for - magic wait macro
*
--
2.39.0
^ permalink raw reply related [flat|nested] 6+ messages in thread
* [PATCH] drm/i915/gt: Retry RING_HEAD reset until it sticks
@ 2022-12-23 12:18 ` Andi Shyti
0 siblings, 0 replies; 6+ messages in thread
From: Andi Shyti @ 2022-12-23 12:18 UTC (permalink / raw)
To: intel-gfx, dri-devel
Cc: Mika Kuoppala, Andi Shyti, Andi Shyti, Andrzej Hajda,
Chris Wilson
From: Chris Wilson <chris@chris-wilson.co.uk>
On Haswell, in particular, we see an issue where resets fails because
the engine resumes from an incorrect RING_HEAD. Since the RING_HEAD
doesn't point to the remaining requests to re-run, but may instead point
into the uninitialised portion of the ring, the GPU may be then fed
invalid instructions from a privileged context, often pushing the GPU
into an unrecoverable hang.
If at first the write doesn't succeed, try, try again.
References: https://gitlab.freedesktop.org/drm/intel/-/issues/5432
References: https://gitlab.freedesktop.org/drm/intel/-/issues/3303
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Andrzej Hajda <andrzej.hajda@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
---
.../gpu/drm/i915/gt/intel_ring_submission.c | 44 +++++++++++++------
drivers/gpu/drm/i915/i915_utils.h | 8 ++++
2 files changed, 38 insertions(+), 14 deletions(-)
diff --git a/drivers/gpu/drm/i915/gt/intel_ring_submission.c b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
index 827adb0cfaea6..cdf283f5b1427 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
@@ -192,6 +192,7 @@ static bool stop_ring(struct intel_engine_cs *engine)
static int xcs_resume(struct intel_engine_cs *engine)
{
struct intel_ring *ring = engine->legacy.ring;
+ ktime_t kt;
ENGINE_TRACE(engine, "ring:{HEAD:%04x, TAIL:%04x}\n",
ring->head, ring->tail);
@@ -230,9 +231,20 @@ static int xcs_resume(struct intel_engine_cs *engine)
set_pp_dir(engine);
/* First wake the ring up to an empty/idle ring */
- ENGINE_WRITE_FW(engine, RING_HEAD, ring->head);
+ until_timeout_ns(kt, 2 * NSEC_PER_MSEC) {
+ ENGINE_WRITE_FW(engine, RING_HEAD, ring->head);
+ if (ENGINE_READ_FW(engine, RING_HEAD) == ring->head)
+ break;
+ }
+
ENGINE_WRITE_FW(engine, RING_TAIL, ring->head);
- ENGINE_POSTING_READ(engine, RING_TAIL);
+ if (ENGINE_READ_FW(engine, RING_HEAD) != ENGINE_READ_FW(engine, RING_TAIL)) {
+ ENGINE_TRACE(engine, "failed to reset empty ring: [%x, %x]: %x\n",
+ ENGINE_READ_FW(engine, RING_HEAD),
+ ENGINE_READ_FW(engine, RING_TAIL),
+ ring->head);
+ goto err;
+ }
ENGINE_WRITE_FW(engine, RING_CTL,
RING_CTL_SIZE(ring->size) | RING_VALID);
@@ -241,12 +253,16 @@ static int xcs_resume(struct intel_engine_cs *engine)
if (__intel_wait_for_register_fw(engine->uncore,
RING_CTL(engine->mmio_base),
RING_VALID, RING_VALID,
- 5000, 0, NULL))
+ 5000, 0, NULL)) {
+ ENGINE_TRACE(engine, "failed to restart\n");
goto err;
+ }
- if (GRAPHICS_VER(engine->i915) > 2)
+ if (GRAPHICS_VER(engine->i915) > 2) {
ENGINE_WRITE_FW(engine,
RING_MI_MODE, _MASKED_BIT_DISABLE(STOP_RING));
+ ENGINE_POSTING_READ(engine, RING_MI_MODE);
+ }
/* Now awake, let it get started */
if (ring->tail != ring->head) {
@@ -259,16 +275,16 @@ static int xcs_resume(struct intel_engine_cs *engine)
return 0;
err:
- drm_err(&engine->i915->drm,
- "%s initialization failed; "
- "ctl %08x (valid? %d) head %08x [%08x] tail %08x [%08x] start %08x [expected %08x]\n",
- engine->name,
- ENGINE_READ(engine, RING_CTL),
- ENGINE_READ(engine, RING_CTL) & RING_VALID,
- ENGINE_READ(engine, RING_HEAD), ring->head,
- ENGINE_READ(engine, RING_TAIL), ring->tail,
- ENGINE_READ(engine, RING_START),
- i915_ggtt_offset(ring->vma));
+ ENGINE_TRACE(engine,
+ "initialization failed; "
+ "ctl %08x (valid? %d) head %08x [%08x] tail %08x [%08x] start %08x [expected %08x]\n",
+ ENGINE_READ(engine, RING_CTL),
+ ENGINE_READ(engine, RING_CTL) & RING_VALID,
+ ENGINE_READ(engine, RING_HEAD), ring->head,
+ ENGINE_READ(engine, RING_TAIL), ring->tail,
+ ENGINE_READ(engine, RING_START),
+ i915_ggtt_offset(ring->vma));
+ GEM_TRACE_DUMP();
return -EIO;
}
diff --git a/drivers/gpu/drm/i915/i915_utils.h b/drivers/gpu/drm/i915/i915_utils.h
index b64192d9c7daa..f24a25c0685e1 100644
--- a/drivers/gpu/drm/i915/i915_utils.h
+++ b/drivers/gpu/drm/i915/i915_utils.h
@@ -254,6 +254,14 @@ wait_remaining_ms_from_jiffies(unsigned long timestamp_jiffies, int to_wait_ms)
}
}
+/**
+ * until_timeout_ns - Keep retrying (busy spin) until the duration has passed
+ */
+#define until_timeout_ns(end, timeout_ns) \
+ for ((end) = ktime_get() + (timeout_ns); \
+ ktime_before(ktime_get(), (end)); \
+ cpu_relax())
+
/**
* __wait_for - magic wait macro
*
--
2.39.0
^ permalink raw reply related [flat|nested] 6+ messages in thread
* [Intel-gfx] ✓ Fi.CI.BAT: success for drm/i915/gt: Retry RING_HEAD reset until it sticks (rev2)
2022-12-23 12:18 ` Andi Shyti
(?)
@ 2022-12-23 13:15 ` Patchwork
-1 siblings, 0 replies; 6+ messages in thread
From: Patchwork @ 2022-12-23 13:15 UTC (permalink / raw)
To: Mauro Carvalho Chehab; +Cc: intel-gfx
[-- Attachment #1: Type: text/plain, Size: 5305 bytes --]
== Series Details ==
Series: drm/i915/gt: Retry RING_HEAD reset until it sticks (rev2)
URL : https://patchwork.freedesktop.org/series/106377/
State : success
== Summary ==
CI Bug Log - changes from CI_DRM_12524 -> Patchwork_106377v2
====================================================
Summary
-------
**SUCCESS**
No regressions found.
External URL: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106377v2/index.html
Participating hosts (45 -> 46)
------------------------------
Additional (1): bat-atsm-1
Possible new issues
-------------------
Here are the unknown changes that may have been introduced in Patchwork_106377v2:
### IGT changes ###
#### Suppressed ####
The following results come from untrusted machines, tests, or statuses.
They do not affect the overall result.
* igt@i915_selftest@live@workarounds:
- {bat-rpls-2}: [PASS][1] -> [DMESG-FAIL][2]
[1]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12524/bat-rpls-2/igt@i915_selftest@live@workarounds.html
[2]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106377v2/bat-rpls-2/igt@i915_selftest@live@workarounds.html
Known issues
------------
Here are the changes found in Patchwork_106377v2 that come from known issues:
### IGT changes ###
#### Issues hit ####
* igt@i915_selftest@live@gt_heartbeat:
- fi-kbl-soraka: [PASS][3] -> [DMESG-FAIL][4] ([i915#5334])
[3]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12524/fi-kbl-soraka/igt@i915_selftest@live@gt_heartbeat.html
[4]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106377v2/fi-kbl-soraka/igt@i915_selftest@live@gt_heartbeat.html
#### Possible fixes ####
* igt@gem_exec_gttfill@basic:
- fi-pnv-d510: [FAIL][5] ([i915#7229]) -> [PASS][6]
[5]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12524/fi-pnv-d510/igt@gem_exec_gttfill@basic.html
[6]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106377v2/fi-pnv-d510/igt@gem_exec_gttfill@basic.html
* igt@i915_selftest@live@migrate:
- bat-adlp-4: [DMESG-FAIL][7] ([i915#7699]) -> [PASS][8]
[7]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12524/bat-adlp-4/igt@i915_selftest@live@migrate.html
[8]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106377v2/bat-adlp-4/igt@i915_selftest@live@migrate.html
* igt@i915_selftest@live@slpc:
- {bat-adln-1}: [DMESG-FAIL][9] ([i915#6997]) -> [PASS][10]
[9]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12524/bat-adln-1/igt@i915_selftest@live@slpc.html
[10]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106377v2/bat-adln-1/igt@i915_selftest@live@slpc.html
* igt@i915_selftest@live@workarounds:
- {bat-rpls-1}: [DMESG-WARN][11] -> [PASS][12]
[11]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12524/bat-rpls-1/igt@i915_selftest@live@workarounds.html
[12]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106377v2/bat-rpls-1/igt@i915_selftest@live@workarounds.html
{name}: This element is suppressed. This means it is ignored when computing
the status of the difference (SUCCESS, WARNING, or FAILURE).
[fdo#109295]: https://bugs.freedesktop.org/show_bug.cgi?id=109295
[i915#1072]: https://gitlab.freedesktop.org/drm/intel/issues/1072
[i915#1836]: https://gitlab.freedesktop.org/drm/intel/issues/1836
[i915#2582]: https://gitlab.freedesktop.org/drm/intel/issues/2582
[i915#4077]: https://gitlab.freedesktop.org/drm/intel/issues/4077
[i915#4079]: https://gitlab.freedesktop.org/drm/intel/issues/4079
[i915#4083]: https://gitlab.freedesktop.org/drm/intel/issues/4083
[i915#4312]: https://gitlab.freedesktop.org/drm/intel/issues/4312
[i915#4983]: https://gitlab.freedesktop.org/drm/intel/issues/4983
[i915#5334]: https://gitlab.freedesktop.org/drm/intel/issues/5334
[i915#6077]: https://gitlab.freedesktop.org/drm/intel/issues/6077
[i915#6078]: https://gitlab.freedesktop.org/drm/intel/issues/6078
[i915#6093]: https://gitlab.freedesktop.org/drm/intel/issues/6093
[i915#6094]: https://gitlab.freedesktop.org/drm/intel/issues/6094
[i915#6166]: https://gitlab.freedesktop.org/drm/intel/issues/6166
[i915#6257]: https://gitlab.freedesktop.org/drm/intel/issues/6257
[i915#6311]: https://gitlab.freedesktop.org/drm/intel/issues/6311
[i915#6621]: https://gitlab.freedesktop.org/drm/intel/issues/6621
[i915#6645]: https://gitlab.freedesktop.org/drm/intel/issues/6645
[i915#6997]: https://gitlab.freedesktop.org/drm/intel/issues/6997
[i915#7229]: https://gitlab.freedesktop.org/drm/intel/issues/7229
[i915#7357]: https://gitlab.freedesktop.org/drm/intel/issues/7357
[i915#7699]: https://gitlab.freedesktop.org/drm/intel/issues/7699
Build changes
-------------
* Linux: CI_DRM_12524 -> Patchwork_106377v2
CI-20190529: 20190529
CI_DRM_12524: a29956c69a562e85ef8657e39382bc207a339941 @ git://anongit.freedesktop.org/gfx-ci/linux
IGT_7102: bacfdc84a9c02556c5441deb21e3a3f18a07347d @ https://gitlab.freedesktop.org/drm/igt-gpu-tools.git
Patchwork_106377v2: a29956c69a562e85ef8657e39382bc207a339941 @ git://anongit.freedesktop.org/gfx-ci/linux
### Linux commits
408162e35b81 drm/i915/gt: Retry RING_HEAD reset until it sticks
== Logs ==
For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106377v2/index.html
[-- Attachment #2: Type: text/html, Size: 4768 bytes --]
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [Intel-gfx] [PATCH] drm/i915/gt: Retry RING_HEAD reset until it sticks
2022-12-23 12:18 ` Andi Shyti
(?)
(?)
@ 2022-12-23 13:21 ` Tvrtko Ursulin
2022-12-27 16:33 ` Jani Nikula
-1 siblings, 1 reply; 6+ messages in thread
From: Tvrtko Ursulin @ 2022-12-23 13:21 UTC (permalink / raw)
To: Andi Shyti, intel-gfx, dri-devel; +Cc: Andrzej Hajda
On 23/12/2022 12:18, Andi Shyti wrote:
> From: Chris Wilson <chris@chris-wilson.co.uk>
>
> On Haswell, in particular, we see an issue where resets fails because
> the engine resumes from an incorrect RING_HEAD. Since the RING_HEAD
> doesn't point to the remaining requests to re-run, but may instead point
> into the uninitialised portion of the ring, the GPU may be then fed
> invalid instructions from a privileged context, often pushing the GPU
> into an unrecoverable hang.
>
> If at first the write doesn't succeed, try, try again.
>
> References: https://gitlab.freedesktop.org/drm/intel/-/issues/5432
> References: https://gitlab.freedesktop.org/drm/intel/-/issues/3303
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> Cc: Andrzej Hajda <andrzej.hajda@intel.com>
> Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
> Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
> ---
> .../gpu/drm/i915/gt/intel_ring_submission.c | 44 +++++++++++++------
> drivers/gpu/drm/i915/i915_utils.h | 8 ++++
> 2 files changed, 38 insertions(+), 14 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/gt/intel_ring_submission.c b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
> index 827adb0cfaea6..cdf283f5b1427 100644
> --- a/drivers/gpu/drm/i915/gt/intel_ring_submission.c
> +++ b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
> @@ -192,6 +192,7 @@ static bool stop_ring(struct intel_engine_cs *engine)
> static int xcs_resume(struct intel_engine_cs *engine)
> {
> struct intel_ring *ring = engine->legacy.ring;
> + ktime_t kt;
>
> ENGINE_TRACE(engine, "ring:{HEAD:%04x, TAIL:%04x}\n",
> ring->head, ring->tail);
> @@ -230,9 +231,20 @@ static int xcs_resume(struct intel_engine_cs *engine)
> set_pp_dir(engine);
>
> /* First wake the ring up to an empty/idle ring */
> - ENGINE_WRITE_FW(engine, RING_HEAD, ring->head);
> + until_timeout_ns(kt, 2 * NSEC_PER_MSEC) {
> + ENGINE_WRITE_FW(engine, RING_HEAD, ring->head);
> + if (ENGINE_READ_FW(engine, RING_HEAD) == ring->head)
> + break;
> + }
2ms?! Shudder..
#define done \
({ \
ENGINE_WRITE_FW(engine, RING_HEAD, ring->head); \
ENGINE_READ_FW(engine, RING_HEAD) == ring->head; \
})
_wait_for_atomic(done, 2 * USEC_PER_MSEC, needs_to_be_atomic_or_not?);
#undef done
Should work and avoid the need to add yet another helper, please
double-check. Not as pretty, but accumulating generic sounding helpers
in i915_utils.h is a bit frowned upon.
Regards,
Tvrtko
> +
> ENGINE_WRITE_FW(engine, RING_TAIL, ring->head);
> - ENGINE_POSTING_READ(engine, RING_TAIL);
> + if (ENGINE_READ_FW(engine, RING_HEAD) != ENGINE_READ_FW(engine, RING_TAIL)) {
> + ENGINE_TRACE(engine, "failed to reset empty ring: [%x, %x]: %x\n",
> + ENGINE_READ_FW(engine, RING_HEAD),
> + ENGINE_READ_FW(engine, RING_TAIL),
> + ring->head);
> + goto err;
> + }
>
> ENGINE_WRITE_FW(engine, RING_CTL,
> RING_CTL_SIZE(ring->size) | RING_VALID);
> @@ -241,12 +253,16 @@ static int xcs_resume(struct intel_engine_cs *engine)
> if (__intel_wait_for_register_fw(engine->uncore,
> RING_CTL(engine->mmio_base),
> RING_VALID, RING_VALID,
> - 5000, 0, NULL))
> + 5000, 0, NULL)) {
> + ENGINE_TRACE(engine, "failed to restart\n");
> goto err;
> + }
>
> - if (GRAPHICS_VER(engine->i915) > 2)
> + if (GRAPHICS_VER(engine->i915) > 2) {
> ENGINE_WRITE_FW(engine,
> RING_MI_MODE, _MASKED_BIT_DISABLE(STOP_RING));
> + ENGINE_POSTING_READ(engine, RING_MI_MODE);
> + }
>
> /* Now awake, let it get started */
> if (ring->tail != ring->head) {
> @@ -259,16 +275,16 @@ static int xcs_resume(struct intel_engine_cs *engine)
> return 0;
>
> err:
> - drm_err(&engine->i915->drm,
> - "%s initialization failed; "
> - "ctl %08x (valid? %d) head %08x [%08x] tail %08x [%08x] start %08x [expected %08x]\n",
> - engine->name,
> - ENGINE_READ(engine, RING_CTL),
> - ENGINE_READ(engine, RING_CTL) & RING_VALID,
> - ENGINE_READ(engine, RING_HEAD), ring->head,
> - ENGINE_READ(engine, RING_TAIL), ring->tail,
> - ENGINE_READ(engine, RING_START),
> - i915_ggtt_offset(ring->vma));
> + ENGINE_TRACE(engine,
> + "initialization failed; "
> + "ctl %08x (valid? %d) head %08x [%08x] tail %08x [%08x] start %08x [expected %08x]\n",
> + ENGINE_READ(engine, RING_CTL),
> + ENGINE_READ(engine, RING_CTL) & RING_VALID,
> + ENGINE_READ(engine, RING_HEAD), ring->head,
> + ENGINE_READ(engine, RING_TAIL), ring->tail,
> + ENGINE_READ(engine, RING_START),
> + i915_ggtt_offset(ring->vma));
> + GEM_TRACE_DUMP();
> return -EIO;
> }
>
> diff --git a/drivers/gpu/drm/i915/i915_utils.h b/drivers/gpu/drm/i915/i915_utils.h
> index b64192d9c7daa..f24a25c0685e1 100644
> --- a/drivers/gpu/drm/i915/i915_utils.h
> +++ b/drivers/gpu/drm/i915/i915_utils.h
> @@ -254,6 +254,14 @@ wait_remaining_ms_from_jiffies(unsigned long timestamp_jiffies, int to_wait_ms)
> }
> }
>
> +/**
> + * until_timeout_ns - Keep retrying (busy spin) until the duration has passed
> + */
> +#define until_timeout_ns(end, timeout_ns) \
> + for ((end) = ktime_get() + (timeout_ns); \
> + ktime_before(ktime_get(), (end)); \
> + cpu_relax())
> + > /**
> * __wait_for - magic wait macro
> *
^ permalink raw reply [flat|nested] 6+ messages in thread
* [Intel-gfx] ✓ Fi.CI.IGT: success for drm/i915/gt: Retry RING_HEAD reset until it sticks (rev2)
2022-12-23 12:18 ` Andi Shyti
` (2 preceding siblings ...)
(?)
@ 2022-12-23 14:30 ` Patchwork
-1 siblings, 0 replies; 6+ messages in thread
From: Patchwork @ 2022-12-23 14:30 UTC (permalink / raw)
To: Mauro Carvalho Chehab; +Cc: intel-gfx
[-- Attachment #1: Type: text/plain, Size: 17316 bytes --]
== Series Details ==
Series: drm/i915/gt: Retry RING_HEAD reset until it sticks (rev2)
URL : https://patchwork.freedesktop.org/series/106377/
State : success
== Summary ==
CI Bug Log - changes from CI_DRM_12524_full -> Patchwork_106377v2_full
====================================================
Summary
-------
**SUCCESS**
No regressions found.
External URL: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106377v2/index.html
Participating hosts (13 -> 10)
------------------------------
Missing (3): pig-skl-6260u pig-kbl-iris pig-glk-j5005
Possible new issues
-------------------
Here are the unknown changes that may have been introduced in Patchwork_106377v2_full:
### IGT changes ###
#### Suppressed ####
The following results come from untrusted machines, tests, or statuses.
They do not affect the overall result.
* igt@gem_exec_whisper@basic-contexts-priority-all:
- {shard-rkl}: [PASS][1] -> [INCOMPLETE][2]
[1]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12524/shard-rkl-1/igt@gem_exec_whisper@basic-contexts-priority-all.html
[2]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106377v2/shard-rkl-5/igt@gem_exec_whisper@basic-contexts-priority-all.html
Known issues
------------
Here are the changes found in Patchwork_106377v2_full that come from known issues:
### IGT changes ###
#### Issues hit ####
* igt@gem_exec_fair@basic-throttle@rcs0:
- shard-glk: [PASS][3] -> [FAIL][4] ([i915#2842]) +2 similar issues
[3]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12524/shard-glk5/igt@gem_exec_fair@basic-throttle@rcs0.html
[4]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106377v2/shard-glk5/igt@gem_exec_fair@basic-throttle@rcs0.html
* igt@kms_flip@plain-flip-fb-recreate@c-hdmi-a1:
- shard-glk: [PASS][5] -> [FAIL][6] ([i915#2122])
[5]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12524/shard-glk4/igt@kms_flip@plain-flip-fb-recreate@c-hdmi-a1.html
[6]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106377v2/shard-glk1/igt@kms_flip@plain-flip-fb-recreate@c-hdmi-a1.html
#### Possible fixes ####
* igt@api_intel_bb@object-reloc-keep-cache:
- {shard-rkl}: [SKIP][7] ([i915#3281]) -> [PASS][8] +4 similar issues
[7]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12524/shard-rkl-1/igt@api_intel_bb@object-reloc-keep-cache.html
[8]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106377v2/shard-rkl-5/igt@api_intel_bb@object-reloc-keep-cache.html
* igt@gem_ctx_persistence@engines-hang@bcs0:
- {shard-rkl}: [SKIP][9] ([i915#6252]) -> [PASS][10]
[9]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12524/shard-rkl-5/igt@gem_ctx_persistence@engines-hang@bcs0.html
[10]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106377v2/shard-rkl-1/igt@gem_ctx_persistence@engines-hang@bcs0.html
* igt@gem_exec_fair@basic-none@vcs0:
- {shard-rkl}: [FAIL][11] ([i915#2842]) -> [PASS][12] +2 similar issues
[11]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12524/shard-rkl-6/igt@gem_exec_fair@basic-none@vcs0.html
[12]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106377v2/shard-rkl-5/igt@gem_exec_fair@basic-none@vcs0.html
* igt@gem_pread@snoop:
- {shard-rkl}: [SKIP][13] ([i915#3282]) -> [PASS][14] +2 similar issues
[13]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12524/shard-rkl-6/igt@gem_pread@snoop.html
[14]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106377v2/shard-rkl-5/igt@gem_pread@snoop.html
* igt@gen9_exec_parse@bb-start-param:
- {shard-rkl}: [SKIP][15] ([i915#2527]) -> [PASS][16] +1 similar issue
[15]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12524/shard-rkl-6/igt@gen9_exec_parse@bb-start-param.html
[16]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106377v2/shard-rkl-5/igt@gen9_exec_parse@bb-start-param.html
* igt@i915_hangman@gt-engine-error@bcs0:
- {shard-rkl}: [SKIP][17] ([i915#6258]) -> [PASS][18]
[17]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12524/shard-rkl-5/igt@i915_hangman@gt-engine-error@bcs0.html
[18]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106377v2/shard-rkl-1/igt@i915_hangman@gt-engine-error@bcs0.html
* igt@i915_pm_rpm@modeset-non-lpsp:
- {shard-dg1}: [SKIP][19] ([i915#1397]) -> [PASS][20] +3 similar issues
[19]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12524/shard-dg1-14/igt@i915_pm_rpm@modeset-non-lpsp.html
[20]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106377v2/shard-dg1-17/igt@i915_pm_rpm@modeset-non-lpsp.html
* igt@i915_pm_rpm@pm-tiling:
- {shard-rkl}: [SKIP][21] ([fdo#109308]) -> [PASS][22]
[21]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12524/shard-rkl-4/igt@i915_pm_rpm@pm-tiling.html
[22]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106377v2/shard-rkl-6/igt@i915_pm_rpm@pm-tiling.html
* igt@kms_atomic@atomic_plane_damage:
- {shard-rkl}: [SKIP][23] ([i915#4098]) -> [PASS][24] +1 similar issue
[23]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12524/shard-rkl-5/igt@kms_atomic@atomic_plane_damage.html
[24]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106377v2/shard-rkl-6/igt@kms_atomic@atomic_plane_damage.html
* igt@kms_ccs@pipe-a-bad-pixel-format-y_tiled_gen12_rc_ccs:
- {shard-rkl}: [SKIP][25] ([i915#1845] / [i915#4098]) -> [PASS][26] +26 similar issues
[25]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12524/shard-rkl-4/igt@kms_ccs@pipe-a-bad-pixel-format-y_tiled_gen12_rc_ccs.html
[26]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106377v2/shard-rkl-6/igt@kms_ccs@pipe-a-bad-pixel-format-y_tiled_gen12_rc_ccs.html
* igt@kms_cursor_legacy@flip-vs-cursor@atomic-transitions-varying-size:
- shard-glk: [FAIL][27] ([i915#2346]) -> [PASS][28]
[27]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12524/shard-glk5/igt@kms_cursor_legacy@flip-vs-cursor@atomic-transitions-varying-size.html
[28]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106377v2/shard-glk5/igt@kms_cursor_legacy@flip-vs-cursor@atomic-transitions-varying-size.html
* igt@kms_flip@plain-flip-ts-check@c-hdmi-a1:
- shard-glk: [FAIL][29] ([i915#2122]) -> [PASS][30]
[29]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12524/shard-glk3/igt@kms_flip@plain-flip-ts-check@c-hdmi-a1.html
[30]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106377v2/shard-glk6/igt@kms_flip@plain-flip-ts-check@c-hdmi-a1.html
* igt@kms_frontbuffer_tracking@psr-1p-primscrn-pri-indfb-draw-render:
- {shard-rkl}: [SKIP][31] ([i915#1849] / [i915#4098]) -> [PASS][32] +15 similar issues
[31]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12524/shard-rkl-5/igt@kms_frontbuffer_tracking@psr-1p-primscrn-pri-indfb-draw-render.html
[32]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106377v2/shard-rkl-6/igt@kms_frontbuffer_tracking@psr-1p-primscrn-pri-indfb-draw-render.html
* igt@kms_plane_scaling@plane-scaler-with-pixel-format-unity-scaling@pipe-b-hdmi-a-1:
- {shard-tglu-10}: [INCOMPLETE][33] -> [PASS][34]
[33]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12524/shard-tglu-10/igt@kms_plane_scaling@plane-scaler-with-pixel-format-unity-scaling@pipe-b-hdmi-a-1.html
[34]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106377v2/shard-tglu-10/igt@kms_plane_scaling@plane-scaler-with-pixel-format-unity-scaling@pipe-b-hdmi-a-1.html
* igt@kms_properties@crtc-properties-legacy:
- {shard-rkl}: [SKIP][35] ([i915#1849]) -> [PASS][36] +1 similar issue
[35]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12524/shard-rkl-5/igt@kms_properties@crtc-properties-legacy.html
[36]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106377v2/shard-rkl-6/igt@kms_properties@crtc-properties-legacy.html
* igt@kms_psr@sprite_plane_move:
- {shard-rkl}: [SKIP][37] ([i915#1072]) -> [PASS][38] +2 similar issues
[37]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_12524/shard-rkl-4/igt@kms_psr@sprite_plane_move.html
[38]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106377v2/shard-rkl-6/igt@kms_psr@sprite_plane_move.html
{name}: This element is suppressed. This means it is ignored when computing
the status of the difference (SUCCESS, WARNING, or FAILURE).
[fdo#109274]: https://bugs.freedesktop.org/show_bug.cgi?id=109274
[fdo#109279]: https://bugs.freedesktop.org/show_bug.cgi?id=109279
[fdo#109280]: https://bugs.freedesktop.org/show_bug.cgi?id=109280
[fdo#109283]: https://bugs.freedesktop.org/show_bug.cgi?id=109283
[fdo#109285]: https://bugs.freedesktop.org/show_bug.cgi?id=109285
[fdo#109289]: https://bugs.freedesktop.org/show_bug.cgi?id=109289
[fdo#109291]: https://bugs.freedesktop.org/show_bug.cgi?id=109291
[fdo#109295]: https://bugs.freedesktop.org/show_bug.cgi?id=109295
[fdo#109308]: https://bugs.freedesktop.org/show_bug.cgi?id=109308
[fdo#109312]: https://bugs.freedesktop.org/show_bug.cgi?id=109312
[fdo#109314]: https://bugs.freedesktop.org/show_bug.cgi?id=109314
[fdo#109315]: https://bugs.freedesktop.org/show_bug.cgi?id=109315
[fdo#109642]: https://bugs.freedesktop.org/show_bug.cgi?id=109642
[fdo#110189]: https://bugs.freedesktop.org/show_bug.cgi?id=110189
[fdo#110542]: https://bugs.freedesktop.org/show_bug.cgi?id=110542
[fdo#110723]: https://bugs.freedesktop.org/show_bug.cgi?id=110723
[fdo#111068]: https://bugs.freedesktop.org/show_bug.cgi?id=111068
[fdo#111614]: https://bugs.freedesktop.org/show_bug.cgi?id=111614
[fdo#111615]: https://bugs.freedesktop.org/show_bug.cgi?id=111615
[fdo#111644]: https://bugs.freedesktop.org/show_bug.cgi?id=111644
[fdo#111825]: https://bugs.freedesktop.org/show_bug.cgi?id=111825
[fdo#111827]: https://bugs.freedesktop.org/show_bug.cgi?id=111827
[fdo#112283]: https://bugs.freedesktop.org/show_bug.cgi?id=112283
[i915#1072]: https://gitlab.freedesktop.org/drm/intel/issues/1072
[i915#132]: https://gitlab.freedesktop.org/drm/intel/issues/132
[i915#1397]: https://gitlab.freedesktop.org/drm/intel/issues/1397
[i915#1769]: https://gitlab.freedesktop.org/drm/intel/issues/1769
[i915#1825]: https://gitlab.freedesktop.org/drm/intel/issues/1825
[i915#1839]: https://gitlab.freedesktop.org/drm/intel/issues/1839
[i915#1845]: https://gitlab.freedesktop.org/drm/intel/issues/1845
[i915#1849]: https://gitlab.freedesktop.org/drm/intel/issues/1849
[i915#1937]: https://gitlab.freedesktop.org/drm/intel/issues/1937
[i915#2122]: https://gitlab.freedesktop.org/drm/intel/issues/2122
[i915#2190]: https://gitlab.freedesktop.org/drm/intel/issues/2190
[i915#2346]: https://gitlab.freedesktop.org/drm/intel/issues/2346
[i915#2434]: https://gitlab.freedesktop.org/drm/intel/issues/2434
[i915#2437]: https://gitlab.freedesktop.org/drm/intel/issues/2437
[i915#2527]: https://gitlab.freedesktop.org/drm/intel/issues/2527
[i915#2575]: https://gitlab.freedesktop.org/drm/intel/issues/2575
[i915#2587]: https://gitlab.freedesktop.org/drm/intel/issues/2587
[i915#2658]: https://gitlab.freedesktop.org/drm/intel/issues/2658
[i915#2672]: https://gitlab.freedesktop.org/drm/intel/issues/2672
[i915#2681]: https://gitlab.freedesktop.org/drm/intel/issues/2681
[i915#2705]: https://gitlab.freedesktop.org/drm/intel/issues/2705
[i915#280]: https://gitlab.freedesktop.org/drm/intel/issues/280
[i915#2842]: https://gitlab.freedesktop.org/drm/intel/issues/2842
[i915#2856]: https://gitlab.freedesktop.org/drm/intel/issues/2856
[i915#2920]: https://gitlab.freedesktop.org/drm/intel/issues/2920
[i915#2994]: https://gitlab.freedesktop.org/drm/intel/issues/2994
[i915#3116]: https://gitlab.freedesktop.org/drm/intel/issues/3116
[i915#3281]: https://gitlab.freedesktop.org/drm/intel/issues/3281
[i915#3282]: https://gitlab.freedesktop.org/drm/intel/issues/3282
[i915#3297]: https://gitlab.freedesktop.org/drm/intel/issues/3297
[i915#3299]: https://gitlab.freedesktop.org/drm/intel/issues/3299
[i915#3359]: https://gitlab.freedesktop.org/drm/intel/issues/3359
[i915#3469]: https://gitlab.freedesktop.org/drm/intel/issues/3469
[i915#3546]: https://gitlab.freedesktop.org/drm/intel/issues/3546
[i915#3555]: https://gitlab.freedesktop.org/drm/intel/issues/3555
[i915#3558]: https://gitlab.freedesktop.org/drm/intel/issues/3558
[i915#3591]: https://gitlab.freedesktop.org/drm/intel/issues/3591
[i915#3637]: https://gitlab.freedesktop.org/drm/intel/issues/3637
[i915#3638]: https://gitlab.freedesktop.org/drm/intel/issues/3638
[i915#3689]: https://gitlab.freedesktop.org/drm/intel/issues/3689
[i915#3708]: https://gitlab.freedesktop.org/drm/intel/issues/3708
[i915#3734]: https://gitlab.freedesktop.org/drm/intel/issues/3734
[i915#3742]: https://gitlab.freedesktop.org/drm/intel/issues/3742
[i915#3840]: https://gitlab.freedesktop.org/drm/intel/issues/3840
[i915#3886]: https://gitlab.freedesktop.org/drm/intel/issues/3886
[i915#3966]: https://gitlab.freedesktop.org/drm/intel/issues/3966
[i915#404]: https://gitlab.freedesktop.org/drm/intel/issues/404
[i915#4070]: https://gitlab.freedesktop.org/drm/intel/issues/4070
[i915#4078]: https://gitlab.freedesktop.org/drm/intel/issues/4078
[i915#4098]: https://gitlab.freedesktop.org/drm/intel/issues/4098
[i915#4103]: https://gitlab.freedesktop.org/drm/intel/issues/4103
[i915#426]: https://gitlab.freedesktop.org/drm/intel/issues/426
[i915#4270]: https://gitlab.freedesktop.org/drm/intel/issues/4270
[i915#4613]: https://gitlab.freedesktop.org/drm/intel/issues/4613
[i915#4767]: https://gitlab.freedesktop.org/drm/intel/issues/4767
[i915#4991]: https://gitlab.freedesktop.org/drm/intel/issues/4991
[i915#5176]: https://gitlab.freedesktop.org/drm/intel/issues/5176
[i915#5235]: https://gitlab.freedesktop.org/drm/intel/issues/5235
[i915#5286]: https://gitlab.freedesktop.org/drm/intel/issues/5286
[i915#5289]: https://gitlab.freedesktop.org/drm/intel/issues/5289
[i915#5325]: https://gitlab.freedesktop.org/drm/intel/issues/5325
[i915#5327]: https://gitlab.freedesktop.org/drm/intel/issues/5327
[i915#533]: https://gitlab.freedesktop.org/drm/intel/issues/533
[i915#5439]: https://gitlab.freedesktop.org/drm/intel/issues/5439
[i915#5461]: https://gitlab.freedesktop.org/drm/intel/issues/5461
[i915#5723]: https://gitlab.freedesktop.org/drm/intel/issues/5723
[i915#5784]: https://gitlab.freedesktop.org/drm/intel/issues/5784
[i915#6095]: https://gitlab.freedesktop.org/drm/intel/issues/6095
[i915#6117]: https://gitlab.freedesktop.org/drm/intel/issues/6117
[i915#6245]: https://gitlab.freedesktop.org/drm/intel/issues/6245
[i915#6247]: https://gitlab.freedesktop.org/drm/intel/issues/6247
[i915#6248]: https://gitlab.freedesktop.org/drm/intel/issues/6248
[i915#6252]: https://gitlab.freedesktop.org/drm/intel/issues/6252
[i915#6258]: https://gitlab.freedesktop.org/drm/intel/issues/6258
[i915#6268]: https://gitlab.freedesktop.org/drm/intel/issues/6268
[i915#6335]: https://gitlab.freedesktop.org/drm/intel/issues/6335
[i915#6344]: https://gitlab.freedesktop.org/drm/intel/issues/6344
[i915#6355]: https://gitlab.freedesktop.org/drm/intel/issues/6355
[i915#6412]: https://gitlab.freedesktop.org/drm/intel/issues/6412
[i915#6433]: https://gitlab.freedesktop.org/drm/intel/issues/6433
[i915#6497]: https://gitlab.freedesktop.org/drm/intel/issues/6497
[i915#6524]: https://gitlab.freedesktop.org/drm/intel/issues/6524
[i915#658]: https://gitlab.freedesktop.org/drm/intel/issues/658
[i915#6590]: https://gitlab.freedesktop.org/drm/intel/issues/6590
[i915#6768]: https://gitlab.freedesktop.org/drm/intel/issues/6768
[i915#6946]: https://gitlab.freedesktop.org/drm/intel/issues/6946
[i915#6953]: https://gitlab.freedesktop.org/drm/intel/issues/6953
[i915#7037]: https://gitlab.freedesktop.org/drm/intel/issues/7037
[i915#7116]: https://gitlab.freedesktop.org/drm/intel/issues/7116
[i915#7118]: https://gitlab.freedesktop.org/drm/intel/issues/7118
[i915#7128]: https://gitlab.freedesktop.org/drm/intel/issues/7128
[i915#7276]: https://gitlab.freedesktop.org/drm/intel/issues/7276
[i915#7561]: https://gitlab.freedesktop.org/drm/intel/issues/7561
[i915#7582]: https://gitlab.freedesktop.org/drm/intel/issues/7582
[i915#7651]: https://gitlab.freedesktop.org/drm/intel/issues/7651
[i915#7681]: https://gitlab.freedesktop.org/drm/intel/issues/7681
[i915#7697]: https://gitlab.freedesktop.org/drm/intel/issues/7697
[i915#7701]: https://gitlab.freedesktop.org/drm/intel/issues/7701
[i915#7707]: https://gitlab.freedesktop.org/drm/intel/issues/7707
Build changes
-------------
* Linux: CI_DRM_12524 -> Patchwork_106377v2
* Piglit: piglit_4509 -> None
CI-20190529: 20190529
CI_DRM_12524: a29956c69a562e85ef8657e39382bc207a339941 @ git://anongit.freedesktop.org/gfx-ci/linux
IGT_7102: bacfdc84a9c02556c5441deb21e3a3f18a07347d @ https://gitlab.freedesktop.org/drm/igt-gpu-tools.git
Patchwork_106377v2: a29956c69a562e85ef8657e39382bc207a339941 @ git://anongit.freedesktop.org/gfx-ci/linux
piglit_4509: fdc5a4ca11124ab8413c7988896eec4c97336694 @ git://anongit.freedesktop.org/piglit
== Logs ==
For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106377v2/index.html
[-- Attachment #2: Type: text/html, Size: 11411 bytes --]
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [Intel-gfx] [PATCH] drm/i915/gt: Retry RING_HEAD reset until it sticks
2022-12-23 13:21 ` [Intel-gfx] [PATCH] drm/i915/gt: Retry RING_HEAD reset until it sticks Tvrtko Ursulin
@ 2022-12-27 16:33 ` Jani Nikula
0 siblings, 0 replies; 6+ messages in thread
From: Jani Nikula @ 2022-12-27 16:33 UTC (permalink / raw)
To: Tvrtko Ursulin, Andi Shyti, intel-gfx, dri-devel; +Cc: Andrzej Hajda
On Fri, 23 Dec 2022, Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com> wrote:
> On 23/12/2022 12:18, Andi Shyti wrote:
>> From: Chris Wilson <chris@chris-wilson.co.uk>
>>
>> On Haswell, in particular, we see an issue where resets fails because
>> the engine resumes from an incorrect RING_HEAD. Since the RING_HEAD
>> doesn't point to the remaining requests to re-run, but may instead point
>> into the uninitialised portion of the ring, the GPU may be then fed
>> invalid instructions from a privileged context, often pushing the GPU
>> into an unrecoverable hang.
>>
>> If at first the write doesn't succeed, try, try again.
>>
>> References: https://gitlab.freedesktop.org/drm/intel/-/issues/5432
>> References: https://gitlab.freedesktop.org/drm/intel/-/issues/3303
>> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
>> Cc: Andrzej Hajda <andrzej.hajda@intel.com>
>> Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
>> Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
>> ---
>> .../gpu/drm/i915/gt/intel_ring_submission.c | 44 +++++++++++++------
>> drivers/gpu/drm/i915/i915_utils.h | 8 ++++
>> 2 files changed, 38 insertions(+), 14 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/i915/gt/intel_ring_submission.c b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
>> index 827adb0cfaea6..cdf283f5b1427 100644
>> --- a/drivers/gpu/drm/i915/gt/intel_ring_submission.c
>> +++ b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
>> @@ -192,6 +192,7 @@ static bool stop_ring(struct intel_engine_cs *engine)
>> static int xcs_resume(struct intel_engine_cs *engine)
>> {
>> struct intel_ring *ring = engine->legacy.ring;
>> + ktime_t kt;
>>
>> ENGINE_TRACE(engine, "ring:{HEAD:%04x, TAIL:%04x}\n",
>> ring->head, ring->tail);
>> @@ -230,9 +231,20 @@ static int xcs_resume(struct intel_engine_cs *engine)
>> set_pp_dir(engine);
>>
>> /* First wake the ring up to an empty/idle ring */
>> - ENGINE_WRITE_FW(engine, RING_HEAD, ring->head);
>> + until_timeout_ns(kt, 2 * NSEC_PER_MSEC) {
>> + ENGINE_WRITE_FW(engine, RING_HEAD, ring->head);
>> + if (ENGINE_READ_FW(engine, RING_HEAD) == ring->head)
>> + break;
>> + }
>
> 2ms?! Shudder..
>
> #define done \
> ({ \
> ENGINE_WRITE_FW(engine, RING_HEAD, ring->head); \
> ENGINE_READ_FW(engine, RING_HEAD) == ring->head; \
> })
> _wait_for_atomic(done, 2 * USEC_PER_MSEC, needs_to_be_atomic_or_not?);
> #undef done
>
> Should work and avoid the need to add yet another helper, please
> double-check. Not as pretty, but accumulating generic sounding helpers
> in i915_utils.h is a bit frowned upon.
Yeah, please no more helpers like this. They're not helping.
BR,
Jani.
>
> Regards,
>
> Tvrtko
>
>> +
>> ENGINE_WRITE_FW(engine, RING_TAIL, ring->head);
>> - ENGINE_POSTING_READ(engine, RING_TAIL);
>> + if (ENGINE_READ_FW(engine, RING_HEAD) != ENGINE_READ_FW(engine, RING_TAIL)) {
>> + ENGINE_TRACE(engine, "failed to reset empty ring: [%x, %x]: %x\n",
>> + ENGINE_READ_FW(engine, RING_HEAD),
>> + ENGINE_READ_FW(engine, RING_TAIL),
>> + ring->head);
>> + goto err;
>> + }
>>
>> ENGINE_WRITE_FW(engine, RING_CTL,
>> RING_CTL_SIZE(ring->size) | RING_VALID);
>> @@ -241,12 +253,16 @@ static int xcs_resume(struct intel_engine_cs *engine)
>> if (__intel_wait_for_register_fw(engine->uncore,
>> RING_CTL(engine->mmio_base),
>> RING_VALID, RING_VALID,
>> - 5000, 0, NULL))
>> + 5000, 0, NULL)) {
>> + ENGINE_TRACE(engine, "failed to restart\n");
>> goto err;
>> + }
>>
>> - if (GRAPHICS_VER(engine->i915) > 2)
>> + if (GRAPHICS_VER(engine->i915) > 2) {
>> ENGINE_WRITE_FW(engine,
>> RING_MI_MODE, _MASKED_BIT_DISABLE(STOP_RING));
>> + ENGINE_POSTING_READ(engine, RING_MI_MODE);
>> + }
>>
>> /* Now awake, let it get started */
>> if (ring->tail != ring->head) {
>> @@ -259,16 +275,16 @@ static int xcs_resume(struct intel_engine_cs *engine)
>> return 0;
>>
>> err:
>> - drm_err(&engine->i915->drm,
>> - "%s initialization failed; "
>> - "ctl %08x (valid? %d) head %08x [%08x] tail %08x [%08x] start %08x [expected %08x]\n",
>> - engine->name,
>> - ENGINE_READ(engine, RING_CTL),
>> - ENGINE_READ(engine, RING_CTL) & RING_VALID,
>> - ENGINE_READ(engine, RING_HEAD), ring->head,
>> - ENGINE_READ(engine, RING_TAIL), ring->tail,
>> - ENGINE_READ(engine, RING_START),
>> - i915_ggtt_offset(ring->vma));
>> + ENGINE_TRACE(engine,
>> + "initialization failed; "
>> + "ctl %08x (valid? %d) head %08x [%08x] tail %08x [%08x] start %08x [expected %08x]\n",
>> + ENGINE_READ(engine, RING_CTL),
>> + ENGINE_READ(engine, RING_CTL) & RING_VALID,
>> + ENGINE_READ(engine, RING_HEAD), ring->head,
>> + ENGINE_READ(engine, RING_TAIL), ring->tail,
>> + ENGINE_READ(engine, RING_START),
>> + i915_ggtt_offset(ring->vma));
>> + GEM_TRACE_DUMP();
>> return -EIO;
>> }
>>
>> diff --git a/drivers/gpu/drm/i915/i915_utils.h b/drivers/gpu/drm/i915/i915_utils.h
>> index b64192d9c7daa..f24a25c0685e1 100644
>> --- a/drivers/gpu/drm/i915/i915_utils.h
>> +++ b/drivers/gpu/drm/i915/i915_utils.h
>> @@ -254,6 +254,14 @@ wait_remaining_ms_from_jiffies(unsigned long timestamp_jiffies, int to_wait_ms)
>> }
>> }
>>
>> +/**
>> + * until_timeout_ns - Keep retrying (busy spin) until the duration has passed
>> + */
>> +#define until_timeout_ns(end, timeout_ns) \
>> + for ((end) = ktime_get() + (timeout_ns); \
>> + ktime_before(ktime_get(), (end)); \
>> + cpu_relax())
>> + > /**
>> * __wait_for - magic wait macro
>> *
--
Jani Nikula, Intel Open Source Graphics Center
^ permalink raw reply [flat|nested] 6+ messages in thread
end of thread, other threads:[~2022-12-27 16:33 UTC | newest]
Thread overview: 6+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2022-12-23 12:18 [Intel-gfx] [PATCH] drm/i915/gt: Retry RING_HEAD reset until it sticks Andi Shyti
2022-12-23 12:18 ` Andi Shyti
2022-12-23 13:15 ` [Intel-gfx] ✓ Fi.CI.BAT: success for drm/i915/gt: Retry RING_HEAD reset until it sticks (rev2) Patchwork
2022-12-23 13:21 ` [Intel-gfx] [PATCH] drm/i915/gt: Retry RING_HEAD reset until it sticks Tvrtko Ursulin
2022-12-27 16:33 ` Jani Nikula
2022-12-23 14:30 ` [Intel-gfx] ✓ Fi.CI.IGT: success for drm/i915/gt: Retry RING_HEAD reset until it sticks (rev2) Patchwork
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.