* [PATCH v4] drm/i915/gt: Use poll_timeout_us in place of sliding sleep window
@ 2026-07-06 15:35 Jonathan Cavitt
2026-07-07 0:30 ` ✗ i915.CI.BAT: failure for drm/i915/gt: Use poll_timeout_us in place of sliding sleep window (rev4) Patchwork
0 siblings, 1 reply; 2+ messages in thread
From: Jonathan Cavitt @ 2026-07-06 15:35 UTC (permalink / raw)
To: intel-gfx
Cc: alex.zuo, jonathan.cavitt, jani.nikula, andi.shyti,
krzysztof.karas
The functions intel_guc_send_busy_loop and ct_send can theoretically
loop forever. In the former case, intel_guc_send_busy_loop can iterate
forever if intel_guc_send_nb repeatedly returns -EBUSY. In the latter
case, ct_send can loop forever if the guc-to-host or host-to-guc buffers
get stuck in a full state.
Rework the functions to use the poll_timeout_us family of functions
instead of calculating sleep_period_ms repeatedly. In both cases now,
if the loop condition is not met after 10 minutes, the function will
report it as a failure.
This also resolves a static analysis issue involving sleep_period_ms
overflowing after several shift-left-logical calls.
v2:
- Reduce default sleep/udelay duration (jcavitt)
v3:
- Use atomic in ct_send (jcavitt)
v4:
- Rework ct_send reimplementation to better preserve original logic
(Andi)
- Define 10 minutes to remove magic numbers (Krzysztof)
Suggested-by: Jani Nikula <jani.nikula@linux.intel.com>
Signed-off-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Cc: Andi Shyti <andi.shyti@intel.com>
Cc: Krzysztof Karas <krzysztof.karas@intel.com>
---
drivers/gpu/drm/i915/gt/uc/intel_guc.h | 33 +++++----
drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c | 90 ++++++++++++++---------
2 files changed, 71 insertions(+), 52 deletions(-)
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
index 053780f562c1..2d3adfbcd163 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
@@ -7,6 +7,7 @@
#define _INTEL_GUC_H_
#include <linux/delay.h>
+#include <linux/iopoll.h>
#include <linux/iosys-map.h>
#include <linux/xarray.h>
@@ -354,14 +355,14 @@ intel_guc_send_and_receive(struct intel_guc *guc, const u32 *action, u32 len,
response_buf, response_buf_size, 0);
}
+#define POLL_TIMEOUT_DUR (600 * USEC_PER_SEC)
static inline int intel_guc_send_busy_loop(struct intel_guc *guc,
const u32 *action,
u32 len,
u32 g2h_len_dw,
bool loop)
{
- int err;
- unsigned int sleep_period_ms = 1;
+ int err, timedout;
bool not_atomic = !in_atomic() && !irqs_disabled();
/*
@@ -374,20 +375,20 @@ static inline int intel_guc_send_busy_loop(struct intel_guc *guc,
/* No sleeping with spin locks, just busy loop */
might_sleep_if(loop && not_atomic);
-retry:
- err = intel_guc_send_nb(guc, action, len, g2h_len_dw);
- if (unlikely(err == -EBUSY && loop)) {
- if (likely(not_atomic)) {
- if (msleep_interruptible(sleep_period_ms))
- return -EINTR;
- sleep_period_ms = sleep_period_ms << 1;
- } else {
- cpu_relax();
- }
- goto retry;
- }
-
- return err;
+ if (!loop)
+ return intel_guc_send_nb(guc, action, len, g2h_len_dw);
+
+ if (not_atomic)
+ timedout = poll_timeout_us(err = intel_guc_send_nb(guc, action,
+ len, g2h_len_dw),
+ err != -EBUSY, USEC_PER_MSEC,
+ POLL_TIMEOUT_DUR, false);
+ else
+ timedout = poll_timeout_us_atomic(err = intel_guc_send_nb(guc, action,
+ len, g2h_len_dw),
+ err != -EBUSY, USEC_PER_MSEC,
+ POLL_TIMEOUT_DUR, false);
+ return timedout ?: err;
}
/* Only call this from the interrupt handler code */
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c
index 1c455d84bf9d..9f9fb5b10ed4 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c
@@ -706,37 +706,19 @@ static int ct_send_nb(struct intel_guc_ct *ct,
return ret;
}
-static int ct_send(struct intel_guc_ct *ct,
- const u32 *action,
- u32 len,
- u32 *response_buf,
- u32 response_buf_size,
- u32 *status)
+static int ct_lazy_spin(struct intel_guc_ct *ct,
+ struct ct_request *request,
+ const u32 *action,
+ u32 len,
+ u32 *response_buf,
+ u32 response_buf_size,
+ u32 *status)
{
struct intel_guc_ct_buffer *ctb = &ct->ctbs.send;
- struct ct_request request;
unsigned long flags;
- unsigned int sleep_period_ms = 1;
- bool send_again;
u32 fence;
int err;
- GEM_BUG_ON(!ct->enabled);
- GEM_BUG_ON(!len);
- GEM_BUG_ON(len > GUC_CTB_HXG_MSG_MAX_LEN - GUC_CTB_HDR_LEN);
- GEM_BUG_ON(!response_buf && response_buf_size);
- might_sleep();
-
-resend:
- send_again = false;
-
- /*
- * We use a lazy spin wait loop here as we believe that if the CT
- * buffers are sized correctly the flow control condition should be
- * rare. Reserving the maximum size in the G2H credits as we don't know
- * how big the response is going to be.
- */
-retry:
spin_lock_irqsave(&ctb->lock, flags);
if (unlikely(!h2g_has_room(ct, len + GUC_CTB_HDR_LEN) ||
!g2h_has_room(ct, GUC_CTB_HXG_MSG_MAX_LEN))) {
@@ -746,31 +728,67 @@ static int ct_send(struct intel_guc_ct *ct,
if (unlikely(ct_deadlocked(ct)))
return -EPIPE;
-
- if (msleep_interruptible(sleep_period_ms))
- return -EINTR;
- sleep_period_ms = sleep_period_ms << 1;
-
- goto retry;
+ return -EBUSY;
}
ct->stall_time = KTIME_MAX;
fence = ct_get_next_fence(ct);
- request.fence = fence;
- request.status = 0;
- request.response_len = response_buf_size;
- request.response_buf = response_buf;
+ request->fence = fence;
+ request->status = 0;
+ request->response_len = response_buf_size;
+ request->response_buf = response_buf;
spin_lock(&ct->requests.lock);
- list_add_tail(&request.link, &ct->requests.pending);
+ list_add_tail(&request->link, &ct->requests.pending);
spin_unlock(&ct->requests.lock);
err = ct_write(ct, action, len, fence, 0);
g2h_reserve_space(ct, GUC_CTB_HXG_MSG_MAX_LEN);
spin_unlock_irqrestore(&ctb->lock, flags);
+ return err;
+}
+static int ct_send(struct intel_guc_ct *ct,
+ const u32 *action,
+ u32 len,
+ u32 *response_buf,
+ u32 response_buf_size,
+ u32 *status)
+{
+ struct ct_request request;
+ unsigned long flags;
+ bool send_again;
+ int err, timedout;
+
+ GEM_BUG_ON(!ct->enabled);
+ GEM_BUG_ON(!len);
+ GEM_BUG_ON(len > GUC_CTB_HXG_MSG_MAX_LEN - GUC_CTB_HDR_LEN);
+ GEM_BUG_ON(!response_buf && response_buf_size);
+ might_sleep();
+
+resend:
+ send_again = false;
+
+ /*
+ * We use a lazy spin wait loop here as we believe that if the CT
+ * buffers are sized correctly the flow control condition should be
+ * rare. Reserving the maximum size in the G2H credits as we don't know
+ * how big the response is going to be.
+ */
+ timedout = poll_timeout_us_atomic(err = ct_lazy_spin(ct, &request, action,
+ len, response_buf,
+ response_buf_size,
+ status),
+ err != -EBUSY, USEC_PER_MSEC,
+ POLL_TIMEOUT_DUR, false);
+
+ /* This is only the case if ct is deadlocked or we time out */
+ if (ct->stall_time != KTIME_MAX)
+ return timedout ?: err;
+
+ /* Otherwise, ct_write failed and we need to clean up */
if (unlikely(err))
goto unlink;
--
2.53.0
^ permalink raw reply related [flat|nested] 2+ messages in thread
* ✗ i915.CI.BAT: failure for drm/i915/gt: Use poll_timeout_us in place of sliding sleep window (rev4)
2026-07-06 15:35 [PATCH v4] drm/i915/gt: Use poll_timeout_us in place of sliding sleep window Jonathan Cavitt
@ 2026-07-07 0:30 ` Patchwork
0 siblings, 0 replies; 2+ messages in thread
From: Patchwork @ 2026-07-07 0:30 UTC (permalink / raw)
To: Jonathan Cavitt; +Cc: intel-gfx
[-- Attachment #1: Type: text/plain, Size: 7052 bytes --]
== Series Details ==
Series: drm/i915/gt: Use poll_timeout_us in place of sliding sleep window (rev4)
URL : https://patchwork.freedesktop.org/series/169454/
State : failure
== Summary ==
CI Bug Log - changes from CI_DRM_18771 -> Patchwork_169454v4
====================================================
Summary
-------
**FAILURE**
Serious unknown changes coming with Patchwork_169454v4 absolutely need to be
verified manually.
If you think the reported changes have nothing to do with the changes
introduced in Patchwork_169454v4, please notify your bug team (I915-ci-infra@lists.freedesktop.org) 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_169454v4/index.html
Participating hosts (41 -> 40)
------------------------------
Additional (1): bat-adls-6
Missing (2): bat-dg2-13 fi-snb-2520m
Possible new issues
-------------------
Here are the unknown changes that may have been introduced in Patchwork_169454v4:
### IGT changes ###
#### Possible regressions ####
* igt@core_hotunplug@unbind-rebind:
- fi-kbl-8809g: [PASS][1] -> [ABORT][2]
[1]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_18771/fi-kbl-8809g/igt@core_hotunplug@unbind-rebind.html
[2]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_169454v4/fi-kbl-8809g/igt@core_hotunplug@unbind-rebind.html
Known issues
------------
Here are the changes found in Patchwork_169454v4 that come from known issues:
### IGT changes ###
#### Issues hit ####
* igt@dmabuf@all-tests:
- bat-adls-6: NOTRUN -> [SKIP][3] ([i915#15931])
[3]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_169454v4/bat-adls-6/igt@dmabuf@all-tests.html
* igt@gem_lmem_swapping@parallel-random-engines:
- bat-adls-6: NOTRUN -> [SKIP][4] ([i915#4613]) +3 other tests skip
[4]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_169454v4/bat-adls-6/igt@gem_lmem_swapping@parallel-random-engines.html
* igt@gem_tiled_pread_basic@basic:
- bat-adls-6: NOTRUN -> [SKIP][5] ([i915#15656])
[5]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_169454v4/bat-adls-6/igt@gem_tiled_pread_basic@basic.html
* igt@i915_selftest@live:
- bat-arlh-2: [PASS][6] -> [INCOMPLETE][7] ([i915#16547])
[6]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_18771/bat-arlh-2/igt@i915_selftest@live.html
[7]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_169454v4/bat-arlh-2/igt@i915_selftest@live.html
- bat-adlp-11: [PASS][8] -> [DMESG-WARN][9] ([i915#16404]) +1 other test dmesg-warn
[8]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_18771/bat-adlp-11/igt@i915_selftest@live.html
[9]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_169454v4/bat-adlp-11/igt@i915_selftest@live.html
* igt@i915_selftest@live@guc_hang:
- bat-arlh-2: [PASS][10] -> [INCOMPLETE][11] ([i915#16376])
[10]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_18771/bat-arlh-2/igt@i915_selftest@live@guc_hang.html
[11]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_169454v4/bat-arlh-2/igt@i915_selftest@live@guc_hang.html
* igt@intel_hwmon@hwmon-read:
- bat-adls-6: NOTRUN -> [SKIP][12] ([i915#7707]) +1 other test skip
[12]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_169454v4/bat-adls-6/igt@intel_hwmon@hwmon-read.html
* igt@kms_cursor_legacy@basic-busy-flip-before-cursor-legacy:
- bat-adls-6: NOTRUN -> [SKIP][13] ([i915#4103]) +1 other test skip
[13]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_169454v4/bat-adls-6/igt@kms_cursor_legacy@basic-busy-flip-before-cursor-legacy.html
* igt@kms_dsc@dsc-basic:
- bat-adls-6: NOTRUN -> [SKIP][14] ([i915#16361])
[14]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_169454v4/bat-adls-6/igt@kms_dsc@dsc-basic.html
* igt@kms_force_connector_basic@force-load-detect:
- bat-adls-6: NOTRUN -> [SKIP][15]
[15]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_169454v4/bat-adls-6/igt@kms_force_connector_basic@force-load-detect.html
* igt@kms_pm_backlight@basic-brightness:
- bat-adls-6: NOTRUN -> [SKIP][16] ([i915#5354])
[16]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_169454v4/bat-adls-6/igt@kms_pm_backlight@basic-brightness.html
* igt@kms_psr@psr-primary-mmap-gtt:
- bat-adls-6: NOTRUN -> [SKIP][17] ([i915#1072] / [i915#9732]) +3 other tests skip
[17]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_169454v4/bat-adls-6/igt@kms_psr@psr-primary-mmap-gtt.html
* igt@kms_setmode@basic-clone-single-crtc:
- bat-adls-6: NOTRUN -> [SKIP][18] ([i915#3555])
[18]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_169454v4/bat-adls-6/igt@kms_setmode@basic-clone-single-crtc.html
* igt@prime_vgem@basic-fence-read:
- bat-adls-6: NOTRUN -> [SKIP][19] ([i915#3291]) +2 other tests skip
[19]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_169454v4/bat-adls-6/igt@prime_vgem@basic-fence-read.html
#### Possible fixes ####
* igt@i915_selftest@live:
- bat-arls-5: [DMESG-FAIL][20] ([i915#16528]) -> [PASS][21] +1 other test pass
[20]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_18771/bat-arls-5/igt@i915_selftest@live.html
[21]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_169454v4/bat-arls-5/igt@i915_selftest@live.html
[i915#1072]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/1072
[i915#15656]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/15656
[i915#15931]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/15931
[i915#16361]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/16361
[i915#16376]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/16376
[i915#16404]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/16404
[i915#16528]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/16528
[i915#16547]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/16547
[i915#3291]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/3291
[i915#3555]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/3555
[i915#4103]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/4103
[i915#4613]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/4613
[i915#5354]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/5354
[i915#7707]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/7707
[i915#9732]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/9732
Build changes
-------------
* Linux: CI_DRM_18771 -> Patchwork_169454v4
CI-20190529: 20190529
CI_DRM_18771: 5f3c5d8ad095d09441648d9f564eaee7d9c30bec @ git://anongit.freedesktop.org/gfx-ci/linux
IGT_8990: 8990
Patchwork_169454v4: 5f3c5d8ad095d09441648d9f564eaee7d9c30bec @ git://anongit.freedesktop.org/gfx-ci/linux
== Logs ==
For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_169454v4/index.html
[-- Attachment #2: Type: text/html, Size: 8031 bytes --]
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2026-07-07 0:30 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-07-06 15:35 [PATCH v4] drm/i915/gt: Use poll_timeout_us in place of sliding sleep window Jonathan Cavitt
2026-07-07 0:30 ` ✗ i915.CI.BAT: failure for drm/i915/gt: Use poll_timeout_us in place of sliding sleep window (rev4) 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.