* [PATCH v4 0/3] drm/xe: fix GuC TLB invalidation ack stalls on ARL (Wa_22016122933)
@ 2026-09-17 16:35 Tales A. Mendonça
2026-09-17 16:35 ` [PATCH v4 1/3] drm/xe: Capture devcoredump on TLB invalidation timeout Tales A. Mendonça
` (6 more replies)
0 siblings, 7 replies; 16+ messages in thread
From: Tales A. Mendonça @ 2026-09-17 16:35 UTC (permalink / raw)
To: intel-xe
Cc: matthew.brost, daniele.ceraolospurio, stuart.summers,
julia.filipchuk, thomas.hellstrom, rodrigo.vivi, jani.nikula,
navonjohnlukose, dri-devel, Tales A. Mendonça
Hi,
v4 of the TLB invalidation ack stall fix for ARL, rebased on today's
drm-tip. Tracked in:
https://gitlab.freedesktop.org/drm/xe/kernel/-/work_items/8678
Recap: on the standalone media GT of MTL/ARL the CPU reads stale cache
lines for data the GuC has already written. The visible symptom is TLB
invalidation acks appearing to stall for a near-constant ~2.3s. i915
works around this as Wa_22016122933; xe never inherited it. Patch 3
implements it, scoped like i915.
In v3 I asked two open questions in this cover letter. Since there was
no preference expressed, v4 makes the conservative choice in both cases
and documents the reasoning in the commit message, so the series is not
blocked on a decision:
1. CPU mapping: keeping XE_BO_FLAG_NEEDS_UC (uncached on both sides).
It is the tested configuration and no throughput difference against
the CPU-WC variant was measurable. Matching i915's exact CPU-WC +
GGTT-UC combination needs either a new BO flag or decoupling the
GGTT cache-mode selection from XE_BO_FLAG_NEEDS_UC; happy to add
that plumbing if parity is preferred.
2. Scope: covering the GuC-shared allocations (CTBs, log, ADS, SLPC,
engine activity), which is where the failures were observed. i915
additionally covers media-GT LRC/ring state; that can be a
follow-up if wanted.
Fixes:/Cc: stable are still left out, since MTL/ARL is require_force_probe
in xe. Also happy to add them.
Validation of patch 3 is now six weeks on two ARL machines (7d51 and
7dd1), across kernels 7.1.6, 7.1.8 and 7.2, with over 10M TLB
invalidations processed and zero ack stalls. Before the fix both
machines reproduced 20-60 stalls/day, every day, on two GuC firmware
versions. The 7dd1 machine, which could not survive a day of media
workloads on xe without a platform freeze, has been running xe full
time since 11 August with zero incidents.
Patches 1-2 are the diagnostics that made the investigation possible
and are unchanged since v3. checkpatch is clean on the series.
v3 -> v4:
- Rebased on drm-tip.
- Patch 3: resolved both open questions in the commit message instead
of leaving them for discussion; refreshed validation data.
Thanks,
Tales
Tales A. Mendonça (3):
drm/xe: Capture devcoredump on TLB invalidation timeout
drm/xe: Log when a timed out TLB invalidation ack finally arrives
drm/xe: Implement Wa_22016122933
drivers/gpu/drm/xe/xe_devcoredump.c | 46 +++++++++++----------
drivers/gpu/drm/xe/xe_devcoredump.h | 15 +++++--
drivers/gpu/drm/xe/xe_guc.c | 16 +++++++
drivers/gpu/drm/xe/xe_guc.h | 2 +
drivers/gpu/drm/xe/xe_guc_ads.c | 3 +-
drivers/gpu/drm/xe/xe_guc_ct.c | 6 ++-
drivers/gpu/drm/xe/xe_guc_engine_activity.c | 6 ++-
drivers/gpu/drm/xe/xe_guc_log.c | 7 +++-
drivers/gpu/drm/xe/xe_guc_pc.c | 3 +-
drivers/gpu/drm/xe/xe_tlb_inval.c | 39 +++++++++++++++++
drivers/gpu/drm/xe/xe_tlb_inval_types.h | 17 ++++++++
drivers/gpu/drm/xe/xe_wa_oob.rules | 1 +
12 files changed, 128 insertions(+), 33 deletions(-)
--
2.55.0
^ permalink raw reply [flat|nested] 16+ messages in thread
* [PATCH v4 1/3] drm/xe: Capture devcoredump on TLB invalidation timeout
2026-09-17 16:35 [PATCH v4 0/3] drm/xe: fix GuC TLB invalidation ack stalls on ARL (Wa_22016122933) Tales A. Mendonça
@ 2026-09-17 16:35 ` Tales A. Mendonça
2026-09-17 16:50 ` sashiko-bot
2026-09-18 22:01 ` Matthew Brost
2026-09-17 16:35 ` [PATCH v4 2/3] drm/xe: Log when a timed out TLB invalidation ack finally arrives Tales A. Mendonça
` (5 subsequent siblings)
6 siblings, 2 replies; 16+ messages in thread
From: Tales A. Mendonça @ 2026-09-17 16:35 UTC (permalink / raw)
To: intel-xe
Cc: matthew.brost, daniele.ceraolospurio, stuart.summers,
julia.filipchuk, thomas.hellstrom, rodrigo.vivi, jani.nikula,
navonjohnlukose, dri-devel, Tales A. Mendonça
TLB invalidation timeouts currently leave no record of the firmware
state behind: there is no exec queue or job to blame, so nothing calls
xe_devcoredump() and the GuC log content at the time of the hang is
lost.
Add xe_devcoredump_gt(), a variant of xe_devcoredump() for hangs that
are not tied to an exec queue or job. It captures the GuC log and CT
state of the affected GT, reusing the existing snapshot machinery and
the "only first snapshot" policy, and hook it up to the TLB invalidation
timeout path.
This was instrumental in diagnosing GuC TLB invalidation ack stalls on
ARL (see Link), where the invalidation request is consumed from the H2G
CTB immediately but the ack G2H only arrives ~2.3s later, after the
timeout has already fired.
Link: https://gitlab.freedesktop.org/drm/xe/kernel/-/work_items/8678
Signed-off-by: Tales A. Mendonça <talesam@gmail.com>
---
drivers/gpu/drm/xe/xe_devcoredump.c | 46 ++++++++++++++++-------------
drivers/gpu/drm/xe/xe_devcoredump.h | 15 +++++++---
drivers/gpu/drm/xe/xe_tlb_inval.c | 20 +++++++++++++
3 files changed, 56 insertions(+), 25 deletions(-)
diff --git a/drivers/gpu/drm/xe/xe_devcoredump.c b/drivers/gpu/drm/xe/xe_devcoredump.c
index 5f2b90b18f9..6bee8933f95 100644
--- a/drivers/gpu/drm/xe/xe_devcoredump.c
+++ b/drivers/gpu/drm/xe/xe_devcoredump.c
@@ -74,11 +74,6 @@ static struct xe_device *coredump_to_xe(const struct xe_devcoredump *coredump)
return container_of(coredump, struct xe_device, devcoredump);
}
-static struct xe_guc *exec_queue_to_guc(struct xe_exec_queue *q)
-{
- return &q->gt->uc.guc;
-}
-
static ssize_t __xe_devcoredump_read(char *buffer, ssize_t count,
ssize_t start,
struct xe_devcoredump *coredump)
@@ -323,40 +318,44 @@ static void xe_devcoredump_deferred_snap_work(struct work_struct *work)
}
static void devcoredump_snapshot(struct xe_devcoredump *coredump,
+ struct xe_gt *gt,
struct xe_exec_queue *q,
struct xe_sched_job *job)
{
struct xe_devcoredump_snapshot *ss = &coredump->snapshot;
- struct xe_guc *guc = exec_queue_to_guc(q);
+ struct xe_guc *guc = >->uc.guc;
const char *process_name = "no process";
bool cookie;
ss->snapshot_time = ktime_get_real();
ss->boot_time = ktime_get_boottime();
- if (q->vm && q->vm->xef) {
+ if (q && q->vm && q->vm->xef) {
process_name = q->vm->xef->process_name;
ss->pid = q->vm->xef->pid;
}
strscpy(ss->process_name, process_name);
- ss->gt = q->gt;
+ ss->gt = gt;
INIT_WORK(&ss->work, xe_devcoredump_deferred_snap_work);
/* keep going if fw fails as we still want to save the memory and SW data */
- CLASS(xe_force_wake, fw_ref)(gt_to_fw(q->gt), XE_FORCEWAKE_ALL);
+ CLASS(xe_force_wake, fw_ref)(gt_to_fw(gt), XE_FORCEWAKE_ALL);
cookie = dma_fence_begin_signalling();
ss->guc.log = xe_guc_log_snapshot_capture(&guc->log, true);
ss->guc.ct = xe_guc_ct_snapshot_capture(&guc->ct);
- ss->ge = xe_guc_exec_queue_snapshot_capture(q);
- if (job)
- ss->job = xe_sched_job_snapshot_capture(job);
- ss->vm = xe_vm_snapshot_capture(q->vm);
- xe_engine_snapshot_capture_for_queue(q);
+ if (q) {
+ ss->ge = xe_guc_exec_queue_snapshot_capture(q);
+ if (job)
+ ss->job = xe_sched_job_snapshot_capture(job);
+ ss->vm = xe_vm_snapshot_capture(q->vm);
+
+ xe_engine_snapshot_capture_for_queue(q);
+ }
queue_work(system_dfl_wq, &ss->work);
@@ -364,19 +363,24 @@ static void devcoredump_snapshot(struct xe_devcoredump *coredump,
}
/**
- * xe_devcoredump - Take the required snapshots and initialize coredump device.
- * @q: The faulty xe_exec_queue, where the issue was detected.
- * @job: The faulty xe_sched_job, where the issue was detected.
+ * __xe_devcoredump - Take the required snapshots and initialize coredump device.
+ * @gt: The GT where the issue was detected.
+ * @q: The faulty xe_exec_queue, where the issue was detected, may be NULL for
+ * hangs that are not tied to an exec queue (e.g. TLB invalidation
+ * timeouts); in that case only the GT-level state (GuC log and CT state)
+ * is captured.
+ * @job: The faulty xe_sched_job, where the issue was detected, may be NULL.
* @fmt: Printf format + args to describe the reason for the core dump
*
* This function should be called at the crash time within the serialized
* gt_reset. It is skipped if we still have the core dump device available
* with the information of the 'first' snapshot.
*/
-__printf(3, 4)
-void xe_devcoredump(struct xe_exec_queue *q, struct xe_sched_job *job, const char *fmt, ...)
+__printf(4, 5)
+void __xe_devcoredump(struct xe_gt *gt, struct xe_exec_queue *q,
+ struct xe_sched_job *job, const char *fmt, ...)
{
- struct xe_device *xe = gt_to_xe(q->gt);
+ struct xe_device *xe = gt_to_xe(gt);
struct xe_devcoredump *coredump = &xe->devcoredump;
va_list varg;
@@ -394,7 +398,7 @@ void xe_devcoredump(struct xe_exec_queue *q, struct xe_sched_job *job, const cha
coredump->snapshot.reason = kvasprintf(GFP_ATOMIC, fmt, varg);
va_end(varg);
- devcoredump_snapshot(coredump, q, job);
+ devcoredump_snapshot(coredump, gt, q, job);
drm_info(&xe->drm, "Xe device coredump has been created\n");
drm_info(&xe->drm, "Check your /sys/class/drm/card%d/device/devcoredump/data\n",
diff --git a/drivers/gpu/drm/xe/xe_devcoredump.h b/drivers/gpu/drm/xe/xe_devcoredump.h
index 5391a80a4d1..bc4800b3a3f 100644
--- a/drivers/gpu/drm/xe/xe_devcoredump.h
+++ b/drivers/gpu/drm/xe/xe_devcoredump.h
@@ -11,15 +11,17 @@
struct drm_printer;
struct xe_device;
struct xe_exec_queue;
+struct xe_gt;
struct xe_sched_job;
#ifdef CONFIG_DEV_COREDUMP
-void xe_devcoredump(struct xe_exec_queue *q, struct xe_sched_job *job, const char *fmt, ...);
+void __xe_devcoredump(struct xe_gt *gt, struct xe_exec_queue *q,
+ struct xe_sched_job *job, const char *fmt, ...);
int xe_devcoredump_init(struct xe_device *xe);
#else
-static inline void xe_devcoredump(struct xe_exec_queue *q,
- struct xe_sched_job *job,
- const char *fmt, ...)
+static inline void __xe_devcoredump(struct xe_gt *gt, struct xe_exec_queue *q,
+ struct xe_sched_job *job,
+ const char *fmt, ...)
{
}
@@ -29,6 +31,11 @@ static inline int xe_devcoredump_init(struct xe_device *xe)
}
#endif
+#define xe_devcoredump(_q, _job, _fmt, ...) \
+ __xe_devcoredump((_q)->gt, _q, _job, _fmt, ##__VA_ARGS__)
+#define xe_devcoredump_gt(_gt, _fmt, ...) \
+ __xe_devcoredump(_gt, NULL, NULL, _fmt, ##__VA_ARGS__)
+
void xe_print_blob_ascii85(struct drm_printer *p, const char *prefix, char suffix,
const void *blob, size_t offset, size_t size);
diff --git a/drivers/gpu/drm/xe/xe_tlb_inval.c b/drivers/gpu/drm/xe/xe_tlb_inval.c
index 7c3bf32d925..7a0c04fac60 100644
--- a/drivers/gpu/drm/xe/xe_tlb_inval.c
+++ b/drivers/gpu/drm/xe/xe_tlb_inval.c
@@ -5,6 +5,7 @@
#include <drm/drm_managed.h>
+#include "xe_devcoredump.h"
#include "xe_device_types.h"
#include "xe_force_wake.h"
#include "xe_gt_stats.h"
@@ -29,6 +30,12 @@
#define FENCE_STACK_BIT DMA_FENCE_FLAG_USER_BITS
+/* The frontend is only ever embedded in a GT */
+static struct xe_gt *tlb_inval_to_gt(struct xe_tlb_inval *tlb_inval)
+{
+ return container_of(tlb_inval, struct xe_gt, tlb_inval);
+}
+
static void xe_tlb_inval_fence_fini(struct xe_tlb_inval_fence *fence)
{
if (WARN_ON_ONCE(!fence->tlb_inval))
@@ -73,6 +80,7 @@ static void xe_tlb_inval_fence_timeout(struct work_struct *work)
struct xe_device *xe = tlb_inval->xe;
struct xe_tlb_inval_fence *fence, *next;
long timeout_delay = tlb_inval->ops->timeout_delay(tlb_inval);
+ int timedout_seqno = 0;
tlb_inval->ops->flush(tlb_inval);
@@ -90,6 +98,8 @@ static void xe_tlb_inval_fence_timeout(struct work_struct *work)
"TLB invalidation fence timeout, seqno=%d recv=%d",
fence->seqno, tlb_inval->seqno_recv);
+ timedout_seqno = fence->seqno;
+
fence->base.error = -ETIME;
xe_tlb_inval_fence_signal(fence);
}
@@ -97,6 +107,16 @@ static void xe_tlb_inval_fence_timeout(struct work_struct *work)
queue_delayed_work(tlb_inval->timeout_wq, &tlb_inval->fence_tdr,
timeout_delay);
spin_unlock_irq(&tlb_inval->pending_lock);
+
+ /*
+ * Capture the GuC log and CT state so the firmware side of the hang
+ * can be inspected; there is no queue or job to blame here. Must be
+ * outside pending_lock as the capture takes sleeping locks.
+ */
+ if (timedout_seqno)
+ xe_devcoredump_gt(tlb_inval_to_gt(tlb_inval),
+ "TLB invalidation fence timeout, seqno=%d recv=%d",
+ timedout_seqno, tlb_inval->seqno_recv);
}
/**
--
2.55.0
^ permalink raw reply related [flat|nested] 16+ messages in thread
* [PATCH v4 2/3] drm/xe: Log when a timed out TLB invalidation ack finally arrives
2026-09-17 16:35 [PATCH v4 0/3] drm/xe: fix GuC TLB invalidation ack stalls on ARL (Wa_22016122933) Tales A. Mendonça
2026-09-17 16:35 ` [PATCH v4 1/3] drm/xe: Capture devcoredump on TLB invalidation timeout Tales A. Mendonça
@ 2026-09-17 16:35 ` Tales A. Mendonça
2026-09-18 22:06 ` Matthew Brost
2026-09-17 16:35 ` [PATCH v4 3/3] drm/xe: Implement Wa_22016122933 Tales A. Mendonça
` (4 subsequent siblings)
6 siblings, 1 reply; 16+ messages in thread
From: Tales A. Mendonça @ 2026-09-17 16:35 UTC (permalink / raw)
To: intel-xe
Cc: matthew.brost, daniele.ceraolospurio, stuart.summers,
julia.filipchuk, thomas.hellstrom, rodrigo.vivi, jani.nikula,
navonjohnlukose, dri-devel, Tales A. Mendonça
When a TLB invalidation fence times out we log the timeout, but if the
ack for that seqno later shows up there is no record of it, making it
impossible to tell from logs whether the ack was lost forever or merely
(very) late.
Track the most recent timed out seqno and log how late its ack arrives,
relative to both the original request and the moment the fence was
signaled with -ETIME.
On ARL with GuC 70.53.0 this shows the acks are never lost: they
consistently arrive ~2.3s after the request, tens of milliseconds after
the TDR has already signaled the fence:
TLB invalidation fence timeout, seqno=10992 recv=10991
TLB invalidation late ack: seqno=10992 recv=10992,
request-to-ack=2314ms, timeout-to-ack=45ms
Link: https://gitlab.freedesktop.org/drm/xe/kernel/-/work_items/8678
Signed-off-by: Tales A. Mendonça <talesam@gmail.com>
---
drivers/gpu/drm/xe/xe_tlb_inval.c | 19 +++++++++++++++++++
drivers/gpu/drm/xe/xe_tlb_inval_types.h | 17 +++++++++++++++++
2 files changed, 36 insertions(+)
diff --git a/drivers/gpu/drm/xe/xe_tlb_inval.c b/drivers/gpu/drm/xe/xe_tlb_inval.c
index 7a0c04fac60..7047a347551 100644
--- a/drivers/gpu/drm/xe/xe_tlb_inval.c
+++ b/drivers/gpu/drm/xe/xe_tlb_inval.c
@@ -14,6 +14,7 @@
#include "xe_guc_tlb_inval.h"
#include "xe_mmio.h"
#include "xe_pm.h"
+#include "xe_printk.h"
#include "xe_tlb_inval.h"
#include "xe_trace.h"
@@ -99,6 +100,11 @@ static void xe_tlb_inval_fence_timeout(struct work_struct *work)
fence->seqno, tlb_inval->seqno_recv);
timedout_seqno = fence->seqno;
+ if (!tlb_inval->timedout_seqno) {
+ tlb_inval->timedout_seqno = fence->seqno;
+ tlb_inval->timedout_inval_time = fence->inval_time;
+ tlb_inval->timedout_time = ktime_get();
+ }
fence->base.error = -ETIME;
xe_tlb_inval_fence_signal(fence);
@@ -227,6 +233,7 @@ void xe_tlb_inval_reset(struct xe_tlb_inval *tlb_inval)
else
pending_seqno = tlb_inval->seqno - 1;
WRITE_ONCE(tlb_inval->seqno_recv, pending_seqno);
+ tlb_inval->timedout_seqno = 0;
list_for_each_entry_safe(fence, next,
&tlb_inval->pending_fences, link)
@@ -454,6 +461,18 @@ void xe_tlb_inval_done_handler(struct xe_tlb_inval *tlb_inval, int seqno)
WRITE_ONCE(tlb_inval->seqno_recv, seqno);
+ if (tlb_inval->timedout_seqno &&
+ xe_tlb_inval_seqno_past(tlb_inval, tlb_inval->timedout_seqno)) {
+ ktime_t now = ktime_get();
+
+ xe_warn(xe,
+ "TLB invalidation late ack: seqno=%d recv=%d, request-to-ack=%lldms, timeout-to-ack=%lldms",
+ tlb_inval->timedout_seqno, seqno,
+ ktime_ms_delta(now, tlb_inval->timedout_inval_time),
+ ktime_ms_delta(now, tlb_inval->timedout_time));
+ tlb_inval->timedout_seqno = 0;
+ }
+
list_for_each_entry_safe(fence, next,
&tlb_inval->pending_fences, link) {
trace_xe_tlb_inval_fence_recv(xe, fence);
diff --git a/drivers/gpu/drm/xe/xe_tlb_inval_types.h b/drivers/gpu/drm/xe/xe_tlb_inval_types.h
index d77be1aedc9..80d2019fa20 100644
--- a/drivers/gpu/drm/xe/xe_tlb_inval_types.h
+++ b/drivers/gpu/drm/xe/xe_tlb_inval_types.h
@@ -112,6 +112,23 @@ struct xe_tlb_inval {
* @pending_lock: protects @pending_fences and updating @seqno_recv.
*/
spinlock_t pending_lock;
+ /**
+ * @timedout_seqno: seqno of the most recent timed out TLB
+ * invalidation, 0 if none. Used to measure how late the ack for a
+ * timed out invalidation actually arrives. Protected by
+ * @pending_lock.
+ */
+ int timedout_seqno;
+ /**
+ * @timedout_inval_time: request time of @timedout_seqno. Protected by
+ * @pending_lock.
+ */
+ ktime_t timedout_inval_time;
+ /**
+ * @timedout_time: time @timedout_seqno was signaled with -ETIME.
+ * Protected by @pending_lock.
+ */
+ ktime_t timedout_time;
/**
* @fence_tdr: schedules a delayed call to xe_tlb_fence_timeout after
* the timeout interval is over.
--
2.55.0
^ permalink raw reply related [flat|nested] 16+ messages in thread
* [PATCH v4 3/3] drm/xe: Implement Wa_22016122933
2026-09-17 16:35 [PATCH v4 0/3] drm/xe: fix GuC TLB invalidation ack stalls on ARL (Wa_22016122933) Tales A. Mendonça
2026-09-17 16:35 ` [PATCH v4 1/3] drm/xe: Capture devcoredump on TLB invalidation timeout Tales A. Mendonça
2026-09-17 16:35 ` [PATCH v4 2/3] drm/xe: Log when a timed out TLB invalidation ack finally arrives Tales A. Mendonça
@ 2026-09-17 16:35 ` Tales A. Mendonça
2026-09-17 16:42 ` ✗ CI.checkpatch: warning for drm/xe: fix GuC TLB invalidation ack stalls on ARL (Wa_22016122933) (rev3) Patchwork
` (3 subsequent siblings)
6 siblings, 0 replies; 16+ messages in thread
From: Tales A. Mendonça @ 2026-09-17 16:35 UTC (permalink / raw)
To: intel-xe
Cc: matthew.brost, daniele.ceraolospurio, stuart.summers,
julia.filipchuk, thomas.hellstrom, rodrigo.vivi, jani.nikula,
navonjohnlukose, dri-devel, Tales A. Mendonça
On platforms with a standalone media GT and media version 13.00
(MTL/ARL), memory shared between the CPU and the media GT's GuC must
not be mapped cached on the CPU side: the CPU can otherwise read stale
cache lines for data the GuC has already written.
i915 implements this as Wa_22016122933 (see
intel_gt_needs_wa_22016122933(), used by intel_guc_allocate_vma() and
intel_gt_coherent_map_type()); xe never inherited it.
The visible symptom on ARL is TLB invalidation acks stalling for a
near-constant ~2.3s: the GuC writes the G2H ack in time, but the CPU
keeps reading a stale (empty) view of the G2H CTB until the line is
naturally evicted, so the fence timeout at 2.25s fires first. GuC log
decode confirmed all invalidations were handled promptly by the
firmware, and only the media GT was affected. See Link for the full
investigation (three machines affected: 7d51, 7dd1, Arc Pro 130T).
Making the mapping coherent instead of uncached does not help: with a
GGTT PAT entry repurposed to WB|COH_2WAY the driver comes up and the
media GT GuC runs, but the stalls remain (request-to-ack 2290ms).
Uncached really is required here. Note that 2-way coherency is not
normally reachable from a GGTT PTE (only 2 PAT bits), so that
experiment needed a modified PAT table and may not reflect a supported
configuration.
Add the OOB workaround scoped like i915 (media version 13.00, media GT
only - MEDIA_VERSION() OOB rules only match the media GT on standalone
media platforms) and apply XE_BO_FLAG_NEEDS_UC to the GuC-shared
allocations the CPU reads from: the CTBs, the GuC log, ADS, the SLPC
shared data and the engine activity buffers. hwconfig and the G2G
buffer are allocated on the primary GT only, where the workaround does
not apply.
Note that XE_BO_FLAG_NEEDS_UC drives both the CPU mapping (uncached)
and the GGTT cache mode (XE_CACHE_NONE instead of XE_CACHE_WB), which is
stricter than i915: i915 documents the workaround as WC on the CPU side
and UC on the GPU side. A CPU-WC variant with the GGTT side kept at
XE_CACHE_NONE was measured to be equally effective, but expressing it
would require either a new BO flag or decoupling the GGTT cache-mode
selection from XE_BO_FLAG_NEEDS_UC - simply swapping in
XE_BO_FLAG_FORCE_WC silently relaxes the GPU side back to WB and the
stalls return. The stricter mapping is kept here since it is the tested
configuration and no throughput difference between the two was
measurable; the extra plumbing can be added later if parity with i915 is
preferred.
Scope is limited to the GuC-shared allocations, which is where the
failures were observed. i915 additionally covers media-GT LRC/ring
state; extending xe to match can be done as a follow-up if wanted.
Validation on two ARL machines (7d51 and 7dd1): before, 20-60 TLB
invalidation ack stalls per day, every day, for weeks, on every kernel
and on two GuC firmware versions (70.53.0 and 70.72.1). After: zero
stalls in six weeks of combined runtime, over 10M TLB invalidations
processed under the same workloads, across kernels 7.1.6, 7.1.8 and
7.2. The 7dd1 machine, which could not survive a day of media
workloads on xe without a platform freeze, has been running xe full
time since 11 August, including days with heavy video transcoding,
with zero stalls and zero freezes.
The coherency experiment, the CPU-WC measurements and the engine
activity coverage gap were found by Navon John Lukose while A/B
testing v2 on an ARL 7d51.
Link: https://gitlab.freedesktop.org/drm/xe/kernel/-/work_items/8678
Suggested-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Tales A. Mendonça <talesam@gmail.com>
Tested-by: Navon John Lukose <navonjohnlukose@gmail.com>
---
drivers/gpu/drm/xe/xe_guc.c | 16 ++++++++++++++++
drivers/gpu/drm/xe/xe_guc.h | 2 ++
drivers/gpu/drm/xe/xe_guc_ads.c | 3 ++-
drivers/gpu/drm/xe/xe_guc_ct.c | 6 ++++--
drivers/gpu/drm/xe/xe_guc_engine_activity.c | 6 ++++--
drivers/gpu/drm/xe/xe_guc_log.c | 7 +++++--
drivers/gpu/drm/xe/xe_guc_pc.c | 3 ++-
drivers/gpu/drm/xe/xe_wa_oob.rules | 1 +
8 files changed, 36 insertions(+), 8 deletions(-)
diff --git a/drivers/gpu/drm/xe/xe_guc.c b/drivers/gpu/drm/xe/xe_guc.c
index c7f8bbd4cb9..3ab4cb9e496 100644
--- a/drivers/gpu/drm/xe/xe_guc.c
+++ b/drivers/gpu/drm/xe/xe_guc.c
@@ -1469,6 +1469,22 @@ int xe_guc_suspend(struct xe_guc *guc)
return 0;
}
+/**
+ * xe_guc_bo_wa_flags - Extra BO flags for memory shared with the GuC
+ * @gt: the &xe_gt whose GuC the buffer will be shared with
+ *
+ * Wa_22016122933: on the standalone media GT, memory shared between the
+ * CPU and the GuC must not be mapped cached on the CPU side, otherwise
+ * the CPU can read stale data written by the GuC (e.g. G2H CTB writes)
+ * for multiple seconds.
+ *
+ * Return: additional XE_BO_FLAG_* to use when allocating GuC-shared memory
+ */
+u32 xe_guc_bo_wa_flags(struct xe_gt *gt)
+{
+ return XE_GT_WA(gt, 22016122933) ? XE_BO_FLAG_NEEDS_UC : 0;
+}
+
void xe_guc_notify(struct xe_guc *guc)
{
struct xe_gt *gt = guc_to_gt(guc);
diff --git a/drivers/gpu/drm/xe/xe_guc.h b/drivers/gpu/drm/xe/xe_guc.h
index 61e3ee19a59..c4eca40d69c 100644
--- a/drivers/gpu/drm/xe/xe_guc.h
+++ b/drivers/gpu/drm/xe/xe_guc.h
@@ -30,6 +30,7 @@
xe_guc_fw_version_at_least((guc), MAKE_GUC_VER_ARGS(ver))
struct drm_printer;
+struct xe_gt;
void xe_guc_comm_init_early(struct xe_guc *guc);
int xe_guc_init_noalloc(struct xe_guc *guc);
@@ -45,6 +46,7 @@ void xe_guc_runtime_suspend(struct xe_guc *guc);
void xe_guc_runtime_resume(struct xe_guc *guc);
int xe_guc_suspend(struct xe_guc *guc);
int xe_guc_softreset(struct xe_guc *guc);
+u32 xe_guc_bo_wa_flags(struct xe_gt *gt);
void xe_guc_notify(struct xe_guc *guc);
int xe_guc_auth_huc(struct xe_guc *guc, u32 rsa_addr);
int xe_guc_mmio_send(struct xe_guc *guc, const u32 *request, u32 len);
diff --git a/drivers/gpu/drm/xe/xe_guc_ads.c b/drivers/gpu/drm/xe/xe_guc_ads.c
index ff8eee3831a..abc7266fc6f 100644
--- a/drivers/gpu/drm/xe/xe_guc_ads.c
+++ b/drivers/gpu/drm/xe/xe_guc_ads.c
@@ -435,7 +435,8 @@ int xe_guc_ads_init(struct xe_guc_ads *ads)
XE_BO_FLAG_SYSTEM |
XE_BO_FLAG_GGTT |
XE_BO_FLAG_GGTT_INVALIDATE |
- XE_BO_FLAG_PINNED_NORESTORE);
+ XE_BO_FLAG_PINNED_NORESTORE |
+ xe_guc_bo_wa_flags(gt));
if (IS_ERR(bo))
return PTR_ERR(bo);
diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c
index 5c4733da385..5c393aa29de 100644
--- a/drivers/gpu/drm/xe/xe_guc_ct.c
+++ b/drivers/gpu/drm/xe/xe_guc_ct.c
@@ -376,7 +376,8 @@ int xe_guc_ct_init(struct xe_guc_ct *ct)
XE_BO_FLAG_SYSTEM |
XE_BO_FLAG_GGTT |
XE_BO_FLAG_GGTT_INVALIDATE |
- XE_BO_FLAG_PINNED_NORESTORE);
+ XE_BO_FLAG_PINNED_NORESTORE |
+ xe_guc_bo_wa_flags(gt));
if (IS_ERR(bo))
return PTR_ERR(bo);
@@ -386,7 +387,8 @@ int xe_guc_ct_init(struct xe_guc_ct *ct)
XE_BO_FLAG_SYSTEM |
XE_BO_FLAG_GGTT |
XE_BO_FLAG_GGTT_INVALIDATE |
- XE_BO_FLAG_PINNED_NORESTORE);
+ XE_BO_FLAG_PINNED_NORESTORE |
+ xe_guc_bo_wa_flags(gt));
if (IS_ERR(bo))
return PTR_ERR(bo);
diff --git a/drivers/gpu/drm/xe/xe_guc_engine_activity.c b/drivers/gpu/drm/xe/xe_guc_engine_activity.c
index a782be57caa..729ce8ac140 100644
--- a/drivers/gpu/drm/xe/xe_guc_engine_activity.c
+++ b/drivers/gpu/drm/xe/xe_guc_engine_activity.c
@@ -97,7 +97,8 @@ static int allocate_engine_activity_buffers(struct xe_guc *guc,
metadata_bo = xe_bo_create_pin_map_novm(gt_to_xe(gt), tile, PAGE_ALIGN(metadata_size),
ttm_bo_type_kernel, XE_BO_FLAG_SYSTEM |
- XE_BO_FLAG_GGTT | XE_BO_FLAG_GGTT_INVALIDATE,
+ XE_BO_FLAG_GGTT | XE_BO_FLAG_GGTT_INVALIDATE |
+ xe_guc_bo_wa_flags(gt),
false);
if (IS_ERR(metadata_bo))
@@ -105,7 +106,8 @@ static int allocate_engine_activity_buffers(struct xe_guc *guc,
bo = xe_bo_create_pin_map_novm(gt_to_xe(gt), tile, PAGE_ALIGN(size),
ttm_bo_type_kernel, XE_BO_FLAG_VRAM_IF_DGFX(tile) |
- XE_BO_FLAG_GGTT | XE_BO_FLAG_GGTT_INVALIDATE, false);
+ XE_BO_FLAG_GGTT | XE_BO_FLAG_GGTT_INVALIDATE |
+ xe_guc_bo_wa_flags(gt), false);
if (IS_ERR(bo)) {
xe_bo_unpin_map_no_vm(metadata_bo);
diff --git a/drivers/gpu/drm/xe/xe_guc_log.c b/drivers/gpu/drm/xe/xe_guc_log.c
index 538d4df0f7a..7d006268ce9 100644
--- a/drivers/gpu/drm/xe/xe_guc_log.c
+++ b/drivers/gpu/drm/xe/xe_guc_log.c
@@ -17,6 +17,7 @@
#include "xe_force_wake.h"
#include "xe_gt_printk.h"
#include "xe_gt_types.h"
+#include "xe_guc.h"
#include "xe_map.h"
#include "xe_mmio.h"
#include "xe_module.h"
@@ -624,14 +625,16 @@ void xe_guc_log_print_lfd(struct xe_guc_log *log, struct drm_printer *p)
int xe_guc_log_init(struct xe_guc_log *log)
{
struct xe_device *xe = log_to_xe(log);
- struct xe_tile *tile = gt_to_tile(log_to_gt(log));
+ struct xe_gt *gt = log_to_gt(log);
+ struct xe_tile *tile = gt_to_tile(gt);
struct xe_bo *bo;
bo = xe_managed_bo_create_pin_map(xe, tile, GUC_LOG_SIZE,
XE_BO_FLAG_SYSTEM |
XE_BO_FLAG_GGTT |
XE_BO_FLAG_GGTT_INVALIDATE |
- XE_BO_FLAG_PINNED_NORESTORE);
+ XE_BO_FLAG_PINNED_NORESTORE |
+ xe_guc_bo_wa_flags(gt));
if (IS_ERR(bo))
return PTR_ERR(bo);
diff --git a/drivers/gpu/drm/xe/xe_guc_pc.c b/drivers/gpu/drm/xe/xe_guc_pc.c
index 097b075bd89..e0105222a2c 100644
--- a/drivers/gpu/drm/xe/xe_guc_pc.c
+++ b/drivers/gpu/drm/xe/xe_guc_pc.c
@@ -1391,7 +1391,8 @@ int xe_guc_pc_init(struct xe_guc_pc *pc)
XE_BO_FLAG_VRAM_IF_DGFX(tile) |
XE_BO_FLAG_GGTT |
XE_BO_FLAG_GGTT_INVALIDATE |
- XE_BO_FLAG_PINNED_NORESTORE);
+ XE_BO_FLAG_PINNED_NORESTORE |
+ xe_guc_bo_wa_flags(gt));
if (IS_ERR(bo))
return PTR_ERR(bo);
diff --git a/drivers/gpu/drm/xe/xe_wa_oob.rules b/drivers/gpu/drm/xe/xe_wa_oob.rules
index dd69ad07f7a..30958b26a1d 100644
--- a/drivers/gpu/drm/xe/xe_wa_oob.rules
+++ b/drivers/gpu/drm/xe/xe_wa_oob.rules
@@ -14,6 +14,7 @@
16017236439 PLATFORM(PVC)
14019821291 MEDIA_VERSION_RANGE(1300, 2000)
14015076503 MEDIA_VERSION(1300)
+22016122933 MEDIA_VERSION(1300)
14018913170 GRAPHICS_VERSION_RANGE(1270, 1274)
MEDIA_VERSION(1300)
PLATFORM(DG2)
--
2.55.0
^ permalink raw reply related [flat|nested] 16+ messages in thread
* ✗ CI.checkpatch: warning for drm/xe: fix GuC TLB invalidation ack stalls on ARL (Wa_22016122933) (rev3)
2026-09-17 16:35 [PATCH v4 0/3] drm/xe: fix GuC TLB invalidation ack stalls on ARL (Wa_22016122933) Tales A. Mendonça
` (2 preceding siblings ...)
2026-09-17 16:35 ` [PATCH v4 3/3] drm/xe: Implement Wa_22016122933 Tales A. Mendonça
@ 2026-09-17 16:42 ` Patchwork
2026-09-17 16:44 ` ✓ CI.KUnit: success " Patchwork
` (2 subsequent siblings)
6 siblings, 0 replies; 16+ messages in thread
From: Patchwork @ 2026-09-17 16:42 UTC (permalink / raw)
To: Tales A. Mendonça; +Cc: intel-xe
== Series Details ==
Series: drm/xe: fix GuC TLB invalidation ack stalls on ARL (Wa_22016122933) (rev3)
URL : https://patchwork.freedesktop.org/series/172110/
State : warning
== Summary ==
+ KERNEL=/kernel
+ git clone https://gitlab.freedesktop.org/drm/maintainer-tools mt
Cloning into 'mt'...
warning: redirecting to https://gitlab.freedesktop.org/drm/maintainer-tools.git/
+ git -C mt rev-list -n1 origin/master
d875049d2b299159a272bd5151994970cdcd1e31
+ cd /kernel
+ git config --global --add safe.directory /kernel
+ git log -n1
commit 5f8cd3317a8da0c63a0233a2e226d1a4609f7cba
Author: Tales A. Mendonça <talesam@gmail.com>
Date: Thu Sep 17 13:35:53 2026 -0300
drm/xe: Implement Wa_22016122933
On platforms with a standalone media GT and media version 13.00
(MTL/ARL), memory shared between the CPU and the media GT's GuC must
not be mapped cached on the CPU side: the CPU can otherwise read stale
cache lines for data the GuC has already written.
i915 implements this as Wa_22016122933 (see
intel_gt_needs_wa_22016122933(), used by intel_guc_allocate_vma() and
intel_gt_coherent_map_type()); xe never inherited it.
The visible symptom on ARL is TLB invalidation acks stalling for a
near-constant ~2.3s: the GuC writes the G2H ack in time, but the CPU
keeps reading a stale (empty) view of the G2H CTB until the line is
naturally evicted, so the fence timeout at 2.25s fires first. GuC log
decode confirmed all invalidations were handled promptly by the
firmware, and only the media GT was affected. See Link for the full
investigation (three machines affected: 7d51, 7dd1, Arc Pro 130T).
Making the mapping coherent instead of uncached does not help: with a
GGTT PAT entry repurposed to WB|COH_2WAY the driver comes up and the
media GT GuC runs, but the stalls remain (request-to-ack 2290ms).
Uncached really is required here. Note that 2-way coherency is not
normally reachable from a GGTT PTE (only 2 PAT bits), so that
experiment needed a modified PAT table and may not reflect a supported
configuration.
Add the OOB workaround scoped like i915 (media version 13.00, media GT
only - MEDIA_VERSION() OOB rules only match the media GT on standalone
media platforms) and apply XE_BO_FLAG_NEEDS_UC to the GuC-shared
allocations the CPU reads from: the CTBs, the GuC log, ADS, the SLPC
shared data and the engine activity buffers. hwconfig and the G2G
buffer are allocated on the primary GT only, where the workaround does
not apply.
Note that XE_BO_FLAG_NEEDS_UC drives both the CPU mapping (uncached)
and the GGTT cache mode (XE_CACHE_NONE instead of XE_CACHE_WB), which is
stricter than i915: i915 documents the workaround as WC on the CPU side
and UC on the GPU side. A CPU-WC variant with the GGTT side kept at
XE_CACHE_NONE was measured to be equally effective, but expressing it
would require either a new BO flag or decoupling the GGTT cache-mode
selection from XE_BO_FLAG_NEEDS_UC - simply swapping in
XE_BO_FLAG_FORCE_WC silently relaxes the GPU side back to WB and the
stalls return. The stricter mapping is kept here since it is the tested
configuration and no throughput difference between the two was
measurable; the extra plumbing can be added later if parity with i915 is
preferred.
Scope is limited to the GuC-shared allocations, which is where the
failures were observed. i915 additionally covers media-GT LRC/ring
state; extending xe to match can be done as a follow-up if wanted.
Validation on two ARL machines (7d51 and 7dd1): before, 20-60 TLB
invalidation ack stalls per day, every day, for weeks, on every kernel
and on two GuC firmware versions (70.53.0 and 70.72.1). After: zero
stalls in six weeks of combined runtime, over 10M TLB invalidations
processed under the same workloads, across kernels 7.1.6, 7.1.8 and
7.2. The 7dd1 machine, which could not survive a day of media
workloads on xe without a platform freeze, has been running xe full
time since 11 August, including days with heavy video transcoding,
with zero stalls and zero freezes.
The coherency experiment, the CPU-WC measurements and the engine
activity coverage gap were found by Navon John Lukose while A/B
testing v2 on an ARL 7d51.
Link: https://gitlab.freedesktop.org/drm/xe/kernel/-/work_items/8678
Suggested-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Tales A. Mendonça <talesam@gmail.com>
Tested-by: Navon John Lukose <navonjohnlukose@gmail.com>
+ /mt/dim checkpatch e970e6f15e212a8ff77f1b821e077ff97e95eb6f drm-intel
7688c7e24d1a drm/xe: Capture devcoredump on TLB invalidation timeout
-:168: CHECK:MACRO_ARG_REUSE: Macro argument reuse '_q' - possible side-effects?
#168: FILE: drivers/gpu/drm/xe/xe_devcoredump.h:34:
+#define xe_devcoredump(_q, _job, _fmt, ...) \
+ __xe_devcoredump((_q)->gt, _q, _job, _fmt, ##__VA_ARGS__)
total: 0 errors, 0 warnings, 1 checks, 184 lines checked
6ed6f05ce4e3 drm/xe: Log when a timed out TLB invalidation ack finally arrives
5f8cd3317a8d drm/xe: Implement Wa_22016122933
^ permalink raw reply [flat|nested] 16+ messages in thread
* ✓ CI.KUnit: success for drm/xe: fix GuC TLB invalidation ack stalls on ARL (Wa_22016122933) (rev3)
2026-09-17 16:35 [PATCH v4 0/3] drm/xe: fix GuC TLB invalidation ack stalls on ARL (Wa_22016122933) Tales A. Mendonça
` (3 preceding siblings ...)
2026-09-17 16:42 ` ✗ CI.checkpatch: warning for drm/xe: fix GuC TLB invalidation ack stalls on ARL (Wa_22016122933) (rev3) Patchwork
@ 2026-09-17 16:44 ` Patchwork
2026-09-17 17:54 ` ✓ Xe.CI.BAT: " Patchwork
2026-09-17 18:45 ` ✓ Xe.CI.FULL: " Patchwork
6 siblings, 0 replies; 16+ messages in thread
From: Patchwork @ 2026-09-17 16:44 UTC (permalink / raw)
To: Tales A. Mendonça; +Cc: intel-xe
== Series Details ==
Series: drm/xe: fix GuC TLB invalidation ack stalls on ARL (Wa_22016122933) (rev3)
URL : https://patchwork.freedesktop.org/series/172110/
State : success
== Summary ==
+ trap cleanup EXIT
+ kunitconfigs=('/kernel/drivers/gpu/tests/.kunitconfig' '/kernel/drivers/gpu/drm/xe/.kunitconfig' '/kernel/drivers/gpu/drm/tests/.kunitconfig' '/kernel/drivers/gpu/drm/ttm/tests/.kunitconfig' '/kernel/drivers/dma-buf/.kunitconfig')
+ for kcfg in "${kunitconfigs[@]}"
+ [[ ! -f /kernel/drivers/gpu/tests/.kunitconfig ]]
+ /kernel/tools/testing/kunit/kunit.py run --kunitconfig /kernel/drivers/gpu/tests/.kunitconfig
[16:42:49] Configuring KUnit Kernel ...
Generating .config ...
Populating config with:
$ make ARCH=um O=.kunit olddefconfig
[16:42:53] Building KUnit Kernel ...
Populating config with:
$ make ARCH=um O=.kunit olddefconfig
Building with:
$ make all compile_commands.json scripts_gdb ARCH=um O=.kunit --jobs=48
[16:43:13] Starting KUnit Kernel (1/1)...
[16:43:13] ============================================================
Running tests with:
$ .kunit/linux kunit.enable=1 mem=1G console=tty kunit_shutdown=halt
[16:43:13] ============= refcount_interrupt (4 subtests) ==============
[16:43:13] [PASSED] test_single_irq_change
[16:43:13] [PASSED] test_nested_irq_change
[16:43:13] [PASSED] test_multiple_irq_change
[16:43:13] [PASSED] test_irq_save
[16:43:13] =============== [PASSED] refcount_interrupt ================
[16:43:13] ================= gpu_buddy (14 subtests) ==================
[16:43:13] [PASSED] gpu_test_buddy_alloc_limit
[16:43:13] [PASSED] gpu_test_buddy_alloc_optimistic
[16:43:13] [PASSED] gpu_test_buddy_alloc_pessimistic
[16:43:13] [PASSED] gpu_test_buddy_alloc_pathological
[16:43:13] [PASSED] gpu_test_buddy_alloc_contiguous
[16:43:13] [PASSED] gpu_test_buddy_alloc_clear
[16:43:13] [PASSED] gpu_test_buddy_alloc_range
[16:43:14] [PASSED] gpu_test_buddy_alloc_range_bias
[16:43:14] [PASSED] gpu_test_buddy_fragmentation_performance
[16:43:15] [PASSED] gpu_test_buddy_dirty_tracker_performance
[16:43:15] [PASSED] gpu_test_buddy_alloc_exceeds_max_order
[16:43:15] [PASSED] gpu_test_buddy_offset_aligned_allocation
[16:43:15] [PASSED] gpu_test_buddy_subtree_offset_alignment_stress
[16:43:15] [PASSED] gpu_test_buddy_addr_to_block
[16:43:15] ==================== [PASSED] gpu_buddy ====================
[16:43:15] ============================================================
[16:43:15] Testing complete. Ran 18 tests: passed: 18
[16:43:15] Elapsed time: 26.520s total, 4.283s configuring, 20.320s building, 1.868s running
+ for kcfg in "${kunitconfigs[@]}"
+ [[ ! -f /kernel/drivers/gpu/drm/xe/.kunitconfig ]]
+ /kernel/tools/testing/kunit/kunit.py run --kunitconfig /kernel/drivers/gpu/drm/xe/.kunitconfig
[16:43:15] Configuring KUnit Kernel ...
Regenerating .config ...
Populating config with:
$ make ARCH=um O=.kunit olddefconfig
[16:43:17] Building KUnit Kernel ...
Populating config with:
$ make ARCH=um O=.kunit olddefconfig
Building with:
$ make all compile_commands.json scripts_gdb ARCH=um O=.kunit --jobs=48
[16:43:51] Starting KUnit Kernel (1/1)...
[16:43:51] ============================================================
Running tests with:
$ .kunit/linux kunit.enable=1 mem=1G console=tty kunit_shutdown=halt
[16:43:51] ============= refcount_interrupt (4 subtests) ==============
[16:43:51] [PASSED] test_single_irq_change
[16:43:51] [PASSED] test_nested_irq_change
[16:43:51] [PASSED] test_multiple_irq_change
[16:43:51] [PASSED] test_irq_save
[16:43:51] =============== [PASSED] refcount_interrupt ================
[16:43:51] ================== guc_buf (11 subtests) ===================
[16:43:51] [PASSED] test_smallest
[16:43:51] [PASSED] test_largest
[16:43:51] [PASSED] test_granular
[16:43:51] [PASSED] test_unique
[16:43:51] [PASSED] test_overlap
[16:43:51] [PASSED] test_reusable
[16:43:51] [PASSED] test_too_big
[16:43:51] [PASSED] test_flush
[16:43:51] [PASSED] test_lookup
[16:43:51] [PASSED] test_data
[16:43:51] [PASSED] test_class
[16:43:51] ===================== [PASSED] guc_buf =====================
[16:43:51] =================== guc_dbm (7 subtests) ===================
[16:43:51] [PASSED] test_empty
[16:43:51] [PASSED] test_default
[16:43:51] ======================== test_size ========================
[16:43:51] [PASSED] 4
[16:43:51] [PASSED] 8
[16:43:51] [PASSED] 32
[16:43:51] [PASSED] 256
[16:43:51] ==================== [PASSED] test_size ====================
[16:43:51] ======================= test_reuse ========================
[16:43:51] [PASSED] 4
[16:43:51] [PASSED] 8
[16:43:51] [PASSED] 32
[16:43:51] [PASSED] 256
[16:43:51] =================== [PASSED] test_reuse ====================
[16:43:51] =================== test_range_overlap ====================
[16:43:51] [PASSED] 4
[16:43:51] [PASSED] 8
[16:43:51] [PASSED] 32
[16:43:51] [PASSED] 256
[16:43:51] =============== [PASSED] test_range_overlap ================
[16:43:51] =================== test_range_compact ====================
[16:43:51] [PASSED] 4
[16:43:51] [PASSED] 8
[16:43:51] [PASSED] 32
[16:43:51] [PASSED] 256
[16:43:51] =============== [PASSED] test_range_compact ================
[16:43:51] ==================== test_range_spare =====================
[16:43:51] [PASSED] 4
[16:43:51] [PASSED] 8
[16:43:51] [PASSED] 32
[16:43:51] [PASSED] 256
[16:43:51] ================ [PASSED] test_range_spare =================
[16:43:51] ===================== [PASSED] guc_dbm =====================
[16:43:51] =================== guc_idm (6 subtests) ===================
[16:43:51] [PASSED] bad_init
[16:43:51] [PASSED] no_init
[16:43:51] [PASSED] init_fini
[16:43:51] [PASSED] check_used
[16:43:51] [PASSED] check_quota
[16:43:51] [PASSED] check_all
[16:43:51] ===================== [PASSED] guc_idm =====================
[16:43:51] =============== guc_klv_helpers (9 subtests) ===============
[16:43:51] [PASSED] test_count
[16:43:51] [PASSED] test_encode_u32
[16:43:51] [PASSED] test_encode_u64
[16:43:51] [PASSED] test_encode_string
[16:43:51] [PASSED] test_encode_object_raw
[16:43:51] [PASSED] test_encode_object_klv
[16:43:51] [PASSED] test_encode_object_nested
[16:43:51] [PASSED] test_encode_object_basic
[16:43:51] [PASSED] test_print
[16:43:51] ================= [PASSED] guc_klv_helpers =================
[16:43:51] =================== xe_log (4 subtests) ====================
[16:43:51] [PASSED] demo_cper
[16:43:51] [PASSED] demo_dmesg
[16:43:51] ======================= test_dmesg ========================
[16:43:51] [PASSED] test_fatal
[16:43:51] [PASSED] test_fatal_tile
[16:43:51] [PASSED] test_fatal_gt
[16:43:51] [PASSED] test_fatal_comp
[16:43:51] [PASSED] test_fatal_comp_tile
[16:43:51] [PASSED] test_fatal_comp_gt
[16:43:51] [PASSED] test_fatal_all
[16:43:51] [PASSED] test_recoverable
[16:43:51] [PASSED] test_recoverable_tile
[16:43:51] [PASSED] test_recoverable_gt
[16:43:51] [PASSED] test_recoverable_comp
[16:43:51] [PASSED] test_recoverable_comp_tile
[16:43:51] [PASSED] test_recoverable_comp_gt
[16:43:51] [PASSED] test_recoverable_all
[16:43:51] [PASSED] test_info
[16:43:51] [PASSED] test_info_tile
[16:43:51] [PASSED] test_info_gt
[16:43:51] [PASSED] test_info_err
[16:43:51] [PASSED] test_info_comp
[16:43:51] [PASSED] test_info_comp_tile
[16:43:51] [PASSED] test_info_comp_gt
[16:43:51] [PASSED] test_info_all
[16:43:51] [PASSED] test_hw_fatal
[16:43:51] [PASSED] test_hw_recoverable
[16:43:51] [PASSED] test_hw_corrected
[16:43:51] [PASSED] test_hw_informational
[16:43:51] =================== [PASSED] test_dmesg ====================
[16:43:51] ====================== test_invalid =======================
[16:43:51] [SKIPPED] no-component no-location no-warn (requires CONFIG_DRM_XE_DEBUG)
[16:43:51] [SKIPPED] reserved location (requires CONFIG_DRM_XE_DEBUG)
[16:43:51] [SKIPPED] unknown location (requires CONFIG_DRM_XE_DEBUG)
[16:43:51] [SKIPPED] nonzero-device-id location (requires CONFIG_DRM_XE_DEBUG)
[16:43:51] [SKIPPED] invalid-tile-id location (requires CONFIG_DRM_XE_DEBUG)
[16:43:51] [SKIPPED] invalid-gt-id location (requires CONFIG_DRM_XE_DEBUG)
[16:43:51] [SKIPPED] unknown component class (requires CONFIG_DRM_XE_DEBUG)
[16:43:51] [SKIPPED] unknown system component (requires CONFIG_DRM_XE_DEBUG)
[16:43:51] [SKIPPED] unknown hardware component (requires CONFIG_DRM_XE_DEBUG)
[16:43:51] [SKIPPED] unknown component and location (requires CONFIG_DRM_XE_DEBUG)
[16:43:51] ================== [SKIPPED] test_invalid ==================
[16:43:51] ===================== [PASSED] xe_log ======================
[16:43:51] ================== no_relay (3 subtests) ===================
[16:43:51] [PASSED] xe_drops_guc2pf_if_not_ready
[16:43:51] [PASSED] xe_drops_guc2vf_if_not_ready
[16:43:51] [PASSED] xe_rejects_send_if_not_ready
[16:43:51] ==================== [PASSED] no_relay =====================
[16:43:51] ================== pf_relay (14 subtests) ==================
[16:43:51] [PASSED] pf_rejects_guc2pf_too_short
[16:43:51] [PASSED] pf_rejects_guc2pf_too_long
[16:43:51] [PASSED] pf_rejects_guc2pf_no_payload
[16:43:51] [PASSED] pf_fails_no_payload
[16:43:51] [PASSED] pf_fails_bad_origin
[16:43:51] [PASSED] pf_fails_bad_type
[16:43:51] [PASSED] pf_txn_reports_error
[16:43:51] [PASSED] pf_txn_sends_pf2guc
[16:43:51] [PASSED] pf_sends_pf2guc
[16:43:51] [SKIPPED] pf_loopback_nop (requires CONFIG_DRM_XE_DEBUG_SRIOV)
[16:43:51] [SKIPPED] pf_loopback_echo (requires CONFIG_DRM_XE_DEBUG_SRIOV)
[16:43:51] [SKIPPED] pf_loopback_fail (requires CONFIG_DRM_XE_DEBUG_SRIOV)
[16:43:51] [SKIPPED] pf_loopback_busy (requires CONFIG_DRM_XE_DEBUG_SRIOV)
[16:43:51] [SKIPPED] pf_loopback_retry (requires CONFIG_DRM_XE_DEBUG_SRIOV)
[16:43:51] ==================== [PASSED] pf_relay =====================
[16:43:51] ================== vf_relay (3 subtests) ===================
[16:43:51] [PASSED] vf_rejects_guc2vf_too_short
[16:43:51] [PASSED] vf_rejects_guc2vf_too_long
[16:43:51] [PASSED] vf_rejects_guc2vf_no_payload
[16:43:51] ==================== [PASSED] vf_relay =====================
[16:43:51] ================ pf_gt_config (9 subtests) =================
[16:43:51] [PASSED] fair_contexts_1vf
[16:43:51] [PASSED] fair_doorbells_1vf
[16:43:51] [PASSED] fair_ggtt_1vf
[16:43:51] ====================== fair_vram_1vf ======================
[16:43:51] [PASSED] 3.50 GiB
[16:43:51] [PASSED] 11.5 GiB
[16:43:51] [PASSED] 15.5 GiB
[16:43:51] [PASSED] 31.5 GiB
[16:43:51] [PASSED] 63.5 GiB
[16:43:51] [PASSED] 1.91 GiB
[16:43:51] ================== [PASSED] fair_vram_1vf ==================
[16:43:51] ================ fair_vram_1vf_admin_only =================
[16:43:51] [PASSED] 3.50 GiB
[16:43:51] [PASSED] 11.5 GiB
[16:43:51] [PASSED] 15.5 GiB
[16:43:51] [PASSED] 31.5 GiB
[16:43:51] [PASSED] 63.5 GiB
[16:43:51] [PASSED] 1.91 GiB
[16:43:51] ============ [PASSED] fair_vram_1vf_admin_only =============
[16:43:51] ====================== fair_contexts ======================
[16:43:51] [PASSED] 1 VF
[16:43:51] [PASSED] 2 VFs
[16:43:51] [PASSED] 3 VFs
[16:43:51] [PASSED] 4 VFs
[16:43:51] [PASSED] 5 VFs
[16:43:51] [PASSED] 6 VFs
[16:43:51] [PASSED] 7 VFs
[16:43:51] [PASSED] 8 VFs
[16:43:51] [PASSED] 9 VFs
[16:43:51] [PASSED] 10 VFs
[16:43:51] [PASSED] 11 VFs
[16:43:51] [PASSED] 12 VFs
[16:43:51] [PASSED] 13 VFs
[16:43:51] [PASSED] 14 VFs
[16:43:51] [PASSED] 15 VFs
[16:43:51] [PASSED] 16 VFs
[16:43:51] [PASSED] 17 VFs
[16:43:51] [PASSED] 18 VFs
[16:43:51] [PASSED] 19 VFs
[16:43:51] [PASSED] 20 VFs
[16:43:51] [PASSED] 21 VFs
[16:43:51] [PASSED] 22 VFs
[16:43:51] [PASSED] 23 VFs
[16:43:51] [PASSED] 24 VFs
[16:43:51] [PASSED] 25 VFs
[16:43:51] [PASSED] 26 VFs
[16:43:51] [PASSED] 27 VFs
[16:43:51] [PASSED] 28 VFs
[16:43:51] [PASSED] 29 VFs
[16:43:51] [PASSED] 30 VFs
[16:43:51] [PASSED] 31 VFs
[16:43:51] [PASSED] 32 VFs
[16:43:51] [PASSED] 33 VFs
[16:43:51] [PASSED] 34 VFs
[16:43:51] [PASSED] 35 VFs
[16:43:51] [PASSED] 36 VFs
[16:43:51] [PASSED] 37 VFs
[16:43:51] [PASSED] 38 VFs
[16:43:51] [PASSED] 39 VFs
[16:43:51] [PASSED] 40 VFs
[16:43:51] [PASSED] 41 VFs
[16:43:51] [PASSED] 42 VFs
[16:43:51] [PASSED] 43 VFs
[16:43:51] [PASSED] 44 VFs
[16:43:51] [PASSED] 45 VFs
[16:43:51] [PASSED] 46 VFs
[16:43:51] [PASSED] 47 VFs
[16:43:51] [PASSED] 48 VFs
[16:43:51] [PASSED] 49 VFs
[16:43:51] [PASSED] 50 VFs
[16:43:51] [PASSED] 51 VFs
[16:43:51] [PASSED] 52 VFs
[16:43:51] [PASSED] 53 VFs
[16:43:51] [PASSED] 54 VFs
[16:43:51] [PASSED] 55 VFs
[16:43:51] [PASSED] 56 VFs
[16:43:51] [PASSED] 57 VFs
[16:43:51] [PASSED] 58 VFs
[16:43:51] [PASSED] 59 VFs
[16:43:51] [PASSED] 60 VFs
[16:43:51] [PASSED] 61 VFs
[16:43:51] [PASSED] 62 VFs
[16:43:51] [PASSED] 63 VFs
[16:43:51] ================== [PASSED] fair_contexts ==================
[16:43:51] ===================== fair_doorbells ======================
[16:43:51] [PASSED] 1 VF
[16:43:51] [PASSED] 2 VFs
[16:43:51] [PASSED] 3 VFs
[16:43:51] [PASSED] 4 VFs
[16:43:51] [PASSED] 5 VFs
[16:43:51] [PASSED] 6 VFs
[16:43:51] [PASSED] 7 VFs
[16:43:51] [PASSED] 8 VFs
[16:43:51] [PASSED] 9 VFs
[16:43:51] [PASSED] 10 VFs
[16:43:51] [PASSED] 11 VFs
[16:43:51] [PASSED] 12 VFs
[16:43:51] [PASSED] 13 VFs
[16:43:51] [PASSED] 14 VFs
[16:43:51] [PASSED] 15 VFs
[16:43:51] [PASSED] 16 VFs
[16:43:51] [PASSED] 17 VFs
[16:43:51] [PASSED] 18 VFs
[16:43:51] [PASSED] 19 VFs
[16:43:51] [PASSED] 20 VFs
[16:43:51] [PASSED] 21 VFs
[16:43:51] [PASSED] 22 VFs
[16:43:51] [PASSED] 23 VFs
[16:43:51] [PASSED] 24 VFs
[16:43:51] [PASSED] 25 VFs
[16:43:51] [PASSED] 26 VFs
[16:43:51] [PASSED] 27 VFs
[16:43:51] [PASSED] 28 VFs
[16:43:51] [PASSED] 29 VFs
[16:43:51] [PASSED] 30 VFs
[16:43:51] [PASSED] 31 VFs
[16:43:51] [PASSED] 32 VFs
[16:43:51] [PASSED] 33 VFs
[16:43:51] [PASSED] 34 VFs
[16:43:51] [PASSED] 35 VFs
[16:43:51] [PASSED] 36 VFs
[16:43:51] [PASSED] 37 VFs
[16:43:51] [PASSED] 38 VFs
[16:43:51] [PASSED] 39 VFs
[16:43:51] [PASSED] 40 VFs
[16:43:51] [PASSED] 41 VFs
[16:43:51] [PASSED] 42 VFs
[16:43:51] [PASSED] 43 VFs
[16:43:51] [PASSED] 44 VFs
[16:43:51] [PASSED] 45 VFs
[16:43:51] [PASSED] 46 VFs
[16:43:51] [PASSED] 47 VFs
[16:43:51] [PASSED] 48 VFs
[16:43:51] [PASSED] 49 VFs
[16:43:51] [PASSED] 50 VFs
[16:43:51] [PASSED] 51 VFs
[16:43:51] [PASSED] 52 VFs
[16:43:51] [PASSED] 53 VFs
[16:43:51] [PASSED] 54 VFs
[16:43:51] [PASSED] 55 VFs
[16:43:51] [PASSED] 56 VFs
[16:43:51] [PASSED] 57 VFs
[16:43:51] [PASSED] 58 VFs
[16:43:51] [PASSED] 59 VFs
[16:43:51] [PASSED] 60 VFs
[16:43:51] [PASSED] 61 VFs
[16:43:51] [PASSED] 62 VFs
[16:43:51] [PASSED] 63 VFs
[16:43:51] ================= [PASSED] fair_doorbells ==================
[16:43:51] ======================== fair_ggtt ========================
[16:43:51] [PASSED] 1 VF
[16:43:51] [PASSED] 2 VFs
[16:43:51] [PASSED] 3 VFs
[16:43:51] [PASSED] 4 VFs
[16:43:51] [PASSED] 5 VFs
[16:43:51] [PASSED] 6 VFs
[16:43:51] [PASSED] 7 VFs
[16:43:51] [PASSED] 8 VFs
[16:43:51] [PASSED] 9 VFs
[16:43:51] [PASSED] 10 VFs
[16:43:51] [PASSED] 11 VFs
[16:43:51] [PASSED] 12 VFs
[16:43:51] [PASSED] 13 VFs
[16:43:51] [PASSED] 14 VFs
[16:43:51] [PASSED] 15 VFs
[16:43:51] [PASSED] 16 VFs
[16:43:51] [PASSED] 17 VFs
[16:43:51] [PASSED] 18 VFs
[16:43:51] [PASSED] 19 VFs
[16:43:51] [PASSED] 20 VFs
[16:43:51] [PASSED] 21 VFs
[16:43:51] [PASSED] 22 VFs
[16:43:51] [PASSED] 23 VFs
[16:43:51] [PASSED] 24 VFs
[16:43:51] [PASSED] 25 VFs
[16:43:51] [PASSED] 26 VFs
[16:43:51] [PASSED] 27 VFs
[16:43:51] [PASSED] 28 VFs
[16:43:51] [PASSED] 29 VFs
[16:43:51] [PASSED] 30 VFs
[16:43:51] [PASSED] 31 VFs
[16:43:51] [PASSED] 32 VFs
[16:43:51] [PASSED] 33 VFs
[16:43:51] [PASSED] 34 VFs
[16:43:51] [PASSED] 35 VFs
[16:43:51] [PASSED] 36 VFs
[16:43:51] [PASSED] 37 VFs
[16:43:51] [PASSED] 38 VFs
[16:43:51] [PASSED] 39 VFs
[16:43:51] [PASSED] 40 VFs
[16:43:51] [PASSED] 41 VFs
[16:43:51] [PASSED] 42 VFs
[16:43:51] [PASSED] 43 VFs
[16:43:51] [PASSED] 44 VFs
[16:43:51] [PASSED] 45 VFs
[16:43:51] [PASSED] 46 VFs
[16:43:51] [PASSED] 47 VFs
[16:43:51] [PASSED] 48 VFs
[16:43:51] [PASSED] 49 VFs
[16:43:51] [PASSED] 50 VFs
[16:43:51] [PASSED] 51 VFs
[16:43:51] [PASSED] 52 VFs
[16:43:51] [PASSED] 53 VFs
[16:43:51] [PASSED] 54 VFs
[16:43:51] [PASSED] 55 VFs
[16:43:51] [PASSED] 56 VFs
[16:43:51] [PASSED] 57 VFs
[16:43:51] [PASSED] 58 VFs
[16:43:51] [PASSED] 59 VFs
[16:43:51] [PASSED] 60 VFs
[16:43:51] [PASSED] 61 VFs
[16:43:51] [PASSED] 62 VFs
[16:43:51] [PASSED] 63 VFs
[16:43:51] ==================== [PASSED] fair_ggtt ====================
[16:43:51] ======================== fair_vram ========================
[16:43:51] [PASSED] 1 VF
[16:43:51] [PASSED] 2 VFs
[16:43:51] [PASSED] 3 VFs
[16:43:51] [PASSED] 4 VFs
[16:43:51] [PASSED] 5 VFs
[16:43:51] [PASSED] 6 VFs
[16:43:51] [PASSED] 7 VFs
[16:43:51] [PASSED] 8 VFs
[16:43:51] [PASSED] 9 VFs
[16:43:51] [PASSED] 10 VFs
[16:43:51] [PASSED] 11 VFs
[16:43:51] [PASSED] 12 VFs
[16:43:51] [PASSED] 13 VFs
[16:43:51] [PASSED] 14 VFs
[16:43:51] [PASSED] 15 VFs
[16:43:51] [PASSED] 16 VFs
[16:43:51] [PASSED] 17 VFs
[16:43:51] [PASSED] 18 VFs
[16:43:51] [PASSED] 19 VFs
[16:43:51] [PASSED] 20 VFs
[16:43:51] [PASSED] 21 VFs
[16:43:51] [PASSED] 22 VFs
[16:43:51] [PASSED] 23 VFs
[16:43:51] [PASSED] 24 VFs
[16:43:51] [PASSED] 25 VFs
[16:43:51] [PASSED] 26 VFs
[16:43:51] [PASSED] 27 VFs
[16:43:51] [PASSED] 28 VFs
[16:43:51] [PASSED] 29 VFs
[16:43:51] [PASSED] 30 VFs
[16:43:51] [PASSED] 31 VFs
[16:43:51] [PASSED] 32 VFs
[16:43:51] [PASSED] 33 VFs
[16:43:51] [PASSED] 34 VFs
[16:43:51] [PASSED] 35 VFs
[16:43:51] [PASSED] 36 VFs
[16:43:51] [PASSED] 37 VFs
[16:43:51] [PASSED] 38 VFs
[16:43:51] [PASSED] 39 VFs
[16:43:51] [PASSED] 40 VFs
[16:43:51] [PASSED] 41 VFs
[16:43:51] [PASSED] 42 VFs
[16:43:51] [PASSED] 43 VFs
[16:43:51] [PASSED] 44 VFs
[16:43:51] [PASSED] 45 VFs
[16:43:51] [PASSED] 46 VFs
[16:43:51] [PASSED] 47 VFs
[16:43:51] [PASSED] 48 VFs
[16:43:51] [PASSED] 49 VFs
[16:43:51] [PASSED] 50 VFs
[16:43:51] [PASSED] 51 VFs
[16:43:51] [PASSED] 52 VFs
[16:43:51] [PASSED] 53 VFs
[16:43:51] [PASSED] 54 VFs
[16:43:51] [PASSED] 55 VFs
[16:43:51] [PASSED] 56 VFs
[16:43:51] [PASSED] 57 VFs
[16:43:51] [PASSED] 58 VFs
[16:43:51] [PASSED] 59 VFs
[16:43:51] [PASSED] 60 VFs
[16:43:51] [PASSED] 61 VFs
[16:43:51] [PASSED] 62 VFs
[16:43:51] [PASSED] 63 VFs
[16:43:51] ==================== [PASSED] fair_vram ====================
[16:43:51] ================== [PASSED] pf_gt_config ===================
[16:43:51] ===================== lmtt (1 subtest) =====================
[16:43:51] ======================== test_ops =========================
[16:43:51] [PASSED] 2-level
[16:43:51] [PASSED] multi-level
[16:43:51] ==================== [PASSED] test_ops =====================
[16:43:51] ====================== [PASSED] lmtt =======================
[16:43:51] ================= sriov_packet (1 subtest) =================
[16:43:51] [PASSED] test_descriptor_init
[16:43:51] ================== [PASSED] sriov_packet ===================
[16:43:51] ================= pf_service (11 subtests) =================
[16:43:51] [PASSED] pf_negotiate_any
[16:43:51] [PASSED] pf_negotiate_base_match
[16:43:51] [PASSED] pf_negotiate_base_newer
[16:43:51] [PASSED] pf_negotiate_base_next
[16:43:51] [SKIPPED] pf_negotiate_base_older (no older minor)
[16:43:51] [PASSED] pf_negotiate_base_prev
[16:43:51] [PASSED] pf_negotiate_latest_match
[16:43:51] [PASSED] pf_negotiate_latest_newer
[16:43:51] [PASSED] pf_negotiate_latest_next
[16:43:51] [SKIPPED] pf_negotiate_latest_older (no older minor)
[16:43:51] [SKIPPED] pf_negotiate_latest_prev (no prev major)
[16:43:51] =================== [PASSED] pf_service ====================
[16:43:51] ================= xe_guc_g2g (2 subtests) ==================
[16:43:51] ============== xe_live_guc_g2g_kunit_default ==============
[16:43:51] ========= [SKIPPED] xe_live_guc_g2g_kunit_default ==========
[16:43:51] ============== xe_live_guc_g2g_kunit_allmem ===============
[16:43:51] ========== [SKIPPED] xe_live_guc_g2g_kunit_allmem ==========
[16:43:51] =================== [SKIPPED] xe_guc_g2g ===================
[16:43:51] =================== xe_mocs (2 subtests) ===================
[16:43:51] ================ xe_live_mocs_kernel_kunit ================
[16:43:51] =========== [SKIPPED] xe_live_mocs_kernel_kunit ============
[16:43:51] ================ xe_live_mocs_reset_kunit =================
[16:43:51] ============ [SKIPPED] xe_live_mocs_reset_kunit ============
[16:43:51] ==================== [SKIPPED] xe_mocs =====================
[16:43:51] ================= xe_migrate (2 subtests) ==================
[16:43:51] ================= xe_migrate_sanity_kunit =================
[16:43:51] ============ [SKIPPED] xe_migrate_sanity_kunit =============
[16:43:51] ================== xe_validate_ccs_kunit ==================
[16:43:51] ============= [SKIPPED] xe_validate_ccs_kunit ==============
[16:43:51] =================== [SKIPPED] xe_migrate ===================
[16:43:51] ================== xe_dma_buf (1 subtest) ==================
[16:43:51] ==================== xe_dma_buf_kunit =====================
[16:43:51] ================ [SKIPPED] xe_dma_buf_kunit ================
[16:43:51] =================== [SKIPPED] xe_dma_buf ===================
[16:43:51] ================= xe_bo_shrink (1 subtest) =================
[16:43:51] =================== xe_bo_shrink_kunit ====================
[16:43:51] =============== [SKIPPED] xe_bo_shrink_kunit ===============
[16:43:51] ================== [SKIPPED] xe_bo_shrink ==================
[16:43:51] ==================== xe_bo (2 subtests) ====================
[16:43:51] ================== xe_ccs_migrate_kunit ===================
[16:43:51] ============== [SKIPPED] xe_ccs_migrate_kunit ==============
[16:43:51] ==================== xe_bo_evict_kunit ====================
[16:43:51] =============== [SKIPPED] xe_bo_evict_kunit ================
[16:43:51] ===================== [SKIPPED] xe_bo ======================
[16:43:51] =================== xe_any (9 subtests) ====================
[16:43:51] [PASSED] test_to_xe
[16:43:51] [PASSED] test_to_dev
[16:43:51] [PASSED] test_to_pdev
[16:43:51] [PASSED] test_to_drm
[16:43:51] [PASSED] test_if_pdev
[16:43:51] [PASSED] test_if_xe
[16:43:51] [PASSED] test_if_tile
[16:43:51] [PASSED] test_if_gt
[16:43:51] [PASSED] test_to_id
[16:43:51] ===================== [PASSED] xe_any ======================
[16:43:51] ==================== args (13 subtests) ====================
[16:43:51] [PASSED] count_args_test
[16:43:51] [PASSED] call_args_example
[16:43:51] [PASSED] call_args_test
[16:43:51] [PASSED] drop_first_arg_example
[16:43:51] [PASSED] drop_first_arg_test
[16:43:51] [PASSED] first_arg_example
[16:43:51] [PASSED] first_arg_test
[16:43:51] [PASSED] last_arg_example
[16:43:51] [PASSED] last_arg_test
[16:43:51] [PASSED] pick_arg_example
[16:43:51] [PASSED] if_args_example
[16:43:51] [PASSED] if_args_test
[16:43:51] [PASSED] sep_comma_example
[16:43:51] ====================== [PASSED] args =======================
[16:43:51] =================== xe_pci (3 subtests) ====================
[16:43:51] ==================== check_graphics_ip ====================
[16:43:51] [PASSED] 12.00 Xe_LP
[16:43:51] [PASSED] 12.10 Xe_LP+
[16:43:51] [PASSED] 12.55 Xe_HPG
[16:43:51] [PASSED] 12.60 Xe_HPC
[16:43:51] [PASSED] 12.70 Xe_LPG
[16:43:51] [PASSED] 12.71 Xe_LPG
[16:43:51] [PASSED] 12.74 Xe_LPG+
[16:43:51] [PASSED] 20.01 Xe2_HPG
[16:43:51] [PASSED] 20.02 Xe2_HPG
[16:43:51] [PASSED] 20.04 Xe2_LPG
[16:43:51] [PASSED] 30.00 Xe3_LPG
[16:43:51] [PASSED] 30.01 Xe3_LPG
[16:43:51] [PASSED] 30.03 Xe3_LPG
[16:43:51] [PASSED] 30.04 Xe3_LPG
[16:43:51] [PASSED] 30.05 Xe3_LPG
[16:43:51] [PASSED] 35.10 Xe3p_LPG
[16:43:51] [PASSED] 35.11 Xe3p_XPC
[16:43:51] ================ [PASSED] check_graphics_ip ================
[16:43:51] ===================== check_media_ip ======================
[16:43:51] [PASSED] 12.00 Xe_M
[16:43:51] [PASSED] 12.55 Xe_HPM
[16:43:51] [PASSED] 13.00 Xe_LPM+
[16:43:51] [PASSED] 13.01 Xe2_HPM
[16:43:51] [PASSED] 20.00 Xe2_LPM
[16:43:51] [PASSED] 30.00 Xe3_LPM
[16:43:51] [PASSED] 30.02 Xe3_LPM
[16:43:51] [PASSED] 35.00 Xe3p_LPM
[16:43:51] [PASSED] 35.03 Xe3p_HPM
[16:43:51] ================= [PASSED] check_media_ip ==================
[16:43:51] =================== check_platform_desc ===================
[16:43:51] [PASSED] 0x9A60 (TIGERLAKE)
[16:43:51] [PASSED] 0x9A68 (TIGERLAKE)
[16:43:51] [PASSED] 0x9A70 (TIGERLAKE)
[16:43:51] [PASSED] 0x9A40 (TIGERLAKE)
[16:43:51] [PASSED] 0x9A49 (TIGERLAKE)
[16:43:51] [PASSED] 0x9A59 (TIGERLAKE)
[16:43:51] [PASSED] 0x9A78 (TIGERLAKE)
[16:43:51] [PASSED] 0x9AC0 (TIGERLAKE)
[16:43:51] [PASSED] 0x9AC9 (TIGERLAKE)
[16:43:51] [PASSED] 0x9AD9 (TIGERLAKE)
[16:43:51] [PASSED] 0x9AF8 (TIGERLAKE)
[16:43:51] [PASSED] 0x4C80 (ROCKETLAKE)
[16:43:51] [PASSED] 0x4C8A (ROCKETLAKE)
[16:43:51] [PASSED] 0x4C8B (ROCKETLAKE)
[16:43:51] [PASSED] 0x4C8C (ROCKETLAKE)
[16:43:51] [PASSED] 0x4C90 (ROCKETLAKE)
[16:43:51] [PASSED] 0x4C9A (ROCKETLAKE)
[16:43:51] [PASSED] 0x4680 (ALDERLAKE_S)
[16:43:51] [PASSED] 0x4682 (ALDERLAKE_S)
[16:43:51] [PASSED] 0x4688 (ALDERLAKE_S)
[16:43:51] [PASSED] 0x468A (ALDERLAKE_S)
[16:43:51] [PASSED] 0x468B (ALDERLAKE_S)
[16:43:51] [PASSED] 0x4690 (ALDERLAKE_S)
[16:43:51] [PASSED] 0x4692 (ALDERLAKE_S)
[16:43:51] [PASSED] 0x4693 (ALDERLAKE_S)
[16:43:51] [PASSED] 0x46A0 (ALDERLAKE_P)
[16:43:51] [PASSED] 0x46A1 (ALDERLAKE_P)
[16:43:51] [PASSED] 0x46A2 (ALDERLAKE_P)
[16:43:51] [PASSED] 0x46A3 (ALDERLAKE_P)
[16:43:51] [PASSED] 0x46A6 (ALDERLAKE_P)
[16:43:51] [PASSED] 0x46A8 (ALDERLAKE_P)
[16:43:51] [PASSED] 0x46AA (ALDERLAKE_P)
[16:43:51] [PASSED] 0x462A (ALDERLAKE_P)
[16:43:51] [PASSED] 0x4626 (ALDERLAKE_P)
[16:43:51] [PASSED] 0x4628 (ALDERLAKE_P)
[16:43:51] [PASSED] 0x46B0 (ALDERLAKE_P)
[16:43:51] [PASSED] 0x46B1 (ALDERLAKE_P)
[16:43:51] [PASSED] 0x46B2 (ALDERLAKE_P)
[16:43:51] [PASSED] 0x46B3 (ALDERLAKE_P)
[16:43:51] [PASSED] 0x46C0 (ALDERLAKE_P)
[16:43:51] [PASSED] 0x46C1 (ALDERLAKE_P)
[16:43:51] [PASSED] 0x46C2 (ALDERLAKE_P)
[16:43:51] [PASSED] 0x46C3 (ALDERLAKE_P)
[16:43:51] [PASSED] 0x46D0 (ALDERLAKE_N)
[16:43:51] [PASSED] 0x46D1 (ALDERLAKE_N)
[16:43:51] [PASSED] 0x46D2 (ALDERLAKE_N)
[16:43:51] [PASSED] 0x46D3 (ALDERLAKE_N)
[16:43:51] [PASSED] 0x46D4 (ALDERLAKE_N)
[16:43:51] [PASSED] 0xA721 (ALDERLAKE_P)
[16:43:51] [PASSED] 0xA7A1 (ALDERLAKE_P)
[16:43:51] [PASSED] 0xA7A9 (ALDERLAKE_P)
[16:43:51] [PASSED] 0xA7AC (ALDERLAKE_P)
[16:43:51] [PASSED] 0xA7AD (ALDERLAKE_P)
[16:43:51] [PASSED] 0xA720 (ALDERLAKE_P)
[16:43:51] [PASSED] 0xA7A0 (ALDERLAKE_P)
[16:43:51] [PASSED] 0xA7A8 (ALDERLAKE_P)
[16:43:51] [PASSED] 0xA7AA (ALDERLAKE_P)
[16:43:51] [PASSED] 0xA7AB (ALDERLAKE_P)
[16:43:51] [PASSED] 0xA780 (ALDERLAKE_S)
[16:43:51] [PASSED] 0xA781 (ALDERLAKE_S)
[16:43:51] [PASSED] 0xA782 (ALDERLAKE_S)
[16:43:51] [PASSED] 0xA783 (ALDERLAKE_S)
[16:43:51] [PASSED] 0xA788 (ALDERLAKE_S)
[16:43:51] [PASSED] 0xA789 (ALDERLAKE_S)
[16:43:51] [PASSED] 0xA78A (ALDERLAKE_S)
[16:43:51] [PASSED] 0xA78B (ALDERLAKE_S)
[16:43:51] [PASSED] 0x4905 (DG1)
[16:43:51] [PASSED] 0x4906 (DG1)
[16:43:51] [PASSED] 0x4907 (DG1)
[16:43:51] [PASSED] 0x4908 (DG1)
[16:43:51] [PASSED] 0x4909 (DG1)
[16:43:51] [PASSED] 0x56C0 (DG2)
[16:43:51] [PASSED] 0x56C2 (DG2)
[16:43:51] [PASSED] 0x56C1 (DG2)
[16:43:51] [PASSED] 0x7D51 (METEORLAKE)
[16:43:51] [PASSED] 0x7DD1 (METEORLAKE)
[16:43:51] [PASSED] 0x7D41 (METEORLAKE)
[16:43:51] [PASSED] 0x7D67 (METEORLAKE)
[16:43:51] [PASSED] 0xB640 (METEORLAKE)
[16:43:51] [PASSED] 0x56A0 (DG2)
[16:43:51] [PASSED] 0x56A1 (DG2)
[16:43:51] [PASSED] 0x56A2 (DG2)
[16:43:51] [PASSED] 0x56BE (DG2)
[16:43:51] [PASSED] 0x56BF (DG2)
[16:43:51] [PASSED] 0x5690 (DG2)
[16:43:51] [PASSED] 0x5691 (DG2)
[16:43:51] [PASSED] 0x5692 (DG2)
[16:43:51] [PASSED] 0x56A5 (DG2)
[16:43:51] [PASSED] 0x56A6 (DG2)
[16:43:51] [PASSED] 0x56B0 (DG2)
[16:43:51] [PASSED] 0x56B1 (DG2)
[16:43:51] [PASSED] 0x56BA (DG2)
[16:43:51] [PASSED] 0x56BB (DG2)
[16:43:51] [PASSED] 0x56BC (DG2)
[16:43:51] [PASSED] 0x56BD (DG2)
[16:43:51] [PASSED] 0x5693 (DG2)
[16:43:51] [PASSED] 0x5694 (DG2)
[16:43:51] [PASSED] 0x5695 (DG2)
[16:43:51] [PASSED] 0x56A3 (DG2)
[16:43:51] [PASSED] 0x56A4 (DG2)
[16:43:51] [PASSED] 0x56B2 (DG2)
[16:43:51] [PASSED] 0x56B3 (DG2)
[16:43:51] [PASSED] 0x5696 (DG2)
[16:43:51] [PASSED] 0x5697 (DG2)
[16:43:51] [PASSED] 0xB69 (PVC)
[16:43:51] [PASSED] 0xB6E (PVC)
[16:43:51] [PASSED] 0xBD4 (PVC)
[16:43:51] [PASSED] 0xBD5 (PVC)
[16:43:51] [PASSED] 0xBD6 (PVC)
[16:43:51] [PASSED] 0xBD7 (PVC)
[16:43:51] [PASSED] 0xBD8 (PVC)
[16:43:51] [PASSED] 0xBD9 (PVC)
[16:43:51] [PASSED] 0xBDA (PVC)
[16:43:51] [PASSED] 0xBDB (PVC)
[16:43:51] [PASSED] 0xBE0 (PVC)
[16:43:51] [PASSED] 0xBE1 (PVC)
[16:43:51] [PASSED] 0xBE5 (PVC)
[16:43:51] [PASSED] 0x7D40 (METEORLAKE)
[16:43:51] [PASSED] 0x7D45 (METEORLAKE)
[16:43:51] [PASSED] 0x7D55 (METEORLAKE)
[16:43:51] [PASSED] 0x7D60 (METEORLAKE)
[16:43:51] [PASSED] 0x7DD5 (METEORLAKE)
[16:43:51] [PASSED] 0x6420 (LUNARLAKE)
[16:43:51] [PASSED] 0x64A0 (LUNARLAKE)
[16:43:51] [PASSED] 0x64B0 (LUNARLAKE)
[16:43:51] [PASSED] 0xE202 (BATTLEMAGE)
[16:43:51] [PASSED] 0xE209 (BATTLEMAGE)
[16:43:51] [PASSED] 0xE20B (BATTLEMAGE)
[16:43:51] [PASSED] 0xE20C (BATTLEMAGE)
[16:43:51] [PASSED] 0xE20D (BATTLEMAGE)
[16:43:51] [PASSED] 0xE210 (BATTLEMAGE)
[16:43:51] [PASSED] 0xE211 (BATTLEMAGE)
[16:43:51] [PASSED] 0xE212 (BATTLEMAGE)
[16:43:51] [PASSED] 0xE216 (BATTLEMAGE)
[16:43:51] [PASSED] 0xE220 (BATTLEMAGE)
[16:43:51] [PASSED] 0xE221 (BATTLEMAGE)
[16:43:51] [PASSED] 0xE222 (BATTLEMAGE)
[16:43:51] [PASSED] 0xE223 (BATTLEMAGE)
[16:43:51] [PASSED] 0xB080 (PANTHERLAKE)
[16:43:51] [PASSED] 0xB081 (PANTHERLAKE)
[16:43:51] [PASSED] 0xB082 (PANTHERLAKE)
[16:43:51] [PASSED] 0xB083 (PANTHERLAKE)
[16:43:51] [PASSED] 0xB084 (PANTHERLAKE)
[16:43:51] [PASSED] 0xB085 (PANTHERLAKE)
[16:43:51] [PASSED] 0xB086 (PANTHERLAKE)
[16:43:51] [PASSED] 0xB087 (PANTHERLAKE)
[16:43:51] [PASSED] 0xB08F (PANTHERLAKE)
[16:43:51] [PASSED] 0xB090 (PANTHERLAKE)
[16:43:51] [PASSED] 0xB0A0 (PANTHERLAKE)
[16:43:51] [PASSED] 0xB0B0 (PANTHERLAKE)
[16:43:51] [PASSED] 0xFD80 (PANTHERLAKE)
[16:43:51] [PASSED] 0xFD81 (PANTHERLAKE)
[16:43:51] [PASSED] 0xD740 (NOVALAKE_S)
[16:43:51] [PASSED] 0xD741 (NOVALAKE_S)
[16:43:51] [PASSED] 0xD742 (NOVALAKE_S)
[16:43:51] [PASSED] 0xD743 (NOVALAKE_S)
[16:43:51] [PASSED] 0xD745 (NOVALAKE_S)
[16:43:51] [PASSED] 0xD74A (NOVALAKE_S)
[16:43:51] [PASSED] 0xD74B (NOVALAKE_S)
[16:43:51] [PASSED] 0x674C (CRESCENTISLAND)
[16:43:51] [PASSED] 0x674D (CRESCENTISLAND)
[16:43:51] [PASSED] 0x674E (CRESCENTISLAND)
[16:43:51] [PASSED] 0x674F (CRESCENTISLAND)
[16:43:51] [PASSED] 0x6750 (CRESCENTISLAND)
[16:43:51] [PASSED] 0xD750 (NOVALAKE_P)
[16:43:51] [PASSED] 0xD751 (NOVALAKE_P)
[16:43:51] [PASSED] 0xD752 (NOVALAKE_P)
[16:43:51] [PASSED] 0xD753 (NOVALAKE_P)
[16:43:51] [PASSED] 0xD754 (NOVALAKE_P)
[16:43:51] [PASSED] 0xD755 (NOVALAKE_P)
[16:43:51] [PASSED] 0xD756 (NOVALAKE_P)
[16:43:51] [PASSED] 0xD757 (NOVALAKE_P)
[16:43:51] [PASSED] 0xD75F (NOVALAKE_P)
[16:43:51] =============== [PASSED] check_platform_desc ===============
[16:43:51] ===================== [PASSED] xe_pci ======================
[16:43:51] ============= xe_rtp_tables_test (5 subtests) ==============
[16:43:51] ================== xe_rtp_table_gt_test ===================
[16:43:51] [PASSED] gt_was/14011060649
[16:43:51] [PASSED] gt_was/14011059788
[16:43:51] [PASSED] gt_was/14015795083
[16:43:51] [PASSED] gt_was/16021867713
[16:43:51] [PASSED] gt_was/14019449301
[16:43:51] [PASSED] gt_was/16028005424
[16:43:51] [PASSED] gt_was/14026578760
[16:43:51] [PASSED] gt_was/1409420604
[16:43:51] [PASSED] gt_was/1408615072
[16:43:51] [PASSED] gt_was/22010523718
[16:43:51] [PASSED] gt_was/14011006942
[16:43:51] [PASSED] gt_was/14014830051
[16:43:51] [PASSED] gt_was/18018781329
[16:43:51] [PASSED] gt_was/1509235366
[16:43:51] [PASSED] gt_was/18018781329
[16:43:51] [PASSED] gt_was/16016694945
[16:43:51] [PASSED] gt_was/14018575942
[16:43:51] [PASSED] gt_was/22016670082
[16:43:51] [PASSED] gt_was/22016670082
[16:43:51] [PASSED] gt_was/14017421178
[16:43:51] [PASSED] gt_was/16025250150
[16:43:51] [PASSED] gt_was/14021871409
[16:43:51] [PASSED] gt_was/16021865536
[16:43:51] [PASSED] gt_was/14021486841
[16:43:51] [PASSED] gt_was/14025160223
[16:43:51] [PASSED] gt_was/14026144927, 16029437861, 14026127056
[16:43:51] [PASSED] gt_was/14025635424
[16:43:51] [PASSED] gt_was/16028005424
[16:43:51] ============== [PASSED] xe_rtp_table_gt_test ===============
[16:43:51] ================== xe_rtp_table_gt_test ===================
[16:43:51] [PASSED] gt_tunings/Tuning: Blend Fill Caching Optimization Disable
[16:43:51] [PASSED] gt_tunings/Tuning: 32B Access Enable
[16:43:51] [PASSED] gt_tunings/Tuning: L3 cache
[16:43:51] [PASSED] gt_tunings/Tuning: L3 cache - media
[16:43:51] [PASSED] gt_tunings/Tuning: Compression Overfetch
[16:43:51] [PASSED] gt_tunings/Tuning: Compression Overfetch - media
[16:43:51] [PASSED] gt_tunings/Tuning: Enable compressible partial write overfetch in L3
[16:43:51] [PASSED] gt_tunings/Tuning: Enable compressible partial write overfetch in L3 - media
[16:43:51] [PASSED] gt_tunings/Tuning: L2 Overfetch Compressible Only
[16:43:51] [PASSED] gt_tunings/Tuning: L2 Overfetch Compressible Only - media
[16:43:51] [PASSED] gt_tunings/Tuning: Stateless compression control
[16:43:51] [PASSED] gt_tunings/Tuning: Stateless compression control - media
[16:43:51] [PASSED] gt_tunings/Tuning: L3 RW flush all Cache
[16:43:51] [PASSED] gt_tunings/Tuning: L3 RW flush all cache - media
[16:43:51] [PASSED] gt_tunings/Tuning: Set STLB Bank Hash Mode to 4KB
[16:43:51] ============== [PASSED] xe_rtp_table_gt_test ===============
[16:43:51] ================== xe_rtp_table_oob_test ==================
[16:43:51] [PASSED] oob_was/1607983814
[16:43:51] [PASSED] oob_was/16010904313
[16:43:51] [PASSED] oob_was/18022495364
[16:43:51] [PASSED] oob_was/22012773006
[16:43:51] [PASSED] oob_was/14014475959
[16:43:51] [PASSED] oob_was/22011391025
[16:43:51] [PASSED] oob_was/22012727170
[16:43:51] [PASSED] oob_was/22012727685
[16:43:51] [PASSED] oob_was/22016596838
[16:43:51] [PASSED] oob_was/18020744125
[16:43:51] [PASSED] oob_was/1409600907
[16:43:51] [PASSED] oob_was/22014953428
[16:43:51] [PASSED] oob_was/16017236439
[16:43:51] [PASSED] oob_was/14019821291
[16:43:51] [PASSED] oob_was/14015076503
[16:43:51] [PASSED] oob_was/22016122933
[16:43:51] [PASSED] oob_was/14018913170
[16:43:51] [PASSED] oob_was/14018094691
[16:43:51] [PASSED] oob_was/18024947630
[16:43:51] [PASSED] oob_was/16022287689
[16:43:51] [PASSED] oob_was/13011645652
[16:43:51] [PASSED] oob_was/14022293748
[16:43:51] [PASSED] oob_was/22019794406
[16:43:51] [PASSED] oob_was/22019338487
[16:43:51] [PASSED] oob_was/16023588340
[16:43:51] [PASSED] oob_was/14019789679
[16:43:51] [PASSED] oob_was/14022866841
[16:43:51] [PASSED] oob_was/16021333562
[16:43:51] [PASSED] oob_was/14016712196
[16:43:51] [PASSED] oob_was/14015568240
[16:43:51] [PASSED] oob_was/18013179988
[16:43:51] [PASSED] oob_was/1508761755
[16:43:51] [PASSED] oob_was/16023105232
[16:43:51] [PASSED] oob_was/16026508708
[16:43:51] [PASSED] oob_was/14020001231
[16:43:51] [PASSED] oob_was/16023683509
[16:43:51] [PASSED] oob_was/14025515070
[16:43:51] [PASSED] oob_was/15015404425_disable
[16:43:51] [PASSED] oob_was/16026007364
[16:43:51] [PASSED] oob_was/14020316580
[16:43:51] [PASSED] oob_was/14025883347
[16:43:51] [PASSED] oob_was/16029380221
[16:43:51] [PASSED] oob_was/22022079272
[16:43:51] [PASSED] oob_was/16029897822
[16:43:51] [PASSED] oob_was/14027054324
[16:43:51] ============== [PASSED] xe_rtp_table_oob_test ==============
[16:43:51] ================ xe_rtp_table_dev_oob_test ================
[16:43:51] [PASSED] device_oob_was/22010954014
[16:43:51] [PASSED] device_oob_was/15015404425
[16:43:51] [PASSED] device_oob_was/22019338487_display
[16:43:51] [PASSED] device_oob_was/14022085890
[16:43:51] [PASSED] device_oob_was/14026539277
[16:43:51] [PASSED] device_oob_was/14026633728
[16:43:51] [PASSED] device_oob_was/14026746987
[16:43:51] [PASSED] device_oob_was/14026779378
[16:43:51] ============ [PASSED] xe_rtp_table_dev_oob_test ============
[16:43:51] ========== xe_rtp_table_missing_upper_bound_test ==========
[16:43:51] [PASSED] register_whitelist/WaAllowPMDepthAndInvocationCountAccessFromUMD, 1408556865
[16:43:51] [PASSED] register_whitelist/1508744258, 14012131227, 1808121037
[16:43:51] [PASSED] register_whitelist/1806527549
[16:43:51] [PASSED] register_whitelist/allow_read_ctx_timestamp
[16:43:51] [PASSED] register_whitelist/allow_read_queue_timestamp
[16:43:51] [PASSED] register_whitelist/16014440446
[16:43:51] [PASSED] register_whitelist/16017236439
[16:43:51] [PASSED] register_whitelist/16020183090
[16:43:51] [PASSED] register_whitelist/14024997852
[16:43:51] [PASSED] register_whitelist/14024997852
[16:43:51] ====== [PASSED] xe_rtp_table_missing_upper_bound_test ======
[16:43:51] =============== [PASSED] xe_rtp_tables_test ================
[16:43:51] =================== xe_rtp (3 subtests) ====================
[16:43:51] =================== xe_rtp_rules_tests ====================
[16:43:51] [PASSED] no
[16:43:51] [PASSED] yes
[16:43:51] [PASSED] no-and-no
[16:43:51] [PASSED] no-and-yes
[16:43:51] [PASSED] yes-and-no
[16:43:51] [PASSED] yes-and-yes
[16:43:51] [PASSED] no-or-no
[16:43:51] [PASSED] no-or-yes
[16:43:51] [PASSED] yes-or-no
[16:43:51] [PASSED] yes-or-yes
[16:43:51] [PASSED] no-yes-or-yes-no
[16:43:51] [PASSED] no-yes-or-yes-yes
[16:43:51] [PASSED] yes-yes-or-no-yes
[16:43:51] [PASSED] yes-yes-or-yes-yes
[16:43:51] [PASSED] no-no-or-yes-or-no
[16:43:51] [PASSED] or
[16:43:51] [PASSED] or-yes
[16:43:51] [PASSED] or-no
[16:43:51] [PASSED] yes-or
[16:43:51] [PASSED] no-or
[16:43:51] [PASSED] no-or-or-yes
[16:43:51] [PASSED] yes-or-or-no
[16:43:51] [PASSED] no-or-or-no
[16:43:51] [PASSED] missing-context-engine-class
[16:43:51] [PASSED] missing-context-engine-class-or-yes
[16:43:51] [PASSED] missing-context-engine-class-or-or-yes
[16:43:51] =============== [PASSED] xe_rtp_rules_tests ================
[16:43:51] =============== xe_rtp_process_to_sr_tests ================
[16:43:51] [PASSED] coalesce-same-reg
[16:43:51] [PASSED] coalesce-same-reg-literal-and-func
[16:43:51] [PASSED] no-match-no-add
[16:43:51] [PASSED] two-regs-two-entries
[16:43:51] [PASSED] clr-one-set-other
[16:43:51] [PASSED] set-field
[16:43:51] [PASSED] conflict-duplicate
[16:43:51] [PASSED] conflict-not-disjoint
[16:43:51] [PASSED] conflict-not-disjoint-literal-and-func
[16:43:51] [PASSED] conflict-reg-type
[16:43:51] [PASSED] bad-mcr-reg-forced-to-regular
[16:43:51] [PASSED] bad-regular-reg-forced-to-mcr
[16:43:51] =========== [PASSED] xe_rtp_process_to_sr_tests ============
[16:43:51] ================== xe_rtp_process_tests ===================
[16:43:51] [PASSED] active1
[16:43:51] [PASSED] active2
[16:43:51] [PASSED] active-inactive
[16:43:51] [PASSED] inactive-active
[16:43:51] [PASSED] inactive-active-inactive
[16:43:51] [PASSED] inactive-inactive-inactive
[16:43:51] ============== [PASSED] xe_rtp_process_tests ===============
[16:43:51] ===================== [PASSED] xe_rtp ======================
[16:43:51] ==================== xe_wa (1 subtest) =====================
[16:43:51] ======================== xe_wa_gt =========================
[16:43:51] [PASSED] TIGERLAKE B0
[16:43:51] [PASSED] DG1 A0
[16:43:51] [PASSED] DG1 B0
[16:43:51] [PASSED] ALDERLAKE_S A0
[16:43:51] [PASSED] ALDERLAKE_S B0
[16:43:51] [PASSED] ALDERLAKE_S C0
[16:43:51] [PASSED] ALDERLAKE_S D0
[16:43:51] [PASSED] ALDERLAKE_P A0
[16:43:51] [PASSED] ALDERLAKE_P B0
[16:43:51] [PASSED] ALDERLAKE_P C0
[16:43:51] [PASSED] ALDERLAKE_S RPLS D0
[16:43:51] [PASSED] ALDERLAKE_P RPLU E0
[16:43:51] [PASSED] DG2 G10 C0
[16:43:51] [PASSED] DG2 G11 B1
[16:43:51] [PASSED] DG2 G12 A1
[16:43:51] [PASSED] METEORLAKE 12.70(Xe_LPG) A0 13.00(Xe_LPM+) A0
[16:43:51] [PASSED] METEORLAKE 12.71(Xe_LPG) A0 13.00(Xe_LPM+) A0
[16:43:51] [PASSED] METEORLAKE 12.74(Xe_LPG+) A0 13.00(Xe_LPM+) A0
[16:43:51] [PASSED] LUNARLAKE 20.04(Xe2_LPG) A0 20.00(Xe2_LPM) A0
[16:43:51] [PASSED] LUNARLAKE 20.04(Xe2_LPG) B0 20.00(Xe2_LPM) A0
[16:43:51] [PASSED] BATTLEMAGE 20.01(Xe2_HPG) A0 13.01(Xe2_HPM) A1
[16:43:51] [PASSED] PANTHERLAKE 30.00(Xe3_LPG) A0 30.00(Xe3_LPM) A0
[16:43:51] ==================== [PASSED] xe_wa_gt =====================
[16:43:51] ====================== [PASSED] xe_wa ======================
[16:43:51] ============================================================
[16:43:51] Testing complete. Ran 794 tests: passed: 766, skipped: 28
[16:43:51] Elapsed time: 36.104s total, 1.872s configuring, 33.516s building, 0.704s running
+ for kcfg in "${kunitconfigs[@]}"
+ [[ ! -f /kernel/drivers/gpu/drm/tests/.kunitconfig ]]
+ /kernel/tools/testing/kunit/kunit.py run --kunitconfig /kernel/drivers/gpu/drm/tests/.kunitconfig
[16:43:51] Configuring KUnit Kernel ...
Regenerating .config ...
Populating config with:
$ make ARCH=um O=.kunit olddefconfig
[16:43:53] Building KUnit Kernel ...
Populating config with:
$ make ARCH=um O=.kunit olddefconfig
Building with:
$ make all compile_commands.json scripts_gdb ARCH=um O=.kunit --jobs=48
[16:44:18] Starting KUnit Kernel (1/1)...
[16:44:18] ============================================================
Running tests with:
$ .kunit/linux kunit.enable=1 mem=1G console=tty kunit_shutdown=halt
[16:44:18] ============= refcount_interrupt (4 subtests) ==============
[16:44:18] [PASSED] test_single_irq_change
[16:44:18] [PASSED] test_nested_irq_change
[16:44:18] [PASSED] test_multiple_irq_change
[16:44:18] [PASSED] test_irq_save
[16:44:18] =============== [PASSED] refcount_interrupt ================
[16:44:18] ============ drm_test_pick_cmdline (2 subtests) ============
[16:44:18] [PASSED] drm_test_pick_cmdline_res_1920_1080_60
[16:44:18] =============== drm_test_pick_cmdline_named ===============
[16:44:18] [PASSED] NTSC
[16:44:18] [PASSED] NTSC-J
[16:44:18] [PASSED] PAL
[16:44:18] [PASSED] PAL-M
[16:44:18] =========== [PASSED] drm_test_pick_cmdline_named ===========
[16:44:18] ============== [PASSED] drm_test_pick_cmdline ==============
[16:44:18] == drm_test_atomic_get_connector_for_encoder (1 subtest) ===
[16:44:18] [PASSED] drm_test_drm_atomic_get_connector_for_encoder
[16:44:18] ==== [PASSED] drm_test_atomic_get_connector_for_encoder ====
[16:44:18] =========== drm_validate_clone_mode (2 subtests) ===========
[16:44:18] ============== drm_test_check_in_clone_mode ===============
[16:44:18] [PASSED] in_clone_mode
[16:44:18] [PASSED] not_in_clone_mode
[16:44:18] ========== [PASSED] drm_test_check_in_clone_mode ===========
[16:44:18] =============== drm_test_check_valid_clones ===============
[16:44:18] [PASSED] not_in_clone_mode
[16:44:18] [PASSED] valid_clone
[16:44:18] [PASSED] invalid_clone
[16:44:18] =========== [PASSED] drm_test_check_valid_clones ===========
[16:44:18] ============= [PASSED] drm_validate_clone_mode =============
[16:44:18] ============= drm_validate_modeset (1 subtest) =============
[16:44:18] [PASSED] drm_test_check_connector_changed_modeset
[16:44:18] ============== [PASSED] drm_validate_modeset ===============
[16:44:18] ====== drm_test_bridge_get_current_state (1 subtest) =======
[16:44:18] [PASSED] drm_test_drm_bridge_get_current_state_atomic
[16:44:18] ======== [PASSED] drm_test_bridge_get_current_state ========
[16:44:18] ====== drm_test_bridge_helper_reset_crtc (3 subtests) ======
[16:44:18] [PASSED] drm_test_drm_bridge_helper_reset_crtc_atomic
[16:44:18] [PASSED] drm_test_drm_bridge_helper_reset_crtc_atomic_disabled
[16:44:18] [PASSED] drm_test_drm_bridge_helper_hdmi_output_bus_fmts
[16:44:18] ======== [PASSED] drm_test_bridge_helper_reset_crtc ========
[16:44:18] ============== drm_bridge_alloc (2 subtests) ===============
[16:44:18] [PASSED] drm_test_drm_bridge_alloc_basic
[16:44:18] [PASSED] drm_test_drm_bridge_alloc_get_put
[16:44:18] ================ [PASSED] drm_bridge_alloc =================
[16:44:18] ============= drm_bridge_bus_fmt (5 subtests) ==============
[16:44:18] [PASSED] drm_test_bridge_rgb_yuv_rgb
[16:44:18] [PASSED] drm_test_bridge_must_convert_to_yuv444
[16:44:18] [PASSED] drm_test_bridge_hdmi_auto_rgb
[16:44:18] [PASSED] drm_test_bridge_auto_first
[16:44:18] [PASSED] drm_test_bridge_rgb_yuv_no_path
[16:44:18] =============== [PASSED] drm_bridge_bus_fmt ================
[16:44:18] ============= drm_cmdline_parser (40 subtests) =============
[16:44:18] [PASSED] drm_test_cmdline_force_d_only
[16:44:18] [PASSED] drm_test_cmdline_force_D_only_dvi
[16:44:18] [PASSED] drm_test_cmdline_force_D_only_hdmi
[16:44:18] [PASSED] drm_test_cmdline_force_D_only_not_digital
[16:44:18] [PASSED] drm_test_cmdline_force_e_only
[16:44:18] [PASSED] drm_test_cmdline_res
[16:44:18] [PASSED] drm_test_cmdline_res_vesa
[16:44:18] [PASSED] drm_test_cmdline_res_vesa_rblank
[16:44:18] [PASSED] drm_test_cmdline_res_rblank
[16:44:18] [PASSED] drm_test_cmdline_res_bpp
[16:44:18] [PASSED] drm_test_cmdline_res_refresh
[16:44:18] [PASSED] drm_test_cmdline_res_bpp_refresh
[16:44:18] [PASSED] drm_test_cmdline_res_bpp_refresh_interlaced
[16:44:18] [PASSED] drm_test_cmdline_res_bpp_refresh_margins
[16:44:18] [PASSED] drm_test_cmdline_res_bpp_refresh_force_off
[16:44:18] [PASSED] drm_test_cmdline_res_bpp_refresh_force_on
[16:44:18] [PASSED] drm_test_cmdline_res_bpp_refresh_force_on_analog
[16:44:18] [PASSED] drm_test_cmdline_res_bpp_refresh_force_on_digital
[16:44:18] [PASSED] drm_test_cmdline_res_bpp_refresh_interlaced_margins_force_on
[16:44:18] [PASSED] drm_test_cmdline_res_margins_force_on
[16:44:18] [PASSED] drm_test_cmdline_res_vesa_margins
[16:44:18] [PASSED] drm_test_cmdline_name
[16:44:18] [PASSED] drm_test_cmdline_name_bpp
[16:44:18] [PASSED] drm_test_cmdline_name_option
[16:44:18] [PASSED] drm_test_cmdline_name_bpp_option
[16:44:18] [PASSED] drm_test_cmdline_rotate_0
[16:44:18] [PASSED] drm_test_cmdline_rotate_90
[16:44:18] [PASSED] drm_test_cmdline_rotate_180
[16:44:18] [PASSED] drm_test_cmdline_rotate_270
[16:44:18] [PASSED] drm_test_cmdline_hmirror
[16:44:18] [PASSED] drm_test_cmdline_vmirror
[16:44:18] [PASSED] drm_test_cmdline_margin_options
[16:44:18] [PASSED] drm_test_cmdline_multiple_options
[16:44:18] [PASSED] drm_test_cmdline_bpp_extra_and_option
[16:44:18] [PASSED] drm_test_cmdline_extra_and_option
[16:44:18] [PASSED] drm_test_cmdline_freestanding_options
[16:44:18] [PASSED] drm_test_cmdline_freestanding_force_e_and_options
[16:44:18] [PASSED] drm_test_cmdline_panel_orientation
[16:44:18] ================ drm_test_cmdline_invalid =================
[16:44:18] [PASSED] margin_only
[16:44:18] [PASSED] interlace_only
[16:44:18] [PASSED] res_missing_x
[16:44:18] [PASSED] res_missing_y
[16:44:18] [PASSED] res_bad_y
[16:44:18] [PASSED] res_missing_y_bpp
[16:44:18] [PASSED] res_bad_bpp
[16:44:18] [PASSED] res_bad_refresh
[16:44:18] [PASSED] res_bpp_refresh_force_on_off
[16:44:18] [PASSED] res_invalid_mode
[16:44:18] [PASSED] res_bpp_wrong_place_mode
[16:44:18] [PASSED] name_bpp_refresh
[16:44:18] [PASSED] name_refresh
[16:44:18] [PASSED] name_refresh_wrong_mode
[16:44:18] [PASSED] name_refresh_invalid_mode
[16:44:18] [PASSED] rotate_multiple
[16:44:18] [PASSED] rotate_invalid_val
[16:44:18] [PASSED] rotate_truncated
[16:44:18] [PASSED] invalid_option
[16:44:18] [PASSED] invalid_tv_option
[16:44:18] [PASSED] truncated_tv_option
[16:44:18] ============ [PASSED] drm_test_cmdline_invalid =============
[16:44:18] =============== drm_test_cmdline_tv_options ===============
[16:44:18] [PASSED] NTSC
[16:44:18] [PASSED] NTSC_443
[16:44:18] [PASSED] NTSC_J
[16:44:18] [PASSED] PAL
[16:44:18] [PASSED] PAL_M
[16:44:18] [PASSED] PAL_N
[16:44:18] [PASSED] SECAM
[16:44:18] [PASSED] MONO_525
[16:44:18] [PASSED] MONO_625
[16:44:18] =========== [PASSED] drm_test_cmdline_tv_options ===========
[16:44:18] =============== [PASSED] drm_cmdline_parser ================
[16:44:18] ========== drmm_connector_hdmi_init (20 subtests) ==========
[16:44:18] [PASSED] drm_test_connector_hdmi_init_valid
[16:44:18] [PASSED] drm_test_connector_hdmi_init_bpc_8
[16:44:18] [PASSED] drm_test_connector_hdmi_init_bpc_10
[16:44:18] [PASSED] drm_test_connector_hdmi_init_bpc_12
[16:44:18] [PASSED] drm_test_connector_hdmi_init_bpc_invalid
[16:44:18] [PASSED] drm_test_connector_hdmi_init_bpc_null
[16:44:18] [PASSED] drm_test_connector_hdmi_init_formats_empty
[16:44:18] [PASSED] drm_test_connector_hdmi_init_formats_no_rgb
[16:44:18] === drm_test_connector_hdmi_init_formats_yuv420_allowed ===
[16:44:18] [PASSED] supported_formats=0x9 yuv420_allowed=1
[16:44:18] [PASSED] supported_formats=0x9 yuv420_allowed=0
[16:44:18] [PASSED] supported_formats=0x5 yuv420_allowed=1
[16:44:18] [PASSED] supported_formats=0x5 yuv420_allowed=0
[16:44:18] === [PASSED] drm_test_connector_hdmi_init_formats_yuv420_allowed ===
[16:44:18] [PASSED] drm_test_connector_hdmi_init_null_ddc
[16:44:18] [PASSED] drm_test_connector_hdmi_init_null_product
[16:44:18] [PASSED] drm_test_connector_hdmi_init_null_vendor
[16:44:18] [PASSED] drm_test_connector_hdmi_init_product_length_exact
[16:44:18] [PASSED] drm_test_connector_hdmi_init_product_length_too_long
[16:44:18] [PASSED] drm_test_connector_hdmi_init_product_valid
[16:44:18] [PASSED] drm_test_connector_hdmi_init_vendor_length_exact
[16:44:18] [PASSED] drm_test_connector_hdmi_init_vendor_length_too_long
[16:44:18] [PASSED] drm_test_connector_hdmi_init_vendor_valid
[16:44:18] ========= drm_test_connector_hdmi_init_type_valid =========
[16:44:18] [PASSED] HDMI-A
[16:44:18] [PASSED] HDMI-B
[16:44:18] ===== [PASSED] drm_test_connector_hdmi_init_type_valid =====
[16:44:18] ======== drm_test_connector_hdmi_init_type_invalid ========
[16:44:18] [PASSED] Unknown
[16:44:18] [PASSED] VGA
[16:44:18] [PASSED] DVI-I
[16:44:18] [PASSED] DVI-D
[16:44:18] [PASSED] DVI-A
[16:44:18] [PASSED] Composite
[16:44:18] [PASSED] SVIDEO
[16:44:18] [PASSED] LVDS
[16:44:18] [PASSED] Component
[16:44:18] [PASSED] DIN
[16:44:18] [PASSED] DP
[16:44:18] [PASSED] TV
[16:44:18] [PASSED] eDP
[16:44:18] [PASSED] Virtual
[16:44:18] [PASSED] DSI
[16:44:18] [PASSED] DPI
[16:44:18] [PASSED] Writeback
[16:44:18] [PASSED] SPI
[16:44:18] [PASSED] USB
[16:44:18] ==== [PASSED] drm_test_connector_hdmi_init_type_invalid ====
[16:44:18] ============ [PASSED] drmm_connector_hdmi_init =============
[16:44:18] ============= drmm_connector_init (3 subtests) =============
[16:44:18] [PASSED] drm_test_drmm_connector_init
[16:44:18] [PASSED] drm_test_drmm_connector_init_null_ddc
[16:44:18] ========= drm_test_drmm_connector_init_type_valid =========
[16:44:18] [PASSED] Unknown
[16:44:18] [PASSED] VGA
[16:44:18] [PASSED] DVI-I
[16:44:18] [PASSED] DVI-D
[16:44:18] [PASSED] DVI-A
[16:44:18] [PASSED] Composite
[16:44:18] [PASSED] SVIDEO
[16:44:18] [PASSED] LVDS
[16:44:18] [PASSED] Component
[16:44:18] [PASSED] DIN
[16:44:18] [PASSED] DP
[16:44:18] [PASSED] HDMI-A
[16:44:18] [PASSED] HDMI-B
[16:44:18] [PASSED] TV
[16:44:18] [PASSED] eDP
[16:44:18] [PASSED] Virtual
[16:44:18] [PASSED] DSI
[16:44:18] [PASSED] DPI
[16:44:18] [PASSED] Writeback
[16:44:18] [PASSED] SPI
[16:44:18] [PASSED] USB
[16:44:18] ===== [PASSED] drm_test_drmm_connector_init_type_valid =====
[16:44:18] =============== [PASSED] drmm_connector_init ===============
[16:44:18] ========= drm_connector_dynamic_init (6 subtests) ==========
[16:44:18] [PASSED] drm_test_drm_connector_dynamic_init
[16:44:18] [PASSED] drm_test_drm_connector_dynamic_init_null_ddc
[16:44:18] [PASSED] drm_test_drm_connector_dynamic_init_not_added
[16:44:18] [PASSED] drm_test_drm_connector_dynamic_init_properties
[16:44:18] ===== drm_test_drm_connector_dynamic_init_type_valid ======
[16:44:18] [PASSED] Unknown
[16:44:18] [PASSED] VGA
[16:44:18] [PASSED] DVI-I
[16:44:18] [PASSED] DVI-D
[16:44:18] [PASSED] DVI-A
[16:44:18] [PASSED] Composite
[16:44:18] [PASSED] SVIDEO
[16:44:18] [PASSED] LVDS
[16:44:18] [PASSED] Component
[16:44:18] [PASSED] DIN
[16:44:18] [PASSED] DP
[16:44:18] [PASSED] HDMI-A
[16:44:18] [PASSED] HDMI-B
[16:44:18] [PASSED] TV
[16:44:18] [PASSED] eDP
[16:44:18] [PASSED] Virtual
[16:44:18] [PASSED] DSI
[16:44:18] [PASSED] DPI
[16:44:18] [PASSED] Writeback
[16:44:18] [PASSED] SPI
[16:44:18] [PASSED] USB
[16:44:18] = [PASSED] drm_test_drm_connector_dynamic_init_type_valid ==
[16:44:18] ======== drm_test_drm_connector_dynamic_init_name =========
[16:44:18] [PASSED] Unknown
[16:44:18] [PASSED] VGA
[16:44:18] [PASSED] DVI-I
[16:44:18] [PASSED] DVI-D
[16:44:18] [PASSED] DVI-A
[16:44:18] [PASSED] Composite
[16:44:18] [PASSED] SVIDEO
[16:44:18] [PASSED] LVDS
[16:44:18] [PASSED] Component
[16:44:18] [PASSED] DIN
[16:44:18] [PASSED] DP
[16:44:18] [PASSED] HDMI-A
[16:44:18] [PASSED] HDMI-B
[16:44:18] [PASSED] TV
[16:44:18] [PASSED] eDP
[16:44:18] [PASSED] Virtual
[16:44:18] [PASSED] DSI
[16:44:18] [PASSED] DPI
[16:44:18] [PASSED] Writeback
[16:44:18] [PASSED] SPI
[16:44:18] [PASSED] USB
[16:44:18] ==== [PASSED] drm_test_drm_connector_dynamic_init_name =====
[16:44:18] =========== [PASSED] drm_connector_dynamic_init ============
[16:44:18] ==== drm_connector_dynamic_register_early (4 subtests) =====
[16:44:18] [PASSED] drm_test_drm_connector_dynamic_register_early_on_list
[16:44:18] [PASSED] drm_test_drm_connector_dynamic_register_early_defer
[16:44:18] [PASSED] drm_test_drm_connector_dynamic_register_early_no_init
[16:44:18] [PASSED] drm_test_drm_connector_dynamic_register_early_no_mode_object
[16:44:18] ====== [PASSED] drm_connector_dynamic_register_early =======
[16:44:18] ======= drm_connector_dynamic_register (7 subtests) ========
[16:44:18] [PASSED] drm_test_drm_connector_dynamic_register_on_list
[16:44:18] [PASSED] drm_test_drm_connector_dynamic_register_no_defer
[16:44:18] [PASSED] drm_test_drm_connector_dynamic_register_no_init
[16:44:18] [PASSED] drm_test_drm_connector_dynamic_register_mode_object
[16:44:18] [PASSED] drm_test_drm_connector_dynamic_register_sysfs
[16:44:18] [PASSED] drm_test_drm_connector_dynamic_register_sysfs_name
[16:44:18] [PASSED] drm_test_drm_connector_dynamic_register_debugfs
[16:44:18] ========= [PASSED] drm_connector_dynamic_register ==========
[16:44:18] = drm_connector_attach_broadcast_rgb_property (2 subtests) =
[16:44:18] [PASSED] drm_test_drm_connector_attach_broadcast_rgb_property
[16:44:18] [PASSED] drm_test_drm_connector_attach_broadcast_rgb_property_hdmi_connector
[16:44:18] === [PASSED] drm_connector_attach_broadcast_rgb_property ===
[16:44:18] ========== drm_get_tv_mode_from_name (2 subtests) ==========
[16:44:18] ========== drm_test_get_tv_mode_from_name_valid ===========
[16:44:18] [PASSED] NTSC
[16:44:18] [PASSED] NTSC-443
[16:44:18] [PASSED] NTSC-J
[16:44:18] [PASSED] PAL
[16:44:18] [PASSED] PAL-M
[16:44:18] [PASSED] PAL-N
[16:44:18] [PASSED] SECAM
[16:44:18] [PASSED] Mono
[16:44:18] ====== [PASSED] drm_test_get_tv_mode_from_name_valid =======
[16:44:18] [PASSED] drm_test_get_tv_mode_from_name_truncated
[16:44:18] ============ [PASSED] drm_get_tv_mode_from_name ============
[16:44:18] = drm_test_connector_hdmi_compute_mode_clock (12 subtests) =
[16:44:18] [PASSED] drm_test_drm_hdmi_compute_mode_clock_rgb
[16:44:18] [PASSED] drm_test_drm_hdmi_compute_mode_clock_rgb_10bpc
[16:44:18] [PASSED] drm_test_drm_hdmi_compute_mode_clock_rgb_10bpc_vic_1
[16:44:18] [PASSED] drm_test_drm_hdmi_compute_mode_clock_rgb_12bpc
[16:44:18] [PASSED] drm_test_drm_hdmi_compute_mode_clock_rgb_12bpc_vic_1
[16:44:18] [PASSED] drm_test_drm_hdmi_compute_mode_clock_rgb_double
[16:44:18] = drm_test_connector_hdmi_compute_mode_clock_yuv420_valid =
[16:44:18] [PASSED] VIC 96
[16:44:18] [PASSED] VIC 97
[16:44:18] [PASSED] VIC 101
[16:44:18] [PASSED] VIC 102
[16:44:18] [PASSED] VIC 106
[16:44:18] [PASSED] VIC 107
[16:44:18] === [PASSED] drm_test_connector_hdmi_compute_mode_clock_yuv420_valid ===
[16:44:18] [PASSED] drm_test_connector_hdmi_compute_mode_clock_yuv420_10_bpc
[16:44:18] [PASSED] drm_test_connector_hdmi_compute_mode_clock_yuv420_12_bpc
[16:44:18] [PASSED] drm_test_connector_hdmi_compute_mode_clock_yuv422_8_bpc
[16:44:18] [PASSED] drm_test_connector_hdmi_compute_mode_clock_yuv422_10_bpc
[16:44:18] [PASSED] drm_test_connector_hdmi_compute_mode_clock_yuv422_12_bpc
[16:44:18] === [PASSED] drm_test_connector_hdmi_compute_mode_clock ====
[16:44:18] == drm_hdmi_connector_get_broadcast_rgb_name (2 subtests) ==
[16:44:18] === drm_test_drm_hdmi_connector_get_broadcast_rgb_name ====
[16:44:18] [PASSED] Automatic
[16:44:18] [PASSED] Full
[16:44:18] [PASSED] Limited 16:235
[16:44:18] === [PASSED] drm_test_drm_hdmi_connector_get_broadcast_rgb_name ===
[16:44:18] [PASSED] drm_test_drm_hdmi_connector_get_broadcast_rgb_name_invalid
[16:44:18] ==== [PASSED] drm_hdmi_connector_get_broadcast_rgb_name ====
[16:44:18] == drm_hdmi_connector_get_output_format_name (2 subtests) ==
[16:44:18] === drm_test_drm_hdmi_connector_get_output_format_name ====
[16:44:18] [PASSED] RGB
[16:44:18] [PASSED] YUV 4:2:0
[16:44:18] [PASSED] YUV 4:2:2
[16:44:18] [PASSED] YUV 4:4:4
[16:44:18] === [PASSED] drm_test_drm_hdmi_connector_get_output_format_name ===
[16:44:18] [PASSED] drm_test_drm_hdmi_connector_get_output_format_name_invalid
[16:44:18] ==== [PASSED] drm_hdmi_connector_get_output_format_name ====
[16:44:18] ============= drm_damage_helper (21 subtests) ==============
[16:44:18] [PASSED] drm_test_damage_iter_no_damage
[16:44:18] [PASSED] drm_test_damage_iter_no_damage_fractional_src
[16:44:18] [PASSED] drm_test_damage_iter_no_damage_src_moved
[16:44:18] [PASSED] drm_test_damage_iter_no_damage_fractional_src_moved
[16:44:18] [PASSED] drm_test_damage_iter_no_damage_not_visible
[16:44:18] [PASSED] drm_test_damage_iter_no_damage_no_crtc
[16:44:18] [PASSED] drm_test_damage_iter_no_damage_no_fb
[16:44:18] [PASSED] drm_test_damage_iter_simple_damage
[16:44:18] [PASSED] drm_test_damage_iter_single_damage
[16:44:18] [PASSED] drm_test_damage_iter_single_damage_intersect_src
[16:44:18] [PASSED] drm_test_damage_iter_single_damage_outside_src
[16:44:18] [PASSED] drm_test_damage_iter_single_damage_fractional_src
[16:44:18] [PASSED] drm_test_damage_iter_single_damage_intersect_fractional_src
[16:44:18] [PASSED] drm_test_damage_iter_single_damage_outside_fractional_src
[16:44:18] [PASSED] drm_test_damage_iter_single_damage_src_moved
[16:44:18] [PASSED] drm_test_damage_iter_single_damage_fractional_src_moved
[16:44:18] [PASSED] drm_test_damage_iter_damage
[16:44:18] [PASSED] drm_test_damage_iter_damage_one_intersect
[16:44:18] [PASSED] drm_test_damage_iter_damage_one_outside
[16:44:18] [PASSED] drm_test_damage_iter_damage_src_moved
[16:44:18] [PASSED] drm_test_damage_iter_damage_not_visible
[16:44:18] ================ [PASSED] drm_damage_helper ================
[16:44:18] ============== drm_dp_mst_helper (3 subtests) ==============
[16:44:18] ============== drm_test_dp_mst_calc_pbn_mode ==============
[16:44:18] [PASSED] Clock 154000 BPP 30 DSC disabled
[16:44:18] [PASSED] Clock 234000 BPP 30 DSC disabled
[16:44:18] [PASSED] Clock 297000 BPP 24 DSC disabled
[16:44:18] [PASSED] Clock 332880 BPP 24 DSC enabled
[16:44:18] [PASSED] Clock 324540 BPP 24 DSC enabled
[16:44:18] ========== [PASSED] drm_test_dp_mst_calc_pbn_mode ==========
[16:44:18] ============== drm_test_dp_mst_calc_pbn_div ===============
[16:44:18] [PASSED] Link rate 2000000 lane count 4
[16:44:18] [PASSED] Link rate 2000000 lane count 2
[16:44:18] [PASSED] Link rate 2000000 lane count 1
[16:44:18] [PASSED] Link rate 1350000 lane count 4
[16:44:18] [PASSED] Link rate 1350000 lane count 2
[16:44:18] [PASSED] Link rate 1350000 lane count 1
[16:44:18] [PASSED] Link rate 1000000 lane count 4
[16:44:18] [PASSED] Link rate 1000000 lane count 2
[16:44:18] [PASSED] Link rate 1000000 lane count 1
[16:44:18] [PASSED] Link rate 810000 lane count 4
[16:44:18] [PASSED] Link rate 810000 lane count 2
[16:44:18] [PASSED] Link rate 810000 lane count 1
[16:44:18] [PASSED] Link rate 540000 lane count 4
[16:44:18] [PASSED] Link rate 540000 lane count 2
[16:44:18] [PASSED] Link rate 540000 lane count 1
[16:44:18] [PASSED] Link rate 270000 lane count 4
[16:44:18] [PASSED] Link rate 270000 lane count 2
[16:44:18] [PASSED] Link rate 270000 lane count 1
[16:44:18] [PASSED] Link rate 162000 lane count 4
[16:44:18] [PASSED] Link rate 162000 lane count 2
[16:44:18] [PASSED] Link rate 162000 lane count 1
[16:44:18] ========== [PASSED] drm_test_dp_mst_calc_pbn_div ===========
[16:44:18] ========= drm_test_dp_mst_sideband_msg_req_decode =========
[16:44:18] [PASSED] DP_ENUM_PATH_RESOURCES with port number
[16:44:18] [PASSED] DP_POWER_UP_PHY with port number
[16:44:18] [PASSED] DP_POWER_DOWN_PHY with port number
[16:44:18] [PASSED] DP_ALLOCATE_PAYLOAD with SDP stream sinks
[16:44:18] [PASSED] DP_ALLOCATE_PAYLOAD with port number
[16:44:18] [PASSED] DP_ALLOCATE_PAYLOAD with VCPI
[16:44:18] [PASSED] DP_ALLOCATE_PAYLOAD with PBN
[16:44:18] [PASSED] DP_QUERY_PAYLOAD with port number
[16:44:18] [PASSED] DP_QUERY_PAYLOAD with VCPI
[16:44:18] [PASSED] DP_REMOTE_DPCD_READ with port number
[16:44:18] [PASSED] DP_REMOTE_DPCD_READ with DPCD address
[16:44:18] [PASSED] DP_REMOTE_DPCD_READ with max number of bytes
[16:44:18] [PASSED] DP_REMOTE_DPCD_WRITE with port number
[16:44:18] [PASSED] DP_REMOTE_DPCD_WRITE with DPCD address
[16:44:18] [PASSED] DP_REMOTE_DPCD_WRITE with data array
[16:44:18] [PASSED] DP_REMOTE_I2C_READ with port number
[16:44:18] [PASSED] DP_REMOTE_I2C_READ with I2C device ID
[16:44:18] [PASSED] DP_REMOTE_I2C_READ with transactions array
[16:44:18] [PASSED] DP_REMOTE_I2C_WRITE with port number
[16:44:18] [PASSED] DP_REMOTE_I2C_WRITE with I2C device ID
[16:44:18] [PASSED] DP_REMOTE_I2C_WRITE with data array
[16:44:18] [PASSED] DP_QUERY_STREAM_ENC_STATUS with stream ID
[16:44:18] [PASSED] DP_QUERY_STREAM_ENC_STATUS with client ID
[16:44:18] [PASSED] DP_QUERY_STREAM_ENC_STATUS with stream event
[16:44:18] [PASSED] DP_QUERY_STREAM_ENC_STATUS with valid stream event
[16:44:18] [PASSED] DP_QUERY_STREAM_ENC_STATUS with stream behavior
[16:44:18] [PASSED] DP_QUERY_STREAM_ENC_STATUS with a valid stream behavior
[16:44:18] ===== [PASSED] drm_test_dp_mst_sideband_msg_req_decode =====
[16:44:18] ================ [PASSED] drm_dp_mst_helper ================
[16:44:18] ================== drm_exec (7 subtests) ===================
[16:44:18] [PASSED] sanitycheck
[16:44:18] [PASSED] test_lock
[16:44:18] [PASSED] test_lock_unlock
[16:44:18] [PASSED] test_duplicates
[16:44:18] [PASSED] test_prepare
[16:44:18] [PASSED] test_prepare_array
[16:44:18] [PASSED] test_multiple_loops
[16:44:18] ==================== [PASSED] drm_exec =====================
[16:44:18] =========== drm_format_helper_test (17 subtests) ===========
[16:44:18] ============== drm_test_fb_xrgb8888_to_gray8 ==============
[16:44:18] [PASSED] single_pixel_source_buffer
[16:44:18] [PASSED] single_pixel_clip_rectangle
[16:44:18] [PASSED] well_known_colors
[16:44:18] [PASSED] destination_pitch
[16:44:18] ========== [PASSED] drm_test_fb_xrgb8888_to_gray8 ==========
[16:44:18] ============= drm_test_fb_xrgb8888_to_rgb332 ==============
[16:44:18] [PASSED] single_pixel_source_buffer
[16:44:18] [PASSED] single_pixel_clip_rectangle
[16:44:18] [PASSED] well_known_colors
[16:44:18] [PASSED] destination_pitch
[16:44:18] ========= [PASSED] drm_test_fb_xrgb8888_to_rgb332 ==========
[16:44:18] ============= drm_test_fb_xrgb8888_to_rgb565 ==============
[16:44:18] [PASSED] single_pixel_source_buffer
[16:44:18] [PASSED] single_pixel_clip_rectangle
[16:44:18] [PASSED] well_known_colors
[16:44:18] [PASSED] destination_pitch
[16:44:18] ========= [PASSED] drm_test_fb_xrgb8888_to_rgb565 ==========
[16:44:18] ============ drm_test_fb_xrgb8888_to_xrgb1555 =============
[16:44:18] [PASSED] single_pixel_source_buffer
[16:44:18] [PASSED] single_pixel_clip_rectangle
[16:44:18] [PASSED] well_known_colors
[16:44:18] [PASSED] destination_pitch
[16:44:18] ======== [PASSED] drm_test_fb_xrgb8888_to_xrgb1555 =========
[16:44:18] ============ drm_test_fb_xrgb8888_to_argb1555 =============
[16:44:18] [PASSED] single_pixel_source_buffer
[16:44:18] [PASSED] single_pixel_clip_rectangle
[16:44:18] [PASSED] well_known_colors
[16:44:18] [PASSED] destination_pitch
[16:44:18] ======== [PASSED] drm_test_fb_xrgb8888_to_argb1555 =========
[16:44:18] ============ drm_test_fb_xrgb8888_to_rgba5551 =============
[16:44:18] [PASSED] single_pixel_source_buffer
[16:44:18] [PASSED] single_pixel_clip_rectangle
[16:44:18] [PASSED] well_known_colors
[16:44:18] [PASSED] destination_pitch
[16:44:18] ======== [PASSED] drm_test_fb_xrgb8888_to_rgba5551 =========
[16:44:18] ============= drm_test_fb_xrgb8888_to_rgb888 ==============
[16:44:18] [PASSED] single_pixel_source_buffer
[16:44:18] [PASSED] single_pixel_clip_rectangle
[16:44:18] [PASSED] well_known_colors
[16:44:18] [PASSED] destination_pitch
[16:44:18] ========= [PASSED] drm_test_fb_xrgb8888_to_rgb888 ==========
[16:44:18] ============= drm_test_fb_xrgb8888_to_bgr888 ==============
[16:44:18] [PASSED] single_pixel_source_buffer
[16:44:18] [PASSED] single_pixel_clip_rectangle
[16:44:18] [PASSED] well_known_colors
[16:44:18] [PASSED] destination_pitch
[16:44:18] ========= [PASSED] drm_test_fb_xrgb8888_to_bgr888 ==========
[16:44:18] ============ drm_test_fb_xrgb8888_to_argb8888 =============
[16:44:18] [PASSED] single_pixel_source_buffer
[16:44:18] [PASSED] single_pixel_clip_rectangle
[16:44:18] [PASSED] well_known_colors
[16:44:18] [PASSED] destination_pitch
[16:44:18] ======== [PASSED] drm_test_fb_xrgb8888_to_argb8888 =========
[16:44:18] =========== drm_test_fb_xrgb8888_to_xrgb2101010 ===========
[16:44:18] [PASSED] single_pixel_source_buffer
[16:44:18] [PASSED] single_pixel_clip_rectangle
[16:44:18] [PASSED] well_known_colors
[16:44:18] [PASSED] destination_pitch
[16:44:18] ======= [PASSED] drm_test_fb_xrgb8888_to_xrgb2101010 =======
[16:44:18] =========== drm_test_fb_xrgb8888_to_argb2101010 ===========
[16:44:18] [PASSED] single_pixel_source_buffer
[16:44:18] [PASSED] single_pixel_clip_rectangle
[16:44:18] [PASSED] well_known_colors
[16:44:18] [PASSED] destination_pitch
[16:44:18] ======= [PASSED] drm_test_fb_xrgb8888_to_argb2101010 =======
[16:44:18] ============== drm_test_fb_xrgb8888_to_mono ===============
[16:44:18] [PASSED] single_pixel_source_buffer
[16:44:18] [PASSED] single_pixel_clip_rectangle
[16:44:18] [PASSED] well_known_colors
[16:44:18] [PASSED] destination_pitch
[16:44:18] ========== [PASSED] drm_test_fb_xrgb8888_to_mono ===========
[16:44:18] ==================== drm_test_fb_swab =====================
[16:44:18] [PASSED] single_pixel_source_buffer
[16:44:18] [PASSED] single_pixel_clip_rectangle
[16:44:18] [PASSED] well_known_colors
[16:44:18] [PASSED] destination_pitch
[16:44:18] ================ [PASSED] drm_test_fb_swab =================
[16:44:18] ============ drm_test_fb_xrgb8888_to_xbgr8888 =============
[16:44:18] [PASSED] single_pixel_source_buffer
[16:44:18] [PASSED] single_pixel_clip_rectangle
[16:44:18] [PASSED] well_known_colors
[16:44:18] [PASSED] destination_pitch
[16:44:18] ======== [PASSED] drm_test_fb_xrgb8888_to_xbgr8888 =========
[16:44:18] ============ drm_test_fb_xrgb8888_to_abgr8888 =============
[16:44:18] [PASSED] single_pixel_source_buffer
[16:44:18] [PASSED] single_pixel_clip_rectangle
[16:44:18] [PASSED] well_known_colors
[16:44:18] [PASSED] destination_pitch
[16:44:18] ======== [PASSED] drm_test_fb_xrgb8888_to_abgr8888 =========
[16:44:18] ================= drm_test_fb_clip_offset =================
[16:44:18] [PASSED] pass through
[16:44:18] [PASSED] horizontal offset
[16:44:18] [PASSED] vertical offset
[16:44:18] [PASSED] horizontal and vertical offset
[16:44:18] [PASSED] horizontal offset (custom pitch)
[16:44:18] [PASSED] vertical offset (custom pitch)
[16:44:18] [PASSED] horizontal and vertical offset (custom pitch)
[16:44:18] ============= [PASSED] drm_test_fb_clip_offset =============
[16:44:18] =================== drm_test_fb_memcpy ====================
[16:44:18] [PASSED] single_pixel_source_buffer: XR24 little-endian (0x34325258)
[16:44:18] [PASSED] single_pixel_source_buffer: XRA8 little-endian (0x38415258)
[16:44:18] [PASSED] single_pixel_source_buffer: YU24 little-endian (0x34325559)
[16:44:18] [PASSED] single_pixel_clip_rectangle: XB24 little-endian (0x34324258)
[16:44:18] [PASSED] single_pixel_clip_rectangle: XRA8 little-endian (0x38415258)
[16:44:18] [PASSED] single_pixel_clip_rectangle: YU24 little-endian (0x34325559)
[16:44:18] [PASSED] well_known_colors: XB24 little-endian (0x34324258)
[16:44:18] [PASSED] well_known_colors: XRA8 little-endian (0x38415258)
[16:44:18] [PASSED] well_known_colors: YU24 little-endian (0x34325559)
[16:44:18] [PASSED] destination_pitch: XB24 little-endian (0x34324258)
[16:44:18] [PASSED] destination_pitch: XRA8 little-endian (0x38415258)
[16:44:18] [PASSED] destination_pitch: YU24 little-endian (0x34325559)
[16:44:18] =============== [PASSED] drm_test_fb_memcpy ================
[16:44:18] ============= [PASSED] drm_format_helper_test ==============
[16:44:18] ================= drm_format (18 subtests) =================
[16:44:18] [PASSED] drm_test_format_block_width_invalid
[16:44:18] [PASSED] drm_test_format_block_width_one_plane
[16:44:18] [PASSED] drm_test_format_block_width_two_plane
[16:44:18] [PASSED] drm_test_format_block_width_three_plane
[16:44:18] [PASSED] drm_test_format_block_width_tiled
[16:44:18] [PASSED] drm_test_format_block_height_invalid
[16:44:18] [PASSED] drm_test_format_block_height_one_plane
[16:44:18] [PASSED] drm_test_format_block_height_two_plane
[16:44:18] [PASSED] drm_test_format_block_height_three_plane
[16:44:18] [PASSED] drm_test_format_block_height_tiled
[16:44:18] [PASSED] drm_test_format_min_pitch_invalid
[16:44:18] [PASSED] drm_test_format_min_pitch_one_plane_8bpp
[16:44:18] [PASSED] drm_test_format_min_pitch_one_plane_16bpp
[16:44:18] [PASSED] drm_test_format_min_pitch_one_plane_24bpp
[16:44:18] [PASSED] drm_test_format_min_pitch_one_plane_32bpp
[16:44:18] [PASSED] drm_test_format_min_pitch_two_plane
[16:44:18] [PASSED] drm_test_format_min_pitch_three_plane_8bpp
[16:44:18] [PASSED] drm_test_format_min_pitch_tiled
[16:44:18] =================== [PASSED] drm_format ====================
[16:44:18] ============== drm_framebuffer (10 subtests) ===============
[16:44:18] ========== drm_test_framebuffer_check_src_coords ==========
[16:44:18] [PASSED] Success: source fits into fb
[16:44:18] [PASSED] Fail: overflowing fb with x-axis coordinate
[16:44:18] [PASSED] Fail: overflowing fb with y-axis coordinate
[16:44:18] [PASSED] Fail: overflowing fb with source width
[16:44:18] [PASSED] Fail: overflowing fb with source height
[16:44:18] ====== [PASSED] drm_test_framebuffer_check_src_coords ======
[16:44:18] [PASSED] drm_test_framebuffer_cleanup
[16:44:18] =============== drm_test_framebuffer_create ===============
[16:44:18] [PASSED] ABGR8888 normal sizes
[16:44:18] [PASSED] ABGR8888 max sizes
[16:44:18] [PASSED] ABGR8888 pitch greater than min required
[16:44:18] [PASSED] ABGR8888 pitch less than min required
[16:44:18] [PASSED] ABGR8888 Invalid width
[16:44:18] [PASSED] ABGR8888 Invalid buffer handle
[16:44:18] [PASSED] No pixel format
[16:44:18] [PASSED] ABGR8888 Width 0
[16:44:18] [PASSED] ABGR8888 Height 0
[16:44:18] [PASSED] ABGR8888 Out of bound height * pitch combination
[16:44:18] [PASSED] ABGR8888 Large buffer offset
[16:44:18] [PASSED] ABGR8888 Buffer offset for inexistent plane
[16:44:18] [PASSED] ABGR8888 Invalid flag
[16:44:18] [PASSED] ABGR8888 Set DRM_MODE_FB_MODIFIERS without modifiers
[16:44:18] [PASSED] ABGR8888 Valid buffer modifier
[16:44:18] [PASSED] ABGR8888 Invalid buffer modifier(DRM_FORMAT_MOD_SAMSUNG_64_32_TILE)
[16:44:18] [PASSED] ABGR8888 Extra pitches without DRM_MODE_FB_MODIFIERS
[16:44:18] [PASSED] ABGR8888 Extra pitches with DRM_MODE_FB_MODIFIERS
[16:44:18] [PASSED] NV12 Normal sizes
[16:44:18] [PASSED] NV12 Max sizes
[16:44:18] [PASSED] NV12 Invalid pitch
[16:44:18] [PASSED] NV12 Invalid modifier/missing DRM_MODE_FB_MODIFIERS flag
[16:44:18] [PASSED] NV12 different modifier per-plane
[16:44:18] [PASSED] NV12 with DRM_FORMAT_MOD_SAMSUNG_64_32_TILE
[16:44:18] [PASSED] NV12 Valid modifiers without DRM_MODE_FB_MODIFIERS
[16:44:18] [PASSED] NV12 Modifier for inexistent plane
[16:44:18] [PASSED] NV12 Handle for inexistent plane
[16:44:18] [PASSED] NV12 Handle for inexistent plane without DRM_MODE_FB_MODIFIERS
[16:44:18] [PASSED] YVU420 DRM_MODE_FB_MODIFIERS set without modifier
[16:44:18] [PASSED] YVU420 Normal sizes
[16:44:18] [PASSED] YVU420 Max sizes
[16:44:18] [PASSED] YVU420 Invalid pitch
[16:44:18] [PASSED] YVU420 Different pitches
[16:44:18] [PASSED] YVU420 Different buffer offsets/pitches
[16:44:18] [PASSED] YVU420 Modifier set just for plane 0, without DRM_MODE_FB_MODIFIERS
[16:44:18] [PASSED] YVU420 Modifier set just for planes 0, 1, without DRM_MODE_FB_MODIFIERS
[16:44:18] [PASSED] YVU420 Modifier set just for plane 0, 1, with DRM_MODE_FB_MODIFIERS
[16:44:18] [PASSED] YVU420 Valid modifier
[16:44:18] [PASSED] YVU420 Different modifiers per plane
[16:44:18] [PASSED] YVU420 Modifier for inexistent plane
[16:44:18] [PASSED] YUV420_10BIT Invalid modifier(DRM_FORMAT_MOD_LINEAR)
[16:44:18] [PASSED] X0L2 Normal sizes
[16:44:18] [PASSED] X0L2 Max sizes
[16:44:18] [PASSED] X0L2 Invalid pitch
[16:44:18] [PASSED] X0L2 Pitch greater than minimum required
[16:44:18] [PASSED] X0L2 Handle for inexistent plane
[16:44:18] [PASSED] X0L2 Offset for inexistent plane, without DRM_MODE_FB_MODIFIERS set
[16:44:18] [PASSED] X0L2 Modifier without DRM_MODE_FB_MODIFIERS set
[16:44:18] [PASSED] X0L2 Valid modifier
[16:44:18] [PASSED] X0L2 Modifier for inexistent plane
[16:44:18] =========== [PASSED] drm_test_framebuffer_create ===========
[16:44:18] [PASSED] drm_test_framebuffer_free
[16:44:18] [PASSED] drm_test_framebuffer_init
[16:44:18] [PASSED] drm_test_framebuffer_init_bad_format
[16:44:18] [PASSED] drm_test_framebuffer_init_dev_mismatch
[16:44:18] [PASSED] drm_test_framebuffer_lookup
[16:44:18] [PASSED] drm_test_framebuffer_lookup_inexistent
[16:44:18] [PASSED] drm_test_framebuffer_modifiers_not_supported
[16:44:18] ================= [PASSED] drm_framebuffer =================
[16:44:18] ================ drm_gem_shmem (8 subtests) ================
[16:44:18] [PASSED] drm_gem_shmem_test_obj_create
[16:44:18] [PASSED] drm_gem_shmem_test_obj_create_private
[16:44:18] [PASSED] drm_gem_shmem_test_pin_pages
[16:44:18] [PASSED] drm_gem_shmem_test_vmap
[16:44:18] [PASSED] drm_gem_shmem_test_get_sg_table
[16:44:18] [PASSED] drm_gem_shmem_test_get_pages_sgt
[16:44:18] [PASSED] drm_gem_shmem_test_madvise
[16:44:18] [PASSED] drm_gem_shmem_test_purge
[16:44:18] ================== [PASSED] drm_gem_shmem ==================
[16:44:18] === drm_atomic_helper_connector_hdmi_check (29 subtests) ===
[16:44:18] [PASSED] drm_test_check_broadcast_rgb_auto_cea_mode
[16:44:18] [PASSED] drm_test_check_broadcast_rgb_auto_cea_mode_vic_1
[16:44:18] [PASSED] drm_test_check_broadcast_rgb_full_cea_mode
[16:44:18] [PASSED] drm_test_check_broadcast_rgb_full_cea_mode_vic_1
[16:44:18] [PASSED] drm_test_check_broadcast_rgb_limited_cea_mode
[16:44:18] [PASSED] drm_test_check_broadcast_rgb_limited_cea_mode_vic_1
[16:44:18] ====== drm_test_check_broadcast_rgb_cea_mode_yuv420 =======
[16:44:18] [PASSED] Automatic
[16:44:18] [PASSED] Full
[16:44:18] [PASSED] Limited 16:235
[16:44:18] == [PASSED] drm_test_check_broadcast_rgb_cea_mode_yuv420 ===
[16:44:18] [PASSED] drm_test_check_broadcast_rgb_crtc_mode_changed
[16:44:18] [PASSED] drm_test_check_broadcast_rgb_crtc_mode_not_changed
[16:44:18] [PASSED] drm_test_check_disable_connector
[16:44:18] [PASSED] drm_test_check_hdmi_funcs_reject_rate
[16:44:18] [PASSED] drm_test_check_max_tmds_rate_bpc_fallback_rgb
[16:44:18] [PASSED] drm_test_check_max_tmds_rate_bpc_fallback_yuv420
[16:44:18] [PASSED] drm_test_check_max_tmds_rate_bpc_fallback_ignore_yuv422
[16:44:18] [PASSED] drm_test_check_max_tmds_rate_bpc_fallback_ignore_yuv420
[16:44:18] [PASSED] drm_test_check_driver_unsupported_fallback_yuv420
[16:44:18] [PASSED] drm_test_check_output_bpc_crtc_mode_changed
[16:44:18] [PASSED] drm_test_check_output_bpc_crtc_mode_not_changed
[16:44:18] [PASSED] drm_test_check_output_bpc_dvi
[16:44:18] [PASSED] drm_test_check_output_bpc_format_vic_1
[16:44:18] [PASSED] drm_test_check_output_bpc_format_display_8bpc_only
[16:44:18] [PASSED] drm_test_check_output_bpc_format_display_rgb_only
[16:44:18] [PASSED] drm_test_check_output_bpc_format_driver_8bpc_only
[16:44:18] [PASSED] drm_test_check_output_bpc_format_driver_rgb_only
[16:44:18] [PASSED] drm_test_check_tmds_char_rate_rgb_8bpc
[16:44:18] [PASSED] drm_test_check_tmds_char_rate_rgb_10bpc
[16:44:18] [PASSED] drm_test_check_tmds_char_rate_rgb_12bpc
[16:44:18] ============ drm_test_check_hdmi_color_format =============
[16:44:18] [PASSED] AUTO -> RGB
[16:44:18] [PASSED] YCBCR422 -> YUV422
[16:44:18] [PASSED] YCBCR420 -> YUV420
[16:44:18] [PASSED] YCBCR444 -> YUV444
[16:44:18] [PASSED] RGB -> RGB
[16:44:18] ======== [PASSED] drm_test_check_hdmi_color_format =========
[16:44:18] ======== drm_test_check_hdmi_color_format_420_only ========
[16:44:18] [PASSED] RGB should fail
[16:44:18] [PASSED] YUV444 should fail
[16:44:18] [PASSED] YUV422 should fail
[16:44:18] [PASSED] YUV420 should work
[16:44:18] ==== [PASSED] drm_test_check_hdmi_color_format_420_only ====
[16:44:18] ===== [PASSED] drm_atomic_helper_connector_hdmi_check ======
[16:44:18] === drm_atomic_helper_connector_hdmi_reset (6 subtests) ====
[16:44:18] [PASSED] drm_test_check_broadcast_rgb_value
[16:44:18] [PASSED] drm_test_check_bpc_8_value
[16:44:18] [PASSED] drm_test_check_bpc_10_value
[16:44:18] [PASSED] drm_test_check_bpc_12_value
[16:44:18] [PASSED] drm_test_check_format_value
[16:44:18] [PASSED] drm_test_check_tmds_char_value
[16:44:18] ===== [PASSED] drm_atomic_helper_connector_hdmi_reset ======
[16:44:18] = drm_atomic_helper_connector_hdmi_mode_valid (7 subtests) =
[16:44:18] [PASSED] drm_test_check_mode_valid
[16:44:18] [PASSED] drm_test_check_mode_valid_reject
[16:44:18] [PASSED] drm_test_check_mode_valid_reject_rate
[16:44:18] [PASSED] drm_test_check_mode_valid_reject_max_clock
[16:44:18] [PASSED] drm_test_check_mode_valid_yuv420_only_max_clock
[16:44:18] [PASSED] drm_test_check_mode_valid_reject_yuv420_only_connector
[16:44:18] [PASSED] drm_test_check_mode_valid_accept_yuv420_also_connector_rgb
[16:44:18] === [PASSED] drm_atomic_helper_connector_hdmi_mode_valid ===
[16:44:18] = drm_atomic_helper_connector_hdmi_infoframes (5 subtests) =
[16:44:18] [PASSED] drm_test_check_infoframes
[16:44:18] [PASSED] drm_test_check_reject_avi_infoframe
[16:44:18] [PASSED] drm_test_check_reject_hdr_infoframe_bpc_8
[16:44:18] [PASSED] drm_test_check_reject_hdr_infoframe_bpc_10
[16:44:18] [PASSED] drm_test_check_reject_audio_infoframe
[16:44:18] === [PASSED] drm_atomic_helper_connector_hdmi_infoframes ===
[16:44:18] ================= drm_managed (2 subtests) =================
[16:44:18] [PASSED] drm_test_managed_release_action
[16:44:18] [PASSED] drm_test_managed_run_action
[16:44:18] =================== [PASSED] drm_managed ===================
[16:44:18] =================== drm_mm (6 subtests) ====================
[16:44:18] [PASSED] drm_test_mm_init
[16:44:18] [PASSED] drm_test_mm_debug
[16:44:18] [PASSED] drm_test_mm_align32
[16:44:18] [PASSED] drm_test_mm_align64
[16:44:18] [PASSED] drm_test_mm_lowest
[16:44:18] [PASSED] drm_test_mm_highest
[16:44:18] ===================== [PASSED] drm_mm ======================
[16:44:18] ============= drm_modes_analog_tv (5 subtests) =============
[16:44:18] [PASSED] drm_test_modes_analog_tv_mono_576i
[16:44:18] [PASSED] drm_test_modes_analog_tv_ntsc_480i
[16:44:18] [PASSED] drm_test_modes_analog_tv_ntsc_480i_inlined
[16:44:18] [PASSED] drm_test_modes_analog_tv_pal_576i
[16:44:18] [PASSED] drm_test_modes_analog_tv_pal_576i_inlined
[16:44:18] =============== [PASSED] drm_modes_analog_tv ===============
[16:44:18] ============== drm_panic_helper (3 subtests) ===============
[16:44:18] ============= drm_test_panic_screen_user_map ==============
[16:44:18] [PASSED] Panic screen user, mode: 1024 x 768 XR24 little-endian (0x34325258)
[16:44:18] [PASSED] Panic screen user, mode: 494 x 494 XR24 little-endian (0x34325258)
[16:44:18] [PASSED] Panic screen user, mode: 1920 x 1080 XR24 little-endian (0x34325258)
[16:44:18] [PASSED] Panic screen user, mode: 1024 x 768 RG16 little-endian (0x36314752)
[16:44:18] [PASSED] Panic screen user, mode: 1024 x 768 RG24 little-endian (0x34324752)
[16:44:18] [PASSED] Panic screen kmsg, mode: 1024 x 768 XR24 little-endian (0x34325258)
[16:44:18] [PASSED] Panic screen kmsg, mode: 494 x 494 XR24 little-endian (0x34325258)
[16:44:18] [PASSED] Panic screen kmsg, mode: 1920 x 1080 XR24 little-endian (0x34325258)
[16:44:18] [PASSED] Panic screen kmsg, mode: 1024 x 768 RG16 little-endian (0x36314752)
[16:44:18] [PASSED] Panic screen kmsg, mode: 1024 x 768 RG24 little-endian (0x34324752)
[16:44:18] ========= [PASSED] drm_test_panic_screen_user_map ==========
[16:44:18] ============= drm_test_panic_screen_user_page =============
[16:44:18] [PASSED] Panic screen user, mode: 1024 x 768 XR24 little-endian (0x34325258)
[16:44:18] [PASSED] Panic screen user, mode: 494 x 494 XR24 little-endian (0x34325258)
[16:44:18] [PASSED] Panic screen user, mode: 1920 x 1080 XR24 little-endian (0x34325258)
[16:44:18] [PASSED] Panic screen user, mode: 1024 x 768 RG16 little-endian (0x36314752)
[16:44:18] [PASSED] Panic screen user, mode: 1024 x 768 RG24 little-endian (0x34324752)
[16:44:18] [PASSED] Panic screen kmsg, mode: 1024 x 768 XR24 little-endian (0x34325258)
[16:44:18] [PASSED] Panic screen kmsg, mode: 494 x 494 XR24 little-endian (0x34325258)
[16:44:19] [PASSED] Panic screen kmsg, mode: 1920 x 1080 XR24 little-endian (0x34325258)
[16:44:19] [PASSED] Panic screen kmsg, mode: 1024 x 768 RG16 little-endian (0x36314752)
[16:44:19] [PASSED] Panic screen kmsg, mode: 1024 x 768 RG24 little-endian (0x34324752)
[16:44:19] ========= [PASSED] drm_test_panic_screen_user_page =========
[16:44:19] ========== drm_test_panic_screen_user_set_pixel ===========
[16:44:19] [PASSED] Panic screen user, mode: 1024 x 768 XR24 little-endian (0x34325258)
[16:44:19] [PASSED] Panic screen user, mode: 494 x 494 XR24 little-endian (0x34325258)
[16:44:19] [PASSED] Panic screen user, mode: 1920 x 1080 XR24 little-endian (0x34325258)
[16:44:19] [PASSED] Panic screen user, mode: 1024 x 768 RG16 little-endian (0x36314752)
[16:44:19] [PASSED] Panic screen user, mode: 1024 x 768 RG24 little-endian (0x34324752)
[16:44:19] [PASSED] Panic screen kmsg, mode: 1024 x 768 XR24 little-endian (0x34325258)
[16:44:19] [PASSED] Panic screen kmsg, mode: 494 x 494 XR24 little-endian (0x34325258)
[16:44:19] [PASSED] Panic screen kmsg, mode: 1920 x 1080 XR24 little-endian (0x34325258)
[16:44:19] [PASSED] Panic screen kmsg, mode: 1024 x 768 RG16 little-endian (0x36314752)
[16:44:19] [PASSED] Panic screen kmsg, mode: 1024 x 768 RG24 little-endian (0x34324752)
[16:44:19] ====== [PASSED] drm_test_panic_screen_user_set_pixel =======
[16:44:19] ================ [PASSED] drm_panic_helper =================
[16:44:19] ============== drm_plane_helper (2 subtests) ===============
[16:44:19] =============== drm_test_check_plane_state ================
[16:44:19] [PASSED] clipping_simple
[16:44:19] [PASSED] clipping_rotate_reflect
[16:44:19] [PASSED] positioning_simple
[16:44:19] [PASSED] upscaling
[16:44:19] [PASSED] downscaling
[16:44:19] [PASSED] rounding1
[16:44:19] [PASSED] rounding2
[16:44:19] [PASSED] rounding3
[16:44:19] [PASSED] rounding4
[16:44:19] =========== [PASSED] drm_test_check_plane_state ============
[16:44:19] =========== drm_test_check_invalid_plane_state ============
[16:44:19] [PASSED] positioning_invalid
[16:44:19] [PASSED] upscaling_invalid
[16:44:19] [PASSED] downscaling_invalid
[16:44:19] ======= [PASSED] drm_test_check_invalid_plane_state ========
[16:44:19] ================ [PASSED] drm_plane_helper =================
[16:44:19] ====== drm_connector_helper_tv_get_modes (1 subtest) =======
[16:44:19] ====== drm_test_connector_helper_tv_get_modes_check =======
[16:44:19] [PASSED] None
[16:44:19] [PASSED] PAL
[16:44:19] [PASSED] NTSC
[16:44:19] [PASSED] Both, NTSC Default
[16:44:19] [PASSED] Both, PAL Default
[16:44:19] [PASSED] Both, NTSC Default, with PAL on command-line
[16:44:19] [PASSED] Both, PAL Default, with NTSC on command-line
[16:44:19] == [PASSED] drm_test_connector_helper_tv_get_modes_check ===
[16:44:19] ======== [PASSED] drm_connector_helper_tv_get_modes ========
[16:44:19] ================== drm_rect (9 subtests) ===================
[16:44:19] [PASSED] drm_test_rect_clip_scaled_div_by_zero
[16:44:19] [PASSED] drm_test_rect_clip_scaled_not_clipped
[16:44:19] [PASSED] drm_test_rect_clip_scaled_clipped
[16:44:19] [PASSED] drm_test_rect_clip_scaled_signed_vs_unsigned
[16:44:19] ================= drm_test_rect_intersect =================
[16:44:19] [PASSED] top-left x bottom-right: 2x2+1+1 x 2x2+0+0
[16:44:19] [PASSED] top-right x bottom-left: 2x2+0+0 x 2x2+1-1
[16:44:19] [PASSED] bottom-left x top-right: 2x2+1-1 x 2x2+0+0
[16:44:19] [PASSED] bottom-right x top-left: 2x2+0+0 x 2x2+1+1
[16:44:19] [PASSED] right x left: 2x1+0+0 x 3x1+1+0
[16:44:19] [PASSED] left x right: 3x1+1+0 x 2x1+0+0
[16:44:19] [PASSED] up x bottom: 1x2+0+0 x 1x3+0-1
[16:44:19] [PASSED] bottom x up: 1x3+0-1 x 1x2+0+0
[16:44:19] [PASSED] touching corner: 1x1+0+0 x 2x2+1+1
[16:44:19] [PASSED] touching side: 1x1+0+0 x 1x1+1+0
[16:44:19] [PASSED] equal rects: 2x2+0+0 x 2x2+0+0
[16:44:19] [PASSED] inside another: 2x2+0+0 x 1x1+1+1
[16:44:19] [PASSED] far away: 1x1+0+0 x 1x1+3+6
[16:44:19] [PASSED] points intersecting: 0x0+5+10 x 0x0+5+10
[16:44:19] [PASSED] points not intersecting: 0x0+0+0 x 0x0+5+10
[16:44:19] ============= [PASSED] drm_test_rect_intersect =============
[16:44:19] ================ drm_test_rect_calc_hscale ================
[16:44:19] [PASSED] normal use
[16:44:19] [PASSED] out of max range
[16:44:19] [PASSED] out of min range
[16:44:19] [PASSED] zero dst
[16:44:19] [PASSED] negative src
[16:44:19] [PASSED] negative dst
[16:44:19] ============ [PASSED] drm_test_rect_calc_hscale ============
[16:44:19] ================ drm_test_rect_calc_vscale ================
[16:44:19] [PASSED] normal use
[16:44:19] [PASSED] out of max range
[16:44:19] [PASSED] out of min range
[16:44:19] [PASSED] zero dst
[16:44:19] [PASSED] negative src
[16:44:19] [PASSED] negative dst
[16:44:19] ============ [PASSED] drm_test_rect_calc_vscale ============
[16:44:19] ================== drm_test_rect_rotate ===================
[16:44:19] [PASSED] reflect-x
[16:44:19] [PASSED] reflect-y
[16:44:19] [PASSED] rotate-0
[16:44:19] [PASSED] rotate-90
[16:44:19] [PASSED] rotate-180
[16:44:19] [PASSED] rotate-270
[16:44:19] ============== [PASSED] drm_test_rect_rotate ===============
[16:44:19] ================ drm_test_rect_rotate_inv =================
[16:44:19] [PASSED] reflect-x
[16:44:19] [PASSED] reflect-y
[16:44:19] [PASSED] rotate-0
[16:44:19] [PASSED] rotate-90
[16:44:19] [PASSED] rotate-180
[16:44:19] [PASSED] rotate-270
[16:44:19] ============ [PASSED] drm_test_rect_rotate_inv =============
[16:44:19] ==================== [PASSED] drm_rect =====================
[16:44:19] ============ drm_sysfb_modeset_test (1 subtest) ============
[16:44:19] ============ drm_test_sysfb_build_fourcc_list =============
[16:44:19] [PASSED] no native formats
[16:44:19] [PASSED] XRGB8888 as native format
[16:44:19] [PASSED] remove duplicates
[16:44:19] [PASSED] convert alpha formats
[16:44:19] [PASSED] random formats
[16:44:19] ======== [PASSED] drm_test_sysfb_build_fourcc_list =========
[16:44:19] ============= [PASSED] drm_sysfb_modeset_test ==============
[16:44:19] ================== drm_fixp (2 subtests) ===================
[16:44:19] [PASSED] drm_test_int2fixp
[16:44:19] [PASSED] drm_test_sm2fixp
[16:44:19] ==================== [PASSED] drm_fixp =====================
[16:44:19] ============================================================
[16:44:19] Testing complete. Ran 671 tests: passed: 671
[16:44:19] Elapsed time: 27.143s total, 1.828s configuring, 24.844s building, 0.418s running
+ for kcfg in "${kunitconfigs[@]}"
+ [[ ! -f /kernel/drivers/gpu/drm/ttm/tests/.kunitconfig ]]
+ /kernel/tools/testing/kunit/kunit.py run --kunitconfig /kernel/drivers/gpu/drm/ttm/tests/.kunitconfig
[16:44:19] Configuring KUnit Kernel ...
Regenerating .config ...
Populating config with:
$ make ARCH=um O=.kunit olddefconfig
[16:44:21] Building KUnit Kernel ...
Populating config with:
$ make ARCH=um O=.kunit olddefconfig
Building with:
$ make all compile_commands.json scripts_gdb ARCH=um O=.kunit --jobs=48
[16:44:31] Starting KUnit Kernel (1/1)...
[16:44:31] ============================================================
Running tests with:
$ .kunit/linux kunit.enable=1 mem=1G console=tty kunit_shutdown=halt
[16:44:31] ============= refcount_interrupt (4 subtests) ==============
[16:44:31] [PASSED] test_single_irq_change
[16:44:31] [PASSED] test_nested_irq_change
[16:44:31] [PASSED] test_multiple_irq_change
[16:44:31] [PASSED] test_irq_save
[16:44:31] =============== [PASSED] refcount_interrupt ================
[16:44:31] ================= ttm_device (5 subtests) ==================
[16:44:31] [PASSED] ttm_device_init_basic
[16:44:31] [PASSED] ttm_device_init_multiple
[16:44:31] [PASSED] ttm_device_fini_basic
[16:44:31] [PASSED] ttm_device_init_no_vma_man
[16:44:31] ================== ttm_device_init_pools ==================
[16:44:31] [PASSED] No DMA allocations, no DMA32 required
[16:44:31] [PASSED] DMA allocations, DMA32 required
[16:44:31] [PASSED] No DMA allocations, DMA32 required
[16:44:31] [PASSED] DMA allocations, no DMA32 required
[16:44:31] ============== [PASSED] ttm_device_init_pools ==============
[16:44:31] =================== [PASSED] ttm_device ====================
[16:44:31] ================== ttm_pool (8 subtests) ===================
[16:44:31] ================== ttm_pool_alloc_basic ===================
[16:44:31] [PASSED] One page
[16:44:31] [PASSED] More than one page
[16:44:31] [PASSED] Above the allocation limit
[16:44:31] [PASSED] One page, with coherent DMA mappings enabled
[16:44:31] [PASSED] Above the allocation limit, with coherent DMA mappings enabled
[16:44:31] ============== [PASSED] ttm_pool_alloc_basic ===============
[16:44:31] ============== ttm_pool_alloc_basic_dma_addr ==============
[16:44:31] [PASSED] One page
[16:44:31] [PASSED] More than one page
[16:44:31] [PASSED] Above the allocation limit
[16:44:31] [PASSED] One page, with coherent DMA mappings enabled
[16:44:31] [PASSED] Above the allocation limit, with coherent DMA mappings enabled
[16:44:31] ========== [PASSED] ttm_pool_alloc_basic_dma_addr ==========
[16:44:31] [PASSED] ttm_pool_alloc_order_caching_match
[16:44:31] [PASSED] ttm_pool_alloc_caching_mismatch
[16:44:31] [PASSED] ttm_pool_alloc_order_mismatch
[16:44:31] [PASSED] ttm_pool_free_dma_alloc
[16:44:31] [PASSED] ttm_pool_free_no_dma_alloc
[16:44:31] [PASSED] ttm_pool_fini_basic
[16:44:31] ==================== [PASSED] ttm_pool =====================
[16:44:31] ================ ttm_resource (8 subtests) =================
[16:44:31] ================= ttm_resource_init_basic =================
[16:44:31] [PASSED] Init resource in TTM_PL_SYSTEM
[16:44:31] [PASSED] Init resource in TTM_PL_VRAM
[16:44:31] [PASSED] Init resource in a private placement
[16:44:31] [PASSED] Init resource in TTM_PL_SYSTEM, set placement flags
[16:44:31] ============= [PASSED] ttm_resource_init_basic =============
[16:44:31] [PASSED] ttm_resource_init_pinned
[16:44:31] [PASSED] ttm_resource_fini_basic
[16:44:31] [PASSED] ttm_resource_manager_init_basic
[16:44:31] [PASSED] ttm_resource_manager_usage_basic
[16:44:31] [PASSED] ttm_resource_manager_set_used_basic
[16:44:31] [PASSED] ttm_sys_man_alloc_basic
[16:44:31] [PASSED] ttm_sys_man_free_basic
[16:44:31] ================== [PASSED] ttm_resource ===================
[16:44:31] =================== ttm_tt (15 subtests) ===================
[16:44:31] ==================== ttm_tt_init_basic ====================
[16:44:31] [PASSED] Page-aligned size
[16:44:31] [PASSED] Extra pages requested
[16:44:31] ================ [PASSED] ttm_tt_init_basic ================
[16:44:31] [PASSED] ttm_tt_init_misaligned
[16:44:31] [PASSED] ttm_tt_fini_basic
[16:44:31] [PASSED] ttm_tt_fini_sg
[16:44:31] [PASSED] ttm_tt_fini_shmem
[16:44:31] [PASSED] ttm_tt_create_basic
[16:44:31] [PASSED] ttm_tt_create_invalid_bo_type
[16:44:31] [PASSED] ttm_tt_create_ttm_exists
[16:44:31] [PASSED] ttm_tt_create_failed
[16:44:31] [PASSED] ttm_tt_destroy_basic
[16:44:31] [PASSED] ttm_tt_populate_null_ttm
[16:44:31] [PASSED] ttm_tt_populate_populated_ttm
[16:44:31] [PASSED] ttm_tt_unpopulate_basic
[16:44:31] [PASSED] ttm_tt_unpopulate_empty_ttm
[16:44:31] [PASSED] ttm_tt_swapin_basic
[16:44:31] ===================== [PASSED] ttm_tt ======================
[16:44:31] =================== ttm_bo (14 subtests) ===================
[16:44:31] =========== ttm_bo_reserve_optimistic_no_ticket ===========
[16:44:31] [PASSED] Cannot be interrupted and sleeps
[16:44:31] [PASSED] Cannot be interrupted, locks straight away
[16:44:31] [PASSED] Can be interrupted, sleeps
[16:44:31] ======= [PASSED] ttm_bo_reserve_optimistic_no_ticket =======
[16:44:31] [PASSED] ttm_bo_reserve_locked_no_sleep
[16:44:31] [PASSED] ttm_bo_reserve_no_wait_ticket
[16:44:31] [PASSED] ttm_bo_reserve_double_resv
[16:44:31] [PASSED] ttm_bo_reserve_interrupted
[16:44:31] [PASSED] ttm_bo_reserve_deadlock
[16:44:31] [PASSED] ttm_bo_unreserve_basic
[16:44:31] [PASSED] ttm_bo_unreserve_pinned
[16:44:31] [PASSED] ttm_bo_unreserve_bulk
[16:44:31] [PASSED] ttm_bo_fini_basic
[16:44:31] [PASSED] ttm_bo_fini_shared_resv
[16:44:31] [PASSED] ttm_bo_pin_basic
[16:44:31] [PASSED] ttm_bo_pin_unpin_resource
[16:44:31] [PASSED] ttm_bo_multiple_pin_one_unpin
[16:44:31] ===================== [PASSED] ttm_bo ======================
[16:44:31] ============== ttm_bo_validate (22 subtests) ===============
[16:44:31] ============== ttm_bo_init_reserved_sys_man ===============
[16:44:31] [PASSED] Buffer object for userspace
[16:44:31] [PASSED] Kernel buffer object
[16:44:31] [PASSED] Shared buffer object
[16:44:31] ========== [PASSED] ttm_bo_init_reserved_sys_man ===========
[16:44:31] ============== ttm_bo_init_reserved_mock_man ==============
[16:44:31] [PASSED] Buffer object for userspace
[16:44:31] [PASSED] Kernel buffer object
[16:44:31] [PASSED] Shared buffer object
[16:44:31] ========== [PASSED] ttm_bo_init_reserved_mock_man ==========
[16:44:31] [PASSED] ttm_bo_init_reserved_resv
[16:44:31] ================== ttm_bo_validate_basic ==================
[16:44:31] [PASSED] Buffer object for userspace
[16:44:31] [PASSED] Kernel buffer object
[16:44:31] [PASSED] Shared buffer object
[16:44:31] ============== [PASSED] ttm_bo_validate_basic ==============
[16:44:31] [PASSED] ttm_bo_validate_invalid_placement
[16:44:31] ============= ttm_bo_validate_same_placement ==============
[16:44:31] [PASSED] System manager
[16:44:31] [PASSED] VRAM manager
[16:44:31] ========= [PASSED] ttm_bo_validate_same_placement ==========
[16:44:31] [PASSED] ttm_bo_validate_failed_alloc
[16:44:31] [PASSED] ttm_bo_validate_pinned
[16:44:31] [PASSED] ttm_bo_validate_busy_placement
[16:44:31] ================ ttm_bo_validate_multihop =================
[16:44:31] [PASSED] Buffer object for userspace
[16:44:31] [PASSED] Kernel buffer object
[16:44:31] [PASSED] Shared buffer object
[16:44:31] ============ [PASSED] ttm_bo_validate_multihop =============
[16:44:31] ========== ttm_bo_validate_no_placement_signaled ==========
[16:44:31] [PASSED] Buffer object in system domain, no page vector
[16:44:31] [PASSED] Buffer object in system domain with an existing page vector
[16:44:31] ====== [PASSED] ttm_bo_validate_no_placement_signaled ======
[16:44:31] ======== ttm_bo_validate_no_placement_not_signaled ========
[16:44:31] [PASSED] Buffer object for userspace
[16:44:31] [PASSED] Kernel buffer object
[16:44:31] [PASSED] Shared buffer object
[16:44:31] ==== [PASSED] ttm_bo_validate_no_placement_not_signaled ====
[16:44:31] [PASSED] ttm_bo_validate_move_fence_signaled
[16:44:31] ========= ttm_bo_validate_move_fence_not_signaled =========
[16:44:31] [PASSED] Waits for GPU
[16:44:31] [PASSED] Tries to lock straight away
[16:44:31] ===== [PASSED] ttm_bo_validate_move_fence_not_signaled =====
[16:44:31] [PASSED] ttm_bo_validate_swapout
[16:44:31] [PASSED] ttm_bo_validate_happy_evict
[16:44:31] [PASSED] ttm_bo_validate_all_pinned_evict
[16:44:31] [PASSED] ttm_bo_validate_allowed_only_evict
[16:44:31] [PASSED] ttm_bo_validate_deleted_evict
[16:44:31] [PASSED] ttm_bo_validate_busy_domain_evict
[16:44:31] [PASSED] ttm_bo_validate_evict_gutting
[16:44:31] [PASSED] ttm_bo_validate_recrusive_evict
[16:44:31] ================= [PASSED] ttm_bo_validate =================
[16:44:31] ============================================================
[16:44:31] Testing complete. Ran 106 tests: passed: 106
[16:44:31] Elapsed time: 12.114s total, 1.833s configuring, 10.066s building, 0.180s running
+ for kcfg in "${kunitconfigs[@]}"
+ [[ ! -f /kernel/drivers/dma-buf/.kunitconfig ]]
+ /kernel/tools/testing/kunit/kunit.py run --kunitconfig /kernel/drivers/dma-buf/.kunitconfig
[16:44:31] Configuring KUnit Kernel ...
Regenerating .config ...
Populating config with:
$ make ARCH=um O=.kunit olddefconfig
[16:44:33] Building KUnit Kernel ...
Populating config with:
$ make ARCH=um O=.kunit olddefconfig
Building with:
$ make all compile_commands.json scripts_gdb ARCH=um O=.kunit --jobs=48
[16:44:42] Starting KUnit Kernel (1/1)...
[16:44:42] ============================================================
Running tests with:
$ .kunit/linux kunit.enable=1 mem=1G console=tty kunit_shutdown=halt
[16:44:42] ============= refcount_interrupt (4 subtests) ==============
[16:44:42] [PASSED] test_single_irq_change
[16:44:42] [PASSED] test_nested_irq_change
[16:44:42] [PASSED] test_multiple_irq_change
[16:44:42] [PASSED] test_irq_save
[16:44:42] =============== [PASSED] refcount_interrupt ================
[16:44:42] =============== dma-buf-fence (12 subtests) ================
[16:44:42] [PASSED] test_sanitycheck
[16:44:42] [PASSED] test_signaling
[16:44:42] [PASSED] test_add_callback
[16:44:42] [PASSED] test_late_add_callback
[16:44:42] [PASSED] test_rm_callback
[16:44:42] [PASSED] test_late_rm_callback
[16:44:42] [PASSED] test_status
[16:44:42] [PASSED] test_error
[16:44:42] [PASSED] test_wait
[16:44:42] [PASSED] test_wait_timeout
[16:44:42] [PASSED] test_stub
[16:44:42] [SKIPPED] test_race_signal_callback (requires at least 2 CPUs)
[16:44:42] ================== [PASSED] dma-buf-fence ==================
[16:44:42] ============ dma-buf-fence-chain (11 subtests) =============
[16:44:42] [PASSED] test_sanitycheck
[16:44:42] [PASSED] test_find_seqno
[16:44:42] [PASSED] test_find_signaled
[16:44:42] [PASSED] test_find_out_of_order
[16:44:47] [PASSED] test_find_gap
[16:44:47] [PASSED] test_find_race
[16:44:47] [PASSED] test_signal_forward
[16:44:47] [PASSED] test_signal_backward
[16:44:47] [PASSED] test_wait_forward
[16:44:47] [PASSED] test_wait_backward
[16:44:47] [PASSED] test_wait_random
[16:44:47] =============== [PASSED] dma-buf-fence-chain ===============
[16:44:47] ============ dma-buf-fence-unwrap (10 subtests) ============
[16:44:47] [PASSED] test_sanitycheck
[16:44:47] [PASSED] test_unwrap_array
[16:44:47] [PASSED] test_unwrap_chain
[16:44:47] [PASSED] test_unwrap_chain_array
[16:44:47] [PASSED] test_unwrap_merge
[16:44:47] [PASSED] test_unwrap_merge_duplicate
[16:44:47] [PASSED] test_unwrap_merge_seqno
[16:44:47] [PASSED] test_unwrap_merge_order
[16:44:47] [PASSED] test_unwrap_merge_complex
[16:44:47] [PASSED] test_unwrap_merge_complex_seqno
[16:44:47] ============== [PASSED] dma-buf-fence-unwrap ===============
[16:44:47] ================ dma-buf-resv (5 subtests) =================
[16:44:47] [PASSED] test_sanitycheck
[16:44:47] ===================== test_signaling ======================
[16:44:47] [PASSED] kernel
[16:44:47] [PASSED] write
[16:44:47] [PASSED] read
[16:44:47] [PASSED] bookkeep
[16:44:47] ================= [PASSED] test_signaling ==================
[16:44:47] ====================== test_for_each ======================
[16:44:47] [PASSED] kernel
[16:44:47] [PASSED] write
[16:44:47] [PASSED] read
[16:44:47] [PASSED] bookkeep
[16:44:47] ================== [PASSED] test_for_each ==================
[16:44:47] ================= test_for_each_unlocked ==================
[16:44:47] [PASSED] kernel
[16:44:47] [PASSED] write
[16:44:47] [PASSED] read
[16:44:47] [PASSED] bookkeep
[16:44:47] ============= [PASSED] test_for_each_unlocked ==============
[16:44:47] ===================== test_get_fences =====================
[16:44:47] [PASSED] kernel
[16:44:47] [PASSED] write
[16:44:47] [PASSED] read
[16:44:47] [PASSED] bookkeep
[16:44:47] ================= [PASSED] test_get_fences =================
[16:44:47] ================== [PASSED] dma-buf-resv ===================
[16:44:47] ============================================================
[16:44:47] Testing complete. Ran 54 tests: passed: 53, skipped: 1
[16:44:47] Elapsed time: 15.765s total, 1.836s configuring, 8.657s building, 5.266s running
+ cleanup
++ stat -c %u:%g /kernel
+ chown -R 1003:1003 /kernel
^ permalink raw reply [flat|nested] 16+ messages in thread
* Re: [PATCH v4 1/3] drm/xe: Capture devcoredump on TLB invalidation timeout
2026-09-17 16:35 ` [PATCH v4 1/3] drm/xe: Capture devcoredump on TLB invalidation timeout Tales A. Mendonça
@ 2026-09-17 16:50 ` sashiko-bot
2026-09-17 23:18 ` Tales A. Mendonça
2026-09-18 22:01 ` Matthew Brost
1 sibling, 1 reply; 16+ messages in thread
From: sashiko-bot @ 2026-09-17 16:50 UTC (permalink / raw)
To: Tales A. Mendonça; +Cc: intel-xe, dri-devel
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Low] drm/xe: data race in xe_tlb_inval_fence_timeout() reading seqno_recv
--
commit ef794f6bbaafa679257b9fec9405245af4942e68
Author: Tales A. Mendonça <talesam@gmail.com>
drm/xe: Capture devcoredump on TLB invalidation timeout
This commit adds xe_devcoredump_gt(), a variant of xe_devcoredump() for hangs
that are not tied to an exec queue or job. It hooks this new capture mechanism
into the TLB invalidation timeout path to capture the GuC log and CT state.
Link: https://gitlab.freedesktop.org/drm/xe/kernel/-/work_items/8678
> diff --git a/drivers/gpu/drm/xe/xe_tlb_inval.c b/drivers/gpu/drm/xe/xe_tlb_inval.c
> index 7c3bf32d9258b..7a0c04fac60aa 100644
> --- a/drivers/gpu/drm/xe/xe_tlb_inval.c
> +++ b/drivers/gpu/drm/xe/xe_tlb_inval.c
[ ... ]
> @@ -97,6 +107,16 @@ static void xe_tlb_inval_fence_timeout(struct work_struct *work)
> queue_delayed_work(tlb_inval->timeout_wq, &tlb_inval->fence_tdr,
> timeout_delay);
> spin_unlock_irq(&tlb_inval->pending_lock);
> +
> + /*
> + * Capture the GuC log and CT state so the firmware side of the hang
> + * can be inspected; there is no queue or job to blame here. Must be
> + * outside pending_lock as the capture takes sleeping locks.
> + */
> + if (timedout_seqno)
> + xe_devcoredump_gt(tlb_inval_to_gt(tlb_inval),
> + "TLB invalidation fence timeout, seqno=%d recv=%d",
> + timedout_seqno, tlb_inval->seqno_recv);
[Severity: Low]
Does this code introduce a data race when reading tlb_inval->seqno_recv?
In xe_tlb_inval_fence_timeout() in drivers/gpu/drm/xe/xe_tlb_inval.c, the
pending_lock spinlock is dropped just before this block. Because seqno_recv
is read locklessly here, and concurrent updates (such as those in
xe_tlb_inval_done_handler()) use WRITE_ONCE(), reading it directly could
result in a data race.
Could this lead to KCSAN warnings or logging a corrupted value in the
devcoredump reason string? Would it be safer to read this using READ_ONCE()
or cache the value while the lock is held?
> }
>
> /**
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260917163553.1742580-1-talesam@gmail.com?part=1
^ permalink raw reply [flat|nested] 16+ messages in thread
* ✓ Xe.CI.BAT: success for drm/xe: fix GuC TLB invalidation ack stalls on ARL (Wa_22016122933) (rev3)
2026-09-17 16:35 [PATCH v4 0/3] drm/xe: fix GuC TLB invalidation ack stalls on ARL (Wa_22016122933) Tales A. Mendonça
` (4 preceding siblings ...)
2026-09-17 16:44 ` ✓ CI.KUnit: success " Patchwork
@ 2026-09-17 17:54 ` Patchwork
2026-09-17 18:45 ` ✓ Xe.CI.FULL: " Patchwork
6 siblings, 0 replies; 16+ messages in thread
From: Patchwork @ 2026-09-17 17:54 UTC (permalink / raw)
To: Tales A. Mendonça; +Cc: intel-xe
[-- Attachment #1: Type: text/plain, Size: 1457 bytes --]
== Series Details ==
Series: drm/xe: fix GuC TLB invalidation ack stalls on ARL (Wa_22016122933) (rev3)
URL : https://patchwork.freedesktop.org/series/172110/
State : success
== Summary ==
CI Bug Log - changes from xe-5765-d4289677143a2d09ce25eb883b0bf16fd7135840_BAT -> xe-pw-172110v3_BAT
====================================================
Summary
-------
**SUCCESS**
No regressions found.
Participating hosts (15 -> 15)
------------------------------
No changes in participating hosts
Known issues
------------
Here are the changes found in xe-pw-172110v3_BAT that come from known issues:
### IGT changes ###
#### Issues hit ####
* igt@core_hotunplug@unbind-rebind:
- bat-bmg-2: [PASS][1] -> [ABORT][2] ([Intel XE#8007])
[1]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-5765-d4289677143a2d09ce25eb883b0bf16fd7135840/bat-bmg-2/igt@core_hotunplug@unbind-rebind.html
[2]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-172110v3/bat-bmg-2/igt@core_hotunplug@unbind-rebind.html
[Intel XE#8007]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/8007
Build changes
-------------
* Linux: xe-5765-d4289677143a2d09ce25eb883b0bf16fd7135840 -> xe-pw-172110v3
IGT_9099: 9099
xe-5765-d4289677143a2d09ce25eb883b0bf16fd7135840: d4289677143a2d09ce25eb883b0bf16fd7135840
xe-pw-172110v3: 172110v3
== Logs ==
For more details see: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-172110v3/index.html
[-- Attachment #2: Type: text/html, Size: 2022 bytes --]
^ permalink raw reply [flat|nested] 16+ messages in thread
* ✓ Xe.CI.FULL: success for drm/xe: fix GuC TLB invalidation ack stalls on ARL (Wa_22016122933) (rev3)
2026-09-17 16:35 [PATCH v4 0/3] drm/xe: fix GuC TLB invalidation ack stalls on ARL (Wa_22016122933) Tales A. Mendonça
` (5 preceding siblings ...)
2026-09-17 17:54 ` ✓ Xe.CI.BAT: " Patchwork
@ 2026-09-17 18:45 ` Patchwork
6 siblings, 0 replies; 16+ messages in thread
From: Patchwork @ 2026-09-17 18:45 UTC (permalink / raw)
To: Tales A. Mendonça; +Cc: intel-xe
[-- Attachment #1: Type: text/plain, Size: 21479 bytes --]
== Series Details ==
Series: drm/xe: fix GuC TLB invalidation ack stalls on ARL (Wa_22016122933) (rev3)
URL : https://patchwork.freedesktop.org/series/172110/
State : success
== Summary ==
CI Bug Log - changes from xe-5765-d4289677143a2d09ce25eb883b0bf16fd7135840_FULL -> xe-pw-172110v3_FULL
====================================================
Summary
-------
**SUCCESS**
No regressions found.
Participating hosts (3 -> 3)
------------------------------
No changes in participating hosts
Known issues
------------
Here are the changes found in xe-pw-172110v3_FULL that come from known issues:
### IGT changes ###
#### Issues hit ####
* igt@kms_async_flips@alternate-sync-async-flip:
- shard-bmg: [PASS][1] -> [FAIL][2] ([Intel XE#3718] / [Intel XE#6078])
[1]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-5765-d4289677143a2d09ce25eb883b0bf16fd7135840/shard-bmg-5/igt@kms_async_flips@alternate-sync-async-flip.html
[2]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-172110v3/shard-bmg-5/igt@kms_async_flips@alternate-sync-async-flip.html
* igt@kms_async_flips@alternate-sync-async-flip@pipe-b-dp-2:
- shard-bmg: [PASS][3] -> [FAIL][4] ([Intel XE#6078])
[3]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-5765-d4289677143a2d09ce25eb883b0bf16fd7135840/shard-bmg-5/igt@kms_async_flips@alternate-sync-async-flip@pipe-b-dp-2.html
[4]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-172110v3/shard-bmg-5/igt@kms_async_flips@alternate-sync-async-flip@pipe-b-dp-2.html
* igt@kms_big_fb@linear-max-hw-stride-64bpp-rotate-0-hflip:
- shard-bmg: NOTRUN -> [SKIP][5] ([Intel XE#7059] / [Intel XE#7085])
[5]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-172110v3/shard-bmg-1/igt@kms_big_fb@linear-max-hw-stride-64bpp-rotate-0-hflip.html
* igt@kms_big_fb@yf-tiled-32bpp-rotate-0:
- shard-bmg: NOTRUN -> [SKIP][6] ([Intel XE#1124]) +4 other tests skip
[6]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-172110v3/shard-bmg-1/igt@kms_big_fb@yf-tiled-32bpp-rotate-0.html
* igt@kms_bw@connected-linear-tiling-3-displays-target-2160x1440p:
- shard-bmg: NOTRUN -> [SKIP][7] ([Intel XE#7679])
[7]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-172110v3/shard-bmg-5/igt@kms_bw@connected-linear-tiling-3-displays-target-2160x1440p.html
* igt@kms_ccs@bad-rotation-90-y-tiled-gen12-rc-ccs-cc:
- shard-bmg: NOTRUN -> [SKIP][8] ([Intel XE#2887]) +6 other tests skip
[8]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-172110v3/shard-bmg-1/igt@kms_ccs@bad-rotation-90-y-tiled-gen12-rc-ccs-cc.html
* igt@kms_chamelium_color@ctm-blue-to-red:
- shard-bmg: NOTRUN -> [SKIP][9] ([Intel XE#2325] / [Intel XE#7358])
[9]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-172110v3/shard-bmg-1/igt@kms_chamelium_color@ctm-blue-to-red.html
* igt@kms_chamelium_hpd@dp-hpd-after-suspend:
- shard-bmg: NOTRUN -> [SKIP][10] ([Intel XE#2252]) +3 other tests skip
[10]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-172110v3/shard-bmg-1/igt@kms_chamelium_hpd@dp-hpd-after-suspend.html
* igt@kms_color_pipeline@plane-lut1d-pre-ctm3x4@pipe-d-plane-4:
- shard-bmg: NOTRUN -> [SKIP][11] ([Intel XE#6969]) +7 other tests skip
[11]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-172110v3/shard-bmg-5/igt@kms_color_pipeline@plane-lut1d-pre-ctm3x4@pipe-d-plane-4.html
* igt@kms_content_protection@atomic-dpms-hdcp14@pipe-a-dp-2:
- shard-bmg: NOTRUN -> [FAIL][12] ([Intel XE#3304] / [Intel XE#7374]) +1 other test fail
[12]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-172110v3/shard-bmg-1/igt@kms_content_protection@atomic-dpms-hdcp14@pipe-a-dp-2.html
* igt@kms_content_protection@content-type-change:
- shard-bmg: NOTRUN -> [SKIP][13] ([Intel XE#7642])
[13]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-172110v3/shard-bmg-5/igt@kms_content_protection@content-type-change.html
* igt@kms_cursor_crc@cursor-offscreen-64x21:
- shard-bmg: NOTRUN -> [SKIP][14] ([Intel XE#2320])
[14]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-172110v3/shard-bmg-5/igt@kms_cursor_crc@cursor-offscreen-64x21.html
* igt@kms_cursor_crc@cursor-onscreen-512x170:
- shard-bmg: NOTRUN -> [SKIP][15] ([Intel XE#2321] / [Intel XE#7355])
[15]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-172110v3/shard-bmg-1/igt@kms_cursor_crc@cursor-onscreen-512x170.html
* igt@kms_dsc@dsc-fractional-bpp:
- shard-bmg: NOTRUN -> [SKIP][16] ([Intel XE#8265]) +1 other test skip
[16]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-172110v3/shard-bmg-1/igt@kms_dsc@dsc-fractional-bpp.html
* igt@kms_flip@2x-flip-vs-suspend-interruptible:
- shard-bmg: [PASS][17] -> [INCOMPLETE][18] ([Intel XE#2049] / [Intel XE#2597] / [Intel XE#8155]) +1 other test incomplete
[17]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-5765-d4289677143a2d09ce25eb883b0bf16fd7135840/shard-bmg-2/igt@kms_flip@2x-flip-vs-suspend-interruptible.html
[18]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-172110v3/shard-bmg-6/igt@kms_flip@2x-flip-vs-suspend-interruptible.html
* igt@kms_frontbuffer_tracking@fbc-2p-scndscrn-indfb-pgflip-blt:
- shard-bmg: NOTRUN -> [SKIP][19] ([Intel XE#4141]) +1 other test skip
[19]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-172110v3/shard-bmg-1/igt@kms_frontbuffer_tracking@fbc-2p-scndscrn-indfb-pgflip-blt.html
* igt@kms_frontbuffer_tracking@fbcdrrshdr-2p-primscrn-pri-shrfb-draw-mmap-wc:
- shard-bmg: NOTRUN -> [SKIP][20] ([Intel XE#2311]) +18 other tests skip
[20]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-172110v3/shard-bmg-5/igt@kms_frontbuffer_tracking@fbcdrrshdr-2p-primscrn-pri-shrfb-draw-mmap-wc.html
* igt@kms_frontbuffer_tracking@fbcdrrshdr-argb161616f-draw-blt:
- shard-bmg: NOTRUN -> [SKIP][21] ([Intel XE#7061]) +1 other test skip
[21]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-172110v3/shard-bmg-5/igt@kms_frontbuffer_tracking@fbcdrrshdr-argb161616f-draw-blt.html
* igt@kms_frontbuffer_tracking@fbcpsr-abgr161616f-draw-mmap-wc:
- shard-bmg: NOTRUN -> [SKIP][22] ([Intel XE#7061] / [Intel XE#7356])
[22]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-172110v3/shard-bmg-5/igt@kms_frontbuffer_tracking@fbcpsr-abgr161616f-draw-mmap-wc.html
* igt@kms_frontbuffer_tracking@psrhdr-rgb565-draw-render:
- shard-bmg: NOTRUN -> [SKIP][23] ([Intel XE#2313]) +25 other tests skip
[23]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-172110v3/shard-bmg-1/igt@kms_frontbuffer_tracking@psrhdr-rgb565-draw-render.html
* igt@kms_plane@pixel-format-4-tiled-mtl-rc-ccs-modifier-source-clamping:
- shard-bmg: NOTRUN -> [SKIP][24] ([Intel XE#7283]) +3 other tests skip
[24]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-172110v3/shard-bmg-1/igt@kms_plane@pixel-format-4-tiled-mtl-rc-ccs-modifier-source-clamping.html
* igt@kms_plane_scaling@planes-upscale-factor-0-25-downscale-factor-0-75:
- shard-bmg: NOTRUN -> [SKIP][25] ([Intel XE#2763] / [Intel XE#6886]) +4 other tests skip
[25]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-172110v3/shard-bmg-1/igt@kms_plane_scaling@planes-upscale-factor-0-25-downscale-factor-0-75.html
* igt@kms_pm_rpm@package-g7:
- shard-bmg: NOTRUN -> [SKIP][26] ([Intel XE#6814] / [Intel XE#7428])
[26]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-172110v3/shard-bmg-5/igt@kms_pm_rpm@package-g7.html
* igt@kms_pm_rpm@system-suspend-modeset:
- shard-bmg: [PASS][27] -> [INCOMPLETE][28] ([Intel XE#9241])
[27]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-5765-d4289677143a2d09ce25eb883b0bf16fd7135840/shard-bmg-3/igt@kms_pm_rpm@system-suspend-modeset.html
[28]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-172110v3/shard-bmg-6/igt@kms_pm_rpm@system-suspend-modeset.html
* igt@kms_psr2_sf@fbc-psr2-overlay-primary-update-sf-dmg-area:
- shard-bmg: NOTRUN -> [SKIP][29] ([Intel XE#1489]) +2 other tests skip
[29]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-172110v3/shard-bmg-5/igt@kms_psr2_sf@fbc-psr2-overlay-primary-update-sf-dmg-area.html
* igt@kms_psr@psr-cursor-plane-onoff:
- shard-bmg: NOTRUN -> [SKIP][30] ([Intel XE#2234] / [Intel XE#2850]) +3 other tests skip
[30]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-172110v3/shard-bmg-1/igt@kms_psr@psr-cursor-plane-onoff.html
* igt@kms_rotation_crc@bad-pixel-format:
- shard-bmg: NOTRUN -> [SKIP][31] ([Intel XE#3904] / [Intel XE#7342])
[31]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-172110v3/shard-bmg-1/igt@kms_rotation_crc@bad-pixel-format.html
* igt@kms_rotation_crc@primary-yf-tiled-reflect-x-0:
- shard-bmg: NOTRUN -> [SKIP][32] ([Intel XE#2330] / [Intel XE#5813])
[32]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-172110v3/shard-bmg-5/igt@kms_rotation_crc@primary-yf-tiled-reflect-x-0.html
* igt@kms_vrr@seamless-rr-switch-drrs:
- shard-bmg: NOTRUN -> [SKIP][33] ([Intel XE#1499] / [Intel XE#9271])
[33]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-172110v3/shard-bmg-1/igt@kms_vrr@seamless-rr-switch-drrs.html
* igt@xe_exec_basic@multigpu-many-execqueues-many-vm-basic-defer-mmap:
- shard-bmg: NOTRUN -> [SKIP][34] ([Intel XE#2322] / [Intel XE#7372]) +2 other tests skip
[34]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-172110v3/shard-bmg-1/igt@xe_exec_basic@multigpu-many-execqueues-many-vm-basic-defer-mmap.html
* igt@xe_exec_fault_mode@many-execqueues-multi-queue-userptr-invalidate-imm:
- shard-bmg: NOTRUN -> [SKIP][35] ([Intel XE#8374]) +6 other tests skip
[35]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-172110v3/shard-bmg-5/igt@xe_exec_fault_mode@many-execqueues-multi-queue-userptr-invalidate-imm.html
* igt@xe_exec_multi_queue@two-queues-preempt-mode-fault-dyn-priority-smem:
- shard-bmg: NOTRUN -> [SKIP][36] ([Intel XE#8364]) +12 other tests skip
[36]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-172110v3/shard-bmg-1/igt@xe_exec_multi_queue@two-queues-preempt-mode-fault-dyn-priority-smem.html
* igt@xe_exec_threads@threads-hang-fd-userptr-invalidate-race:
- shard-bmg: NOTRUN -> [FAIL][37] ([Intel XE#9096])
[37]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-172110v3/shard-bmg-5/igt@xe_exec_threads@threads-hang-fd-userptr-invalidate-race.html
* igt@xe_exec_threads@threads-multi-queue-hang-fd-userptr-invalidate-race:
- shard-bmg: NOTRUN -> [SKIP][38] ([Intel XE#8378]) +3 other tests skip
[38]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-172110v3/shard-bmg-5/igt@xe_exec_threads@threads-multi-queue-hang-fd-userptr-invalidate-race.html
* igt@xe_oa@oa-tlb-invalidate:
- shard-bmg: NOTRUN -> [SKIP][39] ([Intel XE#2248] / [Intel XE#7325] / [Intel XE#7393])
[39]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-172110v3/shard-bmg-5/igt@xe_oa@oa-tlb-invalidate.html
* igt@xe_pat@xa-app-transient-media-on:
- shard-bmg: NOTRUN -> [SKIP][40] ([Intel XE#7590])
[40]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-172110v3/shard-bmg-1/igt@xe_pat@xa-app-transient-media-on.html
* igt@xe_pm@d3cold-basic-exec:
- shard-bmg: NOTRUN -> [SKIP][41] ([Intel XE#2284] / [Intel XE#7370])
[41]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-172110v3/shard-bmg-1/igt@xe_pm@d3cold-basic-exec.html
* igt@xe_pmu@all-fn-engine-activity-load:
- shard-bmg: [PASS][42] -> [FAIL][43] ([Intel XE#7992])
[42]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-5765-d4289677143a2d09ce25eb883b0bf16fd7135840/shard-bmg-3/igt@xe_pmu@all-fn-engine-activity-load.html
[43]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-172110v3/shard-bmg-10/igt@xe_pmu@all-fn-engine-activity-load.html
* igt@xe_query@multigpu-query-pxp-status:
- shard-bmg: NOTRUN -> [SKIP][44] ([Intel XE#944])
[44]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-172110v3/shard-bmg-1/igt@xe_query@multigpu-query-pxp-status.html
* igt@xe_wedged@wedged-mode-toggle:
- shard-bmg: [PASS][45] -> [ABORT][46] ([Intel XE#8007])
[45]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-5765-d4289677143a2d09ce25eb883b0bf16fd7135840/shard-bmg-8/igt@xe_wedged@wedged-mode-toggle.html
[46]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-172110v3/shard-bmg-2/igt@xe_wedged@wedged-mode-toggle.html
#### Possible fixes ####
* igt@kms_flip@flip-vs-expired-vblank@a-edp1:
- {shard-ptl}: [FAIL][47] ([Intel XE#3321]) -> [PASS][48] +1 other test pass
[47]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-5765-d4289677143a2d09ce25eb883b0bf16fd7135840/shard-ptl-7/igt@kms_flip@flip-vs-expired-vblank@a-edp1.html
[48]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-172110v3/shard-ptl-3/igt@kms_flip@flip-vs-expired-vblank@a-edp1.html
* igt@kms_vrr@flip-dpms@pipe-a-edp-1:
- {shard-ptl}: [FAIL][49] ([Intel XE#4227] / [Intel XE#7397]) -> [PASS][50] +1 other test pass
[49]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-5765-d4289677143a2d09ce25eb883b0bf16fd7135840/shard-ptl-8/igt@kms_vrr@flip-dpms@pipe-a-edp-1.html
[50]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-172110v3/shard-ptl-4/igt@kms_vrr@flip-dpms@pipe-a-edp-1.html
* igt@xe_module_load@force-load:
- shard-bmg: [ABORT][51] ([Intel XE#8007]) -> [PASS][52] +1 other test pass
[51]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-5765-d4289677143a2d09ce25eb883b0bf16fd7135840/shard-bmg-7/igt@xe_module_load@force-load.html
[52]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-172110v3/shard-bmg-1/igt@xe_module_load@force-load.html
#### Warnings ####
* igt@kms_hdr@brightness-with-hdr:
- shard-bmg: [SKIP][53] ([Intel XE#3374] / [Intel XE#3544]) -> [SKIP][54] ([Intel XE#3544])
[53]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-5765-d4289677143a2d09ce25eb883b0bf16fd7135840/shard-bmg-8/igt@kms_hdr@brightness-with-hdr.html
[54]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-172110v3/shard-bmg-3/igt@kms_hdr@brightness-with-hdr.html
* igt@kms_tiled_display@basic-test-pattern:
- shard-bmg: [SKIP][55] ([Intel XE#2426] / [Intel XE#5848]) -> [FAIL][56] ([Intel XE#1729] / [Intel XE#7424])
[55]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-5765-d4289677143a2d09ce25eb883b0bf16fd7135840/shard-bmg-9/igt@kms_tiled_display@basic-test-pattern.html
[56]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-172110v3/shard-bmg-1/igt@kms_tiled_display@basic-test-pattern.html
* igt@xe_exec_reset@gt-reset-fault-injection:
- shard-lnl: [DMESG-WARN][57] ([Intel XE#9130]) -> [ABORT][58] ([Intel XE#9140] / [Intel XE#9145])
[57]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-5765-d4289677143a2d09ce25eb883b0bf16fd7135840/shard-lnl-5/igt@xe_exec_reset@gt-reset-fault-injection.html
[58]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-172110v3/shard-lnl-1/igt@xe_exec_reset@gt-reset-fault-injection.html
{name}: This element is suppressed. This means it is ignored when computing
the status of the difference (SUCCESS, WARNING, or FAILURE).
[Intel XE#1124]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/1124
[Intel XE#1489]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/1489
[Intel XE#1499]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/1499
[Intel XE#1729]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/1729
[Intel XE#2049]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2049
[Intel XE#2234]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2234
[Intel XE#2248]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2248
[Intel XE#2252]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2252
[Intel XE#2284]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2284
[Intel XE#2311]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2311
[Intel XE#2313]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2313
[Intel XE#2320]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2320
[Intel XE#2321]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2321
[Intel XE#2322]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2322
[Intel XE#2325]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2325
[Intel XE#2330]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2330
[Intel XE#2426]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2426
[Intel XE#2597]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2597
[Intel XE#2763]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2763
[Intel XE#2850]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2850
[Intel XE#2887]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2887
[Intel XE#3304]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/3304
[Intel XE#3321]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/3321
[Intel XE#3374]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/3374
[Intel XE#3544]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/3544
[Intel XE#3718]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/3718
[Intel XE#3904]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/3904
[Intel XE#4141]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/4141
[Intel XE#4227]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/4227
[Intel XE#5575]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/5575
[Intel XE#5764]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/5764
[Intel XE#5812]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/5812
[Intel XE#5813]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/5813
[Intel XE#5822]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/5822
[Intel XE#5848]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/5848
[Intel XE#5867]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/5867
[Intel XE#6078]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/6078
[Intel XE#6293]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/6293
[Intel XE#6814]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/6814
[Intel XE#6886]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/6886
[Intel XE#6969]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/6969
[Intel XE#7059]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7059
[Intel XE#7061]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7061
[Intel XE#7085]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7085
[Intel XE#7283]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7283
[Intel XE#7325]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7325
[Intel XE#7342]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7342
[Intel XE#7355]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7355
[Intel XE#7356]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7356
[Intel XE#7358]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7358
[Intel XE#7370]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7370
[Intel XE#7372]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7372
[Intel XE#7374]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7374
[Intel XE#7393]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7393
[Intel XE#7397]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7397
[Intel XE#7424]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7424
[Intel XE#7428]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7428
[Intel XE#7482]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7482
[Intel XE#7484]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7484
[Intel XE#7590]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7590
[Intel XE#7642]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7642
[Intel XE#7679]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7679
[Intel XE#7992]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7992
[Intel XE#8007]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/8007
[Intel XE#8155]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/8155
[Intel XE#8265]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/8265
[Intel XE#8364]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/8364
[Intel XE#8369]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/8369
[Intel XE#8374]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/8374
[Intel XE#8378]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/8378
[Intel XE#9096]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/9096
[Intel XE#9130]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/9130
[Intel XE#9140]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/9140
[Intel XE#9145]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/9145
[Intel XE#9241]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/9241
[Intel XE#9271]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/9271
[Intel XE#944]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/944
Build changes
-------------
* Linux: xe-5765-d4289677143a2d09ce25eb883b0bf16fd7135840 -> xe-pw-172110v3
IGT_9099: 9099
xe-5765-d4289677143a2d09ce25eb883b0bf16fd7135840: d4289677143a2d09ce25eb883b0bf16fd7135840
xe-pw-172110v3: 172110v3
== Logs ==
For more details see: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-172110v3/index.html
[-- Attachment #2: Type: text/html, Size: 22507 bytes --]
^ permalink raw reply [flat|nested] 16+ messages in thread
* Re: [PATCH v4 1/3] drm/xe: Capture devcoredump on TLB invalidation timeout
2026-09-17 16:50 ` sashiko-bot
@ 2026-09-17 23:18 ` Tales A. Mendonça
0 siblings, 0 replies; 16+ messages in thread
From: Tales A. Mendonça @ 2026-09-17 23:18 UTC (permalink / raw)
To: sashiko-reviews; +Cc: intel-xe, dri-devel
Good catch - that read is genuinely racy, and it is my patch that
introduced it. seqno_recv is written with WRITE_ONCE() from
xe_tlb_inval_done_handler(), and I deliberately moved the devcoredump
call outside pending_lock (the capture takes sleeping locks), which
left the read unsynchronised.
Fixed locally by sampling it while the lock is still held:
seqno_recv = tlb_inval->seqno_recv;
spin_unlock_irq(&tlb_inval->pending_lock);
...
if (timedout_seqno)
xe_devcoredump_gt(tlb_inval_to_gt(tlb_inval),
"TLB invalidation fence timeout,
seqno=%d recv=%d",
timedout_seqno, seqno_recv);
This will be in v5, together with any other review feedback.
Em qui., 17 de set. de 2026 às 13:50, <sashiko-bot@kernel.org> escreveu:
>
> Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
> - [Low] drm/xe: data race in xe_tlb_inval_fence_timeout() reading seqno_recv
> --
>
> commit ef794f6bbaafa679257b9fec9405245af4942e68
> Author: Tales A. Mendonça <talesam@gmail.com>
>
> drm/xe: Capture devcoredump on TLB invalidation timeout
>
> This commit adds xe_devcoredump_gt(), a variant of xe_devcoredump() for hangs
> that are not tied to an exec queue or job. It hooks this new capture mechanism
> into the TLB invalidation timeout path to capture the GuC log and CT state.
>
> Link: https://gitlab.freedesktop.org/drm/xe/kernel/-/work_items/8678
>
> > diff --git a/drivers/gpu/drm/xe/xe_tlb_inval.c b/drivers/gpu/drm/xe/xe_tlb_inval.c
> > index 7c3bf32d9258b..7a0c04fac60aa 100644
> > --- a/drivers/gpu/drm/xe/xe_tlb_inval.c
> > +++ b/drivers/gpu/drm/xe/xe_tlb_inval.c
> [ ... ]
> > @@ -97,6 +107,16 @@ static void xe_tlb_inval_fence_timeout(struct work_struct *work)
> > queue_delayed_work(tlb_inval->timeout_wq, &tlb_inval->fence_tdr,
> > timeout_delay);
> > spin_unlock_irq(&tlb_inval->pending_lock);
> > +
> > + /*
> > + * Capture the GuC log and CT state so the firmware side of the hang
> > + * can be inspected; there is no queue or job to blame here. Must be
> > + * outside pending_lock as the capture takes sleeping locks.
> > + */
> > + if (timedout_seqno)
> > + xe_devcoredump_gt(tlb_inval_to_gt(tlb_inval),
> > + "TLB invalidation fence timeout, seqno=%d recv=%d",
> > + timedout_seqno, tlb_inval->seqno_recv);
>
> [Severity: Low]
> Does this code introduce a data race when reading tlb_inval->seqno_recv?
>
> In xe_tlb_inval_fence_timeout() in drivers/gpu/drm/xe/xe_tlb_inval.c, the
> pending_lock spinlock is dropped just before this block. Because seqno_recv
> is read locklessly here, and concurrent updates (such as those in
> xe_tlb_inval_done_handler()) use WRITE_ONCE(), reading it directly could
> result in a data race.
>
> Could this lead to KCSAN warnings or logging a corrupted value in the
> devcoredump reason string? Would it be safer to read this using READ_ONCE()
> or cache the value while the lock is held?
>
> > }
> >
> > /**
>
> --
> Sashiko AI review · https://sashiko.dev/#/patchset/20260917163553.1742580-1-talesam@gmail.com?part=1
--
Com os cumprimentos,
Tales A. Mendonça
talesam.org
communitybig.org
^ permalink raw reply [flat|nested] 16+ messages in thread
* Re: [PATCH v4 1/3] drm/xe: Capture devcoredump on TLB invalidation timeout
2026-09-17 16:35 ` [PATCH v4 1/3] drm/xe: Capture devcoredump on TLB invalidation timeout Tales A. Mendonça
2026-09-17 16:50 ` sashiko-bot
@ 2026-09-18 22:01 ` Matthew Brost
2026-09-21 18:06 ` Tales A. Mendonça
1 sibling, 1 reply; 16+ messages in thread
From: Matthew Brost @ 2026-09-18 22:01 UTC (permalink / raw)
To: Tales A. Mendonça
Cc: intel-xe, daniele.ceraolospurio, stuart.summers, julia.filipchuk,
thomas.hellstrom, rodrigo.vivi, jani.nikula, navonjohnlukose,
dri-devel
On Thu, Sep 17, 2026 at 01:35:51PM -0300, Tales A. Mendonça wrote:
> TLB invalidation timeouts currently leave no record of the firmware
> state behind: there is no exec queue or job to blame, so nothing calls
> xe_devcoredump() and the GuC log content at the time of the hang is
> lost.
>
> Add xe_devcoredump_gt(), a variant of xe_devcoredump() for hangs that
> are not tied to an exec queue or job. It captures the GuC log and CT
> state of the affected GT, reusing the existing snapshot machinery and
> the "only first snapshot" policy, and hook it up to the TLB invalidation
> timeout path.
>
> This was instrumental in diagnosing GuC TLB invalidation ack stalls on
> ARL (see Link), where the invalidation request is consumed from the H2G
> CTB immediately but the ack G2H only arrives ~2.3s later, after the
> timeout has already fired.
>
> Link: https://gitlab.freedesktop.org/drm/xe/kernel/-/work_items/8678
> Signed-off-by: Tales A. Mendonça <talesam@gmail.com>
With your v5 fix Sashiko pointed out:
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
> ---
> drivers/gpu/drm/xe/xe_devcoredump.c | 46 ++++++++++++++++-------------
> drivers/gpu/drm/xe/xe_devcoredump.h | 15 +++++++---
> drivers/gpu/drm/xe/xe_tlb_inval.c | 20 +++++++++++++
> 3 files changed, 56 insertions(+), 25 deletions(-)
>
> diff --git a/drivers/gpu/drm/xe/xe_devcoredump.c b/drivers/gpu/drm/xe/xe_devcoredump.c
> index 5f2b90b18f9..6bee8933f95 100644
> --- a/drivers/gpu/drm/xe/xe_devcoredump.c
> +++ b/drivers/gpu/drm/xe/xe_devcoredump.c
> @@ -74,11 +74,6 @@ static struct xe_device *coredump_to_xe(const struct xe_devcoredump *coredump)
> return container_of(coredump, struct xe_device, devcoredump);
> }
>
> -static struct xe_guc *exec_queue_to_guc(struct xe_exec_queue *q)
> -{
> - return &q->gt->uc.guc;
> -}
> -
> static ssize_t __xe_devcoredump_read(char *buffer, ssize_t count,
> ssize_t start,
> struct xe_devcoredump *coredump)
> @@ -323,40 +318,44 @@ static void xe_devcoredump_deferred_snap_work(struct work_struct *work)
> }
>
> static void devcoredump_snapshot(struct xe_devcoredump *coredump,
> + struct xe_gt *gt,
> struct xe_exec_queue *q,
> struct xe_sched_job *job)
> {
> struct xe_devcoredump_snapshot *ss = &coredump->snapshot;
> - struct xe_guc *guc = exec_queue_to_guc(q);
> + struct xe_guc *guc = >->uc.guc;
> const char *process_name = "no process";
> bool cookie;
>
> ss->snapshot_time = ktime_get_real();
> ss->boot_time = ktime_get_boottime();
>
> - if (q->vm && q->vm->xef) {
> + if (q && q->vm && q->vm->xef) {
> process_name = q->vm->xef->process_name;
> ss->pid = q->vm->xef->pid;
> }
>
> strscpy(ss->process_name, process_name);
>
> - ss->gt = q->gt;
> + ss->gt = gt;
> INIT_WORK(&ss->work, xe_devcoredump_deferred_snap_work);
>
> /* keep going if fw fails as we still want to save the memory and SW data */
> - CLASS(xe_force_wake, fw_ref)(gt_to_fw(q->gt), XE_FORCEWAKE_ALL);
> + CLASS(xe_force_wake, fw_ref)(gt_to_fw(gt), XE_FORCEWAKE_ALL);
>
> cookie = dma_fence_begin_signalling();
>
> ss->guc.log = xe_guc_log_snapshot_capture(&guc->log, true);
> ss->guc.ct = xe_guc_ct_snapshot_capture(&guc->ct);
> - ss->ge = xe_guc_exec_queue_snapshot_capture(q);
> - if (job)
> - ss->job = xe_sched_job_snapshot_capture(job);
> - ss->vm = xe_vm_snapshot_capture(q->vm);
>
> - xe_engine_snapshot_capture_for_queue(q);
> + if (q) {
> + ss->ge = xe_guc_exec_queue_snapshot_capture(q);
> + if (job)
> + ss->job = xe_sched_job_snapshot_capture(job);
> + ss->vm = xe_vm_snapshot_capture(q->vm);
> +
> + xe_engine_snapshot_capture_for_queue(q);
> + }
>
> queue_work(system_dfl_wq, &ss->work);
>
> @@ -364,19 +363,24 @@ static void devcoredump_snapshot(struct xe_devcoredump *coredump,
> }
>
> /**
> - * xe_devcoredump - Take the required snapshots and initialize coredump device.
> - * @q: The faulty xe_exec_queue, where the issue was detected.
> - * @job: The faulty xe_sched_job, where the issue was detected.
> + * __xe_devcoredump - Take the required snapshots and initialize coredump device.
> + * @gt: The GT where the issue was detected.
> + * @q: The faulty xe_exec_queue, where the issue was detected, may be NULL for
> + * hangs that are not tied to an exec queue (e.g. TLB invalidation
> + * timeouts); in that case only the GT-level state (GuC log and CT state)
> + * is captured.
> + * @job: The faulty xe_sched_job, where the issue was detected, may be NULL.
> * @fmt: Printf format + args to describe the reason for the core dump
> *
> * This function should be called at the crash time within the serialized
> * gt_reset. It is skipped if we still have the core dump device available
> * with the information of the 'first' snapshot.
> */
> -__printf(3, 4)
> -void xe_devcoredump(struct xe_exec_queue *q, struct xe_sched_job *job, const char *fmt, ...)
> +__printf(4, 5)
> +void __xe_devcoredump(struct xe_gt *gt, struct xe_exec_queue *q,
> + struct xe_sched_job *job, const char *fmt, ...)
> {
> - struct xe_device *xe = gt_to_xe(q->gt);
> + struct xe_device *xe = gt_to_xe(gt);
> struct xe_devcoredump *coredump = &xe->devcoredump;
> va_list varg;
>
> @@ -394,7 +398,7 @@ void xe_devcoredump(struct xe_exec_queue *q, struct xe_sched_job *job, const cha
> coredump->snapshot.reason = kvasprintf(GFP_ATOMIC, fmt, varg);
> va_end(varg);
>
> - devcoredump_snapshot(coredump, q, job);
> + devcoredump_snapshot(coredump, gt, q, job);
>
> drm_info(&xe->drm, "Xe device coredump has been created\n");
> drm_info(&xe->drm, "Check your /sys/class/drm/card%d/device/devcoredump/data\n",
> diff --git a/drivers/gpu/drm/xe/xe_devcoredump.h b/drivers/gpu/drm/xe/xe_devcoredump.h
> index 5391a80a4d1..bc4800b3a3f 100644
> --- a/drivers/gpu/drm/xe/xe_devcoredump.h
> +++ b/drivers/gpu/drm/xe/xe_devcoredump.h
> @@ -11,15 +11,17 @@
> struct drm_printer;
> struct xe_device;
> struct xe_exec_queue;
> +struct xe_gt;
> struct xe_sched_job;
>
> #ifdef CONFIG_DEV_COREDUMP
> -void xe_devcoredump(struct xe_exec_queue *q, struct xe_sched_job *job, const char *fmt, ...);
> +void __xe_devcoredump(struct xe_gt *gt, struct xe_exec_queue *q,
> + struct xe_sched_job *job, const char *fmt, ...);
> int xe_devcoredump_init(struct xe_device *xe);
> #else
> -static inline void xe_devcoredump(struct xe_exec_queue *q,
> - struct xe_sched_job *job,
> - const char *fmt, ...)
> +static inline void __xe_devcoredump(struct xe_gt *gt, struct xe_exec_queue *q,
> + struct xe_sched_job *job,
> + const char *fmt, ...)
> {
> }
>
> @@ -29,6 +31,11 @@ static inline int xe_devcoredump_init(struct xe_device *xe)
> }
> #endif
>
> +#define xe_devcoredump(_q, _job, _fmt, ...) \
> + __xe_devcoredump((_q)->gt, _q, _job, _fmt, ##__VA_ARGS__)
> +#define xe_devcoredump_gt(_gt, _fmt, ...) \
> + __xe_devcoredump(_gt, NULL, NULL, _fmt, ##__VA_ARGS__)
> +
> void xe_print_blob_ascii85(struct drm_printer *p, const char *prefix, char suffix,
> const void *blob, size_t offset, size_t size);
>
> diff --git a/drivers/gpu/drm/xe/xe_tlb_inval.c b/drivers/gpu/drm/xe/xe_tlb_inval.c
> index 7c3bf32d925..7a0c04fac60 100644
> --- a/drivers/gpu/drm/xe/xe_tlb_inval.c
> +++ b/drivers/gpu/drm/xe/xe_tlb_inval.c
> @@ -5,6 +5,7 @@
>
> #include <drm/drm_managed.h>
>
> +#include "xe_devcoredump.h"
> #include "xe_device_types.h"
> #include "xe_force_wake.h"
> #include "xe_gt_stats.h"
> @@ -29,6 +30,12 @@
>
> #define FENCE_STACK_BIT DMA_FENCE_FLAG_USER_BITS
>
> +/* The frontend is only ever embedded in a GT */
> +static struct xe_gt *tlb_inval_to_gt(struct xe_tlb_inval *tlb_inval)
> +{
> + return container_of(tlb_inval, struct xe_gt, tlb_inval);
> +}
> +
> static void xe_tlb_inval_fence_fini(struct xe_tlb_inval_fence *fence)
> {
> if (WARN_ON_ONCE(!fence->tlb_inval))
> @@ -73,6 +80,7 @@ static void xe_tlb_inval_fence_timeout(struct work_struct *work)
> struct xe_device *xe = tlb_inval->xe;
> struct xe_tlb_inval_fence *fence, *next;
> long timeout_delay = tlb_inval->ops->timeout_delay(tlb_inval);
> + int timedout_seqno = 0;
>
> tlb_inval->ops->flush(tlb_inval);
>
> @@ -90,6 +98,8 @@ static void xe_tlb_inval_fence_timeout(struct work_struct *work)
> "TLB invalidation fence timeout, seqno=%d recv=%d",
> fence->seqno, tlb_inval->seqno_recv);
>
> + timedout_seqno = fence->seqno;
> +
> fence->base.error = -ETIME;
> xe_tlb_inval_fence_signal(fence);
> }
> @@ -97,6 +107,16 @@ static void xe_tlb_inval_fence_timeout(struct work_struct *work)
> queue_delayed_work(tlb_inval->timeout_wq, &tlb_inval->fence_tdr,
> timeout_delay);
> spin_unlock_irq(&tlb_inval->pending_lock);
> +
> + /*
> + * Capture the GuC log and CT state so the firmware side of the hang
> + * can be inspected; there is no queue or job to blame here. Must be
> + * outside pending_lock as the capture takes sleeping locks.
> + */
> + if (timedout_seqno)
> + xe_devcoredump_gt(tlb_inval_to_gt(tlb_inval),
> + "TLB invalidation fence timeout, seqno=%d recv=%d",
> + timedout_seqno, tlb_inval->seqno_recv);
> }
>
> /**
> --
> 2.55.0
>
^ permalink raw reply [flat|nested] 16+ messages in thread
* Re: [PATCH v4 2/3] drm/xe: Log when a timed out TLB invalidation ack finally arrives
2026-09-17 16:35 ` [PATCH v4 2/3] drm/xe: Log when a timed out TLB invalidation ack finally arrives Tales A. Mendonça
@ 2026-09-18 22:06 ` Matthew Brost
2026-09-21 5:30 ` Matthew Brost
0 siblings, 1 reply; 16+ messages in thread
From: Matthew Brost @ 2026-09-18 22:06 UTC (permalink / raw)
To: Tales A. Mendonça
Cc: intel-xe, daniele.ceraolospurio, stuart.summers, julia.filipchuk,
thomas.hellstrom, rodrigo.vivi, jani.nikula, navonjohnlukose,
dri-devel
On Thu, Sep 17, 2026 at 01:35:52PM -0300, Tales A. Mendonça wrote:
> When a TLB invalidation fence times out we log the timeout, but if the
> ack for that seqno later shows up there is no record of it, making it
> impossible to tell from logs whether the ack was lost forever or merely
> (very) late.
>
> Track the most recent timed out seqno and log how late its ack arrives,
> relative to both the original request and the moment the fence was
> signaled with -ETIME.
>
> On ARL with GuC 70.53.0 this shows the acks are never lost: they
> consistently arrive ~2.3s after the request, tens of milliseconds after
> the TDR has already signaled the fence:
>
> TLB invalidation fence timeout, seqno=10992 recv=10991
> TLB invalidation late ack: seqno=10992 recv=10992,
> request-to-ack=2314ms, timeout-to-ack=45ms
>
> Link: https://gitlab.freedesktop.org/drm/xe/kernel/-/work_items/8678
> Signed-off-by: Tales A. Mendonça <talesam@gmail.com>
I would give this an RB but my colleagues have done a bunch of work on
SIGID and I haven't been involved at all, so I need some help here.
> ---
> drivers/gpu/drm/xe/xe_tlb_inval.c | 19 +++++++++++++++++++
> drivers/gpu/drm/xe/xe_tlb_inval_types.h | 17 +++++++++++++++++
> 2 files changed, 36 insertions(+)
>
> diff --git a/drivers/gpu/drm/xe/xe_tlb_inval.c b/drivers/gpu/drm/xe/xe_tlb_inval.c
> index 7a0c04fac60..7047a347551 100644
> --- a/drivers/gpu/drm/xe/xe_tlb_inval.c
> +++ b/drivers/gpu/drm/xe/xe_tlb_inval.c
> @@ -14,6 +14,7 @@
> #include "xe_guc_tlb_inval.h"
> #include "xe_mmio.h"
> #include "xe_pm.h"
> +#include "xe_printk.h"
> #include "xe_tlb_inval.h"
> #include "xe_trace.h"
>
> @@ -99,6 +100,11 @@ static void xe_tlb_inval_fence_timeout(struct work_struct *work)
> fence->seqno, tlb_inval->seqno_recv);
>
> timedout_seqno = fence->seqno;
> + if (!tlb_inval->timedout_seqno) {
> + tlb_inval->timedout_seqno = fence->seqno;
> + tlb_inval->timedout_inval_time = fence->inval_time;
> + tlb_inval->timedout_time = ktime_get();
> + }
>
> fence->base.error = -ETIME;
> xe_tlb_inval_fence_signal(fence);
> @@ -227,6 +233,7 @@ void xe_tlb_inval_reset(struct xe_tlb_inval *tlb_inval)
> else
> pending_seqno = tlb_inval->seqno - 1;
> WRITE_ONCE(tlb_inval->seqno_recv, pending_seqno);
> + tlb_inval->timedout_seqno = 0;
>
> list_for_each_entry_safe(fence, next,
> &tlb_inval->pending_fences, link)
> @@ -454,6 +461,18 @@ void xe_tlb_inval_done_handler(struct xe_tlb_inval *tlb_inval, int seqno)
>
> WRITE_ONCE(tlb_inval->seqno_recv, seqno);
>
> + if (tlb_inval->timedout_seqno &&
> + xe_tlb_inval_seqno_past(tlb_inval, tlb_inval->timedout_seqno)) {
> + ktime_t now = ktime_get();
> +
> + xe_warn(xe,
> + "TLB invalidation late ack: seqno=%d recv=%d, request-to-ack=%lldms, timeout-to-ack=%lldms",
> + tlb_inval->timedout_seqno, seqno,
> + ktime_ms_delta(now, tlb_inval->timedout_inval_time),
> + ktime_ms_delta(now, tlb_inval->timedout_time));
Should this be some type SIGID message?
Matt
> + tlb_inval->timedout_seqno = 0;
> + }
> +
> list_for_each_entry_safe(fence, next,
> &tlb_inval->pending_fences, link) {
> trace_xe_tlb_inval_fence_recv(xe, fence);
> diff --git a/drivers/gpu/drm/xe/xe_tlb_inval_types.h b/drivers/gpu/drm/xe/xe_tlb_inval_types.h
> index d77be1aedc9..80d2019fa20 100644
> --- a/drivers/gpu/drm/xe/xe_tlb_inval_types.h
> +++ b/drivers/gpu/drm/xe/xe_tlb_inval_types.h
> @@ -112,6 +112,23 @@ struct xe_tlb_inval {
> * @pending_lock: protects @pending_fences and updating @seqno_recv.
> */
> spinlock_t pending_lock;
> + /**
> + * @timedout_seqno: seqno of the most recent timed out TLB
> + * invalidation, 0 if none. Used to measure how late the ack for a
> + * timed out invalidation actually arrives. Protected by
> + * @pending_lock.
> + */
> + int timedout_seqno;
> + /**
> + * @timedout_inval_time: request time of @timedout_seqno. Protected by
> + * @pending_lock.
> + */
> + ktime_t timedout_inval_time;
> + /**
> + * @timedout_time: time @timedout_seqno was signaled with -ETIME.
> + * Protected by @pending_lock.
> + */
> + ktime_t timedout_time;
> /**
> * @fence_tdr: schedules a delayed call to xe_tlb_fence_timeout after
> * the timeout interval is over.
> --
> 2.55.0
>
^ permalink raw reply [flat|nested] 16+ messages in thread
* Re: [PATCH v4 2/3] drm/xe: Log when a timed out TLB invalidation ack finally arrives
2026-09-18 22:06 ` Matthew Brost
@ 2026-09-21 5:30 ` Matthew Brost
2026-09-21 18:10 ` Tales A. Mendonça
0 siblings, 1 reply; 16+ messages in thread
From: Matthew Brost @ 2026-09-21 5:30 UTC (permalink / raw)
To: Tales A. Mendonça
Cc: intel-xe, daniele.ceraolospurio, stuart.summers, julia.filipchuk,
thomas.hellstrom, rodrigo.vivi, jani.nikula, navonjohnlukose,
dri-devel
On Fri, Sep 18, 2026 at 03:06:25PM -0700, Matthew Brost wrote:
> On Thu, Sep 17, 2026 at 01:35:52PM -0300, Tales A. Mendonça wrote:
> > When a TLB invalidation fence times out we log the timeout, but if the
> > ack for that seqno later shows up there is no record of it, making it
> > impossible to tell from logs whether the ack was lost forever or merely
> > (very) late.
> >
> > Track the most recent timed out seqno and log how late its ack arrives,
> > relative to both the original request and the moment the fence was
> > signaled with -ETIME.
> >
> > On ARL with GuC 70.53.0 this shows the acks are never lost: they
> > consistently arrive ~2.3s after the request, tens of milliseconds after
> > the TDR has already signaled the fence:
> >
> > TLB invalidation fence timeout, seqno=10992 recv=10991
> > TLB invalidation late ack: seqno=10992 recv=10992,
> > request-to-ack=2314ms, timeout-to-ack=45ms
> >
> > Link: https://gitlab.freedesktop.org/drm/xe/kernel/-/work_items/8678
> > Signed-off-by: Tales A. Mendonça <talesam@gmail.com>
>
> I would give this an RB but my colleagues have done a bunch of work on
> SIGID and I haven't been involved at all, so I need some help here.
>
I discussed with my colleagues - the we agree the TLB component should
hook into SIGID for logging but we will do this as a follow up on top of
this change.
So this is:
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
> > ---
> > drivers/gpu/drm/xe/xe_tlb_inval.c | 19 +++++++++++++++++++
> > drivers/gpu/drm/xe/xe_tlb_inval_types.h | 17 +++++++++++++++++
> > 2 files changed, 36 insertions(+)
> >
> > diff --git a/drivers/gpu/drm/xe/xe_tlb_inval.c b/drivers/gpu/drm/xe/xe_tlb_inval.c
> > index 7a0c04fac60..7047a347551 100644
> > --- a/drivers/gpu/drm/xe/xe_tlb_inval.c
> > +++ b/drivers/gpu/drm/xe/xe_tlb_inval.c
> > @@ -14,6 +14,7 @@
> > #include "xe_guc_tlb_inval.h"
> > #include "xe_mmio.h"
> > #include "xe_pm.h"
> > +#include "xe_printk.h"
> > #include "xe_tlb_inval.h"
> > #include "xe_trace.h"
> >
> > @@ -99,6 +100,11 @@ static void xe_tlb_inval_fence_timeout(struct work_struct *work)
> > fence->seqno, tlb_inval->seqno_recv);
> >
> > timedout_seqno = fence->seqno;
> > + if (!tlb_inval->timedout_seqno) {
> > + tlb_inval->timedout_seqno = fence->seqno;
> > + tlb_inval->timedout_inval_time = fence->inval_time;
> > + tlb_inval->timedout_time = ktime_get();
> > + }
> >
> > fence->base.error = -ETIME;
> > xe_tlb_inval_fence_signal(fence);
> > @@ -227,6 +233,7 @@ void xe_tlb_inval_reset(struct xe_tlb_inval *tlb_inval)
> > else
> > pending_seqno = tlb_inval->seqno - 1;
> > WRITE_ONCE(tlb_inval->seqno_recv, pending_seqno);
> > + tlb_inval->timedout_seqno = 0;
> >
> > list_for_each_entry_safe(fence, next,
> > &tlb_inval->pending_fences, link)
> > @@ -454,6 +461,18 @@ void xe_tlb_inval_done_handler(struct xe_tlb_inval *tlb_inval, int seqno)
> >
> > WRITE_ONCE(tlb_inval->seqno_recv, seqno);
> >
> > + if (tlb_inval->timedout_seqno &&
> > + xe_tlb_inval_seqno_past(tlb_inval, tlb_inval->timedout_seqno)) {
> > + ktime_t now = ktime_get();
> > +
> > + xe_warn(xe,
> > + "TLB invalidation late ack: seqno=%d recv=%d, request-to-ack=%lldms, timeout-to-ack=%lldms",
> > + tlb_inval->timedout_seqno, seqno,
> > + ktime_ms_delta(now, tlb_inval->timedout_inval_time),
> > + ktime_ms_delta(now, tlb_inval->timedout_time));
>
> Should this be some type SIGID message?
>
> Matt
>
> > + tlb_inval->timedout_seqno = 0;
> > + }
> > +
> > list_for_each_entry_safe(fence, next,
> > &tlb_inval->pending_fences, link) {
> > trace_xe_tlb_inval_fence_recv(xe, fence);
> > diff --git a/drivers/gpu/drm/xe/xe_tlb_inval_types.h b/drivers/gpu/drm/xe/xe_tlb_inval_types.h
> > index d77be1aedc9..80d2019fa20 100644
> > --- a/drivers/gpu/drm/xe/xe_tlb_inval_types.h
> > +++ b/drivers/gpu/drm/xe/xe_tlb_inval_types.h
> > @@ -112,6 +112,23 @@ struct xe_tlb_inval {
> > * @pending_lock: protects @pending_fences and updating @seqno_recv.
> > */
> > spinlock_t pending_lock;
> > + /**
> > + * @timedout_seqno: seqno of the most recent timed out TLB
> > + * invalidation, 0 if none. Used to measure how late the ack for a
> > + * timed out invalidation actually arrives. Protected by
> > + * @pending_lock.
> > + */
> > + int timedout_seqno;
> > + /**
> > + * @timedout_inval_time: request time of @timedout_seqno. Protected by
> > + * @pending_lock.
> > + */
> > + ktime_t timedout_inval_time;
> > + /**
> > + * @timedout_time: time @timedout_seqno was signaled with -ETIME.
> > + * Protected by @pending_lock.
> > + */
> > + ktime_t timedout_time;
> > /**
> > * @fence_tdr: schedules a delayed call to xe_tlb_fence_timeout after
> > * the timeout interval is over.
> > --
> > 2.55.0
> >
^ permalink raw reply [flat|nested] 16+ messages in thread
* Re: [PATCH v4 1/3] drm/xe: Capture devcoredump on TLB invalidation timeout
2026-09-18 22:01 ` Matthew Brost
@ 2026-09-21 18:06 ` Tales A. Mendonça
0 siblings, 0 replies; 16+ messages in thread
From: Tales A. Mendonça @ 2026-09-21 18:06 UTC (permalink / raw)
To: Matthew Brost
Cc: intel-xe, daniele.ceraolospurio, stuart.summers, julia.filipchuk,
thomas.hellstrom, rodrigo.vivi, jani.nikula, navonjohnlukose,
dri-devel
On Fri, Sep 18, 2026 at 03:02:00PM -0700, Matthew Brost wrote:
> With your v5 fix Sashiko pointed out:
>
> Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Thanks. That fix is in: seqno_recv is now sampled inside pending_lock in
xe_tlb_inval_fence_timeout() and passed to xe_devcoredump_gt() by value,
so the capture itself - which takes sleeping locks - still runs outside
the lock. v5 goes out this week carrying your tag on this patch.
Tales
Em sex., 18 de set. de 2026 às 19:02, Matthew Brost
<matthew.brost@intel.com> escreveu:
>
> On Thu, Sep 17, 2026 at 01:35:51PM -0300, Tales A. Mendonça wrote:
> > TLB invalidation timeouts currently leave no record of the firmware
> > state behind: there is no exec queue or job to blame, so nothing calls
> > xe_devcoredump() and the GuC log content at the time of the hang is
> > lost.
> >
> > Add xe_devcoredump_gt(), a variant of xe_devcoredump() for hangs that
> > are not tied to an exec queue or job. It captures the GuC log and CT
> > state of the affected GT, reusing the existing snapshot machinery and
> > the "only first snapshot" policy, and hook it up to the TLB invalidation
> > timeout path.
> >
> > This was instrumental in diagnosing GuC TLB invalidation ack stalls on
> > ARL (see Link), where the invalidation request is consumed from the H2G
> > CTB immediately but the ack G2H only arrives ~2.3s later, after the
> > timeout has already fired.
> >
> > Link: https://gitlab.freedesktop.org/drm/xe/kernel/-/work_items/8678
> > Signed-off-by: Tales A. Mendonça <talesam@gmail.com>
>
> With your v5 fix Sashiko pointed out:
>
> Reviewed-by: Matthew Brost <matthew.brost@intel.com>
>
> > ---
> > drivers/gpu/drm/xe/xe_devcoredump.c | 46 ++++++++++++++++-------------
> > drivers/gpu/drm/xe/xe_devcoredump.h | 15 +++++++---
> > drivers/gpu/drm/xe/xe_tlb_inval.c | 20 +++++++++++++
> > 3 files changed, 56 insertions(+), 25 deletions(-)
> >
> > diff --git a/drivers/gpu/drm/xe/xe_devcoredump.c b/drivers/gpu/drm/xe/xe_devcoredump.c
> > index 5f2b90b18f9..6bee8933f95 100644
> > --- a/drivers/gpu/drm/xe/xe_devcoredump.c
> > +++ b/drivers/gpu/drm/xe/xe_devcoredump.c
> > @@ -74,11 +74,6 @@ static struct xe_device *coredump_to_xe(const struct xe_devcoredump *coredump)
> > return container_of(coredump, struct xe_device, devcoredump);
> > }
> >
> > -static struct xe_guc *exec_queue_to_guc(struct xe_exec_queue *q)
> > -{
> > - return &q->gt->uc.guc;
> > -}
> > -
> > static ssize_t __xe_devcoredump_read(char *buffer, ssize_t count,
> > ssize_t start,
> > struct xe_devcoredump *coredump)
> > @@ -323,40 +318,44 @@ static void xe_devcoredump_deferred_snap_work(struct work_struct *work)
> > }
> >
> > static void devcoredump_snapshot(struct xe_devcoredump *coredump,
> > + struct xe_gt *gt,
> > struct xe_exec_queue *q,
> > struct xe_sched_job *job)
> > {
> > struct xe_devcoredump_snapshot *ss = &coredump->snapshot;
> > - struct xe_guc *guc = exec_queue_to_guc(q);
> > + struct xe_guc *guc = >->uc.guc;
> > const char *process_name = "no process";
> > bool cookie;
> >
> > ss->snapshot_time = ktime_get_real();
> > ss->boot_time = ktime_get_boottime();
> >
> > - if (q->vm && q->vm->xef) {
> > + if (q && q->vm && q->vm->xef) {
> > process_name = q->vm->xef->process_name;
> > ss->pid = q->vm->xef->pid;
> > }
> >
> > strscpy(ss->process_name, process_name);
> >
> > - ss->gt = q->gt;
> > + ss->gt = gt;
> > INIT_WORK(&ss->work, xe_devcoredump_deferred_snap_work);
> >
> > /* keep going if fw fails as we still want to save the memory and SW data */
> > - CLASS(xe_force_wake, fw_ref)(gt_to_fw(q->gt), XE_FORCEWAKE_ALL);
> > + CLASS(xe_force_wake, fw_ref)(gt_to_fw(gt), XE_FORCEWAKE_ALL);
> >
> > cookie = dma_fence_begin_signalling();
> >
> > ss->guc.log = xe_guc_log_snapshot_capture(&guc->log, true);
> > ss->guc.ct = xe_guc_ct_snapshot_capture(&guc->ct);
> > - ss->ge = xe_guc_exec_queue_snapshot_capture(q);
> > - if (job)
> > - ss->job = xe_sched_job_snapshot_capture(job);
> > - ss->vm = xe_vm_snapshot_capture(q->vm);
> >
> > - xe_engine_snapshot_capture_for_queue(q);
> > + if (q) {
> > + ss->ge = xe_guc_exec_queue_snapshot_capture(q);
> > + if (job)
> > + ss->job = xe_sched_job_snapshot_capture(job);
> > + ss->vm = xe_vm_snapshot_capture(q->vm);
> > +
> > + xe_engine_snapshot_capture_for_queue(q);
> > + }
> >
> > queue_work(system_dfl_wq, &ss->work);
> >
> > @@ -364,19 +363,24 @@ static void devcoredump_snapshot(struct xe_devcoredump *coredump,
> > }
> >
> > /**
> > - * xe_devcoredump - Take the required snapshots and initialize coredump device.
> > - * @q: The faulty xe_exec_queue, where the issue was detected.
> > - * @job: The faulty xe_sched_job, where the issue was detected.
> > + * __xe_devcoredump - Take the required snapshots and initialize coredump device.
> > + * @gt: The GT where the issue was detected.
> > + * @q: The faulty xe_exec_queue, where the issue was detected, may be NULL for
> > + * hangs that are not tied to an exec queue (e.g. TLB invalidation
> > + * timeouts); in that case only the GT-level state (GuC log and CT state)
> > + * is captured.
> > + * @job: The faulty xe_sched_job, where the issue was detected, may be NULL.
> > * @fmt: Printf format + args to describe the reason for the core dump
> > *
> > * This function should be called at the crash time within the serialized
> > * gt_reset. It is skipped if we still have the core dump device available
> > * with the information of the 'first' snapshot.
> > */
> > -__printf(3, 4)
> > -void xe_devcoredump(struct xe_exec_queue *q, struct xe_sched_job *job, const char *fmt, ...)
> > +__printf(4, 5)
> > +void __xe_devcoredump(struct xe_gt *gt, struct xe_exec_queue *q,
> > + struct xe_sched_job *job, const char *fmt, ...)
> > {
> > - struct xe_device *xe = gt_to_xe(q->gt);
> > + struct xe_device *xe = gt_to_xe(gt);
> > struct xe_devcoredump *coredump = &xe->devcoredump;
> > va_list varg;
> >
> > @@ -394,7 +398,7 @@ void xe_devcoredump(struct xe_exec_queue *q, struct xe_sched_job *job, const cha
> > coredump->snapshot.reason = kvasprintf(GFP_ATOMIC, fmt, varg);
> > va_end(varg);
> >
> > - devcoredump_snapshot(coredump, q, job);
> > + devcoredump_snapshot(coredump, gt, q, job);
> >
> > drm_info(&xe->drm, "Xe device coredump has been created\n");
> > drm_info(&xe->drm, "Check your /sys/class/drm/card%d/device/devcoredump/data\n",
> > diff --git a/drivers/gpu/drm/xe/xe_devcoredump.h b/drivers/gpu/drm/xe/xe_devcoredump.h
> > index 5391a80a4d1..bc4800b3a3f 100644
> > --- a/drivers/gpu/drm/xe/xe_devcoredump.h
> > +++ b/drivers/gpu/drm/xe/xe_devcoredump.h
> > @@ -11,15 +11,17 @@
> > struct drm_printer;
> > struct xe_device;
> > struct xe_exec_queue;
> > +struct xe_gt;
> > struct xe_sched_job;
> >
> > #ifdef CONFIG_DEV_COREDUMP
> > -void xe_devcoredump(struct xe_exec_queue *q, struct xe_sched_job *job, const char *fmt, ...);
> > +void __xe_devcoredump(struct xe_gt *gt, struct xe_exec_queue *q,
> > + struct xe_sched_job *job, const char *fmt, ...);
> > int xe_devcoredump_init(struct xe_device *xe);
> > #else
> > -static inline void xe_devcoredump(struct xe_exec_queue *q,
> > - struct xe_sched_job *job,
> > - const char *fmt, ...)
> > +static inline void __xe_devcoredump(struct xe_gt *gt, struct xe_exec_queue *q,
> > + struct xe_sched_job *job,
> > + const char *fmt, ...)
> > {
> > }
> >
> > @@ -29,6 +31,11 @@ static inline int xe_devcoredump_init(struct xe_device *xe)
> > }
> > #endif
> >
> > +#define xe_devcoredump(_q, _job, _fmt, ...) \
> > + __xe_devcoredump((_q)->gt, _q, _job, _fmt, ##__VA_ARGS__)
> > +#define xe_devcoredump_gt(_gt, _fmt, ...) \
> > + __xe_devcoredump(_gt, NULL, NULL, _fmt, ##__VA_ARGS__)
> > +
> > void xe_print_blob_ascii85(struct drm_printer *p, const char *prefix, char suffix,
> > const void *blob, size_t offset, size_t size);
> >
> > diff --git a/drivers/gpu/drm/xe/xe_tlb_inval.c b/drivers/gpu/drm/xe/xe_tlb_inval.c
> > index 7c3bf32d925..7a0c04fac60 100644
> > --- a/drivers/gpu/drm/xe/xe_tlb_inval.c
> > +++ b/drivers/gpu/drm/xe/xe_tlb_inval.c
> > @@ -5,6 +5,7 @@
> >
> > #include <drm/drm_managed.h>
> >
> > +#include "xe_devcoredump.h"
> > #include "xe_device_types.h"
> > #include "xe_force_wake.h"
> > #include "xe_gt_stats.h"
> > @@ -29,6 +30,12 @@
> >
> > #define FENCE_STACK_BIT DMA_FENCE_FLAG_USER_BITS
> >
> > +/* The frontend is only ever embedded in a GT */
> > +static struct xe_gt *tlb_inval_to_gt(struct xe_tlb_inval *tlb_inval)
> > +{
> > + return container_of(tlb_inval, struct xe_gt, tlb_inval);
> > +}
> > +
> > static void xe_tlb_inval_fence_fini(struct xe_tlb_inval_fence *fence)
> > {
> > if (WARN_ON_ONCE(!fence->tlb_inval))
> > @@ -73,6 +80,7 @@ static void xe_tlb_inval_fence_timeout(struct work_struct *work)
> > struct xe_device *xe = tlb_inval->xe;
> > struct xe_tlb_inval_fence *fence, *next;
> > long timeout_delay = tlb_inval->ops->timeout_delay(tlb_inval);
> > + int timedout_seqno = 0;
> >
> > tlb_inval->ops->flush(tlb_inval);
> >
> > @@ -90,6 +98,8 @@ static void xe_tlb_inval_fence_timeout(struct work_struct *work)
> > "TLB invalidation fence timeout, seqno=%d recv=%d",
> > fence->seqno, tlb_inval->seqno_recv);
> >
> > + timedout_seqno = fence->seqno;
> > +
> > fence->base.error = -ETIME;
> > xe_tlb_inval_fence_signal(fence);
> > }
> > @@ -97,6 +107,16 @@ static void xe_tlb_inval_fence_timeout(struct work_struct *work)
> > queue_delayed_work(tlb_inval->timeout_wq, &tlb_inval->fence_tdr,
> > timeout_delay);
> > spin_unlock_irq(&tlb_inval->pending_lock);
> > +
> > + /*
> > + * Capture the GuC log and CT state so the firmware side of the hang
> > + * can be inspected; there is no queue or job to blame here. Must be
> > + * outside pending_lock as the capture takes sleeping locks.
> > + */
> > + if (timedout_seqno)
> > + xe_devcoredump_gt(tlb_inval_to_gt(tlb_inval),
> > + "TLB invalidation fence timeout, seqno=%d recv=%d",
> > + timedout_seqno, tlb_inval->seqno_recv);
> > }
> >
> > /**
> > --
> > 2.55.0
> >
--
Com os cumprimentos,
Tales A. Mendonça
talesam.org
communitybig.org
^ permalink raw reply [flat|nested] 16+ messages in thread
* Re: [PATCH v4 2/3] drm/xe: Log when a timed out TLB invalidation ack finally arrives
2026-09-21 5:30 ` Matthew Brost
@ 2026-09-21 18:10 ` Tales A. Mendonça
2026-09-21 18:19 ` Matthew Brost
0 siblings, 1 reply; 16+ messages in thread
From: Tales A. Mendonça @ 2026-09-21 18:10 UTC (permalink / raw)
To: Matthew Brost
Cc: intel-xe, daniele.ceraolospurio, stuart.summers, julia.filipchuk,
thomas.hellstrom, rodrigo.vivi, jani.nikula, navonjohnlukose,
dri-devel
On Sun, Sep 20, 2026 at 10:30:00PM -0700, Matthew Brost wrote:
> I discussed with my colleagues - the we agree the TLB component should
> hook into SIGID for logging but we will do this as a follow up on top of
> this change.
>
> So this is:
> Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Thanks Matt, and thanks for taking the question to the people who own
SIGID rather than letting it sit.
I will carry your tag on this patch in v5. Agreed on leaving the SIGID
conversion as a follow-up: there is no TLB component in
DEFINE_XE_LOG_COMPONENTS() yet, so adding one touches the log ABI and
belongs with the people doing that work rather than bolted onto a bug
fix. Happy to rebase on top of it once it lands.
v5 is otherwise ready and goes out this week. The only code delta is in
patch 1, from the data race Sashiko spotted after v4.
While you are here - patch 3 is the one that actually stops the stalls,
and it is still the only one without review. It applies
XE_BO_FLAG_NEEDS_UC to the GuC-shared allocations (CTBs, log, ADS, SLPC,
engine activity) on the standalone media GT, scoped by a new OOB rule
(22016122933 MEDIA_VERSION(1300)). The approach was Daniele's
suggestion. It has been running on two ARL machines for about six weeks
across several kernel versions, with over 10 million invalidations and
zero stalls; before it, both machines hit the ~2.3s ack delay 20-60
times a day.
Daniele, Stuart, would either of you be able to take a look at that one?
Tales
Em seg., 21 de set. de 2026 às 02:30, Matthew Brost
<matthew.brost@intel.com> escreveu:
>
> On Fri, Sep 18, 2026 at 03:06:25PM -0700, Matthew Brost wrote:
> > On Thu, Sep 17, 2026 at 01:35:52PM -0300, Tales A. Mendonça wrote:
> > > When a TLB invalidation fence times out we log the timeout, but if the
> > > ack for that seqno later shows up there is no record of it, making it
> > > impossible to tell from logs whether the ack was lost forever or merely
> > > (very) late.
> > >
> > > Track the most recent timed out seqno and log how late its ack arrives,
> > > relative to both the original request and the moment the fence was
> > > signaled with -ETIME.
> > >
> > > On ARL with GuC 70.53.0 this shows the acks are never lost: they
> > > consistently arrive ~2.3s after the request, tens of milliseconds after
> > > the TDR has already signaled the fence:
> > >
> > > TLB invalidation fence timeout, seqno=10992 recv=10991
> > > TLB invalidation late ack: seqno=10992 recv=10992,
> > > request-to-ack=2314ms, timeout-to-ack=45ms
> > >
> > > Link: https://gitlab.freedesktop.org/drm/xe/kernel/-/work_items/8678
> > > Signed-off-by: Tales A. Mendonça <talesam@gmail.com>
> >
> > I would give this an RB but my colleagues have done a bunch of work on
> > SIGID and I haven't been involved at all, so I need some help here.
> >
>
> I discussed with my colleagues - the we agree the TLB component should
> hook into SIGID for logging but we will do this as a follow up on top of
> this change.
>
> So this is:
> Reviewed-by: Matthew Brost <matthew.brost@intel.com>
>
> > > ---
> > > drivers/gpu/drm/xe/xe_tlb_inval.c | 19 +++++++++++++++++++
> > > drivers/gpu/drm/xe/xe_tlb_inval_types.h | 17 +++++++++++++++++
> > > 2 files changed, 36 insertions(+)
> > >
> > > diff --git a/drivers/gpu/drm/xe/xe_tlb_inval.c b/drivers/gpu/drm/xe/xe_tlb_inval.c
> > > index 7a0c04fac60..7047a347551 100644
> > > --- a/drivers/gpu/drm/xe/xe_tlb_inval.c
> > > +++ b/drivers/gpu/drm/xe/xe_tlb_inval.c
> > > @@ -14,6 +14,7 @@
> > > #include "xe_guc_tlb_inval.h"
> > > #include "xe_mmio.h"
> > > #include "xe_pm.h"
> > > +#include "xe_printk.h"
> > > #include "xe_tlb_inval.h"
> > > #include "xe_trace.h"
> > >
> > > @@ -99,6 +100,11 @@ static void xe_tlb_inval_fence_timeout(struct work_struct *work)
> > > fence->seqno, tlb_inval->seqno_recv);
> > >
> > > timedout_seqno = fence->seqno;
> > > + if (!tlb_inval->timedout_seqno) {
> > > + tlb_inval->timedout_seqno = fence->seqno;
> > > + tlb_inval->timedout_inval_time = fence->inval_time;
> > > + tlb_inval->timedout_time = ktime_get();
> > > + }
> > >
> > > fence->base.error = -ETIME;
> > > xe_tlb_inval_fence_signal(fence);
> > > @@ -227,6 +233,7 @@ void xe_tlb_inval_reset(struct xe_tlb_inval *tlb_inval)
> > > else
> > > pending_seqno = tlb_inval->seqno - 1;
> > > WRITE_ONCE(tlb_inval->seqno_recv, pending_seqno);
> > > + tlb_inval->timedout_seqno = 0;
> > >
> > > list_for_each_entry_safe(fence, next,
> > > &tlb_inval->pending_fences, link)
> > > @@ -454,6 +461,18 @@ void xe_tlb_inval_done_handler(struct xe_tlb_inval *tlb_inval, int seqno)
> > >
> > > WRITE_ONCE(tlb_inval->seqno_recv, seqno);
> > >
> > > + if (tlb_inval->timedout_seqno &&
> > > + xe_tlb_inval_seqno_past(tlb_inval, tlb_inval->timedout_seqno)) {
> > > + ktime_t now = ktime_get();
> > > +
> > > + xe_warn(xe,
> > > + "TLB invalidation late ack: seqno=%d recv=%d, request-to-ack=%lldms, timeout-to-ack=%lldms",
> > > + tlb_inval->timedout_seqno, seqno,
> > > + ktime_ms_delta(now, tlb_inval->timedout_inval_time),
> > > + ktime_ms_delta(now, tlb_inval->timedout_time));
> >
> > Should this be some type SIGID message?
> >
> > Matt
> >
> > > + tlb_inval->timedout_seqno = 0;
> > > + }
> > > +
> > > list_for_each_entry_safe(fence, next,
> > > &tlb_inval->pending_fences, link) {
> > > trace_xe_tlb_inval_fence_recv(xe, fence);
> > > diff --git a/drivers/gpu/drm/xe/xe_tlb_inval_types.h b/drivers/gpu/drm/xe/xe_tlb_inval_types.h
> > > index d77be1aedc9..80d2019fa20 100644
> > > --- a/drivers/gpu/drm/xe/xe_tlb_inval_types.h
> > > +++ b/drivers/gpu/drm/xe/xe_tlb_inval_types.h
> > > @@ -112,6 +112,23 @@ struct xe_tlb_inval {
> > > * @pending_lock: protects @pending_fences and updating @seqno_recv.
> > > */
> > > spinlock_t pending_lock;
> > > + /**
> > > + * @timedout_seqno: seqno of the most recent timed out TLB
> > > + * invalidation, 0 if none. Used to measure how late the ack for a
> > > + * timed out invalidation actually arrives. Protected by
> > > + * @pending_lock.
> > > + */
> > > + int timedout_seqno;
> > > + /**
> > > + * @timedout_inval_time: request time of @timedout_seqno. Protected by
> > > + * @pending_lock.
> > > + */
> > > + ktime_t timedout_inval_time;
> > > + /**
> > > + * @timedout_time: time @timedout_seqno was signaled with -ETIME.
> > > + * Protected by @pending_lock.
> > > + */
> > > + ktime_t timedout_time;
> > > /**
> > > * @fence_tdr: schedules a delayed call to xe_tlb_fence_timeout after
> > > * the timeout interval is over.
> > > --
> > > 2.55.0
> > >
--
Com os cumprimentos,
Tales A. Mendonça
talesam.org
communitybig.org
^ permalink raw reply [flat|nested] 16+ messages in thread
* Re: [PATCH v4 2/3] drm/xe: Log when a timed out TLB invalidation ack finally arrives
2026-09-21 18:10 ` Tales A. Mendonça
@ 2026-09-21 18:19 ` Matthew Brost
0 siblings, 0 replies; 16+ messages in thread
From: Matthew Brost @ 2026-09-21 18:19 UTC (permalink / raw)
To: Tales A. Mendonça
Cc: intel-xe, daniele.ceraolospurio, stuart.summers, julia.filipchuk,
thomas.hellstrom, rodrigo.vivi, jani.nikula, navonjohnlukose,
dri-devel
On Mon, Sep 21, 2026 at 03:10:06PM -0300, Tales A. Mendonça wrote:
> On Sun, Sep 20, 2026 at 10:30:00PM -0700, Matthew Brost wrote:
> > I discussed with my colleagues - the we agree the TLB component should
> > hook into SIGID for logging but we will do this as a follow up on top of
> > this change.
> >
> > So this is:
> > Reviewed-by: Matthew Brost <matthew.brost@intel.com>
>
> Thanks Matt, and thanks for taking the question to the people who own
> SIGID rather than letting it sit.
>
> I will carry your tag on this patch in v5. Agreed on leaving the SIGID
> conversion as a follow-up: there is no TLB component in
> DEFINE_XE_LOG_COMPONENTS() yet, so adding one touches the log ABI and
> belongs with the people doing that work rather than bolted onto a bug
> fix. Happy to rebase on top of it once it lands.
>
I think we can stage the SIGID behind this, a colleagues volunteered to
pick this up after.
> v5 is otherwise ready and goes out this week. The only code delta is in
> patch 1, from the data race Sashiko spotted after v4.
>
> While you are here - patch 3 is the one that actually stops the stalls,
> and it is still the only one without review. It applies
> XE_BO_FLAG_NEEDS_UC to the GuC-shared allocations (CTBs, log, ADS, SLPC,
> engine activity) on the standalone media GT, scoped by a new OOB rule
> (22016122933 MEDIA_VERSION(1300)). The approach was Daniele's
> suggestion. It has been running on two ARL machines for about six weeks
> across several kernel versions, with over 10 million invalidations and
> zero stalls; before it, both machines hit the ~2.3s ack delay 20-60
> times a day.
>
> Daniele, Stuart, would either of you be able to take a look at that one?
>
Daniele is out on sabatical, I'll look now but this is typically not my
department but should be able give feedback if I cross code all the
code.
Matt
> Tales
>
> Em seg., 21 de set. de 2026 às 02:30, Matthew Brost
> <matthew.brost@intel.com> escreveu:
> >
> > On Fri, Sep 18, 2026 at 03:06:25PM -0700, Matthew Brost wrote:
> > > On Thu, Sep 17, 2026 at 01:35:52PM -0300, Tales A. Mendonça wrote:
> > > > When a TLB invalidation fence times out we log the timeout, but if the
> > > > ack for that seqno later shows up there is no record of it, making it
> > > > impossible to tell from logs whether the ack was lost forever or merely
> > > > (very) late.
> > > >
> > > > Track the most recent timed out seqno and log how late its ack arrives,
> > > > relative to both the original request and the moment the fence was
> > > > signaled with -ETIME.
> > > >
> > > > On ARL with GuC 70.53.0 this shows the acks are never lost: they
> > > > consistently arrive ~2.3s after the request, tens of milliseconds after
> > > > the TDR has already signaled the fence:
> > > >
> > > > TLB invalidation fence timeout, seqno=10992 recv=10991
> > > > TLB invalidation late ack: seqno=10992 recv=10992,
> > > > request-to-ack=2314ms, timeout-to-ack=45ms
> > > >
> > > > Link: https://gitlab.freedesktop.org/drm/xe/kernel/-/work_items/8678
> > > > Signed-off-by: Tales A. Mendonça <talesam@gmail.com>
> > >
> > > I would give this an RB but my colleagues have done a bunch of work on
> > > SIGID and I haven't been involved at all, so I need some help here.
> > >
> >
> > I discussed with my colleagues - the we agree the TLB component should
> > hook into SIGID for logging but we will do this as a follow up on top of
> > this change.
> >
> > So this is:
> > Reviewed-by: Matthew Brost <matthew.brost@intel.com>
> >
> > > > ---
> > > > drivers/gpu/drm/xe/xe_tlb_inval.c | 19 +++++++++++++++++++
> > > > drivers/gpu/drm/xe/xe_tlb_inval_types.h | 17 +++++++++++++++++
> > > > 2 files changed, 36 insertions(+)
> > > >
> > > > diff --git a/drivers/gpu/drm/xe/xe_tlb_inval.c b/drivers/gpu/drm/xe/xe_tlb_inval.c
> > > > index 7a0c04fac60..7047a347551 100644
> > > > --- a/drivers/gpu/drm/xe/xe_tlb_inval.c
> > > > +++ b/drivers/gpu/drm/xe/xe_tlb_inval.c
> > > > @@ -14,6 +14,7 @@
> > > > #include "xe_guc_tlb_inval.h"
> > > > #include "xe_mmio.h"
> > > > #include "xe_pm.h"
> > > > +#include "xe_printk.h"
> > > > #include "xe_tlb_inval.h"
> > > > #include "xe_trace.h"
> > > >
> > > > @@ -99,6 +100,11 @@ static void xe_tlb_inval_fence_timeout(struct work_struct *work)
> > > > fence->seqno, tlb_inval->seqno_recv);
> > > >
> > > > timedout_seqno = fence->seqno;
> > > > + if (!tlb_inval->timedout_seqno) {
> > > > + tlb_inval->timedout_seqno = fence->seqno;
> > > > + tlb_inval->timedout_inval_time = fence->inval_time;
> > > > + tlb_inval->timedout_time = ktime_get();
> > > > + }
> > > >
> > > > fence->base.error = -ETIME;
> > > > xe_tlb_inval_fence_signal(fence);
> > > > @@ -227,6 +233,7 @@ void xe_tlb_inval_reset(struct xe_tlb_inval *tlb_inval)
> > > > else
> > > > pending_seqno = tlb_inval->seqno - 1;
> > > > WRITE_ONCE(tlb_inval->seqno_recv, pending_seqno);
> > > > + tlb_inval->timedout_seqno = 0;
> > > >
> > > > list_for_each_entry_safe(fence, next,
> > > > &tlb_inval->pending_fences, link)
> > > > @@ -454,6 +461,18 @@ void xe_tlb_inval_done_handler(struct xe_tlb_inval *tlb_inval, int seqno)
> > > >
> > > > WRITE_ONCE(tlb_inval->seqno_recv, seqno);
> > > >
> > > > + if (tlb_inval->timedout_seqno &&
> > > > + xe_tlb_inval_seqno_past(tlb_inval, tlb_inval->timedout_seqno)) {
> > > > + ktime_t now = ktime_get();
> > > > +
> > > > + xe_warn(xe,
> > > > + "TLB invalidation late ack: seqno=%d recv=%d, request-to-ack=%lldms, timeout-to-ack=%lldms",
> > > > + tlb_inval->timedout_seqno, seqno,
> > > > + ktime_ms_delta(now, tlb_inval->timedout_inval_time),
> > > > + ktime_ms_delta(now, tlb_inval->timedout_time));
> > >
> > > Should this be some type SIGID message?
> > >
> > > Matt
> > >
> > > > + tlb_inval->timedout_seqno = 0;
> > > > + }
> > > > +
> > > > list_for_each_entry_safe(fence, next,
> > > > &tlb_inval->pending_fences, link) {
> > > > trace_xe_tlb_inval_fence_recv(xe, fence);
> > > > diff --git a/drivers/gpu/drm/xe/xe_tlb_inval_types.h b/drivers/gpu/drm/xe/xe_tlb_inval_types.h
> > > > index d77be1aedc9..80d2019fa20 100644
> > > > --- a/drivers/gpu/drm/xe/xe_tlb_inval_types.h
> > > > +++ b/drivers/gpu/drm/xe/xe_tlb_inval_types.h
> > > > @@ -112,6 +112,23 @@ struct xe_tlb_inval {
> > > > * @pending_lock: protects @pending_fences and updating @seqno_recv.
> > > > */
> > > > spinlock_t pending_lock;
> > > > + /**
> > > > + * @timedout_seqno: seqno of the most recent timed out TLB
> > > > + * invalidation, 0 if none. Used to measure how late the ack for a
> > > > + * timed out invalidation actually arrives. Protected by
> > > > + * @pending_lock.
> > > > + */
> > > > + int timedout_seqno;
> > > > + /**
> > > > + * @timedout_inval_time: request time of @timedout_seqno. Protected by
> > > > + * @pending_lock.
> > > > + */
> > > > + ktime_t timedout_inval_time;
> > > > + /**
> > > > + * @timedout_time: time @timedout_seqno was signaled with -ETIME.
> > > > + * Protected by @pending_lock.
> > > > + */
> > > > + ktime_t timedout_time;
> > > > /**
> > > > * @fence_tdr: schedules a delayed call to xe_tlb_fence_timeout after
> > > > * the timeout interval is over.
> > > > --
> > > > 2.55.0
> > > >
>
>
>
> --
> Com os cumprimentos,
>
> Tales A. Mendonça
> talesam.org
> communitybig.org
^ permalink raw reply [flat|nested] 16+ messages in thread
end of thread, other threads:[~2026-09-21 18:19 UTC | newest]
Thread overview: 16+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-09-17 16:35 [PATCH v4 0/3] drm/xe: fix GuC TLB invalidation ack stalls on ARL (Wa_22016122933) Tales A. Mendonça
2026-09-17 16:35 ` [PATCH v4 1/3] drm/xe: Capture devcoredump on TLB invalidation timeout Tales A. Mendonça
2026-09-17 16:50 ` sashiko-bot
2026-09-17 23:18 ` Tales A. Mendonça
2026-09-18 22:01 ` Matthew Brost
2026-09-21 18:06 ` Tales A. Mendonça
2026-09-17 16:35 ` [PATCH v4 2/3] drm/xe: Log when a timed out TLB invalidation ack finally arrives Tales A. Mendonça
2026-09-18 22:06 ` Matthew Brost
2026-09-21 5:30 ` Matthew Brost
2026-09-21 18:10 ` Tales A. Mendonça
2026-09-21 18:19 ` Matthew Brost
2026-09-17 16:35 ` [PATCH v4 3/3] drm/xe: Implement Wa_22016122933 Tales A. Mendonça
2026-09-17 16:42 ` ✗ CI.checkpatch: warning for drm/xe: fix GuC TLB invalidation ack stalls on ARL (Wa_22016122933) (rev3) Patchwork
2026-09-17 16:44 ` ✓ CI.KUnit: success " Patchwork
2026-09-17 17:54 ` ✓ Xe.CI.BAT: " Patchwork
2026-09-17 18:45 ` ✓ Xe.CI.FULL: " Patchwork
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox