Skip to contentSkip to conversation

Add CPER logging support for CRI

PATCH Superseded Badal Nilawar 8 participants 49 messages Oct 9 – Oct 27

Subsystems (2)

v4 of 8 Superseded Latest is v8 →

lore
Share & tools
lore
#0 lore raw

v4 cover Add CPER logging support for CRI

This patch series adds CPER (Common Platform Error Record) logging support for Correctable errors reported by Intel Xe GPUs. CPER logging is done through trace event.

v2:
- Extended CPER logging to Uncorrectable errors and xe_ras_get_counter request
- Log CPER records via xe_log SIGID infra

v3:
- Added the patches in incremental order (Raag)
- Fixed Sashiko warnings which are applicable

v4:
- Split the patches further for incremental review (Raag)
- Refactor info queue handling (Raag)
- Fix applicable Sashiko warnings

Badal Nilawar (12):
drm/xe/cper: Add CPER reporting entry point for xe_log drm/xe/cper: Retrieve the error counter record for CPER reporting drm/xe/cper: Initialize Intel-specific error section header drm/xe/cper: Construct CPER record for hardware errors drm/xe/xe_ras: Add support to retrieve info queue data for CRI drm/xe/cper: Prepare Intel CPER error info records drm/xe/cper: Log CPER records for aggregate counter retrieval drm/xe/cper: Emit cper record to trace buf drm/xe/xe_ras: Report device memory errors using SIGID drm/xe/xe_ras: Report core compute errors using SIGID drm/xe/xe_ras: Report soc internal errors using SIGID drm/xe/xe_ras: Report correctable errors using SIGID

 .../ABI/testing/sysfs-driver-intel-xe-cper    |  18 +
 drivers/gpu/drm/xe/Makefile                   |   3 +
 drivers/gpu/drm/xe/xe_cper.c                  | 530 ++++++++++++++++++
 drivers/gpu/drm/xe/xe_cper.h                  |  37 ++
 drivers/gpu/drm/xe/xe_cper_types.h            | 185 ++++++
 drivers/gpu/drm/xe/xe_device_types.h          |   4 +
 drivers/gpu/drm/xe/xe_log.c                   |   5 +-
 drivers/gpu/drm/xe/xe_ras.c                   | 254 ++++++++-
 drivers/gpu/drm/xe/xe_ras.h                   |   5 +
 drivers/gpu/drm/xe/xe_ras_types.h             | 118 +++-
 drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h |   2 +
 drivers/gpu/drm/xe/xe_trace_cper.c            |   9 +
 drivers/gpu/drm/xe/xe_trace_cper.h            |  66 +++
 13 files changed, 1202 insertions(+), 34 deletions(-)
 create mode 100644 Documentation/ABI/testing/sysfs-driver-intel-xe-cper
 create mode 100644 drivers/gpu/drm/xe/xe_cper.c
 create mode 100644 drivers/gpu/drm/xe/xe_cper.h
 create mode 100644 drivers/gpu/drm/xe/xe_cper_types.h
 create mode 100644 drivers/gpu/drm/xe/xe_trace_cper.c
 create mode 100644 drivers/gpu/drm/xe/xe_trace_cper.h
Signature · 1 line
2.54.0
#1 lore raw

PATCH v4 1/12 drm/xe/cper: Add CPER reporting entry point for xe_log

Introduce xe_cper_emit() as the single entry point for emitting CPER records from xe_log. xe_log now forwards every SIGID log entry with its full context (component, location, data/len and formatted message), and xe_cper decides how to report it. Hardware SIGIDs are routed to a hardware error helper, software SIGIDs are left as TODO.

No functional change is intended yet, as the CPER emission logic is added in follow-up patches.

Assisted-by Copilot:Claude-Opus-5.5

---
v4:
- s/CONFIG_UEFI_CPER_X86/CONFIG_UEFI_CPER/ (Raag)
- Use in_range() for hardware SIGID check in xe_cper (Raag)
- Drop unused response param and constify error_class
- Check data len against struct xe_ras_error_class before use (Michal)

---
 drivers/gpu/drm/xe/Makefile  |  2 ++
 drivers/gpu/drm/xe/xe_cper.c | 51 ++++++++++++++++++++++++++++++++++++
 drivers/gpu/drm/xe/xe_cper.h | 26 ++++++++++++++++++
 drivers/gpu/drm/xe/xe_log.c  |  5 +++-
 4 files changed, 83 insertions(+), 1 deletion(-)
 create mode 100644 drivers/gpu/drm/xe/xe_cper.c
 create mode 100644 drivers/gpu/drm/xe/xe_cper.h
drivers/gpu/drm/xe/Makefile +2 -0
index 10930c924070..da78026b0bb4 100644
@@ -168,6 +168,8 @@ xe-$(CONFIG_HWMON) += xe_hwmon.o
 xe-$(CONFIG_PERF_EVENTS) += xe_pmu.o
 xe-$(CONFIG_CONFIGFS_FS) += xe_configfs.o
 
+xe-$(CONFIG_UEFI_CPER) += xe_cper.o
+
 # graphics virtualization (SR-IOV) support
 xe-y += \
 	xe_gt_sriov_vf.o \
drivers/gpu/drm/xe/xe_cper.c new file +51 -0

51 lines not on this page · raw message

drivers/gpu/drm/xe/xe_cper.h new file +26 -0
new file mode 100644
index 000000000000..84676c7645a5
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2026 Intel Corporation
+ */
+
+#ifndef _XE_CPER_H_
+#define _XE_CPER_H_
+
+#include <linux/types.h>
+
+#include "abi/xe_sigid_abi.h"
+
+struct va_format;
+struct xe_device;
+
+#if IS_ENABLED(CONFIG_UEFI_CPER)
+void xe_cper_emit(struct xe_device *xe, int cper_sev, enum xe_sigid sigid,
+		  u32 component, u32 location, const void *data, size_t len,
+		  struct va_format *vaf);
+#else
+static inline void xe_cper_emit(struct xe_device *xe, int cper_sev, enum xe_sigid sigid,
+				u32 component, u32 location, const void *data, size_t len,
+				struct va_format *vaf) {}
+#endif
+
+#endif /* _XE_CPER_H_ */
drivers/gpu/drm/xe/xe_log.c +4 -1
index 29eb16db3320..80e2b1724ceb 100644
@@ -8,6 +8,7 @@
 
 #include "abi/xe_log_abi.h"
 
+#include "xe_cper.h"
 #include "xe_device.h"
 #include "xe_log.h"
 #include "xe_pci_types.h"
@@ -19,7 +20,9 @@ static void log_emit_cper(struct pci_dev *pdev, int cper_sev, enum xe_sigid sigi
 {
 	KUNIT_STATIC_STUB_REDIRECT(log_emit_cper, pdev, cper_sev, sigid,
 				   component, location, data, len, vaf);
-	/* TODO */
+
+	xe_cper_emit(xe_any_to_xe(pdev), cper_sev, sigid,
+		     component, location, data, len, vaf);
 }
 
 static const char *log_unknown_component_prefix(u32 component)
Signature · 1 line
2.54.0
#2 lore raw

Re: [PATCH v4 01/12] drm/xe/cper: Add CPER reporting entry point for xe_log

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider: - [Medium] drm/xe: Silent telemetry loss when hardware SIGIDs lack exact RAS data payload --

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Medium] drm/xe: Silent telemetry loss when hardware SIGIDs lack exact RAS data payload --

commit a8ad6417f3a91a193b5e9bf972e9a0e60ff46e5a
Author: Badal Nilawar <[email protected]>

drm/xe/cper: Add CPER reporting entry point for xe_log

Introduce xe_cper_emit() as the single entry point for emitting CPER records from xe_log. Hardware SIGIDs are routed to a hardware error helper, and software SIGIDs are left as TODO.

Quoted 5 lines
drivers/gpu/drm/xe/xe_cper.c new file +0 -0
new file mode 100644
index 0000000000000..c5caa0e8f496a

[ ... ]

drivers/gpu/drm/xe/xe_cper.c line 47

Quoted 11 lines
drivers/gpu/drm/xe/xe_cper.c new file +11 -0
+void xe_cper_emit(struct xe_device *xe, int cper_sev, enum xe_sigid sigid,
+		  u32 component, u32 location, const void *data, size_t len,
+		  struct va_format *vaf)
+{
+	if (!xe)
+		return;
+
+	if (is_hw_sigid(sigid)) {
+		if (!IS_ERR_OR_NULL(data) && len == sizeof(struct xe_ras_error_class))
+			xe_cper_emit_hw_err(xe, cper_sev, sigid, data);
+		return;

[Severity: Medium]
If a hardware SIGID log entry is missing the expected RAS data payload (e.g., the data pointer is ERR_PTR, NULL, or the length is unexpected), does this unconditionally return and drop the telemetry?

Since there is no fallback to emit a software CPER log or print a warning, it looks like this could result in a silent loss of hardware error data.

Quoted 4 lines
drivers/gpu/drm/xe/xe_cper.c new file +4 -0
+	}
+
+	/* TODO software CPER */
+}
Signature · 1 line
Sashiko AI review · https://sashiko.dev/#/patchset/[email protected]?part=1
#3 lore raw

Re: [PATCH v4 01/12] drm/xe/cper: Add CPER reporting entry point for xe_log

Quoted 35 lines · On 09-10-2026 16:13, [email protected] wrote:

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Medium] drm/xe: Silent telemetry loss when hardware SIGIDs lack exact RAS data payload --

commit a8ad6417f3a91a193b5e9bf972e9a0e60ff46e5a
Author: Badal Nilawar <[email protected]>

drm/xe/cper: Add CPER reporting entry point for xe_log

Introduce xe_cper_emit() as the single entry point for emitting CPER records from xe_log. Hardware SIGIDs are routed to a hardware error helper, and software SIGIDs are left as TODO.

Quoted 5 lines
drivers/gpu/drm/xe/xe_cper.c new file +0 -0
new file mode 100644
index 0000000000000..c5caa0e8f496a

[ ... ]

drivers/gpu/drm/xe/xe_cper.c line 47

Quoted 11 lines
drivers/gpu/drm/xe/xe_cper.c new file +11 -0
+void xe_cper_emit(struct xe_device *xe, int cper_sev, enum xe_sigid sigid,
+		  u32 component, u32 location, const void *data, size_t len,
+		  struct va_format *vaf)
+{
+	if (!xe)
+		return;
+
+	if (is_hw_sigid(sigid)) {
+		if (!IS_ERR_OR_NULL(data) && len == sizeof(struct xe_ras_error_class))
+			xe_cper_emit_hw_err(xe, cper_sev, sigid, data);
+		return;

[Severity: Medium]
If a hardware SIGID log entry is missing the expected RAS data payload (e.g., the data pointer is ERR_PTR, NULL, or the length is unexpected), does this unconditionally return and drop the telemetry?

Quoted 2 lines

Since there is no fallback to emit a software CPER log or print a warning, it looks like this could result in a silent loss of hardware error data.

The log entry is not lost: __xe_log_emit() emits the dmesg entry before the CPER path, so the hardware error is always reported in dmesg.

A hardware CPER record is built from the firmware error counter, which requires the RAS error class; without it there is no meaningful record to emit.

All hardware SIGID users (xe_ras.c) pass the error class, so this path is only a guard against misuse.

Thanks,
Badal

Quoted 5 lines
Quoted 5 lines
drivers/gpu/drm/xe/xe_cper.c new file +4 -0
+	}
+
+	/* TODO software CPER */
+}
#4 lore raw

Re: [PATCH v4 01/12] drm/xe/cper: Add CPER reporting entry point for xe_log

In reply to Badal Nilawar
Quoted 8 lines · Badal Nilawar

Introduce xe_cper_emit() as the single entry point for emitting CPER records from xe_log. xe_log now forwards every SIGID log entry with its full context (component, location, data/len and formatted message), and xe_cper decides how to report it. Hardware SIGIDs are routed to a hardware error helper, software SIGIDs are left as TODO.

No functional change is intended yet, as the CPER emission logic is added in follow-up patches.

This line isn't telling me anything and redundant for this patch.

Quoted 67 lines
Assisted-by Copilot:Claude-Opus-5.5

---
v4:
- s/CONFIG_UEFI_CPER_X86/CONFIG_UEFI_CPER/ (Raag)
- Use in_range() for hardware SIGID check in xe_cper (Raag)
- Drop unused response param and constify error_class
- Check data len against struct xe_ras_error_class before use (Michal)

---
 drivers/gpu/drm/xe/Makefile  |  2 ++
 drivers/gpu/drm/xe/xe_cper.c | 51 ++++++++++++++++++++++++++++++++++++
 drivers/gpu/drm/xe/xe_cper.h | 26 ++++++++++++++++++
 drivers/gpu/drm/xe/xe_log.c  |  5 +++-
 4 files changed, 83 insertions(+), 1 deletion(-)
 create mode 100644 drivers/gpu/drm/xe/xe_cper.c
 create mode 100644 drivers/gpu/drm/xe/xe_cper.h
drivers/gpu/drm/xe/Makefile +2 -0
index 10930c924070..da78026b0bb4 100644
@@ -168,6 +168,8 @@ xe-$(CONFIG_HWMON) += xe_hwmon.o
 xe-$(CONFIG_PERF_EVENTS) += xe_pmu.o
 xe-$(CONFIG_CONFIGFS_FS) += xe_configfs.o
 
+xe-$(CONFIG_UEFI_CPER) += xe_cper.o
+
 # graphics virtualization (SR-IOV) support
 xe-y += \
 	xe_gt_sriov_vf.o \
drivers/gpu/drm/xe/xe_cper.c new file +31 -0
new file mode 100644
index 000000000000..c5caa0e8f496
@@ -0,0 +1,51 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2026 Intel Corporation
+ */
+
+#include <linux/err.h>
+#include <linux/minmax.h>
+
+#include "xe_cper.h"
+#include "xe_device.h"
+#include "xe_ras_types.h"
+
+static bool is_hw_sigid(enum xe_sigid sigid)
+{
+	return in_range(sigid, INTEL_SIGID_GPU_XE_HARDWARE_START, INTEL_SIGID_BATCH);
+}
+
+static void xe_cper_emit_hw_err(struct xe_device *xe, int cper_sev, enum xe_sigid sigid,
+				const struct xe_ras_error_class *error_class)
+{
+	/* TODO */
+}
+
+/**
+ * xe_cper_emit() - Emit a CPER record for a SIGID log entry
+ * @xe: The &xe_device
+ * @cper_sev: CPER severity
+ * @sigid: Error signature identifier
+ * @component: Component identifier
+ * @location: Location details of the @component
+ * @data: Pointer to the additional details, or ERR_PTR, or NULL if not applicable

drivers/gpu/drm/xe/xe_cper.c line 41

Quoted 10 lines
drivers/gpu/drm/xe/xe_cper.c new file +10 -0
+ * @len: Length of the @data in bytes, or 0 if not applicable
+ * @vaf: Formatted log message
+ *
+ * Emit a CPER record for a SIGID log entry
+ */
+void xe_cper_emit(struct xe_device *xe, int cper_sev, enum xe_sigid sigid,
+		  u32 component, u32 location, const void *data, size_t len,
+		  struct va_format *vaf)
+{
+	if (!xe)

Why? Do we plan to shoot in out foot?

drivers/gpu/drm/xe/xe_cper.c line 45

Quoted 4 lines
drivers/gpu/drm/xe/xe_cper.c new file +4 -0
+		return;
+
+	if (is_hw_sigid(sigid)) {
+		if (!IS_ERR_OR_NULL(data) && len == sizeof(struct xe_ras_error_class))

Why the 'len' check?

Note: Any caller with incorrect length is abusing xe_log and will fail silently here, so let's not hide bugs.

Raag

Quoted 64 lines
drivers/gpu/drm/xe/xe_cper.c new file +6 -0
+			xe_cper_emit_hw_err(xe, cper_sev, sigid, data);
+		return;
+	}
+
+	/* TODO software CPER */
+}
drivers/gpu/drm/xe/xe_cper.h new file +26 -0
new file mode 100644
index 000000000000..84676c7645a5
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2026 Intel Corporation
+ */
+
+#ifndef _XE_CPER_H_
+#define _XE_CPER_H_
+
+#include <linux/types.h>
+
+#include "abi/xe_sigid_abi.h"
+
+struct va_format;
+struct xe_device;
+
+#if IS_ENABLED(CONFIG_UEFI_CPER)
+void xe_cper_emit(struct xe_device *xe, int cper_sev, enum xe_sigid sigid,
+		  u32 component, u32 location, const void *data, size_t len,
+		  struct va_format *vaf);
+#else
+static inline void xe_cper_emit(struct xe_device *xe, int cper_sev, enum xe_sigid sigid,
+				u32 component, u32 location, const void *data, size_t len,
+				struct va_format *vaf) {}
+#endif
+
+#endif /* _XE_CPER_H_ */
drivers/gpu/drm/xe/xe_log.c +4 -1
index 29eb16db3320..80e2b1724ceb 100644
@@ -8,6 +8,7 @@
 
 #include "abi/xe_log_abi.h"
 
+#include "xe_cper.h"
 #include "xe_device.h"
 #include "xe_log.h"
 #include "xe_pci_types.h"
@@ -19,7 +20,9 @@ static void log_emit_cper(struct pci_dev *pdev, int cper_sev, enum xe_sigid sigi
 {
 	KUNIT_STATIC_STUB_REDIRECT(log_emit_cper, pdev, cper_sev, sigid,
 				   component, location, data, len, vaf);
-	/* TODO */
+
+	xe_cper_emit(xe_any_to_xe(pdev), cper_sev, sigid,
+		     component, location, data, len, vaf);
 }
 
 static const char *log_unknown_component_prefix(u32 component)
Signature · 1 line
2.54.0
#5 lore raw

PATCH v4 2/12 drm/xe/cper: Retrieve the error counter record for CPER reporting

In reply to Badal Nilawar

Retrieve error counter record required to build a CPER record.

Assisted-by Copilot:Claude-Opus-5.5

---
v4:
- Drop redundant xe_ras_counter_is_valid() check (Raag)
- Add might_sleep() to assert that the caller is in a sleepable context (sashiko)
- Add xe_device_assert_mem_access() to assert the outer runtime PM wake reference requirement (sashiko)

---
 drivers/gpu/drm/xe/xe_cper.c | 14 ++++++++++-
 drivers/gpu/drm/xe/xe_ras.c  | 45 ++++++++++++++++++++++++------------
 drivers/gpu/drm/xe/xe_ras.h  |  2 ++
 3 files changed, 45 insertions(+), 16 deletions(-)
drivers/gpu/drm/xe/xe_cper.c +13 -1
index c5caa0e8f496..4f0ed5096aac 100644
@@ -4,10 +4,13 @@
  */
 
 #include <linux/err.h>
+#include <linux/kernel.h>
 #include <linux/minmax.h>
 
 #include "xe_cper.h"
 #include "xe_device.h"
+#include "xe_printk.h"
+#include "xe_ras.h"
 #include "xe_ras_types.h"
 
 static bool is_hw_sigid(enum xe_sigid sigid)
@@ -18,7 +21,16 @@ static bool is_hw_sigid(enum xe_sigid sigid)
 static void xe_cper_emit_hw_err(struct xe_device *xe, int cper_sev, enum xe_sigid sigid,
 				const struct xe_ras_error_class *error_class)
 {
-	/* TODO */
+	struct xe_ras_get_counter_response local_resp;
+
+	/* Fetching the counter sends a sysctrl command */
+	might_sleep();
+	xe_device_assert_mem_access(xe);
+
+	if (xe_ras_get_counter_response(xe, error_class, &local_resp)) {
+		xe_err(xe, "CPER: failed to get counter, skipping record\n");
+		return;
+	}
 }
 
 /**
drivers/gpu/drm/xe/xe_ras.c +30 -15

109 lines not on this page · raw message

drivers/gpu/drm/xe/xe_ras.h +2 -0
index 0b8669f28d56..84700ea63394 100644
@@ -20,5 +20,7 @@ int xe_ras_get_threshold(struct xe_device *xe, u8 severity, u8 component, u32 *t
 int xe_ras_set_threshold(struct xe_device *xe, u8 severity, u8 component, u32 threshold);
 void xe_ras_init(struct xe_device *xe);
 enum xe_ras_recovery_action xe_ras_process_errors(struct xe_device *xe);
+int xe_ras_get_counter_response(struct xe_device *xe, const struct xe_ras_error_class *counter,
+				struct xe_ras_get_counter_response *out);
 
 #endif
Signature · 1 line
2.54.0
#6 lore raw

Re: [PATCH v4 02/12] drm/xe/cper: Retrieve the error counter record for CPER reporting

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider: - [High] drm/xe: out-of-bounds array access on informational or reserved RAS errors --

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [High] drm/xe: out-of-bounds array access on informational or reserved RAS errors --

commit 27317cc719f71d74be0f7fcd94c5a8fbf53f9e5e
Author: Badal Nilawar <[email protected]>

drm/xe/cper: Retrieve the error counter record for CPER reporting

Retrieve error counter record required to build a CPER record.

Quoted 4 lines
drivers/gpu/drm/xe/xe_ras.c +0 -0
index 7a85735c57d58..5cfc9beff8c13 100644

[ ... ]

Quoted 11 lines
drivers/gpu/drm/xe/xe_ras.c +1 -1
@@ -284,21 +282,21 @@ static void ras_send_error_event(struct xe_device *xe, u8 severity, u8 component)
 {
 	struct xe_ras_error_class counter = {0};
+	struct xe_ras_get_counter_response response = {0};
 	u8 drm_severity, drm_component;
-	u32 value;
 	int ret;
 
 	counter.common.severity = severity;
 	counter.common.component = component;
 

drivers/gpu/drm/xe/xe_ras.c static void ras_send_error_event(struct xe_device *xe, u8 severity, u8 component) · line 298

Quoted 10 lines
drivers/gpu/drm/xe/xe_ras.c +2 -2
-	ret = get_counter(xe, &counter, &value);
+	ret = xe_ras_get_counter_response(xe, &counter, &response);
 	if (ret)
 		return;
 
 	drm_severity = xe_to_drm_ras_severity(severity);
 	drm_component = xe_to_drm_ras_component(component);
 
-	xe_drm_ras_event(xe, drm_component, drm_severity, value);
+	xe_drm_ras_event(xe, drm_component, drm_severity, response.value);

[Severity: High]
When firmware returns valid but unmapped values, like XE_RAS_SEV_INFORMATIONAL or XE_RAS_COMP_RESERVED, is it possible that xe_to_drm_ras_severity() and xe_to_drm_ras_component() will map these to their MAX values (DRM_XE_RAS_ERR_SEV_MAX and DRM_XE_RAS_ERR_COMP_MAX)?

If so, does this call to xe_drm_ras_event() cause out-of-bounds array accesses?

In drivers/gpu/drm/xe/xe_drm_ras.c:xe_drm_ras_event():

    struct xe_drm_ras_counter *info = ras->info[severity];
    ...
    node = &ras->node[severity];

    if (!info || !info[component].name)
        return;

Since the arrays are sized for the valid drm enum mappings, using the MAX values as indices would lead to wild pointer dereferences.

Quoted 3 lines
drivers/gpu/drm/xe/xe_ras.c +0 -0
 }
 
 static u8 handle_core_compute_errors(struct xe_ras_error_array *arr)
Signature · 1 line
Sashiko AI review · https://sashiko.dev/#/patchset/[email protected]?part=2
#7 lore raw

Re: [PATCH v4 02/12] drm/xe/cper: Retrieve the error counter record for CPER reporting

Quoted 55 lines · On 09-10-2026 16:16, [email protected] wrote:

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [High] drm/xe: out-of-bounds array access on informational or reserved RAS errors --

commit 27317cc719f71d74be0f7fcd94c5a8fbf53f9e5e
Author: Badal Nilawar <[email protected]>

drm/xe/cper: Retrieve the error counter record for CPER reporting

Retrieve error counter record required to build a CPER record.

Quoted 4 lines
drivers/gpu/drm/xe/xe_ras.c +0 -0
index 7a85735c57d58..5cfc9beff8c13 100644

[ ... ]

Quoted 11 lines
drivers/gpu/drm/xe/xe_ras.c +1 -1
@@ -284,21 +282,21 @@ static void ras_send_error_event(struct xe_device *xe, u8 severity, u8 component)
  {
  	struct xe_ras_error_class counter = {0};
+	struct xe_ras_get_counter_response response = {0};
  	u8 drm_severity, drm_component;
-	u32 value;
  	int ret;
 
  	counter.common.severity = severity;
  	counter.common.component = component;
 

drivers/gpu/drm/xe/xe_ras.c static void ras_send_error_event(struct xe_device *xe, u8 severity, u8 component) · line 298

Quoted 10 lines
drivers/gpu/drm/xe/xe_ras.c +2 -2
-	ret = get_counter(xe, &counter, &value);
+	ret = xe_ras_get_counter_response(xe, &counter, &response);
  	if (ret)
  		return;
 
  	drm_severity = xe_to_drm_ras_severity(severity);
  	drm_component = xe_to_drm_ras_component(component);
 
-	xe_drm_ras_event(xe, drm_component, drm_severity, value);
+	xe_drm_ras_event(xe, drm_component, drm_severity, response.value);

[Severity: High]
When firmware returns valid but unmapped values, like XE_RAS_SEV_INFORMATIONAL or XE_RAS_COMP_RESERVED, is it possible that xe_to_drm_ras_severity() and xe_to_drm_ras_component() will map these to their MAX values (DRM_XE_RAS_ERR_SEV_MAX and DRM_XE_RAS_ERR_COMP_MAX)?

If so, does this call to xe_drm_ras_event() cause out-of-bounds array accesses?

In drivers/gpu/drm/xe/xe_drm_ras.c:xe_drm_ras_event():

     struct xe_drm_ras_counter *info = ras->info[severity];
     ...
     node = &ras->node[severity];

     if (!info || !info[component].name)
         return;
Quoted 2 lines

Since the arrays are sized for the valid drm enum mappings, using the MAX values as indices would lead to wild pointer dereferences.

Good catch. This is pre-existing (from 6a9493e47075) and is not introduced by this series.

I'll send a separate fix that skips the drm_ras event when the severity or component has no drm mapping.

Thanks,
Badal

Quoted 4 lines
Quoted 4 lines
drivers/gpu/drm/xe/xe_ras.c +0 -0
  }
 
  static u8 handle_core_compute_errors(struct xe_ras_error_array *arr)
#8 lore raw

Re: [PATCH v4 02/12] drm/xe/cper: Retrieve the error counter record for CPER reporting

In reply to Badal Nilawar
Quoted 36 lines · Badal Nilawar

Retrieve error counter record required to build a CPER record.

Assisted-by Copilot:Claude-Opus-5.5

---
v4:
- Drop redundant xe_ras_counter_is_valid() check (Raag)
- Add might_sleep() to assert that the caller is in a sleepable context (sashiko)
- Add xe_device_assert_mem_access() to assert the outer runtime PM wake reference requirement (sashiko)

---
 drivers/gpu/drm/xe/xe_cper.c | 14 ++++++++++-
 drivers/gpu/drm/xe/xe_ras.c  | 45 ++++++++++++++++++++++++------------
 drivers/gpu/drm/xe/xe_ras.h  |  2 ++
 3 files changed, 45 insertions(+), 16 deletions(-)
drivers/gpu/drm/xe/xe_cper.c +3 -0
index c5caa0e8f496..4f0ed5096aac 100644
@@ -4,10 +4,13 @@
  */
 
 #include <linux/err.h>
+#include <linux/kernel.h>
 #include <linux/minmax.h>
 
 #include "xe_cper.h"
 #include "xe_device.h"
+#include "xe_printk.h"
+#include "xe_ras.h"
 #include "xe_ras_types.h"
 
 static bool is_hw_sigid(enum xe_sigid sigid)

drivers/gpu/drm/xe/xe_cper.c static bool is_hw_sigid(enum xe_sigid sigid) · line 24

Quoted 5 lines
drivers/gpu/drm/xe/xe_cper.c +1 -1
@@ -18,7 +21,16 @@ static bool is_hw_sigid(enum xe_sigid sigid)
 static void xe_cper_emit_hw_err(struct xe_device *xe, int cper_sev, enum xe_sigid sigid,
 				const struct xe_ras_error_class *error_class)
 {
-	/* TODO */
+	struct xe_ras_get_counter_response local_resp;

Why 'local'? Do we have any other?

drivers/gpu/drm/xe/xe_cper.c static bool is_hw_sigid(enum xe_sigid sigid) · line 30

Quoted 5 lines
drivers/gpu/drm/xe/xe_cper.c +5 -0
+	/* Fetching the counter sends a sysctrl command */
+	might_sleep();
+	xe_device_assert_mem_access(xe);
+
+	if (xe_ras_get_counter_response(xe, error_class, &local_resp)) {

Make the naming consistent with existing code, i.e. xe_ras_get_counter_response(xe, &counter, &response)

Quoted 20 lines
drivers/gpu/drm/xe/xe_cper.c +3 -0
+		xe_err(xe, "CPER: failed to get counter, skipping record\n");
+		return;
+	}
 }
 
 /**
drivers/gpu/drm/xe/xe_ras.c +0 -2
index 7a85735c57d5..5cfc9beff8c1 100644
@@ -103,8 +103,6 @@ static const char * const gpu_health_states[] = {
 };
 static_assert(ARRAY_SIZE(gpu_health_states) == XE_RAS_HEALTH_MAX);
 
-static int get_counter(struct xe_device *xe, struct xe_ras_error_class *counter, u32 *value);
-
 static u8 drm_to_xe_ras_severity(u8 severity)
 {
 	switch (severity) {

drivers/gpu/drm/xe/xe_ras.c static void ras_usp_aer_init(struct xe_device *xe) · line 285

Quoted 4 lines
drivers/gpu/drm/xe/xe_ras.c +1 -0
@@ -284,21 +282,21 @@ static void ras_usp_aer_init(struct xe_device *xe)
 static void ras_send_error_event(struct xe_device *xe, u8 severity, u8 component)
 {
 	struct xe_ras_error_class counter = {0};
+	struct xe_ras_get_counter_response response = {0};

Hm, not all users of get_counter() are interested in the entire response. So why not have it wrapped? Perhaps something like

static get_counter()

{
	response = {0};
	
	ret = xe_ras_get_counter_response(xe, &counter, &response);
	if (ret)
		return ret;

	*value = response.value;
	return 0;
}

Tidy? ;)

Quoted 21 lines
drivers/gpu/drm/xe/xe_ras.c +2 -3
 	u8 drm_severity, drm_component;
-	u32 value;
 	int ret;
 
 	counter.common.severity = severity;
 	counter.common.component = component;
 
-	ret = get_counter(xe, &counter, &value);
+	ret = xe_ras_get_counter_response(xe, &counter, &response);
 	if (ret)
 		return;
 
 	drm_severity = xe_to_drm_ras_severity(severity);
 	drm_component = xe_to_drm_ras_component(component);
 
-	xe_drm_ras_event(xe, drm_component, drm_severity, value);
+	xe_drm_ras_event(xe, drm_component, drm_severity, response.value);
 }
 
 static u8 handle_core_compute_errors(struct xe_ras_error_array *arr)

drivers/gpu/drm/xe/xe_ras.c void xe_ras_counter_threshold_crossed(struct xe_device *xe, · line 438

Quoted 9 lines
drivers/gpu/drm/xe/xe_ras.c +5 -1
@@ -433,19 +431,30 @@ void xe_ras_counter_threshold_crossed(struct xe_device *xe,
 	}
 }
 
-static int get_counter(struct xe_device *xe, struct xe_ras_error_class *counter, u32 *value)
+/**
+ * xe_ras_get_counter_response() - Get error counter record
+ * @xe: Xe device instance
+ * @counter: RAS error class
+ * @out: Counter record retrieved

Nit: ... to be retrieved

drivers/gpu/drm/xe/xe_ras.c void xe_ras_counter_threshold_crossed(struct xe_device *xe, · line 445

Quoted 6 lines
drivers/gpu/drm/xe/xe_ras.c +6 -0
+ * Retrieve the counter record of a specific error class from firmware.
+ *
+ * Return: 0 on success, negative error code on failure.
+ */
+int xe_ras_get_counter_response(struct xe_device *xe, const struct xe_ras_error_class *counter,
+				struct xe_ras_get_counter_response *out)

'response'?

drivers/gpu/drm/xe/xe_ras.c void xe_ras_counter_threshold_crossed(struct xe_device *xe, · line 453

Quoted 9 lines
drivers/gpu/drm/xe/xe_ras.c +1 -1
 {
-	struct xe_ras_get_counter_response response = {0};
 	struct xe_ras_get_counter_request request = {0};
 	struct xe_sysctrl_mailbox_command command = {0};
 	struct xe_ras_error_common *common;
 	size_t rlen;
 	int ret;
 
+	memset(out, 0, sizeof(*out));

Nack. No modifying input data, the caller is responsible for this.

Quoted 34 lines
drivers/gpu/drm/xe/xe_ras.c +6 -7
 	request.counter = *counter;
 
 	xe_sysctrl_create_command(&command, XE_SYSCTRL_GROUP_GFSP, XE_SYSCTRL_CMD_GET_COUNTER,
-				  &request, sizeof(request), &response, sizeof(response));
+				  &request, sizeof(request), out, sizeof(*out));
 
 	ret = xe_sysctrl_send_command(&xe->sc, &command, &rlen);
 	if (ret) {
@@ -453,19 +462,18 @@ static int get_counter(struct xe_device *xe, struct xe_ras_error_class *counter,
 		return ret;
 	}
 
-	if (rlen != sizeof(response)) {
+	if (rlen != sizeof(*out)) {
 		xe_err(xe, "sysctrl: unexpected get counter response length %zu (expected %zu)\n",
-		       rlen, sizeof(response));
+		       rlen, sizeof(*out));
 		return -EIO;
 	}
 
-	if (!ras_counter_is_valid(xe, &response.counter))
+	if (!ras_counter_is_valid(xe, &out->counter))
 		return -EBADMSG;
 
-	common = &response.counter.common;
-	*value = response.value;
+	common = &out->counter.common;
 
-	xe_dbg(xe, "[RAS]: get counter %u for %s %s\n", *value, comp_to_str(common->component),
+	xe_dbg(xe, "[RAS]: get counter %u for %s %s\n", out->value, comp_to_str(common->component),
 	       sev_to_str(common->severity));
 
 	return 0;

drivers/gpu/drm/xe/xe_ras.c enum xe_ras_recovery_action xe_ras_process_errors(struct xe_device *xe) · line 607

Quoted 4 lines
drivers/gpu/drm/xe/xe_ras.c +1 -0
@@ -596,12 +604,19 @@ enum xe_ras_recovery_action xe_ras_process_errors(struct xe_device *xe)
 int xe_ras_get_counter(struct xe_device *xe, u8 severity, u8 component, u32 *value)
 {
 	struct xe_ras_error_class counter = {0};
+	struct xe_ras_get_counter_response response = {0};

With get_counter() intact, this won't be needed.

Raag

Quoted 31 lines
drivers/gpu/drm/xe/xe_ras.c +7 -1
+	int ret;
 
 	counter.common.severity = drm_to_xe_ras_severity(severity);
 	counter.common.component = drm_to_xe_ras_component(component);
 
 	guard(xe_pm_runtime)(xe);
-	return get_counter(xe, &counter, value);
+	ret = xe_ras_get_counter_response(xe, &counter, &response);
+	if (ret)
+		return ret;
+
+	*value = response.value;
+	return 0;
 }
 
 /**
drivers/gpu/drm/xe/xe_ras.h +2 -0
index 0b8669f28d56..84700ea63394 100644
@@ -20,5 +20,7 @@ int xe_ras_get_threshold(struct xe_device *xe, u8 severity, u8 component, u32 *t
 int xe_ras_set_threshold(struct xe_device *xe, u8 severity, u8 component, u32 threshold);
 void xe_ras_init(struct xe_device *xe);
 enum xe_ras_recovery_action xe_ras_process_errors(struct xe_device *xe);
+int xe_ras_get_counter_response(struct xe_device *xe, const struct xe_ras_error_class *counter,
+				struct xe_ras_get_counter_response *out);
 
 #endif
Signature · 1 line
2.54.0
#9 lore raw

PATCH v4 3/12 drm/xe/cper: Initialize Intel-specific error section header

In reply to Badal Nilawar

Define the Intel-specific CPER error section header and initialize it from the error counter record for Intel GPU hardware errors.

Assisted-by Copilot:Claude-Opus-5.5

---
v4:
- Split from "drm/xe/cper: Prepare CPER record" (Raag)
- Add dedicated struct xe_cper_error_class (Michal)
- Drop empty fill_fw_id() stub, leave a TODO instead
v2:
- Guard against NULL THIS_MODULE->srcversion (sashiko)

---
 drivers/gpu/drm/xe/xe_cper.c       | 43 ++++++++++++++++++
 drivers/gpu/drm/xe/xe_cper_types.h | 72 ++++++++++++++++++++++++++++++
 2 files changed, 115 insertions(+)
 create mode 100644 drivers/gpu/drm/xe/xe_cper_types.h
drivers/gpu/drm/xe/xe_cper.c +43 -0
index 4f0ed5096aac..e7cae449b349 100644
@@ -6,8 +6,10 @@
 #include <linux/err.h>
 #include <linux/kernel.h>
 #include <linux/minmax.h>
+#include <linux/pci.h>
 
 #include "xe_cper.h"
+#include "xe_cper_types.h"
 #include "xe_device.h"
 #include "xe_printk.h"
 #include "xe_ras.h"
@@ -18,9 +20,47 @@ static bool is_hw_sigid(enum xe_sigid sigid)
 	return in_range(sigid, INTEL_SIGID_GPU_XE_HARDWARE_START, INTEL_SIGID_BATCH);
 }
 
+static void xe_cper_init_intel_err_hdr(struct xe_device *xe,
+				       const struct xe_ras_error_class *error_class,
+				       u64 first_timestamp, u32 sig_id, u32 error_count,
+				       struct xe_cper_sec_intel_err_hdr *ihdr)
+{
+	ihdr->error_class.error_type = error_class->common.severity;
+	ihdr->error_class.error_component = error_class->common.component;
+	ihdr->error_class.tile = error_class->product.unit.tile;
+	ihdr->error_class.instance = error_class->product.unit.instance;
+	ihdr->error_class.cause = error_class->product.cause.cause;
+	ihdr->validation_bits |= XE_CPER_VALID_LOCATION;
+
+	if (first_timestamp) {
+		ihdr->first_timestamp = first_timestamp;
+		ihdr->validation_bits |= XE_CPER_VALID_FIRST_TIMESTAMP;
+	}
+
+	if (sig_id != U32_MAX) {
+		ihdr->sig_id = sig_id;
+		ihdr->validation_bits |= XE_CPER_VALID_SIG_ID;
+	}
+
+	ihdr->error_count = error_count;
+
+	strscpy(ihdr->pci_bdf, pci_name(to_pci_dev(xe->drm.dev)), sizeof(ihdr->pci_bdf));
+	ihdr->validation_bits |= XE_CPER_VALID_PCI_BDF;
+
+#ifdef MODULE
+	if (THIS_MODULE->srcversion) {
+		strscpy(ihdr->drv_version, THIS_MODULE->srcversion, sizeof(ihdr->drv_version));
+		ihdr->validation_bits |= XE_CPER_VALID_DRV_VERSION;
+	}
+#endif
+
+	/* TODO: fill fw_id and set XE_CPER_VALID_FW_ID */
+}
+
 static void xe_cper_emit_hw_err(struct xe_device *xe, int cper_sev, enum xe_sigid sigid,
 				const struct xe_ras_error_class *error_class)
 {
+	struct xe_cper_sec_intel_err_hdr ihdr = {};
 	struct xe_ras_get_counter_response local_resp;
 
 	/* Fetching the counter sends a sysctrl command */
@@ -31,6 +71,9 @@ static void xe_cper_emit_hw_err(struct xe_device *xe, int cper_sev, enum xe_sigi
 		xe_err(xe, "CPER: failed to get counter, skipping record\n");
 		return;
 	}
+
+	xe_cper_init_intel_err_hdr(xe, error_class, local_resp.timestamp,
+				   sigid, local_resp.value, &ihdr);
 }
 
 /**
drivers/gpu/drm/xe/xe_cper_types.h new file +72 -0

72 lines not on this page · raw message

Signature · 1 line
2.54.0
#10 lore raw

Re: [PATCH v4 03/12] drm/xe/cper: Initialize Intel-specific error section header

Quoted 1 line · Badal Nilawar

Define the Intel-specific CPER error section header and initialize it

Nit: redundant 'error'.

Quoted 33 lines

from the error counter record for Intel GPU hardware errors.

Assisted-by Copilot:Claude-Opus-5.5

---
v4:
- Split from "drm/xe/cper: Prepare CPER record" (Raag)
- Add dedicated struct xe_cper_error_class (Michal)
- Drop empty fill_fw_id() stub, leave a TODO instead
v2:
- Guard against NULL THIS_MODULE->srcversion (sashiko)

---
 drivers/gpu/drm/xe/xe_cper.c       | 43 ++++++++++++++++++
 drivers/gpu/drm/xe/xe_cper_types.h | 72 ++++++++++++++++++++++++++++++
 2 files changed, 115 insertions(+)
 create mode 100644 drivers/gpu/drm/xe/xe_cper_types.h
drivers/gpu/drm/xe/xe_cper.c +2 -0
index 4f0ed5096aac..e7cae449b349 100644
@@ -6,8 +6,10 @@
 #include <linux/err.h>
 #include <linux/kernel.h>
 #include <linux/minmax.h>
+#include <linux/pci.h>
 
 #include "xe_cper.h"
+#include "xe_cper_types.h"
 #include "xe_device.h"
 #include "xe_printk.h"
 #include "xe_ras.h"

drivers/gpu/drm/xe/xe_cper.c static bool is_hw_sigid(enum xe_sigid sigid) · line 23

Quoted 4 lines
drivers/gpu/drm/xe/xe_cper.c +1 -0
@@ -18,9 +20,47 @@ static bool is_hw_sigid(enum xe_sigid sigid)
 	return in_range(sigid, INTEL_SIGID_GPU_XE_HARDWARE_START, INTEL_SIGID_BATCH);
 }
 
+static void xe_cper_init_intel_err_hdr(struct xe_device *xe,

'err' is redundant. Let's not invent unnecessarily long names that warrant ugly wrapping.

drivers/gpu/drm/xe/xe_cper.c static bool is_hw_sigid(enum xe_sigid sigid) · line 24

Quoted 1 line
drivers/gpu/drm/xe/xe_cper.c +1 -0
+				       const struct xe_ras_error_class *error_class,

Ditto, 'counter'.

Quoted 6 lines
drivers/gpu/drm/xe/xe_cper.c +6 -0
+				       u64 first_timestamp, u32 sig_id, u32 error_count,
+				       struct xe_cper_sec_intel_err_hdr *ihdr)
+{
+	ihdr->error_class.error_type = error_class->common.severity;
+	ihdr->error_class.error_component = error_class->common.component;
+	ihdr->error_class.tile = error_class->product.unit.tile;

drivers/gpu/drm/xe/xe_cper.c static bool is_hw_sigid(enum xe_sigid sigid) · line 40

Quoted 10 lines
drivers/gpu/drm/xe/xe_cper.c +10 -0
+	ihdr->error_class.instance = error_class->product.unit.instance;
+	ihdr->error_class.cause = error_class->product.cause.cause;
+	ihdr->validation_bits |= XE_CPER_VALID_LOCATION;
+
+	if (first_timestamp) {
+		ihdr->first_timestamp = first_timestamp;
+		ihdr->validation_bits |= XE_CPER_VALID_FIRST_TIMESTAMP;
+	}
+
+	if (sig_id != U32_MAX) {

Shouldn't this be is_sigid_valid() or something?

Quoted 53 lines
drivers/gpu/drm/xe/xe_cper.c +23 -0
+		ihdr->sig_id = sig_id;
+		ihdr->validation_bits |= XE_CPER_VALID_SIG_ID;
+	}
+
+	ihdr->error_count = error_count;
+
+	strscpy(ihdr->pci_bdf, pci_name(to_pci_dev(xe->drm.dev)), sizeof(ihdr->pci_bdf));
+	ihdr->validation_bits |= XE_CPER_VALID_PCI_BDF;
+
+#ifdef MODULE
+	if (THIS_MODULE->srcversion) {
+		strscpy(ihdr->drv_version, THIS_MODULE->srcversion, sizeof(ihdr->drv_version));
+		ihdr->validation_bits |= XE_CPER_VALID_DRV_VERSION;
+	}
+#endif
+
+	/* TODO: fill fw_id and set XE_CPER_VALID_FW_ID */
+}
+
 static void xe_cper_emit_hw_err(struct xe_device *xe, int cper_sev, enum xe_sigid sigid,
 				const struct xe_ras_error_class *error_class)
 {
+	struct xe_cper_sec_intel_err_hdr ihdr = {};
 	struct xe_ras_get_counter_response local_resp;
 
 	/* Fetching the counter sends a sysctrl command */
@@ -31,6 +71,9 @@ static void xe_cper_emit_hw_err(struct xe_device *xe, int cper_sev, enum xe_sigi
 		xe_err(xe, "CPER: failed to get counter, skipping record\n");
 		return;
 	}
+
+	xe_cper_init_intel_err_hdr(xe, error_class, local_resp.timestamp,
+				   sigid, local_resp.value, &ihdr);
 }
 
 /**
drivers/gpu/drm/xe/xe_cper_types.h new file +11 -0
new file mode 100644
index 000000000000..74307e7f78a2
@@ -0,0 +1,72 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2026 Intel Corporation
+ */
+
+#ifndef _XE_CPER_TYPES_H_
+#define _XE_CPER_TYPES_H_
+
+#include <linux/types.h>
+
+/*

drivers/gpu/drm/xe/xe_cper_types.h line 21

Quoted 10 lines
drivers/gpu/drm/xe/xe_cper_types.h new file +10 -0
+ * Validation bits definition for validation_bits in struct
+ * xe_cper_sec_intel_err_hdr. When set, corresponding fields in header
+ * contains valid data
+ */
+#define XE_CPER_VALID_LOCATION		0x0001
+#define XE_CPER_VALID_FIRST_TIMESTAMP	0x0002
+#define XE_CPER_VALID_SIG_ID		0x0004
+#define XE_CPER_VALID_PCI_BDF		0x0008
+#define XE_CPER_VALID_DRV_VERSION	0x0010
+#define XE_CPER_VALID_FW_ID		0x0020

Introduce in the patch you actually use it.

drivers/gpu/drm/xe/xe_cper_types.h line 23

Quoted 1 line
drivers/gpu/drm/xe/xe_cper_types.h new file +1 -0
+#pragma pack(push, 1)

I'd rather use __packed for individual structs, so I know it's an ABI without fumbling through the header without my coffee :)

Although the long term plan is to move all of them inside xe/abi directory, but only when they become stable.

Quoted 15 lines
drivers/gpu/drm/xe/xe_cper_types.h new file +15 -0
+/**
+ * struct xe_cper_error_class - Intel GPU CPER error classification
+ */
+struct xe_cper_error_class {
+	/** @error_type: RAS error severity */
+	u8  error_type;
+	/** @error_component: IP block that raised the error */
+	u8  error_component;
+	/** @tile: Tile number */
+	u8  tile;
+	/** @instance: Instance within the tile */
+	u32 instance;
+	/** @cause: Error cause code */
+	u32 cause;
+	/** @reserved: Reserved, must be zero */

drivers/gpu/drm/xe/xe_cper_types.h line 49

Quoted 10 lines
drivers/gpu/drm/xe/xe_cper_types.h new file +10 -0
+	u8  reserved;
+};
+
+/**
+ * struct xe_cper_sec_intel_err_hdr - Intel-specific CPER error section header
+ *
+ * Fixed-size header for the Intel GPU error section of a CPER record.
+ * All multi-byte fields are little-endian; the structure is packed.
+ */
+struct xe_cper_sec_intel_err_hdr {

Same as above, drop the 'err'.

drivers/gpu/drm/xe/xe_cper_types.h line 51

Quoted 2 lines
drivers/gpu/drm/xe/xe_cper_types.h new file +2 -0
+	/** @error_class: Error classification (type, component, location, cause) */
+	struct xe_cper_error_class error_class;

Why not just reuse struct xe_ras_error_class?

Raag

Quoted 24 lines
drivers/gpu/drm/xe/xe_cper_types.h new file +21 -0
+	/** @first_timestamp: First occurrence of this error class, in ticks */
+	u64 first_timestamp;
+	/** @sig_id: Aggregated error class SIG ID; set to U32_MAX if unknown */
+	u32 sig_id;
+	/** @error_count: Number of times this error has been observed */
+	u32 error_count;
+	/** @validation_bits: Raw u16 view of all valid bits */
+	u16 validation_bits;
+	/** @pci_bdf: PCI location string, format "DDDD:bb:dd.f" */
+	char pci_bdf[16];
+	/** @drv_version: Driver source version string (THIS_MODULE->srcversion) */
+	char drv_version[25];
+	/** @fw_id: Firmware version string (GFSP+PCODE+CSC+GUC or MNG+NUC+RAS+GUC) */
+	char fw_id[256];
+	/** @reserved: Reserved for future use, must be zero */
+	u8 reserved[5];
+};
+
+#pragma pack(pop)
+
+#endif
Signature · 1 line
2.54.0
#11 lore raw

PATCH v4 4/12 drm/xe/cper: Construct CPER record for hardware errors

In reply to Badal Nilawar

Assemble the CPER record header, section descriptor and the Intel error section for Intel GPU hardware errors. Emitting the record is added in a follow-up patch.

Assisted-by Copilot:Claude-Opus-5.5

---
v4:
- Split from "drm/xe/cper: Prepare CPER record" (Raag)
- Use xe->device_uid for FRU ID
- Add platform IDs for all CRI PCI device IDs
v2:
- Encode cper_record_header timestamp in BCD format (sashiko)

---
 drivers/gpu/drm/xe/xe_cper.c       | 122 +++++++++++++++++++++++++++++
 drivers/gpu/drm/xe/xe_cper_types.h |  53 +++++++++++++
 2 files changed, 175 insertions(+)
drivers/gpu/drm/xe/xe_cper.c +122 -0
index e7cae449b349..1000c78b41e9 100644
@@ -3,10 +3,14 @@
  * Copyright © 2026 Intel Corporation
  */
 
+#include <linux/bcd.h>
 #include <linux/err.h>
 #include <linux/kernel.h>
 #include <linux/minmax.h>
 #include <linux/pci.h>
+#include <linux/slab.h>
+#include <linux/time.h>
+#include <linux/timekeeping.h>
 
 #include "xe_cper.h"
 #include "xe_cper_types.h"
@@ -20,6 +24,60 @@ static bool is_hw_sigid(enum xe_sigid sigid)
 	return in_range(sigid, INTEL_SIGID_GPU_XE_HARDWARE_START, INTEL_SIGID_BATCH);
 }
 
+static const struct xe_platform_id_entry xe_platform_ids[] = {
+	/* 0x674C  platform/8086:674c */
+	{ 0x674C, GUID_INIT(0x9046afe5, 0x9041, 0x5124,
+			    0x86, 0x14, 0x92, 0x55, 0x0d, 0x9e, 0x9d, 0xa6) },
+	/* 0x674D  platform/8086:674d */
+	{ 0x674D, GUID_INIT(0xf95911b8, 0x6564, 0x5905,
+			    0xa6, 0xa7, 0xb9, 0xbf, 0x54, 0xab, 0x6c, 0x27) },
+	/* 0x674E  platform/8086:674e */
+	{ 0x674E, GUID_INIT(0xb8d24106, 0x0108, 0x59f1,
+			    0x8f, 0xfc, 0x9f, 0xc4, 0xa9, 0xc9, 0xb7, 0xb0) },
+	/* 0x674F  platform/8086:674f */
+	{ 0x674F, GUID_INIT(0xdd8dd88e, 0xef2f, 0x59b1,
+			    0x99, 0x15, 0xdb, 0x6f, 0x1d, 0xc9, 0xb4, 0x5d) },
+	/* 0x6750  platform/8086:6750 */
+	{ 0x6750, GUID_INIT(0x1dd66c44, 0x87d5, 0x524a,
+			    0xad, 0x6e, 0xfc, 0x18, 0x9d, 0x42, 0x6f, 0x1a) },
+	/* 0x6751  platform/8086:6751 */
+	{ 0x6751, GUID_INIT(0x17d0dd04, 0x2fad, 0x5400,
+			    0x99, 0xc8, 0x9b, 0x45, 0x51, 0x3b, 0x67, 0xe3) },
+};
+
+static const guid_t *lookup_platform_id(const struct pci_dev *pdev)
+{
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(xe_platform_ids); i++)
+		if (xe_platform_ids[i].device_id == pdev->device)
+			return &xe_platform_ids[i].platform_id;
+	return NULL;
+}
+
+static u64 cper_timestamp_now(void)
+{
+	struct tm tm;
+	u64 ts = 0;
+	u8 *p = (u8 *)&ts;
+	int year;
+
+	time64_to_tm(ktime_get_real_seconds(), 0, &tm);
+
+	year = tm.tm_year + 1900;
+
+	p[0] = bin2bcd(tm.tm_sec);
+	p[1] = bin2bcd(tm.tm_min);
+	p[2] = bin2bcd(tm.tm_hour);
+	p[3] = 0x1; /* precise time */
+	p[4] = bin2bcd(tm.tm_mday);
+	p[5] = bin2bcd(tm.tm_mon + 1);
+	p[6] = bin2bcd(year % 100);
+	p[7] = bin2bcd(year / 100);
+
+	return ts;
+}
+
 static void xe_cper_init_intel_err_hdr(struct xe_device *xe,
 				       const struct xe_ras_error_class *error_class,
 				       u64 first_timestamp, u32 sig_id, u32 error_count,
@@ -57,6 +115,67 @@ static void xe_cper_init_intel_err_hdr(struct xe_device *xe,
 	/* TODO: fill fw_id and set XE_CPER_VALID_FW_ID */
 }
 
+static void xe_cper_record_emit(struct xe_device *xe, u8 severity,
+				const guid_t *notification_type,
+				const struct xe_cper_sec_intel_err_hdr *ihdr,
+				const void *einfo, u32 einfo_len)
+{
+	struct pci_dev *pdev = to_pci_dev(xe->drm.dev);
+	const guid_t *platform_id = lookup_platform_id(pdev);
+	u32 total_len = sizeof(struct xe_cper_nonstd_record) + einfo_len;
+	struct cper_section_descriptor *sdesc;
+	struct cper_record_header *rhdr;
+	struct xe_cper_nonstd_record *rec;
+
+	rec = kzalloc(total_len, GFP_KERNEL);
+	if (!rec)
+		return;
+
+	rhdr = &rec->record_hdr;
+	sdesc = &rec->section_desc;
+
+	/* Assemble the CPER record header (UEFI Appendix N.2.1) */
+	memcpy(rhdr->signature, CPER_SIG_RECORD, CPER_SIG_SIZE);
+	rhdr->revision          = CPER_RECORD_REV;
+	rhdr->signature_end     = CPER_SIG_END;
+	rhdr->section_count     = 1;
+	rhdr->error_severity    = severity;
+	rhdr->validation_bits   = CPER_VALID_TIMESTAMP;
+	rhdr->record_length     = total_len;
+	rhdr->timestamp         = cper_timestamp_now();
+	if (platform_id) {
+		rhdr->platform_id      = *platform_id;
+		rhdr->validation_bits |= CPER_VALID_PLATFORM_ID;
+	}
+	rhdr->creator_id        = INTEL_CPER_CREATOR_XEKMD;
+	rhdr->notification_type = *notification_type;
+	rhdr->record_id         = cper_next_record_id();
+
+	/* Assemble the section descriptor (UEFI Appendix N.2.2) */
+	sdesc->section_offset   = sizeof(struct cper_record_header) +
+				  sizeof(struct cper_section_descriptor);
+	sdesc->section_length   = sizeof(struct xe_cper_sec_intel_err_hdr) + einfo_len;
+	sdesc->revision         = CPER_SEC_REV;
+	sdesc->validation_bits  = 0;
+	sdesc->section_type     = INTEL_CPER_SECTION_ACCEL_GENERIC;
+	if (xe->info.has_device_uid) {
+		memcpy(&sdesc->fru_id, &xe->device_uid, sizeof(xe->device_uid));
+		sdesc->validation_bits |= CPER_SEC_VALID_FRU_ID;
+	}
+	sdesc->section_severity = severity;
+
+	/* Copy the Intel-specific section header */
+	rec->intel_hdr = *ihdr;
+
+	/* Append optional variable-length error info */
+	if (einfo && einfo_len)
+		memcpy((u8 *)rec + sizeof(*rec), einfo, einfo_len);
+
+	/* TODO: Emit trace event */
+
+	kfree(rec);
+}
+
 static void xe_cper_emit_hw_err(struct xe_device *xe, int cper_sev, enum xe_sigid sigid,
 				const struct xe_ras_error_class *error_class)
 {
@@ -74,6 +193,9 @@ static void xe_cper_emit_hw_err(struct xe_device *xe, int cper_sev, enum xe_sigi
 
 	xe_cper_init_intel_err_hdr(xe, error_class, local_resp.timestamp,
 				   sigid, local_resp.value, &ihdr);
+
+	xe_cper_record_emit(xe, cper_sev, &INTEL_CPER_NOTIFY_GPU_ERROR,
+			    &ihdr, NULL, 0);
 }
 
 /**
drivers/gpu/drm/xe/xe_cper_types.h +53 -0

72 lines not on this page · raw message

Signature · 1 line
2.54.0
#12 lore raw

Re: [PATCH v4 04/12] drm/xe/cper: Construct CPER record for hardware errors

Cc Matt for platform stuff
Quoted 3 lines · Badal Nilawar

Assemble the CPER record header, section descriptor and the Intel error section for Intel GPU hardware errors. Emitting the record is added in a follow-up patch.

Commit message should describe what _this_ patch does, not _next_.

Quoted 47 lines
Assisted-by Copilot:Claude-Opus-5.5

---
v4:
- Split from "drm/xe/cper: Prepare CPER record" (Raag)
- Use xe->device_uid for FRU ID
- Add platform IDs for all CRI PCI device IDs
v2:
- Encode cper_record_header timestamp in BCD format (sashiko)

---
 drivers/gpu/drm/xe/xe_cper.c       | 122 +++++++++++++++++++++++++++++
 drivers/gpu/drm/xe/xe_cper_types.h |  53 +++++++++++++
 2 files changed, 175 insertions(+)
drivers/gpu/drm/xe/xe_cper.c +14 -0
index e7cae449b349..1000c78b41e9 100644
@@ -3,10 +3,14 @@
  * Copyright © 2026 Intel Corporation
  */
 
+#include <linux/bcd.h>
 #include <linux/err.h>
 #include <linux/kernel.h>
 #include <linux/minmax.h>
 #include <linux/pci.h>
+#include <linux/slab.h>
+#include <linux/time.h>
+#include <linux/timekeeping.h>
 
 #include "xe_cper.h"
 #include "xe_cper_types.h"
@@ -20,6 +24,60 @@ static bool is_hw_sigid(enum xe_sigid sigid)
 	return in_range(sigid, INTEL_SIGID_GPU_XE_HARDWARE_START, INTEL_SIGID_BATCH);
 }
 
+static const struct xe_platform_id_entry xe_platform_ids[] = {
+	/* 0x674C  platform/8086:674c */
+	{ 0x674C, GUID_INIT(0x9046afe5, 0x9041, 0x5124,
+			    0x86, 0x14, 0x92, 0x55, 0x0d, 0x9e, 0x9d, 0xa6) },
+	/* 0x674D  platform/8086:674d */
+	{ 0x674D, GUID_INIT(0xf95911b8, 0x6564, 0x5905,
+			    0xa6, 0xa7, 0xb9, 0xbf, 0x54, 0xab, 0x6c, 0x27) },
+	/* 0x674E  platform/8086:674e */
+	{ 0x674E, GUID_INIT(0xb8d24106, 0x0108, 0x59f1,
+			    0x8f, 0xfc, 0x9f, 0xc4, 0xa9, 0xc9, 0xb7, 0xb0) },

drivers/gpu/drm/xe/xe_cper.c static bool is_hw_sigid(enum xe_sigid sigid) · line 46

Quoted 10 lines
drivers/gpu/drm/xe/xe_cper.c +10 -0
+	/* 0x674F  platform/8086:674f */
+	{ 0x674F, GUID_INIT(0xdd8dd88e, 0xef2f, 0x59b1,
+			    0x99, 0x15, 0xdb, 0x6f, 0x1d, 0xc9, 0xb4, 0x5d) },
+	/* 0x6750  platform/8086:6750 */
+	{ 0x6750, GUID_INIT(0x1dd66c44, 0x87d5, 0x524a,
+			    0xad, 0x6e, 0xfc, 0x18, 0x9d, 0x42, 0x6f, 0x1a) },
+	/* 0x6751  platform/8086:6751 */
+	{ 0x6751, GUID_INIT(0x17d0dd04, 0x2fad, 0x5400,
+			    0x99, 0xc8, 0x9b, 0x45, 0x51, 0x3b, 0x67, 0xe3) },
+};

This is unrelated to cper and shouldn't be here. I'll rely on Matt's input on how to deal with these.

Quoted 37 lines
drivers/gpu/drm/xe/xe_cper.c +33 -0
+static const guid_t *lookup_platform_id(const struct pci_dev *pdev)
+{
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(xe_platform_ids); i++)
+		if (xe_platform_ids[i].device_id == pdev->device)
+			return &xe_platform_ids[i].platform_id;
+	return NULL;
+}
+
+static u64 cper_timestamp_now(void)
+{
+	struct tm tm;
+	u64 ts = 0;
+	u8 *p = (u8 *)&ts;
+	int year;
+
+	time64_to_tm(ktime_get_real_seconds(), 0, &tm);
+
+	year = tm.tm_year + 1900;
+
+	p[0] = bin2bcd(tm.tm_sec);
+	p[1] = bin2bcd(tm.tm_min);
+	p[2] = bin2bcd(tm.tm_hour);
+	p[3] = 0x1; /* precise time */
+	p[4] = bin2bcd(tm.tm_mday);
+	p[5] = bin2bcd(tm.tm_mon + 1);
+	p[6] = bin2bcd(year % 100);
+	p[7] = bin2bcd(year / 100);
+
+	return ts;
+}
+
 static void xe_cper_init_intel_err_hdr(struct xe_device *xe,
 				       const struct xe_ras_error_class *error_class,
 				       u64 first_timestamp, u32 sig_id, u32 error_count,

drivers/gpu/drm/xe/xe_cper.c static void xe_cper_init_intel_err_hdr(struct xe_device *xe, · line 124

Quoted 10 lines
drivers/gpu/drm/xe/xe_cper.c +7 -0
@@ -57,6 +115,67 @@ static void xe_cper_init_intel_err_hdr(struct xe_device *xe,
 	/* TODO: fill fw_id and set XE_CPER_VALID_FW_ID */
 }
 
+static void xe_cper_record_emit(struct xe_device *xe, u8 severity,
+				const guid_t *notification_type,
+				const struct xe_cper_sec_intel_err_hdr *ihdr,
+				const void *einfo, u32 einfo_len)
+{
+	struct pci_dev *pdev = to_pci_dev(xe->drm.dev);
+	const guid_t *platform_id = lookup_platform_id(pdev);

Delay the assignments where possible, preferably after kzalloc().

drivers/gpu/drm/xe/xe_cper.c static void xe_cper_init_intel_err_hdr(struct xe_device *xe, · line 128

Quoted 4 lines
drivers/gpu/drm/xe/xe_cper.c +4 -0
+	u32 total_len = sizeof(struct xe_cper_nonstd_record) + einfo_len;
+	struct cper_section_descriptor *sdesc;
+	struct cper_record_header *rhdr;
+	struct xe_cper_nonstd_record *rec;

Reverse xmas tree order please!

Quoted 13 lines
drivers/gpu/drm/xe/xe_cper.c +13 -0
+	rec = kzalloc(total_len, GFP_KERNEL);
+	if (!rec)
+		return;
+
+	rhdr = &rec->record_hdr;
+	sdesc = &rec->section_desc;
+
+	/* Assemble the CPER record header (UEFI Appendix N.2.1) */
+	memcpy(rhdr->signature, CPER_SIG_RECORD, CPER_SIG_SIZE);
+	rhdr->revision          = CPER_RECORD_REV;
+	rhdr->signature_end     = CPER_SIG_END;
+	rhdr->section_count     = 1;
+	rhdr->error_severity    = severity;

drivers/gpu/drm/xe/xe_cper.c static void xe_cper_init_intel_err_hdr(struct xe_device *xe, · line 152

Quoted 10 lines
drivers/gpu/drm/xe/xe_cper.c +10 -0
+	rhdr->validation_bits   = CPER_VALID_TIMESTAMP;
+	rhdr->record_length     = total_len;
+	rhdr->timestamp         = cper_timestamp_now();
+	if (platform_id) {
+		rhdr->platform_id      = *platform_id;
+		rhdr->validation_bits |= CPER_VALID_PLATFORM_ID;
+	}
+	rhdr->creator_id        = INTEL_CPER_CREATOR_XEKMD;
+	rhdr->notification_type = *notification_type;
+	rhdr->record_id         = cper_next_record_id();

This looks like a small function that prepares rhdr.

drivers/gpu/drm/xe/xe_cper.c static void xe_cper_init_intel_err_hdr(struct xe_device *xe, · line 165

Quoted 12 lines
drivers/gpu/drm/xe/xe_cper.c +12 -0
+	/* Assemble the section descriptor (UEFI Appendix N.2.2) */
+	sdesc->section_offset   = sizeof(struct cper_record_header) +
+				  sizeof(struct cper_section_descriptor);
+	sdesc->section_length   = sizeof(struct xe_cper_sec_intel_err_hdr) + einfo_len;
+	sdesc->revision         = CPER_SEC_REV;
+	sdesc->validation_bits  = 0;
+	sdesc->section_type     = INTEL_CPER_SECTION_ACCEL_GENERIC;
+	if (xe->info.has_device_uid) {
+		memcpy(&sdesc->fru_id, &xe->device_uid, sizeof(xe->device_uid));
+		sdesc->validation_bits |= CPER_SEC_VALID_FRU_ID;
+	}
+	sdesc->section_severity = severity;

Ditto for sdesc.

Raag

Quoted 107 lines
drivers/gpu/drm/xe/xe_cper.c +15 -0
+	/* Copy the Intel-specific section header */
+	rec->intel_hdr = *ihdr;
+
+	/* Append optional variable-length error info */
+	if (einfo && einfo_len)
+		memcpy((u8 *)rec + sizeof(*rec), einfo, einfo_len);
+
+	/* TODO: Emit trace event */
+
+	kfree(rec);
+}
+
 static void xe_cper_emit_hw_err(struct xe_device *xe, int cper_sev, enum xe_sigid sigid,
 				const struct xe_ras_error_class *error_class)
 {
@@ -74,6 +193,9 @@ static void xe_cper_emit_hw_err(struct xe_device *xe, int cper_sev, enum xe_sigi
 
 	xe_cper_init_intel_err_hdr(xe, error_class, local_resp.timestamp,
 				   sigid, local_resp.value, &ihdr);
+
+	xe_cper_record_emit(xe, cper_sev, &INTEL_CPER_NOTIFY_GPU_ERROR,
+			    &ihdr, NULL, 0);
 }
 
 /**
drivers/gpu/drm/xe/xe_cper_types.h +53 -0
index 74307e7f78a2..7612518c9d47 100644
@@ -6,7 +6,9 @@
 #ifndef _XE_CPER_TYPES_H_
 #define _XE_CPER_TYPES_H_
 
+#include <linux/cper.h>
 #include <linux/types.h>
+#include <linux/uuid.h>
 
 /*
  * Validation bits definition for validation_bits in struct
@@ -20,6 +22,28 @@
 #define XE_CPER_VALID_DRV_VERSION	0x0010
 #define XE_CPER_VALID_FW_ID		0x0020
 
+/*
+ * Intel CPER GUID Namespace — RFC 9562 UUIDv5 (SHA-1 name-based)
+ *
+ * All values below are generated deterministically by uuid generator.
+ * Do not hand-edit the byte values.
+ */
+
+/* Creator IDs */
+#define INTEL_CPER_CREATOR_XEKMD \
+	GUID_INIT(0x9a42070f, 0xdf9d, 0x555e, \
+		  0xba, 0x02, 0x7c, 0xbc, 0x86, 0x3d, 0x37, 0x1c)
+
+/* Notification Types */
+#define INTEL_CPER_NOTIFY_GPU_ERROR \
+	GUID_INIT(0x4ae12aef, 0x8745, 0x5fc7, \
+		  0xb9, 0x96, 0x71, 0xee, 0xbb, 0x51, 0xf2, 0x23)
+
+/* Section Types */
+#define INTEL_CPER_SECTION_ACCEL_GENERIC \
+	GUID_INIT(0xea9d8f84, 0x4258, 0x5227, \
+		  0x80, 0x28, 0xb9, 0xb1, 0x3e, 0x6d, 0x58, 0xb0)
+
 #pragma pack(push, 1)
 
 /**
@@ -67,6 +91,35 @@ struct xe_cper_sec_intel_err_hdr {
 	u8 reserved[5];
 };
 
+/**
+ * struct xe_cper_nonstd_record - Intel GPU CPER record
+ *
+ * Contains the standard CPER record header, section descriptor, and the
+ * Intel error section header.
+ */
+struct xe_cper_nonstd_record {
+	/** @record_hdr: Standard CPER record header (UEFI Appendix N.2.1) */
+	struct cper_record_header record_hdr;
+	/** @section_desc: CPER section descriptor */
+	struct cper_section_descriptor section_desc;
+	/** @intel_hdr: Intel-specific error section header */
+	struct xe_cper_sec_intel_err_hdr intel_hdr;
+};
+
 #pragma pack(pop)
 
+/**
+ * struct xe_platform_id_entry - Mapping from PCI device ID to CPER platform GUID
+ *
+ * Used to resolve the platform_id field in a CPER section descriptor.
+ * GUIDs are UUIDv5 (RFC 9562, SHA-1) derived from the Intel CPER namespace
+ * with name string "platform/8086:<dev_id_hex_lower>".
+ */
+struct xe_platform_id_entry {
+	/** @device_id: PCI device ID */
+	u16       device_id;
+	/** @platform_id: Corresponding UUIDv5 platform GUID */
+	guid_t    platform_id;
+};
+
 #endif
Signature · 1 line
2.54.0
#13 lore raw

Re: [PATCH v4 04/12] drm/xe/cper: Construct CPER record for hardware errors

Quoted 14 lines · Raag Jadav
Quoted 14 lines
drivers/gpu/drm/xe/xe_cper.c +14 -0
+static const struct xe_platform_id_entry xe_platform_ids[] = {
+	/* 0x674C  platform/8086:674c */
+	{ 0x674C, GUID_INIT(0x9046afe5, 0x9041, 0x5124,
+			    0x86, 0x14, 0x92, 0x55, 0x0d, 0x9e, 0x9d, 0xa6) },
+	/* 0x674D  platform/8086:674d */
+	{ 0x674D, GUID_INIT(0xf95911b8, 0x6564, 0x5905,
+			    0xa6, 0xa7, 0xb9, 0xbf, 0x54, 0xab, 0x6c, 0x27) },
+	/* 0x674E  platform/8086:674e */
+	{ 0x674E, GUID_INIT(0xb8d24106, 0x0108, 0x59f1,
+			    0x8f, 0xfc, 0x9f, 0xc4, 0xa9, 0xc9, 0xb7, 0xb0) },
+	/* 0x674F  platform/8086:674f */
+	{ 0x674F, GUID_INIT(0xdd8dd88e, 0xef2f, 0x59b1,
+			    0x99, 0x15, 0xdb, 0x6f, 0x1d, 0xc9, 0xb4, 0x5d) },
+	/* 0x6750  platform/8086:6750 */
Quoted 8 lines

drivers/gpu/drm/xe/xe_cper.c static bool is_hw_sigid(enum xe_sigid sigid) · line 46

Quoted 6 lines
drivers/gpu/drm/xe/xe_cper.c +6 -0
+	{ 0x6750, GUID_INIT(0x1dd66c44, 0x87d5, 0x524a,
+			    0xad, 0x6e, 0xfc, 0x18, 0x9d, 0x42, 0x6f, 0x1a) },
+	/* 0x6751  platform/8086:6751 */
+	{ 0x6751, GUID_INIT(0x17d0dd04, 0x2fad, 0x5400,
+			    0x99, 0xc8, 0x9b, 0x45, 0x51, 0x3b, 0x67, 0xe3) },
+};

This is unrelated to cper and shouldn't be here. I'll rely on Matt's input on how to deal with these.

Agreed, I don't think this is the ideal place either. For now, I'll keep it here and, based on Matt's input, consider moving it to xe_pci.c, which maintains the PCI ID list for the platforms supported by Xe.

Thanks,
Badal

Quoted 11 lines
Quoted 11 lines
drivers/gpu/drm/xe/xe_cper.c +10 -0
+static const guid_t *lookup_platform_id(const struct pci_dev *pdev)
+{
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(xe_platform_ids); i++)
+		if (xe_platform_ids[i].device_id == pdev->device)
+			return &xe_platform_ids[i].platform_id;
+	return NULL;
+}
+
#14 lore raw

Re: [PATCH v4 04/12] drm/xe/cper: Construct CPER record for hardware errors

Quoted 26 lines · Badal
Quoted 14 lines · Raag Jadav
Quoted 14 lines
drivers/gpu/drm/xe/xe_cper.c +14 -0
+static const struct xe_platform_id_entry xe_platform_ids[] = {
+	/* 0x674C  platform/8086:674c */
+	{ 0x674C, GUID_INIT(0x9046afe5, 0x9041, 0x5124,
+			    0x86, 0x14, 0x92, 0x55, 0x0d, 0x9e, 0x9d, 0xa6) },
+	/* 0x674D  platform/8086:674d */
+	{ 0x674D, GUID_INIT(0xf95911b8, 0x6564, 0x5905,
+			    0xa6, 0xa7, 0xb9, 0xbf, 0x54, 0xab, 0x6c, 0x27) },
+	/* 0x674E  platform/8086:674e */
+	{ 0x674E, GUID_INIT(0xb8d24106, 0x0108, 0x59f1,
+			    0x8f, 0xfc, 0x9f, 0xc4, 0xa9, 0xc9, 0xb7, 0xb0) },
+	/* 0x674F  platform/8086:674f */
+	{ 0x674F, GUID_INIT(0xdd8dd88e, 0xef2f, 0x59b1,
+			    0x99, 0x15, 0xdb, 0x6f, 0x1d, 0xc9, 0xb4, 0x5d) },
+	/* 0x6750  platform/8086:6750 */
Quoted 8 lines

drivers/gpu/drm/xe/xe_cper.c static bool is_hw_sigid(enum xe_sigid sigid) · line 46

Quoted 6 lines
drivers/gpu/drm/xe/xe_cper.c +6 -0
+	{ 0x6750, GUID_INIT(0x1dd66c44, 0x87d5, 0x524a,
+			    0xad, 0x6e, 0xfc, 0x18, 0x9d, 0x42, 0x6f, 0x1a) },
+	/* 0x6751  platform/8086:6751 */
+	{ 0x6751, GUID_INIT(0x17d0dd04, 0x2fad, 0x5400,
+			    0x99, 0xc8, 0x9b, 0x45, 0x51, 0x3b, 0x67, 0xe3) },
+};

This is unrelated to cper and shouldn't be here. I'll rely on Matt's input on how to deal with these.

Quoted 2 lines

Agreed, I don't think this is the ideal place either. For now, I'll keep it here and, based on Matt's input, consider moving it to xe_pci.c, which maintains the PCI ID list for the platforms supported by Xe.

One reason I placed the table here is that these aren’t general-purpose platform GUIDs; they’re UUIDv5 values generated specifically for CPER’s platform_id field, using platform/8086:<device-id> as the name.

Since CPER is their only consumer, keeping the mapping with the CPER code seems reasonable to me.  I’m happy to follow Matt’s input if there’s a preferred place for this kind of mapping.

$ uuidgen --sha1 -n "$INTEL_NS" -N "platform/8086:674c"
9046afe5-9041-5124-8614-92550d9e9da6
$ uuidgen --sha1 -n "$INTEL_NS" -N "platform/8086:674d"
f95911b8-6564-5905-a6a7-b9bf54ab6c27
$ uuidgen --sha1 -n "$INTEL_NS" -N "platform/8086:674e"
b8d24106-0108-59f1-8ffc-9fc4a9c9b7b0
$ uuidgen --sha1 -n "$INTEL_NS" -N "platform/8086:674f"
dd8dd88e-ef2f-59b1-9915-db6f1dc9b45d
$ uuidgen --sha1 -n "$INTEL_NS" -N "platform/8086:6750"
1dd66c44-87d5-524a-ad6e-fc189d426f1a
$ uuidgen --sha1 -n "$INTEL_NS" -N "platform/8086:6751"
17d0dd04-2fad-5400-99c8-9b45513b67e3

Thanks,
Badal

Quoted 14 lines

Thanks,
Badal

Quoted 10 lines
Quoted 10 lines
drivers/gpu/drm/xe/xe_cper.c +10 -0
+static const guid_t *lookup_platform_id(const struct pci_dev *pdev)
+{
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(xe_platform_ids); i++)
+		if (xe_platform_ids[i].device_id == pdev->device)
+			return &xe_platform_ids[i].platform_id;
+	return NULL;
+}
+
#15 lore raw

Re: [PATCH v4 04/12] drm/xe/cper: Construct CPER record for hardware errors

Quoted 32 lines · Badal
Quoted 26 lines · Badal
Quoted 14 lines · Raag Jadav
Quoted 14 lines
drivers/gpu/drm/xe/xe_cper.c +14 -0
+static const struct xe_platform_id_entry xe_platform_ids[] = {
+	/* 0x674C  platform/8086:674c */
+	{ 0x674C, GUID_INIT(0x9046afe5, 0x9041, 0x5124,
+			    0x86, 0x14, 0x92, 0x55, 0x0d, 0x9e, 0x9d, 0xa6) },
+	/* 0x674D  platform/8086:674d */
+	{ 0x674D, GUID_INIT(0xf95911b8, 0x6564, 0x5905,
+			    0xa6, 0xa7, 0xb9, 0xbf, 0x54, 0xab, 0x6c, 0x27) },
+	/* 0x674E  platform/8086:674e */
+	{ 0x674E, GUID_INIT(0xb8d24106, 0x0108, 0x59f1,
+			    0x8f, 0xfc, 0x9f, 0xc4, 0xa9, 0xc9, 0xb7, 0xb0) },
+	/* 0x674F  platform/8086:674f */
+	{ 0x674F, GUID_INIT(0xdd8dd88e, 0xef2f, 0x59b1,
+			    0x99, 0x15, 0xdb, 0x6f, 0x1d, 0xc9, 0xb4, 0x5d) },
+	/* 0x6750  platform/8086:6750 */
Quoted 8 lines

drivers/gpu/drm/xe/xe_cper.c static bool is_hw_sigid(enum xe_sigid sigid) · line 46

Quoted 6 lines
drivers/gpu/drm/xe/xe_cper.c +6 -0
+	{ 0x6750, GUID_INIT(0x1dd66c44, 0x87d5, 0x524a,
+			    0xad, 0x6e, 0xfc, 0x18, 0x9d, 0x42, 0x6f, 0x1a) },
+	/* 0x6751  platform/8086:6751 */
+	{ 0x6751, GUID_INIT(0x17d0dd04, 0x2fad, 0x5400,
+			    0x99, 0xc8, 0x9b, 0x45, 0x51, 0x3b, 0x67, 0xe3) },
+};

This is unrelated to cper and shouldn't be here. I'll rely on Matt's input on how to deal with these.

Quoted 4 lines

Agreed, I don't think this is the ideal place either. For now, I'll keep it here and, based on Matt's input, consider moving it to xe_pci.c, which maintains the PCI ID list for the platforms supported by Xe.

Quoted 7 lines

One reason I placed the table here is that these aren’t general-purpose platform GUIDs; they’re UUIDv5 values generated specifically for CPER’s platform_id field, using platform/8086:<device-id> as the name.

Since CPER is their only consumer, keeping the mapping with the CPER code seems reasonable to me.  I’m happy to follow Matt’s input if there’s a preferred place for this kind of mapping.

My only concern is that we usually don't have device ids lying around in random components, but that I think is upto the maintainers.

Raag

#16 lore raw

Re: [PATCH v4 04/12] drm/xe/cper: Construct CPER record for hardware errors

Quoted 37 lines · Raag Jadav
Quoted 36 lines · Badal
Quoted 26 lines · Badal
Quoted 14 lines · Raag Jadav
Quoted 14 lines
drivers/gpu/drm/xe/xe_cper.c +14 -0
+static const struct xe_platform_id_entry xe_platform_ids[] = {
+	/* 0x674C  platform/8086:674c */
+	{ 0x674C, GUID_INIT(0x9046afe5, 0x9041, 0x5124,
+			    0x86, 0x14, 0x92, 0x55, 0x0d, 0x9e, 0x9d, 0xa6) },
+	/* 0x674D  platform/8086:674d */
+	{ 0x674D, GUID_INIT(0xf95911b8, 0x6564, 0x5905,
+			    0xa6, 0xa7, 0xb9, 0xbf, 0x54, 0xab, 0x6c, 0x27) },
+	/* 0x674E  platform/8086:674e */
+	{ 0x674E, GUID_INIT(0xb8d24106, 0x0108, 0x59f1,
+			    0x8f, 0xfc, 0x9f, 0xc4, 0xa9, 0xc9, 0xb7, 0xb0) },
+	/* 0x674F  platform/8086:674f */
+	{ 0x674F, GUID_INIT(0xdd8dd88e, 0xef2f, 0x59b1,
+			    0x99, 0x15, 0xdb, 0x6f, 0x1d, 0xc9, 0xb4, 0x5d) },
+	/* 0x6750  platform/8086:6750 */
Quoted 8 lines

drivers/gpu/drm/xe/xe_cper.c static bool is_hw_sigid(enum xe_sigid sigid) · line 46

Quoted 6 lines
drivers/gpu/drm/xe/xe_cper.c +6 -0
+	{ 0x6750, GUID_INIT(0x1dd66c44, 0x87d5, 0x524a,
+			    0xad, 0x6e, 0xfc, 0x18, 0x9d, 0x42, 0x6f, 0x1a) },
+	/* 0x6751  platform/8086:6751 */
+	{ 0x6751, GUID_INIT(0x17d0dd04, 0x2fad, 0x5400,
+			    0x99, 0xc8, 0x9b, 0x45, 0x51, 0x3b, 0x67, 0xe3) },
+};

This is unrelated to cper and shouldn't be here. I'll rely on Matt's input on how to deal with these.

Quoted 4 lines

Agreed, I don't think this is the ideal place either. For now, I'll keep it here and, based on Matt's input, consider moving it to xe_pci.c, which maintains the PCI ID list for the platforms supported by Xe.

One reason I placed the table here is that these aren’t general-purpose platform GUIDs; they’re UUIDv5 values generated specifically for CPER’s platform_id field, using platform/8086:<device-id> as the name.

Quoted 6 lines
Quoted 3 lines

Since CPER is their only consumer, keeping the mapping with the CPER code seems reasonable to me.  I’m happy to follow Matt’s input if there’s a preferred place for this kind of mapping.

My only concern is that we usually don't have device ids lying around in random components, but that I think is upto the maintainers.

Yeah, I'm not familiar with these structures. If they're CPER-specific, then keeping them in the CPER file seems natural to me. But it's also true that it could be easy for these to get out of sync with our general PCI ID list if PCI IDs are added/removed.

If a new PCI ID shows up, how do we know what the values should be here? Are they documented in the bspec somewhere? How do these values wind up getting used? Are there uapi / ABI implications of these values?

Aside from everything else, should we also add some kind of kunit test that makes sure we each PCI ID has an entry in this table and vice-versa to make sure we don't forget to update this table when platform PCI IDs are added/removed?

Matt

Quoted 2 lines

Raag

Signature · 4 lines
Matt Roper
Graphics Software Engineer
Linux GPU Platform Enablement
Intel Corporation
#17 lore raw

Re: [PATCH v4 04/12] drm/xe/cper: Construct CPER record for hardware errors

Quoted 35 lines · Matt Roper
Quoted 34 lines · Raag Jadav
Quoted 33 lines · Badal
Quoted 24 lines · Badal
Quoted 14 lines · Raag Jadav
Quoted 14 lines
drivers/gpu/drm/xe/xe_cper.c +14 -0
+static const struct xe_platform_id_entry xe_platform_ids[] = {
+	/* 0x674C  platform/8086:674c */
+	{ 0x674C, GUID_INIT(0x9046afe5, 0x9041, 0x5124,
+			    0x86, 0x14, 0x92, 0x55, 0x0d, 0x9e, 0x9d, 0xa6) },
+	/* 0x674D  platform/8086:674d */
+	{ 0x674D, GUID_INIT(0xf95911b8, 0x6564, 0x5905,
+			    0xa6, 0xa7, 0xb9, 0xbf, 0x54, 0xab, 0x6c, 0x27) },
+	/* 0x674E  platform/8086:674e */
+	{ 0x674E, GUID_INIT(0xb8d24106, 0x0108, 0x59f1,
+			    0x8f, 0xfc, 0x9f, 0xc4, 0xa9, 0xc9, 0xb7, 0xb0) },
+	/* 0x674F  platform/8086:674f */
+	{ 0x674F, GUID_INIT(0xdd8dd88e, 0xef2f, 0x59b1,
+			    0x99, 0x15, 0xdb, 0x6f, 0x1d, 0xc9, 0xb4, 0x5d) },
+	/* 0x6750  platform/8086:6750 */
Quoted 8 lines

drivers/gpu/drm/xe/xe_cper.c static bool is_hw_sigid(enum xe_sigid sigid) · line 46

Quoted 6 lines
drivers/gpu/drm/xe/xe_cper.c +6 -0
+	{ 0x6750, GUID_INIT(0x1dd66c44, 0x87d5, 0x524a,
+			    0xad, 0x6e, 0xfc, 0x18, 0x9d, 0x42, 0x6f, 0x1a) },
+	/* 0x6751  platform/8086:6751 */
+	{ 0x6751, GUID_INIT(0x17d0dd04, 0x2fad, 0x5400,
+			    0x99, 0xc8, 0x9b, 0x45, 0x51, 0x3b, 0x67, 0xe3) },
+};

This is unrelated to cper and shouldn't be here. I'll rely on Matt's input on how to deal with these.

Quoted 4 lines

Agreed, I don't think this is the ideal place either. For now, I'll keep it here and, based on Matt's input, consider moving it to xe_pci.c, which maintains the PCI ID list for the platforms supported by Xe.

One reason I placed the table here is that these aren’t general-purpose platform GUIDs; they’re UUIDv5 values generated specifically for CPER’s platform_id field, using platform/8086:<device-id> as the name.

Quoted 7 lines
Quoted 5 lines
Quoted 3 lines

Since CPER is their only consumer, keeping the mapping with the CPER code seems reasonable to me.  I’m happy to follow Matt’s input if there’s a preferred place for this kind of mapping.

My only concern is that we usually don't have device ids lying around in random components, but that I think is upto the maintainers.

Yeah, I'm not familiar with these structures. If they're CPER-specific, then keeping them in the CPER file seems natural to me.

Fine, I will keep them here only.

Quoted 6 lines

But it's also
true that it could be easy for these to get out of sync with our general PCI ID list if PCI IDs are added/removed.

If a new PCI ID shows up, how do we know what the values should be here? Are they documented in the bspec somewhere?

No these are generated as using uuidgen utility as UUIDv5.

$ INTEL_NS=$(uuidgen --sha1 -n @dns -N "intel.com")

uuidgen --sha1 -n "$INTEL_NS" -N "platform/8086:674c" 9046afe5-9041-5124-8614-92550d9e9da6

Quoted 2 lines

How do these values wind up
getting used?

This UUID is populated in CPER record to identify the platform/SKU associated with it.

Quoted 1 line

Are there uapi / ABI implications of these values?

No uapi implications. As they are part of CPER record should remain stable for given platform/PCI ID.

I am considering generating the platform UUID dynamically using UUIDv5, with the PCI vendor/device ID as the name.

This keeps the UUID deterministic for a given PCI ID and avoids maintaining a separate mapping table when PCI IDs are added or removed.

+/* Namespace: uuidgen --sha1 -n @dns -N "intel.com" */ +#define INTEL_CPER_NAMESPACE \
+       UUID_INIT(0x3e54f727, 0x549c, 0x5ab3, \
+                 0x90, 0x73, 0x52, 0x2a, 0x81, 0x15, 0x20, 0xe7) +

+/*
+ * Platform GUID is UUIDv5 (RFC 9562) of "platform/8086:<devid>" in the
+ * Intel CPER namespace, stored in the mixed-endian guid_t layout used by CPER.
+ */
+static void cper_platform_id(const struct pci_dev *pdev, guid_t *guid) +{
+       static const uuid_t ns = INTEL_CPER_NAMESPACE;
+       u8 digest[SHA1_DIGEST_SIZE];
+       struct sha1_ctx ctx;
+       char name[sizeof("platform/8086:ffff")];
+       int len;
+
+       len = scnprintf(name, sizeof(name), "platform/%04x:%04x",
+                       pdev->vendor, pdev->device);
+
+       sha1_init(&ctx);
+       sha1_update(&ctx, ns.b, UUID_SIZE);
+       sha1_update(&ctx, name, len);
+       sha1_final(&ctx, digest);
+
+       digest[6] = (digest[6] & 0x0f) | 0x50;
+       digest[8] = (digest[8] & 0x3f) | 0x80;
+
+       *guid = GUID_INIT(get_unaligned_be32(&digest[0]),
+                         get_unaligned_be16(&digest[4]),
+                         get_unaligned_be16(&digest[6]),
+                         digest[8], digest[9], digest[10], digest[11], +                         digest[12], digest[13], digest[14], digest[15]); }

Quoted 5 lines

Aside from everything else, should we also add some kind of kunit test that makes sure we each PCI ID has an entry in this table and vice-versa to make sure we don't forget to update this table when platform PCI IDs are added/removed?

Agree, Kunit can be added as follow up.

Thanks,
Badal

Quoted 5 lines

Matt

Quoted 1 line

Raag

#18 lore raw

Re: [PATCH v4 04/12] drm/xe/cper: Construct CPER record for hardware errors

Quoted 109 lines · Badal
Quoted 34 lines · Matt Roper
Quoted 33 lines · Raag Jadav
Quoted 32 lines · Badal
Quoted 23 lines · Badal
Quoted 14 lines · Raag Jadav
Quoted 14 lines
(quoted diff) +14 -0
+static const struct xe_platform_id_entry xe_platform_ids[] = {
+	/* 0x674C  platform/8086:674c */
+	{ 0x674C, GUID_INIT(0x9046afe5, 0x9041, 0x5124,
+			    0x86, 0x14, 0x92, 0x55, 0x0d, 0x9e, 0x9d, 0xa6) },
+	/* 0x674D  platform/8086:674d */
+	{ 0x674D, GUID_INIT(0xf95911b8, 0x6564, 0x5905,
+			    0xa6, 0xa7, 0xb9, 0xbf, 0x54, 0xab, 0x6c, 0x27) },
+	/* 0x674E  platform/8086:674e */
+	{ 0x674E, GUID_INIT(0xb8d24106, 0x0108, 0x59f1,
+			    0x8f, 0xfc, 0x9f, 0xc4, 0xa9, 0xc9, 0xb7, 0xb0) },
+	/* 0x674F  platform/8086:674f */
+	{ 0x674F, GUID_INIT(0xdd8dd88e, 0xef2f, 0x59b1,
+			    0x99, 0x15, 0xdb, 0x6f, 0x1d, 0xc9, 0xb4, 0x5d) },
+	/* 0x6750  platform/8086:6750 */
Quoted 8 lines

Review

Quoted 6 lines
(quoted diff) +6 -0
+	{ 0x6750, GUID_INIT(0x1dd66c44, 0x87d5, 0x524a,
+			    0xad, 0x6e, 0xfc, 0x18, 0x9d, 0x42, 0x6f, 0x1a) },
+	/* 0x6751  platform/8086:6751 */
+	{ 0x6751, GUID_INIT(0x17d0dd04, 0x2fad, 0x5400,
+			    0x99, 0xc8, 0x9b, 0x45, 0x51, 0x3b, 0x67, 0xe3) },
+};

This is unrelated to cper and shouldn't be here. I'll rely on Matt's input on how to deal with these.

Quoted 4 lines

Agreed, I don't think this is the ideal place either. For now, I'll keep it here and, based on Matt's input, consider moving it to xe_pci.c, which maintains the PCI ID list for the platforms supported by Xe.

One reason I placed the table here is that these aren’t general-purpose platform GUIDs; they’re UUIDv5 values generated specifically for CPER’s platform_id field, using platform/8086:<device-id> as the name.

Quoted 7 lines
Quoted 5 lines
Quoted 3 lines

Since CPER is their only consumer, keeping the mapping with the CPER code seems reasonable to me.  I’m happy to follow Matt’s input if there’s a preferred place for this kind of mapping.

My only concern is that we usually don't have device ids lying around in random components, but that I think is upto the maintainers.

Yeah, I'm not familiar with these structures. If they're CPER-specific, then keeping them in the CPER file seems natural to me.

Fine, I will keep them here only.

Quoted 6 lines

But it's also
true that it could be easy for these to get out of sync with our general PCI ID list if PCI IDs are added/removed.

If a new PCI ID shows up, how do we know what the values should be here? Are they documented in the bspec somewhere?

No these are generated as using uuidgen utility as UUIDv5.

$ INTEL_NS=$(uuidgen --sha1 -n @dns -N "intel.com")

uuidgen --sha1 -n "$INTEL_NS" -N "platform/8086:674c" 9046afe5-9041-5124-8614-92550d9e9da6

Quoted 2 lines

How do these values wind up
getting used?

This UUID is populated in CPER record to identify the platform/SKU associated with it.

Quoted 1 line

Are there uapi / ABI implications of these values?

No uapi implications. As they are part of CPER record should remain stable for given platform/PCI ID.

I am considering generating the platform UUID dynamically using UUIDv5, with the PCI vendor/device ID as the name.

This keeps the UUID deterministic for a given PCI ID and avoids maintaining a separate mapping table when PCI IDs are added or removed.

(quoted diff) +8 -0
+/* Namespace: uuidgen --sha1 -n @dns -N "intel.com" */
+#define INTEL_CPER_NAMESPACE \
+       UUID_INIT(0x3e54f727, 0x549c, 0x5ab3, \
+                 0x90, 0x73, 0x52, 0x2a, 0x81, 0x15, 0x20, 0xe7)
+
 
+/*
+ * Platform GUID is UUIDv5 (RFC 9562) of "platform/8086:<devid>" in the
+ * Intel CPER namespace, stored in the mixed-endian guid_t layout 

used by CPER.
+ */

(quoted diff) +24 -0
+static void cper_platform_id(const struct pci_dev *pdev, guid_t *guid)
+{
+       static const uuid_t ns = INTEL_CPER_NAMESPACE;
+       u8 digest[SHA1_DIGEST_SIZE];
+       struct sha1_ctx ctx;
+       char name[sizeof("platform/8086:ffff")];
+       int len;
+
+       len = scnprintf(name, sizeof(name), "platform/%04x:%04x",
+                       pdev->vendor, pdev->device);
+
+       sha1_init(&ctx);
+       sha1_update(&ctx, ns.b, UUID_SIZE);
+       sha1_update(&ctx, name, len);
+       sha1_final(&ctx, digest);
+
+       digest[6] = (digest[6] & 0x0f) | 0x50;
+       digest[8] = (digest[8] & 0x3f) | 0x80;
+
+       *guid = GUID_INIT(get_unaligned_be32(&digest[0]),
+                         get_unaligned_be16(&digest[4]),
+                         get_unaligned_be16(&digest[6]),
+                         digest[8], digest[9], digest[10], digest[11],
+                         digest[12], digest[13], digest[14], digest[15]);
Quoted 2 lines

 }

If we want to go this way, IMO this logic should be placed in lib/uuid.c and not in Xe. But ...

Quoted 7 lines
Quoted 4 lines

Aside from everything else, should we also add some kind of kunit test that makes sure we each PCI ID has an entry in this table and vice-versa to make sure we don't forget to update this table when platform PCI IDs are added/removed?

Agree, Kunit can be added as follow up.

... any reason the Kunit isn't enough with a static table? If we add it immediately instead of later, we'd be sure to get a CI failure if a new PCI ID is added without the matching GUID. Compared to the dynamic generation, we wouldn't get the GUID for free if we get a new PCI ID, but overall it should be less work IMO.

Daniele

Quoted 6 lines

Thanks,
Badal

Quoted 3 lines

Matt

Quoted 1 line

Raag

#19 lore raw

Re: [PATCH v4 04/12] drm/xe/cper: Construct CPER record for hardware errors

Quoted 117 lines · Daniele
Quoted 109 lines · Badal
Quoted 34 lines · Matt Roper
Quoted 33 lines · Raag Jadav
Quoted 32 lines · Badal
Quoted 23 lines · Badal
Quoted 14 lines · Raag Jadav
Quoted 14 lines
(quoted diff) +14 -0
+static const struct xe_platform_id_entry xe_platform_ids[] = {
+	/* 0x674C  platform/8086:674c */
+	{ 0x674C, GUID_INIT(0x9046afe5, 0x9041, 0x5124,
+			    0x86, 0x14, 0x92, 0x55, 0x0d, 0x9e, 0x9d, 0xa6) },
+	/* 0x674D  platform/8086:674d */
+	{ 0x674D, GUID_INIT(0xf95911b8, 0x6564, 0x5905,
+			    0xa6, 0xa7, 0xb9, 0xbf, 0x54, 0xab, 0x6c, 0x27) },
+	/* 0x674E  platform/8086:674e */
+	{ 0x674E, GUID_INIT(0xb8d24106, 0x0108, 0x59f1,
+			    0x8f, 0xfc, 0x9f, 0xc4, 0xa9, 0xc9, 0xb7, 0xb0) },
+	/* 0x674F  platform/8086:674f */
+	{ 0x674F, GUID_INIT(0xdd8dd88e, 0xef2f, 0x59b1,
+			    0x99, 0x15, 0xdb, 0x6f, 0x1d, 0xc9, 0xb4, 0x5d) },
+	/* 0x6750  platform/8086:6750 */
Quoted 8 lines

Review

Quoted 6 lines
(quoted diff) +6 -0
+	{ 0x6750, GUID_INIT(0x1dd66c44, 0x87d5, 0x524a,
+			    0xad, 0x6e, 0xfc, 0x18, 0x9d, 0x42, 0x6f, 0x1a) },
+	/* 0x6751  platform/8086:6751 */
+	{ 0x6751, GUID_INIT(0x17d0dd04, 0x2fad, 0x5400,
+			    0x99, 0xc8, 0x9b, 0x45, 0x51, 0x3b, 0x67, 0xe3) },
+};

This is unrelated to cper and shouldn't be here. I'll rely on Matt's input on how to deal with these.

Quoted 4 lines

Agreed, I don't think this is the ideal place either. For now, I'll keep it here and, based on Matt's input, consider moving it to xe_pci.c, which maintains the PCI ID list for the platforms supported by Xe.

One reason I placed the table here is that these aren’t general-purpose platform GUIDs; they’re UUIDv5 values generated specifically for CPER’s platform_id field, using platform/8086:<device-id> as the name.

Quoted 7 lines
Quoted 5 lines
Quoted 3 lines

Since CPER is their only consumer, keeping the mapping with the CPER code seems reasonable to me.  I’m happy to follow Matt’s input if there’s a preferred place for this kind of mapping.

My only concern is that we usually don't have device ids lying around in random components, but that I think is upto the maintainers.

Yeah, I'm not familiar with these structures. If they're CPER-specific, then keeping them in the CPER file seems natural to me.

Fine, I will keep them here only.

Quoted 6 lines

But it's also
true that it could be easy for these to get out of sync with our general PCI ID list if PCI IDs are added/removed.

If a new PCI ID shows up, how do we know what the values should be here? Are they documented in the bspec somewhere?

No these are generated as using uuidgen utility as UUIDv5.

$ INTEL_NS=$(uuidgen --sha1 -n @dns -N "intel.com")

uuidgen --sha1 -n "$INTEL_NS" -N "platform/8086:674c" 9046afe5-9041-5124-8614-92550d9e9da6

Quoted 2 lines

How do these values wind up
getting used?

This UUID is populated in CPER record to identify the platform/SKU associated with it.

Quoted 1 line

Are there uapi / ABI implications of these values?

No uapi implications. As they are part of CPER record should remain stable for given platform/PCI ID.

I am considering generating the platform UUID dynamically using UUIDv5, with the PCI vendor/device ID as the name.

This keeps the UUID deterministic for a given PCI ID and avoids maintaining a separate mapping table when PCI IDs are added or removed.

(quoted diff) +8 -0
+/* Namespace: uuidgen --sha1 -n @dns -N "intel.com" */
+#define INTEL_CPER_NAMESPACE \
+       UUID_INIT(0x3e54f727, 0x549c, 0x5ab3, \
+                 0x90, 0x73, 0x52, 0x2a, 0x81, 0x15, 0x20, 0xe7)
+
 
+/*
+ * Platform GUID is UUIDv5 (RFC 9562) of "platform/8086:<devid>" in the
+ * Intel CPER namespace, stored in the mixed-endian guid_t layout 

used by CPER.
+ */

(quoted diff) +24 -0
+static void cper_platform_id(const struct pci_dev *pdev, guid_t *guid)
+{
+       static const uuid_t ns = INTEL_CPER_NAMESPACE;
+       u8 digest[SHA1_DIGEST_SIZE];
+       struct sha1_ctx ctx;
+       char name[sizeof("platform/8086:ffff")];
+       int len;
+
+       len = scnprintf(name, sizeof(name), "platform/%04x:%04x",
+                       pdev->vendor, pdev->device);
+
+       sha1_init(&ctx);
+       sha1_update(&ctx, ns.b, UUID_SIZE);
+       sha1_update(&ctx, name, len);
+       sha1_final(&ctx, digest);
+
+       digest[6] = (digest[6] & 0x0f) | 0x50;
+       digest[8] = (digest[8] & 0x3f) | 0x80;
+
+       *guid = GUID_INIT(get_unaligned_be32(&digest[0]),
+                         get_unaligned_be16(&digest[4]),
+                         get_unaligned_be16(&digest[6]),
+                         digest[8], digest[9], digest[10], digest[11],
+                         digest[12], digest[13], digest[14], 
Quoted 3 lines

digest[15]);
 }

If we want to go this way, IMO this logic should be placed in lib/uuid.c and not in Xe. But ...

Quoted 9 lines
Quoted 7 lines
Quoted 4 lines

Aside from everything else, should we also add some kind of kunit test that makes sure we each PCI ID has an entry in this table and vice-versa to make sure we don't forget to update this table when platform PCI IDs are added/removed?

Agree, Kunit can be added as follow up.

... any reason the Kunit isn't enough with a static table? If we add it immediately instead of later, we'd be sure to get a CI failure if a new PCI ID is added without the matching GUID. Compared to the dynamic generation, we wouldn't get the GUID for free if we get a new PCI ID, but overall it should be less work IMO.

Agree, a static table makes more sense. I'll keep the static table and add a WARN_ONCE() for PCI IDs without a corresponding GUID. Since the current table covers all existing CRI PCI IDs, I'd prefer to add the KUnit coverage as a follow-up with the SW CPER work.

Badal

Quoted 8 lines

Daniele

Quoted 6 lines

Thanks,
Badal

Quoted 3 lines

Matt

Quoted 1 line

Raag

#20 lore raw

PATCH v4 5/12 drm/xe/xe_ras: Add support to retrieve info queue data for CRI

In reply to Badal Nilawar

Retrieve the RAS info queue data, in multiple chunks, and assemble it into a flat buffer. A follow-up patch will use this data to prepare the CPER error info.

Assisted-by Copilot:Claude-Opus-5.5

---
v4:
- Simplify info queue handling and validation (Raag)
- Clean up info queue naming and definitions (Raag)
- Validate each chunk against the requested offset

---
 drivers/gpu/drm/xe/xe_ras.c                   | 117 +++++++++++++++++
 drivers/gpu/drm/xe/xe_ras.h                   |   3 +
 drivers/gpu/drm/xe/xe_ras_types.h             | 118 +++++++++++++++++-
 drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h |   2 +
 4 files changed, 238 insertions(+), 2 deletions(-)
drivers/gpu/drm/xe/xe_ras.c +117 -0
index 5cfc9beff8c1..900319938fe5 100644
@@ -788,6 +788,123 @@ int xe_ras_set_threshold(struct xe_device *xe, u8 severity, u8 component, u32 th
 	return 0;
 }
 
+static int get_info_queue_data(struct xe_device *xe,
+			       struct xe_ras_get_info_queue_request *req,
+			       struct xe_ras_get_info_queue_response *out)
+{
+	struct xe_ras_get_info_queue_response response = {0};
+	struct xe_sysctrl_mailbox_command command = {0};
+	const struct xe_ras_info_queue_header *hdr;
+	size_t rlen;
+	int ret;
+
+	xe_sysctrl_create_command(&command, XE_SYSCTRL_GROUP_GFSP, XE_SYSCTRL_CMD_GET_INFO_QUEUE,
+				  req, sizeof(*req), &response, sizeof(response));
+
+	ret = xe_sysctrl_send_command(&xe->sc, &command, &rlen);
+	if (ret) {
+		xe_err(xe, "sysctrl: failed to get info queue data %d\n", ret);
+		return ret;
+	}
+
+	if (rlen != sizeof(response)) {
+		xe_err(xe, "sysctrl: unexpected get info queue data response length %zu (expected %zu)\n",
+		       rlen, sizeof(response));
+		return -EIO;
+	}
+
+	hdr = &response.queue_response.header;
+	xe_dbg(xe, "[RAS]: info queue data: status=%u chunk_size=%u flags=0x%x\n",
+	       response.operation_status, hdr->chunk_size, hdr->flags);
+
+	*out = response;
+	return 0;
+}
+
+static bool chunk_is_valid(const struct xe_ras_info_queue_header *hdr,
+			   u32 expected_offset, u32 dest_size)
+{
+	u32 end;
+
+	return hdr->chunk_offset == expected_offset &&
+	       hdr->chunk_size && hdr->chunk_size <= XE_RAS_INFO_QUEUE_MAX_CHUNK_SIZE &&
+	       !check_add_overflow(hdr->chunk_offset, hdr->chunk_size, &end) &&
+	       end <= XE_RAS_INFO_QUEUE_MAX_TOTAL_SIZE && end <= dest_size;
+}
+
+/**
+ * xe_ras_drain_info_queue_raw() - Drain the full RAS info queue into a flat buffer
+ * @xe: xe device
+ * @counter_resp: counter response carrying the first embedded chunk and the
+ *                counter identifier used as the source context for subsequent
+ *                GET_INFO_QUEUE fetches
+ * @dest_buf: destination buffer supplied by the caller
+ * @dest_size: size of @dest_buf in bytes; also caps the total amount of data
+ *             assembled from the info queue
+ *
+ * Copies the first chunk already embedded in @counter_resp, then loops
+ * issuing GET_INFO_QUEUE to fetch any remaining chunks until the queue
+ * signals no more data or a transport/bounds error is encountered.  On
+ * transport or bounds errors the function stops and returns whatever has
+ * been assembled so far.
+ *
+ * Returns: number of valid bytes written into @dest_buf.  Zero if @dest_buf is
+ *          NULL or @dest_size is 0.
+ */
+u32 xe_ras_drain_info_queue_raw(struct xe_device *xe,
+				const struct xe_ras_get_counter_response *counter_resp,
+				u8 *dest_buf, u32 dest_size)
+{
+	const struct xe_ras_info_queue_header *first_hdr = &counter_resp->first.header;
+	struct xe_ras_get_info_queue_request req = {0};
+	struct xe_ras_get_info_queue_response resp;
+	u32 flags = first_hdr->flags;
+	u32 offset = 0;
+
+	if (!dest_buf || !dest_size)
+		return 0;
+
+	if (first_hdr->total_size > dest_size)
+		xe_warn(xe, "[RAS]: info queue size %u exceeds %u, truncating\n",
+			first_hdr->total_size, dest_size);
+
+	/* Copy first chunk already embedded in the counter response */
+	if (chunk_is_valid(first_hdr, offset, dest_size)) {
+		memcpy(dest_buf, counter_resp->first.data, first_hdr->chunk_size);
+		offset = first_hdr->chunk_size;
+	}
+
+	req.source_command = XE_SYSCTRL_CMD_GET_COUNTER;
+	req.source_context = counter_resp->counter;
+	req.queue_request.session_id = counter_resp->counter;
+
+	/* Fetch any remaining chunks */
+	while ((flags & XE_RAS_INFO_QUEUE_FLAG_MORE_DATA) && offset < dest_size) {
+		const struct xe_ras_info_queue_header *hdr = &resp.queue_response.header;
+
+		req.queue_request.offset = offset;
+		req.queue_request.size = min(XE_RAS_INFO_QUEUE_MAX_CHUNK_SIZE, dest_size - offset);
+
+		if (get_info_queue_data(xe, &req, &resp)) {
+			xe_err(xe, "[RAS]: info queue drain aborted: fetch at offset=%u failed\n",
+			       offset);
+			return offset;
+		}
+
+		if (!chunk_is_valid(hdr, offset, dest_size)) {
+			xe_warn(xe, "[RAS]: invalid info queue chunk (offset=%u size=%u, expected offset=%u)\n",
+				hdr->chunk_offset, hdr->chunk_size, offset);
+			return offset;
+		}
+
+		memcpy(dest_buf + offset, resp.queue_response.data, hdr->chunk_size);
+		offset += hdr->chunk_size;
+		flags = hdr->flags;
+	}
+
+	return min(offset, first_hdr->total_size);
+}
+
 static ssize_t gpu_health_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	struct xe_ras_get_health_response response = {0};
drivers/gpu/drm/xe/xe_ras.h +3 -0
index 84700ea63394..27ce6265ace5 100644
@@ -22,5 +22,8 @@ void xe_ras_init(struct xe_device *xe);
 enum xe_ras_recovery_action xe_ras_process_errors(struct xe_device *xe);
 int xe_ras_get_counter_response(struct xe_device *xe, const struct xe_ras_error_class *counter,
 				struct xe_ras_get_counter_response *out);
+u32 xe_ras_drain_info_queue_raw(struct xe_device *xe,
+				const struct xe_ras_get_counter_response *counter_resp,
+				u8 *dest_buf, u32 dest_size);
 
 #endif
drivers/gpu/drm/xe/xe_ras_types.h +116 -2

136 lines not on this page · raw message

drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h +2 -0
index a0628eb47bff..299d12b94574 100644
@@ -34,6 +34,7 @@ enum xe_sysctrl_group {
  * @XE_SYSCTRL_CMD_GET_PENDING_EVENT: Retrieve pending event
  * @XE_SYSCTRL_CMD_GET_HEALTH: Retrieve gpu health
  * @XE_SYSCTRL_CMD_SET_HEALTH: Set gpu health
+ * @XE_SYSCTRL_CMD_GET_INFO_QUEUE: Retrieve a chunk of info queue data
  */
 enum xe_sysctrl_gfsp_cmd {
 	XE_SYSCTRL_CMD_GET_SOC_ERROR		= 0x01,
@@ -44,6 +45,7 @@ enum xe_sysctrl_gfsp_cmd {
 	XE_SYSCTRL_CMD_GET_PENDING_EVENT	= 0x07,
 	XE_SYSCTRL_CMD_GET_HEALTH		= 0x0B,
 	XE_SYSCTRL_CMD_SET_HEALTH		= 0x0C,
+	XE_SYSCTRL_CMD_GET_INFO_QUEUE		= 0x0D,
 };
 
 /**
Signature · 1 line
2.54.0
#21 lore raw

Re: [PATCH v4 05/12] drm/xe/xe_ras: Add support to retrieve info queue data for CRI

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider: - [Medium] xe_ras: missing validation of operation_status in get_info_queue_data --

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Medium] xe_ras: missing validation of operation_status in get_info_queue_data --

commit 7080ef5206c9792b353853f321f38646d98e4924
Author: Badal Nilawar <[email protected]>

drm/xe/xe_ras: Add support to retrieve info queue data for CRI

Retrieve the RAS info queue data, in multiple chunks, and assemble it into a flat buffer. A follow-up patch will use this data to prepare the CPER error info.

Quoted 4 lines
drivers/gpu/drm/xe/xe_ras.c +0 -0
index 5cfc9beff8c13..900319938fe54 100644

[ ... ]

Quoted 4 lines
drivers/gpu/drm/xe/xe_ras.c +4 -0
+static int get_info_queue_data(struct xe_device *xe,
+			       struct xe_ras_get_info_queue_request *req,
+			       struct xe_ras_get_info_queue_response *out)
+{

[ ... ]

drivers/gpu/drm/xe/xe_ras.c int xe_ras_set_threshold(struct xe_device *xe, u8 severity, u8 component, u32 th · line 822

Quoted 13 lines
drivers/gpu/drm/xe/xe_ras.c +13 -0
+	if (rlen != sizeof(response)) {
+		xe_err(xe, "sysctrl: unexpected get info queue data response length %zu (expected %zu)\n",
+		       rlen, sizeof(response));
+		return -EIO;
+	}
+
+	hdr = &response.queue_response.header;
+	xe_dbg(xe, "[RAS]: info queue data: status=%u chunk_size=%u flags=0x%x\n",
+	       response.operation_status, hdr->chunk_size, hdr->flags);
+
+	*out = response;
+	return 0;
+}

[Severity: Medium]
Does this code need to validate response.operation_status and return an error if the firmware operation failed?

get_info_queue_data() executes the XE_SYSCTRL_CMD_GET_INFO_QUEUE mailbox command to fetch chunks from the firmware. The firmware response includes an operation_status field to indicate whether the request was successful or rejected (e.g., due to an invalid session ID or out-of-bounds offset).

However, this only logs the status in a debug message and unconditionally returns 0 (success). Because it fails to return an error (such as converting the status via ras_status_to_errno()), the caller xe_ras_drain_info_queue_raw() will proceed to validate and process the payload. If the firmware did not populate the payload on error, it will contain zeroes or garbage, resulting in a confusing "invalid info queue chunk" warning or silent failure, rather than properly halting the fetch with the correct error code.

Signature · 1 line
Sashiko AI review · https://sashiko.dev/#/patchset/[email protected]?part=5
#22 lore raw

Re: [PATCH v4 05/12] drm/xe/xe_ras: Add support to retrieve info queue data for CRI

Quoted 45 lines · On 09-10-2026 16:10, [email protected] wrote:

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Medium] xe_ras: missing validation of operation_status in get_info_queue_data --

commit 7080ef5206c9792b353853f321f38646d98e4924
Author: Badal Nilawar <[email protected]>

drm/xe/xe_ras: Add support to retrieve info queue data for CRI

Retrieve the RAS info queue data, in multiple chunks, and assemble it into a flat buffer. A follow-up patch will use this data to prepare the CPER error info.

Quoted 4 lines
drivers/gpu/drm/xe/xe_ras.c +0 -0
index 5cfc9beff8c13..900319938fe54 100644

[ ... ]

Quoted 4 lines
drivers/gpu/drm/xe/xe_ras.c +4 -0
+static int get_info_queue_data(struct xe_device *xe,
+			       struct xe_ras_get_info_queue_request *req,
+			       struct xe_ras_get_info_queue_response *out)
+{

[ ... ]

drivers/gpu/drm/xe/xe_ras.c int xe_ras_set_threshold(struct xe_device *xe, u8 severity, u8 component, u32 th · line 822

Quoted 13 lines
drivers/gpu/drm/xe/xe_ras.c +13 -0
+	if (rlen != sizeof(response)) {
+		xe_err(xe, "sysctrl: unexpected get info queue data response length %zu (expected %zu)\n",
+		       rlen, sizeof(response));
+		return -EIO;
+	}
+
+	hdr = &response.queue_response.header;
+	xe_dbg(xe, "[RAS]: info queue data: status=%u chunk_size=%u flags=0x%x\n",
+	       response.operation_status, hdr->chunk_size, hdr->flags);
+
+	*out = response;
+	return 0;
+}

[Severity: Medium]
Does this code need to validate response.operation_status and return an error if the firmware operation failed?

get_info_queue_data() executes the XE_SYSCTRL_CMD_GET_INFO_QUEUE mailbox command to fetch chunks from the firmware. The firmware response includes an operation_status field to indicate whether the request was successful or rejected (e.g., due to an invalid session ID or out-of-bounds offset).

Quoted 8 lines

However, this only logs the status in a debug message and unconditionally returns 0 (success). Because it fails to return an error (such as converting the status via ras_status_to_errno()), the caller xe_ras_drain_info_queue_raw() will proceed to validate and process the payload. If the firmware did not populate the payload on error, it will contain zeroes or garbage, resulting in a confusing "invalid info queue chunk" warning or silent failure, rather than properly halting the fetch with the correct error code.

The firmware does not use operation_status for GET_INFO_QUEUE.

It should have been marked reserved like the other unused info queue fields, and I missed it in v4.

I'll mark it reserved in v5 and drop it from the debug print.

The field stays in the struct because the response layout is part of the firmware ABI.

Each chunk header is still validated by chunk_is_valid() (expected offset, non-zero size, bounds) before any data is copied, so a rejected or malformed response stops the drain.

Thanks,
Badal

Quoted 1 line
#23 lore raw

Re: [PATCH v4 05/12] drm/xe/xe_ras: Add support to retrieve info queue data for CRI

In reply to Badal Nilawar

On Fri, Oct 09, 2026 at 04:16:08PM +0530, Badal Nilawar wrote:

Nit: Although this is only available on selected platforms, the implementation is platform agnostic. So I'd remove CRI from subject.

Quoted 3 lines

Retrieve the RAS info queue data, in multiple chunks, and assemble it into a flat buffer. A follow-up patch will use this data to prepare the CPER error info.

Again, no follow-up. Just describe this patch.

Quoted 19 lines
Assisted-by Copilot:Claude-Opus-5.5

---
v4:
- Simplify info queue handling and validation (Raag)
- Clean up info queue naming and definitions (Raag)
- Validate each chunk against the requested offset

---
 drivers/gpu/drm/xe/xe_ras.c                   | 117 +++++++++++++++++
 drivers/gpu/drm/xe/xe_ras.h                   |   3 +
 drivers/gpu/drm/xe/xe_ras_types.h             | 118 +++++++++++++++++-
 drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h |   2 +
 4 files changed, 238 insertions(+), 2 deletions(-)
drivers/gpu/drm/xe/xe_ras.c +0 -0
index 5cfc9beff8c1..900319938fe5 100644

drivers/gpu/drm/xe/xe_ras.c int xe_ras_set_threshold(struct xe_device *xe, u8 severity, u8 component, u32 th · line 793

Quoted 6 lines
drivers/gpu/drm/xe/xe_ras.c +3 -0
@@ -788,6 +788,123 @@ int xe_ras_set_threshold(struct xe_device *xe, u8 severity, u8 component, u32 th
 	return 0;
 }
 
+static int get_info_queue_data(struct xe_device *xe,
+			       struct xe_ras_get_info_queue_request *req,
+			       struct xe_ras_get_info_queue_response *out)

'resp'.

drivers/gpu/drm/xe/xe_ras.c int xe_ras_set_threshold(struct xe_device *xe, u8 severity, u8 component, u32 th · line 795

Quoted 2 lines
drivers/gpu/drm/xe/xe_ras.c +2 -0
+{
+	struct xe_ras_get_info_queue_response response = {0};

No need for local response, you already got it from caller.

Quoted 9 lines
drivers/gpu/drm/xe/xe_ras.c +9 -0
+	struct xe_sysctrl_mailbox_command command = {0};
+	const struct xe_ras_info_queue_header *hdr;
+	size_t rlen;
+	int ret;
+
+	xe_sysctrl_create_command(&command, XE_SYSCTRL_GROUP_GFSP, XE_SYSCTRL_CMD_GET_INFO_QUEUE,
+				  req, sizeof(*req), &response, sizeof(response));
+
+	ret = xe_sysctrl_send_command(&xe->sc, &command, &rlen);

drivers/gpu/drm/xe/xe_ras.c int xe_ras_set_threshold(struct xe_device *xe, u8 severity, u8 component, u32 th · line 814

Quoted 10 lines
drivers/gpu/drm/xe/xe_ras.c +10 -0
+	if (ret) {
+		xe_err(xe, "sysctrl: failed to get info queue data %d\n", ret);
+		return ret;
+	}
+
+	if (rlen != sizeof(response)) {
+		xe_err(xe, "sysctrl: unexpected get info queue data response length %zu (expected %zu)\n",
+		       rlen, sizeof(response));
+		return -EIO;
+	}

If we got a response status, we may want to look for failures here. You can refer to clear_counter() and set_threshold() for examples.

drivers/gpu/drm/xe/xe_ras.c int xe_ras_set_threshold(struct xe_device *xe, u8 severity, u8 component, u32 th · line 818

Quoted 3 lines
drivers/gpu/drm/xe/xe_ras.c +3 -0
+	hdr = &response.queue_response.header;
+	xe_dbg(xe, "[RAS]: info queue data: status=%u chunk_size=%u flags=0x%x\n",
+	       response.operation_status, hdr->chunk_size, hdr->flags);

Looking at the header definition, we may want to log more details. At the bare minimum, we should have total_size, chunk_offset and chunk_size. The rest are upto you.

drivers/gpu/drm/xe/xe_ras.c int xe_ras_set_threshold(struct xe_device *xe, u8 severity, u8 component, u32 th · line 832

Quoted 13 lines
drivers/gpu/drm/xe/xe_ras.c +13 -0
+	*out = response;
+	return 0;
+}
+
+static bool chunk_is_valid(const struct xe_ras_info_queue_header *hdr,
+			   u32 expected_offset, u32 dest_size)
+{
+	u32 end;
+
+	return hdr->chunk_offset == expected_offset &&
+	       hdr->chunk_size && hdr->chunk_size <= XE_RAS_INFO_QUEUE_MAX_CHUNK_SIZE &&
+	       !check_add_overflow(hdr->chunk_offset, hdr->chunk_size, &end) &&
+	       end <= XE_RAS_INFO_QUEUE_MAX_TOTAL_SIZE && end <= dest_size;

Curious, should I worry about termination byte?

Quoted 9 lines
drivers/gpu/drm/xe/xe_ras.c +9 -0
+}
+
+/**
+ * xe_ras_drain_info_queue_raw() - Drain the full RAS info queue into a flat buffer
+ * @xe: xe device
+ * @counter_resp: counter response carrying the first embedded chunk and the
+ *                counter identifier used as the source context for subsequent
+ *                GET_INFO_QUEUE fetches
+ * @dest_buf: destination buffer supplied by the caller

drivers/gpu/drm/xe/xe_ras.c int xe_ras_set_threshold(struct xe_device *xe, u8 severity, u8 component, u32 th · line 851

Quoted 10 lines
drivers/gpu/drm/xe/xe_ras.c +10 -0
+ * @dest_size: size of @dest_buf in bytes; also caps the total amount of data
+ *             assembled from the info queue
+ *
+ * Copies the first chunk already embedded in @counter_resp, then loops
+ * issuing GET_INFO_QUEUE to fetch any remaining chunks until the queue
+ * signals no more data or a transport/bounds error is encountered.  On
+ * transport or bounds errors the function stops and returns whatever has
+ * been assembled so far.
+ *
+ * Returns: number of valid bytes written into @dest_buf.  Zero if @dest_buf is

Nit: 'Number' with capital N.

drivers/gpu/drm/xe/xe_ras.c int xe_ras_set_threshold(struct xe_device *xe, u8 severity, u8 component, u32 th · line 860

Quoted 9 lines
drivers/gpu/drm/xe/xe_ras.c +9 -0
+ *          NULL or @dest_size is 0.
+ */
+u32 xe_ras_drain_info_queue_raw(struct xe_device *xe,
+				const struct xe_ras_get_counter_response *counter_resp,
+				u8 *dest_buf, u32 dest_size)
+{
+	const struct xe_ras_info_queue_header *first_hdr = &counter_resp->first.header;
+	struct xe_ras_get_info_queue_request req = {0};
+	struct xe_ras_get_info_queue_response resp;

This one should be inside the while loop.

drivers/gpu/drm/xe/xe_ras.c int xe_ras_set_threshold(struct xe_device *xe, u8 severity, u8 component, u32 th · line 869

Quoted 9 lines
drivers/gpu/drm/xe/xe_ras.c +9 -0
+	u32 flags = first_hdr->flags;
+	u32 offset = 0;
+
+	if (!dest_buf || !dest_size)
+		return 0;
+
+	if (first_hdr->total_size > dest_size)
+		xe_warn(xe, "[RAS]: info queue size %u exceeds %u, truncating\n",
+			first_hdr->total_size, dest_size);

Why not return error here?

drivers/gpu/drm/xe/xe_ras.c int xe_ras_set_threshold(struct xe_device *xe, u8 severity, u8 component, u32 th · line 872

Quoted 2 lines
drivers/gpu/drm/xe/xe_ras.c +2 -0
+	/* Copy first chunk already embedded in the counter response */
+	if (chunk_is_valid(first_hdr, offset, dest_size)) {

Ditto, why do we continue after invalid chunk?

drivers/gpu/drm/xe/xe_ras.c int xe_ras_set_threshold(struct xe_device *xe, u8 severity, u8 component, u32 th · line 879

Quoted 7 lines
drivers/gpu/drm/xe/xe_ras.c +7 -0
+		memcpy(dest_buf, counter_resp->first.data, first_hdr->chunk_size);
+		offset = first_hdr->chunk_size;
+	}
+
+	req.source_command = XE_SYSCTRL_CMD_GET_COUNTER;
+	req.source_context = counter_resp->counter;
+	req.queue_request.session_id = counter_resp->counter;

Why the duplication?

drivers/gpu/drm/xe/xe_ras.c int xe_ras_set_threshold(struct xe_device *xe, u8 severity, u8 component, u32 th · line 883

Quoted 3 lines
drivers/gpu/drm/xe/xe_ras.c +3 -0
+	/* Fetch any remaining chunks */
+	while ((flags & XE_RAS_INFO_QUEUE_FLAG_MORE_DATA) && offset < dest_size) {
+		const struct xe_ras_info_queue_header *hdr = &resp.queue_response.header;

memset(resp, 0)

drivers/gpu/drm/xe/xe_ras.c int xe_ras_set_threshold(struct xe_device *xe, u8 severity, u8 component, u32 th · line 889

Quoted 5 lines
drivers/gpu/drm/xe/xe_ras.c +5 -0
+		req.queue_request.offset = offset;
+		req.queue_request.size = min(XE_RAS_INFO_QUEUE_MAX_CHUNK_SIZE, dest_size - offset);
+
+		if (get_info_queue_data(xe, &req, &resp)) {
+			xe_err(xe, "[RAS]: info queue drain aborted: fetch at offset=%u failed\n",

... with "%d\n

drivers/gpu/drm/xe/xe_ras.c int xe_ras_set_threshold(struct xe_device *xe, u8 severity, u8 component, u32 th · line 890

Quoted 1 line
drivers/gpu/drm/xe/xe_ras.c +1 -0
+			       offset);

, ret);

Quoted 63 lines
drivers/gpu/drm/xe/xe_ras.c +17 -0
+			return offset;
+		}
+
+		if (!chunk_is_valid(hdr, offset, dest_size)) {
+			xe_warn(xe, "[RAS]: invalid info queue chunk (offset=%u size=%u, expected offset=%u)\n",
+				hdr->chunk_offset, hdr->chunk_size, offset);
+			return offset;
+		}
+
+		memcpy(dest_buf + offset, resp.queue_response.data, hdr->chunk_size);
+		offset += hdr->chunk_size;
+		flags = hdr->flags;
+	}
+
+	return min(offset, first_hdr->total_size);
+}
+
 static ssize_t gpu_health_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	struct xe_ras_get_health_response response = {0};
drivers/gpu/drm/xe/xe_ras.h +3 -0
index 84700ea63394..27ce6265ace5 100644
@@ -22,5 +22,8 @@ void xe_ras_init(struct xe_device *xe);
 enum xe_ras_recovery_action xe_ras_process_errors(struct xe_device *xe);
 int xe_ras_get_counter_response(struct xe_device *xe, const struct xe_ras_error_class *counter,
 				struct xe_ras_get_counter_response *out);
+u32 xe_ras_drain_info_queue_raw(struct xe_device *xe,
+				const struct xe_ras_get_counter_response *counter_resp,
+				u8 *dest_buf, u32 dest_size);
 
 #endif
drivers/gpu/drm/xe/xe_ras_types.h +15 -0
index fe6f3658a2a4..9901fd034e3f 100644
@@ -17,6 +17,10 @@
 #define XE_RAS_MEMORY_POISON			BIT(2)
 #define XE_RAS_MEMORY_DATA_PARITY		BIT(5)
 
+#define XE_RAS_INFO_QUEUE_MAX_CHUNK_SIZE	200
+#define XE_RAS_INFO_QUEUE_MAX_TOTAL_SIZE	5120
+#define XE_RAS_INFO_QUEUE_FLAG_MORE_DATA	0x02
+
 /**
  * enum xe_ras_recovery_action - RAS recovery actions
  *
@@ -95,6 +99,110 @@ struct xe_ras_threshold_crossed {
 	struct xe_ras_error_class counters[XE_RAS_NUM_COUNTERS];
 } __packed;
 
+/**
+ * struct xe_ras_info_queue_header - Metadata for large info queue data transfers
+ *
+ * Provides chunk metadata for commands that support extended info queue
+ * functionality. Used when the total data exceeds a single mailbox response.
+ */
+struct xe_ras_info_queue_header {
+	/** @total_size: Total size of the complete info queue data in bytes */
+	u32 total_size;
+	/** @chunk_offset: Offset of this chunk within the total data in bytes */
+	u32 chunk_offset;

drivers/gpu/drm/xe/xe_ras_types.h struct xe_ras_threshold_crossed { · line 122

Quoted 10 lines
drivers/gpu/drm/xe/xe_ras_types.h +10 -0
+	/** @chunk_size: Size of the data in this chunk in bytes */
+	u32 chunk_size;
+	/** @reserved0: Reserved for future use */
+	u32 reserved0;
+	/** @flags: Info queue control flags (XE_RAS_INFO_QUEUE_FLAG_*) */
+	u32 flags:8;
+	/** @reserved1: Reserved for future use */
+	u32 reserved1:4;
+	/** @num_headers: Number of detailed counter headers at start of the data */
+	u32 num_headers:5;

Is this actually used here?

drivers/gpu/drm/xe/xe_ras_types.h struct xe_ras_threshold_crossed { · line 126

Quoted 4 lines
drivers/gpu/drm/xe/xe_ras_types.h +4 -0
+	/** @reserved2: Reserved for future use */
+	u32 reserved2:15;
+	/** @checksum: CRC32 checksum of this chunk data */
+	u32 checksum;

Ditto.

Quoted 33 lines
drivers/gpu/drm/xe/xe_ras_types.h +33 -0
+} __packed;
+
+/**
+ * struct xe_ras_info_queue_data_request - Request for a specific chunk of info queue data
+ *
+ * Allows the driver to request continuation of large info queue transfers
+ * by specifying an offset and size within the full data set.
+ */
+struct xe_ras_info_queue_data_request {
+	/** @offset: Byte offset of the requested data chunk */
+	u32 offset;
+	/** @size: Maximum size of the requested chunk in bytes */
+	u32 size;
+	/** @session_id: Session ID to correlate multi-chunk transfers */
+	struct xe_ras_error_class session_id;
+	/** @reserved: Reserved for future use */
+	u32 reserved;
+} __packed;
+
+/**
+ * struct xe_ras_info_queue_data_response - Generic response for commands with info queues
+ *
+ * Standard response format for any command that returns an info queue
+ * payload. May be embedded in a command-specific response structure.
+ */
+struct xe_ras_info_queue_data_response {
+	/** @header: Info queue metadata for this chunk */
+	struct xe_ras_info_queue_header header;
+	/** @data: Info queue data for this chunk */
+	u8 data[XE_RAS_INFO_QUEUE_MAX_CHUNK_SIZE];
+} __packed;
+
+/**

drivers/gpu/drm/xe/xe_ras_types.h struct xe_ras_threshold_crossed { · line 169

Quoted 10 lines
drivers/gpu/drm/xe/xe_ras_types.h +10 -0
+ * struct xe_ras_info_queue_dynamic_counter_hdr - Aggregate counter header entry
+ *
+ * When a session requests aggregate counter data, one header per matching
+ * dynamic counter class is prepended to the queue data. The @counter field
+ * is the error count of this class; at most XE_RAS_NUM_COUNTERS error log
+ * entries follow for it.
+ */
+struct xe_ras_info_queue_dynamic_counter_hdr {
+	/** @error_class: Error class associated with this counter group */
+	struct xe_ras_error_class error_class;

'counter'

drivers/gpu/drm/xe/xe_ras_types.h struct xe_ras_threshold_crossed { · line 171

Quoted 2 lines
drivers/gpu/drm/xe/xe_ras_types.h +2 -0
+	/** @counter: Error count of this class */
+	u32 counter;

'count'

Quoted 20 lines
drivers/gpu/drm/xe/xe_ras_types.h +20 -0
+} __packed;
+
+/**
+ * struct xe_ras_error_log - Single error log entry following dynamic counter headers
+ */
+struct xe_ras_error_log {
+	/** @timestamp: Timestamp when the error was recorded */
+	u64 timestamp;
+	/** @error_details: Error-specific details */
+	u32 error_details[16];
+} __packed;
+
+/**
+ * struct xe_ras_get_info_queue_request - Request for XE_SYSCTRL_CMD_GET_INFO_QUEUE
+ */
+struct xe_ras_get_info_queue_request {
+	/** @queue_request: Info queue request parameters */
+	struct xe_ras_info_queue_data_request queue_request;
+	/** @source_command: Original command that generated the info queue */
+	u32 source_command;

drivers/gpu/drm/xe/xe_ras_types.h struct xe_ras_threshold_crossed { · line 201

Quoted 10 lines
drivers/gpu/drm/xe/xe_ras_types.h +10 -0
+	/** @source_context: Context from original command, if applicable */
+	struct xe_ras_error_class source_context;
+} __packed;
+
+/**
+ * struct xe_ras_get_info_queue_response - Response for XE_SYSCTRL_CMD_GET_INFO_QUEUE
+ */
+struct xe_ras_get_info_queue_response {
+	/** @operation_status: Status of the retrieval operation */
+	u32 operation_status;

'status'

Quoted 8 lines
drivers/gpu/drm/xe/xe_ras_types.h +4 -0
+	/** @queue_response: Info queue data chunk */
+	struct xe_ras_info_queue_data_response queue_response;
+} __packed;
+
 /**
  * struct xe_ras_get_counter_request - Request structure for get counter
  */

drivers/gpu/drm/xe/xe_ras_types.h struct xe_ras_get_counter_response { · line 231

Quoted 9 lines
drivers/gpu/drm/xe/xe_ras_types.h +4 -2
@@ -117,8 +225,14 @@ struct xe_ras_get_counter_response {
 	u64 timestamp;
 	/** @threshold: Threshold value for the counter */
 	u32 threshold;
-	/** @reserved: Reserved  */
-	u32 reserved[57];
+	/** @reserved: Reserved for future use */
+	u32 reserved:9;
+	/** @has_info_queue: Set if info queue is available */
+	u32 has_info_queue:1;

Hmm...

drivers/gpu/drm/xe/xe_ras_types.h struct xe_ras_get_counter_response { · line 234

Quoted 3 lines
drivers/gpu/drm/xe/xe_ras_types.h +3 -0
+	/** @reserved1: Reserved for future use */
+	u32 reserved1:22;
+	/** @first: First info queue chunk, if @has_info_queue is set */

... so where is this condition?

Raag

Quoted 27 lines
drivers/gpu/drm/xe/xe_ras_types.h +1 -0
+	struct xe_ras_info_queue_data_response first;
 } __packed;
 
 /**
drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h +2 -0
index a0628eb47bff..299d12b94574 100644
@@ -34,6 +34,7 @@ enum xe_sysctrl_group {
  * @XE_SYSCTRL_CMD_GET_PENDING_EVENT: Retrieve pending event
  * @XE_SYSCTRL_CMD_GET_HEALTH: Retrieve gpu health
  * @XE_SYSCTRL_CMD_SET_HEALTH: Set gpu health
+ * @XE_SYSCTRL_CMD_GET_INFO_QUEUE: Retrieve a chunk of info queue data
  */
 enum xe_sysctrl_gfsp_cmd {
 	XE_SYSCTRL_CMD_GET_SOC_ERROR		= 0x01,
@@ -44,6 +45,7 @@ enum xe_sysctrl_gfsp_cmd {
 	XE_SYSCTRL_CMD_GET_PENDING_EVENT	= 0x07,
 	XE_SYSCTRL_CMD_GET_HEALTH		= 0x0B,
 	XE_SYSCTRL_CMD_SET_HEALTH		= 0x0C,
+	XE_SYSCTRL_CMD_GET_INFO_QUEUE		= 0x0D,
 };
 
 /**
Signature · 1 line
2.54.0
#24 lore raw

PATCH v4 6/12 drm/xe/cper: Prepare Intel CPER error info records

In reply to Badal Nilawar

Prepare xe_cper_sec_intel_error_info records from RAS info queue data. Depending on the error class type, detail or aggregate, one or more error info records may be generated and embedded in the CPER record.

Assisted-by Copilot:Claude-Opus-5.5

---
v4:
- Move struct xe_cper_einfo_entry to xe_cper_types.h (Raag)
- Use kzalloc_flex()/kzalloc_objs() (Raag)
- Allocate info queue buffer from reported total size (Raag)

---
 drivers/gpu/drm/xe/xe_cper.c       | 247 +++++++++++++++++++++++++++--
 drivers/gpu/drm/xe/xe_cper_types.h |  54 ++++++-
 2 files changed, 290 insertions(+), 11 deletions(-)
drivers/gpu/drm/xe/xe_cper.c +237 -10
index 1000c78b41e9..7acb503efd11 100644
@@ -78,16 +78,22 @@ static u64 cper_timestamp_now(void)
 	return ts;
 }
 
+static void fill_cper_error_class(struct xe_cper_error_class *dst,
+				  const struct xe_ras_error_class *src)
+{
+	dst->error_type = src->common.severity;
+	dst->error_component = src->common.component;
+	dst->tile = src->product.unit.tile;
+	dst->instance = src->product.unit.instance;
+	dst->cause = src->product.cause.cause;
+}
+
 static void xe_cper_init_intel_err_hdr(struct xe_device *xe,
 				       const struct xe_ras_error_class *error_class,
 				       u64 first_timestamp, u32 sig_id, u32 error_count,
 				       struct xe_cper_sec_intel_err_hdr *ihdr)
 {
-	ihdr->error_class.error_type = error_class->common.severity;
-	ihdr->error_class.error_component = error_class->common.component;
-	ihdr->error_class.tile = error_class->product.unit.tile;
-	ihdr->error_class.instance = error_class->product.unit.instance;
-	ihdr->error_class.cause = error_class->product.cause.cause;
+	fill_cper_error_class(&ihdr->error_class, error_class);
 	ihdr->validation_bits |= XE_CPER_VALID_LOCATION;
 
 	if (first_timestamp) {
@@ -176,11 +182,209 @@ static void xe_cper_record_emit(struct xe_device *xe, u8 severity,
 	kfree(rec);
 }
 
+/* Entries built from RAS error logs carry fixed-size error_details */
+#define XE_CPER_RAS_LOG_ENTRY_SIZE \
+	(offsetof(struct xe_intel_priv_event_entry, metadata) + \
+	 sizeof_field(struct xe_ras_error_log, error_details))
+
+static struct xe_cper_sec_intel_error_info *
+build_einfo(const struct xe_ras_error_log *logs, u32 num_logs,
+	    const struct xe_ras_error_class *ec, u32 error_count)
+{
+	u32 queue_len = num_logs * XE_CPER_RAS_LOG_ENTRY_SIZE;
+	struct xe_cper_sec_intel_error_info *einfo;
+	struct xe_intel_priv_event_entry *entry;
+	u32 i;
+
+	einfo = kzalloc_flex(*einfo, event_queue, queue_len);
+	if (!einfo)
+		return NULL;
+
+	einfo->error_count        = error_count;
+	einfo->event_queue_length = queue_len;
+	einfo->event_queue_count  = num_logs;
+	fill_cper_error_class(&einfo->error_class, ec);
+
+	entry = (struct xe_intel_priv_event_entry *)einfo->event_queue;
+	for (i = 0; i < num_logs; i++) {
+		entry->entry_length = sizeof_field(struct xe_ras_error_log, error_details);
+		entry->timestamp    = logs[i].timestamp;
+		memcpy(entry->metadata, logs[i].error_details, sizeof(logs[i].error_details));
+		entry = (void *)entry + XE_CPER_RAS_LOG_ENTRY_SIZE;
+	}
+
+	return einfo;
+}
+
+static void free_einfo_arr(struct xe_cper_einfo_entry *einfo_arr, u32 count)
+{
+	u32 i;
+
+	for (i = 0; i < count; i++)
+		kfree(einfo_arr[i].einfo);
+	kfree(einfo_arr);
+}
+
+static bool fill_einfo_entry(struct xe_cper_einfo_entry *entry,
+			     const struct xe_ras_info_queue_dynamic_counter_hdr *hdr,
+			     const struct xe_ras_error_log *logs, u32 num_logs)
+{
+	entry->einfo = build_einfo(logs, num_logs, &hdr->error_class, hdr->counter);
+	if (!entry->einfo)
+		return false;
+
+	entry->einfo_size = struct_size(entry->einfo, event_queue,
+					entry->einfo->event_queue_length);
+	/* The first log is the first occurrence of the error */
+	entry->timestamp = logs[0].timestamp;
+	entry->hdr = *hdr;
+	return true;
+}
+
+static u32 build_detail_einfo(const struct xe_ras_error_class *error_class, u32 error_count,
+			      const struct xe_ras_error_log *logs, u32 num_logs,
+			      struct xe_cper_einfo_entry *einfo_arr)
+{
+	/* All logs belong to the queried class; the error count may exceed the logs kept */
+	const struct xe_ras_info_queue_dynamic_counter_hdr hdr = {
+		.error_class = *error_class,
+		.counter = error_count,
+	};
+
+	if (!num_logs)
+		return 0;
+
+	return fill_einfo_entry(&einfo_arr[0], &hdr, logs, num_logs) ? 1 : 0;
+}
+
+static u32 build_aggregate_einfo(struct xe_device *xe,
+				 const struct xe_ras_info_queue_dynamic_counter_hdr *hdrs,
+				 u32 num_hdrs, const struct xe_ras_error_log *logs,
+				 u32 avail_logs, struct xe_cper_einfo_entry *einfo_arr)
+{
+	u32 log_offset = 0, count = 0, i;
+
+	for (i = 0; i < num_hdrs; i++) {
+		/* @counter is the error count; firmware logs at most XE_RAS_NUM_COUNTERS */
+		u32 num_logs = min_t(u32, hdrs[i].counter, XE_RAS_NUM_COUNTERS);
+
+		if (num_logs > avail_logs - log_offset) {
+			xe_warn(xe, "CPER: header[%u] claims %u logs but only %u remain\n",
+				i, num_logs, avail_logs - log_offset);
+			break;
+		}
+
+		if (!num_logs)
+			continue;
+
+		if (!fill_einfo_entry(&einfo_arr[count], &hdrs[i], &logs[log_offset], num_logs))
+			break;
+
+		log_offset += num_logs;
+		count++;
+	}
+
+	return count;
+}
+
+/**
+ * xe_prepare_cper_error_info() - Build the CPER error info records from RAS info queue data
+ * @xe: xe device instance
+ * @counter_resp: counter response containing the first embedded chunk
+ * @error_class: RAS error class used to populate the einfo error_class fields
+ * @count_out: output number of entries in the returned array
+ *
+ * Assembles the complete raw info queue data from the first chunk already
+ * embedded in @counter_resp and any additional chunks fetched via
+ * GET_INFO_QUEUE.  Two use cases are supported based on num_headers in
+ * the info queue header:
+ *
+ * Detail error counter (num_headers == 0)::
+ *
+ *   [xe_ras_error_log * N]
+ *
+ *   Returns one xe_cper_einfo_entry covering all N logs.
+ *
+ * Aggregate error counter (num_headers > 0)::
+ *
+ *   [xe_ras_info_queue_dynamic_counter_hdr * num_headers]
+ *   [xe_ras_error_log * N]
+ *
+ *   Returns one xe_cper_einfo_entry per header.  Each header's @counter field
+ *   is the error count of its class; at most XE_RAS_NUM_COUNTERS
+ *   xe_ras_error_log entries follow it and its @error_class is used to
+ *   populate the entry's einfo->error_class.
+ *
+ * Returns: allocated xe_cper_einfo_entry array on success (caller must free it
+ *          with free_einfo_arr()), NULL if no error info could be built.
+ *          @count_out is set to the number of entries in the array.
+ */
+static struct xe_cper_einfo_entry *
+xe_prepare_cper_error_info(struct xe_device *xe,
+			   const struct xe_ras_get_counter_response *counter_resp,
+			   const struct xe_ras_error_class *error_class,
+			   u32 *count_out)
+{
+	const struct xe_ras_info_queue_header *first_qhdr = &counter_resp->first.header;
+	struct xe_cper_einfo_entry *einfo_arr = NULL;
+	const struct xe_ras_error_log *logs;
+	u32 buf_size, raw_total, num_headers, headers_size;
+	u32 avail_logs, count = 0;
+	u8 *raw_buf = NULL;
+
+	if (!first_qhdr->total_size) {
+		xe_warn(xe, "CPER: info queue reports zero total size\n");
+		goto out;
+	}
+
+	buf_size = min(first_qhdr->total_size, XE_RAS_INFO_QUEUE_MAX_TOTAL_SIZE);
+	raw_buf = kzalloc_objs(*raw_buf, buf_size);
+	if (!raw_buf)
+		goto out;
+
+	raw_total = xe_ras_drain_info_queue_raw(xe, counter_resp, raw_buf, buf_size);
+	if (!raw_total)
+		goto out;
+
+	num_headers = first_qhdr->num_headers;
+	headers_size = num_headers * sizeof(struct xe_ras_info_queue_dynamic_counter_hdr);
+	if (headers_size > raw_total) {
+		xe_warn(xe, "CPER: aggregate headers size (%u) exceeds raw total (%u)\n",
+			headers_size, raw_total);
+		goto out;
+	}
+
+	logs = (const struct xe_ras_error_log *)(raw_buf + headers_size);
+	avail_logs = (raw_total - headers_size) / sizeof(*logs);
+
+	einfo_arr = kzalloc_objs(*einfo_arr, num_headers ?: 1);
+	if (!einfo_arr)
+		goto out;
+
+	if (num_headers)
+		count = build_aggregate_einfo(xe, (const void *)raw_buf, num_headers,
+					      logs, avail_logs, einfo_arr);
+	else
+		count = build_detail_einfo(error_class, counter_resp->value,
+					   logs, avail_logs, einfo_arr);
+
+	if (!count) {
+		kfree(einfo_arr);
+		einfo_arr = NULL;
+	}
+out:
+	kfree(raw_buf);
+	*count_out = count;
+	return einfo_arr;
+}
+
 static void xe_cper_emit_hw_err(struct xe_device *xe, int cper_sev, enum xe_sigid sigid,
 				const struct xe_ras_error_class *error_class)
 {
-	struct xe_cper_sec_intel_err_hdr ihdr = {};
+	struct xe_cper_einfo_entry *einfo_arr = NULL, *entries;
 	struct xe_ras_get_counter_response local_resp;
+	struct xe_cper_einfo_entry single = {};
+	u32 einfo_count = 0, count, i;
 
 	/* Fetching the counter sends a sysctrl command */
 	might_sleep();
@@ -191,11 +395,34 @@ static void xe_cper_emit_hw_err(struct xe_device *xe, int cper_sev, enum xe_sigi
 		return;
 	}
 
-	xe_cper_init_intel_err_hdr(xe, error_class, local_resp.timestamp,
-				   sigid, local_resp.value, &ihdr);
+	/* Without info queue data, emit a single record from the counter itself */
+	single.hdr.error_class = *error_class;
+	single.hdr.counter = local_resp.value;
+	single.timestamp = local_resp.timestamp;
+	entries = &single;
+	count = 1;
+
+	if (local_resp.has_info_queue) {
+		einfo_arr = xe_prepare_cper_error_info(xe, &local_resp, error_class, &einfo_count);
+		if (einfo_arr) {
+			entries = einfo_arr;
+			count = einfo_count;
+		} else {
+			xe_warn(xe, "CPER: failed to build error info from info queue, emitting record without it\n");
+		}
+	}
+
+	for (i = 0; i < count; i++) {
+		struct xe_cper_sec_intel_err_hdr ihdr = {};
+
+		xe_cper_init_intel_err_hdr(xe, &entries[i].hdr.error_class, entries[i].timestamp,
+					   sigid, entries[i].hdr.counter, &ihdr);
+
+		xe_cper_record_emit(xe, cper_sev, &INTEL_CPER_NOTIFY_GPU_ERROR, &ihdr,
+				    entries[i].einfo, entries[i].einfo_size);
+	}
 
-	xe_cper_record_emit(xe, cper_sev, &INTEL_CPER_NOTIFY_GPU_ERROR,
-			    &ihdr, NULL, 0);
+	free_einfo_arr(einfo_arr, einfo_count);
 }
 
 /**
drivers/gpu/drm/xe/xe_cper_types.h +53 -1

74 lines not on this page · raw message

Signature · 1 line
2.54.0
#25 lore raw

Re: [PATCH v4 06/12] drm/xe/cper: Prepare Intel CPER error info records

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider: - [High] xe/cper: missing __packed attributes on CPER structs causes ABI breakage and unaligned access --

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [High] xe/cper: missing __packed attributes on CPER structs causes ABI breakage and unaligned access --

commit 48cc4e07bb3144fabbe0d059b7aa4e8d590267c1
Author: Badal Nilawar <[email protected]>

drm/xe/cper: Prepare Intel CPER error info records

This commit prepares xe_cper_sec_intel_error_info records from RAS info queue data. Depending on the error class type, one or more error info records may be generated and embedded in the CPER record.

Quoted 4 lines
drivers/gpu/drm/xe/xe_cper.c +0 -0
index 1000c78b41e97..7acb503efd118 100644

[ ... ]

Quoted 12 lines
drivers/gpu/drm/xe/xe_cper.c +12 -0
+static struct xe_cper_sec_intel_error_info *
+build_einfo(const struct xe_ras_error_log *logs, u32 num_logs,
+	    const struct xe_ras_error_class *ec, u32 error_count)
+{
+	u32 queue_len = num_logs * XE_CPER_RAS_LOG_ENTRY_SIZE;
+	struct xe_cper_sec_intel_error_info *einfo;
+	struct xe_intel_priv_event_entry *entry;
+	u32 i;
+
+	einfo = kzalloc_flex(*einfo, event_queue, queue_len);
+	if (!einfo)
+		return NULL;

drivers/gpu/drm/xe/xe_cper.c static void xe_cper_record_emit(struct xe_device *xe, u8 severity, · line 211

Quoted 10 lines
drivers/gpu/drm/xe/xe_cper.c +10 -0
+
+	einfo->error_count        = error_count;
+	einfo->event_queue_length = queue_len;
+	einfo->event_queue_count  = num_logs;
+	fill_cper_error_class(&einfo->error_class, ec);
+
+	entry = (struct xe_intel_priv_event_entry *)einfo->event_queue;
+	for (i = 0; i < num_logs; i++) {
+		entry->entry_length = sizeof_field(struct xe_ras_error_log, error_details);
+		entry->timestamp    = logs[i].timestamp;

[Severity: High]
Can this assignment cause an alignment fault?

Because xe_cper_sec_intel_error_info is evaluated as 28 bytes in size, event_queue starts at offset 28. In xe_intel_priv_event_entry, the timestamp is at offset 8. The resulting address for the timestamp field is therefore 36 bytes from the kzalloc base, which is not 8-byte aligned.

Writing a 64-bit value to a 4-byte-aligned address can cause a kernel panic on architectures that strictly enforce 64-bit alignment.

Quoted 6 lines
drivers/gpu/drm/xe/xe_cper.c +6 -0
+		memcpy(entry->metadata, logs[i].error_details, sizeof(logs[i].error_details));
+		entry = (void *)entry + XE_CPER_RAS_LOG_ENTRY_SIZE;
+	}
+
+	return einfo;
+}

[ ... ]

Quoted 4 lines
drivers/gpu/drm/xe/xe_cper_types.h +0 -0
index 7612518c9d47b..627c7117f23eb 100644

[ ... ]

Quoted 17 lines
drivers/gpu/drm/xe/xe_cper_types.h +17 -0
+struct xe_cper_sec_intel_error_info {
+	/** @error_class: Error classification */
+	struct xe_cper_error_class error_class;
+	/** @error_count: Total number of errors recorded */
+	u32 error_count;
+	/** @event_queue_length: Total byte size of the @event_queue array */
+	u32 event_queue_length;
+	/** @event_queue_count: Number of entries in @event_queue */
+	u32 event_queue_count;
+	/** @event_queue: Packed array of &xe_intel_priv_event_entry records */
+	u8 event_queue[];
+};
+
+/**
+ * struct xe_intel_priv_event_entry - Single error event in the event queue
+ *
+ * Each entry is variable-length; @entry_length gives the byte size of

drivers/gpu/drm/xe/xe_cper_types.h struct xe_cper_sec_intel_err_hdr { · line 129

Quoted 10 lines
drivers/gpu/drm/xe/xe_cper_types.h +10 -0
+ * @metadata only (not including @entry_length or @timestamp).
+ */
+struct xe_intel_priv_event_entry {
+	/** @entry_length: Byte length of the @metadata payload */
+	u32 entry_length;
+	/** @timestamp: Timestamp of this event, in firmware ticks */
+	u64 timestamp;
+	/** @metadata: Event-specific payload bytes */
+	u8  metadata[];
+};

[Severity: High]
Are these structures missing the __packed attribute?

Without it, the compiler injects a 4-byte hole before the timestamp field, which also enforces 8-byte alignment for the struct. This implicit padding corrupts the intended binary CPER layout, potentially leading to ABI breakage when the records are parsed by external tools. It also causes the memory alignment issues mentioned above.

Signature · 1 line
Sashiko AI review · https://sashiko.dev/#/patchset/[email protected]?part=6
#26 lore raw

Re: [PATCH v4 06/12] drm/xe/cper: Prepare Intel CPER error info records

Quoted 43 lines · On 09-10-2026 16:11, [email protected] wrote:

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [High] xe/cper: missing __packed attributes on CPER structs causes ABI breakage and unaligned access --

commit 48cc4e07bb3144fabbe0d059b7aa4e8d590267c1
Author: Badal Nilawar <[email protected]>

drm/xe/cper: Prepare Intel CPER error info records

This commit prepares xe_cper_sec_intel_error_info records from RAS info queue data. Depending on the error class type, one or more error info records may be generated and embedded in the CPER record.

Quoted 4 lines
drivers/gpu/drm/xe/xe_cper.c +0 -0
index 1000c78b41e97..7acb503efd118 100644

[ ... ]

Quoted 12 lines
drivers/gpu/drm/xe/xe_cper.c +12 -0
+static struct xe_cper_sec_intel_error_info *
+build_einfo(const struct xe_ras_error_log *logs, u32 num_logs,
+	    const struct xe_ras_error_class *ec, u32 error_count)
+{
+	u32 queue_len = num_logs * XE_CPER_RAS_LOG_ENTRY_SIZE;
+	struct xe_cper_sec_intel_error_info *einfo;
+	struct xe_intel_priv_event_entry *entry;
+	u32 i;
+
+	einfo = kzalloc_flex(*einfo, event_queue, queue_len);
+	if (!einfo)
+		return NULL;

drivers/gpu/drm/xe/xe_cper.c static void xe_cper_record_emit(struct xe_device *xe, u8 severity, · line 211

Quoted 10 lines
drivers/gpu/drm/xe/xe_cper.c +10 -0
+
+	einfo->error_count        = error_count;
+	einfo->event_queue_length = queue_len;
+	einfo->event_queue_count  = num_logs;
+	fill_cper_error_class(&einfo->error_class, ec);
+
+	entry = (struct xe_intel_priv_event_entry *)einfo->event_queue;
+	for (i = 0; i < num_logs; i++) {
+		entry->entry_length = sizeof_field(struct xe_ras_error_log, error_details);
+		entry->timestamp    = logs[i].timestamp;

[Severity: High]
Can this assignment cause an alignment fault?

Quoted 7 lines

Because xe_cper_sec_intel_error_info is evaluated as 28 bytes in size, event_queue starts at offset 28. In xe_intel_priv_event_entry, the timestamp is at offset 8. The resulting address for the timestamp field is therefore 36 bytes from the kzalloc base, which is not 8-byte aligned.

Writing a 64-bit value to a 4-byte-aligned address can cause a kernel panic on architectures that strictly enforce 64-bit alignment.

No, these structures are inside the #pragma pack(push, 1) / #pragma pack(pop) block in xe_cper_types.h, so they are packed.

struct xe_cper_sec_intel_error_info is 24 bytes and @timestamp sits at offset 4 in struct xe_intel_priv_event_entry.

Because the members are accessed through packed types, the compiler emits unaligned-safe accesses, so this can't cause an alignment fault

Quoted 43 lines
Quoted 7 lines
drivers/gpu/drm/xe/xe_cper.c +6 -0
+		memcpy(entry->metadata, logs[i].error_details, sizeof(logs[i].error_details));
+		entry = (void *)entry + XE_CPER_RAS_LOG_ENTRY_SIZE;
+	}
+
+	return einfo;
+}

[ ... ]

Quoted 4 lines
drivers/gpu/drm/xe/xe_cper_types.h +0 -0
index 7612518c9d47b..627c7117f23eb 100644

[ ... ]

Quoted 17 lines
drivers/gpu/drm/xe/xe_cper_types.h +17 -0
+struct xe_cper_sec_intel_error_info {
+	/** @error_class: Error classification */
+	struct xe_cper_error_class error_class;
+	/** @error_count: Total number of errors recorded */
+	u32 error_count;
+	/** @event_queue_length: Total byte size of the @event_queue array */
+	u32 event_queue_length;
+	/** @event_queue_count: Number of entries in @event_queue */
+	u32 event_queue_count;
+	/** @event_queue: Packed array of &xe_intel_priv_event_entry records */
+	u8 event_queue[];
+};
+
+/**
+ * struct xe_intel_priv_event_entry - Single error event in the event queue
+ *
+ * Each entry is variable-length; @entry_length gives the byte size of

drivers/gpu/drm/xe/xe_cper_types.h struct xe_cper_sec_intel_err_hdr { · line 129

Quoted 10 lines
drivers/gpu/drm/xe/xe_cper_types.h +10 -0
+ * @metadata only (not including @entry_length or @timestamp).
+ */
+struct xe_intel_priv_event_entry {
+	/** @entry_length: Byte length of the @metadata payload */
+	u32 entry_length;
+	/** @timestamp: Timestamp of this event, in firmware ticks */
+	u64 timestamp;
+	/** @metadata: Event-specific payload bytes */
+	u8  metadata[];
+};

[Severity: High]
Are these structures missing the __packed attribute?

Quoted 5 lines

Without it, the compiler injects a 4-byte hole before the timestamp field, which also enforces 8-byte alignment for the struct. This implicit padding corrupts the intended binary CPER layout, potentially leading to ABI breakage when the records are parsed by external tools. It also causes the memory alignment issues mentioned above.

No, they are packed by the same #pragma pack block, so there is no hole before @timestamp.

Thanks,
Badal

#27 lore raw

Re: [PATCH v4 06/12] drm/xe/cper: Prepare Intel CPER error info records

In reply to Badal Nilawar
Quoted 23 lines · Badal Nilawar

Prepare xe_cper_sec_intel_error_info records from RAS info queue data. Depending on the error class type, detail or aggregate, one or more error info records may be generated and embedded in the CPER record.

Assisted-by Copilot:Claude-Opus-5.5

---
v4:
- Move struct xe_cper_einfo_entry to xe_cper_types.h (Raag)
- Use kzalloc_flex()/kzalloc_objs() (Raag)
- Allocate info queue buffer from reported total size (Raag)

---
 drivers/gpu/drm/xe/xe_cper.c       | 247 +++++++++++++++++++++++++++--
 drivers/gpu/drm/xe/xe_cper_types.h |  54 ++++++-
 2 files changed, 290 insertions(+), 11 deletions(-)
drivers/gpu/drm/xe/xe_cper.c +0 -0
index 1000c78b41e9..7acb503efd11 100644
@@ -78,16 +78,22 @@ static u64 cper_timestamp_now(void)
 	return ts;
 }

drivers/gpu/drm/xe/xe_cper.c static u64 cper_timestamp_now(void) · line 89

Quoted 10 lines
drivers/gpu/drm/xe/xe_cper.c +9 -0
 
+static void fill_cper_error_class(struct xe_cper_error_class *dst,
+				  const struct xe_ras_error_class *src)
+{
+	dst->error_type = src->common.severity;
+	dst->error_component = src->common.component;
+	dst->tile = src->product.unit.tile;
+	dst->instance = src->product.unit.instance;
+	dst->cause = src->product.cause.cause;
+}

No needless refactoring, please introduce this function in the original patch. Assuming you'll reuse struct xe_ras_error_class here, this can simply be a memcpy().

...

drivers/gpu/drm/xe/xe_cper.c static u64 cper_timestamp_now(void) · line 91

Quoted 2 lines
drivers/gpu/drm/xe/xe_cper.c +2 -0
+/**
+ * struct xe_cper_sec_intel_error_info - Variable-length Intel GPU error payload

Do we really need to add 'error' everywhere?

drivers/gpu/drm/xe/xe_cper.c static u64 cper_timestamp_now(void) · line 98

Quoted 7 lines
drivers/gpu/drm/xe/xe_cper.c +7 -0
+ * Appended after &xe_cper_sec_intel_err_hdr when detailed per-event data
+ * is available. The @event_queue flexible array holds @event_queue_count
+ * packed &xe_intel_priv_event_entry records.
+ */
+struct xe_cper_sec_intel_error_info {
+	/** @error_class: Error classification */
+	struct xe_cper_error_class error_class;

'counter'

drivers/gpu/drm/xe/xe_cper.c static u64 cper_timestamp_now(void)

Quoted 2 lines
drivers/gpu/drm/xe/xe_cper.c +2 -0
+	/** @error_count: Total number of errors recorded */
+	u32 error_count;

'count'

drivers/gpu/drm/xe/xe_cper.c

Quoted 2 lines
drivers/gpu/drm/xe/xe_cper.c +2 -0
+	/** @event_queue_length: Total byte size of the @event_queue array */
+	u32 event_queue_length;

'queue_length'

drivers/gpu/drm/xe/xe_cper.c

Quoted 2 lines
drivers/gpu/drm/xe/xe_cper.c +2 -0
+	/** @event_queue_count: Number of entries in @event_queue */
+	u32 event_queue_count;

'queue_count'

drivers/gpu/drm/xe/xe_cper.c

Quoted 2 lines
drivers/gpu/drm/xe/xe_cper.c +2 -0
+	/** @event_queue: Packed array of &xe_intel_priv_event_entry records */
+	u8 event_queue[];

'queue'

drivers/gpu/drm/xe/xe_cper.c

Quoted 4 lines
drivers/gpu/drm/xe/xe_cper.c +4 -0
+};
+
+/**
+ * struct xe_intel_priv_event_entry - Single error event in the event queue

All cper struct must contain 'cper' naming. Also, redundant 'event'.

drivers/gpu/drm/xe/xe_cper.c

Quoted 6 lines

+ * Each entry is variable-length; @entry_length gives the byte size of
+ * @metadata only (not including @entry_length or @timestamp).
+ */

drivers/gpu/drm/xe/xe_cper.c +3 -0
+struct xe_intel_priv_event_entry {
+	/** @entry_length: Byte length of the @metadata payload */
+	u32 entry_length;

'length'

drivers/gpu/drm/xe/xe_cper.c

Quoted 4 lines
drivers/gpu/drm/xe/xe_cper.c +4 -0
+	/** @timestamp: Timestamp of this event, in firmware ticks */
+	u64 timestamp;
+	/** @metadata: Event-specific payload bytes */
+	u8  metadata[];

Nit: Fix the spacing.

Quoted 16 lines
drivers/gpu/drm/xe/xe_cper.c +4 -1
+};
+
 /**
  * struct xe_cper_nonstd_record - Intel GPU CPER record
  *
  * Contains the standard CPER record header, section descriptor, and the
- * Intel error section header.
+ * Intel error section header. A &xe_cper_sec_intel_error_info payload
+ * may be appended dynamically.
  */
 struct xe_cper_nonstd_record {
 	/** @record_hdr: Standard CPER record header (UEFI Appendix N.2.1) */
@@ -122,4 +160,18 @@ struct xe_platform_id_entry {
 	guid_t    platform_id;
 };
 

drivers/gpu/drm/xe/xe_cper.c struct xe_platform_id_entry { · line 172

Quoted 10 lines
drivers/gpu/drm/xe/xe_cper.c +10 -0
+/**
+ * struct xe_cper_einfo_entry - One CPER error info payload and its source counter
+ */
+struct xe_cper_einfo_entry {
+	/** @hdr: Error class and counter value used for the CPER section header */
+	struct xe_ras_info_queue_dynamic_counter_hdr hdr;
+	/** @einfo: Allocated error info payload, NULL if none */
+	struct xe_cper_sec_intel_error_info *einfo;
+	/** @einfo_size: Byte size of @einfo including the event queue */
+	u32 einfo_size;

You're using length and size interchangeably. Whatever your preference, please use consistent naming for the terminology (in all places where applicable).

Raag

Quoted 8 lines
drivers/gpu/drm/xe/xe_cper.c +4 -0
+	/** @timestamp: Timestamp of the first occurrence of this error class */
+	u64 timestamp;
+};
+
 #endif
Signature · 1 line
2.54.0
#28 lore raw

PATCH v4 7/12 drm/xe/cper: Log CPER records for aggregate counter retrieval

In reply to Badal Nilawar

Log CPER records for aggregate counter retrieval from userspace when cper_on_query sysfs is enabled.

Assisted-by Copilot:Claude-Opus-5.5

---
v4:
- Add xe_cper_emit_counter() to emit records from the counter response already fetched for userspace, instead of fetching it again
- Move cper_on_query to struct xe_cper and xe_cper.c (Raag)
- Document cper_on_query sysfs in ABI
- Fix sysfs attribute cper_on_query permissions (sashiko)

---
 .../ABI/testing/sysfs-driver-intel-xe-cper    | 18 ++++
 drivers/gpu/drm/xe/xe_cper.c                  | 99 ++++++++++++++++---
 drivers/gpu/drm/xe/xe_cper.h                  | 11 +++
 drivers/gpu/drm/xe/xe_cper_types.h            |  8 ++
 drivers/gpu/drm/xe/xe_device_types.h          |  4 +
 drivers/gpu/drm/xe/xe_ras.c                   | 42 ++++++++
 6 files changed, 169 insertions(+), 13 deletions(-)
 create mode 100644 Documentation/ABI/testing/sysfs-driver-intel-xe-cper
Documentation/ABI/testing/sysfs-driver-intel-xe-cper new file +18 -0
new file mode 100644
index 000000000000..19f56d2c0ab3
@@ -0,0 +1,18 @@
+What:		/sys/bus/pci/drivers/xe/.../cper_on_query
+Date:		October 2026
+KernelVersion:	7.4
+Contact:	[email protected]
+Description:
+		This file controls whether a CPER (Common Platform Error Record)
+		is emitted each time a RAS error counter is queried.
+
+		This sysfs file is present only on Intel Xe platforms that support
+		the RAS error counter interface and when the kernel is built with
+		CPER support. Reading the current setting is available to all
+		users, while updating it is restricted to administrative users
+		only.
+
+		The value is a boolean. When set to 1, every counter query emits
+		a CPER record built from the counter and its associated info
+		queue data. When set to 0 (default), no record is emitted on
+		query.
drivers/gpu/drm/xe/xe_cper.c +86 -13

138 lines not on this page · raw message

drivers/gpu/drm/xe/xe_cper.h +11 -0
index 84676c7645a5..ad50349c0a6f 100644
@@ -12,15 +12,26 @@
 
 struct va_format;
 struct xe_device;
+struct xe_ras_error_class;
+struct xe_ras_get_counter_response;
 
 #if IS_ENABLED(CONFIG_UEFI_CPER)
 void xe_cper_emit(struct xe_device *xe, int cper_sev, enum xe_sigid sigid,
 		  u32 component, u32 location, const void *data, size_t len,
 		  struct va_format *vaf);
+void xe_cper_emit_counter(struct xe_device *xe, int cper_sev, enum xe_sigid sigid,
+			  const struct xe_ras_error_class *error_class,
+			  const struct xe_ras_get_counter_response *resp);
+int xe_cper_sysfs_init(struct xe_device *xe);
 #else
 static inline void xe_cper_emit(struct xe_device *xe, int cper_sev, enum xe_sigid sigid,
 				u32 component, u32 location, const void *data, size_t len,
 				struct va_format *vaf) {}
+static inline void xe_cper_emit_counter(struct xe_device *xe, int cper_sev,
+					enum xe_sigid sigid,
+					const struct xe_ras_error_class *error_class,
+					const struct xe_ras_get_counter_response *resp) {}
+static inline int xe_cper_sysfs_init(struct xe_device *xe) { return 0; }
 #endif
 
 #endif /* _XE_CPER_H_ */
drivers/gpu/drm/xe/xe_cper_types.h +8 -0
index 627c7117f23e..e0034429e661 100644
@@ -174,4 +174,12 @@ struct xe_cper_einfo_entry {
 	u64 timestamp;
 };
 
+/**
+ * struct xe_cper - Xe CPER state
+ */
+struct xe_cper {
+	/** @on_query: Emit a CPER record on each RAS counter query */
+	bool on_query;
+};
+
 #endif
drivers/gpu/drm/xe/xe_device_types.h +4 -0
index 41f703a87916..d88e0768bc3e 100644
@@ -12,6 +12,7 @@
 #include <drm/drm_file.h>
 #include <drm/ttm/ttm_device.h>
 
+#include "xe_cper_types.h"
 #include "xe_devcoredump_types.h"
 #include "xe_drm_ras_types.h"
 #include "xe_heci_gsc.h"
@@ -579,6 +580,9 @@ struct xe_device {
 	/** @ras: RAS structure for device */
 	struct xe_drm_ras ras;
 
+	/** @cper: CPER state */
+	struct xe_cper cper;
+
 	/** @i2c: I2C host controller */
 	struct xe_i2c *i2c;
 
drivers/gpu/drm/xe/xe_ras.c +42 -0

64 lines not on this page · raw message

Signature · 1 line
2.54.0
#29 lore raw

Re: [PATCH v4 07/12] drm/xe/cper: Log CPER records for aggregate counter retrieval

Quoted 2 lines · Badal Nilawar

Log CPER records for aggregate counter retrieval from userspace when cper_on_query sysfs is enabled.

...

Quoted 14 lines
drivers/gpu/drm/xe/xe_cper.c +12 -2
-static void xe_cper_emit_hw_err(struct xe_device *xe, int cper_sev, enum xe_sigid sigid,
-				const struct xe_ras_error_class *error_class)
+/**
+ * xe_cper_emit_counter() - Emit CPER records for an already fetched error counter
+ * @xe: The &xe_device
+ * @cper_sev: CPER severity
+ * @sigid: Error signature identifier
+ * @error_class: RAS error class of the counter
+ * @resp: Counter response returned by firmware for @error_class
+ *
+ * Build and emit CPER records from @resp, including any info queue data.
+ * Must be called from a sleepable context with a runtime PM reference held.
+ */
+void xe_cper_emit_counter(struct xe_device *xe, int cper_sev, enum xe_sigid sigid,

drivers/gpu/drm/xe/xe_cper.c xe_prepare_cper_error_info(struct xe_device *xe, · line 402

Quoted 10 lines
drivers/gpu/drm/xe/xe_cper.c +3 -2
+			  const struct xe_ras_error_class *error_class,
+			  const struct xe_ras_get_counter_response *resp)
 {
 	struct xe_cper_einfo_entry *einfo_arr = NULL, *entries;
-	struct xe_ras_get_counter_response local_resp;
 	struct xe_cper_einfo_entry single = {};
 	u32 einfo_count = 0, count, i;
 
-	/* Fetching the counter sends a sysctrl command */
+	if (!is_hw_sigid(sigid))

Nack. No guardrails for abusers, they are expected to fail.

Quoted 37 lines
drivers/gpu/drm/xe/xe_cper.c +13 -9
+		return;
+
+	/* Draining the info queue sends sysctrl commands */
 	might_sleep();
 	xe_device_assert_mem_access(xe);
 
-	if (xe_ras_get_counter_response(xe, error_class, &local_resp)) {
-		xe_err(xe, "CPER: failed to get counter, skipping record\n");
-		return;
-	}
-
 	/* Without info queue data, emit a single record from the counter itself */
 	single.hdr.error_class = *error_class;
-	single.hdr.counter = local_resp.value;
-	single.timestamp = local_resp.timestamp;
+	single.hdr.counter = resp->value;
+	single.timestamp = resp->timestamp;
 	entries = &single;
 	count = 1;
 
-	if (local_resp.has_info_queue) {
-		einfo_arr = xe_prepare_cper_error_info(xe, &local_resp, error_class, &einfo_count);
+	if (resp->has_info_queue) {
+		einfo_arr = xe_prepare_cper_error_info(xe, resp, error_class, &einfo_count);
 		if (einfo_arr) {
 			entries = einfo_arr;
 			count = einfo_count;
@@ -425,6 +436,23 @@ static void xe_cper_emit_hw_err(struct xe_device *xe, int cper_sev, enum xe_sigi
 	free_einfo_arr(einfo_arr, einfo_count);
 }
 
+static void xe_cper_emit_hw_err(struct xe_device *xe, int cper_sev, enum xe_sigid sigid,
+				const struct xe_ras_error_class *error_class)
+{
+	struct xe_ras_get_counter_response resp;
+
+	/* Fetching the counter sends a sysctrl command */

drivers/gpu/drm/xe/xe_cper.c static void xe_cper_emit_hw_err(struct xe_device *xe, int cper_sev, enum xe_sigi · line 454

Quoted 10 lines
drivers/gpu/drm/xe/xe_cper.c +10 -0
+	might_sleep();
+	xe_device_assert_mem_access(xe);
+
+	if (xe_ras_get_counter_response(xe, error_class, &resp)) {
+		xe_err(xe, "CPER: failed to get counter, skipping record\n");
+		return;
+	}
+
+	xe_cper_emit_counter(xe, cper_sev, sigid, error_class, &resp);
+}

This is how I think it should've been introduced in the original patch, so we don't churn here.

...

drivers/gpu/drm/xe/xe_ras.c int xe_ras_get_counter(struct xe_device *xe, u8 severity, u8 component, u32 *val · line 653

Quoted 6 lines
drivers/gpu/drm/xe/xe_ras.c +2 -0
@@ -616,6 +649,11 @@ int xe_ras_get_counter(struct xe_device *xe, u8 severity, u8 component, u32 *val
 		return ret;
 
 	*value = response.value;
+
+	if (READ_ONCE(xe->cper.on_query))

Following the comments on patch 2, this condition will now be passed as a bool argument to get_counter(). Based on which, it will go on to call xe_cper_emit_counter().

The callers that aren't interesed in the entire response will pass explicit false to get_counter(), so cper isn't emitted in those cases.

Raag

Quoted 18 lines
drivers/gpu/drm/xe/xe_ras.c +7 -0
+		xe_cper_emit_counter(xe, ras_sev_to_cper_sev(counter.common.severity),
+				     ras_comp_to_hw_sigid(counter.common.component),
+				     &counter, &response);
 	return 0;
 }
 
@@ -1067,4 +1105,8 @@ void xe_ras_init(struct xe_device *xe)
 	ret = devm_device_add_group(xe->drm.dev, &gpu_health_group);
 	if (ret)
 		xe_err(xe, "Failed to create GPU health sysfs, err=%d\n", ret);
+
+	ret = xe_cper_sysfs_init(xe);
+	if (ret)
+		xe_err(xe, "Failed to create cper_on_query sysfs, err=%d\n", ret);
 }
Signature · 1 line
2.54.0
#30 lore raw

PATCH v4 8/12 drm/xe/cper: Emit cper record to trace buf

In reply to Badal Nilawar

Add the xe_error_cper tracepoint and emit each assembled CPER record through it. Besides the raw record, the event carries the device name, platform ID, FRU ID, severity and the Intel error section header, so tools can pick up the records from the trace buffer.

Assisted-by Copilot:claude-sonnet-4.6

---
v4:
- Build xe_trace_cper.o with CONFIG_UEFI_CPER instead of CONFIG_UEFI_CPER_X86

---
 drivers/gpu/drm/xe/Makefile        |  3 +-
 drivers/gpu/drm/xe/xe_cper.c       |  4 +-
 drivers/gpu/drm/xe/xe_trace_cper.c |  9 ++++
 drivers/gpu/drm/xe/xe_trace_cper.h | 66 ++++++++++++++++++++++++++++++
 4 files changed, 80 insertions(+), 2 deletions(-)
 create mode 100644 drivers/gpu/drm/xe/xe_trace_cper.c
 create mode 100644 drivers/gpu/drm/xe/xe_trace_cper.h
drivers/gpu/drm/xe/Makefile +2 -1
index da78026b0bb4..5458119ddf40 100644
@@ -168,7 +168,8 @@ xe-$(CONFIG_HWMON) += xe_hwmon.o
 xe-$(CONFIG_PERF_EVENTS) += xe_pmu.o
 xe-$(CONFIG_CONFIGFS_FS) += xe_configfs.o
 
-xe-$(CONFIG_UEFI_CPER) += xe_cper.o
+xe-$(CONFIG_UEFI_CPER) += xe_cper.o \
+			  xe_trace_cper.o
 
 # graphics virtualization (SR-IOV) support
 xe-y += \
drivers/gpu/drm/xe/xe_cper.c +3 -1
index 709fc3d52fcf..0fedef06e138 100644
@@ -20,6 +20,7 @@
 #include "xe_printk.h"
 #include "xe_ras.h"
 #include "xe_ras_types.h"
+#include "xe_trace_cper.h"
 
 static bool is_hw_sigid(enum xe_sigid sigid)
 {
@@ -179,7 +180,8 @@ static void xe_cper_record_emit(struct xe_device *xe, u8 severity,
 	if (einfo && einfo_len)
 		memcpy((u8 *)rec + sizeof(*rec), einfo, einfo_len);
 
-	/* TODO: Emit trace event */
+	trace_xe_error_cper(xe, &rhdr->platform_id, &sdesc->fru_id, severity,
+			    &rec->intel_hdr, total_len, (u8 *)rec);
 
 	kfree(rec);
 }
drivers/gpu/drm/xe/xe_trace_cper.c new file +9 -0
new file mode 100644
index 000000000000..caea8783ab7c
@@ -0,0 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright © 2026 Intel Corporation
+ */
+
+#ifndef __CHECKER__
+#define CREATE_TRACE_POINTS
+#include "xe_trace_cper.h"
+#endif
drivers/gpu/drm/xe/xe_trace_cper.h new file +66 -0

66 lines not on this page · raw message

Signature · 1 line
2.54.0
#31 lore raw

Re: [PATCH v4 08/12] drm/xe/cper: Emit cper record to trace buf

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider: - [Low] trace: xe_error_cper uses %pU instead of %pUl for guid_t formatting --

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Low] trace: xe_error_cper uses %pU instead of %pUl for guid_t formatting --

commit 2df74abeb761bb9cbc4580031c2be3af5f19e10b
Author: Badal Nilawar <[email protected]>

drm/xe/cper: Emit cper record to trace buf

This commit introduces the xe_error_cper tracepoint to emit assembled CPER records to the trace buffer. The events carry the device name, platform ID, FRU ID, severity, and the Intel error section header so tools can pick them up.

Quoted 4 lines
drivers/gpu/drm/xe/xe_trace_cper.h new file +0 -0
new file mode 100644

[ ... ]

Quoted 3 lines
drivers/gpu/drm/xe/xe_trace_cper.h new file +3 -0
+TRACE_EVENT(xe_error_cper,
+	TP_PROTO(struct xe_device *xe,
+	    const guid_t *platform_id, const guid_t *fru_id,

[ ... ]

drivers/gpu/drm/xe/xe_trace_cper.h line 49

Quoted 12 lines
drivers/gpu/drm/xe/xe_trace_cper.h new file +12 -0
+	TP_fast_assign(
+	    __assign_str(dev);
+	    __entry->sev = severity;
+	    memcpy(__entry->platform_id, platform_id, UUID_SIZE);
+	    memcpy(__entry->fru_id, fru_id, UUID_SIZE);
+	    memcpy(__entry->ihdr_raw, ihdr, sizeof(struct xe_cper_sec_intel_err_hdr));
+	    __entry->cper_len = cper_len;
+	    memcpy(__get_dynamic_array(cper), cper, cper_len);
+	    ),
+
+	TP_printk("dev=%s severity=%d platform_id=%pU fru_id=%pU "
+		"intel_err_hdr_raw=%s cper_len=%u cper_raw=%s",

[Severity: Low]
Since platform_id and fru_id are guid_t types (which are little-endian per UEFI/CPER specifications), shouldn't this use the %pUl format specifier instead of %pU?

The Linux kernel's %pU specifier assumes a big-endian uuid_t layout. Using it here will cause the first three groups of the UUID to be byte-swapped in the trace output, which might break correlation with platform specifications and CPER tooling.

Quoted 8 lines
drivers/gpu/drm/xe/xe_trace_cper.h new file +8 -0
+		__get_str(dev), __entry->sev,
+		__entry->platform_id, __entry->fru_id,
+		__print_hex(__entry->ihdr_raw,
+		    sizeof(struct xe_cper_sec_intel_err_hdr)),
+		__entry->cper_len,
+		__print_hex(__get_dynamic_array(cper),
+		    __entry->cper_len))
+);
Signature · 1 line
Sashiko AI review · https://sashiko.dev/#/patchset/[email protected]?part=8
#32 lore raw

PATCH v4 9/12 drm/xe/xe_ras: Report device memory errors using SIGID

In reply to Badal Nilawar

Use xe_log_comp_info helper to report device memory errors.

---
 drivers/gpu/drm/xe/xe_ras.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)
drivers/gpu/drm/xe/xe_ras.c +7 -4
index 25ea178228f7..8ed4a6992ef1 100644
@@ -409,14 +409,17 @@ static u8 handle_device_memory_errors(struct xe_device *xe, struct xe_ras_error_
 	 */
 	switch (info->category) {
 	case XE_RAS_MEMORY_POISON:
-		xe_info(xe, "[RAS]: Poison error detected\n");
+		xe_log_comp_info(xe, DEVICE_MEMORY, &arr->counter, sizeof(arr->counter),
+				 "Poison error detected\n");
 		break;
 	case XE_RAS_MEMORY_DATA_PARITY:
-		xe_info(xe, "[RAS]: Data parity error detected\n");
+		xe_log_comp_info(xe, DEVICE_MEMORY, &arr->counter, sizeof(arr->counter),
+				 "Data parity error detected\n");
 		break;
 	case XE_RAS_MEMORY_DB_ECC:
-		xe_info(xe, "[RAS]: Double-bit ECC error detected at sw address 0x%llx\n",
-			info->sw_address);
+		xe_log_comp_info(xe, DEVICE_MEMORY, &arr->counter, sizeof(arr->counter),
+				 "Double-bit ECC error detected at sw address 0x%llx\n",
+				 info->sw_address);
 		/* TODO: Add page offlining for Double-bit ECC error */
 		fallthrough;
 	default:
Signature · 1 line
2.54.0
Reviewed-by on v4 9/12
#33 lore raw

Re: [PATCH v4 09/12] drm/xe/xe_ras: Report device memory errors using SIGID

Quoted 3 lines · Badal Nilawar

Use xe_log_comp_info helper to report device memory errors.

LGTM,

Quoted 31 lines
Cc Riana Tauro <[email protected]>
---
  drivers/gpu/drm/xe/xe_ras.c | 11 +++++++----
  1 file changed, 7 insertions(+), 4 deletions(-)
drivers/gpu/drm/xe/xe_ras.c +7 -4
index 25ea178228f7..8ed4a6992ef1 100644
@@ -409,14 +409,17 @@ static u8 handle_device_memory_errors(struct xe_device *xe, struct xe_ras_error_
  	 */
  	switch (info->category) {
  	case XE_RAS_MEMORY_POISON:
-		xe_info(xe, "[RAS]: Poison error detected\n");
+		xe_log_comp_info(xe, DEVICE_MEMORY, &arr->counter, sizeof(arr->counter),
+				 "Poison error detected\n");
  		break;
  	case XE_RAS_MEMORY_DATA_PARITY:
-		xe_info(xe, "[RAS]: Data parity error detected\n");
+		xe_log_comp_info(xe, DEVICE_MEMORY, &arr->counter, sizeof(arr->counter),
+				 "Data parity error detected\n");
  		break;
  	case XE_RAS_MEMORY_DB_ECC:
-		xe_info(xe, "[RAS]: Double-bit ECC error detected at sw address 0x%llx\n",
-			info->sw_address);
+		xe_log_comp_info(xe, DEVICE_MEMORY, &arr->counter, sizeof(arr->counter),
+				 "Double-bit ECC error detected at sw address 0x%llx\n",
+				 info->sw_address);
  		/* TODO: Add page offlining for Double-bit ECC error */
  		fallthrough;
  	default:
#34 lore raw

PATCH v4 10/12 drm/xe/xe_ras: Report core compute errors using SIGID

In reply to Badal Nilawar

Use xe_log_* helpers to report core compute errors.

---
v2:
- Pass RAS firmware reported severity to xe_log

---
 drivers/gpu/drm/xe/xe_ras.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)
drivers/gpu/drm/xe/xe_ras.c +9 -3
index 8ed4a6992ef1..6647300c7f17 100644
@@ -332,21 +332,27 @@ static void ras_send_error_event(struct xe_device *xe, u8 severity, u8 component
 	xe_drm_ras_event(xe, drm_component, drm_severity, response.value);
 }
 
-static u8 handle_core_compute_errors(struct xe_ras_error_array *arr)
+static u8 handle_core_compute_errors(struct xe_device *xe, struct xe_ras_error_array *arr)
 {
 	struct xe_ras_compute_error *error_info = (void *)arr->details;
+	u8 cper_sev = ras_sev_to_cper_sev(arr->counter.common.severity);
 	u8 uncorr_type;
 
 	uncorr_type = FIELD_GET(CORE_COMPUTE_UNCORR_TYPE, error_info->log_header);
 
 	/* Request a reset if error is global */
-	if (uncorr_type == GLOBAL_UNCORR_ERROR)
+	if (uncorr_type == GLOBAL_UNCORR_ERROR) {
+		xe_log_comp(xe, cper_sev, CORE_COMPUTE, &arr->counter, sizeof(arr->counter),
+			    "Global uncorrectable error detected\n");
 		return XE_RAS_RECOVERY_ACTION_RESET;
+	}
 
 	/*
 	 * No action needed for other errors.
 	 * Local errors are recovered using an engine reset by GuC.
 	 */
+	xe_log_comp(xe, cper_sev, CORE_COMPUTE, &arr->counter, sizeof(arr->counter),
+		    "Other compute errors\n");
 	return XE_RAS_RECOVERY_ACTION_RECOVERED;
 }
 
@@ -592,7 +598,7 @@ enum xe_ras_recovery_action xe_ras_process_errors(struct xe_device *xe)
 
 			switch (component) {
 			case XE_RAS_COMP_CORE_COMPUTE:
-				action = handle_core_compute_errors(arr);
+				action = handle_core_compute_errors(xe, arr);
 				break;
 			case XE_RAS_COMP_SOC_INTERNAL:
 				action = handle_soc_internal_errors(xe, arr);
Signature · 1 line
2.54.0
Reviewed-by on v4 10/12
#35 lore raw

Re: [PATCH v4 10/12] drm/xe/xe_ras: Report core compute errors using SIGID

Quoted 3 lines · Badal Nilawar

Use xe_log_* helpers to report core compute errors.

LGTM,

Quoted 51 lines
Cc Riana Tauro <[email protected]>

---
v2:
- Pass RAS firmware reported severity to xe_log

---
  drivers/gpu/drm/xe/xe_ras.c | 12 +++++++++---
  1 file changed, 9 insertions(+), 3 deletions(-)
drivers/gpu/drm/xe/xe_ras.c +9 -3
index 8ed4a6992ef1..6647300c7f17 100644
@@ -332,21 +332,27 @@ static void ras_send_error_event(struct xe_device *xe, u8 severity, u8 component
  	xe_drm_ras_event(xe, drm_component, drm_severity, response.value);
  }
 
-static u8 handle_core_compute_errors(struct xe_ras_error_array *arr)
+static u8 handle_core_compute_errors(struct xe_device *xe, struct xe_ras_error_array *arr)
  {
  	struct xe_ras_compute_error *error_info = (void *)arr->details;
+	u8 cper_sev = ras_sev_to_cper_sev(arr->counter.common.severity);
  	u8 uncorr_type;
 
  	uncorr_type = FIELD_GET(CORE_COMPUTE_UNCORR_TYPE, error_info->log_header);
 
  	/* Request a reset if error is global */
-	if (uncorr_type == GLOBAL_UNCORR_ERROR)
+	if (uncorr_type == GLOBAL_UNCORR_ERROR) {
+		xe_log_comp(xe, cper_sev, CORE_COMPUTE, &arr->counter, sizeof(arr->counter),
+			    "Global uncorrectable error detected\n");
  		return XE_RAS_RECOVERY_ACTION_RESET;
+	}
 
  	/*
  	 * No action needed for other errors.
  	 * Local errors are recovered using an engine reset by GuC.
  	 */
+	xe_log_comp(xe, cper_sev, CORE_COMPUTE, &arr->counter, sizeof(arr->counter),
+		    "Other compute errors\n");
  	return XE_RAS_RECOVERY_ACTION_RECOVERED;
  }
 
@@ -592,7 +598,7 @@ enum xe_ras_recovery_action xe_ras_process_errors(struct xe_device *xe)
 
  			switch (component) {
  			case XE_RAS_COMP_CORE_COMPUTE:
-				action = handle_core_compute_errors(arr);
+				action = handle_core_compute_errors(xe, arr);
  				break;
  			case XE_RAS_COMP_SOC_INTERNAL:
  				action = handle_soc_internal_errors(xe, arr);
#36 lore raw

Re: [PATCH v4 10/12] drm/xe/xe_ras: Report core compute errors using SIGID

Quoted 7 lines · Koujalagi
Quoted 3 lines · Badal Nilawar

Use xe_log_* helpers to report core compute errors.

LGTM,

The previous revision review comments need to be addressed. We are not seeing SIGID logs for all errors. Please do not merge this without that fix.

Thanks
Riana

Quoted 49 lines
Quoted 49 lines
Cc Riana Tauro <[email protected]>

---
v2:
   - Pass RAS firmware reported severity to xe_log
---
  drivers/gpu/drm/xe/xe_ras.c | 12 +++++++++---

  1 file changed, 9 insertions(+), 3 deletions(-)
drivers/gpu/drm/xe/xe_ras.c +0 -0
index 8ed4a6992ef1..6647300c7f17 100644
@@ -332,21 +332,27 @@ static void ras_send_error_event(struct 

xe_device *xe, u8 severity, u8 component
      xe_drm_ras_event(xe, drm_component, drm_severity, response.value);
  }
  -static u8 handle_core_compute_errors(struct xe_ras_error_array *arr) +static u8 handle_core_compute_errors(struct xe_device *xe, struct xe_ras_error_array *arr)
  {
      struct xe_ras_compute_error *error_info = (void *)arr->details;
+    u8 cper_sev = ras_sev_to_cper_sev(arr->counter.common.severity);
      u8 uncorr_type;
        uncorr_type = FIELD_GET(CORE_COMPUTE_UNCORR_TYPE, error_info->log_header); /* Request a reset if error is global */
-    if (uncorr_type == GLOBAL_UNCORR_ERROR)
+    if (uncorr_type == GLOBAL_UNCORR_ERROR) {
+        xe_log_comp(xe, cper_sev, CORE_COMPUTE, &arr->counter, sizeof(arr->counter),
+                "Global uncorrectable error detected\n");
          return XE_RAS_RECOVERY_ACTION_RESET;
+    }
        /*
       * No action needed for other errors.
       * Local errors are recovered using an engine reset by GuC.
       */
+    xe_log_comp(xe, cper_sev, CORE_COMPUTE, &arr->counter, sizeof(arr->counter),
+            "Other compute errors\n");
      return XE_RAS_RECOVERY_ACTION_RECOVERED;
  }
  @@ -592,7 +598,7 @@ enum xe_ras_recovery_action xe_ras_process_errors(struct xe_device *xe) switch (component) {
              case XE_RAS_COMP_CORE_COMPUTE:
-                action = handle_core_compute_errors(arr);
+                action = handle_core_compute_errors(xe, arr);
                  break;
              case XE_RAS_COMP_SOC_INTERNAL:
                  action = handle_soc_internal_errors(xe, arr);

#37 lore raw

Re: [PATCH v4 10/12] drm/xe/xe_ras: Report core compute errors using SIGID

In reply to Badal Nilawar
Quoted 32 lines · Badal Nilawar

Use xe_log_* helpers to report core compute errors.

---
v2:
- Pass RAS firmware reported severity to xe_log

---
 drivers/gpu/drm/xe/xe_ras.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)
drivers/gpu/drm/xe/xe_ras.c +4 -2
index 8ed4a6992ef1..6647300c7f17 100644
@@ -332,21 +332,27 @@ static void ras_send_error_event(struct xe_device *xe, u8 severity, u8 component
 	xe_drm_ras_event(xe, drm_component, drm_severity, response.value);
 }
 
-static u8 handle_core_compute_errors(struct xe_ras_error_array *arr)
+static u8 handle_core_compute_errors(struct xe_device *xe, struct xe_ras_error_array *arr)
 {
 	struct xe_ras_compute_error *error_info = (void *)arr->details;
+	u8 cper_sev = ras_sev_to_cper_sev(arr->counter.common.severity);
 	u8 uncorr_type;
 
 	uncorr_type = FIELD_GET(CORE_COMPUTE_UNCORR_TYPE, error_info->log_header);
 
 	/* Request a reset if error is global */
-	if (uncorr_type == GLOBAL_UNCORR_ERROR)
+	if (uncorr_type == GLOBAL_UNCORR_ERROR) {
+		xe_log_comp(xe, cper_sev, CORE_COMPUTE, &arr->counter, sizeof(arr->counter),

drivers/gpu/drm/xe/xe_ras.c static void ras_send_error_event(struct xe_device *xe, u8 severity, u8 component · line 355

Quoted 10 lines
drivers/gpu/drm/xe/xe_ras.c +4 -0
+			    "Global uncorrectable error detected\n");
 		return XE_RAS_RECOVERY_ACTION_RESET;
+	}
 
 	/*
 	 * No action needed for other errors.
 	 * Local errors are recovered using an engine reset by GuC.
 	 */
+	xe_log_comp(xe, cper_sev, CORE_COMPUTE, &arr->counter, sizeof(arr->counter),
+		    "Other compute errors\n");

'Other' errors isn't telling me anything, no they are documented here. If we don't know what they are, use 'unknown' or something more specific.

Raag

Quoted 15 lines
drivers/gpu/drm/xe/xe_ras.c +1 -1
 	return XE_RAS_RECOVERY_ACTION_RECOVERED;
 }
 
@@ -592,7 +598,7 @@ enum xe_ras_recovery_action xe_ras_process_errors(struct xe_device *xe)
 
 			switch (component) {
 			case XE_RAS_COMP_CORE_COMPUTE:
-				action = handle_core_compute_errors(arr);
+				action = handle_core_compute_errors(xe, arr);
 				break;
 			case XE_RAS_COMP_SOC_INTERNAL:
 				action = handle_soc_internal_errors(xe, arr);
Signature · 1 line
2.54.0
#38 lore raw

PATCH v4 11/12 drm/xe/xe_ras: Report soc internal errors using SIGID

In reply to Badal Nilawar

Use xe_log_* helpers to report soc internal errors.

---
 drivers/gpu/drm/xe/xe_ras.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)
drivers/gpu/drm/xe/xe_ras.c +5 -7
index 6647300c7f17..af2970941b59 100644
@@ -366,7 +366,6 @@ static u8 handle_soc_internal_errors(struct xe_device *xe, struct xe_ras_error_a
 {
 	struct xe_ras_soc_error *info = (void *)arr->details;
 	struct xe_ras_soc_error_source *source = &info->source;
-	struct xe_ras_error_class *counter = &arr->counter;
 
 	if (source->csc) {
 		struct xe_ras_csc_error *csc_error = (void *)info->details;
@@ -380,9 +379,8 @@ static u8 handle_soc_internal_errors(struct xe_device *xe, struct xe_ras_error_a
 		 * is required.
 		 */
 		if (csc_error->hec_fw_error) {
-			xe_err(xe, "[RAS]: CSC %s detected: 0x%x\n",
-			       sev_to_str(counter->common.severity),
-			       csc_error->hec_fw_error);
+			xe_log_comp_fatal(xe, SOC_INTERNAL, &arr->counter, sizeof(arr->counter),
+					  "CSC error detected: 0x%x\n", csc_error->hec_fw_error);
 			xe_survivability_mode_runtime_enable(xe);
 			return XE_RAS_RECOVERY_ACTION_DISCONNECT;
 		}
@@ -390,9 +388,9 @@ static u8 handle_soc_internal_errors(struct xe_device *xe, struct xe_ras_error_a
 		struct xe_ras_ieh_error *ieh_error = (void *)info->details;
 
 		if (ieh_error->global_error_status & XE_RAS_SOC_IEH_PUNIT) {
-			xe_err(xe, "[RAS]: PUNIT %s detected: 0x%x\n",
-			       sev_to_str(counter->common.severity),
-			       ieh_error->global_error_status);
+			xe_log_comp_fatal(xe, SOC_INTERNAL, &arr->counter, sizeof(arr->counter),
+					  "PUNIT error detected: 0x%x\n",
+					  ieh_error->global_error_status);
 			punit_error_handler(xe);
 			return XE_RAS_RECOVERY_ACTION_DISCONNECT;
 		}
Signature · 1 line
2.54.0
Reviewed-by on v4 11/12
#39 lore raw

Re: [PATCH v4 11/12] drm/xe/xe_ras: Report soc internal errors using SIGID

Quoted 4 lines · Badal Nilawar

Use xe_log_* helpers to report soc internal errors.

LGTM,

Quoted 42 lines
Cc Riana Tauro <[email protected]>
---
  drivers/gpu/drm/xe/xe_ras.c | 12 +++++-------
  1 file changed, 5 insertions(+), 7 deletions(-)
drivers/gpu/drm/xe/xe_ras.c +5 -7
index 6647300c7f17..af2970941b59 100644
@@ -366,7 +366,6 @@ static u8 handle_soc_internal_errors(struct xe_device *xe, struct xe_ras_error_a
  {
  	struct xe_ras_soc_error *info = (void *)arr->details;
  	struct xe_ras_soc_error_source *source = &info->source;
-	struct xe_ras_error_class *counter = &arr->counter;
 
  	if (source->csc) {
  		struct xe_ras_csc_error *csc_error = (void *)info->details;
@@ -380,9 +379,8 @@ static u8 handle_soc_internal_errors(struct xe_device *xe, struct xe_ras_error_a
  		 * is required.
  		 */
  		if (csc_error->hec_fw_error) {
-			xe_err(xe, "[RAS]: CSC %s detected: 0x%x\n",
-			       sev_to_str(counter->common.severity),
-			       csc_error->hec_fw_error);
+			xe_log_comp_fatal(xe, SOC_INTERNAL, &arr->counter, sizeof(arr->counter),
+					  "CSC error detected: 0x%x\n", csc_error->hec_fw_error);
  			xe_survivability_mode_runtime_enable(xe);
  			return XE_RAS_RECOVERY_ACTION_DISCONNECT;
  		}
@@ -390,9 +388,9 @@ static u8 handle_soc_internal_errors(struct xe_device *xe, struct xe_ras_error_a
  		struct xe_ras_ieh_error *ieh_error = (void *)info->details;
 
  		if (ieh_error->global_error_status & XE_RAS_SOC_IEH_PUNIT) {
-			xe_err(xe, "[RAS]: PUNIT %s detected: 0x%x\n",
-			       sev_to_str(counter->common.severity),
-			       ieh_error->global_error_status);
+			xe_log_comp_fatal(xe, SOC_INTERNAL, &arr->counter, sizeof(arr->counter),
+					  "PUNIT error detected: 0x%x\n",
+					  ieh_error->global_error_status);
  			punit_error_handler(xe);
  			return XE_RAS_RECOVERY_ACTION_DISCONNECT;
  		}
#40 lore raw

Re: [PATCH v4 11/12] drm/xe/xe_ras: Report soc internal errors using SIGID

In reply to Badal Nilawar
Quoted 22 lines · Badal Nilawar

Use xe_log_* helpers to report soc internal errors.

---
 drivers/gpu/drm/xe/xe_ras.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)
drivers/gpu/drm/xe/xe_ras.c +0 -1
index 6647300c7f17..af2970941b59 100644
@@ -366,7 +366,6 @@ static u8 handle_soc_internal_errors(struct xe_device *xe, struct xe_ras_error_a
 {
 	struct xe_ras_soc_error *info = (void *)arr->details;
 	struct xe_ras_soc_error_source *source = &info->source;
-	struct xe_ras_error_class *counter = &arr->counter;
 
 	if (source->csc) {
 		struct xe_ras_csc_error *csc_error = (void *)info->details;

drivers/gpu/drm/xe/xe_ras.c static u8 handle_soc_internal_errors(struct xe_device *xe, struct xe_ras_error_a · line 383

Quoted 4 lines
drivers/gpu/drm/xe/xe_ras.c +0 -1
@@ -380,9 +379,8 @@ static u8 handle_soc_internal_errors(struct xe_device *xe, struct xe_ras_error_a
 		 * is required.
 		 */
 		if (csc_error->hec_fw_error) {
-			xe_err(xe, "[RAS]: CSC %s detected: 0x%x\n",

Nit: Use fixed format (0x%08x) for readability. It's also easier to parse (just in case).

drivers/gpu/drm/xe/xe_ras.c static u8 handle_soc_internal_errors(struct xe_device *xe, struct xe_ras_error_a · line 393

Quoted 12 lines
drivers/gpu/drm/xe/xe_ras.c +2 -3
-			       sev_to_str(counter->common.severity),
-			       csc_error->hec_fw_error);
+			xe_log_comp_fatal(xe, SOC_INTERNAL, &arr->counter, sizeof(arr->counter),
+					  "CSC error detected: 0x%x\n", csc_error->hec_fw_error);
 			xe_survivability_mode_runtime_enable(xe);
 			return XE_RAS_RECOVERY_ACTION_DISCONNECT;
 		}
@@ -390,9 +388,9 @@ static u8 handle_soc_internal_errors(struct xe_device *xe, struct xe_ras_error_a
 		struct xe_ras_ieh_error *ieh_error = (void *)info->details;
 
 		if (ieh_error->global_error_status & XE_RAS_SOC_IEH_PUNIT) {
-			xe_err(xe, "[RAS]: PUNIT %s detected: 0x%x\n",

Ditto.

Raag

Quoted 11 lines
drivers/gpu/drm/xe/xe_ras.c +3 -2
-			       sev_to_str(counter->common.severity),
-			       ieh_error->global_error_status);
+			xe_log_comp_fatal(xe, SOC_INTERNAL, &arr->counter, sizeof(arr->counter),
+					  "PUNIT error detected: 0x%x\n",
+					  ieh_error->global_error_status);
 			punit_error_handler(xe);
 			return XE_RAS_RECOVERY_ACTION_DISCONNECT;
 		}
Signature · 1 line
2.54.0
#41 lore raw

PATCH v4 12/12 drm/xe/xe_ras: Report correctable errors using SIGID

In reply to Badal Nilawar

Use xe_log_* helper to report correctable errors.

Assisted-by Copilot:Claude-Opus-5.5
Cc Raag Jadav <[email protected]>

---
v4:
- Pass structured log component to xe_log_from() (sashiko)

---
 drivers/gpu/drm/xe/xe_ras.c | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)
drivers/gpu/drm/xe/xe_ras.c +13 -2
index af2970941b59..9df2e8942bda 100644
@@ -3,6 +3,8 @@
  * Copyright © 2026 Intel Corporation
  */
 
+#include <linux/bitfield.h>
+
 #include "xe_configfs.h"
 #include "xe_cper.h"
 #include "xe_debugfs.h"
@@ -216,6 +218,12 @@ static u8 ras_sev_to_cper_sev(u8 ras_sev)
 	}
 }
 
+static u16 ras_comp_to_log_comp(u8 component)
+{
+	return FIELD_PREP(XE_LOG_COMPONENT_CLASS_MASK, XE_LOG_COMPONENT_CLASS_HARDWARE) |
+	       FIELD_PREP(XE_LOG_COMPONENT_TYPE_MASK, component);
+}
+
 static inline const char *sev_to_str(u8 severity)
 {
 	if (severity >= XE_RAS_SEV_MAX)
@@ -459,8 +467,11 @@ void xe_ras_counter_threshold_crossed(struct xe_device *xe,
 		if (!ras_counter_is_valid(xe, &errors[id]))
 			continue;
 
-		xe_warn(xe, "[RAS]: %s %s detected\n",
-			comp_to_str(component), sev_to_str(severity));
+		xe_log_from(xe, ras_sev_to_cper_sev(severity),
+			    ras_comp_to_hw_sigid(component),
+			    ras_comp_to_log_comp(component),
+			    &errors[id], sizeof(errors[id]),
+			    "error detected\n");
 
 		/* Send event once per component */
 		if (sent & BIT(component))
Signature · 1 line
2.54.0
#42 lore raw

Re: [PATCH v4 12/12] drm/xe/xe_ras: Report correctable errors using SIGID

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider: - [Medium] xe_ras: WARN on valid XE_RAS_COMP_RESERVED telemetry --

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Medium] xe_ras: WARN on valid XE_RAS_COMP_RESERVED telemetry
--

commit ce7ef0dce322046ec43ef7cd45243457eb7f0974
Author: Badal Nilawar <[email protected]>

drm/xe/xe_ras: Report correctable errors using SIGID

This commit updates the reporting of correctable RAS errors to use the xe_log_from helper instead of xe_warn. It introduces mapping functions to convert RAS severity and components to the appropriate logging types and IDs.

Quoted 3 lines
drivers/gpu/drm/xe/xe_ras.c +0 -0

[ ... ]

drivers/gpu/drm/xe/xe_ras.c void xe_ras_counter_threshold_crossed(struct xe_device *xe, · line 474

Quoted 11 lines
drivers/gpu/drm/xe/xe_ras.c +5 -2
@@ -459,8 +467,11 @@ void xe_ras_counter_threshold_crossed(struct xe_device *xe,
 		if (!ras_counter_is_valid(xe, &errors[id]))
 			continue;
 
-		xe_warn(xe, "[RAS]: %s %s detected\n",
-			comp_to_str(component), sev_to_str(severity));
+		xe_log_from(xe, ras_sev_to_cper_sev(severity),
+			    ras_comp_to_hw_sigid(component),
+			    ras_comp_to_log_comp(component),
+			    &errors[id], sizeof(errors[id]),
+			    "error detected\n");

[Severity: Medium]
Could this trigger a WARN for the XE_RAS_COMP_RESERVED component ID?

Looking at ras_counter_is_valid(), it validates the component using:
in_range(component, XE_RAS_COMP_NOT_SUPPORTED + 1, XE_RAS_COMP_MAX - 1)

Since in_range(val, start, len) evaluates val >= start && val < start + len, passing in component 3 (XE_RAS_COMP_RESERVED) returns true, allowing it to pass the validity check.

When this reserved component is passed to xe_log_from(), it triggers the logging subsystem. Because the xe_log macro framework lacks a definition for HARDWARE, 3, log_component_prefix() falls back to log_unknown_component_prefix(), which triggers a kernel WARN().

This warning will crash systems configured with panic_on_warn when they encounter expected or reserved hardware telemetry data. Should we explicitly filter out reserved component IDs before passing them to the logging framework?

Signature · 1 line
Sashiko AI review · https://sashiko.dev/#/patchset/[email protected]?part=12
#43 lore raw

Re: [PATCH v4 12/12] drm/xe/xe_ras: Report correctable errors using SIGID

In reply to Badal Nilawar
Quoted 39 lines · Badal Nilawar

Use xe_log_* helper to report correctable errors.

Assisted-by Copilot:Claude-Opus-5.5
Cc Raag Jadav <[email protected]>

---
v4:
- Pass structured log component to xe_log_from() (sashiko)

---
 drivers/gpu/drm/xe/xe_ras.c | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)
drivers/gpu/drm/xe/xe_ras.c +8 -0
index af2970941b59..9df2e8942bda 100644
@@ -3,6 +3,8 @@
  * Copyright © 2026 Intel Corporation
  */
 
+#include <linux/bitfield.h>
+
 #include "xe_configfs.h"
 #include "xe_cper.h"
 #include "xe_debugfs.h"
@@ -216,6 +218,12 @@ static u8 ras_sev_to_cper_sev(u8 ras_sev)
 	}
 }
 
+static u16 ras_comp_to_log_comp(u8 component)
+{
+	return FIELD_PREP(XE_LOG_COMPONENT_CLASS_MASK, XE_LOG_COMPONENT_CLASS_HARDWARE) |
+	       FIELD_PREP(XE_LOG_COMPONENT_TYPE_MASK, component);
+}
+
 static inline const char *sev_to_str(u8 severity)
 {
 	if (severity >= XE_RAS_SEV_MAX)

drivers/gpu/drm/xe/xe_ras.c void xe_ras_counter_threshold_crossed(struct xe_device *xe, · line 474

Quoted 10 lines
drivers/gpu/drm/xe/xe_ras.c +5 -2
@@ -459,8 +467,11 @@ void xe_ras_counter_threshold_crossed(struct xe_device *xe,
 		if (!ras_counter_is_valid(xe, &errors[id]))
 			continue;
 
-		xe_warn(xe, "[RAS]: %s %s detected\n",
-			comp_to_str(component), sev_to_str(severity));
+		xe_log_from(xe, ras_sev_to_cper_sev(severity),
+			    ras_comp_to_hw_sigid(component),
+			    ras_comp_to_log_comp(component),
+			    &errors[id], sizeof(errors[id]),
+			    "error detected\n");

Please add a reference log in commit message, so we don't leave people guessing (in all patches).

Raag

Quoted 5 lines
drivers/gpu/drm/xe/xe_ras.c +0 -0
 		/* Send event once per component */
 		if (sent & BIT(component))
Signature · 1 line
2.54.0
#44 lore raw

✗ CI.checkpatch: warning for Add CPER logging support for CRI (rev4)

In reply to Badal Nilawar
== Series Details ==

== Series Details ==

Series: Add CPER logging support for CRI (rev4)
URL : https://patchwork.freedesktop.org/series/169692/
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 6bef5ce5c74dc76b4ee69ab2832c0d1fd63c91c7
+ cd /kernel
+ git config --global --add safe.directory /kernel
+ git log -n1
commit be9d02e26570df0fe7473d41fd7963fa71737f22

Author: Badal Nilawar <[email protected]>
Date:   Fri Oct 9 16:16:15 2026 +0530

drm/xe/xe_ras: Report correctable errors using SIGID

Use xe_log_* helper to report correctable errors.

Assisted-by Copilot:Claude-Opus-5.5
Cc Raag Jadav <[email protected]>

+ /mt/dim checkpatch 3bd4f625aafdf70814dbf075de96e224355c9f1e drm-intel 5663ce929103 drm/xe/cper: Add CPER reporting entry point for xe_log
-:32: WARNING:FILE_PATH_CHANGES: added, moved or deleted file(s), does MAINTAINERS need updating? #32:
new file mode 100644

total: 0 errors, 1 warnings, 0 checks, 102 lines checked
d0f12a32ce41 drm/xe/cper: Retrieve the error counter record for CPER reporting cbcf11412d7c drm/xe/cper: Initialize Intel-specific error section header
-:86: WARNING:FILE_PATH_CHANGES: added, moved or deleted file(s), does MAINTAINERS need updating? #86:
new file mode 100644

total: 0 errors, 1 warnings, 0 checks, 138 lines checked
09e074473c25 drm/xe/cper: Construct CPER record for hardware errors
11904ebb7f37 drm/xe/xe_ras: Add support to retrieve info queue data for CRI d046214a5a48 drm/xe/cper: Prepare Intel CPER error info records
dd6a5cb0551e drm/xe/cper: Log CPER records for aggregate counter retrieval
-:13: WARNING:FILE_PATH_CHANGES: added, moved or deleted file(s), does MAINTAINERS need updating? #13:
new file mode 100644

total: 0 errors, 1 warnings, 0 checks, 274 lines checked
5f85699f13df drm/xe/cper: Emit cper record to trace buf
-:51: WARNING:FILE_PATH_CHANGES: added, moved or deleted file(s), does MAINTAINERS need updating? #51:
new file mode 100644

-:91: CHECK:PARENTHESIS_ALIGNMENT: Alignment should match open parenthesis #91: FILE: drivers/gpu/drm/xe/xe_trace_cper.h:21:
+TRACE_EVENT(xe_error_cper,
+ TP_PROTO(struct xe_device *xe,

-:92: CHECK:PARENTHESIS_ALIGNMENT: Alignment should match open parenthesis #92: FILE: drivers/gpu/drm/xe/xe_trace_cper.h:22:
+ TP_PROTO(struct xe_device *xe,
+ const guid_t *platform_id, const guid_t *fru_id,

-:98: CHECK:OPEN_ENDED_LINE: Lines should not end with a '(' #98: FILE: drivers/gpu/drm/xe/xe_trace_cper.h:28:
+ TP_STRUCT__entry(

-:108: CHECK:OPEN_ENDED_LINE: Lines should not end with a '(' #108: FILE: drivers/gpu/drm/xe/xe_trace_cper.h:38:
+ TP_fast_assign(

-:123: CHECK:PARENTHESIS_ALIGNMENT: Alignment should match open parenthesis #123: FILE: drivers/gpu/drm/xe/xe_trace_cper.h:53:
+ __print_hex(__entry->ihdr_raw,
+ sizeof(struct xe_cper_sec_intel_err_hdr)),

-:126: CHECK:PARENTHESIS_ALIGNMENT: Alignment should match open parenthesis #126: FILE: drivers/gpu/drm/xe/xe_trace_cper.h:56:
+ __print_hex(__get_dynamic_array(cper),
+ __entry->cper_len))

-:134: CHECK:SPACING: spaces preferred around that '/' (ctx:VxV) #134: FILE: drivers/gpu/drm/xe/xe_trace_cper.h:64:
+#define TRACE_INCLUDE_PATH ../../drivers/gpu/drm/xe

                              ^

-:134: CHECK:SPACING: spaces preferred around that '/' (ctx:VxV) #134: FILE: drivers/gpu/drm/xe/xe_trace_cper.h:64:
+#define TRACE_INCLUDE_PATH ../../drivers/gpu/drm/xe

                                 ^

-:134: CHECK:SPACING: spaces preferred around that '/' (ctx:VxV) #134: FILE: drivers/gpu/drm/xe/xe_trace_cper.h:64:
+#define TRACE_INCLUDE_PATH ../../drivers/gpu/drm/xe

                                         ^

-:134: CHECK:SPACING: spaces preferred around that '/' (ctx:VxV) #134: FILE: drivers/gpu/drm/xe/xe_trace_cper.h:64:
+#define TRACE_INCLUDE_PATH ../../drivers/gpu/drm/xe

                                             ^

-:134: CHECK:SPACING: spaces preferred around that '/' (ctx:VxV) #134: FILE: drivers/gpu/drm/xe/xe_trace_cper.h:64:
+#define TRACE_INCLUDE_PATH ../../drivers/gpu/drm/xe

                                                 ^

total: 0 errors, 1 warnings, 11 checks, 100 lines checked 3c8ecb566740 drm/xe/xe_ras: Report device memory errors using SIGID 6067cb1a946c drm/xe/xe_ras: Report core compute errors using SIGID 18e5eebfeb22 drm/xe/xe_ras: Report soc internal errors using SIGID be9d02e26570 drm/xe/xe_ras: Report correctable errors using SIGID

#45 lore raw

✓ CI.KUnit: success for Add CPER logging support for CRI (rev4)

In reply to Badal Nilawar
== Series Details ==

== Series Details ==

Series: Add CPER logging support for CRI (rev4)
URL : https://patchwork.freedesktop.org/series/169692/
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
[10:54:08] Configuring KUnit Kernel ...
Generating .config ...
Populating config with:

$ make ARCH=um O=.kunit olddefconfig
[10:54:12] 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
[10:54:32] Starting KUnit Kernel (1/1)...
[10:54:32] ============================================================
Running tests with:
$ .kunit/linux kunit.enable=1 mem=1G console=tty kunit_shutdown=halt
[10:54:33] ================= gpu_buddy (14 subtests) ==================
[10:54:33] [PASSED] gpu_test_buddy_alloc_limit
[10:54:33] [PASSED] gpu_test_buddy_alloc_optimistic
[10:54:33] [PASSED] gpu_test_buddy_alloc_pessimistic
[10:54:33] [PASSED] gpu_test_buddy_alloc_pathological
[10:54:33] [PASSED] gpu_test_buddy_alloc_contiguous
[10:54:33] [PASSED] gpu_test_buddy_alloc_clear
[10:54:33] [PASSED] gpu_test_buddy_alloc_range
[10:54:33] [PASSED] gpu_test_buddy_alloc_range_bias
[10:54:34] [PASSED] gpu_test_buddy_fragmentation_performance
[10:54:34] [PASSED] gpu_test_buddy_dirty_tracker_performance
[10:54:34] [PASSED] gpu_test_buddy_alloc_exceeds_max_order
[10:54:34] [PASSED] gpu_test_buddy_offset_aligned_allocation
[10:54:34] [PASSED] gpu_test_buddy_subtree_offset_alignment_stress
[10:54:34] [PASSED] gpu_test_buddy_addr_to_block
[10:54:34] ==================== [PASSED] gpu_buddy ====================
[10:54:34] ============================================================
[10:54:34] Testing complete. Ran 14 tests: passed: 14
[10:54:34] Elapsed time: 26.827s total, 4.456s configuring, 20.504s building, 1.821s 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 [10:54:34] Configuring KUnit Kernel ...
Regenerating .config ...
Populating config with:

$ make ARCH=um O=.kunit olddefconfig
[10:54:36] 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
[10:55:10] Starting KUnit Kernel (1/1)...
[10:55:10] ============================================================
Running tests with:
$ .kunit/linux kunit.enable=1 mem=1G console=tty kunit_shutdown=halt
[10:55:10] ================== guc_buf (11 subtests) ===================
[10:55:10] [PASSED] test_smallest
[10:55:10] [PASSED] test_largest
[10:55:11] [PASSED] test_granular
[10:55:11] [PASSED] test_unique
[10:55:11] [PASSED] test_overlap
[10:55:11] [PASSED] test_reusable
[10:55:11] [PASSED] test_too_big
[10:55:11] [PASSED] test_flush
[10:55:11] [PASSED] test_lookup
[10:55:11] [PASSED] test_data
[10:55:11] [PASSED] test_class
[10:55:11] ===================== [PASSED] guc_buf =====================
[10:55:11] =================== guc_dbm (7 subtests) ===================
[10:55:11] [PASSED] test_empty
[10:55:11] [PASSED] test_default
[10:55:11] ======================== test_size  ========================
[10:55:11] [PASSED] 4
[10:55:11] [PASSED] 8
[10:55:11] [PASSED] 32
[10:55:11] [PASSED] 256
[10:55:11] ==================== [PASSED] test_size ====================
[10:55:11] ======================= test_reuse  ========================
[10:55:11] [PASSED] 4
[10:55:11] [PASSED] 8
[10:55:11] [PASSED] 32
[10:55:11] [PASSED] 256
[10:55:11] =================== [PASSED] test_reuse ====================
[10:55:11] =================== test_range_overlap  ====================
[10:55:11] [PASSED] 4
[10:55:11] [PASSED] 8
[10:55:11] [PASSED] 32
[10:55:11] [PASSED] 256
[10:55:11] =============== [PASSED] test_range_overlap ================
[10:55:11] =================== test_range_compact  ====================
[10:55:11] [PASSED] 4
[10:55:11] [PASSED] 8
[10:55:11] [PASSED] 32
[10:55:11] [PASSED] 256
[10:55:11] =============== [PASSED] test_range_compact ================
[10:55:11] ==================== test_range_spare  =====================
[10:55:11] [PASSED] 4
[10:55:11] [PASSED] 8
[10:55:11] [PASSED] 32
[10:55:11] [PASSED] 256
[10:55:11] ================ [PASSED] test_range_spare =================
[10:55:11] ===================== [PASSED] guc_dbm =====================
[10:55:11] =================== guc_idm (6 subtests) ===================
[10:55:11] [PASSED] bad_init
[10:55:11] [PASSED] no_init
[10:55:11] [PASSED] init_fini
[10:55:11] [PASSED] check_used
[10:55:11] [PASSED] check_quota
[10:55:11] [PASSED] check_all
[10:55:11] ===================== [PASSED] guc_idm =====================
[10:55:11] ============== guc_klv_helpers (13 subtests) ===============
[10:55:11] [PASSED] test_count
[10:55:11] [PASSED] test_encode_u32
[10:55:11] [PASSED] test_encode_u64
[10:55:11] [PASSED] test_encode_string
[10:55:11] [PASSED] test_encode_object_raw
[10:55:11] [PASSED] test_encode_object_klv
[10:55:11] [PASSED] test_encode_object_nested
[10:55:11] [PASSED] test_encode_object_basic
[10:55:11] ===================== test_decode_u16  =====================
[10:55:11] [PASSED] empty
[10:55:11] [PASSED] valid
[10:55:11] [PASSED] max
[10:55:11] [PASSED] big
[10:55:11] [PASSED] long
[10:55:11] ================= [PASSED] test_decode_u16 =================
[10:55:11] ===================== test_decode_u32  =====================
[10:55:11] [PASSED] empty
[10:55:11] [PASSED] valid
[10:55:11] [PASSED] max
[10:55:11] [PASSED] long
[10:55:11] ================= [PASSED] test_decode_u32 =================
[10:55:11] ===================== test_decode_u64  =====================
[10:55:11] [PASSED] empty
[10:55:11] [PASSED] short
[10:55:11] [PASSED] valid
[10:55:11] [PASSED] max
[10:55:11] [PASSED] long
[10:55:11] ================= [PASSED] test_decode_u64 =================
[10:55:11] ===================== test_decode_str  =====================
[10:55:11] [PASSED] empty
[10:55:11] [PASSED] one
[10:55:11] [PASSED] one_trash
[10:55:11] [PASSED] two
[10:55:11] [PASSED] two_trash
[10:55:11] [PASSED] three
[10:55:11] [PASSED] dword
[10:55:11] [PASSED] four
[10:55:11] [PASSED] five
[10:55:11] [PASSED] six
[10:55:11] [PASSED] seven
[10:55:11] [PASSED] qword
[10:55:11] ================= [PASSED] test_decode_str =================
[10:55:11] [PASSED] test_print
[10:55:11] ================= [PASSED] guc_klv_helpers =================
[10:55:11] =================== xe_log (4 subtests) ====================
[10:55:11] [PASSED] demo_cper
[10:55:11] [PASSED] demo_dmesg
[10:55:11] ======================= test_dmesg  ========================
[10:55:11] [PASSED] test_fatal
[10:55:11] [PASSED] test_fatal_tile
[10:55:11] [PASSED] test_fatal_gt
[10:55:11] [PASSED] test_fatal_comp
[10:55:11] [PASSED] test_fatal_comp_tile
[10:55:11] [PASSED] test_fatal_comp_gt
[10:55:11] [PASSED] test_fatal_all
[10:55:11] [PASSED] test_recoverable
[10:55:11] [PASSED] test_recoverable_tile
[10:55:11] [PASSED] test_recoverable_gt
[10:55:11] [PASSED] test_recoverable_comp
[10:55:11] [PASSED] test_recoverable_comp_tile
[10:55:11] [PASSED] test_recoverable_comp_gt
[10:55:11] [PASSED] test_recoverable_all
[10:55:11] [PASSED] test_info
[10:55:11] [PASSED] test_info_tile
[10:55:11] [PASSED] test_info_gt
[10:55:11] [PASSED] test_info_err
[10:55:11] [PASSED] test_info_comp
[10:55:11] [PASSED] test_info_comp_tile
[10:55:11] [PASSED] test_info_comp_gt
[10:55:11] [PASSED] test_info_all
[10:55:11] [PASSED] test_hw_fatal
[10:55:11] [PASSED] test_hw_recoverable
[10:55:11] [PASSED] test_hw_corrected
[10:55:11] [PASSED] test_hw_informational
[10:55:11] =================== [PASSED] test_dmesg ====================
[10:55:11] ====================== test_invalid  =======================
[10:55:11] [SKIPPED] no-component no-location no-warn (requires CONFIG_DRM_XE_DEBUG)
[10:55:11] [SKIPPED] reserved location (requires CONFIG_DRM_XE_DEBUG)
[10:55:11] [SKIPPED] unknown location (requires CONFIG_DRM_XE_DEBUG)
[10:55:11] [SKIPPED] nonzero-device-id location (requires CONFIG_DRM_XE_DEBUG)
[10:55:11] [SKIPPED] invalid-tile-id location (requires CONFIG_DRM_XE_DEBUG)
[10:55:11] [SKIPPED] invalid-gt-id location (requires CONFIG_DRM_XE_DEBUG)
[10:55:11] [SKIPPED] unknown component class (requires CONFIG_DRM_XE_DEBUG)
[10:55:11] [SKIPPED] unknown system component (requires CONFIG_DRM_XE_DEBUG)
[10:55:11] [SKIPPED] unknown hardware component (requires CONFIG_DRM_XE_DEBUG)
[10:55:11] [SKIPPED] unknown component and location (requires CONFIG_DRM_XE_DEBUG)
[10:55:11] ================== [SKIPPED] test_invalid ==================
[10:55:11] ===================== [PASSED] xe_log ======================
[10:55:11] ================== no_relay (3 subtests) ===================
[10:55:11] [PASSED] xe_drops_guc2pf_if_not_ready
[10:55:11] [PASSED] xe_drops_guc2vf_if_not_ready
[10:55:11] [PASSED] xe_rejects_send_if_not_ready
[10:55:11] ==================== [PASSED] no_relay =====================
[10:55:11] ================== pf_relay (14 subtests) ==================
[10:55:11] [PASSED] pf_rejects_guc2pf_too_short
[10:55:11] [PASSED] pf_rejects_guc2pf_too_long
[10:55:11] [PASSED] pf_rejects_guc2pf_no_payload
[10:55:11] [PASSED] pf_fails_no_payload
[10:55:11] [PASSED] pf_fails_bad_origin
[10:55:11] [PASSED] pf_fails_bad_type
[10:55:11] [PASSED] pf_txn_reports_error
[10:55:11] [PASSED] pf_txn_sends_pf2guc
[10:55:11] [PASSED] pf_sends_pf2guc
[10:55:11] [SKIPPED] pf_loopback_nop (requires CONFIG_DRM_XE_DEBUG_SRIOV)
[10:55:11] [SKIPPED] pf_loopback_echo (requires CONFIG_DRM_XE_DEBUG_SRIOV)
[10:55:11] [SKIPPED] pf_loopback_fail (requires CONFIG_DRM_XE_DEBUG_SRIOV)
[10:55:11] [SKIPPED] pf_loopback_busy (requires CONFIG_DRM_XE_DEBUG_SRIOV)
[10:55:11] [SKIPPED] pf_loopback_retry (requires CONFIG_DRM_XE_DEBUG_SRIOV)
[10:55:11] ==================== [PASSED] pf_relay =====================
[10:55:11] ================== vf_relay (3 subtests) ===================
[10:55:11] [PASSED] vf_rejects_guc2vf_too_short
[10:55:11] [PASSED] vf_rejects_guc2vf_too_long
[10:55:11] [PASSED] vf_rejects_guc2vf_no_payload
[10:55:11] ==================== [PASSED] vf_relay =====================
[10:55:11] ================ pf_gt_config (9 subtests) =================
[10:55:11] [PASSED] fair_contexts_1vf
[10:55:11] [PASSED] fair_doorbells_1vf
[10:55:11] [PASSED] fair_ggtt_1vf
[10:55:11] ====================== fair_vram_1vf  ======================
[10:55:11] [PASSED] 3.50 GiB
[10:55:11] [PASSED] 11.5 GiB
[10:55:11] [PASSED] 15.5 GiB
[10:55:11] [PASSED] 31.5 GiB
[10:55:11] [PASSED] 63.5 GiB
[10:55:11] [PASSED] 1.91 GiB
[10:55:11] ================== [PASSED] fair_vram_1vf ==================
[10:55:11] ================ fair_vram_1vf_admin_only  =================
[10:55:11] [PASSED] 3.50 GiB
[10:55:11] [PASSED] 11.5 GiB
[10:55:11] [PASSED] 15.5 GiB
[10:55:11] [PASSED] 31.5 GiB
[10:55:11] [PASSED] 63.5 GiB
[10:55:11] [PASSED] 1.91 GiB
[10:55:11] ============ [PASSED] fair_vram_1vf_admin_only =============
[10:55:11] ====================== fair_contexts  ======================
[10:55:11] [PASSED] 1 VF
[10:55:11] [PASSED] 2 VFs
[10:55:11] [PASSED] 3 VFs
[10:55:11] [PASSED] 4 VFs
[10:55:11] [PASSED] 5 VFs
[10:55:11] [PASSED] 6 VFs
[10:55:11] [PASSED] 7 VFs
[10:55:11] [PASSED] 8 VFs
[10:55:11] [PASSED] 9 VFs
[10:55:11] [PASSED] 10 VFs
[10:55:11] [PASSED] 11 VFs
[10:55:11] [PASSED] 12 VFs
[10:55:11] [PASSED] 13 VFs
[10:55:11] [PASSED] 14 VFs
[10:55:11] [PASSED] 15 VFs
[10:55:11] [PASSED] 16 VFs
[10:55:11] [PASSED] 17 VFs
[10:55:11] [PASSED] 18 VFs
[10:55:11] [PASSED] 19 VFs
[10:55:11] [PASSED] 20 VFs
[10:55:11] [PASSED] 21 VFs
[10:55:11] [PASSED] 22 VFs
[10:55:11] [PASSED] 23 VFs
[10:55:11] [PASSED] 24 VFs
[10:55:11] [PASSED] 25 VFs
[10:55:11] [PASSED] 26 VFs
[10:55:11] [PASSED] 27 VFs
[10:55:11] [PASSED] 28 VFs
[10:55:11] [PASSED] 29 VFs
[10:55:11] [PASSED] 30 VFs
[10:55:11] [PASSED] 31 VFs
[10:55:11] [PASSED] 32 VFs
[10:55:11] [PASSED] 33 VFs
[10:55:11] [PASSED] 34 VFs
[10:55:11] [PASSED] 35 VFs
[10:55:11] [PASSED] 36 VFs
[10:55:11] [PASSED] 37 VFs
[10:55:11] [PASSED] 38 VFs
[10:55:11] [PASSED] 39 VFs
[10:55:11] [PASSED] 40 VFs
[10:55:11] [PASSED] 41 VFs
[10:55:11] [PASSED] 42 VFs
[10:55:11] [PASSED] 43 VFs
[10:55:11] [PASSED] 44 VFs
[10:55:11] [PASSED] 45 VFs
[10:55:11] [PASSED] 46 VFs
[10:55:11] [PASSED] 47 VFs
[10:55:11] [PASSED] 48 VFs
[10:55:11] [PASSED] 49 VFs
[10:55:11] [PASSED] 50 VFs
[10:55:11] [PASSED] 51 VFs
[10:55:11] [PASSED] 52 VFs
[10:55:11] [PASSED] 53 VFs
[10:55:11] [PASSED] 54 VFs
[10:55:11] [PASSED] 55 VFs
[10:55:11] [PASSED] 56 VFs
[10:55:11] [PASSED] 57 VFs
[10:55:11] [PASSED] 58 VFs
[10:55:11] [PASSED] 59 VFs
[10:55:11] [PASSED] 60 VFs
[10:55:11] [PASSED] 61 VFs
[10:55:11] [PASSED] 62 VFs
[10:55:11] [PASSED] 63 VFs
[10:55:11] ================== [PASSED] fair_contexts ==================
[10:55:11] ===================== fair_doorbells  ======================
[10:55:11] [PASSED] 1 VF
[10:55:11] [PASSED] 2 VFs
[10:55:11] [PASSED] 3 VFs
[10:55:11] [PASSED] 4 VFs
[10:55:11] [PASSED] 5 VFs
[10:55:11] [PASSED] 6 VFs
[10:55:11] [PASSED] 7 VFs
[10:55:11] [PASSED] 8 VFs
[10:55:11] [PASSED] 9 VFs
[10:55:11] [PASSED] 10 VFs
[10:55:11] [PASSED] 11 VFs
[10:55:11] [PASSED] 12 VFs
[10:55:11] [PASSED] 13 VFs
[10:55:11] [PASSED] 14 VFs
[10:55:11] [PASSED] 15 VFs
[10:55:11] [PASSED] 16 VFs
[10:55:11] [PASSED] 17 VFs
[10:55:11] [PASSED] 18 VFs
[10:55:11] [PASSED] 19 VFs
[10:55:11] [PASSED] 20 VFs
[10:55:11] [PASSED] 21 VFs
[10:55:11] [PASSED] 22 VFs
[10:55:11] [PASSED] 23 VFs
[10:55:11] [PASSED] 24 VFs
[10:55:11] [PASSED] 25 VFs
[10:55:11] [PASSED] 26 VFs
[10:55:11] [PASSED] 27 VFs
[10:55:11] [PASSED] 28 VFs
[10:55:11] [PASSED] 29 VFs
[10:55:11] [PASSED] 30 VFs
[10:55:11] [PASSED] 31 VFs
[10:55:11] [PASSED] 32 VFs
[10:55:11] [PASSED] 33 VFs
[10:55:11] [PASSED] 34 VFs
[10:55:11] [PASSED] 35 VFs
[10:55:11] [PASSED] 36 VFs
[10:55:11] [PASSED] 37 VFs
[10:55:11] [PASSED] 38 VFs
[10:55:11] [PASSED] 39 VFs
[10:55:11] [PASSED] 40 VFs
[10:55:11] [PASSED] 41 VFs
[10:55:11] [PASSED] 42 VFs
[10:55:11] [PASSED] 43 VFs
[10:55:11] [PASSED] 44 VFs
[10:55:11] [PASSED] 45 VFs
[10:55:11] [PASSED] 46 VFs
[10:55:11] [PASSED] 47 VFs
[10:55:11] [PASSED] 48 VFs
[10:55:11] [PASSED] 49 VFs
[10:55:11] [PASSED] 50 VFs
[10:55:11] [PASSED] 51 VFs
[10:55:11] [PASSED] 52 VFs
[10:55:11] [PASSED] 53 VFs
[10:55:11] [PASSED] 54 VFs
[10:55:11] [PASSED] 55 VFs
[10:55:11] [PASSED] 56 VFs
[10:55:11] [PASSED] 57 VFs
[10:55:11] [PASSED] 58 VFs
[10:55:11] [PASSED] 59 VFs
[10:55:11] [PASSED] 60 VFs
[10:55:11] [PASSED] 61 VFs
[10:55:11] [PASSED] 62 VFs
[10:55:11] [PASSED] 63 VFs
[10:55:11] ================= [PASSED] fair_doorbells ==================
[10:55:11] ======================== fair_ggtt  ========================
[10:55:11] [PASSED] 1 VF
[10:55:11] [PASSED] 2 VFs
[10:55:11] [PASSED] 3 VFs
[10:55:11] [PASSED] 4 VFs
[10:55:11] [PASSED] 5 VFs
[10:55:11] [PASSED] 6 VFs
[10:55:11] [PASSED] 7 VFs
[10:55:11] [PASSED] 8 VFs
[10:55:11] [PASSED] 9 VFs
[10:55:11] [PASSED] 10 VFs
[10:55:11] [PASSED] 11 VFs
[10:55:11] [PASSED] 12 VFs
[10:55:11] [PASSED] 13 VFs
[10:55:11] [PASSED] 14 VFs
[10:55:11] [PASSED] 15 VFs
[10:55:11] [PASSED] 16 VFs
[10:55:11] [PASSED] 17 VFs
[10:55:11] [PASSED] 18 VFs
[10:55:11] [PASSED] 19 VFs
[10:55:11] [PASSED] 20 VFs
[10:55:11] [PASSED] 21 VFs
[10:55:11] [PASSED] 22 VFs
[10:55:11] [PASSED] 23 VFs
[10:55:11] [PASSED] 24 VFs
[10:55:11] [PASSED] 25 VFs
[10:55:11] [PASSED] 26 VFs
[10:55:11] [PASSED] 27 VFs
[10:55:11] [PASSED] 28 VFs
[10:55:11] [PASSED] 29 VFs
[10:55:11] [PASSED] 30 VFs
[10:55:11] [PASSED] 31 VFs
[10:55:11] [PASSED] 32 VFs
[10:55:11] [PASSED] 33 VFs
[10:55:11] [PASSED] 34 VFs
[10:55:11] [PASSED] 35 VFs
[10:55:11] [PASSED] 36 VFs
[10:55:11] [PASSED] 37 VFs
[10:55:11] [PASSED] 38 VFs
[10:55:11] [PASSED] 39 VFs
[10:55:11] [PASSED] 40 VFs
[10:55:11] [PASSED] 41 VFs
[10:55:11] [PASSED] 42 VFs
[10:55:11] [PASSED] 43 VFs
[10:55:11] [PASSED] 44 VFs
[10:55:11] [PASSED] 45 VFs
[10:55:11] [PASSED] 46 VFs
[10:55:11] [PASSED] 47 VFs
[10:55:11] [PASSED] 48 VFs
[10:55:11] [PASSED] 49 VFs
[10:55:11] [PASSED] 50 VFs
[10:55:11] [PASSED] 51 VFs
[10:55:11] [PASSED] 52 VFs
[10:55:11] [PASSED] 53 VFs
[10:55:11] [PASSED] 54 VFs
[10:55:11] [PASSED] 55 VFs
[10:55:11] [PASSED] 56 VFs
[10:55:11] [PASSED] 57 VFs
[10:55:11] [PASSED] 58 VFs
[10:55:11] [PASSED] 59 VFs
[10:55:11] [PASSED] 60 VFs
[10:55:11] [PASSED] 61 VFs
[10:55:11] [PASSED] 62 VFs
[10:55:11] [PASSED] 63 VFs
[10:55:11] ==================== [PASSED] fair_ggtt ====================
[10:55:11] ======================== fair_vram  ========================
[10:55:11] [PASSED] 1 VF
[10:55:11] [PASSED] 2 VFs
[10:55:11] [PASSED] 3 VFs
[10:55:11] [PASSED] 4 VFs
[10:55:11] [PASSED] 5 VFs
[10:55:11] [PASSED] 6 VFs
[10:55:11] [PASSED] 7 VFs
[10:55:11] [PASSED] 8 VFs
[10:55:11] [PASSED] 9 VFs
[10:55:11] [PASSED] 10 VFs
[10:55:11] [PASSED] 11 VFs
[10:55:11] [PASSED] 12 VFs
[10:55:11] [PASSED] 13 VFs
[10:55:11] [PASSED] 14 VFs
[10:55:11] [PASSED] 15 VFs
[10:55:11] [PASSED] 16 VFs
[10:55:11] [PASSED] 17 VFs
[10:55:11] [PASSED] 18 VFs
[10:55:11] [PASSED] 19 VFs
[10:55:11] [PASSED] 20 VFs
[10:55:11] [PASSED] 21 VFs
[10:55:11] [PASSED] 22 VFs
[10:55:11] [PASSED] 23 VFs
[10:55:11] [PASSED] 24 VFs
[10:55:11] [PASSED] 25 VFs
[10:55:11] [PASSED] 26 VFs
[10:55:11] [PASSED] 27 VFs
[10:55:11] [PASSED] 28 VFs
[10:55:11] [PASSED] 29 VFs
[10:55:11] [PASSED] 30 VFs
[10:55:11] [PASSED] 31 VFs
[10:55:11] [PASSED] 32 VFs
[10:55:11] [PASSED] 33 VFs
[10:55:11] [PASSED] 34 VFs
[10:55:11] [PASSED] 35 VFs
[10:55:11] [PASSED] 36 VFs
[10:55:11] [PASSED] 37 VFs
[10:55:11] [PASSED] 38 VFs
[10:55:11] [PASSED] 39 VFs
[10:55:11] [PASSED] 40 VFs
[10:55:11] [PASSED] 41 VFs
[10:55:11] [PASSED] 42 VFs
[10:55:11] [PASSED] 43 VFs
[10:55:11] [PASSED] 44 VFs
[10:55:11] [PASSED] 45 VFs
[10:55:11] [PASSED] 46 VFs
[10:55:11] [PASSED] 47 VFs
[10:55:11] [PASSED] 48 VFs
[10:55:11] [PASSED] 49 VFs
[10:55:11] [PASSED] 50 VFs
[10:55:11] [PASSED] 51 VFs
[10:55:11] [PASSED] 52 VFs
[10:55:11] [PASSED] 53 VFs
[10:55:11] [PASSED] 54 VFs
[10:55:11] [PASSED] 55 VFs
[10:55:11] [PASSED] 56 VFs
[10:55:11] [PASSED] 57 VFs
[10:55:11] [PASSED] 58 VFs
[10:55:11] [PASSED] 59 VFs
[10:55:11] [PASSED] 60 VFs
[10:55:11] [PASSED] 61 VFs
[10:55:11] [PASSED] 62 VFs
[10:55:11] [PASSED] 63 VFs
[10:55:11] ==================== [PASSED] fair_vram ====================
[10:55:11] ================== [PASSED] pf_gt_config ===================
[10:55:11] ===================== lmtt (1 subtest) =====================
[10:55:11] ======================== test_ops  =========================
[10:55:11] [PASSED] 2-level
[10:55:11] [PASSED] multi-level
[10:55:11] ==================== [PASSED] test_ops =====================
[10:55:11] ====================== [PASSED] lmtt =======================
[10:55:11] ================= sriov_packet (1 subtest) =================
[10:55:11] [PASSED] test_descriptor_init
[10:55:11] ================== [PASSED] sriov_packet ===================
[10:55:11] ================= pf_service (11 subtests) =================
[10:55:11] [PASSED] pf_negotiate_any
[10:55:11] [PASSED] pf_negotiate_base_match
[10:55:11] [PASSED] pf_negotiate_base_newer
[10:55:11] [PASSED] pf_negotiate_base_next
[10:55:11] [SKIPPED] pf_negotiate_base_older (no older minor)
[10:55:11] [PASSED] pf_negotiate_base_prev
[10:55:11] [PASSED] pf_negotiate_latest_match
[10:55:11] [PASSED] pf_negotiate_latest_newer
[10:55:11] [PASSED] pf_negotiate_latest_next
[10:55:11] [SKIPPED] pf_negotiate_latest_older (no older minor)
[10:55:11] [SKIPPED] pf_negotiate_latest_prev (no prev major)
[10:55:11] =================== [PASSED] pf_service ====================
[10:55:11] ================= xe_guc_g2g (2 subtests) ==================
[10:55:11] ============== xe_live_guc_g2g_kunit_default  ==============
[10:55:11] ========= [SKIPPED] xe_live_guc_g2g_kunit_default ==========
[10:55:11] ============== xe_live_guc_g2g_kunit_allmem  ===============
[10:55:11] ========== [SKIPPED] xe_live_guc_g2g_kunit_allmem ==========
[10:55:11] =================== [SKIPPED] xe_guc_g2g ===================
[10:55:11] =================== xe_mocs (2 subtests) ===================
[10:55:11] ================ xe_live_mocs_kernel_kunit  ================
[10:55:11] =========== [SKIPPED] xe_live_mocs_kernel_kunit ============
[10:55:11] ================ xe_live_mocs_reset_kunit  =================
[10:55:11] ============ [SKIPPED] xe_live_mocs_reset_kunit ============
[10:55:11] ==================== [SKIPPED] xe_mocs =====================
[10:55:11] ================= xe_migrate (2 subtests) ==================
[10:55:11] ================= xe_migrate_sanity_kunit  =================
[10:55:11] ============ [SKIPPED] xe_migrate_sanity_kunit =============
[10:55:11] ================== xe_validate_ccs_kunit  ==================
[10:55:11] ============= [SKIPPED] xe_validate_ccs_kunit ==============
[10:55:11] =================== [SKIPPED] xe_migrate ===================
[10:55:11] ================== xe_dma_buf (1 subtest) ==================
[10:55:11] ==================== xe_dma_buf_kunit  =====================
[10:55:11] ================ [SKIPPED] xe_dma_buf_kunit ================
[10:55:11] =================== [SKIPPED] xe_dma_buf ===================
[10:55:11] ================= xe_bo_shrink (1 subtest) =================
[10:55:11] =================== xe_bo_shrink_kunit  ====================
[10:55:11] =============== [SKIPPED] xe_bo_shrink_kunit ===============
[10:55:11] ================== [SKIPPED] xe_bo_shrink ==================
[10:55:11] ==================== xe_bo (2 subtests) ====================
[10:55:11] ================== xe_ccs_migrate_kunit  ===================
[10:55:11] ============== [SKIPPED] xe_ccs_migrate_kunit ==============
[10:55:11] ==================== xe_bo_evict_kunit  ====================
[10:55:11] =============== [SKIPPED] xe_bo_evict_kunit ================
[10:55:11] ===================== [SKIPPED] xe_bo ======================
[10:55:11] =================== xe_any (9 subtests) ====================
[10:55:11] [PASSED] test_to_xe
[10:55:11] [PASSED] test_to_dev
[10:55:11] [PASSED] test_to_pdev
[10:55:11] [PASSED] test_to_drm
[10:55:11] [PASSED] test_if_pdev
[10:55:11] [PASSED] test_if_xe
[10:55:11] [PASSED] test_if_tile
[10:55:11] [PASSED] test_if_gt
[10:55:11] [PASSED] test_to_id
[10:55:11] ===================== [PASSED] xe_any ======================
[10:55:11] ==================== args (13 subtests) ====================
[10:55:11] [PASSED] count_args_test
[10:55:11] [PASSED] call_args_example
[10:55:11] [PASSED] call_args_test
[10:55:11] [PASSED] drop_first_arg_example
[10:55:11] [PASSED] drop_first_arg_test
[10:55:11] [PASSED] first_arg_example
[10:55:11] [PASSED] first_arg_test
[10:55:11] [PASSED] last_arg_example
[10:55:11] [PASSED] last_arg_test
[10:55:11] [PASSED] pick_arg_example
[10:55:11] [PASSED] if_args_example
[10:55:11] [PASSED] if_args_test
[10:55:11] [PASSED] sep_comma_example
[10:55:11] ====================== [PASSED] args =======================
[10:55:11] =================== xe_pci (3 subtests) ====================
[10:55:11] ==================== check_graphics_ip  ====================
[10:55:11] [PASSED] 12.00 Xe_LP
[10:55:11] [PASSED] 12.10 Xe_LP+
[10:55:11] [PASSED] 12.55 Xe_HPG
[10:55:11] [PASSED] 12.60 Xe_HPC
[10:55:11] [PASSED] 12.70 Xe_LPG
[10:55:11] [PASSED] 12.71 Xe_LPG
[10:55:11] [PASSED] 12.74 Xe_LPG+
[10:55:11] [PASSED] 20.01 Xe2_HPG
[10:55:11] [PASSED] 20.02 Xe2_HPG
[10:55:11] [PASSED] 20.04 Xe2_LPG
[10:55:11] [PASSED] 30.00 Xe3_LPG
[10:55:11] [PASSED] 30.01 Xe3_LPG
[10:55:11] [PASSED] 30.03 Xe3_LPG
[10:55:11] [PASSED] 30.04 Xe3_LPG
[10:55:11] [PASSED] 30.05 Xe3_LPG
[10:55:11] [PASSED] 35.10 Xe3p_LPG
[10:55:11] [PASSED] 35.11 Xe3p_XPC
[10:55:11] ================ [PASSED] check_graphics_ip ================
[10:55:11] ===================== check_media_ip  ======================
[10:55:11] [PASSED] 12.00 Xe_M
[10:55:11] [PASSED] 12.55 Xe_HPM
[10:55:11] [PASSED] 13.00 Xe_LPM+
[10:55:11] [PASSED] 13.01 Xe2_HPM
[10:55:11] [PASSED] 20.00 Xe2_LPM
[10:55:11] [PASSED] 30.00 Xe3_LPM
[10:55:11] [PASSED] 30.02 Xe3_LPM
[10:55:11] [PASSED] 35.00 Xe3p_LPM
[10:55:11] [PASSED] 35.03 Xe3p_HPM
[10:55:11] ================= [PASSED] check_media_ip ==================
[10:55:11] =================== check_platform_desc  ===================
[10:55:11] [PASSED] 0x9A60 (TIGERLAKE)
[10:55:11] [PASSED] 0x9A68 (TIGERLAKE)
[10:55:11] [PASSED] 0x9A70 (TIGERLAKE)
[10:55:11] [PASSED] 0x9A40 (TIGERLAKE)
[10:55:11] [PASSED] 0x9A49 (TIGERLAKE)
[10:55:11] [PASSED] 0x9A59 (TIGERLAKE)
[10:55:11] [PASSED] 0x9A78 (TIGERLAKE)
[10:55:11] [PASSED] 0x9AC0 (TIGERLAKE)
[10:55:11] [PASSED] 0x9AC9 (TIGERLAKE)
[10:55:11] [PASSED] 0x9AD9 (TIGERLAKE)
[10:55:11] [PASSED] 0x9AF8 (TIGERLAKE)
[10:55:11] [PASSED] 0x4C80 (ROCKETLAKE)
[10:55:11] [PASSED] 0x4C8A (ROCKETLAKE)
[10:55:11] [PASSED] 0x4C8B (ROCKETLAKE)
[10:55:11] [PASSED] 0x4C8C (ROCKETLAKE)
[10:55:11] [PASSED] 0x4C90 (ROCKETLAKE)
[10:55:11] [PASSED] 0x4C9A (ROCKETLAKE)
[10:55:11] [PASSED] 0x4680 (ALDERLAKE_S)
[10:55:11] [PASSED] 0x4682 (ALDERLAKE_S)
[10:55:11] [PASSED] 0x4688 (ALDERLAKE_S)
[10:55:11] [PASSED] 0x468A (ALDERLAKE_S)
[10:55:11] [PASSED] 0x468B (ALDERLAKE_S)
[10:55:11] [PASSED] 0x4690 (ALDERLAKE_S)
[10:55:11] [PASSED] 0x4692 (ALDERLAKE_S)
[10:55:11] [PASSED] 0x4693 (ALDERLAKE_S)
[10:55:11] [PASSED] 0x46A0 (ALDERLAKE_P)
[10:55:11] [PASSED] 0x46A1 (ALDERLAKE_P)
[10:55:11] [PASSED] 0x46A2 (ALDERLAKE_P)
[10:55:11] [PASSED] 0x46A3 (ALDERLAKE_P)
[10:55:11] [PASSED] 0x46A6 (ALDERLAKE_P)
[10:55:11] [PASSED] 0x46A8 (ALDERLAKE_P)
[10:55:11] [PASSED] 0x46AA (ALDERLAKE_P)
[10:55:11] [PASSED] 0x462A (ALDERLAKE_P)
[10:55:11] [PASSED] 0x4626 (ALDERLAKE_P)
[10:55:11] [PASSED] 0x4628 (ALDERLAKE_P)
[10:55:11] [PASSED] 0x46B0 (ALDERLAKE_P)
[10:55:11] [PASSED] 0x46B1 (ALDERLAKE_P)
[10:55:11] [PASSED] 0x46B2 (ALDERLAKE_P)
[10:55:11] [PASSED] 0x46B3 (ALDERLAKE_P)
[10:55:11] [PASSED] 0x46C0 (ALDERLAKE_P)
[10:55:11] [PASSED] 0x46C1 (ALDERLAKE_P)
[10:55:11] [PASSED] 0x46C2 (ALDERLAKE_P)
[10:55:11] [PASSED] 0x46C3 (ALDERLAKE_P)
[10:55:11] [PASSED] 0x46D0 (ALDERLAKE_N)
[10:55:11] [PASSED] 0x46D1 (ALDERLAKE_N)
[10:55:11] [PASSED] 0x46D2 (ALDERLAKE_N)
[10:55:11] [PASSED] 0x46D3 (ALDERLAKE_N)
[10:55:11] [PASSED] 0x46D4 (ALDERLAKE_N)
[10:55:11] [PASSED] 0xA721 (ALDERLAKE_P)
[10:55:11] [PASSED] 0xA7A1 (ALDERLAKE_P)
[10:55:11] [PASSED] 0xA7A9 (ALDERLAKE_P)
[10:55:11] [PASSED] 0xA7AC (ALDERLAKE_P)
[10:55:11] [PASSED] 0xA7AD (ALDERLAKE_P)
[10:55:11] [PASSED] 0xA720 (ALDERLAKE_P)
[10:55:11] [PASSED] 0xA7A0 (ALDERLAKE_P)
[10:55:11] [PASSED] 0xA7A8 (ALDERLAKE_P)
[10:55:11] [PASSED] 0xA7AA (ALDERLAKE_P)
[10:55:11] [PASSED] 0xA7AB (ALDERLAKE_P)
[10:55:11] [PASSED] 0xA780 (ALDERLAKE_S)
[10:55:11] [PASSED] 0xA781 (ALDERLAKE_S)
[10:55:11] [PASSED] 0xA782 (ALDERLAKE_S)
[10:55:11] [PASSED] 0xA783 (ALDERLAKE_S)
[10:55:11] [PASSED] 0xA788 (ALDERLAKE_S)
[10:55:11] [PASSED] 0xA789 (ALDERLAKE_S)
[10:55:11] [PASSED] 0xA78A (ALDERLAKE_S)
[10:55:11] [PASSED] 0xA78B (ALDERLAKE_S)
[10:55:11] [PASSED] 0x4905 (DG1)
[10:55:11] [PASSED] 0x4906 (DG1)
[10:55:11] [PASSED] 0x4907 (DG1)
[10:55:11] [PASSED] 0x4908 (DG1)
[10:55:11] [PASSED] 0x4909 (DG1)
[10:55:11] [PASSED] 0x56C0 (DG2)
[10:55:11] [PASSED] 0x56C2 (DG2)
[10:55:11] [PASSED] 0x56C1 (DG2)
[10:55:11] [PASSED] 0x7D51 (METEORLAKE)
[10:55:11] [PASSED] 0x7DD1 (METEORLAKE)
[10:55:11] [PASSED] 0x7D41 (METEORLAKE)
[10:55:11] [PASSED] 0x7D67 (METEORLAKE)
[10:55:11] [PASSED] 0xB640 (METEORLAKE)
[10:55:11] [PASSED] 0x56A0 (DG2)
[10:55:11] [PASSED] 0x56A1 (DG2)
[10:55:11] [PASSED] 0x56A2 (DG2)
[10:55:11] [PASSED] 0x56BE (DG2)
[10:55:11] [PASSED] 0x56BF (DG2)
[10:55:11] [PASSED] 0x5690 (DG2)
[10:55:11] [PASSED] 0x5691 (DG2)
[10:55:11] [PASSED] 0x5692 (DG2)
[10:55:11] [PASSED] 0x56A5 (DG2)
[10:55:11] [PASSED] 0x56A6 (DG2)
[10:55:11] [PASSED] 0x56B0 (DG2)
[10:55:11] [PASSED] 0x56B1 (DG2)
[10:55:11] [PASSED] 0x56BA (DG2)
[10:55:11] [PASSED] 0x56BB (DG2)
[10:55:11] [PASSED] 0x56BC (DG2)
[10:55:11] [PASSED] 0x56BD (DG2)
[10:55:11] [PASSED] 0x5693 (DG2)
[10:55:11] [PASSED] 0x5694 (DG2)
[10:55:11] [PASSED] 0x5695 (DG2)
[10:55:11] [PASSED] 0x56A3 (DG2)
[10:55:11] [PASSED] 0x56A4 (DG2)
[10:55:11] [PASSED] 0x56B2 (DG2)
[10:55:11] [PASSED] 0x56B3 (DG2)
[10:55:11] [PASSED] 0x5696 (DG2)
[10:55:11] [PASSED] 0x5697 (DG2)
[10:55:11] [PASSED] 0xB69 (PVC)
[10:55:11] [PASSED] 0xB6E (PVC)
[10:55:11] [PASSED] 0xBD4 (PVC)
[10:55:11] [PASSED] 0xBD5 (PVC)
[10:55:11] [PASSED] 0xBD6 (PVC)
[10:55:11] [PASSED] 0xBD7 (PVC)
[10:55:11] [PASSED] 0xBD8 (PVC)
[10:55:11] [PASSED] 0xBD9 (PVC)
[10:55:11] [PASSED] 0xBDA (PVC)
[10:55:11] [PASSED] 0xBDB (PVC)
[10:55:11] [PASSED] 0xBE0 (PVC)
[10:55:11] [PASSED] 0xBE1 (PVC)
[10:55:11] [PASSED] 0xBE5 (PVC)
[10:55:11] [PASSED] 0x7D40 (METEORLAKE)
[10:55:11] [PASSED] 0x7D45 (METEORLAKE)
[10:55:11] [PASSED] 0x7D55 (METEORLAKE)
[10:55:11] [PASSED] 0x7D60 (METEORLAKE)
[10:55:11] [PASSED] 0x7DD5 (METEORLAKE)
[10:55:11] [PASSED] 0x6420 (LUNARLAKE)
[10:55:11] [PASSED] 0x64A0 (LUNARLAKE)
[10:55:11] [PASSED] 0x64B0 (LUNARLAKE)
[10:55:11] [PASSED] 0xE202 (BATTLEMAGE)
[10:55:11] [PASSED] 0xE209 (BATTLEMAGE)
[10:55:11] [PASSED] 0xE20B (BATTLEMAGE)
[10:55:11] [PASSED] 0xE20C (BATTLEMAGE)
[10:55:11] [PASSED] 0xE20D (BATTLEMAGE)
[10:55:11] [PASSED] 0xE210 (BATTLEMAGE)
[10:55:11] [PASSED] 0xE211 (BATTLEMAGE)
[10:55:11] [PASSED] 0xE212 (BATTLEMAGE)
[10:55:11] [PASSED] 0xE216 (BATTLEMAGE)
[10:55:11] [PASSED] 0xE220 (BATTLEMAGE)
[10:55:11] [PASSED] 0xE221 (BATTLEMAGE)
[10:55:11] [PASSED] 0xE222 (BATTLEMAGE)
[10:55:11] [PASSED] 0xE223 (BATTLEMAGE)
[10:55:11] [PASSED] 0xB080 (PANTHERLAKE)
[10:55:11] [PASSED] 0xB081 (PANTHERLAKE)
[10:55:11] [PASSED] 0xB082 (PANTHERLAKE)
[10:55:11] [PASSED] 0xB083 (PANTHERLAKE)
[10:55:11] [PASSED] 0xB084 (PANTHERLAKE)
[10:55:11] [PASSED] 0xB085 (PANTHERLAKE)
[10:55:11] [PASSED] 0xB086 (PANTHERLAKE)
[10:55:11] [PASSED] 0xB087 (PANTHERLAKE)
[10:55:11] [PASSED] 0xB08F (PANTHERLAKE)
[10:55:11] [PASSED] 0xB090 (PANTHERLAKE)
[10:55:11] [PASSED] 0xB0A0 (PANTHERLAKE)
[10:55:11] [PASSED] 0xB0A1 (PANTHERLAKE)
[10:55:11] [PASSED] 0xB0B0 (PANTHERLAKE)
[10:55:11] [PASSED] 0xFD80 (PANTHERLAKE)
[10:55:11] [PASSED] 0xFD81 (PANTHERLAKE)
[10:55:11] [PASSED] 0xD740 (NOVALAKE_S)
[10:55:11] [PASSED] 0xD741 (NOVALAKE_S)
[10:55:11] [PASSED] 0xD742 (NOVALAKE_S)
[10:55:11] [PASSED] 0xD743 (NOVALAKE_S)
[10:55:11] [PASSED] 0xD745 (NOVALAKE_S)
[10:55:11] [PASSED] 0xD74A (NOVALAKE_S)
[10:55:11] [PASSED] 0xD74B (NOVALAKE_S)
[10:55:11] [PASSED] 0x674C (CRESCENTISLAND)
[10:55:11] [PASSED] 0x674D (CRESCENTISLAND)
[10:55:11] [PASSED] 0x674E (CRESCENTISLAND)
[10:55:11] [PASSED] 0x674F (CRESCENTISLAND)
[10:55:11] [PASSED] 0x6750 (CRESCENTISLAND)
[10:55:11] [PASSED] 0x6751 (CRESCENTISLAND)
[10:55:11] [PASSED] 0xD750 (NOVALAKE_P)
[10:55:11] [PASSED] 0xD751 (NOVALAKE_P)
[10:55:11] [PASSED] 0xD752 (NOVALAKE_P)
[10:55:11] [PASSED] 0xD753 (NOVALAKE_P)
[10:55:11] [PASSED] 0xD754 (NOVALAKE_P)
[10:55:11] [PASSED] 0xD755 (NOVALAKE_P)
[10:55:11] [PASSED] 0xD756 (NOVALAKE_P)
[10:55:11] [PASSED] 0xD757 (NOVALAKE_P)
[10:55:11] [PASSED] 0xD75F (NOVALAKE_P)
[10:55:11] =============== [PASSED] check_platform_desc ===============
[10:55:11] ===================== [PASSED] xe_pci ======================
[10:55:11] ============= xe_rtp_tables_test (5 subtests) ==============
[10:55:11] ================== xe_rtp_table_gt_test  ===================
[10:55:11] [PASSED] gt_was/14011060649
[10:55:11] [PASSED] gt_was/14011059788
[10:55:11] [PASSED] gt_was/14015795083
[10:55:11] [PASSED] gt_was/16021867713
[10:55:11] [PASSED] gt_was/14019449301
[10:55:11] [PASSED] gt_was/16028005424
[10:55:11] [PASSED] gt_was/14026578760
[10:55:11] [PASSED] gt_was/1409420604
[10:55:11] [PASSED] gt_was/1408615072
[10:55:11] [PASSED] gt_was/22010523718
[10:55:11] [PASSED] gt_was/14011006942
[10:55:11] [PASSED] gt_was/14014830051
[10:55:11] [PASSED] gt_was/18018781329
[10:55:11] [PASSED] gt_was/1509235366
[10:55:11] [PASSED] gt_was/18018781329
[10:55:11] [PASSED] gt_was/16016694945
[10:55:11] [PASSED] gt_was/14018575942
[10:55:11] [PASSED] gt_was/22016670082
[10:55:11] [PASSED] gt_was/22016670082
[10:55:11] [PASSED] gt_was/14017421178
[10:55:11] [PASSED] gt_was/16025250150
[10:55:11] [PASSED] gt_was/14021871409
[10:55:11] [PASSED] gt_was/16021865536
[10:55:11] [PASSED] gt_was/14021486841
[10:55:11] [PASSED] gt_was/14025160223
[10:55:11] [PASSED] gt_was/14026144927, 16029437861, 14026127056
[10:55:11] [PASSED] gt_was/14025635424
[10:55:11] [PASSED] gt_was/16028005424
[10:55:11] ============== [PASSED] xe_rtp_table_gt_test ===============
[10:55:11] ================== xe_rtp_table_gt_test  ===================
[10:55:11] [PASSED] gt_tunings/Tuning: Blend Fill Caching Optimization Disable
[10:55:11] [PASSED] gt_tunings/Tuning: 32B Access Enable
[10:55:11] [PASSED] gt_tunings/Tuning: L3 cache
[10:55:11] [PASSED] gt_tunings/Tuning: L3 cache - media
[10:55:11] [PASSED] gt_tunings/Tuning: Compression Overfetch
[10:55:11] [PASSED] gt_tunings/Tuning: Compression Overfetch - media
[10:55:11] [PASSED] gt_tunings/Tuning: Enable compressible partial write overfetch in L3
[10:55:11] [PASSED] gt_tunings/Tuning: Enable compressible partial write overfetch in L3 - media
[10:55:11] [PASSED] gt_tunings/Tuning: L2 Overfetch Compressible Only
[10:55:11] [PASSED] gt_tunings/Tuning: L2 Overfetch Compressible Only - media
[10:55:11] [PASSED] gt_tunings/Tuning: Stateless compression control
[10:55:11] [PASSED] gt_tunings/Tuning: Stateless compression control - media
[10:55:11] [PASSED] gt_tunings/Tuning: L3 RW flush all Cache
[10:55:11] [PASSED] gt_tunings/Tuning: L3 RW flush all cache - media
[10:55:11] [PASSED] gt_tunings/Tuning: Set STLB Bank Hash Mode to 4KB
[10:55:11] [PASSED] gt_tunings/Tuning: Force All Non-Compressible Memory Reads to be 256B Overfetches
[10:55:11] ============== [PASSED] xe_rtp_table_gt_test ===============
[10:55:11] ================== xe_rtp_table_oob_test  ==================
[10:55:11] [PASSED] oob_was/1607983814
[10:55:11] [PASSED] oob_was/16010904313
[10:55:11] [PASSED] oob_was/18022495364
[10:55:11] [PASSED] oob_was/22012773006
[10:55:11] [PASSED] oob_was/14014475959
[10:55:11] [PASSED] oob_was/22011391025
[10:55:11] [PASSED] oob_was/22012727170
[10:55:11] [PASSED] oob_was/22012727685
[10:55:11] [PASSED] oob_was/22016596838
[10:55:11] [PASSED] oob_was/18020744125
[10:55:11] [PASSED] oob_was/1409600907
[10:55:11] [PASSED] oob_was/22014953428
[10:55:11] [PASSED] oob_was/16017236439
[10:55:11] [PASSED] oob_was/14019821291
[10:55:11] [PASSED] oob_was/14015076503
[10:55:11] [PASSED] oob_was/22016122933
[10:55:11] [PASSED] oob_was/14018913170
[10:55:11] [PASSED] oob_was/14018094691
[10:55:11] [PASSED] oob_was/18024947630
[10:55:11] [PASSED] oob_was/16022287689
[10:55:11] [PASSED] oob_was/13011645652
[10:55:11] [PASSED] oob_was/14022293748
[10:55:11] [PASSED] oob_was/22019794406
[10:55:11] [PASSED] oob_was/22019338487
[10:55:11] [PASSED] oob_was/16023588340
[10:55:11] [PASSED] oob_was/14019789679
[10:55:11] [PASSED] oob_was/14022866841
[10:55:11] [PASSED] oob_was/16021333562
[10:55:11] [PASSED] oob_was/14016712196
[10:55:11] [PASSED] oob_was/14015568240
[10:55:11] [PASSED] oob_was/18013179988
[10:55:11] [PASSED] oob_was/1508761755
[10:55:11] [PASSED] oob_was/16023105232
[10:55:11] [PASSED] oob_was/16026508708
[10:55:11] [PASSED] oob_was/14020001231
[10:55:11] [PASSED] oob_was/16023683509
[10:55:11] [PASSED] oob_was/14025515070
[10:55:11] [PASSED] oob_was/15015404425_disable
[10:55:11] [PASSED] oob_was/16026007364
[10:55:11] [PASSED] oob_was/14020316580
[10:55:11] [PASSED] oob_was/14025883347
[10:55:11] [PASSED] oob_was/16029380221
[10:55:11] [PASSED] oob_was/22022079272
[10:55:11] [PASSED] oob_was/16029897822
[10:55:11] [PASSED] oob_was/14027054324
[10:55:11] [PASSED] oob_was/14025941587
[10:55:11] [PASSED] oob_was/16030224309
[10:55:11] ============== [PASSED] xe_rtp_table_oob_test ==============
[10:55:11] ================ xe_rtp_table_dev_oob_test  ================
[10:55:11] [PASSED] device_oob_was/22010954014
[10:55:11] [PASSED] device_oob_was/15015404425
[10:55:11] [PASSED] device_oob_was/22019338487_display
[10:55:11] [PASSED] device_oob_was/14022085890
[10:55:11] [PASSED] device_oob_was/14026539277
[10:55:11] [PASSED] device_oob_was/14026633728
[10:55:11] [PASSED] device_oob_was/14026746987
[10:55:11] [PASSED] device_oob_was/14026779378
[10:55:11] ============ [PASSED] xe_rtp_table_dev_oob_test ============
[10:55:11] ========== xe_rtp_table_missing_upper_bound_test  ==========
[10:55:11] [PASSED] register_whitelist/WaAllowPMDepthAndInvocationCountAccessFromUMD, 1408556865
[10:55:11] [PASSED] register_whitelist/1508744258, 14012131227, 1808121037
[10:55:11] [PASSED] register_whitelist/1806527549
[10:55:11] [PASSED] register_whitelist/allow_read_ctx_timestamp
[10:55:11] [PASSED] register_whitelist/allow_read_queue_timestamp
[10:55:11] [PASSED] register_whitelist/16014440446
[10:55:11] [PASSED] register_whitelist/16017236439
[10:55:11] [PASSED] register_whitelist/16020183090
[10:55:11] [PASSED] register_whitelist/14024997852
[10:55:11] [PASSED] register_whitelist/14024997852
[10:55:11] ====== [PASSED] xe_rtp_table_missing_upper_bound_test ======
[10:55:11] =============== [PASSED] xe_rtp_tables_test ================
[10:55:11] =================== xe_rtp (3 subtests) ====================
[10:55:11] =================== xe_rtp_rules_tests  ====================
[10:55:11] [PASSED] no
[10:55:11] [PASSED] yes
[10:55:11] [PASSED] no-and-no
[10:55:11] [PASSED] no-and-yes
[10:55:11] [PASSED] yes-and-no
[10:55:11] [PASSED] yes-and-yes
[10:55:11] [PASSED] no-or-no
[10:55:11] [PASSED] no-or-yes
[10:55:11] [PASSED] yes-or-no
[10:55:11] [PASSED] yes-or-yes
[10:55:11] [PASSED] no-yes-or-yes-no
[10:55:11] [PASSED] no-yes-or-yes-yes
[10:55:11] [PASSED] yes-yes-or-no-yes
[10:55:11] [PASSED] yes-yes-or-yes-yes
[10:55:11] [PASSED] no-no-or-yes-or-no
[10:55:11] [PASSED] or
[10:55:11] [PASSED] or-yes
[10:55:11] [PASSED] or-no
[10:55:11] [PASSED] yes-or
[10:55:11] [PASSED] no-or
[10:55:11] [PASSED] no-or-or-yes
[10:55:11] [PASSED] yes-or-or-no
[10:55:11] [PASSED] no-or-or-no
[10:55:11] [PASSED] missing-context-engine-class
[10:55:11] [PASSED] missing-context-engine-class-or-yes
[10:55:11] [PASSED] missing-context-engine-class-or-or-yes
[10:55:11] =============== [PASSED] xe_rtp_rules_tests ================
[10:55:11] =============== xe_rtp_process_to_sr_tests  ================
[10:55:11] [PASSED] coalesce-same-reg
[10:55:11] [PASSED] coalesce-same-reg-literal-and-func
[10:55:11] [PASSED] no-match-no-add
[10:55:11] [PASSED] two-regs-two-entries
[10:55:11] [PASSED] clr-one-set-other
[10:55:11] [PASSED] set-field
[10:55:11] [PASSED] conflict-duplicate
[10:55:11] [PASSED] conflict-not-disjoint
[10:55:11] [PASSED] conflict-not-disjoint-literal-and-func
[10:55:11] [PASSED] conflict-reg-type
[10:55:11] [PASSED] bad-mcr-reg-forced-to-regular
[10:55:11] [PASSED] bad-regular-reg-forced-to-mcr
[10:55:11] =========== [PASSED] xe_rtp_process_to_sr_tests ============
[10:55:11] ================== xe_rtp_process_tests  ===================
[10:55:11] [PASSED] active1
[10:55:11] [PASSED] active2
[10:55:11] [PASSED] active-inactive
[10:55:11] [PASSED] inactive-active
[10:55:11] [PASSED] inactive-active-inactive
[10:55:11] [PASSED] inactive-inactive-inactive
[10:55:11] ============== [PASSED] xe_rtp_process_tests ===============
[10:55:11] ===================== [PASSED] xe_rtp ======================
[10:55:11] ==================== xe_wa (1 subtest) =====================
[10:55:11] ======================== xe_wa_gt  =========================
[10:55:11] [PASSED] TIGERLAKE B0
[10:55:11] [PASSED] DG1 A0
[10:55:11] [PASSED] DG1 B0
[10:55:11] [PASSED] ALDERLAKE_S A0
[10:55:11] [PASSED] ALDERLAKE_S B0
[10:55:11] [PASSED] ALDERLAKE_S C0
[10:55:11] [PASSED] ALDERLAKE_S D0
[10:55:11] [PASSED] ALDERLAKE_P A0
[10:55:11] [PASSED] ALDERLAKE_P B0
[10:55:11] [PASSED] ALDERLAKE_P C0
[10:55:11] [PASSED] ALDERLAKE_S RPLS D0
[10:55:11] [PASSED] ALDERLAKE_P RPLU E0
[10:55:11] [PASSED] DG2 G10 C0
[10:55:11] [PASSED] DG2 G11 B1
[10:55:11] [PASSED] DG2 G12 A1
[10:55:11] [PASSED] METEORLAKE 12.70(Xe_LPG) A0 13.00(Xe_LPM+) A0
[10:55:11] [PASSED] METEORLAKE 12.71(Xe_LPG) A0 13.00(Xe_LPM+) A0
[10:55:11] [PASSED] METEORLAKE 12.74(Xe_LPG+) A0 13.00(Xe_LPM+) A0
[10:55:11] [PASSED] LUNARLAKE 20.04(Xe2_LPG) A0 20.00(Xe2_LPM) A0
[10:55:11] [PASSED] LUNARLAKE 20.04(Xe2_LPG) B0 20.00(Xe2_LPM) A0
[10:55:11] [PASSED] BATTLEMAGE 20.01(Xe2_HPG) A0 13.01(Xe2_HPM) A1
[10:55:11] [PASSED] PANTHERLAKE 30.00(Xe3_LPG) A0 30.00(Xe3_LPM) A0
[10:55:11] ==================== [PASSED] xe_wa_gt =====================
[10:55:11] ====================== [PASSED] xe_wa ======================
[10:55:11] ============================================================
[10:55:11] Testing complete. Ran 821 tests: passed: 793, skipped: 28
[10:55:11] Elapsed time: 36.576s total, 1.848s configuring, 33.961s building, 0.717s 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 [10:55:11] Configuring KUnit Kernel ...
Regenerating .config ...
Populating config with:

$ make ARCH=um O=.kunit olddefconfig
[10:55:13] 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
[10:55:38] Starting KUnit Kernel (1/1)...
[10:55:38] ============================================================
Running tests with:
$ .kunit/linux kunit.enable=1 mem=1G console=tty kunit_shutdown=halt
[10:55:38] ============ drm_test_pick_cmdline (2 subtests) ============
[10:55:38] [PASSED] drm_test_pick_cmdline_res_1920_1080_60
[10:55:38] =============== drm_test_pick_cmdline_named  ===============
[10:55:38] [PASSED] NTSC
[10:55:38] [PASSED] NTSC-J
[10:55:38] [PASSED] PAL
[10:55:38] [PASSED] PAL-M
[10:55:38] =========== [PASSED] drm_test_pick_cmdline_named ===========
[10:55:38] ============== [PASSED] drm_test_pick_cmdline ==============
[10:55:38] == drm_test_atomic_get_connector_for_encoder (1 subtest) ===
[10:55:38] [PASSED] drm_test_drm_atomic_get_connector_for_encoder
[10:55:38] ==== [PASSED] drm_test_atomic_get_connector_for_encoder ====
[10:55:38] =========== drm_validate_clone_mode (2 subtests) ===========
[10:55:38] ============== drm_test_check_in_clone_mode  ===============
[10:55:38] [PASSED] in_clone_mode
[10:55:38] [PASSED] not_in_clone_mode
[10:55:38] ========== [PASSED] drm_test_check_in_clone_mode ===========
[10:55:38] =============== drm_test_check_valid_clones  ===============
[10:55:38] [PASSED] not_in_clone_mode
[10:55:38] [PASSED] valid_clone
[10:55:38] [PASSED] invalid_clone
[10:55:38] =========== [PASSED] drm_test_check_valid_clones ===========
[10:55:38] ============= [PASSED] drm_validate_clone_mode =============
[10:55:38] ============= drm_validate_modeset (1 subtest) =============
[10:55:38] [PASSED] drm_test_check_connector_changed_modeset
[10:55:38] ============== [PASSED] drm_validate_modeset ===============
[10:55:38] ====== drm_test_bridge_get_current_state (1 subtest) =======
[10:55:38] [PASSED] drm_test_drm_bridge_get_current_state_atomic
[10:55:38] ======== [PASSED] drm_test_bridge_get_current_state ========
[10:55:38] ====== drm_test_bridge_helper_reset_crtc (3 subtests) ======
[10:55:38] [PASSED] drm_test_drm_bridge_helper_reset_crtc_atomic
[10:55:38] [PASSED] drm_test_drm_bridge_helper_reset_crtc_atomic_disabled
[10:55:38] [PASSED] drm_test_drm_bridge_helper_hdmi_output_bus_fmts
[10:55:38] ======== [PASSED] drm_test_bridge_helper_reset_crtc ========
[10:55:38] ============== drm_bridge_alloc (2 subtests) ===============
[10:55:38] [PASSED] drm_test_drm_bridge_alloc_basic
[10:55:38] [PASSED] drm_test_drm_bridge_alloc_get_put
[10:55:38] ================ [PASSED] drm_bridge_alloc =================
[10:55:38] ============= drm_bridge_bus_fmt (5 subtests) ==============
[10:55:38] [PASSED] drm_test_bridge_rgb_yuv_rgb
[10:55:38] [PASSED] drm_test_bridge_must_convert_to_yuv444
[10:55:38] [PASSED] drm_test_bridge_hdmi_auto_rgb
[10:55:38] [PASSED] drm_test_bridge_auto_first
[10:55:38] [PASSED] drm_test_bridge_rgb_yuv_no_path
[10:55:38] =============== [PASSED] drm_bridge_bus_fmt ================
[10:55:38] ============= drm_cmdline_parser (40 subtests) =============
[10:55:38] [PASSED] drm_test_cmdline_force_d_only
[10:55:38] [PASSED] drm_test_cmdline_force_D_only_dvi
[10:55:38] [PASSED] drm_test_cmdline_force_D_only_hdmi
[10:55:38] [PASSED] drm_test_cmdline_force_D_only_not_digital
[10:55:38] [PASSED] drm_test_cmdline_force_e_only
[10:55:38] [PASSED] drm_test_cmdline_res
[10:55:38] [PASSED] drm_test_cmdline_res_vesa
[10:55:38] [PASSED] drm_test_cmdline_res_vesa_rblank
[10:55:38] [PASSED] drm_test_cmdline_res_rblank
[10:55:38] [PASSED] drm_test_cmdline_res_bpp
[10:55:38] [PASSED] drm_test_cmdline_res_refresh
[10:55:38] [PASSED] drm_test_cmdline_res_bpp_refresh
[10:55:38] [PASSED] drm_test_cmdline_res_bpp_refresh_interlaced
[10:55:38] [PASSED] drm_test_cmdline_res_bpp_refresh_margins
[10:55:38] [PASSED] drm_test_cmdline_res_bpp_refresh_force_off
[10:55:38] [PASSED] drm_test_cmdline_res_bpp_refresh_force_on
[10:55:38] [PASSED] drm_test_cmdline_res_bpp_refresh_force_on_analog
[10:55:38] [PASSED] drm_test_cmdline_res_bpp_refresh_force_on_digital
[10:55:38] [PASSED] drm_test_cmdline_res_bpp_refresh_interlaced_margins_force_on
[10:55:38] [PASSED] drm_test_cmdline_res_margins_force_on
[10:55:38] [PASSED] drm_test_cmdline_res_vesa_margins
[10:55:38] [PASSED] drm_test_cmdline_name
[10:55:38] [PASSED] drm_test_cmdline_name_bpp
[10:55:38] [PASSED] drm_test_cmdline_name_option
[10:55:38] [PASSED] drm_test_cmdline_name_bpp_option
[10:55:38] [PASSED] drm_test_cmdline_rotate_0
[10:55:38] [PASSED] drm_test_cmdline_rotate_90
[10:55:38] [PASSED] drm_test_cmdline_rotate_180
[10:55:38] [PASSED] drm_test_cmdline_rotate_270
[10:55:38] [PASSED] drm_test_cmdline_hmirror
[10:55:38] [PASSED] drm_test_cmdline_vmirror
[10:55:38] [PASSED] drm_test_cmdline_margin_options
[10:55:38] [PASSED] drm_test_cmdline_multiple_options
[10:55:38] [PASSED] drm_test_cmdline_bpp_extra_and_option
[10:55:38] [PASSED] drm_test_cmdline_extra_and_option
[10:55:38] [PASSED] drm_test_cmdline_freestanding_options
[10:55:38] [PASSED] drm_test_cmdline_freestanding_force_e_and_options
[10:55:38] [PASSED] drm_test_cmdline_panel_orientation
[10:55:38] ================ drm_test_cmdline_invalid  =================
[10:55:38] [PASSED] margin_only
[10:55:38] [PASSED] interlace_only
[10:55:38] [PASSED] res_missing_x
[10:55:38] [PASSED] res_missing_y
[10:55:38] [PASSED] res_bad_y
[10:55:38] [PASSED] res_missing_y_bpp
[10:55:38] [PASSED] res_bad_bpp
[10:55:38] [PASSED] res_bad_refresh
[10:55:38] [PASSED] res_bpp_refresh_force_on_off
[10:55:38] [PASSED] res_invalid_mode
[10:55:38] [PASSED] res_bpp_wrong_place_mode
[10:55:38] [PASSED] name_bpp_refresh
[10:55:38] [PASSED] name_refresh
[10:55:38] [PASSED] name_refresh_wrong_mode
[10:55:38] [PASSED] name_refresh_invalid_mode
[10:55:38] [PASSED] rotate_multiple
[10:55:38] [PASSED] rotate_invalid_val
[10:55:38] [PASSED] rotate_truncated
[10:55:38] [PASSED] invalid_option
[10:55:38] [PASSED] invalid_tv_option
[10:55:38] [PASSED] truncated_tv_option
[10:55:38] ============ [PASSED] drm_test_cmdline_invalid =============
[10:55:38] =============== drm_test_cmdline_tv_options  ===============
[10:55:38] [PASSED] NTSC
[10:55:38] [PASSED] NTSC_443
[10:55:38] [PASSED] NTSC_J
[10:55:38] [PASSED] PAL
[10:55:38] [PASSED] PAL_M
[10:55:38] [PASSED] PAL_N
[10:55:38] [PASSED] SECAM
[10:55:38] [PASSED] MONO_525
[10:55:38] [PASSED] MONO_625
[10:55:38] =========== [PASSED] drm_test_cmdline_tv_options ===========
[10:55:38] =============== [PASSED] drm_cmdline_parser ================
[10:55:38] ========== drmm_connector_hdmi_init (20 subtests) ==========
[10:55:38] [PASSED] drm_test_connector_hdmi_init_valid
[10:55:38] [PASSED] drm_test_connector_hdmi_init_bpc_8
[10:55:38] [PASSED] drm_test_connector_hdmi_init_bpc_10
[10:55:38] [PASSED] drm_test_connector_hdmi_init_bpc_12
[10:55:38] [PASSED] drm_test_connector_hdmi_init_bpc_invalid
[10:55:38] [PASSED] drm_test_connector_hdmi_init_bpc_null
[10:55:38] [PASSED] drm_test_connector_hdmi_init_formats_empty
[10:55:38] [PASSED] drm_test_connector_hdmi_init_formats_no_rgb
[10:55:38] === drm_test_connector_hdmi_init_formats_yuv420_allowed  ===
[10:55:38] [PASSED] supported_formats=0x9 yuv420_allowed=1
[10:55:38] [PASSED] supported_formats=0x9 yuv420_allowed=0
[10:55:38] [PASSED] supported_formats=0x5 yuv420_allowed=1
[10:55:38] [PASSED] supported_formats=0x5 yuv420_allowed=0
[10:55:38] === [PASSED] drm_test_connector_hdmi_init_formats_yuv420_allowed ===
[10:55:38] [PASSED] drm_test_connector_hdmi_init_null_ddc
[10:55:38] [PASSED] drm_test_connector_hdmi_init_null_product
[10:55:38] [PASSED] drm_test_connector_hdmi_init_null_vendor
[10:55:38] [PASSED] drm_test_connector_hdmi_init_product_length_exact
[10:55:38] [PASSED] drm_test_connector_hdmi_init_product_length_too_long
[10:55:38] [PASSED] drm_test_connector_hdmi_init_product_valid
[10:55:38] [PASSED] drm_test_connector_hdmi_init_vendor_length_exact
[10:55:38] [PASSED] drm_test_connector_hdmi_init_vendor_length_too_long
[10:55:38] [PASSED] drm_test_connector_hdmi_init_vendor_valid
[10:55:38] ========= drm_test_connector_hdmi_init_type_valid  =========
[10:55:38] [PASSED] HDMI-A
[10:55:38] [PASSED] HDMI-B
[10:55:38] ===== [PASSED] drm_test_connector_hdmi_init_type_valid =====
[10:55:38] ======== drm_test_connector_hdmi_init_type_invalid  ========
[10:55:38] [PASSED] Unknown
[10:55:38] [PASSED] VGA
[10:55:38] [PASSED] DVI-I
[10:55:38] [PASSED] DVI-D
[10:55:38] [PASSED] DVI-A
[10:55:38] [PASSED] Composite
[10:55:38] [PASSED] SVIDEO
[10:55:38] [PASSED] LVDS
[10:55:38] [PASSED] Component
[10:55:38] [PASSED] DIN
[10:55:38] [PASSED] DP
[10:55:38] [PASSED] TV
[10:55:38] [PASSED] eDP
[10:55:38] [PASSED] Virtual
[10:55:38] [PASSED] DSI
[10:55:38] [PASSED] DPI
[10:55:38] [PASSED] Writeback
[10:55:38] [PASSED] SPI
[10:55:38] [PASSED] USB
[10:55:38] ==== [PASSED] drm_test_connector_hdmi_init_type_invalid ====
[10:55:38] ============ [PASSED] drmm_connector_hdmi_init =============
[10:55:38] ============= drmm_connector_init (3 subtests) =============
[10:55:38] [PASSED] drm_test_drmm_connector_init
[10:55:38] [PASSED] drm_test_drmm_connector_init_null_ddc
[10:55:38] ========= drm_test_drmm_connector_init_type_valid  =========
[10:55:38] [PASSED] Unknown
[10:55:38] [PASSED] VGA
[10:55:38] [PASSED] DVI-I
[10:55:38] [PASSED] DVI-D
[10:55:38] [PASSED] DVI-A
[10:55:38] [PASSED] Composite
[10:55:38] [PASSED] SVIDEO
[10:55:38] [PASSED] LVDS
[10:55:38] [PASSED] Component
[10:55:38] [PASSED] DIN
[10:55:38] [PASSED] DP
[10:55:38] [PASSED] HDMI-A
[10:55:38] [PASSED] HDMI-B
[10:55:38] [PASSED] TV
[10:55:38] [PASSED] eDP
[10:55:38] [PASSED] Virtual
[10:55:38] [PASSED] DSI
[10:55:38] [PASSED] DPI
[10:55:38] [PASSED] Writeback
[10:55:38] [PASSED] SPI
[10:55:38] [PASSED] USB
[10:55:38] ===== [PASSED] drm_test_drmm_connector_init_type_valid =====
[10:55:38] =============== [PASSED] drmm_connector_init ===============
[10:55:38] ========= drm_connector_dynamic_init (6 subtests) ==========
[10:55:38] [PASSED] drm_test_drm_connector_dynamic_init
[10:55:38] [PASSED] drm_test_drm_connector_dynamic_init_null_ddc
[10:55:38] [PASSED] drm_test_drm_connector_dynamic_init_not_added
[10:55:38] [PASSED] drm_test_drm_connector_dynamic_init_properties
[10:55:38] ===== drm_test_drm_connector_dynamic_init_type_valid  ======
[10:55:38] [PASSED] Unknown
[10:55:38] [PASSED] VGA
[10:55:38] [PASSED] DVI-I
[10:55:38] [PASSED] DVI-D
[10:55:38] [PASSED] DVI-A
[10:55:38] [PASSED] Composite
[10:55:38] [PASSED] SVIDEO
[10:55:38] [PASSED] LVDS
[10:55:38] [PASSED] Component
[10:55:38] [PASSED] DIN
[10:55:38] [PASSED] DP
[10:55:38] [PASSED] HDMI-A
[10:55:38] [PASSED] HDMI-B
[10:55:38] [PASSED] TV
[10:55:38] [PASSED] eDP
[10:55:38] [PASSED] Virtual
[10:55:38] [PASSED] DSI
[10:55:38] [PASSED] DPI
[10:55:38] [PASSED] Writeback
[10:55:38] [PASSED] SPI
[10:55:38] [PASSED] USB
[10:55:38] = [PASSED] drm_test_drm_connector_dynamic_init_type_valid ==
[10:55:38] ======== drm_test_drm_connector_dynamic_init_name  =========
[10:55:38] [PASSED] Unknown
[10:55:38] [PASSED] VGA
[10:55:38] [PASSED] DVI-I
[10:55:38] [PASSED] DVI-D
[10:55:38] [PASSED] DVI-A
[10:55:38] [PASSED] Composite
[10:55:38] [PASSED] SVIDEO
[10:55:38] [PASSED] LVDS
[10:55:38] [PASSED] Component
[10:55:38] [PASSED] DIN
[10:55:38] [PASSED] DP
[10:55:38] [PASSED] HDMI-A
[10:55:38] [PASSED] HDMI-B
[10:55:38] [PASSED] TV
[10:55:38] [PASSED] eDP
[10:55:38] [PASSED] Virtual
[10:55:38] [PASSED] DSI
[10:55:38] [PASSED] DPI
[10:55:38] [PASSED] Writeback
[10:55:38] [PASSED] SPI
[10:55:38] [PASSED] USB
[10:55:38] ==== [PASSED] drm_test_drm_connector_dynamic_init_name =====
[10:55:38] =========== [PASSED] drm_connector_dynamic_init ============
[10:55:38] ==== drm_connector_dynamic_register_early (4 subtests) =====
[10:55:38] [PASSED] drm_test_drm_connector_dynamic_register_early_on_list
[10:55:38] [PASSED] drm_test_drm_connector_dynamic_register_early_defer
[10:55:38] [PASSED] drm_test_drm_connector_dynamic_register_early_no_init
[10:55:38] [PASSED] drm_test_drm_connector_dynamic_register_early_no_mode_object
[10:55:38] ====== [PASSED] drm_connector_dynamic_register_early =======
[10:55:38] ======= drm_connector_dynamic_register (7 subtests) ========
[10:55:38] [PASSED] drm_test_drm_connector_dynamic_register_on_list
[10:55:38] [PASSED] drm_test_drm_connector_dynamic_register_no_defer
[10:55:38] [PASSED] drm_test_drm_connector_dynamic_register_no_init
[10:55:38] [PASSED] drm_test_drm_connector_dynamic_register_mode_object
[10:55:38] [PASSED] drm_test_drm_connector_dynamic_register_sysfs
[10:55:38] [PASSED] drm_test_drm_connector_dynamic_register_sysfs_name
[10:55:38] [PASSED] drm_test_drm_connector_dynamic_register_debugfs
[10:55:38] ========= [PASSED] drm_connector_dynamic_register ==========
[10:55:38] = drm_connector_attach_broadcast_rgb_property (2 subtests) =
[10:55:38] [PASSED] drm_test_drm_connector_attach_broadcast_rgb_property
[10:55:38] [PASSED] drm_test_drm_connector_attach_broadcast_rgb_property_hdmi_connector
[10:55:38] === [PASSED] drm_connector_attach_broadcast_rgb_property ===
[10:55:38] ========== drm_get_tv_mode_from_name (2 subtests) ==========
[10:55:38] ========== drm_test_get_tv_mode_from_name_valid  ===========
[10:55:38] [PASSED] NTSC
[10:55:38] [PASSED] NTSC-443
[10:55:38] [PASSED] NTSC-J
[10:55:38] [PASSED] PAL
[10:55:38] [PASSED] PAL-M
[10:55:38] [PASSED] PAL-N
[10:55:38] [PASSED] SECAM
[10:55:38] [PASSED] Mono
[10:55:38] ====== [PASSED] drm_test_get_tv_mode_from_name_valid =======
[10:55:38] [PASSED] drm_test_get_tv_mode_from_name_truncated
[10:55:38] ============ [PASSED] drm_get_tv_mode_from_name ============
[10:55:38] = drm_test_connector_hdmi_compute_mode_clock (12 subtests) =
[10:55:38] [PASSED] drm_test_drm_hdmi_compute_mode_clock_rgb
[10:55:38] [PASSED] drm_test_drm_hdmi_compute_mode_clock_rgb_10bpc
[10:55:38] [PASSED] drm_test_drm_hdmi_compute_mode_clock_rgb_10bpc_vic_1
[10:55:38] [PASSED] drm_test_drm_hdmi_compute_mode_clock_rgb_12bpc
[10:55:38] [PASSED] drm_test_drm_hdmi_compute_mode_clock_rgb_12bpc_vic_1
[10:55:38] [PASSED] drm_test_drm_hdmi_compute_mode_clock_rgb_double
[10:55:38] = drm_test_connector_hdmi_compute_mode_clock_yuv420_valid  =
[10:55:38] [PASSED] VIC 96
[10:55:38] [PASSED] VIC 97
[10:55:38] [PASSED] VIC 101
[10:55:38] [PASSED] VIC 102
[10:55:38] [PASSED] VIC 106
[10:55:38] [PASSED] VIC 107
[10:55:38] === [PASSED] drm_test_connector_hdmi_compute_mode_clock_yuv420_valid ===
[10:55:38] [PASSED] drm_test_connector_hdmi_compute_mode_clock_yuv420_10_bpc
[10:55:38] [PASSED] drm_test_connector_hdmi_compute_mode_clock_yuv420_12_bpc
[10:55:38] [PASSED] drm_test_connector_hdmi_compute_mode_clock_yuv422_8_bpc
[10:55:38] [PASSED] drm_test_connector_hdmi_compute_mode_clock_yuv422_10_bpc
[10:55:38] [PASSED] drm_test_connector_hdmi_compute_mode_clock_yuv422_12_bpc
[10:55:38] === [PASSED] drm_test_connector_hdmi_compute_mode_clock ====
[10:55:38] == drm_hdmi_connector_get_broadcast_rgb_name (2 subtests) ==
[10:55:38] === drm_test_drm_hdmi_connector_get_broadcast_rgb_name  ====
[10:55:38] [PASSED] Automatic
[10:55:38] [PASSED] Full
[10:55:38] [PASSED] Limited 16:235
[10:55:38] === [PASSED] drm_test_drm_hdmi_connector_get_broadcast_rgb_name ===
[10:55:38] [PASSED] drm_test_drm_hdmi_connector_get_broadcast_rgb_name_invalid
[10:55:38] ==== [PASSED] drm_hdmi_connector_get_broadcast_rgb_name ====
[10:55:38] == drm_hdmi_connector_get_output_format_name (2 subtests) ==
[10:55:38] === drm_test_drm_hdmi_connector_get_output_format_name  ====
[10:55:38] [PASSED] RGB
[10:55:38] [PASSED] YUV 4:2:0
[10:55:38] [PASSED] YUV 4:2:2
[10:55:38] [PASSED] YUV 4:4:4
[10:55:38] === [PASSED] drm_test_drm_hdmi_connector_get_output_format_name ===
[10:55:38] [PASSED] drm_test_drm_hdmi_connector_get_output_format_name_invalid
[10:55:38] ==== [PASSED] drm_hdmi_connector_get_output_format_name ====
[10:55:38] ============= drm_damage_helper (21 subtests) ==============
[10:55:38] [PASSED] drm_test_damage_iter_no_damage
[10:55:38] [PASSED] drm_test_damage_iter_no_damage_fractional_src
[10:55:38] [PASSED] drm_test_damage_iter_no_damage_src_moved
[10:55:38] [PASSED] drm_test_damage_iter_no_damage_fractional_src_moved
[10:55:38] [PASSED] drm_test_damage_iter_no_damage_not_visible
[10:55:38] [PASSED] drm_test_damage_iter_no_damage_no_crtc
[10:55:38] [PASSED] drm_test_damage_iter_no_damage_no_fb
[10:55:38] [PASSED] drm_test_damage_iter_simple_damage
[10:55:38] [PASSED] drm_test_damage_iter_single_damage
[10:55:38] [PASSED] drm_test_damage_iter_single_damage_intersect_src
[10:55:38] [PASSED] drm_test_damage_iter_single_damage_outside_src
[10:55:38] [PASSED] drm_test_damage_iter_single_damage_fractional_src
[10:55:38] [PASSED] drm_test_damage_iter_single_damage_intersect_fractional_src
[10:55:38] [PASSED] drm_test_damage_iter_single_damage_outside_fractional_src
[10:55:38] [PASSED] drm_test_damage_iter_single_damage_src_moved
[10:55:38] [PASSED] drm_test_damage_iter_single_damage_fractional_src_moved
[10:55:38] [PASSED] drm_test_damage_iter_damage
[10:55:38] [PASSED] drm_test_damage_iter_damage_one_intersect
[10:55:38] [PASSED] drm_test_damage_iter_damage_one_outside
[10:55:38] [PASSED] drm_test_damage_iter_damage_src_moved
[10:55:38] [PASSED] drm_test_damage_iter_damage_not_visible
[10:55:38] ================ [PASSED] drm_damage_helper ================
[10:55:38] ============== drm_dp_mst_helper (3 subtests) ==============
[10:55:38] ============== drm_test_dp_mst_calc_pbn_mode  ==============
[10:55:38] [PASSED] Clock 154000 BPP 30 DSC disabled
[10:55:38] [PASSED] Clock 234000 BPP 30 DSC disabled
[10:55:38] [PASSED] Clock 297000 BPP 24 DSC disabled
[10:55:38] [PASSED] Clock 332880 BPP 24 DSC enabled
[10:55:38] [PASSED] Clock 324540 BPP 24 DSC enabled
[10:55:38] ========== [PASSED] drm_test_dp_mst_calc_pbn_mode ==========
[10:55:38] ============== drm_test_dp_mst_calc_pbn_div  ===============
[10:55:38] [PASSED] Link rate 2000000 lane count 4
[10:55:38] [PASSED] Link rate 2000000 lane count 2
[10:55:38] [PASSED] Link rate 2000000 lane count 1
[10:55:38] [PASSED] Link rate 1350000 lane count 4
[10:55:38] [PASSED] Link rate 1350000 lane count 2
[10:55:38] [PASSED] Link rate 1350000 lane count 1
[10:55:38] [PASSED] Link rate 1000000 lane count 4
[10:55:38] [PASSED] Link rate 1000000 lane count 2
[10:55:38] [PASSED] Link rate 1000000 lane count 1
[10:55:38] [PASSED] Link rate 810000 lane count 4
[10:55:38] [PASSED] Link rate 810000 lane count 2
[10:55:38] [PASSED] Link rate 810000 lane count 1
[10:55:38] [PASSED] Link rate 540000 lane count 4
[10:55:38] [PASSED] Link rate 540000 lane count 2
[10:55:38] [PASSED] Link rate 540000 lane count 1
[10:55:38] [PASSED] Link rate 270000 lane count 4
[10:55:38] [PASSED] Link rate 270000 lane count 2
[10:55:38] [PASSED] Link rate 270000 lane count 1
[10:55:38] [PASSED] Link rate 162000 lane count 4
[10:55:38] [PASSED] Link rate 162000 lane count 2
[10:55:38] [PASSED] Link rate 162000 lane count 1
[10:55:38] ========== [PASSED] drm_test_dp_mst_calc_pbn_div ===========
[10:55:38] ========= drm_test_dp_mst_sideband_msg_req_decode  =========
[10:55:38] [PASSED] DP_ENUM_PATH_RESOURCES with port number
[10:55:38] [PASSED] DP_POWER_UP_PHY with port number
[10:55:38] [PASSED] DP_POWER_DOWN_PHY with port number
[10:55:38] [PASSED] DP_ALLOCATE_PAYLOAD with SDP stream sinks
[10:55:38] [PASSED] DP_ALLOCATE_PAYLOAD with port number
[10:55:38] [PASSED] DP_ALLOCATE_PAYLOAD with VCPI
[10:55:38] [PASSED] DP_ALLOCATE_PAYLOAD with PBN
[10:55:38] [PASSED] DP_QUERY_PAYLOAD with port number
[10:55:38] [PASSED] DP_QUERY_PAYLOAD with VCPI
[10:55:38] [PASSED] DP_REMOTE_DPCD_READ with port number
[10:55:38] [PASSED] DP_REMOTE_DPCD_READ with DPCD address
[10:55:38] [PASSED] DP_REMOTE_DPCD_READ with max number of bytes
[10:55:38] [PASSED] DP_REMOTE_DPCD_WRITE with port number
[10:55:38] [PASSED] DP_REMOTE_DPCD_WRITE with DPCD address
[10:55:38] [PASSED] DP_REMOTE_DPCD_WRITE with data array
[10:55:38] [PASSED] DP_REMOTE_I2C_READ with port number
[10:55:38] [PASSED] DP_REMOTE_I2C_READ with I2C device ID
[10:55:38] [PASSED] DP_REMOTE_I2C_READ with transactions array
[10:55:38] [PASSED] DP_REMOTE_I2C_WRITE with port number
[10:55:38] [PASSED] DP_REMOTE_I2C_WRITE with I2C device ID
[10:55:38] [PASSED] DP_REMOTE_I2C_WRITE with data array
[10:55:38] [PASSED] DP_QUERY_STREAM_ENC_STATUS with stream ID
[10:55:38] [PASSED] DP_QUERY_STREAM_ENC_STATUS with client ID
[10:55:38] [PASSED] DP_QUERY_STREAM_ENC_STATUS with stream event
[10:55:38] [PASSED] DP_QUERY_STREAM_ENC_STATUS with valid stream event
[10:55:38] [PASSED] DP_QUERY_STREAM_ENC_STATUS with stream behavior
[10:55:38] [PASSED] DP_QUERY_STREAM_ENC_STATUS with a valid stream behavior
[10:55:38] ===== [PASSED] drm_test_dp_mst_sideband_msg_req_decode =====
[10:55:38] ================ [PASSED] drm_dp_mst_helper ================
[10:55:38] ================== drm_exec (7 subtests) ===================
[10:55:38] [PASSED] sanitycheck
[10:55:38] [PASSED] test_lock
[10:55:38] [PASSED] test_lock_unlock
[10:55:38] [PASSED] test_duplicates
[10:55:38] [PASSED] test_prepare
[10:55:38] [PASSED] test_prepare_array
[10:55:38] [PASSED] test_multiple_loops
[10:55:38] ==================== [PASSED] drm_exec =====================
[10:55:38] =========== drm_format_helper_test (17 subtests) ===========
[10:55:38] ============== drm_test_fb_xrgb8888_to_gray8  ==============
[10:55:38] [PASSED] single_pixel_source_buffer
[10:55:38] [PASSED] single_pixel_clip_rectangle
[10:55:38] [PASSED] well_known_colors
[10:55:38] [PASSED] destination_pitch
[10:55:38] ========== [PASSED] drm_test_fb_xrgb8888_to_gray8 ==========
[10:55:38] ============= drm_test_fb_xrgb8888_to_rgb332  ==============
[10:55:38] [PASSED] single_pixel_source_buffer
[10:55:38] [PASSED] single_pixel_clip_rectangle
[10:55:38] [PASSED] well_known_colors
[10:55:38] [PASSED] destination_pitch
[10:55:38] ========= [PASSED] drm_test_fb_xrgb8888_to_rgb332 ==========
[10:55:38] ============= drm_test_fb_xrgb8888_to_rgb565  ==============
[10:55:38] [PASSED] single_pixel_source_buffer
[10:55:38] [PASSED] single_pixel_clip_rectangle
[10:55:38] [PASSED] well_known_colors
[10:55:38] [PASSED] destination_pitch
[10:55:38] ========= [PASSED] drm_test_fb_xrgb8888_to_rgb565 ==========
[10:55:38] ============ drm_test_fb_xrgb8888_to_xrgb1555  =============
[10:55:38] [PASSED] single_pixel_source_buffer
[10:55:38] [PASSED] single_pixel_clip_rectangle
[10:55:38] [PASSED] well_known_colors
[10:55:38] [PASSED] destination_pitch
[10:55:38] ======== [PASSED] drm_test_fb_xrgb8888_to_xrgb1555 =========
[10:55:38] ============ drm_test_fb_xrgb8888_to_argb1555  =============
[10:55:38] [PASSED] single_pixel_source_buffer
[10:55:38] [PASSED] single_pixel_clip_rectangle
[10:55:38] [PASSED] well_known_colors
[10:55:38] [PASSED] destination_pitch
[10:55:38] ======== [PASSED] drm_test_fb_xrgb8888_to_argb1555 =========
[10:55:38] ============ drm_test_fb_xrgb8888_to_rgba5551  =============
[10:55:38] [PASSED] single_pixel_source_buffer
[10:55:38] [PASSED] single_pixel_clip_rectangle
[10:55:38] [PASSED] well_known_colors
[10:55:38] [PASSED] destination_pitch
[10:55:38] ======== [PASSED] drm_test_fb_xrgb8888_to_rgba5551 =========
[10:55:38] ============= drm_test_fb_xrgb8888_to_rgb888  ==============
[10:55:38] [PASSED] single_pixel_source_buffer
[10:55:38] [PASSED] single_pixel_clip_rectangle
[10:55:38] [PASSED] well_known_colors
[10:55:38] [PASSED] destination_pitch
[10:55:38] ========= [PASSED] drm_test_fb_xrgb8888_to_rgb888 ==========
[10:55:38] ============= drm_test_fb_xrgb8888_to_bgr888  ==============
[10:55:38] [PASSED] single_pixel_source_buffer
[10:55:38] [PASSED] single_pixel_clip_rectangle
[10:55:38] [PASSED] well_known_colors
[10:55:38] [PASSED] destination_pitch
[10:55:38] ========= [PASSED] drm_test_fb_xrgb8888_to_bgr888 ==========
[10:55:38] ============ drm_test_fb_xrgb8888_to_argb8888  =============
[10:55:38] [PASSED] single_pixel_source_buffer
[10:55:38] [PASSED] single_pixel_clip_rectangle
[10:55:38] [PASSED] well_known_colors
[10:55:38] [PASSED] destination_pitch
[10:55:38] ======== [PASSED] drm_test_fb_xrgb8888_to_argb8888 =========
[10:55:38] =========== drm_test_fb_xrgb8888_to_xrgb2101010  ===========
[10:55:38] [PASSED] single_pixel_source_buffer
[10:55:38] [PASSED] single_pixel_clip_rectangle
[10:55:38] [PASSED] well_known_colors
[10:55:38] [PASSED] destination_pitch
[10:55:38] ======= [PASSED] drm_test_fb_xrgb8888_to_xrgb2101010 =======
[10:55:38] =========== drm_test_fb_xrgb8888_to_argb2101010  ===========
[10:55:38] [PASSED] single_pixel_source_buffer
[10:55:38] [PASSED] single_pixel_clip_rectangle
[10:55:38] [PASSED] well_known_colors
[10:55:38] [PASSED] destination_pitch
[10:55:38] ======= [PASSED] drm_test_fb_xrgb8888_to_argb2101010 =======
[10:55:38] ============== drm_test_fb_xrgb8888_to_mono  ===============
[10:55:38] [PASSED] single_pixel_source_buffer
[10:55:38] [PASSED] single_pixel_clip_rectangle
[10:55:38] [PASSED] well_known_colors
[10:55:38] [PASSED] destination_pitch
[10:55:38] ========== [PASSED] drm_test_fb_xrgb8888_to_mono ===========
[10:55:38] ==================== drm_test_fb_swab  =====================
[10:55:38] [PASSED] single_pixel_source_buffer
[10:55:38] [PASSED] single_pixel_clip_rectangle
[10:55:38] [PASSED] well_known_colors
[10:55:38] [PASSED] destination_pitch
[10:55:38] ================ [PASSED] drm_test_fb_swab =================
[10:55:38] ============ drm_test_fb_xrgb8888_to_xbgr8888  =============
[10:55:38] [PASSED] single_pixel_source_buffer
[10:55:38] [PASSED] single_pixel_clip_rectangle
[10:55:38] [PASSED] well_known_colors
[10:55:38] [PASSED] destination_pitch
[10:55:38] ======== [PASSED] drm_test_fb_xrgb8888_to_xbgr8888 =========
[10:55:38] ============ drm_test_fb_xrgb8888_to_abgr8888  =============
[10:55:38] [PASSED] single_pixel_source_buffer
[10:55:38] [PASSED] single_pixel_clip_rectangle
[10:55:38] [PASSED] well_known_colors
[10:55:38] [PASSED] destination_pitch
[10:55:38] ======== [PASSED] drm_test_fb_xrgb8888_to_abgr8888 =========
[10:55:38] ================= drm_test_fb_clip_offset  =================
[10:55:38] [PASSED] pass through
[10:55:38] [PASSED] horizontal offset
[10:55:38] [PASSED] vertical offset
[10:55:38] [PASSED] horizontal and vertical offset
[10:55:38] [PASSED] horizontal offset (custom pitch)
[10:55:38] [PASSED] vertical offset (custom pitch)
[10:55:38] [PASSED] horizontal and vertical offset (custom pitch)
[10:55:38] ============= [PASSED] drm_test_fb_clip_offset =============
[10:55:38] =================== drm_test_fb_memcpy  ====================
[10:55:38] [PASSED] single_pixel_source_buffer: XR24 little-endian (0x34325258)
[10:55:38] [PASSED] single_pixel_source_buffer: XRA8 little-endian (0x38415258)
[10:55:38] [PASSED] single_pixel_source_buffer: YU24 little-endian (0x34325559)
[10:55:38] [PASSED] single_pixel_clip_rectangle: XB24 little-endian (0x34324258)
[10:55:38] [PASSED] single_pixel_clip_rectangle: XRA8 little-endian (0x38415258)
[10:55:38] [PASSED] single_pixel_clip_rectangle: YU24 little-endian (0x34325559)
[10:55:38] [PASSED] well_known_colors: XB24 little-endian (0x34324258)
[10:55:38] [PASSED] well_known_colors: XRA8 little-endian (0x38415258)
[10:55:38] [PASSED] well_known_colors: YU24 little-endian (0x34325559)
[10:55:38] [PASSED] destination_pitch: XB24 little-endian (0x34324258)
[10:55:38] [PASSED] destination_pitch: XRA8 little-endian (0x38415258)
[10:55:38] [PASSED] destination_pitch: YU24 little-endian (0x34325559)
[10:55:38] =============== [PASSED] drm_test_fb_memcpy ================
[10:55:38] ============= [PASSED] drm_format_helper_test ==============
[10:55:38] ================= drm_format (18 subtests) =================
[10:55:38] [PASSED] drm_test_format_block_width_invalid
[10:55:38] [PASSED] drm_test_format_block_width_one_plane
[10:55:38] [PASSED] drm_test_format_block_width_two_plane
[10:55:38] [PASSED] drm_test_format_block_width_three_plane
[10:55:38] [PASSED] drm_test_format_block_width_tiled
[10:55:38] [PASSED] drm_test_format_block_height_invalid
[10:55:38] [PASSED] drm_test_format_block_height_one_plane
[10:55:38] [PASSED] drm_test_format_block_height_two_plane
[10:55:38] [PASSED] drm_test_format_block_height_three_plane
[10:55:38] [PASSED] drm_test_format_block_height_tiled
[10:55:38] [PASSED] drm_test_format_min_pitch_invalid
[10:55:38] [PASSED] drm_test_format_min_pitch_one_plane_8bpp
[10:55:38] [PASSED] drm_test_format_min_pitch_one_plane_16bpp
[10:55:38] [PASSED] drm_test_format_min_pitch_one_plane_24bpp
[10:55:38] [PASSED] drm_test_format_min_pitch_one_plane_32bpp
[10:55:38] [PASSED] drm_test_format_min_pitch_two_plane
[10:55:38] [PASSED] drm_test_format_min_pitch_three_plane_8bpp
[10:55:38] [PASSED] drm_test_format_min_pitch_tiled
[10:55:38] =================== [PASSED] drm_format ====================
[10:55:38] ============== drm_framebuffer (10 subtests) ===============
[10:55:38] ========== drm_test_framebuffer_check_src_coords  ==========
[10:55:38] [PASSED] Success: source fits into fb
[10:55:38] [PASSED] Fail: overflowing fb with x-axis coordinate
[10:55:38] [PASSED] Fail: overflowing fb with y-axis coordinate
[10:55:38] [PASSED] Fail: overflowing fb with source width
[10:55:38] [PASSED] Fail: overflowing fb with source height
[10:55:38] ====== [PASSED] drm_test_framebuffer_check_src_coords ======
[10:55:38] [PASSED] drm_test_framebuffer_cleanup
[10:55:38] =============== drm_test_framebuffer_create  ===============
[10:55:38] [PASSED] ABGR8888 normal sizes
[10:55:38] [PASSED] ABGR8888 max sizes
[10:55:38] [PASSED] ABGR8888 pitch greater than min required
[10:55:38] [PASSED] ABGR8888 pitch less than min required
[10:55:38] [PASSED] ABGR8888 Invalid width
[10:55:38] [PASSED] ABGR8888 Invalid buffer handle
[10:55:38] [PASSED] No pixel format
[10:55:38] [PASSED] ABGR8888 Width 0
[10:55:38] [PASSED] ABGR8888 Height 0
[10:55:38] [PASSED] ABGR8888 Out of bound height * pitch combination
[10:55:38] [PASSED] ABGR8888 Large buffer offset
[10:55:38] [PASSED] ABGR8888 Buffer offset for inexistent plane
[10:55:38] [PASSED] ABGR8888 Invalid flag
[10:55:38] [PASSED] ABGR8888 Set DRM_MODE_FB_MODIFIERS without modifiers
[10:55:38] [PASSED] ABGR8888 Valid buffer modifier
[10:55:38] [PASSED] ABGR8888 Invalid buffer modifier(DRM_FORMAT_MOD_SAMSUNG_64_32_TILE)
[10:55:38] [PASSED] ABGR8888 Extra pitches without DRM_MODE_FB_MODIFIERS
[10:55:38] [PASSED] ABGR8888 Extra pitches with DRM_MODE_FB_MODIFIERS
[10:55:38] [PASSED] NV12 Normal sizes
[10:55:38] [PASSED] NV12 Max sizes
[10:55:38] [PASSED] NV12 Invalid pitch
[10:55:38] [PASSED] NV12 Invalid modifier/missing DRM_MODE_FB_MODIFIERS flag
[10:55:38] [PASSED] NV12 different  modifier per-plane
[10:55:38] [PASSED] NV12 with DRM_FORMAT_MOD_SAMSUNG_64_32_TILE
[10:55:38] [PASSED] NV12 Valid modifiers without DRM_MODE_FB_MODIFIERS
[10:55:38] [PASSED] NV12 Modifier for inexistent plane
[10:55:38] [PASSED] NV12 Handle for inexistent plane
[10:55:38] [PASSED] NV12 Handle for inexistent plane without DRM_MODE_FB_MODIFIERS
[10:55:38] [PASSED] YVU420 DRM_MODE_FB_MODIFIERS set without modifier
[10:55:38] [PASSED] YVU420 Normal sizes
[10:55:38] [PASSED] YVU420 Max sizes
[10:55:38] [PASSED] YVU420 Invalid pitch
[10:55:38] [PASSED] YVU420 Different pitches
[10:55:38] [PASSED] YVU420 Different buffer offsets/pitches
[10:55:38] [PASSED] YVU420 Modifier set just for plane 0, without DRM_MODE_FB_MODIFIERS
[10:55:38] [PASSED] YVU420 Modifier set just for planes 0, 1, without DRM_MODE_FB_MODIFIERS
[10:55:38] [PASSED] YVU420 Modifier set just for plane 0, 1, with DRM_MODE_FB_MODIFIERS
[10:55:38] [PASSED] YVU420 Valid modifier
[10:55:38] [PASSED] YVU420 Different modifiers per plane
[10:55:38] [PASSED] YVU420 Modifier for inexistent plane
[10:55:38] [PASSED] YUV420_10BIT Invalid modifier(DRM_FORMAT_MOD_LINEAR)
[10:55:38] [PASSED] X0L2 Normal sizes
[10:55:38] [PASSED] X0L2 Max sizes
[10:55:38] [PASSED] X0L2 Invalid pitch
[10:55:38] [PASSED] X0L2 Pitch greater than minimum required
[10:55:38] [PASSED] X0L2 Handle for inexistent plane
[10:55:38] [PASSED] X0L2 Offset for inexistent plane, without DRM_MODE_FB_MODIFIERS set
[10:55:38] [PASSED] X0L2 Modifier without DRM_MODE_FB_MODIFIERS set
[10:55:38] [PASSED] X0L2 Valid modifier
[10:55:38] [PASSED] X0L2 Modifier for inexistent plane
[10:55:38] =========== [PASSED] drm_test_framebuffer_create ===========
[10:55:38] [PASSED] drm_test_framebuffer_free
[10:55:38] [PASSED] drm_test_framebuffer_init
[10:55:38] [PASSED] drm_test_framebuffer_init_bad_format
[10:55:38] [PASSED] drm_test_framebuffer_init_dev_mismatch
[10:55:38] [PASSED] drm_test_framebuffer_lookup
[10:55:38] [PASSED] drm_test_framebuffer_lookup_inexistent
[10:55:38] [PASSED] drm_test_framebuffer_modifiers_not_supported
[10:55:38] ================= [PASSED] drm_framebuffer =================
[10:55:38] ================ drm_gem_shmem (8 subtests) ================
[10:55:38] [PASSED] drm_gem_shmem_test_obj_create
[10:55:38] [PASSED] drm_gem_shmem_test_obj_create_private
[10:55:38] [PASSED] drm_gem_shmem_test_pin_pages
[10:55:38] [PASSED] drm_gem_shmem_test_vmap
[10:55:38] [PASSED] drm_gem_shmem_test_get_sg_table
[10:55:38] [PASSED] drm_gem_shmem_test_get_pages_sgt
[10:55:38] [PASSED] drm_gem_shmem_test_madvise
[10:55:38] [PASSED] drm_gem_shmem_test_purge
[10:55:38] ================== [PASSED] drm_gem_shmem ==================
[10:55:38] === drm_atomic_helper_connector_hdmi_check (29 subtests) ===
[10:55:38] [PASSED] drm_test_check_broadcast_rgb_auto_cea_mode
[10:55:38] [PASSED] drm_test_check_broadcast_rgb_auto_cea_mode_vic_1
[10:55:38] [PASSED] drm_test_check_broadcast_rgb_full_cea_mode
[10:55:38] [PASSED] drm_test_check_broadcast_rgb_full_cea_mode_vic_1
[10:55:38] [PASSED] drm_test_check_broadcast_rgb_limited_cea_mode
[10:55:38] [PASSED] drm_test_check_broadcast_rgb_limited_cea_mode_vic_1
[10:55:38] ====== drm_test_check_broadcast_rgb_cea_mode_yuv420  =======
[10:55:38] [PASSED] Automatic
[10:55:38] [PASSED] Full
[10:55:38] [PASSED] Limited 16:235
[10:55:38] == [PASSED] drm_test_check_broadcast_rgb_cea_mode_yuv420 ===
[10:55:38] [PASSED] drm_test_check_broadcast_rgb_crtc_mode_changed
[10:55:38] [PASSED] drm_test_check_broadcast_rgb_crtc_mode_not_changed
[10:55:38] [PASSED] drm_test_check_disable_connector
[10:55:38] [PASSED] drm_test_check_hdmi_funcs_reject_rate
[10:55:38] [PASSED] drm_test_check_max_tmds_rate_bpc_fallback_rgb
[10:55:38] [PASSED] drm_test_check_max_tmds_rate_bpc_fallback_yuv420
[10:55:38] [PASSED] drm_test_check_max_tmds_rate_bpc_fallback_ignore_yuv422
[10:55:38] [PASSED] drm_test_check_max_tmds_rate_bpc_fallback_ignore_yuv420
[10:55:38] [PASSED] drm_test_check_driver_unsupported_fallback_yuv420
[10:55:38] [PASSED] drm_test_check_output_bpc_crtc_mode_changed
[10:55:38] [PASSED] drm_test_check_output_bpc_crtc_mode_not_changed
[10:55:38] [PASSED] drm_test_check_output_bpc_dvi
[10:55:38] [PASSED] drm_test_check_output_bpc_format_vic_1
[10:55:38] [PASSED] drm_test_check_output_bpc_format_display_8bpc_only
[10:55:38] [PASSED] drm_test_check_output_bpc_format_display_rgb_only
[10:55:38] [PASSED] drm_test_check_output_bpc_format_driver_8bpc_only
[10:55:38] [PASSED] drm_test_check_output_bpc_format_driver_rgb_only
[10:55:38] [PASSED] drm_test_check_tmds_char_rate_rgb_8bpc
[10:55:38] [PASSED] drm_test_check_tmds_char_rate_rgb_10bpc
[10:55:38] [PASSED] drm_test_check_tmds_char_rate_rgb_12bpc
[10:55:38] ============ drm_test_check_hdmi_color_format  =============
[10:55:38] [PASSED] AUTO -> RGB
[10:55:38] [PASSED] YCBCR422 -> YUV422
[10:55:38] [PASSED] YCBCR420 -> YUV420
[10:55:38] [PASSED] YCBCR444 -> YUV444
[10:55:38] [PASSED] RGB -> RGB
[10:55:38] ======== [PASSED] drm_test_check_hdmi_color_format =========
[10:55:38] ======== drm_test_check_hdmi_color_format_420_only  ========
[10:55:38] [PASSED] RGB should fail
[10:55:38] [PASSED] YUV444 should fail
[10:55:38] [PASSED] YUV422 should fail
[10:55:38] [PASSED] YUV420 should work
[10:55:38] ==== [PASSED] drm_test_check_hdmi_color_format_420_only ====
[10:55:38] ===== [PASSED] drm_atomic_helper_connector_hdmi_check ======
[10:55:38] === drm_atomic_helper_connector_hdmi_reset (6 subtests) ====
[10:55:38] [PASSED] drm_test_check_broadcast_rgb_value
[10:55:38] [PASSED] drm_test_check_bpc_8_value
[10:55:38] [PASSED] drm_test_check_bpc_10_value
[10:55:38] [PASSED] drm_test_check_bpc_12_value
[10:55:38] [PASSED] drm_test_check_format_value
[10:55:38] [PASSED] drm_test_check_tmds_char_value
[10:55:38] ===== [PASSED] drm_atomic_helper_connector_hdmi_reset ======
[10:55:38] = drm_atomic_helper_connector_hdmi_mode_valid (7 subtests) =
[10:55:38] [PASSED] drm_test_check_mode_valid
[10:55:38] [PASSED] drm_test_check_mode_valid_reject
[10:55:38] [PASSED] drm_test_check_mode_valid_reject_rate
[10:55:38] [PASSED] drm_test_check_mode_valid_reject_max_clock
[10:55:38] [PASSED] drm_test_check_mode_valid_yuv420_only_max_clock
[10:55:38] [PASSED] drm_test_check_mode_valid_reject_yuv420_only_connector
[10:55:38] [PASSED] drm_test_check_mode_valid_accept_yuv420_also_connector_rgb
[10:55:38] === [PASSED] drm_atomic_helper_connector_hdmi_mode_valid ===
[10:55:38] = drm_atomic_helper_connector_hdmi_infoframes (5 subtests) =
[10:55:38] [PASSED] drm_test_check_infoframes
[10:55:38] [PASSED] drm_test_check_reject_avi_infoframe
[10:55:38] [PASSED] drm_test_check_reject_hdr_infoframe_bpc_8
[10:55:38] [PASSED] drm_test_check_reject_hdr_infoframe_bpc_10
[10:55:38] [PASSED] drm_test_check_reject_audio_infoframe
[10:55:38] === [PASSED] drm_atomic_helper_connector_hdmi_infoframes ===
[10:55:38] ================= drm_managed (2 subtests) =================
[10:55:38] [PASSED] drm_test_managed_release_action
[10:55:38] [PASSED] drm_test_managed_run_action
[10:55:38] =================== [PASSED] drm_managed ===================
[10:55:38] =================== drm_mm (6 subtests) ====================
[10:55:38] [PASSED] drm_test_mm_init
[10:55:38] [PASSED] drm_test_mm_debug
[10:55:38] [PASSED] drm_test_mm_align32
[10:55:38] [PASSED] drm_test_mm_align64
[10:55:38] [PASSED] drm_test_mm_lowest
[10:55:38] [PASSED] drm_test_mm_highest
[10:55:38] ===================== [PASSED] drm_mm ======================
[10:55:38] ============= drm_modes_analog_tv (5 subtests) =============
[10:55:38] [PASSED] drm_test_modes_analog_tv_mono_576i
[10:55:38] [PASSED] drm_test_modes_analog_tv_ntsc_480i
[10:55:38] [PASSED] drm_test_modes_analog_tv_ntsc_480i_inlined
[10:55:38] [PASSED] drm_test_modes_analog_tv_pal_576i
[10:55:38] [PASSED] drm_test_modes_analog_tv_pal_576i_inlined
[10:55:38] =============== [PASSED] drm_modes_analog_tv ===============
[10:55:38] ============== drm_panic_helper (3 subtests) ===============
[10:55:38] ============= drm_test_panic_screen_user_map  ==============
[10:55:38] [PASSED] Panic screen user, mode: 1024 x 768 	XR24 little-endian (0x34325258)
[10:55:38] [PASSED] Panic screen user, mode: 494 x 494 	XR24 little-endian (0x34325258)
[10:55:38] [PASSED] Panic screen user, mode: 1920 x 1080 	XR24 little-endian (0x34325258)
[10:55:38] [PASSED] Panic screen user, mode: 1024 x 768 	RG16 little-endian (0x36314752)
[10:55:38] [PASSED] Panic screen user, mode: 1024 x 768 	RG24 little-endian (0x34324752)
[10:55:38] [PASSED] Panic screen kmsg, mode: 1024 x 768 	XR24 little-endian (0x34325258)
[10:55:38] [PASSED] Panic screen kmsg, mode: 494 x 494 	XR24 little-endian (0x34325258)
[10:55:38] [PASSED] Panic screen kmsg, mode: 1920 x 1080 	XR24 little-endian (0x34325258)
[10:55:38] [PASSED] Panic screen kmsg, mode: 1024 x 768 	RG16 little-endian (0x36314752)
[10:55:38] [PASSED] Panic screen kmsg, mode: 1024 x 768 	RG24 little-endian (0x34324752)
[10:55:38] ========= [PASSED] drm_test_panic_screen_user_map ==========
[10:55:38] ============= drm_test_panic_screen_user_page  =============
[10:55:38] [PASSED] Panic screen user, mode: 1024 x 768 	XR24 little-endian (0x34325258)
[10:55:38] [PASSED] Panic screen user, mode: 494 x 494 	XR24 little-endian (0x34325258)
[10:55:38] [PASSED] Panic screen user, mode: 1920 x 1080 	XR24 little-endian (0x34325258)
[10:55:38] [PASSED] Panic screen user, mode: 1024 x 768 	RG16 little-endian (0x36314752)
[10:55:38] [PASSED] Panic screen user, mode: 1024 x 768 	RG24 little-endian (0x34324752)
[10:55:38] [PASSED] Panic screen kmsg, mode: 1024 x 768 	XR24 little-endian (0x34325258)
[10:55:38] [PASSED] Panic screen kmsg, mode: 494 x 494 	XR24 little-endian (0x34325258)
[10:55:39] [PASSED] Panic screen kmsg, mode: 1920 x 1080 	XR24 little-endian (0x34325258)
[10:55:39] [PASSED] Panic screen kmsg, mode: 1024 x 768 	RG16 little-endian (0x36314752)
[10:55:39] [PASSED] Panic screen kmsg, mode: 1024 x 768 	RG24 little-endian (0x34324752)
[10:55:39] ========= [PASSED] drm_test_panic_screen_user_page =========
[10:55:39] ========== drm_test_panic_screen_user_set_pixel  ===========
[10:55:39] [PASSED] Panic screen user, mode: 1024 x 768 	XR24 little-endian (0x34325258)
[10:55:39] [PASSED] Panic screen user, mode: 494 x 494 	XR24 little-endian (0x34325258)
[10:55:39] [PASSED] Panic screen user, mode: 1920 x 1080 	XR24 little-endian (0x34325258)
[10:55:39] [PASSED] Panic screen user, mode: 1024 x 768 	RG16 little-endian (0x36314752)
[10:55:39] [PASSED] Panic screen user, mode: 1024 x 768 	RG24 little-endian (0x34324752)
[10:55:39] [PASSED] Panic screen kmsg, mode: 1024 x 768 	XR24 little-endian (0x34325258)
[10:55:39] [PASSED] Panic screen kmsg, mode: 494 x 494 	XR24 little-endian (0x34325258)
[10:55:39] [PASSED] Panic screen kmsg, mode: 1920 x 1080 	XR24 little-endian (0x34325258)
[10:55:39] [PASSED] Panic screen kmsg, mode: 1024 x 768 	RG16 little-endian (0x36314752)
[10:55:39] [PASSED] Panic screen kmsg, mode: 1024 x 768 	RG24 little-endian (0x34324752)
[10:55:39] ====== [PASSED] drm_test_panic_screen_user_set_pixel =======
[10:55:39] ================ [PASSED] drm_panic_helper =================
[10:55:39] ============== drm_plane_helper (2 subtests) ===============
[10:55:39] =============== drm_test_check_plane_state  ================
[10:55:39] [PASSED] clipping_simple
[10:55:39] [PASSED] clipping_rotate_reflect
[10:55:39] [PASSED] positioning_simple
[10:55:39] [PASSED] upscaling
[10:55:39] [PASSED] downscaling
[10:55:39] [PASSED] rounding1
[10:55:39] [PASSED] rounding2
[10:55:39] [PASSED] rounding3
[10:55:39] [PASSED] rounding4
[10:55:39] =========== [PASSED] drm_test_check_plane_state ============
[10:55:39] =========== drm_test_check_invalid_plane_state  ============
[10:55:39] [PASSED] positioning_invalid
[10:55:39] [PASSED] upscaling_invalid
[10:55:39] [PASSED] downscaling_invalid
[10:55:39] ======= [PASSED] drm_test_check_invalid_plane_state ========
[10:55:39] ================ [PASSED] drm_plane_helper =================
[10:55:39] ====== drm_connector_helper_tv_get_modes (1 subtest) =======
[10:55:39] ====== drm_test_connector_helper_tv_get_modes_check  =======
[10:55:39] [PASSED] None
[10:55:39] [PASSED] PAL
[10:55:39] [PASSED] NTSC
[10:55:39] [PASSED] Both, NTSC Default
[10:55:39] [PASSED] Both, PAL Default
[10:55:39] [PASSED] Both, NTSC Default, with PAL on command-line
[10:55:39] [PASSED] Both, PAL Default, with NTSC on command-line
[10:55:39] == [PASSED] drm_test_connector_helper_tv_get_modes_check ===
[10:55:39] ======== [PASSED] drm_connector_helper_tv_get_modes ========
[10:55:39] ================== drm_rect (9 subtests) ===================
[10:55:39] [PASSED] drm_test_rect_clip_scaled_div_by_zero
[10:55:39] [PASSED] drm_test_rect_clip_scaled_not_clipped
[10:55:39] [PASSED] drm_test_rect_clip_scaled_clipped
[10:55:39] [PASSED] drm_test_rect_clip_scaled_signed_vs_unsigned
[10:55:39] ================= drm_test_rect_intersect  =================
[10:55:39] [PASSED] top-left x bottom-right: 2x2+1+1 x 2x2+0+0
[10:55:39] [PASSED] top-right x bottom-left: 2x2+0+0 x 2x2+1-1
[10:55:39] [PASSED] bottom-left x top-right: 2x2+1-1 x 2x2+0+0
[10:55:39] [PASSED] bottom-right x top-left: 2x2+0+0 x 2x2+1+1
[10:55:39] [PASSED] right x left: 2x1+0+0 x 3x1+1+0
[10:55:39] [PASSED] left x right: 3x1+1+0 x 2x1+0+0
[10:55:39] [PASSED] up x bottom: 1x2+0+0 x 1x3+0-1
[10:55:39] [PASSED] bottom x up: 1x3+0-1 x 1x2+0+0
[10:55:39] [PASSED] touching corner: 1x1+0+0 x 2x2+1+1
[10:55:39] [PASSED] touching side: 1x1+0+0 x 1x1+1+0
[10:55:39] [PASSED] equal rects: 2x2+0+0 x 2x2+0+0
[10:55:39] [PASSED] inside another: 2x2+0+0 x 1x1+1+1
[10:55:39] [PASSED] far away: 1x1+0+0 x 1x1+3+6
[10:55:39] [PASSED] points intersecting: 0x0+5+10 x 0x0+5+10
[10:55:39] [PASSED] points not intersecting: 0x0+0+0 x 0x0+5+10
[10:55:39] ============= [PASSED] drm_test_rect_intersect =============
[10:55:39] ================ drm_test_rect_calc_hscale  ================
[10:55:39] [PASSED] normal use
[10:55:39] [PASSED] out of max range
[10:55:39] [PASSED] out of min range
[10:55:39] [PASSED] zero dst
[10:55:39] [PASSED] negative src
[10:55:39] [PASSED] negative dst
[10:55:39] ============ [PASSED] drm_test_rect_calc_hscale ============
[10:55:39] ================ drm_test_rect_calc_vscale  ================
[10:55:39] [PASSED] normal use
[10:55:39] [PASSED] out of max range
[10:55:39] [PASSED] out of min range
[10:55:39] [PASSED] zero dst
[10:55:39] [PASSED] negative src
[10:55:39] [PASSED] negative dst
[10:55:39] ============ [PASSED] drm_test_rect_calc_vscale ============
[10:55:39] ================== drm_test_rect_rotate  ===================
[10:55:39] [PASSED] reflect-x
[10:55:39] [PASSED] reflect-y
[10:55:39] [PASSED] rotate-0
[10:55:39] [PASSED] rotate-90
[10:55:39] [PASSED] rotate-180
[10:55:39] [PASSED] rotate-270
[10:55:39] ============== [PASSED] drm_test_rect_rotate ===============
[10:55:39] ================ drm_test_rect_rotate_inv  =================
[10:55:39] [PASSED] reflect-x
[10:55:39] [PASSED] reflect-y
[10:55:39] [PASSED] rotate-0
[10:55:39] [PASSED] rotate-90
[10:55:39] [PASSED] rotate-180
[10:55:39] [PASSED] rotate-270
[10:55:39] ============ [PASSED] drm_test_rect_rotate_inv =============
[10:55:39] ==================== [PASSED] drm_rect =====================
[10:55:39] ============ drm_sysfb_modeset_test (1 subtest) ============
[10:55:39] ============ drm_test_sysfb_build_fourcc_list  =============
[10:55:39] [PASSED] no native formats
[10:55:39] [PASSED] XRGB8888 as native format
[10:55:39] [PASSED] remove duplicates
[10:55:39] [PASSED] convert alpha formats
[10:55:39] [PASSED] random formats
[10:55:39] ======== [PASSED] drm_test_sysfb_build_fourcc_list =========
[10:55:39] ============= [PASSED] drm_sysfb_modeset_test ==============
[10:55:39] ================== drm_fixp (2 subtests) ===================
[10:55:39] [PASSED] drm_test_int2fixp
[10:55:39] [PASSED] drm_test_sm2fixp
[10:55:39] ==================== [PASSED] drm_fixp =====================
[10:55:39] ============================================================
[10:55:39] Testing complete. Ran 667 tests: passed: 667
[10:55:39] Elapsed time: 27.417s total, 1.749s configuring, 25.251s building, 0.411s 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 [10:55:39] Configuring KUnit Kernel ...
Regenerating .config ...
Populating config with:

$ make ARCH=um O=.kunit olddefconfig
[10:55:41] 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
[10:55:51] Starting KUnit Kernel (1/1)...
[10:55:51] ============================================================
Running tests with:
$ .kunit/linux kunit.enable=1 mem=1G console=tty kunit_shutdown=halt
[10:55:51] ================= ttm_device (5 subtests) ==================
[10:55:51] [PASSED] ttm_device_init_basic
[10:55:51] [PASSED] ttm_device_init_multiple
[10:55:51] [PASSED] ttm_device_fini_basic
[10:55:51] [PASSED] ttm_device_init_no_vma_man
[10:55:51] ================== ttm_device_init_pools  ==================
[10:55:51] [PASSED] No DMA allocations, no DMA32 required
[10:55:51] [PASSED] DMA allocations, DMA32 required
[10:55:51] [PASSED] No DMA allocations, DMA32 required
[10:55:51] [PASSED] DMA allocations, no DMA32 required
[10:55:51] ============== [PASSED] ttm_device_init_pools ==============
[10:55:51] =================== [PASSED] ttm_device ====================
[10:55:51] ================== ttm_pool (8 subtests) ===================
[10:55:51] ================== ttm_pool_alloc_basic  ===================
[10:55:51] [PASSED] One page
[10:55:51] [PASSED] More than one page
[10:55:51] [PASSED] Above the allocation limit
[10:55:51] [PASSED] One page, with coherent DMA mappings enabled
[10:55:51] [PASSED] Above the allocation limit, with coherent DMA mappings enabled
[10:55:51] ============== [PASSED] ttm_pool_alloc_basic ===============
[10:55:51] ============== ttm_pool_alloc_basic_dma_addr  ==============
[10:55:51] [PASSED] One page
[10:55:51] [PASSED] More than one page
[10:55:51] [PASSED] Above the allocation limit
[10:55:51] [PASSED] One page, with coherent DMA mappings enabled
[10:55:51] [PASSED] Above the allocation limit, with coherent DMA mappings enabled
[10:55:51] ========== [PASSED] ttm_pool_alloc_basic_dma_addr ==========
[10:55:51] [PASSED] ttm_pool_alloc_order_caching_match
[10:55:51] [PASSED] ttm_pool_alloc_caching_mismatch
[10:55:51] [PASSED] ttm_pool_alloc_order_mismatch
[10:55:51] [PASSED] ttm_pool_free_dma_alloc
[10:55:51] [PASSED] ttm_pool_free_no_dma_alloc
[10:55:51] [PASSED] ttm_pool_fini_basic
[10:55:51] ==================== [PASSED] ttm_pool =====================
[10:55:51] ================ ttm_resource (8 subtests) =================
[10:55:51] ================= ttm_resource_init_basic  =================
[10:55:51] [PASSED] Init resource in TTM_PL_SYSTEM
[10:55:51] [PASSED] Init resource in TTM_PL_VRAM
[10:55:51] [PASSED] Init resource in a private placement
[10:55:51] [PASSED] Init resource in TTM_PL_SYSTEM, set placement flags
[10:55:51] ============= [PASSED] ttm_resource_init_basic =============
[10:55:51] [PASSED] ttm_resource_init_pinned
[10:55:51] [PASSED] ttm_resource_fini_basic
[10:55:51] [PASSED] ttm_resource_manager_init_basic
[10:55:51] [PASSED] ttm_resource_manager_usage_basic
[10:55:51] [PASSED] ttm_resource_manager_set_used_basic
[10:55:51] [PASSED] ttm_sys_man_alloc_basic
[10:55:51] [PASSED] ttm_sys_man_free_basic
[10:55:51] ================== [PASSED] ttm_resource ===================
[10:55:51] =================== ttm_tt (15 subtests) ===================
[10:55:51] ==================== ttm_tt_init_basic  ====================
[10:55:51] [PASSED] Page-aligned size
[10:55:51] [PASSED] Extra pages requested
[10:55:51] ================ [PASSED] ttm_tt_init_basic ================
[10:55:51] [PASSED] ttm_tt_init_misaligned
[10:55:51] [PASSED] ttm_tt_fini_basic
[10:55:51] [PASSED] ttm_tt_fini_sg
[10:55:51] [PASSED] ttm_tt_fini_shmem
[10:55:51] [PASSED] ttm_tt_create_basic
[10:55:51] [PASSED] ttm_tt_create_invalid_bo_type
[10:55:51] [PASSED] ttm_tt_create_ttm_exists
[10:55:51] [PASSED] ttm_tt_create_failed
[10:55:51] [PASSED] ttm_tt_destroy_basic
[10:55:51] [PASSED] ttm_tt_populate_null_ttm
[10:55:51] [PASSED] ttm_tt_populate_populated_ttm
[10:55:51] [PASSED] ttm_tt_unpopulate_basic
[10:55:51] [PASSED] ttm_tt_unpopulate_empty_ttm
[10:55:51] [PASSED] ttm_tt_swapin_basic
[10:55:51] ===================== [PASSED] ttm_tt ======================
[10:55:51] =================== ttm_bo (14 subtests) ===================
[10:55:51] =========== ttm_bo_reserve_optimistic_no_ticket  ===========
[10:55:51] [PASSED] Cannot be interrupted and sleeps
[10:55:51] [PASSED] Cannot be interrupted, locks straight away
[10:55:51] [PASSED] Can be interrupted, sleeps
[10:55:51] ======= [PASSED] ttm_bo_reserve_optimistic_no_ticket =======
[10:55:51] [PASSED] ttm_bo_reserve_locked_no_sleep
[10:55:51] [PASSED] ttm_bo_reserve_no_wait_ticket
[10:55:51] [PASSED] ttm_bo_reserve_double_resv
[10:55:51] [PASSED] ttm_bo_reserve_interrupted
[10:55:51] [PASSED] ttm_bo_reserve_deadlock
[10:55:51] [PASSED] ttm_bo_unreserve_basic
[10:55:51] [PASSED] ttm_bo_unreserve_pinned
[10:55:51] [PASSED] ttm_bo_unreserve_bulk
[10:55:51] [PASSED] ttm_bo_fini_basic
[10:55:51] [PASSED] ttm_bo_fini_shared_resv
[10:55:51] [PASSED] ttm_bo_pin_basic
[10:55:51] [PASSED] ttm_bo_pin_unpin_resource
[10:55:51] [PASSED] ttm_bo_multiple_pin_one_unpin
[10:55:51] ===================== [PASSED] ttm_bo ======================
[10:55:51] ============== ttm_bo_validate (22 subtests) ===============
[10:55:51] ============== ttm_bo_init_reserved_sys_man  ===============
[10:55:51] [PASSED] Buffer object for userspace
[10:55:51] [PASSED] Kernel buffer object
[10:55:51] [PASSED] Shared buffer object
[10:55:51] ========== [PASSED] ttm_bo_init_reserved_sys_man ===========
[10:55:51] ============== ttm_bo_init_reserved_mock_man  ==============
[10:55:51] [PASSED] Buffer object for userspace
[10:55:51] [PASSED] Kernel buffer object
[10:55:51] [PASSED] Shared buffer object
[10:55:51] ========== [PASSED] ttm_bo_init_reserved_mock_man ==========
[10:55:51] [PASSED] ttm_bo_init_reserved_resv
[10:55:51] ================== ttm_bo_validate_basic  ==================
[10:55:51] [PASSED] Buffer object for userspace
[10:55:51] [PASSED] Kernel buffer object
[10:55:51] [PASSED] Shared buffer object
[10:55:51] ============== [PASSED] ttm_bo_validate_basic ==============
[10:55:51] [PASSED] ttm_bo_validate_invalid_placement
[10:55:51] ============= ttm_bo_validate_same_placement  ==============
[10:55:51] [PASSED] System manager
[10:55:51] [PASSED] VRAM manager
[10:55:51] ========= [PASSED] ttm_bo_validate_same_placement ==========
[10:55:51] [PASSED] ttm_bo_validate_failed_alloc
[10:55:51] [PASSED] ttm_bo_validate_pinned
[10:55:51] [PASSED] ttm_bo_validate_busy_placement
[10:55:51] ================ ttm_bo_validate_multihop  =================
[10:55:51] [PASSED] Buffer object for userspace
[10:55:51] [PASSED] Kernel buffer object
[10:55:51] [PASSED] Shared buffer object
[10:55:51] ============ [PASSED] ttm_bo_validate_multihop =============
[10:55:51] ========== ttm_bo_validate_no_placement_signaled  ==========
[10:55:51] [PASSED] Buffer object in system domain, no page vector
[10:55:51] [PASSED] Buffer object in system domain with an existing page vector
[10:55:51] ====== [PASSED] ttm_bo_validate_no_placement_signaled ======
[10:55:51] ======== ttm_bo_validate_no_placement_not_signaled  ========
[10:55:51] [PASSED] Buffer object for userspace
[10:55:51] [PASSED] Kernel buffer object
[10:55:51] [PASSED] Shared buffer object
[10:55:51] ==== [PASSED] ttm_bo_validate_no_placement_not_signaled ====
[10:55:51] [PASSED] ttm_bo_validate_move_fence_signaled
[10:55:51] ========= ttm_bo_validate_move_fence_not_signaled  =========
[10:55:51] [PASSED] Waits for GPU
[10:55:51] [PASSED] Tries to lock straight away
[10:55:51] ===== [PASSED] ttm_bo_validate_move_fence_not_signaled =====
[10:55:51] [PASSED] ttm_bo_validate_swapout
[10:55:51] [PASSED] ttm_bo_validate_happy_evict
[10:55:51] [PASSED] ttm_bo_validate_all_pinned_evict
[10:55:51] [PASSED] ttm_bo_validate_allowed_only_evict
[10:55:51] [PASSED] ttm_bo_validate_deleted_evict
[10:55:51] [PASSED] ttm_bo_validate_busy_domain_evict
[10:55:51] [PASSED] ttm_bo_validate_evict_gutting
[10:55:51] [PASSED] ttm_bo_validate_recrusive_evict
[10:55:51] ================= [PASSED] ttm_bo_validate =================
[10:55:51] ============================================================
[10:55:51] Testing complete. Ran 102 tests: passed: 102
[10:55:51] Elapsed time: 12.218s total, 1.886s configuring, 10.117s building, 0.174s running

+ for kcfg in "${kunitconfigs[@]}"
+ [[ ! -f /kernel/drivers/dma-buf/.kunitconfig ]]
+ /kernel/tools/testing/kunit/kunit.py run --kunitconfig /kernel/drivers/dma-buf/.kunitconfig [10:55:51] Configuring KUnit Kernel ...
Regenerating .config ...
Populating config with:

$ make ARCH=um O=.kunit olddefconfig
[10:55:53] 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
[10:56:02] Starting KUnit Kernel (1/1)...
[10:56:02] ============================================================
Running tests with:
$ .kunit/linux kunit.enable=1 mem=1G console=tty kunit_shutdown=halt
[10:56:02] =============== dma-buf-fence (12 subtests) ================
[10:56:02] [PASSED] test_sanitycheck
[10:56:02] [PASSED] test_signaling
[10:56:02] [PASSED] test_add_callback
[10:56:02] [PASSED] test_late_add_callback
[10:56:02] [PASSED] test_rm_callback
[10:56:02] [PASSED] test_late_rm_callback
[10:56:02] [PASSED] test_status
[10:56:02] [PASSED] test_error
[10:56:02] [PASSED] test_wait
[10:56:02] [PASSED] test_wait_timeout
[10:56:02] [PASSED] test_stub
[10:56:02] [SKIPPED] test_race_signal_callback (requires at least 2 CPUs)
[10:56:02] ================== [PASSED] dma-buf-fence ==================
[10:56:02] ============ dma-buf-fence-chain (11 subtests) =============
[10:56:02] [PASSED] test_sanitycheck
[10:56:02] [PASSED] test_find_seqno
[10:56:02] [PASSED] test_find_signaled
[10:56:02] [PASSED] test_find_out_of_order
[10:56:07] [PASSED] test_find_gap
[10:56:07] [PASSED] test_find_race
[10:56:07] [PASSED] test_signal_forward
[10:56:07] [PASSED] test_signal_backward
[10:56:07] [PASSED] test_wait_forward
[10:56:07] [PASSED] test_wait_backward
[10:56:07] [PASSED] test_wait_random
[10:56:07] =============== [PASSED] dma-buf-fence-chain ===============
[10:56:07] ============ dma-buf-fence-unwrap (10 subtests) ============
[10:56:07] [PASSED] test_sanitycheck
[10:56:07] [PASSED] test_unwrap_array
[10:56:07] [PASSED] test_unwrap_chain
[10:56:07] [PASSED] test_unwrap_chain_array
[10:56:07] [PASSED] test_unwrap_merge
[10:56:07] [PASSED] test_unwrap_merge_duplicate
[10:56:07] [PASSED] test_unwrap_merge_seqno
[10:56:07] [PASSED] test_unwrap_merge_order
[10:56:07] [PASSED] test_unwrap_merge_complex
[10:56:07] [PASSED] test_unwrap_merge_complex_seqno
[10:56:07] ============== [PASSED] dma-buf-fence-unwrap ===============
[10:56:07] ================ dma-buf-resv (5 subtests) =================
[10:56:07] [PASSED] test_sanitycheck
[10:56:07] ===================== test_signaling  ======================
[10:56:07] [PASSED] kernel
[10:56:07] [PASSED] write
[10:56:07] [PASSED] read
[10:56:07] [PASSED] bookkeep
[10:56:07] ================= [PASSED] test_signaling ==================
[10:56:07] ====================== test_for_each  ======================
[10:56:07] [PASSED] kernel
[10:56:07] [PASSED] write
[10:56:07] [PASSED] read
[10:56:07] [PASSED] bookkeep
[10:56:07] ================== [PASSED] test_for_each ==================
[10:56:07] ================= test_for_each_unlocked  ==================
[10:56:07] [PASSED] kernel
[10:56:07] [PASSED] write
[10:56:07] [PASSED] read
[10:56:07] [PASSED] bookkeep
[10:56:07] ============= [PASSED] test_for_each_unlocked ==============
[10:56:07] ===================== test_get_fences  =====================
[10:56:07] [PASSED] kernel
[10:56:07] [PASSED] write
[10:56:07] [PASSED] read
[10:56:07] [PASSED] bookkeep
[10:56:07] ================= [PASSED] test_get_fences =================
[10:56:07] ================== [PASSED] dma-buf-resv ===================
[10:56:07] ============================================================
[10:56:07] Testing complete. Ran 50 tests: passed: 49, skipped: 1
[10:56:07] Elapsed time: 15.916s total, 1.864s configuring, 8.731s building, 5.270s running

+ cleanup
++ stat -c %u:%g /kernel
+ chown -R 1003:1003 /kernel

#46 lore raw

✗ Xe.CI.BAT: failure for Add CPER logging support for CRI (rev4)

In reply to Badal Nilawar
== Series Details ==

== Series Details ==

Series: Add CPER logging support for CRI (rev4)
URL : https://patchwork.freedesktop.org/series/169692/
State : failure

== Summary ==

CI Bug Log - changes from xe-5915-3bd4f625aafdf70814dbf075de96e224355c9f1e_BAT -> xe-pw-169692v4_BAT
====================================================

Summary
-------

**FAILURE**

Serious unknown changes coming with xe-pw-169692v4_BAT absolutely need to be verified manually.

If you think the reported changes have nothing to do with the changes
introduced in xe-pw-169692v4_BAT, please notify your bug team ([email protected]) to allow them to document this new failure mode, which will reduce false positives in CI.

Participating hosts (14 -> 14)
------------------------------

No changes in participating hosts

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

Here are the unknown changes that may have been introduced in xe-pw-169692v4_BAT:

### IGT changes ###

#### Possible regressions ####

* igt@xe_exec_fault_mode@twice-bindexecqueue-prefetch:
- bat-wcl-1: [PASS][1] -> [FAIL][2]
[1]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-5915-3bd4f625aafdf70814dbf075de96e224355c9f1e/bat-wcl-1/igt@[email protected]
[2]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/bat-wcl-1/igt@[email protected]

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

* Linux: xe-5915-3bd4f625aafdf70814dbf075de96e224355c9f1e -> xe-pw-169692v4

IGT_9138: 9138
xe-5915-3bd4f625aafdf70814dbf075de96e224355c9f1e: 3bd4f625aafdf70814dbf075de96e224355c9f1e
xe-pw-169692v4: 169692v4

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/index.html

#47 lore raw

✓ Xe.CI.FULL: success for Add CPER logging support for CRI (rev4)

In reply to Badal Nilawar
== Series Details ==

== Series Details ==

Series: Add CPER logging support for CRI (rev4)
URL : https://patchwork.freedesktop.org/series/169692/
State : success

== Summary ==

CI Bug Log - changes from xe-5915-3bd4f625aafdf70814dbf075de96e224355c9f1e_FULL -> xe-pw-169692v4_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-169692v4_FULL that come from known issues:

### IGT changes ###

#### Issues hit ####

* igt@kms_async_flips@async-flip-suspend-resume@pipe-a-edp-1:
- shard-ptl: [PASS][1] -> [ABORT][2] ([Intel XE#9362]) +6 other tests abort
[1]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-5915-3bd4f625aafdf70814dbf075de96e224355c9f1e/shard-ptl-4/igt@kms_async_flips@[email protected]
[2]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-2/igt@kms_async_flips@[email protected]

* igt@kms_atomic_transition@plane-all-modeset-transition:
- shard-ptl: NOTRUN -> [SKIP][3] ([Intel XE#5947])
[3]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-4/igt@[email protected]

* igt@kms_big_fb@4-tiled-8bpp-rotate-90:
- shard-bmg: NOTRUN -> [SKIP][4] ([Intel XE#2327]) +4 other tests skip
[4]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-10/igt@[email protected]
- shard-lnl: NOTRUN -> [SKIP][5] ([Intel XE#1407]) +1 other test skip
[5]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-lnl-7/igt@[email protected]

* igt@kms_big_fb@linear-16bpp-rotate-270:
- shard-ptl: NOTRUN -> [SKIP][6] ([Intel XE#5901]) +1 other test skip
[6]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-8/igt@[email protected]

* igt@kms_big_fb@linear-max-hw-stride-32bpp-rotate-180-hflip:
- shard-ptl: NOTRUN -> [SKIP][7] ([Intel XE#7085])
[7]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-4/igt@[email protected]

* igt@kms_big_fb@y-tiled-16bpp-rotate-90:
- shard-lnl: NOTRUN -> [SKIP][8] ([Intel XE#1124]) +1 other test skip
[8]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-lnl-7/igt@[email protected]

* igt@kms_big_fb@y-tiled-addfb-size-offset-overflow:
- shard-ptl: NOTRUN -> [SKIP][9] ([Intel XE#5851])
[9]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-8/igt@[email protected]

* igt@kms_big_fb@y-tiled-max-hw-stride-32bpp-rotate-180-async-flip:
- shard-bmg: NOTRUN -> [SKIP][10] ([Intel XE#1124]) +9 other tests skip
[10]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-7/igt@kms_big_fb@y-tiled-max-hw-stride-32bpp-rotate-180-async-flip.html

* igt@kms_big_fb@yf-tiled-64bpp-rotate-180:
- shard-ptl: NOTRUN -> [SKIP][11] ([Intel XE#5808]) +14 other tests skip
[11]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-5/igt@[email protected]

* igt@kms_big_fb@yf-tiled-addfb-size-overflow:
- shard-bmg: NOTRUN -> [SKIP][12] ([Intel XE#610] / [Intel XE#7387])
[12]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-1/igt@[email protected]

* igt@kms_bw@connected-linear-tiling-4-displays-target-1920x1080p:
- shard-bmg: NOTRUN -> [SKIP][13] ([Intel XE#7679]) +2 other tests skip
[13]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-7/igt@[email protected]
- shard-ptl: NOTRUN -> [SKIP][14] ([Intel XE#7679]) +1 other test skip
[14]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-8/igt@[email protected]

* igt@kms_bw@linear-tiling-3-displays-target-2560x1440p:
- shard-ptl: NOTRUN -> [SKIP][15] ([Intel XE#367]) +1 other test skip
[15]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-5/igt@[email protected]

* igt@kms_bw@linear-tiling-4-displays-target-2560x1440p:
- shard-bmg: NOTRUN -> [SKIP][16] ([Intel XE#367])
[16]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-5/igt@[email protected]

* igt@kms_ccs@bad-rotation-90-4-tiled-bmg-ccs@pipe-c-edp-1:
- shard-ptl: NOTRUN -> [SKIP][17] ([Intel XE#5823] / [Intel XE#6918]) +4 other tests skip
[17]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-8/igt@kms_ccs@[email protected]

* igt@kms_ccs@bad-rotation-90-y-tiled-gen12-rc-ccs-cc:
- shard-bmg: NOTRUN -> [SKIP][18] ([Intel XE#2887]) +13 other tests skip
[18]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-5/igt@[email protected]

* igt@kms_ccs@crc-primary-rotation-180-4-tiled-mtl-mc-ccs:
- shard-ptl: NOTRUN -> [SKIP][19] ([Intel XE#5822]) +12 other tests skip
[19]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-5/igt@[email protected]

* igt@kms_ccs@crc-primary-suspend-4-tiled-lnl-ccs@pipe-a-dp-2:
- shard-bmg: NOTRUN -> [SKIP][20] ([Intel XE#2652]) +8 other tests skip
[20]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-1/igt@kms_ccs@[email protected]

* igt@kms_ccs@crc-primary-suspend-y-tiled-ccs:
- shard-bmg: NOTRUN -> [SKIP][21] ([Intel XE#3432])
[21]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-6/igt@[email protected]

* igt@kms_ccs@missing-ccs-buffer-y-tiled-gen12-rc-ccs-cc:
- shard-lnl: NOTRUN -> [SKIP][22] ([Intel XE#2887]) +4 other tests skip
[22]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-lnl-7/igt@[email protected]

* igt@kms_chamelium_color@ctm-blue-to-red:
- shard-lnl: NOTRUN -> [SKIP][23] ([Intel XE#306] / [Intel XE#7358])
[23]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-lnl-7/igt@[email protected]

* igt@kms_chamelium_color@degamma:
- shard-ptl: NOTRUN -> [SKIP][24] ([Intel XE#5824])
[24]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-8/igt@[email protected]

* igt@kms_chamelium_color@gamma:
- shard-bmg: NOTRUN -> [SKIP][25] ([Intel XE#2325] / [Intel XE#7358])
[25]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-6/igt@[email protected]

* igt@kms_chamelium_color_pipeline@plane-ctm3x4:
- shard-ptl: NOTRUN -> [SKIP][26] ([Intel XE#8391]) +1 other test skip
[26]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-8/igt@[email protected]

* igt@kms_chamelium_color_pipeline@plane-lut1d:
- shard-bmg: NOTRUN -> [SKIP][27] ([Intel XE#7358]) +1 other test skip
[27]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-1/igt@[email protected]

* igt@kms_chamelium_edid@dp-edid-change-during-hibernate:
- shard-bmg: NOTRUN -> [SKIP][28] ([Intel XE#2252]) +8 other tests skip
[28]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-10/igt@[email protected]

* igt@kms_chamelium_frames@hdmi-crc-nonplanar-formats:
- shard-ptl: NOTRUN -> [SKIP][29] ([Intel XE#2252]) +3 other tests skip
[29]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-8/igt@[email protected]

* igt@kms_chamelium_hpd@hdmi-hpd-storm:
- shard-lnl: NOTRUN -> [SKIP][30] ([Intel XE#373]) +2 other tests skip
[30]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-lnl-7/igt@[email protected]

* igt@kms_color_pipeline@plane-lut1d-ctm3x4-lut1d@pipe-c-plane-4:
- shard-lnl: NOTRUN -> [SKIP][31] ([Intel XE#6969]) +5 other tests skip
[31]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-lnl-7/igt@kms_color_pipeline@[email protected]

* igt@kms_color_pipeline@plane-lut1d-lut1d@pipe-b-plane-3:
- shard-ptl: NOTRUN -> [SKIP][32] ([Intel XE#6969]) +7 other tests skip
[32]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-4/igt@kms_color_pipeline@[email protected]

* igt@kms_content_protection@dp-mst-type-0-suspend-resume:
- shard-lnl: NOTRUN -> [SKIP][33] ([Intel XE#6974])
[33]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-lnl-7/igt@[email protected]

* igt@kms_content_protection@dp-mst-type-1:
- shard-bmg: NOTRUN -> [SKIP][34] ([Intel XE#2390] / [Intel XE#6974])
[34]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-6/igt@[email protected]

* igt@kms_content_protection@legacy@pipe-a-dp-1:
- shard-bmg: NOTRUN -> [FAIL][35] ([Intel XE#3304])
[35]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-7/igt@kms_content_protection@[email protected]

* igt@kms_content_protection@lic-type-0-hdcp14@pipe-a-dp-2:
- shard-bmg: NOTRUN -> [FAIL][36] ([Intel XE#1178] / [Intel XE#3304] / [Intel XE#7374]) +3 other tests fail
[36]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-5/igt@kms_content_protection@[email protected]

* igt@kms_content_protection@lic-type-1:
- shard-ptl: NOTRUN -> [SKIP][37] ([Intel XE#7642]) +2 other tests skip
[37]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-4/igt@[email protected]

* igt@kms_content_protection@uevent:
- shard-bmg: NOTRUN -> [FAIL][38] ([Intel XE#6707] / [Intel XE#7439]) +1 other test fail
[38]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-1/igt@[email protected]

* igt@kms_cursor_crc@cursor-offscreen-32x32:
- shard-bmg: NOTRUN -> [SKIP][39] ([Intel XE#2320]) +4 other tests skip
[39]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-7/igt@[email protected]

* igt@kms_cursor_crc@cursor-onscreen-512x512:
- shard-ptl: NOTRUN -> [SKIP][40] ([Intel XE#5846])
[40]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-5/igt@[email protected]

* igt@kms_cursor_crc@cursor-random-512x170:
- shard-bmg: NOTRUN -> [SKIP][41] ([Intel XE#2321] / [Intel XE#7355]) +1 other test skip
[41]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-1/igt@[email protected]

* igt@kms_cursor_crc@cursor-random-max-size:
- shard-ptl: NOTRUN -> [SKIP][42] ([Intel XE#5900]) +2 other tests skip
[42]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-4/igt@[email protected]

* igt@kms_cursor_crc@cursor-rapid-movement-64x21:
- shard-lnl: NOTRUN -> [SKIP][43] ([Intel XE#1424]) +1 other test skip
[43]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-lnl-7/igt@[email protected]

* igt@kms_cursor_legacy@2x-cursor-vs-flip-atomic:
- shard-lnl: NOTRUN -> [SKIP][44] ([Intel XE#309] / [Intel XE#7343])
[44]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-lnl-7/igt@[email protected]

* igt@kms_cursor_legacy@cursorb-vs-flipa-atomic-transitions-varying-size:
- shard-ptl: NOTRUN -> [SKIP][45] ([Intel XE#5962]) +1 other test skip
[45]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-8/igt@kms_cursor_legacy@cursorb-vs-flipa-atomic-transitions-varying-size.html

* igt@kms_cursor_legacy@cursorb-vs-flipb-atomic-transitions:
- shard-ptl: NOTRUN -> [SKIP][46] ([Intel XE#5962] / [Intel XE#7343])
[46]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-5/igt@[email protected]

* igt@kms_dp_link_training@non-uhbr-mst:
- shard-lnl: NOTRUN -> [SKIP][47] ([Intel XE#9536])
[47]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-lnl-7/igt@[email protected]

* igt@kms_dsc@dsc-fractional-bpp-ultrajoiner:
- shard-lnl: NOTRUN -> [SKIP][48] ([Intel XE#8265])
[48]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-lnl-7/igt@[email protected]

* igt@kms_dsc@dsc-with-bpc-formats-bigjoiner:
- shard-bmg: NOTRUN -> [SKIP][49] ([Intel XE#8265]) +1 other test skip
[49]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-5/igt@[email protected]

* igt@kms_dsc@dsc-with-bpc-ultrajoiner:
- shard-ptl: NOTRUN -> [SKIP][50] ([Intel XE#5907]) +2 other tests skip
[50]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-4/igt@[email protected]

* igt@kms_feature_discovery@chamelium:
- shard-bmg: NOTRUN -> [SKIP][51] ([Intel XE#2372] / [Intel XE#7359])
[51]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-1/igt@[email protected]

* igt@kms_feature_discovery@psr1:
- shard-bmg: NOTRUN -> [SKIP][52] ([Intel XE#2374] / [Intel XE#6127])
[52]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-6/igt@[email protected]

* igt@kms_flip@2x-absolute-wf_vblank-interruptible:
- shard-ptl: NOTRUN -> [SKIP][53] ([Intel XE#2316]) +5 other tests skip
[53]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-8/igt@kms_flip@2x-absolute-wf_vblank-interruptible.html

* igt@kms_flip@2x-flip-vs-expired-vblank:
- shard-lnl: NOTRUN -> [SKIP][54] ([Intel XE#1421]) +2 other tests skip
[54]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-lnl-7/igt@[email protected]

* igt@kms_flip@2x-plain-flip-fb-recreate:
- shard-bmg: NOTRUN -> [FAIL][55] ([Intel XE#5408] / [Intel XE#6266]) +1 other test fail
[55]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-8/igt@[email protected]

* igt@kms_flip@flip-vs-expired-vblank@a-edp1:
- shard-lnl: [PASS][56] -> [FAIL][57] ([Intel XE#301])
[56]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-5915-3bd4f625aafdf70814dbf075de96e224355c9f1e/shard-lnl-3/igt@kms_flip@[email protected]
[57]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-lnl-3/igt@kms_flip@[email protected]

* igt@kms_flip_scaled_crc@flip-32bpp-4tile-to-32bpp-4tiledg2rcccs-downscaling:
- shard-ptl: NOTRUN -> [SKIP][58] ([Intel XE#7178]) +2 other tests skip
[58]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-4/igt@kms_flip_scaled_crc@flip-32bpp-4tile-to-32bpp-4tiledg2rcccs-downscaling.html

* igt@kms_flip_scaled_crc@flip-32bpp-ytile-to-64bpp-ytile-upscaling:
- shard-lnl: NOTRUN -> [SKIP][59] ([Intel XE#7178] / [Intel XE#7351])
[59]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-lnl-7/igt@kms_flip_scaled_crc@flip-32bpp-ytile-to-64bpp-ytile-upscaling.html

* igt@kms_flip_scaled_crc@flip-64bpp-4tile-to-32bpp-4tile-downscaling@pipe-a-default-mode:
- shard-ptl: NOTRUN -> [SKIP][60] ([Intel XE#5828]) +3 other tests skip
[60]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-8/igt@kms_flip_scaled_crc@flip-64bpp-4tile-to-32bpp-4tile-downscaling@pipe-a-default-mode.html

* igt@kms_flip_scaled_crc@flip-64bpp-4tile-to-32bpp-4tiledg2rcccs-upscaling:
- shard-bmg: NOTRUN -> [SKIP][61] ([Intel XE#7178] / [Intel XE#7349])
[61]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-6/igt@kms_flip_scaled_crc@flip-64bpp-4tile-to-32bpp-4tiledg2rcccs-upscaling.html

* igt@kms_flip_scaled_crc@flip-64bpp-ytile-to-16bpp-ytile-downscaling:
- shard-bmg: NOTRUN -> [SKIP][62] ([Intel XE#7178] / [Intel XE#7351])
[62]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-6/igt@kms_flip_scaled_crc@flip-64bpp-ytile-to-16bpp-ytile-downscaling.html

* igt@kms_flip_scaled_crc@flip-p016-linear-to-p016-linear-reflect-x:
- shard-bmg: NOTRUN -> [SKIP][63] ([Intel XE#7179])
[63]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-10/igt@kms_flip_scaled_crc@flip-p016-linear-to-p016-linear-reflect-x.html
- shard-lnl: NOTRUN -> [SKIP][64] ([Intel XE#7179])
[64]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-lnl-7/igt@kms_flip_scaled_crc@flip-p016-linear-to-p016-linear-reflect-x.html

* igt@kms_frontbuffer_tracking@drrs-1p-primscrn-pri-shrfb-draw-mmap-wc:
- shard-lnl: NOTRUN -> [SKIP][65] ([Intel XE#6312] / [Intel XE#651]) +3 other tests skip
[65]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-lnl-7/igt@kms_frontbuffer_tracking@drrs-1p-primscrn-pri-shrfb-draw-mmap-wc.html

* igt@kms_frontbuffer_tracking@drrs-1p-primscrn-spr-indfb-onoff:
- shard-ptl: NOTRUN -> [SKIP][66] ([Intel XE#5800] / [Intel XE#6312]) +10 other tests skip
[66]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-5/igt@[email protected]

* igt@kms_frontbuffer_tracking@drrs-argb161616f-draw-render:
- shard-lnl: NOTRUN -> [SKIP][67] ([Intel XE#7061] / [Intel XE#7356])
[67]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-lnl-7/igt@[email protected]

* igt@kms_frontbuffer_tracking@drrshdr-1p-primscrn-indfb-msflip-blt:
- shard-ptl: NOTRUN -> [SKIP][68] ([Intel XE#6312]) +10 other tests skip
[68]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-8/igt@kms_frontbuffer_tracking@drrshdr-1p-primscrn-indfb-msflip-blt.html

* igt@kms_frontbuffer_tracking@drrshdr-1p-primscrn-shrfb-pgflip-blt:
- shard-lnl: NOTRUN -> [SKIP][69] ([Intel XE#6312]) +2 other tests skip
[69]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-lnl-7/igt@kms_frontbuffer_tracking@drrshdr-1p-primscrn-shrfb-pgflip-blt.html

* igt@kms_frontbuffer_tracking@drrshdr-2p-scndscrn-spr-indfb-draw-blt:
- shard-bmg: NOTRUN -> [SKIP][70] ([Intel XE#2311]) +49 other tests skip
[70]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-6/igt@kms_frontbuffer_tracking@drrshdr-2p-scndscrn-spr-indfb-draw-blt.html

* igt@kms_frontbuffer_tracking@fbc-2p-scndscrn-spr-indfb-onoff:
- shard-bmg: NOTRUN -> [SKIP][71] ([Intel XE#4141]) +12 other tests skip
[71]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-6/igt@[email protected]

* igt@kms_frontbuffer_tracking@fbcdrrs-abgr161616f-draw-blt:
- shard-ptl: NOTRUN -> [SKIP][72] ([Intel XE#7061] / [Intel XE#7356]) +1 other test skip
[72]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-4/igt@[email protected]

* igt@kms_frontbuffer_tracking@fbcdrrs-argb161616f-draw-mmap-wc:
- shard-bmg: NOTRUN -> [SKIP][73] ([Intel XE#7061] / [Intel XE#7356]) +4 other tests skip
[73]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-6/igt@[email protected]

* igt@kms_frontbuffer_tracking@fbchdr-argb161616f-draw-mmap-wc:
- shard-ptl: NOTRUN -> [SKIP][74] ([Intel XE#7061]) +1 other test skip
[74]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-8/igt@[email protected]

* igt@kms_frontbuffer_tracking@fbchdr-argb161616f-draw-render:
- shard-bmg: NOTRUN -> [SKIP][75] ([Intel XE#7061]) +9 other tests skip
[75]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-1/igt@[email protected]

* igt@kms_frontbuffer_tracking@fbcpsr-2p-primscrn-cur-indfb-onoff:
- shard-ptl: NOTRUN -> [SKIP][76] ([Intel XE#5812]) +63 other tests skip
[76]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-8/igt@[email protected]

* igt@kms_frontbuffer_tracking@fbcpsr-2p-scndscrn-spr-indfb-draw-mmap-wc:
- shard-lnl: NOTRUN -> [SKIP][77] ([Intel XE#656] / [Intel XE#7905]) +8 other tests skip
[77]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-lnl-7/igt@kms_frontbuffer_tracking@fbcpsr-2p-scndscrn-spr-indfb-draw-mmap-wc.html

* igt@kms_frontbuffer_tracking@fbcpsrhdr-2p-scndscrn-shrfb-msflip-blt:
- shard-lnl: NOTRUN -> [SKIP][78] ([Intel XE#7905]) +12 other tests skip
[78]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-lnl-7/igt@kms_frontbuffer_tracking@fbcpsrhdr-2p-scndscrn-shrfb-msflip-blt.html

* igt@kms_frontbuffer_tracking@hdr-1p-offscreen-pri-shrfb-draw-mmap-wc:
- shard-lnl: NOTRUN -> [SKIP][79] ([Intel XE#7865]) +3 other tests skip
[79]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-lnl-7/igt@kms_frontbuffer_tracking@hdr-1p-offscreen-pri-shrfb-draw-mmap-wc.html

* igt@kms_frontbuffer_tracking@hdr-1p-primscrn-pri-indfb-draw-blt:
- shard-ptl: NOTRUN -> [SKIP][80] ([Intel XE#7865]) +21 other tests skip
[80]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-8/igt@[email protected]

* igt@kms_frontbuffer_tracking@psrhdr-2p-scndscrn-pri-indfb-draw-mmap-wc:
- shard-bmg: NOTRUN -> [SKIP][81] ([Intel XE#2313]) +40 other tests skip
[81]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-1/igt@kms_frontbuffer_tracking@psrhdr-2p-scndscrn-pri-indfb-draw-mmap-wc.html

* igt@kms_frontbuffer_tracking@psrhdr-abgr161616f-draw-mmap-wc:
- shard-lnl: NOTRUN -> [SKIP][82] ([Intel XE#7061]) +1 other test skip
[82]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-lnl-7/igt@[email protected]

* igt@kms_hdmi_audio_bw@dpms-audio-recovery:
- shard-lnl: NOTRUN -> [SKIP][83] ([Intel XE#9312])
[83]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-lnl-7/igt@[email protected]

* igt@kms_hdr@static-toggle:
- shard-ptl: NOTRUN -> [SKIP][84] ([Intel XE#5917] / [Intel XE#6174])
[84]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-8/igt@[email protected]

* igt@kms_multipipe_modeset@basic-max-pipe-crc-check:
- shard-bmg: NOTRUN -> [SKIP][85] ([Intel XE#7591])
[85]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-1/igt@[email protected]

* igt@kms_plane@pixel-format-4-tiled-mtl-mc-ccs-modifier-source-clamping:
- shard-ptl: NOTRUN -> [SKIP][86] ([Intel XE#7283]) +4 other tests skip
[86]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-4/igt@kms_plane@pixel-format-4-tiled-mtl-mc-ccs-modifier-source-clamping.html

* igt@kms_plane@pixel-format-4-tiled-mtl-rc-ccs-cc-modifier:
- shard-lnl: NOTRUN -> [SKIP][87] ([Intel XE#7283]) +1 other test skip
[87]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-lnl-7/igt@[email protected]

* igt@kms_plane@pixel-format-yf-tiled-ccs-modifier-source-clamping:
- shard-bmg: NOTRUN -> [SKIP][88] ([Intel XE#7283]) +1 other test skip
[88]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-6/igt@kms_plane@pixel-format-yf-tiled-ccs-modifier-source-clamping.html

* igt@kms_plane@plane-panning-bottom-right-suspend:
- shard-bmg: [PASS][89] -> [ABORT][90] ([Intel XE#9422]) +1 other test abort
[89]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-5915-3bd4f625aafdf70814dbf075de96e224355c9f1e/shard-bmg-3/igt@[email protected]
[90]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-7/igt@[email protected]

* igt@kms_plane_multiple@2x-tiling-yf:
- shard-ptl: NOTRUN -> [SKIP][91] ([Intel XE#4596] / [Intel XE#5854])
[91]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-4/igt@[email protected]

* igt@kms_plane_scaling@planes-downscale-factor-0-5-upscale-20x20@pipe-b:
- shard-ptl: NOTRUN -> [SKIP][92] ([Intel XE#6886]) +9 other tests skip
[92]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-4/igt@kms_plane_scaling@[email protected]

* igt@kms_plane_scaling@planes-downscale-factor-0-75@pipe-a:
- shard-bmg: NOTRUN -> [SKIP][93] ([Intel XE#2763] / [Intel XE#6886]) +4 other tests skip
[93]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-1/igt@kms_plane_scaling@[email protected]

* igt@kms_plane_scaling@planes-upscale-factor-0-25-downscale-factor-0-75@pipe-a:
- shard-lnl: NOTRUN -> [SKIP][94] ([Intel XE#2763] / [Intel XE#6886]) +3 other tests skip
[94]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-lnl-7/igt@kms_plane_scaling@[email protected]

* igt@kms_pm_backlight@bad-brightness:
- shard-bmg: NOTRUN -> [SKIP][95] ([Intel XE#7376] / [Intel XE#7760] / [Intel XE#870])
[95]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-7/igt@[email protected]

* igt@kms_pm_dc@dc6-psr:
- shard-bmg: NOTRUN -> [SKIP][96] ([Intel XE#7794])
[96]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-1/igt@[email protected]

* igt@kms_psr2_sf@fbc-psr2-overlay-plane-move-continuous-sf@pipe-a-edp-1:
- shard-ptl: NOTRUN -> [SKIP][97] ([Intel XE#5858])
[97]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-4/igt@kms_psr2_sf@[email protected]

* igt@kms_psr2_sf@fbc-psr2-overlay-plane-move-continuous-sf@pipe-b-edp-1:
- shard-ptl: NOTRUN -> [SKIP][98] ([Intel XE#5858] / [Intel XE#7304]) +1 other test skip
[98]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-4/igt@kms_psr2_sf@[email protected]

* igt@kms_psr2_sf@pr-cursor-plane-update-sf:
- shard-lnl: NOTRUN -> [SKIP][99] ([Intel XE#2893] / [Intel XE#7304]) +1 other test skip
[99]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-lnl-7/igt@[email protected]

* igt@kms_psr2_sf@pr-overlay-plane-update-continuous-sf:
- shard-ptl: NOTRUN -> [SKIP][100] ([Intel XE#7304]) +2 other tests skip
[100]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-8/igt@[email protected]

* igt@kms_psr2_sf@psr2-primary-plane-update-sf-dmg-area-big-fb:
- shard-bmg: NOTRUN -> [SKIP][101] ([Intel XE#1489]) +6 other tests skip
[101]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-5/igt@[email protected]

* igt@kms_psr2_su@page_flip-p010:
- shard-bmg: NOTRUN -> [SKIP][102] ([Intel XE#2387] / [Intel XE#7429])
[102]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-1/igt@kms_psr2_su@page_flip-p010.html

* igt@kms_psr@fbc-pr-cursor-plane-move:
- shard-ptl: NOTRUN -> [SKIP][103] ([Intel XE#1406]) +2 other tests skip
[103]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-8/igt@[email protected]

* igt@kms_psr@fbc-pr-sprite-plane-onoff:
- shard-lnl: NOTRUN -> [SKIP][104] ([Intel XE#1406])
[104]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-lnl-7/igt@[email protected]

* igt@kms_psr@fbc-psr2-basic:
- shard-lnl: NOTRUN -> [SKIP][105] ([Intel XE#1406] / [Intel XE#7345])
[105]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-lnl-7/igt@[email protected]

* igt@kms_psr@fbc-psr2-basic@edp-1:
- shard-lnl: NOTRUN -> [SKIP][106] ([Intel XE#1406] / [Intel XE#4609] / [Intel XE#7345])
[106]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-lnl-7/igt@kms_psr@[email protected]

* igt@kms_psr@fbc-psr2-sprite-blt@edp-1:
- shard-ptl: NOTRUN -> [SKIP][107] ([Intel XE#1406] / [Intel XE#5835]) +1 other test skip
[107]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-4/igt@kms_psr@[email protected]

* igt@kms_psr@pr-suspend:
- shard-bmg: NOTRUN -> [SKIP][108] ([Intel XE#2234] / [Intel XE#2850]) +9 other tests skip
[108]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-5/igt@[email protected]

* igt@kms_psr@psr2-primary-render:
- shard-bmg: NOTRUN -> [SKIP][109] ([Intel XE#2234])
[109]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-8/igt@[email protected]

* igt@kms_psr_stress_test@invalidate-primary-flip-overlay:
- shard-bmg: NOTRUN -> [SKIP][110] ([Intel XE#7795])
[110]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-5/igt@[email protected]

* igt@kms_rotation_crc@bad-tiling:
- shard-ptl: NOTRUN -> [SKIP][111] ([Intel XE#5821])
[111]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-8/igt@[email protected]

* igt@kms_rotation_crc@primary-yf-tiled-reflect-x-0:
- shard-bmg: NOTRUN -> [SKIP][112] ([Intel XE#2330] / [Intel XE#5813])
[112]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-7/igt@[email protected]

* igt@kms_rotation_crc@primary-yf-tiled-reflect-x-180:
- shard-ptl: NOTRUN -> [SKIP][113] ([Intel XE#5813]) +2 other tests skip
[113]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-5/igt@[email protected]

* igt@kms_rotation_crc@sprite-rotation-270:
- shard-bmg: NOTRUN -> [SKIP][114] ([Intel XE#3904] / [Intel XE#7342])
[114]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-5/igt@[email protected]

* igt@kms_scaling_modes@scaling-mode-full-aspect:
- shard-bmg: NOTRUN -> [SKIP][115] ([Intel XE#2413]) +1 other test skip
[115]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-1/igt@[email protected]

* igt@kms_setmode@invalid-clone-exclusive-crtc:
- shard-ptl: NOTRUN -> [SKIP][116] ([Intel XE#5910])
[116]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-8/igt@[email protected]

* igt@kms_sharpness_filter@filter-suspend:
- shard-ptl: [PASS][117] -> [ABORT][118] ([Intel XE#9375]) +1 other test abort
[117]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-5915-3bd4f625aafdf70814dbf075de96e224355c9f1e/shard-ptl-4/igt@[email protected]
[118]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-7/igt@[email protected]

* igt@kms_tiled_display@basic-test-pattern:
- shard-bmg: NOTRUN -> [SKIP][119] ([Intel XE#2426] / [Intel XE#5848]) +1 other test skip
[119]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-6/igt@[email protected]

* igt@kms_tiled_display@basic-test-pattern-with-chamelium:
- shard-ptl: NOTRUN -> [SKIP][120] ([Intel XE#5848])
[120]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-8/igt@[email protected]

* igt@kms_vblank@ts-continuation-dpms-suspend:
- shard-bmg: NOTRUN -> [DMESG-WARN][121] ([Intel XE#9365] / [Intel XE#9465])
[121]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-10/igt@[email protected]

* igt@kms_vblank@ts-continuation-dpms-suspend@pipe-d-dp-2:
- shard-bmg: NOTRUN -> [DMESG-WARN][122] ([Intel XE#9365])
[122]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-10/igt@kms_vblank@[email protected]

* igt@kms_vrr@flip-dpms@pipe-a-edp-1:
- shard-ptl: [PASS][123] -> [FAIL][124] ([Intel XE#4227] / [Intel XE#7397]) +1 other test fail
[123]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-5915-3bd4f625aafdf70814dbf075de96e224355c9f1e/shard-ptl-7/igt@kms_vrr@[email protected]
[124]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-1/igt@kms_vrr@[email protected]

* igt@kms_vrr@lobf:
- shard-bmg: NOTRUN -> [SKIP][125] ([Intel XE#2168] / [Intel XE#7444])
[125]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-8/igt@[email protected]

* igt@kms_vrr@seamless-rr-switch-virtual:
- shard-bmg: NOTRUN -> [SKIP][126] ([Intel XE#1499] / [Intel XE#9271])
[126]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-1/igt@[email protected]

* igt@xe_ccs@vm-bind-fault-mode-decompress:
- shard-lnl: NOTRUN -> [SKIP][127] ([Intel XE#7644])
[127]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-lnl-7/igt@[email protected]

* igt@xe_compute@eu-busy-10s:
- shard-bmg: NOTRUN -> [SKIP][128] ([Intel XE#6599])
[128]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-1/igt@[email protected]

* igt@xe_compute_preempt@compute-preempt-many-vram-evict:
- shard-ptl: NOTRUN -> [SKIP][129] ([Intel XE#5191]) +1 other test skip
[129]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-5/igt@[email protected]

* igt@xe_create@multigpu-create-massive-size:
- shard-ptl: NOTRUN -> [SKIP][130] ([Intel XE#5878])
[130]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-4/igt@[email protected]

* igt@xe_evict@evict-beng-mixed-many-threads-large:
- shard-lnl: NOTRUN -> [SKIP][131] ([Intel XE#6540] / [Intel XE#688]) +2 other tests skip
[131]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-lnl-7/igt@[email protected]

* igt@xe_evict@evict-large-external:
- shard-ptl: NOTRUN -> [SKIP][132] ([Intel XE#5764]) +6 other tests skip
[132]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-4/igt@[email protected]

* igt@xe_evict@evict-mixed-many-threads-small:
- shard-bmg: NOTRUN -> [INCOMPLETE][133] ([Intel XE#6321] / [Intel XE#8355]) +1 other test incomplete
[133]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-1/igt@[email protected]

* igt@xe_evict@evict-small-multi-queue-priority-cm:
- shard-bmg: NOTRUN -> [SKIP][134] ([Intel XE#8370])
[134]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-5/igt@[email protected]

* igt@xe_evict_ccs@evict-overcommit-standalone-nofree-samefd:
- shard-ptl: NOTRUN -> [SKIP][135] ([Intel XE#6144])
[135]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-4/igt@[email protected]

* igt@xe_exec_balancer@many-execqueues-cm-parallel-rebind:
- shard-lnl: NOTRUN -> [SKIP][136] ([Intel XE#7482]) +4 other tests skip
[136]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-lnl-7/igt@[email protected]

* igt@xe_exec_balancer@virtual-all-active:
- shard-ptl: NOTRUN -> [SKIP][137] ([Intel XE#7482]) +13 other tests skip
[137]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-5/igt@[email protected]

* igt@xe_exec_basic@multigpu-many-execqueues-many-vm-userptr-invalidate-race:
- shard-bmg: NOTRUN -> [SKIP][138] ([Intel XE#2322] / [Intel XE#7372]) +4 other tests skip
[138]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-6/igt@xe_exec_basic@multigpu-many-execqueues-many-vm-userptr-invalidate-race.html

* igt@xe_exec_basic@multigpu-no-exec-bindexecqueue-userptr-rebind:
- shard-lnl: NOTRUN -> [SKIP][139] ([Intel XE#1392]) +1 other test skip
[139]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-lnl-7/igt@[email protected]

* igt@xe_exec_basic@multigpu-no-exec-userptr-invalidate-race:
- shard-ptl: NOTRUN -> [SKIP][140] ([Intel XE#5575] / [Intel XE#7484]) +7 other tests skip
[140]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-4/igt@[email protected]

* igt@xe_exec_fault_mode@many-execqueues-multi-queue-prefetch:
- shard-ptl: NOTRUN -> [SKIP][141] ([Intel XE#8374]) +12 other tests skip
[141]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-5/igt@[email protected]

* igt@xe_exec_fault_mode@once-multi-queue-rebind-prefetch:
- shard-bmg: NOTRUN -> [SKIP][142] ([Intel XE#8374]) +8 other tests skip
[142]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-1/igt@[email protected]

* igt@xe_exec_fault_mode@twice-multi-queue-invalid-userptr-fault:
- shard-lnl: NOTRUN -> [SKIP][143] ([Intel XE#8374]) +2 other tests skip
[143]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-lnl-7/igt@[email protected]

* igt@xe_exec_multi_queue@many-execs-close-fd-smem:
- shard-bmg: NOTRUN -> [SKIP][144] ([Intel XE#8364]) +24 other tests skip
[144]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-1/igt@[email protected]

* igt@xe_exec_multi_queue@one-queue-close-fd-smem:
- shard-ptl: NOTRUN -> [SKIP][145] ([Intel XE#8364]) +18 other tests skip
[145]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-8/igt@[email protected]

* igt@xe_exec_multi_queue@one-queue-preempt-mode-fault-close-fd-smem:
- shard-lnl: NOTRUN -> [SKIP][146] ([Intel XE#8364]) +6 other tests skip
[146]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-lnl-7/igt@xe_exec_multi_queue@one-queue-preempt-mode-fault-close-fd-smem.html

* igt@xe_exec_reset@cm-multi-queue-gt-reset:
- shard-bmg: NOTRUN -> [SKIP][147] ([Intel XE#8369]) +1 other test skip
[147]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-8/igt@[email protected]

* igt@xe_exec_reset@multi-queue-cat-error-on-secondary:
- shard-lnl: NOTRUN -> [SKIP][148] ([Intel XE#8369]) +1 other test skip
[148]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-lnl-7/igt@[email protected]

* igt@xe_exec_reset@multi-queue-gt-reset:
- shard-ptl: NOTRUN -> [SKIP][149] ([Intel XE#8369]) +1 other test skip
[149]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-4/igt@[email protected]

* igt@xe_exec_threads@threads-hang-userptr-invalidate-race:
- shard-lnl: [PASS][150] -> [FAIL][151] ([Intel XE#9096])
[150]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-5915-3bd4f625aafdf70814dbf075de96e224355c9f1e/shard-lnl-4/igt@[email protected]
[151]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-lnl-2/igt@[email protected]

* igt@xe_exec_threads@threads-multi-queue-cm-shared-vm-userptr-rebind:
- shard-lnl: NOTRUN -> [SKIP][152] ([Intel XE#8378]) +1 other test skip
[152]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-lnl-7/igt@xe_exec_threads@threads-multi-queue-cm-shared-vm-userptr-rebind.html

* igt@xe_exec_threads@threads-multi-queue-cm-userptr-invalidate-race:
- shard-ptl: NOTRUN -> [SKIP][153] ([Intel XE#8378]) +6 other tests skip
[153]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-5/igt@xe_exec_threads@threads-multi-queue-cm-userptr-invalidate-race.html

* igt@xe_exec_threads@threads-multi-queue-mixed-shared-vm-userptr:
- shard-bmg: NOTRUN -> [SKIP][154] ([Intel XE#8378]) +8 other tests skip
[154]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-1/igt@[email protected]

* igt@xe_mmap@pci-membarrier-bad-pagesize:
- shard-lnl: NOTRUN -> [SKIP][155] ([Intel XE#5100] / [Intel XE#7322] / [Intel XE#7408])
[155]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-lnl-7/igt@[email protected]

* igt@xe_mmap@small-bar:
- shard-ptl: NOTRUN -> [SKIP][156] ([Intel XE#5867])
[156]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-8/igt@[email protected]

* igt@xe_multigpu_svm@mgpu-atomic-op-basic:
- shard-bmg: NOTRUN -> [SKIP][157] ([Intel XE#6964]) +4 other tests skip
[157]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-5/igt@[email protected]

* igt@xe_multigpu_svm@mgpu-atomic-op-prefetch:
- shard-lnl: NOTRUN -> [SKIP][158] ([Intel XE#6964])
[158]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-lnl-7/igt@[email protected]

* igt@xe_multigpu_svm@mgpu-latency-copy-prefetch:
- shard-ptl: NOTRUN -> [SKIP][159] ([Intel XE#6964]) +1 other test skip
[159]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-5/igt@[email protected]

* igt@xe_oa@oa-tlb-invalidate:
- shard-bmg: NOTRUN -> [SKIP][160] ([Intel XE#2248] / [Intel XE#7325] / [Intel XE#7393])
[160]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-1/igt@[email protected]

* igt@xe_page_reclaim@prl-max-entries:
- shard-bmg: NOTRUN -> [SKIP][161] ([Intel XE#7793]) +2 other tests skip
[161]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-7/igt@[email protected]
- shard-ptl: NOTRUN -> [SKIP][162] ([Intel XE#7793]) +2 other tests skip
[162]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-8/igt@[email protected]

* igt@xe_page_reclaim@random:
- shard-lnl: NOTRUN -> [SKIP][163] ([Intel XE#7793])
[163]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-lnl-7/igt@[email protected]

* igt@xe_pm@d3cold-multiple-execs:
- shard-lnl: NOTRUN -> [SKIP][164] ([Intel XE#2284] / [Intel XE#366] / [Intel XE#7370])
[164]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-lnl-7/igt@[email protected]

* igt@xe_pm@s2idle-d3cold-basic-exec:
- shard-bmg: NOTRUN -> [SKIP][165] ([Intel XE#2284] / [Intel XE#7370]) +3 other tests skip
[165]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-1/igt@[email protected]

* igt@xe_pm@s4-basic:
- shard-lnl: [PASS][166] -> [ABORT][167] ([Intel XE#9362])
[166]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-5915-3bd4f625aafdf70814dbf075de96e224355c9f1e/shard-lnl-3/igt@[email protected]
[167]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-lnl-4/igt@[email protected]

* igt@xe_pm@s4-mocs:
- shard-ptl: [PASS][168] -> [DMESG-WARN][169] ([Intel XE#7727])
[168]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-5915-3bd4f625aafdf70814dbf075de96e224355c9f1e/shard-ptl-2/igt@[email protected]
[169]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-6/igt@[email protected]

* igt@xe_pm_residency@cpg-basic:
- shard-bmg: [PASS][170] -> [ABORT][171] ([Intel XE#9362]) +1 other test abort
[170]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-5915-3bd4f625aafdf70814dbf075de96e224355c9f1e/shard-bmg-9/igt@[email protected]
[171]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-2/igt@[email protected]

* igt@xe_prefetch_fault@l2-prefetch-fault:
- shard-lnl: NOTRUN -> [SKIP][172] ([Intel XE#8815])
[172]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-lnl-7/igt@[email protected]

* igt@xe_prefetch_fault@l2-prefetch-fault-svm:
- shard-ptl: NOTRUN -> [SKIP][173] ([Intel XE#8815])
[173]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-4/igt@[email protected]

* igt@xe_prefetch_fault@prefetch-fault-svm:
- shard-bmg: NOTRUN -> [SKIP][174] ([Intel XE#7599])
[174]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-6/igt@[email protected]

* igt@xe_pxp@pxp-stale-queue-post-suspend:
- shard-bmg: NOTRUN -> [SKIP][175] ([Intel XE#4733] / [Intel XE#7417])
[175]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-10/igt@[email protected]

* igt@xe_query@multigpu-query-gt-list:
- shard-lnl: NOTRUN -> [SKIP][176] ([Intel XE#944])
[176]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-lnl-7/igt@[email protected]

* igt@xe_query@multigpu-query-invalid-extension:
- shard-bmg: NOTRUN -> [SKIP][177] ([Intel XE#944]) +2 other tests skip
[177]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-1/igt@[email protected]

* igt@xe_query@multigpu-query-mem-usage:
- shard-ptl: NOTRUN -> [SKIP][178] ([Intel XE#6019]) +2 other tests skip
[178]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-5/igt@[email protected]

* igt@xe_sriov_admin@default-sched-attributes-vfs-disabled:
- shard-lnl: NOTRUN -> [SKIP][179] ([Intel XE#7174])
[179]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-lnl-7/igt@[email protected]

* igt@xe_survivability@runtime-survivability:
- shard-lnl: NOTRUN -> [SKIP][180] ([Intel XE#8415])
[180]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-lnl-7/igt@[email protected]

* igt@xe_wedged@wedged-at-any-timeout:
- shard-bmg: NOTRUN -> [DMESG-WARN][181] ([Intel XE#8963])
[181]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-1/igt@[email protected]

#### Possible fixes ####

* igt@kms_atomic_transition@plane-all-modeset-transition-fencing:
- shard-bmg: [FAIL][182] ([Intel XE#8098]) -> [PASS][183]
[182]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-5915-3bd4f625aafdf70814dbf075de96e224355c9f1e/shard-bmg-7/igt@[email protected]
[183]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-8/igt@[email protected]

* igt@kms_ccs@crc-primary-suspend-4-tiled-bmg-ccs:
- shard-bmg: [ABORT][184] ([Intel XE#9393] / [Intel XE#9422]) -> [PASS][185]
[184]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-5915-3bd4f625aafdf70814dbf075de96e224355c9f1e/shard-bmg-7/igt@[email protected]
[185]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-8/igt@[email protected]

* igt@kms_ccs@crc-primary-suspend-4-tiled-bmg-ccs@pipe-b-hdmi-a-3:
- shard-bmg: [DMESG-WARN][186] -> [PASS][187]
[186]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-5915-3bd4f625aafdf70814dbf075de96e224355c9f1e/shard-bmg-7/igt@kms_ccs@[email protected]
[187]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-8/igt@kms_ccs@[email protected]

* igt@kms_ccs@crc-primary-suspend-4-tiled-bmg-ccs@pipe-c-hdmi-a-3:
- shard-bmg: [INCOMPLETE][188] ([Intel XE#7084] / [Intel XE#8150]) -> [PASS][189]
[188]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-5915-3bd4f625aafdf70814dbf075de96e224355c9f1e/shard-bmg-7/igt@kms_ccs@[email protected]
[189]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-8/igt@kms_ccs@[email protected]

* igt@kms_cursor_crc@cursor-suspend:
- shard-bmg: [DMESG-WARN][190] ([Intel XE#9365]) -> [PASS][191] +1 other test pass
[190]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-5915-3bd4f625aafdf70814dbf075de96e224355c9f1e/shard-bmg-1/igt@[email protected]
[191]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-3/igt@[email protected]

* igt@kms_flip@flip-vs-expired-vblank@b-edp1:
- shard-lnl: [FAIL][192] ([Intel XE#301]) -> [PASS][193]
[192]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-5915-3bd4f625aafdf70814dbf075de96e224355c9f1e/shard-lnl-3/igt@kms_flip@[email protected]
[193]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-lnl-3/igt@kms_flip@[email protected]

* igt@kms_flip@flip-vs-suspend:
- shard-bmg: [ABORT][194] ([Intel XE#9362]) -> [PASS][195] +4 other tests pass
[194]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-5915-3bd4f625aafdf70814dbf075de96e224355c9f1e/shard-bmg-3/igt@[email protected]
[195]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-10/igt@[email protected]

* igt@kms_pm_backlight@fade-with-suspend:
- shard-ptl: [ABORT][196] ([Intel XE#9362]) -> [PASS][197] +3 other tests pass
[196]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-5915-3bd4f625aafdf70814dbf075de96e224355c9f1e/shard-ptl-5/igt@[email protected]
[197]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-5/igt@[email protected]

* igt@xe_fault_injection@inject-fault-probe-function-xe_device_probe_early:
- shard-bmg: [ABORT][198] ([Intel XE#9463]) -> [PASS][199] +1 other test pass
[198]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-5915-3bd4f625aafdf70814dbf075de96e224355c9f1e/shard-bmg-4/igt@xe_fault_injection@inject-fault-probe-function-xe_device_probe_early.html
[199]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-6/igt@xe_fault_injection@inject-fault-probe-function-xe_device_probe_early.html

#### Warnings ####

* igt@kms_hdr@brightness-with-hdr:
- shard-bmg: [SKIP][200] ([Intel XE#3374] / [Intel XE#3544]) -> [SKIP][201] ([Intel XE#3544])
[200]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-5915-3bd4f625aafdf70814dbf075de96e224355c9f1e/shard-bmg-6/igt@[email protected]
[201]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-bmg-9/igt@[email protected]

* igt@xe_pat@pat-sw-hw-suspend:
- shard-ptl: [ABORT][202] ([Intel XE#9362]) -> [FAIL][203] ([Intel XE#7695])
[202]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-5915-3bd4f625aafdf70814dbf075de96e224355c9f1e/shard-ptl-8/igt@[email protected]
[203]: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/shard-ptl-8/igt@[email protected]

[Intel XE#1124]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/1124
[Intel XE#1178]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/1178
[Intel XE#1392]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/1392
[Intel XE#1406]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/1406
[Intel XE#1407]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/1407
[Intel XE#1421]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/1421
[Intel XE#1424]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/1424
[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#2168]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2168
[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#2316]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2316
[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#2327]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2327
[Intel XE#2330]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2330
[Intel XE#2372]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2372
[Intel XE#2374]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2374
[Intel XE#2387]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2387
[Intel XE#2390]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2390
[Intel XE#2413]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2413
[Intel XE#2426]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2426
[Intel XE#2652]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2652
[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#2893]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/2893
[Intel XE#301]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/301
[Intel XE#306]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/306
[Intel XE#309]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/309
[Intel XE#3304]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/3304
[Intel XE#3374]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/3374
[Intel XE#3432]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/3432
[Intel XE#3544]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/3544
[Intel XE#366]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/366
[Intel XE#367]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/367
[Intel XE#373]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/373
[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#4596]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/4596
[Intel XE#4609]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/4609
[Intel XE#4733]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/4733
[Intel XE#5100]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/5100
[Intel XE#5191]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/5191
[Intel XE#5408]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/5408
[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#5800]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/5800
[Intel XE#5808]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/5808
[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#5821]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/5821
[Intel XE#5822]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/5822
[Intel XE#5823]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/5823
[Intel XE#5824]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/5824
[Intel XE#5828]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/5828
[Intel XE#5835]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/5835
[Intel XE#5846]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/5846
[Intel XE#5848]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/5848
[Intel XE#5851]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/5851
[Intel XE#5854]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/5854
[Intel XE#5858]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/5858
[Intel XE#5867]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/5867
[Intel XE#5878]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/5878
[Intel XE#5900]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/5900
[Intel XE#5901]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/5901
[Intel XE#5907]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/5907
[Intel XE#5910]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/5910
[Intel XE#5917]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/5917
[Intel XE#5947]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/5947
[Intel XE#5962]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/5962
[Intel XE#6019]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/6019
[Intel XE#610]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/610
[Intel XE#6127]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/6127
[Intel XE#6144]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/6144
[Intel XE#6174]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/6174
[Intel XE#6266]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/6266
[Intel XE#6312]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/6312
[Intel XE#6321]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/6321
[Intel XE#651]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/651
[Intel XE#6540]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/6540
[Intel XE#656]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/656
[Intel XE#6599]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/6599
[Intel XE#6707]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/6707
[Intel XE#688]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/688
[Intel XE#6886]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/6886
[Intel XE#6918]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/6918
[Intel XE#6964]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/6964
[Intel XE#6969]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/6969
[Intel XE#6974]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/6974
[Intel XE#7061]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7061
[Intel XE#7084]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7084
[Intel XE#7085]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7085
[Intel XE#7174]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7174
[Intel XE#7178]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7178
[Intel XE#7179]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7179
[Intel XE#7283]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7283
[Intel XE#7304]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7304
[Intel XE#7322]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7322
[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#7343]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7343
[Intel XE#7345]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7345
[Intel XE#7349]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7349
[Intel XE#7351]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7351
[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#7359]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7359
[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#7376]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7376
[Intel XE#7387]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7387
[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#7408]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7408
[Intel XE#7417]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7417
[Intel XE#7429]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7429
[Intel XE#7439]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7439
[Intel XE#7444]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7444
[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#7591]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7591
[Intel XE#7599]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7599
[Intel XE#7642]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7642
[Intel XE#7644]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7644
[Intel XE#7679]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7679
[Intel XE#7695]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7695
[Intel XE#7727]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7727
[Intel XE#7760]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7760
[Intel XE#7793]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7793
[Intel XE#7794]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7794
[Intel XE#7795]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7795
[Intel XE#7865]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7865
[Intel XE#7905]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/7905
[Intel XE#8098]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/8098
[Intel XE#8150]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/8150
[Intel XE#8265]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/8265
[Intel XE#8355]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/8355
[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#8370]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/8370
[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#8391]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/8391
[Intel XE#8415]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/8415
[Intel XE#870]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/870
[Intel XE#8815]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/8815
[Intel XE#8963]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/8963
[Intel XE#9096]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/9096
[Intel XE#9271]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/9271
[Intel XE#9312]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/9312
[Intel XE#9362]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/9362
[Intel XE#9365]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/9365
[Intel XE#9375]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/9375
[Intel XE#9393]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/9393
[Intel XE#9422]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/9422
[Intel XE#944]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/944
[Intel XE#9463]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/9463
[Intel XE#9465]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/9465
[Intel XE#9536]: https://gitlab.freedesktop.org/drm/xe/kernel/issues/9536

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

* Linux: xe-5915-3bd4f625aafdf70814dbf075de96e224355c9f1e -> xe-pw-169692v4

IGT_9138: 9138
xe-5915-3bd4f625aafdf70814dbf075de96e224355c9f1e: 3bd4f625aafdf70814dbf075de96e224355c9f1e
xe-pw-169692v4: 169692v4

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/intel-xe/xe-pw-169692v4/index.html

#48 lore raw
In reply to Badal Nilawar
Quoted 2 lines · Badal Nilawar

This patch series adds CPER (Common Platform Error Record) logging support for Correctable errors reported by Intel Xe GPUs. CPER logging is done

Is it still correctable errors?

Raag

Quoted 54 lines

through trace event.

v2:
- Extended CPER logging to Uncorrectable errors and xe_ras_get_counter request
- Log CPER records via xe_log SIGID infra

v3:
- Added the patches in incremental order (Raag)
- Fixed Sashiko warnings which are applicable

v4:
- Split the patches further for incremental review (Raag)
- Refactor info queue handling (Raag)
- Fix applicable Sashiko warnings

Badal Nilawar (12):
drm/xe/cper: Add CPER reporting entry point for xe_log drm/xe/cper: Retrieve the error counter record for CPER reporting drm/xe/cper: Initialize Intel-specific error section header drm/xe/cper: Construct CPER record for hardware errors drm/xe/xe_ras: Add support to retrieve info queue data for CRI drm/xe/cper: Prepare Intel CPER error info records drm/xe/cper: Log CPER records for aggregate counter retrieval drm/xe/cper: Emit cper record to trace buf drm/xe/xe_ras: Report device memory errors using SIGID drm/xe/xe_ras: Report core compute errors using SIGID drm/xe/xe_ras: Report soc internal errors using SIGID drm/xe/xe_ras: Report correctable errors using SIGID

 .../ABI/testing/sysfs-driver-intel-xe-cper    |  18 +
 drivers/gpu/drm/xe/Makefile                   |   3 +
 drivers/gpu/drm/xe/xe_cper.c                  | 530 ++++++++++++++++++
 drivers/gpu/drm/xe/xe_cper.h                  |  37 ++
 drivers/gpu/drm/xe/xe_cper_types.h            | 185 ++++++
 drivers/gpu/drm/xe/xe_device_types.h          |   4 +
 drivers/gpu/drm/xe/xe_log.c                   |   5 +-
 drivers/gpu/drm/xe/xe_ras.c                   | 254 ++++++++-
 drivers/gpu/drm/xe/xe_ras.h                   |   5 +
 drivers/gpu/drm/xe/xe_ras_types.h             | 118 +++-
 drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h |   2 +
 drivers/gpu/drm/xe/xe_trace_cper.c            |   9 +
 drivers/gpu/drm/xe/xe_trace_cper.h            |  66 +++
 13 files changed, 1202 insertions(+), 34 deletions(-)
 create mode 100644 Documentation/ABI/testing/sysfs-driver-intel-xe-cper
 create mode 100644 drivers/gpu/drm/xe/xe_cper.c
 create mode 100644 drivers/gpu/drm/xe/xe_cper.h
 create mode 100644 drivers/gpu/drm/xe/xe_cper_types.h
 create mode 100644 drivers/gpu/drm/xe/xe_trace_cper.c
 create mode 100644 drivers/gpu/drm/xe/xe_trace_cper.h
Signature · 1 line
2.54.0