Thread (16 messages) 16 messages, 4 authors, 2026-05-04

[PATCH 4/4] drm/xe/xe_drm_ras: Add error-event support in XE DRM RAS

flat view
STALE156d

From: Riana Tauro <hidden>
Date: 2026-03-11 09:58:44
Also in: dri-devel, intel-xe
Subsystem: drm drivers, intel drm xe driver (lunar lake and newer), the rest · Maintainers: David Airlie, Simona Vetter, Matthew Brost, Thomas Hellström, Rodrigo Vivi, Linus Torvalds

Add error-event support in XE DRM RAS to notify userspace
whenever a GT or SoC error occurs.

$ sudo ynl --family drm_ras --subscribe error-notify
{'msg': {'error-id': 1, 'node-id': 1}, 'name': 'error-event'}

Signed-off-by: Riana Tauro <redacted>
---
 drivers/gpu/drm/xe/xe_drm_ras.c  | 17 +++++++++++++++++
 drivers/gpu/drm/xe/xe_drm_ras.h  |  7 +++++++
 drivers/gpu/drm/xe/xe_hw_error.c |  5 +++++
 3 files changed, 29 insertions(+)
diff --git a/drivers/gpu/drm/xe/xe_drm_ras.c b/drivers/gpu/drm/xe/xe_drm_ras.c
index c21c8b428de6..47c040c80175 100644
--- a/drivers/gpu/drm/xe/xe_drm_ras.c
+++ b/drivers/gpu/drm/xe/xe_drm_ras.c
@@ -181,6 +181,23 @@ static void xe_drm_ras_unregister_nodes(struct drm_device *device, void *arg)
 	}
 }
 
+/**
+ * xe_drm_ras_notify() - Notify userspace of an error event
+ * @ras:  ras structure
+ * @error_id: error id
+ * @severity: error severity
+ * @flags: flags for allocation
+ *
+ * Notifies userspace of an error.
+ */
+void xe_drm_ras_notify(struct xe_drm_ras *ras, u32 error_id,
+		       const enum drm_xe_ras_error_severity severity, gfp_t flags)
+{
+	struct drm_ras_node *node = &ras->node[severity];
+
+	drm_ras_error_notify(node, error_id, flags);
+}
+
 /**
  * xe_drm_ras_init() - Initialize DRM RAS
  * @xe: xe device instance
diff --git a/drivers/gpu/drm/xe/xe_drm_ras.h b/drivers/gpu/drm/xe/xe_drm_ras.h
index 5cc8f0124411..ac347d0d63eb 100644
--- a/drivers/gpu/drm/xe/xe_drm_ras.h
+++ b/drivers/gpu/drm/xe/xe_drm_ras.h
@@ -5,11 +5,18 @@
 #ifndef XE_DRM_RAS_H_
 #define XE_DRM_RAS_H_
 
+#include <linux/types.h>
+
+#include <drm/xe_drm.h>
+
 struct xe_device;
+struct xe_drm_ras;
 
 #define for_each_error_severity(i)	\
 	for (i = 0; i < DRM_XE_RAS_ERR_SEV_MAX; i++)
 
 int xe_drm_ras_init(struct xe_device *xe);
+void xe_drm_ras_notify(struct xe_drm_ras *ras, u32 error_id,
+		       const enum drm_xe_ras_error_severity severity, gfp_t flags);
 
 #endif
diff --git a/drivers/gpu/drm/xe/xe_hw_error.c b/drivers/gpu/drm/xe/xe_hw_error.c
index 2a31b430570e..17424e07e72c 100644
--- a/drivers/gpu/drm/xe/xe_hw_error.c
+++ b/drivers/gpu/drm/xe/xe_hw_error.c
@@ -332,6 +332,8 @@ static void gt_hw_error_handler(struct xe_tile *tile, const enum hardware_error
 
 		xe_mmio_write32(mmio, ERR_STAT_GT_VECTOR_REG(hw_err, i), vector);
 	}
+
+	xe_drm_ras_notify(ras, error_id, severity, GFP_ATOMIC);
 }
 
 static void soc_slave_ieh_handler(struct xe_tile *tile, const enum hardware_error hw_err, u32 error_id)
@@ -368,6 +370,7 @@ static void soc_hw_error_handler(struct xe_tile *tile, const enum hardware_error
 {
 	const enum drm_xe_ras_error_severity severity = hw_err_to_severity(hw_err);
 	struct xe_device *xe = tile_to_xe(tile);
+	struct xe_drm_ras *ras = &xe->ras;
 	struct xe_mmio *mmio = &tile->mmio;
 	unsigned long master_global_errstat, master_local_errstat;
 	u32 master, slave, regbit;
@@ -418,6 +421,8 @@ static void soc_hw_error_handler(struct xe_tile *tile, const enum hardware_error
 	for (i = 0; i < XE_SOC_NUM_IEH; i++)
 		xe_mmio_write32(mmio, SOC_GSYSEVTCTL_REG(master, slave, i),
 				(HARDWARE_ERROR_MAX << 1) + 1);
+
+	xe_drm_ras_notify(ras, error_id, severity, GFP_ATOMIC);
 }
 
 static void hw_error_source_handler(struct xe_tile *tile, const enum hardware_error hw_err)
-- 
2.47.1
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help