Merge tag 'drm-xe-next-2026-08-31-1' of https://gitlab.freedesktop.org/drm/xe/kernel into drm-next

Cross-subsystem Changes:
- MAINTAINERS: Add entries for drm_ras (Rodrigo)
- alerts and controller enabling modifications (Heikki)

Core Changes:
- Introduce cold reset recovery method (Mallesh)
- Add drm_ras netlink error event support (Riana)
- Introduce error threshold to drm_ras (Raag)

Driver Changes:
- Remove sysfs entry on idr_alloc failure in xe_oa_add_config_ioctl (Lu)
- match argument naming with PCODE_DATAx (Grzelak)
- fix stale GGTT mappings on unmap (Tangudu)
- Introduce error threshold to drm_ras (Raag)
- Add debugfs knob to control GPGPU preemption granularity (Varun)
- fix vecs config for powergating info (Ashutosh)
- Read mailbox phase bit from hardware (Anoop)
- alerts and controller enabling modifications (Heikki)
- Use int instead of u32 for mailbox status (Umesh)
- Reject page faults from non-fault-mode scratch VMs (Arvind)
- Add CCS to the powergating info print (Balasubramani)
- Do not apply WA 14025883347 to media 3503 (Daniele)
- don't WARN on kernel job timeout when device already wedged (Nitin)
- handle exec queue teardown after hot-unplug (Nitin)
- Allow debugging PCI errors (Raag)
- Add structured SIGID error logging infrastructure (Wajdeczko, Rodrigo)
- Enable package and vram temperatures for CRI (Karthik)
- Introduce cold reset recovery method (Mallesh)
- fix error message in xe_migrate_sanity_test (Dan Carpenter)
- Add drm_ras netlink error event support (Riana)
- Fix a bug in pc_adjust_freq_bounds() (Vinay)
- Fix xe_device_probe() failure (Raag)
- Page fault cleanups (Wajdeczko)
- OA memory fixes (Linmao)
- document sentinel and make CTX_TIMESTAMP read TOCTOU-safe (Gajendra)
- Move has_drm_ras check to drm_ras layer (Raag)
- add termination on resume (Daniele)
- Add _locked variants of some config functions (Wajdeczko)
- Order ring writes before ring tail updates (Brost)
- Parallel page fault handling (Brost)
- handle CRI+ power interval encoding (Karthik)
- allocate UM queues in a separate UC BO (Jia)
- Fix boot-time ras error processing (Raag)
- VF migration for multi-queue (Niranjana)
- Apply RCS/CCS yield policy to SR-IOV VFs (Marcin)
- Fix memory leak in exec_queue_set_hang_replay_state (Winiarski)
- Use IBC v3 on PTL (Vinay)
- Reduce MERT debug log spam (Lukasz, Piotr)
- Validate sysctrl response (Raag)
- Changes for Xe3p_HPM media (Ashutosh)

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Matthew Brost <matthew.brost@intel.com>
Link: https://patch.msgid.link/apYbnrklyk6nNO7Q@gsse-cloud1.jf.intel.com

3 files changed, 53 insertions, 0 deletions

diff --git a/include/drm/drm_device.h b/include/drm/drm_device.h
index 768a8dae83c5..75f030d027ee 100644
--- a/include/drm/drm_device.h
+++ b/include/drm/drm_device.h
@@ -37,6 +37,7 @@ struct pci_controller;
 #define DRM_WEDGE_RECOVERY_REBIND	BIT(1)	/* unbind + bind driver */
 #define DRM_WEDGE_RECOVERY_BUS_RESET	BIT(2)	/* unbind + reset bus device + bind */
 #define DRM_WEDGE_RECOVERY_VENDOR	BIT(3)	/* vendor specific recovery method */
+#define DRM_WEDGE_RECOVERY_COLD_RESET	BIT(4)	/* remove device + slot power cycle + rescan */
 
 /**
  * struct drm_wedge_task_info - information about the guilty task of a wedge dev
diff --git a/include/drm/drm_ras.h b/include/drm/drm_ras.h
index 0beede3ddc4e..1765a3130b09 100644
--- a/include/drm/drm_ras.h
+++ b/include/drm/drm_ras.h
@@ -71,6 +71,35 @@ struct drm_ras_node {
 	 */
 	int (*clear_error_counter)(struct drm_ras_node *node, u32 error_id);
 
+	/**
+	 * @query_error_threshold:
+	 *
+	 * This callback is used by drm-ras to query error threshold of a
+	 * specific counter.
+	 *
+	 * Driver should expect query_error_threshold() to be called with
+	 * error_id from `error_counter_range.first` to
+	 * `error_counter_range.last`.
+	 *
+	 * Returns: 0 on success, negative error code on failure.
+	 */
+	int (*query_error_threshold)(struct drm_ras_node *node, u32 error_id, const char **name,
+				     u32 *threshold);
+
+	/**
+	 * @set_error_threshold:
+	 *
+	 * This callback is used by drm-ras to set error threshold of a specific
+	 * counter.
+	 *
+	 * Driver should expect set_error_threshold() to be called with error_id
+	 * from `error_counter_range.first` to `error_counter_range.last`.
+	 * Driver is responsible for error threshold bounds checking.
+	 *
+	 * Returns: 0 on success, negative error code on failure.
+	 */
+	int (*set_error_threshold)(struct drm_ras_node *node, u32 error_id, u32 threshold);
+
 	/** @priv: Driver private data */
 	void *priv;
 };
@@ -80,9 +109,14 @@ struct drm_device;
 #if IS_ENABLED(CONFIG_DRM_RAS)
 int drm_ras_node_register(struct drm_ras_node *node);
 void drm_ras_node_unregister(struct drm_ras_node *node);
+int drm_ras_nl_error_event(struct drm_ras_node *node, u32 error_id, const char *error_name,
+			   u32 value);
 #else
 static inline int drm_ras_node_register(struct drm_ras_node *node) { return 0; }
 static inline void drm_ras_node_unregister(struct drm_ras_node *node) { }
+static inline int drm_ras_nl_error_event(struct drm_ras_node *node, u32 error_id,
+					 const char *error_name, u32 value)
+{ return 0; }
 #endif
 
 #endif
diff --git a/include/uapi/drm/drm_ras.h b/include/uapi/drm/drm_ras.h
index 218a3ee86805..2f832275ee6e 100644
--- a/include/uapi/drm/drm_ras.h
+++ b/include/uapi/drm/drm_ras.h
@@ -33,18 +33,36 @@ enum {
 	DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_ID,
 	DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_NAME,
 	DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_VALUE,
+	DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_THRESHOLD,
 
 	__DRM_RAS_A_ERROR_COUNTER_ATTRS_MAX,
 	DRM_RAS_A_ERROR_COUNTER_ATTRS_MAX = (__DRM_RAS_A_ERROR_COUNTER_ATTRS_MAX - 1)
 };
 
 enum {
+	DRM_RAS_A_ERROR_EVENT_ATTRS_DEVICE_NAME = 1,
+	DRM_RAS_A_ERROR_EVENT_ATTRS_NODE_ID,
+	DRM_RAS_A_ERROR_EVENT_ATTRS_NODE_NAME,
+	DRM_RAS_A_ERROR_EVENT_ATTRS_ERROR_ID,
+	DRM_RAS_A_ERROR_EVENT_ATTRS_ERROR_NAME,
+	DRM_RAS_A_ERROR_EVENT_ATTRS_ERROR_VALUE,
+
+	__DRM_RAS_A_ERROR_EVENT_ATTRS_MAX,
+	DRM_RAS_A_ERROR_EVENT_ATTRS_MAX = (__DRM_RAS_A_ERROR_EVENT_ATTRS_MAX - 1)
+};
+
+enum {
 	DRM_RAS_CMD_LIST_NODES = 1,
 	DRM_RAS_CMD_GET_ERROR_COUNTER,
 	DRM_RAS_CMD_CLEAR_ERROR_COUNTER,
+	DRM_RAS_CMD_ERROR_EVENT,
+	DRM_RAS_CMD_GET_ERROR_THRESHOLD,
+	DRM_RAS_CMD_SET_ERROR_THRESHOLD,
 
 	__DRM_RAS_CMD_MAX,
 	DRM_RAS_CMD_MAX = (__DRM_RAS_CMD_MAX - 1)
 };
 
+#define DRM_RAS_MCGRP_ERROR_REPORT	"error-report"
+
 #endif /* _UAPI_LINUX_DRM_RAS_H */