intel-xe.lists.freedesktop.org archive mirror
 help / color / mirror / Atom feed
From: Riana Tauro <riana.tauro@intel.com>
To: intel-xe@lists.freedesktop.org
Cc: riana.tauro@intel.com, anshuman.gupta@intel.com,
	rodrigo.vivi@intel.com, aravind.iddamsetty@linux.intel.com,
	badal.nilawar@intel.com, raag.jadav@intel.com,
	ravi.kishore.koppuravuri@intel.com, mallesh.koujalagi@intel.com,
	soham.purkait@intel.com
Subject: [PATCH v4 06/13] drm/xe/xe_ras: Add basic structures and commands for uncorrectable errors
Date: Fri, 17 Apr 2026 14:28:18 +0530	[thread overview]
Message-ID: <20260417085812.4013309-21-riana.tauro@intel.com> (raw)
In-Reply-To: <20260417085812.4013309-15-riana.tauro@intel.com>

Add the commands and common structures for the get_soc_error
sysctrl command.

Signed-off-by: Riana Tauro <riana.tauro@intel.com>
---
v2: use macro max error details (Mallesh)
    use static_assert
    fix kernel-doc

v3: simplify check (Raag)
    add counter value

v4: use not_supported instead of unknown (Raag)
---
 drivers/gpu/drm/xe/xe_ras.c                   | 57 +++++++++++
 drivers/gpu/drm/xe/xe_ras_types.h             | 96 +++++++++++++++++++
 drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h | 13 +++
 3 files changed, 166 insertions(+)
 create mode 100644 drivers/gpu/drm/xe/xe_ras_types.h

diff --git a/drivers/gpu/drm/xe/xe_ras.c b/drivers/gpu/drm/xe/xe_ras.c
index 4f705deaeefa..bf780e953925 100644
--- a/drivers/gpu/drm/xe/xe_ras.c
+++ b/drivers/gpu/drm/xe/xe_ras.c
@@ -3,9 +3,66 @@
  * Copyright © 2026 Intel Corporation
  */
 
+#include "xe_assert.h"
 #include "xe_device_types.h"
 #include "xe_ras.h"
 
+/* Severity classification of detected errors */
+enum xe_ras_severity {
+	XE_RAS_SEVERITY_NOT_SUPPORTED = 0,
+	XE_RAS_SEVERITY_CORRECTABLE,
+	XE_RAS_SEVERITY_UNCORRECTABLE,
+	XE_RAS_SEVERITY_INFORMATIONAL,
+	XE_RAS_SEVERITY_MAX
+};
+
+/* major IP blocks where errors can originate */
+enum xe_ras_component {
+	XE_RAS_COMPONENT_NOT_SUPPORTED = 0,
+	XE_RAS_COMPONENT_DEVICE_MEMORY,
+	XE_RAS_COMPONENT_CORE_COMPUTE,
+	XE_RAS_COMPONENT_RESERVED,
+	XE_RAS_COMPONENT_PCIE,
+	XE_RAS_COMPONENT_FABRIC,
+	XE_RAS_COMPONENT_SOC_INTERNAL,
+	XE_RAS_COMPONENT_MAX
+};
+
+static const char * const xe_ras_severities[] = {
+	[XE_RAS_SEVERITY_NOT_SUPPORTED]		= "Not Supported",
+	[XE_RAS_SEVERITY_CORRECTABLE]		= "Correctable",
+	[XE_RAS_SEVERITY_UNCORRECTABLE]		= "Uncorrectable",
+	[XE_RAS_SEVERITY_INFORMATIONAL]		= "Informational",
+};
+static_assert(ARRAY_SIZE(xe_ras_severities) == XE_RAS_SEVERITY_MAX);
+
+static const char * const xe_ras_components[] = {
+	[XE_RAS_COMPONENT_NOT_SUPPORTED]	= "Not Supported",
+	[XE_RAS_COMPONENT_DEVICE_MEMORY]	= "Device Memory",
+	[XE_RAS_COMPONENT_CORE_COMPUTE]		= "Core Compute",
+	[XE_RAS_COMPONENT_RESERVED]		= "Reserved",
+	[XE_RAS_COMPONENT_PCIE]			= "PCIe",
+	[XE_RAS_COMPONENT_FABRIC]		= "Fabric",
+	[XE_RAS_COMPONENT_SOC_INTERNAL]		= "SoC Internal",
+};
+static_assert(ARRAY_SIZE(xe_ras_components) == XE_RAS_COMPONENT_MAX);
+
+static inline const char *severity_to_str(struct xe_device *xe, u32 severity)
+{
+	if (severity >= XE_RAS_SEVERITY_MAX)
+		severity = XE_RAS_SEVERITY_NOT_SUPPORTED;
+
+	return xe_ras_severities[severity];
+}
+
+static inline const char *comp_to_str(struct xe_device *xe, u32 comp)
+{
+	if (comp >= XE_RAS_COMPONENT_MAX)
+		comp = XE_RAS_COMPONENT_NOT_SUPPORTED;
+
+	return xe_ras_components[comp];
+}
+
 #ifdef CONFIG_PCIEAER
 static void aer_unmask_and_downgrade_internal_error(struct xe_device *xe)
 {
diff --git a/drivers/gpu/drm/xe/xe_ras_types.h b/drivers/gpu/drm/xe/xe_ras_types.h
new file mode 100644
index 000000000000..3d0f9e94a404
--- /dev/null
+++ b/drivers/gpu/drm/xe/xe_ras_types.h
@@ -0,0 +1,96 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2026 Intel Corporation
+ */
+
+#ifndef _XE_RAS_TYPES_H_
+#define _XE_RAS_TYPES_H_
+
+#include <linux/types.h>
+
+#define XE_RAS_NUM_ERROR_ARR		3
+#define XE_RAS_MAX_ERROR_DETAILS	16
+
+/**
+ * struct xe_ras_error_common - Common RAS error class
+ *
+ * This structure contains error severity and component information
+ * across all products
+ */
+struct xe_ras_error_common {
+	/** @severity: Error Severity */
+	u8 severity;
+	/** @component: IP where the error originated */
+	u8 component;
+} __packed;
+
+/**
+ * struct xe_ras_error_unit - Error unit information
+ */
+struct xe_ras_error_unit {
+	/** @tile: Tile identifier */
+	u8 tile;
+	/** @instance: Instance identifier within a component */
+	u32 instance;
+} __packed;
+
+/**
+ * struct xe_ras_error_cause - Error cause information
+ */
+struct xe_ras_error_cause {
+	/** @cause: Cause */
+	u32 cause;
+	/** @reserved: For future use */
+	u8 reserved;
+} __packed;
+
+/**
+ * struct xe_ras_error_product - Error fields that are specific to the product
+ */
+struct xe_ras_error_product {
+	/** @unit: Unit within IP block */
+	struct xe_ras_error_unit unit;
+	/** @error_cause: Cause/checker */
+	struct xe_ras_error_cause error_cause;
+} __packed;
+
+/**
+ * struct xe_ras_error_class - Complete RAS Error Class
+ *
+ * This structure provides the complete error classification by combining
+ * the common error class with the product-specific error class.
+ */
+struct xe_ras_error_class {
+	/** @common: Common error severity and component */
+	struct xe_ras_error_common common;
+	/** @product: Product-specific unit and cause */
+	struct xe_ras_error_product product;
+} __packed;
+
+/**
+ * struct xe_ras_error_array - Details of the error types
+ */
+struct xe_ras_error_array {
+	/** @counter_value: Counter value of the returned error */
+	u32 counter_value;
+	/** @error_class: Error class */
+	struct xe_ras_error_class error_class;
+	/** @timestamp: Timestamp */
+	u64 timestamp;
+	/** @error_details: Error details specific to the class */
+	u32 error_details[XE_RAS_MAX_ERROR_DETAILS];
+} __packed;
+
+/**
+ * struct xe_ras_get_error_response - Response from get soc error command
+ */
+struct xe_ras_get_error_response {
+	/** @num_errors: Number of errors reported in this response */
+	u8 num_errors;
+	/** @additional_errors: Indicates if the errors are pending */
+	u8 additional_errors;
+	/** @error_arr: Array of up to 3 errors */
+	struct xe_ras_error_array error_arr[XE_RAS_NUM_ERROR_ARR];
+} __packed;
+
+#endif
diff --git a/drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h b/drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h
index 89456aec6097..00a0f05aab32 100644
--- a/drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h
+++ b/drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h
@@ -10,6 +10,19 @@
 
 #include "abi/xe_sysctrl_abi.h"
 
+/**
+ * enum xe_sysctrl_mailbox_command_id - Command ID's for GFSP group
+ *
+ * @XE_SYSCTRL_CMD_GET_SOC_ERROR: Get basic error information
+ */
+enum xe_sysctrl_mailbox_command_id {
+	XE_SYSCTRL_CMD_GET_SOC_ERROR		= 0x01
+};
+
+enum xe_sysctrl_group {
+	XE_SYSCTRL_GROUP_GFSP = 1
+};
+
 /**
  * struct xe_sysctrl_mailbox_command - System Controller mailbox command
  */
-- 
2.47.1


  parent reply	other threads:[~2026-04-17  8:25 UTC|newest]

Thread overview: 45+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-04-17  8:58 [PATCH v4 00/13] Introduce Xe Uncorrectable Error Handling Riana Tauro
2026-04-17  8:58 ` [PATCH v4 01/13] drm/xe/xe_survivability: Decouple survivability info from boot survivability Riana Tauro
2026-04-17  8:58 ` [PATCH v4 02/13] drm/xe/xe_pci_error: Implement PCI error recovery callbacks Riana Tauro
2026-04-27  6:35   ` Raag Jadav
2026-05-06 13:59     ` Tauro, Riana
2026-04-17  8:58 ` [PATCH v4 03/13] drm/xe/xe_pci_error: Group all devres to release them on PCIe slot reset Riana Tauro
2026-04-17  8:58 ` [PATCH v4 04/13] drm/xe: Skip device access during PCI error recovery Riana Tauro
2026-04-30 12:58   ` Anshuman Gupta
2026-05-06 15:41     ` Tauro, Riana
2026-04-17  8:58 ` [PATCH v4 05/13] drm/xe/xe_ras: Initialize Uncorrectable AER Registers Riana Tauro
2026-04-27  7:56   ` Raag Jadav
2026-05-05  5:22     ` Tauro, Riana
2026-04-17  8:58 ` Riana Tauro [this message]
2026-04-17 17:38   ` [PATCH v4 06/13] drm/xe/xe_ras: Add basic structures and commands for uncorrectable errors Matt Roper
2026-04-17 21:25     ` Jadav, Raag
2026-04-17 21:32       ` Matt Roper
2026-04-20  5:34         ` Tauro, Riana
2026-04-20  7:49           ` Raag Jadav
2026-04-17  8:58 ` [PATCH v4 07/13] drm/xe/xe_ras: Add support for uncorrectable core-compute errors Riana Tauro
2026-04-27  8:24   ` Raag Jadav
2026-05-05  5:28     ` Tauro, Riana
2026-04-17  8:58 ` [PATCH v4 08/13] drm/xe/xe_ras: Handle uncorrectable SoC Internal errors Riana Tauro
2026-04-17  8:58 ` [PATCH v4 09/13] drm/xe/xe_ras: Handle uncorrectable device memory errors Riana Tauro
2026-04-21  6:08   ` Upadhyay, Tejas
2026-05-05  5:03     ` Tauro, Riana
2026-04-17  8:58 ` [PATCH v4 10/13] drm/xe/xe_ras: Add support to offline/decline a page Riana Tauro
2026-04-21  6:21   ` Upadhyay, Tejas
2026-05-05  5:16     ` Tauro, Riana
2026-04-17  8:58 ` [PATCH v4 11/13] drm/xe/xe_ras: Add support for page offline list and queue commands Riana Tauro
2026-04-21  6:19   ` Upadhyay, Tejas
2026-05-05  5:08     ` Tauro, Riana
2026-04-21  9:10   ` Upadhyay, Tejas
2026-05-05  5:17     ` Tauro, Riana
2026-04-17  8:58 ` [PATCH v4 12/13] drm/xe/xe_ras: Query errors from system controller on probe Riana Tauro
2026-04-28 11:46   ` Raag Jadav
2026-05-05 13:50     ` Tauro, Riana
2026-04-17  8:58 ` [PATCH v4 13/13] drm/xe/xe_pci_error: Process errors in mmio_enabled Riana Tauro
2026-04-28 11:39   ` Raag Jadav
2026-05-05  5:31     ` Tauro, Riana
2026-04-30 11:15   ` Gupta, Anshuman
2026-05-02 17:55     ` Raag Jadav
2026-04-20 13:33 ` ✗ CI.checkpatch: warning for Introduce Xe Uncorrectable Error Handling (rev4) Patchwork
2026-04-20 13:35 ` ✓ CI.KUnit: success " Patchwork
2026-04-20 14:42 ` ✓ Xe.CI.BAT: " Patchwork
2026-04-20 17:14 ` ✗ Xe.CI.FULL: failure " Patchwork

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260417085812.4013309-21-riana.tauro@intel.com \
    --to=riana.tauro@intel.com \
    --cc=anshuman.gupta@intel.com \
    --cc=aravind.iddamsetty@linux.intel.com \
    --cc=badal.nilawar@intel.com \
    --cc=intel-xe@lists.freedesktop.org \
    --cc=mallesh.koujalagi@intel.com \
    --cc=raag.jadav@intel.com \
    --cc=ravi.kishore.koppuravuri@intel.com \
    --cc=rodrigo.vivi@intel.com \
    --cc=soham.purkait@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).