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,
	Tejas Upadhyay <tejas.upadhyay@intel.com>,
	Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Subject: [PATCH v4 09/13] drm/xe/xe_ras: Handle uncorrectable device memory errors
Date: Fri, 17 Apr 2026 14:28:21 +0530	[thread overview]
Message-ID: <20260417085812.4013309-24-riana.tauro@intel.com> (raw)
In-Reply-To: <20260417085812.4013309-15-riana.tauro@intel.com>

Add support to handle uncorrectable device memory errors. Double bit ECC
(Error Correcting Code) errors are logged. These will be handled using
Page offlining in a later patch. The other memory error categories require
a Secondary bus reset (SBR) to recover.

Cc: Tejas Upadhyay <tejas.upadhyay@intel.com>
Cc: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Signed-off-by: Riana Tauro <riana.tauro@intel.com>
---
Memory offlining patch will be integrated once 
https://patchwork.freedesktop.org/series/161473/ is merged.
---
 drivers/gpu/drm/xe/xe_ras.c       | 23 ++++++++++++
 drivers/gpu/drm/xe/xe_ras_types.h | 61 +++++++++++++++++++++++++++++++
 2 files changed, 84 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_ras.c b/drivers/gpu/drm/xe/xe_ras.c
index 5010cf6211ea..347844b3d2bf 100644
--- a/drivers/gpu/drm/xe/xe_ras.c
+++ b/drivers/gpu/drm/xe/xe_ras.c
@@ -138,6 +138,26 @@ static enum xe_ras_recovery_action handle_soc_internal_errors(struct xe_device *
 	return XE_RAS_RECOVERY_ACTION_RESET;
 }
 
+static enum xe_ras_recovery_action handle_memory_errors(struct xe_device *xe,
+							struct xe_ras_error_array *arr)
+{
+	struct xe_ras_memory_error *error_info = (struct xe_ras_memory_error *)arr->error_details;
+	struct xe_ras_error_category category = error_info->category;
+	struct xe_ras_error_common common = arr->error_class.common;
+
+	xe_err(xe, "[RAS]: %s %s Error detected", severity_to_str(xe, common.severity),
+	       comp_to_str(xe, common.component));
+
+	if (category.ecc_error) {
+		xe_err(xe, "[RAS]: Double bit ECC error detected at sw address 0x%llx\n",
+		       (unsigned long long)error_info->sw_address);
+		/* TODO: page offline handling for 2-bit ECC errors and return accordingly */
+	}
+
+	/* Request a RESET for other device memory error categories */
+	return XE_RAS_RECOVERY_ACTION_RESET;
+}
+
 static void prepare_sysctrl_command(struct xe_sysctrl_mailbox_command *command,
 				    u32 cmd_mask, void *request, size_t request_len,
 				    void *response, size_t response_len)
@@ -217,6 +237,9 @@ enum xe_ras_recovery_action xe_ras_process_errors(struct xe_device *xe)
 			case XE_RAS_COMPONENT_SOC_INTERNAL:
 				action = handle_soc_internal_errors(xe, &arr);
 				break;
+			case XE_RAS_COMPONENT_DEVICE_MEMORY:
+				action = handle_memory_errors(xe, &arr);
+				break;
 			default:
 				xe_err(xe, "[RAS]: Unknown error component %u\n", component);
 				action = XE_RAS_RECOVERY_ACTION_RESET;
diff --git a/drivers/gpu/drm/xe/xe_ras_types.h b/drivers/gpu/drm/xe/xe_ras_types.h
index 4f640124f38f..020e3f92a057 100644
--- a/drivers/gpu/drm/xe/xe_ras_types.h
+++ b/drivers/gpu/drm/xe/xe_ras_types.h
@@ -199,4 +199,65 @@ struct xe_ras_ieh_error {
 	/** @additional_info: Additional information */
 	u32 additional_info[10];
 } __packed;
+
+/**
+ * struct xe_ras_hardware_address - Device memory hardware address details
+ *
+ * Hardware physical address structure for device memory error reporting.
+ */
+struct xe_ras_hardware_address {
+	/** @column: Column address */
+	u64 column:6;
+	/** @bank: Bank */
+	u64 bank:2;
+	/** @bank_group: Bank group */
+	u64 bank_group:2;
+	/** @row: Row address */
+	u64 row:16;
+	/** @channel: Memory Channel */
+	u64 channel:8;
+	/** @msu: MSU index */
+	u64 msu:8;
+	/** @reserved: Reserved for future use */
+	u64 reserved:22;
+} __packed;
+
+/**
+ * struct xe_ras_error_category - Device memory error category details
+ */
+struct xe_ras_error_category {
+	/** @pma_error: PMA (Power Management Agent) error */
+	u8 pma_error:1;
+	/** @ecc_error: Double bit ECC error */
+	u8 ecc_error:1;
+	/** @poison_detected: Write poison detected */
+	u8 poison_detected:1;
+	/** @parity_error: Parity error */
+	u8 parity_error:1;
+	/** @phy_error: PHY error */
+	u8 phy_error:1;
+	/** @reserved: Reserved for future use */
+	u8 reserved:3;
+} __packed;
+
+/**
+ * struct xe_ras_memory_error - Device memory error details
+ *
+ * This structure provides detailed information about a device memory error.
+ * Cast from error_details array for device memory errors.
+ */
+struct xe_ras_memory_error {
+	/** @category: Device memory error category */
+	struct xe_ras_error_category category;
+	/** @reserved: Reserved for future use */
+	u8 reserved[7];
+	/** @hw_address: Memory hardware physical address */
+	struct xe_ras_hardware_address hw_address;
+	/** @sw_address: Software address where error occurred */
+	u64 sw_address;
+	/** @log_array: Error syndromes associated with the error */
+	u32 log_array[8];
+	/** @reserved2: Reserved for future use */
+	u32 reserved2[2];
+} __packed;
 #endif
-- 
2.47.1


  parent reply	other threads:[~2026-04-17  8:26 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 ` [PATCH v4 06/13] drm/xe/xe_ras: Add basic structures and commands for uncorrectable errors Riana Tauro
2026-04-17 17:38   ` 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 ` Riana Tauro [this message]
2026-04-21  6:08   ` [PATCH v4 09/13] drm/xe/xe_ras: Handle uncorrectable device memory errors 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=20260417085812.4013309-24-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=himal.prasad.ghimiray@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 \
    --cc=tejas.upadhyay@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).