accel/qaic: Add Reliability, Accessibility, Serviceability (RAS)

AIC100 devices generates Reliability, Availability, Serviceability events
via MHI QAIC_STATUS channel. Support such events and print a structured
log with details of the events, and if the event describes an uncorrected
error, reset the device to put it back into service. As these events may
not all be reported via other mechanisms like AER, maintain counts of
the number of errors observed for each type.

Signed-off-by: Jeff Hugo <jeff.hugo@oss.qualcomm.com>
Reviewed-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Reviewed-by: Troy Hanson <quic_thanson@quicinc.com>
Reviewed-by: Maciej Falkowski <maciej.falkowski@linux.intel.com>
Link: https://lore.kernel.org/r/20250516160634.1408309-1-jeff.hugo@oss.qualcomm.com

Documentation/ABI/testing/sysfs-driver-qaic

@@ -0,0 +1,18 @@
+What:		/sys/bus/pci/drivers/qaic/XXXX:XX:XX.X/ce_count
+Date:		May 2025
+KernelVersion:	6.17
+Contact:	dri-devel@lists.freedesktop.org
+Description:	Number of correctable errors received from device since driver is loaded.
+
+What:		/sys/bus/pci/drivers/qaic/XXXX:XX:XX.X/ue_count
+Date:		May 2025
+KernelVersion:	6.17
+Contact:	dri-devel@lists.freedesktop.org
+Description:	Number of uncorrectable errors received from device since driver is loaded.
+
+What:		/sys/bus/pci/drivers/qaic/XXXX:XX:XX.X/ue_nonfatal_count
+Date:		May 2025
+KernelVersion:	6.17
+Contact:	dri-devel@lists.freedesktop.org
+Description:	Number of uncorrectable non-fatal errors received from device since driver
+		is loaded.

MAINTAINERS

@@ -19952,6 +19952,7 @@ L:	linux-arm-msm@vger.kernel.org
 L:	dri-devel@lists.freedesktop.org
 S:	Supported
 T:	git https://gitlab.freedesktop.org/drm/misc/kernel.git
+F:	Documentation/ABI/testing/sysfs-driver-qaic
 F:	Documentation/accel/qaic/
 F:	drivers/accel/qaic/
 F:	include/uapi/drm/qaic_accel.h

drivers/accel/qaic/Makefile

@@ -10,6 +10,7 @@ qaic-y := \
 	qaic_control.o \
 	qaic_data.o \
 	qaic_drv.o \
+	qaic_ras.o \
 	qaic_timesync.o \
 	sahara.o
 

drivers/accel/qaic/qaic.h

@@ -167,6 +167,14 @@ struct qaic_device {
 	struct workqueue_struct *bootlog_wq;
 	/* Synchronizes access of pages in MHI bootlog device */
 	struct mutex            bootlog_mutex;
+	/* MHI RAS channel device */
+	struct mhi_device	*ras_ch;
+	/* Correctable error count */
+	unsigned int		ce_count;
+	/* Un-correctable error count */
+	unsigned int		ue_count;
+	/* Un-correctable non-fatal error count */
+	unsigned int		ue_nf_count;
 };
 
 struct qaic_drm_device {

drivers/accel/qaic/qaic_drv.c

@@ -29,6 +29,7 @@
 #include "mhi_controller.h"
 #include "qaic.h"
 #include "qaic_debugfs.h"
+#include "qaic_ras.h"
 #include "qaic_timesync.h"
 #include "sahara.h"
 
@@ -695,6 +696,10 @@ static int __init qaic_init(void)
 	if (ret)
 		pr_debug("qaic: qaic_bootlog_register failed %d\n", ret);
 
+	ret = qaic_ras_register();
+	if (ret)
+		pr_debug("qaic: qaic_ras_register failed %d\n", ret);
+
 	return 0;
 
 free_mhi:
@@ -722,6 +727,7 @@ static void __exit qaic_exit(void)
 	 * reinitializing the link_up state after the cleanup is done.
 	 */
 	link_up = true;
+	qaic_ras_unregister();
 	qaic_bootlog_unregister();
 	qaic_timesync_deinit();
 	sahara_unregister();

drivers/accel/qaic/qaic_ras.h

@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (c) 2020, The Linux Foundation. All rights reserved. */
+
+#ifndef __QAIC_RAS_H__
+#define __QAIC_RAS_H__
+
+int qaic_ras_register(void);
+void qaic_ras_unregister(void);
+
+#endif /* __QAIC_RAS_H__ */