Merge tag 'drm-misc-next-2025-06-12' of https://gitlab.freedesktop.org/drm/misc/kernel into drm-next

drm-misc-next for 6.17:

UAPI Changes:

Cross-subsystem Changes:

Core Changes:
 - atomic-helpers: Tune the enable / disable sequence
 - bridge: Add destroy hook
 - color management: Add helpers for hardware gamma LUT handling
 - HDMI: Add CEC handling, YUV420 output support
 - sched: tracing improvements

Driver Changes:
 - hyperv: Move out of simple-kms, drm_panic support
 - i915: drm_panel_follower support
 - imx: Add IMX8qxq Display Controller Support
 - lima: Add Rockchip RK3528 GPU Support
 - nouveau: fence handling cleanup
 - panfrost: Add BO labeling, 64-bit registers access
 - qaic: Add RAS Support
 - rz-du: Add RZ/V2H(P) Support, MIPI-DSI DCS Support
 - sun4i: Add H616 Support
 - tidss: Add TI AM62L Support
 - vkms: YUV and R* formats support

 - bridges:
   - Switched to reference counted drm_bridge allocations

 - panels:
   - Switched to reference counted drm_panel allocations
   - Add support for fwnode-based panel lookup
   - himax-hx8394: Support for Huiling hl055fhv028c
   - ilitek-ili9881c: Support for 7" Raspberry Pi 720x1280
   - panel-edp: Support for KDC KD116N3730A05, N160JCE-ELL CMN,
   - panel-simple: Support for AUO P238HAN01
   - st7701: Support for Winstar wf40eswaa6mnn0
   - visionox-rm69299: Support for rm69299-shift
   - New panels: Renesas R61307, Renesas R69328

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Maxime Ripard <mripard@redhat.com>
Link: https://lore.kernel.org/r/20250612-coucal-of-impossible-cleaning-a5eecf@houat

11 files changed, 689 insertions, 29 deletions

diff --git a/drivers/accel/amdxdna/aie2_ctx.c b/drivers/accel/amdxdna/aie2_ctx.c
index e04549f64d69..3e38a5f637ea 100644
--- a/drivers/accel/amdxdna/aie2_ctx.c
+++ b/drivers/accel/amdxdna/aie2_ctx.c
@@ -848,7 +848,8 @@ int aie2_cmd_submit(struct amdxdna_hwctx *hwctx, struct amdxdna_sched_job *job,
 		goto up_sem;
 	}
 
-	ret = drm_sched_job_init(&job->base, &hwctx->priv->entity, 1, hwctx);
+	ret = drm_sched_job_init(&job->base, &hwctx->priv->entity, 1, hwctx,
+				 hwctx->client->filp->client_id);
 	if (ret) {
 		XDNA_ERR(xdna, "DRM job init failed, ret %d", ret);
 		goto free_chain;
diff --git a/drivers/accel/habanalabs/common/device.c b/drivers/accel/habanalabs/common/device.c
index 68eebed3b050..80fa08bf57bd 100644
--- a/drivers/accel/habanalabs/common/device.c
+++ b/drivers/accel/habanalabs/common/device.c
@@ -1066,28 +1066,11 @@ static bool is_pci_link_healthy(struct hl_device *hdev)
 	return (device_id == hdev->pdev->device);
 }
 
-static void stringify_time_of_last_heartbeat(struct hl_device *hdev, char *time_str, size_t size,
-						bool is_pq_hb)
-{
-	time64_t seconds = is_pq_hb ? hdev->heartbeat_debug_info.last_pq_heartbeat_ts
-					: hdev->heartbeat_debug_info.last_eq_heartbeat_ts;
-	struct tm tm;
-
-	if (!seconds)
-		return;
-
-	time64_to_tm(seconds, 0, &tm);
-
-	snprintf(time_str, size, "%ld-%02d-%02d %02d:%02d:%02d (UTC)",
-		tm.tm_year + 1900, tm.tm_mon, tm.tm_mday, tm.tm_hour, tm.tm_min, tm.tm_sec);
-}
-
 static bool hl_device_eq_heartbeat_received(struct hl_device *hdev)
 {
 	struct eq_heartbeat_debug_info *heartbeat_debug_info = &hdev->heartbeat_debug_info;
 	u32 cpu_q_id = heartbeat_debug_info->cpu_queue_id, pq_pi_mask = (HL_QUEUE_LENGTH << 1) - 1;
 	struct asic_fixed_properties *prop = &hdev->asic_prop;
-	char pq_time_str[64] = "N/A", eq_time_str[64] = "N/A";
 
 	if (!prop->cpucp_info.eq_health_check_supported)
 		return true;
@@ -1095,17 +1078,15 @@ static bool hl_device_eq_heartbeat_received(struct hl_device *hdev)
 	if (!hdev->eq_heartbeat_received) {
 		dev_err(hdev->dev, "EQ heartbeat event was not received!\n");
 
-		stringify_time_of_last_heartbeat(hdev, pq_time_str, sizeof(pq_time_str), true);
-		stringify_time_of_last_heartbeat(hdev, eq_time_str, sizeof(eq_time_str), false);
 		dev_err(hdev->dev,
-			"EQ: {CI %u, HB counter %u, last HB time: %s}, PQ: {PI: %u, CI: %u (%u), last HB time: %s}\n",
+			"EQ: {CI %u, HB counter %u, last HB time: %ptTs}, PQ: {PI: %u, CI: %u (%u), last HB time: %ptTs}\n",
 			hdev->event_queue.ci,
 			heartbeat_debug_info->heartbeat_event_counter,
-			eq_time_str,
+			&hdev->heartbeat_debug_info.last_eq_heartbeat_ts,
 			hdev->kernel_queues[cpu_q_id].pi,
 			atomic_read(&hdev->kernel_queues[cpu_q_id].ci),
 			atomic_read(&hdev->kernel_queues[cpu_q_id].ci) & pq_pi_mask,
-			pq_time_str);
+			&hdev->heartbeat_debug_info.last_pq_heartbeat_ts);
 
 		hl_eq_dump(hdev, &hdev->event_queue);
 
diff --git a/drivers/accel/ivpu/ivpu_drv.h b/drivers/accel/ivpu/ivpu_drv.h
index 5497e7030e91..b6d6b3238b59 100644
--- a/drivers/accel/ivpu/ivpu_drv.h
+++ b/drivers/accel/ivpu/ivpu_drv.h
@@ -165,6 +165,7 @@ struct ivpu_device {
 		int boot;
 		int jsm;
 		int tdr;
+		int inference;
 		int autosuspend;
 		int d0i3_entry_msg;
 		int state_dump_msg;
diff --git a/drivers/accel/ivpu/ivpu_hw.c b/drivers/accel/ivpu/ivpu_hw.c
index 633160470c93..08dcc31b56f4 100644
--- a/drivers/accel/ivpu/ivpu_hw.c
+++ b/drivers/accel/ivpu/ivpu_hw.c
@@ -94,12 +94,14 @@ static void timeouts_init(struct ivpu_device *vdev)
 		vdev->timeout.boot = -1;
 		vdev->timeout.jsm = -1;
 		vdev->timeout.tdr = -1;
+		vdev->timeout.inference = -1;
 		vdev->timeout.autosuspend = -1;
 		vdev->timeout.d0i3_entry_msg = -1;
 	} else if (ivpu_is_fpga(vdev)) {
 		vdev->timeout.boot = 50;
 		vdev->timeout.jsm = 15000;
 		vdev->timeout.tdr = 30000;
+		vdev->timeout.inference = 900000;
 		vdev->timeout.autosuspend = -1;
 		vdev->timeout.d0i3_entry_msg = 500;
 		vdev->timeout.state_dump_msg = 10000;
@@ -107,6 +109,7 @@ static void timeouts_init(struct ivpu_device *vdev)
 		vdev->timeout.boot = 50;
 		vdev->timeout.jsm = 500;
 		vdev->timeout.tdr = 10000;
+		vdev->timeout.inference = 300000;
 		vdev->timeout.autosuspend = 100;
 		vdev->timeout.d0i3_entry_msg = 100;
 		vdev->timeout.state_dump_msg = 10;
@@ -114,6 +117,7 @@ static void timeouts_init(struct ivpu_device *vdev)
 		vdev->timeout.boot = 1000;
 		vdev->timeout.jsm = 500;
 		vdev->timeout.tdr = 2000;
+		vdev->timeout.inference = 60000;
 		if (ivpu_hw_ip_gen(vdev) == IVPU_HW_IP_37XX)
 			vdev->timeout.autosuspend = 10;
 		else
diff --git a/drivers/accel/ivpu/ivpu_pm.c b/drivers/accel/ivpu/ivpu_pm.c
index ea30db181cd7..eacda1dbe840 100644
--- a/drivers/accel/ivpu/ivpu_pm.c
+++ b/drivers/accel/ivpu/ivpu_pm.c
@@ -33,8 +33,11 @@ static unsigned long ivpu_tdr_timeout_ms;
 module_param_named(tdr_timeout_ms, ivpu_tdr_timeout_ms, ulong, 0644);
 MODULE_PARM_DESC(tdr_timeout_ms, "Timeout for device hang detection, in milliseconds, 0 - default");
 
+static unsigned long ivpu_inference_timeout_ms;
+module_param_named(inference_timeout_ms, ivpu_inference_timeout_ms, ulong, 0644);
+MODULE_PARM_DESC(inference_timeout_ms, "Inference maximum duration, in milliseconds, 0 - default");
+
 #define PM_RESCHEDULE_LIMIT     5
-#define PM_TDR_HEARTBEAT_LIMIT  30
 
 static void ivpu_pm_prepare_cold_boot(struct ivpu_device *vdev)
 {
@@ -191,6 +194,10 @@ static void ivpu_job_timeout_work(struct work_struct *work)
 {
 	struct ivpu_pm_info *pm = container_of(work, struct ivpu_pm_info, job_timeout_work.work);
 	struct ivpu_device *vdev = pm->vdev;
+	unsigned long timeout_ms = ivpu_tdr_timeout_ms ? ivpu_tdr_timeout_ms : vdev->timeout.tdr;
+	unsigned long inference_timeout_ms = ivpu_inference_timeout_ms ? ivpu_inference_timeout_ms :
+					     vdev->timeout.inference;
+	u64 inference_max_retries;
 	u64 heartbeat;
 
 	if (ivpu_jsm_get_heartbeat(vdev, 0, &heartbeat) || heartbeat <= vdev->fw->last_heartbeat) {
@@ -198,8 +205,10 @@ static void ivpu_job_timeout_work(struct work_struct *work)
 		goto recovery;
 	}
 
-	if (atomic_fetch_inc(&vdev->job_timeout_counter) > PM_TDR_HEARTBEAT_LIMIT) {
-		ivpu_err(vdev, "Job timeout detected, heartbeat limit exceeded\n");
+	inference_max_retries = DIV_ROUND_UP(inference_timeout_ms, timeout_ms);
+	if (atomic_fetch_inc(&vdev->job_timeout_counter) >= inference_max_retries) {
+		ivpu_err(vdev, "Job timeout detected, heartbeat limit (%lld) exceeded\n",
+			 inference_max_retries);
 		goto recovery;
 	}
 
diff --git a/drivers/accel/qaic/Makefile b/drivers/accel/qaic/Makefile
index 35e883515629..1106b876f737 100644
--- a/drivers/accel/qaic/Makefile
+++ b/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
 
diff --git a/drivers/accel/qaic/qaic.h b/drivers/accel/qaic/qaic.h
index 0dbb8e32e4b9..c31081e42cee 100644
--- a/drivers/accel/qaic/qaic.h
+++ b/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 {
@@ -213,8 +221,6 @@ struct qaic_bo {
 	bool			sliced;
 	/* Request ID of this BO if it is queued for execution */
 	u16			req_id;
-	/* Handle assigned to this BO */
-	u32			handle;
 	/* Wait on this for completion of DMA transfer of this BO */
 	struct completion	xfer_done;
 	/*
diff --git a/drivers/accel/qaic/qaic_data.c b/drivers/accel/qaic/qaic_data.c
index 1bce1af7c72c..797289e9d780 100644
--- a/drivers/accel/qaic/qaic_data.c
+++ b/drivers/accel/qaic/qaic_data.c
@@ -731,7 +731,6 @@ int qaic_create_bo_ioctl(struct drm_device *dev, void *data, struct drm_file *fi
 	if (ret)
 		goto free_bo;
 
-	bo->handle = args->handle;
 	drm_gem_object_put(obj);
 	srcu_read_unlock(&qdev->dev_lock, qdev_rcu_id);
 	srcu_read_unlock(&usr->qddev_lock, usr_rcu_id);
diff --git a/drivers/accel/qaic/qaic_drv.c b/drivers/accel/qaic/qaic_drv.c
index 3b415e2c9431..e31bcb0ecfc9 100644
--- a/drivers/accel/qaic/qaic_drv.c
+++ b/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();
diff --git a/drivers/accel/qaic/qaic_ras.c b/drivers/accel/qaic/qaic_ras.c
new file mode 100644
index 000000000000..914ffc4a9970
--- /dev/null
+++ b/drivers/accel/qaic/qaic_ras.c
@@ -0,0 +1,642 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+/* Copyright (c) 2020-2021, The Linux Foundation. All rights reserved. */
+/* Copyright (c) 2022-2024 Qualcomm Innovation Center, Inc. All rights reserved. */
+/* Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */
+
+#include <asm/byteorder.h>
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/mhi.h>
+
+#include "qaic.h"
+#include "qaic_ras.h"
+
+#define MAGIC		0x55AA
+#define VERSION		0x2
+#define HDR_SZ		12
+#define NUM_TEMP_LVL	3
+#define POWER_BREAK	BIT(0)
+
+enum msg_type {
+	MSG_PUSH, /* async push from device */
+	MSG_REQ,  /* sync request to device */
+	MSG_RESP, /* sync response from device */
+};
+
+enum err_type {
+	CE,	/* correctable error */
+	UE,	/* uncorrectable error */
+	UE_NF,	/* uncorrectable error that is non-fatal, expect a disruption */
+	ERR_TYPE_MAX,
+};
+
+static const char * const err_type_str[] = {
+	[CE]    = "Correctable",
+	[UE]    = "Uncorrectable",
+	[UE_NF] = "Uncorrectable Non-Fatal",
+};
+
+static const char * const err_class_str[] = {
+	[CE]    = "Warning",
+	[UE]    = "Fatal",
+	[UE_NF] = "Warning",
+};
+
+enum err_source {
+	SOC_MEM,
+	PCIE,
+	DDR,
+	SYS_BUS1,
+	SYS_BUS2,
+	NSP_MEM,
+	TSENS,
+};
+
+static const char * const err_src_str[TSENS + 1] = {
+	[SOC_MEM]	= "SoC Memory",
+	[PCIE]		= "PCIE",
+	[DDR]		= "DDR",
+	[SYS_BUS1]	= "System Bus source 1",
+	[SYS_BUS2]	= "System Bus source 2",
+	[NSP_MEM]	= "NSP Memory",
+	[TSENS]		= "Temperature Sensors",
+};
+
+struct ras_data {
+	/* header start */
+	/* Magic number to validate the message */
+	u16 magic;
+	/* RAS version number */
+	u16 ver;
+	u32 seq_num;
+	/* RAS message type */
+	u8  type;
+	u8  id;
+	/* Size of RAS message without the header in byte */
+	u16 len;
+	/* header end */
+	s32 result;
+	/*
+	 * Error source
+	 * 0 : SoC Memory
+	 * 1 : PCIE
+	 * 2 : DDR
+	 * 3 : System Bus source 1
+	 * 4 : System Bus source 2
+	 * 5 : NSP Memory
+	 * 6 : Temperature Sensors
+	 */
+	u32 source;
+	/*
+	 * Stores the error type, there are three types of error in RAS
+	 * 0 : correctable error (CE)
+	 * 1 : uncorrectable error (UE)
+	 * 2 : uncorrectable error that is non-fatal (UE_NF)
+	 */
+	u32 err_type;
+	u32 err_threshold;
+	u32 ce_count;
+	u32 ue_count;
+	u32 intr_num;
+	/* Data specific to error source */
+	u8  syndrome[64];
+} __packed;
+
+struct soc_mem_syndrome {
+	u64 error_address[8];
+} __packed;
+
+struct nsp_mem_syndrome {
+	u32 error_address[8];
+	u8 nsp_id;
+} __packed;
+
+struct ddr_syndrome {
+	u32 count;
+	u32 irq_status;
+	u32 data_31_0[2];
+	u32 data_63_32[2];
+	u32 data_95_64[2];
+	u32 data_127_96[2];
+	u32 addr_lsb;
+	u16 addr_msb;
+	u16 parity_bits;
+	u16 instance;
+	u16 err_type;
+} __packed;
+
+struct tsens_syndrome {
+	u32 threshold_type;
+	s32 temp;
+} __packed;
+
+struct sysbus1_syndrome {
+	u32 slave;
+	u32 err_type;
+	u16 addr[8];
+	u8  instance;
+} __packed;
+
+struct sysbus2_syndrome {
+	u32 lsb3;
+	u32 msb3;
+	u32 lsb2;
+	u32 msb2;
+	u32 ext_id;
+	u16 path;
+	u16 op_type;
+	u16 len;
+	u16 redirect;
+	u8  valid;
+	u8  word_error;
+	u8  non_secure;
+	u8  opc;
+	u8  error_code;
+	u8  trans_type;
+	u8  addr_space;
+	u8  instance;
+} __packed;
+
+struct pcie_syndrome {
+	/* CE info */
+	u32 bad_tlp;
+	u32 bad_dllp;
+	u32 replay_rollover;
+	u32 replay_timeout;
+	u32 rx_err;
+	u32 internal_ce_count;
+	/* UE_NF info */
+	u32 fc_timeout;
+	u32 poison_tlp;
+	u32 ecrc_err;
+	u32 unsupported_req;
+	u32 completer_abort;
+	u32 completion_timeout;
+	/* UE info */
+	u32 addr;
+	u8  index;
+	/*
+	 * Flag to indicate specific event of PCIe
+	 * BIT(0): Power break (low power)
+	 * BIT(1) to BIT(7): Reserved
+	 */
+	u8 flag;
+} __packed;
+
+static const char * const threshold_type_str[NUM_TEMP_LVL] = {
+	[0] = "lower",
+	[1] = "upper",
+	[2] = "critical",
+};
+
+static void ras_msg_to_cpu(struct ras_data *msg)
+{
+	struct sysbus1_syndrome *sysbus1_syndrome = (struct sysbus1_syndrome *)&msg->syndrome[0];
+	struct sysbus2_syndrome *sysbus2_syndrome = (struct sysbus2_syndrome *)&msg->syndrome[0];
+	struct soc_mem_syndrome *soc_syndrome = (struct soc_mem_syndrome *)&msg->syndrome[0];
+	struct nsp_mem_syndrome *nsp_syndrome = (struct nsp_mem_syndrome *)&msg->syndrome[0];
+	struct tsens_syndrome *tsens_syndrome = (struct tsens_syndrome *)&msg->syndrome[0];
+	struct pcie_syndrome *pcie_syndrome = (struct pcie_syndrome *)&msg->syndrome[0];
+	struct ddr_syndrome *ddr_syndrome = (struct ddr_syndrome *)&msg->syndrome[0];
+	int i;
+
+	le16_to_cpus(&msg->magic);
+	le16_to_cpus(&msg->ver);
+	le32_to_cpus(&msg->seq_num);
+	le16_to_cpus(&msg->len);
+	le32_to_cpus(&msg->result);
+	le32_to_cpus(&msg->source);
+	le32_to_cpus(&msg->err_type);
+	le32_to_cpus(&msg->err_threshold);
+	le32_to_cpus(&msg->ce_count);
+	le32_to_cpus(&msg->ue_count);
+	le32_to_cpus(&msg->intr_num);
+
+	switch (msg->source) {
+	case SOC_MEM:
+		for (i = 0; i < 8; i++)
+			le64_to_cpus(&soc_syndrome->error_address[i]);
+		break;
+	case PCIE:
+		le32_to_cpus(&pcie_syndrome->bad_tlp);
+		le32_to_cpus(&pcie_syndrome->bad_dllp);
+		le32_to_cpus(&pcie_syndrome->replay_rollover);
+		le32_to_cpus(&pcie_syndrome->replay_timeout);
+		le32_to_cpus(&pcie_syndrome->rx_err);
+		le32_to_cpus(&pcie_syndrome->internal_ce_count);
+		le32_to_cpus(&pcie_syndrome->fc_timeout);
+		le32_to_cpus(&pcie_syndrome->poison_tlp);
+		le32_to_cpus(&pcie_syndrome->ecrc_err);
+		le32_to_cpus(&pcie_syndrome->unsupported_req);
+		le32_to_cpus(&pcie_syndrome->completer_abort);
+		le32_to_cpus(&pcie_syndrome->completion_timeout);
+		le32_to_cpus(&pcie_syndrome->addr);
+		break;
+	case DDR:
+		le16_to_cpus(&ddr_syndrome->instance);
+		le16_to_cpus(&ddr_syndrome->err_type);
+		le32_to_cpus(&ddr_syndrome->count);
+		le32_to_cpus(&ddr_syndrome->irq_status);
+		le32_to_cpus(&ddr_syndrome->data_31_0[0]);
+		le32_to_cpus(&ddr_syndrome->data_31_0[1]);
+		le32_to_cpus(&ddr_syndrome->data_63_32[0]);
+		le32_to_cpus(&ddr_syndrome->data_63_32[1]);
+		le32_to_cpus(&ddr_syndrome->data_95_64[0]);
+		le32_to_cpus(&ddr_syndrome->data_95_64[1]);
+		le32_to_cpus(&ddr_syndrome->data_127_96[0]);
+		le32_to_cpus(&ddr_syndrome->data_127_96[1]);
+		le16_to_cpus(&ddr_syndrome->parity_bits);
+		le16_to_cpus(&ddr_syndrome->addr_msb);
+		le32_to_cpus(&ddr_syndrome->addr_lsb);
+		break;
+	case SYS_BUS1:
+		le32_to_cpus(&sysbus1_syndrome->slave);
+		le32_to_cpus(&sysbus1_syndrome->err_type);
+		for (i = 0; i < 8; i++)
+			le16_to_cpus(&sysbus1_syndrome->addr[i]);
+		break;
+	case SYS_BUS2:
+		le16_to_cpus(&sysbus2_syndrome->op_type);
+		le16_to_cpus(&sysbus2_syndrome->len);
+		le16_to_cpus(&sysbus2_syndrome->redirect);
+		le16_to_cpus(&sysbus2_syndrome->path);
+		le32_to_cpus(&sysbus2_syndrome->ext_id);
+		le32_to_cpus(&sysbus2_syndrome->lsb2);
+		le32_to_cpus(&sysbus2_syndrome->msb2);
+		le32_to_cpus(&sysbus2_syndrome->lsb3);
+		le32_to_cpus(&sysbus2_syndrome->msb3);
+		break;
+	case NSP_MEM:
+		for (i = 0; i < 8; i++)
+			le32_to_cpus(&nsp_syndrome->error_address[i]);
+		break;
+	case TSENS:
+		le32_to_cpus(&tsens_syndrome->threshold_type);
+		le32_to_cpus(&tsens_syndrome->temp);
+		break;
+	}
+}
+
+static void decode_ras_msg(struct qaic_device *qdev, struct ras_data *msg)
+{
+	struct sysbus1_syndrome *sysbus1_syndrome = (struct sysbus1_syndrome *)&msg->syndrome[0];
+	struct sysbus2_syndrome *sysbus2_syndrome = (struct sysbus2_syndrome *)&msg->syndrome[0];
+	struct soc_mem_syndrome *soc_syndrome = (struct soc_mem_syndrome *)&msg->syndrome[0];
+	struct nsp_mem_syndrome *nsp_syndrome = (struct nsp_mem_syndrome *)&msg->syndrome[0];
+	struct tsens_syndrome *tsens_syndrome = (struct tsens_syndrome *)&msg->syndrome[0];
+	struct pcie_syndrome *pcie_syndrome = (struct pcie_syndrome *)&msg->syndrome[0];
+	struct ddr_syndrome *ddr_syndrome = (struct ddr_syndrome *)&msg->syndrome[0];
+	char *class;
+	char *level;
+
+	if (msg->magic != MAGIC) {
+		pci_warn(qdev->pdev, "Dropping RAS message with invalid magic %x\n", msg->magic);
+		return;
+	}
+
+	if (!msg->ver || msg->ver > VERSION) {
+		pci_warn(qdev->pdev, "Dropping RAS message with invalid version %d\n", msg->ver);
+		return;
+	}
+
+	if (msg->type != MSG_PUSH) {
+		pci_warn(qdev->pdev, "Dropping non-PUSH RAS message\n");
+		return;
+	}
+
+	if (msg->len != sizeof(*msg) - HDR_SZ) {
+		pci_warn(qdev->pdev, "Dropping RAS message with invalid len %d\n", msg->len);
+		return;
+	}
+
+	if (msg->err_type >= ERR_TYPE_MAX) {
+		pci_warn(qdev->pdev, "Dropping RAS message with err type %d\n", msg->err_type);
+		return;
+	}
+
+	if (msg->err_type == UE)
+		level = KERN_ERR;
+	else
+		level = KERN_WARNING;
+
+	switch (msg->source) {
+	case SOC_MEM:
+		dev_printk(level, &qdev->pdev->dev, "RAS event.\nClass:%s\nDescription:%s %s %s\nError Threshold for this report %d\nSyndrome:\n    0x%llx\n    0x%llx\n    0x%llx\n    0x%llx\n    0x%llx\n    0x%llx\n    0x%llx\n    0x%llx\n",
+			   err_class_str[msg->err_type],
+			   err_type_str[msg->err_type],
+			   "error from",
+			   err_src_str[msg->source],
+			   msg->err_threshold,
+			   soc_syndrome->error_address[0],
+			   soc_syndrome->error_address[1],
+			   soc_syndrome->error_address[2],
+			   soc_syndrome->error_address[3],
+			   soc_syndrome->error_address[4],
+			   soc_syndrome->error_address[5],
+			   soc_syndrome->error_address[6],
+			   soc_syndrome->error_address[7]);
+		break;
+	case PCIE:
+		dev_printk(level, &qdev->pdev->dev, "RAS event.\nClass:%s\nDescription:%s %s %s\nError Threshold for this report %d\n",
+			   err_class_str[msg->err_type],
+			   err_type_str[msg->err_type],
+			   "error from",
+			   err_src_str[msg->source],
+			   msg->err_threshold);
+
+		switch (msg->err_type) {
+		case CE:
+			/*
+			 * Modeled after AER prints. This continues the dev_printk() from a few
+			 * lines up. We reduce duplication of code, but also avoid re-printing the
+			 * PCI device info so that the end result looks uniform to the log user.
+			 */
+			printk(KERN_WARNING pr_fmt("Syndrome:\n    Bad TLP count %d\n    Bad DLLP count %d\n    Replay Rollover count %d\n    Replay Timeout count %d\n    Recv Error count %d\n    Internal CE count %d\n"),
+			       pcie_syndrome->bad_tlp,
+			       pcie_syndrome->bad_dllp,
+			       pcie_syndrome->replay_rollover,
+			       pcie_syndrome->replay_timeout,
+			       pcie_syndrome->rx_err,
+			       pcie_syndrome->internal_ce_count);
+			if (msg->ver > 0x1)
+				pr_warn("    Power break %s\n",
+					pcie_syndrome->flag & POWER_BREAK ? "ON" : "OFF");
+			break;
+		case UE:
+			printk(KERN_ERR pr_fmt("Syndrome:\n    Index %d\n    Address 0x%x\n"),
+			       pcie_syndrome->index, pcie_syndrome->addr);
+			break;
+		case UE_NF:
+			printk(KERN_WARNING pr_fmt("Syndrome:\n    FC timeout count %d\n    Poisoned TLP count %d\n    ECRC error count %d\n    Unsupported request count %d\n    Completer abort count %d\n    Completion timeout count %d\n"),
+			       pcie_syndrome->fc_timeout,
+			       pcie_syndrome->poison_tlp,
+			       pcie_syndrome->ecrc_err,
+			       pcie_syndrome->unsupported_req,
+			       pcie_syndrome->completer_abort,
+			       pcie_syndrome->completion_timeout);
+			break;
+		default:
+			break;
+		}
+		break;
+	case DDR:
+		dev_printk(level, &qdev->pdev->dev, "RAS event.\nClass:%s\nDescription:%s %s %s\nError Threshold for this report %d\nSyndrome:\n    Instance %d\n    Count %d\n    Data 31_0 0x%x 0x%x\n    Data 63_32 0x%x 0x%x\n    Data 95_64 0x%x 0x%x\n    Data 127_96 0x%x 0x%x\n    Parity bits 0x%x\n    Address msb 0x%x\n    Address lsb 0x%x\n",
+			   err_class_str[msg->err_type],
+			   err_type_str[msg->err_type],
+			   "error from",
+			   err_src_str[msg->source],
+			   msg->err_threshold,
+			   ddr_syndrome->instance,
+			   ddr_syndrome->count,
+			   ddr_syndrome->data_31_0[1],
+			   ddr_syndrome->data_31_0[0],
+			   ddr_syndrome->data_63_32[1],
+			   ddr_syndrome->data_63_32[0],
+			   ddr_syndrome->data_95_64[1],
+			   ddr_syndrome->data_95_64[0],
+			   ddr_syndrome->data_127_96[1],
+			   ddr_syndrome->data_127_96[0],
+			   ddr_syndrome->parity_bits,
+			   ddr_syndrome->addr_msb,
+			   ddr_syndrome->addr_lsb);
+		break;
+	case SYS_BUS1:
+		dev_printk(level, &qdev->pdev->dev, "RAS event.\nClass:%s\nDescription:%s %s %s\nError Threshold for this report %d\nSyndrome:\n    instance %d\n    %s\n    err_type %d\n    address0 0x%x\n    address1 0x%x\n    address2 0x%x\n    address3 0x%x\n    address4 0x%x\n    address5 0x%x\n    address6 0x%x\n    address7 0x%x\n",
+			   err_class_str[msg->err_type],
+			   err_type_str[msg->err_type],
+			   "error from",
+			   err_src_str[msg->source],
+			   msg->err_threshold,
+			   sysbus1_syndrome->instance,
+			   sysbus1_syndrome->slave ? "Slave" : "Master",
+			   sysbus1_syndrome->err_type,
+			   sysbus1_syndrome->addr[0],
+			   sysbus1_syndrome->addr[1],
+			   sysbus1_syndrome->addr[2],
+			   sysbus1_syndrome->addr[3],
+			   sysbus1_syndrome->addr[4],
+			   sysbus1_syndrome->addr[5],
+			   sysbus1_syndrome->addr[6],
+			   sysbus1_syndrome->addr[7]);
+		break;
+	case SYS_BUS2:
+		dev_printk(level, &qdev->pdev->dev, "RAS event.\nClass:%s\nDescription:%s %s %s\nError Threshold for this report %d\nSyndrome:\n    instance %d\n    valid %d\n    word error %d\n    non-secure %d\n    opc %d\n    error code %d\n    transaction type %d\n    address space %d\n    operation type %d\n    len %d\n    redirect %d\n    path %d\n    ext_id %d\n    lsb2 %d\n    msb2 %d\n    lsb3 %d\n    msb3 %d\n",
+			   err_class_str[msg->err_type],
+			   err_type_str[msg->err_type],
+			   "error from",
+			   err_src_str[msg->source],
+			   msg->err_threshold,
+			   sysbus2_syndrome->instance,
+			   sysbus2_syndrome->valid,
+			   sysbus2_syndrome->word_error,
+			   sysbus2_syndrome->non_secure,
+			   sysbus2_syndrome->opc,
+			   sysbus2_syndrome->error_code,
+			   sysbus2_syndrome->trans_type,
+			   sysbus2_syndrome->addr_space,
+			   sysbus2_syndrome->op_type,
+			   sysbus2_syndrome->len,
+			   sysbus2_syndrome->redirect,
+			   sysbus2_syndrome->path,
+			   sysbus2_syndrome->ext_id,
+			   sysbus2_syndrome->lsb2,
+			   sysbus2_syndrome->msb2,
+			   sysbus2_syndrome->lsb3,
+			   sysbus2_syndrome->msb3);
+		break;
+	case NSP_MEM:
+		dev_printk(level, &qdev->pdev->dev, "RAS event.\nClass:%s\nDescription:%s %s %s\nError Threshold for this report %d\nSyndrome:\n    NSP ID %d\n    0x%x\n    0x%x\n    0x%x\n    0x%x\n    0x%x\n    0x%x\n    0x%x\n    0x%x\n",
+			   err_class_str[msg->err_type],
+			   err_type_str[msg->err_type],
+			   "error from",
+			   err_src_str[msg->source],
+			   msg->err_threshold,
+			   nsp_syndrome->nsp_id,
+			   nsp_syndrome->error_address[0],
+			   nsp_syndrome->error_address[1],
+			   nsp_syndrome->error_address[2],
+			   nsp_syndrome->error_address[3],
+			   nsp_syndrome->error_address[4],
+			   nsp_syndrome->error_address[5],
+			   nsp_syndrome->error_address[6],
+			   nsp_syndrome->error_address[7]);
+		break;
+	case TSENS:
+		if (tsens_syndrome->threshold_type >= NUM_TEMP_LVL) {
+			pci_warn(qdev->pdev, "Dropping RAS message with invalid temp threshold %d\n",
+				 tsens_syndrome->threshold_type);
+			break;
+		}
+
+		if (msg->err_type)
+			class = "Fatal";
+		else if (tsens_syndrome->threshold_type)
+			class = "Critical";
+		else
+			class = "Warning";
+
+		dev_printk(level, &qdev->pdev->dev, "RAS event.\nClass:%s\nDescription:%s %s %s\nError Threshold for this report %d\nSyndrome:\n    %s threshold\n    %d deg C\n",
+			   class,
+			   err_type_str[msg->err_type],
+			   "error from",
+			   err_src_str[msg->source],
+			   msg->err_threshold,
+			   threshold_type_str[tsens_syndrome->threshold_type],
+			   tsens_syndrome->temp);
+		break;
+	}
+
+	/* Uncorrectable errors are fatal */
+	if (msg->err_type == UE)
+		mhi_soc_reset(qdev->mhi_cntrl);
+
+	switch (msg->err_type) {
+	case CE:
+		if (qdev->ce_count != UINT_MAX)
+			qdev->ce_count++;
+		break;
+	case UE:
+		if (qdev->ce_count != UINT_MAX)
+			qdev->ue_count++;
+		break;
+	case UE_NF:
+		if (qdev->ce_count != UINT_MAX)
+			qdev->ue_nf_count++;
+		break;
+	default:
+		/* not possible */
+		break;
+	}
+}
+
+static ssize_t ce_count_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct qaic_device *qdev = pci_get_drvdata(to_pci_dev(dev));
+
+	return snprintf(buf, PAGE_SIZE, "%d\n", qdev->ce_count);
+}
+
+static ssize_t ue_count_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct qaic_device *qdev = pci_get_drvdata(to_pci_dev(dev));
+
+	return snprintf(buf, PAGE_SIZE, "%d\n", qdev->ue_count);
+}
+
+static ssize_t ue_nonfatal_count_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct qaic_device *qdev = pci_get_drvdata(to_pci_dev(dev));
+
+	return snprintf(buf, PAGE_SIZE, "%d\n", qdev->ue_nf_count);
+}
+
+static DEVICE_ATTR_RO(ce_count);
+static DEVICE_ATTR_RO(ue_count);
+static DEVICE_ATTR_RO(ue_nonfatal_count);
+
+static struct attribute *ras_attrs[] = {
+	&dev_attr_ce_count.attr,
+	&dev_attr_ue_count.attr,
+	&dev_attr_ue_nonfatal_count.attr,
+	NULL,
+};
+
+static struct attribute_group ras_group = {
+	.attrs = ras_attrs,
+};
+
+static int qaic_ras_mhi_probe(struct mhi_device *mhi_dev, const struct mhi_device_id *id)
+{
+	struct qaic_device *qdev = pci_get_drvdata(to_pci_dev(mhi_dev->mhi_cntrl->cntrl_dev));
+	struct ras_data *resp;
+	int ret;
+
+	ret = mhi_prepare_for_transfer(mhi_dev);
+	if (ret)
+		return ret;
+
+	resp = kzalloc(sizeof(*resp), GFP_KERNEL);
+	if (!resp) {
+		mhi_unprepare_from_transfer(mhi_dev);
+		return -ENOMEM;
+	}
+
+	ret = mhi_queue_buf(mhi_dev, DMA_FROM_DEVICE, resp, sizeof(*resp), MHI_EOT);
+	if (ret) {
+		kfree(resp);
+		mhi_unprepare_from_transfer(mhi_dev);
+		return ret;
+	}
+
+	ret = device_add_group(&qdev->pdev->dev, &ras_group);
+	if (ret) {
+		mhi_unprepare_from_transfer(mhi_dev);
+		pci_dbg(qdev->pdev, "ras add sysfs failed %d\n", ret);
+		return ret;
+	}
+
+	dev_set_drvdata(&mhi_dev->dev, qdev);
+	qdev->ras_ch = mhi_dev;
+
+	return ret;
+}
+
+static void qaic_ras_mhi_remove(struct mhi_device *mhi_dev)
+{
+	struct qaic_device *qdev;
+
+	qdev = dev_get_drvdata(&mhi_dev->dev);
+	qdev->ras_ch = NULL;
+	device_remove_group(&qdev->pdev->dev, &ras_group);
+	mhi_unprepare_from_transfer(mhi_dev);
+}
+
+static void qaic_ras_mhi_ul_xfer_cb(struct mhi_device *mhi_dev, struct mhi_result *mhi_result) {}
+
+static void qaic_ras_mhi_dl_xfer_cb(struct mhi_device *mhi_dev, struct mhi_result *mhi_result)
+{
+	struct qaic_device *qdev = dev_get_drvdata(&mhi_dev->dev);
+	struct ras_data *msg = mhi_result->buf_addr;
+	int ret;
+
+	if (mhi_result->transaction_status) {
+		kfree(msg);
+		return;
+	}
+
+	ras_msg_to_cpu(msg);
+	decode_ras_msg(qdev, msg);
+
+	ret = mhi_queue_buf(qdev->ras_ch, DMA_FROM_DEVICE, msg, sizeof(*msg), MHI_EOT);
+	if (ret) {
+		dev_err(&mhi_dev->dev, "Cannot requeue RAS recv buf %d\n", ret);
+		kfree(msg);
+	}
+}
+
+static const struct mhi_device_id qaic_ras_mhi_match_table[] = {
+	{ .chan = "QAIC_STATUS", },
+	{},
+};
+
+static struct mhi_driver qaic_ras_mhi_driver = {
+	.id_table = qaic_ras_mhi_match_table,
+	.remove = qaic_ras_mhi_remove,
+	.probe = qaic_ras_mhi_probe,
+	.ul_xfer_cb = qaic_ras_mhi_ul_xfer_cb,
+	.dl_xfer_cb = qaic_ras_mhi_dl_xfer_cb,
+	.driver = {
+		.name = "qaic_ras",
+	},
+};
+
+int qaic_ras_register(void)
+{
+	return mhi_driver_register(&qaic_ras_mhi_driver);
+}
+
+void qaic_ras_unregister(void)
+{
+	mhi_driver_unregister(&qaic_ras_mhi_driver);
+}
diff --git a/drivers/accel/qaic/qaic_ras.h b/drivers/accel/qaic/qaic_ras.h
new file mode 100644
index 000000000000..d44a4eeeb060
--- /dev/null
+++ b/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__ */