From: Lizhi Hou <lizhi.hou@amd.com>
To: Mario Limonciello <mario.limonciello@amd.com>,
<ogabbay@kernel.org>, <quic_jhugo@quicinc.com>,
<dri-devel@lists.freedesktop.org>,
<maciej.falkowski@linux.intel.com>
Cc: <linux-kernel@vger.kernel.org>, <max.zhen@amd.com>,
<sonal.santan@amd.com>
Subject: Re: [PATCH V2] accel/amdxdna: Support retrieving hardware context debug information
Date: Tue, 17 Mar 2026 14:11:59 -0700 [thread overview]
Message-ID: <7ba9b420-1542-32ef-1616-4fe5b97141b9@amd.com> (raw)
In-Reply-To: <65849b9e-6a94-458b-b389-c6a9b418d2a1@amd.com>
Applied to drm-misc-next.
On 3/17/26 12:25, Mario Limonciello wrote:
>
>
> On 3/16/26 23:49, Lizhi Hou wrote:
>> The firmware implements the GET_APP_HEALTH command to collect debug
>> information for a specific hardware context.
>>
>> When a command times out, the driver issues this command to collect the
>> relevant debug information. User space tools can also retrieve this
>> information through the hardware context query IOCTL.
>>
>> Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
> Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
>> ---
>> drivers/accel/amdxdna/aie2_ctx.c | 85 ++++++++++++++++++++++++---
>> drivers/accel/amdxdna/aie2_message.c | 41 +++++++++++++
>> drivers/accel/amdxdna/aie2_msg_priv.h | 52 ++++++++++++++++
>> drivers/accel/amdxdna/aie2_pci.c | 14 +++++
>> drivers/accel/amdxdna/aie2_pci.h | 5 ++
>> drivers/accel/amdxdna/amdxdna_ctx.c | 6 +-
>> drivers/accel/amdxdna/amdxdna_ctx.h | 18 +++++-
>> drivers/accel/amdxdna/npu4_regs.c | 3 +-
>> 8 files changed, 213 insertions(+), 11 deletions(-)
>>
>> diff --git a/drivers/accel/amdxdna/aie2_ctx.c
>> b/drivers/accel/amdxdna/aie2_ctx.c
>> index 779ac70d62d7..6292349868c5 100644
>> --- a/drivers/accel/amdxdna/aie2_ctx.c
>> +++ b/drivers/accel/amdxdna/aie2_ctx.c
>> @@ -29,6 +29,16 @@ MODULE_PARM_DESC(force_cmdlist, "Force use command
>> list (Default true)");
>> #define HWCTX_MAX_TIMEOUT 60000 /* milliseconds */
>> +struct aie2_ctx_health {
>> + struct amdxdna_ctx_health header;
>> + u32 txn_op_idx;
>> + u32 ctx_pc;
>> + u32 fatal_error_type;
>> + u32 fatal_error_exception_type;
>> + u32 fatal_error_exception_pc;
>> + u32 fatal_error_app_module;
>> +};
>> +
>> static void aie2_job_release(struct kref *ref)
>> {
>> struct amdxdna_sched_job *job;
>> @@ -39,6 +49,7 @@ static void aie2_job_release(struct kref *ref)
>> wake_up(&job->hwctx->priv->job_free_wq);
>> if (job->out_fence)
>> dma_fence_put(job->out_fence);
>> + kfree(job->aie2_job_health);
>> kfree(job);
>> }
>> @@ -176,6 +187,50 @@ aie2_sched_notify(struct amdxdna_sched_job *job)
>> aie2_job_put(job);
>> }
>> +static void aie2_set_cmd_timeout(struct amdxdna_sched_job *job)
>> +{
>> + struct aie2_ctx_health *aie2_health __free(kfree) = NULL;
>> + struct amdxdna_dev *xdna = job->hwctx->client->xdna;
>> + struct amdxdna_gem_obj *cmd_abo = job->cmd_bo;
>> + struct app_health_report *report = job->aie2_job_health;
>> + u32 fail_cmd_idx = 0;
>> +
>> + if (!report)
>> + goto set_timeout;
>> +
>> + XDNA_ERR(xdna, "Firmware timeout state capture:");
>> + XDNA_ERR(xdna, "\tVersion: %d.%d", report->major, report->minor);
>> + XDNA_ERR(xdna, "\tReport size: 0x%x", report->size);
>> + XDNA_ERR(xdna, "\tContext ID: %d", report->context_id);
>> + XDNA_ERR(xdna, "\tDPU PC: 0x%x", report->dpu_pc);
>> + XDNA_ERR(xdna, "\tTXN OP ID: 0x%x", report->txn_op_id);
>> + XDNA_ERR(xdna, "\tContext PC: 0x%x", report->ctx_pc);
>> + XDNA_ERR(xdna, "\tFatal error type: 0x%x",
>> report->fatal_info.fatal_type);
>> + XDNA_ERR(xdna, "\tFatal error exception type: 0x%x",
>> report->fatal_info.exception_type);
>> + XDNA_ERR(xdna, "\tFatal error exception PC: 0x%x",
>> report->fatal_info.exception_pc);
>> + XDNA_ERR(xdna, "\tFatal error app module: 0x%x",
>> report->fatal_info.app_module);
>> + XDNA_ERR(xdna, "\tFatal error task ID: %d",
>> report->fatal_info.task_index);
>> + XDNA_ERR(xdna, "\tTimed out sub command ID: %d",
>> report->run_list_id);
>> +
>> + fail_cmd_idx = report->run_list_id;
>> + aie2_health = kzalloc_obj(*aie2_health);
>> + if (!aie2_health)
>> + goto set_timeout;
>> +
>> + aie2_health->header.version = AMDXDNA_CMD_CTX_HEALTH_V1;
>> + aie2_health->header.npu_gen = AMDXDNA_CMD_CTX_HEALTH_AIE2;
>> + aie2_health->txn_op_idx = report->txn_op_id;
>> + aie2_health->ctx_pc = report->ctx_pc;
>> + aie2_health->fatal_error_type = report->fatal_info.fatal_type;
>> + aie2_health->fatal_error_exception_type =
>> report->fatal_info.exception_type;
>> + aie2_health->fatal_error_exception_pc =
>> report->fatal_info.exception_pc;
>> + aie2_health->fatal_error_app_module =
>> report->fatal_info.app_module;
>> +
>> +set_timeout:
>> + amdxdna_cmd_set_error(cmd_abo, job, fail_cmd_idx,
>> ERT_CMD_STATE_TIMEOUT,
>> + aie2_health, sizeof(*aie2_health));
>> +}
>> +
>> static int
>> aie2_sched_resp_handler(void *handle, void __iomem *data, size_t size)
>> {
>> @@ -187,13 +242,13 @@ aie2_sched_resp_handler(void *handle, void
>> __iomem *data, size_t size)
>> cmd_abo = job->cmd_bo;
>> if (unlikely(job->job_timeout)) {
>> - amdxdna_cmd_set_error(cmd_abo, job, 0, ERT_CMD_STATE_TIMEOUT);
>> + aie2_set_cmd_timeout(job);
>> ret = -EINVAL;
>> goto out;
>> }
>> if (unlikely(!data) || unlikely(size != sizeof(u32))) {
>> - amdxdna_cmd_set_error(cmd_abo, job, 0, ERT_CMD_STATE_ABORT);
>> + amdxdna_cmd_set_error(cmd_abo, job, 0, ERT_CMD_STATE_ABORT,
>> NULL, 0);
>> ret = -EINVAL;
>> goto out;
>> }
>> @@ -203,7 +258,7 @@ aie2_sched_resp_handler(void *handle, void
>> __iomem *data, size_t size)
>> if (status == AIE2_STATUS_SUCCESS)
>> amdxdna_cmd_set_state(cmd_abo, ERT_CMD_STATE_COMPLETED);
>> else
>> - amdxdna_cmd_set_error(cmd_abo, job, 0, ERT_CMD_STATE_ERROR);
>> + amdxdna_cmd_set_error(cmd_abo, job, 0, ERT_CMD_STATE_ERROR,
>> NULL, 0);
>> out:
>> aie2_sched_notify(job);
>> @@ -237,21 +292,21 @@ aie2_sched_cmdlist_resp_handler(void *handle,
>> void __iomem *data, size_t size)
>> struct amdxdna_sched_job *job = handle;
>> struct amdxdna_gem_obj *cmd_abo;
>> struct amdxdna_dev *xdna;
>> + u32 fail_cmd_idx = 0;
>> u32 fail_cmd_status;
>> - u32 fail_cmd_idx;
>> u32 cmd_status;
>> int ret = 0;
>> cmd_abo = job->cmd_bo;
>> if (unlikely(job->job_timeout)) {
>> - amdxdna_cmd_set_error(cmd_abo, job, 0, ERT_CMD_STATE_TIMEOUT);
>> + aie2_set_cmd_timeout(job);
>> ret = -EINVAL;
>> goto out;
>> }
>> if (unlikely(!data) || unlikely(size != sizeof(u32) * 3)) {
>> - amdxdna_cmd_set_error(cmd_abo, job, 0, ERT_CMD_STATE_ABORT);
>> + amdxdna_cmd_set_error(cmd_abo, job, 0, ERT_CMD_STATE_ABORT,
>> NULL, 0);
>> ret = -EINVAL;
>> goto out;
>> }
>> @@ -271,10 +326,10 @@ aie2_sched_cmdlist_resp_handler(void *handle,
>> void __iomem *data, size_t size)
>> fail_cmd_idx, fail_cmd_status);
>> if (fail_cmd_status == AIE2_STATUS_SUCCESS) {
>> - amdxdna_cmd_set_error(cmd_abo, job, fail_cmd_idx,
>> ERT_CMD_STATE_ABORT);
>> + amdxdna_cmd_set_error(cmd_abo, job, fail_cmd_idx,
>> ERT_CMD_STATE_ABORT, NULL, 0);
>> ret = -EINVAL;
>> } else {
>> - amdxdna_cmd_set_error(cmd_abo, job, fail_cmd_idx,
>> ERT_CMD_STATE_ERROR);
>> + amdxdna_cmd_set_error(cmd_abo, job, fail_cmd_idx,
>> ERT_CMD_STATE_ERROR, NULL, 0);
>> }
>> out:
>> @@ -363,12 +418,26 @@ aie2_sched_job_timedout(struct drm_sched_job
>> *sched_job)
>> {
>> struct amdxdna_sched_job *job = drm_job_to_xdna_job(sched_job);
>> struct amdxdna_hwctx *hwctx = job->hwctx;
>> + struct app_health_report *report;
>> struct amdxdna_dev *xdna;
>> + int ret;
>> xdna = hwctx->client->xdna;
>> trace_xdna_job(sched_job, hwctx->name, "job timedout", job->seq);
>> job->job_timeout = true;
>> +
>> mutex_lock(&xdna->dev_lock);
>> + report = kzalloc_obj(*report);
>> + if (!report)
>> + goto reset_hwctx;
>> +
>> + ret = aie2_query_app_health(xdna->dev_handle, hwctx->fw_ctx_id,
>> report);
>> + if (ret)
>> + kfree(report);
>> + else
>> + job->aie2_job_health = report;
>> +
>> +reset_hwctx:
>> aie2_hwctx_stop(xdna, hwctx, sched_job);
>> aie2_hwctx_restart(xdna, hwctx);
>> diff --git a/drivers/accel/amdxdna/aie2_message.c
>> b/drivers/accel/amdxdna/aie2_message.c
>> index 798128b6b7b7..4ec591306854 100644
>> --- a/drivers/accel/amdxdna/aie2_message.c
>> +++ b/drivers/accel/amdxdna/aie2_message.c
>> @@ -1185,3 +1185,44 @@ int aie2_config_debug_bo(struct amdxdna_hwctx
>> *hwctx, struct amdxdna_sched_job *
>> return xdna_mailbox_send_msg(chann, &msg, TX_TIMEOUT);
>> }
>> +
>> +int aie2_query_app_health(struct amdxdna_dev_hdl *ndev, u32 context_id,
>> + struct app_health_report *report)
>> +{
>> + DECLARE_AIE2_MSG(get_app_health, MSG_OP_GET_APP_HEALTH);
>> + struct amdxdna_dev *xdna = ndev->xdna;
>> + struct app_health_report *buf;
>> + dma_addr_t dma_addr;
>> + u32 buf_size;
>> + int ret;
>> +
>> + if (!AIE2_FEATURE_ON(ndev, AIE2_APP_HEALTH)) {
>> + XDNA_DBG(xdna, "App health feature not supported");
>> + return -EOPNOTSUPP;
>> + }
>> +
>> + buf_size = sizeof(*report);
>> + buf = aie2_alloc_msg_buffer(ndev, &buf_size, &dma_addr);
>> + if (IS_ERR(buf)) {
>> + XDNA_ERR(xdna, "Failed to allocate buffer for app health");
>> + return PTR_ERR(buf);
>> + }
>> +
>> + req.buf_addr = dma_addr;
>> + req.context_id = context_id;
>> + req.buf_size = buf_size;
>> +
>> + drm_clflush_virt_range(buf, sizeof(*report));
>> + ret = aie2_send_mgmt_msg_wait(ndev, &msg);
>> + if (ret) {
>> + XDNA_ERR(xdna, "Get app health failed, ret %d status 0x%x",
>> ret, resp.status);
>> + goto free_buf;
>> + }
>> +
>> + /* Copy the report to caller's buffer */
>> + memcpy(report, buf, sizeof(*report));
>> +
>> +free_buf:
>> + aie2_free_msg_buffer(ndev, buf_size, buf, dma_addr);
>> + return ret;
>> +}
>> diff --git a/drivers/accel/amdxdna/aie2_msg_priv.h
>> b/drivers/accel/amdxdna/aie2_msg_priv.h
>> index 728ef56f7f0a..f18e89a39e35 100644
>> --- a/drivers/accel/amdxdna/aie2_msg_priv.h
>> +++ b/drivers/accel/amdxdna/aie2_msg_priv.h
>> @@ -31,6 +31,7 @@ enum aie2_msg_opcode {
>> MSG_OP_SET_RUNTIME_CONFIG = 0x10A,
>> MSG_OP_GET_RUNTIME_CONFIG = 0x10B,
>> MSG_OP_REGISTER_ASYNC_EVENT_MSG = 0x10C,
>> + MSG_OP_GET_APP_HEALTH = 0x114,
>> MSG_OP_MAX_DRV_OPCODE,
>> MSG_OP_GET_PROTOCOL_VERSION = 0x301,
>> MSG_OP_MAX_OPCODE
>> @@ -451,4 +452,55 @@ struct config_debug_bo_req {
>> struct config_debug_bo_resp {
>> enum aie2_msg_status status;
>> } __packed;
>> +
>> +struct fatal_error_info {
>> + __u32 fatal_type; /* Fatal error type */
>> + __u32 exception_type; /* Only valid if fatal_type is a
>> specific value */
>> + __u32 exception_argument; /* Argument based on exception type */
>> + __u32 exception_pc; /* Program Counter at the time of the
>> exception */
>> + __u32 app_module; /* Error module name */
>> + __u32 task_index; /* Index of the task in which the
>> error occurred */
>> + __u32 reserved[128];
>> +};
>> +
>> +struct app_health_report {
>> + __u16 major;
>> + __u16 minor;
>> + __u32 size;
>> + __u32 context_id;
>> + /*
>> + * Program Counter (PC) of the last initiated DPU opcode, as
>> reported by the ERT
>> + * application. Before execution begins or after successful
>> completion, the value is set
>> + * to UINT_MAX. If execution halts prematurely due to an error,
>> this field retains the
>> + * opcode's PC value.
>> + * Note: To optimize performance, the ERT may simplify certain
>> aspects of reporting.
>> + * Proper interpretation requires familiarity with the
>> implementation details.
>> + */
>> + __u32 dpu_pc;
>> + /*
>> + * Index of the last initiated TXN opcode.
>> + * Before execution starts or after successful completion, the
>> value is set to UINT_MAX.
>> + * If execution halts prematurely due to an error, this field
>> retains the opcode's ID.
>> + * Note: To optimize performance, the ERT may simplify certain
>> aspects of reporting.
>> + * Proper interpretation requires familiarity with the
>> implementation details.
>> + */
>> + __u32 txn_op_id;
>> + /* The PC of the context at the time of the report */
>> + __u32 ctx_pc;
>> + struct fatal_error_info fatal_info;
>> + /* Index of the most recently executed run list entry. */
>> + __u32 run_list_id;
>> +};
>> +
>> +struct get_app_health_req {
>> + __u32 context_id;
>> + __u32 buf_size;
>> + __u64 buf_addr;
>> +} __packed;
>> +
>> +struct get_app_health_resp {
>> + enum aie2_msg_status status;
>> + __u32 required_buffer_size;
>> + __u32 reserved[7];
>> +} __packed;
>> #endif /* _AIE2_MSG_PRIV_H_ */
>> diff --git a/drivers/accel/amdxdna/aie2_pci.c
>> b/drivers/accel/amdxdna/aie2_pci.c
>> index ddd3d82f3426..9e39bfe75971 100644
>> --- a/drivers/accel/amdxdna/aie2_pci.c
>> +++ b/drivers/accel/amdxdna/aie2_pci.c
>> @@ -846,7 +846,10 @@ static int aie2_hwctx_status_cb(struct
>> amdxdna_hwctx *hwctx, void *arg)
>> struct amdxdna_drm_hwctx_entry *tmp __free(kfree) = NULL;
>> struct amdxdna_drm_get_array *array_args = arg;
>> struct amdxdna_drm_hwctx_entry __user *buf;
>> + struct app_health_report report;
>> + struct amdxdna_dev_hdl *ndev;
>> u32 size;
>> + int ret;
>> if (!array_args->num_element)
>> return -EINVAL;
>> @@ -869,6 +872,17 @@ static int aie2_hwctx_status_cb(struct
>> amdxdna_hwctx *hwctx, void *arg)
>> tmp->latency = hwctx->qos.latency;
>> tmp->frame_exec_time = hwctx->qos.frame_exec_time;
>> tmp->state = AMDXDNA_HWCTX_STATE_ACTIVE;
>> + ndev = hwctx->client->xdna->dev_handle;
>> + ret = aie2_query_app_health(ndev, hwctx->fw_ctx_id, &report);
>> + if (!ret) {
>> + /* Fill in app health report fields */
>> + tmp->txn_op_idx = report.txn_op_id;
>> + tmp->ctx_pc = report.ctx_pc;
>> + tmp->fatal_error_type = report.fatal_info.fatal_type;
>> + tmp->fatal_error_exception_type =
>> report.fatal_info.exception_type;
>> + tmp->fatal_error_exception_pc = report.fatal_info.exception_pc;
>> + tmp->fatal_error_app_module = report.fatal_info.app_module;
>> + }
>> buf = u64_to_user_ptr(array_args->buffer);
>> size = min(sizeof(*tmp), array_args->element_size);
>> diff --git a/drivers/accel/amdxdna/aie2_pci.h
>> b/drivers/accel/amdxdna/aie2_pci.h
>> index 885ae7e6bfc7..efcf4be035f0 100644
>> --- a/drivers/accel/amdxdna/aie2_pci.h
>> +++ b/drivers/accel/amdxdna/aie2_pci.h
>> @@ -10,6 +10,7 @@
>> #include <linux/limits.h>
>> #include <linux/semaphore.h>
>> +#include "aie2_msg_priv.h"
>> #include "amdxdna_mailbox.h"
>> #define AIE2_INTERVAL 20000 /* us */
>> @@ -261,6 +262,7 @@ enum aie2_fw_feature {
>> AIE2_NPU_COMMAND,
>> AIE2_PREEMPT,
>> AIE2_TEMPORAL_ONLY,
>> + AIE2_APP_HEALTH,
>> AIE2_FEATURE_MAX
>> };
>> @@ -271,6 +273,7 @@ struct aie2_fw_feature_tbl {
>> u32 min_minor;
>> };
>> +#define AIE2_ALL_FEATURES GENMASK_ULL(AIE2_FEATURE_MAX - 1,
>> AIE2_NPU_COMMAND)
>> #define AIE2_FEATURE_ON(ndev, feature) test_bit(feature,
>> &(ndev)->feature_mask)
>> struct amdxdna_dev_priv {
>> @@ -341,6 +344,8 @@ int aie2_query_aie_version(struct amdxdna_dev_hdl
>> *ndev, struct aie_version *ver
>> int aie2_query_aie_metadata(struct amdxdna_dev_hdl *ndev, struct
>> aie_metadata *metadata);
>> int aie2_query_firmware_version(struct amdxdna_dev_hdl *ndev,
>> struct amdxdna_fw_ver *fw_ver);
>> +int aie2_query_app_health(struct amdxdna_dev_hdl *ndev, u32 context_id,
>> + struct app_health_report *report);
>> int aie2_create_context(struct amdxdna_dev_hdl *ndev, struct
>> amdxdna_hwctx *hwctx);
>> int aie2_destroy_context(struct amdxdna_dev_hdl *ndev, struct
>> amdxdna_hwctx *hwctx);
>> int aie2_map_host_buf(struct amdxdna_dev_hdl *ndev, u32 context_id,
>> u64 addr, u64 size);
>> diff --git a/drivers/accel/amdxdna/amdxdna_ctx.c
>> b/drivers/accel/amdxdna/amdxdna_ctx.c
>> index 666dfd7b2a80..4b921715176d 100644
>> --- a/drivers/accel/amdxdna/amdxdna_ctx.c
>> +++ b/drivers/accel/amdxdna/amdxdna_ctx.c
>> @@ -137,7 +137,8 @@ u32 amdxdna_cmd_get_cu_idx(struct amdxdna_gem_obj
>> *abo)
>> int amdxdna_cmd_set_error(struct amdxdna_gem_obj *abo,
>> struct amdxdna_sched_job *job, u32 cmd_idx,
>> - enum ert_cmd_state error_state)
>> + enum ert_cmd_state error_state,
>> + void *err_data, size_t size)
>> {
>> struct amdxdna_client *client = job->hwctx->client;
>> struct amdxdna_cmd *cmd = abo->mem.kva;
>> @@ -156,6 +157,9 @@ int amdxdna_cmd_set_error(struct amdxdna_gem_obj
>> *abo,
>> }
>> memset(cmd->data, 0xff, abo->mem.size - sizeof(*cmd));
>> + if (err_data)
>> + memcpy(cmd->data, err_data, min(size, abo->mem.size -
>> sizeof(*cmd)));
>> +
>> if (cc)
>> amdxdna_gem_put_obj(abo);
>> diff --git a/drivers/accel/amdxdna/amdxdna_ctx.h
>> b/drivers/accel/amdxdna/amdxdna_ctx.h
>> index fbdf9d000871..57db1527a93b 100644
>> --- a/drivers/accel/amdxdna/amdxdna_ctx.h
>> +++ b/drivers/accel/amdxdna/amdxdna_ctx.h
>> @@ -72,6 +72,13 @@ struct amdxdna_cmd_preempt_data {
>> u32 prop_args[]; /* properties and regular kernel arguments */
>> };
>> +#define AMDXDNA_CMD_CTX_HEALTH_V1 1
>> +#define AMDXDNA_CMD_CTX_HEALTH_AIE2 0
>> +struct amdxdna_ctx_health {
>> + u32 version;
>> + u32 npu_gen;
>> +};
>> +
>> /* Exec buffer command header format */
>> #define AMDXDNA_CMD_STATE GENMASK(3, 0)
>> #define AMDXDNA_CMD_EXTRA_CU_MASK GENMASK(11, 10)
>> @@ -122,6 +129,11 @@ struct amdxdna_drv_cmd {
>> u32 result;
>> };
>> +struct app_health_report;
>> +union amdxdna_job_priv {
>> + struct app_health_report *aie2_health;
>> +};
>> +
>> struct amdxdna_sched_job {
>> struct drm_sched_job base;
>> struct kref refcnt;
>> @@ -136,10 +148,13 @@ struct amdxdna_sched_job {
>> u64 seq;
>> struct amdxdna_drv_cmd *drv_cmd;
>> struct amdxdna_gem_obj *cmd_bo;
>> + union amdxdna_job_priv priv;
>> size_t bo_cnt;
>> struct drm_gem_object *bos[] __counted_by(bo_cnt);
>> };
>> +#define aie2_job_health priv.aie2_health
>> +
>> static inline u32
>> amdxdna_cmd_get_op(struct amdxdna_gem_obj *abo)
>> {
>> @@ -169,7 +184,8 @@ void *amdxdna_cmd_get_payload(struct
>> amdxdna_gem_obj *abo, u32 *size);
>> u32 amdxdna_cmd_get_cu_idx(struct amdxdna_gem_obj *abo);
>> int amdxdna_cmd_set_error(struct amdxdna_gem_obj *abo,
>> struct amdxdna_sched_job *job, u32 cmd_idx,
>> - enum ert_cmd_state error_state);
>> + enum ert_cmd_state error_state,
>> + void *err_data, size_t size);
>> void amdxdna_sched_job_cleanup(struct amdxdna_sched_job *job);
>> void amdxdna_hwctx_remove_all(struct amdxdna_client *client);
>> diff --git a/drivers/accel/amdxdna/npu4_regs.c
>> b/drivers/accel/amdxdna/npu4_regs.c
>> index ce25eef5fc34..619bff042e52 100644
>> --- a/drivers/accel/amdxdna/npu4_regs.c
>> +++ b/drivers/accel/amdxdna/npu4_regs.c
>> @@ -93,7 +93,8 @@ const struct aie2_fw_feature_tbl
>> npu4_fw_feature_table[] = {
>> { .features = BIT_U64(AIE2_NPU_COMMAND), .major = 6, .min_minor
>> = 15 },
>> { .features = BIT_U64(AIE2_PREEMPT), .major = 6, .min_minor =
>> 12 },
>> { .features = BIT_U64(AIE2_TEMPORAL_ONLY), .major = 6,
>> .min_minor = 12 },
>> - { .features = GENMASK_ULL(AIE2_TEMPORAL_ONLY, AIE2_NPU_COMMAND),
>> .major = 7 },
>> + { .features = BIT_U64(AIE2_APP_HEALTH), .major = 6, .min_minor =
>> 18 },
>> + { .features = AIE2_ALL_FEATURES, .major = 7 },
>> { 0 }
>> };
>
prev parent reply other threads:[~2026-03-17 21:13 UTC|newest]
Thread overview: 3+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-03-17 4:49 Lizhi Hou
2026-03-17 19:25 ` Mario Limonciello
2026-03-17 21:11 ` Lizhi Hou [this message]
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=7ba9b420-1542-32ef-1616-4fe5b97141b9@amd.com \
--to=lizhi.hou@amd.com \
--cc=dri-devel@lists.freedesktop.org \
--cc=linux-kernel@vger.kernel.org \
--cc=maciej.falkowski@linux.intel.com \
--cc=mario.limonciello@amd.com \
--cc=max.zhen@amd.com \
--cc=ogabbay@kernel.org \
--cc=quic_jhugo@quicinc.com \
--cc=sonal.santan@amd.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
all inboxes | Powered by JetHome®