[PATCH V0 03/21] accel/amdxdna: Add CERT firmware version support
From: David Zhang
Date: Fri Sep 25 2026 - 21:36:24 EST
AIE4 platforms run two separate firmware binaries: NPU firmware for
management and CERT (Column Enternal Run Time) firmware for
handling execution contexts and queues.
Add support to query and validate CERT firmware version:
- Add mailbox opcodes and structs to query NPU firmware version (identify)
and CERT firmware version.
- Unify firmware version storage by using struct
amdxdna_drm_query_firmware_version across the driver.
- Introduce aie_check_cert_protocol() and cert_feature_tbl to validate
CERT firmware host queue protocol compatibility against driver
capabilities.
- Add helper functions amdxdna_get_firmware_version() and
amdxdna_get_aie_version() to share version query handling across
generations.
Note on patch ordering:
Introducing CERT firmware protocol validation prior to the firmware 6.0
upgrade ensures host queue protocol compatibility (host_queue_major/minor)
is validated before the host queue layout restructure, preserving
bisectability.
Signed-off-by: David Zhang <yidong.zhang@xxxxxxx>
---
drivers/accel/amdxdna/aie.c | 45 ++++++++++++++++++++---
drivers/accel/amdxdna/aie.h | 9 ++++-
drivers/accel/amdxdna/aie2_message.c | 4 +--
drivers/accel/amdxdna/aie2_pci.c | 47 +++----------------------
drivers/accel/amdxdna/aie2_pci.h | 4 +--
drivers/accel/amdxdna/aie4_message.c | 45 +++++++++++++++++++++++
drivers/accel/amdxdna/aie4_msg_priv.h | 30 ++++++++++++++++
drivers/accel/amdxdna/aie4_pci.c | 17 ++++++++-
drivers/accel/amdxdna/aie4_pci.h | 11 ++++++
drivers/accel/amdxdna/amdxdna_pci_drv.h | 10 ++----
drivers/accel/amdxdna/amdxdna_sysfs.c | 2 +-
drivers/accel/amdxdna/npu3_regs.c | 8 +++++
12 files changed, 170 insertions(+), 62 deletions(-)
diff --git a/drivers/accel/amdxdna/aie.c b/drivers/accel/amdxdna/aie.c
index dd6f36f222c7..01a439c0ccf4 100644
--- a/drivers/accel/amdxdna/aie.c
+++ b/drivers/accel/amdxdna/aie.c
@@ -65,13 +65,12 @@ int aie_send_mgmt_msg_wait(struct aie_device *aie, struct xdna_mailbox_msg *msg)
return ret;
}
-int aie_check_protocol(struct aie_device *aie, u32 fw_major, u32 fw_minor)
+static int aie_check_protocol_impl(struct aie_device *aie, u32 fw_major, u32 fw_minor,
+ const struct amdxdna_fw_feature_tbl *feature)
{
- const struct amdxdna_fw_feature_tbl *feature;
bool found = false;
- for (feature = aie->xdna->dev_info->fw_feature_tbl;
- feature->major; feature++) {
+ for (; feature && feature->major; feature++) {
if (feature->major != fw_major)
continue;
if (fw_minor < feature->min_minor)
@@ -88,6 +87,44 @@ int aie_check_protocol(struct aie_device *aie, u32 fw_major, u32 fw_minor)
return found ? 0 : -EOPNOTSUPP;
}
+int aie_check_protocol(struct aie_device *aie, u32 fw_major, u32 fw_minor)
+{
+ return aie_check_protocol_impl(aie, fw_major, fw_minor,
+ aie->xdna->dev_info->fw_feature_tbl);
+}
+
+int aie_check_cert_protocol(struct aie_device *aie, u32 cert_major, u32 cert_minor)
+{
+ return aie_check_protocol_impl(aie, cert_major, cert_minor,
+ aie->xdna->dev_info->cert_feature_tbl);
+}
+
+int amdxdna_get_aie_version(struct amdxdna_client *client,
+ struct amdxdna_drm_get_info *args,
+ struct amdxdna_drm_query_aie_version *version)
+{
+ u32 buf_sz;
+
+ buf_sz = min_t(u32, args->buffer_size, sizeof(*version));
+ if (copy_to_user(u64_to_user_ptr(args->buffer), version, buf_sz))
+ return -EFAULT;
+
+ return 0;
+}
+
+int amdxdna_get_firmware_version(struct amdxdna_client *client,
+ struct amdxdna_drm_get_info *args,
+ struct amdxdna_drm_query_firmware_version *version)
+{
+ u32 buf_sz;
+
+ buf_sz = min_t(u32, args->buffer_size, sizeof(*version));
+ if (copy_to_user(u64_to_user_ptr(args->buffer), version, buf_sz))
+ return -EFAULT;
+
+ return 0;
+}
+
static void amdxdna_update_vbnv(struct amdxdna_dev *xdna,
const struct amdxdna_rev_vbnv *tbl,
u32 rev)
diff --git a/drivers/accel/amdxdna/aie.h b/drivers/accel/amdxdna/aie.h
index 0483d582b7f8..899399756661 100644
--- a/drivers/accel/amdxdna/aie.h
+++ b/drivers/accel/amdxdna/aie.h
@@ -28,6 +28,7 @@ struct aie_device {
struct psp_device *psp_hdl;
struct smu_device *smu_hdl;
+ struct amdxdna_drm_query_aie_version version;
struct amdxdna_drm_query_aie_metadata metadata;
};
@@ -96,6 +97,7 @@ void aie_dump_mgmt_chann_debug(struct aie_device *aie);
void aie_destroy_chann(struct aie_device *aie, struct mailbox_channel **chann);
int aie_send_mgmt_msg_wait(struct aie_device *aie, struct xdna_mailbox_msg *msg);
int aie_check_protocol(struct aie_device *aie, u32 fw_major, u32 fw_minor);
+int aie_check_cert_protocol(struct aie_device *aie, u32 fw_major, u32 fw_minor);
void amdxdna_vbnv_init(struct amdxdna_dev *xdna);
int amdxdna_get_metadata(struct aie_device *aie, struct amdxdna_client *client,
struct amdxdna_drm_get_info *args);
@@ -103,7 +105,12 @@ void *amdxdna_alloc_msg_buffer(struct amdxdna_dev *xdna, u32 *size,
dma_addr_t *dma_addr);
void amdxdna_free_msg_buffer(struct amdxdna_dev *xdna, size_t size,
void *cpu_addr, dma_addr_t dma_addr);
-
+int amdxdna_get_aie_version(struct amdxdna_client *client,
+ struct amdxdna_drm_get_info *args,
+ struct amdxdna_drm_query_aie_version *version);
+int amdxdna_get_firmware_version(struct amdxdna_client *client,
+ struct amdxdna_drm_get_info *args,
+ struct amdxdna_drm_query_firmware_version *version);
/* aie_psp.c */
struct psp_device *aiem_psp_create(struct drm_device *ddev, struct psp_config *conf);
int aie_psp_start(struct psp_device *psp);
diff --git a/drivers/accel/amdxdna/aie2_message.c b/drivers/accel/amdxdna/aie2_message.c
index f658760c3d48..bae0cc4c3580 100644
--- a/drivers/accel/amdxdna/aie2_message.c
+++ b/drivers/accel/amdxdna/aie2_message.c
@@ -149,7 +149,7 @@ int aie2_query_aie_metadata(struct amdxdna_dev_hdl *ndev,
}
int aie2_query_firmware_version(struct amdxdna_dev_hdl *ndev,
- struct amdxdna_fw_ver *fw_ver)
+ struct amdxdna_drm_query_firmware_version *fw_ver)
{
DECLARE_AIE_MSG(firmware_version, MSG_OP_GET_FIRMWARE_VERSION);
int ret;
@@ -160,7 +160,7 @@ int aie2_query_firmware_version(struct amdxdna_dev_hdl *ndev,
fw_ver->major = resp.major;
fw_ver->minor = resp.minor;
- fw_ver->sub = resp.sub;
+ fw_ver->patch = resp.sub;
fw_ver->build = resp.build;
return 0;
diff --git a/drivers/accel/amdxdna/aie2_pci.c b/drivers/accel/amdxdna/aie2_pci.c
index 7a4314ca843b..5dc6e5b97afc 100644
--- a/drivers/accel/amdxdna/aie2_pci.c
+++ b/drivers/accel/amdxdna/aie2_pci.c
@@ -205,15 +205,16 @@ static int aie2_mgmt_fw_init(struct amdxdna_dev_hdl *ndev)
static int aie2_mgmt_fw_query(struct amdxdna_dev_hdl *ndev)
{
+ struct amdxdna_dev *xdna = ndev->aie.xdna;
int ret;
- ret = aie2_query_firmware_version(ndev, &ndev->aie.xdna->fw_ver);
+ ret = aie2_query_firmware_version(ndev, &xdna->fw_ver);
if (ret) {
XDNA_ERR(ndev->aie.xdna, "query firmware version failed");
return ret;
}
- ret = aie2_query_aie_version(ndev, &ndev->version);
+ ret = aie2_query_aie_version(ndev, &ndev->aie.version);
if (ret) {
XDNA_ERR(ndev->aie.xdna, "Query AIE version failed");
return ret;
@@ -673,44 +674,6 @@ static int aie2_get_aie_status(struct amdxdna_client *client,
return 0;
}
-static int aie2_get_aie_version(struct amdxdna_client *client,
- struct amdxdna_drm_get_info *args)
-{
- struct amdxdna_drm_query_aie_version version;
- struct amdxdna_dev *xdna = client->xdna;
- struct amdxdna_dev_hdl *ndev;
- u32 buf_sz;
-
- ndev = xdna->dev_handle;
- version.major = ndev->version.major;
- version.minor = ndev->version.minor;
-
- buf_sz = min(args->buffer_size, sizeof(version));
- if (copy_to_user(u64_to_user_ptr(args->buffer), &version, buf_sz))
- return -EFAULT;
-
- return 0;
-}
-
-static int aie2_get_firmware_version(struct amdxdna_client *client,
- struct amdxdna_drm_get_info *args)
-{
- struct amdxdna_drm_query_firmware_version version;
- struct amdxdna_dev *xdna = client->xdna;
- u32 buf_sz;
-
- version.major = xdna->fw_ver.major;
- version.minor = xdna->fw_ver.minor;
- version.patch = xdna->fw_ver.sub;
- version.build = xdna->fw_ver.build;
-
- buf_sz = min(args->buffer_size, sizeof(version));
- if (copy_to_user(u64_to_user_ptr(args->buffer), &version, buf_sz))
- return -EFAULT;
-
- return 0;
-}
-
static int aie2_get_power_mode(struct amdxdna_client *client,
struct amdxdna_drm_get_info *args)
{
@@ -1025,7 +988,7 @@ static int aie2_get_info(struct amdxdna_client *client, struct amdxdna_drm_get_i
ret = amdxdna_get_metadata(&ndev->aie, client, args);
break;
case DRM_AMDXDNA_QUERY_AIE_VERSION:
- ret = aie2_get_aie_version(client, args);
+ ret = amdxdna_get_aie_version(client, args, &ndev->aie.version);
break;
case DRM_AMDXDNA_QUERY_CLOCK_METADATA:
ret = aie2_get_clock_metadata(client, args);
@@ -1037,7 +1000,7 @@ static int aie2_get_info(struct amdxdna_client *client, struct amdxdna_drm_get_i
ret = aie2_get_hwctx_status(client, args);
break;
case DRM_AMDXDNA_QUERY_FIRMWARE_VERSION:
- ret = aie2_get_firmware_version(client, args);
+ ret = amdxdna_get_firmware_version(client, args, &xdna->fw_ver);
break;
case DRM_AMDXDNA_GET_POWER_MODE:
ret = aie2_get_power_mode(client, args);
diff --git a/drivers/accel/amdxdna/aie2_pci.h b/drivers/accel/amdxdna/aie2_pci.h
index 2c7019bd26b5..67971f0c4acf 100644
--- a/drivers/accel/amdxdna/aie2_pci.h
+++ b/drivers/accel/amdxdna/aie2_pci.h
@@ -74,7 +74,6 @@ enum aie2_sram_reg_idx {
};
struct amdxdna_client;
-struct amdxdna_fw_ver;
struct amdxdna_hwctx;
struct amdxdna_sched_job;
@@ -150,7 +149,6 @@ struct amdxdna_dev_hdl {
void __iomem *mbox_base;
u32 total_col;
- struct amdxdna_drm_query_aie_version version;
struct aie2_exec_msg_ops *exec_msg_ops;
struct drm_gpu_scheduler *hwctx_sched;
struct ida hwctx_sched_ida;
@@ -263,7 +261,7 @@ int aie2_query_aie_version(struct amdxdna_dev_hdl *ndev,
int aie2_query_aie_metadata(struct amdxdna_dev_hdl *ndev,
struct amdxdna_drm_query_aie_metadata *metadata);
int aie2_query_firmware_version(struct amdxdna_dev_hdl *ndev,
- struct amdxdna_fw_ver *fw_ver);
+ struct amdxdna_drm_query_firmware_version *fw_ver);
int aie2_query_app_health(struct amdxdna_dev_hdl *ndev, u32 context_id,
struct app_health_report *report);
int aie2_get_dev_revision(struct amdxdna_dev_hdl *ndev, enum aie2_dev_revision *rev);
diff --git a/drivers/accel/amdxdna/aie4_message.c b/drivers/accel/amdxdna/aie4_message.c
index 88037edbb02a..b137a2a40b34 100644
--- a/drivers/accel/amdxdna/aie4_message.c
+++ b/drivers/accel/amdxdna/aie4_message.c
@@ -64,6 +64,51 @@ int aie4_query_aie_metadata(struct amdxdna_dev_hdl *ndev,
return 0;
}
+int aie4_query_npu_firmware_version(struct amdxdna_dev_hdl *ndev,
+ struct amdxdna_drm_query_firmware_version *fw_version)
+{
+ DECLARE_AIE_MSG(aie4_msg_identify, AIE4_MSG_OP_IDENTIFY);
+ int ret;
+
+ ret = aie_send_mgmt_msg_wait(&ndev->aie, &msg);
+ if (ret)
+ return ret;
+
+ fw_version->major = resp.fw_major;
+ fw_version->minor = resp.fw_minor;
+ fw_version->patch = resp.fw_patch;
+ fw_version->build = resp.fw_build;
+
+ return 0;
+}
+
+int aie4_query_cert_firmware_version(struct amdxdna_dev_hdl *ndev,
+ struct amdxdna_drm_query_firmware_version *cert_version)
+{
+ DECLARE_AIE_MSG(aie4_msg_query_cert_firmware_version,
+ AIE4_MSG_OP_QUERY_CERT_FIRMWARE_VERSION);
+ int ret;
+
+ ret = aie_send_mgmt_msg_wait(&ndev->aie, &msg);
+ if (ret)
+ return ret;
+
+ ret = aie_check_cert_protocol(&ndev->aie,
+ resp.host_queue_major, resp.host_queue_minor);
+ if (ret) {
+ XDNA_ERR(ndev->aie.xdna, "host queue %d.%d is not supported",
+ resp.host_queue_major, resp.host_queue_minor);
+ return ret;
+ }
+
+ cert_version->major = resp.major_version;
+ cert_version->minor = resp.minor_version;
+ cert_version->patch = resp.hotfix;
+ cert_version->build = resp.build;
+
+ return 0;
+}
+
int aie4_attach_work_buffer(struct amdxdna_dev_hdl *ndev)
{
DECLARE_AIE_MSG(aie4_msg_attach_work_buffer, AIE4_MSG_OP_ATTACH_WORK_BUFFER);
diff --git a/drivers/accel/amdxdna/aie4_msg_priv.h b/drivers/accel/amdxdna/aie4_msg_priv.h
index af0866045b91..5b97c8057de0 100644
--- a/drivers/accel/amdxdna/aie4_msg_priv.h
+++ b/drivers/accel/amdxdna/aie4_msg_priv.h
@@ -10,8 +10,10 @@
#include <linux/types.h>
enum aie4_msg_opcode {
+ AIE4_MSG_OP_IDENTIFY = 0x10002,
AIE4_MSG_OP_SUSPEND = 0x10003,
AIE4_MSG_OP_ATTACH_WORK_BUFFER = 0x1000D,
+ AIE4_MSG_OP_QUERY_CERT_FIRMWARE_VERSION = 0x1000F,
AIE4_MSG_OP_CREATE_VFS = 0x20001,
AIE4_MSG_OP_DESTROY_VFS = 0x20002,
@@ -30,6 +32,18 @@ enum aie4_msg_status {
MAX_AIE4_MSG_STATUS_CODE = 0x4,
};
+struct aie4_msg_identify_req {
+ __u32 rsvd;
+} __packed;
+
+struct aie4_msg_identify_resp {
+ enum aie4_msg_status status;
+ __u32 fw_major;
+ __u32 fw_minor;
+ __u32 fw_patch;
+ __u32 fw_build;
+} __packed;
+
struct aie4_msg_suspend_req {
__u32 rsvd;
} __packed;
@@ -132,6 +146,22 @@ struct aie4_msg_aie4_tile_info_resp {
struct aie4_tile_info info;
} __packed;
+struct aie4_msg_query_cert_firmware_version_req {
+ __u32 resvd;
+} __packed;
+
+struct aie4_msg_query_cert_firmware_version_resp {
+ enum aie4_msg_status status;
+ __u8 major_version;
+ __u8 minor_version;
+ __u8 git_hash[41];
+ __u8 date[11];
+ __u8 hotfix;
+ __u8 build;
+ __u16 host_queue_major;
+ __u16 host_queue_minor;
+} __packed;
+
#define AIE4_WORK_BUFFER_MIN_SIZE SZ_4M
struct aie4_msg_attach_work_buffer_req {
diff --git a/drivers/accel/amdxdna/aie4_pci.c b/drivers/accel/amdxdna/aie4_pci.c
index db02d25e3f4a..3cb81bc1b627 100644
--- a/drivers/accel/amdxdna/aie4_pci.c
+++ b/drivers/accel/amdxdna/aie4_pci.c
@@ -271,7 +271,22 @@ static void aie4_partition_fini(struct amdxdna_dev_hdl *ndev)
static int aie4_query(struct amdxdna_dev_hdl *ndev)
{
- return aie4_query_aie_metadata(ndev, &ndev->aie.metadata);
+ struct amdxdna_dev *xdna = ndev->aie.xdna;
+ int ret;
+
+ ret = aie4_query_npu_firmware_version(ndev, &xdna->fw_ver);
+ if (ret)
+ return ret;
+
+ ret = aie4_query_cert_firmware_version(ndev, &ndev->cert_version);
+ if (ret)
+ return ret;
+
+ ret = aie4_query_aie_metadata(ndev, &ndev->aie.metadata);
+ if (ret)
+ return ret;
+
+ return 0;
}
static int aie4_pf_hw_start(struct amdxdna_dev_hdl *ndev)
diff --git a/drivers/accel/amdxdna/aie4_pci.h b/drivers/accel/amdxdna/aie4_pci.h
index c6219544dc0f..8c62ee6a9b23 100644
--- a/drivers/accel/amdxdna/aie4_pci.h
+++ b/drivers/accel/amdxdna/aie4_pci.h
@@ -57,6 +57,13 @@ struct amdxdna_dev_hdl {
void *work_buf;
dma_addr_t work_buf_addr;
u32 work_buf_size;
+
+ struct amdxdna_drm_query_firmware_version cert_version;
+};
+
+enum aie4_fw_feature {
+ AIE4_HSA_COMMAND = 5,
+ AIE4_FEATURE_MAX
};
/* aie4_message.c */
@@ -64,6 +71,10 @@ int aie4_query_aie_metadata(struct amdxdna_dev_hdl *ndev,
struct amdxdna_drm_query_aie_metadata *metadata);
int aie4_suspend_fw(struct amdxdna_dev_hdl *ndev);
int aie4_attach_work_buffer(struct amdxdna_dev_hdl *ndev);
+int aie4_query_npu_firmware_version(struct amdxdna_dev_hdl *ndev,
+ struct amdxdna_drm_query_firmware_version *fw_version);
+int aie4_query_cert_firmware_version(struct amdxdna_dev_hdl *ndev,
+ struct amdxdna_drm_query_firmware_version *cert_version);
/* aie4_ctx.c */
int aie4_hwctx_init(struct amdxdna_hwctx *hwctx);
diff --git a/drivers/accel/amdxdna/amdxdna_pci_drv.h b/drivers/accel/amdxdna/amdxdna_pci_drv.h
index 84c8973e9197..0002e6ef32ba 100644
--- a/drivers/accel/amdxdna/amdxdna_pci_drv.h
+++ b/drivers/accel/amdxdna/amdxdna_pci_drv.h
@@ -99,16 +99,10 @@ struct amdxdna_dev_info {
size_t dev_heap_max_size;
const struct amdxdna_dev_priv *dev_priv;
const struct amdxdna_fw_feature_tbl *fw_feature_tbl;
+ const struct amdxdna_fw_feature_tbl *cert_feature_tbl;
const struct amdxdna_dev_ops *ops;
};
-struct amdxdna_fw_ver {
- u32 major;
- u32 minor;
- u32 sub;
- u32 build;
-};
-
struct amdxdna_carveout;
struct amdxdna_dev {
@@ -120,7 +114,7 @@ struct amdxdna_dev {
struct mutex dev_lock; /* per device lock */
struct list_head client_list;
struct mutex client_lock; /* client_list */
- struct amdxdna_fw_ver fw_ver;
+ struct amdxdna_drm_query_firmware_version fw_ver;
struct rw_semaphore notifier_lock; /* for mmu notifier*/
struct workqueue_struct *notifier_wq;
diff --git a/drivers/accel/amdxdna/amdxdna_sysfs.c b/drivers/accel/amdxdna/amdxdna_sysfs.c
index d9e359ee8182..e20b7fb1e5d1 100644
--- a/drivers/accel/amdxdna/amdxdna_sysfs.c
+++ b/drivers/accel/amdxdna/amdxdna_sysfs.c
@@ -37,7 +37,7 @@ static ssize_t fw_version_show(struct device *dev, struct device_attribute *attr
struct amdxdna_dev *xdna = dev_get_drvdata(dev);
return sprintf(buf, "%d.%d.%d.%d\n", xdna->fw_ver.major,
- xdna->fw_ver.minor, xdna->fw_ver.sub,
+ xdna->fw_ver.minor, xdna->fw_ver.patch,
xdna->fw_ver.build);
}
static DEVICE_ATTR_RO(fw_version);
diff --git a/drivers/accel/amdxdna/npu3_regs.c b/drivers/accel/amdxdna/npu3_regs.c
index 8d287ef32fff..31208c42ad5f 100644
--- a/drivers/accel/amdxdna/npu3_regs.c
+++ b/drivers/accel/amdxdna/npu3_regs.c
@@ -42,6 +42,12 @@ static const struct amdxdna_fw_feature_tbl npu3_fw_feature_table[] = {
{ 0 }
};
+static const struct amdxdna_fw_feature_tbl npu3_cert_feature_table[] = {
+ { .major = 1, .min_minor = 0 },
+ { .features = BIT_U64(AIE4_HSA_COMMAND), .major = 1, .min_minor = 0 },
+ { 0 }
+};
+
static const struct amdxdna_dev_priv npu3_dev_priv = {
.npufw_path = "npu.sbin",
.certfw_path = "cert.sbin",
@@ -85,6 +91,7 @@ const struct amdxdna_dev_info dev_npu3_pf_info = {
.device_type = AMDXDNA_DEV_TYPE_PF,
.dev_priv = &npu3_dev_priv,
.fw_feature_tbl = npu3_fw_feature_table,
+ .cert_feature_tbl = npu3_cert_feature_table,
.ops = &aie4_pf_ops,
};
@@ -96,5 +103,6 @@ const struct amdxdna_dev_info dev_npu3_vf_info = {
.device_type = AMDXDNA_DEV_TYPE_UMQ,
.dev_priv = &npu3_dev_vf_priv,
.fw_feature_tbl = npu3_fw_feature_table,
+ .cert_feature_tbl = npu3_cert_feature_table,
.ops = &aie4_vf_ops,
};
--
2.34.1