@@ -1756,17 +1756,15 @@ static void add_files_to_device(struct hl_device *hdev, struct hl_dbg_device_ent
}
}
-void hl_debugfs_add_device(struct hl_device *hdev)
+int hl_debugfs_device_init(struct hl_device *hdev)
{
struct hl_dbg_device_entry *dev_entry = &hdev->hl_debugfs;
int count = ARRAY_SIZE(hl_debugfs_list);
dev_entry->hdev = hdev;
- dev_entry->entry_arr = kmalloc_array(count,
- sizeof(struct hl_debugfs_entry),
- GFP_KERNEL);
+ dev_entry->entry_arr = kmalloc_array(count, sizeof(struct hl_debugfs_entry), GFP_KERNEL);
if (!dev_entry->entry_arr)
- return;
+ return -ENOMEM;
dev_entry->data_dma_blob_desc.size = 0;
dev_entry->data_dma_blob_desc.data = NULL;
@@ -1787,21 +1785,14 @@ void hl_debugfs_add_device(struct hl_device *hdev)
spin_lock_init(&dev_entry->userptr_spinlock);
mutex_init(&dev_entry->ctx_mem_hash_mutex);
- dev_entry->root = debugfs_create_dir(dev_name(hdev->dev),
- hl_debug_root);
-
- add_files_to_device(hdev, dev_entry, dev_entry->root);
- if (!hdev->asic_prop.fw_security_enabled)
- add_secured_nodes(dev_entry, dev_entry->root);
+ return 0;
}
-void hl_debugfs_remove_device(struct hl_device *hdev)
+void hl_debugfs_device_fini(struct hl_device *hdev)
{
struct hl_dbg_device_entry *entry = &hdev->hl_debugfs;
int i;
- debugfs_remove_recursive(entry->root);
-
mutex_destroy(&entry->ctx_mem_hash_mutex);
mutex_destroy(&entry->file_mutex);
@@ -1814,6 +1805,24 @@ void hl_debugfs_remove_device(struct hl_device *hdev)
kfree(entry->entry_arr);
}
+void hl_debugfs_add_device(struct hl_device *hdev)
+{
+ struct hl_dbg_device_entry *dev_entry = &hdev->hl_debugfs;
+
+ dev_entry->root = debugfs_create_dir(dev_name(hdev->dev), hl_debug_root);
+
+ add_files_to_device(hdev, dev_entry, dev_entry->root);
+ if (!hdev->asic_prop.fw_security_enabled)
+ add_secured_nodes(dev_entry, dev_entry->root);
+}
+
+void hl_debugfs_remove_device(struct hl_device *hdev)
+{
+ struct hl_dbg_device_entry *entry = &hdev->hl_debugfs;
+
+ debugfs_remove_recursive(entry->root);
+}
+
void hl_debugfs_add_file(struct hl_fpriv *hpriv)
{
struct hl_dbg_device_entry *dev_entry = &hpriv->hdev->hl_debugfs;
@@ -674,7 +674,7 @@ static int device_init_cdev(struct hl_device *hdev, struct class *class,
return 0;
}
-static int device_cdev_sysfs_add(struct hl_device *hdev)
+static int cdev_sysfs_debugfs_add(struct hl_device *hdev)
{
int rc;
@@ -699,7 +699,9 @@ static int device_cdev_sysfs_add(struct hl_device *hdev)
goto delete_ctrl_cdev_device;
}
- hdev->cdev_sysfs_created = true;
+ hl_debugfs_add_device(hdev);
+
+ hdev->cdev_sysfs_debugfs_created = true;
return 0;
@@ -710,11 +712,12 @@ static int device_cdev_sysfs_add(struct hl_device *hdev)
return rc;
}
-static void device_cdev_sysfs_del(struct hl_device *hdev)
+static void cdev_sysfs_debugfs_remove(struct hl_device *hdev)
{
- if (!hdev->cdev_sysfs_created)
+ if (!hdev->cdev_sysfs_debugfs_created)
goto put_devices;
+ hl_debugfs_remove_device(hdev);
hl_sysfs_fini(hdev);
cdev_device_del(&hdev->cdev_ctrl, hdev->dev_ctrl);
cdev_device_del(&hdev->cdev, hdev->dev);
@@ -2054,7 +2057,7 @@ static int create_cdev(struct hl_device *hdev)
int hl_device_init(struct hl_device *hdev)
{
int i, rc, cq_cnt, user_interrupt_cnt, cq_ready_cnt;
- bool add_cdev_sysfs_on_err = false;
+ bool expose_interfaces_on_err = false;
rc = create_cdev(hdev);
if (rc)
@@ -2170,16 +2173,22 @@ int hl_device_init(struct hl_device *hdev)
hdev->device_release_watchdog_timeout_sec = HL_DEVICE_RELEASE_WATCHDOG_TIMEOUT_SEC;
hdev->memory_scrub_val = MEM_SCRUB_DEFAULT_VAL;
- hl_debugfs_add_device(hdev);
- /* debugfs nodes are created in hl_ctx_init so it must be called after
- * hl_debugfs_add_device.
+ rc = hl_debugfs_device_init(hdev);
+ if (rc) {
+ dev_err(hdev->dev, "failed to initialize debugfs entry structure\n");
+ kfree(hdev->kernel_ctx);
+ goto mmu_fini;
+ }
+
+ /* The debugfs entry structure is accessed in hl_ctx_init(), so it must be called after
+ * hl_debugfs_device_init().
*/
rc = hl_ctx_init(hdev, hdev->kernel_ctx, true);
if (rc) {
dev_err(hdev->dev, "failed to initialize kernel context\n");
kfree(hdev->kernel_ctx);
- goto remove_device_from_debugfs;
+ goto debugfs_device_fini;
}
rc = hl_cb_pool_init(hdev);
@@ -2195,11 +2204,10 @@ int hl_device_init(struct hl_device *hdev)
}
/*
- * From this point, override rc (=0) in case of an error to allow
- * debugging (by adding char devices and create sysfs nodes as part of
- * the error flow).
+ * From this point, override rc (=0) in case of an error to allow debugging
+ * (by adding char devices and creating sysfs/debugfs files as part of the error flow).
*/
- add_cdev_sysfs_on_err = true;
+ expose_interfaces_on_err = true;
/* Device is now enabled as part of the initialization requires
* communication with the device firmware to get information that
@@ -2241,15 +2249,13 @@ int hl_device_init(struct hl_device *hdev)
}
/*
- * Expose devices and sysfs nodes to user.
- * From here there is no need to add char devices and create sysfs nodes
- * in case of an error.
+ * Expose devices and sysfs/debugfs files to user.
+ * From here there is no need to expose them in case of an error.
*/
- add_cdev_sysfs_on_err = false;
- rc = device_cdev_sysfs_add(hdev);
+ expose_interfaces_on_err = false;
+ rc = cdev_sysfs_debugfs_add(hdev);
if (rc) {
- dev_err(hdev->dev,
- "Failed to add char devices and sysfs nodes\n");
+ dev_err(hdev->dev, "Failed to add char devices and sysfs/debugfs files\n");
rc = 0;
goto out_disabled;
}
@@ -2295,8 +2301,8 @@ int hl_device_init(struct hl_device *hdev)
if (hl_ctx_put(hdev->kernel_ctx) != 1)
dev_err(hdev->dev,
"kernel ctx is still alive on initialization failure\n");
-remove_device_from_debugfs:
- hl_debugfs_remove_device(hdev);
+debugfs_device_fini:
+ hl_debugfs_device_fini(hdev);
mmu_fini:
hl_mmu_fini(hdev);
eq_fini:
@@ -2320,8 +2326,8 @@ int hl_device_init(struct hl_device *hdev)
put_device(hdev->dev);
out_disabled:
hdev->disabled = true;
- if (add_cdev_sysfs_on_err)
- device_cdev_sysfs_add(hdev);
+ if (expose_interfaces_on_err)
+ cdev_sysfs_debugfs_add(hdev);
if (hdev->pdev)
dev_err(&hdev->pdev->dev,
"Failed to initialize hl%d. Device %s is NOT usable !\n",
@@ -2447,8 +2453,6 @@ void hl_device_fini(struct hl_device *hdev)
if ((hdev->kernel_ctx) && (hl_ctx_put(hdev->kernel_ctx) != 1))
dev_err(hdev->dev, "kernel ctx is still alive\n");
- hl_debugfs_remove_device(hdev);
-
hl_dec_fini(hdev);
hl_vm_fini(hdev);
@@ -2473,8 +2477,10 @@ void hl_device_fini(struct hl_device *hdev)
device_early_fini(hdev);
- /* Hide devices and sysfs nodes from user */
- device_cdev_sysfs_del(hdev);
+ /* Hide devices and sysfs/debugfs files from user */
+ cdev_sysfs_debugfs_remove(hdev);
+
+ hl_debugfs_device_fini(hdev);
pr_info("removed device successfully\n");
}
@@ -3292,7 +3292,7 @@ struct hl_reset_info {
* @in_debug: whether the device is in a state where the profiling/tracing infrastructure
* can be used. This indication is needed because in some ASICs we need to do
* specific operations to enable that infrastructure.
- * @cdev_sysfs_created: were char devices and sysfs nodes created.
+ * @cdev_sysfs_debugfs_created: were char devices and sysfs/debugfs files created.
* @stop_on_err: true if engines should stop on error.
* @supports_sync_stream: is sync stream supported.
* @sync_stream_queue_idx: helper index for sync stream queues initialization.
@@ -3459,7 +3459,7 @@ struct hl_device {
u8 init_done;
u8 device_cpu_disabled;
u8 in_debug;
- u8 cdev_sysfs_created;
+ u8 cdev_sysfs_debugfs_created;
u8 stop_on_err;
u8 supports_sync_stream;
u8 sync_stream_queue_idx;
@@ -3978,6 +3978,8 @@ void hl_handle_fw_err(struct hl_device *hdev, struct hl_info_fw_err_info *info);
void hl_debugfs_init(void);
void hl_debugfs_fini(void);
+int hl_debugfs_device_init(struct hl_device *hdev);
+void hl_debugfs_device_fini(struct hl_device *hdev);
void hl_debugfs_add_device(struct hl_device *hdev);
void hl_debugfs_remove_device(struct hl_device *hdev);
void hl_debugfs_add_file(struct hl_fpriv *hpriv);