Skip to content

Make driver init() function optional #3565

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
HiFiPhile merged 3 commits into from
Mar 22, 2026
+6 −5
Merged

Make driver init() function optional #3565

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
c9fdfc7
Don't crash on driver without init()
ceedriic Mar 21, 2026
ebd18f5
Update documentation
ceedriic Mar 22, 2026
f0d7db1
Unifiy Device and Host side
ceedriic Mar 22, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion docs/reference/architecture.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -189,13 +189,13 @@ Class Driver Interface
See ``usbd.c``.

**Required Functions**:
- ``init()``: Initialize class driver
- ``reset()``: Reset class state
- ``open()``: Configure class endpoints
- ``control_xfer_cb()``: Handle control requests
- ``xfer_cb()``: Handle data transfer completion

**Optional Functions**:
- ``init()``: Initialize class driver
Comment on lines 196 to +198
Copy link

Copilot AI Mar 22, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This section still references device-side behavior ("See usbd.c"), where init() is required (the stack asserts driver->init). Moving init() to Optional Functions here makes the documentation inaccurate unless the device-side requirement is also relaxed, or the doc is clarified/split for host vs device class driver interfaces.

Suggested change
**Optional Functions**:
- ``init()``: Initialize class driver
- ``init()``: Initialize class driver
**Optional Functions**:

Copilot uses AI. Check for mistakes.
Copy link
Copy Markdown
Collaborator

@HiFiPhile HiFiPhile Mar 22, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@copilot make device side init() optional

Copy link
Copy Markdown
Contributor Author

@ceedriic ceedriic Mar 22, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Let's see if I'm a good copilot...

- ``close()``: Clean up class resources
- ``deinit()``: Deinitialize class driver
- ``sof()``: Start-of-frame processing
Expand Down
2 changes: 1 addition & 1 deletion src/host/usbh.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -544,7 +544,7 @@ bool tuh_rhport_init(uint8_t rhport, const tusb_rhport_init_t* rh_init) {
// Class drivers
for (uint8_t drv_id = 0; drv_id < TOTAL_DRIVER_COUNT; drv_id++) {
usbh_class_driver_t const* driver = get_driver(drv_id);
if (driver != NULL) {
if (driver != NULL && driver->init) {
TU_LOG_USBH("%s init\r\n", driver->name);
driver->init();
Copy link

Copilot AI Mar 22, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

driver->init() returns bool (see usbh_class_driver_t), but its return value is ignored. Several built-in class init functions can return false on internal TU_ASSERT failures, so tuh_rhport_init() may still succeed even though a class driver failed to initialize. Consider asserting/propagating the init result (e.g., fail tuh_rhport_init() if any present init() returns false).

Suggested change
driver->init();
bool inited = driver->init();
TU_ASSERT(inited);
if (!inited) {
return false;
}

Copilot uses AI. Check for mistakes.
}
Expand Down
Loading