kernel/linux.git/drivers/usb/serial/digi_acceleport.c, branch v6.6.129

USB: serial: return errors from break handling

2023-06-07T15:00:23+00:00

Start propagating errors to user space when setting the break state fails. This will be used by follow-on changes to also report when a driver or device does not support break control. Tested-by: Corey Minyard Signed-off-by: Johan Hovold

usb: serial: Make ->set_termios() old ktermios const

2022-08-30T12:22:35+00:00

There should be no reason to adjust old ktermios which is going to get discarded anyway. Reviewed-by: Andy Shevchenko Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20220816115739.10928-8-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman

USB: serial: drop irq-flags initialisations

2021-05-21T13:46:25+00:00

There's no need to initialise irq-flags variables before saving the interrupt state. Drop the redundant initialisations from the three drivers that got this wrong. Reviewed-by: Greg Kroah-Hartman Signed-off-by: Johan Hovold

USB: serial: digi_acceleport: add chars_in_buffer locking

2021-05-21T13:46:02+00:00

Both the dp_write_urb_in_use flag and dp_out_buf_len counter should be accessed while holding the driver port lock. Add the missing locking to chars_in_buffer and clean up the implementation somewhat by using a common exit path. Reviewed-by: Greg Kroah-Hartman Signed-off-by: Johan Hovold

USB: serial: digi_acceleport: reduce chars_in_buffer over-reporting

2021-05-21T13:45:35+00:00

Due to an ancient quirk in n_tty poll implementation, the digi_acceleport driver has been reporting that its queue contains 256 (WAKEUP_CHARS) characters whenever its write URB is in use. This has not been necessary since 2003 when the line-discipline started taking the write room into account so let's return the maximum transfer size again in order to over-report a little less and incidentally fix the related debug statement. Reviewed-by: Greg Kroah-Hartman Signed-off-by: Johan Hovold

USB: serial: make usb_serial_driver::chars_in_buffer return uint

2021-05-19T08:56:41+00:00

tty_operations::chars_in_buffer is being switched to return uint. Do the same for usb_serial_driver's chars_in_buffer. Signed-off-by: Jiri Slaby [ johan: amend commit message ] Signed-off-by: Johan Hovold

USB: serial: make usb_serial_driver::write_room return uint

2021-05-19T08:56:40+00:00

Line disciplines expect a positive value or zero returned from tty->ops->write_room (invoked by tty_write_room). Both of them are being updated to return an unsigned int. Switch also usb_serial_driver::write_room and all its users. Signed-off-by: Jiri Slaby [ johan: amend commit message, drop unrelated comment change ] Signed-off-by: Johan Hovold

USB: serial: make remove callback return void

2021-02-09T12:13:58+00:00

All usb_serial drivers return 0 in their remove callbacks and driver core ignores the value returned by usb_serial_device_remove(). So change the remove callback to return void and return 0 unconditionally in usb_serial_device_remove(). Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20210208143149.963644-2-uwe@kleine-koenig.org Signed-off-by: Johan Hovold

USB: serial: remove write wait queue

2020-11-04T10:11:29+00:00

The digi_acceleport driver is the only driver still using the port write wake queue so move it to that driver's port data. Reviewed-by: Greg Kroah-Hartman Signed-off-by: Johan Hovold

USB: serial: digi_acceleport: fix write-wakeup deadlocks

2020-11-04T10:11:29+00:00

The driver must not call tty_wakeup() while holding its private lock as line disciplines are allowed to call back into write() from write_wakeup(), leading to a deadlock. Also remove the unneeded work struct that was used to defer wakeup in order to work around a possible race in ancient times (see comment about n_tty write_chan() in commit 14b54e39b412 ("USB: serial: remove changelogs and old todo entries")). Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Cc: stable@vger.kernel.org Reviewed-by: Greg Kroah-Hartman Signed-off-by: Johan Hovold