linux/drivers/tty/mxser.c, branch v5.17

mxser: use PCI_DEVICE_DATA

2021-11-25T17:33:22Z

Now that we have all the PCI device IDs unified, we can use PCI_DEVICE_DATA() macro to simplify mxser's pci_device_id list, i.e. mxser_pcibrds. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20211118073125.12283-20-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman

mxser: move ids from pci_ids.h here

2021-11-25T17:33:22Z

There is no point having MOXA PCI device IDs in include/linux/pci_ids.h. Move them to the driver and sort them all by the ID. Cc: Bjorn Helgaas Cc: linux-pci@vger.kernel.org Acked-by: Bjorn Helgaas Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20211118073125.12283-19-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman

mxser: add MOXA prefix to some PCI device IDs

2021-11-25T17:33:22Z

Some of the MOXA PCI device IDs contain _MOXA_, some don't. Add it to the latter, so that they are all unified. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20211118073125.12283-18-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman

mxser: increase buf_overrun if tty_insert_flip_char() fails

2021-11-25T17:33:22Z

mxser doesn't increase port->icount.buf_overrun at all. Do so if overrun happens, so that it can be read from the stats. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20211118073125.12283-17-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman

mxser: remove tty parameter from mxser_receive_chars_new()

2021-11-25T17:33:22Z

After the previous change (no plays with of tty->receive_room), the tty parameter is unused. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20211118073125.12283-16-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman

mxser: don't throttle manually

2021-11-25T17:33:22Z

First, checking tty->receive_room to signalize whether there is enough space in the tty buffers does not make much sense. Provided the tty buffers are in tty_port and those are not checked at all. Second, if the rx path is throttled, with CRTSCTS, RTS is deasserted, but is never asserted again. This leads to port "lockup", not accepting any more input. So: 1) stty -F /dev/ttyMI0 crtscts # the mxser port 2) stty -F /dev/ttyS6 crtscts # the connected port 3) cat /dev/ttyMI0 4) "write in a loop" to /dev/ttyS6 5) cat from 3) produces the bytes from 4) 6) killall -STOP cat (the 3)'s one) 7) wait for RTS to drop on /dev/ttyMI0 8) killall -CONT cat (again the 3)'s one) cat erroneously produces no more output now (i.e. no data sent from ttyS6 to ttyMI can be seen). Note that the step 7) is performed twice: once from n_tty by tty_throttle_safe(), once by mxser_stoprx() from the receive path. Then after step 7), n_tty correctly unthrottles the input, but mxser calls mxser_stoprx() again as there is still only a little space in n_tty buffers (tty->receive_room mentioned at the beginning), but the device's FIFO is/can be already filled. After this patch, the output is correctly resumed, i.e. n_tty both throttles and unthrottles without interfering with mxser's attempts. This allows us to get rid of the non-standard ldisc_stop_rx flag from struct mxser_port. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20211118073125.12283-15-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman

mxser: clean up timeout handling in mxser_wait_until_sent()

2021-11-25T17:33:22Z

timeout cannot be zero at the point of use. So no need to check for zero. Also precompute the expiration time (into expire) and use it. This makes the code more clear. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20211118073125.12283-14-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman

mxser: use msleep_interruptible() in mxser_wait_until_sent()

2021-11-25T17:33:22Z

Instead of schedule_timeout_interruptible(), because: 1) we don't have to bother with the task state, and 2) msleep* guarantees to sleep that time (if not interrupted). Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20211118073125.12283-13-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman

mxser: extract TX empty check from mxser_wait_until_sent()

2021-11-25T17:33:22Z

And move it to new mxser_tx_empty(), because: 1) it simplifies the code (esp. the locking), and 2) serial_core needs such a hook anyway, so have it ready. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20211118073125.12283-12-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman

mxser: use tty_port_close() in mxser_close()

2021-11-25T17:33:22Z

Finally, the mxser_close() code in is mostly identical to tty_port_close(), so replace the code by a single call to the function. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20211118073125.12283-11-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman