linux/drivers/tty/mxser.c, branch v6.0

tty: remove BOTHER ifdefs

2022-05-19T16:26:17Z

BOTHER is defined by all architectures since commit d0ffb805b729 ("arch/alpha, termios: implement BOTHER, IBSHIFT and termios2"). Reviewed-by: Johan Hovold Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20220513082906.11096-3-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman

mxser: make use of UART_LCR_WLEN() + tty_get_char_size()

2022-02-28T21:17:25Z

Having a generic UART_LCR_WLEN() macro and the tty_get_char_size() helper, we can remove all those repeated switch-cases in drivers. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20220224095558.30929-5-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman

mxser: switch from xmit_buf to kfifo

2022-01-26T13:54:48Z

Use kfifo for xmit buffer handling. The change is mostly straightforward. It saves complexity both on the stuffing side (mxser_write() and mxser_put_char()) and pulling side (mxser_transmit_chars()). In fact, the loop in mxser_write() can be completely deleted as the wrap of the buffer is taken care of in the kfifo code now. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20220124071430.14907-8-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman

mxser: use tty_port xmit_buf helpers

2022-01-26T13:54:48Z

For the mxser driver to use kfifo, use tty_port_alloc_xmit_buf() and tty_port_free_xmit_buf() helpers in activate/shutdown, respectively. As these calls have to be done in a non-atomic context, we have to move them outside spinlock and make sure irq is really stopped after we write to the ISR register. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20220124071430.14907-7-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman

mxser: fix xmit_buf leak in activate when LSR == 0xff

2022-01-26T13:54:48Z

When LSR is 0xff in ->activate() (rather unlike), we return an error. Provided ->shutdown() is not called when ->activate() fails, nothing actually frees the buffer in this case. Fix this by properly freeing the buffer in a designated label. We jump there also from the "!info->type" if now too. Fixes: 6769140d3047 ("tty: mxser: use the tty_port_open method") Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20220124071430.14907-6-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman

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