tmp_suning_uos_patched/drivers/tty
Lukas Wunner a5d0a72b80 serial: 8250: Fix RTS modem control while in rs485 mode
commit f85e04503f369b3f2be28c83fc48b74e19936ebc upstream.

Commit f45709df77 ("serial: 8250: Don't touch RTS modem control while
in rs485 mode") sought to prevent user space from interfering with rs485
communication by ignoring a TIOCMSET ioctl() which changes RTS polarity.

It did so in serial8250_do_set_mctrl(), which turns out to be too deep
in the call stack:  When a uart_port is opened, RTS polarity is set by
the rs485-aware function uart_port_dtr_rts().  It calls down to
serial8250_do_set_mctrl() and that particular RTS polarity change should
*not* be ignored.

The user-visible result is that on 8250_omap ports which use rs485 with
inverse polarity (RTS bit in MCR register is 1 to receive, 0 to send),
a newly opened port initially sets up RTS for sending instead of
receiving.  That's because omap_8250_startup() sets the cached value
up->mcr to 0 and omap_8250_restore_regs() subsequently writes it to the
MCR register.  Due to the commit, serial8250_do_set_mctrl() preserves
that incorrect register value:

do_sys_openat2
  do_filp_open
    path_openat
      vfs_open
        do_dentry_open
	  chrdev_open
	    tty_open
	      uart_open
	        tty_port_open
		  uart_port_activate
		    uart_startup
		      uart_port_startup
		        serial8250_startup
			  omap_8250_startup # up->mcr = 0
			uart_change_speed
			  serial8250_set_termios
			    omap_8250_set_termios
			      omap_8250_restore_regs
			        serial8250_out_MCR # up->mcr written
		  tty_port_block_til_ready
		    uart_dtr_rts
		      uart_port_dtr_rts
		        serial8250_set_mctrl
			  omap8250_set_mctrl
			    serial8250_do_set_mctrl # mcr[1] = 1 ignored

Fix by intercepting RTS changes from user space in uart_tiocmset()
instead.

Link: https://lore.kernel.org/linux-serial/20211027111644.1996921-1-baocheng.su@siemens.com/
Fixes: f45709df77 ("serial: 8250: Don't touch RTS modem control while in rs485 mode")
Cc: Chao Zeng <chao.zeng@siemens.com>
Cc: stable@vger.kernel.org # v5.7+
Reported-by: Su Bao Cheng <baocheng.su@siemens.com>
Reported-by: Jan Kiszka <jan.kiszka@siemens.com>
Tested-by: Su Bao Cheng <baocheng.su@siemens.com>
Signed-off-by: Lukas Wunner <lukas@wunner.de>
Link: https://lore.kernel.org/r/21170e622a1aaf842a50b32146008b5374b3dd1d.1637596432.git.lukas@wunner.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2021-12-08 09:03:29 +01:00
..
hvc tty: hvc: replace BUG_ON() with negative return value 2021-12-01 09:19:10 +01:00
ipwireless
serdev
serial serial: 8250: Fix RTS modem control while in rs485 mode 2021-12-08 09:03:29 +01:00
vt tty: Fix out-of-bound vmalloc access in imageblit 2021-10-06 15:55:45 +02:00
amiserial.c
cyclades.c
ehv_bytechan.c
goldfish.c
isicom.c
Kconfig
Makefile
mips_ejtag_fdc.c
moxa.c
moxa.h
mxser.c
mxser.h
n_gsm.c
n_hdlc.c
n_null.c
n_r3964.c
n_tracerouter.c
n_tracesink.c
n_tracesink.h
n_tty.c
nozomi.c tty: nozomi: Fix the error handling path of 'nozomi_card_init()' 2021-07-14 16:56:39 +02:00
pty.c
rocket_int.h
rocket.c
rocket.h
synclink_gt.c tty: synclink_gt: rename a conflicting function name 2021-09-30 10:11:03 +02:00
synclink.c
synclinkmp.c
sysrq.c
tty_audit.c
tty_baudrate.c
tty_buffer.c tty: tty_buffer: Fix the softlockup issue in flush_to_ldisc 2021-11-26 10:39:10 +01:00
tty_io.c tty: Fix data race between tiocsti() and flush_to_ldisc() 2021-09-15 09:50:47 +02:00
tty_ioctl.c
tty_jobctrl.c
tty_ldisc.c
tty_ldsem.c
tty_mutex.c
tty_port.c
ttynull.c
vcc.c