[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20211206145604.015861899@linuxfoundation.org>
Date: Mon, 6 Dec 2021 15:57:23 +0100
From: Greg Kroah-Hartman <gregkh@...uxfoundation.org>
To: linux-kernel@...r.kernel.org
Cc: Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
stable@...r.kernel.org, Chao Zeng <chao.zeng@...mens.com>,
Su Bao Cheng <baocheng.su@...mens.com>,
Jan Kiszka <jan.kiszka@...mens.com>,
Lukas Wunner <lukas@...ner.de>
Subject: [PATCH 5.10 126/130] serial: 8250: Fix RTS modem control while in rs485 mode
From: Lukas Wunner <lukas@...ner.de>
commit f85e04503f369b3f2be28c83fc48b74e19936ebc upstream.
Commit f45709df7731 ("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: f45709df7731 ("serial: 8250: Don't touch RTS modem control while in rs485 mode")
Cc: Chao Zeng <chao.zeng@...mens.com>
Cc: stable@...r.kernel.org # v5.7+
Reported-by: Su Bao Cheng <baocheng.su@...mens.com>
Reported-by: Jan Kiszka <jan.kiszka@...mens.com>
Tested-by: Su Bao Cheng <baocheng.su@...mens.com>
Signed-off-by: Lukas Wunner <lukas@...ner.de>
Link: https://lore.kernel.org/r/21170e622a1aaf842a50b32146008b5374b3dd1d.1637596432.git.lukas@wunner.de
Signed-off-by: Greg Kroah-Hartman <gregkh@...uxfoundation.org>
---
drivers/tty/serial/8250/8250_port.c | 7 -------
drivers/tty/serial/serial_core.c | 5 +++++
2 files changed, 5 insertions(+), 7 deletions(-)
--- a/drivers/tty/serial/8250/8250_port.c
+++ b/drivers/tty/serial/8250/8250_port.c
@@ -2029,13 +2029,6 @@ void serial8250_do_set_mctrl(struct uart
struct uart_8250_port *up = up_to_u8250p(port);
unsigned char mcr;
- if (port->rs485.flags & SER_RS485_ENABLED) {
- if (serial8250_in_MCR(up) & UART_MCR_RTS)
- mctrl |= TIOCM_RTS;
- else
- mctrl &= ~TIOCM_RTS;
- }
-
mcr = serial8250_TIOCM_to_MCR(mctrl);
mcr = (mcr & up->mcr_mask) | up->mcr_force | up->mcr;
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -1102,6 +1102,11 @@ uart_tiocmset(struct tty_struct *tty, un
goto out;
if (!tty_io_error(tty)) {
+ if (uport->rs485.flags & SER_RS485_ENABLED) {
+ set &= ~TIOCM_RTS;
+ clear &= ~TIOCM_RTS;
+ }
+
uart_update_mctrl(uport, set, clear);
ret = 0;
}
Powered by blists - more mailing lists