diff options
| author |  Emil Kronborg <emil.kronborg@protonmail.com>
| 2024-03-20 12:15:36 +0000 |
|---|---|---|
| committer |  Greg Kroah-Hartman <gregkh@linuxfoundation.org>
| 2024-04-09 15:56:41 +0200 |
| commit | 54c4ec5f8c471b7c1137a1f769648549c423c026 (patch) | |
| tree | ca16cd7725792fbb7ecebc7d9a58732d62d0209e /drivers/tty/serial/max3100.c | |
| parent | serial: 8250_dw: Revert: Do not reclock if already at correct rate (diff) | |
| download | linux-54c4ec5f8c471b7c1137a1f769648549c423c026.tar.gz linux-54c4ec5f8c471b7c1137a1f769648549c423c026.tar.bz2 linux-54c4ec5f8c471b7c1137a1f769648549c423c026.zip | |
serial: mxs-auart: add spinlock around changing cts state
The uart_handle_cts_change() function in serial_core expects the caller
to hold uport->lock. For example, I have seen the below kernel splat,
when the Bluetooth driver is loaded on an i.MX28 board.
[ 85.119255] ------------[ cut here ]------------
[ 85.124413] WARNING: CPU: 0 PID: 27 at /drivers/tty/serial/serial_core.c:3453 uart_handle_cts_change+0xb4/0xec
[ 85.134694] Modules linked in: hci_uart bluetooth ecdh_generic ecc wlcore_sdio configfs
[ 85.143314] CPU: 0 PID: 27 Comm: kworker/u3:0 Not tainted 6.6.3-00021-gd62a2f068f92 #1
[ 85.151396] Hardware name: Freescale MXS (Device Tree)
[ 85.156679] Workqueue: hci0 hci_power_on [bluetooth]
(...)
[ 85.191765] uart_handle_cts_change from mxs_auart_irq_handle+0x380/0x3f4
[ 85.198787] mxs_auart_irq_handle from __handle_irq_event_percpu+0x88/0x210
(...)
Cc: stable@vger.kernel.org
Fixes: 4d90bb147ef6 ("serial: core: Document and assert lock requirements for irq helpers")
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Signed-off-by: Emil Kronborg <emil.kronborg@protonmail.com>
Link: https://lore.kernel.org/r/20240320121530.11348-1-emil.kronborg@protonmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Diffstat (limited to 'drivers/tty/serial/max3100.c')
0 files changed, 0 insertions, 0 deletions