There is a small window in time during resume where the hardware
flow control signal RTS can be asserted (which allows a sender to
resume sending data to the UART) but the baud rate has not yet
been restored. This will cause corrupted data and FRAMING, OVERRUN
and BREAK errors. This is happening because the MCTRL register is
shadowed in uart_port struct and is later used during resume to set
the MCTRL register during both serial8250_do_startup() and
uart_resume_port(). Unfortunately, serial8250_do_startup()
happens before the UART baud rate is restored. The fix is to clear
the shadowed mctrl value at the end of suspend and restore it at the
end of resume.
Fixes: 41a469482d ("serial: 8250: Add new 8250-core based Broadcom STB driver")
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Al Cooper <alcooperx@gmail.com>
Link: https://lore.kernel.org/r/20211201201402.47446-1-alcooperx@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Have pericom_do_set_divisor() use the uartclk instead of a hard coded
value to work with different speed crystals. Tested with 14.7456 and 24
MHz crystals.
Have pericom_do_set_divisor() always calculate the divisor rather than
call serial8250_do_set_divisor() for rates below baud_base.
Do not write registers or call serial8250_do_set_divisor() if valid
divisors could not be found.
Fixes: 6bf4e42f1d ("serial: 8250: Add support for higher baud rates to Pericom chips")
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Jay Dolan <jay.dolan@accesio.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20211122120604.3909-3-andriy.shevchenko@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
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>
The driver was updating the port uartclk before setting the new rate in
an attempt to avoid having the clock notifier redundantly update the
divisors.
The set_termios() callback is however called under the termios semaphore
and tty-port mutex so the worker scheduled by the clock notifier will
block in serial8250_update_uartclk() until the uartclk and divisors have
been updated anyway.
Drop the unnecessary swaps and incorrect comment and simply update the
uartclk field if the clock-rate change was successful.
Tested-by: Serge Semin <fancer.lancer@gmail.com>
Reviewed-by: Serge Semin <fancer.lancer@gmail.com>
Acked-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/r/20211015111422.1027-4-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This reverts commit 32262e2e42.
The commit in question claims to determine the inverse of
serial8250_get_divisor() but failed to notice that some drivers override
the default implementation using a get_divisor() callback.
This means that the computed line-speed values can be completely wrong
and results in regular TCSETS requests failing (the incorrect values
would also be passed to any overridden set_divisor() callback).
Similarly, it also failed to honour the old (deprecated) ASYNC_SPD_FLAGS
and would break applications relying on those when re-encoding the
actual line speed.
There are also at least two quirks, UART_BUG_QUOT and an OMAP1510
workaround, which were happily ignored and that are now broken.
Finally, even if the offending commit were to be implemented correctly,
this is a new feature and not something which should be backported to
stable.
Cc: Pali Rohár <pali@kernel.org>
Fixes: 32262e2e42 ("serial: 8250: Fix reporting real baudrate value in c_ospeed field")
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/r/20211007133146.28949-1-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The SERIAL_8250_FSL option is used to enable a workaround for a
break-detection erratum for Freescale 16550 UARTs in the 8250 driver and
is currently also used to enable support for ACPI enumeration.
It is enabled on PPC, ARM and ARM64 whenever 8250 console support is
enabled (since the quirk is needed for sysrq handling).
Commit b1442c55ce ("serial: 8250: extend compile-test coverage")
enabled compile testing of the code in question but did not provide a
means to disable the option when COMPILE_TEST is enabled.
Add a conditional input prompt instead so that SERIAL_8250_FSL is no
longer enabled by default when compile testing while continuing to
always enable the quirk for platforms that may need it.
Fixes: b1442c55ce ("serial: 8250: extend compile-test coverage")
Reported-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Johan Hovold <johan@kernel.org>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/20210924141232.4419-1-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
In most cases it is not possible to set exact baudrate value to hardware.
So fix reporting real baudrate value which was set to hardware via c_ospeed
termios field. It can be retrieved by ioctl(TCGETS2) from userspace.
Real baudrate value is calculated from chosen hardware divisor and base
clock. It is implemented in a new function serial8250_compute_baud_rate()
which is inverse of serial8250_get_divisor() function.
With this change is fixed also UART timeout value (it is updated via
uart_update_timeout() function), which is calculated from the now fixed
baudrate value too.
Cc: stable@vger.kernel.org
Signed-off-by: Pali Rohár <pali@kernel.org>
Link: https://lore.kernel.org/r/20210927093704.19768-1-pali@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Handle optional overrun-throttle-ms property as done for 8250_fsl in commit
6d7f677a2a ("serial: 8250: Rate limit serial port rx interrupts during
input overruns"). This can be used to rate limit the UART interrupts on
noisy lines that end up producing messages like the following:
ttyS ttyS2: 4 input overrun(s)
At least on droid4, the multiplexed USB and UART port is left to UART mode
by the bootloader for a debug console, and if a USB charger is connected
on boot, we get noise on the UART until the PMIC related drivers for PHY
and charger are loaded.
With this patch and overrun-throttle-ms = <500> we avoid the extra rx
interrupts.
Cc: Carl Philipp Klemm <philipp@uvos.xyz>
Cc: Merlijn Wajer <merlijn@wizzup.org>
Cc: Pavel Machek <pavel@ucw.cz>
Cc: Sebastian Reichel <sre@kernel.org>
Cc: Vignesh Raghavendra <vigneshr@ti.com>
Signed-off-by: Tony Lindgren <tony@atomide.com>
Link: https://lore.kernel.org/r/20210727103533.51547-2-tony@atomide.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This attempts to fix a bug found with a serial port card which uses
an MCS9922 chip, one of the 4 models for which MSI-X interrupts are
currently supported. I don't possess such a card, and i'm not
experienced with the serial subsystem, so this patch is based on what
i think i found as a likely reason for failure, based on walking the
user who actually owns the card through some diagnostic.
The user who reported the problem finds the following in his dmesg
output for the relevant ttyS4 and ttyS5:
[ 0.580425] serial 0000:02:00.0: enabling device (0000 -> 0003)
[ 0.601448] 0000:02:00.0: ttyS4 at I/O 0x3010 (irq = 125, base_baud = 115200) is a ST16650V2
[ 0.603089] serial 0000:02:00.1: enabling device (0000 -> 0003)
[ 0.624119] 0000:02:00.1: ttyS5 at I/O 0x3000 (irq = 126, base_baud = 115200) is a ST16650V2
...
[ 6.323784] genirq: Flags mismatch irq 128. 00000080 (ttyS5) vs. 00000000 (xhci_hcd)
[ 6.324128] genirq: Flags mismatch irq 128. 00000080 (ttyS5) vs. 00000000 (xhci_hcd)
...
Output of setserial -a:
/dev/ttyS4, Line 4, UART: 16650V2, Port: 0x3010, IRQ: 127
Baud_base: 115200, close_delay: 50, divisor: 0
closing_wait: 3000
Flags: spd_normal skip_test
This suggests to me that the serial driver wants to register and share a
MSI/MSI-X irq 128 with the xhci_hcd driver, whereas the xhci driver does
not want to share the irq, as flags 0x00000080 (== IRQF_SHARED) from the
serial port driver means to share the irq, and this mismatch ends in some
failed irq init?
With this setup, data reception works very unreliable, with dropped data,
already at a transmission rate of only a 16 Bytes chunk every 1/120th of
a second, ie. 1920 Bytes/sec, presumably due to rx fifo overflow due to
mishandled or not used at all rx irq's?
See full discussion thread with attempted diagnosis at:
https://psychtoolbox.discourse.group/t/issues-with-iscan-serial-port-recording/3886
Disabling the use of MSI interrupts for the serial port pci card did
fix the reliability problems. The user executed the following sequence
of commands to achieve this:
echo 0000:02:00.0 | sudo tee /sys/bus/pci/drivers/serial/unbind
echo 0000:02:00.1 | sudo tee /sys/bus/pci/drivers/serial/unbind
echo 0 | sudo tee /sys/bus/pci/devices/0000:02:00.0/msi_bus
echo 0 | sudo tee /sys/bus/pci/devices/0000:02:00.1/msi_bus
echo 0000:02:00.0 | sudo tee /sys/bus/pci/drivers/serial/bind
echo 0000:02:00.1 | sudo tee /sys/bus/pci/drivers/serial/bind
This resulted in the following log output:
[ 82.179021] pci 0000:02:00.0: MSI/MSI-X disallowed for future drivers
[ 87.003031] pci 0000:02:00.1: MSI/MSI-X disallowed for future drivers
[ 98.537010] 0000:02:00.0: ttyS4 at I/O 0x3010 (irq = 17, base_baud = 115200) is a ST16650V2
[ 103.648124] 0000:02:00.1: ttyS5 at I/O 0x3000 (irq = 18, base_baud = 115200) is a ST16650V2
This patch attempts to fix the problem by disabling irq sharing when
using MSI irq's. Note that all i know for sure is that disabling MSI
irq's fixed the problem for the user, so this patch could be wrong and
is untested. Please review with caution, keeping this in mind.
Fixes: 8428413b1d ("serial: 8250_pci: Implement MSI(-X) support")
Cc: Ralf Ramsauer <ralf.ramsauer@oth-regensburg.de>
Cc: stable <stable@vger.kernel.org>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Mario Kleiner <mario.kleiner.de@gmail.com>
Link: https://lore.kernel.org/r/20210729043306.18528-1-mario.kleiner.de@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Fix uart corruption issue when rx power off.
Add spin lock in mtk8250_dma_rx_complete function in APDMA mode.
when uart is used as a communication port with external device(GPS).
when external device(GPS) power off, the power of rx pin is also from
1.8v to 0v. Even if there is not any data in rx. But uart rx pin can
capture the data "0".
If uart don't receive any data in specified cycle, uart will generates
BI(Break interrupt) interrupt.
If external device(GPS) power off, we found that BI interrupt appeared
continuously and very frequently.
When uart interrupt type is BI, uart IRQ handler(8250 framwork
API:serial8250_handle_irq) will push data to tty buffer.
mtk8250_dma_rx_complete is a task of mtk_uart_apdma_rx_handler.
mtk8250_dma_rx_complete priority is lower than uart irq
handler(serial8250_handle_irq).
if we are in process of mtk8250_dma_rx_complete, uart appear BI
interrupt:1)serial8250_handle_irq will priority execution.2)it may cause
write tty buffer conflict in mtk8250_dma_rx_complete.
So the spin lock protect the rx receive data process is not break.
Signed-off-by: Zhiyong Tao <zhiyong.tao@mediatek.com>
Cc: stable <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20210729084640.17613-2-zhiyong.tao@mediatek.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Oxford Semiconductor 950 serial port devices have a 128-byte FIFO and in
the enhanced (650) mode, which we select in `autoconfig_has_efr' with
the ECB bit set in the EFR register, they support the receive interrupt
trigger level selectable with FCR bits 7:6 from the set of 16, 32, 112,
120. This applies to the original OX16C950 discrete UART[1] as well as
950 cores embedded into more complex devices.
For these devices we set the default to 112, which sets an excessively
high level of 112 or 7/8 of the FIFO capacity, unlike with other port
types where we choose at most 1/2 of their respective FIFO capacities.
Additionally we don't make the trigger level configurable. Consequently
frequent input overruns happen with high bit rates where hardware flow
control cannot be used (e.g. terminal applications) even with otherwise
highly-performant systems.
Lower the default receive interrupt trigger level to 32 then, and make
it configurable. Document the trigger levels along with other port
types, including the set of 16, 32, 64, 112 for the transmit interrupt
as well[2].
References:
[1] "OX16C950 rev B High Performance UART with 128 byte FIFOs", Oxford
Semiconductor, Inc., DS-0031, Sep 05, Table 10: "Receiver Trigger
Levels", p. 22
[2] same, Table 9: "Transmit Interrupt Trigger Levels", p. 22
Signed-off-by: Maciej W. Rozycki <macro@orcam.me.uk>
Link: https://lore.kernel.org/r/alpine.DEB.2.21.2106260608480.37803@angie.orcam.me.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The 8250 handle_irq callback is not just called from the interrupt
handler but also from a timer callback when polling (e.g. for ports
without an interrupt line). Consequently the callback must explicitly
disable interrupts to avoid a potential deadlock with another interrupt
in polled mode.
Add back an irqrestore-version of the sysrq port-unlock helper and use
it in the 8250 callbacks that need it.
Fixes: 75f4e830fa ("serial: do not restore interrupt state in sysrq helper")
Cc: stable@vger.kernel.org # 5.13
Cc: Joel Stanley <joel@jms.id.au>
Cc: Andrew Jeffery <andrew@aj.id.au>
Reported-by: kernel test robot <oliver.sang@intel.com>
Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/r/20210714080427.28164-1-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Make sure only actual 8 bits of the IIR register are used in determining
the port type in `autoconfig'.
The `serial_in' port accessor returns the `unsigned int' type, meaning
that with UPIO_AU, UPIO_MEM16, UPIO_MEM32, and UPIO_MEM32BE access types
more than 8 bits of data are returned, of which the high order bits will
often come from bus lines that are left floating in the data phase. For
example with the MIPS Malta board's CBUS UART, where the registers are
aligned on 8-byte boundaries and which uses 32-bit accesses, data as
follows is returned:
YAMON> dump -32 0xbf000900 0x40
BF000900: 1F000942 1F000942 1F000900 1F000900 ...B...B........
BF000910: 1F000901 1F000901 1F000900 1F000900 ................
BF000920: 1F000900 1F000900 1F000960 1F000960 ...........`...`
BF000930: 1F000900 1F000900 1F0009FF 1F0009FF ................
YAMON>
Evidently high-order 24 bits return values previously driven in the
address phase (the 3 highest order address bits used with the command
above are masked out in the simple virtual address mapping used here and
come out at zeros on the external bus), a common scenario with bus lines
left floating, due to bus capacitance.
Consequently when the value of IIR, mapped at 0x1f000910, is retrieved
in `autoconfig', it comes out at 0x1f0009c1 and when it is right-shifted
by 6 and then assigned to 8-bit `scratch' variable, the value calculated
is 0x27, not one of 0, 1, 2, 3 expected in port type determination.
Fix the issue then, by assigning the value returned from `serial_in' to
`scratch' first, which masks out 24 high-order bits retrieved, and only
then right-shift the resulting 8-bit data quantity, producing the value
of 3 in this case, as expected. Fix the same issue in `serial_dl_read'.
The problem first appeared with Linux 2.6.9-rc3 which predates our repo
history, but the origin could be identified with the old MIPS/Linux repo
also at: <git://git.kernel.org/pub/scm/linux/kernel/git/ralf/linux.git>
as commit e0d2356c0777 ("Merge with Linux 2.6.9-rc3."), where code in
`serial_in' was updated with this case:
+ case UPIO_MEM32:
+ return readl(up->port.membase + offset);
+
which made it produce results outside the unsigned 8-bit range for the
first time, though obviously it is system dependent what actual values
appear in the high order bits retrieved and it may well have been zeros
in the relevant positions with the system the change originally was
intended for. It is at that point that code in `autoconf' should have
been updated accordingly, but clearly it was overlooked.
Fixes: 1da177e4c3 ("Linux-2.6.12-rc2")
Cc: stable@vger.kernel.org # v2.6.12+
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Signed-off-by: Maciej W. Rozycki <macro@orcam.me.uk>
Link: https://lore.kernel.org/r/alpine.DEB.2.21.2106260516220.37803@angie.orcam.me.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Don't populate the const array k3_soc_devices on the stack but instead it
static. Makes the object code smaller by 44 bytes:
Before:
text data bss dec hex filename
31628 5609 128 37365 91f5 drivers/tty/serial/8250/8250_omap.o
After:
text data bss dec hex filename
31520 5673 128 37321 91c9 drivers/tty/serial/8250/8250_omap.o
Reduction of 44 bytes
(gcc version 10.3.0)
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Link: https://lore.kernel.org/r/20210715140759.27244-1-colin.king@canonical.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
On K3 family of SoCs (which includes AM654 SoC), it is observed that RX
TIMEOUT is signalled after RX FIFO has been drained, in which case a
dummy read of RX FIFO is required to clear RX TIMEOUT condition.
Otherwise, this would lead to an interrupt storm.
Fix this by introducing UART_RX_TIMEOUT_QUIRK flag and doing a dummy
read in IRQ handler when RX TIMEOUT is reported with no data in RX FIFO.
Fixes: be70874498 ("serial: 8250_omap: Add support for AM654 UART controller")
Reported-by: Jan Kiszka <jan.kiszka@siemens.com>
Tested-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com>
Link: https://lore.kernel.org/r/20210622145704.11168-1-vigneshr@ti.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Handle custom baud rates requested in the UPF_MAGIC_MULTIPLIER range
with BOTHER. Currently matching is exact, that is if a baud rate that
is not either of clk/4 or clk/8 is requested, then we fall through to
the default case, which will just divide the clock rate by 16 times the
rate requested, round it to closest integer, and possibly yield even
worse results then if clamping to the extra baud rates was chosen.
So for example if we have the usual base rate of 115200 and request a
rate of 230399, then the fall-through divisor calculation will yield 1,
and consequently the baud rate of 115200 will be programmed even though
obviously the magic rate of 230400 would be more appropriate.
Make the selection of the magic rates range-qualified then and use clk/4
for rates from clk/6 up (assuming `serial8250_get_baud_rate' has already
rejected any rates too far beyond clk/4), and otherwise use clk/8 for
rates from clk/12 up, and finally fall through to the standard divisor
calculation. Explicitly void using the undocumented rate of 153600bps
and stick to documented divisor values only.
Signed-off-by: Maciej W. Rozycki <macro@orcam.me.uk>
Link: https://lore.kernel.org/r/alpine.DEB.2.21.2105200232090.29169@angie.orcam.me.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Support for magic baud rate divisors of 32770 and 32769 used with SMSC
Super I/O chips for extra baud rates of 230400 and 460800 respectively
where base rate is 115200[1] has been added around Linux 2.5.64, which
predates our repo history, but the origin could be identified as commit
2a717aad772f ("Merge with Linux 2.5.64.") with the old MIPS/Linux repo
also at: <git://git.kernel.org/pub/scm/linux/kernel/git/ralf/linux.git>.
Code that is now in `serial8250_do_get_divisor' was added back then to
`serial8250_get_divisor', but that code would only ever trigger if one
of the higher baud rates was actually requested, and that cannot ever
happen, because the earlier call to `serial8250_get_baud_rate' never
returns them. This is because it calls `uart_get_baud_rate' with the
maximum requested being the base rate, that is clk/16 or 115200 for SMSC
chips at their nominal clock rate.
Fix it then and allow UPF_MAGIC_MULTIPLIER baud rates to be selected, by
requesting the maximum baud rate of clk/4 rather than clk/16 if the flag
has been set. Also correct the minimum baud rate, observing that these
ports only support actual (non-magic) divisors of up to 32767 only.
References:
[1] "FDC37M81x, PC98/99 Compliant Enhanced Super I/O Controller with
Keyboard/Mouse Wake-Up", Standard Microsystems Corporation, Rev.
03/27/2000, Table 31 - "Baud Rates", p. 77
Fixes: 1da177e4c3 ("Linux-2.6.12-rc2")
Signed-off-by: Maciej W. Rozycki <macro@orcam.me.uk>
Link: https://lore.kernel.org/r/alpine.DEB.2.21.2105190412280.29169@angie.orcam.me.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Contrary to what SMSC documentation says and unlike NS16C550A UARTs the
SMSC Super I/O IC claims compatibility with the SMSC UART implementation
does not support dividing the internal PLL clock by any divisor from 1
to 65535[1], with the exception of two magic divisors of 32769 and 32770
used respectively to select the high-speed data rates of 460800bps and
230400bps[2] if enabled on a port-by-port basis in with the Serial Port
Mode Register in the Device Configuration Space[3][4].
Instead empirical evidence indicates that the divisor, as stored in the
DLL and DLM register pair, has the range of 1 to 32767 only, and bit 7
of the DLM register (bit 15 of the divisor) effectively serves as a
selection bit for the prescaler from the base frequency of 7.3728MHz,
either 4 if the bit is 0, or 1 if the bit is 1 and high-speed operation
has been enabled with the Serial Port Mode Register.
So if high-speed operation has not been enabled, then say the values of
1 and 32769 (0x8001) written into the combined DLL and DLM register pair
both select the divisor of 1 and the baud rate of 115200bps.
[1] "FDC37M81x, PC98/99 Compliant Enhanced Super I/O Controller with
Keyboard/Mouse Wake-Up", Standard Microsystems Corporation, Rev.
03/27/2000, Section "Programmable Baud Rate Generator (and Divisor
Latches DLH, DLL)", p. 75
[2] same, Table 31 - "Baud Rates", p. 77
[3] same, Table 60 - "Serial Port 1, Logical Device 4 [Logical Device
Number = 0x04]", p. 153
[4] same, Table 61 - "Serial Port 2, Logical Device 5 [Logical Device
Number = 0x05]", p. 153
Signed-off-by: Maciej W. Rozycki <macro@orcam.me.uk>
Link: https://lore.kernel.org/r/alpine.DEB.2.21.2106092330530.5469@angie.orcam.me.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Oxford Semiconductor PCIe (Tornado) serial port devices are driven by a
fixed 62.5MHz clock input derived from the 100MHz PCI Express clock.
In the enhanced (650) mode, which we select in `autoconfig_has_efr' by
setting the ECB bit in the EFR register, and in the absence of clock
reconfiguration, which we currently don't do, the clock rate is divided
only by the oversampling rate of 16 as it is supplied to the baud rate
generator, yielding the baud base of 3906250. This comes from the reset
values of the TCR and MCR[7] registers which are both zero[1][2][3][4],
choosing the oversampling rate of 16 and the normal (divide by 1) baud
rate generator prescaler respectively. This is the rate that is divided
by the value held in the divisor latch to determine the baud rate used.
Replace the incorrect baud base of 4000000 with the right value of
3906250 then.
References:
[1] "OXPCIe200 PCI Express Multi-Port Bridge", Oxford Semiconductor,
Inc., DS-0045, 10 Nov 2008, Section "Reset Configuration", p. 72
[2] "OXPCIe952 PCI Express Bridge to Dual Serial & Parallel Port",
Oxford Semiconductor, Inc., DS-0046, Mar 06 08, Section "Reset
Configuration", p. 27
[3] "OXPCIe954 PCI Express Bridge to Quad Serial Port", Oxford
Semiconductor, Inc., DS-0047, Feb 08, Section "Reset Configuration",
p. 28
[4] "OXPCIe958 PCI Express Bridge to Octal Serial Port", Oxford
Semiconductor, Inc., DS-0048, Feb 08, Section "Reset Configuration",
p. 28
Fixes: 7106b4e333 ("8250: Oxford Semiconductor Devices")
Signed-off-by: Maciej W. Rozycki <macro@orcam.me.uk>
Link: https://lore.kernel.org/r/alpine.DEB.2.21.2106100203510.5469@angie.orcam.me.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
