Check if the pointer lcd->ops->init_display exists before dereferencing it.
If a driver called charlcd_init() without defining the ops, this would
return segmentation fault, as happened to me when implementing a charlcd
driver. Checking the pointer before dereferencing protects from
segmentation fault.
Signed-off-by: Luiz Sampaio <sampaio.ime@gmail.com>
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
Removing 'int' from 'unsigned long int' declaration, which is unnecessary.
Signed-off-by: Luiz Sampaio <sampaio.ime@gmail.com>
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
For structure initializers the fields are 0 (or NULL) by default, so
there is no need to fill them explicitly. Besides that, much easier
to read when initializers use C99 style. Hence, convert to C99 style
as well.
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Acked-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
charlcd_write() is invoked as a VFS->write() callback and as such it is
always invoked from preemptible context and may sleep.
charlcd_puts() is invoked from register/unregister callback which is
preemptible. The reboot notifier callback is also invoked from
preemptible context.
Therefore there is no need to use in_interrupt() to figure out if it
is safe to sleep because it always is. in_interrupt() and related
context checks are being removed from non-core code.
Using schedule() to schedule (and be friendly to others) is
discouraged and cond_resched() should be used instead.
Remove in_interrupt() and use cond_resched() to schedule every 32
iterations if needed.
Link: https://lkml.kernel.org/r/20200914204209.256266093@linutronix.de
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
[mo: fixed a couple typos in comment and commit message]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
Skip printing characters at the end of a display line. This fits to the
behaviour we already had, that the cursor is nailed to the last position
of a line.
This might slightly change behaviour.
On hd44780 displays with one or two lines the previous implementation
did still write characters to the buffer of the display even if they are
currently not visible. The shift_display command could be used to set
the "viewing window" to a new position in the buffer and then you could
see the characters previously written.
This described behaviour does not work for hd44780 displays with more
than two display lines. There simply is not enough buffer.
So the behaviour was a bit inconsistent across different displays.
The new behaviour is to stop writing characters at the end of a visible
line, even if there would be room in the buffer. This allows us to have
an easy implementation, that should behave equal on all supported
displays. This is not hd44780 hardware dependent anymore.
Reviewed-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Lars Poeschel <poeschel@lemonage.de>
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
Change the calling interface for gotoxy from supplying the x and y
coordinates in the charlcd struct to explicitly supplying x and y in
the function arguments. This is more intuitive and allows for moving
the cursor to positions independent from the position saved in the
charlcd struct.
Reviewed-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Lars Poeschel <poeschel@lemonage.de>
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
These are the last bits left in charlcd.c that are device specific and
they are removed now.
In detail this is:
* bwidth, which is the width of the display buffer per line. This is
replaced by width of the display.
* hwidth, which is the size of the display buffer as a whole. This is
replaced by looping all chars of a line by all lines.
* the hd44780_common header include can go away.
Reviewed-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Lars Poeschel <poeschel@lemonage.de>
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
We remove the hd44780_clear_fast (display) clear implementation. With
the new timeout the normal clear_display is reasonably fast. So there is
no need for a clear_fast anymore.
Link: https://lore.kernel.org/lkml/20200922092121.GG16421@1wt.eu/
Signed-off-by: Lars Poeschel <poeschel@lemonage.de>
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
This moves the call to charlcd_backlight from the end of the switch
into the actual case statement that originates the change of the
backlight. This is more consistent to what is now found in this switch.
Reviewed-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Lars Poeschel <poeschel@lemonage.de>
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
Take the code to redefine characters out of charlcd and move it to
hd44780_common, as this is hd44780 specific.
There is now a function hd44780_common_redefine_char that drivers use
and charlcd calls it through its ops function pointer.
Reviewed-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Lars Poeschel <poeschel@lemonage.de>
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
This cleans up now unnecessary hd44780 specific code from charlcd. We
obsoleted this with the last patch. So another chunk of hd44780 specific
code can be dropped from charlcd.
Reviewed-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Lars Poeschel <poeschel@lemonage.de>
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
This implements various hd44780_common_ functions for hd44780 compatible
display drivers to use. charlcd then calls these functions through its
ops function pointer.
The functions namely are:
- hd44780_common_shift_cursor
- hd44780_common_display_shift
- hd44780_common_display
- hd44780_common_cursor
- hd44780_common_blink
- hd44780_common_fontsize
- hd44780_common_lines
Reviewed-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Lars Poeschel <poeschel@lemonage.de>
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
The init_display function is moved over to hd44780_common. charlcd uses
it via its ops function pointer and drivers initialize the ops with the
common hd44780_common_init_display function.
Reviewed-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Lars Poeschel <poeschel@lemonage.de>
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
To turn the backlight on or off use our new enum CHARLCD_ON /
CHARLCD_OFF.
Reviewed-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Lars Poeschel <poeschel@lemonage.de>
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
hd44780_common wants to use the charlcd_backlight function, so make it
visible.
Reviewed-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Lars Poeschel <poeschel@lemonage.de>
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
This moves the clear_display function from charlcd to hd44780_common.
This is one more step to make charlcd independent from device specific
code. The two hd44780 drivers use the new function from hd44780_common
and charlcd calls this function through its function pointer in its ops
structure.
Reviewed-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Lars Poeschel <poeschel@lemonage.de>
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
This adds a home function to the charlcd_ops struct and offer an
implementation for hd44780_common. This implementation is used by our
two hd44780 drivers. This is to make charlcd device independent.
Reviewed-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Lars Poeschel <poeschel@lemonage.de>
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
Provide a hd44780_common_gotoxy function and a pointer in the ops for
charlcd to use to move the cursor.
Reviewed-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Lars Poeschel <poeschel@lemonage.de>
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
We create a hd44780_common_print function. It is derived from the
original charlcd_print. charlcd_print becomes a device independent print
function, that then only calls via its ops function pointers, into the
print function offered by drivers.
Reported-by: kernel test robot <lkp@intel.com>
Reviewed-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Lars Poeschel <poeschel@lemonage.de>
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
Move out the struct addr from struct charlcd_priv into the less private
struct charlcd. This member is used to pass position information. The
individual drivers need to be able to read this information, so we move
this out of charlcd_priv to charlcd structure.
Reviewed-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Lars Poeschel <poeschel@lemonage.de>
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
The write_cmd function is used to send commands to hd44780 displays.
The individual hd44780 drivers then implement their appropriate way of
doing this with their supported displays. So we move this pointer so
hd44780_common.
Reviewed-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Lars Poeschel <poeschel@lemonage.de>
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
This moves the write_data function pointer from struct charlcd_ops to
struct hd44780_common. This is the function that actually writes the
character to the display. This hd44780 hardware specific function is
used by two drivers at the moment.
Reviewed-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Lars Poeschel <poeschel@lemonage.de>
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
Move struct charlcd member ifwidth to our new struct hd44780_common.
ifwidth is hd44780 device specific and is used by two drivers at the
moment, so we move it to a common place, where both can use this.
Reviewed-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Lars Poeschel <poeschel@lemonage.de>
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
hwidth is for the hardware buffer size and bwidth is for the buffer
width of one single line. This is specific to the hd44780 displays and
so it is moved out from charlcd to struct hd44780_common.
Reviewed-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Lars Poeschel <poeschel@lemonage.de>
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
We use an enum for calling the functions in charlcd, that turn the
backlight on or off. This enum is generic and can be used for other
charlcd turn on / turn off operations as well.
Reviewed-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Lars Poeschel <poeschel@lemonage.de>
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
hex_to_bin() may be used to convert hexdecimal digit to its binary
representation.
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
HWRNG_MINOR and RNG_MISCDEV_MINOR are duplicate definitions, use
unified HWRNG_MINOR instead and moved into miscdevice.h
ANSLCD_MINOR and LCD_MINOR are duplicate definitions, use unified
LCD_MINOR instead and moved into miscdevice.h
MISCDEV_MINOR is renamed to PXA3XX_GCU_MINOR and moved into
miscdevice.h
Other definitions are just moved without any change.
Link: https://lore.kernel.org/lkml/20200120221323.GJ15860@mit.edu/t/
Suggested-by: Arnd Bergmann <arnd@arndb.de>
Build-tested-by: Willy TARREAU <wtarreau@haproxy.com>
Build-tested-by: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
Signed-off-by: Zhenzhong Duan <zhenzhong.duan@gmail.com>
Acked-by: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Link: https://lore.kernel.org/r/20200311071654.335-2-zhenzhong.duan@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The current codebase makes use of the zero-length array language
extension to the C90 standard, but the preferred mechanism to declare
variable-length types such as these ones is a flexible array member[1][2],
introduced in C99:
struct foo {
int stuff;
struct boo array[];
};
By making use of the mechanism above, we will get a compiler warning
in case the flexible array does not occur last in the structure, which
will help us prevent some kind of undefined behavior bugs from being
inadvertently introduced[3] to the codebase from now on.
Also, notice that, dynamic memory allocations won't be affected by
this change:
"Flexible array members have incomplete type, and so the sizeof operator
may not be applied. As a quirk of the original implementation of
zero-length arrays, sizeof evaluates to zero."[1]
This issue was found with the help of Coccinelle.
[1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html
[2] https://github.com/KSPP/linux/issues/21
[3] commit 7649773293 ("cxgb3/l2t: Fix undefined behaviour")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
Like in commit 8b2303de39 ("serial: core: Fix handling of options
after MMIO address") we may use simple_strtoul() which in comparison to
kstrtoul() can do conversion in-place without additional and unnecessary
code to be written.
Link: http://lkml.kernel.org/r/20190801192904.41087-2-andriy.shevchenko@linux.intel.com
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Petr Mladek <pmladek@suse.com>
Cc: Geert Uytterhoeven <geert+renesas@glider.be>
Cc: Mans Rullgard <mans@mansr.com>
Cc: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This header is included in drivers/auxdisplay/. Make it a local header.
Reviewed-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Signed-off-by: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
The charlcd driver currently flashes the backlight once on init.
This may not be desirable. Thus, add options for turning the
backlight off or on as well.
Signed-off-by: Mans Rullgard <mans@mansr.com>
Signed-off-by: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
If CONFIG_PANEL_CHANGE_MESSAGE is set, CONFIG_PANEL_BOOT_MESSAGE will
also be defined, so the double ifdef is pointless. Simplify the code
further by using an intermediate macro rather duplicating most of the
line.
Signed-off-by: Mans Rullgard <mans@mansr.com>
Signed-off-by: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
The charlcd_free() is a counterpart to charlcd_alloc()
and should be called symmetrically on tear down.
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
In order to be more particular in names, rename to_priv() macro
to charlcd_to_priv().
No functional change intended.
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
The x/y command parsing has been broken since commit 129957069e
("staging: panel: Fixed checkpatch warning about simple_strtoul()").
Commit b34050fadb ("auxdisplay: charlcd: Fix and clean up handling of
x/y commands") fixed some problems by rewriting the parsing code,
but also broke things further by removing the check for a complete
command before attempting to parse it. As a result, parsing is
terminated at the first x or y character.
This reinstates the check for a final semicolon. Whereas the original
code use strchr(), this is wasteful seeing as the semicolon is always
at the end of the buffer. Thus check this character directly instead.
Signed-off-by: Mans Rullgard <mans@mansr.com>
Signed-off-by: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
The function long_sleep() calls mdelay() when in an interrupt handler.
But only charlcd_clear_display() and charlcd_init_display calls
long_sleep(), and my tool finds that the two functions
are never called in an interrupt handler.
Thus mdelay() and in_interrupt() are not necessary.
This is found by a static analysis tool named DCNS written by myself.
Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Acked-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
The current version is not parsing multiple x/y commands as the code
originally intended. On top of that, kstrtoul() expects
NULL-terminated strings. Finally, the code does two passes over
the string.
Some explanations about the supported syntax are added as well.
Cc: Willy Tarreau <w@1wt.eu>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Andy Shevchenko <andy.shevchenko@gmail.com>
Cc: Robert Abel <rabel@robertabel.eu>
Signed-off-by: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
The graphics command expects 16 hexadecimal literals, but would allow
characters in range [0-9a-zA-Z] instead of [0-9a-fA-F].
Signed-off-by: Robert Abel <rabel@robertabel.eu>
Acked-by: Willy Tarreau <w@1wt.eu>
Reviewed-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
Signed-off-by: Robert Abel <rabel@robertabel.eu>
Reviewed-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
There is no need to resort to octal escape sequence for the form feed
character when an established escape sequence exists.
Signed-off-by: Robert Abel <rabel@robertabel.eu>
Signed-off-by: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
Using '\0' instead of plain 0 makes the intent clearer that this is
indeed a string and not a series of integers.
Signed-off-by: Robert Abel <rabel@robertabel.eu>
Signed-off-by: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
If the line extends beyond the width to the screen, nothing changes. The
existing code will call charlcd_gotoxy every time for this case.
Signed-off-by: Sean Young <sean@mess.org>
Reviewed-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
Commit f4757af ("staging: panel: Fix single-open policy race condition")
introduced in 3.19-rc1 attempted to fix a race condition on the open, but
failed to properly do it and used to exit without restoring the semaphore.
This results in -EBUSY being returned after the first open error until
the module is reloaded or the system restarted (ie: consecutive to a
dual open resulting in -EBUSY or to a permission error).
[ Note for stable maintainers: the code moved from drivers/misc/panel.c
to drivers/auxdisplay/{charlcd,panel}.c during 4.12. The patch easily
applies there (modulo the renamed atomic counter) but I can provide a
tested backport if desired. ]
Fixes: f4757af85 # 3.19-rc1
Cc: stable@vger.kernel.org
Cc: Mariusz Gorski <marius.gorski@gmail.com>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Miguel Ojeda Sandonis <miguel.ojeda.sandonis@gmail.com>
Signed-off-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
On displays with more than two lines, the additional lines are stored in
the buffers used for the first two lines, but beyond the visible parts.
Adjust the DDRAM address calculation to cater for this.
When clearing the display, avoid writing more spaces than the actual
size of the physical buffer.
Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
In 4-bit mode, 8-bit commands and data are written using two raw writes
to the data interface: high nibble first, low nibble last. This must be
handled by the low-level driver.
However, as we don't know in which mode (4-bit or 8-bit) nor 4-bit phase
the LCD was left, initialization must always be handled using raw
writes, and needs to configure the LCD for 8-bit mode first.
Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Extract the character LCD core from the Parallel port LCD/Keypad Panel
driver in the misc subsystem, and convert it into a subdriver in the
auxdisplay subsystem. This allows the character LCD core to be used by
other drivers later.
Compilation is controlled by its own Kconfig symbol CHARLCD, which is to
be selected by its users, but can be enabled manually for
compile-testing.
All functions changed their prefix from "lcd_" to "charlcd_", and gained
a "struct charlcd *" parameter to operate on a specific instance.
While the driver API thus is ready to support multiple instances, the
current limitation of a single display (/dev/lcd has a single misc minor
assigned) is retained.
No functional changes intended.
Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Luiz Sampaio