[PATCH 0/3] staging/fbtft: Minor cleanups.

[PATCH 0/3] staging/fbtft: Minor cleanups.

[Panagiotis Gravias]

Solved some style errors,
parenthesis spacing, aligning arguments, replacing udelay() with
usleep_range().

I hope this makes future checks with the style script cleaner and more
helpfull.

Panagiotis Gravias (3):
  staging/fbtft: Remove prohibited space before close parenthesis
  staging/fbtft: Align arguments to match open parenthesis
  staging: fbtft: Replace udelay with usleep_range

 drivers/staging/fbtft/fb_ra8875.c    |  4 ++--
 drivers/staging/fbtft/fb_tinylcd.c   |  2 +-
 drivers/staging/fbtft/fb_upd161704.c | 18 +++++++++---------
 drivers/staging/fbtft/fbtft-bus.c    |  4 ++--
 4 files changed, 14 insertions(+), 14 deletions(-)

-- 
2.55.0

[PATCH 1/3] staging/fbtft: Remove prohibited space before close parenthesis

[Panagiotis Gravias]

Fix checkpatch error: "space prohibited before that close parenthesis"
in the define_fbtft_write_reg macro.

Signed-off-by: Panagiotis Gravias <graviaspanagiotis1@gmail.com>
---
 drivers/staging/fbtft/fbtft-bus.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/staging/fbtft/fbtft-bus.c b/drivers/staging/fbtft/fbtft-bus.c
index 30e436ff19e4..38697992f5e1 100644
--- a/drivers/staging/fbtft/fbtft-bus.c
+++ b/drivers/staging/fbtft/fbtft-bus.c
@@ -62,9 +62,9 @@ out:									      \
 }                                                                             \
 EXPORT_SYMBOL(func);
 
-define_fbtft_write_reg(fbtft_write_reg8_bus8, u8, u8, )
+define_fbtft_write_reg(fbtft_write_reg8_bus8, u8, u8,)
 define_fbtft_write_reg(fbtft_write_reg16_bus8, __be16, u16, cpu_to_be16)
-define_fbtft_write_reg(fbtft_write_reg16_bus16, u16, u16, )
+define_fbtft_write_reg(fbtft_write_reg16_bus16, u16, u16,)
 
 void fbtft_write_reg8_bus9(struct fbtft_par *par, int len, ...)
 {
-- 
2.55.0

[PATCH 2/3] staging/fbtft: Align arguments to match open parenthesis

[Panagiotis Gravias]

Fix checkpatch warning for alignment in write_reg() call to match
the open parenthesis, improving code readability.

Signed-off-by: Panagiotis Gravias <graviaspanagiotis1@gmail.com>
---
 drivers/staging/fbtft/fb_tinylcd.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/staging/fbtft/fb_tinylcd.c b/drivers/staging/fbtft/fb_tinylcd.c
index afa8f1c740c5..d58b1247262b 100644
--- a/drivers/staging/fbtft/fb_tinylcd.c
+++ b/drivers/staging/fbtft/fb_tinylcd.c
@@ -38,7 +38,7 @@ static int init_display(struct fbtft_par *par)
 	write_reg(par, 0xE5, 0x00);
 	write_reg(par, 0xF0, 0x36, 0xA5, 0x53);
 	write_reg(par, 0xE0, 0x00, 0x35, 0x33, 0x00, 0x00, 0x00,
-		       0x00, 0x35, 0x33, 0x00, 0x00, 0x00);
+		  0x00, 0x35, 0x33, 0x00, 0x00, 0x00);
 	write_reg(par, MIPI_DCS_SET_PIXEL_FORMAT, 0x55);
 	write_reg(par, MIPI_DCS_EXIT_SLEEP_MODE);
 	fsleep(250);
-- 
2.55.0

[PATCH 3/3] staging: fbtft: Replace udelay with usleep_range

[Panagiotis Gravias]

Fix checkpatch warnings preferring usleep_range over udelay.
Replaced udelay() calls with usleep_range() providing a reasonable
upper bound to allow the scheduler to coalesce timer interrupts.

Signed-off-by: Panagiotis Gravias <graviaspanagiotis1@gmail.com>
---
 drivers/staging/fbtft/fb_ra8875.c    |  4 ++--
 drivers/staging/fbtft/fb_upd161704.c | 18 +++++++++---------
 2 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/drivers/staging/fbtft/fb_ra8875.c b/drivers/staging/fbtft/fb_ra8875.c
index 0ab1de6647d0..d2400bb44f1c 100644
--- a/drivers/staging/fbtft/fb_ra8875.c
+++ b/drivers/staging/fbtft/fb_ra8875.c
@@ -210,7 +210,7 @@ static void write_reg8_bus8(struct fbtft_par *par, int len, ...)
 	}
 	len--;
 
-	udelay(100);
+	usleep_range(100, 200);
 
 	if (len) {
 		buf = (u8 *)par->buf;
@@ -231,7 +231,7 @@ static void write_reg8_bus8(struct fbtft_par *par, int len, ...)
 
 	/* restore user spi-speed */
 	par->fbtftops.write = fbtft_write_spi;
-	udelay(100);
+	usleep_range(100, 200);
 }
 
 static int write_vmem16_bus8(struct fbtft_par *par, size_t offset, size_t len)
diff --git a/drivers/staging/fbtft/fb_upd161704.c b/drivers/staging/fbtft/fb_upd161704.c
index c680160d6380..e26766f58a50 100644
--- a/drivers/staging/fbtft/fb_upd161704.c
+++ b/drivers/staging/fbtft/fb_upd161704.c
@@ -32,27 +32,27 @@ static int init_display(struct fbtft_par *par)
 
 	/* oscillator start */
 	write_reg(par, 0x003A, 0x0001);	/*Oscillator 0: stop, 1: operation */
-	udelay(100);
+	usleep_range(100, 200);
 
 	/* y-setting */
 	write_reg(par, 0x0024, 0x007B);	/* amplitude setting */
-	udelay(10);
+	usleep_range(10, 20);
 	write_reg(par, 0x0025, 0x003B);	/* amplitude setting */
 	write_reg(par, 0x0026, 0x0034);	/* amplitude setting */
-	udelay(10);
+	usleep_range(10, 20);
 	write_reg(par, 0x0027, 0x0004);	/* amplitude setting */
 	write_reg(par, 0x0052, 0x0025);	/* circuit setting 1 */
-	udelay(10);
+	usleep_range(10, 20);
 	write_reg(par, 0x0053, 0x0033);	/* circuit setting 2 */
 	write_reg(par, 0x0061, 0x001C);	/* adjustment V10 positive polarity */
-	udelay(10);
+	usleep_range(10, 20);
 	write_reg(par, 0x0062, 0x002C);	/* adjustment V9 negative polarity */
 	write_reg(par, 0x0063, 0x0022);	/* adjustment V34 positive polarity */
-	udelay(10);
+	usleep_range(10, 20);
 	write_reg(par, 0x0064, 0x0027);	/* adjustment V31 negative polarity */
-	udelay(10);
+	usleep_range(10, 20);
 	write_reg(par, 0x0065, 0x0014);	/* adjustment V61 negative polarity */
-	udelay(10);
+	usleep_range(10, 20);
 	write_reg(par, 0x0066, 0x0010);	/* adjustment V61 negative polarity */
 
 	/* Basical clock for 1 line (BASECOUNT[7:0]) number specified */
@@ -60,7 +60,7 @@ static int init_display(struct fbtft_par *par)
 
 	/* Power supply setting */
 	write_reg(par, 0x0019, 0x0000);	/* DC/DC output setting */
-	udelay(200);
+	usleep_range(200, 300);
 	write_reg(par, 0x001A, 0x1000);	/* DC/DC frequency setting */
 	write_reg(par, 0x001B, 0x0023);	/* DC/DC rising setting */
 	write_reg(par, 0x001C, 0x0C01);	/* Regulator voltage setting */
-- 
2.55.0

Re: [PATCH 1/3] staging/fbtft: Remove prohibited space before close parenthesis

[Andy Shevchenko]

On Tue, Jul 14, 2026 at 10:09:40PM +0300, Panagiotis Gravias wrote:
> Fix checkpatch error: "space prohibited before that close parenthesis"
> in the define_fbtft_write_reg macro.

NAK.

-- 
With Best Regards,
Andy Shevchenko

Re: [PATCH 2/3] staging/fbtft: Align arguments to match open parenthesis

[Andy Shevchenko]

On Tue, Jul 14, 2026 at 10:09:41PM +0300, Panagiotis Gravias wrote:
> Fix checkpatch warning for alignment in write_reg() call to match
> the open parenthesis, improving code readability.

NAK.

-- 
With Best Regards,
Andy Shevchenko

Re: [PATCH 3/3] staging: fbtft: Replace udelay with usleep_range

[Andy Shevchenko]

On Tue, Jul 14, 2026 at 10:09:42PM +0300, Panagiotis Gravias wrote:
> Fix checkpatch warnings preferring usleep_range over udelay.
> Replaced udelay() calls with usleep_range() providing a reasonable
> upper bound to allow the scheduler to coalesce timer interrupts.

NAK.

-- 
With Best Regards,
Andy Shevchenko

Re: [PATCH 0/3] staging/fbtft: Minor cleanups.

[Andy Shevchenko]

On Tue, Jul 14, 2026 at 10:09:38PM +0300, Panagiotis Gravias wrote:
> Solved some style errors,
> parenthesis spacing, aligning arguments, replacing udelay() with
> usleep_range().
> 
> I hope this makes future checks with the style script cleaner and more
> helpfull.

To understand the resolution, read the mailing list archives for
the last ~6-9 months against this driver.

Also read and understand README in the folder of the driver.

-- 
With Best Regards,
Andy Shevchenko

Re: [PATCH 1/3] staging/fbtft: Remove prohibited space before close parenthesis

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:

Pre-existing issues:
- [High] Constructing and dereferencing unaligned 16-bit pointers causes undefined behavior and potential kernel panics on strict-alignment architectures.
- [High] Incorrect SPI buffer size calculation transmits uninitialized memory when multiple parameters are sent with `startbyte` enabled.
--

--- Patch [1]: [PATCH 1/3] staging/fbtft: Remove prohibited space before close parenthesis ---
commit b5aeca6fddf7088401c92f0dfc0d9c7d04fb863a
Author: Panagiotis Gravias <graviaspanagiotis1@gmail.com>

staging/fbtft: Remove prohibited space before close parenthesis

This commit cleans up a checkpatch error by removing a prohibited space
before the close parenthesis in the define_fbtft_write_reg macro
invocations.

> diff --git a/drivers/staging/fbtft/fbtft-bus.c b/drivers/staging/fbtft/fbtft-bus.c
> index 30e436ff19e4c..38697992f5e1b 100644
> --- a/drivers/staging/fbtft/fbtft-bus.c
> +++ b/drivers/staging/fbtft/fbtft-bus.c
> @@ -62,9 +62,9 @@ out:									      \
>  }                                                                             \
>  EXPORT_SYMBOL(func);
>  
> -define_fbtft_write_reg(fbtft_write_reg8_bus8, u8, u8, )
> +define_fbtft_write_reg(fbtft_write_reg8_bus8, u8, u8,)
>  define_fbtft_write_reg(fbtft_write_reg16_bus8, __be16, u16, cpu_to_be16)
> -define_fbtft_write_reg(fbtft_write_reg16_bus16, u16, u16, )
> +define_fbtft_write_reg(fbtft_write_reg16_bus16, u16, u16,)

[Severity: High]
This is a pre-existing issue, but does expanding this macro for 16-bit
types like fbtft_write_reg16_bus16 create an unaligned pointer dereference?

In the define_fbtft_write_reg() macro definition, when a startbyte is used:

	if (par->startbyte) {
		*(u8 *)par->buf = par->startbyte;
		buf = (buffer_type *)(par->buf + 1);
		offset = 1;
	}

The pointer is advanced by 1 byte. When buffer_type is a 16-bit type, this
creates an odd-aligned pointer. Later, the macro writes to it:

	*buf = modifier((data_type)va_arg(args, unsigned int));

This can cause unaligned memory access faults and lead to kernel panics on
strict-alignment architectures. This same pattern also appears in
fbtft_write_vmem16_bus8() where par->txbuf.buf + 1 is cast to a 16-bit
pointer.

[Severity: High]
This is also a pre-existing issue within the same macro, but could the
SPI buffer size calculation send uninitialized memory?

When sending multiple parameters with a startbyte active, the macro packs
exactly one start byte followed by the parameters. However, the transmission
size is calculated as:

	if (len) {
		...
		fbtft_write_buf_dc(par, par->buf,
				   len * (sizeof(data_type) + offset), 1);
	}

Because offset is 1, if len is greater than 1, this calculates to
len * sizeof(data_type) + len, instead of the actual payload size of
1 + len * sizeof(data_type). Could this force the SPI core to transmit extra
uninitialized out-of-bounds bytes and potentially corrupt the display
controller's initialization state?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260714190958.219437-2-graviaspanagiotis1@gmail.com?part=1

Re: [PATCH 3/3] staging: fbtft: Replace udelay with usleep_range

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:

Pre-existing issues:
- [High] If a SPI write fails in `write_reg8_bus8`, the function returns early without restoring `par->fbtftops.write` to its original value, permanently downgrading the SPI interface speed.
- [High] The `txbuf16` pointer in `write_vmem16_bus8` is assigned to an odd-aligned address, causing unaligned memory writes that can trigger a kernel panic on strict architectures.
--

--- Patch [3]: [PATCH 3/3] staging: fbtft: Replace udelay with usleep_range ---
commit 7f6e8faf1241a2de5c5b0d51aa0632d9694e2167
Author: Panagiotis Gravias <graviaspanagiotis1@gmail.com>

staging: fbtft: Replace udelay with usleep_range

This commit replaces calls to udelay() with usleep_range() in the fbtft 
driver. This addresses checkpatch warnings and provides an upper bound to 
allow the scheduler to coalesce timer interrupts.

> diff --git a/drivers/staging/fbtft/fb_ra8875.c b/drivers/staging/fbtft/fb_ra8875.c
> index 0ab1de6647d07..d2400bb44f1c6 100644
> --- a/drivers/staging/fbtft/fb_ra8875.c
> +++ b/drivers/staging/fbtft/fb_ra8875.c
[ ... ]
> @@ -231,7 +231,7 @@ static void write_reg8_bus8(struct fbtft_par *par, int len, ...)
>  
>  	/* restore user spi-speed */
>  	par->fbtftops.write = fbtft_write_spi;
> -	udelay(100);
> +	usleep_range(100, 200);
>  }

[Severity: High]
This isn't a bug introduced by this patch, but I noticed something about the
error handling in write_reg8_bus8() related to the SPI speed restore.

When par->fbtftops.write() fails earlier in this function, it returns 
immediately:

if (ret < 0) {
        va_end(args);
        dev_err(par->info->device, "write() failed and returned %dn", ret);
        return;
}

Does this leave par->fbtftops.write permanently assigned to the slow
write_spi function? It appears that if a register write fails, the driver
never restores the fast fbtft_write_spi pointer, which might severely impact
the performance of all future bulk video memory writes.

[Severity: High]
This is also a pre-existing issue, but looking at the neighboring 
write_vmem16_bus8() function in the same file:

write_vmem16_bus8() {
    ...
    txbuf16 = par->txbuf.buf + 1;
    ...
    for (i = 0; i < to_copy; i++)
        txbuf16[i] = cpu_to_be16(vmem16[i]);
}

Is there a risk of an alignment fault here? The txbuf16 pointer is assigned 
an odd-aligned address (buf + 1). On architectures that do not support 
unaligned memory access in hardware (which is common for systems with SPI 
displays), would these 16-bit writes trigger a kernel panic? Should this 
be using put_unaligned_be16() instead?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260714190958.219437-2-graviaspanagiotis1@gmail.com?part=3

Re: [PATCH 0/3] staging/fbtft: Minor cleanups.

[Dan Carpenter]

On Tue, Jul 14, 2026 at 10:09:38PM +0300, Panagiotis Gravias wrote:
> Solved some style errors,
> parenthesis spacing, aligning arguments, replacing udelay() with
> usleep_range().
> 
> I hope this makes future checks with the style script cleaner and more
> helpfull.
> 

With old code you should search lore for why it still exists.

regards,
dan carpenter