* [PATCH] Input: rmi4 - release F54 queue on video registration failure
From: Myeonghun Pak @ 2026-05-24 18:23 UTC (permalink / raw)
To: Dmitry Torokhov
Cc: linux-input, linux-kernel, Myeonghun Pak, stable, Ijae Kim
rmi_f54_probe() initializes the videobuf2 queue before registering the
video device. If video_register_device() fails, probe only unregisters
the V4L2 device and leaves the initialized queue unwound by neither
remove nor file release paths.
Release the queue before continuing through the existing probe error
path.
This issue was identified during our ongoing static-analysis research while
reviewing kernel code.
Fixes: 3a762dbd5347 ("[media] Input: synaptics-rmi4 - add support for F54 diagnostics")
Cc: stable@vger.kernel.org
Co-developed-by: Ijae Kim <ae878000@gmail.com>
Signed-off-by: Ijae Kim <ae878000@gmail.com>
Signed-off-by: Myeonghun Pak <mhun512@gmail.com>
---
drivers/input/rmi4/rmi_f54.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/input/rmi4/rmi_f54.c b/drivers/input/rmi4/rmi_f54.c
index 61909e1a39..fca7b9fec5 100644
--- a/drivers/input/rmi4/rmi_f54.c
+++ b/drivers/input/rmi4/rmi_f54.c
@@ -722,6 +722,7 @@ static int rmi_f54_probe(struct rmi_function *fn)
ret = video_register_device(&f54->vdev, VFL_TYPE_TOUCH, -1);
if (ret) {
dev_err(&fn->dev, "Unable to register video subdevice.");
+ vb2_queue_release(&f54->queue);
goto remove_v4l2;
}
--
2.47.1
^ permalink raw reply related
* Re: [PATCH] HID: wacom: stop hardware after post-start probe failures
From: sashiko-bot @ 2026-05-24 18:41 UTC (permalink / raw)
To: Myeonghun Pak; +Cc: dmitry.torokhov, linux-input
In-Reply-To: <20260524175552.1973-1-mhun512@gmail.com>
Thank you for your contribution! Sashiko AI review found 3 potential issue(s) to consider:
Pre-existing issues:
- [High] The error path in `wacom_parse_and_register()` fails to cancel asynchronous works and timers, leading to a Use-After-Free when the `wacom` structure is freed.
- [High] Dismantling software state before the hardware is stopped on failure paths creates race conditions with active interrupt handlers, leading to a NULL pointer dereference.
- [High] Releasing driver resources before stopping HID hardware in `wacom_wireless_work()` leads to a Use-After-Free on incoming events.
--
commit 6396bf377f7e81b67088a1a9500d030c3776a230
Author: Myeonghun Pak <mhun512@gmail.com>
HID: wacom: stop hardware after post-start probe failures
This commit modifies wacom_parse_and_register() to route post-hid_hw_start()
failures through hid_hw_stop() before releasing driver resources.
> diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c
> index a32320b351e3e..76dc833f5f2e9 100644
> --- a/drivers/hid/wacom_sys.c
> +++ b/drivers/hid/wacom_sys.c
[ ... ]
> @@ -2456,16 +2456,16 @@ static int wacom_parse_and_register(struct wacom *wacom, bool wireless)
>
> error = wacom_register_inputs(wacom);
> if (error)
> - goto fail;
> + goto fail_hw_stop;
[Severity: High]
This is a pre-existing issue, but does setting the input pointers to NULL
before stopping the hardware create a race condition?
When wacom_register_inputs() fails, its error path sets wacom_wac->pad_input
to NULL. However, because hid_hw_stop() hasn't been called yet, the
hardware can still generate interrupts:
wacom_parse_and_register()
wacom_register_inputs()
fail:
wacom_wac->pad_input = NULL;
return error;
goto fail_hw_stop;
If an interrupt arrives before hid_hw_stop() completes, will the interrupt
handler dereference the NULL pad_input pointer?
>
> if (wacom->wacom_wac.features.device_type & WACOM_DEVICETYPE_PAD) {
> error = wacom_initialize_leds(wacom);
> if (error)
> - goto fail;
> + goto fail_hw_stop;
>
> error = wacom_initialize_remotes(wacom);
> if (error)
> - goto fail;
> + goto fail_hw_stop;
> }
>
> if (!wireless) {
[ ... ]
> @@ -2496,6 +2496,7 @@ static int wacom_parse_and_register(struct wacom *wacom, bool wireless)
> return 0;
>
> fail_quirks:
> +fail_hw_stop:
> hid_hw_stop(hdev);
[Severity: High]
This is a pre-existing issue, but does this error path leave pending
asynchronous works and timers running?
While hid_hw_stop() stops new interrupts from the hardware, works like
wireless_work, battery_work, remote_work, or timers that were already
scheduled while the hardware was active might still be pending.
Because wacom_probe() will propagate this error and trigger devres cleanup
to free the wacom structure, could these pending works execute later and
attempt to dereference the freed wacom pointer?
> fail:
> wacom_release_resources(wacom);
[Severity: High]
This is a pre-existing issue, but does releasing resources before
stopping the hardware in other code paths create a similar race
condition?
For example, in wacom_wireless_work(), wacom_release_resources() is
called before stopping the HID hardware. This frees resources like
pen_fifo via devres_release_group().
If an incoming HID report arrives after devres_release_group() but
before the hardware is stopped, could wacom_raw_event() attempt to
push data to the freed pen_fifo via wacom_wac_queue_insert(), causing
a use-after-free?
> return error;
> }
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260524175552.1973-1-mhun512@gmail.com?part=1
^ permalink raw reply
* Re: [PATCH] Input: rmi4 - release F54 queue on video registration failure
From: sashiko-bot @ 2026-05-24 18:59 UTC (permalink / raw)
To: Myeonghun Pak; +Cc: dmitry.torokhov, linux-input
In-Reply-To: <20260524182351.27658-1-mhun512@gmail.com>
Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
Pre-existing issues:
- [High] Embedding `struct video_device` and `struct vb2_queue` inside a devm-managed structure causes a Use-After-Free if the device node is held open after unbind.
- [High] `destroy_workqueue()` is called in `rmi_f54_remove()` without first canceling the delayed work, risking a Use-After-Free.
--
commit f89d07a2e226d7667f0c3e90fb7262a70db54401
Author: Myeonghun Pak <mhun512@gmail.com>
Input: rmi4 - release F54 queue on video registration failure
rmi_f54_probe() initializes the videobuf2 queue before registering the
video device. If video_register_device() fails, probe only unregisters
the V4L2 device and leaves the initialized queue unwound.
> diff --git a/drivers/input/rmi4/rmi_f54.c b/drivers/input/rmi4/rmi_f54.c
> index ac4041a69fcd3..d35b5164b170a 100644
> --- a/drivers/input/rmi4/rmi_f54.c
> +++ b/drivers/input/rmi4/rmi_f54.c
> @@ -722,6 +722,7 @@ static int rmi_f54_probe(struct rmi_function *fn)
> ret = video_register_device(&f54->vdev, VFL_TYPE_TOUCH, -1);
> if (ret) {
> dev_err(&fn->dev, "Unable to register video subdevice.");
> + vb2_queue_release(&f54->queue);
[Severity: High]
This isn't a bug introduced by this patch, but does embedding struct
video_device and struct vb2_queue inside the devm-managed f54_data
structure cause a use-after-free if the device node is held open after
unbind?
In rmi_f54_remove(), video_unregister_device(&f54->vdev) is called, which
clears the registered flag and drops one reference to vdev. However, if a
userspace process still has the character device open, the V4L2 core has
elevated the vdev refcount.
When rmi_f54_remove() returns, f54_data is immediately freed by devres,
even though vdev still has active references. When userspace later closes
the file descriptor, v4l2_release() calls the driver's .release operation,
which dereferences the already-freed vdev and vdev->queue.
> goto remove_v4l2;
> }
[Severity: High]
This is a pre-existing issue, but is there also a use-after-free risk in
rmi_f54_remove() regarding the delayed work?
destroy_workqueue(f54->workqueue) is called in rmi_f54_remove() without
first calling cancel_delayed_work_sync(&f54->work).
destroy_workqueue() drains pending work but does not cancel or wait for
non-pending delayed_work that is only linked on the timer side. After
rmi_f54_remove() completes, f54_data is freed by devres.
When the pending timer subsequently expires, it will attempt to access the
freed f54->work structure and schedule work on the destroyed workqueue.
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260524182351.27658-1-mhun512@gmail.com?part=1
^ permalink raw reply
* [PATCH v4 00/36] HID: iio: basic clean up and introduce devm_ API for HID sensors
From: Sanjay Chitroda @ 2026-05-24 19:20 UTC (permalink / raw)
To: jikos, jic23, srinivas.pandruvada
Cc: dlechner, nuno.sa, andy, sanjayembeddedse, sakari.ailus,
linux-input, linux-iio, linux-kernel
From: Sanjay Chitroda <sanjayembeddedse@gmail.com>
Key highlights:
- 0000-0024: General cleanup and kernel few coding style fixes across HID IIO drivers
- 0025: Remove unused iio_dev argument from HID IIO sensor helper
- 0026: Introduce devm_hid_sensor_setup_trigger() device-managed API
- 0027-0036: Convert HID IIO sensor drivers to use the new devm-based trigger setup
changes in v4:
- Extend the series to cover remaining HID IIO drivers with devm API usage
- Reorder patches to place cleanup and warning fix at beginning and,
devm-related changes toward the end based on feedback from David
- v3 series -> https://lore.kernel.org/all/20260509101040.791404-1-sanjayembedded@gmail.com/
changes in v3:
- Added cleanup and prepratory changes before adding devm_ API
conversion based on self review: 0002, 0004, 0006, 0007 and 0008
- Address andy's review comment on commit message and coding style
- v2 series -> https://lore.kernel.org/all/20260429175918.2541914-1-sanjayembedded@gmail.com/
changes in v2:
- Following input from Jonathan and Andy, squash initial patch v1
series in single change as individual change should not break anything
- Add devm API support and two driver using the same
- v1 series -> https://lore.kernel.org/all/20260428071613.1134053-1-sanjayembedded@gmail.com/
Testing:
- Compiled with W=1 for each patch in series
- Build-tested on QEMU x86_64
P.S.
- Sashiko reported an issue in a different driver and noted that it is not
introduced by this series. I have taken this feedback into account and
will address the actual issue in a separate series focus on that driver.
- Once this series is merged into the IIO tree, a number of HID IIO
drivers will become available to fully converted to devm API usage.
- The changes are organized across drivers to keep similar modifications
grouped together for consistency, making the series easier to review,
rather than grouping all changes per driver.
Thanks,
Sanjay Chitroda
Sanjay Chitroda (36):
iio: hid-sensors: add missing blank line after declarations
iio: gyro: hid-sensor-gyro-3d: use u32 instead of unsigned
iio: accel: hid-sensor-accel-3d: use u32 instead of unsigned
iio: light: hid-sensor-als: use u32 instead of unsigned
iio: light: hid-sensor-prox: use u32 instead of unsigned
iio: orientation: hid-sensor-incl-3d: use u32 instead of unsigned
iio: orientation: hid-sensor-rotation: use u32 instead of unsigned
iio: pressure: hid-sensor-press: use u32 instead of unsigned
iio: humidity: hid-sensor-humidity: align parenthesis for readability
iio: gyro: hid-sensor-gyro-3d: align parenthesis for readability
iio: magnetometer: hid-sensor-magn-3d: align parenthesis for
readability
iio: humidity: hid-sensor-humidity: use common device for devres
iio: position: hid-sensor-custom-intel-hinge: use common device for
devres
iio: temperature: hid-sensor-temperature: use common device for devres
iio: humidity: hid-sensor-humidity: use local struct device
iio: gyro: hid-sensor-gyro-3d: use local struct device
iio: accel: hid-sensor-accel-3d: use local struct device
iio: light: hid-sensor-als: use local struct device
iio: light: hid-sensor-prox: use local struct device
iio: magnetometer: hid-sensor-magn-3d: use local struct device
iio: orientation: hid-sensor-incl-3d: use local struct device
iio: orientation: hid-sensor-rotation: use local struct device
iio: position: hid-sensor-custom-intel-hinge: use local struct device
iio: pressure: hid-sensor-press: use local struct device
iio: hid-sensors: remove unused iio_dev argument
iio: hid-sensors: introduce device managed API
iio: gyro: hid-sensor-gyro-3d: drop hid_sensor_remove_trigger() using
devm API
iio: humidity: hid-sensor-humidity: drop hid_sensor_remove_trigger()
using devm API
iio: light: hid-sensor-prox: drop hid_sensor_remove_trigger() using
devm API
iio: light: hid-sensor-als: drop hid_sensor_remove_trigger() using
devm API
iio: magnetometer: hid-sensor-magn-3d: drop
hid_sensor_remove_trigger() using devm API
iio: orientation: hid-sensor-incl-3d: drop hid_sensor_remove_trigger()
using devm API
iio: orientation: hid-sensor-rotation: drop
hid_sensor_remove_trigger() using devm API
iio: position: hid-sensor-custom-intel-hinge: drop
hid_sensor_remove_trigger() using devm API
iio: pressure: hid-sensor-press: drop hid_sensor_remove_trigger()
using devm API
iio: temperature: hid-sensor-temperature: drop
hid_sensor_remove_trigger() using devm API
drivers/iio/accel/hid-sensor-accel-3d.c | 30 ++---
.../common/hid-sensors/hid-sensor-trigger.c | 24 +++-
.../common/hid-sensors/hid-sensor-trigger.h | 5 +-
drivers/iio/gyro/hid-sensor-gyro-3d.c | 96 ++++++++-------
drivers/iio/humidity/hid-sensor-humidity.c | 61 +++++-----
drivers/iio/light/hid-sensor-als.c | 31 +++--
drivers/iio/light/hid-sensor-prox.c | 30 ++---
drivers/iio/magnetometer/hid-sensor-magn-3d.c | 112 +++++++++---------
drivers/iio/orientation/hid-sensor-incl-3d.c | 36 +++---
drivers/iio/orientation/hid-sensor-rotation.c | 38 +++---
.../position/hid-sensor-custom-intel-hinge.c | 27 ++---
drivers/iio/pressure/hid-sensor-press.c | 36 +++---
.../iio/temperature/hid-sensor-temperature.c | 15 +--
13 files changed, 264 insertions(+), 277 deletions(-)
base-commit: 08297ca8422541dde6c8b7e6b1d68bd4aa4568ef
--
2.34.1
^ permalink raw reply
* [PATCH v4 01/36] iio: hid-sensors: add missing blank line after declarations
From: Sanjay Chitroda @ 2026-05-24 19:20 UTC (permalink / raw)
To: jikos, jic23, srinivas.pandruvada
Cc: dlechner, nuno.sa, andy, sanjayembeddedse, sakari.ailus,
linux-input, linux-iio, linux-kernel
In-Reply-To: <20260524192059.1193716-1-sanjayembedded@gmail.com>
From: Sanjay Chitroda <sanjayembeddedse@gmail.com>
Add a blank line after variable declarations to improve
readability and align with kernel coding style.
Signed-off-by: Sanjay Chitroda <sanjayembeddedse@gmail.com>
---
Changes in v4:
- Rectify commit message with input from David
---
drivers/iio/common/hid-sensors/hid-sensor-trigger.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/iio/common/hid-sensors/hid-sensor-trigger.c b/drivers/iio/common/hid-sensors/hid-sensor-trigger.c
index 417c4ab8c1b2..c8ccf96f3d03 100644
--- a/drivers/iio/common/hid-sensors/hid-sensor-trigger.c
+++ b/drivers/iio/common/hid-sensors/hid-sensor-trigger.c
@@ -314,7 +314,9 @@ static int __maybe_unused hid_sensor_resume(struct device *dev)
{
struct iio_dev *indio_dev = dev_get_drvdata(dev);
struct hid_sensor_common *attrb = iio_device_get_drvdata(indio_dev);
+
schedule_work(&attrb->work);
+
return 0;
}
@@ -322,6 +324,7 @@ static int __maybe_unused hid_sensor_runtime_resume(struct device *dev)
{
struct iio_dev *indio_dev = dev_get_drvdata(dev);
struct hid_sensor_common *attrb = iio_device_get_drvdata(indio_dev);
+
return _hid_sensor_power_state(attrb, true);
}
--
2.34.1
^ permalink raw reply related
* [PATCH v4 02/36] iio: gyro: hid-sensor-gyro-3d: use u32 instead of unsigned
From: Sanjay Chitroda @ 2026-05-24 19:20 UTC (permalink / raw)
To: jikos, jic23, srinivas.pandruvada
Cc: dlechner, nuno.sa, andy, sanjayembeddedse, sakari.ailus,
linux-input, linux-iio, linux-kernel
In-Reply-To: <20260524192059.1193716-1-sanjayembedded@gmail.com>
From: Sanjay Chitroda <sanjayembeddedse@gmail.com>
Prefer 'u32' instead of bare 'unsigned' variable to improve code
clarity and consistency with kernel style.
Signed-off-by: Sanjay Chitroda <sanjayembeddedse@gmail.com>
---
Changes in v4:
- Use 'u32' instead of 'unsigned int' as driver is already uses that and respective prototype has same data type with input from David and Andy
- Link to v3 -> https://lore.kernel.org/all/20260509101040.791404-5-sanjayembedded@gmail.com/
---
drivers/iio/gyro/hid-sensor-gyro-3d.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/iio/gyro/hid-sensor-gyro-3d.c b/drivers/iio/gyro/hid-sensor-gyro-3d.c
index c340cc899a7c..020812639947 100644
--- a/drivers/iio/gyro/hid-sensor-gyro-3d.c
+++ b/drivers/iio/gyro/hid-sensor-gyro-3d.c
@@ -187,7 +187,7 @@ static const struct iio_info gyro_3d_info = {
/* Callback handler to send event after all samples are received and captured */
static int gyro_3d_proc_event(struct hid_sensor_hub_device *hsdev,
- unsigned usage_id,
+ u32 usage_id,
void *priv)
{
struct iio_dev *indio_dev = platform_get_drvdata(priv);
@@ -209,7 +209,7 @@ static int gyro_3d_proc_event(struct hid_sensor_hub_device *hsdev,
/* Capture samples in local storage */
static int gyro_3d_capture_sample(struct hid_sensor_hub_device *hsdev,
- unsigned usage_id,
+ u32 usage_id,
size_t raw_len, char *raw_data,
void *priv)
{
@@ -244,7 +244,7 @@ static int gyro_3d_capture_sample(struct hid_sensor_hub_device *hsdev,
static int gyro_3d_parse_report(struct platform_device *pdev,
struct hid_sensor_hub_device *hsdev,
struct iio_chan_spec *channels,
- unsigned usage_id,
+ u32 usage_id,
struct gyro_3d_state *st)
{
int ret;
--
2.34.1
^ permalink raw reply related
* [PATCH v4 03/36] iio: accel: hid-sensor-accel-3d: use u32 instead of unsigned
From: Sanjay Chitroda @ 2026-05-24 19:20 UTC (permalink / raw)
To: jikos, jic23, srinivas.pandruvada
Cc: dlechner, nuno.sa, andy, sanjayembeddedse, sakari.ailus,
linux-input, linux-iio, linux-kernel
In-Reply-To: <20260524192059.1193716-1-sanjayembedded@gmail.com>
From: Sanjay Chitroda <sanjayembeddedse@gmail.com>
Prefer 'u32' instead of bare 'unsigned' variable to improve code
clarity and consistency with kernel style.
Signed-off-by: Sanjay Chitroda <sanjayembeddedse@gmail.com>
---
drivers/iio/accel/hid-sensor-accel-3d.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/iio/accel/hid-sensor-accel-3d.c b/drivers/iio/accel/hid-sensor-accel-3d.c
index 2ff591b3458f..67fb8efd6b10 100644
--- a/drivers/iio/accel/hid-sensor-accel-3d.c
+++ b/drivers/iio/accel/hid-sensor-accel-3d.c
@@ -233,7 +233,7 @@ static void hid_sensor_push_data(struct iio_dev *indio_dev, void *data,
/* Callback handler to send event after all samples are received and captured */
static int accel_3d_proc_event(struct hid_sensor_hub_device *hsdev,
- unsigned usage_id,
+ u32 usage_id,
void *priv)
{
struct iio_dev *indio_dev = platform_get_drvdata(priv);
@@ -257,7 +257,7 @@ static int accel_3d_proc_event(struct hid_sensor_hub_device *hsdev,
/* Capture samples in local storage */
static int accel_3d_capture_sample(struct hid_sensor_hub_device *hsdev,
- unsigned usage_id,
+ u32 usage_id,
size_t raw_len, char *raw_data,
void *priv)
{
@@ -293,7 +293,7 @@ static int accel_3d_capture_sample(struct hid_sensor_hub_device *hsdev,
static int accel_3d_parse_report(struct platform_device *pdev,
struct hid_sensor_hub_device *hsdev,
struct iio_chan_spec *channels,
- unsigned usage_id,
+ u32 usage_id,
struct accel_3d_state *st)
{
int ret;
--
2.34.1
^ permalink raw reply related
* [PATCH v4 04/36] iio: light: hid-sensor-als: use u32 instead of unsigned
From: Sanjay Chitroda @ 2026-05-24 19:20 UTC (permalink / raw)
To: jikos, jic23, srinivas.pandruvada
Cc: dlechner, nuno.sa, andy, sanjayembeddedse, sakari.ailus,
linux-input, linux-iio, linux-kernel
In-Reply-To: <20260524192059.1193716-1-sanjayembedded@gmail.com>
From: Sanjay Chitroda <sanjayembeddedse@gmail.com>
Prefer 'u32' instead of bare 'unsigned' variable to improve code
clarity and consistency with kernel style.
Signed-off-by: Sanjay Chitroda <sanjayembeddedse@gmail.com>
---
drivers/iio/light/hid-sensor-als.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/iio/light/hid-sensor-als.c b/drivers/iio/light/hid-sensor-als.c
index 384572844162..ac654b2bbc1b 100644
--- a/drivers/iio/light/hid-sensor-als.c
+++ b/drivers/iio/light/hid-sensor-als.c
@@ -251,7 +251,7 @@ static const struct iio_info als_info = {
/* Callback handler to send event after all samples are received and captured */
static int als_proc_event(struct hid_sensor_hub_device *hsdev,
- unsigned usage_id,
+ u32 usage_id,
void *priv)
{
struct iio_dev *indio_dev = platform_get_drvdata(priv);
@@ -273,7 +273,7 @@ static int als_proc_event(struct hid_sensor_hub_device *hsdev,
/* Capture samples in local storage */
static int als_capture_sample(struct hid_sensor_hub_device *hsdev,
- unsigned usage_id,
+ u32 usage_id,
size_t raw_len, char *raw_data,
void *priv)
{
@@ -315,7 +315,7 @@ static int als_capture_sample(struct hid_sensor_hub_device *hsdev,
/* Parse report which is specific to an usage id*/
static int als_parse_report(struct platform_device *pdev,
struct hid_sensor_hub_device *hsdev,
- unsigned usage_id,
+ u32 usage_id,
struct als_state *st)
{
struct iio_chan_spec *channels;
--
2.34.1
^ permalink raw reply related
* [PATCH v4 05/36] iio: light: hid-sensor-prox: use u32 instead of unsigned
From: Sanjay Chitroda @ 2026-05-24 19:20 UTC (permalink / raw)
To: jikos, jic23, srinivas.pandruvada
Cc: dlechner, nuno.sa, andy, sanjayembeddedse, sakari.ailus,
linux-input, linux-iio, linux-kernel
In-Reply-To: <20260524192059.1193716-1-sanjayembedded@gmail.com>
From: Sanjay Chitroda <sanjayembeddedse@gmail.com>
Prefer 'u32' instead of bare 'unsigned' variable to improve code
clarity and consistency with kernel style.
Signed-off-by: Sanjay Chitroda <sanjayembeddedse@gmail.com>
---
drivers/iio/light/hid-sensor-prox.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/iio/light/hid-sensor-prox.c b/drivers/iio/light/hid-sensor-prox.c
index efa904a70d0e..ac55808f161b 100644
--- a/drivers/iio/light/hid-sensor-prox.c
+++ b/drivers/iio/light/hid-sensor-prox.c
@@ -176,7 +176,7 @@ static const struct iio_info prox_info = {
/* Callback handler to send event after all samples are received and captured */
static int prox_proc_event(struct hid_sensor_hub_device *hsdev,
- unsigned usage_id,
+ u32 usage_id,
void *priv)
{
struct iio_dev *indio_dev = platform_get_drvdata(priv);
@@ -193,7 +193,7 @@ static int prox_proc_event(struct hid_sensor_hub_device *hsdev,
/* Capture samples in local storage */
static int prox_capture_sample(struct hid_sensor_hub_device *hsdev,
- unsigned usage_id,
+ u32 usage_id,
size_t raw_len, char *raw_data,
void *priv)
{
--
2.34.1
^ permalink raw reply related
* [PATCH v4 06/36] iio: orientation: hid-sensor-incl-3d: use u32 instead of unsigned
From: Sanjay Chitroda @ 2026-05-24 19:20 UTC (permalink / raw)
To: jikos, jic23, srinivas.pandruvada
Cc: dlechner, nuno.sa, andy, sanjayembeddedse, sakari.ailus,
linux-input, linux-iio, linux-kernel
In-Reply-To: <20260524192059.1193716-1-sanjayembedded@gmail.com>
From: Sanjay Chitroda <sanjayembeddedse@gmail.com>
Prefer 'u32' instead of bare 'unsigned' variable to improve code
clarity and consistency with kernel style.
Signed-off-by: Sanjay Chitroda <sanjayembeddedse@gmail.com>
---
drivers/iio/orientation/hid-sensor-incl-3d.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/iio/orientation/hid-sensor-incl-3d.c b/drivers/iio/orientation/hid-sensor-incl-3d.c
index 4e23a598a3fb..c7fbff498be7 100644
--- a/drivers/iio/orientation/hid-sensor-incl-3d.c
+++ b/drivers/iio/orientation/hid-sensor-incl-3d.c
@@ -189,7 +189,7 @@ static const struct iio_info incl_3d_info = {
/* Callback handler to send event after all samples are received and captured */
static int incl_3d_proc_event(struct hid_sensor_hub_device *hsdev,
- unsigned usage_id,
+ u32 usage_id,
void *priv)
{
struct iio_dev *indio_dev = platform_get_drvdata(priv);
@@ -212,7 +212,7 @@ static int incl_3d_proc_event(struct hid_sensor_hub_device *hsdev,
/* Capture samples in local storage */
static int incl_3d_capture_sample(struct hid_sensor_hub_device *hsdev,
- unsigned usage_id,
+ u32 usage_id,
size_t raw_len, char *raw_data,
void *priv)
{
@@ -247,7 +247,7 @@ static int incl_3d_capture_sample(struct hid_sensor_hub_device *hsdev,
static int incl_3d_parse_report(struct platform_device *pdev,
struct hid_sensor_hub_device *hsdev,
struct iio_chan_spec *channels,
- unsigned usage_id,
+ u32 usage_id,
struct incl_3d_state *st)
{
int ret;
--
2.34.1
^ permalink raw reply related
* [PATCH v4 07/36] iio: orientation: hid-sensor-rotation: use u32 instead of unsigned
From: Sanjay Chitroda @ 2026-05-24 19:20 UTC (permalink / raw)
To: jikos, jic23, srinivas.pandruvada
Cc: dlechner, nuno.sa, andy, sanjayembeddedse, sakari.ailus,
linux-input, linux-iio, linux-kernel
In-Reply-To: <20260524192059.1193716-1-sanjayembedded@gmail.com>
From: Sanjay Chitroda <sanjayembeddedse@gmail.com>
Prefer 'u32' instead of bare 'unsigned' variable to improve code
clarity and consistency with kernel style.
Signed-off-by: Sanjay Chitroda <sanjayembeddedse@gmail.com>
---
drivers/iio/orientation/hid-sensor-rotation.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/iio/orientation/hid-sensor-rotation.c b/drivers/iio/orientation/hid-sensor-rotation.c
index 4a11e4555099..20563d8efaf6 100644
--- a/drivers/iio/orientation/hid-sensor-rotation.c
+++ b/drivers/iio/orientation/hid-sensor-rotation.c
@@ -176,7 +176,7 @@ static const struct iio_info dev_rot_info = {
/* Callback handler to send event after all samples are received and captured */
static int dev_rot_proc_event(struct hid_sensor_hub_device *hsdev,
- unsigned usage_id,
+ u32 usage_id,
void *priv)
{
struct iio_dev *indio_dev = platform_get_drvdata(priv);
@@ -209,7 +209,7 @@ static int dev_rot_proc_event(struct hid_sensor_hub_device *hsdev,
/* Capture samples in local storage */
static int dev_rot_capture_sample(struct hid_sensor_hub_device *hsdev,
- unsigned usage_id,
+ u32 usage_id,
size_t raw_len, char *raw_data,
void *priv)
{
@@ -240,7 +240,7 @@ static int dev_rot_capture_sample(struct hid_sensor_hub_device *hsdev,
/* Parse report which is specific to an usage id*/
static int dev_rot_parse_report(struct platform_device *pdev,
struct hid_sensor_hub_device *hsdev,
- unsigned usage_id,
+ u32 usage_id,
struct dev_rot_state *st)
{
int ret;
--
2.34.1
^ permalink raw reply related
* [PATCH v4 08/36] iio: pressure: hid-sensor-press: use u32 instead of unsigned
From: Sanjay Chitroda @ 2026-05-24 19:20 UTC (permalink / raw)
To: jikos, jic23, srinivas.pandruvada
Cc: dlechner, nuno.sa, andy, sanjayembeddedse, sakari.ailus,
linux-input, linux-iio, linux-kernel
In-Reply-To: <20260524192059.1193716-1-sanjayembedded@gmail.com>
From: Sanjay Chitroda <sanjayembeddedse@gmail.com>
Prefer 'u32' instead of bare 'unsigned' variable to improve code
clarity and consistency with kernel style.
Signed-off-by: Sanjay Chitroda <sanjayembeddedse@gmail.com>
---
drivers/iio/pressure/hid-sensor-press.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/iio/pressure/hid-sensor-press.c b/drivers/iio/pressure/hid-sensor-press.c
index 5f1d6abda3e4..a5db5220d3d5 100644
--- a/drivers/iio/pressure/hid-sensor-press.c
+++ b/drivers/iio/pressure/hid-sensor-press.c
@@ -165,7 +165,7 @@ static const struct iio_info press_info = {
/* Callback handler to send event after all samples are received and captured */
static int press_proc_event(struct hid_sensor_hub_device *hsdev,
- unsigned usage_id,
+ u32 usage_id,
void *priv)
{
struct iio_dev *indio_dev = platform_get_drvdata(priv);
@@ -186,7 +186,7 @@ static int press_proc_event(struct hid_sensor_hub_device *hsdev,
/* Capture samples in local storage */
static int press_capture_sample(struct hid_sensor_hub_device *hsdev,
- unsigned usage_id,
+ u32 usage_id,
size_t raw_len, char *raw_data,
void *priv)
{
@@ -214,7 +214,7 @@ static int press_capture_sample(struct hid_sensor_hub_device *hsdev,
static int press_parse_report(struct platform_device *pdev,
struct hid_sensor_hub_device *hsdev,
struct iio_chan_spec *channels,
- unsigned usage_id,
+ u32 usage_id,
struct press_state *st)
{
int ret;
--
2.34.1
^ permalink raw reply related
* [PATCH v4 09/36] iio: humidity: hid-sensor-humidity: align parenthesis for readability
From: Sanjay Chitroda @ 2026-05-24 19:20 UTC (permalink / raw)
To: jikos, jic23, srinivas.pandruvada
Cc: dlechner, nuno.sa, andy, sanjayembeddedse, sakari.ailus,
linux-input, linux-iio, linux-kernel
In-Reply-To: <20260524192059.1193716-1-sanjayembedded@gmail.com>
From: Sanjay Chitroda <sanjayembeddedse@gmail.com>
Adjust alignment of parentheses to improve readability and
maintain consistency with kernel coding style
Signed-off-by: Sanjay Chitroda <sanjayembeddedse@gmail.com>
---
drivers/iio/humidity/hid-sensor-humidity.c | 46 +++++++++++-----------
1 file changed, 23 insertions(+), 23 deletions(-)
diff --git a/drivers/iio/humidity/hid-sensor-humidity.c b/drivers/iio/humidity/hid-sensor-humidity.c
index be2338d5f407..6fed019f4099 100644
--- a/drivers/iio/humidity/hid-sensor-humidity.c
+++ b/drivers/iio/humidity/hid-sensor-humidity.c
@@ -45,7 +45,7 @@ static const struct iio_chan_spec humidity_channels[] = {
/* Adjust channel real bits based on report descriptor */
static void humidity_adjust_channel_bit_mask(struct iio_chan_spec *channels,
- int channel, int size)
+ int channel, int size)
{
channels[channel].scan_type.sign = 's';
/* Real storage bits will change based on the report desc. */
@@ -55,8 +55,8 @@ static void humidity_adjust_channel_bit_mask(struct iio_chan_spec *channels,
}
static int humidity_read_raw(struct iio_dev *indio_dev,
- struct iio_chan_spec const *chan,
- int *val, int *val2, long mask)
+ struct iio_chan_spec const *chan,
+ int *val, int *val2, long mask)
{
struct hid_humidity_state *humid_st = iio_priv(indio_dev);
@@ -101,8 +101,8 @@ static int humidity_read_raw(struct iio_dev *indio_dev,
}
static int humidity_write_raw(struct iio_dev *indio_dev,
- struct iio_chan_spec const *chan,
- int val, int val2, long mask)
+ struct iio_chan_spec const *chan,
+ int val, int val2, long mask)
{
struct hid_humidity_state *humid_st = iio_priv(indio_dev);
@@ -127,7 +127,7 @@ static const struct iio_info humidity_info = {
/* Callback handler to send event after all samples are received and captured */
static int humidity_proc_event(struct hid_sensor_hub_device *hsdev,
- unsigned int usage_id, void *pdev)
+ unsigned int usage_id, void *pdev)
{
struct iio_dev *indio_dev = platform_get_drvdata(pdev);
struct hid_humidity_state *humid_st = iio_priv(indio_dev);
@@ -141,8 +141,8 @@ static int humidity_proc_event(struct hid_sensor_hub_device *hsdev,
/* Capture samples in local storage */
static int humidity_capture_sample(struct hid_sensor_hub_device *hsdev,
- unsigned int usage_id, size_t raw_len,
- char *raw_data, void *pdev)
+ unsigned int usage_id, size_t raw_len,
+ char *raw_data, void *pdev)
{
struct iio_dev *indio_dev = platform_get_drvdata(pdev);
struct hid_humidity_state *humid_st = iio_priv(indio_dev);
@@ -159,17 +159,17 @@ static int humidity_capture_sample(struct hid_sensor_hub_device *hsdev,
/* Parse report which is specific to an usage id */
static int humidity_parse_report(struct platform_device *pdev,
- struct hid_sensor_hub_device *hsdev,
- struct iio_chan_spec *channels,
- unsigned int usage_id,
- struct hid_humidity_state *st)
+ struct hid_sensor_hub_device *hsdev,
+ struct iio_chan_spec *channels,
+ unsigned int usage_id,
+ struct hid_humidity_state *st)
{
int ret;
ret = sensor_hub_input_get_attribute_info(hsdev, HID_INPUT_REPORT,
- usage_id,
- HID_USAGE_SENSOR_ATMOSPHERIC_HUMIDITY,
- &st->humidity_attr);
+ usage_id,
+ HID_USAGE_SENSOR_ATMOSPHERIC_HUMIDITY,
+ &st->humidity_attr);
if (ret < 0)
return ret;
@@ -208,20 +208,20 @@ static int hid_humidity_probe(struct platform_device *pdev)
humid_st->common_attributes.pdev = pdev;
ret = hid_sensor_parse_common_attributes(hsdev,
- HID_USAGE_SENSOR_HUMIDITY,
- &humid_st->common_attributes,
- humidity_sensitivity_addresses,
- ARRAY_SIZE(humidity_sensitivity_addresses));
+ HID_USAGE_SENSOR_HUMIDITY,
+ &humid_st->common_attributes,
+ humidity_sensitivity_addresses,
+ ARRAY_SIZE(humidity_sensitivity_addresses));
if (ret)
return ret;
humid_chans = devm_kmemdup(&indio_dev->dev, humidity_channels,
- sizeof(humidity_channels), GFP_KERNEL);
+ sizeof(humidity_channels), GFP_KERNEL);
if (!humid_chans)
return -ENOMEM;
ret = humidity_parse_report(pdev, hsdev, humid_chans,
- HID_USAGE_SENSOR_HUMIDITY, humid_st);
+ HID_USAGE_SENSOR_HUMIDITY, humid_st);
if (ret)
return ret;
@@ -234,7 +234,7 @@ static int hid_humidity_probe(struct platform_device *pdev)
atomic_set(&humid_st->common_attributes.data_ready, 0);
ret = hid_sensor_setup_trigger(indio_dev, name,
- &humid_st->common_attributes);
+ &humid_st->common_attributes);
if (ret)
return ret;
@@ -242,7 +242,7 @@ static int hid_humidity_probe(struct platform_device *pdev)
humidity_callbacks.pdev = pdev;
ret = sensor_hub_register_callback(hsdev, HID_USAGE_SENSOR_HUMIDITY,
- &humidity_callbacks);
+ &humidity_callbacks);
if (ret)
goto error_remove_trigger;
--
2.34.1
^ permalink raw reply related
* [PATCH v4 10/36] iio: gyro: hid-sensor-gyro-3d: align parenthesis for readability
From: Sanjay Chitroda @ 2026-05-24 19:25 UTC (permalink / raw)
To: jikos, jic23, srinivas.pandruvada
Cc: dlechner, nuno.sa, andy, sanjayembeddedse, sakari.ailus,
linux-input, linux-iio, linux-kernel
From: Sanjay Chitroda <sanjayembeddedse@gmail.com>
Adjust alignment of parentheses to improve readability and
maintain consistency with kernel coding style
Signed-off-by: Sanjay Chitroda <sanjayembeddedse@gmail.com>
---
drivers/iio/gyro/hid-sensor-gyro-3d.c | 67 ++++++++++++++-------------
1 file changed, 34 insertions(+), 33 deletions(-)
diff --git a/drivers/iio/gyro/hid-sensor-gyro-3d.c b/drivers/iio/gyro/hid-sensor-gyro-3d.c
index 020812639947..05ce6258fd3b 100644
--- a/drivers/iio/gyro/hid-sensor-gyro-3d.c
+++ b/drivers/iio/gyro/hid-sensor-gyro-3d.c
@@ -84,7 +84,7 @@ static const struct iio_chan_spec gyro_3d_channels[] = {
/* Adjust channel real bits based on report descriptor */
static void gyro_3d_adjust_channel_bit_mask(struct iio_chan_spec *channels,
- int channel, int size)
+ int channel, int size)
{
channels[channel].scan_type.sign = 's';
/* Real storage bits will change based on the report desc. */
@@ -95,9 +95,9 @@ static void gyro_3d_adjust_channel_bit_mask(struct iio_chan_spec *channels,
/* Channel read_raw handler */
static int gyro_3d_read_raw(struct iio_dev *indio_dev,
- struct iio_chan_spec const *chan,
- int *val, int *val2,
- long mask)
+ struct iio_chan_spec const *chan,
+ int *val, int *val2,
+ long mask)
{
struct gyro_3d_state *gyro_state = iio_priv(indio_dev);
int report_id = -1;
@@ -122,8 +122,7 @@ static int gyro_3d_read_raw(struct iio_dev *indio_dev,
min < 0);
else {
*val = 0;
- hid_sensor_power_state(&gyro_state->common_attributes,
- false);
+ hid_sensor_power_state(&gyro_state->common_attributes, false);
return -EINVAL;
}
hid_sensor_power_state(&gyro_state->common_attributes, false);
@@ -156,10 +155,10 @@ static int gyro_3d_read_raw(struct iio_dev *indio_dev,
/* Channel write_raw handler */
static int gyro_3d_write_raw(struct iio_dev *indio_dev,
- struct iio_chan_spec const *chan,
- int val,
- int val2,
- long mask)
+ struct iio_chan_spec const *chan,
+ int val,
+ int val2,
+ long mask)
{
struct gyro_3d_state *gyro_state = iio_priv(indio_dev);
int ret = 0;
@@ -187,8 +186,8 @@ static const struct iio_info gyro_3d_info = {
/* Callback handler to send event after all samples are received and captured */
static int gyro_3d_proc_event(struct hid_sensor_hub_device *hsdev,
- u32 usage_id,
- void *priv)
+ u32 usage_id,
+ void *priv)
{
struct iio_dev *indio_dev = platform_get_drvdata(priv);
struct gyro_3d_state *gyro_state = iio_priv(indio_dev);
@@ -209,9 +208,9 @@ static int gyro_3d_proc_event(struct hid_sensor_hub_device *hsdev,
/* Capture samples in local storage */
static int gyro_3d_capture_sample(struct hid_sensor_hub_device *hsdev,
- u32 usage_id,
- size_t raw_len, char *raw_data,
- void *priv)
+ u32 usage_id,
+ size_t raw_len, char *raw_data,
+ void *priv)
{
struct iio_dev *indio_dev = platform_get_drvdata(priv);
struct gyro_3d_state *gyro_state = iio_priv(indio_dev);
@@ -251,22 +250,24 @@ static int gyro_3d_parse_report(struct platform_device *pdev,
int i;
for (i = 0; i <= CHANNEL_SCAN_INDEX_Z; ++i) {
- ret = sensor_hub_input_get_attribute_info(hsdev,
- HID_INPUT_REPORT,
- usage_id,
- HID_USAGE_SENSOR_ANGL_VELOCITY_X_AXIS + i,
- &st->gyro[CHANNEL_SCAN_INDEX_X + i]);
+ ret = sensor_hub_input_get_attribute_info(
+ hsdev,
+ HID_INPUT_REPORT,
+ usage_id,
+ HID_USAGE_SENSOR_ANGL_VELOCITY_X_AXIS + i,
+ &st->gyro[CHANNEL_SCAN_INDEX_X + i]);
if (ret < 0)
break;
- gyro_3d_adjust_channel_bit_mask(channels,
- CHANNEL_SCAN_INDEX_X + i,
- st->gyro[CHANNEL_SCAN_INDEX_X + i].size);
+ gyro_3d_adjust_channel_bit_mask(
+ channels,
+ CHANNEL_SCAN_INDEX_X + i,
+ st->gyro[CHANNEL_SCAN_INDEX_X + i].size);
}
dev_dbg(&pdev->dev, "gyro_3d %x:%x, %x:%x, %x:%x\n",
- st->gyro[0].index,
- st->gyro[0].report_id,
- st->gyro[1].index, st->gyro[1].report_id,
- st->gyro[2].index, st->gyro[2].report_id);
+ st->gyro[0].index,
+ st->gyro[0].report_id,
+ st->gyro[1].index, st->gyro[1].report_id,
+ st->gyro[2].index, st->gyro[2].report_id);
st->scale_precision = hid_sensor_format_scale(
HID_USAGE_SENSOR_GYRO_3D,
@@ -295,10 +296,10 @@ static int hid_gyro_3d_probe(struct platform_device *pdev)
gyro_state->common_attributes.pdev = pdev;
ret = hid_sensor_parse_common_attributes(hsdev,
- HID_USAGE_SENSOR_GYRO_3D,
- &gyro_state->common_attributes,
- gyro_3d_sensitivity_addresses,
- ARRAY_SIZE(gyro_3d_sensitivity_addresses));
+ HID_USAGE_SENSOR_GYRO_3D,
+ &gyro_state->common_attributes,
+ gyro_3d_sensitivity_addresses,
+ ARRAY_SIZE(gyro_3d_sensitivity_addresses));
if (ret) {
dev_err(&pdev->dev, "failed to setup common attributes\n");
return ret;
@@ -327,7 +328,7 @@ static int hid_gyro_3d_probe(struct platform_device *pdev)
atomic_set(&gyro_state->common_attributes.data_ready, 0);
ret = hid_sensor_setup_trigger(indio_dev, name,
- &gyro_state->common_attributes);
+ &gyro_state->common_attributes);
if (ret < 0) {
dev_err(&pdev->dev, "trigger setup failed\n");
return ret;
@@ -343,7 +344,7 @@ static int hid_gyro_3d_probe(struct platform_device *pdev)
gyro_state->callbacks.capture_sample = gyro_3d_capture_sample;
gyro_state->callbacks.pdev = pdev;
ret = sensor_hub_register_callback(hsdev, HID_USAGE_SENSOR_GYRO_3D,
- &gyro_state->callbacks);
+ &gyro_state->callbacks);
if (ret < 0) {
dev_err(&pdev->dev, "callback reg failed\n");
goto error_iio_unreg;
--
2.34.1
^ permalink raw reply related
* [PATCH v4 11/36] iio: magnetometer: hid-sensor-magn-3d: align parenthesis for readability
From: Sanjay Chitroda @ 2026-05-24 19:25 UTC (permalink / raw)
To: jikos, jic23, srinivas.pandruvada
Cc: dlechner, nuno.sa, andy, sanjayembeddedse, sakari.ailus,
linux-input, linux-iio, linux-kernel
In-Reply-To: <20260524192556.1195042-1-sanjayembedded@gmail.com>
From: Sanjay Chitroda <sanjayembeddedse@gmail.com>
Adjust alignment of parentheses to improve readability and
maintain consistency with kernel coding style
Signed-off-by: Sanjay Chitroda <sanjayembeddedse@gmail.com>
---
drivers/iio/magnetometer/hid-sensor-magn-3d.c | 72 +++++++++----------
1 file changed, 36 insertions(+), 36 deletions(-)
diff --git a/drivers/iio/magnetometer/hid-sensor-magn-3d.c b/drivers/iio/magnetometer/hid-sensor-magn-3d.c
index b01dd53eb100..73dd2e7768db 100644
--- a/drivers/iio/magnetometer/hid-sensor-magn-3d.c
+++ b/drivers/iio/magnetometer/hid-sensor-magn-3d.c
@@ -134,7 +134,7 @@ static const struct iio_chan_spec magn_3d_channels[] = {
/* Adjust channel real bits based on report descriptor */
static void magn_3d_adjust_channel_bit_mask(struct iio_chan_spec *channels,
- int channel, int size)
+ int channel, int size)
{
channels[channel].scan_type.sign = 's';
/* Real storage bits will change based on the report desc. */
@@ -145,9 +145,9 @@ static void magn_3d_adjust_channel_bit_mask(struct iio_chan_spec *channels,
/* Channel read_raw handler */
static int magn_3d_read_raw(struct iio_dev *indio_dev,
- struct iio_chan_spec const *chan,
- int *val, int *val2,
- long mask)
+ struct iio_chan_spec const *chan,
+ int *val, int *val2,
+ long mask)
{
struct magn_3d_state *magn_state = iio_priv(indio_dev);
int report_id = -1;
@@ -177,8 +177,7 @@ static int magn_3d_read_raw(struct iio_dev *indio_dev,
false);
return -EINVAL;
}
- hid_sensor_power_state(&magn_state->magn_flux_attributes,
- false);
+ hid_sensor_power_state(&magn_state->magn_flux_attributes, false);
ret_type = IIO_VAL_INT;
break;
case IIO_CHAN_INFO_SCALE:
@@ -239,10 +238,10 @@ static int magn_3d_read_raw(struct iio_dev *indio_dev,
/* Channel write_raw handler */
static int magn_3d_write_raw(struct iio_dev *indio_dev,
- struct iio_chan_spec const *chan,
- int val,
- int val2,
- long mask)
+ struct iio_chan_spec const *chan,
+ int val,
+ int val2,
+ long mask)
{
struct magn_3d_state *magn_state = iio_priv(indio_dev);
int ret = 0;
@@ -280,8 +279,8 @@ static const struct iio_info magn_3d_info = {
/* Callback handler to send event after all samples are received and captured */
static int magn_3d_proc_event(struct hid_sensor_hub_device *hsdev,
- u32 usage_id,
- void *priv)
+ u32 usage_id,
+ void *priv)
{
struct iio_dev *indio_dev = platform_get_drvdata(priv);
struct magn_3d_state *magn_state = iio_priv(indio_dev);
@@ -302,9 +301,9 @@ static int magn_3d_proc_event(struct hid_sensor_hub_device *hsdev,
/* Capture samples in local storage */
static int magn_3d_capture_sample(struct hid_sensor_hub_device *hsdev,
- u32 usage_id,
- size_t raw_len, char *raw_data,
- void *priv)
+ u32 usage_id,
+ size_t raw_len, char *raw_data,
+ void *priv)
{
struct iio_dev *indio_dev = platform_get_drvdata(priv);
struct magn_3d_state *magn_state = iio_priv(indio_dev);
@@ -363,7 +362,8 @@ static int magn_3d_parse_report(struct platform_device *pdev,
u32 address = magn_3d_addresses[i];
/* Check if usage attribute exists in the sensor hub device */
- status = sensor_hub_input_get_attribute_info(hsdev,
+ status = sensor_hub_input_get_attribute_info(
+ hsdev,
HID_INPUT_REPORT,
usage_id,
address,
@@ -378,18 +378,17 @@ static int magn_3d_parse_report(struct platform_device *pdev,
return -EINVAL;
}
- dev_dbg(&pdev->dev, "magn_3d Found %d usage attributes\n",
- attr_count);
+ dev_dbg(&pdev->dev, "magn_3d Found %d usage attributes\n", attr_count);
dev_dbg(&pdev->dev, "magn_3d X: %x:%x Y: %x:%x Z: %x:%x\n",
- st->magn[0].index,
- st->magn[0].report_id,
- st->magn[1].index, st->magn[1].report_id,
- st->magn[2].index, st->magn[2].report_id);
+ st->magn[0].index,
+ st->magn[0].report_id,
+ st->magn[1].index, st->magn[1].report_id,
+ st->magn[2].index, st->magn[2].report_id);
/* Setup IIO channel array */
_channels = devm_kcalloc(&pdev->dev, attr_count,
- sizeof(struct iio_chan_spec),
- GFP_KERNEL);
+ sizeof(struct iio_chan_spec),
+ GFP_KERNEL);
if (!_channels) {
dev_err(&pdev->dev,
"failed to allocate space for iio channels\n");
@@ -434,8 +433,7 @@ static int magn_3d_parse_report(struct platform_device *pdev,
*channels = _channels;
- dev_dbg(&pdev->dev, "magn_3d Setup %d IIO channels\n",
- *chan_count);
+ dev_dbg(&pdev->dev, "magn_3d Setup %d IIO channels\n", *chan_count);
st->magn_flux_attr.scale_precision = hid_sensor_format_scale(
HID_USAGE_SENSOR_COMPASS_3D,
@@ -450,7 +448,8 @@ static int magn_3d_parse_report(struct platform_device *pdev,
&st->rot_attr.scale_post_decml);
if (st->rot_attributes.sensitivity.index < 0) {
- sensor_hub_input_get_attribute_info(hsdev,
+ sensor_hub_input_get_attribute_info(
+ hsdev,
HID_FEATURE_REPORT, usage_id,
HID_USAGE_SENSOR_DATA_MOD_CHANGE_SENSITIVITY_ABS |
HID_USAGE_SENSOR_ORIENT_COMP_MAGN_NORTH,
@@ -485,11 +484,12 @@ static int hid_magn_3d_probe(struct platform_device *pdev)
magn_state->magn_flux_attributes.hsdev = hsdev;
magn_state->magn_flux_attributes.pdev = pdev;
- ret = hid_sensor_parse_common_attributes(hsdev,
- HID_USAGE_SENSOR_COMPASS_3D,
- &magn_state->magn_flux_attributes,
- magn_3d_sensitivity_addresses,
- ARRAY_SIZE(magn_3d_sensitivity_addresses));
+ ret = hid_sensor_parse_common_attributes(
+ hsdev,
+ HID_USAGE_SENSOR_COMPASS_3D,
+ &magn_state->magn_flux_attributes,
+ magn_3d_sensitivity_addresses,
+ ARRAY_SIZE(magn_3d_sensitivity_addresses));
if (ret) {
dev_err(&pdev->dev, "failed to setup common attributes\n");
return ret;
@@ -499,8 +499,8 @@ static int hid_magn_3d_probe(struct platform_device *pdev)
magn_state->rot_attributes.sensitivity.index = -1;
ret = magn_3d_parse_report(pdev, hsdev,
- &channels, &chan_count,
- HID_USAGE_SENSOR_COMPASS_3D, magn_state);
+ &channels, &chan_count,
+ HID_USAGE_SENSOR_COMPASS_3D, magn_state);
if (ret) {
dev_err(&pdev->dev, "failed to parse report\n");
return ret;
@@ -515,7 +515,7 @@ static int hid_magn_3d_probe(struct platform_device *pdev)
atomic_set(&magn_state->magn_flux_attributes.data_ready, 0);
ret = hid_sensor_setup_trigger(indio_dev, name,
- &magn_state->magn_flux_attributes);
+ &magn_state->magn_flux_attributes);
if (ret < 0) {
dev_err(&pdev->dev, "trigger setup failed\n");
return ret;
@@ -531,7 +531,7 @@ static int hid_magn_3d_probe(struct platform_device *pdev)
magn_state->callbacks.capture_sample = magn_3d_capture_sample;
magn_state->callbacks.pdev = pdev;
ret = sensor_hub_register_callback(hsdev, HID_USAGE_SENSOR_COMPASS_3D,
- &magn_state->callbacks);
+ &magn_state->callbacks);
if (ret < 0) {
dev_err(&pdev->dev, "callback reg failed\n");
goto error_iio_unreg;
--
2.34.1
^ permalink raw reply related
* [PATCH v4 12/36] iio: humidity: hid-sensor-humidity: use common device for devres
From: Sanjay Chitroda @ 2026-05-24 19:25 UTC (permalink / raw)
To: jikos, jic23, srinivas.pandruvada
Cc: dlechner, nuno.sa, andy, sanjayembeddedse, sakari.ailus,
linux-input, linux-iio, linux-kernel
In-Reply-To: <20260524192556.1195042-1-sanjayembedded@gmail.com>
From: Sanjay Chitroda <sanjayembeddedse@gmail.com>
kmemdup() is used for memory that is logically tied to the HID
platform device, even though the driver binds into the IIO framework.
Using &indio_dev->dev for devres allocations works functionally, but it
results in two separate devres ownership trees—one for the HID
platform device (pdev) and another for the IIO device (indio_dev).
The devres framework is intended to have a single, well-defined parent
device. Since the memory originates from HID sensor probing and is not
IIO-specific, &pdev->dev is the correct and logical owner.
Switch to using the platform device for devm_kmemdup() so that all
resources are released deterministically and consistently.
Signed-off-by: Sanjay Chitroda <sanjayembeddedse@gmail.com>
Tested-by: Zhang Lixu <lixu.zhang@intel.com>
---
drivers/iio/humidity/hid-sensor-humidity.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/iio/humidity/hid-sensor-humidity.c b/drivers/iio/humidity/hid-sensor-humidity.c
index 6fed019f4099..73120b87d641 100644
--- a/drivers/iio/humidity/hid-sensor-humidity.c
+++ b/drivers/iio/humidity/hid-sensor-humidity.c
@@ -215,7 +215,7 @@ static int hid_humidity_probe(struct platform_device *pdev)
if (ret)
return ret;
- humid_chans = devm_kmemdup(&indio_dev->dev, humidity_channels,
+ humid_chans = devm_kmemdup(&pdev->dev, humidity_channels,
sizeof(humidity_channels), GFP_KERNEL);
if (!humid_chans)
return -ENOMEM;
--
2.34.1
^ permalink raw reply related
* [PATCH v4 13/36] iio: position: hid-sensor-custom-intel-hinge: use common device for devres
From: Sanjay Chitroda @ 2026-05-24 19:25 UTC (permalink / raw)
To: jikos, jic23, srinivas.pandruvada
Cc: dlechner, nuno.sa, andy, sanjayembeddedse, sakari.ailus,
linux-input, linux-iio, linux-kernel
In-Reply-To: <20260524192556.1195042-1-sanjayembedded@gmail.com>
From: Sanjay Chitroda <sanjayembeddedse@gmail.com>
kmemdup() is used for memory that is logically tied to the HID
platform device, even though the driver binds into the IIO framework.
Using &indio_dev->dev for devres allocations works functionally, but it
results in two separate devres ownership trees—one for the HID
platform device (pdev) and another for the IIO device (indio_dev).
The devres framework is intended to have a single, well-defined parent
device. Since the memory originates from HID sensor probing and is not
IIO-specific, &pdev->dev is the correct and logical owner.
Switch to using the platform device for devm_kmemdup() so that all
resources are released deterministically and consistently.
Signed-off-by: Sanjay Chitroda <sanjayembeddedse@gmail.com>
---
drivers/iio/position/hid-sensor-custom-intel-hinge.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/iio/position/hid-sensor-custom-intel-hinge.c b/drivers/iio/position/hid-sensor-custom-intel-hinge.c
index a26d391661fd..0ba9d2d43913 100644
--- a/drivers/iio/position/hid-sensor-custom-intel-hinge.c
+++ b/drivers/iio/position/hid-sensor-custom-intel-hinge.c
@@ -292,7 +292,7 @@ static int hid_hinge_probe(struct platform_device *pdev)
}
indio_dev->num_channels = ARRAY_SIZE(hinge_channels);
- indio_dev->channels = devm_kmemdup(&indio_dev->dev, hinge_channels,
+ indio_dev->channels = devm_kmemdup(&pdev->dev, hinge_channels,
sizeof(hinge_channels), GFP_KERNEL);
if (!indio_dev->channels)
return -ENOMEM;
--
2.34.1
^ permalink raw reply related
* [PATCH v4 14/36] iio: temperature: hid-sensor-temperature: use common device for devres
From: Sanjay Chitroda @ 2026-05-24 19:25 UTC (permalink / raw)
To: jikos, jic23, srinivas.pandruvada
Cc: dlechner, nuno.sa, andy, sanjayembeddedse, sakari.ailus,
linux-input, linux-iio, linux-kernel
In-Reply-To: <20260524192556.1195042-1-sanjayembedded@gmail.com>
From: Sanjay Chitroda <sanjayembeddedse@gmail.com>
kmemdup() is used for memory that is logically tied to the HID
platform device, even though the driver binds into the IIO framework.
Using &indio_dev->dev for devres allocations works functionally, but it
results in two separate devres ownership trees—one for the HID
platform device (pdev) and another for the IIO device (indio_dev).
The devres framework is intended to have a single, well-defined parent
device. Since the memory originates from HID sensor probing and is not
IIO-specific, &pdev->dev is the correct and logical owner.
Switch to using the platform device for devm_kmemdup() so that all
resources are released deterministically and consistently.
Signed-off-by: Sanjay Chitroda <sanjayembeddedse@gmail.com>
---
drivers/iio/temperature/hid-sensor-temperature.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/iio/temperature/hid-sensor-temperature.c b/drivers/iio/temperature/hid-sensor-temperature.c
index 9f628a8e5cfb..31ebfd1a1fe2 100644
--- a/drivers/iio/temperature/hid-sensor-temperature.c
+++ b/drivers/iio/temperature/hid-sensor-temperature.c
@@ -213,8 +213,8 @@ static int hid_temperature_probe(struct platform_device *pdev)
if (ret)
return ret;
- temp_chans = devm_kmemdup(&indio_dev->dev, temperature_channels,
- sizeof(temperature_channels), GFP_KERNEL);
+ temp_chans = devm_kmemdup(&pdev->dev, temperature_channels,
+ sizeof(temperature_channels), GFP_KERNEL);
if (!temp_chans)
return -ENOMEM;
--
2.34.1
^ permalink raw reply related
* [PATCH v4 15/36] iio: humidity: hid-sensor-humidity: use local struct device
From: Sanjay Chitroda @ 2026-05-24 19:25 UTC (permalink / raw)
To: jikos, jic23, srinivas.pandruvada
Cc: dlechner, nuno.sa, andy, sanjayembeddedse, sakari.ailus,
linux-input, linux-iio, linux-kernel
In-Reply-To: <20260524192556.1195042-1-sanjayembedded@gmail.com>
From: Sanjay Chitroda <sanjayembeddedse@gmail.com>
Introduce a local struct device pointer derived from &pdev->dev.
This avoids repeated &pdev->dev usage and improves readability.
Signed-off-by: Sanjay Chitroda <sanjayembeddedse@gmail.com>
---
drivers/iio/humidity/hid-sensor-humidity.c | 7 ++++---
1 file changed, 4 insertions(+), 3 deletions(-)
diff --git a/drivers/iio/humidity/hid-sensor-humidity.c b/drivers/iio/humidity/hid-sensor-humidity.c
index 73120b87d641..ea6f66ce0f8e 100644
--- a/drivers/iio/humidity/hid-sensor-humidity.c
+++ b/drivers/iio/humidity/hid-sensor-humidity.c
@@ -196,10 +196,11 @@ static int hid_humidity_probe(struct platform_device *pdev)
struct iio_dev *indio_dev;
struct hid_humidity_state *humid_st;
struct iio_chan_spec *humid_chans;
- struct hid_sensor_hub_device *hsdev = dev_get_platdata(&pdev->dev);
+ struct device *dev = &pdev->dev;
+ struct hid_sensor_hub_device *hsdev = dev_get_platdata(dev);
int ret;
- indio_dev = devm_iio_device_alloc(&pdev->dev, sizeof(*humid_st));
+ indio_dev = devm_iio_device_alloc(dev, sizeof(*humid_st));
if (!indio_dev)
return -ENOMEM;
@@ -215,7 +216,7 @@ static int hid_humidity_probe(struct platform_device *pdev)
if (ret)
return ret;
- humid_chans = devm_kmemdup(&pdev->dev, humidity_channels,
+ humid_chans = devm_kmemdup(dev, humidity_channels,
sizeof(humidity_channels), GFP_KERNEL);
if (!humid_chans)
return -ENOMEM;
--
2.34.1
^ permalink raw reply related
* [PATCH v4 16/36] iio: gyro: hid-sensor-gyro-3d: use local struct device
From: Sanjay Chitroda @ 2026-05-24 19:25 UTC (permalink / raw)
To: jikos, jic23, srinivas.pandruvada
Cc: dlechner, nuno.sa, andy, sanjayembeddedse, sakari.ailus,
linux-input, linux-iio, linux-kernel
In-Reply-To: <20260524192556.1195042-1-sanjayembedded@gmail.com>
From: Sanjay Chitroda <sanjayembeddedse@gmail.com>
Introduce a local struct device pointer derived from &pdev->dev.
This avoids repeated &pdev->dev usage and improves readability.
Signed-off-by: Sanjay Chitroda <sanjayembeddedse@gmail.com>
---
drivers/iio/gyro/hid-sensor-gyro-3d.c | 19 ++++++++++---------
1 file changed, 10 insertions(+), 9 deletions(-)
diff --git a/drivers/iio/gyro/hid-sensor-gyro-3d.c b/drivers/iio/gyro/hid-sensor-gyro-3d.c
index 4d56bd5b9f21..c891b1bb09dd 100644
--- a/drivers/iio/gyro/hid-sensor-gyro-3d.c
+++ b/drivers/iio/gyro/hid-sensor-gyro-3d.c
@@ -280,13 +280,14 @@ static int gyro_3d_parse_report(struct platform_device *pdev,
/* Function to initialize the processing for usage id */
static int hid_gyro_3d_probe(struct platform_device *pdev)
{
- struct hid_sensor_hub_device *hsdev = dev_get_platdata(&pdev->dev);
+ struct device *dev = &pdev->dev;
+ struct hid_sensor_hub_device *hsdev = dev_get_platdata(dev);
int ret = 0;
static const char *name = "gyro_3d";
struct iio_dev *indio_dev;
struct gyro_3d_state *gyro_state;
- indio_dev = devm_iio_device_alloc(&pdev->dev, sizeof(*gyro_state));
+ indio_dev = devm_iio_device_alloc(dev, sizeof(*gyro_state));
if (!indio_dev)
return -ENOMEM;
platform_set_drvdata(pdev, indio_dev);
@@ -301,14 +302,14 @@ static int hid_gyro_3d_probe(struct platform_device *pdev)
gyro_3d_sensitivity_addresses,
ARRAY_SIZE(gyro_3d_sensitivity_addresses));
if (ret) {
- dev_err(&pdev->dev, "failed to setup common attributes\n");
+ dev_err(dev, "failed to setup common attributes\n");
return ret;
}
- indio_dev->channels = devm_kmemdup(&pdev->dev, gyro_3d_channels,
+ indio_dev->channels = devm_kmemdup(dev, gyro_3d_channels,
sizeof(gyro_3d_channels), GFP_KERNEL);
if (!indio_dev->channels) {
- dev_err(&pdev->dev, "failed to duplicate channels\n");
+ dev_err(dev, "failed to duplicate channels\n");
return -ENOMEM;
}
@@ -316,7 +317,7 @@ static int hid_gyro_3d_probe(struct platform_device *pdev)
(struct iio_chan_spec *)indio_dev->channels,
HID_USAGE_SENSOR_GYRO_3D, gyro_state);
if (ret) {
- dev_err(&pdev->dev, "failed to setup attributes\n");
+ dev_err(dev, "failed to setup attributes\n");
return ret;
}
@@ -330,13 +331,13 @@ static int hid_gyro_3d_probe(struct platform_device *pdev)
ret = hid_sensor_setup_trigger(indio_dev, name,
&gyro_state->common_attributes);
if (ret < 0) {
- dev_err(&pdev->dev, "trigger setup failed\n");
+ dev_err(dev, "trigger setup failed\n");
return ret;
}
ret = iio_device_register(indio_dev);
if (ret) {
- dev_err(&pdev->dev, "device register failed\n");
+ dev_err(dev, "device register failed\n");
goto error_remove_trigger;
}
@@ -346,7 +347,7 @@ static int hid_gyro_3d_probe(struct platform_device *pdev)
ret = sensor_hub_register_callback(hsdev, HID_USAGE_SENSOR_GYRO_3D,
&gyro_state->callbacks);
if (ret < 0) {
- dev_err(&pdev->dev, "callback reg failed\n");
+ dev_err(dev, "callback reg failed\n");
goto error_iio_unreg;
}
--
2.34.1
^ permalink raw reply related
* [PATCH v4 17/36] iio: accel: hid-sensor-accel-3d: use local struct device
From: Sanjay Chitroda @ 2026-05-24 19:25 UTC (permalink / raw)
To: jikos, jic23, srinivas.pandruvada
Cc: dlechner, nuno.sa, andy, sanjayembeddedse, sakari.ailus,
linux-input, linux-iio, linux-kernel
In-Reply-To: <20260524192556.1195042-1-sanjayembedded@gmail.com>
From: Sanjay Chitroda <sanjayembeddedse@gmail.com>
Introduce a local struct device pointer derived from &pdev->dev.
This avoids repeated &pdev->dev usage and improves readability.
Signed-off-by: Sanjay Chitroda <sanjayembeddedse@gmail.com>
---
drivers/iio/accel/hid-sensor-accel-3d.c | 20 ++++++++++----------
1 file changed, 10 insertions(+), 10 deletions(-)
diff --git a/drivers/iio/accel/hid-sensor-accel-3d.c b/drivers/iio/accel/hid-sensor-accel-3d.c
index 67fb8efd6b10..561d9784d936 100644
--- a/drivers/iio/accel/hid-sensor-accel-3d.c
+++ b/drivers/iio/accel/hid-sensor-accel-3d.c
@@ -328,7 +328,8 @@ static int accel_3d_parse_report(struct platform_device *pdev,
/* Function to initialize the processing for usage id */
static int hid_accel_3d_probe(struct platform_device *pdev)
{
- struct hid_sensor_hub_device *hsdev = dev_get_platdata(&pdev->dev);
+ struct device *dev = &pdev->dev;
+ struct hid_sensor_hub_device *hsdev = dev_get_platdata(dev);
int ret = 0;
const char *name;
struct iio_dev *indio_dev;
@@ -336,8 +337,7 @@ static int hid_accel_3d_probe(struct platform_device *pdev)
const struct iio_chan_spec *channel_spec;
int channel_size;
- indio_dev = devm_iio_device_alloc(&pdev->dev,
- sizeof(struct accel_3d_state));
+ indio_dev = devm_iio_device_alloc(dev, sizeof(struct accel_3d_state));
if (indio_dev == NULL)
return -ENOMEM;
@@ -364,21 +364,21 @@ static int hid_accel_3d_probe(struct platform_device *pdev)
accel_3d_sensitivity_addresses,
ARRAY_SIZE(accel_3d_sensitivity_addresses));
if (ret) {
- dev_err(&pdev->dev, "failed to setup common attributes\n");
+ dev_err(dev, "failed to setup common attributes\n");
return ret;
}
- indio_dev->channels = devm_kmemdup(&pdev->dev, channel_spec,
+ indio_dev->channels = devm_kmemdup(dev, channel_spec,
channel_size, GFP_KERNEL);
if (!indio_dev->channels) {
- dev_err(&pdev->dev, "failed to duplicate channels\n");
+ dev_err(dev, "failed to duplicate channels\n");
return -ENOMEM;
}
ret = accel_3d_parse_report(pdev, hsdev,
(struct iio_chan_spec *)indio_dev->channels,
hsdev->usage, accel_state);
if (ret) {
- dev_err(&pdev->dev, "failed to setup attributes\n");
+ dev_err(dev, "failed to setup attributes\n");
return ret;
}
@@ -391,13 +391,13 @@ static int hid_accel_3d_probe(struct platform_device *pdev)
ret = hid_sensor_setup_trigger(indio_dev, name,
&accel_state->common_attributes);
if (ret < 0) {
- dev_err(&pdev->dev, "trigger setup failed\n");
+ dev_err(dev, "trigger setup failed\n");
return ret;
}
ret = iio_device_register(indio_dev);
if (ret) {
- dev_err(&pdev->dev, "device register failed\n");
+ dev_err(dev, "device register failed\n");
goto error_remove_trigger;
}
@@ -407,7 +407,7 @@ static int hid_accel_3d_probe(struct platform_device *pdev)
ret = sensor_hub_register_callback(hsdev, hsdev->usage,
&accel_state->callbacks);
if (ret < 0) {
- dev_err(&pdev->dev, "callback reg failed\n");
+ dev_err(dev, "callback reg failed\n");
goto error_iio_unreg;
}
--
2.34.1
^ permalink raw reply related
* [PATCH v4 18/36] iio: light: hid-sensor-als: use local struct device
From: Sanjay Chitroda @ 2026-05-24 19:25 UTC (permalink / raw)
To: jikos, jic23, srinivas.pandruvada
Cc: dlechner, nuno.sa, andy, sanjayembeddedse, sakari.ailus,
linux-input, linux-iio, linux-kernel
In-Reply-To: <20260524192556.1195042-1-sanjayembedded@gmail.com>
From: Sanjay Chitroda <sanjayembeddedse@gmail.com>
Introduce a local struct device pointer derived from &pdev->dev.
This avoids repeated &pdev->dev usage and improves readability.
Signed-off-by: Sanjay Chitroda <sanjayembeddedse@gmail.com>
---
drivers/iio/light/hid-sensor-als.c | 15 ++++++++-------
1 file changed, 8 insertions(+), 7 deletions(-)
diff --git a/drivers/iio/light/hid-sensor-als.c b/drivers/iio/light/hid-sensor-als.c
index ac654b2bbc1b..c84fb4cc5105 100644
--- a/drivers/iio/light/hid-sensor-als.c
+++ b/drivers/iio/light/hid-sensor-als.c
@@ -357,13 +357,14 @@ static int als_parse_report(struct platform_device *pdev,
/* Function to initialize the processing for usage id */
static int hid_als_probe(struct platform_device *pdev)
{
- struct hid_sensor_hub_device *hsdev = dev_get_platdata(&pdev->dev);
+ struct device *dev = &pdev->dev;
+ struct hid_sensor_hub_device *hsdev = dev_get_platdata(dev);
int ret = 0;
static const char *name = "als";
struct iio_dev *indio_dev;
struct als_state *als_state;
- indio_dev = devm_iio_device_alloc(&pdev->dev, sizeof(struct als_state));
+ indio_dev = devm_iio_device_alloc(dev, sizeof(struct als_state));
if (!indio_dev)
return -ENOMEM;
platform_set_drvdata(pdev, indio_dev);
@@ -378,7 +379,7 @@ static int hid_als_probe(struct platform_device *pdev)
als_sensitivity_addresses,
ARRAY_SIZE(als_sensitivity_addresses));
if (ret) {
- dev_err(&pdev->dev, "failed to setup common attributes\n");
+ dev_err(dev, "failed to setup common attributes\n");
return ret;
}
@@ -386,7 +387,7 @@ static int hid_als_probe(struct platform_device *pdev)
hsdev->usage,
als_state);
if (ret) {
- dev_err(&pdev->dev, "failed to setup attributes\n");
+ dev_err(dev, "failed to setup attributes\n");
return ret;
}
@@ -408,13 +409,13 @@ static int hid_als_probe(struct platform_device *pdev)
ret = hid_sensor_setup_trigger(indio_dev, name,
&als_state->common_attributes);
if (ret < 0) {
- dev_err(&pdev->dev, "trigger setup failed\n");
+ dev_err(dev, "trigger setup failed\n");
return ret;
}
ret = iio_device_register(indio_dev);
if (ret) {
- dev_err(&pdev->dev, "device register failed\n");
+ dev_err(dev, "device register failed\n");
goto error_remove_trigger;
}
@@ -423,7 +424,7 @@ static int hid_als_probe(struct platform_device *pdev)
als_state->callbacks.pdev = pdev;
ret = sensor_hub_register_callback(hsdev, hsdev->usage, &als_state->callbacks);
if (ret < 0) {
- dev_err(&pdev->dev, "callback reg failed\n");
+ dev_err(dev, "callback reg failed\n");
goto error_iio_unreg;
}
--
2.34.1
^ permalink raw reply related
* [PATCH v4 19/36] iio: light: hid-sensor-prox: use local struct device
From: Sanjay Chitroda @ 2026-05-24 19:25 UTC (permalink / raw)
To: jikos, jic23, srinivas.pandruvada
Cc: dlechner, nuno.sa, andy, sanjayembeddedse, sakari.ailus,
linux-input, linux-iio, linux-kernel
In-Reply-To: <20260524192556.1195042-1-sanjayembedded@gmail.com>
From: Sanjay Chitroda <sanjayembeddedse@gmail.com>
Introduce a local struct device pointer derived from &pdev->dev.
This avoids repeated &pdev->dev usage and improves readability.
Signed-off-by: Sanjay Chitroda <sanjayembeddedse@gmail.com>
---
drivers/iio/light/hid-sensor-prox.c | 16 ++++++++--------
1 file changed, 8 insertions(+), 8 deletions(-)
diff --git a/drivers/iio/light/hid-sensor-prox.c b/drivers/iio/light/hid-sensor-prox.c
index ac55808f161b..033dace06681 100644
--- a/drivers/iio/light/hid-sensor-prox.c
+++ b/drivers/iio/light/hid-sensor-prox.c
@@ -272,14 +272,14 @@ static int prox_parse_report(struct platform_device *pdev,
/* Function to initialize the processing for usage id */
static int hid_prox_probe(struct platform_device *pdev)
{
- struct hid_sensor_hub_device *hsdev = dev_get_platdata(&pdev->dev);
+ struct device *dev = &pdev->dev;
+ struct hid_sensor_hub_device *hsdev = dev_get_platdata(dev);
int ret = 0;
static const char *name = "prox";
struct iio_dev *indio_dev;
struct prox_state *prox_state;
- indio_dev = devm_iio_device_alloc(&pdev->dev,
- sizeof(struct prox_state));
+ indio_dev = devm_iio_device_alloc(dev, sizeof(struct prox_state));
if (!indio_dev)
return -ENOMEM;
platform_set_drvdata(pdev, indio_dev);
@@ -293,13 +293,13 @@ static int hid_prox_probe(struct platform_device *pdev)
prox_sensitivity_addresses,
ARRAY_SIZE(prox_sensitivity_addresses));
if (ret) {
- dev_err(&pdev->dev, "failed to setup common attributes\n");
+ dev_err(dev, "failed to setup common attributes\n");
return ret;
}
ret = prox_parse_report(pdev, hsdev, prox_state);
if (ret) {
- dev_err(&pdev->dev, "failed to setup attributes\n");
+ dev_err(dev, "failed to setup attributes\n");
return ret;
}
@@ -315,13 +315,13 @@ static int hid_prox_probe(struct platform_device *pdev)
ret = hid_sensor_setup_trigger(indio_dev, name,
&prox_state->common_attributes);
if (ret) {
- dev_err(&pdev->dev, "trigger setup failed\n");
+ dev_err(dev, "trigger setup failed\n");
return ret;
}
ret = iio_device_register(indio_dev);
if (ret) {
- dev_err(&pdev->dev, "device register failed\n");
+ dev_err(dev, "device register failed\n");
goto error_remove_trigger;
}
@@ -331,7 +331,7 @@ static int hid_prox_probe(struct platform_device *pdev)
ret = sensor_hub_register_callback(hsdev, hsdev->usage,
&prox_state->callbacks);
if (ret < 0) {
- dev_err(&pdev->dev, "callback reg failed\n");
+ dev_err(dev, "callback reg failed\n");
goto error_iio_unreg;
}
--
2.34.1
^ permalink raw reply related
* [PATCH v4 20/36] iio: magnetometer: hid-sensor-magn-3d: use local struct device
From: Sanjay Chitroda @ 2026-05-24 19:28 UTC (permalink / raw)
To: jikos, jic23, srinivas.pandruvada
Cc: dlechner, nuno.sa, andy, sanjayembeddedse, sakari.ailus,
linux-input, linux-iio, linux-kernel
From: Sanjay Chitroda <sanjayembeddedse@gmail.com>
Introduce a local struct device pointer derived from &pdev->dev.
This avoids repeated &pdev->dev usage and improves readability.
Signed-off-by: Sanjay Chitroda <sanjayembeddedse@gmail.com>
---
drivers/iio/magnetometer/hid-sensor-magn-3d.c | 36 ++++++++++---------
1 file changed, 19 insertions(+), 17 deletions(-)
diff --git a/drivers/iio/magnetometer/hid-sensor-magn-3d.c b/drivers/iio/magnetometer/hid-sensor-magn-3d.c
index 73dd2e7768db..cf08503ff1ef 100644
--- a/drivers/iio/magnetometer/hid-sensor-magn-3d.c
+++ b/drivers/iio/magnetometer/hid-sensor-magn-3d.c
@@ -352,6 +352,7 @@ static int magn_3d_parse_report(struct platform_device *pdev,
u32 usage_id,
struct magn_3d_state *st)
{
+ struct device *dev = &pdev->dev;
int i;
int attr_count = 0;
struct iio_chan_spec *_channels;
@@ -373,34 +374,34 @@ static int magn_3d_parse_report(struct platform_device *pdev,
}
if (attr_count <= 0) {
- dev_err(&pdev->dev,
+ dev_err(dev,
"failed to find any supported usage attributes in report\n");
return -EINVAL;
}
- dev_dbg(&pdev->dev, "magn_3d Found %d usage attributes\n", attr_count);
- dev_dbg(&pdev->dev, "magn_3d X: %x:%x Y: %x:%x Z: %x:%x\n",
+ dev_dbg(dev, "magn_3d Found %d usage attributes\n", attr_count);
+ dev_dbg(dev, "magn_3d X: %x:%x Y: %x:%x Z: %x:%x\n",
st->magn[0].index,
st->magn[0].report_id,
st->magn[1].index, st->magn[1].report_id,
st->magn[2].index, st->magn[2].report_id);
/* Setup IIO channel array */
- _channels = devm_kcalloc(&pdev->dev, attr_count,
+ _channels = devm_kcalloc(dev, attr_count,
sizeof(struct iio_chan_spec),
GFP_KERNEL);
if (!_channels) {
- dev_err(&pdev->dev,
+ dev_err(dev,
"failed to allocate space for iio channels\n");
return -ENOMEM;
}
/* attr_count include timestamp channel, and the iio_vals should be aligned to 8byte */
- st->iio_vals = devm_kcalloc(&pdev->dev,
+ st->iio_vals = devm_kcalloc(dev,
((attr_count + 1) % 2 + (attr_count + 1) / 2) * 2,
sizeof(u32), GFP_KERNEL);
if (!st->iio_vals) {
- dev_err(&pdev->dev,
+ dev_err(dev,
"failed to allocate space for iio values array\n");
return -ENOMEM;
}
@@ -426,14 +427,14 @@ static int magn_3d_parse_report(struct platform_device *pdev,
}
if (*chan_count <= 0) {
- dev_err(&pdev->dev,
+ dev_err(dev,
"failed to find any magnetic channels setup\n");
return -EINVAL;
}
*channels = _channels;
- dev_dbg(&pdev->dev, "magn_3d Setup %d IIO channels\n", *chan_count);
+ dev_dbg(dev, "magn_3d Setup %d IIO channels\n", *chan_count);
st->magn_flux_attr.scale_precision = hid_sensor_format_scale(
HID_USAGE_SENSOR_COMPASS_3D,
@@ -454,7 +455,7 @@ static int magn_3d_parse_report(struct platform_device *pdev,
HID_USAGE_SENSOR_DATA_MOD_CHANGE_SENSITIVITY_ABS |
HID_USAGE_SENSOR_ORIENT_COMP_MAGN_NORTH,
&st->rot_attributes.sensitivity);
- dev_dbg(&pdev->dev, "Sensitivity index:report %d:%d\n",
+ dev_dbg(dev, "Sensitivity index:report %d:%d\n",
st->rot_attributes.sensitivity.index,
st->rot_attributes.sensitivity.report_id);
}
@@ -465,7 +466,8 @@ static int magn_3d_parse_report(struct platform_device *pdev,
/* Function to initialize the processing for usage id */
static int hid_magn_3d_probe(struct platform_device *pdev)
{
- struct hid_sensor_hub_device *hsdev = dev_get_platdata(&pdev->dev);
+ struct device *dev = &pdev->dev;
+ struct hid_sensor_hub_device *hsdev = dev_get_platdata(dev);
int ret = 0;
static char *name = "magn_3d";
struct iio_dev *indio_dev;
@@ -473,7 +475,7 @@ static int hid_magn_3d_probe(struct platform_device *pdev)
struct iio_chan_spec *channels;
int chan_count = 0;
- indio_dev = devm_iio_device_alloc(&pdev->dev,
+ indio_dev = devm_iio_device_alloc(dev,
sizeof(struct magn_3d_state));
if (indio_dev == NULL)
return -ENOMEM;
@@ -491,7 +493,7 @@ static int hid_magn_3d_probe(struct platform_device *pdev)
magn_3d_sensitivity_addresses,
ARRAY_SIZE(magn_3d_sensitivity_addresses));
if (ret) {
- dev_err(&pdev->dev, "failed to setup common attributes\n");
+ dev_err(dev, "failed to setup common attributes\n");
return ret;
}
magn_state->rot_attributes = magn_state->magn_flux_attributes;
@@ -502,7 +504,7 @@ static int hid_magn_3d_probe(struct platform_device *pdev)
&channels, &chan_count,
HID_USAGE_SENSOR_COMPASS_3D, magn_state);
if (ret) {
- dev_err(&pdev->dev, "failed to parse report\n");
+ dev_err(dev, "failed to parse report\n");
return ret;
}
@@ -517,13 +519,13 @@ static int hid_magn_3d_probe(struct platform_device *pdev)
ret = hid_sensor_setup_trigger(indio_dev, name,
&magn_state->magn_flux_attributes);
if (ret < 0) {
- dev_err(&pdev->dev, "trigger setup failed\n");
+ dev_err(dev, "trigger setup failed\n");
return ret;
}
ret = iio_device_register(indio_dev);
if (ret) {
- dev_err(&pdev->dev, "device register failed\n");
+ dev_err(dev, "device register failed\n");
goto error_remove_trigger;
}
@@ -533,7 +535,7 @@ static int hid_magn_3d_probe(struct platform_device *pdev)
ret = sensor_hub_register_callback(hsdev, HID_USAGE_SENSOR_COMPASS_3D,
&magn_state->callbacks);
if (ret < 0) {
- dev_err(&pdev->dev, "callback reg failed\n");
+ dev_err(dev, "callback reg failed\n");
goto error_iio_unreg;
}
--
2.34.1
^ permalink raw reply related
* [PATCH v4 21/36] iio: orientation: hid-sensor-incl-3d: use local struct device
From: Sanjay Chitroda @ 2026-05-24 19:28 UTC (permalink / raw)
To: jikos, jic23, srinivas.pandruvada
Cc: dlechner, nuno.sa, andy, sanjayembeddedse, sakari.ailus,
linux-input, linux-iio, linux-kernel
In-Reply-To: <20260524192812.1196549-1-sanjayembedded@gmail.com>
From: Sanjay Chitroda <sanjayembeddedse@gmail.com>
Introduce a local struct device pointer derived from &pdev->dev.
This avoids repeated &pdev->dev usage and improves readability.
Signed-off-by: Sanjay Chitroda <sanjayembeddedse@gmail.com>
---
drivers/iio/orientation/hid-sensor-incl-3d.c | 20 ++++++++++----------
1 file changed, 10 insertions(+), 10 deletions(-)
diff --git a/drivers/iio/orientation/hid-sensor-incl-3d.c b/drivers/iio/orientation/hid-sensor-incl-3d.c
index c7fbff498be7..93fce8510468 100644
--- a/drivers/iio/orientation/hid-sensor-incl-3d.c
+++ b/drivers/iio/orientation/hid-sensor-incl-3d.c
@@ -299,14 +299,14 @@ static int incl_3d_parse_report(struct platform_device *pdev,
/* Function to initialize the processing for usage id */
static int hid_incl_3d_probe(struct platform_device *pdev)
{
- struct hid_sensor_hub_device *hsdev = dev_get_platdata(&pdev->dev);
+ struct device *dev = &pdev->dev;
+ struct hid_sensor_hub_device *hsdev = dev_get_platdata(dev);
int ret;
static char *name = "incli_3d";
struct iio_dev *indio_dev;
struct incl_3d_state *incl_state;
- indio_dev = devm_iio_device_alloc(&pdev->dev,
- sizeof(struct incl_3d_state));
+ indio_dev = devm_iio_device_alloc(dev, sizeof(struct incl_3d_state));
if (indio_dev == NULL)
return -ENOMEM;
@@ -322,14 +322,14 @@ static int hid_incl_3d_probe(struct platform_device *pdev)
incl_3d_sensitivity_addresses,
ARRAY_SIZE(incl_3d_sensitivity_addresses));
if (ret) {
- dev_err(&pdev->dev, "failed to setup common attributes\n");
+ dev_err(dev, "failed to setup common attributes\n");
return ret;
}
- indio_dev->channels = devm_kmemdup(&pdev->dev, incl_3d_channels,
+ indio_dev->channels = devm_kmemdup(dev, incl_3d_channels,
sizeof(incl_3d_channels), GFP_KERNEL);
if (!indio_dev->channels) {
- dev_err(&pdev->dev, "failed to duplicate channels\n");
+ dev_err(dev, "failed to duplicate channels\n");
return -ENOMEM;
}
@@ -338,7 +338,7 @@ static int hid_incl_3d_probe(struct platform_device *pdev)
HID_USAGE_SENSOR_INCLINOMETER_3D,
incl_state);
if (ret) {
- dev_err(&pdev->dev, "failed to setup attributes\n");
+ dev_err(dev, "failed to setup attributes\n");
return ret;
}
@@ -352,13 +352,13 @@ static int hid_incl_3d_probe(struct platform_device *pdev)
ret = hid_sensor_setup_trigger(indio_dev, name,
&incl_state->common_attributes);
if (ret) {
- dev_err(&pdev->dev, "trigger setup failed\n");
+ dev_err(dev, "trigger setup failed\n");
return ret;
}
ret = iio_device_register(indio_dev);
if (ret) {
- dev_err(&pdev->dev, "device register failed\n");
+ dev_err(dev, "device register failed\n");
goto error_remove_trigger;
}
@@ -369,7 +369,7 @@ static int hid_incl_3d_probe(struct platform_device *pdev)
HID_USAGE_SENSOR_INCLINOMETER_3D,
&incl_state->callbacks);
if (ret) {
- dev_err(&pdev->dev, "callback reg failed\n");
+ dev_err(dev, "callback reg failed\n");
goto error_iio_unreg;
}
--
2.34.1
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox