[PATCH 0/7] HID: iio: basic clean up for usage_id

[PATCH 0/7] HID: iio: basic clean up for usage_id

[Sanjay Chitroda]

Hi all,

This series updates all HID IIO drivers to use 'u32' instead of
bare 'unsigned' for the usage_id parameter.

This improves type clarity and ensures consistency with kernel
coding style, as HID usage IDs are defined as 32-bit values.

No functional changes are introduced.

Testing:
  - Compiled with W=1 for each patch in the series

---
Sanjay Chitroda (7):
      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

 drivers/iio/accel/hid-sensor-accel-3d.c       | 6 +++---
 drivers/iio/gyro/hid-sensor-gyro-3d.c         | 6 +++---
 drivers/iio/light/hid-sensor-als.c            | 6 +++---
 drivers/iio/light/hid-sensor-prox.c           | 4 ++--
 drivers/iio/orientation/hid-sensor-incl-3d.c  | 6 +++---
 drivers/iio/orientation/hid-sensor-rotation.c | 6 +++---
 drivers/iio/pressure/hid-sensor-press.c       | 6 +++---
 7 files changed, 20 insertions(+), 20 deletions(-)
---
base-commit: ae696dfa47c30016cd429b9db5e70b259b8f509e
change-id: 20260606-6-june-hid-iio-correct-usage-id-57ce92cb102b

Best regards,
--  
Sanjay Chitroda <sanjayembeddedse@gmail.com>

[PATCH 1/7] iio: gyro: hid-sensor-gyro-3d: use u32 instead of unsigned

[Sanjay Chitroda]

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
- v3 link -> 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 e48c25c87b6d..bbca2111e79b 100644
--- a/drivers/iio/gyro/hid-sensor-gyro-3d.c
+++ b/drivers/iio/gyro/hid-sensor-gyro-3d.c
@@ -177,7 +177,7 @@ 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);
@@ -199,7 +199,7 @@ 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)
 {
@@ -234,7 +234,7 @@ 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

[PATCH 2/7] iio: accel: hid-sensor-accel-3d: use u32 instead of unsigned

[Sanjay Chitroda]

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 2bf05ab5235e..42c4259bf209 100644
--- a/drivers/iio/accel/hid-sensor-accel-3d.c
+++ b/drivers/iio/accel/hid-sensor-accel-3d.c
@@ -223,7 +223,7 @@ 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);
@@ -247,7 +247,7 @@ 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)
 {
@@ -283,7 +283,7 @@ 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

[PATCH 3/7] iio: light: hid-sensor-als: use u32 instead of unsigned

[Sanjay Chitroda]

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 d72e260b8266..ae2fda8dc500 100644
--- a/drivers/iio/light/hid-sensor-als.c
+++ b/drivers/iio/light/hid-sensor-als.c
@@ -241,7 +241,7 @@ 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);
@@ -263,7 +263,7 @@ 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)
 {
@@ -305,7 +305,7 @@ 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

[PATCH 4/7] iio: light: hid-sensor-prox: use u32 instead of unsigned

[Sanjay Chitroda]

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 edc9274a2c07..9059f00f0ced 100644
--- a/drivers/iio/light/hid-sensor-prox.c
+++ b/drivers/iio/light/hid-sensor-prox.c
@@ -166,7 +166,7 @@ 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);
@@ -183,7 +183,7 @@ 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

[PATCH 5/7] iio: orientation: hid-sensor-incl-3d: use u32 instead of unsigned

[Sanjay Chitroda]

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

[PATCH 6/7] iio: orientation: hid-sensor-rotation: use u32 instead of unsigned

[Sanjay Chitroda]

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

[PATCH 7/7] iio: pressure: hid-sensor-press: use u32 instead of unsigned

[Sanjay Chitroda]

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 a039b99d9851..3e47a10d72a8 100644
--- a/drivers/iio/pressure/hid-sensor-press.c
+++ b/drivers/iio/pressure/hid-sensor-press.c
@@ -155,7 +155,7 @@ 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);
@@ -176,7 +176,7 @@ 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)
 {
@@ -204,7 +204,7 @@ 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

Re: [PATCH 2/7] iio: accel: hid-sensor-accel-3d: use u32 instead of unsigned

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:

Pre-existing issues:
- [High] Unsafe memory access via out-of-bounds read and unaligned dereference.
--

commit f0677ef9176d20b908a2aa7a22d8817abe7925a7
Author: Sanjay Chitroda <sanjayembeddedse@gmail.com>

iio: accel: hid-sensor-accel-3d: use u32 instead of unsigned

This commit updates the hid-sensor-accel-3d driver to use u32 instead of
unsigned for the usage_id variables. This improves code clarity and maintains
consistency with kernel coding styles.

> diff --git a/drivers/iio/accel/hid-sensor-accel-3d.c b/drivers/iio/accel/hid-sensor-accel-3d.c
> --- a/drivers/iio/accel/hid-sensor-accel-3d.c
> +++ b/drivers/iio/accel/hid-sensor-accel-3d.c

[ ... ]

> @@ -247,7 +247,7 @@ 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)
>  {
>  	struct iio_dev *indio_dev = platform_get_drvdata(priv);
>  	struct accel_3d_state *accel_state = iio_priv(indio_dev);
>  	int offset;
>  	int ret = -EINVAL;
>  
>  	switch (usage_id) {
>  	case HID_USAGE_SENSOR_ACCEL_X_AXIS:
>  	case HID_USAGE_SENSOR_ACCEL_Y_AXIS:
>  	case HID_USAGE_SENSOR_ACCEL_Z_AXIS:
>  		offset = usage_id - HID_USAGE_SENSOR_ACCEL_X_AXIS;
>  		accel_state->scan.accel_val[CHANNEL_SCAN_INDEX_X + offset] =
>  						*(u32 *)raw_data;

[Severity: High]
This is a pre-existing issue, but I noticed a potential problem with how
raw_data is accessed here. Does this direct cast to a 32-bit integer pointer
assume that raw_len is always at least 4 bytes and that raw_data is always
4-byte aligned?

If a device provides a smaller report, could this result in an out-of-bounds
read? Also, since raw_data comes from a HID report buffer, could this trigger
an alignment fault on architectures with strict alignment requirements if the
data is unaligned?

>  		ret = 0;
>  	break;
>  	case HID_USAGE_SENSOR_TIME_TIMESTAMP:
>  		accel_state->timestamp =
>  			hid_sensor_convert_timestamp(
>  					&accel_state->common_attributes,
>  					*(int64_t *)raw_data);

[Severity: High]
This is also a pre-existing issue, but similar to the above, does this direct
cast to a 64-bit integer pointer require raw_len to be at least 8 bytes and
raw_data to be 8-byte aligned?

Would it be safer to use get_unaligned() and check raw_len before
dereferencing these pointers to avoid potential slab-out-of-bounds panics
or alignment faults?

>  		ret = 0;
>  	break;

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260606-6-june-hid-iio-correct-usage-id-v1-0-dd4a6820b674@gmail.com?part=2

Re: [PATCH 4/7] iio: light: hid-sensor-prox: use u32 instead of unsigned

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:

Pre-existing issues:
- [High] Direct casting of the raw HID byte stream pointer (`raw_data`) to `u16 *` and `u32 *` causes unaligned memory accesses and misinterprets little-endian HID data on big-endian architectures.
--

commit e810e65c50acb8fcba7f1cd54ed67e25dac1f409
Author: Sanjay Chitroda <sanjayembeddedse@gmail.com>

iio: light: hid-sensor-prox: use u32 instead of unsigned

This patch updates the usage_id parameter to use u32 instead of a bare
unsigned type. This improves code clarity and consistency with standard
kernel style.

> diff --git a/drivers/iio/light/hid-sensor-prox.c b/drivers/iio/light/hid-sensor-prox.c
> index edc9274a2c076..9059f00f0cedf 100644
> --- a/drivers/iio/light/hid-sensor-prox.c
> +++ b/drivers/iio/light/hid-sensor-prox.c
[ ... ]
> @@ -183,7 +183,7 @@ 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)
>  {

[Severity: High]
This is a pre-existing issue, but since you are updating types in this
function, could we also address how the raw_data pointer is accessed?

Further down in prox_capture_sample(), the raw HID byte stream is directly
cast to u16 and u32 pointers:

	switch (raw_len) {
	case 1:
		prox_state->human_presence[chan] = *(u8 *)raw_data * multiplier;
		return 0;
	case 2:
		prox_state->human_presence[chan] = *(u16 *)raw_data * multiplier;
		return 0;
	case 4:
		prox_state->human_presence[chan] = *(u32 *)raw_data * multiplier;
		return 0;
	}

Can this sequence cause unaligned memory accesses or endianness issues?

Because HID fields are tightly packed and can have arbitrary lengths, the
raw_data pointer is not guaranteed to be 2-byte or 4-byte aligned.
Dereferencing it directly could trigger unaligned access traps on
architectures that do not natively support them.

Additionally, HID reports are transmitted in little-endian format over the
wire. Reading them via a direct cast evaluates them in host byte-order,
which could yield corrupted data on big-endian architectures.

Would it be better to use get_unaligned_le16() and get_unaligned_le32()
here to safely extract the payload?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260606-6-june-hid-iio-correct-usage-id-v1-0-dd4a6820b674@gmail.com?part=4

Re: [PATCH 6/7] iio: orientation: hid-sensor-rotation: use u32 instead of unsigned

[sashiko-bot]

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

Pre-existing issues:
- [High] Out-of-bounds read and information leak due to unverified raw_len in dev_rot_capture_sample().
- [High] Unaligned and endian-unsafe access when parsing HID raw byte streams.
--

commit 1678aae0ba9cfb6e8824b0811f3f770a159c5a16
Author: Sanjay Chitroda <sanjayembeddedse@gmail.com>

iio: orientation: hid-sensor-rotation: use u32 instead of unsigned

This commit replaces bare unsigned types with u32 for usage_id parameters
across the HID sensor rotation driver to improve code clarity and
consistency with kernel style.

> --- a/drivers/iio/orientation/hid-sensor-rotation.c
> +++ b/drivers/iio/orientation/hid-sensor-rotation.c

[ ... ]

> @@ -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)
>  {

[Severity: High]
This is a pre-existing issue, but does this function perform unaligned and
endian-unsafe reads?

Looking further down in dev_rot_capture_sample(), when raw_data is accessed:

        if (raw_len / 4 == sizeof(s16)) {
            rot_state->scan.sampled_vals[0] = ((s16 *)raw_data)[0];
            rot_state->scan.sampled_vals[1] = ((s16 *)raw_data)[1];
            rot_state->scan.sampled_vals[2] = ((s16 *)raw_data)[2];
            rot_state->scan.sampled_vals[3] = ((s16 *)raw_data)[3];

Since raw_data points to a byte array from a tightly packed HID report, it
is not guaranteed to be aligned to a 2-byte boundary. Casting directly to
s16 pointers might cause bus errors or panics on architectures that do not
support unaligned loads. 

Also, native CPU casts will read garbage values on big-endian architectures. 
Should this use get_unaligned_le16() instead?

[Severity: High]
This isn't a bug introduced by this patch, but can the fallback memcpy 
result in an out-of-bounds read?

If raw_len is not exactly 8 bytes, the code unconditionally copies 16 bytes:

        } else {
            memcpy(&rot_state->scan.sampled_vals, raw_data,
                   sizeof(rot_state->scan.sampled_vals));
        }

If a malformed or malicious HID descriptor specifies a size smaller than
16 bytes, this would read past the end of the raw_data buffer into adjacent
kernel memory. 

The copied data could then be pushed to userspace via iio_push_to_buffers(),
potentially creating an information leak.

[Severity: High]
This is a pre-existing issue, but does the timestamp handling also have
bounds checking and alignment issues?

Later in the same function:

    } else if (usage_id == HID_USAGE_SENSOR_TIME_TIMESTAMP) {
        rot_state->timestamp = hid_sensor_convert_timestamp(
                                    &rot_state->common_attributes,
                                    *(s64 *)raw_data);

The raw_data pointer is cast directly to a 64-bit integer without verifying
that raw_len is at least 8 bytes. 

Similar to the unaligned reads above, a direct cast to an s64 pointer on an
unaligned buffer could cause bus errors on certain architectures, and it is
also not endian-safe.

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260606-6-june-hid-iio-correct-usage-id-v1-0-dd4a6820b674@gmail.com?part=6

Re: [PATCH 3/7] iio: light: hid-sensor-als: use u32 instead of unsigned

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:

Pre-existing issues:
- [High] Unconditional casting and dereferencing of `raw_data` to `u32*` and `s64*` without checking `raw_len` causes out-of-bounds reads, kernel memory disclosure, unaligned access exceptions, and incorrect endianness handling.
--

commit 7ad652d49fe4e7dcab137b42945a51bbeaea25a3
Author: Sanjay Chitroda <sanjayembeddedse@gmail.com>

iio: light: hid-sensor-als: use u32 instead of unsigned

This commit updates the HID sensor ALS driver to use 'u32' instead of a bare
'unsigned' variable for the usage_id parameter. This improves code clarity
and consistency with kernel style.

> --- a/drivers/iio/light/hid-sensor-als.c
> +++ b/drivers/iio/light/hid-sensor-als.c

[ ... ]

>  /* 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)
>  {
>  	struct iio_dev *indio_dev = platform_get_drvdata(priv);
>  	struct als_state *als_state = iio_priv(indio_dev);
>  	int ret = -EINVAL;
>  	u32 sample_data = *(u32 *)raw_data;

[Severity: High]
This isn't a bug introduced by this patch, but does this direct cast cause
out-of-bounds reads or unaligned accesses if raw_len is less than 4 or
raw_data is unaligned?

Since raw_len is derived from the HID report descriptor, a malicious or
malfunctioning device could specify a smaller field size, potentially exposing
adjacent kernel memory. Should this code check raw_len and use something like
get_unaligned_le32() since HID data is little-endian?

>  
>  	switch (usage_id) {
>  	case HID_USAGE_SENSOR_LIGHT_ILLUM:

[ ... ]

>  	case HID_USAGE_SENSOR_TIME_TIMESTAMP:
>  		als_state->timestamp = hid_sensor_convert_timestamp(&als_state->common_attributes,
>  								    *(s64 *)raw_data);

[Severity: High]
This is also a pre-existing issue, but does this face similar risks with
8-byte reads from raw_data?

Could this trigger an out-of-bounds read if raw_len is less than 8, or cause
alignment faults on strict-alignment architectures?

>  		ret = 0;
>  		break;

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260606-6-june-hid-iio-correct-usage-id-v1-0-dd4a6820b674@gmail.com?part=3

Re: [PATCH 1/7] iio: gyro: hid-sensor-gyro-3d: use u32 instead of unsigned

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:

Pre-existing issues:
- [High] The capture_sample callback casts the `raw_data` pointer to `u32*` and `s64*` without validating `raw_len` or pointer alignment, potentially causing out-of-bounds reads, kernel memory leaks, and unaligned access faults.
--

commit e250748ae8811d708c463dcef4e525db238816e3
Author: Sanjay Chitroda <sanjayembeddedse@gmail.com>

iio: gyro: hid-sensor-gyro-3d: use u32 instead of unsigned

This commit replaces bare unsigned variables with the u32 type in the HID
sensor 3D gyro driver to improve code clarity and adhere to kernel style
guidelines.

> diff --git a/drivers/iio/gyro/hid-sensor-gyro-3d.c b/drivers/iio/gyro/hid-sensor-gyro-3d.c
> index e48c25c87b6d6..bbca2111e79bb 100644
> --- a/drivers/iio/gyro/hid-sensor-gyro-3d.c
> +++ b/drivers/iio/gyro/hid-sensor-gyro-3d.c
[ ... ]
> @@ -199,7 +199,7 @@ 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)
>  {

[Severity: High]
This is a pre-existing issue, but looking at the rest of this function, it
appears we cast the raw_data pointer directly to u32* and s64* without checking
raw_len or alignment:

gyro_3d_capture_sample() {
	...
	gyro_state->scan.gyro_val[CHANNEL_SCAN_INDEX_X + offset] =
			*(u32 *)raw_data;
	...
	gyro_state->timestamp =
		hid_sensor_convert_timestamp(&gyro_state->common_attributes,
					     *(s64 *)raw_data);
	...
}

Could a buggy or malicious HID device supply a field size smaller than 4 or 8
bytes, leading to an out-of-bounds read that leaks kernel heap data into the
IIO buffer?

Also, since raw_data is only guaranteed to be byte-aligned, could these native
casts trigger unaligned access exceptions on architectures that do not support
unaligned loads? Would it be safer to validate raw_len and use get_unaligned()
or memcpy() here?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260606-6-june-hid-iio-correct-usage-id-v1-0-dd4a6820b674@gmail.com?part=1

Re: [PATCH 5/7] iio: orientation: hid-sensor-incl-3d: use u32 instead of unsigned

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 3 potential issue(s) to consider:

Pre-existing issues:
- [High] Out-of-bounds read and information leak in `incl_3d_capture_sample` due to ignored `raw_len`.
- [High] Endianness mismatch in `incl_3d_capture_sample` due to direct pointer cast.
- [High] Unaligned memory access in `incl_3d_capture_sample`.
--

commit bb48c83224153ec8c20c69c57c293183eb5211a7
Author: Sanjay Chitroda <sanjayembeddedse@gmail.com>

iio: orientation: hid-sensor-incl-3d: use u32 instead of unsigned

This patch updates the hid-sensor-incl-3d driver to use u32 instead of a
bare unsigned type in callback signatures, improving code clarity and
consistency.

> diff --git a/drivers/iio/orientation/hid-sensor-incl-3d.c b/drivers/iio/orientation/hid-sensor-incl-3d.c
> index 4e23a598a3fb9..c7fbff498be7a 100644
> --- a/drivers/iio/orientation/hid-sensor-incl-3d.c
> +++ b/drivers/iio/orientation/hid-sensor-incl-3d.c

[ ... ]

> @@ -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)
>  {

[Severity: High]
This is a pre-existing issue, but by ignoring raw_len in
incl_3d_capture_sample(), could we read out-of-bounds if a malicious HID
device provides a report descriptor with a smaller field size?

It appears we unconditionally cast char *raw_data to u32 * or s64 * and
dereference it:

drivers/iio/orientation/hid-sensor-incl-3d.c:incl_3d_capture_sample() {
    ...
    case HID_USAGE_SENSOR_ORIENT_TILT_X:
        incl_state->scan.incl_val[CHANNEL_SCAN_INDEX_X] = *(u32 *)raw_data;
    ...
}

If the field is placed at the end of the HID report buffer, this might
read past the allocated buffer and leak kernel heap memory into the
sensor readings.

[Severity: High]
This is a pre-existing issue, but does this direct cast also cause
incorrect sensor values on big-endian architectures?

The USB HID protocol specifies that report data is strictly little-endian,
but casting directly to u32 * and dereferencing it uses the CPU native
byte order.

[Severity: High]
This is a pre-existing issue, but can this dereference trigger alignment
exceptions on architectures that do not support unaligned accesses?

Since the pointer passed as raw_data is iteratively incremented by the
byte sizes of preceding fields, it might not be aligned to a 4-byte
boundary when we cast it to u32 * and dereference it.

Should we be extracting these values safely using helpers like
get_unaligned_le32() instead?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260606-6-june-hid-iio-correct-usage-id-v1-0-dd4a6820b674@gmail.com?part=5

Re: [PATCH 7/7] iio: pressure: hid-sensor-press: use u32 instead of unsigned

[sashiko-bot]

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

Pre-existing issues:
- [High] Unaligned memory access and out-of-bounds read in `press_capture_sample` due to unconditional pointer cast and ignoring `raw_len`.
- [High] Stale software timestamp reused for all subsequent samples if the device lacks hardware timestamps.
--

commit a1f5a54c679fcb699d59de1d79aadcc9a8177858
Author: Sanjay Chitroda <sanjayembeddedse@gmail.com>

iio: pressure: hid-sensor-press: use u32 instead of unsigned

Prefer 'u32' instead of bare 'unsigned' variable to improve code
clarity and consistency with kernel style.

> diff --git a/drivers/iio/pressure/hid-sensor-press.c b/drivers/iio/pressure/hid-sensor-press.c
> index a039b99d9851d..3e47a10d72a89 100644
> --- a/drivers/iio/pressure/hid-sensor-press.c
> +++ b/drivers/iio/pressure/hid-sensor-press.c
> @@ -155,7 +155,7 @@ 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)
>  {

[Severity: High]
This isn't a bug introduced by this patch, but I noticed a potential problem
with how timestamps are handled in press_proc_event().

When a hardware timestamp isn't provided, the driver generates a software
timestamp:

	if (atomic_read(&press_state->common_attributes.data_ready)) {
		if (!press_state->timestamp)
			press_state->timestamp = iio_get_time_ns(indio_dev);

		iio_push_to_buffers_with_ts(indio_dev, &press_state->scan,
					    sizeof(press_state->scan),
					    press_state->timestamp);
	}

Because press_state->timestamp is never cleared back to 0 after pushing the
buffer, will all subsequent samples incorrectly reuse the exact same timestamp
instead of generating a new one?

[ ... ]

> @@ -176,7 +176,7 @@ 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)
>  {

[Severity: High]
This is a pre-existing issue, but could this cause unaligned accesses or
out-of-bounds reads?

Looking at press_capture_sample(), raw_data is cast directly to a pointer
without using the unaligned access helpers:

	case HID_USAGE_SENSOR_ATMOSPHERIC_PRESSURE:
		press_state->scan.press_data = *(u32 *)raw_data;
		ret = 0;
		break;
	case HID_USAGE_SENSOR_TIME_TIMESTAMP:
		press_state->timestamp = hid_sensor_convert_timestamp(
			&press_state->common_attributes, *(s64 *)raw_data);

Since raw_data points into a HID report, it might not be aligned, which could
cause undefined behavior on strictly aligned architectures.

Additionally, we're unconditionally reading 4 or 8 bytes here without checking
raw_len. If the HID descriptor specifies a smaller field size, could this read
past the end of the valid data buffer?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260606-6-june-hid-iio-correct-usage-id-v1-0-dd4a6820b674@gmail.com?part=7