Linux Input/HID development
 help / color / mirror / Atom feed
* Re: [PATCH v5 8/9] HID: steelseries: Add async status interface support
From: sashiko-bot @ 2026-06-30 17:39 UTC (permalink / raw)
  To: Sriman Achanta; +Cc: linux-input, dmitry.torokhov
In-Reply-To: <c993054229da167e96332fc142d372091e8c7406.1782840133.git.srimanachanta@gmail.com>

Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
- [High] Unsynchronized access to the sibling interface's HID device and driver data in `steelseries_get_sibling_sd()` leads to Use-After-Free vulnerabilities during concurrent unbinding.
- [High] Unsafe retrieval of `intfdata` from a sibling USB interface without verifying the bound USB driver leads to type confusion.
--

commit 184e416637c40dbd71e035542907c5105f99d55d
Author: Sriman Achanta <srimanachanta@gmail.com>

HID: steelseries: Add async status interface support

This patch adds support for an async status interface on some Steelseries
headsets. The driver binds both sync and async interfaces, using the async
interface to push status events and delay its probe until the sync interface
is fully initialized.

> diff --git a/drivers/hid/hid-steelseries-arctis.c b/drivers/hid/hid-steelseries-arctis.c
> --- a/drivers/hid/hid-steelseries-arctis.c
> +++ b/drivers/hid/hid-steelseries-arctis.c

[ ... ]

> +static struct steelseries_device *
> +steelseries_get_sibling_sd(struct hid_device *hdev, int interface_num)
> +{
> +	struct usb_interface *intf = to_usb_interface(hdev->dev.parent);
> +	struct usb_device *usb_dev = interface_to_usbdev(intf);
> +	struct usb_interface *sibling_intf;
> +	struct hid_device *sibling_hdev;
> +	struct steelseries_device *sd;
> +
> +	sibling_intf = usb_ifnum_to_if(usb_dev, interface_num);
> +	if (!sibling_intf)
> +		return NULL;
> +
> +	sibling_hdev = usb_get_intfdata(sibling_intf);
> +	if (!sibling_hdev || sibling_hdev->driver != &steelseries_arctis_driver)

[Severity: High]
Can a malicious USB device trigger an out-of-bounds read here?

If the device advertises the sync interface as a non-HID class (like Mass
Storage) but the async interface as HID, the USB core might bind a different
driver to the sync interface. In that case, usb_get_intfdata() would return
a driver-specific structure (like struct us_data) rather than a
struct hid_device.

Would it be safer to verify the bound USB driver on the sibling interface
before casting the intfdata and dereferencing sibling_hdev->driver?

> +		return NULL;
> +
> +	sd = hid_get_drvdata(sibling_hdev);
> +	if (sd)
> +		kref_get(&sd->refcnt);

[Severity: High]
Is there a race condition with concurrent unbinding here?

If the sync interface is concurrently unbound (e.g., via sysfs or physical
disconnection) while the async interface is probing, usb_get_intfdata()
and hid_get_drvdata() are called without holding device_lock() for the
sibling interface's device.

Could this allow the hid_device to be freed before checking
sibling_hdev->driver, or allow the steelseries_device (sd) to be freed
before kref_get() is called?

> +
> +	return sd;
> +}

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/cover.1782840133.git.srimanachanta@gmail.com?part=8

^ permalink raw reply

* Re: [PATCH v5 5/9] HID: steelseries: Report POWER_SUPPLY_STATUS_FULL when full
From: sashiko-bot @ 2026-06-30 17:39 UTC (permalink / raw)
  To: Sriman Achanta; +Cc: dmitry.torokhov, linux-input
In-Reply-To: <3d06ba7fcb4873c9d9d69c1fcbcd3d6bc21fadd0.1782840133.git.srimanachanta@gmail.com>

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Medium] The patch incorrectly reports POWER_SUPPLY_STATUS_FULL for an unplugged, actively discharging wireless headset solely because its capacity is 100%.
--

commit 7a846a17b1f3241f94405b831860eba9d3123648
Author: Sriman Achanta <srimanachanta@gmail.com>

HID: steelseries: Report POWER_SUPPLY_STATUS_FULL when full

This commit updates the battery status reporting for SteelSeries headsets.
It now returns POWER_SUPPLY_STATUS_FULL when the headset is connected, not
charging, and at 100% capacity instead of returning DISCHARGING.

> diff --git a/drivers/hid/hid-steelseries-arctis.c b/drivers/hid/hid-steelseries-arctis.c
> --- a/drivers/hid/hid-steelseries-arctis.c
> +++ b/drivers/hid/hid-steelseries-arctis.c
> @@ -215,6 +215,8 @@ static int steelseries_battery_get_property(struct power_supply *psy,
>  			val->intval = POWER_SUPPLY_STATUS_UNKNOWN;
>  		else if (sd->battery_charging)
>  			val->intval = POWER_SUPPLY_STATUS_CHARGING;
> +		else if (sd->battery_capacity >= 100)
> +			val->intval = POWER_SUPPLY_STATUS_FULL;

[Severity: Medium]
Will this incorrectly report POWER_SUPPLY_STATUS_FULL for an unplugged,
actively discharging wireless headset just because its capacity is at 100%?

When the headset is unplugged from external power but still fully charged,
sd->battery_charging is false and sd->battery_capacity is 100. It appears
this logic will now return POWER_SUPPLY_STATUS_FULL instead of
POWER_SUPPLY_STATUS_DISCHARGING, because there is no explicit check to verify
if the device is currently receiving external power.

Is there a way to ensure the headset is actually plugged in before returning
FULL, so that userspace tools don't incorrectly hide the discharge state
until the capacity drops below 100%?

>  		else
>  			val->intval = POWER_SUPPLY_STATUS_DISCHARGING;
>  		break;

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/cover.1782840133.git.srimanachanta@gmail.com?part=5

^ permalink raw reply

* Re: [PATCH v5 9/9] HID: steelseries: Add support for Arctis Nova 7 Gen2 family
From: sashiko-bot @ 2026-06-30 17:44 UTC (permalink / raw)
  To: Sriman Achanta; +Cc: linux-input, dmitry.torokhov
In-Reply-To: <8d6f139f082f2b985bad0cb3f60f260e60a7f2e9.1782840133.git.srimanachanta@gmail.com>

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

New issues:
- [Medium] The global bounds check `if (size < 4)` incorrectly drops valid, shorter unsolicited status reports.

Pre-existing issues:
- [High] Concurrent sysfs unbind leads to Use-After-Free of sibling `hid_device` and `steelseries_device`.
- [High] Type confusion when retrieving the sibling HID device can lead to an out-of-bounds memory read.
--

commit 70087cd16ba3bb84894fac86ae371e8ee1265c7a
Author: Sriman Achanta <srimanachanta@gmail.com>

HID: steelseries: Add support for Arctis Nova 7 Gen2 family

This patch adds support for the Arctis Nova 7 Gen2 headsets. It introduces a
new parser for unsolicited battery and connection updates on a second HID
interface, and adds eight new USB product IDs to the supported devices list.

> diff --git a/drivers/hid/hid-steelseries-arctis.c b/drivers/hid/hid-steelseries-arctis.c
> index 689435c60ecbd..31d31f3f4b0e9 100644
> --- a/drivers/hid/hid-steelseries-arctis.c
> +++ b/drivers/hid/hid-steelseries-arctis.c
[ ... ]
> @@ -162,6 +169,30 @@ static void steelseries_arctis_9_parse_status(struct steelseries_device *sd,
>  	}
>  }
>  
> +static void steelseries_arctis_nova_7_gen2_parse_status(struct steelseries_device *sd,
> +							u8 *data, int size)
> +{
> +	if (size < 4)
> +		return;

[Severity: Medium]
Could this global bounds check prematurely discard valid unsolicited battery
and connection updates?

The new opcodes 0xb7, 0xb9, and 0xbb only require up to data[1] to be valid.
If the headset firmware sends these unsolicited updates as 2-byte short USB
HID packets reflecting their actual content size, this check will drop them.

[ ... ]
> @@ -180,6 +211,14 @@ static const struct steelseries_device_info arctis_9_info = {
>  	.parse_status = steelseries_arctis_9_parse_status,
>  };
>  
> +static const struct steelseries_device_info arctis_nova_7_gen2_info = {
> +	.sync_interface = 3,
> +	.async_interface = 5,

[Severity: High]
This is a pre-existing issue, but the addition of these new devices using the
async/sync interface mechanism heavily exercises it. Is it possible for a
concurrent sysfs unbind to cause a use-after-free?

During the async interface probe, steelseries_get_sibling_sd() calls
usb_get_intfdata(sibling_intf) without holding the device lock for the sibling
interface. If a user concurrently unbinds the sibling interface (e.g., via
sysfs), usbhid destroys the hid_device. This causes the probe path to
locklessly dereference the freed sibling_hdev->driver:

	sibling_hdev = usb_get_intfdata(sibling_intf);
	if (!sibling_hdev || sibling_hdev->driver != &steelseries_arctis_driver)
		return NULL;

	sd = hid_get_drvdata(sibling_hdev);
	if (sd)
		kref_get(&sd->refcnt);

It then calls kref_get(&sd->refcnt) on the associated private data, modifying
freed memory.

[Severity: High]
This isn't a bug introduced by this patch, but adding these devices expands
the exposure to a pre-existing type confusion issue. Could this lead to an
out-of-bounds memory read?

In steelseries_get_sibling_sd(), the driver extracts the private data via
usb_get_intfdata() and assumes it is a struct hid_device *:

	sibling_intf = usb_ifnum_to_if(usb_dev, interface_num);
	if (!sibling_intf)
		return NULL;

	sibling_hdev = usb_get_intfdata(sibling_intf);
	if (!sibling_hdev || sibling_hdev->driver != &steelseries_arctis_driver)
		return NULL;

If a crafted USB device is plugged in where the sibling interface (e.g.,
interface 0 or 3) is a non-HID class like USB Audio, a different driver will
bind and store its own private structure in intfdata.

The driver field sits hundreds of bytes deep into struct hid_device. Reading
it from a smaller structure belonging to another driver will read out-of-bounds
of the allocated SLUB object.

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/cover.1782840133.git.srimanachanta@gmail.com?part=9

^ permalink raw reply

* Re: [PATCH] HID: asus: add new Asus EC hid device for keyboard backlight and FN HotKeys
From: Alexandru Serdeliuc @ 2026-06-30 16:43 UTC (permalink / raw)
  To: Jiri Kosina, Benjamin Tissoires; +Cc: linux-kernel, linux-input
In-Reply-To: <20251221-add-support-for-the-asus-hid-ec-v1-1-35d7d70fbbfc@yahoo.com>

Hi Jiri, Benjamin,

Enquiring if anyone has had a chance to look over this patch series from 
December?

To provide a bit of architectural context, this is a 100% pure HID 
client driver.

This laptop (Asus Zenbook A14 UX3407QA) runs on the Qualcomm ARM64 
Snapdragon platform.

Because it is an ARM device, it does not use traditional legacy x86 
ACPI/WMI code.

Instead, the Fn hotkeys and keyboard backlight controls are routed 
completely through standard vendor-specific HID reports (using Report ID 
0x5A) over the existing I2C-HID transport layer.

It requires absolutely zero Device Tree modifications or external 
platform subsystem hooks to bind or function.

The driver matches strictly on Vendor/Product ID (0x0B05 / 0x0220) 
passed directly through the core HID subsystem.

I would highly appreciate any architectural feedback or a quick review!

Best regards,
Alexandru Marc Serdeliuc


On 12/21/25 12:12, Alexandru Marc Serdeliuc via B4 Relay wrote:
> From: Alexandru Marc Serdeliuc <serdeliuk@yahoo.com>
> 
> Add support for Asus Embedded Controlled accessed via HID
> 
> Currently working features:
> - Keyboard Backlight
> - FN HotKeys
> 
> Signed-off-by: Alexandru Marc Serdeliuc <serdeliuk@yahoo.com>
> ---
> Add support for Asus Embedded Controlled accessed via HID
> 
> Currently working features:
> - Keyboard Backlight
> - FN HotKeys
> ---
>   drivers/hid/Kconfig       |  10 ++
>   drivers/hid/Makefile      |   1 +
>   drivers/hid/hid-asus-ec.c | 386 ++++++++++++++++++++++++++++++++++++++++++++++
>   3 files changed, 397 insertions(+)
> 
> diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig
> index 920a64b66b25b39e8259105c7c9b975fb77b2725..f0fbc951735eeea39198137294a9429f5b9d34b8 100644
> --- a/drivers/hid/Kconfig
> +++ b/drivers/hid/Kconfig
> @@ -202,6 +202,16 @@ config HID_ASUS
>   	- GL553V series
>   	- GL753V series
>   
> +config HID_ASUS_EC
> +	tristate "ASUS EC HID support (Zenbook A14 UX3407QA)"
> +	depends on HID && I2C_HID
> +	help
> +	  Say Y here if you have an ASUS Zenbook A14 (UX3407QA) and want
> +	  support for its EC-controlled keyboard backlight and Fn hotkeys
> +
> +	  This driver is currently only tested on the ASUS Zenbook A14
> +	  UX3407QA; behaviour on other models is unknown.
> +
>   config HID_AUREAL
>   	tristate "Aureal"
>   	help
> diff --git a/drivers/hid/Makefile b/drivers/hid/Makefile
> index 361a7daedeb85454114def8afb5f58caeab58a00..bacccf00482c1b787ce59660e4366f8224aeefee 100644
> --- a/drivers/hid/Makefile
> +++ b/drivers/hid/Makefile
> @@ -34,6 +34,7 @@ obj-$(CONFIG_HID_APPLETB_BL)	+= hid-appletb-bl.o
>   obj-$(CONFIG_HID_APPLETB_KBD)	+= hid-appletb-kbd.o
>   obj-$(CONFIG_HID_CREATIVE_SB0540)	+= hid-creative-sb0540.o
>   obj-$(CONFIG_HID_ASUS)		+= hid-asus.o
> +obj-$(CONFIG_HID_ASUS_EC)	+= hid-asus-ec.o
>   obj-$(CONFIG_HID_AUREAL)	+= hid-aureal.o
>   obj-$(CONFIG_HID_BELKIN)	+= hid-belkin.o
>   obj-$(CONFIG_HID_BETOP_FF)	+= hid-betopff.o
> diff --git a/drivers/hid/hid-asus-ec.c b/drivers/hid/hid-asus-ec.c
> new file mode 100644
> index 0000000000000000000000000000000000000000..1cf61fb2468d079827bfdb1db49daca905e53874
> --- /dev/null
> +++ b/drivers/hid/hid-asus-ec.c
> @@ -0,0 +1,386 @@
> +// SPDX-License-Identifier: GPL-2.0-or-later
> +/*
> + * ASUS EC HID driver for Zenbook A14 (UX3407QA)
> + *
> + * EC I2C HID driver for keyboard backlight and Fn hotkeys.
> + *
> + * Copyright (c) 2025 Alexandru Marc Serdeliuc <serdeliuk@yahoo.com>
> + */
> +
> +#include <linux/module.h>
> +#include <linux/init.h>
> +#include <linux/hid.h>
> +#include <linux/input.h>
> +#include <linux/leds.h>
> +#include <linux/slab.h>
> +#include <linux/kernel.h>
> +#include <linux/list.h>
> +#include <linux/string.h>
> +#include <linux/delay.h>
> +#include <linux/pm.h>
> +
> +#define ASUS_VENDOR_ID		0x0B05
> +#define ASUS_PRODUCT_ID		0x0220
> +
> +#define A14_EC_REPORT_ID	0x5A
> +#define A14_EC_REPORT_SIZE	64
> +#define A14_EC_MAX_BACKLIGHT	3
> +
> +#define A14_EC_EVT_KEY_FN_ESC	0x4E
> +#define A14_EC_EVT_KEY_FN_F4	0xC7
> +#define A14_EC_EVT_KEY_FN_F5	0x10
> +#define A14_EC_EVT_KEY_FN_F6	0x20
> +#define A14_EC_EVT_KEY_FN_F8	0x7E
> +#define A14_EC_EVT_KEY_FN_F9	0x7C
> +#define A14_EC_EVT_KEY_FN_F10	0x85
> +#define A14_EC_EVT_KEY_FN_F11	0x6B
> +#define A14_EC_EVT_KEY_FN_F12	0x86
> +#define A14_EC_EVT_KEY_FN_F	0x9d
> +
> +
> +struct asus_hid_data {
> +	struct hid_device *hdev;
> +	struct led_classdev kbd_led_cdev;
> +	struct input_dev *hotkey_input_dev;
> +	enum led_brightness saved_brightness;
> +};
> +
> +static struct asus_hid_data *asus_data;
> +
> +static int asus_send_ec_command(struct hid_device *hdev, u8 *cmd_buf)
> +{
> +	int ret;
> +	u8 report_id = cmd_buf[0];
> +
> +	ret = hid_hw_raw_request(hdev, report_id, cmd_buf, A14_EC_REPORT_SIZE,
> +				     HID_FEATURE_REPORT,
> +				     HID_REQ_SET_REPORT);
> +
> +	if (ret < 0)
> +		dev_err(&hdev->dev, "hid_hw_raw_request failed with status: %d\n", ret);
> +
> +	return ret;
> +}
> +
> +static int asus_kbd_led_init(struct hid_device *hdev)
> +{
> +	u8 ec_init_cmd[A14_EC_REPORT_SIZE] = { A14_EC_REPORT_ID, 0xD0, 0x8F, 0x01 };
> +	int ret;
> +
> +	ret = asus_send_ec_command(hdev, ec_init_cmd);
> +
> +	if (ret < 0)
> +		return ret;
> +
> +	u8 brightness_cmd[A14_EC_REPORT_SIZE] = { A14_EC_REPORT_ID, 0xBA, 0xC5,
> +				    0xC4, A14_EC_MAX_BACKLIGHT };
> +
> +	ret = asus_send_ec_command(hdev, brightness_cmd);
> +	if (ret < 0)
> +		dev_warn(&hdev->dev, "Brightness init failed: %d\n", ret);
> +
> +	return ret;
> +}
> +
> +static void asus_kbd_set_brightness(struct led_classdev *led_cdev,
> +				    enum led_brightness brightness)
> +{
> +	struct asus_hid_data *data = container_of(led_cdev, struct asus_hid_data, kbd_led_cdev);
> +
> +	u8 level = (u8)brightness;
> +
> +	if (level > A14_EC_MAX_BACKLIGHT)
> +		level = A14_EC_MAX_BACKLIGHT;
> +
> +	u8 buf[A14_EC_REPORT_SIZE] = { A14_EC_REPORT_ID, 0xBA, 0xC5, 0xC4, level };
> +
> +	asus_send_ec_command(data->hdev, buf);
> +	msleep(20);
> +	data->saved_brightness = (enum led_brightness)level;
> +}
> +
> +static int asus_raw_event(struct hid_device *hdev, struct hid_report *report,
> +			  u8 *raw_data, int size)
> +{
> +	struct asus_hid_data *data = hid_get_drvdata(hdev);
> +	struct input_dev *input_dev = data->hotkey_input_dev;
> +
> +	if (report->id == A14_EC_REPORT_ID && size >= 2) {
> +		u8 usage_code = raw_data[1];
> +
> +		switch (usage_code) {
> +		case A14_EC_EVT_KEY_FN_ESC:
> +			input_event(input_dev, EV_KEY, KEY_FN_ESC, 1);
> +			input_sync(input_dev);
> +			input_event(input_dev, EV_KEY, KEY_FN_ESC, 0);
> +			input_sync(input_dev);
> +			return 1;
> +
> +		/* FN + F1, F2 and F3 are not managed by EC*/
> +
> +		case A14_EC_EVT_KEY_FN_F4:
> +			if (size >= 3) {
> +				u8 current_level = data->saved_brightness;
> +				u8 max_level = A14_EC_MAX_BACKLIGHT;
> +				u8 next_level = (current_level + 1) % (max_level + 1);
> +
> +				asus_kbd_set_brightness(&data->kbd_led_cdev,
> +							(enum led_brightness)next_level);
> +				if (next_level > current_level ||
> +				    (current_level == max_level && next_level == 0)) {
> +					if (next_level == 0) {
> +						input_event(input_dev, EV_KEY,
> +							    KEY_KBDILLUMDOWN, 1);
> +						input_sync(input_dev);
> +						input_event(input_dev, EV_KEY,
> +							    KEY_KBDILLUMDOWN, 0);
> +						input_sync(input_dev);
> +						input_event(input_dev, EV_KEY,
> +							    KEY_KBDILLUMDOWN, 1);
> +						input_sync(input_dev);
> +						input_event(input_dev, EV_KEY,
> +							    KEY_KBDILLUMDOWN, 0);
> +						input_sync(input_dev);
> +						input_event(input_dev, EV_KEY,
> +							    KEY_KBDILLUMDOWN, 1);
> +						input_sync(input_dev);
> +						input_event(input_dev, EV_KEY,
> +							    KEY_KBDILLUMDOWN, 0);
> +						input_sync(input_dev);
> +					} else {
> +						input_event(input_dev, EV_KEY,
> +							    KEY_KBDILLUMUP, 1);
> +						input_sync(input_dev);
> +						input_event(input_dev, EV_KEY,
> +							    KEY_KBDILLUMUP, 0);
> +						input_sync(input_dev);
> +					}
> +				} else if (next_level < current_level) {
> +					input_event(input_dev, EV_KEY,
> +						    KEY_KBDILLUMDOWN, 1);
> +					input_sync(input_dev);
> +					input_event(input_dev, EV_KEY,
> +						    KEY_KBDILLUMDOWN, 0);
> +					input_sync(input_dev);
> +					input_event(input_dev, EV_KEY,
> +						    KEY_KBDILLUMDOWN, 1);
> +					input_sync(input_dev);
> +					input_event(input_dev, EV_KEY,
> +						    KEY_KBDILLUMDOWN, 0);
> +					input_sync(input_dev);
> +					input_event(input_dev, EV_KEY,
> +						    KEY_KBDILLUMDOWN, 1);
> +					input_sync(input_dev);
> +					input_event(input_dev, EV_KEY,
> +						    KEY_KBDILLUMDOWN, 0);
> +					input_sync(input_dev);
> +				}
> +			}
> +			return 1;
> +		case A14_EC_EVT_KEY_FN_F5:
> +			input_event(input_dev, EV_KEY, KEY_BRIGHTNESSDOWN, 1);
> +			input_sync(input_dev);
> +			input_event(input_dev, EV_KEY, KEY_BRIGHTNESSDOWN, 0);
> +			input_sync(input_dev);
> +			return 1;
> +		case A14_EC_EVT_KEY_FN_F6:
> +			input_event(input_dev, EV_KEY, KEY_BRIGHTNESSUP, 1);
> +			input_sync(input_dev);
> +			input_event(input_dev, EV_KEY, KEY_BRIGHTNESSUP, 0);
> +			input_sync(input_dev);
> +			return 1;
> +
> +		/* FN + F7 is not managed by the EC*/
> +
> +		case A14_EC_EVT_KEY_FN_F8:
> +			input_event(input_dev, EV_KEY, KEY_EMOJI_PICKER, 1);
> +			input_sync(input_dev);
> +			input_event(input_dev, EV_KEY, KEY_EMOJI_PICKER, 0);
> +			input_sync(input_dev);
> +			return 1;
> +		case A14_EC_EVT_KEY_FN_F9:
> +			input_event(input_dev, EV_KEY, KEY_MICMUTE, 1);
> +			input_sync(input_dev);
> +			input_event(input_dev, EV_KEY, KEY_MICMUTE, 0);
> +			input_sync(input_dev);
> +			return 1;
> +		case A14_EC_EVT_KEY_FN_F10:
> +			input_event(input_dev, EV_KEY, KEY_CAMERA_ACCESS_TOGGLE, 1);
> +			input_sync(input_dev);
> +			input_event(input_dev, EV_KEY, KEY_CAMERA_ACCESS_TOGGLE, 0);
> +			input_sync(input_dev);
> +			return 1;
> +		case A14_EC_EVT_KEY_FN_F11:
> +			input_event(input_dev, EV_KEY, KEY_TOUCHPAD_TOGGLE, 1);
> +			input_sync(input_dev);
> +			input_event(input_dev, EV_KEY, KEY_TOUCHPAD_TOGGLE, 0);
> +			input_sync(input_dev);
> +			return 1;
> +		case A14_EC_EVT_KEY_FN_F12:
> +			input_event(input_dev, EV_KEY, KEY_PROG1, 1);
> +			input_sync(input_dev);
> +			input_event(input_dev, EV_KEY, KEY_PROG1, 0);
> +			input_sync(input_dev);
> +			return 1;
> +		case A14_EC_EVT_KEY_FN_F:
> +			input_event(input_dev, EV_KEY, KEY_PERFORMANCE, 1);
> +			input_sync(input_dev);
> +			input_event(input_dev, EV_KEY, KEY_PERFORMANCE, 0);
> +			input_sync(input_dev);
> +			return 1;
> +		default:
> +			return 0;
> +		}
> +	}
> +	return 0;
> +}
> +
> +static int asus_hid_suspend(struct hid_device *hdev, pm_message_t message)
> +{
> +	struct asus_hid_data *data = hid_get_drvdata(hdev);
> +
> +	if (message.event == PM_EVENT_SUSPEND || message.event == PM_EVENT_HIBERNATE) {
> +		asus_kbd_set_brightness(&data->kbd_led_cdev, LED_OFF);
> +		return 0;
> +	}
> +
> +	dev_dbg(&hdev->dev, "Runtime suspend: turning off keyboard backlight\n");
> +	asus_kbd_set_brightness(&data->kbd_led_cdev, LED_OFF);
> +	return 0;
> +}
> +
> +
> +static int asus_hid_resume(struct hid_device *hdev)
> +{
> +	struct asus_hid_data *data = hid_get_drvdata(hdev);
> +	int ret;
> +	int retry_count;
> +
> +	msleep(40);
> +
> +	dev_dbg(&hdev->dev, "Re-initialising EC backlight communication\n");
> +	retry_count = 0;
> +	do {
> +		ret = asus_kbd_led_init(hdev);
> +		if (ret >= 0) {
> +			dev_dbg(&hdev->dev,
> +				"EC init successful on attempt %d\n",
> +				retry_count + 1);
> +			break;
> +		}
> +		retry_count++;
> +		dev_warn(&hdev->dev,
> +			 "EC init attempt %d failed: %d, retrying...\n",
> +			 retry_count, ret);
> +		msleep(300 * retry_count);
> +	} while (retry_count < 5);
> +
> +	if (ret < 0) {
> +		dev_err(&hdev->dev,
> +			"EC init on resume failed after %d attempts: %d\n",
> +			retry_count, ret);
> +		dev_err(&hdev->dev,
> +			"Keyboard backlight may not work; try reloading the driver\n");
> +	} else {
> +		dev_dbg(&hdev->dev, "EC backlight communication restored\n");
> +	}
> +
> +	asus_kbd_set_brightness(&data->kbd_led_cdev, data->saved_brightness);
> +
> +	dev_info(&hdev->dev, "Resume complete\n");
> +	return 0;
> +}
> +
> +static const struct hid_device_id asus_hid_devices[] = {
> +	/* Tested on ASUS Zenbook A14 (UX3407QA) only. */
> +	{ HID_DEVICE(0x18, 0x00, ASUS_VENDOR_ID, ASUS_PRODUCT_ID) },
> +	{ } /* Terminating entry */
> +};
> +MODULE_DEVICE_TABLE(hid, asus_hid_devices);
> +
> +static int asus_hid_probe(struct hid_device *hdev, const struct hid_device_id *id)
> +{
> +	int ret;
> +	struct asus_hid_data *data;
> +
> +	data = devm_kzalloc(&hdev->dev, sizeof(*data), GFP_KERNEL);
> +	if (!data)
> +		return -ENOMEM;
> +	data->hdev = hdev;
> +	hid_set_drvdata(hdev, data);
> +	asus_data = data;
> +	data->saved_brightness = A14_EC_MAX_BACKLIGHT;
> +	ret = hid_parse(hdev);
> +	if (ret)
> +		return ret;
> +	ret = hid_hw_start(hdev, HID_INPUT_REPORT | HID_OUTPUT_REPORT | HID_FEATURE_REPORT);
> +	if (ret)
> +		return ret;
> +	data->hotkey_input_dev = input_allocate_device();
> +	if (!data->hotkey_input_dev) {
> +		dev_err(&hdev->dev, "Failed to allocate hotkey input device\n");
> +		hid_hw_stop(hdev); return -ENOMEM;
> +	}
> +	data->hotkey_input_dev->name = "ASUS EC I2C HID hotkeys";
> +	data->hotkey_input_dev->phys = "i2c-hid/input1/hotkeys";
> +	data->hotkey_input_dev->id.bustype = hdev->bus;
> +	data->hotkey_input_dev->id.vendor = hdev->vendor;
> +	data->hotkey_input_dev->id.product = hdev->product;
> +	data->hotkey_input_dev->dev.parent = &hdev->dev;
> +	set_bit(EV_KEY, data->hotkey_input_dev->evbit);
> +	set_bit(KEY_FN_ESC, data->hotkey_input_dev->keybit);
> +	set_bit(KEY_KBDILLUMUP, data->hotkey_input_dev->keybit);
> +	set_bit(KEY_KBDILLUMDOWN, data->hotkey_input_dev->keybit);
> +	set_bit(KEY_BRIGHTNESSDOWN, data->hotkey_input_dev->keybit);
> +	set_bit(KEY_BRIGHTNESSUP, data->hotkey_input_dev->keybit);
> +	set_bit(KEY_SWITCHVIDEOMODE, data->hotkey_input_dev->keybit);
> +	set_bit(KEY_EMOJI_PICKER, data->hotkey_input_dev->keybit);
> +	set_bit(KEY_MICMUTE, data->hotkey_input_dev->keybit);
> +	set_bit(KEY_CAMERA_ACCESS_TOGGLE, data->hotkey_input_dev->keybit);
> +	set_bit(KEY_TOUCHPAD_TOGGLE, data->hotkey_input_dev->keybit);
> +	set_bit(KEY_PROG1, data->hotkey_input_dev->keybit);
> +	set_bit(KEY_PERFORMANCE, data->hotkey_input_dev->keybit);
> +
> +	ret = input_register_device(data->hotkey_input_dev);
> +	if (ret) {
> +		dev_err(&hdev->dev, "Failed to register hotkey input device\n");
> +		input_free_device(data->hotkey_input_dev); hid_hw_stop(hdev);
> +		return ret;
> +	}
> +	asus_kbd_led_init(hdev);
> +	data->kbd_led_cdev.name = "asus::kbd_backlight";
> +	data->kbd_led_cdev.brightness_set = asus_kbd_set_brightness;
> +	data->kbd_led_cdev.max_brightness = A14_EC_MAX_BACKLIGHT;
> +	ret = led_classdev_register(&hdev->dev, &data->kbd_led_cdev);
> +	if (ret) {
> +		input_unregister_device(data->hotkey_input_dev);
> +		hid_hw_stop(hdev);
> +		return ret;
> +	}
> +	dev_info(&hdev->dev,
> +		 "ASUS EC HID driver for Zenbook A14 loaded for 0x%04x:0x%04x\n",
> +		 ASUS_VENDOR_ID, ASUS_PRODUCT_ID);
> +	return 0;
> +}
> +static void asus_hid_remove(struct hid_device *hdev)
> +{
> +	struct asus_hid_data *data = hid_get_drvdata(hdev);
> +
> +	led_classdev_unregister(&data->kbd_led_cdev);
> +	input_unregister_device(data->hotkey_input_dev);
> +	hid_hw_stop(hdev);
> +	asus_data = NULL;
> +}
> +static struct hid_driver hid_asus_ec_driver = {
> +	.name       = "hid-asus-ec",
> +	.id_table   = asus_hid_devices,
> +	.probe      = asus_hid_probe,
> +	.remove     = asus_hid_remove,
> +	.raw_event  = asus_raw_event,
> +	.suspend    = asus_hid_suspend,
> +	.resume     = asus_hid_resume,
> +};
> +module_hid_driver(hid_asus_ec_driver);
> +MODULE_AUTHOR("Alexandru Marc Serdeliuc <serdeliuk@yahoo.com>");
> +MODULE_DESCRIPTION("ASUS EC HID driver for Zenbook A14 (UX3407QA)");
> +MODULE_LICENSE("GPL");
> 
> ---
> base-commit: 8f0b4cce4481fb22653697cced8d0d04027cb1e8
> change-id: 20251221-add-support-for-the-asus-hid-ec-a60b9a2d74b3
> 
> Best regards,


^ permalink raw reply

* [dtor-input:for-linus] BUILD SUCCESS ee89db004238bd0b034f2a6176e175561658750b
From: kernel test robot @ 2026-06-30 18:42 UTC (permalink / raw)
  To: Dmitry Torokhov; +Cc: linux-input

tree/branch: https://git.kernel.org/pub/scm/linux/kernel/git/dtor/input.git for-linus
branch HEAD: ee89db004238bd0b034f2a6176e175561658750b  Input: maplemouse - fix NULL pointer dereference in open()

elapsed time: 746m

configs tested: 284
configs skipped: 3

The following configs have been built successfully.
More configs may be tested in the coming days.

tested configs:
alpha                             allnoconfig    gcc-16.1.0
alpha                            allyesconfig    gcc-16.1.0
alpha                               defconfig    gcc-16.1.0
arc                              allmodconfig    clang-23
arc                              allmodconfig    gcc-16.1.0
arc                               allnoconfig    gcc-16.1.0
arc                              allyesconfig    clang-23
arc                              allyesconfig    gcc-16.1.0
arc                                 defconfig    gcc-16.1.0
arc                   randconfig-001-20260630    clang-23
arc                   randconfig-001-20260701    gcc-12.5.0
arc                   randconfig-002-20260630    clang-23
arc                   randconfig-002-20260701    gcc-12.5.0
arm                               allnoconfig    clang-23
arm                               allnoconfig    gcc-16.1.0
arm                              allyesconfig    clang-23
arm                              allyesconfig    gcc-16.1.0
arm                                 defconfig    gcc-16.1.0
arm                   randconfig-001-20260630    clang-23
arm                   randconfig-001-20260701    gcc-12.5.0
arm                   randconfig-002-20260630    clang-23
arm                   randconfig-002-20260701    gcc-12.5.0
arm                   randconfig-003-20260630    clang-23
arm                   randconfig-003-20260701    gcc-12.5.0
arm                   randconfig-004-20260630    clang-23
arm                   randconfig-004-20260701    gcc-12.5.0
arm64                            allmodconfig    clang-23
arm64                             allnoconfig    gcc-16.1.0
arm64                               defconfig    gcc-16.1.0
arm64                 randconfig-001-20260630    clang-23
arm64                 randconfig-002-20260630    clang-23
arm64                 randconfig-003-20260630    clang-23
arm64                 randconfig-004-20260630    clang-23
csky                             allmodconfig    gcc-16.1.0
csky                              allnoconfig    gcc-16.1.0
csky                                defconfig    gcc-16.1.0
csky                  randconfig-001-20260630    clang-23
csky                  randconfig-002-20260630    clang-23
hexagon                          allmodconfig    clang-23
hexagon                          allmodconfig    gcc-16.1.0
hexagon                           allnoconfig    clang-23
hexagon                           allnoconfig    gcc-16.1.0
hexagon                             defconfig    gcc-16.1.0
hexagon               randconfig-001-20260630    clang-18
hexagon               randconfig-002-20260630    clang-18
i386                             allmodconfig    clang-22
i386                             allmodconfig    gcc-14
i386                              allnoconfig    gcc-14
i386                              allnoconfig    gcc-16.1.0
i386                             allyesconfig    clang-22
i386                             allyesconfig    gcc-14
i386                 buildonly-randconfig-001    clang-22
i386        buildonly-randconfig-001-20260630    clang-22
i386        buildonly-randconfig-001-20260701    clang-22
i386                 buildonly-randconfig-002    clang-22
i386        buildonly-randconfig-002-20260630    clang-22
i386        buildonly-randconfig-002-20260701    clang-22
i386                 buildonly-randconfig-003    clang-22
i386        buildonly-randconfig-003-20260630    clang-22
i386        buildonly-randconfig-003-20260701    clang-22
i386                 buildonly-randconfig-004    clang-22
i386        buildonly-randconfig-004-20260630    clang-22
i386        buildonly-randconfig-004-20260701    clang-22
i386                 buildonly-randconfig-005    clang-22
i386        buildonly-randconfig-005-20260630    clang-22
i386        buildonly-randconfig-005-20260701    clang-22
i386                 buildonly-randconfig-006    clang-22
i386        buildonly-randconfig-006-20260630    clang-22
i386        buildonly-randconfig-006-20260701    clang-22
i386                                defconfig    gcc-16.1.0
i386                           randconfig-001    clang-22
i386                  randconfig-001-20260630    clang-22
i386                           randconfig-002    clang-22
i386                  randconfig-002-20260630    clang-22
i386                           randconfig-003    clang-22
i386                  randconfig-003-20260630    clang-22
i386                           randconfig-004    clang-22
i386                  randconfig-004-20260630    clang-22
i386                           randconfig-005    clang-22
i386                  randconfig-005-20260630    clang-22
i386                           randconfig-006    clang-22
i386                  randconfig-006-20260630    clang-22
i386                           randconfig-007    clang-22
i386                  randconfig-007-20260630    clang-22
i386                           randconfig-011    gcc-12
i386                  randconfig-011-20260630    gcc-12
i386                           randconfig-012    gcc-12
i386                  randconfig-012-20260630    gcc-12
i386                           randconfig-013    gcc-12
i386                  randconfig-013-20260630    gcc-12
i386                           randconfig-014    gcc-12
i386                  randconfig-014-20260630    gcc-12
i386                           randconfig-015    gcc-12
i386                  randconfig-015-20260630    gcc-12
i386                           randconfig-016    gcc-12
i386                  randconfig-016-20260630    gcc-12
i386                           randconfig-017    gcc-12
i386                  randconfig-017-20260630    gcc-12
loongarch                        allmodconfig    clang-19
loongarch                        allmodconfig    clang-23
loongarch                         allnoconfig    clang-20
loongarch                         allnoconfig    gcc-16.1.0
loongarch                           defconfig    clang-23
loongarch             randconfig-001-20260630    clang-18
loongarch             randconfig-002-20260630    clang-18
m68k                             alldefconfig    gcc-16.1.0
m68k                             allmodconfig    gcc-16.1.0
m68k                              allnoconfig    gcc-16.1.0
m68k                             allyesconfig    clang-23
m68k                             allyesconfig    gcc-16.1.0
m68k                                defconfig    clang-23
microblaze                        allnoconfig    gcc-16.1.0
microblaze                       allyesconfig    gcc-16.1.0
microblaze                          defconfig    clang-23
mips                             allmodconfig    gcc-16.1.0
mips                              allnoconfig    gcc-16.1.0
mips                             allyesconfig    gcc-16.1.0
mips                      bmips_stb_defconfig    clang-17
mips                      malta_kvm_defconfig    gcc-16.1.0
nios2                            allmodconfig    clang-20
nios2                            allmodconfig    gcc-11.5.0
nios2                             allnoconfig    clang-23
nios2                             allnoconfig    gcc-11.5.0
nios2                               defconfig    clang-23
nios2                 randconfig-001-20260630    clang-18
nios2                 randconfig-002-20260630    clang-18
openrisc                         allmodconfig    clang-20
openrisc                         allmodconfig    gcc-16.1.0
openrisc                          allnoconfig    clang-23
openrisc                          allnoconfig    gcc-16.1.0
openrisc                            defconfig    gcc-16.1.0
parisc                           allmodconfig    gcc-16.1.0
parisc                            allnoconfig    clang-23
parisc                            allnoconfig    gcc-16.1.0
parisc                           allyesconfig    clang-17
parisc                           allyesconfig    gcc-16.1.0
parisc                              defconfig    gcc-16.1.0
parisc                randconfig-001-20260630    clang-22
parisc                randconfig-001-20260701    clang-17
parisc                randconfig-002-20260630    clang-22
parisc                randconfig-002-20260701    clang-17
parisc64                            defconfig    clang-23
powerpc                          allmodconfig    gcc-16.1.0
powerpc                           allnoconfig    clang-23
powerpc                           allnoconfig    gcc-16.1.0
powerpc               randconfig-001-20260630    clang-22
powerpc               randconfig-001-20260701    clang-17
powerpc               randconfig-002-20260630    clang-22
powerpc               randconfig-002-20260701    clang-17
powerpc64             randconfig-001-20260630    clang-22
powerpc64             randconfig-001-20260701    clang-17
powerpc64             randconfig-002-20260630    clang-22
powerpc64             randconfig-002-20260701    clang-17
riscv                            allmodconfig    clang-23
riscv                             allnoconfig    clang-23
riscv                             allnoconfig    gcc-16.1.0
riscv                            allyesconfig    clang-23
riscv                               defconfig    gcc-16.1.0
riscv                          randconfig-001    gcc-9.5.0
riscv                 randconfig-001-20260630    gcc-9.5.0
riscv                          randconfig-002    gcc-9.5.0
riscv                 randconfig-002-20260630    gcc-9.5.0
s390                             allmodconfig    clang-17
s390                             allmodconfig    clang-23
s390                              allnoconfig    clang-23
s390                             allyesconfig    gcc-16.1.0
s390                                defconfig    gcc-16.1.0
s390                           randconfig-001    gcc-9.5.0
s390                  randconfig-001-20260630    gcc-9.5.0
s390                           randconfig-002    gcc-9.5.0
s390                  randconfig-002-20260630    gcc-9.5.0
sh                               allmodconfig    gcc-16.1.0
sh                                allnoconfig    clang-23
sh                                allnoconfig    gcc-16.1.0
sh                               allyesconfig    clang-17
sh                               allyesconfig    gcc-16.1.0
sh                                  defconfig    gcc-14
sh                             randconfig-001    gcc-9.5.0
sh                    randconfig-001-20260630    gcc-9.5.0
sh                             randconfig-002    gcc-9.5.0
sh                    randconfig-002-20260630    gcc-9.5.0
sh                           se7750_defconfig    gcc-16.1.0
sparc                             allnoconfig    clang-23
sparc                             allnoconfig    gcc-16.1.0
sparc                               defconfig    gcc-16.1.0
sparc                          randconfig-001    clang-17
sparc                 randconfig-001-20260630    clang-17
sparc                          randconfig-002    clang-17
sparc                 randconfig-002-20260630    clang-17
sparc64                          allmodconfig    clang-20
sparc64                             defconfig    gcc-14
sparc64                        randconfig-001    clang-17
sparc64               randconfig-001-20260630    clang-17
sparc64                        randconfig-002    clang-17
sparc64               randconfig-002-20260630    clang-17
um                               allmodconfig    clang-17
um                               allmodconfig    clang-23
um                                allnoconfig    clang-16
um                                allnoconfig    clang-23
um                               allyesconfig    gcc-14
um                               allyesconfig    gcc-16.1.0
um                                  defconfig    gcc-14
um                             i386_defconfig    gcc-14
um                             randconfig-001    clang-17
um                    randconfig-001-20260630    clang-17
um                             randconfig-002    clang-17
um                    randconfig-002-20260630    clang-17
um                           x86_64_defconfig    gcc-14
x86_64                           allmodconfig    clang-22
x86_64                            allnoconfig    clang-22
x86_64                            allnoconfig    clang-23
x86_64                           allyesconfig    clang-22
x86_64               buildonly-randconfig-001    clang-22
x86_64      buildonly-randconfig-001-20260630    clang-22
x86_64               buildonly-randconfig-002    clang-22
x86_64      buildonly-randconfig-002-20260630    clang-22
x86_64      buildonly-randconfig-002-20260630    gcc-14
x86_64               buildonly-randconfig-003    clang-22
x86_64      buildonly-randconfig-003-20260630    clang-22
x86_64               buildonly-randconfig-004    clang-22
x86_64      buildonly-randconfig-004-20260630    clang-22
x86_64               buildonly-randconfig-005    clang-22
x86_64      buildonly-randconfig-005-20260630    clang-22
x86_64               buildonly-randconfig-006    clang-22
x86_64      buildonly-randconfig-006-20260630    clang-22
x86_64                              defconfig    gcc-14
x86_64                                  kexec    clang-22
x86_64                         randconfig-001    gcc-14
x86_64                randconfig-001-20260630    gcc-14
x86_64                         randconfig-002    gcc-14
x86_64                randconfig-002-20260630    gcc-14
x86_64                         randconfig-003    gcc-14
x86_64                randconfig-003-20260630    gcc-14
x86_64                         randconfig-004    gcc-14
x86_64                randconfig-004-20260630    gcc-14
x86_64                         randconfig-005    gcc-14
x86_64                randconfig-005-20260630    gcc-14
x86_64                         randconfig-006    gcc-14
x86_64                randconfig-006-20260630    gcc-14
x86_64                randconfig-011-20260630    gcc-14
x86_64                randconfig-012-20260630    gcc-14
x86_64                randconfig-013-20260630    gcc-14
x86_64                randconfig-014-20260630    gcc-14
x86_64                randconfig-015-20260630    gcc-14
x86_64                randconfig-016-20260630    gcc-14
x86_64                         randconfig-071    gcc-13
x86_64                randconfig-071-20260630    clang-22
x86_64                randconfig-071-20260630    gcc-13
x86_64                randconfig-071-20260701    gcc-14
x86_64                         randconfig-072    gcc-13
x86_64                randconfig-072-20260630    clang-22
x86_64                randconfig-072-20260630    gcc-13
x86_64                randconfig-072-20260701    gcc-14
x86_64                         randconfig-073    gcc-13
x86_64                randconfig-073-20260630    clang-22
x86_64                randconfig-073-20260630    gcc-13
x86_64                randconfig-073-20260701    gcc-14
x86_64                         randconfig-074    gcc-13
x86_64                randconfig-074-20260630    clang-22
x86_64                randconfig-074-20260630    gcc-13
x86_64                randconfig-074-20260701    gcc-14
x86_64                         randconfig-075    gcc-13
x86_64                randconfig-075-20260630    clang-22
x86_64                randconfig-075-20260630    gcc-13
x86_64                randconfig-075-20260701    gcc-14
x86_64                         randconfig-076    gcc-13
x86_64                randconfig-076-20260630    clang-22
x86_64                randconfig-076-20260630    gcc-13
x86_64                randconfig-076-20260701    gcc-14
x86_64                               rhel-9.4    clang-22
x86_64                           rhel-9.4-bpf    gcc-14
x86_64                          rhel-9.4-func    clang-22
x86_64                    rhel-9.4-kselftests    clang-22
x86_64                         rhel-9.4-kunit    gcc-14
x86_64                           rhel-9.4-ltp    gcc-14
x86_64                          rhel-9.4-rust    clang-22
xtensa                            allnoconfig    clang-23
xtensa                            allnoconfig    gcc-16.1.0
xtensa                           allyesconfig    clang-20
xtensa                         randconfig-001    clang-17
xtensa                randconfig-001-20260630    clang-17
xtensa                         randconfig-002    clang-17
xtensa                randconfig-002-20260630    clang-17
xtensa                    smp_lx200_defconfig    gcc-16.1.0

--
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki

^ permalink raw reply

* Re: [PATCH] Input: maplemouse - set driver data before registering input device
From: Florian Fuchs @ 2026-06-30 19:15 UTC (permalink / raw)
  To: Dmitry Torokhov; +Cc: linux-input, Adrian McMenamin, linux-kernel
In-Reply-To: <akNXw45L_8bxD6QV@google.com>

On 29 Jun 22:47, Dmitry Torokhov wrote:
> Set maple driver data before calling input_register_device() to
> ensure that it is available if the device is opened immediately and
> the callback is triggered.
> 
> Cc: stable@vger.kernel.org
> Assisted-by: Antigravity:gemini-3.5-flash
> Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
> ---
>  drivers/input/mouse/maplemouse.c | 4 +++-
>  1 file changed, 3 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/input/mouse/maplemouse.c b/drivers/input/mouse/maplemouse.c
> index c41182766538..0c8f7d1b02aa 100644
> --- a/drivers/input/mouse/maplemouse.c
> +++ b/drivers/input/mouse/maplemouse.c
> @@ -88,6 +88,8 @@ static int probe_maple_mouse(struct device *dev)
>  	mse->dev = input_dev;
>  	mse->mdev = mdev;
>  
> +	maple_set_drvdata(mdev, mse);
> +
>  	input_set_drvdata(input_dev, mse);
>  	input_dev->evbit[0] = BIT_MASK(EV_KEY) | BIT_MASK(EV_REL);
>  	input_dev->keybit[BIT_WORD(BTN_MOUSE)] = BIT_MASK(BTN_LEFT) |
> @@ -103,12 +105,12 @@ static int probe_maple_mouse(struct device *dev)
>  		goto fail_register;
>  
>  	mdev->driver = mdrv;
> -	maple_set_drvdata(mdev, mse);
>  
>  	return error;
>  
>  fail_register:
>  	input_free_device(input_dev);
> +	maple_set_drvdata(mdev, NULL);
>  fail_nomem:
>  	kfree(mse);
>  fail:
> -- 
> 2.55.0.rc0.799.gd6f94ed593-goog
> 
> 
> -- 
> Dmitry

Tested-by: Florian Fuchs <fuchsfl@gmail.com>

Regards
Florian

^ permalink raw reply

* Re: [PATCH] Input: maplecontrol - set driver data before registering input device
From: Florian Fuchs @ 2026-06-30 19:15 UTC (permalink / raw)
  To: Dmitry Torokhov; +Cc: Adrian McMenamin, linux-input, linux-kernel
In-Reply-To: <akNYib9hQFNN1fA9@google.com>

On 29 Jun 22:49, Dmitry Torokhov wrote:
> Set maple driver data before calling input_register_device() to
> ensure that it is available if the device is opened immediately and
> the callback is triggered.
> 
> Cc: stable@vger.kernel.org
> Assisted-by: Antigravity:gemini-3.5-flash
> Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
> ---
>  drivers/input/joystick/maplecontrol.c | 3 ++-
>  1 file changed, 2 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/input/joystick/maplecontrol.c b/drivers/input/joystick/maplecontrol.c
> index 7f36f73844a9..6293b6e8148b 100644
> --- a/drivers/input/joystick/maplecontrol.c
> +++ b/drivers/input/joystick/maplecontrol.c
> @@ -112,6 +112,8 @@ static int probe_maple_controller(struct device *dev)
>  	pad->dev = idev;
>  	pad->mdev = mdev;
>  
> +	maple_set_drvdata(mdev, pad);
> +
>  	idev->open = dc_pad_open;
>  	idev->close = dc_pad_close;
>  
> @@ -146,7 +148,6 @@ static int probe_maple_controller(struct device *dev)
>  		goto fail;
>  
>  	mdev->driver = mdrv;
> -	maple_set_drvdata(mdev, pad);
>  
>  	return 0;
>  
> -- 
> 2.55.0.rc0.799.gd6f94ed593-goog
> 
> 
> -- 
> Dmitry

Tested-by: Florian Fuchs <fuchsfl@gmail.com>

Regards
Florian

^ permalink raw reply

* [PATCH] HID: hiddev: set report-init policy before device registration
From: Yousef Alhouseen @ 2026-06-30 21:18 UTC (permalink / raw)
  To: Jiri Kosina, Benjamin Tissoires
  Cc: linux-usb, linux-input, linux-kernel, Yousef Alhouseen

usb_register_dev() publishes the hiddev character device before
hiddev_connect() initializes the report policy. A process that opens the
new node immediately can issue a usage ioctl while initialized is still
false and trigger usbhid_init_reports(), bypassing
HID_QUIRK_NO_INIT_REPORTS.

Set initialized before registering the character device so every opener
observes the quirk-selected policy.

Signed-off-by: Yousef Alhouseen <alhouseenyousef@gmail.com>
---
 drivers/hid/usbhid/hiddev.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/hid/usbhid/hiddev.c b/drivers/hid/usbhid/hiddev.c
index 6378801b22c6..c822e7dee8b7 100644
--- a/drivers/hid/usbhid/hiddev.c
+++ b/drivers/hid/usbhid/hiddev.c
@@ -900,6 +900,8 @@ int hiddev_connect(struct hid_device *hid, unsigned int force)
 	hid->hiddev = hiddev;
 	hiddev->hid = hid;
 	hiddev->exist = 1;
+	/* Honor NO_INIT_REPORTS before the character device becomes visible. */
+	hiddev->initialized = hid->quirks & HID_QUIRK_NO_INIT_REPORTS;
 	retval = usb_register_dev(usbhid->intf, &hiddev_class);
 	if (retval) {
 		hid_err(hid, "Not able to get a minor for this device\n");
@@ -908,12 +910,6 @@ int hiddev_connect(struct hid_device *hid, unsigned int force)
 		return retval;
 	}
 
-	/*
-	 * If HID_QUIRK_NO_INIT_REPORTS is set, make sure we don't initialize
-	 * the reports.
-	 */
-	hiddev->initialized = hid->quirks & HID_QUIRK_NO_INIT_REPORTS;
-
 	hiddev->minor = usbhid->intf->minor;
 
 	return 0;
-- 
2.55.0


^ permalink raw reply related

* Re: [PATCH 00/13] treewide: replace linux/gpio.h
From: Linus Walleij @ 2026-06-30 21:39 UTC (permalink / raw)
  To: Arnd Bergmann
  Cc: linux-gpio, Arnd Bergmann, Bartosz Golaszewski, Andrew Lunn,
	Sebastian Hesselbarth, Gregory Clement, Frank Li, Robert Jarzmik,
	Krzysztof Kozlowski, Greg Ungerer, Thomas Bogendoerfer,
	Hauke Mehrtens, Rafał Miłecki, Yoshinori Sato,
	John Paul Adrian Glaubitz, Dmitry Torokhov, Jakub Kicinski,
	Paolo Abeni, Dominik Brodowski, linux-kernel, linux-arm-kernel,
	linux-samsung-soc, patches, linux-m68k, linux-mips, linux-sh,
	linux-input, linux-media, netdev, linux-sunxi, linux-phy,
	linux-rockchip, linux-sound
In-Reply-To: <20260629132633.1300009-1-arnd@kernel.org>

On Mon, Jun 29, 2026 at 3:26 PM Arnd Bergmann <arnd@kernel.org> wrote:

> From: Arnd Bergmann <arnd@arndb.de>
>
> The linux/gpio.h header used to be the global definition for the gpio
> interfaces, with 1100 users back in linux-3.17. In linux-7.2, only about
> 130 of those remain, so this series cleans out the rest.
>
> In each subsystem, we can replace the header either with
> linux/gpio/consumer.h for users of the modern gpio descriptor interface,
> or linux/gpio/legacy.h for the few remaining users of the old number
> based interface.
>
> All patches in this series can get applied independently, so my
> preference would be for each subsystem maintainer to apply these
> directly, with the rest going into the gpio tree at some point.
>
> The final patch here obviously needs to wait for all the others
> to get merged first.

This is helpful.
The series:
Reviewed-by: Linus Walleij <linusw@kernel.org>

Yours,
Linus Walleij

^ permalink raw reply

* Re: [PATCH 03/13] mips: replace linux/gpio.h inclusions
From: Philippe Mathieu-Daudé @ 2026-06-30 22:08 UTC (permalink / raw)
  To: Arnd Bergmann, linux-gpio
  Cc: Arnd Bergmann, Bartosz Golaszewski, Andrew Lunn,
	Sebastian Hesselbarth, Gregory Clement, Frank Li, Robert Jarzmik,
	Krzysztof Kozlowski, Greg Ungerer, Thomas Bogendoerfer,
	Hauke Mehrtens, Rafał Miłecki, Yoshinori Sato,
	John Paul Adrian Glaubitz, Linus Walleij, Dmitry Torokhov,
	Jakub Kicinski, Paolo Abeni, Dominik Brodowski, linux-kernel,
	linux-arm-kernel, linux-samsung-soc, patches, linux-m68k,
	linux-mips, linux-sh, linux-input, linux-media, netdev,
	linux-sunxi, linux-phy, linux-rockchip, linux-sound
In-Reply-To: <20260629132633.1300009-4-arnd@kernel.org>

On 29/6/26 15:26, Arnd Bergmann wrote:
> From: Arnd Bergmann <arnd@arndb.de>
> 
> linux/gpio.h should no longer be used, convert these instead to
> either linux/gpio/consumer.h or linux/gpio/legacy.h as needed.
> 
> Signed-off-by: Arnd Bergmann <arnd@arndb.de>
> ---
>   arch/mips/alchemy/board-xxs1500.c                   | 2 +-
>   arch/mips/alchemy/devboards/db1000.c                | 2 +-
>   arch/mips/alchemy/devboards/db1200.c                | 2 +-
>   arch/mips/alchemy/devboards/db1550.c                | 2 +-
>   arch/mips/bcm47xx/workarounds.c                     | 2 +-
>   arch/mips/bcm63xx/boards/board_bcm963xx.c           | 1 +
>   arch/mips/include/asm/mach-bcm63xx/board_bcm963xx.h | 2 +-
>   arch/mips/txx9/rbtx4927/setup.c                     | 2 +-
>   8 files changed, 8 insertions(+), 7 deletions(-)

Reviewed-by: Philippe Mathieu-Daudé <philmd@oss.qualcomm.com>

^ permalink raw reply

* Re: [PATCH 04/13] sh: replace linux/gpio.h inclusions
From: Philippe Mathieu-Daudé @ 2026-06-30 22:08 UTC (permalink / raw)
  To: Arnd Bergmann, linux-gpio
  Cc: Arnd Bergmann, Bartosz Golaszewski, Andrew Lunn,
	Sebastian Hesselbarth, Gregory Clement, Frank Li, Robert Jarzmik,
	Krzysztof Kozlowski, Greg Ungerer, Thomas Bogendoerfer,
	Hauke Mehrtens, Rafał Miłecki, Yoshinori Sato,
	John Paul Adrian Glaubitz, Linus Walleij, Dmitry Torokhov,
	Jakub Kicinski, Paolo Abeni, Dominik Brodowski, linux-kernel,
	linux-arm-kernel, linux-samsung-soc, patches, linux-m68k,
	linux-mips, linux-sh, linux-input, linux-media, netdev,
	linux-sunxi, linux-phy, linux-rockchip, linux-sound
In-Reply-To: <20260629132633.1300009-5-arnd@kernel.org>

On 29/6/26 15:26, Arnd Bergmann wrote:
> From: Arnd Bergmann <arnd@arndb.de>
> 
> linux/gpio.h should no longer be used, convert these instead to
> linux/gpio/legacy.h for the sh boards using the legacy interfaces,
> or remove it where it is not needed at all.
> 
> Signed-off-by: Arnd Bergmann <arnd@arndb.de>
> ---
>   arch/sh/boards/board-magicpanelr2.c             | 2 +-
>   arch/sh/boards/board-sh7757lcr.c                | 2 +-
>   arch/sh/boards/board-urquell.c                  | 2 +-
>   arch/sh/boards/mach-ap325rxa/setup.c            | 2 +-
>   arch/sh/boards/mach-ecovec24/setup.c            | 2 +-
>   arch/sh/boards/mach-highlander/pinmux-r7785rp.c | 2 +-
>   arch/sh/boards/mach-kfr2r09/lcd_wqvga.c         | 2 +-
>   arch/sh/boards/mach-kfr2r09/setup.c             | 2 +-
>   arch/sh/boards/mach-migor/lcd_qvga.c            | 2 +-
>   arch/sh/boards/mach-migor/setup.c               | 2 +-
>   arch/sh/boards/mach-rsk/devices-rsk7203.c       | 2 +-
>   arch/sh/boards/mach-rsk/devices-rsk7269.c       | 1 -
>   arch/sh/boards/mach-se/7724/setup.c             | 2 +-
>   arch/sh/include/mach-common/mach/magicpanelr2.h | 2 --
>   arch/sh/kernel/cpu/sh4a/setup-shx3.c            | 2 +-
>   15 files changed, 13 insertions(+), 16 deletions(-)

Reviewed-by: Philippe Mathieu-Daudé <philmd@oss.qualcomm.com>

^ permalink raw reply

* Re: [PATCH 13/13] gpiolib: remove linux/gpio.h
From: Philippe Mathieu-Daudé @ 2026-06-30 22:09 UTC (permalink / raw)
  To: Arnd Bergmann, linux-gpio
  Cc: Arnd Bergmann, Bartosz Golaszewski, Andrew Lunn,
	Sebastian Hesselbarth, Gregory Clement, Frank Li, Robert Jarzmik,
	Krzysztof Kozlowski, Greg Ungerer, Thomas Bogendoerfer,
	Hauke Mehrtens, Rafał Miłecki, Yoshinori Sato,
	John Paul Adrian Glaubitz, Linus Walleij, Dmitry Torokhov,
	Jakub Kicinski, Paolo Abeni, Dominik Brodowski, linux-kernel,
	linux-arm-kernel, linux-samsung-soc, patches, linux-m68k,
	linux-mips, linux-sh, linux-input, linux-media, netdev,
	linux-sunxi, linux-phy, linux-rockchip, linux-sound
In-Reply-To: <20260629132633.1300009-14-arnd@kernel.org>

On 29/6/26 15:26, Arnd Bergmann wrote:
> From: Arnd Bergmann <arnd@arndb.de>
> 
> After all other drivers have converted to linux/gpio/consumer.h
> or linux/gpio/legacy.h, remove the final leftover bits here.
> 
> Signed-off-by: Arnd Bergmann <arnd@arndb.de>
> ---
>   MAINTAINERS                   |  1 -
>   drivers/gpio/TODO             |  4 +---
>   drivers/gpio/gpiolib-cdev.c   |  2 +-
>   drivers/gpio/gpiolib-legacy.c |  3 +--
>   drivers/gpio/gpiolib.c        |  2 +-
>   include/linux/gpio.h          | 22 ----------------------
>   6 files changed, 4 insertions(+), 30 deletions(-)
>   delete mode 100644 include/linux/gpio.h

Reviewed-by: Philippe Mathieu-Daudé <philmd@oss.qualcomm.com>

^ permalink raw reply

* Re: [PATCH v4 1/3] HID: wacom: Fix Use-After-Free in wacom_intuos_pad
From: Jason Gerecke @ 2026-06-30 23:27 UTC (permalink / raw)
  To: Lee Jones
  Cc: Ping Cheng, Jason Gerecke, Jiri Kosina, Benjamin Tissoires,
	Peter Hutterer, Dmitry Torokhov, linux-input, linux-kernel
In-Reply-To: <20260616092658.1714548-1-lee@kernel.org>

I'm still working on testing and reviewing this set as a whole, but I
can provide some immediate feedback on this first patch at least:

On Tue, Jun 16, 2026 at 2:29 AM Lee Jones <lee@kernel.org> wrote:
>
> wacom_intuos_pad() accesses wacom->shared->touch_input locklessly
> inside the interrupt handler context.  If the Touch sibling device
> is disconnected, wacom_remove_shared_data() clears 'touch_input'
> outside any lock, creating a Time-of-Check to Time-of-Use (TOCTOU)
> race condition where a preempted reader in interrupt context
> dereferences the freed pointer, leading to a Use-After-Free.
>
> Resolve this by introducing RCU protection for the touch_input
> pointer:
>
>  - Annotate 'touch_input' in wacom_shared struct with __rcu
>  - Wrap all lockless readers in wacom_wac.c with rcu_read_lock() and
>    rcu_dereference() using a unified wacom_report_touch_mute()
>    helper
>  - Update writers in wacom_sys.c using rcu_assign_pointer()
>  - Call synchronize_rcu() in wacom_remove_shared_data() to ensure
>    all active RCU readers have finished before the input device is
>    freed
>
> Also wrap wacom_set_shared_values() and touch/pen assignments in
> wacom_add_shared_data() inside the wacom_udev_list_lock to serialize
> concurrent probe assignments, and verify that 'shared->touch == hdev'
> before setting touch_input to prevent concurrent sibling probe state
> desynchronization.
>
> Finally, advertise the SW_MUTE_DEVICE capability on Touch input
> devices prior to registration in wacom_setup_touch_input_capabilities()
> to prevent invalid post-registration capability modifications.
>

It seems like this patch can be split into at least two different
patches, maybe even three. The changes to
wacom_setup_touch_input_capabilities() especially feel like they could
be seperate from the introduction of RCU for shared->touch_input.

> Fixes: 961794a00eab ("Input: wacom - add reporting of SW_MUTE_DEVICE events")
> Signed-off-by: Lee Jones <lee@kernel.org>
> ---
>
> v1 -> v2: Split and use RCU as per Dmitry's review
> v2 -> v3: Sashiko fixes
> v3 -> v4: Dmitry's review [redundant check and guard()]
>
>  drivers/hid/wacom_sys.c | 41 ++++++++++++++-----------
>  drivers/hid/wacom_wac.c | 66 +++++++++++++++++++++--------------------
>  drivers/hid/wacom_wac.h |  2 +-
>  3 files changed, 58 insertions(+), 51 deletions(-)
>
> diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c
> index 2220168bf116..86895f13dbae 100644
> --- a/drivers/hid/wacom_sys.c
> +++ b/drivers/hid/wacom_sys.c
> @@ -877,10 +877,16 @@ static void wacom_remove_shared_data(void *res)
>                 data = container_of(wacom_wac->shared, struct wacom_hdev_data,
>                                     shared);
>
> -               if (wacom_wac->shared->touch == wacom->hdev)
> -                       wacom_wac->shared->touch = NULL;
> -               else if (wacom_wac->shared->pen == wacom->hdev)
> -                       wacom_wac->shared->pen = NULL;
> +               scoped_guard(mutex, &wacom_udev_list_lock) {
> +                       if (wacom_wac->shared->touch == wacom->hdev) {
> +                               wacom_wac->shared->touch = NULL;
> +                               rcu_assign_pointer(wacom_wac->shared->touch_input, NULL);
> +                       } else if (wacom_wac->shared->pen == wacom->hdev) {
> +                               wacom_wac->shared->pen = NULL;
> +                       }
> +               }
> +
> +               synchronize_rcu();
>
>                 kref_put(&data->kref, wacom_release_shared_data);
>                 wacom_wac->shared = NULL;
> @@ -909,6 +915,11 @@ static int wacom_add_shared_data(struct hid_device *hdev)
>                 list_add_tail(&data->list, &wacom_udev_list);
>         }
>
> +       if (wacom_wac->features.device_type & WACOM_DEVICETYPE_TOUCH)
> +               data->shared.touch = hdev;
> +       else if (wacom_wac->features.device_type & WACOM_DEVICETYPE_PEN)
> +               data->shared.pen = hdev;
> +
>         mutex_unlock(&wacom_udev_list_lock);
>
>         wacom_wac->shared = &data->shared;
> @@ -917,11 +928,6 @@ static int wacom_add_shared_data(struct hid_device *hdev)
>         if (retval)
>                 return retval;
>
> -       if (wacom_wac->features.device_type & WACOM_DEVICETYPE_TOUCH)
> -               wacom_wac->shared->touch = hdev;
> -       else if (wacom_wac->features.device_type & WACOM_DEVICETYPE_PEN)
> -               wacom_wac->shared->pen = hdev;
> -
>         return retval;
>  }
>
> @@ -2345,9 +2351,15 @@ static void wacom_release_resources(struct wacom *wacom)
>
>  static void wacom_set_shared_values(struct wacom_wac *wacom_wac)
>  {
> +       struct wacom *wacom = container_of(wacom_wac, struct wacom, wacom_wac);
> +
> +       guard(mutex)(&wacom_udev_list_lock);
> +
>         if (wacom_wac->features.device_type & WACOM_DEVICETYPE_TOUCH) {
> -               wacom_wac->shared->type = wacom_wac->features.type;
> -               wacom_wac->shared->touch_input = wacom_wac->touch_input;
> +               if (wacom_wac->shared->touch == wacom->hdev) {
> +                       wacom_wac->shared->type = wacom_wac->features.type;
> +                       rcu_assign_pointer(wacom_wac->shared->touch_input, wacom_wac->touch_input);
> +               }
>         }
>
>         if (wacom_wac->has_mute_touch_switch) {
> @@ -2360,13 +2372,6 @@ static void wacom_set_shared_values(struct wacom_wac *wacom_wac)
>                 if (wacom_wac->is_soft_touch_switch)
>                         wacom_wac->shared->is_touch_on = true;
>         }
> -
> -       if (wacom_wac->shared->has_mute_touch_switch &&
> -           wacom_wac->shared->touch_input) {
> -               set_bit(EV_SW, wacom_wac->shared->touch_input->evbit);
> -               input_set_capability(wacom_wac->shared->touch_input, EV_SW,
> -                                    SW_MUTE_DEVICE);
> -       }
>  }
>
>  static int wacom_parse_and_register(struct wacom *wacom, bool wireless)
> diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c
> index da1f0ea85625..23eaa81cd827 100644
> --- a/drivers/hid/wacom_wac.c
> +++ b/drivers/hid/wacom_wac.c
> @@ -510,6 +510,18 @@ static void wacom_intuos_schedule_prox_event(struct wacom_wac *wacom_wac)
>         }
>  }
>
> +static void wacom_report_touch_mute(struct wacom_wac *wacom_wac, bool mute)
> +{
> +       struct input_dev *touch_input;
> +
> +       guard(rcu)();
> +       touch_input = rcu_dereference(wacom_wac->shared->touch_input);
> +       if (touch_input) {
> +               input_report_switch(touch_input, SW_MUTE_DEVICE, mute);
> +               input_sync(touch_input);
> +       }
> +}
> +
>  static int wacom_intuos_pad(struct wacom_wac *wacom)
>  {
>         struct wacom_features *features = &wacom->features;
> @@ -650,12 +662,8 @@ static int wacom_intuos_pad(struct wacom_wac *wacom)
>         input_report_key(input, KEY_CONTROLPANEL, menu);
>         input_report_key(input, KEY_INFO, info);
>
> -       if (wacom->shared && wacom->shared->touch_input) {
> -               input_report_switch(wacom->shared->touch_input,
> -                                   SW_MUTE_DEVICE,
> -                                   !wacom->shared->is_touch_on);
> -               input_sync(wacom->shared->touch_input);
> -       }
> +       if (wacom->shared)
> +               wacom_report_touch_mute(wacom, !wacom->shared->is_touch_on);
>
>         input_report_abs(input, ABS_RX, strip1);
>         input_report_abs(input, ABS_RY, strip2);
> @@ -2153,7 +2161,7 @@ static void wacom_wac_pad_event(struct hid_device *hdev, struct hid_field *field
>          */
>         if ((equivalent_usage == WACOM_HID_WD_MUTE_DEVICE) ||
>            (equivalent_usage == WACOM_HID_WD_TOUCHONOFF)) {
> -               if (wacom_wac->shared->touch_input) {
> +               if (wacom_wac->shared) {
>                         bool *is_touch_on = &wacom_wac->shared->is_touch_on;
>
>                         if (equivalent_usage == WACOM_HID_WD_MUTE_DEVICE && value)
> @@ -2161,9 +2169,7 @@ static void wacom_wac_pad_event(struct hid_device *hdev, struct hid_field *field
>                         else if (equivalent_usage == WACOM_HID_WD_TOUCHONOFF)
>                                 *is_touch_on = value;
>
> -                       input_report_switch(wacom_wac->shared->touch_input,
> -                                           SW_MUTE_DEVICE, !(*is_touch_on));
> -                       input_sync(wacom_wac->shared->touch_input);
> +                       wacom_report_touch_mute(wacom_wac, !(*is_touch_on));
>                 }
>                 return;
>         }
> @@ -3381,11 +3387,8 @@ static int wacom_wireless_irq(struct wacom_wac *wacom, size_t len)
>
>                 if ((wacom->shared->type == INTUOSHT ||
>                     wacom->shared->type == INTUOSHT2) &&
> -                   wacom->shared->touch_input &&
>                     wacom->shared->touch_max) {
> -                       input_report_switch(wacom->shared->touch_input,
> -                                       SW_MUTE_DEVICE, data[5] & 0x40);
> -                       input_sync(wacom->shared->touch_input);
> +                       wacom_report_touch_mute(wacom, data[5] & 0x40);
>                 }
>
>                 pid = get_unaligned_be16(&data[6]);
> @@ -3420,11 +3423,8 @@ static int wacom_status_irq(struct wacom_wac *wacom_wac, size_t len)
>
>         if ((features->type == INTUOSHT ||
>             features->type == INTUOSHT2) &&
> -           wacom_wac->shared->touch_input &&
>             features->touch_max) {
> -               input_report_switch(wacom_wac->shared->touch_input,
> -                                   SW_MUTE_DEVICE, data[8] & 0x40);
> -               input_sync(wacom_wac->shared->touch_input);
> +               wacom_report_touch_mute(wacom_wac, data[8] & 0x40);
>         }
>
>         if (data[9] & 0x02) { /* wireless module is attached */
> @@ -3951,11 +3951,22 @@ int wacom_setup_pen_input_capabilities(struct input_dev *input_dev,
>  int wacom_setup_touch_input_capabilities(struct input_dev *input_dev,
>                                          struct wacom_wac *wacom_wac)
>  {
> +       struct wacom *wacom = container_of(wacom_wac, struct wacom, wacom_wac);
> +       struct hid_device *hdev = wacom->hdev;
>         struct wacom_features *features = &wacom_wac->features;
>
>         if (!(features->device_type & WACOM_DEVICETYPE_TOUCH))
>                 return -ENODEV;
>
> +       if (features->type != TABLETPC &&
> +           features->type != TABLETPC2FG &&
> +           features->type != MTSCREEN &&
> +           features->type != MTTPC &&
> +           features->type != MTTPC_B) {
> +               input_dev->evbit[0] |= BIT_MASK(EV_SW);
> +               __set_bit(SW_MUTE_DEVICE, input_dev->swbit);
> +       }
> +

1. This if statement is missing a number of cases. INTUOS5, for
example (and among others) is missing and would incorrectly gain
SW_MUTE_DEVICE. The list of cases from the big switch below needs to
be consulted again.

2. It seems like this would result in SW_MUTE_DEVICE being given to
all HID_GENERIC touch devices. It should only be added in the case
that `wacom_wac->has_mute_touch_switch` is true, however.

3. I'm not sure why we're even bothering with moving all of the
initialization for SW_MUTE_DEVICE from the individual cases out to a
single awkward if statement. The only thing I can think of is that
HID_GENERIC devices need to have it set (when appropriate) now that
the responsibility has been removed from wacom_set_shared_values(). It
should be much cleaner, however, to simply add the SW_MUTE_DEVICE
setup for HID_GENERIC devices right before the function returns early
for them.

>         if (features->device_type & WACOM_DEVICETYPE_DIRECT)
>                 __set_bit(INPUT_PROP_DIRECT, input_dev->propbit);
>         else
> @@ -3992,22 +4003,17 @@ int wacom_setup_touch_input_capabilities(struct input_dev *input_dev,
>         switch (features->type) {
>         case INTUOSP2_BT:
>         case INTUOSP2S_BT:
> -               input_dev->evbit[0] |= BIT_MASK(EV_SW);
> -               __set_bit(SW_MUTE_DEVICE, input_dev->swbit);
> -
> -               if (wacom_wac->shared->touch->product == 0x361) {
> +               if (hdev->product == 0x361) {
>                         input_set_abs_params(input_dev, ABS_MT_POSITION_X,
>                                              0, 12440, 4, 0);
>                         input_set_abs_params(input_dev, ABS_MT_POSITION_Y,
>                                              0, 8640, 4, 0);
> -               }
> -               else if (wacom_wac->shared->touch->product == 0x360) {
> +               } else if (hdev->product == 0x360) {
>                         input_set_abs_params(input_dev, ABS_MT_POSITION_X,
>                                              0, 8960, 4, 0);
>                         input_set_abs_params(input_dev, ABS_MT_POSITION_Y,
>                                              0, 5920, 4, 0);
> -               }
> -               else if (wacom_wac->shared->touch->product == 0x393) {
> +               } else if (hdev->product == 0x393) {
>                         input_set_abs_params(input_dev, ABS_MT_POSITION_X,
>                                              0, 6400, 4, 0);
>                         input_set_abs_params(input_dev, ABS_MT_POSITION_Y,
> @@ -4037,10 +4043,8 @@ int wacom_setup_touch_input_capabilities(struct input_dev *input_dev,
>                 fallthrough;
>
>         case WACOM_27QHDT:
> -               if (wacom_wac->shared->touch->product == 0x32C ||
> -                   wacom_wac->shared->touch->product == 0xF6) {
> -                       input_dev->evbit[0] |= BIT_MASK(EV_SW);
> -                       __set_bit(SW_MUTE_DEVICE, input_dev->swbit);
> +               if (hdev->product == 0x32C ||
> +                   hdev->product == 0xF6) {
>                         wacom_wac->has_mute_touch_switch = true;
>                         wacom_wac->is_soft_touch_switch = true;
>                 }
> @@ -4059,8 +4063,6 @@ int wacom_setup_touch_input_capabilities(struct input_dev *input_dev,
>
>         case INTUOSHT:
>         case INTUOSHT2:
> -               input_dev->evbit[0] |= BIT_MASK(EV_SW);
> -               __set_bit(SW_MUTE_DEVICE, input_dev->swbit);
>                 fallthrough;
>
>         case BAMBOO_PT:
> diff --git a/drivers/hid/wacom_wac.h b/drivers/hid/wacom_wac.h
> index 126bec6e5c0c..a8bbba4a6f37 100644
> --- a/drivers/hid/wacom_wac.h
> +++ b/drivers/hid/wacom_wac.h
> @@ -285,7 +285,7 @@ struct wacom_shared {
>         /* for wireless device to access USB interfaces */
>         unsigned touch_max;
>         int type;
> -       struct input_dev *touch_input;
> +       struct input_dev __rcu *touch_input;
>         struct hid_device *pen;
>         struct hid_device *touch;
>         bool has_mute_touch_switch;
> --
> 2.54.0.1136.gdb2ca164c4-goog
>
>

^ permalink raw reply

* [PATCH v3] HID: cleanup help indentation in kconfig
From: Julian Braha @ 2026-06-30 23:34 UTC (permalink / raw)
  To: jikos, bentiss; +Cc: linux-input, linux-kernel, Julian Braha

The indentation in this kconfig was all over the place:
Half of the 'help' texts were not indented, while the other
half indented by the more standard 2 spaces shown in the
kconfig documentation.

Let's standardize to 2 spaces.

Signed-off-by: Julian Braha <julianbraha@gmail.com>
---
v3: fix even more lines' indentation (sashiko, again)
Link to v2:
https://lore.kernel.org/all/20260630150134.514348-1-julianbraha@gmail.com/

v2: fix 2 more lines' indentation, thanks sashiko
Link to v1:
https://lore.kernel.org/all/20260630142043.496559-1-julianbraha@gmail.com/


 drivers/hid/Kconfig | 662 ++++++++++++++++++++++----------------------
 1 file changed, 331 insertions(+), 331 deletions(-)

diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig
index f9bcaeb66385..9f72b8b5966b 100644
--- a/drivers/hid/Kconfig
+++ b/drivers/hid/Kconfig
@@ -38,77 +38,77 @@ config HID_BATTERY_STRENGTH
 	select POWER_SUPPLY
 	default n
 	help
-	This option adds support of reporting battery strength (for HID devices
-	that support this feature) through power_supply class so that userspace
-	tools, such as upower, can display it.
+	  This option adds support of reporting battery strength (for HID devices
+	  that support this feature) through power_supply class so that userspace
+	  tools, such as upower, can display it.
 
 config HIDRAW
 	bool "/dev/hidraw raw HID device support"
 	help
-	Say Y here if you want to support HID devices (from the USB
-	specification standpoint) that aren't strictly user interface
-	devices, like monitor controls and Uninterruptible Power Supplies.
+	  Say Y here if you want to support HID devices (from the USB
+	  specification standpoint) that aren't strictly user interface
+	  devices, like monitor controls and Uninterruptible Power Supplies.
 
-	This module supports these devices separately using a separate
-	event interface on /dev/hidraw.
+	  This module supports these devices separately using a separate
+	  event interface on /dev/hidraw.
 
-	There is also a /dev/hiddev configuration option in the USB HID
-	configuration menu. In comparison to hiddev, this device does not process
-	the hid events at all (no parsing, no lookups). This lets applications
-	to work on raw hid events when they want to, and avoid using transport-specific
-	userspace libhid/libusb libraries.
+	  There is also a /dev/hiddev configuration option in the USB HID
+	  configuration menu. In comparison to hiddev, this device does not process
+	  the hid events at all (no parsing, no lookups). This lets applications
+	  to work on raw hid events when they want to, and avoid using transport-specific
+	  userspace libhid/libusb libraries.
 
-	If unsure, say Y.
+	  If unsure, say Y.
 
 config UHID
 	tristate "User-space I/O driver support for HID subsystem"
 	default n
 	help
-	Say Y here if you want to provide HID I/O Drivers from user-space.
-	This allows to write I/O drivers in user-space and feed the data from
-	the device into the kernel. The kernel parses the HID reports, loads the
-	corresponding HID Device Driver or provides input devices on top of your
-	user-space device.
+	  Say Y here if you want to provide HID I/O Drivers from user-space.
+	  This allows to write I/O drivers in user-space and feed the data from
+	  the device into the kernel. The kernel parses the HID reports, loads the
+	  corresponding HID Device Driver or provides input devices on top of your
+	  user-space device.
 
-	This driver cannot be used to parse HID-reports in user-space and write
-	special HID-drivers. You should use hidraw for that.
-	Instead, this driver allows to write the transport-layer driver in
-	user-space like USB-HID and Bluetooth-HID do in kernel-space.
+	  This driver cannot be used to parse HID-reports in user-space and write
+	  special HID-drivers. You should use hidraw for that.
+	  Instead, this driver allows to write the transport-layer driver in
+	  user-space like USB-HID and Bluetooth-HID do in kernel-space.
 
-	If unsure, say N.
+	  If unsure, say N.
 
-	To compile this driver as a module, choose M here: the
-	module will be called uhid.
+	  To compile this driver as a module, choose M here: the
+	  module will be called uhid.
 
 config HID_GENERIC
 	tristate "Generic HID driver"
 	default HID
 	help
-	Support for generic devices on the HID bus. This includes most
-	keyboards and mice, joysticks, tablets and digitizers.
+	  Support for generic devices on the HID bus. This includes most
+	  keyboards and mice, joysticks, tablets and digitizers.
 
-	To compile this driver as a module, choose M here: the module
-	will be called hid-generic.
+	  To compile this driver as a module, choose M here: the module
+	  will be called hid-generic.
 
-	If unsure, say Y.
+	  If unsure, say Y.
 
 config HID_HAPTIC
 	bool "Haptic touchpad support"
 	default n
 	help
-	Support for touchpads with force sensors and haptic actuators instead of a
-	traditional button.
-	Adds extra parsing and FF device for the hid multitouch driver.
-	It can be used for Elan 2703 haptic touchpad.
+	  Support for touchpads with force sensors and haptic actuators instead of a
+	  traditional button.
+	  Adds extra parsing and FF device for the hid multitouch driver.
+	  It can be used for Elan 2703 haptic touchpad.
 
-	If unsure, say N.
+	  If unsure, say N.
 
 menu "Special HID drivers"
 
 config HID_A4TECH
 	tristate "A4TECH mice"
 	help
-	Support for some A4TECH mice with two scroll wheels.
+	  Support for some A4TECH mice with two scroll wheels.
 
 config HID_ACCUTOUCH
 	tristate "Accutouch touch device"
@@ -118,44 +118,44 @@ config HID_ACCUTOUCH
 
 	  The driver works around a problem in the reported device capabilities
 	  which causes userspace to detect the device as a mouse rather than
-          a touchscreen.
+	  a touchscreen.
 
 	  Say Y here if you have a Accutouch 2216 touch controller.
 
 config HID_ACRUX
 	tristate "ACRUX game controller support"
 	help
-	Say Y here if you want to enable support for ACRUX game controllers.
+	  Say Y here if you want to enable support for ACRUX game controllers.
 
 config HID_ACRUX_FF
 	bool "ACRUX force feedback support"
 	depends on HID_ACRUX
 	select INPUT_FF_MEMLESS
 	help
-	Say Y here if you want to enable force feedback support for ACRUX
-	game controllers.
+	  Say Y here if you want to enable force feedback support for ACRUX
+	  game controllers.
 
 config HID_APPLE
 	tristate "Apple {i,Power,Mac}Books"
 	depends on LEDS_CLASS
 	depends on NEW_LEDS
 	help
-	Support for some Apple devices which less or more break
-	HID specification.
+	  Support for some Apple devices which less or more break
+	  HID specification.
 
-	Say Y here if you want support for keyboards of	Apple iBooks, PowerBooks,
-	MacBooks, MacBook Pros and Apple Aluminum.
+	  Say Y here if you want support for keyboards of	Apple iBooks, PowerBooks,
+	  MacBooks, MacBook Pros and Apple Aluminum.
 
 config HID_APPLEIR
 	tristate "Apple infrared receiver"
 	depends on (USB_HID)
 	help
-	Support for Apple infrared remote control. All the Apple computers from
+	  Support for Apple infrared remote control. All the Apple computers from
 	  2005 onwards include such a port, except the unibody Macbook (2009),
 	  and Mac Pros. This receiver is also used in the Apple TV set-top box
 	  prior to the 2010 model.
 
-	Say Y here if you want support for Apple infrared remote control.
+	  Say Y here if you want support for Apple infrared remote control.
 
 config HID_APPLETB_BL
 	tristate "Apple Touch Bar Backlight"
@@ -191,34 +191,34 @@ config HID_ASUS
 	depends on ASUS_WMI || ASUS_WMI=n
 	select POWER_SUPPLY
 	help
-	Support for Asus notebook built-in keyboard and touchpad via i2c, and
-	the Asus Republic of Gamers laptop keyboard special keys.
+	  Support for Asus notebook built-in keyboard and touchpad via i2c, and
+	  the Asus Republic of Gamers laptop keyboard special keys.
 
-	Supported devices:
-	- EeeBook X205TA
-	- VivoBook E200HA
-	- GL553V series
-	- GL753V series
+	  Supported devices:
+	  - EeeBook X205TA
+	  - VivoBook E200HA
+	  - GL553V series
+	  - GL753V series
 
 config HID_AUREAL
 	tristate "Aureal"
 	help
-	Support for Aureal Cy se W-01RN Remote Controller and other Aureal derived remotes.
+	  Support for Aureal Cy se W-01RN Remote Controller and other Aureal derived remotes.
 
 config HID_BELKIN
 	tristate "Belkin Flip KVM and Wireless keyboard"
 	help
-	Support for Belkin Flip KVM and Wireless keyboard.
+	  Support for Belkin Flip KVM and Wireless keyboard.
 
 config HID_BETOP_FF
 	tristate "Betop Production Inc. force feedback support"
 	depends on USB_HID
 	select INPUT_FF_MEMLESS
 	help
-	Say Y here if you want to enable force feedback support for devices by
-	BETOP Production Ltd.
-	Currently the following devices are known to be supported:
-	 - BETOP 2185 PC & BFM MODE
+	  Say Y here if you want to enable force feedback support for devices by
+	  BETOP Production Ltd.
+	  Currently the following devices are known to be supported:
+	  - BETOP 2185 PC & BFM MODE
 
 config HID_BIGBEN_FF
 	tristate "BigBen Interactive Kids' gamepad support"
@@ -235,54 +235,54 @@ config HID_BIGBEN_FF
 config HID_CHERRY
 	tristate "Cherry Cymotion keyboard"
 	help
-	Support for Cherry Cymotion keyboard.
+	  Support for Cherry Cymotion keyboard.
 
 config HID_CHICONY
 	tristate "Chicony devices"
 	depends on USB_HID
 	help
-	Support for Chicony Tactical pad and special keys on Chicony keyboards.
+	  Support for Chicony Tactical pad and special keys on Chicony keyboards.
 
 config HID_CORSAIR
 	tristate "Corsair devices"
 	depends on USB_HID && LEDS_CLASS
 	select POWER_SUPPLY
 	help
-	Support for Corsair devices that are not fully compliant with the
-	HID standard.
-	Support for Corsair Void headsets.
+	  Support for Corsair devices that are not fully compliant with the
+	  HID standard.
+	  Support for Corsair Void headsets.
 
-	Supported devices:
-	- Vengeance K90
-	- Scimitar PRO RGB
-	- Corsair Void headsets
+	  Supported devices:
+	  - Vengeance K90
+	  - Scimitar PRO RGB
+	  - Corsair Void headsets
 
 config HID_COUGAR
 	tristate "Cougar devices"
 	help
-	Support for Cougar devices that are not fully compliant with the
-	HID standard.
+	  Support for Cougar devices that are not fully compliant with the
+	  HID standard.
 
-	Supported devices:
-	- Cougar 500k Gaming Keyboard
+	  Supported devices:
+	  - Cougar 500k Gaming Keyboard
 
 config HID_MACALLY
 	tristate "Macally devices"
 	help
-	Support for Macally devices that are not fully compliant with the
-	HID standard.
+	  Support for Macally devices that are not fully compliant with the
+	  HID standard.
 
-	supported devices:
-	- Macally ikey keyboard
+	  supported devices:
+	  - Macally ikey keyboard
 
 config HID_PRODIKEYS
 	tristate "Prodikeys PC-MIDI Keyboard support"
 	depends on USB_HID && SND
 	select SND_RAWMIDI
 	help
-	Support for Prodikeys PC-MIDI Keyboard device support.
-	Say Y here to enable support for this device.
-	- Prodikeys PC-MIDI keyboard.
+	  Support for Prodikeys PC-MIDI Keyboard device support.
+	  Say Y here to enable support for this device.
+	    - Prodikeys PC-MIDI keyboard.
 	  The Prodikeys PC-MIDI acts as a USB Audio device, with one MIDI
 	  input and one MIDI output. These MIDI jacks appear as
 	  a sound "card" in the ALSA sound system.
@@ -293,97 +293,97 @@ config HID_PRODIKEYS
 config HID_CMEDIA
 	tristate "CMedia audio chips"
 	help
-	Support for CMedia CM6533 HID audio jack controls
-        and HS100B mute buttons.
+	  Support for CMedia CM6533 HID audio jack controls
+	  and HS100B mute buttons.
 
 config HID_CP2112
 	tristate "Silicon Labs CP2112 HID USB-to-SMBus Bridge support"
 	depends on USB_HID && HIDRAW && I2C && GPIOLIB
 	select GPIOLIB_IRQCHIP
 	help
-	Support for Silicon Labs CP2112 HID USB to SMBus Master Bridge.
-	This is a HID device driver which registers as an i2c adapter
-	and gpiochip to expose these functions of the CP2112. The
-	customizable USB descriptor fields are exposed as sysfs attributes.
+	  Support for Silicon Labs CP2112 HID USB to SMBus Master Bridge.
+	  This is a HID device driver which registers as an i2c adapter
+	  and gpiochip to expose these functions of the CP2112. The
+	  customizable USB descriptor fields are exposed as sysfs attributes.
 
 config HID_CREATIVE_SB0540
 	tristate "Creative SB0540 infrared receiver"
 	depends on USB_HID
 	help
-	Support for Creative infrared SB0540-compatible remote controls, such
-	as the RM-1500 and RM-1800 remotes.
+	  Support for Creative infrared SB0540-compatible remote controls, such
+	  as the RM-1500 and RM-1800 remotes.
 
-	Say Y here if you want support for Creative SB0540 infrared receiver.
+	  Say Y here if you want support for Creative SB0540 infrared receiver.
 
 config HID_CYPRESS
 	tristate "Cypress mouse and barcode readers"
 	help
-	Support for cypress mouse and barcode readers.
+	  Support for cypress mouse and barcode readers.
 
 config HID_DRAGONRISE
 	tristate "DragonRise Inc. game controller"
 	help
-	Say Y here if you have DragonRise Inc. game controllers.
-	These might be branded as:
-	- Tesun USB-703
-	- Media-tech MT1504 "Rogue"
-	- DVTech JS19 "Gear"
-	- Defender Game Master
+	  Say Y here if you have DragonRise Inc. game controllers.
+	  These might be branded as:
+	    - Tesun USB-703
+	    - Media-tech MT1504 "Rogue"
+	    - DVTech JS19 "Gear"
+	    - Defender Game Master
 
 config DRAGONRISE_FF
 	bool "DragonRise Inc. force feedback"
 	depends on HID_DRAGONRISE
 	select INPUT_FF_MEMLESS
 	help
-	Say Y here if you want to enable force feedback support for DragonRise Inc.
-	game controllers.
+	  Say Y here if you want to enable force feedback support for DragonRise Inc.
+	  game controllers.
 
 config HID_EMS_FF
 	tristate "EMS Production Inc. force feedback support"
 	select INPUT_FF_MEMLESS
 	help
-	Say Y here if you want to enable force feedback support for devices by
-	EMS Production Ltd.
-	Currently the following devices are known to be supported:
-	 - Trio Linker Plus II
+	  Say Y here if you want to enable force feedback support for devices by
+	  EMS Production Ltd.
+	  Currently the following devices are known to be supported:
+	    - Trio Linker Plus II
 
 config HID_ELAN
 	tristate "ELAN USB Touchpad Support"
 	depends on LEDS_CLASS && USB_HID
 	help
-	Say Y to enable support for the USB ELAN touchpad
-	Currently the following devices are known to be supported:
-	 - HP Pavilion X2 10-p0XX.
+	  Say Y to enable support for the USB ELAN touchpad
+	  Currently the following devices are known to be supported:
+	    - HP Pavilion X2 10-p0XX.
 
 config HID_ELECOM
 	tristate "ELECOM HID devices"
 	help
-	Support for ELECOM devices:
-	  - BM084 Bluetooth Mouse
-	  - EX-G Trackballs (M-XT3DRBK, M-XT3URBK)
-	  - DEFT Trackballs (M-DT1DRBK, M-DT1URBK, M-DT2DRBK, M-DT2URBK)
-	  - HUGE Trackballs (M-HT1DRBK, M-HT1URBK)
-	  - HUGE Plus Trackball (M-HT1MRBK)
+	  Support for ELECOM devices:
+	    - BM084 Bluetooth Mouse
+	    - EX-G Trackballs (M-XT3DRBK, M-XT3URBK)
+	    - DEFT Trackballs (M-DT1DRBK, M-DT1URBK, M-DT2DRBK, M-DT2URBK)
+	    - HUGE Trackballs (M-HT1DRBK, M-HT1URBK)
+	    - HUGE Plus Trackball (M-HT1MRBK)
 
 config HID_ELO
 	tristate "ELO USB 4000/4500 touchscreen"
 	depends on USB_HID
 	help
-	Support for the ELO USB 4000/4500 touchscreens. Note that this is for
-	different devices than those handled by CONFIG_TOUCHSCREEN_USB_ELO.
+	  Support for the ELO USB 4000/4500 touchscreens. Note that this is for
+	  different devices than those handled by CONFIG_TOUCHSCREEN_USB_ELO.
 
 config HID_EVISION
 	tristate "EVision Keyboards Support"
 	depends on HID
 	help
-	Support for some EVision keyboards. Note that this is needed only when
-	applying customization using userspace programs.
-	Support for some EVision devices requiring report descriptor fixups.
+	  Support for some EVision keyboards. Note that this is needed only when
+	  applying customization using userspace programs.
+	  Support for some EVision devices requiring report descriptor fixups.
 
 config HID_EZKEY
 	tristate "Ezkey BTC 8193 keyboard"
 	help
-	Support for Ezkey BTC 8193 keyboard.
+	  Support for Ezkey BTC 8193 keyboard.
 
 config HID_FT260
 	tristate "FTDI FT260 USB HID to I2C host support"
@@ -399,12 +399,12 @@ config HID_FT260
 config HID_GEMBIRD
 	tristate "Gembird Joypad"
 	help
-	Support for Gembird JPD-DualForce 2.
+	  Support for Gembird JPD-DualForce 2.
 
 config HID_GFRM
 	tristate "Google Fiber TV Box remote control support"
 	help
-	Support for Google Fiber TV Box remote controls
+	  Support for Google Fiber TV Box remote controls
 
 config HID_GLORIOUS
 	tristate "Glorious PC Gaming Race mice"
@@ -416,14 +416,14 @@ config HID_HOLTEK
 	tristate "Holtek HID devices"
 	depends on USB_HID
 	help
-	Support for Holtek based devices:
-	  - Holtek On Line Grip based game controller
-	  - Trust GXT 18 Gaming Keyboard
-	  - Sharkoon Drakonia / Perixx MX-2000 gaming mice
-	  - Tracer Sniper TRM-503 / NOVA Gaming Slider X200 /
-	    Zalman ZM-GM1
-	  - SHARKOON DarkGlider Gaming mouse
-	  - LEETGION Hellion Gaming Mouse
+	  Support for Holtek based devices:
+	    - Holtek On Line Grip based game controller
+	    - Trust GXT 18 Gaming Keyboard
+	    - Sharkoon Drakonia / Perixx MX-2000 gaming mice
+	    - Tracer Sniper TRM-503 / NOVA Gaming Slider X200 /
+	      Zalman ZM-GM1
+	    - SHARKOON DarkGlider Gaming mouse
+	    - LEETGION Hellion Gaming Mouse
 
 config HOLTEK_FF
 	bool "Holtek On Line Grip force feedback support"
@@ -452,14 +452,14 @@ config HID_GOOGLE_HAMMER
 	select INPUT_VIVALDIFMAP
 	depends on USB_HID && LEDS_CLASS && CROS_EC
 	help
-	Say Y here if you have a Google Hammer device.
+	  Say Y here if you have a Google Hammer device.
 
 config HID_GOOGLE_STADIA_FF
 	tristate "Google Stadia force feedback"
 	select INPUT_FF_MEMLESS
 	help
-	Say Y here if you want to enable force feedback support for the Google
-	Stadia controller.
+	  Say Y here if you want to enable force feedback support for the Google
+	  Stadia controller.
 
 config HID_VIVALDI
 	tristate "Vivaldi Keyboard"
@@ -475,51 +475,51 @@ config HID_GT683R
 	tristate "MSI GT68xR LED support"
 	depends on LEDS_CLASS && USB_HID
 	help
-	Say Y here if you want to enable support for the three MSI GT68xR LEDs
+	  Say Y here if you want to enable support for the three MSI GT68xR LEDs
 
-	This driver support following modes:
-	  - Normal: LEDs are fully on when enabled
-	  - Audio:  LEDs brightness depends on sound level
-	  - Breathing: LEDs brightness varies at human breathing rate
+	  This driver support following modes:
+	    - Normal: LEDs are fully on when enabled
+	    - Audio:  LEDs brightness depends on sound level
+	    - Breathing: LEDs brightness varies at human breathing rate
 
-	Currently the following devices are know to be supported:
-	  - MSI GT683R
+	  Currently the following devices are know to be supported:
+	    - MSI GT683R
 
 config HID_KEYTOUCH
 	tristate "Keytouch HID devices"
 	help
-	Support for Keytouch HID devices not fully compliant with
-	the specification. Currently supported:
+	  Support for Keytouch HID devices not fully compliant with
+	  the specification. Currently supported:
 		- Keytouch IEC 60945
 
 config HID_KYE
 	tristate "KYE/Genius devices"
 	help
-	Support for KYE/Genius devices not fully compliant with HID standard:
-	- Ergo Mouse
-	- EasyPen i405X tablet
-	- MousePen i608X tablet
-	- EasyPen M610X tablet
+	  Support for KYE/Genius devices not fully compliant with HID standard:
+	  - Ergo Mouse
+	  - EasyPen i405X tablet
+	  - MousePen i608X tablet
+	  - EasyPen M610X tablet
 
 config HID_KYSONA
 	tristate "Kysona devices"
 	depends on USB_HID
 	help
-	Support for Kysona mice.
+	  Support for Kysona mice.
 
-	Say Y here if you have a Kysona M600 mouse
-	and want to be able to read its battery capacity.
+	  Say Y here if you have a Kysona M600 mouse
+	  and want to be able to read its battery capacity.
 
 config HID_UCLOGIC
 	tristate "UC-Logic"
 	depends on USB_HID
 	help
-	Support for UC-Logic and Huion tablets.
+	  Support for UC-Logic and Huion tablets.
 
 config HID_WALTOP
 	tristate "Waltop"
 	help
-	Support for Waltop tablets.
+	  Support for Waltop tablets.
 
 config HID_VIEWSONIC
 	tristate "ViewSonic/Signotec"
@@ -530,11 +530,11 @@ config HID_VRC2
 	tristate "VRC-2 Car Controller"
 	depends on HID
 	help
-        Support for VRC-2 which is a 2-axis controller often used in
-        car simulators.
+	  Support for VRC-2 which is a 2-axis controller often used in
+	  car simulators.
 
-        To compile this driver as a module, choose M here: the
-        module will be called hid-vrc2.
+	  To compile this driver as a module, choose M here: the
+	  module will be called hid-vrc2.
 
 config HID_XIAOMI
 	tristate "Xiaomi"
@@ -545,95 +545,95 @@ config HID_XIAOMI
 config HID_GYRATION
 	tristate "Gyration remote control"
 	help
-	Support for Gyration remote control.
+	  Support for Gyration remote control.
 
 config HID_ICADE
 	tristate "ION iCade arcade controller"
 	help
-	Support for the ION iCade arcade controller to work as a joystick.
+	  Support for the ION iCade arcade controller to work as a joystick.
 
-	To compile this driver as a module, choose M here: the
-	module will be called hid-icade.
+	  To compile this driver as a module, choose M here: the
+	  module will be called hid-icade.
 
 config HID_ITE
 	tristate "ITE devices"
 	help
-	Support for ITE devices not fully compliant with HID standard.
+	  Support for ITE devices not fully compliant with HID standard.
 
 config HID_JABRA
 	tristate "Jabra USB HID Driver"
 	help
-	Support for Jabra USB HID devices.
+	  Support for Jabra USB HID devices.
 
-	Prevents mapping of vendor defined HID usages to input events. Without
-	this driver HID	reports from Jabra devices may incorrectly be seen as
-	mouse button events.
-	Say M here if you may ever plug in a Jabra USB device.
+	  Prevents mapping of vendor defined HID usages to input events. Without
+	  this driver HID	reports from Jabra devices may incorrectly be seen as
+	  mouse button events.
+	  Say M here if you may ever plug in a Jabra USB device.
 
 config HID_TWINHAN
 	tristate "Twinhan IR remote control"
 	help
-	Support for Twinhan IR remote control.
+	  Support for Twinhan IR remote control.
 
 config HID_KENSINGTON
 	tristate "Kensington Slimblade Trackball"
 	help
-	Support for Kensington Slimblade Trackball.
+	  Support for Kensington Slimblade Trackball.
 
 config HID_LCPOWER
 	tristate "LC-Power"
 	help
-	Support for LC-Power RC1000MCE RF remote control.
+	  Support for LC-Power RC1000MCE RF remote control.
 
 config HID_LED
 	tristate "Simple RGB LED support"
 	depends on LEDS_CLASS
 	help
-	Support for simple RGB LED devices. Currently supported are:
-	- Riso Kagaku Webmail Notifier
-	- Dream Cheeky Webmail Notifier and Friends Alert
-	- ThingM blink(1)
-	- Delcom Visual Signal Indicator Generation 2
-	- Greynut Luxafor
+	  Support for simple RGB LED devices. Currently supported are:
+	  - Riso Kagaku Webmail Notifier
+	  - Dream Cheeky Webmail Notifier and Friends Alert
+	  - ThingM blink(1)
+	  - Delcom Visual Signal Indicator Generation 2
+	  - Greynut Luxafor
 
-	To compile this driver as a module, choose M here: the
-	module will be called hid-led.
+	  To compile this driver as a module, choose M here: the
+	  module will be called hid-led.
 
 config HID_LENOVO
 	tristate "Lenovo / Thinkpad devices"
 	depends on LEDS_CLASS
 	help
-	Support for IBM/Lenovo devices that are not fully compliant with HID standard.
+	  Support for IBM/Lenovo devices that are not fully compliant with HID standard.
 
-	Say Y if you want support for horizontal scrolling of the IBM/Lenovo
-	Scrollpoint mice or the non-compliant features of the Lenovo Thinkpad
-	standalone keyboards, e.g:
-	- ThinkPad USB Keyboard with TrackPoint (supports extra LEDs and trackpoint
-	  configuration)
-	- ThinkPad Compact Bluetooth Keyboard with TrackPoint (supports Fn keys)
-	- ThinkPad Compact USB Keyboard with TrackPoint (supports Fn keys)
+	  Say Y if you want support for horizontal scrolling of the IBM/Lenovo
+	  Scrollpoint mice or the non-compliant features of the Lenovo Thinkpad
+	  standalone keyboards, e.g:
+	  - ThinkPad USB Keyboard with TrackPoint (supports extra LEDs and trackpoint
+	    configuration)
+	  - ThinkPad Compact Bluetooth Keyboard with TrackPoint (supports Fn keys)
+	  - ThinkPad Compact USB Keyboard with TrackPoint (supports Fn keys)
 
 config HID_LENOVO_GO
 	tristate "HID Driver for Lenovo Legion Go Series Controllers"
 	depends on USB_HID
 	depends on LEDS_CLASS_MULTICOLOR
 	help
-	Support for Lenovo Legion Go devices with detachable controllers.
+	  Support for Lenovo Legion Go devices with detachable controllers.
 
-	Say Y here to include configuration interface support for the Lenovo Legion Go
-	and Legion Go 2 Handheld Console Controllers. Say M here to compile this
-	driver as a module. The module will be called hid-lenovo-go.
+	  Say Y here to include configuration interface support for the Lenovo Legion Go
+	  and Legion Go 2 Handheld Console Controllers. Say M here to compile this
+	  driver as a module. The module will be called hid-lenovo-go.
 
 config HID_LENOVO_GO_S
 	tristate "HID Driver for Lenovo Legion Go S Controller"
 	depends on USB_HID
 	depends on LEDS_CLASS_MULTICOLOR
 	help
-	Support for Lenovo Legion Go S Handheld Console Controller.
+	  Support for Lenovo Legion Go S Handheld Console Controller.
 
-	Say Y here to include configuration interface support for the Lenovo Legion Go
-	S. Say M here to compile this driver as a module. The module will be called
-	hid-lenovo-go-s.
+	  Say Y here to include configuration interface support for the Lenovo Legion Go
+	  S. Say M here to compile this driver as a module. The module will be called
+	  hid-lenovo-go-s.
 
 config HID_LETSKETCH
 	tristate "Letsketch WP9620N tablets"
@@ -655,7 +655,7 @@ config HID_LOGITECH
 	depends on LEDS_CLASS
 	depends on LEDS_CLASS_MULTICOLOR
 	help
-	Support for Logitech devices that are not fully compliant with HID standard.
+	  Support for Logitech devices that are not fully compliant with HID standard.
 
 config HID_LOGITECH_DJ
 	tristate "Logitech receivers full support"
@@ -664,23 +664,23 @@ config HID_LOGITECH_DJ
 	depends on HID_LOGITECH
 	select HID_LOGITECH_HIDPP
 	help
-	Say Y if you want support for Logitech receivers and devices.
-	Logitech receivers are capable of pairing multiple Logitech compliant
-	devices to the same receiver. Without this driver it will be handled by
-	generic USB_HID driver and all incoming events will be multiplexed
-	into a single mouse and a single keyboard device.
+	  Say Y if you want support for Logitech receivers and devices.
+	  Logitech receivers are capable of pairing multiple Logitech compliant
+	  devices to the same receiver. Without this driver it will be handled by
+	  generic USB_HID driver and all incoming events will be multiplexed
+	  into a single mouse and a single keyboard device.
 
 config HID_LOGITECH_HIDPP
 	tristate "Logitech HID++ devices support"
 	depends on HID_LOGITECH
 	select POWER_SUPPLY
 	help
-	Support for Logitech devices relying on the HID++ Logitech specification
+	  Support for Logitech devices relying on the HID++ Logitech specification
 
-	Say Y if you want support for Logitech devices relying on the HID++
-	specification. Such devices are the various Logitech Touchpads (T650,
-	T651, TK820), some mice (Zone Touch mouse), or even keyboards (Solar
-	Keyboard).
+	  Say Y if you want support for Logitech devices relying on the HID++
+	  specification. Such devices are the various Logitech Touchpads (T650,
+	  T651, TK820), some mice (Zone Touch mouse), or even keyboards (Solar
+	  Keyboard).
 
 config LOGITECH_FF
 	bool "Logitech force feedback support"
@@ -740,31 +740,31 @@ config LOGIWHEELS_FF
 config HID_MAGICMOUSE
 	tristate "Apple Magic Mouse/Trackpad multi-touch support"
 	help
-	Support for the Apple Magic Mouse/Trackpad multi-touch.
+	  Support for the Apple Magic Mouse/Trackpad multi-touch.
 
-	Say Y here if you want support for the multi-touch features of the
-	Apple Wireless "Magic" Mouse and the Apple Wireless "Magic" Trackpad.
+	  Say Y here if you want support for the multi-touch features of the
+	  Apple Wireless "Magic" Mouse and the Apple Wireless "Magic" Trackpad.
 
 config HID_MALTRON
 	tristate "Maltron L90 keyboard"
 	help
-	Adds support for the volume up, volume down, mute, and play/pause buttons
-	of the Maltron L90 keyboard.
+	  Adds support for the volume up, volume down, mute, and play/pause buttons
+	  of the Maltron L90 keyboard.
 
 config HID_MAYFLASH
 	tristate "Mayflash game controller adapter force feedback"
 	select INPUT_FF_MEMLESS
 	help
-	Say Y here if you have HJZ Mayflash PS3 game controller adapters
-	and want to enable force feedback support.
+	  Say Y here if you have HJZ Mayflash PS3 game controller adapters
+	  and want to enable force feedback support.
 
 config HID_MEGAWORLD_FF
 	tristate "Mega World based game controller force feedback support"
 	depends on USB_HID
 	select INPUT_FF_MEMLESS
 	help
-	Say Y here if you have a Mega World based game controller and want
-	to have force feedback support for it.
+	  Say Y here if you have a Mega World based game controller and want
+	  to have force feedback support for it.
 
 config HID_RAKK
 	tristate "Rakk support"
@@ -778,18 +778,18 @@ config HID_RAKK
 config HID_REDRAGON
 	tristate "Redragon keyboards"
 	help
-    Support for Redragon keyboards that need fix-ups to work properly.
+	  Support for Redragon keyboards that need fix-ups to work properly.
 
 config HID_MICROSOFT
 	tristate "Microsoft non-fully HID-compliant devices"
 	select INPUT_FF_MEMLESS
 	help
-	Support for Microsoft devices that are not fully compliant with HID standard.
+	  Support for Microsoft devices that are not fully compliant with HID standard.
 
 config HID_MONTEREY
 	tristate "Monterey Genius KB29E keyboard"
 	help
-	Support for Monterey Genius KB29E.
+	  Support for Monterey Genius KB29E.
 
 config HID_MULTITOUCH
 	tristate "HID Multitouch panels"
@@ -843,35 +843,35 @@ config HID_NINTENDO
 	depends on LEDS_CLASS
 	select POWER_SUPPLY
 	help
-	Adds support for the Nintendo Switch Joy-Cons, NSO, Pro Controller.
-	All controllers support bluetooth, and the Pro Controller also supports
-	its USB mode. This also includes support for the Nintendo Switch Online
-	Controllers which include the NES, Genesis, SNES, and N64 controllers.
+	  Adds support for the Nintendo Switch Joy-Cons, NSO, Pro Controller.
+	  All controllers support bluetooth, and the Pro Controller also supports
+	  its USB mode. This also includes support for the Nintendo Switch Online
+	  Controllers which include the NES, Genesis, SNES, and N64 controllers.
 
-	To compile this driver as a module, choose M here: the
-	module will be called hid-nintendo.
+	  To compile this driver as a module, choose M here: the
+	  module will be called hid-nintendo.
 
 config NINTENDO_FF
 	bool "Nintendo Switch controller force feedback support"
 	depends on HID_NINTENDO
 	select INPUT_FF_MEMLESS
 	help
-	Say Y here if you have a Nintendo Switch controller and want to enable
-	force feedback support for it. This works for both joy-cons, the pro
-	controller, and the NSO N64 controller. For the pro controller, both
-	rumble motors can be controlled individually.
+	  Say Y here if you have a Nintendo Switch controller and want to enable
+	  force feedback support for it. This works for both joy-cons, the pro
+	  controller, and the NSO N64 controller. For the pro controller, both
+	  rumble motors can be controlled individually.
 
 config HID_NTI
 	tristate "NTI keyboard adapters"
 	help
-	Support for the "extra" Sun keyboard keys on keyboards attached
-	through Network Technologies USB-SUN keyboard adapters.
+	  Support for the "extra" Sun keyboard keys on keyboards attached
+	  through Network Technologies USB-SUN keyboard adapters.
 
 config HID_NTRIG
 	tristate "N-Trig touch screen"
 	depends on USB_HID
 	help
-	Support for N-Trig touch screen.
+	  Support for N-Trig touch screen.
 
 config HID_NVIDIA_SHIELD
 	tristate "NVIDIA SHIELD devices"
@@ -896,14 +896,14 @@ config NVIDIA_SHIELD_FF
 config HID_ORTEK
 	tristate "Ortek PKB-1700/WKB-2000/Skycable wireless keyboard and mouse trackpad"
 	help
-	There are certain devices which have LogicalMaximum wrong in the keyboard
-	usage page of their report descriptor. The most prevailing ones so far
-	are manufactured by Ortek, thus the name of the driver. Currently
-	supported devices by this driver are
+	  There are certain devices which have LogicalMaximum wrong in the keyboard
+	  usage page of their report descriptor. The most prevailing ones so far
+	  are manufactured by Ortek, thus the name of the driver. Currently
+	  supported devices by this driver are
 
-	   - Ortek PKB-1700
-	   - Ortek WKB-2000
-	   - Skycable wireless presenter
+	    - Ortek PKB-1700
+	    - Ortek WKB-2000
+	    - Skycable wireless presenter
 
 config HID_OXP
 	tristate "OneXPlayer handheld controller configuration support"
@@ -946,7 +946,7 @@ config HID_PENMOUNT
 config HID_PETALYNX
 	tristate "Petalynx Maxter remote control"
 	help
-	Support for Petalynx Maxter remote control.
+	  Support for Petalynx Maxter remote control.
 
 config HID_PICOLCD
 	tristate "PicoLCD (graphic version)"
@@ -1038,77 +1038,77 @@ config PLAYSTATION_FF
 	  PlayStation game controllers.
 
 config HID_PXRC
-       tristate "PhoenixRC HID Flight Controller"
-       depends on HID
-       help
-       Support for PhoenixRC HID Flight Controller, a 8-axis flight controller.
+	tristate "PhoenixRC HID Flight Controller"
+	depends on HID
+	help
+	  Support for PhoenixRC HID Flight Controller, a 8-axis flight controller.
 
-       To compile this driver as a module, choose M here: the
-       module will be called hid-pxrc.
+	  To compile this driver as a module, choose M here: the
+	  module will be called hid-pxrc.
 
 config HID_RAPOO
 	tristate "Rapoo non-fully HID-compliant devices"
 	help
-	Support for Rapoo devices that are not fully compliant with the
-	HID standard.
+	  Support for Rapoo devices that are not fully compliant with the
+	  HID standard.
 
 config HID_RAZER
 	tristate "Razer non-fully HID-compliant devices"
 	help
-	Support for Razer devices that are not fully compliant with the
-	HID standard.
+	  Support for Razer devices that are not fully compliant with the
+	  HID standard.
 
 config HID_PRIMAX
 	tristate "Primax non-fully HID-compliant devices"
 	help
-	Support for Primax devices that are not fully compliant with the
-	HID standard.
+	  Support for Primax devices that are not fully compliant with the
+	  HID standard.
 
 config HID_RETRODE
 	tristate "Retrode 2 USB adapter for vintage video games"
 	depends on USB_HID
 	help
-	Support for
-	  * Retrode 2 cartridge and controller adapter
+	  Support for
+	    * Retrode 2 cartridge and controller adapter
 
 config HID_ROCCAT
 	tristate "Roccat device support"
 	depends on USB_HID
 	help
-	Support for Roccat devices.
-	Say Y here if you have a Roccat mouse or keyboard and want
-	support for its special functionalities.
+	  Support for Roccat devices.
+	  Say Y here if you have a Roccat mouse or keyboard and want
+	  support for its special functionalities.
 
 config HID_SAITEK
 	tristate "Saitek (Mad Catz) non-fully HID-compliant devices"
 	help
-	Support for Saitek devices that are not fully compliant with the
-	HID standard.
+	  Support for Saitek devices that are not fully compliant with the
+	  HID standard.
 
-	Supported devices:
-	- PS1000 Dual Analog Pad
-	- Saitek R.A.T.7, R.A.T.9, M.M.O.7 Gaming Mice
-	- Mad Catz R.A.T.5, R.A.T.9 Gaming Mice
+	  Supported devices:
+	  - PS1000 Dual Analog Pad
+	  - Saitek R.A.T.7, R.A.T.9, M.M.O.7 Gaming Mice
+	  - Mad Catz R.A.T.5, R.A.T.9 Gaming Mice
 
 config HID_SAMSUNG
 	tristate "Samsung InfraRed remote control or keyboards"
 	depends on USB_HID
 	help
-	Support for Samsung InfraRed remote control or keyboards.
+	  Support for Samsung InfraRed remote control or keyboards.
 
 config HID_SEMITEK
 	tristate "Semitek USB keyboards"
 	help
-	Support for Semitek USB keyboards that are not fully compliant
-	with the HID standard.
+	  Support for Semitek USB keyboards that are not fully compliant
+	  with the HID standard.
 
-	There are many variants, including:
-	- GK61, GK64, GK68, GK84, GK96, etc.
-	- SK61, SK64, SK68, SK84, SK96, etc.
-	- Dierya DK61/DK66
-	- Tronsmart TK09R
-	- Woo-dy
-	- X-Bows Nature/Knight
+	  There are many variants, including:
+	  - GK61, GK64, GK68, GK84, GK96, etc.
+	  - SK61, SK64, SK68, SK84, SK96, etc.
+	  - Dierya DK61/DK66
+	  - Tronsmart TK09R
+	  - Woo-dy
+	  - X-Bows Nature/Knight
 
 config HID_SIGMAMICRO
 	tristate "SiGma Micro-based keyboards"
@@ -1128,58 +1128,58 @@ config HID_SONY
 	select POWER_SUPPLY
 	select CRC32
 	help
-	Support for
+	  Support for
 
-	  * Sixaxis controllers for PS3
-	  * Buzz controllers
-	  * Blu-ray Disc Remote Control for PS3
-	  * Logitech Harmony adapter for PS3
-	  * Guitar Hero Live PS3, Wii U and PS4 guitars
-	  * Guitar Hero PS3 and PC guitars
-	  * Rock Band 1, 2 and 3 PS3 and Wii instruments
-	  * Rock Band 4 PS4 and PS5 guitars
-	  * DJ Hero Turntable for PS3
+	    * Sixaxis controllers for PS3
+	    * Buzz controllers
+	    * Blu-ray Disc Remote Control for PS3
+	    * Logitech Harmony adapter for PS3
+	    * Guitar Hero Live PS3, Wii U and PS4 guitars
+	    * Guitar Hero PS3 and PC guitars
+	    * Rock Band 1, 2 and 3 PS3 and Wii instruments
+	    * Rock Band 4 PS4 and PS5 guitars
+	    * DJ Hero Turntable for PS3
 
 config SONY_FF
 	bool "Sony PS2/3/4 accessories force feedback support"
 	depends on HID_SONY
 	select INPUT_FF_MEMLESS
 	help
-	Say Y here if you have a Sony PS2/3/4 accessory and want to enable
-	force feedback support for it.
+	  Say Y here if you have a Sony PS2/3/4 accessory and want to enable
+	  force feedback support for it.
 
 config HID_SPEEDLINK
 	tristate "Speedlink VAD Cezanne mouse support"
 	help
-	Support for Speedlink Vicious and Divine Cezanne mouse.
+	  Support for Speedlink Vicious and Divine Cezanne mouse.
 
 config HID_STEAM
 	tristate "Steam Controller/Deck support"
 	select POWER_SUPPLY
 	help
-	Say Y here if you have a Steam Controller or Deck if you want to use it
-	without running the Steam Client. It supports both the wired and
-	the wireless adaptor.
+	  Say Y here if you have a Steam Controller or Deck if you want to use it
+	  without running the Steam Client. It supports both the wired and
+	  the wireless adaptor.
 
 config STEAM_FF
 	bool "Steam Deck force feedback support"
 	depends on HID_STEAM
 	select INPUT_FF_MEMLESS
 	help
-	Say Y here if you want to enable force feedback support for the Steam
-	Deck.
+	  Say Y here if you want to enable force feedback support for the Steam
+	  Deck.
 
 config HID_STEELSERIES
 	tristate "Steelseries devices support"
 	depends on USB_HID
 	help
-	Support for Steelseries SRW-S1 steering wheel, and the Steelseries
-	Arctis 1 Wireless for XBox headset.
+	  Support for Steelseries SRW-S1 steering wheel, and the Steelseries
+	  Arctis 1 Wireless for XBox headset.
 
 config HID_SUNPLUS
 	tristate "Sunplus wireless desktop"
 	help
-	Support for Sunplus wireless desktop.
+	  Support for Sunplus wireless desktop.
 
 config HID_RMI
 	tristate "Synaptics RMI4 device support"
@@ -1190,9 +1190,9 @@ config HID_RMI
 	select RMI4_F30
 	select RMI4_F3A
 	help
-	Support for Synaptics RMI4 touchpads.
-	Say Y here if you have a Synaptics RMI4 touchpads over i2c-hid or usbhid
-	and want support for its special functionalities.
+	  Support for Synaptics RMI4 touchpads.
+	  Say Y here if you have a Synaptics RMI4 touchpads over i2c-hid or usbhid
+	  and want support for its special functionalities.
 
 config HID_GREENASIA
 	tristate "GreenAsia (Product ID 0x12) game controller support"
@@ -1205,59 +1205,59 @@ config GREENASIA_FF
 	depends on HID_GREENASIA
 	select INPUT_FF_MEMLESS
 	help
-	Say Y here if you have a GreenAsia (Product ID 0x12) based game controller
-	(like MANTA Warrior MM816 and SpeedLink Strike2 SL-6635) or adapter
-	and want to enable force feedback support for it.
+	  Say Y here if you have a GreenAsia (Product ID 0x12) based game controller
+	  (like MANTA Warrior MM816 and SpeedLink Strike2 SL-6635) or adapter
+	  and want to enable force feedback support for it.
 
 config HID_HYPERV_MOUSE
 	tristate "Microsoft Hyper-V mouse driver"
 	depends on HYPERV_VMBUS
 	help
-	Select this option to enable the Hyper-V mouse driver.
+	  Select this option to enable the Hyper-V mouse driver.
 
 config HID_SMARTJOYPLUS
 	tristate "SmartJoy PLUS PS2/USB adapter support"
 	help
-	Support for SmartJoy PLUS PS2/USB adapter, Super Dual Box,
-	Super Joy Box 3 Pro, Super Dual Box Pro, and Super Joy Box 5 Pro.
+	  Support for SmartJoy PLUS PS2/USB adapter, Super Dual Box,
+	  Super Joy Box 3 Pro, Super Dual Box Pro, and Super Joy Box 5 Pro.
 
-	Note that DDR (Dance Dance Revolution) mode is not supported, nor
-	is pressure sensitive buttons on the pro models.
+	  Note that DDR (Dance Dance Revolution) mode is not supported, nor
+	  is pressure sensitive buttons on the pro models.
 
 config SMARTJOYPLUS_FF
 	bool "SmartJoy PLUS PS2/USB adapter force feedback support"
 	depends on HID_SMARTJOYPLUS
 	select INPUT_FF_MEMLESS
 	help
-	Say Y here if you have a SmartJoy PLUS PS2/USB adapter and want to
-	enable force feedback support for it.
+	  Say Y here if you have a SmartJoy PLUS PS2/USB adapter and want to
+	  enable force feedback support for it.
 
 config HID_TIVO
 	tristate "TiVo Slide Bluetooth remote control support"
 	help
-	Say Y if you have a TiVo Slide Bluetooth remote control.
+	  Say Y if you have a TiVo Slide Bluetooth remote control.
 
 config HID_TOPSEED
 	tristate "TopSeed Cyberlink, BTC Emprex, Conceptronic remote control support"
 	help
-	Say Y if you have a TopSeed Cyberlink or BTC Emprex or Conceptronic
-	CLLRCMCE remote control.
+	  Say Y if you have a TopSeed Cyberlink or BTC Emprex or Conceptronic
+	  CLLRCMCE remote control.
 
 config HID_TOPRE
 	tristate "Topre REALFORCE keyboards"
 	depends on HID
 	help
 	  Say Y for N-key rollover support on Topre REALFORCE R2 108/87 key and
-          Topre REALFORCE R3S 87 key keyboards.
+	  Topre REALFORCE R3S 87 key keyboards.
 
 config HID_THINGM
 	tristate "ThingM blink(1) USB RGB LED"
 	depends on LEDS_CLASS
 	select HID_LED
 	help
-	Support for the ThingM blink(1) USB RGB LED. This driver has been
-	merged into the generic hid led driver. Config symbol HID_THINGM
-	just selects HID_LED and will be removed soon.
+	  Support for the ThingM blink(1) USB RGB LED. This driver has been
+	  merged into the generic hid led driver. Config symbol HID_THINGM
+	  just selects HID_LED and will be removed soon.
 
 config HID_THRUSTMASTER
 	tristate "ThrustMaster devices support"
@@ -1332,23 +1332,23 @@ config HID_WIIMOTE
 	select POWER_SUPPLY
 	select INPUT_FF_MEMLESS
 	help
-	Support for Nintendo Wii and Wii U Bluetooth peripherals. Supported
-	devices are the Wii Remote and its extension devices, but also devices
-	based on the Wii Remote like the Wii U Pro Controller or the
-	Wii Balance Board.
+	  Support for Nintendo Wii and Wii U Bluetooth peripherals. Supported
+	  devices are the Wii Remote and its extension devices, but also devices
+	  based on the Wii Remote like the Wii U Pro Controller or the
+	  Wii Balance Board.
 
-	Support for all official Nintendo extensions is available, however, 3rd
-	party extensions might not be supported. Please report these devices to:
+	  Support for all official Nintendo extensions is available, however, 3rd
+	  party extensions might not be supported. Please report these devices to:
 	  http://github.com/dvdhrm/xwiimote/issues
 
-	Other Nintendo Wii U peripherals that are IEEE 802.11 based (including
-	the Wii U Gamepad) might be supported in the future. But currently
-	support is limited to Bluetooth based devices.
+	  Other Nintendo Wii U peripherals that are IEEE 802.11 based (including
+	  the Wii U Gamepad) might be supported in the future. But currently
+	  support is limited to Bluetooth based devices.
 
-	If unsure, say N.
+	  If unsure, say N.
 
-	To compile this driver as a module, choose M here: the
-	module will be called hid-wiimote.
+	  To compile this driver as a module, choose M here: the
+	  module will be called hid-wiimote.
 
 config HID_WINWING
 	tristate "WinWing Orion2 throttle support"
@@ -1371,9 +1371,9 @@ config HID_WINWING
 config HID_XINMO
 	tristate "Xin-Mo non-fully compliant devices"
 	help
-	Support for Xin-Mo devices that are not fully compliant with the HID
-	standard. Currently only supports the Xin-Mo Dual Arcade. Say Y here
-	if you have a Xin-Mo Dual Arcade controller.
+	  Support for Xin-Mo devices that are not fully compliant with the HID
+	  standard. Currently only supports the Xin-Mo Dual Arcade. Say Y here
+	  if you have a Xin-Mo Dual Arcade controller.
 
 config HID_ZEROPLUS
 	tristate "Zeroplus based game controller support"
@@ -1391,7 +1391,7 @@ config ZEROPLUS_FF
 config HID_ZYDACRON
 	tristate "Zydacron remote control support"
 	help
-	Support for Zydacron remote control.
+	  Support for Zydacron remote control.
 
 config HID_SENSOR_HUB
 	tristate "HID Sensors framework support"
@@ -1425,9 +1425,9 @@ config HID_SENSOR_CUSTOM_SENSOR
 config HID_ALPS
 	tristate "Alps HID device support"
 	help
-	Support for Alps I2C HID touchpads and StickPointer.
-	Say Y here if you have a Alps touchpads over i2c-hid or usbhid
-	and want support for its special functionalities.
+	  Support for Alps I2C HID touchpads and StickPointer.
+	  Say Y here if you have a Alps touchpads over i2c-hid or usbhid
+	  and want support for its special functionalities.
 
 config HID_MCP2200
 	tristate "Microchip MCP2200 HID USB-to-GPIO bridge"
@@ -1444,11 +1444,11 @@ config HID_MCP2221
 	imply GPIOLIB
 	imply IIO
 	help
-	Provides I2C and SMBUS host adapter functionality over USB-HID
-	through MCP2221 device.
+	  Provides I2C and SMBUS host adapter functionality over USB-HID
+	  through MCP2221 device.
 
-	To compile this driver as a module, choose M here: the module
-	will be called hid-mcp2221.ko.
+	  To compile this driver as a module, choose M here: the module
+	  will be called hid-mcp2221.ko.
 
 config HID_KUNIT_TEST
 	tristate "KUnit tests for HID" if !KUNIT_ALL_TESTS
-- 
2.54.0


^ permalink raw reply related

* Re: [PATCH 00/13] treewide: replace linux/gpio.h
From: patchwork-bot+netdevbpf @ 2026-07-01  0:00 UTC (permalink / raw)
  To: Arnd Bergmann
  Cc: linux-gpio, arnd, brgl, andrew, sebastian.hesselbarth,
	gregory.clement, Frank.Li, robert.jarzmik, krzk, gerg, tsbogend,
	hauke, zajec5, ysato, glaubitz, linusw, dmitry.torokhov, kuba,
	pabeni, linux, linux-kernel, linux-arm-kernel, linux-samsung-soc,
	patches, linux-m68k, linux-mips, linux-sh, linux-input,
	linux-media, netdev, linux-sunxi, linux-phy, linux-rockchip,
	linux-sound
In-Reply-To: <20260629132633.1300009-1-arnd@kernel.org>

Hello:

This series was applied to netdev/net-next.git (main)
by Jakub Kicinski <kuba@kernel.org>:

On Mon, 29 Jun 2026 15:26:20 +0200 you wrote:
> From: Arnd Bergmann <arnd@arndb.de>
> 
> The linux/gpio.h header used to be the global definition for the gpio
> interfaces, with 1100 users back in linux-3.17. In linux-7.2, only about
> 130 of those remain, so this series cleans out the rest.
> 
> In each subsystem, we can replace the header either with
> linux/gpio/consumer.h for users of the modern gpio descriptor interface,
> or linux/gpio/legacy.h for the few remaining users of the old number
> based interface.
> 
> [...]

Here is the summary with links:
  - [01/13] ARM: replace linux/gpio.h inclusions
    (no matching commit)
  - [02/13] m68k/coldfire: replace linux/gpio.h inclusions
    (no matching commit)
  - [03/13] mips: replace linux/gpio.h inclusions
    (no matching commit)
  - [04/13] sh: replace linux/gpio.h inclusions
    (no matching commit)
  - [05/13] mfd: replace linux/gpio.h inclusions
    (no matching commit)
  - [06/13,net-next] net: replace linux/gpio.h inclusions
    https://git.kernel.org/netdev/net-next/c/a53d1872f2be
  - [07/13] ASoC: replace linux/gpio.h inclusions
    (no matching commit)
  - [08/13] pcmcia: replace linux/gpio.h inclusions
    (no matching commit)
  - [09/13] phy: replace linux/gpio.h inclusions
    (no matching commit)
  - [10/13] media: replace linux/gpio.h inclusions
    (no matching commit)
  - [11/13] Input: matrix_keyboard - replace linux/gpio.h inclusion
    (no matching commit)
  - [12/13] gpib: gpio: replace linux/gpio.h inclusion
    (no matching commit)
  - [13/13] gpiolib: remove linux/gpio.h
    (no matching commit)

You are awesome, thank you!
-- 
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html



^ permalink raw reply

* [PATCH 0/3] HID: Intel-thc-hid: Refine error recovery flow
From: Even Xu @ 2026-07-01  2:04 UTC (permalink / raw)
  To: bentiss, jikos; +Cc: srinivas.pandruvada, linux-input, linux-kernel, Even Xu

This series refines the fatal error recovery flow for the Intel THC
(Touch Host Controller) subsystem, covering both the QuickI2C and
QuickSPI drivers.

Currently, when a fatal DMA error is detected in the IRQ thread handler,
the recovery is performed inline: the interrupt handler calls
try_recover() directly, which unconfigures and reconfigures the DMA
engine.

This approach has several problems:
1. Recovery runs in the IRQ thread context, which is not ideal for
   potentially slow reset operations.
2. The interrupt is re-enabled before recovery completes, risking an
   interrupt storm if DMA errors persist.
3. The DMA reset logic is open-coded in each protocol driver, leading
   to duplication and divergence over time.

This patch series addresses all of the above:

By adding a new thc_rxdma_reset() API to the THC core layer, QuickI2C
and QuickSPI drivers can call it respectively to refine the recovery
callback.

The synchronous try_recover() call in the IRQ thread is replaced with
schedule_work(), deferring recovery to a workqueue.  Within the work
function:
- The interrupt line is disabled before any DMA manipulation.
- thc_rxdma_reset() is used instead of the open-coded sequence.
- On failure the device is marked DISABLED and the interrupt remains
  off, preventing an interrupt storm.

Even Xu (3):
  HID: Intel-thc-hid: Intel-thc: Add API to reset read DMA
  HID: Intel-thc-hid: Intel-quicki2c: Refine recover callback
  HID: Intel-thc-hid: Intel-quickspi: Refine recover callback

 .../intel-quicki2c/pci-quicki2c.c             | 31 +++++++---------
 .../intel-quicki2c/quicki2c-dev.h             |  2 +
 .../intel-quickspi/pci-quickspi.c             | 37 +++++++------------
 .../intel-quickspi/quickspi-dev.h             |  2 +
 .../intel-thc-hid/intel-thc/intel-thc-dma.c   | 37 +++++++++++++++++++
 .../intel-thc-hid/intel-thc/intel-thc-dma.h   |  1 +
 6 files changed, 68 insertions(+), 42 deletions(-)

-- 
2.43.0


^ permalink raw reply

* [PATCH 1/3] HID: Intel-thc-hid: Intel-thc: Add API to reset read DMA
From: Even Xu @ 2026-07-01  2:04 UTC (permalink / raw)
  To: bentiss, jikos; +Cc: srinivas.pandruvada, linux-input, linux-kernel, Even Xu
In-Reply-To: <20260701020432.3774514-1-even.xu@intel.com>

Add a helper function thc_rxdam_reset() to do read DMA reset, it can be
called when fatal DMA error happens.

Signed-off-by: Even Xu <even.xu@intel.com>
---
 .../intel-thc-hid/intel-thc/intel-thc-dma.c   | 37 +++++++++++++++++++
 .../intel-thc-hid/intel-thc/intel-thc-dma.h   |  1 +
 2 files changed, 38 insertions(+)

diff --git a/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dma.c b/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dma.c
index 6ee675e0a738..d771c85dff28 100644
--- a/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dma.c
+++ b/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dma.c
@@ -532,6 +532,43 @@ void thc_dma_unconfigure(struct thc_device *dev)
 }
 EXPORT_SYMBOL_NS_GPL(thc_dma_unconfigure, "INTEL_THC");
 
+/**
+ * thc_rxdma_reset - Reset all read DMA engines
+ *
+ * @dev: The pointer of THC private device context
+ *
+ * This is a helper function to reset RxDMA configure. It's typically used
+ * for RxDMA recovery when fatal error happens.
+ */
+int thc_rxdma_reset(struct thc_device *dev)
+{
+	int ret;
+
+	if (mutex_lock_interruptible(&dev->thc_bus_lock))
+		return -EINTR;
+
+	ret = thc_interrupt_quiesce(dev, true);
+	if (ret) {
+		dev_err_once(dev->dev, "Quiesce interrupt failed during RxDMA reset\n");
+		goto end;
+	}
+
+	thc_dma_unconfigure(dev);
+
+	ret = thc_dma_configure(dev);
+	if (ret) {
+		dev_err_once(dev->dev, "Re-config DMA failed during RxDMA reset\n");
+		goto end;
+	}
+
+	thc_interrupt_quiesce(dev, false);
+
+end:
+	mutex_unlock(&dev->thc_bus_lock);
+	return ret;
+}
+EXPORT_SYMBOL_NS_GPL(thc_rxdma_reset, "INTEL_THC");
+
 static int thc_wait_for_dma_pause(struct thc_device *dev, enum thc_dma_channel channel)
 {
 	u32 ctrl_reg, sts_reg, sts;
diff --git a/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dma.h b/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dma.h
index 541d33995baf..715423453a9d 100644
--- a/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dma.h
+++ b/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dma.h
@@ -145,6 +145,7 @@ int  thc_dma_allocate(struct thc_device *dev);
 int  thc_dma_configure(struct thc_device *dev);
 void thc_dma_unconfigure(struct thc_device *dev);
 void thc_dma_release(struct thc_device *dev);
+int  thc_rxdma_reset(struct thc_device *dev);
 int  thc_rxdma_read(struct thc_device *dev, enum thc_dma_channel dma_channel,
 		    void *read_buff, size_t *read_len, int *read_finished);
 int  thc_swdma_read(struct thc_device *dev, void *write_buff, size_t write_len,
-- 
2.43.0


^ permalink raw reply related

* [PATCH 2/3] HID: Intel-thc-hid: Intel-quicki2c: Refine recover callback
From: Even Xu @ 2026-07-01  2:04 UTC (permalink / raw)
  To: bentiss, jikos; +Cc: srinivas.pandruvada, linux-input, linux-kernel, Even Xu
In-Reply-To: <20260701020432.3774514-1-even.xu@intel.com>

Refine recover flow:
1. Use workqueue to handle recover flow instead of processing in irq
   handler.
2. Call thc_rxdma_reset() API to simplify the recover operation.
3. Disable interrupt during whole recover flow.
4. If recover fails, disable interrupt to avoid interrupt storm.

Signed-off-by: Even Xu <even.xu@intel.com>
---
 .../intel-quicki2c/pci-quicki2c.c             | 31 ++++++++-----------
 .../intel-quicki2c/quicki2c-dev.h             |  2 ++
 2 files changed, 15 insertions(+), 18 deletions(-)

diff --git a/drivers/hid/intel-thc-hid/intel-quicki2c/pci-quicki2c.c b/drivers/hid/intel-thc-hid/intel-quicki2c/pci-quicki2c.c
index 46d3e9a01999..411d7a0ab90e 100644
--- a/drivers/hid/intel-thc-hid/intel-quicki2c/pci-quicki2c.c
+++ b/drivers/hid/intel-thc-hid/intel-quicki2c/pci-quicki2c.c
@@ -245,28 +245,23 @@ static irqreturn_t quicki2c_irq_quick_handler(int irq, void *dev_id)
 }
 
 /**
- * try_recover - Try to recovery THC and Device
- * @qcdev: Pointer to quicki2c_device structure
+ * try_recover - Recover callback to recover THC
+ * @work: pointer to work_struct
  *
  * This function is an error handler, called when fatal error happens.
- * It try to reset touch device and re-configure THC to recovery
- * communication between touch device and THC.
- *
- * Return: 0 if successful or error code on failure
+ * It try to reset Touch Device and re-configure THC to recover
+ * transferring between Device and THC.
  */
-static int try_recover(struct quicki2c_device *qcdev)
+static void try_recover(struct work_struct *work)
 {
-	int ret;
+	struct quicki2c_device *qcdev = container_of(work, struct quicki2c_device, recover_work);
 
-	thc_dma_unconfigure(qcdev->thc_hw);
-
-	ret = thc_dma_configure(qcdev->thc_hw);
-	if (ret) {
-		dev_err(qcdev->dev, "Reconfig DMA failed\n");
-		return ret;
-	}
+	thc_interrupt_enable(qcdev->thc_hw, false);
 
-	return 0;
+	if (thc_rxdma_reset(qcdev->thc_hw))
+		qcdev->state = QUICKI2C_DISABLED;
+	else
+		thc_interrupt_enable(qcdev->thc_hw, true);
 }
 
 static int handle_input_report(struct quicki2c_device *qcdev)
@@ -346,8 +341,7 @@ static irqreturn_t quicki2c_irq_thread_handler(int irq, void *dev_id)
 	thc_interrupt_enable(qcdev->thc_hw, true);
 
 	if (err_recover)
-		if (try_recover(qcdev))
-			qcdev->state = QUICKI2C_DISABLED;
+		schedule_work(&qcdev->recover_work);
 
 	pm_runtime_put_autosuspend(qcdev->dev);
 
@@ -386,6 +380,7 @@ static struct quicki2c_device *quicki2c_dev_init(struct pci_dev *pdev, void __io
 	qcdev->ddata = ddata;
 
 	init_waitqueue_head(&qcdev->reset_ack_wq);
+	INIT_WORK(&qcdev->recover_work, try_recover);
 
 	/* THC hardware init */
 	qcdev->thc_hw = thc_dev_init(qcdev->dev, qcdev->mem_addr);
diff --git a/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-dev.h b/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-dev.h
index 61dbdece59a1..aedf85291e60 100644
--- a/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-dev.h
+++ b/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-dev.h
@@ -222,6 +222,8 @@ struct quicki2c_device {
 	wait_queue_head_t reset_ack_wq;
 	bool reset_ack;
 
+	struct work_struct recover_work;
+
 	u32 i2c_max_frame_size_enable;
 	u32 i2c_max_frame_size;
 	u32 i2c_int_delay_enable;
-- 
2.43.0


^ permalink raw reply related

* [PATCH 3/3] HID: Intel-thc-hid: Intel-quickspi: Refine recover callback
From: Even Xu @ 2026-07-01  2:04 UTC (permalink / raw)
  To: bentiss, jikos; +Cc: srinivas.pandruvada, linux-input, linux-kernel, Even Xu
In-Reply-To: <20260701020432.3774514-1-even.xu@intel.com>

Refine recover flow:
1. Use workqueue to handle recover flow instead of processing in irq
   handler.
2. Call thc_rxdma_reset() API to simplify the recover operation.
3. Disable interrupt during whole recover flow.
4. If recover fails, disable interrupt to avoid interrupt storm.

Signed-off-by: Even Xu <even.xu@intel.com>
---
 .../intel-quickspi/pci-quickspi.c             | 37 +++++++------------
 .../intel-quickspi/quickspi-dev.h             |  2 +
 2 files changed, 15 insertions(+), 24 deletions(-)

diff --git a/drivers/hid/intel-thc-hid/intel-quickspi/pci-quickspi.c b/drivers/hid/intel-thc-hid/intel-quickspi/pci-quickspi.c
index f669235f1883..1e63b183b3b1 100644
--- a/drivers/hid/intel-thc-hid/intel-quickspi/pci-quickspi.c
+++ b/drivers/hid/intel-thc-hid/intel-quickspi/pci-quickspi.c
@@ -252,34 +252,23 @@ static irqreturn_t quickspi_irq_quick_handler(int irq, void *dev_id)
 }
 
 /**
- * try_recover - Try to recovery THC and Device
- * @qsdev: pointer to quickspi device
+ * try_recover - Recover callback to recover THC
+ * @work: pointer to work_struct
  *
- * This function is a error handler, called when fatal error happens.
- * It try to reset Touch Device and re-configure THC to recovery
+ * This function is an error handler, called when fatal error happens.
+ * It try to reset Touch Device and re-configure THC to recover
  * transferring between Device and THC.
- *
- * Return: 0 if successful or error code on failed.
  */
-static int try_recover(struct quickspi_device *qsdev)
+static void try_recover(struct work_struct *work)
 {
-	int ret;
+	struct quickspi_device *qsdev = container_of(work, struct quickspi_device, recover_work);
 
-	ret = reset_tic(qsdev);
-	if (ret) {
-		dev_err(qsdev->dev, "Reset touch device failed, ret = %d\n", ret);
-		return ret;
-	}
-
-	thc_dma_unconfigure(qsdev->thc_hw);
-
-	ret = thc_dma_configure(qsdev->thc_hw);
-	if (ret) {
-		dev_err(qsdev->dev, "Re-configure THC DMA failed, ret = %d\n", ret);
-		return ret;
-	}
+	thc_interrupt_enable(qsdev->thc_hw, false);
 
-	return 0;
+	if (thc_rxdma_reset(qsdev->thc_hw))
+		qsdev->state = QUICKSPI_DISABLED;
+	else
+		thc_interrupt_enable(qsdev->thc_hw, true);
 }
 
 /**
@@ -340,8 +329,7 @@ static irqreturn_t quickspi_irq_thread_handler(int irq, void *dev_id)
 	thc_interrupt_enable(qsdev->thc_hw, true);
 
 	if (err_recover)
-		if (try_recover(qsdev))
-			qsdev->state = QUICKSPI_DISABLED;
+		schedule_work(&qsdev->recover_work);
 
 	pm_runtime_put_autosuspend(qsdev->dev);
 
@@ -385,6 +373,7 @@ static struct quickspi_device *quickspi_dev_init(struct pci_dev *pdev, void __io
 	init_waitqueue_head(&qsdev->report_desc_got_wq);
 	init_waitqueue_head(&qsdev->get_report_cmpl_wq);
 	init_waitqueue_head(&qsdev->set_report_cmpl_wq);
+	INIT_WORK(&qsdev->recover_work, try_recover);
 
 	/* thc hw init */
 	qsdev->thc_hw = thc_dev_init(qsdev->dev, qsdev->mem_addr);
diff --git a/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-dev.h b/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-dev.h
index bf5e18f5a5f4..b0c1219866a4 100644
--- a/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-dev.h
+++ b/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-dev.h
@@ -173,6 +173,8 @@ struct quickspi_device {
 
 	wait_queue_head_t set_report_cmpl_wq;
 	bool set_report_cmpl;
+
+	struct work_struct recover_work;
 };
 
 #endif /* _QUICKSPI_DEV_H_ */
-- 
2.43.0


^ permalink raw reply related

* Re: [PATCH 2/3] HID: Intel-thc-hid: Intel-quicki2c: Refine recover callback
From: sashiko-bot @ 2026-07-01  2:15 UTC (permalink / raw)
  To: Even Xu; +Cc: linux-input, dmitry.torokhov
In-Reply-To: <20260701020432.3774514-3-even.xu@intel.com>

Thank you for your contribution! Sashiko AI review found 3 potential issue(s) to consider:
- [High] Missing cancellation of the scheduled asynchronous recovery work during device removal and shutdown leads to a Use-After-Free.
- [High] Unconditionally re-enabling hardware interrupts before the asynchronous recovery completes causes an immediate interrupt storm.
- [High] The deferred `try_recover` work function accesses hardware registers directly without acquiring a Runtime PM reference.
--

commit 8f5c7d640eb5d690c93bdf294d89a5d9087edae5
Author: Even Xu <even.xu@intel.com>

HID: Intel-thc-hid: Intel-quicki2c: Refine recover callback

This commit refines the recover flow by moving the hardware recovery operation
to an asynchronous workqueue. It replaces the inline recover operation with a
call to schedule_work() and simplifies the recover callback using
thc_rxdma_reset().

> diff --git a/drivers/hid/intel-thc-hid/intel-quicki2c/pci-quicki2c.c b/drivers/hid/intel-thc-hid/intel-quicki2c/pci-quicki2c.c
> index 46d3e9a019995..411d7a0ab90ef 100644
> --- a/drivers/hid/intel-thc-hid/intel-quicki2c/pci-quicki2c.c
> +++ b/drivers/hid/intel-thc-hid/intel-quicki2c/pci-quicki2c.c
[ ... ]
> @@ -245,28 +245,23 @@ static irqreturn_t quicki2c_irq_quick_handler(int irq, void *dev_id)
>  }
>  
> -static int try_recover(struct quicki2c_device *qcdev)
> +static void try_recover(struct work_struct *work)
>  {
> +	struct quicki2c_device *qcdev = container_of(work, struct quicki2c_device, recover_work);
>  
> +	thc_interrupt_enable(qcdev->thc_hw, false);
>  

[Severity: High]
Is it safe to access the hardware registers in this work function without
holding a runtime PM reference?

Since the IRQ handler calls pm_runtime_put_autosuspend() right after
scheduling the work, could the device transition to a suspended state before
try_recover() executes, resulting in invalid MMIO accesses when trying to
manipulate the THC registers?

> -	thc_dma_unconfigure(qcdev->thc_hw);
> -
> -	ret = thc_dma_configure(qcdev->thc_hw);
> -	if (ret) {
> -		dev_err(qcdev->dev, "Reconfig DMA failed\n");
> -		return ret;
> -	}
> +	if (thc_rxdma_reset(qcdev->thc_hw))
> +		qcdev->state = QUICKI2C_DISABLED;
> +	else
> +		thc_interrupt_enable(qcdev->thc_hw, true);
>  }
[ ... ]
> @@ -346,8 +341,7 @@ static irqreturn_t quicki2c_irq_thread_handler(int irq, void *dev_id)
>  	thc_interrupt_enable(qcdev->thc_hw, true);
>  

[Severity: High]
Does re-enabling the interrupt here before the recovery work executes cause
an interrupt storm?

Because the actual hardware error state isn't cleared until thc_rxdma_reset()
runs asynchronously in the workqueue, unmasking the interrupt here might
cause the hardware to instantly re-assert the interrupt. Could this lead to
an infinite loop between the hard IRQ and threaded IRQ handlers, thereby
starving the system workqueue from ever executing try_recover()?

>  	if (err_recover)
> -		if (try_recover(qcdev))
> -			qcdev->state = QUICKI2C_DISABLED;
> +		schedule_work(&qcdev->recover_work);
>  
>  	pm_runtime_put_autosuspend(qcdev->dev);
[ ... ]
> @@ -386,6 +380,7 @@ static struct quicki2c_device *quicki2c_dev_init(struct pci_dev *pdev, void __io
>  	qcdev->ddata = ddata;
>  
>  	init_waitqueue_head(&qcdev->reset_ack_wq);
> +	INIT_WORK(&qcdev->recover_work, try_recover);
>  

[Severity: High]
When the device is removed, could the scheduled work run after the device
context is freed?

Looking at quicki2c_remove(), there is no call to cancel_work_sync() before
tearing down the device. Since qcdev is allocated with devres, might
this lead to a use-after-free if the recovery work is still queued on the
system workqueue when the removal path finishes?

>  	/* THC hardware init */
>  	qcdev->thc_hw = thc_dev_init(qcdev->dev, qcdev->mem_addr);

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260701020432.3774514-1-even.xu@intel.com?part=2

^ permalink raw reply

* Re: [PATCH 3/3] HID: Intel-thc-hid: Intel-quickspi: Refine recover callback
From: sashiko-bot @ 2026-07-01  2:16 UTC (permalink / raw)
  To: Even Xu; +Cc: dmitry.torokhov, linux-input
In-Reply-To: <20260701020432.3774514-4-even.xu@intel.com>

Thank you for your contribution! Sashiko AI review found 5 potential issue(s) to consider:

New issues:
- [High] Use-after-free of qsdev during device removal due to uncanceled async work
- [High] Missing runtime PM protection during asynchronous hardware recovery
- [High] Unconditional interrupt unmasking causes severe interrupt storm
- [High] Data race on DMA configuration between IRQ thread and async recovery

Pre-existing issues:
- [High] Invalid runtime PM teardown causes unpowered hardware accesses during removal
--

commit b4ff70b4c528a251392ae3368aa0d2f80233ab2e
Author: Even Xu <even.xu@intel.com>
Subject: HID: Intel-thc-hid: Intel-quickspi: Refine recover callback

This commit refines the recovery flow by using a workqueue to handle
recovery instead of processing it in the IRQ handler. It calls
thc_rxdma_reset() to simplify operations and disables interrupts during
the recovery process.

> diff --git a/drivers/hid/intel-thc-hid/intel-quickspi/pci-quickspi.c b/drivers/hid/intel-thc-hid/intel-quickspi/pci-quickspi.c
> index 4ae2e1718b30c..a2428db5f9414 100644
> --- a/drivers/hid/intel-thc-hid/intel-quickspi/pci-quickspi.c
> +++ b/drivers/hid/intel-thc-hid/intel-quickspi/pci-quickspi.c
> @@ -252,34 +252,23 @@ static irqreturn_t quickspi_irq_quick_handler(int irq, void *dev_id)
[ ... ]
> +static void try_recover(struct work_struct *work)
> +{
> +	struct quickspi_device *qsdev = container_of(work, struct quickspi_device, recover_work);
> +
> +	thc_interrupt_enable(qsdev->thc_hw, false);
> +

[Severity: High]
Does this asynchronously scheduled work need to acquire its own runtime PM
reference?

The IRQ thread drops its PM reference with pm_runtime_put_autosuspend()
immediately after scheduling this work. If the autosuspend delay expires
before this workqueue executes, the device may enter a suspended state.

Will calling thc_interrupt_enable() and thc_rxdma_reset() here cause a system
crash or silent failure by accessing unpowered hardware registers?

> +	if (thc_rxdma_reset(qsdev->thc_hw))

[Severity: High]
Is there a potential data race here with the IRQ thread?

The try_recover() function calls thc_rxdma_reset(), which holds the
thc_bus_lock while unconfiguring and reconfiguring the DMA hardware.
However, if a concurrent interrupt occurs, quickspi_irq_thread_handler()
calls thc_rxdma_read() without holding thc_bus_lock.

Could this allow the IRQ thread to read from DMA rings while they are
actively being torn down and rebuilt by the recovery work on another CPU?

> +		qsdev->state = QUICKSPI_DISABLED;
> +	else
> +		thc_interrupt_enable(qsdev->thc_hw, true);
>  }
[ ... ]
> @@ -340,8 +329,7 @@ static irqreturn_t quickspi_irq_thread_handler(int irq, void *dev_id)
>  	thc_interrupt_enable(qsdev->thc_hw, true);
>  
>  	if (err_recover)
> -		if (try_recover(qsdev))
> -			qsdev->state = QUICKSPI_DISABLED;
> +		schedule_work(&qsdev->recover_work);

[Severity: High]
Could this unconditional interrupt unmasking cause an interrupt storm?

When the hardware signals a fatal error, the handler unmasks the interrupt
here before returning, but the hardware reset is deferred to the asynchronous
workqueue.

Since the hardware error condition hasn't been cleared yet, won't the
device immediately re-assert the interrupt and trap the CPU in an endless
hardirq-to-thread loop before the workqueue ever has a chance to execute?

>  
>  	pm_runtime_put_autosuspend(qsdev->dev);
>  
> @@ -385,6 +373,7 @@ static struct quickspi_device *quickspi_dev_init(struct pci_dev *pdev, void __io
>  	init_waitqueue_head(&qsdev->report_desc_got_wq);
>  	init_waitqueue_head(&qsdev->get_report_cmpl_wq);
>  	init_waitqueue_head(&qsdev->set_report_cmpl_wq);
> +	INIT_WORK(&qsdev->recover_work, try_recover);

[Severity: High]
Does this newly added work item need to be explicitly canceled during device
removal?

In the driver removal path in quickspi_remove(), there is no call to
cancel_work_sync().

Since qsdev is allocated with devm_kzalloc(), it will be freed shortly after
quickspi_remove() returns. If a fatal error interrupt schedules this work just
before or during driver unbind, could the workqueue execute after qsdev is
freed, causing a use-after-free when try_recover() dereferences it?

[Severity: High]
This is a pre-existing issue, but does quickspi_remove() properly wake the
device before accessing its hardware registers?

Currently, quickspi_remove() uses pm_runtime_get_noresume():

quickspi_remove() {
    ...
    pm_runtime_get_noresume(qsdev->dev);
    quickspi_dev_deinit(qsdev);
    ...
}

Calling pm_runtime_get_noresume() only increments the usage counter, it does
not resume the device. If the device was already auto-suspended,
quickspi_dev_deinit() will write to unpowered registers.

Could this lead to dropped writes or a PCIe bus error?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260701020432.3774514-1-even.xu@intel.com?part=3

^ permalink raw reply

* Re: [PATCH 1/3] HID: Intel-thc-hid: Intel-thc: Add API to reset read DMA
From: sashiko-bot @ 2026-07-01  2:19 UTC (permalink / raw)
  To: Even Xu; +Cc: dmitry.torokhov, linux-input
In-Reply-To: <20260701020432.3774514-2-even.xu@intel.com>

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

New issues:
- [Medium] Using dev_err_once() hides subsequent failures during fatal error recovery.

Pre-existing issues:
- [High] Zeroing the Physical Region Descriptor (PRD) base addresses before pausing the DMA engines can cause IOMMU faults or memory corruption.
--

commit fb285a619300634b9f208053996047e32855d49b
Author: Even Xu <even.xu@intel.com>
Date:   Wed Jul 1 02:04:30 2026 +0000

HID: Intel-thc-hid: Intel-thc: Add API to reset read DMA

Add a helper function thc_rxdam_reset() to do read DMA reset, it can be
called when fatal DMA error happens.

> diff --git a/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dma.c b/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dma.c
> index 6ee675e0a7384..d771c85dff28b 100644
> --- a/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dma.c
> +++ b/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dma.c

[ ... ]

> @@ -532,6 +532,43 @@ void thc_dma_unconfigure(struct thc_device *dev)
>  }
>  EXPORT_SYMBOL_NS_GPL(thc_dma_unconfigure, "INTEL_THC");
>  
> +/**
> + * thc_rxdma_reset - Reset all read DMA engines
> + *
> + * @dev: The pointer of THC private device context
> + *
> + * This is a helper function to reset RxDMA configure. It's typically used
> + * for RxDMA recovery when fatal error happens.
> + */
> +int thc_rxdma_reset(struct thc_device *dev)
> +{
> +	int ret;
> +
> +	if (mutex_lock_interruptible(&dev->thc_bus_lock))
> +		return -EINTR;
> +
> +	ret = thc_interrupt_quiesce(dev, true);
> +	if (ret) {
> +		dev_err_once(dev->dev, "Quiesce interrupt failed during RxDMA reset\n");

[Severity: Medium]
Since thc_rxdma_reset() is called as part of a recurring fatal error
recovery flow, will dev_err_once() hide subsequent failures?

If a device successfully recovers the first time but encounters an
unrecoverable failure during a subsequent fatal error later in its uptime,
the failure will be silently ignored because dev_err_once() only prints
once per boot.

Should dev_err_ratelimited() or dev_err() be used instead?

> +		goto end;
> +	}
> +
> +	thc_dma_unconfigure(dev);

[Severity: High]
This is a pre-existing issue, but does calling thc_dma_unconfigure()
here risk IOMMU faults or memory corruption?

When thc_rxdma_reset() invokes thc_dma_unconfigure() during fatal error
recovery, the hardware DMA engine might still be actively fetching or in
an unpredictable state. 

Looking at thc_dma_unconfigure(), it zeroes out the PRD base addresses
before clearing the DMA START bits:

thc_dma_unconfigure() {
    for (chan = 0; chan < MAX_THC_DMA_CHANNEL; chan++) {
        dma_set_prd_base_addr(dev, 0, &dev->dma_ctx->dma_config[chan]);
        ...
    }
    regmap_write_bits(dev->thc_regmap, THC_M_PRT_READ_DMA_CNTRL_1_OFFSET,
                      THC_M_PRT_READ_DMA_CNTRL_START, 0);
}

If the hardware DMA engine is active and continues fetching descriptors
before the START bit is cleared, will it attempt to fetch from physical
address 0x0?

Should it wait for the ACTIVE status to clear (e.g., using
thc_wait_for_dma_pause()) before clearing the base addresses?

> +
> +	ret = thc_dma_configure(dev);
> +	if (ret) {
> +		dev_err_once(dev->dev, "Re-config DMA failed during RxDMA reset\n");
> +		goto end;
> +	}
> +
> +	thc_interrupt_quiesce(dev, false);
> +
> +end:
> +	mutex_unlock(&dev->thc_bus_lock);
> +	return ret;
> +}
> +EXPORT_SYMBOL_NS_GPL(thc_rxdma_reset, "INTEL_THC");

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260701020432.3774514-1-even.xu@intel.com?part=1

^ permalink raw reply

* [PATCH v8 0/3] HID: nintendo: Add preliminary Switch 2 controller driver
From: Vicki Pfau @ 2026-07-01  3:15 UTC (permalink / raw)
  To: Dmitry Torokhov, Jiri Kosina, Benjamin Tissoires, linux-input
  Cc: Vicki Pfau, Silvan Jegen

This series adds preliminary support for Switch 2 controllers using the
same split-driver model as previous versions. This is a minor iteration on
v7, fixing errors pointed out by sashiko as well as trying to clean up
unplug somewhat further beyond what it pointed out.

Vicki Pfau (3):
  HID: nintendo: Add preliminary Switch 2 controller driver
  HID: nintendo: Add rumble support for Switch 2 controllers
  HID: nintendo: Add unified report format support

 MAINTAINERS                                   |    1 +
 drivers/hid/Kconfig                           |   19 +-
 drivers/hid/hid-ids.h                         |    4 +
 drivers/hid/hid-nintendo.c                    | 1668 ++++++++++++++++-
 drivers/hid/hid-nintendo.h                    |   72 +
 drivers/input/joystick/Kconfig                |   11 +
 drivers/input/joystick/Makefile               |    1 +
 drivers/input/joystick/nintendo-switch2-usb.c |  453 +++++
 8 files changed, 2188 insertions(+), 41 deletions(-)
 create mode 100644 drivers/hid/hid-nintendo.h
 create mode 100644 drivers/input/joystick/nintendo-switch2-usb.c

-- 
2.54.0


^ permalink raw reply

* [PATCH v8 2/3] HID: nintendo: Add rumble support for Switch 2 controllers
From: Vicki Pfau @ 2026-07-01  3:15 UTC (permalink / raw)
  To: Dmitry Torokhov, Jiri Kosina, Benjamin Tissoires, linux-input
  Cc: Vicki Pfau, Silvan Jegen
In-Reply-To: <20260701031513.3068035-1-vi@endrift.com>

This adds rumble support for both the "HD Rumble" linear resonant actuator
type as used in the Joy-Cons and Pro Controller, as well as the eccentric
rotating mass type used in the GameCube controller. Note that since there's
currently no API for exposing full control of LRAs with evdev, it only
simulates a basic rumble for now.

Signed-off-by: Vicki Pfau <vi@endrift.com>
---
 drivers/hid/Kconfig        |   8 +-
 drivers/hid/hid-nintendo.c | 217 ++++++++++++++++++++++++++++++++++++-
 2 files changed, 218 insertions(+), 7 deletions(-)

diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig
index 19c77c323ec9..851eed76c236 100644
--- a/drivers/hid/Kconfig
+++ b/drivers/hid/Kconfig
@@ -859,10 +859,10 @@ config NINTENDO_FF
 	depends on HID_NINTENDO
 	select INPUT_FF_MEMLESS
 	help
-	Say Y here if you have a Nintendo Switch controller and want to enable
-	force feedback support for it. This works for both joy-cons, the pro
-	controller, and the NSO N64 controller. For the pro controller, both
-	rumble motors can be controlled individually.
+	Say Y here if you have a Nintendo Switch or Switch 2 controller and want
+	to enable force feedback support for it. This works for Joy-Cons, the Pro
+	Controllers, and the NSO N64 and GameCube controller. For the Pro
+	Controller, both rumble motors can be controlled individually.
 
 config HID_NTI
 	tristate "NTI keyboard adapters"
diff --git a/drivers/hid/hid-nintendo.c b/drivers/hid/hid-nintendo.c
index 20e5b18039b8..00ab4bee3dab 100644
--- a/drivers/hid/hid-nintendo.c
+++ b/drivers/hid/hid-nintendo.c
@@ -2989,6 +2989,7 @@ enum switch2_init_step {
 	NS2_INIT_READ_USER_SECONDARY_CALIB,
 	NS2_INIT_SET_FEATURE_MASK,
 	NS2_INIT_ENABLE_FEATURES,
+	NS2_INIT_ENABLE_RUMBLE,
 	NS2_INIT_GRIP_BUTTONS,
 	NS2_INIT_REPORT_FORMAT,
 	NS2_INIT_SET_PLAYER_LEDS,
@@ -3020,6 +3021,18 @@ struct switch2_stick_calibration {
 	struct switch2_axis_calibration y;
 };
 
+struct switch2_hd_rumble {
+	uint16_t hi_freq : 10;
+	uint16_t hi_amp : 10;
+	uint16_t lo_freq : 10;
+	uint16_t lo_amp : 10;
+} __packed;
+
+struct switch2_erm_rumble {
+	uint16_t error;
+	uint16_t amplitude;
+};
+
 struct switch2_controller {
 	struct hid_device *hdev;
 	struct switch2_cfg_intf *cfg;
@@ -3043,8 +3056,45 @@ struct switch2_controller {
 
 	uint32_t player_id;
 	struct led_classdev leds[4];
+
+#if IS_ENABLED(CONFIG_NINTENDO_FF)
+	spinlock_t rumble_lock;
+	uint8_t rumble_seq;
+	union {
+		struct switch2_hd_rumble hd;
+		struct switch2_erm_rumble sd;
+	} rumble;
+	uint64_t last_rumble_work;
+	struct delayed_work rumble_work;
+	uint8_t *rumble_buffer;
+#endif
 };
 
+enum gc_rumble {
+	GC_RUMBLE_OFF = 0,
+	GC_RUMBLE_ON = 1,
+	GC_RUMBLE_STOP = 2,
+};
+
+/*
+ * The highest rumble level for "HD Rumble" is strong enough to potentially damage the controller,
+ * and also leaves your hands feeling like melted jelly, so we set a semi-arbitrary scaling factor
+ * to artificially limit the maximum for safety and comfort. It is currently unknown if the Switch
+ * 2 itself does something similar, but it's quite likely.
+ *
+ * This value must be between 0 and 1024, otherwise the math below will overflow.
+ */
+#define RUMBLE_MAX 450u
+
+/*
+ * Semi-arbitrary values used to simulate the "rumble" sensation of an eccentric rotating
+ * mass type haptic motor on the Switch 2 controllers' linear resonant actuator type haptics.
+ *
+ * The units used are unknown, but the values must be between 0 and 1023.
+ */
+#define RUMBLE_HI_FREQ 0x187
+#define RUMBLE_LO_FREQ 0x112
+
 static DEFINE_MUTEX(switch2_controllers_lock);
 static LIST_HEAD(switch2_controllers);
 
@@ -3136,7 +3186,7 @@ static const uint8_t switch2_init_cmd_data[] = {
 static const uint8_t switch2_one_data[] = { 0x01, 0x00, 0x00, 0x00 };
 
 static const uint8_t switch2_feature_mask[] = {
-	NS2_FEATURE_BUTTONS | NS2_FEATURE_ANALOG | NS2_FEATURE_IMU,
+	NS2_FEATURE_BUTTONS | NS2_FEATURE_ANALOG | NS2_FEATURE_IMU | NS2_FEATURE_RUMBLE,
 	0x00, 0x00, 0x00
 };
 
@@ -3197,7 +3247,11 @@ static void switch2_controller_put(struct switch2_controller *ns2)
 static void switch2_kref_put(struct kref *refcount)
 {
 	struct switch2_controller *ns2 = container_of(refcount,
-		struct switch2_controller, refcount);
+					struct switch2_controller, refcount);
+
+#if IS_ENABLED(CONFIG_NINTENDO_FF)
+	cancel_delayed_work_sync(&ns2->rumble_work);
+#endif
 
 	guard(mutex)(&switch2_controllers_lock);
 	list_del_init(&ns2->entry);
@@ -3205,6 +3259,125 @@ static void switch2_kref_put(struct kref *refcount)
 	kfree(ns2);
 }
 
+#if IS_ENABLED(CONFIG_NINTENDO_FF)
+static void switch2_encode_rumble(struct switch2_hd_rumble *rumble, uint8_t buffer[5])
+{
+	buffer[0] = rumble->hi_freq;
+	buffer[1] = (rumble->hi_freq >> 8) | (rumble->hi_amp << 2);
+	buffer[2] = (rumble->hi_amp >> 6) | (rumble->lo_freq << 4);
+	buffer[3] = (rumble->lo_freq >> 4) | (rumble->lo_amp << 6);
+	buffer[4] = rumble->lo_amp >> 2;
+}
+
+static int switch2_play_effect(struct input_dev *dev, void *data, struct ff_effect *effect)
+{
+	struct switch2_controller *ns2 = input_get_drvdata(dev);
+	unsigned long flags;
+
+	if (effect->type != FF_RUMBLE)
+		return 0;
+
+	spin_lock_irqsave(&ns2->rumble_lock, flags);
+	if (ns2->ctlr_type == NS2_CTLR_TYPE_GC) {
+		ns2->rumble.sd.amplitude = max(effect->u.rumble.strong_magnitude,
+			(uint16_t) (effect->u.rumble.weak_magnitude >> 1));
+	} else {
+		ns2->rumble.hd.hi_freq = RUMBLE_HI_FREQ;
+		ns2->rumble.hd.lo_freq = RUMBLE_LO_FREQ;
+		ns2->rumble.hd.hi_amp = effect->u.rumble.weak_magnitude * RUMBLE_MAX >> 16;
+		ns2->rumble.hd.lo_amp = effect->u.rumble.strong_magnitude * RUMBLE_MAX >> 16;
+	}
+	spin_unlock_irqrestore(&ns2->rumble_lock, flags);
+
+	schedule_delayed_work(&ns2->rumble_work, 0);
+
+	return 0;
+}
+
+static void switch2_rumble_work(struct work_struct *work)
+{
+	struct switch2_controller *ns2 = container_of(to_delayed_work(work),
+						      struct switch2_controller, rumble_work);
+	unsigned long flags;
+	bool active;
+	int ret = 0;
+
+	spin_lock_irqsave(&ns2->rumble_lock, flags);
+	ns2->rumble_buffer[0x1] = 0x50 | ns2->rumble_seq;
+	if (ns2->ctlr_type == NS2_CTLR_TYPE_GC) {
+		ns2->rumble_buffer[0] = 3;
+		if (ns2->rumble.sd.amplitude == 0) {
+			ns2->rumble_buffer[2] = GC_RUMBLE_STOP;
+			ns2->rumble.sd.error = 0;
+			active = false;
+		} else {
+			if (ns2->rumble.sd.error < ns2->rumble.sd.amplitude) {
+				ns2->rumble_buffer[2] = GC_RUMBLE_ON;
+				ns2->rumble.sd.error += U16_MAX - ns2->rumble.sd.amplitude;
+			} else {
+				ns2->rumble_buffer[2] = GC_RUMBLE_OFF;
+				ns2->rumble.sd.error -= ns2->rumble.sd.amplitude;
+			}
+			active = true;
+		}
+	} else {
+		ns2->rumble_buffer[0] = 1;
+		switch2_encode_rumble(&ns2->rumble.hd, &ns2->rumble_buffer[0x2]);
+		active = ns2->rumble.hd.hi_amp || ns2->rumble.hd.lo_amp;
+		if (ns2->ctlr_type == NS2_CTLR_TYPE_PRO) {
+			/*
+			 * The Pro Controller contains separate LRAs on each
+			 * side that can be controlled individually.
+			 */
+			ns2->rumble_buffer[0] = 2;
+			ns2->rumble_buffer[0x11] = 0x50 | ns2->rumble_seq;
+			switch2_encode_rumble(&ns2->rumble.hd, &ns2->rumble_buffer[0x12]);
+		}
+	}
+	ns2->rumble_seq = (ns2->rumble_seq + 1) & 0xF;
+	spin_unlock_irqrestore(&ns2->rumble_lock, flags);
+
+	if (active) {
+		unsigned long interval = msecs_to_jiffies(4);
+		uint64_t current_jiffies = get_jiffies_64();
+
+		if (!ns2->last_rumble_work)
+			ns2->last_rumble_work = current_jiffies;
+		else
+			ns2->last_rumble_work += interval;
+
+		/* Reschedule a little early to make sure the buffer never underruns */
+		interval += msecs_to_jiffies(2);
+		if (ns2->last_rumble_work + interval >= current_jiffies)
+			schedule_delayed_work(&ns2->rumble_work,
+				ns2->last_rumble_work + interval - current_jiffies);
+		else
+			schedule_delayed_work(&ns2->rumble_work, 0);
+	} else {
+		ns2->last_rumble_work = 0;
+	}
+
+	mutex_lock(&ns2->lock);
+	if (!ns2->hdev) {
+		cancel_delayed_work(&ns2->rumble_work);
+	} else {
+		ret = hid_hw_output_report(ns2->hdev, ns2->rumble_buffer, 64);
+		/*
+		 * Don't log on ENODEV, ESHUTDOWN, or EPROTO, which can happen
+		 * mid-hotplug. Also cancel any further work on ENODEV or
+		 * ESHUTDOWN as they're clear indications that the endpoint
+		 * is dead.
+		 */
+		if (ret == -ENODEV || ret == -ESHUTDOWN)
+			cancel_delayed_work(&ns2->rumble_work);
+		else if (ret < 0 && ret != -EPROTO)
+			hid_warn_ratelimited(ns2->hdev,
+				"Failed to send output report ret=%d\n", ret);
+	}
+	mutex_unlock(&ns2->lock);
+}
+#endif
+
 static int switch2_set_leds(struct switch2_controller *ns2)
 {
 	int i;
@@ -3275,6 +3448,9 @@ static void switch2_input_deref(struct input_dev *input)
 {
 	struct switch2_controller *ns2 = input_get_drvdata(input);
 
+#if IS_ENABLED(CONFIG_NINTENDO_FF)
+	cancel_delayed_work_sync(&ns2->rumble_work);
+#endif
 	kref_put(&ns2->refcount, switch2_kref_put);
 }
 
@@ -3346,6 +3522,20 @@ static int switch2_init_input(struct switch2_controller *ns2)
 		return -EINVAL;
 	}
 
+#if IS_ENABLED(CONFIG_NINTENDO_FF)
+	ns2->rumble_buffer = devm_kzalloc(&input->dev, 64, GFP_KERNEL);
+	if (!ns2->rumble_buffer) {
+		input_free_device(input);
+		return -ENOMEM;
+	}
+	input_set_capability(input, EV_FF, FF_RUMBLE);
+	ret = input_ff_create_memless(input, NULL, switch2_play_effect);
+	if (ret) {
+		input_free_device(input);
+		return ret;
+	}
+#endif
+
 	hid_info(ns2->hdev, "Firmware version %u.%u.%u (type %i)\n", ns2->version.major,
 		ns2->version.minor, ns2->version.patch, ns2->version.ctlr_type);
 	if (ns2->version.dsp_type >= 0)
@@ -3749,7 +3939,16 @@ static int switch2_init_controller(struct switch2_controller *ns2)
 		return ns2->cfg->send_command(NS2_CMD_FEATSEL, NS2_SUBCMD_FEATSEL_SET_MASK,
 			switch2_feature_mask, sizeof(switch2_feature_mask), ns2->cfg);
 	case NS2_INIT_ENABLE_FEATURES:
-		return switch2_features_enable(ns2, NS2_FEATURE_BUTTONS | NS2_FEATURE_ANALOG);
+		return switch2_features_enable(ns2, NS2_FEATURE_BUTTONS |
+			NS2_FEATURE_ANALOG | NS2_FEATURE_RUMBLE);
+	case NS2_INIT_ENABLE_RUMBLE:
+		/*
+		 * It is unclear what this packet is supposed to be for, but it
+		 * appears to be needed for rumble to work reliably. The reply
+		 * data indicates it might be a query of some sort, but we
+		 * ignore the reply so long as it doesn't return an error.
+		 */
+		return ns2->cfg->send_command(0x11, 1, NULL, 0, ns2->cfg);
 	case NS2_INIT_GRIP_BUTTONS:
 		if (!switch2_ctlr_is_joycon(ns2->ctlr_type)) {
 			switch2_init_step_done(ns2, ns2->init_step);
@@ -3861,6 +4060,10 @@ int switch2_receive_command(struct switch2_controller *ns2,
 			switch2_init_step_done(ns2, NS2_INIT_GET_FIRMWARE_INFO);
 		}
 		break;
+	case 0x11:
+		if (header->subcommand == 1)
+			switch2_init_step_done(ns2, NS2_INIT_ENABLE_RUMBLE);
+		break;
 	default:
 		break;
 	}
@@ -3979,6 +4182,11 @@ static int switch2_probe(struct hid_device *hdev, const struct hid_device_id *id
 
 	switch2_leds_create(ns2);
 
+#if IS_ENABLED(CONFIG_NINTENDO_FF)
+	spin_lock_init(&ns2->rumble_lock);
+	INIT_DELAYED_WORK(&ns2->rumble_work, switch2_rumble_work);
+#endif
+
 	ret = hid_hw_start(hdev, HID_CONNECT_HIDRAW);
 	if (ret) {
 		hid_err(hdev, "hw_start failed %d\n", ret);
@@ -4018,6 +4226,9 @@ static void switch2_remove(struct hid_device *hdev)
 {
 	struct switch2_controller *ns2 = hid_get_drvdata(hdev);
 
+#if IS_ENABLED(CONFIG_NINTENDO_FF)
+	cancel_delayed_work_sync(&ns2->rumble_work);
+#endif
 	hid_hw_close(hdev);
 	hid_hw_stop(hdev);
 	mutex_lock(&ns2->lock);
-- 
2.54.0


^ permalink raw reply related

* [PATCH v8 3/3] HID: nintendo: Add unified report format support
From: Vicki Pfau @ 2026-07-01  3:15 UTC (permalink / raw)
  To: Dmitry Torokhov, Jiri Kosina, Benjamin Tissoires, linux-input
  Cc: Vicki Pfau, Silvan Jegen
In-Reply-To: <20260701031513.3068035-1-vi@endrift.com>

This adds support for the "unified" report format that all controllers also
support, which has overlapping fields for like buttons and axes between
them.

Signed-off-by: Vicki Pfau <vi@endrift.com>
---
 drivers/hid/hid-nintendo.c | 151 +++++++++++++++++++++++++++++++++++--
 1 file changed, 146 insertions(+), 5 deletions(-)

diff --git a/drivers/hid/hid-nintendo.c b/drivers/hid/hid-nintendo.c
index 00ab4bee3dab..0bddfd84fd17 100644
--- a/drivers/hid/hid-nintendo.c
+++ b/drivers/hid/hid-nintendo.c
@@ -2872,6 +2872,36 @@ static int joycon_suspend(struct hid_device *hdev, pm_message_t message)
 #define NS2_BTN3_SR	BIT(6)
 #define NS2_BTN3_SL	BIT(7)
 
+#define NS2_BTN_U1_Y	BIT(0)
+#define NS2_BTN_U1_X	BIT(1)
+#define NS2_BTN_U1_B	BIT(2)
+#define NS2_BTN_U1_A	BIT(3)
+#define NS2_BTN_U1_SR	BIT(4)
+#define NS2_BTN_U1_SL	BIT(5)
+#define NS2_BTN_U1_R	BIT(6)
+#define NS2_BTN_U1_ZR	BIT(7)
+
+#define NS2_BTN_U2_MINUS	BIT(0)
+#define NS2_BTN_U2_PLUS		BIT(1)
+#define NS2_BTN_U2_RS		BIT(2)
+#define NS2_BTN_U2_LS		BIT(3)
+#define NS2_BTN_U2_HOME		BIT(4)
+#define NS2_BTN_U2_CAPTURE	BIT(5)
+#define NS2_BTN_U2_C		BIT(6)
+
+#define NS2_BTN_U3_DOWN		BIT(0)
+#define NS2_BTN_U3_UP		BIT(1)
+#define NS2_BTN_U3_RIGHT	BIT(2)
+#define NS2_BTN_U3_LEFT		BIT(3)
+#define NS2_BTN_U3_SR		BIT(4)
+#define NS2_BTN_U3_SL		BIT(5)
+#define NS2_BTN_U3_L		BIT(6)
+#define NS2_BTN_U3_ZL		BIT(7)
+
+#define NS2_BTN_U4_GR		BIT(0)
+#define NS2_BTN_U4_GL		BIT(1)
+#define NS2_BTN_U4_HEADSET	BIT(5)
+
 #define NS2_BTN_JCR_HOME	BIT(0)
 #define NS2_BTN_JCR_GR		BIT(2)
 #define NS2_BTN_JCR_C		NS2_BTN3_C
@@ -3120,6 +3150,22 @@ static const struct switch2_ctlr_button_mapping ns2_left_joycon_button_mappings[
 	{ /* sentinel */ },
 };
 
+static const struct switch2_ctlr_button_mapping ns2_left_joycon_button_unified_mappings[] = {
+	{ BTN_DPAD_LEFT,	2, NS2_BTN_U3_LEFT,	},
+	{ BTN_DPAD_UP,		2, NS2_BTN_U3_UP,	},
+	{ BTN_DPAD_DOWN,	2, NS2_BTN_U3_DOWN,	},
+	{ BTN_DPAD_RIGHT,	2, NS2_BTN_U3_RIGHT,	},
+	{ BTN_TL,		2, NS2_BTN_U3_L,	},
+	{ BTN_TL2,		2, NS2_BTN_U3_ZL,	},
+	{ BTN_SELECT,		1, NS2_BTN_U2_MINUS,	},
+	{ BTN_THUMBL,		1, NS2_BTN_U2_LS,	},
+	{ KEY_RECORD,		1, NS2_BTN_U2_CAPTURE,	},
+	{ BTN_GRIPR,		2, NS2_BTN_U3_SL,	},
+	{ BTN_GRIPR2,		2, NS2_BTN_U3_SR,	},
+	{ BTN_GRIPL,		3, NS2_BTN_U4_GL,	},
+	{ /* sentinel */ },
+};
+
 static const struct switch2_ctlr_button_mapping ns2_right_joycon_button_mappings[] = {
 	{ BTN_SOUTH,	0, NS2_BTNR_A,		},
 	{ BTN_EAST,	0, NS2_BTNR_B,		},
@@ -3137,6 +3183,23 @@ static const struct switch2_ctlr_button_mapping ns2_right_joycon_button_mappings
 	{ /* sentinel */ },
 };
 
+static const struct switch2_ctlr_button_mapping ns2_right_joycon_button_unified_mappings[] = {
+	{ BTN_SOUTH,	0, NS2_BTN_U1_A,	},
+	{ BTN_EAST,	0, NS2_BTN_U1_B,	},
+	{ BTN_NORTH,	0, NS2_BTN_U1_X,	},
+	{ BTN_WEST,	0, NS2_BTN_U1_Y,	},
+	{ BTN_TR,	0, NS2_BTN_U1_R,	},
+	{ BTN_TR2,	0, NS2_BTN_U1_ZR	},
+	{ BTN_START,	1, NS2_BTN_U2_PLUS,	},
+	{ BTN_THUMBR,	1, NS2_BTN_U2_RS,	},
+	{ BTN_C,	1, NS2_BTN_U2_C,	},
+	{ BTN_MODE,	1, NS2_BTN_U2_HOME,	},
+	{ BTN_GRIPL2,	0, NS2_BTN_U1_SL,	},
+	{ BTN_GRIPL,	0, NS2_BTN_U1_SR,	},
+	{ BTN_GRIPR,	3, NS2_BTN_U4_GR,	},
+	{ /* sentinel */ },
+};
+
 static const struct switch2_ctlr_button_mapping ns2_procon_mappings[] = {
 	{ BTN_SOUTH,	0, NS2_BTNR_A,		},
 	{ BTN_EAST,	0, NS2_BTNR_B,		},
@@ -3158,6 +3221,27 @@ static const struct switch2_ctlr_button_mapping ns2_procon_mappings[] = {
 	{ /* sentinel */ },
 };
 
+static const struct switch2_ctlr_button_mapping ns2_procon_unified_mappings[] = {
+	{ BTN_SOUTH,	0, NS2_BTN_U1_A,	},
+	{ BTN_EAST,	0, NS2_BTN_U1_B,	},
+	{ BTN_NORTH,	0, NS2_BTN_U1_X,	},
+	{ BTN_WEST,	0, NS2_BTN_U1_Y,	},
+	{ BTN_TL,	2, NS2_BTN_U3_L,	},
+	{ BTN_TR,	0, NS2_BTN_U1_R,	},
+	{ BTN_TL2,	2, NS2_BTN_U3_ZL,	},
+	{ BTN_TR2,	0, NS2_BTN_U1_ZR,	},
+	{ BTN_SELECT,	1, NS2_BTN_U2_MINUS,	},
+	{ BTN_START,	1, NS2_BTN_U2_PLUS,	},
+	{ BTN_THUMBL,	1, NS2_BTN_U2_LS,	},
+	{ BTN_THUMBR,	1, NS2_BTN_U2_RS,	},
+	{ BTN_MODE,	1, NS2_BTN_U2_HOME	},
+	{ KEY_RECORD,	1, NS2_BTN_U2_CAPTURE	},
+	{ BTN_GRIPR,	3, NS2_BTN_U4_GR	},
+	{ BTN_GRIPL,	3, NS2_BTN_U4_GL	},
+	{ BTN_C,	1, NS2_BTN_U2_C		},
+	{ /* sentinel */ },
+};
+
 static const struct switch2_ctlr_button_mapping ns2_gccon_mappings[] = {
 	{ BTN_SOUTH,	0, NS2_BTNR_A,		},
 	{ BTN_EAST,	0, NS2_BTNR_B,		},
@@ -3175,6 +3259,23 @@ static const struct switch2_ctlr_button_mapping ns2_gccon_mappings[] = {
 	{ /* sentinel */ },
 };
 
+static const struct switch2_ctlr_button_mapping ns2_gccon_unified_mappings[] = {
+	{ BTN_SOUTH,	0, NS2_BTN_U1_A,	},
+	{ BTN_EAST,	0, NS2_BTN_U1_B,	},
+	{ BTN_NORTH,	0, NS2_BTN_U1_X,	},
+	{ BTN_WEST,	0, NS2_BTN_U1_Y,	},
+	{ BTN_TL2,	2, NS2_BTN_U3_L,	},
+	{ BTN_TR2,	0, NS2_BTN_U1_R,	},
+	{ BTN_TL,	2, NS2_BTN_U3_ZL	},
+	{ BTN_TR,	0, NS2_BTN_U1_ZR	},
+	{ BTN_SELECT,	1, NS2_BTN_U2_MINUS,	},
+	{ BTN_START,	1, NS2_BTN_U2_PLUS,	},
+	{ BTN_MODE,	1, NS2_BTN_U2_HOME	},
+	{ KEY_RECORD,	1, NS2_BTN_U2_CAPTURE	},
+	{ BTN_C,	1, NS2_BTN_U2_C		},
+	{ /* sentinel */ },
+};
+
 static const uint8_t switch2_init_cmd_data[] = {
 	/*
 	 * The last 6 bytes of this packet are the MAC address of
@@ -3787,11 +3888,51 @@ static int switch2_event(struct hid_device *hdev, struct hid_report *report, uin
 
 	switch (report->id) {
 	case NS2_REPORT_UNIFIED:
-		/*
-		 * TODO
-		 * This won't be sent unless the report type gets changed via command
-		 * 03-0A, but we should support it at some point regardless.
-		 */
+		if (size < 0x3f)
+			return -EINVAL;
+
+		switch (ns2->ctlr_type) {
+		case NS2_CTLR_TYPE_JCL:
+			switch2_report_stick(input, &ns2->stick_calib[0],
+				ABS_X, false, ABS_Y, true, &raw_data[11]);
+			switch2_report_buttons(input, &raw_data[5],
+				ns2_left_joycon_button_unified_mappings);
+			break;
+		case NS2_CTLR_TYPE_JCR:
+			switch2_report_stick(input, &ns2->stick_calib[0],
+				ABS_X, false, ABS_Y, true, &raw_data[14]);
+			switch2_report_buttons(input, &raw_data[5],
+				ns2_right_joycon_button_unified_mappings);
+			break;
+		case NS2_CTLR_TYPE_GC:
+			input_report_abs(input, ABS_HAT0X,
+				!!(raw_data[7] & NS2_BTN_U3_RIGHT) -
+				!!(raw_data[7] & NS2_BTN_U3_LEFT));
+			input_report_abs(input, ABS_HAT0Y,
+				!!(raw_data[7] & NS2_BTN_U3_DOWN) -
+				!!(raw_data[7] & NS2_BTN_U3_UP));
+			switch2_report_buttons(input, &raw_data[5], ns2_gccon_unified_mappings);
+			switch2_report_stick(input, &ns2->stick_calib[0],
+				ABS_X, false, ABS_Y, true, &raw_data[11]);
+			switch2_report_stick(input, &ns2->stick_calib[1],
+				ABS_RX, false, ABS_RY, true, &raw_data[14]);
+			switch2_report_trigger(input, ns2->lt_zero, ABS_Z, raw_data[0x3d]);
+			switch2_report_trigger(input, ns2->rt_zero, ABS_RZ, raw_data[0x3e]);
+			break;
+		case NS2_CTLR_TYPE_PRO:
+			input_report_abs(input, ABS_HAT0X,
+				!!(raw_data[7] & NS2_BTN_U3_RIGHT) -
+				!!(raw_data[7] & NS2_BTN_U3_LEFT));
+			input_report_abs(input, ABS_HAT0Y,
+				!!(raw_data[7] & NS2_BTN_U3_DOWN) -
+				!!(raw_data[7] & NS2_BTN_U3_UP));
+			switch2_report_buttons(input, &raw_data[5], ns2_procon_unified_mappings);
+			switch2_report_stick(input, &ns2->stick_calib[0],
+				ABS_X, false, ABS_Y, true, &raw_data[11]);
+			switch2_report_stick(input, &ns2->stick_calib[1],
+				ABS_RX, false, ABS_RY, true, &raw_data[14]);
+			break;
+		}
 		break;
 	case NS2_REPORT_JCL:
 		switch2_report_stick(input, &ns2->stick_calib[0], ABS_X, false,
-- 
2.54.0


^ permalink raw reply related


This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox