* [PATCH v2] HID: asus: do not send keyboard init reports to touchpads
@ 2026-08-18 15:14 Panz Dev
2026-08-18 15:29 ` sashiko-bot
0 siblings, 1 reply; 2+ messages in thread
From: Panz Dev @ 2026-08-18 15:14 UTC (permalink / raw)
To: Jiri Kosina, Benjamin Tissoires
Cc: Denis Benato, linux-input, linux-kernel, stable, Panz Dev
Commit 0919db9f3583 ("HID: asus: always fully initialize devices") added a
loop during asus_probe() to send keyboard feature report initializations
(asus_kbd_init) to all ASUS HID devices.
On ASUS laptops with I2C/HID touchpads (such as the ASUS E200HA), sending
keyboard feature reports (FEATURE_KBD_REPORT_ID) to touchpad endpoints
sends invalid feature requests to touchpad hardware, corrupting probe
state and causing the touchpad to become unresponsive.
Wrap the asus_report_id_init loop in an `if (!drvdata->tp)` check so
keyboard feature initialization only runs for actual keyboards.
Tested on ASUS E200HA (where touchpad functionality is fully restored)
and ASUS VivoBook Flip 14 TP401MA (confirming zero regressions).
Fixes: 0919db9f3583 ("HID: asus: always fully initialize devices")
Cc: stable@vger.kernel.org
Signed-off-by: Panz Dev <panz.development@gmail.com>
---
v2:
- Keep asus_start_multitouch() inside the HID_CLAIMED_INPUT check to avoid
any UAF risk if input registration fails (as pointed out by Denis Benato
and automated review).
- Focus the fix on skipping keyboard report initialization for touchpads.
---
drivers/hid/hid-asus.c | 12 +++++++-----
1 file changed, 7 insertions(+), 5 deletions(-)
diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c
index 3f5e96900b67..7f19ca1e5a1b 100644
--- a/drivers/hid/hid-asus.c
+++ b/drivers/hid/hid-asus.c
@@ -1294,12 +1294,14 @@ static int asus_probe(struct hid_device *hdev, const struct hid_device_id *id)
return ret;
}
- for (int r = 0; r < ARRAY_SIZE(asus_report_id_init); r++) {
- if (asus_has_report_id(hdev, asus_report_id_init[r])) {
- ret = asus_kbd_init(hdev, asus_report_id_init[r]);
- if (ret < 0)
- hid_warn(hdev, "Failed to initialize 0x%x: %d.\n",
- asus_report_id_init[r], ret);
+ if (!drvdata->tp) {
+ for (int r = 0; r < ARRAY_SIZE(asus_report_id_init); r++) {
+ if (asus_has_report_id(hdev, asus_report_id_init[r])) {
+ ret = asus_kbd_init(hdev, asus_report_id_init[r]);
+ if (ret < 0)
+ hid_warn(hdev, "Failed to initialize 0x%x: %d.\n",
+ asus_report_id_init[r], ret);
+ }
}
}
--
2.47.0
^ permalink raw reply related [flat|nested] 2+ messages in thread* Re: [PATCH v2] HID: asus: do not send keyboard init reports to touchpads
2026-08-18 15:14 [PATCH v2] HID: asus: do not send keyboard init reports to touchpads Panz Dev
@ 2026-08-18 15:29 ` sashiko-bot
0 siblings, 0 replies; 2+ messages in thread
From: sashiko-bot @ 2026-08-18 15:29 UTC (permalink / raw)
To: Panz Dev; +Cc: dmitry.torokhov, linux-input
Thank you for your contribution! Sashiko AI review found 4 potential issue(s) to consider:
Pre-existing issues:
- [Critical] Missing `hid_is_usb()` check before casting the parent device to a `usb_interface` in `asus_kbd_register_leds()`.
- [High] Dangling pointer `drvdata->kbd_backlight` causes a Use-After-Free in `asus_remove()` if `asus_hid_register_listener()` fails.
- [High] Incorrect teardown order in `asus_remove()` cancels `fn_lock_sync_work` before stopping the hardware, leading to a Use-After-Free race condition.
- [High] Dangling pointer dereference of `drvdata->input` in `asus_probe()` when a device has multiple report IDs or applications and the last one has no mapped usages.
--
--- Patch [1]: [PATCH v2] HID: asus: do not send keyboard init reports to touchpads ---
commit 83a2843d77c483e6b894c00208643414ac5b2d26
Author: Panz Dev <panz.development@gmail.com>
HID: asus: do not send keyboard init reports to touchpads
This commit avoids sending keyboard feature reports to touchpad endpoints
by wrapping the initialization loop in an if (!drvdata->tp) check. This
prevents sending invalid feature requests that could corrupt the touchpad
probe state.
> diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c
> --- a/drivers/hid/hid-asus.c
> +++ b/drivers/hid/hid-asus.c
[ ... ]
> - for (int r = 0; r < ARRAY_SIZE(asus_report_id_init); r++) {
> - if (asus_has_report_id(hdev, asus_report_id_init[r])) {
> - ret = asus_kbd_init(hdev, asus_report_id_init[r]);
> - if (ret < 0)
> - hid_warn(hdev, "Failed to initialize 0x%x: %d.\n",
> - asus_report_id_init[r], ret);
> + if (!drvdata->tp) {
> + for (int r = 0; r < ARRAY_SIZE(asus_report_id_init); r++) {
> + if (asus_has_report_id(hdev, asus_report_id_init[r])) {
> + ret = asus_kbd_init(hdev, asus_report_id_init[r]);
> + if (ret < 0)
> + hid_warn(hdev, "Failed to initialize 0x%x: %d.\n",
> + asus_report_id_init[r], ret);
> + }
> }
> }
[ ... ]
> if (drvdata->input && (hdev->claimed & HID_CLAIMED_INPUT)) {
> if (drvdata->tp)
> drvdata->input->name = "Asus TouchPad";
[Severity: High]
This is a pre-existing issue, but can this lead to a use-after-free?
When a device uses HID_QUIRK_MULTI_INPUT, hidinput_connect() creates a
separate hid_input for each application. The asus_input_configured() function
unconditionally assigns drvdata->input = hi->input.
If the last report ID processed has no valid input usages, the hid_input and
its input_dev are freed by the core, leaving drvdata->input pointing to
freed memory.
Since earlier valid report IDs successfully registered, HID_CLAIMED_INPUT is
set. Could this dereference the freed pointer here to set the name?
While reviewing the driver, I also noticed a few other pre-existing issues
in this file:
> static int asus_kbd_register_leds(struct hid_device *hdev)
> {
[ ... ]
> if (drvdata->quirks & QUIRK_ROG_ALLY_XPAD) {
> intf = to_usb_interface(hdev->dev.parent);
> udev = interface_to_usbdev(intf);
> validate_mcu_fw_version(hdev,
> le16_to_cpu(udev->descriptor.idProduct));
> }
[Severity: Critical]
This is a pre-existing issue, but does asus_kbd_register_leds() need to verify
the transport type before casting the parent device?
If the driver is bound via a non-USB transport like an injected uhid device,
the parent is not a USB interface. Can this read of the product ID access
invalid memory and cause a crash?
[ ... ]
> ret = asus_hid_register_listener(&drvdata->kbd_backlight->listener);
> if (ret < 0) {
> /* No need to have this still around */
> devm_kfree(&hdev->dev, drvdata->kbd_backlight);
> }
[Severity: High]
This isn't a bug introduced by this patch, but does asus_kbd_register_leds()
leave a dangling pointer if asus_hid_register_listener() fails?
The error path calls devm_kfree() on drvdata->kbd_backlight but doesn't
set the pointer to NULL.
During unbind, asus_remove() checks if (drvdata->kbd_backlight) and
dereferences it. Could this cause a use-after-free?
[ ... ]
> static void asus_remove(struct hid_device *hdev)
> {
> struct asus_drvdata *drvdata = hid_get_drvdata(hdev);
[ ... ]
> if (drvdata->quirks & QUIRK_HID_FN_LOCK)
> cancel_work_sync(&drvdata->fn_lock_sync_work);
>
> hid_hw_stop(hdev);
[Severity: High]
This is a pre-existing issue, but is the teardown order in asus_remove()
safe from race conditions?
cancel_work_sync() is called before hid_hw_stop(). Because the hardware is
not stopped, incoming HID reports can continue to trigger asus_event() and
unconditionally re-queue the worker:
drivers/hid/hid-asus.c:asus_event() {
...
if (drvdata->quirks & QUIRK_HID_FN_LOCK) {
drvdata->fn_lock = !drvdata->fn_lock;
schedule_work(&drvdata->fn_lock_sync_work);
}
...
}
Could the pending work item execute after devres frees drvdata, leading to a
use-after-free?
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260818151431.939132-1-panz.development@gmail.com?part=1
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2026-08-18 15:29 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-08-18 15:14 [PATCH v2] HID: asus: do not send keyboard init reports to touchpads Panz Dev
2026-08-18 15:29 ` sashiko-bot
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox