* [PATCH] HID: usbhid: Use seq_buf_putc() in three functions
@ 2026-06-25 9:22 Markus Elfring
2026-06-25 9:32 ` sashiko-bot
0 siblings, 1 reply; 4+ messages in thread
From: Markus Elfring @ 2026-06-25 9:22 UTC (permalink / raw)
To: linux-input, linux-usb, Benjamin Tissoires, Jiri Kosina,
Mahad Ibrahim
Cc: LKML, kernel-janitors, Woradorn Laodhanadhaworn
From: Markus Elfring <elfring@users.sourceforge.net>
Date: Thu, 25 Jun 2026 11:11:26 +0200
A single space character should occasionally be put into a sequence buffer.
Thus use the function “seq_buf_putc” in these implementations.
The source code was transformed by using the Coccinelle software.
Signed-off-by: Markus Elfring <elfring@users.sourceforge.net>
---
drivers/hid/usbhid/hid-core.c | 2 +-
drivers/hid/usbhid/usbkbd.c | 2 +-
drivers/hid/usbhid/usbmouse.c | 2 +-
3 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c
index 96b0181cf819..a755102b8cfe 100644
--- a/drivers/hid/usbhid/hid-core.c
+++ b/drivers/hid/usbhid/hid-core.c
@@ -1412,7 +1412,7 @@ static int usbhid_probe(struct usb_interface *intf, const struct usb_device_id *
if (dev->product) {
if (dev->manufacturer)
- seq_buf_puts(&hid_name, " ");
+ seq_buf_putc(&hid_name, ' ');
seq_buf_puts(&hid_name, dev->product);
}
diff --git a/drivers/hid/usbhid/usbkbd.c b/drivers/hid/usbhid/usbkbd.c
index 83d4df0d7a45..02abd54eca49 100644
--- a/drivers/hid/usbhid/usbkbd.c
+++ b/drivers/hid/usbhid/usbkbd.c
@@ -302,7 +302,7 @@ static int usb_kbd_probe(struct usb_interface *iface,
if (dev->product) {
if (dev->manufacturer)
- seq_buf_puts(&kbd_name, " ");
+ seq_buf_putc(&kbd_name, ' ');
seq_buf_puts(&kbd_name, dev->product);
}
diff --git a/drivers/hid/usbhid/usbmouse.c b/drivers/hid/usbhid/usbmouse.c
index b3b2abeee614..9fce51d65cd6 100644
--- a/drivers/hid/usbhid/usbmouse.c
+++ b/drivers/hid/usbhid/usbmouse.c
@@ -150,7 +150,7 @@ static int usb_mouse_probe(struct usb_interface *intf, const struct usb_device_i
if (dev->product) {
if (dev->manufacturer)
- seq_buf_puts(&mouse_name, " ");
+ seq_buf_putc(&mouse_name, ' ');
seq_buf_puts(&mouse_name, dev->product);
}
--
2.54.0
^ permalink raw reply related [flat|nested] 4+ messages in thread* Re: [PATCH] HID: usbhid: Use seq_buf_putc() in three functions
2026-06-25 9:22 [PATCH] HID: usbhid: Use seq_buf_putc() in three functions Markus Elfring
@ 2026-06-25 9:32 ` sashiko-bot
2026-06-25 9:55 ` Markus Elfring
2026-06-25 16:55 ` Markus Elfring
0 siblings, 2 replies; 4+ messages in thread
From: sashiko-bot @ 2026-06-25 9:32 UTC (permalink / raw)
To: Markus Elfring; +Cc: linux-input, dmitry.torokhov
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Medium] Replacing `seq_buf_puts()` with `seq_buf_putc()` introduces a NUL-termination bug when the manufacturer string is exactly 127 bytes long, leading to an out-of-bounds read.
--
commit c41669030bdd8635988fc175a1caf4183a28344a
Author: Markus Elfring <elfring@users.sourceforge.net>
HID: usbhid: Use seq_buf_putc() in three functions
This patch updates three probe functions to use seq_buf_putc() instead
of seq_buf_puts() when inserting a single space character into sequence
buffers.
> diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c
> --- a/drivers/hid/usbhid/hid-core.c
> +++ b/drivers/hid/usbhid/hid-core.c
> @@ -1412,7 +1412,7 @@ static int usbhid_probe(struct usb_interface *intf, const struct usb_device_id *
>
> if (dev->product) {
> if (dev->manufacturer)
> - seq_buf_puts(&hid_name, " ");
> + seq_buf_putc(&hid_name, ' ');
[Severity: Medium]
Does this change introduce a missing null termination bug in usbhid_probe()
if the manufacturer string is exactly 127 bytes long?
The previous code using seq_buf_puts() requires two bytes of available
capacity (one for the space, one for the trailing null byte) and safely fails
if there isn't enough room.
Looking at seq_buf_putc(), it only checks if there is room for one byte.
If the sequence buffer is exactly 128 bytes long and already contains 127
characters from dev->manufacturer plus the null terminator, seq_buf_putc()
will overwrite the null terminator at index 127 with a space character.
This leaves hid->name completely unterminated. When exposed to userspace via
sysfs or input ioctls, this could lead to an out-of-bounds read into the
adjacent hid->phys memory field.
> seq_buf_puts(&hid_name, dev->product);
> }
>
> diff --git a/drivers/hid/usbhid/usbkbd.c b/drivers/hid/usbhid/usbkbd.c
> --- a/drivers/hid/usbhid/usbkbd.c
> +++ b/drivers/hid/usbhid/usbkbd.c
[ ... ]
> @@ -302,7 +302,7 @@ static int usb_kbd_probe(struct usb_interface *iface,
>
> if (dev->product) {
> if (dev->manufacturer)
> - seq_buf_puts(&kbd_name, " ");
> + seq_buf_putc(&kbd_name, ' ');
[Severity: Medium]
Does this have the same unterminated string issue for kbd->name in
usb_kbd_probe()?
If an untrusted USB device presents a manufacturer string of exactly 127
bytes, this overwrite could allow an out-of-bounds read into the adjacent
kbd->phys array.
> seq_buf_puts(&kbd_name, dev->product);
> }
>
> diff --git a/drivers/hid/usbhid/usbmouse.c b/drivers/hid/usbhid/usbmouse.c
> --- a/drivers/hid/usbhid/usbmouse.c
> +++ b/drivers/hid/usbhid/usbmouse.c
[ ... ]
> @@ -150,7 +150,7 @@ static int usb_mouse_probe(struct usb_interface *intf, const struct usb_device_i
>
> if (dev->product) {
> if (dev->manufacturer)
> - seq_buf_puts(&mouse_name, " ");
> + seq_buf_putc(&mouse_name, ' ');
[Severity: Medium]
Is mouse->name vulnerable to the same null terminator overwrite here in
usb_mouse_probe()?
Similarly, this could leak the contents of mouse->phys to userspace.
> seq_buf_puts(&mouse_name, dev->product);
> }
>
--
Sashiko AI review · https://sashiko.dev/#/patchset/89e9c672-efee-4ed2-9ef5-637ec9707f0b@web.de?part=1
^ permalink raw reply [flat|nested] 4+ messages in thread* Re: [PATCH] HID: usbhid: Use seq_buf_putc() in three functions
2026-06-25 9:32 ` sashiko-bot
@ 2026-06-25 9:55 ` Markus Elfring
2026-06-25 16:55 ` Markus Elfring
1 sibling, 0 replies; 4+ messages in thread
From: Markus Elfring @ 2026-06-25 9:55 UTC (permalink / raw)
To: sashiko-reviews, linux-input, linux-usb, Benjamin Tissoires,
Jiri Kosina, Mahad Ibrahim
Cc: Dmitry Torokhov, Woradorn Laodhanadhaworn, LKML, kernel-janitors
> Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
> - [Medium] Replacing `seq_buf_puts()` with `seq_buf_putc()` introduces a NUL-termination bug when the manufacturer string is exactly 127 bytes long, leading to an out-of-bounds read.
These functions were used without error detection so far.
> --
>
> commit c41669030bdd8635988fc175a1caf4183a28344a
> Author: Markus Elfring <elfring@users.sourceforge.net>
>
> HID: usbhid: Use seq_buf_putc() in three functions
>
> This patch updates three probe functions to use seq_buf_putc() instead
> of seq_buf_puts() when inserting a single space character into sequence
> buffers.
>
>> diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c
>> --- a/drivers/hid/usbhid/hid-core.c
>> +++ b/drivers/hid/usbhid/hid-core.c
>> @@ -1412,7 +1412,7 @@ static int usbhid_probe(struct usb_interface *intf, const struct usb_device_id *
>>
>> if (dev->product) {
>> if (dev->manufacturer)
>> - seq_buf_puts(&hid_name, " ");
>> + seq_buf_putc(&hid_name, ' ');
>
> [Severity: Medium]
> Does this change introduce a missing null termination bug in usbhid_probe()
> if the manufacturer string is exactly 127 bytes long?
>
> The previous code using seq_buf_puts() requires two bytes of available
> capacity (one for the space, one for the trailing null byte) and safely fails
> if there isn't enough room.
Can descriptions be extended for possible failure conditions?
https://elixir.bootlin.com/linux/v7.1.1/source/lib/seq_buf.c#L203-L221
> Looking at seq_buf_putc(), it only checks if there is room for one byte.
> If the sequence buffer is exactly 128 bytes long and already contains 127
> characters from dev->manufacturer plus the null terminator, seq_buf_putc()
> will overwrite the null terminator at index 127 with a space character.
>
> This leaves hid->name completely unterminated. When exposed to userspace via
> sysfs or input ioctls, this could lead to an out-of-bounds read into the
> adjacent hid->phys memory field.
>
>> seq_buf_puts(&hid_name, dev->product);
How likely is it that such product information will be appended as expected
at mentioned source code places?
Regards,
Markus
^ permalink raw reply [flat|nested] 4+ messages in thread* Re: [PATCH] HID: usbhid: Use seq_buf_putc() in three functions
2026-06-25 9:32 ` sashiko-bot
2026-06-25 9:55 ` Markus Elfring
@ 2026-06-25 16:55 ` Markus Elfring
1 sibling, 0 replies; 4+ messages in thread
From: Markus Elfring @ 2026-06-25 16:55 UTC (permalink / raw)
To: sashiko-reviews, linux-input, linux-usb, Benjamin Tissoires,
Jiri Kosina, Mahad Ibrahim
Cc: Dmitry Torokhov, Steven Rostedt, Woradorn Laodhanadhaworn, LKML,
kernel-janitors
>> +++ b/drivers/hid/usbhid/hid-core.c
>> @@ -1412,7 +1412,7 @@ static int usbhid_probe(struct usb_interface *intf, const struct usb_device_id *
>>
>> if (dev->product) {
>> if (dev->manufacturer)
>> - seq_buf_puts(&hid_name, " ");
>> + seq_buf_putc(&hid_name, ' ');
>
> [Severity: Medium]
> Does this change introduce a missing null termination bug in usbhid_probe()
> if the manufacturer string is exactly 127 bytes long?
>
> The previous code using seq_buf_puts() requires two bytes of available
> capacity (one for the space, one for the trailing null byte) and safely fails
> if there isn't enough room.
I see a need to reconsider such information in more detail.
> Looking at seq_buf_putc(), it only checks if there is room for one byte.
> If the sequence buffer is exactly 128 bytes long
This is the case as such a technical detail can be determined from the member “name”
of the data structure “hid_device”.
https://elixir.bootlin.com/linux/v7.1.1/source/include/linux/hid.h#L721
> and already contains 127
> characters from dev->manufacturer plus the null terminator, seq_buf_putc()
> will overwrite the null terminator at index 127 with a space character.
Other contributors can add further experiences for corresponding data length characteristics.
> This leaves hid->name completely unterminated.
I would like to point the comment “Don't count the trailing null byte against the capacity”
once more from the implementation of the function “seq_buf_puts”.
https://elixir.bootlin.com/linux/v7.1.1/source/lib/seq_buf.c#L193-L194
> When exposed to userspace via
> sysfs or input ioctls, this could lead to an out-of-bounds read into the
> adjacent hid->phys memory field.
If such a data reuse would be attempted, API requirements for sequence buffers
should probably be taken better into account at a concrete place.
Regards,
Markus
^ permalink raw reply [flat|nested] 4+ messages in thread
end of thread, other threads:[~2026-06-25 16:55 UTC | newest]
Thread overview: 4+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-06-25 9:22 [PATCH] HID: usbhid: Use seq_buf_putc() in three functions Markus Elfring
2026-06-25 9:32 ` sashiko-bot
2026-06-25 9:55 ` Markus Elfring
2026-06-25 16:55 ` Markus Elfring
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox