* [PATCH] HID: core: demote data shortness warning to debug level
@ 2026-05-23 10:38 Matteo Croce
2026-05-23 10:45 ` sashiko-bot
0 siblings, 1 reply; 2+ messages in thread
From: Matteo Croce @ 2026-05-23 10:38 UTC (permalink / raw)
To: Jiri Kosina, Benjamin Tissoires, Lee Jones
Cc: linux-input, linux-kernel, Matteo Croce
From: Matteo Croce <teknoraver@meta.com>
Commit 0a3fe972a7cb ("HID: core: Mitigate potential OOB by removing
bogus memset()") changed the log level of the short report message from
debug to warning, flooding syslog on systems with devices that
regularly send short reports, in my case an UPS:
$ dmesg |grep -c 'Event data for report .* was too short'
35
Demote it back to debug level.
Fixes: 0a3fe972a7cb ("HID: core: Mitigate potential OOB by removing bogus memset()")
Signed-off-by: Matteo Croce <teknoraver@meta.com>
---
drivers/hid/hid-core.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index 41a79e43c82b..76cfed8b93c1 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -2050,8 +2050,8 @@ int hid_report_raw_event(struct hid_device *hid, enum hid_report_type type, u8 *
return 0;
if (unlikely(bsize < csize)) {
- hid_warn_ratelimited(hid, "Event data for report %d is incorrect (%d vs %zu)\n",
- report->id, csize, bsize);
+ hid_dbg_ratelimited(hid, "Event data for report %d is incorrect (%d vs %zu)\n",
+ report->id, csize, bsize);
return -EINVAL;
}
--
2.50.1
^ permalink raw reply related [flat|nested] 2+ messages in thread
* Re: [PATCH] HID: core: demote data shortness warning to debug level
2026-05-23 10:38 [PATCH] HID: core: demote data shortness warning to debug level Matteo Croce
@ 2026-05-23 10:45 ` sashiko-bot
0 siblings, 0 replies; 2+ messages in thread
From: sashiko-bot @ 2026-05-23 10:45 UTC (permalink / raw)
To: Matteo Croce; +Cc: dmitry.torokhov, linux-input
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Medium] The patch modifies the wrong warning message, failing to fix the stated issue and inappropriately masking a different error.
--
commit a5df696ba5cc949fba165e62139d8984b9884331
Author: Matteo Croce <teknoraver@meta.com>
HID: core: demote data shortness warning to debug level
This commit intends to reduce syslog flooding from devices that regularly
send short reports by demoting the "was too short" warning to a debug print.
> diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
> index 41a79e43c82b3..76cfed8b93c15 100644
> --- a/drivers/hid/hid-core.c
> +++ b/drivers/hid/hid-core.c
> @@ -2050,8 +2050,8 @@ int hid_report_raw_event(struct hid_device *hid, enum hid_report_type type, u8 *
> return 0;
>
> if (unlikely(bsize < csize)) {
> - hid_warn_ratelimited(hid, "Event data for report %d is incorrect (%d vs %zu)\n",
> - report->id, csize, bsize);
> + hid_dbg_ratelimited(hid, "Event data for report %d is incorrect (%d vs %zu)\n",
> + report->id, csize, bsize);
[Severity: Medium]
Does this change modify the intended warning message?
The commit message notes the intention to silence the "was too short" warning.
However, this patch modifies the "is incorrect" warning instead, which triggers
when the reported size claims to be larger than the actual buffer size
(bsize < csize).
The target "was too short" warning appears further down in the function during
the bsize < rsize check.
As a result, this might leave the original syslog flooding issue unresolved
while potentially hiding a different transport driver condition.
> return -EINVAL;
> }
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260523103806.60480-1-technoboy85@gmail.com?part=1
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2026-05-23 10:45 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-05-23 10:38 [PATCH] HID: core: demote data shortness warning to debug level Matteo Croce
2026-05-23 10:45 ` sashiko-bot
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox