* [PATCH] HID: core: Fix bsize printk specifier in hid_report_raw_event()
@ 2026-05-22 7:27 yaolu
2026-05-22 7:31 ` sashiko-bot
2026-05-22 8:46 ` Benjamin Tissoires
0 siblings, 2 replies; 3+ messages in thread
From: yaolu @ 2026-05-22 7:27 UTC (permalink / raw)
To: jikos, bentiss; +Cc: linux-input, linux-kernel, Lu Yao, k2ci
From: Lu Yao <yaolu@kylinos.cn>
Fix the following warning during build time:
drivers/hid/hid-core.c:2053:43: error: format ‘%ld’ expects argument of type ‘long int’, but argument 5 has type ‘size_t’ {aka ‘unsigned int’} [-Werror=format=]
drivers/hid/hid-core.c:2075:43: error: format ‘%ld’ expects argument of type ‘long int’, but argument 5 has type ‘size_t’ {aka ‘unsigned int’} [-Werror=format=]
Fixes: 2c85c61d1332 ("HID: pass the buffer size to hid_report_raw_event")
Reported-by: k2ci <kernel-bot@kylinos.cn>
Signed-off-by: Lu Yao <yaolu@kylinos.cn>
---
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 b3596851c719..c21c58d7bf02 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -2050,7 +2050,7 @@ 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 %ld)\n",
+ hid_warn_ratelimited(hid, "Event data for report %d is incorrect (%d vs %u)\n",
report->id, csize, bsize);
return -EINVAL;
}
@@ -2072,7 +2072,7 @@ int hid_report_raw_event(struct hid_device *hid, enum hid_report_type type, u8 *
rsize = max_buffer_size;
if (bsize < rsize) {
- hid_warn_ratelimited(hid, "Event data for report %d was too short (%d vs %ld)\n",
+ hid_warn_ratelimited(hid, "Event data for report %d was too short (%d vs %u)\n",
report->id, rsize, bsize);
return -EINVAL;
}
--
2.25.1
^ permalink raw reply related [flat|nested] 3+ messages in thread* Re: [PATCH] HID: core: Fix bsize printk specifier in hid_report_raw_event()
2026-05-22 7:27 [PATCH] HID: core: Fix bsize printk specifier in hid_report_raw_event() yaolu
@ 2026-05-22 7:31 ` sashiko-bot
2026-05-22 8:46 ` Benjamin Tissoires
1 sibling, 0 replies; 3+ messages in thread
From: sashiko-bot @ 2026-05-22 7:31 UTC (permalink / raw)
To: yaolu; +Cc: linux-input, dmitry.torokhov
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Low] Incorrect format specifier for the `size_t` variable `bsize`. The patch replaces `%ld` with `%u` to fix a warning on 32-bit architectures (where `size_t` is `unsigned int`), but this introduces a new warning on 64-bit architectures (where `size_t` is `unsigned long`). The correct format specifier for `size_t` is `%zu`.
--
commit d6a5fb9c76c9718771a50e1f79f29b3df496f869
Author: Lu Yao <yaolu@kylinos.cn>
HID: core: Fix bsize printk specifier in hid_report_raw_event()
This commit attempts to fix a build warning on 32-bit architectures by
changing the format specifier for a size_t variable from %ld to %u.
> diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
> index b3596851c7191..c21c58d7bf02b 100644
> --- a/drivers/hid/hid-core.c
> +++ b/drivers/hid/hid-core.c
> @@ -2050,7 +2050,7 @@ 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 %ld)\n",
> + hid_warn_ratelimited(hid, "Event data for report %d is incorrect (%d vs %u)\n",
[Severity: Low]
Will this cause a new format string warning on 64-bit architectures? bsize is
of type size_t, which is an unsigned long on 64-bit systems. Should this use
the %zu format specifier instead to be portable across both 32-bit and 64-bit
architectures?
> report->id, csize, bsize);
> return -EINVAL;
> }
[ ... ]
> @@ -2072,7 +2072,7 @@ int hid_report_raw_event(struct hid_device *hid, enum hid_report_type type, u8 *
> rsize = max_buffer_size;
>
> if (bsize < rsize) {
> - hid_warn_ratelimited(hid, "Event data for report %d was too short (%d vs %ld)\n",
> + hid_warn_ratelimited(hid, "Event data for report %d was too short (%d vs %u)\n",
[Severity: Low]
Similarly here, should this also use %zu for the size_t variable bsize?
> report->id, rsize, bsize);
> return -EINVAL;
> }
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260522072718.186707-1-yaolu@kylinos.cn?part=1
^ permalink raw reply [flat|nested] 3+ messages in thread* Re: [PATCH] HID: core: Fix bsize printk specifier in hid_report_raw_event()
2026-05-22 7:27 [PATCH] HID: core: Fix bsize printk specifier in hid_report_raw_event() yaolu
2026-05-22 7:31 ` sashiko-bot
@ 2026-05-22 8:46 ` Benjamin Tissoires
1 sibling, 0 replies; 3+ messages in thread
From: Benjamin Tissoires @ 2026-05-22 8:46 UTC (permalink / raw)
To: yaolu; +Cc: jikos, linux-input, linux-kernel, k2ci
On May 22 2026, yaolu@kylinos.cn wrote:
> From: Lu Yao <yaolu@kylinos.cn>
>
> Fix the following warning during build time:
>
> drivers/hid/hid-core.c:2053:43: error: format ‘%ld’ expects argument of type ‘long int’, but argument 5 has type ‘size_t’ {aka ‘unsigned int’} [-Werror=format=]
> drivers/hid/hid-core.c:2075:43: error: format ‘%ld’ expects argument of type ‘long int’, but argument 5 has type ‘size_t’ {aka ‘unsigned int’} [-Werror=format=]
>
> Fixes: 2c85c61d1332 ("HID: pass the buffer size to hid_report_raw_event")
> Reported-by: k2ci <kernel-bot@kylinos.cn>
> Signed-off-by: Lu Yao <yaolu@kylinos.cn>
In addition to shashiko comments about %zu, it's already in linus' tree:
4d3a2a466b8d ("HID: core: Fix size_t specifier in hid_report_raw_event()")
Cheers,
Benjamin
> ---
> 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 b3596851c719..c21c58d7bf02 100644
> --- a/drivers/hid/hid-core.c
> +++ b/drivers/hid/hid-core.c
> @@ -2050,7 +2050,7 @@ 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 %ld)\n",
> + hid_warn_ratelimited(hid, "Event data for report %d is incorrect (%d vs %u)\n",
> report->id, csize, bsize);
> return -EINVAL;
> }
> @@ -2072,7 +2072,7 @@ int hid_report_raw_event(struct hid_device *hid, enum hid_report_type type, u8 *
> rsize = max_buffer_size;
>
> if (bsize < rsize) {
> - hid_warn_ratelimited(hid, "Event data for report %d was too short (%d vs %ld)\n",
> + hid_warn_ratelimited(hid, "Event data for report %d was too short (%d vs %u)\n",
> report->id, rsize, bsize);
> return -EINVAL;
> }
> --
> 2.25.1
>
>
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2026-05-22 8:46 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-05-22 7:27 [PATCH] HID: core: Fix bsize printk specifier in hid_report_raw_event() yaolu
2026-05-22 7:31 ` sashiko-bot
2026-05-22 8:46 ` Benjamin Tissoires
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox