From: sashiko-bot@kernel.org
To: "Geert Uytterhoeven" <geert+renesas@glider.be>
Cc: linux-amlogic@lists.infradead.org, linux-clk@vger.kernel.org,
neil.armstrong@linaro.org, linux-hwmon@vger.kernel.org
Subject: Re: [PATCH treewide 4/5] iio: frequency: adf4377: Make sure clk_init_data is fully initialized
Date: Wed, 19 Aug 2026 19:13:16 +0000 [thread overview]
Message-ID: <20260819191316.8F2F21F000E9@smtp.kernel.org> (raw)
In-Reply-To: <302584628c4c0699239a0218376fe1c11cdc8944.1787165329.git.geert+renesas@glider.be>
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
Pre-existing issues:
- [High] Incomplete fix for uninitialized stack variables: `struct clk_parent_data parent_data` remains uninitialized on the stack, leading to a kernel crash during clock registration.
--
--- Patch [4]: [PATCH treewide 4/5] iio: frequency: adf4377: Make sure clk_init_data is fully initialized ---
commit 99e024a77f5bce5921d3c6b46054263aa450610d
Author: Geert Uytterhoeven <geert+renesas@glider.be>
iio: frequency: adf4377: Make sure clk_init_data is fully initialized
This commit initializes the clk_init_data structure in
adf4377_clk_register() to zero. This prevents crashes caused by
uninitialized fields like parent_names when CONFIG_INIT_STACK_ALL_PATTERN
or CONFIG_INIT_STACK_NONE is enabled.
> diff --git a/drivers/iio/frequency/adf4377.c b/drivers/iio/frequency/adf4377.c
> --- a/drivers/iio/frequency/adf4377.c
> +++ b/drivers/iio/frequency/adf4377.c
> @@ -999,7 +999,7 @@ static int adf4377_clk_register(struct adf4377_state *st)
> {
> struct spi_device *spi = st->spi;
> struct device *dev = &spi->dev;
> - struct clk_init_data init;
> + struct clk_init_data init = {};
> struct clk_parent_data parent_data;
[Severity: High]
This is a pre-existing issue, but does this struct clk_parent_data also
need to be zero-initialized?
Only fw_name is explicitly assigned below, leaving name, hw, and index
populated with stack garbage. When adf4377_clk_register() passes this to
the clock framework, clk_core_populate_parent_map() will read
parent_data.name and pass it to clk_cpy_name(), which ultimately calls
strlen() and can cause a page fault during probe.
[ ... ]
> parent_data.fw_name = "ref_in";
>
> init.ops = &adf4377_clk_ops;
> init.parent_data = &parent_data;
--
Sashiko AI review · https://sashiko.dev/#/patchset/cover.1787165329.git.geert+renesas@glider.be?part=4
_______________________________________________
linux-amlogic mailing list
linux-amlogic@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-amlogic
WARNING: multiple messages have this Message-ID (diff)
From: sashiko-bot@kernel.org
To: "Geert Uytterhoeven" <geert+renesas@glider.be>
Cc: linux-amlogic@lists.infradead.org, linux-clk@vger.kernel.org,
neil.armstrong@linaro.org, linux-hwmon@vger.kernel.org
Subject: Re: [PATCH treewide 4/5] iio: frequency: adf4377: Make sure clk_init_data is fully initialized
Date: Wed, 19 Aug 2026 19:13:16 +0000 [thread overview]
Message-ID: <20260819191316.8F2F21F000E9@smtp.kernel.org> (raw)
In-Reply-To: <302584628c4c0699239a0218376fe1c11cdc8944.1787165329.git.geert+renesas@glider.be>
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
Pre-existing issues:
- [High] Incomplete fix for uninitialized stack variables: `struct clk_parent_data parent_data` remains uninitialized on the stack, leading to a kernel crash during clock registration.
--
--- Patch [4]: [PATCH treewide 4/5] iio: frequency: adf4377: Make sure clk_init_data is fully initialized ---
commit 99e024a77f5bce5921d3c6b46054263aa450610d
Author: Geert Uytterhoeven <geert+renesas@glider.be>
iio: frequency: adf4377: Make sure clk_init_data is fully initialized
This commit initializes the clk_init_data structure in
adf4377_clk_register() to zero. This prevents crashes caused by
uninitialized fields like parent_names when CONFIG_INIT_STACK_ALL_PATTERN
or CONFIG_INIT_STACK_NONE is enabled.
> diff --git a/drivers/iio/frequency/adf4377.c b/drivers/iio/frequency/adf4377.c
> --- a/drivers/iio/frequency/adf4377.c
> +++ b/drivers/iio/frequency/adf4377.c
> @@ -999,7 +999,7 @@ static int adf4377_clk_register(struct adf4377_state *st)
> {
> struct spi_device *spi = st->spi;
> struct device *dev = &spi->dev;
> - struct clk_init_data init;
> + struct clk_init_data init = {};
> struct clk_parent_data parent_data;
[Severity: High]
This is a pre-existing issue, but does this struct clk_parent_data also
need to be zero-initialized?
Only fw_name is explicitly assigned below, leaving name, hw, and index
populated with stack garbage. When adf4377_clk_register() passes this to
the clock framework, clk_core_populate_parent_map() will read
parent_data.name and pass it to clk_cpy_name(), which ultimately calls
strlen() and can cause a page fault during probe.
[ ... ]
> parent_data.fw_name = "ref_in";
>
> init.ops = &adf4377_clk_ops;
> init.parent_data = &parent_data;
--
Sashiko AI review · https://sashiko.dev/#/patchset/cover.1787165329.git.geert+renesas@glider.be?part=4
next prev parent reply other threads:[~2026-08-19 19:13 UTC|newest]
Thread overview: 44+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-08-19 19:05 [PATCH treewide 0/5] clk: Make sure clk_init_data is fully initialized (part 1) Geert Uytterhoeven
2026-08-19 19:05 ` Geert Uytterhoeven
2026-08-19 19:05 ` [PATCH treewide 1/5] clk: ti: Make sure clk_init_data is fully initialized Geert Uytterhoeven
2026-08-19 19:05 ` Geert Uytterhoeven
2026-08-19 19:10 ` sashiko-bot
2026-08-19 19:10 ` sashiko-bot
2026-08-19 21:21 ` Brian Masney
2026-08-19 21:21 ` Brian Masney
2026-08-20 5:02 ` Mathieu Dubois-Briand
2026-08-20 5:02 ` Mathieu Dubois-Briand
2026-08-20 5:56 ` Stephen Boyd
2026-08-20 5:56 ` Stephen Boyd
2026-08-19 19:05 ` [PATCH treewide 2/5] clk: visconti: " Geert Uytterhoeven
2026-08-19 19:05 ` Geert Uytterhoeven
2026-08-19 19:14 ` sashiko-bot
2026-08-19 19:14 ` sashiko-bot
2026-08-19 21:21 ` Brian Masney
2026-08-19 21:21 ` Brian Masney
2026-08-20 2:03 ` nobuhiro.iwamatsu.x90
2026-08-20 2:03 ` nobuhiro.iwamatsu.x90
2026-08-20 5:56 ` Stephen Boyd
2026-08-20 5:56 ` Stephen Boyd
2026-08-19 19:05 ` [PATCH treewide 3/5] hwmon: (ltc4282) " Geert Uytterhoeven
2026-08-19 19:05 ` Geert Uytterhoeven
2026-08-19 19:12 ` sashiko-bot
2026-08-19 19:12 ` sashiko-bot
2026-08-19 20:32 ` Guenter Roeck
2026-08-19 20:32 ` Guenter Roeck
2026-08-19 21:22 ` Brian Masney
2026-08-19 21:22 ` Brian Masney
2026-08-19 19:05 ` [PATCH treewide 4/5] iio: frequency: adf4377: " Geert Uytterhoeven
2026-08-19 19:05 ` Geert Uytterhoeven
2026-08-19 19:13 ` sashiko-bot [this message]
2026-08-19 19:13 ` sashiko-bot
2026-08-19 21:22 ` Brian Masney
2026-08-19 21:22 ` Brian Masney
2026-08-20 1:38 ` Jonathan Cameron
2026-08-20 1:38 ` Jonathan Cameron
2026-08-19 19:05 ` [PATCH treewide 5/5] spi: amlogic-spisg: " Geert Uytterhoeven
2026-08-19 19:05 ` Geert Uytterhoeven
2026-08-19 19:13 ` sashiko-bot
2026-08-19 19:13 ` sashiko-bot
2026-08-19 21:23 ` Brian Masney
2026-08-19 21:23 ` Brian Masney
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20260819191316.8F2F21F000E9@smtp.kernel.org \
--to=sashiko-bot@kernel.org \
--cc=geert+renesas@glider.be \
--cc=linux-amlogic@lists.infradead.org \
--cc=linux-clk@vger.kernel.org \
--cc=linux-hwmon@vger.kernel.org \
--cc=neil.armstrong@linaro.org \
--cc=sashiko-reviews@lists.linux.dev \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.