* Re: [PATCH v2 1/9] dt-bindings: adm1275: ROHM BD12780 hot-swap controller
From: Conor Dooley @ 2026-06-26 15:58 UTC (permalink / raw)
To: Matti Vaittinen
Cc: Matti Vaittinen, Matti Vaittinen, Guenter Roeck, Rob Herring,
Krzysztof Kozlowski, Conor Dooley, Jonathan Corbet, Shuah Khan,
Wensheng Wang, Ashish Yadav, Vasileios Amoiridis, Kim Seer Paller,
ChiShih Tsai, Chris Packham, Robert Coulson, linux-hwmon,
devicetree, linux-kernel, linux-doc
In-Reply-To: <2b7d5bb8cba773d0bba1d6779f0e6daa6a40eed4.1782458224.git.mazziesaccount@gmail.com>
[-- Attachment #1: Type: text/plain, Size: 75 bytes --]
Acked-by: Conor Dooley <conor.dooley@microchip.com>
pw-bot: not-applicable
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 228 bytes --]
^ permalink raw reply
* Re: [PATCH v2 2/2] hwmon: (chipcap2) Add support for label
From: Javier Carrasco @ 2026-06-26 10:14 UTC (permalink / raw)
To: Flaviu Nistor, Guenter Roeck, Javier Carrasco, Rob Herring,
Krzysztof Kozlowski, Conor Dooley, Jonathan Corbet, Shuah Khan
Cc: linux-hwmon, linux-kernel, devicetree, linux-doc
In-Reply-To: <20260625160423.17882-2-flaviu.nistor@gmail.com>
On Thu Jun 25, 2026 at 6:04 PM CEST, Flaviu Nistor wrote:
> Add support for label sysfs attribute similar to other hwmon devices.
> This is particularly useful for systems with multiple sensors on the
> same board, where identifying individual sensors is much easier since
> labels can be defined via device tree.
>
> Signed-off-by: Flaviu Nistor <flaviu.nistor@gmail.com>
> ---
> Changes in v2:
> - No change for this patch in the patch series.
> - Link to v1: https://lore.kernel.org/all/20260622122200.14245-1-flaviu.nistor@gmail.com/
>
> Documentation/hwmon/chipcap2.rst | 2 ++
> drivers/hwmon/chipcap2.c | 25 +++++++++++++++++++++++--
> 2 files changed, 25 insertions(+), 2 deletions(-)
>
> diff --git a/Documentation/hwmon/chipcap2.rst b/Documentation/hwmon/chipcap2.rst
> index dc165becc64c..c38d87b91b69 100644
> --- a/Documentation/hwmon/chipcap2.rst
> +++ b/Documentation/hwmon/chipcap2.rst
> @@ -70,4 +70,6 @@ humidity1_min_hyst: RW humidity low hystersis
> humidity1_max_hyst: RW humidity high hystersis
> humidity1_min_alarm: RO humidity low alarm indicator
> humidity1_max_alarm: RO humidity high alarm indicator
> +humidity1_label: RO descriptive name for the sensor
> +temp1_label: RO descriptive name for the sensor
> =============================== ======= ========================================
> diff --git a/drivers/hwmon/chipcap2.c b/drivers/hwmon/chipcap2.c
> index 4aecf463180f..086571d556b7 100644
> --- a/drivers/hwmon/chipcap2.c
> +++ b/drivers/hwmon/chipcap2.c
> @@ -22,6 +22,8 @@
> #include <linux/irq.h>
> #include <linux/module.h>
> #include <linux/regulator/consumer.h>
> +#include <linux/mod_devicetable.h>
> +#include <linux/property.h>
>
> #define CC2_START_CM 0xA0
> #define CC2_START_NOM 0x80
> @@ -83,6 +85,7 @@ struct cc2_data {
> struct i2c_client *client;
> struct regulator *regulator;
> const char *name;
> + const char *label;
> int irq_ready;
> int irq_low;
> int irq_high;
> @@ -449,6 +452,8 @@ static umode_t cc2_is_visible(const void *data, enum hwmon_sensor_types type,
> switch (attr) {
> case hwmon_humidity_input:
> return 0444;
> + case hwmon_humidity_label:
> + return cc2->label ? 0444 : 0;
> case hwmon_humidity_min_alarm:
> return cc2->rh_alarm.low_alarm_visible ? 0444 : 0;
> case hwmon_humidity_max_alarm:
> @@ -466,6 +471,8 @@ static umode_t cc2_is_visible(const void *data, enum hwmon_sensor_types type,
> switch (attr) {
> case hwmon_temp_input:
> return 0444;
> + case hwmon_temp_label:
> + return cc2->label ? 0444 : 0;
> default:
> return 0;
> }
> @@ -552,6 +559,16 @@ static int cc2_humidity_max_alarm_status(struct cc2_data *data, long *val)
> return 0;
> }
>
> +static int cc2_read_string(struct device *dev, enum hwmon_sensor_types type,
> + u32 attr, int channel, const char **str)
> +{
> + struct cc2_data *data = dev_get_drvdata(dev);
> +
> + *str = data->label;
> +
> + return 0;
> +}
> +
> static int cc2_read(struct device *dev, enum hwmon_sensor_types type, u32 attr,
> int channel, long *val)
> {
> @@ -670,8 +687,9 @@ static int cc2_request_alarm_irqs(struct cc2_data *data, struct device *dev)
> }
>
> static const struct hwmon_channel_info *cc2_info[] = {
> - HWMON_CHANNEL_INFO(temp, HWMON_T_INPUT),
> - HWMON_CHANNEL_INFO(humidity, HWMON_H_INPUT | HWMON_H_MIN | HWMON_H_MAX |
> + HWMON_CHANNEL_INFO(temp, HWMON_T_INPUT | HWMON_T_LABEL),
> + HWMON_CHANNEL_INFO(humidity, HWMON_H_INPUT | HWMON_H_LABEL |
> + HWMON_H_MIN | HWMON_H_MAX |
> HWMON_H_MIN_HYST | HWMON_H_MAX_HYST |
> HWMON_H_MIN_ALARM | HWMON_H_MAX_ALARM),
> NULL
> @@ -680,6 +698,7 @@ static const struct hwmon_channel_info *cc2_info[] = {
> static const struct hwmon_ops cc2_hwmon_ops = {
> .is_visible = cc2_is_visible,
> .read = cc2_read,
> + .read_string = cc2_read_string,
> .write = cc2_write,
> };
>
> @@ -710,6 +729,8 @@ static int cc2_probe(struct i2c_client *client)
> return dev_err_probe(dev, PTR_ERR(data->regulator),
> "Failed to get regulator\n");
>
> + device_property_read_string(dev, "label", &data->label);
> +
> ret = cc2_request_ready_irq(data, dev);
> if (ret)
> return dev_err_probe(dev, ret, "Failed to request ready irq\n");
Reviewed-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
^ permalink raw reply
* Re: [PATCH v2 1/2] dt-bindings: hwmon: chipcap2: Add label property
From: Krzysztof Kozlowski @ 2026-06-26 10:05 UTC (permalink / raw)
To: Flaviu Nistor
Cc: Guenter Roeck, Javier Carrasco, Rob Herring, Krzysztof Kozlowski,
Conor Dooley, Jonathan Corbet, Shuah Khan, linux-hwmon,
linux-kernel, devicetree, linux-doc
In-Reply-To: <20260625160423.17882-1-flaviu.nistor@gmail.com>
On Thu, Jun 25, 2026 at 07:04:22PM +0300, Flaviu Nistor wrote:
> Add support for an optional label property similar to other hwmon devices.
> This allows, in case of boards with multiple CHIPCAP2 sensors, to assign
> distinct names to each instance.
>
> Signed-off-by: Flaviu Nistor <flaviu.nistor@gmail.com>
> ---
> Changes in v2:
> - Implement suggestion from Javier Carrasco as proposed by Krzysztof Kozlowski.
> - Link to v1: https://lore.kernel.org/all/20260622122200.14245-1-flaviu.nistor@gmail.com/
>
> .../devicetree/bindings/hwmon/amphenol,chipcap2.yaml | 6 ++++++
> 1 file changed, 6 insertions(+)
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Best regards,
Krzysztof
^ permalink raw reply
* [ANNOUNCEMENT] LPC 2026: System Monitoring and Observability Microconference
From: Breno Leitao @ 2026-06-26 9:56 UTC (permalink / raw)
To: linux-acpi, linux-hwmon, netdev, linux-kernel, linux-arm-kernel,
kernel-team, linux-mm
Cc: Breno Leitao, kerneljasonxing, iipeace5, gavinguo, linux,
amscanne, sj, gpiccoli, Daniel Gomez, mfo, platform-driver-x86,
acpica-devel
We are pleased to announce the Call for Proposals (CFP) for another
edition of System Monitoring and Observability Microconference, this
time at the 2026 Linux Plumbers Conference (LPC), taking place in
Prague, Czechia, from Oct 5-7, 2026.
https://lpc.events/event/20/sessions/262/
This microconference provides a valuable forum for key engineering areas
such as:
- Kernel Health and Runtime Monitoring
- Hardware Integration and Error Detection
- Correlation of Issues (crashes, stalls, bugs)
- Virtualization Stack Monitoring
- Memory Management Monitoring and Observability
- Anomaly Detection Algorithms for System Behavior
- Automated Analysis, Remediation and post mortem analyzes
The purpose of each talk is to share challenges and discuss potential
improvements. Sessions will last 20 to 30 minutes and aim to encourage
brainstorming and open dialogue about ongoing issues rather than
delivering immediate solutions.
The conference acts as both a knowledge-sharing platform and a strategic
venue for guiding the future of kernel technologies to better meet the
demands of large-scale infrastructure.
We invite you to submit your proposals here:
https://lpc.events/event/20/abstracts/
Please select track "Linux System Monitoring and Observability MC"
^ permalink raw reply
* Re: [PATCH v2 9/9] hwmon: adm1275: Support ROHM BD12790
From: Matti Vaittinen @ 2026-06-26 7:49 UTC (permalink / raw)
To: sashiko-reviews; +Cc: linux-hwmon, robh, conor+dt, devicetree
In-Reply-To: <20260626073347.A06981F000E9@smtp.kernel.org>
On 26/06/2026 10:33, sashiko-bot@kernel.org wrote:
> If we evaluate m = round(k / 10^(-3-R)) for a value of R=-2 and k=35119.94,
> it yields 351199.4. However, the actual code below correctly implements the
> value as 3512, which implies the formula should use multiplication rather
> than division.
Gah. I think Sashiko is right. The fixed comment should say:
m = round(k * 10^(-3-R))
-- Matti
--
Matti Vaittinen
Linux kernel developer at ROHM Semiconductors
Oulu Finland
~~ When things go utterly wrong vim users can always type :help! ~~
^ permalink raw reply
* Re: [PATCH v2 5/9] doc: Add ROHM BD12780 and BD12780A
From: sashiko-bot @ 2026-06-26 7:36 UTC (permalink / raw)
To: Matti Vaittinen; +Cc: conor+dt, linux-hwmon, devicetree, robh
In-Reply-To: <5ff4a4a7a939cd642522fde407b5c9fa123a7089.1782458224.git.mazziesaccount@gmail.com>
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Low] Incorrect hwmon sysfs prefix documented for the BD12780A device.
--
commit f0582b872b8ac6d6f116162797af818e8508125f
Author: Matti Vaittinen <mazziesaccount@gmail.com>
doc: Add ROHM BD12780 and BD12780A
This commit updates the adm1275 hardware monitoring driver documentation to
include support for the ROHM Semiconductor BD12780 and BD12780A power switch
ICs.
> diff --git a/Documentation/hwmon/adm1275.rst b/Documentation/hwmon/adm1275.rst
> index cf923f20fa523..8a793dd2b412b 100644
> --- a/Documentation/hwmon/adm1275.rst
> +++ b/Documentation/hwmon/adm1275.rst
[ ... ]
> @@ -67,6 +67,22 @@ Supported chips:
>
> Datasheet: https://www.analog.com/media/en/technical-documentation/data-sheets/ADM1293_1294.pdf
>
> + * ROHM Semiconductor BD12780
> +
> + Prefix: 'bd12780'
> +
> + Addresses scanned: -
> +
> + Datasheet: https://fscdn.rohm.com/en/products/databook/datasheet/ic/power/power_switch/bd12780muv-lb-e.pdf
> +
> + * ROHM Semiconductor BD12780A
> +
> + Prefix: 'bd12780'
^^^^^^^^^
[Severity: Low]
Is this prefix accurate for the BD12780A?
When the device is instantiated via Device Tree using the compatible string
"rohm,bd12780a", the I2C core's of_i2c_get_board_info() function extracts
this string, strips the vendor prefix, and sets client->name to "bd12780a".
The pmbus_do_probe() function then uses client->name to register the hwmon
device, which results in the prefix being "bd12780a" instead of the
documented "bd12780".
Could this cause issues for userspace tools relying on the documentation to
find the device?
> +
> + Addresses scanned: -
> +
> + Datasheet: https://fscdn.rohm.com/en/products/databook/datasheet/ic/power/power_switch/bd12780amuv-lb-e.pdf
> +
--
Sashiko AI review · https://sashiko.dev/#/patchset/cover.1782458224.git.mazziesaccount@gmail.com?part=5
^ permalink raw reply
* Re: [PATCH v2 7/9] dt-bindings: adm1275: ROHM BD12790 hot-swap controller
From: sashiko-bot @ 2026-06-26 7:35 UTC (permalink / raw)
To: Matti Vaittinen; +Cc: conor+dt, linux-hwmon, devicetree, robh
In-Reply-To: <753a6ded3e1aff1aaba7d932f0a883f789d9dfaa.1782458224.git.mazziesaccount@gmail.com>
> From: Matti Vaittinen <mazziesaccount@gmail.com>
>
> Support ROHM BD12790 hot-swap controller which is largely compatible
> with the Analog Devices adm1272.
>
> Signed-off-by: Matti Vaittinen <mazziesaccount@gmail.com>
Sashiko has reviewed this patch and found no issues. It looks great!
--
Sashiko AI review · https://sashiko.dev/#/patchset/cover.1782458224.git.mazziesaccount@gmail.com?part=7
^ permalink raw reply
* Re: [PATCH v2 3/9] hwmon: adm1275: Detect coefficient overflow
From: sashiko-bot @ 2026-06-26 7:35 UTC (permalink / raw)
To: Matti Vaittinen; +Cc: linux-hwmon, conor+dt, robh, devicetree
In-Reply-To: <d9e3320dbd62e094ff89598cb3aac5b5e716f9e7.1782458224.git.mazziesaccount@gmail.com>
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [High] The patch introduces spurious probe failures by restricting the intermediate `shunt * m` multiplication to a 32-bit limit instead of using a 64-bit calculation, needlessly rejecting perfectly valid shunt resistor configurations.
--
commit 02af229d429dc5c77e875edeb815b9caba7e6da2
Author: Matti Vaittinen <mazziesaccount@gmail.com>
hwmon: adm1275: Detect coefficient overflow
This commit detects potential coefficient overflow when a large shunt
resistor is used and aborts the probe if an overflow is detected.
> diff --git a/drivers/hwmon/pmbus/adm1275.c b/drivers/hwmon/pmbus/adm1275.c
> index 43baa5ded35e5..ccc3ad21e38e7 100644
> --- a/drivers/hwmon/pmbus/adm1275.c
> +++ b/drivers/hwmon/pmbus/adm1275.c
> @@ -839,15 +839,25 @@ static int adm1275_probe(struct i2c_client *client)
> info->R[PSC_VOLTAGE_OUT] = coefficients[voindex].R;
> }
> if (cindex >= 0) {
> + u32 m;
> +
> /* Scale current with sense resistor value */
> - info->m[PSC_CURRENT_OUT] =
> - coefficients[cindex].m * shunt / 1000;
> + if (unlikely(check_mul_overflow(coefficients[cindex].m, shunt, &m))) {
[Severity: High]
Does this code introduce a spurious probe failure for valid setups?
By checking for overflow on the intermediate product using a 32-bit
unsigned integer, the probe will fail for configurations where the
product exceeds U32_MAX, but the final scaled value after dividing by
1000 would safely fit into the 32-bit signed integer target field.
Could we use a 64-bit intermediate calculation instead, such as
div_s64((s64)coefficients[cindex].m * shunt, 1000), to prevent this
regression and avoid needlessly rejecting valid shunt resistor setups?
> + dev_err(&client->dev, "Current coefficient overflow\n");
> + return -EOVERFLOW;
> + }
> + info->m[PSC_CURRENT_OUT] = m / 1000;
> info->b[PSC_CURRENT_OUT] = coefficients[cindex].b;
> info->R[PSC_CURRENT_OUT] = coefficients[cindex].R;
> }
> if (pindex >= 0) {
> - info->m[PSC_POWER] =
> - coefficients[pindex].m * shunt / 1000;
> + u32 m;
> +
> + if (unlikely(check_mul_overflow(coefficients[pindex].m, shunt, &m))) {
[Severity: High]
Can this similarly cause the probe to abort prematurely?
For example, configuring an ADM1293 on the 100mV range with a 250000 uOhm
shunt resistor yields a power coefficient product of 26042 * 250000, which
is 6,510,500,000. This mathematically overflows the 32-bit check here, but
the final value of 6,510,500 easily fits in the target field.
Would it be better to calculate this using 64-bit math so the device can
successfully initialize all of its sensors?
> + dev_err(&client->dev, "Power coefficient overflow\n");
> + return -EOVERFLOW;
> + }
> + info->m[PSC_POWER] = m / 1000;
--
Sashiko AI review · https://sashiko.dev/#/patchset/cover.1782458224.git.mazziesaccount@gmail.com?part=3
^ permalink raw reply
* Re: [PATCH v2 9/9] hwmon: adm1275: Support ROHM BD12790
From: sashiko-bot @ 2026-06-26 7:33 UTC (permalink / raw)
To: Matti Vaittinen; +Cc: linux-hwmon, robh, conor+dt, devicetree
In-Reply-To: <b209c1b47712b69f17b52cfd7a7a38ed76024ca7.1782458224.git.mazziesaccount@gmail.com>
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Low] The mathematical formula documented in the comment for computing the power coefficient contradicts the actual mathematically correct implementation in the code.
--
commit 7dff114234776369f1046124af65696c292fcd41
Author: Matti Vaittinen <mazziesaccount@gmail.com>
hwmon: adm1275: Support ROHM BD12790
This commit adds support for the ROHM BD12790 hot-swap controller to the
adm1275 driver. It introduces a dedicated coefficient table for the new
device based on its voltage and current-sense ranges.
> diff --git a/drivers/hwmon/pmbus/adm1275.c b/drivers/hwmon/pmbus/adm1275.c
> index 81c50fab7687b..406b448523769 100644
> --- a/drivers/hwmon/pmbus/adm1275.c
> +++ b/drivers/hwmon/pmbus/adm1275.c
[ ... ]
> @@ -136,6 +136,30 @@ static const struct coefficients adm1272_coefficients[] = {
>
> };
>
> +/*
> + * BD12790 coefficients derived from preliminary datasheet, Table 1 (p.18)
> + * and the PMBus direct-format relationship X = (Y * 10^(-R) - b) / m.
> + *
> + * Voltage: V[V] = 14.77e-3 * code (60V) / 24.62e-3 * code (100V)
> + * -> m = 6770, R=-2 / m = 4062, R=-2
> + * Current: code = I[A] * RS * 132802.1 + 2048 (15mV) / * 66401.06 + 2048 (30mV)
> + * -> m = 1328, b = 2048 * 10^(-R) = 20480, R=-1 / m = 664, same b and R
> + * Power: code = k * RS * PIN, k = 35119.94 / 17559.97 / 21071.44 / 10535.72
> + * -> m = round(k / 10^(-3-R)), R=-2 for 60V/15mV, R=-3 for the other three
[Severity: Low]
This isn't a bug, but does the formula in this comment correctly document
how the power coefficients are calculated?
If we evaluate m = round(k / 10^(-3-R)) for a value of R=-2 and k=35119.94,
it yields 351199.4. However, the actual code below correctly implements the
value as 3512, which implies the formula should use multiplication rather
than division.
> + * Temperature: code = 4.2 * T + 3188 -> m = 42, b = 3188 * 10 = 31880, R=-1
> + */
> +static const struct coefficients bd12790_coefficients[] = {
> + [0] = { 6770, 0, -2 }, /* voltage, vrange 60V */
> + [1] = { 4062, 0, -2 }, /* voltage, vrange 100V */
> + [2] = { 1328, 20480, -1 }, /* current, vsense range 15mV */
> + [3] = { 664, 20480, -1 }, /* current, vsense range 30mV */
> + [4] = { 3512, 0, -2 }, /* power, vrange 60V, irange 15mV */
> + [5] = { 21071, 0, -3 }, /* power, vrange 100V, irange 15mV */
> + [6] = { 17560, 0, -3 }, /* power, vrange 60V, irange 30mV */
> + [7] = { 10536, 0, -3 }, /* power, vrange 100V, irange 30mV */
> + [8] = { 42, 31880, -1 }, /* temperature */
> +};
> +
--
Sashiko AI review · https://sashiko.dev/#/patchset/cover.1782458224.git.mazziesaccount@gmail.com?part=9
^ permalink raw reply
* Re: [PATCH v2 2/9] hwmon: adm1275: Prevent reading uninitialized stack
From: sashiko-bot @ 2026-06-26 7:32 UTC (permalink / raw)
To: Matti Vaittinen; +Cc: linux-hwmon, robh, devicetree, conor+dt
In-Reply-To: <c8ad38e0cdb347261c6245de2b7965e747f28d22.1782458224.git.mazziesaccount@gmail.com>
> From: Matti Vaittinen <mazziesaccount@gmail.com>
>
> While adding support for the ROHM BD127X0 hot-swap controllers, sashiko
> reported an error in device-name comparison, which can lead to reading
> uninitialized stack memory.
>
> Quoting Sashiko:
>
> This is a pre-existing issue, but I noticed that just before this block in
> adm1275_probe(), there might be an out-of-bounds stack read:
>
> ret = i2c_smbus_read_block_data(client, PMBUS_MFR_MODEL, block_buffer);
> if (ret < 0) { ... }
> for (mid = adm1275_id; mid->name[0]; mid++) {
> if (!strncasecmp(mid->name, block_buffer, strlen(mid->name)))
> break;
> }
>
> Since i2c_smbus_read_block_data() reads up to 32 bytes into the
> uninitialized stack array block_buffer without appending a null
> terminator, strncasecmp() could read past the valid bytes returned in ret.
>
> For example, if the device returns a shorter string like "adm12", checking
> it against "adm1275" up to the length of "adm1275" will continue reading
> into uninitialized stack bounds.
>
> Prevent reading uninitialized memory by zeroing the stack array.
>
> Signed-off-by: Matti Vaittinen <mazziesaccount@gmail.com>
Sashiko has reviewed this patch and found no issues. It looks great!
--
Sashiko AI review · https://sashiko.dev/#/patchset/cover.1782458224.git.mazziesaccount@gmail.com?part=2
^ permalink raw reply
* Re: [PATCH v2 8/9] doc: adm1275: Add ROHM BD12790
From: sashiko-bot @ 2026-06-26 7:32 UTC (permalink / raw)
To: Matti Vaittinen; +Cc: devicetree, conor+dt, robh, linux-hwmon
In-Reply-To: <9bafcfe37190b5a3925e8dcfa3b59f8d240234ba.1782458224.git.mazziesaccount@gmail.com>
> From: Matti Vaittinen <mazziesaccount@gmail.com>
>
> Add the ROHM BD12790 to the list of the ICs supported by the adm1275
> driver.
>
> Signed-off-by: Matti Vaittinen <mazziesaccount@gmail.com>
Sashiko has reviewed this patch and found no issues. It looks great!
--
Sashiko AI review · https://sashiko.dev/#/patchset/cover.1782458224.git.mazziesaccount@gmail.com?part=8
^ permalink raw reply
* Re: [PATCH v2 6/9] hwmon: adm1275: Support ROHM BD12780
From: sashiko-bot @ 2026-06-26 7:32 UTC (permalink / raw)
To: Matti Vaittinen; +Cc: linux-hwmon, devicetree, conor+dt, robh
In-Reply-To: <e1e6e6218c08b562311356ef9c57378d32c26b08.1782458224.git.mazziesaccount@gmail.com>
> From: Matti Vaittinen <mazziesaccount@gmail.com>
>
> ROHM BD12780 and BD12780A are hot-swap controllers. They are largely
> similar to Analog Devices ADM1278. Besides the ID registers and some
> added functionality, the BD12780 and BD12780A mark PMON_CONFIG bits
> [15:14] as reserved. Hence TSFILT setting must be omitted on these ICs.
>
> The BD12780 has 3 pins usable for configuring the I2C address. The
> BD12780A lists the ADDR3-pin as "not connect".
>
> Support ROHM BD12780 and BD12780A controllers.
>
> Signed-off-by: Matti Vaittinen <mazziesaccount@gmail.com>
Sashiko has reviewed this patch and found no issues. It looks great!
--
Sashiko AI review · https://sashiko.dev/#/patchset/cover.1782458224.git.mazziesaccount@gmail.com?part=6
^ permalink raw reply
* Re: [PATCH v2 4/9] hwmon: adm1275: Support module auto-loading
From: sashiko-bot @ 2026-06-26 7:31 UTC (permalink / raw)
To: Matti Vaittinen; +Cc: devicetree, linux-hwmon, conor+dt, robh
In-Reply-To: <9eca6831f9fe2d781bb88337397c39b10e36f5c6.1782458224.git.mazziesaccount@gmail.com>
> From: Matti Vaittinen <mazziesaccount@gmail.com>
>
> Populating the i2c_device_id -table is not enough to make the
> driver module automatically load when device-tree node for the
> power-monitor is parsed at boot.
>
> Adding the of_device_id tables causes the driver module to be
> automatically load at boot. Testing has been done with rather old Debian
> system.
>
> When inspecting the generated module-aliases with the insmod, following
> entries seem to be the difference:
>
> alias: of:N*T*Cadi,adm1075C*
> alias: of:N*T*Cadi,adm1075
>
> I suspect these are required for the module loading to work.
>
> Signed-off-by: Matti Vaittinen <mazziesaccount@gmail.com>
Sashiko has reviewed this patch and found no issues. It looks great!
--
Sashiko AI review · https://sashiko.dev/#/patchset/cover.1782458224.git.mazziesaccount@gmail.com?part=4
^ permalink raw reply
* Re: [PATCH v2 1/9] dt-bindings: adm1275: ROHM BD12780 hot-swap controller
From: sashiko-bot @ 2026-06-26 7:31 UTC (permalink / raw)
To: Matti Vaittinen; +Cc: devicetree, robh, conor+dt, linux-hwmon
In-Reply-To: <2b7d5bb8cba773d0bba1d6779f0e6daa6a40eed4.1782458224.git.mazziesaccount@gmail.com>
> From: Matti Vaittinen <mazziesaccount@gmail.com>
>
> Support ROHM BD12780 and BD12780A hot-swap controllers, which are largely
> compatible with the Analog Devices adm1278. Main difference between
> the BD12780 and the BD12780A is, that the BD12780 has one I2C address
> configuration pin more (ADDR3) than the BD12780A.
>
> Introduce own compatibles for both variants but require the BD12780A to
> always have the BD12780 as a fall-back.
>
> Signed-off-by: Matti Vaittinen <mazziesaccount@gmail.com>
Sashiko has reviewed this patch and found no issues. It looks great!
--
Sashiko AI review · https://sashiko.dev/#/patchset/cover.1782458224.git.mazziesaccount@gmail.com?part=1
^ permalink raw reply
* [PATCH v2 9/9] hwmon: adm1275: Support ROHM BD12790
From: Matti Vaittinen @ 2026-06-26 7:26 UTC (permalink / raw)
To: Matti Vaittinen, Matti Vaittinen, Matti Vaittinen
Cc: Guenter Roeck, Rob Herring, Krzysztof Kozlowski, Conor Dooley,
Jonathan Corbet, Shuah Khan, Wensheng Wang, Matti Vaittinen,
Ashish Yadav, Vasileios Amoiridis, Kim Seer Paller, ChiShih Tsai,
Chris Packham, Robert Coulson, linux-hwmon, devicetree,
linux-kernel, linux-doc
In-Reply-To: <cover.1782458224.git.mazziesaccount@gmail.com>
[-- Attachment #1: Type: text/plain, Size: 7213 bytes --]
From: Matti Vaittinen <mazziesaccount@gmail.com>
Add support for ROHM BD12790 hot-swap controller which is largely
similar to Analog Devices adm1272.
The BD12790 uses the same selectable 60V/100V voltage ranges and
15mV/30mV current-sense ranges as the ADM1272, and the same VRANGE
(bit 5) and IRANGE (bit 0) layout in PMON_CONFIG. It therefore uses
a dedicated coefficient table that mirrors adm1272_coefficients, with
the following differences derived from BD12790 datasheet Table 1 (p.18):
- power 60V/30mV: m=17560 (vs. 17561)
- power 100V/30mV: m=10536 (vs. 10535)
- temperature: b=31880 (vs. 31871, reflecting T[11:0] = 4.2*T + 3188)
Signed-off-by: Matti Vaittinen <mazziesaccount@gmail.com>
Assisted-by: GitHub Copilot:claude-sonnet-4.6
---
Revision history:
v1 => v2: Changes mostly based on the review by Guenter:
- Add own 'case' for the bd12790.
- Don't use wildcard in the macro name.
- Fix the coefficient computation comment for power to take the
shunt-resistor scale into account.
---
drivers/hwmon/pmbus/Kconfig | 4 +-
drivers/hwmon/pmbus/adm1275.c | 79 +++++++++++++++++++++++++++++++++--
2 files changed, 78 insertions(+), 5 deletions(-)
diff --git a/drivers/hwmon/pmbus/Kconfig b/drivers/hwmon/pmbus/Kconfig
index b3c27f3b2712..6ebc01e26db3 100644
--- a/drivers/hwmon/pmbus/Kconfig
+++ b/drivers/hwmon/pmbus/Kconfig
@@ -52,8 +52,8 @@ config SENSORS_ADM1275
help
If you say yes here you get hardware monitoring support for Analog
Devices ADM1075, ADM1272, ADM1273, ADM1275, ADM1276, ADM1278, ADM1281,
- ADM1293, ADM1294, ROHM BD12780, and SQ24905C Hot-Swap Controller and
- Digital Power Monitors.
+ ADM1293, ADM1294, ROHM BD12780, ROHM BD12790, and SQ24905C
+ Hot-Swap Controller and Digital Power Monitors.
This driver can also be built as a module. If so, the module will
be called adm1275.
diff --git a/drivers/hwmon/pmbus/adm1275.c b/drivers/hwmon/pmbus/adm1275.c
index 81c50fab7687..406b44852376 100644
--- a/drivers/hwmon/pmbus/adm1275.c
+++ b/drivers/hwmon/pmbus/adm1275.c
@@ -19,7 +19,7 @@
#include "pmbus.h"
enum chips { adm1075, adm1272, adm1273, adm1275, adm1276, adm1278, adm1281,
- adm1293, adm1294, bd12780, sq24905c };
+ adm1293, adm1294, bd12780, bd12790, sq24905c };
#define ADM1275_MFR_STATUS_IOUT_WARN2 BIT(0)
#define ADM1293_MFR_STATUS_VAUX_UV_WARN BIT(5)
@@ -47,7 +47,7 @@ enum chips { adm1075, adm1272, adm1273, adm1275, adm1276, adm1278, adm1281,
#define ADM1278_VOUT_EN BIT(1)
#define ADM1278_PMON_DEFCONFIG (ADM1278_VOUT_EN | ADM1278_TEMP1_EN | ADM1278_TSFILT)
-/* The BD12780 data sheets mark TSFILT bit as reserved. */
+/* The BD127[89]0 data sheets mark TSFILT bit as reserved. */
#define BD12780_PMON_DEFCONFIG (ADM1278_VOUT_EN | ADM1278_TEMP1_EN)
#define ADM1293_IRANGE_25 0
@@ -136,6 +136,30 @@ static const struct coefficients adm1272_coefficients[] = {
};
+/*
+ * BD12790 coefficients derived from preliminary datasheet, Table 1 (p.18)
+ * and the PMBus direct-format relationship X = (Y * 10^(-R) - b) / m.
+ *
+ * Voltage: V[V] = 14.77e-3 * code (60V) / 24.62e-3 * code (100V)
+ * -> m = 6770, R=-2 / m = 4062, R=-2
+ * Current: code = I[A] * RS * 132802.1 + 2048 (15mV) / * 66401.06 + 2048 (30mV)
+ * -> m = 1328, b = 2048 * 10^(-R) = 20480, R=-1 / m = 664, same b and R
+ * Power: code = k * RS * PIN, k = 35119.94 / 17559.97 / 21071.44 / 10535.72
+ * -> m = round(k / 10^(-3-R)), R=-2 for 60V/15mV, R=-3 for the other three
+ * Temperature: code = 4.2 * T + 3188 -> m = 42, b = 3188 * 10 = 31880, R=-1
+ */
+static const struct coefficients bd12790_coefficients[] = {
+ [0] = { 6770, 0, -2 }, /* voltage, vrange 60V */
+ [1] = { 4062, 0, -2 }, /* voltage, vrange 100V */
+ [2] = { 1328, 20480, -1 }, /* current, vsense range 15mV */
+ [3] = { 664, 20480, -1 }, /* current, vsense range 30mV */
+ [4] = { 3512, 0, -2 }, /* power, vrange 60V, irange 15mV */
+ [5] = { 21071, 0, -3 }, /* power, vrange 100V, irange 15mV */
+ [6] = { 17560, 0, -3 }, /* power, vrange 60V, irange 30mV */
+ [7] = { 10536, 0, -3 }, /* power, vrange 100V, irange 30mV */
+ [8] = { 42, 31880, -1 }, /* temperature */
+};
+
static const struct coefficients adm1275_coefficients[] = {
[0] = { 19199, 0, -2 }, /* voltage, vrange set */
[1] = { 6720, 0, -1 }, /* voltage, vrange not set */
@@ -490,6 +514,7 @@ static const struct i2c_device_id adm1275_id[] = {
{ "adm1293", adm1293 },
{ "adm1294", adm1294 },
{ "bd12780", bd12780 },
+ { "bd12790", bd12790 },
{ "mc09c", sq24905c },
{ }
};
@@ -567,7 +592,8 @@ static int adm1275_probe(struct i2c_client *client)
if (mid->driver_data == adm1272 || mid->driver_data == adm1273 ||
mid->driver_data == adm1278 || mid->driver_data == adm1281 ||
mid->driver_data == adm1293 || mid->driver_data == adm1294 ||
- mid->driver_data == bd12780 || mid->driver_data == sq24905c)
+ mid->driver_data == bd12780 || mid->driver_data == bd12790 ||
+ mid->driver_data == sq24905c)
config_read_fn = i2c_smbus_read_word_data;
else
config_read_fn = i2c_smbus_read_byte_data;
@@ -647,6 +673,7 @@ static int adm1275_probe(struct i2c_client *client)
data->have_power_sampling = true;
coefficients = adm1272_coefficients;
+
vindex = (config & ADM1275_VRANGE) ? 1 : 0;
cindex = (config & ADM1272_IRANGE) ? 3 : 2;
/* pindex depends on the combination of the above */
@@ -679,6 +706,51 @@ static int adm1275_probe(struct i2c_client *client)
if (config & ADM1278_VIN_EN)
info->func[0] |= PMBUS_HAVE_VIN;
break;
+
+ /*
+ * The BD12790 is almost identical to the adm1272. Only the defconfig
+ * and coefficients have minor differences.
+ */
+ case bd12790:
+ data->have_vout = true;
+ data->have_pin_max = true;
+ data->have_temp_max = true;
+ data->have_power_sampling = true;
+
+ coefficients = bd12790_coefficients;
+
+ vindex = (config & ADM1275_VRANGE) ? 1 : 0;
+ cindex = (config & ADM1272_IRANGE) ? 3 : 2;
+ /* pindex depends on the combination of the above */
+ switch (config & (ADM1275_VRANGE | ADM1272_IRANGE)) {
+ case 0:
+ default:
+ pindex = 4;
+ break;
+ case ADM1275_VRANGE:
+ pindex = 5;
+ break;
+ case ADM1272_IRANGE:
+ pindex = 6;
+ break;
+ case ADM1275_VRANGE | ADM1272_IRANGE:
+ pindex = 7;
+ break;
+ }
+ tindex = 8;
+
+ info->func[0] |= PMBUS_HAVE_PIN | PMBUS_HAVE_STATUS_INPUT |
+ PMBUS_HAVE_VOUT | PMBUS_HAVE_STATUS_VOUT |
+ PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP;
+
+ ret = adm1275_enable_vout_temp(data, client, config,
+ BD12780_PMON_DEFCONFIG);
+ if (ret)
+ return ret;
+
+ if (config & ADM1278_VIN_EN)
+ info->func[0] |= PMBUS_HAVE_VIN;
+ break;
case adm1275:
if (device_config & ADM1275_IOUT_WARN2_SELECT)
data->have_oc_fault = true;
@@ -919,6 +991,7 @@ static const struct of_device_id adm1275_of_match[] = {
{ .compatible = "adi,adm1293", },
{ .compatible = "adi,adm1294", },
{ .compatible = "rohm,bd12780", },
+ { .compatible = "rohm,bd12790", },
{ .compatible = "silergy,mc09c", },
{ }
};
--
2.54.0
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]
^ permalink raw reply related
* [PATCH v2 8/9] doc: adm1275: Add ROHM BD12790
From: Matti Vaittinen @ 2026-06-26 7:25 UTC (permalink / raw)
To: Matti Vaittinen, Matti Vaittinen, Matti Vaittinen
Cc: Guenter Roeck, Rob Herring, Krzysztof Kozlowski, Conor Dooley,
Jonathan Corbet, Shuah Khan, Wensheng Wang, Matti Vaittinen,
Ashish Yadav, Vasileios Amoiridis, Kim Seer Paller, ChiShih Tsai,
Chris Packham, Robert Coulson, linux-hwmon, devicetree,
linux-kernel, linux-doc
In-Reply-To: <cover.1782458224.git.mazziesaccount@gmail.com>
[-- Attachment #1: Type: text/plain, Size: 864 bytes --]
From: Matti Vaittinen <mazziesaccount@gmail.com>
Add the ROHM BD12790 to the list of the ICs supported by the adm1275
driver.
Signed-off-by: Matti Vaittinen <mazziesaccount@gmail.com>
---
Revision history:
v1 => :
- No changes
---
Documentation/hwmon/adm1275.rst | 8 ++++++++
1 file changed, 8 insertions(+)
diff --git a/Documentation/hwmon/adm1275.rst b/Documentation/hwmon/adm1275.rst
index 8a793dd2b412..d8495be313b8 100644
--- a/Documentation/hwmon/adm1275.rst
+++ b/Documentation/hwmon/adm1275.rst
@@ -83,6 +83,14 @@ Supported chips:
Datasheet: https://fscdn.rohm.com/en/products/databook/datasheet/ic/power/power_switch/bd12780amuv-lb-e.pdf
+ * ROHM Semiconductor BD12790
+
+ Prefix: 'bd12790'
+
+ Addresses scanned: -
+
+ Datasheet: -
+
* Silergy SQ24905C
Prefix: 'mc09c'
--
2.54.0
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]
^ permalink raw reply related
* [PATCH v2 7/9] dt-bindings: adm1275: ROHM BD12790 hot-swap controller
From: Matti Vaittinen @ 2026-06-26 7:25 UTC (permalink / raw)
To: Matti Vaittinen, Matti Vaittinen, Matti Vaittinen
Cc: Guenter Roeck, Rob Herring, Krzysztof Kozlowski, Conor Dooley,
Jonathan Corbet, Shuah Khan, Wensheng Wang, Matti Vaittinen,
Ashish Yadav, Vasileios Amoiridis, Kim Seer Paller, ChiShih Tsai,
Chris Packham, Robert Coulson, linux-hwmon, devicetree,
linux-kernel, linux-doc
In-Reply-To: <cover.1782458224.git.mazziesaccount@gmail.com>
[-- Attachment #1: Type: text/plain, Size: 1581 bytes --]
From: Matti Vaittinen <mazziesaccount@gmail.com>
Support ROHM BD12790 hot-swap controller which is largely compatible
with the Analog Devices adm1272.
Signed-off-by: Matti Vaittinen <mazziesaccount@gmail.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
---
Revision history:
v1 => :
- Fixed double space from description
---
Documentation/devicetree/bindings/hwmon/adi,adm1275.yaml | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/Documentation/devicetree/bindings/hwmon/adi,adm1275.yaml b/Documentation/devicetree/bindings/hwmon/adi,adm1275.yaml
index 503e93756584..283cd1662689 100644
--- a/Documentation/devicetree/bindings/hwmon/adi,adm1275.yaml
+++ b/Documentation/devicetree/bindings/hwmon/adi,adm1275.yaml
@@ -33,6 +33,9 @@ description: |
https://fscdn.rohm.com/en/products/databook/datasheet/ic/power/power_switch/bd12780muv-lb-e.pdf
https://fscdn.rohm.com/en/products/databook/datasheet/ic/power/power_switch/bd12780amuv-lb-e.pdf
+ The BD12790 is a ROHM hot-swap controller, functionally similar to the
+ ADM1272.
+
properties:
compatible:
oneOf:
@@ -47,6 +50,7 @@ properties:
- adi,adm1293
- adi,adm1294
- rohm,bd12780
+ - rohm,bd12790
- silergy,mc09c
# Require BD12780 as a fall-back for BD12780A.
@@ -103,6 +107,7 @@ allOf:
enum:
- adi,adm1272
- adi,adm1273
+ - rohm,bd12790
then:
properties:
adi,volt-curr-sample-average:
--
2.54.0
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]
^ permalink raw reply related
* [PATCH v2 6/9] hwmon: adm1275: Support ROHM BD12780
From: Matti Vaittinen @ 2026-06-26 7:24 UTC (permalink / raw)
To: Matti Vaittinen, Matti Vaittinen, Matti Vaittinen
Cc: Guenter Roeck, Rob Herring, Krzysztof Kozlowski, Conor Dooley,
Jonathan Corbet, Shuah Khan, Wensheng Wang, Matti Vaittinen,
Ashish Yadav, Vasileios Amoiridis, Kim Seer Paller, ChiShih Tsai,
Chris Packham, Robert Coulson, linux-hwmon, devicetree,
linux-kernel, linux-doc
In-Reply-To: <cover.1782458224.git.mazziesaccount@gmail.com>
[-- Attachment #1: Type: text/plain, Size: 6290 bytes --]
From: Matti Vaittinen <mazziesaccount@gmail.com>
ROHM BD12780 and BD12780A are hot-swap controllers. They are largely
similar to Analog Devices ADM1278. Besides the ID registers and some
added functionality, the BD12780 and BD12780A mark PMON_CONFIG bits
[15:14] as reserved. Hence TSFILT setting must be omitted on these ICs.
The BD12780 has 3 pins usable for configuring the I2C address. The
BD12780A lists the ADDR3-pin as "not connect".
Support ROHM BD12780 and BD12780A controllers.
Signed-off-by: Matti Vaittinen <mazziesaccount@gmail.com>
---
Revision history:
v1 => v2: Changes based on the review by Guenter:
- Drop i2c_device_id for bd12780a
- Add own 'case' for the bd12780 instead of overloading the existing
one and still having an 'if (id == bd12780)' inside the case.
---
drivers/hwmon/pmbus/Kconfig | 2 +-
drivers/hwmon/pmbus/adm1275.c | 55 ++++++++++++++++++++++++++++++-----
2 files changed, 48 insertions(+), 9 deletions(-)
diff --git a/drivers/hwmon/pmbus/Kconfig b/drivers/hwmon/pmbus/Kconfig
index 8f4bff375ecb..b3c27f3b2712 100644
--- a/drivers/hwmon/pmbus/Kconfig
+++ b/drivers/hwmon/pmbus/Kconfig
@@ -52,7 +52,7 @@ config SENSORS_ADM1275
help
If you say yes here you get hardware monitoring support for Analog
Devices ADM1075, ADM1272, ADM1273, ADM1275, ADM1276, ADM1278, ADM1281,
- ADM1293, ADM1294 and SQ24905C Hot-Swap Controller and
+ ADM1293, ADM1294, ROHM BD12780, and SQ24905C Hot-Swap Controller and
Digital Power Monitors.
This driver can also be built as a module. If so, the module will
diff --git a/drivers/hwmon/pmbus/adm1275.c b/drivers/hwmon/pmbus/adm1275.c
index 1ea2037711e1..81c50fab7687 100644
--- a/drivers/hwmon/pmbus/adm1275.c
+++ b/drivers/hwmon/pmbus/adm1275.c
@@ -19,7 +19,7 @@
#include "pmbus.h"
enum chips { adm1075, adm1272, adm1273, adm1275, adm1276, adm1278, adm1281,
- adm1293, adm1294, sq24905c };
+ adm1293, adm1294, bd12780, sq24905c };
#define ADM1275_MFR_STATUS_IOUT_WARN2 BIT(0)
#define ADM1293_MFR_STATUS_VAUX_UV_WARN BIT(5)
@@ -47,6 +47,8 @@ enum chips { adm1075, adm1272, adm1273, adm1275, adm1276, adm1278, adm1281,
#define ADM1278_VOUT_EN BIT(1)
#define ADM1278_PMON_DEFCONFIG (ADM1278_VOUT_EN | ADM1278_TEMP1_EN | ADM1278_TSFILT)
+/* The BD12780 data sheets mark TSFILT bit as reserved. */
+#define BD12780_PMON_DEFCONFIG (ADM1278_VOUT_EN | ADM1278_TEMP1_EN)
#define ADM1293_IRANGE_25 0
#define ADM1293_IRANGE_50 BIT(6)
@@ -487,6 +489,7 @@ static const struct i2c_device_id adm1275_id[] = {
{ "adm1281", adm1281 },
{ "adm1293", adm1293 },
{ "adm1294", adm1294 },
+ { "bd12780", bd12780 },
{ "mc09c", sq24905c },
{ }
};
@@ -494,12 +497,13 @@ MODULE_DEVICE_TABLE(i2c, adm1275_id);
/* Enable VOUT & TEMP1 if not enabled (disabled by default) */
static int adm1275_enable_vout_temp(struct adm1275_data *data,
- struct i2c_client *client, int config)
+ struct i2c_client *client, int config,
+ u16 defconfig)
{
int ret;
- if ((config & ADM1278_PMON_DEFCONFIG) != ADM1278_PMON_DEFCONFIG) {
- config |= ADM1278_PMON_DEFCONFIG;
+ if ((config & defconfig) != defconfig) {
+ config |= defconfig;
ret = adm1275_write_pmon_config(data, client, config);
if (ret < 0) {
dev_err(&client->dev, "Failed to enable VOUT/TEMP1 monitoring\n");
@@ -535,7 +539,8 @@ static int adm1275_probe(struct i2c_client *client)
return ret;
}
if ((ret != 3 || strncmp(block_buffer, "ADI", 3)) &&
- (ret != 2 || strncmp(block_buffer, "SY", 2))) {
+ (ret != 2 || strncmp(block_buffer, "SY", 2)) &&
+ (ret != 4 || strncmp(block_buffer, "ROHM", 4))) {
dev_err(&client->dev, "Unsupported Manufacturer ID\n");
return -ENODEV;
}
@@ -562,7 +567,7 @@ static int adm1275_probe(struct i2c_client *client)
if (mid->driver_data == adm1272 || mid->driver_data == adm1273 ||
mid->driver_data == adm1278 || mid->driver_data == adm1281 ||
mid->driver_data == adm1293 || mid->driver_data == adm1294 ||
- mid->driver_data == sq24905c)
+ mid->driver_data == bd12780 || mid->driver_data == sq24905c)
config_read_fn = i2c_smbus_read_word_data;
else
config_read_fn = i2c_smbus_read_byte_data;
@@ -666,7 +671,8 @@ static int adm1275_probe(struct i2c_client *client)
PMBUS_HAVE_VOUT | PMBUS_HAVE_STATUS_VOUT |
PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP;
- ret = adm1275_enable_vout_temp(data, client, config);
+ ret = adm1275_enable_vout_temp(data, client, config,
+ ADM1278_PMON_DEFCONFIG);
if (ret)
return ret;
@@ -728,13 +734,45 @@ static int adm1275_probe(struct i2c_client *client)
PMBUS_HAVE_VOUT | PMBUS_HAVE_STATUS_VOUT |
PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP;
- ret = adm1275_enable_vout_temp(data, client, config);
+ ret = adm1275_enable_vout_temp(data, client, config,
+ ADM1278_PMON_DEFCONFIG);
if (ret)
return ret;
if (config & ADM1278_VIN_EN)
info->func[0] |= PMBUS_HAVE_VIN;
break;
+
+ /*
+ * The BD12780 is almost functionally identical with the adm1278 above.
+ * Only differences visible to the driver are lack of TSFILT bits and
+ * different identification register contents.
+ */
+ case bd12780:
+ data->have_vout = true;
+ data->have_pin_max = true;
+ data->have_temp_max = true;
+ data->have_power_sampling = true;
+
+ coefficients = adm1278_coefficients;
+ vindex = 0;
+ cindex = 1;
+ pindex = 2;
+ tindex = 3;
+
+ info->func[0] |= PMBUS_HAVE_PIN | PMBUS_HAVE_STATUS_INPUT |
+ PMBUS_HAVE_VOUT | PMBUS_HAVE_STATUS_VOUT |
+ PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP;
+
+ ret = adm1275_enable_vout_temp(data, client, config,
+ BD12780_PMON_DEFCONFIG);
+ if (ret)
+ return ret;
+
+ if (config & ADM1278_VIN_EN)
+ info->func[0] |= PMBUS_HAVE_VIN;
+
+ break;
case adm1293:
case adm1294:
data->have_iout_min = true;
@@ -880,6 +918,7 @@ static const struct of_device_id adm1275_of_match[] = {
{ .compatible = "adi,adm1281", },
{ .compatible = "adi,adm1293", },
{ .compatible = "adi,adm1294", },
+ { .compatible = "rohm,bd12780", },
{ .compatible = "silergy,mc09c", },
{ }
};
--
2.54.0
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]
^ permalink raw reply related
* [PATCH v2 5/9] doc: Add ROHM BD12780 and BD12780A
From: Matti Vaittinen @ 2026-06-26 7:24 UTC (permalink / raw)
To: Matti Vaittinen, Matti Vaittinen, Matti Vaittinen
Cc: Guenter Roeck, Rob Herring, Krzysztof Kozlowski, Conor Dooley,
Jonathan Corbet, Shuah Khan, Wensheng Wang, Matti Vaittinen,
Ashish Yadav, Vasileios Amoiridis, Kim Seer Paller, ChiShih Tsai,
Chris Packham, Robert Coulson, linux-hwmon, devicetree,
linux-kernel, linux-doc
In-Reply-To: <cover.1782458224.git.mazziesaccount@gmail.com>
[-- Attachment #1: Type: text/plain, Size: 1186 bytes --]
From: Matti Vaittinen <mazziesaccount@gmail.com>
Add the ROHM BD12780 and the BD12780A to the list of the ICs supported by
the adm1275 driver.
Signed-off-by: Matti Vaittinen <mazziesaccount@gmail.com>
---
Revision history:
v1 => :
- No changes
---
Documentation/hwmon/adm1275.rst | 16 ++++++++++++++++
1 file changed, 16 insertions(+)
diff --git a/Documentation/hwmon/adm1275.rst b/Documentation/hwmon/adm1275.rst
index cf923f20fa52..8a793dd2b412 100644
--- a/Documentation/hwmon/adm1275.rst
+++ b/Documentation/hwmon/adm1275.rst
@@ -67,6 +67,22 @@ Supported chips:
Datasheet: https://www.analog.com/media/en/technical-documentation/data-sheets/ADM1293_1294.pdf
+ * ROHM Semiconductor BD12780
+
+ Prefix: 'bd12780'
+
+ Addresses scanned: -
+
+ Datasheet: https://fscdn.rohm.com/en/products/databook/datasheet/ic/power/power_switch/bd12780muv-lb-e.pdf
+
+ * ROHM Semiconductor BD12780A
+
+ Prefix: 'bd12780'
+
+ Addresses scanned: -
+
+ Datasheet: https://fscdn.rohm.com/en/products/databook/datasheet/ic/power/power_switch/bd12780amuv-lb-e.pdf
+
* Silergy SQ24905C
Prefix: 'mc09c'
--
2.54.0
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]
^ permalink raw reply related
* [PATCH v2 4/9] hwmon: adm1275: Support module auto-loading
From: Matti Vaittinen @ 2026-06-26 7:24 UTC (permalink / raw)
To: Matti Vaittinen, Matti Vaittinen, Matti Vaittinen
Cc: Guenter Roeck, Rob Herring, Krzysztof Kozlowski, Conor Dooley,
Jonathan Corbet, Shuah Khan, Wensheng Wang, Matti Vaittinen,
Ashish Yadav, Vasileios Amoiridis, Kim Seer Paller, ChiShih Tsai,
Chris Packham, Robert Coulson, linux-hwmon, devicetree,
linux-kernel, linux-doc
In-Reply-To: <cover.1782458224.git.mazziesaccount@gmail.com>
[-- Attachment #1: Type: text/plain, Size: 1948 bytes --]
From: Matti Vaittinen <mazziesaccount@gmail.com>
Populating the i2c_device_id -table is not enough to make the
driver module automatically load when device-tree node for the
power-monitor is parsed at boot.
Adding the of_device_id tables causes the driver module to be
automatically load at boot. Testing has been done with rather old Debian
system.
When inspecting the generated module-aliases with the insmod, following
entries seem to be the difference:
alias: of:N*T*Cadi,adm1075C*
alias: of:N*T*Cadi,adm1075
I suspect these are required for the module loading to work.
Signed-off-by: Matti Vaittinen <mazziesaccount@gmail.com>
---
Revision history:
v1 => v2:
- New patch as discussed with Guenter here:
https://lore.kernel.org/all/f080e20e-6ec7-4744-9794-0a92d03f48d8@roeck-us.net/
---
drivers/hwmon/pmbus/adm1275.c | 16 ++++++++++++++++
1 file changed, 16 insertions(+)
diff --git a/drivers/hwmon/pmbus/adm1275.c b/drivers/hwmon/pmbus/adm1275.c
index ccc3ad21e38e..1ea2037711e1 100644
--- a/drivers/hwmon/pmbus/adm1275.c
+++ b/drivers/hwmon/pmbus/adm1275.c
@@ -870,9 +870,25 @@ static int adm1275_probe(struct i2c_client *client)
return pmbus_do_probe(client, info);
}
+static const struct of_device_id adm1275_of_match[] = {
+ { .compatible = "adi,adm1075", },
+ { .compatible = "adi,adm1272", },
+ { .compatible = "adi,adm1273", },
+ { .compatible = "adi,adm1275", },
+ { .compatible = "adi,adm1276", },
+ { .compatible = "adi,adm1278", },
+ { .compatible = "adi,adm1281", },
+ { .compatible = "adi,adm1293", },
+ { .compatible = "adi,adm1294", },
+ { .compatible = "silergy,mc09c", },
+ { }
+};
+MODULE_DEVICE_TABLE(of, adm1275_of_match);
+
static struct i2c_driver adm1275_driver = {
.driver = {
.name = "adm1275",
+ .of_match_table = adm1275_of_match,
},
.probe = adm1275_probe,
.id_table = adm1275_id,
--
2.54.0
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]
^ permalink raw reply related
* [PATCH v2 3/9] hwmon: adm1275: Detect coefficient overflow
From: Matti Vaittinen @ 2026-06-26 7:23 UTC (permalink / raw)
To: Matti Vaittinen, Matti Vaittinen, Matti Vaittinen
Cc: Guenter Roeck, Rob Herring, Krzysztof Kozlowski, Conor Dooley,
Jonathan Corbet, Shuah Khan, Wensheng Wang, Matti Vaittinen,
Ashish Yadav, Vasileios Amoiridis, Kim Seer Paller, ChiShih Tsai,
Chris Packham, Robert Coulson, linux-hwmon, devicetree,
linux-kernel, linux-doc
In-Reply-To: <cover.1782458224.git.mazziesaccount@gmail.com>
[-- Attachment #1: Type: text/plain, Size: 2645 bytes --]
From: Matti Vaittinen <mazziesaccount@gmail.com>
Sashiko detected potential coefficient overflow if large shunt resistor
is used. When going unnoticed it can cause "drastically incorrect
telemetry scaling factors" as Sashiko put it.
I am not convinced such "drastically incorrect telemetry scaling
factors" could have gone unnoticed, so I suspect such large shunt
resistors aren't really used. Well, it shouldn't hurt to detect the
error and abort the probe before Really Wrong current / power -values
are reported to user by the hwmon.
Signed-off-by: Matti Vaittinen <mazziesaccount@gmail.com>
---
Revision history:
v1 => v2:
- New patch
This patch returns -EOVERFLOW with an error print if overflow is
detected. IF there really are systems where the overflow truly occurs,
then this change will cause the probe to fail - which might hurt the
boot process. It might be safer to only print the warning. One could
also try changing the order of the shunt resistor value division (/1000)
and the multiplication and see if overflow goes away - but it'll be
somewhat more complex then. Hence, I just decided to error-out if this
happens, and leave this for the people facing the real overflow to fix
(if needed)... It's still fair to mention this might cause issues.
---
drivers/hwmon/pmbus/adm1275.c | 18 ++++++++++++++----
1 file changed, 14 insertions(+), 4 deletions(-)
diff --git a/drivers/hwmon/pmbus/adm1275.c b/drivers/hwmon/pmbus/adm1275.c
index 43baa5ded35e..ccc3ad21e38e 100644
--- a/drivers/hwmon/pmbus/adm1275.c
+++ b/drivers/hwmon/pmbus/adm1275.c
@@ -839,15 +839,25 @@ static int adm1275_probe(struct i2c_client *client)
info->R[PSC_VOLTAGE_OUT] = coefficients[voindex].R;
}
if (cindex >= 0) {
+ u32 m;
+
/* Scale current with sense resistor value */
- info->m[PSC_CURRENT_OUT] =
- coefficients[cindex].m * shunt / 1000;
+ if (unlikely(check_mul_overflow(coefficients[cindex].m, shunt, &m))) {
+ dev_err(&client->dev, "Current coefficient overflow\n");
+ return -EOVERFLOW;
+ }
+ info->m[PSC_CURRENT_OUT] = m / 1000;
info->b[PSC_CURRENT_OUT] = coefficients[cindex].b;
info->R[PSC_CURRENT_OUT] = coefficients[cindex].R;
}
if (pindex >= 0) {
- info->m[PSC_POWER] =
- coefficients[pindex].m * shunt / 1000;
+ u32 m;
+
+ if (unlikely(check_mul_overflow(coefficients[pindex].m, shunt, &m))) {
+ dev_err(&client->dev, "Power coefficient overflow\n");
+ return -EOVERFLOW;
+ }
+ info->m[PSC_POWER] = m / 1000;
info->b[PSC_POWER] = coefficients[pindex].b;
info->R[PSC_POWER] = coefficients[pindex].R;
}
--
2.54.0
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]
^ permalink raw reply related
* [PATCH v2 2/9] hwmon: adm1275: Prevent reading uninitialized stack
From: Matti Vaittinen @ 2026-06-26 7:22 UTC (permalink / raw)
To: Matti Vaittinen, Matti Vaittinen, Matti Vaittinen
Cc: Guenter Roeck, Rob Herring, Krzysztof Kozlowski, Conor Dooley,
Jonathan Corbet, Shuah Khan, Wensheng Wang, Matti Vaittinen,
Ashish Yadav, Vasileios Amoiridis, Kim Seer Paller, ChiShih Tsai,
Chris Packham, Robert Coulson, linux-hwmon, devicetree,
linux-kernel, linux-doc
In-Reply-To: <cover.1782458224.git.mazziesaccount@gmail.com>
[-- Attachment #1: Type: text/plain, Size: 1975 bytes --]
From: Matti Vaittinen <mazziesaccount@gmail.com>
While adding support for the ROHM BD127X0 hot-swap controllers, sashiko
reported an error in device-name comparison, which can lead to reading
uninitialized stack memory.
Quoting Sashiko:
This is a pre-existing issue, but I noticed that just before this block in
adm1275_probe(), there might be an out-of-bounds stack read:
ret = i2c_smbus_read_block_data(client, PMBUS_MFR_MODEL, block_buffer);
if (ret < 0) { ... }
for (mid = adm1275_id; mid->name[0]; mid++) {
if (!strncasecmp(mid->name, block_buffer, strlen(mid->name)))
break;
}
Since i2c_smbus_read_block_data() reads up to 32 bytes into the
uninitialized stack array block_buffer without appending a null
terminator, strncasecmp() could read past the valid bytes returned in ret.
For example, if the device returns a shorter string like "adm12", checking
it against "adm1275" up to the length of "adm1275" will continue reading
into uninitialized stack bounds.
Prevent reading uninitialized memory by zeroing the stack array.
Signed-off-by: Matti Vaittinen <mazziesaccount@gmail.com>
Fixes: 87102808d039 ("hwmon: (pmbus/adm1275) Validate device ID")
---
Revision history:
v1 => v2:
- New patch
---
drivers/hwmon/pmbus/adm1275.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/hwmon/pmbus/adm1275.c b/drivers/hwmon/pmbus/adm1275.c
index bc2a6a07dc3e..43baa5ded35e 100644
--- a/drivers/hwmon/pmbus/adm1275.c
+++ b/drivers/hwmon/pmbus/adm1275.c
@@ -512,7 +512,7 @@ static int adm1275_enable_vout_temp(struct adm1275_data *data,
static int adm1275_probe(struct i2c_client *client)
{
s32 (*config_read_fn)(const struct i2c_client *client, u8 reg);
- u8 block_buffer[I2C_SMBUS_BLOCK_MAX + 1];
+ u8 block_buffer[I2C_SMBUS_BLOCK_MAX + 1] = {0};
int config, device_config;
int ret;
struct pmbus_driver_info *info;
--
2.54.0
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]
^ permalink raw reply related
* [PATCH v2 1/9] dt-bindings: adm1275: ROHM BD12780 hot-swap controller
From: Matti Vaittinen @ 2026-06-26 7:21 UTC (permalink / raw)
To: Matti Vaittinen, Matti Vaittinen, Matti Vaittinen
Cc: Guenter Roeck, Rob Herring, Krzysztof Kozlowski, Conor Dooley,
Jonathan Corbet, Shuah Khan, Wensheng Wang, Matti Vaittinen,
Ashish Yadav, Vasileios Amoiridis, Kim Seer Paller, ChiShih Tsai,
Chris Packham, Robert Coulson, linux-hwmon, devicetree,
linux-kernel, linux-doc
In-Reply-To: <cover.1782458224.git.mazziesaccount@gmail.com>
[-- Attachment #1: Type: text/plain, Size: 2599 bytes --]
From: Matti Vaittinen <mazziesaccount@gmail.com>
Support ROHM BD12780 and BD12780A hot-swap controllers, which are largely
compatible with the Analog Devices adm1278. Main difference between
the BD12780 and the BD12780A is, that the BD12780 has one I2C address
configuration pin more (ADDR3) than the BD12780A.
Introduce own compatibles for both variants but require the BD12780A to
always have the BD12780 as a fall-back.
Signed-off-by: Matti Vaittinen <mazziesaccount@gmail.com>
---
Revision history:
v1 => v2:
- Drop extra -items from the compatible list as suggested by Krzysztof
---
.../bindings/hwmon/adi,adm1275.yaml | 38 +++++++++++++------
1 file changed, 27 insertions(+), 11 deletions(-)
diff --git a/Documentation/devicetree/bindings/hwmon/adi,adm1275.yaml b/Documentation/devicetree/bindings/hwmon/adi,adm1275.yaml
index d6a7517f2a50..503e93756584 100644
--- a/Documentation/devicetree/bindings/hwmon/adi,adm1275.yaml
+++ b/Documentation/devicetree/bindings/hwmon/adi,adm1275.yaml
@@ -25,19 +25,34 @@ description: |
https://www.silergy.com/
download/downloadFile?id=5669&type=product&ftype=note
+ The BD12780 and BD12780A are hot-swap controllers from ROHM. They are
+ functionally compatible with the ADM1278. The main difference between
+ the BD12780A and the BD12780 is amount of configurable I2C addresses.
+
+ Datasheets:
+ https://fscdn.rohm.com/en/products/databook/datasheet/ic/power/power_switch/bd12780muv-lb-e.pdf
+ https://fscdn.rohm.com/en/products/databook/datasheet/ic/power/power_switch/bd12780amuv-lb-e.pdf
+
properties:
compatible:
- enum:
- - adi,adm1075
- - adi,adm1272
- - adi,adm1273
- - adi,adm1275
- - adi,adm1276
- - adi,adm1278
- - adi,adm1281
- - adi,adm1293
- - adi,adm1294
- - silergy,mc09c
+ oneOf:
+ - enum:
+ - adi,adm1075
+ - adi,adm1272
+ - adi,adm1273
+ - adi,adm1275
+ - adi,adm1276
+ - adi,adm1278
+ - adi,adm1281
+ - adi,adm1293
+ - adi,adm1294
+ - rohm,bd12780
+ - silergy,mc09c
+
+ # Require BD12780 as a fall-back for BD12780A.
+ - items:
+ - const: rohm,bd12780a
+ - const: rohm,bd12780
reg:
maxItems: 1
@@ -104,6 +119,7 @@ allOf:
- adi,adm1281
- adi,adm1293
- adi,adm1294
+ - rohm,bd12780
- silergy,mc09c
then:
properties:
--
2.54.0
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]
^ permalink raw reply related
* [PATCH v2 0/9] Support ROHM BD127x0 hot-swap controllers
From: Matti Vaittinen @ 2026-06-26 7:21 UTC (permalink / raw)
To: Matti Vaittinen, Matti Vaittinen, Matti Vaittinen
Cc: Guenter Roeck, Rob Herring, Krzysztof Kozlowski, Conor Dooley,
Jonathan Corbet, Shuah Khan, Wensheng Wang, Matti Vaittinen,
Ashish Yadav, Vasileios Amoiridis, Kim Seer Paller, ChiShih Tsai,
Chris Packham, Robert Coulson, linux-hwmon, devicetree,
linux-kernel, linux-doc
[-- Attachment #1: Type: text/plain, Size: 1924 bytes --]
Support ROHM BD12780(A) and BD12790
The BD12780 and BD12780A hot-swap controllers are very similar to Analog
Devices ADM1278. There are only some minor differences in the registers.
The BD12790 is largely similar to the ADM1272, with slightly different
coefficients and minor register changes.
This series adds basic support for these ROHM ICs.
Additionally, this series contains couple of fixes, which can be applied
independently from the bd127x0 support patches. Fixes are:
Patch 2/9: Prevent read from uninitialized stack (found by Sashiko)
Patch 3/9: Prevent coefficient overflow with larget shunt resistor (found
by Sashiko)
Patch 4/9: Support module auto-loading when DT is used.
Revision history:
v1 => v2:
dt-bindings:
- Fix compatible list as suggested by Krzysztof
adm1275:
- Add patches to fix issues pointed by Sashiko.
- Add of_device_ids for all supported devices.
- Add own switch 'case's for the new ICs instead of overloading
existing ones
- Drop i2c_device_id for bd12780a
- Don't use IC-wildcard in macro name.
---
Matti Vaittinen (9):
dt-bindings: adm1275: ROHM BD12780 hot-swap controller
hwmon: adm1275: Prevent reading uninitialized stack
hwmon: adm1275: Detect coefficient overflow
hwmon: adm1275: Support module auto-loading
doc: Add ROHM BD12780 and BD12780A
hwmon: adm1275: Support ROHM BD12780
dt-bindings: adm1275: ROHM BD12790 hot-swap controller
doc: adm1275: Add ROHM BD12790
hwmon: adm1275: Support ROHM BD12790
.../bindings/hwmon/adi,adm1275.yaml | 43 +++--
Documentation/hwmon/adm1275.rst | 24 +++
drivers/hwmon/pmbus/Kconfig | 4 +-
drivers/hwmon/pmbus/adm1275.c | 162 ++++++++++++++++--
4 files changed, 208 insertions(+), 25 deletions(-)
base-commit: 254f49634ee16a731174d2ae34bc50bd5f45e731
--
2.54.0
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]
^ permalink raw reply
* Re: [RFC PATCH v5] platform/x86: panasonic-laptop: add fan speed mode for newer models
From: sashiko-bot @ 2026-06-26 5:47 UTC (permalink / raw)
To: Alex Yeo; +Cc: linux-hwmon
In-Reply-To: <20260626053235.25834-1-alexyeo362@gmail.com>
Thank you for your contribution! Sashiko AI review found 5 potential issue(s) to consider:
- [High] Returning `100` (max_state) for the thermal cooling device's current state when in AUTO mode defeats the thermal governor and permanently degrades cooling.
- [Medium] The driver assigns standard Linux error codes to an `acpi_status` variable and evaluates them using `ACPI_FAILURE()`.
- [Medium] The `pcc_pwm_fan_hwmon_read` function lacks bounds checking for the raw PWM speed returned by the hardware, potentially violating the hwmon ABI.
- [Low] The driver introduces a private mutex (`pwm_fan_lock`) instead of using the hwmon subsystem's locking mechanism.
- [Low] The global `quirks` variable is assigned in a DMI callback but never used.
--
commit bc34c0a562a71eb6eb4101fca6fd721a3d653df2
Author: Alex Yeo <alexyeo362@gmail.com>
platform/x86: panasonic-laptop: add fan speed mode for newer models
This commit adds fan speed and mode support for newer Panasonic laptop models
like the CF-SR4. It utilizes ACPI methods to read and write the fan profile
and registers the fan with both the hwmon and thermal subsystems.
> diff --git a/drivers/platform/x86/panasonic-laptop.c b/drivers/platform/x86/panasonic-laptop.c
> index b83113c26f885..a1837106ff6b1 100644
> --- a/drivers/platform/x86/panasonic-laptop.c
> +++ b/drivers/platform/x86/panasonic-laptop.c
[ ... ]
> @@ -238,19 +258,53 @@ static const struct key_entry panasonic_keymap[] = {
> };
>
> struct pcc_acpi {
[ ... ]
> + struct thermal_cooling_device *pwm_fan_cdev;
> + struct device *pwm_fan_hwmon;
> + struct mutex pwm_fan_lock;
[Severity: Low]
Does this driver need a private mutex for the hwmon attributes?
The hardware monitoring subsystem guidelines dictate using hwmon_lock() and
hwmon_unlock() for attributes registered outside the core, rather than
implementing a driver-specific lock.
> };
> +
> +/*
> + * Declare quirks and apply matches
> + */
> +static struct quirk_entry *quirks;
> +
> +static struct quirk_entry quirk_cf_sr4 = {
> + .has_ospm_pwm_fan = true,
> +};
> +
> +/* DMI matching for quirks copied from asus-nb-wmi.c */
> +static int dmi_matched(const struct dmi_system_id *dmi)
> +{
> + pr_info("Identified laptop model '%s'\n", dmi->ident);
> + quirks = dmi->driver_data;
[Severity: Low]
Is this global quirks variable necessary?
The dmi_matched() callback assigns the matched data here, but the driver
appears to ignore this global variable later, instead directly assigning
pcc->quirks = dmi_id->driver_data during probe.
> + return 1;
> +}
[ ... ]
> @@ -825,6 +1052,240 @@ static const struct attribute_group pcc_attr_group = {
> .is_visible = pcc_sysfs_is_visible,
> };
>
> +/* hwmon */
[ ... ]
> +static int pcc_pwm_fan_hwmon_read(struct device *dev,
> + enum hwmon_sensor_types type, u32 attr,
> + int channel, long *val)
> +{
> + struct pcc_acpi *pcc;
> + acpi_status status;
> + int pwm_speed;
> + int pwm_mode;
> + int result;
> +
> + pcc = dev_get_drvdata(dev);
> +
> + if (type != hwmon_pwm)
> + return -EOPNOTSUPP;
> +
> + switch (attr) {
> + case hwmon_pwm_input:
> + mutex_lock(&pcc->pwm_fan_lock);
> +
> + status = pcc_pwm_fan_speed_read(&pwm_speed);
> + if (ACPI_FAILURE(status)) {
> + result = status;
[Severity: Medium]
Does this safely mix Linux error codes with ACPI status codes?
Helper functions like pcc_pwm_fan_speed_read() return negative standard
Linux error codes (e.g., -EINVAL), but here they are assigned to an
acpi_status variable and evaluated with ACPI_FAILURE().
While ACPI_FAILURE() might evaluate to true for negative values due to two's
complement representation, it violates the ACPICA API contract and can lead
to swallowed or mangled error codes being passed back to userspace.
> + } else {
> + *val = (pwm_speed * 255) / 100;
[Severity: Medium]
Could this calculation expose an out-of-bounds value to userspace?
If the ACPI method returns a value greater than 100 (which can happen for
unknown or indeterminate states like 255), this unchecked math will produce
a value outside the standard 0-255 range mandated by the hwmon ABI for
pwm attributes.
> + result = 0;
> + }
> +
> + mutex_unlock(&pcc->pwm_fan_lock);
> + return result;
[ ... ]
> +static int
> +pcc_pwm_fan_thermal_get_current_pwm(struct thermal_cooling_device *cdev,
> + unsigned long *state)
> +{
> + struct pcc_acpi *pcc;
> + acpi_status status;
> + int current_pwm;
> + int pwm_mode;
> + int result;
> +
> + pcc = cdev->devdata;
> +
> + mutex_lock(&pcc->pwm_fan_lock);
> +
> + status = pcc_pwm_fan_mode_read(&pwm_mode);
> + if (ACPI_FAILURE(status)) {
> + pr_err("%s: failed to get fan pwm mode\n", __func__);
> + result = -ENODATA;
> + goto out;
> + }
> + if (pwm_mode == HWMON_PCC_FAN_PWM_AUTO) {
> + *state = 100; /* Return failsafe value on EC mode */
[Severity: High]
Does returning 100 (the maximum state) while in AUTO mode paralyze the
thermal governor?
If the system overheats while the fan is in AUTO mode, the step_wise
governor will read the current state as 100 and assume it is at maximum
cooling capacity, doing nothing to ramp up the fan.
When the temperature drops, it will decrease the state to 99, invoking
set_cur_state(99). This immediately and permanently switches the fan to
MANUAL mode, which has a lower maximum speed limit than AUTO mode, degrading
cooling performance permanently.
> + result = 0;
> + goto out;
> + }
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260626053235.25834-1-alexyeo362@gmail.com?part=1
^ permalink raw reply
page: next (older)
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox