[PATCH] hwmon: emc1812: reject channel index 0 in device tree config

[PATCH] hwmon: emc1812: reject channel index 0 in device tree config

[Ivy Lopez]

Channel index 0 is reserved for the internal diode and is set
unconditionally before parsing child nodes. If a child node specifies
reg = 0, it silently overwrites the internal diode label

Reject reg = 0 in child nodes and improve the error message to
include the invalid index value.

Signed-off-by: Ivy Lopez <skunkolee@gmail.com>
---
 drivers/hwmon/emc1812.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/hwmon/emc1812.c b/drivers/hwmon/emc1812.c
index 68575c27d090..143c3c07dbaa 100644
--- a/drivers/hwmon/emc1812.c
+++ b/drivers/hwmon/emc1812.c
@@ -809,9 +809,10 @@ static int emc1812_parse_fw_config(struct emc1812_data *data, struct device *dev
 
 	device_for_each_child_node_scoped(dev, child) {
 		ret = fwnode_property_read_u32(child, "reg", &reg_nr);
-		if (ret || reg_nr >= data->chip->phys_channels)
+		if (ret || reg_nr == 0 || reg_nr >= data->chip->phys_channels)
 			return dev_err_probe(dev, -EINVAL,
-					     "The index is higher then the chip supports\n");
+					"Invalid channel index %u\n",
+					reg_nr);
 		/* Mark channel as active */
 		set_bit(reg_nr, &data->active_ch_mask);
 
-- 
2.55.0

Re: [PATCH] hwmon: emc1812: reject channel index 0 in device tree config

[Guenter Roeck]

On 7/15/26 17:25, Ivy Lopez wrote:
> Channel index 0 is reserved for the internal diode and is set
> unconditionally before parsing child nodes. If a child node specifies
> reg = 0, it silently overwrites the internal diode label
> 

The label string "internal_diode" is completely meaningless.
If anything, it should be dropped. I see it as a good thing,
not as a bug, that it can be overwritten.

NACK.

Guenter

Re: [PATCH] hwmon: emc1812: reject channel index 0 in device tree config

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
- [Critical] Rejecting channel index 0 (`reg = 0`) breaks Devicetree ABI backward compatibility and prevents probing of valid, existing device trees.
- [Low] When reading the `reg` property fails, the error message logs an unread, stale `reg_nr` value, misdirecting debugging efforts.
--

--- Patch [1]: [PATCH] hwmon: emc1812: reject channel index 0 in device tree config ---
commit f33e5fdce14729c5f30dbfaad69487c1d7f783de
Author: Ivy Lopez <skunkolee@gmail.com>

hwmon: emc1812: reject channel index 0 in device tree config

This commit explicitly rejects channel index 0 in child nodes to prevent
the internal diode label from being overwritten. It also updates the error
message to include the invalid index.

> diff --git a/drivers/hwmon/emc1812.c b/drivers/hwmon/emc1812.c
> --- a/drivers/hwmon/emc1812.c
> +++ b/drivers/hwmon/emc1812.c
> @@ -809,9 +809,10 @@ static int emc1812_parse_fw_config(struct emc1812_data *data, struct device *dev
>  
>  	device_for_each_child_node_scoped(dev, child) {
>  		ret = fwnode_property_read_u32(child, "reg", &reg_nr);
> -		if (ret || reg_nr >= data->chip->phys_channels)
> +		if (ret || reg_nr == 0 || reg_nr >= data->chip->phys_channels)

[Severity: Critical]
Does adding reg_nr == 0 break Devicetree ABI backward compatibility?

If there are existing device trees that specify a child node for the internal
sensor (channel@0), emc1812_parse_fw_config() will now return -EINVAL during
probe and fail to load the driver.

>  			return dev_err_probe(dev, -EINVAL,
> -					     "The index is higher then the chip supports\n");
> +					"Invalid channel index %u\n",
> +					reg_nr);

[Severity: Low]
If fwnode_property_read_u32() fails and returns a non-zero error code 
(ret != 0), is it safe to print reg_nr?

If the child node is missing the reg property, fwnode_property_read_u32() 
leaves reg_nr unmodified. The error message would then log a stale reg_nr 
value from the previous iteration of the loop, which might misdirect 
debugging efforts.

>  		/* Mark channel as active */
>  		set_bit(reg_nr, &data->active_ch_mask);
>

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260716002543.26711-1-skunkolee@gmail.com?part=1