* [PATCH v9 01/10] spmi: Remove redundant dev_name() print in spmi_device_add()
2026-06-08 10:09 [PATCH v9 00/10] SPMI: Implement sub-devices and migrate drivers AngeloGioacchino Del Regno
@ 2026-06-08 10:09 ` AngeloGioacchino Del Regno
2026-06-08 10:09 ` [PATCH v9 02/10] spmi: Print error status with %pe format AngeloGioacchino Del Regno
` (8 subsequent siblings)
9 siblings, 0 replies; 19+ messages in thread
From: AngeloGioacchino Del Regno @ 2026-06-08 10:09 UTC (permalink / raw)
To: jic23
Cc: dlechner, nuno.sa, andy, arnd, gregkh, srini, vkoul,
neil.armstrong, sre, sboyd, angelogioacchino.delregno, krzk,
dmitry.baryshkov, quic_wcheng, melody.olvera, quic_nsekar,
ivo.ivanov.ivanov1, abelvesa, luca.weiss, konrad.dybcio,
mitltlatltl, krishna.kurapati, linux-arm-msm, linux-iio,
linux-kernel, linux-phy, linux-pm, kernel, Andy Shevchenko
Function spmi_device_add() uses dev_{dbg,err}() for respectively
debug and error prints, and passes the same device pointer as both
the dev_{dbg,err}() parameters and to a dev_name() that is part of
the actual message.
This means that the device name gets printed twice!
Remove the redundant dev_name() from the messages.
Acked-by: Stephen Boyd <sboyd@kernel.org>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@intel.com>
Signed-off-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
---
drivers/spmi/spmi.c | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
diff --git a/drivers/spmi/spmi.c b/drivers/spmi/spmi.c
index 57b7c0cb4240..152787ae82ca 100644
--- a/drivers/spmi/spmi.c
+++ b/drivers/spmi/spmi.c
@@ -68,12 +68,11 @@ int spmi_device_add(struct spmi_device *sdev)
err = device_add(&sdev->dev);
if (err < 0) {
- dev_err(&sdev->dev, "Can't add %s, status %d\n",
- dev_name(&sdev->dev), err);
+ dev_err(&sdev->dev, "Can't add device, status %d\n", err);
goto err_device_add;
}
- dev_dbg(&sdev->dev, "device %s registered\n", dev_name(&sdev->dev));
+ dev_dbg(&sdev->dev, "device registered\n");
err_device_add:
return err;
--
2.54.0
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply related [flat|nested] 19+ messages in thread* [PATCH v9 02/10] spmi: Print error status with %pe format
2026-06-08 10:09 [PATCH v9 00/10] SPMI: Implement sub-devices and migrate drivers AngeloGioacchino Del Regno
2026-06-08 10:09 ` [PATCH v9 01/10] spmi: Remove redundant dev_name() print in spmi_device_add() AngeloGioacchino Del Regno
@ 2026-06-08 10:09 ` AngeloGioacchino Del Regno
2026-06-08 10:37 ` sashiko-bot
2026-06-08 10:09 ` [PATCH v9 03/10] spmi: Remove unneeded goto in spmi_device_add() error path AngeloGioacchino Del Regno
` (7 subsequent siblings)
9 siblings, 1 reply; 19+ messages in thread
From: AngeloGioacchino Del Regno @ 2026-06-08 10:09 UTC (permalink / raw)
To: jic23
Cc: dlechner, nuno.sa, andy, arnd, gregkh, srini, vkoul,
neil.armstrong, sre, sboyd, angelogioacchino.delregno, krzk,
dmitry.baryshkov, quic_wcheng, melody.olvera, quic_nsekar,
ivo.ivanov.ivanov1, abelvesa, luca.weiss, konrad.dybcio,
mitltlatltl, krishna.kurapati, linux-arm-msm, linux-iio,
linux-kernel, linux-phy, linux-pm, kernel, Andy Shevchenko
Instead of printing just a number, use the %pe format for error
status, increasing readability of error prints.
Acked-by: Stephen Boyd <sboyd@kernel.org>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@intel.com>
Signed-off-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
---
drivers/spmi/spmi.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/spmi/spmi.c b/drivers/spmi/spmi.c
index 152787ae82ca..b0017bd61d95 100644
--- a/drivers/spmi/spmi.c
+++ b/drivers/spmi/spmi.c
@@ -68,7 +68,7 @@ int spmi_device_add(struct spmi_device *sdev)
err = device_add(&sdev->dev);
if (err < 0) {
- dev_err(&sdev->dev, "Can't add device, status %d\n", err);
+ dev_err(&sdev->dev, "Can't add device, status %pe\n", ERR_PTR(err));
goto err_device_add;
}
@@ -493,8 +493,8 @@ static void of_spmi_register_devices(struct spmi_controller *ctrl)
err = of_property_read_u32_array(node, "reg", reg, 2);
if (err) {
dev_err(&ctrl->dev,
- "node %pOF err (%d) does not have 'reg' property\n",
- node, err);
+ "node %pOF err (%pe) does not have 'reg' property\n",
+ node, ERR_PTR(err));
continue;
}
@@ -522,7 +522,7 @@ static void of_spmi_register_devices(struct spmi_controller *ctrl)
err = spmi_device_add(sdev);
if (err) {
dev_err(&sdev->dev,
- "failure adding device. status %d\n", err);
+ "failure adding device. status %pe\n", ERR_PTR(err));
spmi_device_put(sdev);
}
}
--
2.54.0
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply related [flat|nested] 19+ messages in thread* Re: [PATCH v9 02/10] spmi: Print error status with %pe format
2026-06-08 10:09 ` [PATCH v9 02/10] spmi: Print error status with %pe format AngeloGioacchino Del Regno
@ 2026-06-08 10:37 ` sashiko-bot
2026-06-08 11:29 ` AngeloGioacchino Del Regno
0 siblings, 1 reply; 19+ messages in thread
From: sashiko-bot @ 2026-06-08 10:37 UTC (permalink / raw)
To: AngeloGioacchino Del Regno; +Cc: neil.armstrong, linux-phy, vkoul, olteanv
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
Pre-existing issues:
- [High] The OF device node assigned to the newly allocated SPMI device does not have its reference count incremented, creating a potential use-after-free condition when the iterator macro automatically drops the reference.
--
commit eb2ded032315a7ba1f8c878f6e0a10db80cf0346
Author: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
spmi: Print error status with %pe format
This commit updates error messages in the SPMI driver to use the %pe format
specifier for printing error statuses instead of printing integer error codes.
> diff --git a/drivers/spmi/spmi.c b/drivers/spmi/spmi.c
> index e93fc2c957590..95db19a0a44ec 100644
> --- a/drivers/spmi/spmi.c
> +++ b/drivers/spmi/spmi.c
[ ... ]
> @@ -522,7 +522,7 @@ static void of_spmi_register_devices(struct spmi_controller *ctrl)
> err = spmi_device_add(sdev);
> if (err) {
> dev_err(&sdev->dev,
> - "failure adding device. status %d\n", err);
> + "failure adding device. status %pe\n", ERR_PTR(err));
[Severity: High]
This is a pre-existing issue, but I noticed a potential use-after-free
condition with the OF node reference counting.
In drivers/spmi/spmi.c:of_spmi_register_devices(), the
for_each_available_child_of_node() loop iterates through child nodes,
automatically calling of_node_put() on the previous node when advancing.
Inside the loop, the node is assigned to the SPMI device:
device_set_node(&sdev->dev, of_fwnode_handle(node));
Does this assignment need to invoke of_node_get() to increment the node's
reference count? Without it, when the loop advances, the node's reference
is dropped, leaving sdev->dev.of_node as a dangling pointer.
If the device tree node is dynamically managed (e.g., via DT overlays),
unloading the overlay will free the node, causing a use-after-free whenever
the active SPMI device later accesses its of_node.
Additionally, drivers/spmi/spmi.c:spmi_dev_release() lacks an of_node_put()
to balance the required reference:
static void spmi_dev_release(struct device *dev)
{
struct spmi_device *sdev = to_spmi_device(dev);
kfree(sdev);
}
Should spmi_dev_release() be updated to safely release the reference once
it is correctly obtained?
> spmi_device_put(sdev);
> }
> }
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260608100949.36309-1-angelogioacchino.delregno@collabora.com?part=2
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply [flat|nested] 19+ messages in thread* Re: [PATCH v9 02/10] spmi: Print error status with %pe format
2026-06-08 10:37 ` sashiko-bot
@ 2026-06-08 11:29 ` AngeloGioacchino Del Regno
0 siblings, 0 replies; 19+ messages in thread
From: AngeloGioacchino Del Regno @ 2026-06-08 11:29 UTC (permalink / raw)
To: sashiko-reviews; +Cc: neil.armstrong, linux-phy, vkoul, olteanv
On 6/8/26 12:37, sashiko-bot@kernel.org wrote:
> Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
>
> Pre-existing issues:
> - [High] The OF device node assigned to the newly allocated SPMI device does not have its reference count incremented, creating a potential use-after-free condition when the iterator macro automatically drops the reference.
> --
>
> commit eb2ded032315a7ba1f8c878f6e0a10db80cf0346
> Author: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
>
> spmi: Print error status with %pe format
>
> This commit updates error messages in the SPMI driver to use the %pe format
> specifier for printing error statuses instead of printing integer error codes.
>
>> diff --git a/drivers/spmi/spmi.c b/drivers/spmi/spmi.c
>> index e93fc2c957590..95db19a0a44ec 100644
>> --- a/drivers/spmi/spmi.c
>> +++ b/drivers/spmi/spmi.c
> [ ... ]
>> @@ -522,7 +522,7 @@ static void of_spmi_register_devices(struct spmi_controller *ctrl)
>> err = spmi_device_add(sdev);
>> if (err) {
>> dev_err(&sdev->dev,
>> - "failure adding device. status %d\n", err);
>> + "failure adding device. status %pe\n", ERR_PTR(err));
>
> [Severity: High]
> This is a pre-existing issue, but I noticed a potential use-after-free
> condition with the OF node reference counting.
>
> In drivers/spmi/spmi.c:of_spmi_register_devices(), the
> for_each_available_child_of_node() loop iterates through child nodes,
> automatically calling of_node_put() on the previous node when advancing.
>
> Inside the loop, the node is assigned to the SPMI device:
>
> device_set_node(&sdev->dev, of_fwnode_handle(node));
>
> Does this assignment need to invoke of_node_get() to increment the node's
> reference count? Without it, when the loop advances, the node's reference
> is dropped, leaving sdev->dev.of_node as a dangling pointer.
>
> If the device tree node is dynamically managed (e.g., via DT overlays),
> unloading the overlay will free the node, causing a use-after-free whenever
> the active SPMI device later accesses its of_node.
>
> Additionally, drivers/spmi/spmi.c:spmi_dev_release() lacks an of_node_put()
> to balance the required reference:
>
> static void spmi_dev_release(struct device *dev)
> {
> struct spmi_device *sdev = to_spmi_device(dev);
>
> kfree(sdev);
> }
>
> Should spmi_dev_release() be updated to safely release the reference once
> it is correctly obtained?
>
>> spmi_device_put(sdev);
>> }
>> }
>
Although very unlikely to happen at this moment in time, this is a valid concern.
It's out of scope for this series - so I will send a fix separately.
This should not block this series.
Cheers,
Angelo
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply [flat|nested] 19+ messages in thread
* [PATCH v9 03/10] spmi: Remove unneeded goto in spmi_device_add() error path
2026-06-08 10:09 [PATCH v9 00/10] SPMI: Implement sub-devices and migrate drivers AngeloGioacchino Del Regno
2026-06-08 10:09 ` [PATCH v9 01/10] spmi: Remove redundant dev_name() print in spmi_device_add() AngeloGioacchino Del Regno
2026-06-08 10:09 ` [PATCH v9 02/10] spmi: Print error status with %pe format AngeloGioacchino Del Regno
@ 2026-06-08 10:09 ` AngeloGioacchino Del Regno
2026-06-08 10:09 ` [PATCH v9 04/10] spmi: Implement spmi_subdevice_alloc_and_add() and devm variant AngeloGioacchino Del Regno
` (6 subsequent siblings)
9 siblings, 0 replies; 19+ messages in thread
From: AngeloGioacchino Del Regno @ 2026-06-08 10:09 UTC (permalink / raw)
To: jic23
Cc: dlechner, nuno.sa, andy, arnd, gregkh, srini, vkoul,
neil.armstrong, sre, sboyd, angelogioacchino.delregno, krzk,
dmitry.baryshkov, quic_wcheng, melody.olvera, quic_nsekar,
ivo.ivanov.ivanov1, abelvesa, luca.weiss, konrad.dybcio,
mitltlatltl, krishna.kurapati, linux-arm-msm, linux-iio,
linux-kernel, linux-phy, linux-pm, kernel, Andy Shevchenko
If any error happens during device_add() just return inside of the
conditional, as the goto path doesn't do anything else if not just
returning.
While at it, to improve readability, also change this function to
explicitly return 0 (for success) at the end.
Acked-by: Stephen Boyd <sboyd@kernel.org>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@intel.com>
Signed-off-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
---
drivers/spmi/spmi.c | 6 ++----
1 file changed, 2 insertions(+), 4 deletions(-)
diff --git a/drivers/spmi/spmi.c b/drivers/spmi/spmi.c
index b0017bd61d95..0f32f099b0ce 100644
--- a/drivers/spmi/spmi.c
+++ b/drivers/spmi/spmi.c
@@ -69,13 +69,11 @@ int spmi_device_add(struct spmi_device *sdev)
err = device_add(&sdev->dev);
if (err < 0) {
dev_err(&sdev->dev, "Can't add device, status %pe\n", ERR_PTR(err));
- goto err_device_add;
+ return err;
}
dev_dbg(&sdev->dev, "device registered\n");
-
-err_device_add:
- return err;
+ return 0;
}
EXPORT_SYMBOL_GPL(spmi_device_add);
--
2.54.0
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply related [flat|nested] 19+ messages in thread* [PATCH v9 04/10] spmi: Implement spmi_subdevice_alloc_and_add() and devm variant
2026-06-08 10:09 [PATCH v9 00/10] SPMI: Implement sub-devices and migrate drivers AngeloGioacchino Del Regno
` (2 preceding siblings ...)
2026-06-08 10:09 ` [PATCH v9 03/10] spmi: Remove unneeded goto in spmi_device_add() error path AngeloGioacchino Del Regno
@ 2026-06-08 10:09 ` AngeloGioacchino Del Regno
2026-06-08 10:43 ` sashiko-bot
2026-06-08 10:09 ` [PATCH v9 05/10] nvmem: qcom-spmi-sdam: Migrate to devm_spmi_subdevice_alloc_and_add() AngeloGioacchino Del Regno
` (5 subsequent siblings)
9 siblings, 1 reply; 19+ messages in thread
From: AngeloGioacchino Del Regno @ 2026-06-08 10:09 UTC (permalink / raw)
To: jic23
Cc: dlechner, nuno.sa, andy, arnd, gregkh, srini, vkoul,
neil.armstrong, sre, sboyd, angelogioacchino.delregno, krzk,
dmitry.baryshkov, quic_wcheng, melody.olvera, quic_nsekar,
ivo.ivanov.ivanov1, abelvesa, luca.weiss, konrad.dybcio,
mitltlatltl, krishna.kurapati, linux-arm-msm, linux-iio,
linux-kernel, linux-phy, linux-pm, kernel, Jonathan Cameron,
Andy Shevchenko
Some devices connected over the SPMI bus may be big, in the sense
that those may be a complex of devices managed by a single chip
over the SPMI bus, reachable through a single SID.
Add new functions aimed at managing sub-devices of a SPMI device
spmi_subdevice_alloc_and_add() and a spmi_subdevice_remove() for
adding a new subdevice and removing it respectively, and also
add their devm_* variants.
The need for such functions comes from the existence of those
complex Power Management ICs (PMICs), which feature one or many
sub-devices, in some cases with these being even addressable on
the chip in form of SPMI register ranges.
Examples of those devices can be found in both Qualcomm platforms
with their PMICs having PON, RTC, SDAM, GPIO controller, and other
sub-devices, and in newer MediaTek platforms showing similar HW
features and a similar layout with those also having many subdevs.
Also, instead of generally exporting symbols, export them with a
new "SPMI" namespace: all users will have to import this namespace
to make use of the newly introduced exports.
Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Tested-by: Neil Armstrong <neil.armstrong@linaro.org> # on SM8650-QRD
Acked-by: Stephen Boyd <sboyd@kernel.org>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@intel.com>
Signed-off-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
---
drivers/spmi/spmi-devres.c | 24 ++++++++++++
drivers/spmi/spmi.c | 78 ++++++++++++++++++++++++++++++++++++++
include/linux/spmi.h | 16 ++++++++
3 files changed, 118 insertions(+)
diff --git a/drivers/spmi/spmi-devres.c b/drivers/spmi/spmi-devres.c
index 62c4b3f24d06..c3e889fe1b6e 100644
--- a/drivers/spmi/spmi-devres.c
+++ b/drivers/spmi/spmi-devres.c
@@ -60,5 +60,29 @@ int devm_spmi_controller_add(struct device *parent, struct spmi_controller *ctrl
}
EXPORT_SYMBOL_GPL(devm_spmi_controller_add);
+static void devm_spmi_subdevice_remove(void *sub_sdev)
+{
+ spmi_subdevice_remove(sub_sdev);
+}
+
+struct spmi_subdevice *devm_spmi_subdevice_alloc_and_add(struct device *dev,
+ struct spmi_device *sparent)
+{
+ struct spmi_subdevice *sub_sdev;
+ int ret;
+
+ sub_sdev = spmi_subdevice_alloc_and_add(sparent);
+ if (IS_ERR(sub_sdev))
+ return sub_sdev;
+
+ ret = devm_add_action_or_reset(dev, devm_spmi_subdevice_remove, sub_sdev);
+ if (ret)
+ return ERR_PTR(ret);
+
+ return sub_sdev;
+}
+EXPORT_SYMBOL_NS_GPL(devm_spmi_subdevice_alloc_and_add, "SPMI");
+
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("SPMI devres helpers");
+MODULE_IMPORT_NS("SPMI");
diff --git a/drivers/spmi/spmi.c b/drivers/spmi/spmi.c
index 0f32f099b0ce..0d587248665e 100644
--- a/drivers/spmi/spmi.c
+++ b/drivers/spmi/spmi.c
@@ -19,6 +19,7 @@
static bool is_registered;
static DEFINE_IDA(ctrl_ida);
+static DEFINE_IDA(spmi_subdevice_ida);
static void spmi_dev_release(struct device *dev)
{
@@ -31,6 +32,19 @@ static const struct device_type spmi_dev_type = {
.release = spmi_dev_release,
};
+static void spmi_subdev_release(struct device *dev)
+{
+ struct spmi_device *sdev = to_spmi_device(dev);
+ struct spmi_subdevice *sub_sdev = container_of(sdev, struct spmi_subdevice, sdev);
+
+ ida_free(&spmi_subdevice_ida, sub_sdev->devid);
+ kfree(sub_sdev);
+}
+
+static const struct device_type spmi_subdev_type = {
+ .release = spmi_subdev_release,
+};
+
static void spmi_ctrl_release(struct device *dev)
{
struct spmi_controller *ctrl = to_spmi_controller(dev);
@@ -87,6 +101,18 @@ void spmi_device_remove(struct spmi_device *sdev)
}
EXPORT_SYMBOL_GPL(spmi_device_remove);
+/**
+ * spmi_subdevice_remove() - Remove an SPMI subdevice
+ * @sub_sdev: spmi_device to be removed
+ */
+void spmi_subdevice_remove(struct spmi_subdevice *sub_sdev)
+{
+ struct spmi_device *sdev = &sub_sdev->sdev;
+
+ device_unregister(&sdev->dev);
+}
+EXPORT_SYMBOL_NS_GPL(spmi_subdevice_remove, "SPMI");
+
static inline int
spmi_cmd(struct spmi_controller *ctrl, u8 opcode, u8 sid)
{
@@ -428,6 +454,58 @@ struct spmi_device *spmi_device_alloc(struct spmi_controller *ctrl)
}
EXPORT_SYMBOL_GPL(spmi_device_alloc);
+/**
+ * spmi_subdevice_alloc_and_add(): Allocate and add a new SPMI sub-device
+ * @sparent: SPMI parent device with previously registered SPMI controller
+ *
+ * Returns:
+ * Pointer to newly allocated SPMI sub-device for success or error pointer.
+ */
+struct spmi_subdevice *spmi_subdevice_alloc_and_add(struct spmi_device *sparent)
+{
+ struct spmi_subdevice *sub_sdev;
+ struct spmi_device *sdev;
+ int ret;
+
+ sub_sdev = kzalloc(sizeof(*sub_sdev), GFP_KERNEL);
+ if (!sub_sdev)
+ return ERR_PTR(-ENOMEM);
+
+ sdev = &sub_sdev->sdev;
+ sdev->ctrl = sparent->ctrl;
+ sdev->usid = sparent->usid;
+
+ ret = ida_alloc(&spmi_subdevice_ida, GFP_KERNEL);
+ if (ret < 0) {
+ kfree(sub_sdev);
+ return ERR_PTR(ret);
+ }
+ sub_sdev->devid = ret;
+
+ device_initialize(&sdev->dev);
+ sdev->dev.parent = &sparent->dev;
+ sdev->dev.bus = &spmi_bus_type;
+ sdev->dev.type = &spmi_subdev_type;
+
+ ret = dev_set_name(&sdev->dev, "%u-%02x.%d.auto",
+ sdev->ctrl->nr, sdev->usid, sub_sdev->devid);
+ if (ret)
+ goto err_put_dev;
+
+ ret = device_add(&sdev->dev);
+ if (ret) {
+ dev_err(&sdev->dev, "Can't add device, status %pe\n", ERR_PTR(ret));
+ goto err_put_dev;
+ }
+
+ return sub_sdev;
+
+err_put_dev:
+ put_device(&sdev->dev);
+ return ERR_PTR(ret);
+}
+EXPORT_SYMBOL_NS_GPL(spmi_subdevice_alloc_and_add, "SPMI");
+
/**
* spmi_controller_alloc() - Allocate a new SPMI controller
* @parent: parent device
diff --git a/include/linux/spmi.h b/include/linux/spmi.h
index 4eb9564a7fb3..a78a8924b2ac 100644
--- a/include/linux/spmi.h
+++ b/include/linux/spmi.h
@@ -69,6 +69,22 @@ int spmi_device_add(struct spmi_device *sdev);
void spmi_device_remove(struct spmi_device *sdev);
+/**
+ * struct spmi_subdevice - Basic representation of an SPMI sub-device
+ * @sdev: Sub-device representation of an SPMI device
+ * @devid: Platform Device ID of an SPMI sub-device
+ */
+struct spmi_subdevice {
+ struct spmi_device sdev;
+ unsigned int devid;
+};
+
+struct spmi_subdevice *spmi_subdevice_alloc_and_add(struct spmi_device *sparent);
+void spmi_subdevice_remove(struct spmi_subdevice *sdev);
+
+struct spmi_subdevice *devm_spmi_subdevice_alloc_and_add(struct device *dev,
+ struct spmi_device *sparent);
+
/**
* struct spmi_controller - interface to the SPMI master controller
* @dev: Driver model representation of the device.
--
2.54.0
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply related [flat|nested] 19+ messages in thread* Re: [PATCH v9 04/10] spmi: Implement spmi_subdevice_alloc_and_add() and devm variant
2026-06-08 10:09 ` [PATCH v9 04/10] spmi: Implement spmi_subdevice_alloc_and_add() and devm variant AngeloGioacchino Del Regno
@ 2026-06-08 10:43 ` sashiko-bot
2026-06-08 11:27 ` AngeloGioacchino Del Regno
0 siblings, 1 reply; 19+ messages in thread
From: sashiko-bot @ 2026-06-08 10:43 UTC (permalink / raw)
To: AngeloGioacchino Del Regno; +Cc: linux-phy, vkoul, olteanv, neil.armstrong
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Low] dev_set_name() uses the '%d' format specifier for a variable of type 'unsigned int', which will cause a -Wformat compiler warning.
--
commit 35ac69140b9b2d8a3b0e2aa01fe5f5ac3ffe4d02
Author: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
spmi: Implement spmi_subdevice_alloc_and_add() and devm variant
This commit introduces functions for managing sub-devices of an SPMI
device, including spmi_subdevice_alloc_and_add() and its devm
variant. These allow complex PMICs with multiple sub-devices to be
properly modeled and managed via the SPMI bus.
> diff --git a/drivers/spmi/spmi.c b/drivers/spmi/spmi.c
> index 91a40ea8031ad..7945cacf6d655 100644
> --- a/drivers/spmi/spmi.c
> +++ b/drivers/spmi/spmi.c
[ ... ]
> @@ -428,6 +454,58 @@ struct spmi_device *spmi_device_alloc(struct spmi_controller *ctrl)
> }
> EXPORT_SYMBOL_GPL(spmi_device_alloc);
>
> +/**
> + * spmi_subdevice_alloc_and_add(): Allocate and add a new SPMI sub-device
> + * @sparent: SPMI parent device with previously registered SPMI controller
> + *
> + * Returns:
> + * Pointer to newly allocated SPMI sub-device for success or error pointer.
> + */
> +struct spmi_subdevice *spmi_subdevice_alloc_and_add(struct spmi_device *sparent)
> +{
> + struct spmi_subdevice *sub_sdev;
> + struct spmi_device *sdev;
> + int ret;
> +
> + sub_sdev = kzalloc(sizeof(*sub_sdev), GFP_KERNEL);
> + if (!sub_sdev)
> + return ERR_PTR(-ENOMEM);
> +
> + sdev = &sub_sdev->sdev;
> + sdev->ctrl = sparent->ctrl;
> + sdev->usid = sparent->usid;
> +
> + ret = ida_alloc(&spmi_subdevice_ida, GFP_KERNEL);
> + if (ret < 0) {
> + kfree(sub_sdev);
> + return ERR_PTR(ret);
> + }
> + sub_sdev->devid = ret;
> +
> + device_initialize(&sdev->dev);
> + sdev->dev.parent = &sparent->dev;
> + sdev->dev.bus = &spmi_bus_type;
> + sdev->dev.type = &spmi_subdev_type;
> +
> + ret = dev_set_name(&sdev->dev, "%u-%02x.%d.auto",
> + sdev->ctrl->nr, sdev->usid, sub_sdev->devid);
[Severity: Low]
This isn't a bug, but should this use %u instead of %d for the format
specifier? The devid field in struct spmi_subdevice is defined as an
unsigned int, which can cause a -Wformat compiler warning here.
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260608100949.36309-1-angelogioacchino.delregno@collabora.com?part=4
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply [flat|nested] 19+ messages in thread* Re: [PATCH v9 04/10] spmi: Implement spmi_subdevice_alloc_and_add() and devm variant
2026-06-08 10:43 ` sashiko-bot
@ 2026-06-08 11:27 ` AngeloGioacchino Del Regno
0 siblings, 0 replies; 19+ messages in thread
From: AngeloGioacchino Del Regno @ 2026-06-08 11:27 UTC (permalink / raw)
To: Stephen Boyd, Jonathan Cameron
Cc: linux-phy, vkoul, olteanv, neil.armstrong, sashiko-reviews
On 6/8/26 12:43, sashiko-bot@kernel.org wrote:
> Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
> - [Low] dev_set_name() uses the '%d' format specifier for a variable of type 'unsigned int', which will cause a -Wformat compiler warning.
> --
>
> commit 35ac69140b9b2d8a3b0e2aa01fe5f5ac3ffe4d02
> Author: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
>
> spmi: Implement spmi_subdevice_alloc_and_add() and devm variant
>
> This commit introduces functions for managing sub-devices of an SPMI
> device, including spmi_subdevice_alloc_and_add() and its devm
> variant. These allow complex PMICs with multiple sub-devices to be
> properly modeled and managed via the SPMI bus.
>
>> diff --git a/drivers/spmi/spmi.c b/drivers/spmi/spmi.c
>> index 91a40ea8031ad..7945cacf6d655 100644
>> --- a/drivers/spmi/spmi.c
>> +++ b/drivers/spmi/spmi.c
>
> [ ... ]
>
>> @@ -428,6 +454,58 @@ struct spmi_device *spmi_device_alloc(struct spmi_controller *ctrl)
>> }
>> EXPORT_SYMBOL_GPL(spmi_device_alloc);
>>
>> +/**
>> + * spmi_subdevice_alloc_and_add(): Allocate and add a new SPMI sub-device
>> + * @sparent: SPMI parent device with previously registered SPMI controller
>> + *
>> + * Returns:
>> + * Pointer to newly allocated SPMI sub-device for success or error pointer.
>> + */
>> +struct spmi_subdevice *spmi_subdevice_alloc_and_add(struct spmi_device *sparent)
>> +{
>> + struct spmi_subdevice *sub_sdev;
>> + struct spmi_device *sdev;
>> + int ret;
>> +
>> + sub_sdev = kzalloc(sizeof(*sub_sdev), GFP_KERNEL);
>> + if (!sub_sdev)
>> + return ERR_PTR(-ENOMEM);
>> +
>> + sdev = &sub_sdev->sdev;
>> + sdev->ctrl = sparent->ctrl;
>> + sdev->usid = sparent->usid;
>> +
>> + ret = ida_alloc(&spmi_subdevice_ida, GFP_KERNEL);
>> + if (ret < 0) {
>> + kfree(sub_sdev);
>> + return ERR_PTR(ret);
>> + }
>> + sub_sdev->devid = ret;
>> +
>> + device_initialize(&sdev->dev);
>> + sdev->dev.parent = &sparent->dev;
>> + sdev->dev.bus = &spmi_bus_type;
>> + sdev->dev.type = &spmi_subdev_type;
>> +
>> + ret = dev_set_name(&sdev->dev, "%u-%02x.%d.auto",
>> + sdev->ctrl->nr, sdev->usid, sub_sdev->devid);
>
> [Severity: Low]
> This isn't a bug, but should this use %u instead of %d for the format
> specifier? The devid field in struct spmi_subdevice is defined as an
> unsigned int, which can cause a -Wformat compiler warning here.
>
I wonder if this can be fixed while applying please?
Thanks,
Angelo
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply [flat|nested] 19+ messages in thread
* [PATCH v9 05/10] nvmem: qcom-spmi-sdam: Migrate to devm_spmi_subdevice_alloc_and_add()
2026-06-08 10:09 [PATCH v9 00/10] SPMI: Implement sub-devices and migrate drivers AngeloGioacchino Del Regno
` (3 preceding siblings ...)
2026-06-08 10:09 ` [PATCH v9 04/10] spmi: Implement spmi_subdevice_alloc_and_add() and devm variant AngeloGioacchino Del Regno
@ 2026-06-08 10:09 ` AngeloGioacchino Del Regno
2026-06-08 10:54 ` sashiko-bot
2026-06-08 10:09 ` [PATCH v9 06/10] power: reset: qcom-pon: " AngeloGioacchino Del Regno
` (4 subsequent siblings)
9 siblings, 1 reply; 19+ messages in thread
From: AngeloGioacchino Del Regno @ 2026-06-08 10:09 UTC (permalink / raw)
To: jic23
Cc: dlechner, nuno.sa, andy, arnd, gregkh, srini, vkoul,
neil.armstrong, sre, sboyd, angelogioacchino.delregno, krzk,
dmitry.baryshkov, quic_wcheng, melody.olvera, quic_nsekar,
ivo.ivanov.ivanov1, abelvesa, luca.weiss, konrad.dybcio,
mitltlatltl, krishna.kurapati, linux-arm-msm, linux-iio,
linux-kernel, linux-phy, linux-pm, kernel, Andy Shevchenko
Some Qualcomm PMICs integrate a SDAM device, internally located in
a specific address range reachable through SPMI communication.
Instead of using the parent SPMI device (the main PMIC) as a kind
of syscon in this driver, register a new SPMI sub-device for SDAM
and initialize its own regmap with this sub-device's specific base
address, retrieved from the devicetree.
This allows to stop manually adding the register base address to
every R/W call in this driver, as this can be, and is now, handled
by the regmap API instead.
Reviewed-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Tested-by: Neil Armstrong <neil.armstrong@linaro.org> # on SM8650-QRD
Acked-by: Srinivas Kandagatla <srini@kernel.org>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@intel.com>
Signed-off-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
---
drivers/nvmem/Kconfig | 1 +
drivers/nvmem/qcom-spmi-sdam.c | 38 +++++++++++++++++++++++-----------
2 files changed, 27 insertions(+), 12 deletions(-)
diff --git a/drivers/nvmem/Kconfig b/drivers/nvmem/Kconfig
index e10f7ff725ff..cc032d60b8c1 100644
--- a/drivers/nvmem/Kconfig
+++ b/drivers/nvmem/Kconfig
@@ -380,6 +380,7 @@ config NVMEM_SNVS_LPGPR
config NVMEM_SPMI_SDAM
tristate "SPMI SDAM Support"
depends on SPMI
+ select REGMAP_SPMI
help
This driver supports the Shared Direct Access Memory Module on
Qualcomm Technologies, Inc. PMICs. It provides the clients
diff --git a/drivers/nvmem/qcom-spmi-sdam.c b/drivers/nvmem/qcom-spmi-sdam.c
index 4f1cca6eab71..4974105dd963 100644
--- a/drivers/nvmem/qcom-spmi-sdam.c
+++ b/drivers/nvmem/qcom-spmi-sdam.c
@@ -9,6 +9,7 @@
#include <linux/nvmem-provider.h>
#include <linux/platform_device.h>
#include <linux/regmap.h>
+#include <linux/spmi.h>
#define SDAM_MEM_START 0x40
#define REGISTER_MAP_ID 0x40
@@ -20,7 +21,6 @@
struct sdam_chip {
struct regmap *regmap;
struct nvmem_config sdam_config;
- unsigned int base;
unsigned int size;
};
@@ -73,7 +73,7 @@ static int sdam_read(void *priv, unsigned int offset, void *val,
return -EINVAL;
}
- rc = regmap_bulk_read(sdam->regmap, sdam->base + offset, val, bytes);
+ rc = regmap_bulk_read(sdam->regmap, offset, val, bytes);
if (rc < 0)
dev_err(dev, "Failed to read SDAM offset %#x len=%zd, rc=%d\n",
offset, bytes, rc);
@@ -100,7 +100,7 @@ static int sdam_write(void *priv, unsigned int offset, void *val,
return -EINVAL;
}
- rc = regmap_bulk_write(sdam->regmap, sdam->base + offset, val, bytes);
+ rc = regmap_bulk_write(sdam->regmap, offset, val, bytes);
if (rc < 0)
dev_err(dev, "Failed to write SDAM offset %#x len=%zd, rc=%d\n",
offset, bytes, rc);
@@ -110,8 +110,17 @@ static int sdam_write(void *priv, unsigned int offset, void *val,
static int sdam_probe(struct platform_device *pdev)
{
+ struct regmap_config sdam_regmap_config = {
+ .reg_bits = 16,
+ .val_bits = 8,
+ .max_register = 0xff,
+ .fast_io = true,
+ };
struct sdam_chip *sdam;
struct nvmem_device *nvmem;
+ struct spmi_device *sparent;
+ struct spmi_subdevice *sub_sdev;
+ struct device *dev = &pdev->dev;
unsigned int val;
int rc;
@@ -119,19 +128,23 @@ static int sdam_probe(struct platform_device *pdev)
if (!sdam)
return -ENOMEM;
- sdam->regmap = dev_get_regmap(pdev->dev.parent, NULL);
- if (!sdam->regmap) {
- dev_err(&pdev->dev, "Failed to get regmap handle\n");
- return -ENXIO;
- }
+ sparent = to_spmi_device(dev->parent);
+ sub_sdev = devm_spmi_subdevice_alloc_and_add(dev, sparent);
+ if (IS_ERR(sub_sdev))
+ return PTR_ERR(sub_sdev);
- rc = of_property_read_u32(pdev->dev.of_node, "reg", &sdam->base);
+ rc = device_property_read_u32(dev, "reg", &sdam_regmap_config.reg_base);
if (rc < 0) {
- dev_err(&pdev->dev, "Failed to get SDAM base, rc=%d\n", rc);
+ dev_err(dev, "Failed to get SDAM base, rc=%d\n", rc);
return -EINVAL;
}
- rc = regmap_read(sdam->regmap, sdam->base + SDAM_SIZE, &val);
+ sdam->regmap = devm_regmap_init_spmi_ext(&sub_sdev->sdev, &sdam_regmap_config);
+ if (IS_ERR(sdam->regmap))
+ return dev_err_probe(dev, PTR_ERR(sdam->regmap),
+ "Failed to get regmap handle\n");
+
+ rc = regmap_read(sdam->regmap, SDAM_SIZE, &val);
if (rc < 0) {
dev_err(&pdev->dev, "Failed to read SDAM_SIZE rc=%d\n", rc);
return -EINVAL;
@@ -159,7 +172,7 @@ static int sdam_probe(struct platform_device *pdev)
}
dev_dbg(&pdev->dev,
"SDAM base=%#x size=%u registered successfully\n",
- sdam->base, sdam->size);
+ sdam_regmap_config.reg_base, sdam->size);
return 0;
}
@@ -181,3 +194,4 @@ module_platform_driver(sdam_driver);
MODULE_DESCRIPTION("QCOM SPMI SDAM driver");
MODULE_LICENSE("GPL v2");
+MODULE_IMPORT_NS("SPMI");
--
2.54.0
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply related [flat|nested] 19+ messages in thread* Re: [PATCH v9 05/10] nvmem: qcom-spmi-sdam: Migrate to devm_spmi_subdevice_alloc_and_add()
2026-06-08 10:09 ` [PATCH v9 05/10] nvmem: qcom-spmi-sdam: Migrate to devm_spmi_subdevice_alloc_and_add() AngeloGioacchino Del Regno
@ 2026-06-08 10:54 ` sashiko-bot
2026-06-08 11:32 ` AngeloGioacchino Del Regno
0 siblings, 1 reply; 19+ messages in thread
From: sashiko-bot @ 2026-06-08 10:54 UTC (permalink / raw)
To: AngeloGioacchino Del Regno; +Cc: linux-phy, vkoul, neil.armstrong, olteanv
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [High] The driver blindly casts `dev->parent` to a `struct spmi_device *` without validating the parent device type, leading to a wild pointer dereference on malformed device trees.
--
commit b6b479ab20e3f2d7a7247657ca4bb0a5a70fc75a
Author: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
nvmem: qcom-spmi-sdam: Migrate to devm_spmi_subdevice_alloc_and_add()
This commit migrates the SDAM driver to use devm_spmi_subdevice_alloc_and_add().
It registers a new SPMI sub-device for SDAM and initializes a regmap with its
specific base address retrieved from the devicetree.
> diff --git a/drivers/nvmem/qcom-spmi-sdam.c b/drivers/nvmem/qcom-spmi-sdam.c
> index 4f1cca6eab71e..4974105dd9632 100644
> --- a/drivers/nvmem/qcom-spmi-sdam.c
> +++ b/drivers/nvmem/qcom-spmi-sdam.c
[ ... ]
> @@ -110,8 +110,17 @@ static int sdam_write(void *priv, unsigned int offset, void *val,
>
> static int sdam_probe(struct platform_device *pdev)
> {
[ ... ]
> struct sdam_chip *sdam;
> struct nvmem_device *nvmem;
> + struct spmi_device *sparent;
> + struct spmi_subdevice *sub_sdev;
> + struct device *dev = &pdev->dev;
> unsigned int val;
> int rc;
>
> @@ -119,19 +128,23 @@ static int sdam_probe(struct platform_device *pdev)
> if (!sdam)
> return -ENOMEM;
>
> - sdam->regmap = dev_get_regmap(pdev->dev.parent, NULL);
> - if (!sdam->regmap) {
> - dev_err(&pdev->dev, "Failed to get regmap handle\n");
> - return -ENXIO;
> - }
> + sparent = to_spmi_device(dev->parent);
> + sub_sdev = devm_spmi_subdevice_alloc_and_add(dev, sparent);
[Severity: High]
Does this code assume that the parent device is always a valid SPMI device?
If the device tree is malformed and this node is placed under a simple-bus
instead of an SPMI PMIC, the parent device will not be an spmi_device.
Because to_spmi_device() uses container_of(), this will result in a bogus
pointer.
When that bogus pointer is passed into devm_spmi_subdevice_alloc_and_add(),
does it cause a wild pointer dereference when accessing sparent->ctrl or
sparent->usid?
Prior to this patch, dev_get_regmap(pdev->dev.parent, NULL) would gracefully
return NULL for malformed hierarchies, but this change appears to introduce
a potential kernel panic.
> + if (IS_ERR(sub_sdev))
> + return PTR_ERR(sub_sdev);
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260608100949.36309-1-angelogioacchino.delregno@collabora.com?part=5
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply [flat|nested] 19+ messages in thread* Re: [PATCH v9 05/10] nvmem: qcom-spmi-sdam: Migrate to devm_spmi_subdevice_alloc_and_add()
2026-06-08 10:54 ` sashiko-bot
@ 2026-06-08 11:32 ` AngeloGioacchino Del Regno
0 siblings, 0 replies; 19+ messages in thread
From: AngeloGioacchino Del Regno @ 2026-06-08 11:32 UTC (permalink / raw)
To: sashiko-reviews; +Cc: linux-phy, vkoul, neil.armstrong, olteanv
On 6/8/26 12:54, sashiko-bot@kernel.org wrote:
> Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
> - [High] The driver blindly casts `dev->parent` to a `struct spmi_device *` without validating the parent device type, leading to a wild pointer dereference on malformed device trees.
> --
>
> commit b6b479ab20e3f2d7a7247657ca4bb0a5a70fc75a
> Author: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
>
> nvmem: qcom-spmi-sdam: Migrate to devm_spmi_subdevice_alloc_and_add()
>
> This commit migrates the SDAM driver to use devm_spmi_subdevice_alloc_and_add().
> It registers a new SPMI sub-device for SDAM and initializes a regmap with its
> specific base address retrieved from the devicetree.
>
>> diff --git a/drivers/nvmem/qcom-spmi-sdam.c b/drivers/nvmem/qcom-spmi-sdam.c
>> index 4f1cca6eab71e..4974105dd9632 100644
>> --- a/drivers/nvmem/qcom-spmi-sdam.c
>> +++ b/drivers/nvmem/qcom-spmi-sdam.c
> [ ... ]
>> @@ -110,8 +110,17 @@ static int sdam_write(void *priv, unsigned int offset, void *val,
>>
>> static int sdam_probe(struct platform_device *pdev)
>> {
> [ ... ]
>> struct sdam_chip *sdam;
>> struct nvmem_device *nvmem;
>> + struct spmi_device *sparent;
>> + struct spmi_subdevice *sub_sdev;
>> + struct device *dev = &pdev->dev;
>> unsigned int val;
>> int rc;
>>
>> @@ -119,19 +128,23 @@ static int sdam_probe(struct platform_device *pdev)
>> if (!sdam)
>> return -ENOMEM;
>>
>> - sdam->regmap = dev_get_regmap(pdev->dev.parent, NULL);
>> - if (!sdam->regmap) {
>> - dev_err(&pdev->dev, "Failed to get regmap handle\n");
>> - return -ENXIO;
>> - }
>> + sparent = to_spmi_device(dev->parent);
>> + sub_sdev = devm_spmi_subdevice_alloc_and_add(dev, sparent);
>
> [Severity: High]
> Does this code assume that the parent device is always a valid SPMI device?
>
Yes - and that's ok, because this device cannot exist outside of SPMI and will
never be registered on its own without a SPMI parent.
Overcautious coding bloats drivers for no reason.
> If the device tree is malformed and this node is placed under a simple-bus
> instead of an SPMI PMIC, the parent device will not be an spmi_device.
> Because to_spmi_device() uses container_of(), this will result in a bogus
> pointer.
>
> When that bogus pointer is passed into devm_spmi_subdevice_alloc_and_add(),
> does it cause a wild pointer dereference when accessing sparent->ctrl or
> sparent->usid?
>
> Prior to this patch, dev_get_regmap(pdev->dev.parent, NULL) would gracefully
> return NULL for malformed hierarchies, but this change appears to introduce
> a potential kernel panic.
>
>> + if (IS_ERR(sub_sdev))
>> + return PTR_ERR(sub_sdev);
>
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply [flat|nested] 19+ messages in thread
* [PATCH v9 06/10] power: reset: qcom-pon: Migrate to devm_spmi_subdevice_alloc_and_add()
2026-06-08 10:09 [PATCH v9 00/10] SPMI: Implement sub-devices and migrate drivers AngeloGioacchino Del Regno
` (4 preceding siblings ...)
2026-06-08 10:09 ` [PATCH v9 05/10] nvmem: qcom-spmi-sdam: Migrate to devm_spmi_subdevice_alloc_and_add() AngeloGioacchino Del Regno
@ 2026-06-08 10:09 ` AngeloGioacchino Del Regno
2026-06-08 10:09 ` [PATCH v9 07/10] phy: qualcomm: eusb2-repeater: " AngeloGioacchino Del Regno
` (3 subsequent siblings)
9 siblings, 0 replies; 19+ messages in thread
From: AngeloGioacchino Del Regno @ 2026-06-08 10:09 UTC (permalink / raw)
To: jic23
Cc: dlechner, nuno.sa, andy, arnd, gregkh, srini, vkoul,
neil.armstrong, sre, sboyd, angelogioacchino.delregno, krzk,
dmitry.baryshkov, quic_wcheng, melody.olvera, quic_nsekar,
ivo.ivanov.ivanov1, abelvesa, luca.weiss, konrad.dybcio,
mitltlatltl, krishna.kurapati, linux-arm-msm, linux-iio,
linux-kernel, linux-phy, linux-pm, kernel, Sebastian Reichel,
Andy Shevchenko
Some Qualcomm PMICs integrates a Power On device supporting pwrkey
and resin along with the Android reboot reason action identifier.
Instead of using the parent SPMI device (the main PMIC) as a kind
of syscon in this driver, register a new SPMI sub-device for PON
and initialize its own regmap with this sub-device's specific base
address, retrieved from the devicetree.
This allows to stop manually adding the register base address to
every R/W call in this driver, as this can be, and is now, handled
by the regmap API instead.
Reviewed-by: Sebastian Reichel <sebastian.reichel@collabora.com>
Tested-by: Neil Armstrong <neil.armstrong@linaro.org> # on SM8650-QRD
Reviewed-by: Andy Shevchenko <andriy.shevchenko@intel.com>
Signed-off-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
---
drivers/power/reset/qcom-pon.c | 33 ++++++++++++++++++++++++---------
1 file changed, 24 insertions(+), 9 deletions(-)
diff --git a/drivers/power/reset/qcom-pon.c b/drivers/power/reset/qcom-pon.c
index 7e108982a582..182af188c9be 100644
--- a/drivers/power/reset/qcom-pon.c
+++ b/drivers/power/reset/qcom-pon.c
@@ -11,6 +11,7 @@
#include <linux/reboot.h>
#include <linux/reboot-mode.h>
#include <linux/regmap.h>
+#include <linux/spmi.h>
#define PON_SOFT_RB_SPARE 0x8f
@@ -22,7 +23,6 @@
struct qcom_pon {
struct device *dev;
struct regmap *regmap;
- u32 baseaddr;
struct reboot_mode_driver reboot_mode;
long reason_shift;
};
@@ -35,7 +35,7 @@ static int qcom_pon_reboot_mode_write(struct reboot_mode_driver *reboot,
int ret;
ret = regmap_update_bits(pon->regmap,
- pon->baseaddr + PON_SOFT_RB_SPARE,
+ PON_SOFT_RB_SPARE,
GENMASK(7, pon->reason_shift),
magic << pon->reason_shift);
if (ret < 0)
@@ -46,27 +46,41 @@ static int qcom_pon_reboot_mode_write(struct reboot_mode_driver *reboot,
static int qcom_pon_probe(struct platform_device *pdev)
{
+ struct regmap_config qcom_pon_regmap_config = {
+ .reg_bits = 16,
+ .val_bits = 8,
+ .max_register = 0xff,
+ .fast_io = true,
+ };
+ struct device *dev = &pdev->dev;
+ struct spmi_subdevice *sub_sdev;
+ struct spmi_device *sparent;
struct qcom_pon *pon;
long reason_shift;
int error;
+ if (!dev->parent)
+ return -ENODEV;
+
pon = devm_kzalloc(&pdev->dev, sizeof(*pon), GFP_KERNEL);
if (!pon)
return -ENOMEM;
pon->dev = &pdev->dev;
- pon->regmap = dev_get_regmap(pdev->dev.parent, NULL);
- if (!pon->regmap) {
- dev_err(&pdev->dev, "failed to locate regmap\n");
- return -ENODEV;
- }
+ sparent = to_spmi_device(dev->parent);
+ sub_sdev = devm_spmi_subdevice_alloc_and_add(dev, sparent);
+ if (IS_ERR(sub_sdev))
+ return PTR_ERR(sub_sdev);
- error = of_property_read_u32(pdev->dev.of_node, "reg",
- &pon->baseaddr);
+ error = device_property_read_u32(dev, "reg", &qcom_pon_regmap_config.reg_base);
if (error)
return error;
+ pon->regmap = devm_regmap_init_spmi_ext(&sub_sdev->sdev, &qcom_pon_regmap_config);
+ if (IS_ERR(pon->regmap))
+ return PTR_ERR(pon->regmap);
+
reason_shift = (long)of_device_get_match_data(&pdev->dev);
if (reason_shift != NO_REASON_SHIFT) {
@@ -106,3 +120,4 @@ module_platform_driver(qcom_pon_driver);
MODULE_DESCRIPTION("Qualcomm Power On driver");
MODULE_LICENSE("GPL v2");
+MODULE_IMPORT_NS("SPMI");
--
2.54.0
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply related [flat|nested] 19+ messages in thread* [PATCH v9 07/10] phy: qualcomm: eusb2-repeater: Migrate to devm_spmi_subdevice_alloc_and_add()
2026-06-08 10:09 [PATCH v9 00/10] SPMI: Implement sub-devices and migrate drivers AngeloGioacchino Del Regno
` (5 preceding siblings ...)
2026-06-08 10:09 ` [PATCH v9 06/10] power: reset: qcom-pon: " AngeloGioacchino Del Regno
@ 2026-06-08 10:09 ` AngeloGioacchino Del Regno
2026-06-08 10:09 ` [PATCH v9 08/10] misc: qcom-coincell: " AngeloGioacchino Del Regno
` (2 subsequent siblings)
9 siblings, 0 replies; 19+ messages in thread
From: AngeloGioacchino Del Regno @ 2026-06-08 10:09 UTC (permalink / raw)
To: jic23
Cc: dlechner, nuno.sa, andy, arnd, gregkh, srini, vkoul,
neil.armstrong, sre, sboyd, angelogioacchino.delregno, krzk,
dmitry.baryshkov, quic_wcheng, melody.olvera, quic_nsekar,
ivo.ivanov.ivanov1, abelvesa, luca.weiss, konrad.dybcio,
mitltlatltl, krishna.kurapati, linux-arm-msm, linux-iio,
linux-kernel, linux-phy, linux-pm, kernel, Abel Vesa,
Andy Shevchenko
Some Qualcomm PMICs integrate an USB Repeater device, used to
convert between eUSB2 and USB 2.0 signaling levels, reachable
in a specific address range over SPMI.
Instead of using the parent SPMI device (the main PMIC) as a kind
of syscon in this driver, register a new SPMI sub-device for EUSB2
and initialize its own regmap with this sub-device's specific base
address, retrieved from the devicetree.
This allows to stop manually adding the register base address to
every R/W call in this driver, as this can be, and is now, handled
by the regmap API instead.
Tested-by: Neil Armstrong <neil.armstrong@linaro.org> # on SM8650-QRD
Reviewed-by: Abel Vesa <abel.vesa@linaro.org>
Acked-by: Vinod Koul <vkoul@kernel.org>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@intel.com>
Signed-off-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
---
drivers/phy/qualcomm/Kconfig | 2 +
.../phy/qualcomm/phy-qcom-eusb2-repeater.c | 54 +++++++++++--------
2 files changed, 35 insertions(+), 21 deletions(-)
diff --git a/drivers/phy/qualcomm/Kconfig b/drivers/phy/qualcomm/Kconfig
index 60a0ead127fa..902a788f35f1 100644
--- a/drivers/phy/qualcomm/Kconfig
+++ b/drivers/phy/qualcomm/Kconfig
@@ -128,7 +128,9 @@ config PHY_QCOM_QUSB2
config PHY_QCOM_EUSB2_REPEATER
tristate "Qualcomm PMIC eUSB2 Repeater Driver"
depends on OF && (ARCH_QCOM || COMPILE_TEST)
+ depends on SPMI
select GENERIC_PHY
+ select REGMAP_SPMI
help
Enable support for the USB high-speed eUSB2 repeater on Qualcomm
PMICs. The repeater is paired with a Synopsys or M31 eUSB2 Phy
diff --git a/drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c b/drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c
index efeec4709a15..878ae03f70af 100644
--- a/drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c
+++ b/drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c
@@ -9,6 +9,7 @@
#include <linux/regmap.h>
#include <linux/of.h>
#include <linux/phy/phy.h>
+#include <linux/spmi.h>
/* eUSB2 status registers */
#define EUSB2_RPTR_STATUS 0x08
@@ -66,7 +67,6 @@ struct eusb2_repeater {
struct phy *phy;
struct regulator_bulk_data *vregs;
const struct eusb2_repeater_cfg *cfg;
- u32 base;
enum phy_mode mode;
};
@@ -143,7 +143,6 @@ static int eusb2_repeater_init(struct phy *phy)
struct eusb2_repeater *rptr = phy_get_drvdata(phy);
struct device_node *np = rptr->dev->of_node;
struct regmap *regmap = rptr->regmap;
- u32 base = rptr->base;
u32 poll_val;
s32 dt_val;
int ret;
@@ -154,37 +153,37 @@ static int eusb2_repeater_init(struct phy *phy)
if (ret)
return ret;
- regmap_write(regmap, base + EUSB2_EN_CTL1, EUSB2_RPTR_EN);
+ regmap_write(regmap, EUSB2_EN_CTL1, EUSB2_RPTR_EN);
/* Write registers from init table */
for (int i = 0; i < rptr->cfg->init_tbl_num; i++)
- regmap_write(regmap, base + rptr->cfg->init_tbl[i].reg,
+ regmap_write(regmap, rptr->cfg->init_tbl[i].reg,
rptr->cfg->init_tbl[i].value);
/* Override registers from devicetree values */
if (!of_property_read_u8(np, "qcom,tune-usb2-preem", &val))
- regmap_write(regmap, base + EUSB2_TUNE_USB2_PREEM, val);
+ regmap_write(regmap, EUSB2_TUNE_USB2_PREEM, val);
if (!of_property_read_u8(np, "qcom,tune-usb2-disc-thres", &val))
- regmap_write(regmap, base + EUSB2_TUNE_HSDISC, val);
+ regmap_write(regmap, EUSB2_TUNE_HSDISC, val);
if (!of_property_read_u8(np, "qcom,tune-usb2-amplitude", &val))
- regmap_write(regmap, base + EUSB2_TUNE_IUSB2, val);
+ regmap_write(regmap, EUSB2_TUNE_IUSB2, val);
if (!of_property_read_u8(np, "qcom,tune-res-fsdif", &val))
- regmap_write(regmap, base + EUSB2_TUNE_RES_FSDIF, val);
+ regmap_write(regmap, EUSB2_TUNE_RES_FSDIF, val);
if (!of_property_read_s32(np, "qcom,squelch-detector-bp", &dt_val)) {
for (i = 0; i < ARRAY_SIZE(squelch_detector); i++) {
if (squelch_detector[i] == dt_val) {
- regmap_write(regmap, base + EUSB2_TUNE_SQUELCH_U, i);
+ regmap_write(regmap, EUSB2_TUNE_SQUELCH_U, i);
break;
}
}
}
/* Wait for status OK */
- ret = regmap_read_poll_timeout(regmap, base + EUSB2_RPTR_STATUS, poll_val,
+ ret = regmap_read_poll_timeout(regmap, EUSB2_RPTR_STATUS, poll_val,
poll_val & RPTR_OK, 10, 5);
if (ret)
dev_err(rptr->dev, "initialization timed-out\n");
@@ -197,7 +196,6 @@ static int eusb2_repeater_set_mode(struct phy *phy,
{
struct eusb2_repeater *rptr = phy_get_drvdata(phy);
struct regmap *regmap = rptr->regmap;
- u32 base = rptr->base;
switch (mode) {
case PHY_MODE_USB_HOST:
@@ -206,8 +204,8 @@ static int eusb2_repeater_set_mode(struct phy *phy,
* per eUSB 1.2 Spec. Below implement software workaround until
* PHY and controller is fixing seen observation.
*/
- regmap_write(regmap, base + EUSB2_FORCE_EN_5, F_CLK_19P2M_EN);
- regmap_write(regmap, base + EUSB2_FORCE_VAL_5, V_CLK_19P2M_EN);
+ regmap_write(regmap, EUSB2_FORCE_EN_5, F_CLK_19P2M_EN);
+ regmap_write(regmap, EUSB2_FORCE_VAL_5, V_CLK_19P2M_EN);
break;
case PHY_MODE_USB_DEVICE:
/*
@@ -216,8 +214,8 @@ static int eusb2_repeater_set_mode(struct phy *phy,
* repeater doesn't clear previous value due to shared
* regulators (say host <-> device mode switch).
*/
- regmap_write(regmap, base + EUSB2_FORCE_EN_5, 0);
- regmap_write(regmap, base + EUSB2_FORCE_VAL_5, 0);
+ regmap_write(regmap, EUSB2_FORCE_EN_5, 0);
+ regmap_write(regmap, EUSB2_FORCE_VAL_5, 0);
break;
default:
return -EINVAL;
@@ -242,13 +240,23 @@ static const struct phy_ops eusb2_repeater_ops = {
static int eusb2_repeater_probe(struct platform_device *pdev)
{
+ struct regmap_config eusb2_regmap_config = {
+ .reg_bits = 16,
+ .val_bits = 8,
+ .max_register = 0xff,
+ .fast_io = true,
+ };
+ struct spmi_device *sparent;
struct eusb2_repeater *rptr;
+ struct spmi_subdevice *sub_sdev;
struct device *dev = &pdev->dev;
struct phy_provider *phy_provider;
struct device_node *np = dev->of_node;
- u32 res;
int ret;
+ if (!dev->parent)
+ return -ENODEV;
+
rptr = devm_kzalloc(dev, sizeof(*rptr), GFP_KERNEL);
if (!rptr)
return -ENOMEM;
@@ -260,15 +268,18 @@ static int eusb2_repeater_probe(struct platform_device *pdev)
if (!rptr->cfg)
return -EINVAL;
- rptr->regmap = dev_get_regmap(dev->parent, NULL);
- if (!rptr->regmap)
- return -ENODEV;
+ sparent = to_spmi_device(dev->parent);
+ sub_sdev = devm_spmi_subdevice_alloc_and_add(dev, sparent);
+ if (IS_ERR(sub_sdev))
+ return PTR_ERR(sub_sdev);
- ret = of_property_read_u32(np, "reg", &res);
+ ret = device_property_read_u32(dev, "reg", &eusb2_regmap_config.reg_base);
if (ret < 0)
return ret;
- rptr->base = res;
+ rptr->regmap = devm_regmap_init_spmi_ext(&sub_sdev->sdev, &eusb2_regmap_config);
+ if (IS_ERR(rptr->regmap))
+ return PTR_ERR(rptr->regmap);
ret = eusb2_repeater_init_vregs(rptr);
if (ret < 0) {
@@ -335,3 +346,4 @@ module_platform_driver(eusb2_repeater_driver);
MODULE_DESCRIPTION("Qualcomm PMIC eUSB2 Repeater driver");
MODULE_LICENSE("GPL");
+MODULE_IMPORT_NS("SPMI");
--
2.54.0
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply related [flat|nested] 19+ messages in thread* [PATCH v9 08/10] misc: qcom-coincell: Migrate to devm_spmi_subdevice_alloc_and_add()
2026-06-08 10:09 [PATCH v9 00/10] SPMI: Implement sub-devices and migrate drivers AngeloGioacchino Del Regno
` (6 preceding siblings ...)
2026-06-08 10:09 ` [PATCH v9 07/10] phy: qualcomm: eusb2-repeater: " AngeloGioacchino Del Regno
@ 2026-06-08 10:09 ` AngeloGioacchino Del Regno
2026-06-08 11:09 ` sashiko-bot
2026-06-08 10:09 ` [PATCH v9 09/10] iio: adc: qcom-spmi-iadc: " AngeloGioacchino Del Regno
2026-06-08 10:09 ` [PATCH v9 10/10] iio: adc: qcom-spmi-iadc: Remove regmap R/W wrapper functions AngeloGioacchino Del Regno
9 siblings, 1 reply; 19+ messages in thread
From: AngeloGioacchino Del Regno @ 2026-06-08 10:09 UTC (permalink / raw)
To: jic23
Cc: dlechner, nuno.sa, andy, arnd, gregkh, srini, vkoul,
neil.armstrong, sre, sboyd, angelogioacchino.delregno, krzk,
dmitry.baryshkov, quic_wcheng, melody.olvera, quic_nsekar,
ivo.ivanov.ivanov1, abelvesa, luca.weiss, konrad.dybcio,
mitltlatltl, krishna.kurapati, linux-arm-msm, linux-iio,
linux-kernel, linux-phy, linux-pm, kernel, Andy Shevchenko
Some Qualcomm PMICs integrate a charger for coincells, usually
powering an RTC when external (or main battery) power is missing.
Instead of using the parent SPMI device (the main PMIC) as a kind
of syscon in this driver, register a new SPMI sub-device and
initialize its own regmap with this sub-device's specific base
address, retrieved from the devicetree.
This allows to stop manually adding the register base address to
every R/W call in this driver, as this can be, and is now, handled
by the regmap API instead.
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Tested-by: Neil Armstrong <neil.armstrong@linaro.org> # on SM8650-QRD
Reviewed-by: Andy Shevchenko <andriy.shevchenko@intel.com>
Signed-off-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
---
drivers/misc/Kconfig | 2 ++
drivers/misc/qcom-coincell.c | 45 +++++++++++++++++++++++++-----------
2 files changed, 34 insertions(+), 13 deletions(-)
diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig
index 390256ed91f4..90947c015179 100644
--- a/drivers/misc/Kconfig
+++ b/drivers/misc/Kconfig
@@ -291,6 +291,8 @@ config HP_ILO
config QCOM_COINCELL
tristate "Qualcomm coincell charger support"
depends on MFD_SPMI_PMIC || COMPILE_TEST
+ depends on SPMI
+ select REGMAP_SPMI
help
This driver supports the coincell block found inside of
Qualcomm PMICs. The coincell charger provides a means to
diff --git a/drivers/misc/qcom-coincell.c b/drivers/misc/qcom-coincell.c
index 3c57f7429147..b0904f441300 100644
--- a/drivers/misc/qcom-coincell.c
+++ b/drivers/misc/qcom-coincell.c
@@ -9,11 +9,11 @@
#include <linux/of.h>
#include <linux/regmap.h>
#include <linux/platform_device.h>
+#include <linux/spmi.h>
struct qcom_coincell {
struct device *dev;
struct regmap *regmap;
- u32 base_addr;
};
#define QCOM_COINCELL_REG_RSET 0x44
@@ -35,7 +35,7 @@ static int qcom_coincell_chgr_config(struct qcom_coincell *chgr, int rset,
/* if disabling, just do that and skip other operations */
if (!enable)
return regmap_write(chgr->regmap,
- chgr->base_addr + QCOM_COINCELL_REG_ENABLE, 0);
+ QCOM_COINCELL_REG_ENABLE, 0);
/* find index for current-limiting resistor */
for (i = 0; i < ARRAY_SIZE(qcom_rset_map); i++)
@@ -58,7 +58,7 @@ static int qcom_coincell_chgr_config(struct qcom_coincell *chgr, int rset,
}
rc = regmap_write(chgr->regmap,
- chgr->base_addr + QCOM_COINCELL_REG_RSET, i);
+ QCOM_COINCELL_REG_RSET, i);
if (rc) {
/*
* This is mainly to flag a bad base_addr (reg) from dts.
@@ -71,37 +71,55 @@ static int qcom_coincell_chgr_config(struct qcom_coincell *chgr, int rset,
}
rc = regmap_write(chgr->regmap,
- chgr->base_addr + QCOM_COINCELL_REG_VSET, j);
+ QCOM_COINCELL_REG_VSET, j);
if (rc)
return rc;
/* set 'enable' register */
return regmap_write(chgr->regmap,
- chgr->base_addr + QCOM_COINCELL_REG_ENABLE,
+ QCOM_COINCELL_REG_ENABLE,
QCOM_COINCELL_ENABLE);
}
static int qcom_coincell_probe(struct platform_device *pdev)
{
- struct device_node *node = pdev->dev.of_node;
+ struct regmap_config qcom_coincell_regmap_config = {
+ .reg_bits = 16,
+ .val_bits = 8,
+ .max_register = 0xff,
+ .fast_io = true,
+ };
+ struct device *dev = &pdev->dev;
+ struct device_node *node = dev->of_node;
+ struct spmi_subdevice *sub_sdev;
+ struct spmi_device *sparent;
struct qcom_coincell chgr;
u32 rset = 0;
u32 vset = 0;
bool enable;
int rc;
- chgr.dev = &pdev->dev;
+ if (!dev->parent)
+ return -ENODEV;
- chgr.regmap = dev_get_regmap(pdev->dev.parent, NULL);
- if (!chgr.regmap) {
- dev_err(chgr.dev, "Unable to get regmap\n");
- return -EINVAL;
- }
+ chgr.dev = &pdev->dev;
- rc = of_property_read_u32(node, "reg", &chgr.base_addr);
+ rc = device_property_read_u32(dev, "reg", &qcom_coincell_regmap_config.reg_base);
if (rc)
return rc;
+ sparent = to_spmi_device(dev->parent);
+ sub_sdev = devm_spmi_subdevice_alloc_and_add(dev, sparent);
+ if (IS_ERR(sub_sdev))
+ return PTR_ERR(sub_sdev);
+
+ chgr.regmap = devm_regmap_init_spmi_ext(&sub_sdev->sdev,
+ &qcom_coincell_regmap_config);
+ if (IS_ERR(chgr.regmap)) {
+ dev_err(chgr.dev, "Unable to get regmap\n");
+ return PTR_ERR(chgr.regmap);
+ }
+
enable = !of_property_read_bool(node, "qcom,charger-disable");
if (enable) {
@@ -142,3 +160,4 @@ module_platform_driver(qcom_coincell_driver);
MODULE_DESCRIPTION("Qualcomm PMIC coincell charger driver");
MODULE_LICENSE("GPL v2");
+MODULE_IMPORT_NS("SPMI");
--
2.54.0
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply related [flat|nested] 19+ messages in thread* Re: [PATCH v9 08/10] misc: qcom-coincell: Migrate to devm_spmi_subdevice_alloc_and_add()
2026-06-08 10:09 ` [PATCH v9 08/10] misc: qcom-coincell: " AngeloGioacchino Del Regno
@ 2026-06-08 11:09 ` sashiko-bot
2026-06-08 11:32 ` AngeloGioacchino Del Regno
0 siblings, 1 reply; 19+ messages in thread
From: sashiko-bot @ 2026-06-08 11:09 UTC (permalink / raw)
To: AngeloGioacchino Del Regno; +Cc: neil.armstrong, vkoul, olteanv, linux-phy
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [High] Unsafe downcast of `dev->parent` to `struct spmi_device` causing out-of-bounds read and kernel panic
--
commit eb0fe105cd38bff6269804925b90232e1c422522
Author: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
misc: qcom-coincell: Migrate to devm_spmi_subdevice_alloc_and_add()
This commit updates the qcom-coincell driver to use a dedicated SPMI
sub-device instead of fetching the regmap from its parent. It creates the
sub-device using the parent device and initializes a specific regmap to
handle the base address offsets automatically.
> diff --git a/drivers/misc/qcom-coincell.c b/drivers/misc/qcom-coincell.c
> index 3c57f74291476..b0904f441300c 100644
> --- a/drivers/misc/qcom-coincell.c
> +++ b/drivers/misc/qcom-coincell.c
> @@ -71,37 +71,55 @@ static int qcom_coincell_probe(struct platform_device *pdev)
[ ... ]
> - rc = of_property_read_u32(node, "reg", &chgr.base_addr);
> + rc = device_property_read_u32(dev, "reg", &qcom_coincell_regmap_config.reg_base);
> if (rc)
> return rc;
>
> + sparent = to_spmi_device(dev->parent);
> + sub_sdev = devm_spmi_subdevice_alloc_and_add(dev, sparent);
[Severity: High]
Could this lead to a panic if the parent device is not actually an SPMI
device?
If this driver is bound to a device whose parent is a regular platform
device (for example, via a malformed device tree or a manual sysfs bind),
dev->parent will not point to a valid spmi_device.
Because to_spmi_device() is a container_of cast, it will blindly cast the
parent device. When passed to devm_spmi_subdevice_alloc_and_add(), the
underlying spmi_subdevice_alloc_and_add() function reads sparent->ctrl:
drivers/spmi/spmi.c:spmi_subdevice_alloc_and_add() {
...
sdev->ctrl = sparent->ctrl;
...
}
Since the parent is actually a platform_device, this ends up reading the
memory offset corresponding to platform_dma_mask instead of a valid ctrl
pointer. Later regmap initialization will dereference this invalid pointer,
causing an out-of-bounds read.
The previous dev_get_regmap() approach avoided this by safely searching the
parent's devres list without relying on a structural cast. Is there a way to
verify the parent device type before casting?
> + if (IS_ERR(sub_sdev))
> + return PTR_ERR(sub_sdev);
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260608100949.36309-1-angelogioacchino.delregno@collabora.com?part=8
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply [flat|nested] 19+ messages in thread* Re: [PATCH v9 08/10] misc: qcom-coincell: Migrate to devm_spmi_subdevice_alloc_and_add()
2026-06-08 11:09 ` sashiko-bot
@ 2026-06-08 11:32 ` AngeloGioacchino Del Regno
0 siblings, 0 replies; 19+ messages in thread
From: AngeloGioacchino Del Regno @ 2026-06-08 11:32 UTC (permalink / raw)
To: sashiko-reviews; +Cc: neil.armstrong, vkoul, olteanv, linux-phy
On 6/8/26 13:09, sashiko-bot@kernel.org wrote:
> Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
> - [High] Unsafe downcast of `dev->parent` to `struct spmi_device` causing out-of-bounds read and kernel panic
> --
>
> commit eb0fe105cd38bff6269804925b90232e1c422522
> Author: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
>
> misc: qcom-coincell: Migrate to devm_spmi_subdevice_alloc_and_add()
>
> This commit updates the qcom-coincell driver to use a dedicated SPMI
> sub-device instead of fetching the regmap from its parent. It creates the
> sub-device using the parent device and initializes a specific regmap to
> handle the base address offsets automatically.
>
>> diff --git a/drivers/misc/qcom-coincell.c b/drivers/misc/qcom-coincell.c
>> index 3c57f74291476..b0904f441300c 100644
>> --- a/drivers/misc/qcom-coincell.c
>> +++ b/drivers/misc/qcom-coincell.c
>> @@ -71,37 +71,55 @@ static int qcom_coincell_probe(struct platform_device *pdev)
> [ ... ]
>> - rc = of_property_read_u32(node, "reg", &chgr.base_addr);
>> + rc = device_property_read_u32(dev, "reg", &qcom_coincell_regmap_config.reg_base);
>> if (rc)
>> return rc;
>>
>> + sparent = to_spmi_device(dev->parent);
>> + sub_sdev = devm_spmi_subdevice_alloc_and_add(dev, sparent);
>
> [Severity: High]
> Could this lead to a panic if the parent device is not actually an SPMI
> device?
>
> If this driver is bound to a device whose parent is a regular platform
> device (for example, via a malformed device tree or a manual sysfs bind),
> dev->parent will not point to a valid spmi_device.
>
This device cannot exist outside of SPMI and will never be registered on its
own without a SPMI parent.
Overcautious coding bloats drivers for no reason, so this is fine.
> Because to_spmi_device() is a container_of cast, it will blindly cast the
> parent device. When passed to devm_spmi_subdevice_alloc_and_add(), the
> underlying spmi_subdevice_alloc_and_add() function reads sparent->ctrl:
>
> drivers/spmi/spmi.c:spmi_subdevice_alloc_and_add() {
> ...
> sdev->ctrl = sparent->ctrl;
> ...
> }
>
> Since the parent is actually a platform_device, this ends up reading the
> memory offset corresponding to platform_dma_mask instead of a valid ctrl
> pointer. Later regmap initialization will dereference this invalid pointer,
> causing an out-of-bounds read.
>
> The previous dev_get_regmap() approach avoided this by safely searching the
> parent's devres list without relying on a structural cast. Is there a way to
> verify the parent device type before casting?
>
>> + if (IS_ERR(sub_sdev))
>> + return PTR_ERR(sub_sdev);
>
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply [flat|nested] 19+ messages in thread
* [PATCH v9 09/10] iio: adc: qcom-spmi-iadc: Migrate to devm_spmi_subdevice_alloc_and_add()
2026-06-08 10:09 [PATCH v9 00/10] SPMI: Implement sub-devices and migrate drivers AngeloGioacchino Del Regno
` (7 preceding siblings ...)
2026-06-08 10:09 ` [PATCH v9 08/10] misc: qcom-coincell: " AngeloGioacchino Del Regno
@ 2026-06-08 10:09 ` AngeloGioacchino Del Regno
2026-06-08 10:09 ` [PATCH v9 10/10] iio: adc: qcom-spmi-iadc: Remove regmap R/W wrapper functions AngeloGioacchino Del Regno
9 siblings, 0 replies; 19+ messages in thread
From: AngeloGioacchino Del Regno @ 2026-06-08 10:09 UTC (permalink / raw)
To: jic23
Cc: dlechner, nuno.sa, andy, arnd, gregkh, srini, vkoul,
neil.armstrong, sre, sboyd, angelogioacchino.delregno, krzk,
dmitry.baryshkov, quic_wcheng, melody.olvera, quic_nsekar,
ivo.ivanov.ivanov1, abelvesa, luca.weiss, konrad.dybcio,
mitltlatltl, krishna.kurapati, linux-arm-msm, linux-iio,
linux-kernel, linux-phy, linux-pm, kernel, Jonathan Cameron,
Andy Shevchenko
Some Qualcomm PMICs integrate an Current ADC device, reachable
in a specific address range over SPMI.
Instead of using the parent SPMI device (the main PMIC) as a kind
of syscon in this driver, register a new SPMI sub-device and
initialize its own regmap with this sub-device's specific base
address, retrieved from the devicetree.
This allows to stop manually adding the register base address to
every R/W call in this driver, as this can be, and is now, handled
by the regmap API instead.
Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Tested-by: Neil Armstrong <neil.armstrong@linaro.org> # on SM8650-QRD
Reviewed-by: Andy Shevchenko <andriy.shevchenko@intel.com>
Signed-off-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
---
drivers/iio/adc/qcom-spmi-iadc.c | 35 ++++++++++++++++++++++----------
1 file changed, 24 insertions(+), 11 deletions(-)
diff --git a/drivers/iio/adc/qcom-spmi-iadc.c b/drivers/iio/adc/qcom-spmi-iadc.c
index 0ec3a0c4b1de..ad66bb92fe19 100644
--- a/drivers/iio/adc/qcom-spmi-iadc.c
+++ b/drivers/iio/adc/qcom-spmi-iadc.c
@@ -16,6 +16,7 @@
#include <linux/platform_device.h>
#include <linux/regmap.h>
#include <linux/slab.h>
+#include <linux/spmi.h>
/* IADC register and bit definition */
#define IADC_REVISION2 0x1
@@ -94,7 +95,6 @@
* struct iadc_chip - IADC Current ADC device structure.
* @regmap: regmap for register read/write.
* @dev: This device pointer.
- * @base: base offset for the ADC peripheral.
* @rsense: Values of the internal and external sense resister in micro Ohms.
* @poll_eoc: Poll for end of conversion instead of waiting for IRQ.
* @offset: Raw offset values for the internal and external channels.
@@ -105,7 +105,6 @@
struct iadc_chip {
struct regmap *regmap;
struct device *dev;
- u16 base;
bool poll_eoc;
u32 rsense[2];
u16 offset[2];
@@ -119,7 +118,7 @@ static int iadc_read(struct iadc_chip *iadc, u16 offset, u8 *data)
unsigned int val;
int ret;
- ret = regmap_read(iadc->regmap, iadc->base + offset, &val);
+ ret = regmap_read(iadc->regmap, offset, &val);
if (ret < 0)
return ret;
@@ -129,7 +128,7 @@ static int iadc_read(struct iadc_chip *iadc, u16 offset, u8 *data)
static int iadc_write(struct iadc_chip *iadc, u16 offset, u8 data)
{
- return regmap_write(iadc->regmap, iadc->base + offset, data);
+ return regmap_write(iadc->regmap, offset, data);
}
static int iadc_reset(struct iadc_chip *iadc)
@@ -270,7 +269,7 @@ static int iadc_poll_wait_eoc(struct iadc_chip *iadc, unsigned int interval_us)
static int iadc_read_result(struct iadc_chip *iadc, u16 *data)
{
- return regmap_bulk_read(iadc->regmap, iadc->base + IADC_DATA, data, 2);
+ return regmap_bulk_read(iadc->regmap, IADC_DATA, data, 2);
}
static int iadc_do_conversion(struct iadc_chip *iadc, int chan, u16 *data)
@@ -488,12 +487,22 @@ static void iadc_disable_irq_wake(void *data)
static int iadc_probe(struct platform_device *pdev)
{
+ struct regmap_config iadc_regmap_config = {
+ .reg_bits = 16,
+ .val_bits = 8,
+ .max_register = 0xff,
+ .fast_io = true,
+ };
struct device_node *node = pdev->dev.of_node;
struct device *dev = &pdev->dev;
+ struct spmi_subdevice *sub_sdev;
+ struct spmi_device *sparent;
struct iio_dev *indio_dev;
struct iadc_chip *iadc;
int ret, irq_eoc;
- u32 res;
+
+ if (!dev->parent)
+ return -ENODEV;
indio_dev = devm_iio_device_alloc(dev, sizeof(*iadc));
if (!indio_dev)
@@ -502,18 +511,21 @@ static int iadc_probe(struct platform_device *pdev)
iadc = iio_priv(indio_dev);
iadc->dev = dev;
- iadc->regmap = dev_get_regmap(dev->parent, NULL);
- if (!iadc->regmap)
- return -ENODEV;
+ sparent = to_spmi_device(dev->parent);
+ sub_sdev = devm_spmi_subdevice_alloc_and_add(dev, sparent);
+ if (IS_ERR(sub_sdev))
+ return PTR_ERR(sub_sdev);
init_completion(&iadc->complete);
mutex_init(&iadc->lock);
- ret = of_property_read_u32(node, "reg", &res);
+ ret = device_property_read_u32(dev, "reg", &iadc_regmap_config.reg_base);
if (ret < 0)
return -ENODEV;
- iadc->base = res;
+ iadc->regmap = devm_regmap_init_spmi_ext(&sub_sdev->sdev, &iadc_regmap_config);
+ if (IS_ERR(iadc->regmap))
+ return PTR_ERR(iadc->regmap);
ret = iadc_version_check(iadc);
if (ret < 0)
@@ -596,3 +608,4 @@ MODULE_ALIAS("platform:qcom-spmi-iadc");
MODULE_DESCRIPTION("Qualcomm SPMI PMIC current ADC driver");
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR("Ivan T. Ivanov <iivanov@mm-sol.com>");
+MODULE_IMPORT_NS("SPMI");
--
2.54.0
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply related [flat|nested] 19+ messages in thread* [PATCH v9 10/10] iio: adc: qcom-spmi-iadc: Remove regmap R/W wrapper functions
2026-06-08 10:09 [PATCH v9 00/10] SPMI: Implement sub-devices and migrate drivers AngeloGioacchino Del Regno
` (8 preceding siblings ...)
2026-06-08 10:09 ` [PATCH v9 09/10] iio: adc: qcom-spmi-iadc: " AngeloGioacchino Del Regno
@ 2026-06-08 10:09 ` AngeloGioacchino Del Regno
9 siblings, 0 replies; 19+ messages in thread
From: AngeloGioacchino Del Regno @ 2026-06-08 10:09 UTC (permalink / raw)
To: jic23
Cc: dlechner, nuno.sa, andy, arnd, gregkh, srini, vkoul,
neil.armstrong, sre, sboyd, angelogioacchino.delregno, krzk,
dmitry.baryshkov, quic_wcheng, melody.olvera, quic_nsekar,
ivo.ivanov.ivanov1, abelvesa, luca.weiss, konrad.dybcio,
mitltlatltl, krishna.kurapati, linux-arm-msm, linux-iio,
linux-kernel, linux-phy, linux-pm, kernel, Jonathan Cameron,
Andy Shevchenko
This driver doesn't need to add any register base address to any
regmap call anymore since it was migrated to register as a SPMI
subdevice with its own regmap reg_base, which makes the regmap
API to automatically add such base address internally.
Since the iadc_{read,write,read_result}() functions now only do
call regmap_{read,write,bulk_read}() and nothing else, simplify
the driver by removing them and by calling regmap APIs directly.
Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Tested-by: Neil Armstrong <neil.armstrong@linaro.org> # on SM8650-QRD
Reviewed-by: Andy Shevchenko <andriy.shevchenko@intel.com>
Signed-off-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
---
drivers/iio/adc/qcom-spmi-iadc.c | 89 ++++++++++++--------------------
1 file changed, 33 insertions(+), 56 deletions(-)
diff --git a/drivers/iio/adc/qcom-spmi-iadc.c b/drivers/iio/adc/qcom-spmi-iadc.c
index ad66bb92fe19..29e71e6ac374 100644
--- a/drivers/iio/adc/qcom-spmi-iadc.c
+++ b/drivers/iio/adc/qcom-spmi-iadc.c
@@ -113,77 +113,59 @@ struct iadc_chip {
struct completion complete;
};
-static int iadc_read(struct iadc_chip *iadc, u16 offset, u8 *data)
-{
- unsigned int val;
- int ret;
-
- ret = regmap_read(iadc->regmap, offset, &val);
- if (ret < 0)
- return ret;
-
- *data = val;
- return 0;
-}
-
-static int iadc_write(struct iadc_chip *iadc, u16 offset, u8 data)
-{
- return regmap_write(iadc->regmap, offset, data);
-}
-
static int iadc_reset(struct iadc_chip *iadc)
{
- u8 data;
+ u32 data;
int ret;
- ret = iadc_write(iadc, IADC_SEC_ACCESS, IADC_SEC_ACCESS_DATA);
+ ret = regmap_write(iadc->regmap, IADC_SEC_ACCESS, IADC_SEC_ACCESS_DATA);
if (ret < 0)
return ret;
- ret = iadc_read(iadc, IADC_PERH_RESET_CTL3, &data);
+ ret = regmap_read(iadc->regmap, IADC_PERH_RESET_CTL3, &data);
if (ret < 0)
return ret;
- ret = iadc_write(iadc, IADC_SEC_ACCESS, IADC_SEC_ACCESS_DATA);
+ ret = regmap_write(iadc->regmap, IADC_SEC_ACCESS, IADC_SEC_ACCESS_DATA);
if (ret < 0)
return ret;
data |= IADC_FOLLOW_WARM_RB;
- return iadc_write(iadc, IADC_PERH_RESET_CTL3, data);
+ return regmap_write(iadc->regmap, IADC_PERH_RESET_CTL3, data);
}
static int iadc_set_state(struct iadc_chip *iadc, bool state)
{
- return iadc_write(iadc, IADC_EN_CTL1, state ? IADC_EN_CTL1_SET : 0);
+ return regmap_write(iadc->regmap, IADC_EN_CTL1, state ? IADC_EN_CTL1_SET : 0);
}
static void iadc_status_show(struct iadc_chip *iadc)
{
- u8 mode, sta1, chan, dig, en, req;
+ u32 mode, sta1, chan, dig, en, req;
int ret;
- ret = iadc_read(iadc, IADC_MODE_CTL, &mode);
+ ret = regmap_read(iadc->regmap, IADC_MODE_CTL, &mode);
if (ret < 0)
return;
- ret = iadc_read(iadc, IADC_DIG_PARAM, &dig);
+ ret = regmap_read(iadc->regmap, IADC_DIG_PARAM, &dig);
if (ret < 0)
return;
- ret = iadc_read(iadc, IADC_CH_SEL_CTL, &chan);
+ ret = regmap_read(iadc->regmap, IADC_CH_SEL_CTL, &chan);
if (ret < 0)
return;
- ret = iadc_read(iadc, IADC_CONV_REQ, &req);
+ ret = regmap_read(iadc->regmap, IADC_CONV_REQ, &req);
if (ret < 0)
return;
- ret = iadc_read(iadc, IADC_STATUS1, &sta1);
+ ret = regmap_read(iadc->regmap, IADC_STATUS1, &sta1);
if (ret < 0)
return;
- ret = iadc_read(iadc, IADC_EN_CTL1, &en);
+ ret = regmap_read(iadc->regmap, IADC_EN_CTL1, &en);
if (ret < 0)
return;
@@ -199,34 +181,34 @@ static int iadc_configure(struct iadc_chip *iadc, int channel)
/* Mode selection */
mode = (IADC_OP_MODE_NORMAL << IADC_OP_MODE_SHIFT) | IADC_TRIM_EN;
- ret = iadc_write(iadc, IADC_MODE_CTL, mode);
+ ret = regmap_write(iadc->regmap, IADC_MODE_CTL, mode);
if (ret < 0)
return ret;
/* Channel selection */
- ret = iadc_write(iadc, IADC_CH_SEL_CTL, channel);
+ ret = regmap_write(iadc->regmap, IADC_CH_SEL_CTL, channel);
if (ret < 0)
return ret;
/* Digital parameter setup */
decim = IADC_DEF_DECIMATION << IADC_DIG_DEC_RATIO_SEL_SHIFT;
- ret = iadc_write(iadc, IADC_DIG_PARAM, decim);
+ ret = regmap_write(iadc->regmap, IADC_DIG_PARAM, decim);
if (ret < 0)
return ret;
/* HW settle time delay */
- ret = iadc_write(iadc, IADC_HW_SETTLE_DELAY, IADC_DEF_HW_SETTLE_TIME);
+ ret = regmap_write(iadc->regmap, IADC_HW_SETTLE_DELAY, IADC_DEF_HW_SETTLE_TIME);
if (ret < 0)
return ret;
- ret = iadc_write(iadc, IADC_FAST_AVG_CTL, IADC_DEF_AVG_SAMPLES);
+ ret = regmap_write(iadc->regmap, IADC_FAST_AVG_CTL, IADC_DEF_AVG_SAMPLES);
if (ret < 0)
return ret;
if (IADC_DEF_AVG_SAMPLES)
- ret = iadc_write(iadc, IADC_FAST_AVG_EN, IADC_FAST_AVG_EN_SET);
+ ret = regmap_write(iadc->regmap, IADC_FAST_AVG_EN, IADC_FAST_AVG_EN_SET);
else
- ret = iadc_write(iadc, IADC_FAST_AVG_EN, 0);
+ ret = regmap_write(iadc->regmap, IADC_FAST_AVG_EN, 0);
if (ret < 0)
return ret;
@@ -239,19 +221,19 @@ static int iadc_configure(struct iadc_chip *iadc, int channel)
return ret;
/* Request conversion */
- return iadc_write(iadc, IADC_CONV_REQ, IADC_CONV_REQ_SET);
+ return regmap_write(iadc->regmap, IADC_CONV_REQ, IADC_CONV_REQ_SET);
}
static int iadc_poll_wait_eoc(struct iadc_chip *iadc, unsigned int interval_us)
{
unsigned int count, retry;
+ u32 sta1;
int ret;
- u8 sta1;
retry = interval_us / IADC_CONV_TIME_MIN_US;
for (count = 0; count < retry; count++) {
- ret = iadc_read(iadc, IADC_STATUS1, &sta1);
+ ret = regmap_read(iadc->regmap, IADC_STATUS1, &sta1);
if (ret < 0)
return ret;
@@ -267,11 +249,6 @@ static int iadc_poll_wait_eoc(struct iadc_chip *iadc, unsigned int interval_us)
return -ETIMEDOUT;
}
-static int iadc_read_result(struct iadc_chip *iadc, u16 *data)
-{
- return regmap_bulk_read(iadc->regmap, IADC_DATA, data, 2);
-}
-
static int iadc_do_conversion(struct iadc_chip *iadc, int chan, u16 *data)
{
unsigned int wait;
@@ -296,7 +273,7 @@ static int iadc_do_conversion(struct iadc_chip *iadc, int chan, u16 *data)
}
if (!ret)
- ret = iadc_read_result(iadc, data);
+ ret = regmap_bulk_read(iadc->regmap, IADC_DATA, data, sizeof(*data));
exit:
iadc_set_state(iadc, false);
if (ret < 0)
@@ -392,33 +369,33 @@ static int iadc_update_offset(struct iadc_chip *iadc)
static int iadc_version_check(struct iadc_chip *iadc)
{
- u8 val;
+ u32 val;
int ret;
- ret = iadc_read(iadc, IADC_PERPH_TYPE, &val);
+ ret = regmap_read(iadc->regmap, IADC_PERPH_TYPE, &val);
if (ret < 0)
return ret;
if (val < IADC_PERPH_TYPE_ADC) {
- dev_err(iadc->dev, "%d is not ADC\n", val);
+ dev_err(iadc->dev, "%u is not ADC\n", val);
return -EINVAL;
}
- ret = iadc_read(iadc, IADC_PERPH_SUBTYPE, &val);
+ ret = regmap_read(iadc->regmap, IADC_PERPH_SUBTYPE, &val);
if (ret < 0)
return ret;
if (val < IADC_PERPH_SUBTYPE_IADC) {
- dev_err(iadc->dev, "%d is not IADC\n", val);
+ dev_err(iadc->dev, "%u is not IADC\n", val);
return -EINVAL;
}
- ret = iadc_read(iadc, IADC_REVISION2, &val);
+ ret = regmap_read(iadc->regmap, IADC_REVISION2, &val);
if (ret < 0)
return ret;
if (val < IADC_REVISION2_SUPPORTED_IADC) {
- dev_err(iadc->dev, "revision %d not supported\n", val);
+ dev_err(iadc->dev, "revision %u not supported\n", val);
return -EINVAL;
}
@@ -428,7 +405,7 @@ static int iadc_version_check(struct iadc_chip *iadc)
static int iadc_rsense_read(struct iadc_chip *iadc, struct device_node *node)
{
int ret, sign, int_sense;
- u8 deviation;
+ u32 deviation;
ret = of_property_read_u32(node, "qcom,external-resistor-micro-ohms",
&iadc->rsense[IADC_EXT_RSENSE]);
@@ -440,7 +417,7 @@ static int iadc_rsense_read(struct iadc_chip *iadc, struct device_node *node)
return -EINVAL;
}
- ret = iadc_read(iadc, IADC_NOMINAL_RSENSE, &deviation);
+ ret = regmap_read(iadc->regmap, IADC_NOMINAL_RSENSE, &deviation);
if (ret < 0)
return ret;
--
2.54.0
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply related [flat|nested] 19+ messages in thread