* [PATCH v13 1/5] phy: core: Add phy_get_by_of_node()
2026-07-28 9:35 [PATCH v13 0/5] Add dt-bindings and PHY updates for CAMSS on x1e80100 silicon Bryan O'Donoghue
@ 2026-07-28 9:35 ` Bryan O'Donoghue
2026-07-28 9:46 ` sashiko-bot
2026-07-28 9:35 ` [PATCH v13 2/5] phy: core: Add devm_phy_get_by_of_node() Bryan O'Donoghue
` (3 subsequent siblings)
4 siblings, 1 reply; 17+ messages in thread
From: Bryan O'Donoghue @ 2026-07-28 9:35 UTC (permalink / raw)
To: Bjorn Andersson, Michael Turquette, Stephen Boyd, Rob Herring,
Krzysztof Kozlowski, Conor Dooley, Robert Foss, Todor Tomov,
Mauro Carvalho Chehab, Konrad Dybcio, Vladimir Zapolskiy,
Bryan O'Donoghue, Loic Poulain, Vinod Koul, Neil Armstrong
Cc: linux-arm-msm, linux-clk, devicetree, linux-kernel, linux-media,
linux-phy, Bryan O'Donoghue, Krzysztof Kozlowski
Add new function phy_get_by_of_node() allowing lookup of a phy by
device_node. Separates existing logic in _of_phy_get() into an internal
helper method _of_phy_get_with_args() to allow for reuse in new method.
Signed-off-by: Bryan O'Donoghue <bryan.odonoghue@linaro.org>
---
drivers/phy/phy-core.c | 95 +++++++++++++++++++++++++++++++++++--------------
include/linux/phy/phy.h | 6 ++++
2 files changed, 75 insertions(+), 26 deletions(-)
diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c
index 21aaf2f76e53e..ebfad5325072e 100644
--- a/drivers/phy/phy-core.c
+++ b/drivers/phy/phy-core.c
@@ -607,54 +607,69 @@ int phy_validate(struct phy *phy, enum phy_mode mode, int submode,
EXPORT_SYMBOL_GPL(phy_validate);
/**
- * _of_phy_get() - lookup and obtain a reference to a phy by phandle
- * @np: device_node for which to get the phy
- * @index: the index of the phy
+ * _of_phy_get_with_args() - lookup and obtain a reference to a phy by of_phandle_args
+ * @args: of_phandle_args to the phy
*
- * Returns the phy associated with the given phandle value,
- * after getting a refcount to it or -ENODEV if there is no such phy or
- * -EPROBE_DEFER if there is a phandle to the phy, but the device is
- * not yet loaded. This function uses of_xlate call back function provided
- * while registering the phy_provider to find the phy instance.
+ * Returns the phy from the provider's of_xlate, -ENODEV if disabled,
+ * -EPROBE_DEFER if the provider is not yet registered.
*/
-static struct phy *_of_phy_get(struct device_node *np, int index)
+static struct phy *_of_phy_get_with_args(struct of_phandle_args *args)
{
- int ret;
+ struct phy *phy;
struct phy_provider *phy_provider;
- struct phy *phy = NULL;
- struct of_phandle_args args;
-
- ret = of_parse_phandle_with_args(np, "phys", "#phy-cells",
- index, &args);
- if (ret)
- return ERR_PTR(-ENODEV);
-
- /* This phy type handled by the usb-phy subsystem for now */
- if (of_device_is_compatible(args.np, "usb-nop-xceiv")) {
- phy = ERR_PTR(-ENODEV);
- goto out_put_node;
- }
mutex_lock(&phy_provider_mutex);
- phy_provider = of_phy_provider_lookup(args.np);
+ phy_provider = of_phy_provider_lookup(args->np);
if (IS_ERR(phy_provider) || !try_module_get(phy_provider->owner)) {
phy = ERR_PTR(-EPROBE_DEFER);
goto out_unlock;
}
- if (!of_device_is_available(args.np)) {
+ if (!of_device_is_available(args->np)) {
dev_warn(phy_provider->dev, "Requested PHY is disabled\n");
phy = ERR_PTR(-ENODEV);
goto out_put_module;
}
- phy = phy_provider->of_xlate(phy_provider->dev, &args);
+ phy = phy_provider->of_xlate(phy_provider->dev, args);
out_put_module:
module_put(phy_provider->owner);
out_unlock:
mutex_unlock(&phy_provider_mutex);
+
+ return phy;
+}
+
+/**
+ * _of_phy_get() - lookup and obtain a reference to a phy by phandle
+ * @np: device_node for which to get the phy
+ * @index: the index of the phy
+ *
+ * Returns the phy associated with the given phandle value after getting
+ * a refcount to it; -ENODEV if there is no such phy or the phy is
+ * disabled; -EPROBE_DEFER if the phy provider is not yet available.
+ */
+static struct phy *_of_phy_get(struct device_node *np, int index)
+{
+ int ret;
+ struct phy *phy;
+ struct of_phandle_args args;
+
+ ret = of_parse_phandle_with_args(np, "phys", "#phy-cells",
+ index, &args);
+ if (ret)
+ return ERR_PTR(-ENODEV);
+
+ /* This phy type handled by the usb-phy subsystem for now */
+ if (of_device_is_compatible(args.np, "usb-nop-xceiv")) {
+ phy = ERR_PTR(-ENODEV);
+ goto out_put_node;
+ }
+
+ phy = _of_phy_get_with_args(&args);
+
out_put_node:
of_node_put(args.np);
@@ -986,6 +1001,34 @@ struct phy *devm_of_phy_get_by_index(struct device *dev, struct device_node *np,
}
EXPORT_SYMBOL_GPL(devm_of_phy_get_by_index);
+/**
+ * phy_get_by_of_node() - lookup and obtain a reference to a phy by device_node
+ * @np: node containing the phy
+ *
+ * Returns the phy associated with the device node or ERR_PTR.
+ */
+struct phy *phy_get_by_of_node(struct device_node *np)
+{
+ struct of_phandle_args args = { .np = np, .args_count = 0 };
+ struct phy *phy;
+
+ if (!np)
+ return ERR_PTR(-EINVAL);
+
+ phy = _of_phy_get_with_args(&args);
+
+ if (IS_ERR(phy))
+ return phy;
+
+ if (!try_module_get(phy->ops->owner))
+ return ERR_PTR(-EPROBE_DEFER);
+
+ get_device(&phy->dev);
+
+ return phy;
+}
+EXPORT_SYMBOL_GPL(phy_get_by_of_node);
+
/**
* phy_create() - create a new phy
* @dev: device that is creating the new phy
diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h
index ea47975e288ae..71c2e16397130 100644
--- a/include/linux/phy/phy.h
+++ b/include/linux/phy/phy.h
@@ -284,6 +284,7 @@ struct phy *devm_of_phy_optional_get(struct device *dev, struct device_node *np,
const char *con_id);
struct phy *devm_of_phy_get_by_index(struct device *dev, struct device_node *np,
int index);
+struct phy *phy_get_by_of_node(struct device_node *np);
void of_phy_put(struct phy *phy);
void phy_put(struct device *dev, struct phy *phy);
void devm_phy_put(struct device *dev, struct phy *phy);
@@ -493,6 +494,11 @@ static inline struct phy *devm_of_phy_get_by_index(struct device *dev,
return ERR_PTR(-ENOSYS);
}
+static inline struct phy *phy_get_by_of_node(struct device_node *np)
+{
+ return ERR_PTR(-ENOSYS);
+}
+
static inline void of_phy_put(struct phy *phy)
{
}
--
2.54.0
^ permalink raw reply related [flat|nested] 17+ messages in thread* Re: [PATCH v13 1/5] phy: core: Add phy_get_by_of_node()
2026-07-28 9:35 ` [PATCH v13 1/5] phy: core: Add phy_get_by_of_node() Bryan O'Donoghue
@ 2026-07-28 9:46 ` sashiko-bot
2026-07-28 10:01 ` Bryan O'Donoghue
0 siblings, 1 reply; 17+ messages in thread
From: sashiko-bot @ 2026-07-28 9:46 UTC (permalink / raw)
To: Bryan O'Donoghue
Cc: robh, olteanv, devicetree, media-ci, linux-phy, neil.armstrong,
conor+dt, vkoul
Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
New issues:
- [High] The newly introduced phy_get_by_of_node() API bypasses the usb-nop-xceiv compatibility check, leading to infinite probe deferral.
Pre-existing issues:
- [High] A Time-of-Check to Time-of-Use (TOCTOU) race condition during PHY lookup returns an unpinned pointer, allowing concurrent PHY destruction to cause a Use-After-Free.
--
--- Patch [1]: [PATCH v13 1/5] phy: core: Add phy_get_by_of_node() ---
commit 2964f1957e7138a13d72185f47a72cbb1e4e193c
Author: Bryan O'Donoghue <bryan.odonoghue@linaro.org>
phy: core: Add phy_get_by_of_node()
Add new function phy_get_by_of_node() allowing lookup of a phy by
device_node. Separates existing logic in _of_phy_get() into an internal
helper method _of_phy_get_with_args() to allow for reuse in new method.
> diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c
> index 21aaf2f76e53e..ebfad5325072e 100644
> --- a/drivers/phy/phy-core.c
> +++ b/drivers/phy/phy-core.c
[ ... ]
> @@ -607,54 +607,69 @@ int phy_validate(struct phy *phy, enum phy_mode mode, int submode,
[ ... ]
> +static struct phy *_of_phy_get(struct device_node *np, int index)
> +{
> + int ret;
> + struct phy *phy;
> + struct of_phandle_args args;
> +
> + ret = of_parse_phandle_with_args(np, "phys", "#phy-cells",
> + index, &args);
> + if (ret)
> + return ERR_PTR(-ENODEV);
> +
> + /* This phy type handled by the usb-phy subsystem for now */
> + if (of_device_is_compatible(args.np, "usb-nop-xceiv")) {
> + phy = ERR_PTR(-ENODEV);
> + goto out_put_node;
> + }
> +
> + phy = _of_phy_get_with_args(&args);
[Severity: High]
If a caller uses the new phy_get_by_of_node() API on a device node compatible
with "usb-nop-xceiv", will it bypass this check?
Because the compatibility check was left here in _of_phy_get() instead of
being moved into the shared _of_phy_get_with_args() helper, it appears the
new API will skip this fallback and could enter an infinite probe deferral
instead of correctly returning -ENODEV.
[ ... ]
> @@ -986,6 +1001,34 @@ struct phy *devm_of_phy_get_by_index(struct device *dev, struct device_node *np,
> }
> EXPORT_SYMBOL_GPL(devm_of_phy_get_by_index);
>
> +/**
> + * phy_get_by_of_node() - lookup and obtain a reference to a phy by device_node
> + * @np: node containing the phy
> + *
> + * Returns the phy associated with the device node or ERR_PTR.
> + */
> +struct phy *phy_get_by_of_node(struct device_node *np)
> +{
> + struct of_phandle_args args = { .np = np, .args_count = 0 };
> + struct phy *phy;
> +
> + if (!np)
> + return ERR_PTR(-EINVAL);
> +
> + phy = _of_phy_get_with_args(&args);
> +
> + if (IS_ERR(phy))
> + return phy;
> +
> + if (!try_module_get(phy->ops->owner))
[Severity: High]
This isn't a bug introduced by this patch, but is there a race condition
here between retrieving the phy and pinning its module?
The _of_phy_get_with_args() helper retrieves the phy pointer via the
provider's of_xlate callback. Typical callbacks (like of_phy_simple_xlate())
drop the PHY device reference before returning. _of_phy_get_with_args() then
unlocks phy_provider_mutex and drops the provider's module reference.
Could a concurrent thread unbinding the PHY provider destroy the PHY object
before this caller evaluates try_module_get(phy->ops->owner), resulting in a
use-after-free?
> + return ERR_PTR(-EPROBE_DEFER);
> +
> + get_device(&phy->dev);
> +
> + return phy;
> +}
> +EXPORT_SYMBOL_GPL(phy_get_by_of_node);
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260728-b4-linux-next-25-03-13-dtsi-x1e80100-camss-v13-0-ae811e2f0799@linaro.org?part=1
^ permalink raw reply [flat|nested] 17+ messages in thread* Re: [PATCH v13 1/5] phy: core: Add phy_get_by_of_node()
2026-07-28 9:46 ` sashiko-bot
@ 2026-07-28 10:01 ` Bryan O'Donoghue
0 siblings, 0 replies; 17+ messages in thread
From: Bryan O'Donoghue @ 2026-07-28 10:01 UTC (permalink / raw)
To: sashiko-reviews
Cc: robh, olteanv, devicetree, media-ci, linux-phy, neil.armstrong,
conor+dt, vkoul
On 28/07/2026 10:46, sashiko-bot@kernel.org wrote:
> [Severity: High]
> If a caller uses the new phy_get_by_of_node() API on a device node compatible
> with "usb-nop-xceiv", will it bypass this check?
No it won't but, it is not _supposed_ to.
Literally just doing functional decomposition here. If someone misuses
that decomp, that's on them, not part of this patch.
I don't see much point in moving that specific workaround into a
lower-level boiler-plate but, its up to the PHY maintainers to decide.
---
bod
^ permalink raw reply [flat|nested] 17+ messages in thread
* [PATCH v13 2/5] phy: core: Add devm_phy_get_by_of_node()
2026-07-28 9:35 [PATCH v13 0/5] Add dt-bindings and PHY updates for CAMSS on x1e80100 silicon Bryan O'Donoghue
2026-07-28 9:35 ` [PATCH v13 1/5] phy: core: Add phy_get_by_of_node() Bryan O'Donoghue
@ 2026-07-28 9:35 ` Bryan O'Donoghue
2026-07-28 9:47 ` sashiko-bot
2026-07-28 10:46 ` Dmitry Baryshkov
2026-07-28 9:35 ` [PATCH v13 3/5] media: qcom: camss: Add support for PHY API devices Bryan O'Donoghue
` (2 subsequent siblings)
4 siblings, 2 replies; 17+ messages in thread
From: Bryan O'Donoghue @ 2026-07-28 9:35 UTC (permalink / raw)
To: Bjorn Andersson, Michael Turquette, Stephen Boyd, Rob Herring,
Krzysztof Kozlowski, Conor Dooley, Robert Foss, Todor Tomov,
Mauro Carvalho Chehab, Konrad Dybcio, Vladimir Zapolskiy,
Bryan O'Donoghue, Loic Poulain, Vinod Koul, Neil Armstrong
Cc: linux-arm-msm, linux-clk, devicetree, linux-kernel, linux-media,
linux-phy, Bryan O'Donoghue, Krzysztof Kozlowski
Add a devm variant of phy_get_by_of_node() to allow for the familiar
pattern of having devres automatically release resources on the driver's
exit path.
Signed-off-by: Bryan O'Donoghue <bryan.odonoghue@linaro.org>
---
drivers/phy/phy-core.c | 34 ++++++++++++++++++++++++++++++++++
include/linux/phy/phy.h | 7 +++++++
2 files changed, 41 insertions(+)
diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c
index ebfad5325072e..7af24f2f4120f 100644
--- a/drivers/phy/phy-core.c
+++ b/drivers/phy/phy-core.c
@@ -1029,6 +1029,40 @@ struct phy *phy_get_by_of_node(struct device_node *np)
}
EXPORT_SYMBOL_GPL(phy_get_by_of_node);
+/**
+ * devm_phy_get_by_of_node() - devm managed lookup and obtain phy reference by device node
+ * @dev: device requesting the PHY
+ * @np: device_node of the PHY provider
+ *
+ * Returns phy associated with the device_node or ERR_PTR. devres manages
+ * releasing resources.
+ */
+struct phy *devm_phy_get_by_of_node(struct device *dev, struct device_node *np)
+{
+ struct phy **ptr, *phy;
+ struct device_link *link;
+
+ ptr = devres_alloc(devm_phy_release, sizeof(*ptr), GFP_KERNEL);
+ if (!ptr)
+ return ERR_PTR(-ENOMEM);
+
+ phy = phy_get_by_of_node(np);
+ if (IS_ERR(phy)) {
+ devres_free(ptr);
+ return phy;
+ }
+
+ *ptr = phy;
+ devres_add(dev, ptr);
+ link = device_link_add(dev, &phy->dev, DL_FLAG_STATELESS);
+ if (!link)
+ dev_dbg(dev, "failed to create device link to %s\n",
+ dev_name(phy->dev.parent));
+
+ return phy;
+}
+EXPORT_SYMBOL_GPL(devm_phy_get_by_of_node);
+
/**
* phy_create() - create a new phy
* @dev: device that is creating the new phy
diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h
index 71c2e16397130..14b924a88411f 100644
--- a/include/linux/phy/phy.h
+++ b/include/linux/phy/phy.h
@@ -285,6 +285,7 @@ struct phy *devm_of_phy_optional_get(struct device *dev, struct device_node *np,
struct phy *devm_of_phy_get_by_index(struct device *dev, struct device_node *np,
int index);
struct phy *phy_get_by_of_node(struct device_node *np);
+struct phy *devm_phy_get_by_of_node(struct device *dev, struct device_node *np);
void of_phy_put(struct phy *phy);
void phy_put(struct device *dev, struct phy *phy);
void devm_phy_put(struct device *dev, struct phy *phy);
@@ -499,6 +500,12 @@ static inline struct phy *phy_get_by_of_node(struct device_node *np)
return ERR_PTR(-ENOSYS);
}
+static inline struct phy *devm_phy_get_by_of_node(struct device *dev,
+ struct device_node *np)
+{
+ return ERR_PTR(-ENOSYS);
+}
+
static inline void of_phy_put(struct phy *phy)
{
}
--
2.54.0
^ permalink raw reply related [flat|nested] 17+ messages in thread* Re: [PATCH v13 2/5] phy: core: Add devm_phy_get_by_of_node()
2026-07-28 9:35 ` [PATCH v13 2/5] phy: core: Add devm_phy_get_by_of_node() Bryan O'Donoghue
@ 2026-07-28 9:47 ` sashiko-bot
2026-07-28 10:21 ` Bryan O'Donoghue
2026-07-28 10:46 ` Dmitry Baryshkov
1 sibling, 1 reply; 17+ messages in thread
From: sashiko-bot @ 2026-07-28 9:47 UTC (permalink / raw)
To: Bryan O'Donoghue
Cc: neil.armstrong, robh, devicetree, vkoul, olteanv, conor+dt,
media-ci, linux-phy
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
Pre-existing issues:
- [High] A TOCTOU race condition exists between looking up the PHY and acquiring its module/device references, leading to a Use-After-Free (UAF).
--
--- Patch [2]: [PATCH v13 2/5] phy: core: Add devm_phy_get_by_of_node() ---
commit 65a24031fe496953334387cf190f1425a8b31168
Author: Bryan O'Donoghue <bryan.odonoghue@linaro.org>
phy: core: Add devm_phy_get_by_of_node()
Add a devm variant of phy_get_by_of_node() to allow for the familiar
pattern of having devres automatically release resources on the driver's
exit path.
> diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c
> index ebfad5325072e..7af24f2f4120f 100644
> --- a/drivers/phy/phy-core.c
> +++ b/drivers/phy/phy-core.c
[ ... ]
> @@ -1029,6 +1029,40 @@ struct phy *phy_get_by_of_node(struct device_node *np)
> }
> EXPORT_SYMBOL_GPL(phy_get_by_of_node);
>
> +/**
> + * devm_phy_get_by_of_node() - devm managed lookup and obtain phy reference by device node
> + * @dev: device requesting the PHY
> + * @np: device_node of the PHY provider
> + *
> + * Returns phy associated with the device_node or ERR_PTR. devres manages
> + * releasing resources.
> + */
> +struct phy *devm_phy_get_by_of_node(struct device *dev, struct device_node *np)
> +{
> + struct phy **ptr, *phy;
> + struct device_link *link;
> +
> + ptr = devres_alloc(devm_phy_release, sizeof(*ptr), GFP_KERNEL);
> + if (!ptr)
> + return ERR_PTR(-ENOMEM);
> +
> + phy = phy_get_by_of_node(np);
[Severity: High]
This is a pre-existing issue, but does a TOCTOU race condition exist in the
underlying phy_get_by_of_node() that could lead to a use-after-free here?
Looking at phy_get_by_of_node(), it calls _of_phy_get_with_args() to look up
the PHY. Inside _of_phy_get_with_args(), the function temporarily elevates the
provider's module refcount, calls of_xlate() (which returns a bare phy
pointer without incrementing the device refcount), and then drops the module
refcount and unlocks phy_provider_mutex before returning the raw phy pointer.
The caller then accesses phy->ops->owner and calls get_device(&phy->dev):
drivers/phy/phy-core.c:phy_get_by_of_node() {
...
phy = _of_phy_get_with_args(&args);
if (IS_ERR(phy))
return phy;
if (!try_module_get(phy->ops->owner))
return ERR_PTR(-EPROBE_DEFER);
get_device(&phy->dev);
...
}
If the PHY provider module is unloaded or its driver is unbound via sysfs
concurrently in the window between _of_phy_get_with_args() returning and the
try_module_get() call, the phy struct could be unregistered and freed.
Could this cause the subsequent dereferences of phy->ops and phy->dev to
access freed memory?
> + if (IS_ERR(phy)) {
> + devres_free(ptr);
> + return phy;
> + }
> +
> + *ptr = phy;
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260728-b4-linux-next-25-03-13-dtsi-x1e80100-camss-v13-0-ae811e2f0799@linaro.org?part=2
^ permalink raw reply [flat|nested] 17+ messages in thread* Re: [PATCH v13 2/5] phy: core: Add devm_phy_get_by_of_node()
2026-07-28 9:47 ` sashiko-bot
@ 2026-07-28 10:21 ` Bryan O'Donoghue
0 siblings, 0 replies; 17+ messages in thread
From: Bryan O'Donoghue @ 2026-07-28 10:21 UTC (permalink / raw)
To: sashiko-reviews
Cc: neil.armstrong, robh, devicetree, vkoul, olteanv, conor+dt,
media-ci, linux-phy
On 28/07/2026 10:47, sashiko-bot@kernel.org wrote:
>> +struct phy *devm_phy_get_by_of_node(struct device *dev, struct device_node *np)
>> +{
>> + struct phy **ptr, *phy;
>> + struct device_link *link;
>> +
>> + ptr = devres_alloc(devm_phy_release, sizeof(*ptr), GFP_KERNEL);
>> + if (!ptr)
>> + return ERR_PTR(-ENOMEM);
>> +
>> + phy = phy_get_by_of_node(np);
> [Severity: High]
> This is a pre-existing issue, but does a TOCTOU race condition exist in the
> underlying phy_get_by_of_node() that could lead to a use-after-free here?
>
> Looking at phy_get_by_of_node(), it calls _of_phy_get_with_args() to look up
> the PHY. Inside _of_phy_get_with_args(), the function temporarily elevates the
> provider's module refcount, calls of_xlate() (which returns a bare phy
> pointer without incrementing the device refcount), and then drops the module
> refcount and unlocks phy_provider_mutex before returning the raw phy pointer.
This is an interesting idea.
Sounds not implausible and I haven't taken the mutex given in this file
which is used for adding.
Yes taking the phy_provider mutex seems warranted until the get_device()
completes.
Actually this is a result of functional decomposition so, I think I
should add a patch prior here to take the mutex and hold until the
get_device() in the existing code, then decompose that.
thx
---
bod
^ permalink raw reply [flat|nested] 17+ messages in thread
* Re: [PATCH v13 2/5] phy: core: Add devm_phy_get_by_of_node()
2026-07-28 9:35 ` [PATCH v13 2/5] phy: core: Add devm_phy_get_by_of_node() Bryan O'Donoghue
2026-07-28 9:47 ` sashiko-bot
@ 2026-07-28 10:46 ` Dmitry Baryshkov
2026-07-28 10:51 ` Bryan O'Donoghue
1 sibling, 1 reply; 17+ messages in thread
From: Dmitry Baryshkov @ 2026-07-28 10:46 UTC (permalink / raw)
To: Bryan O'Donoghue
Cc: Bjorn Andersson, Michael Turquette, Stephen Boyd, Rob Herring,
Krzysztof Kozlowski, Conor Dooley, Robert Foss, Todor Tomov,
Mauro Carvalho Chehab, Konrad Dybcio, Vladimir Zapolskiy,
Bryan O'Donoghue, Loic Poulain, Vinod Koul, Neil Armstrong,
linux-arm-msm, linux-clk, devicetree, linux-kernel, linux-media,
linux-phy, Krzysztof Kozlowski
On Tue, Jul 28, 2026 at 10:35:33AM +0100, Bryan O'Donoghue wrote:
> Add a devm variant of phy_get_by_of_node() to allow for the familiar
> pattern of having devres automatically release resources on the driver's
> exit path.
>
> Signed-off-by: Bryan O'Donoghue <bryan.odonoghue@linaro.org>
> ---
> drivers/phy/phy-core.c | 34 ++++++++++++++++++++++++++++++++++
> include/linux/phy/phy.h | 7 +++++++
> 2 files changed, 41 insertions(+)
>
> diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c
> index ebfad5325072e..7af24f2f4120f 100644
> --- a/drivers/phy/phy-core.c
> +++ b/drivers/phy/phy-core.c
> @@ -1029,6 +1029,40 @@ struct phy *phy_get_by_of_node(struct device_node *np)
> }
> EXPORT_SYMBOL_GPL(phy_get_by_of_node);
>
> +/**
> + * devm_phy_get_by_of_node() - devm managed lookup and obtain phy reference by device node
> + * @dev: device requesting the PHY
> + * @np: device_node of the PHY provider
> + *
> + * Returns phy associated with the device_node or ERR_PTR. devres manages
> + * releasing resources.
> + */
> +struct phy *devm_phy_get_by_of_node(struct device *dev, struct device_node *np)
> +{
> + struct phy **ptr, *phy;
> + struct device_link *link;
> +
> + ptr = devres_alloc(devm_phy_release, sizeof(*ptr), GFP_KERNEL);
> + if (!ptr)
> + return ERR_PTR(-ENOMEM);
> +
> + phy = phy_get_by_of_node(np);
> + if (IS_ERR(phy)) {
> + devres_free(ptr);
> + return phy;
> + }
> +
> + *ptr = phy;
> + devres_add(dev, ptr);
> + link = device_link_add(dev, &phy->dev, DL_FLAG_STATELESS);
Why are you adding devlink here?
> + if (!link)
> + dev_dbg(dev, "failed to create device link to %s\n",
> + dev_name(phy->dev.parent));
> +
> + return phy;
> +}
> +EXPORT_SYMBOL_GPL(devm_phy_get_by_of_node);
> +
> /**
> * phy_create() - create a new phy
> * @dev: device that is creating the new phy
> diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h
> index 71c2e16397130..14b924a88411f 100644
> --- a/include/linux/phy/phy.h
> +++ b/include/linux/phy/phy.h
> @@ -285,6 +285,7 @@ struct phy *devm_of_phy_optional_get(struct device *dev, struct device_node *np,
> struct phy *devm_of_phy_get_by_index(struct device *dev, struct device_node *np,
> int index);
> struct phy *phy_get_by_of_node(struct device_node *np);
> +struct phy *devm_phy_get_by_of_node(struct device *dev, struct device_node *np);
> void of_phy_put(struct phy *phy);
> void phy_put(struct device *dev, struct phy *phy);
> void devm_phy_put(struct device *dev, struct phy *phy);
> @@ -499,6 +500,12 @@ static inline struct phy *phy_get_by_of_node(struct device_node *np)
> return ERR_PTR(-ENOSYS);
> }
>
> +static inline struct phy *devm_phy_get_by_of_node(struct device *dev,
> + struct device_node *np)
> +{
> + return ERR_PTR(-ENOSYS);
> +}
> +
> static inline void of_phy_put(struct phy *phy)
> {
> }
>
> --
> 2.54.0
>
--
With best wishes
Dmitry
^ permalink raw reply [flat|nested] 17+ messages in thread* Re: [PATCH v13 2/5] phy: core: Add devm_phy_get_by_of_node()
2026-07-28 10:46 ` Dmitry Baryshkov
@ 2026-07-28 10:51 ` Bryan O'Donoghue
0 siblings, 0 replies; 17+ messages in thread
From: Bryan O'Donoghue @ 2026-07-28 10:51 UTC (permalink / raw)
To: Dmitry Baryshkov
Cc: Bjorn Andersson, Michael Turquette, Stephen Boyd, Rob Herring,
Krzysztof Kozlowski, Conor Dooley, Robert Foss, Todor Tomov,
Mauro Carvalho Chehab, Konrad Dybcio, Vladimir Zapolskiy,
Bryan O'Donoghue, Loic Poulain, Vinod Koul, Neil Armstrong,
linux-arm-msm, linux-clk, devicetree, linux-kernel, linux-media,
linux-phy, Krzysztof Kozlowski
On 28/07/2026 11:46, Dmitry Baryshkov wrote:
> On Tue, Jul 28, 2026 at 10:35:33AM +0100, Bryan O'Donoghue wrote:
>> Add a devm variant of phy_get_by_of_node() to allow for the familiar
>> pattern of having devres automatically release resources on the driver's
>> exit path.
>>
>> Signed-off-by: Bryan O'Donoghue<bryan.odonoghue@linaro.org>
>> ---
>> drivers/phy/phy-core.c | 34 ++++++++++++++++++++++++++++++++++
>> include/linux/phy/phy.h | 7 +++++++
>> 2 files changed, 41 insertions(+)
>>
>> diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c
>> index ebfad5325072e..7af24f2f4120f 100644
>> --- a/drivers/phy/phy-core.c
>> +++ b/drivers/phy/phy-core.c
>> @@ -1029,6 +1029,40 @@ struct phy *phy_get_by_of_node(struct device_node *np)
>> }
>> EXPORT_SYMBOL_GPL(phy_get_by_of_node);
>>
>> +/**
>> + * devm_phy_get_by_of_node() - devm managed lookup and obtain phy reference by device node
>> + * @dev: device requesting the PHY
>> + * @np: device_node of the PHY provider
>> + *
>> + * Returns phy associated with the device_node or ERR_PTR. devres manages
>> + * releasing resources.
>> + */
>> +struct phy *devm_phy_get_by_of_node(struct device *dev, struct device_node *np)
>> +{
>> + struct phy **ptr, *phy;
>> + struct device_link *link;
>> +
>> + ptr = devres_alloc(devm_phy_release, sizeof(*ptr), GFP_KERNEL);
>> + if (!ptr)
>> + return ERR_PTR(-ENOMEM);
>> +
>> + phy = phy_get_by_of_node(np);
>> + if (IS_ERR(phy)) {
>> + devres_free(ptr);
>> + return phy;
>> + }
>> +
>> + *ptr = phy;
>> + devres_add(dev, ptr);
>> + link = device_link_add(dev, &phy->dev, DL_FLAG_STATELESS);
> Why are you adding devlink here?
Looking at 987351e1ea77 ("phy: core: Add consumer device link support")
- adds this link to
phy_get()/devm_of_phy_get()/devm_of_phy_get_by_index() to enforce
suspend/resume ordering between PHY consumer and provider.
So the get_by_of_node() replicates that logic.
---
bod
^ permalink raw reply [flat|nested] 17+ messages in thread
* [PATCH v13 3/5] media: qcom: camss: Add support for PHY API devices
2026-07-28 9:35 [PATCH v13 0/5] Add dt-bindings and PHY updates for CAMSS on x1e80100 silicon Bryan O'Donoghue
2026-07-28 9:35 ` [PATCH v13 1/5] phy: core: Add phy_get_by_of_node() Bryan O'Donoghue
2026-07-28 9:35 ` [PATCH v13 2/5] phy: core: Add devm_phy_get_by_of_node() Bryan O'Donoghue
@ 2026-07-28 9:35 ` Bryan O'Donoghue
2026-07-28 9:51 ` sashiko-bot
` (2 more replies)
2026-07-28 9:35 ` [PATCH v13 4/5] dt-bindings: media: qcom,x1e80100-camss: Describe iommu entries Bryan O'Donoghue
2026-07-28 9:35 ` [PATCH v13 5/5] dt-bindings: media: qcom,x1e80100-camss: Make vdd-csiphy supplies optional Bryan O'Donoghue
4 siblings, 3 replies; 17+ messages in thread
From: Bryan O'Donoghue @ 2026-07-28 9:35 UTC (permalink / raw)
To: Bjorn Andersson, Michael Turquette, Stephen Boyd, Rob Herring,
Krzysztof Kozlowski, Conor Dooley, Robert Foss, Todor Tomov,
Mauro Carvalho Chehab, Konrad Dybcio, Vladimir Zapolskiy,
Bryan O'Donoghue, Loic Poulain, Vinod Koul, Neil Armstrong
Cc: linux-arm-msm, linux-clk, devicetree, linux-kernel, linux-media,
linux-phy, Bryan O'Donoghue, Krzysztof Kozlowski
Add the ability to use a PHY pointer which interacts with the standard PHY
API.
In the first instance the code will try to use the new PHY interface. If no
PHYs are present in the DT then the legacy method will be attempted.
Signed-off-by: Bryan O'Donoghue <bryan.odonoghue@linaro.org>
---
drivers/media/platform/qcom/camss/Kconfig | 1 +
drivers/media/platform/qcom/camss/camss-csiphy.c | 177 +++++++++++++++++++++--
drivers/media/platform/qcom/camss/camss-csiphy.h | 11 +-
drivers/media/platform/qcom/camss/camss.c | 104 +++++++++++--
drivers/media/platform/qcom/camss/camss.h | 1 +
5 files changed, 263 insertions(+), 31 deletions(-)
diff --git a/drivers/media/platform/qcom/camss/Kconfig b/drivers/media/platform/qcom/camss/Kconfig
index 4eda48cb1adf0..1edc5e5a1829e 100644
--- a/drivers/media/platform/qcom/camss/Kconfig
+++ b/drivers/media/platform/qcom/camss/Kconfig
@@ -7,3 +7,4 @@ config VIDEO_QCOM_CAMSS
select VIDEO_V4L2_SUBDEV_API
select VIDEOBUF2_DMA_SG
select V4L2_FWNODE
+ select PHY_QCOM_MIPI_CSI2
diff --git a/drivers/media/platform/qcom/camss/camss-csiphy.c b/drivers/media/platform/qcom/camss/camss-csiphy.c
index 539ac4888b608..e00748dd83b02 100644
--- a/drivers/media/platform/qcom/camss/camss-csiphy.c
+++ b/drivers/media/platform/qcom/camss/camss-csiphy.c
@@ -13,6 +13,8 @@
#include <linux/io.h>
#include <linux/kernel.h>
#include <linux/of.h>
+#include <linux/of_graph.h>
+#include <linux/phy/phy.h>
#include <linux/platform_device.h>
#include <linux/pm_runtime.h>
#include <media/media-entity.h>
@@ -131,10 +133,10 @@ static u8 csiphy_get_bpp(const struct csiphy_format_info *formats,
}
/*
- * csiphy_set_clock_rates - Calculate and set clock rates on CSIPHY module
+ * csiphy_set_clock_rates_legacy - Calculate and set clock rates on CSIPHY module
* @csiphy: CSIPHY device
*/
-static int csiphy_set_clock_rates(struct csiphy_device *csiphy)
+static int csiphy_set_clock_rates_legacy(struct csiphy_device *csiphy)
{
struct device *dev = csiphy->camss->dev;
s64 link_freq;
@@ -200,7 +202,7 @@ static int csiphy_set_clock_rates(struct csiphy_device *csiphy)
*
* Return 0 on success or a negative error code otherwise
*/
-static int csiphy_set_power(struct v4l2_subdev *sd, int on)
+static int csiphy_set_power_legacy(struct v4l2_subdev *sd, int on)
{
struct csiphy_device *csiphy = v4l2_get_subdevdata(sd);
struct device *dev = csiphy->camss->dev;
@@ -219,7 +221,7 @@ static int csiphy_set_power(struct v4l2_subdev *sd, int on)
return ret;
}
- ret = csiphy_set_clock_rates(csiphy);
+ ret = csiphy_set_clock_rates_legacy(csiphy);
if (ret < 0) {
regulator_bulk_disable(csiphy->num_supplies,
csiphy->supplies);
@@ -254,7 +256,7 @@ static int csiphy_set_power(struct v4l2_subdev *sd, int on)
}
/*
- * csiphy_stream_on - Enable streaming on CSIPHY module
+ * csiphy_stream_on_legacy - Enable streaming on CSIPHY module
* @csiphy: CSIPHY device
*
* Helper function to enable streaming on CSIPHY module.
@@ -262,7 +264,7 @@ static int csiphy_set_power(struct v4l2_subdev *sd, int on)
*
* Return 0 on success or a negative error code otherwise
*/
-static int csiphy_stream_on(struct csiphy_device *csiphy)
+static int csiphy_stream_on_legacy(struct csiphy_device *csiphy)
{
struct csiphy_config *cfg = &csiphy->cfg;
s64 link_freq;
@@ -306,11 +308,88 @@ static int csiphy_stream_on(struct csiphy_device *csiphy)
*
* Helper function to disable streaming on CSIPHY module
*/
-static void csiphy_stream_off(struct csiphy_device *csiphy)
+static void csiphy_stream_off_legacy(struct csiphy_device *csiphy)
{
csiphy->res->hw_ops->lanes_disable(csiphy, &csiphy->cfg);
}
+/*
+ * csiphy_stream_on - Enable streaming on CSIPHY module
+ * @csiphy: CSIPHY device
+ *
+ * Helper function to enable streaming on CSIPHY module.
+ * Main configuration of CSIPHY module is also done here.
+ *
+ * Return 0 on success or a negative error code otherwise
+ */
+static int csiphy_stream_on(struct csiphy_device *csiphy)
+{
+ u8 bpp = csiphy_get_bpp(csiphy->res->formats->formats, csiphy->res->formats->nformats,
+ csiphy->fmt[MSM_CSIPHY_PAD_SINK].code);
+ struct csiphy_lanes_cfg *lncfg = &csiphy->cfg.csi2->lane_cfg;
+ struct phy_configure_opts_mipi_dphy *dphy_cfg;
+ union phy_configure_opts dphy_opts = { 0 };
+ struct device *dev = csiphy->camss->dev;
+ u8 num_lanes = lncfg->num_data;
+ s64 link_freq;
+ int ret;
+
+ dphy_cfg = &dphy_opts.mipi_dphy;
+
+ link_freq = camss_get_link_freq(&csiphy->subdev.entity, bpp, num_lanes);
+
+ if (link_freq < 0) {
+ dev_err(dev,
+ "Cannot get CSI2 transmitter's link frequency\n");
+ return -EINVAL;
+ }
+
+ phy_mipi_dphy_get_default_config_for_hsclk(link_freq, num_lanes, dphy_cfg);
+
+ phy_set_mode(csiphy->phy, PHY_MODE_MIPI_DPHY);
+
+ ret = phy_configure(csiphy->phy, &dphy_opts);
+ if (ret) {
+ dev_err(dev, "failed to configure MIPI D-PHY\n");
+ goto error;
+ }
+
+ return phy_power_on(csiphy->phy);
+
+error:
+ return ret;
+}
+
+/*
+ * csiphy_stream_off - Disable streaming on CSIPHY module
+ * @csiphy: CSIPHY device
+ *
+ * Helper function to disable streaming on CSIPHY module
+ */
+static void csiphy_stream_off(struct csiphy_device *csiphy)
+{
+ phy_power_off(csiphy->phy);
+}
+
+/*
+ * csiphy_set_stream - Enable/disable streaming on CSIPHY module
+ * @sd: CSIPHY V4L2 subdevice
+ * @enable: Requested streaming state
+ *
+ * Return 0 on success or a negative error code otherwise
+ */
+static int csiphy_set_stream_legacy(struct v4l2_subdev *sd, int enable)
+{
+ struct csiphy_device *csiphy = v4l2_get_subdevdata(sd);
+ int ret = 0;
+
+ if (enable)
+ ret = csiphy_stream_on_legacy(csiphy);
+ else
+ csiphy_stream_off_legacy(csiphy);
+
+ return ret;
+}
/*
* csiphy_set_stream - Enable/disable streaming on CSIPHY module
@@ -572,16 +651,16 @@ csiphy_match_clock_name(const char *clock_name, const char *format, ...)
}
/*
- * msm_csiphy_subdev_init - Initialize CSIPHY device structure and resources
+ * msm_csiphy_subdev_init_legacy - Initialize CSIPHY device structure and resources
* @csiphy: CSIPHY device
* @res: CSIPHY module resources table
* @id: CSIPHY module id
*
* Return 0 on success or a negative error code otherwise
*/
-int msm_csiphy_subdev_init(struct camss *camss,
- struct csiphy_device *csiphy,
- const struct camss_subdev_resources *res, u8 id)
+int msm_csiphy_subdev_init_legacy(struct camss *camss,
+ struct csiphy_device *csiphy,
+ const struct camss_subdev_resources *res, u8 id)
{
struct device *dev = camss->dev;
struct platform_device *pdev = to_platform_device(dev);
@@ -709,6 +788,56 @@ int msm_csiphy_subdev_init(struct camss *camss,
return ret;
}
+/*
+ * msm_csiphy_subdev_init - Initialize CSIPHY device structure and resources
+ * @camss: CAMSS structure
+ * @port: DT port index
+ *
+ * Return 0 on success or absence of link, negative error code otherwise
+ */
+int msm_csiphy_subdev_init(struct camss *camss, u8 port)
+{
+ const struct camss_subdev_resources *res = &camss->res->csiphy_res[port];
+ struct csiphy_device *csiphy = &camss->csiphy[port];
+ struct device *dev = camss->dev;
+ struct device_node *ep, *remote;
+ int ret;
+
+ ep = of_graph_get_endpoint_by_regs(dev->of_node, port, -1);
+ if (!ep)
+ return 0;
+
+ remote = of_graph_get_remote_port_parent(ep);
+ of_node_put(ep);
+ if (!remote)
+ return 0;
+
+ if (!of_device_is_available(remote)) {
+ of_node_put(remote);
+ return 0;
+ }
+
+ csiphy->phy = devm_phy_get_by_of_node(dev, remote);
+ of_node_put(remote);
+ if (IS_ERR(csiphy->phy)) {
+ ret = PTR_ERR(csiphy->phy);
+ goto done;
+ }
+
+ csiphy->camss = camss;
+ csiphy->id = res->csiphy.id;
+ csiphy->res = &res->csiphy;
+
+ snprintf(csiphy->name, ARRAY_SIZE(csiphy->name), "csi%d", csiphy->id);
+
+ ret = phy_init(csiphy->phy);
+ if (ret)
+ dev_err(dev, "%s init fail %d\n", csiphy->name, ret);
+
+done:
+ return ret;
+}
+
/*
* csiphy_link_setup - Setup CSIPHY connections
* @entity: Pointer to media entity structure
@@ -743,8 +872,12 @@ static int csiphy_link_setup(struct media_entity *entity,
return 0;
}
-static const struct v4l2_subdev_core_ops csiphy_core_ops = {
- .s_power = csiphy_set_power,
+static const struct v4l2_subdev_core_ops csiphy_core_ops_legacy = {
+ .s_power = csiphy_set_power_legacy,
+};
+
+static const struct v4l2_subdev_video_ops csiphy_video_ops_legacy = {
+ .s_stream = csiphy_set_stream_legacy,
};
static const struct v4l2_subdev_video_ops csiphy_video_ops = {
@@ -758,8 +891,13 @@ static const struct v4l2_subdev_pad_ops csiphy_pad_ops = {
.set_fmt = csiphy_set_format,
};
+static const struct v4l2_subdev_ops csiphy_v4l2_ops_legacy = {
+ .core = &csiphy_core_ops_legacy,
+ .video = &csiphy_video_ops_legacy,
+ .pad = &csiphy_pad_ops,
+};
+
static const struct v4l2_subdev_ops csiphy_v4l2_ops = {
- .core = &csiphy_core_ops,
.video = &csiphy_video_ops,
.pad = &csiphy_pad_ops,
};
@@ -785,10 +923,15 @@ int msm_csiphy_register_entity(struct csiphy_device *csiphy,
{
struct v4l2_subdev *sd = &csiphy->subdev;
struct media_pad *pads = csiphy->pads;
- struct device *dev = csiphy->camss->dev;
+ struct camss *camss = csiphy->camss;
+ struct device *dev = camss->dev;
int ret;
- v4l2_subdev_init(sd, &csiphy_v4l2_ops);
+ if (camss->legacy_phy)
+ v4l2_subdev_init(sd, &csiphy_v4l2_ops_legacy);
+ else
+ v4l2_subdev_init(sd, &csiphy_v4l2_ops);
+
sd->internal_ops = &csiphy_v4l2_internal_ops;
sd->flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
snprintf(sd->name, ARRAY_SIZE(sd->name), "%s%d",
@@ -828,6 +971,8 @@ int msm_csiphy_register_entity(struct csiphy_device *csiphy,
*/
void msm_csiphy_unregister_entity(struct csiphy_device *csiphy)
{
+ if (!IS_ERR(csiphy->phy))
+ phy_exit(csiphy->phy);
v4l2_device_unregister_subdev(&csiphy->subdev);
media_entity_cleanup(&csiphy->subdev.entity);
}
diff --git a/drivers/media/platform/qcom/camss/camss-csiphy.h b/drivers/media/platform/qcom/camss/camss-csiphy.h
index 9d9657b82f748..7a357044b9fdb 100644
--- a/drivers/media/platform/qcom/camss/camss-csiphy.h
+++ b/drivers/media/platform/qcom/camss/camss-csiphy.h
@@ -12,6 +12,7 @@
#include <linux/clk.h>
#include <linux/interrupt.h>
+#include <linux/phy/phy.h>
#include <media/media-entity.h>
#include <media/v4l2-device.h>
#include <media/v4l2-mediabus.h>
@@ -97,6 +98,7 @@ struct csiphy_device_regs {
struct csiphy_device {
struct camss *camss;
+ struct phy *phy;
u8 id;
struct v4l2_subdev subdev;
struct media_pad pads[MSM_CSIPHY_PADS_NUM];
@@ -104,6 +106,7 @@ struct csiphy_device {
void __iomem *base_clk_mux;
u32 irq;
char irq_name[30];
+ char name[16];
struct camss_clock *clock;
bool *rate_set;
int nclocks;
@@ -118,9 +121,11 @@ struct csiphy_device {
struct camss_subdev_resources;
-int msm_csiphy_subdev_init(struct camss *camss,
- struct csiphy_device *csiphy,
- const struct camss_subdev_resources *res, u8 id);
+int msm_csiphy_subdev_init_legacy(struct camss *camss,
+ struct csiphy_device *csiphy,
+ const struct camss_subdev_resources *res, u8 id);
+
+int msm_csiphy_subdev_init(struct camss *camss, u8 port);
int msm_csiphy_register_entity(struct csiphy_device *csiphy,
struct v4l2_device *v4l2_dev);
diff --git a/drivers/media/platform/qcom/camss/camss.c b/drivers/media/platform/qcom/camss/camss.c
index 2123f6388e3d7..84097d82d99c9 100644
--- a/drivers/media/platform/qcom/camss/camss.c
+++ b/drivers/media/platform/qcom/camss/camss.c
@@ -4799,8 +4799,43 @@ static int camss_parse_ports(struct camss *camss)
fwnode_graph_for_each_endpoint(fwnode, ep) {
struct camss_async_subdev *csd;
- csd = v4l2_async_nf_add_fwnode_remote(&camss->notifier, ep,
- typeof(*csd));
+ if (!fwnode_device_is_available(ep))
+ continue;
+
+ if (camss->legacy_phy) {
+ csd = v4l2_async_nf_add_fwnode_remote(&camss->notifier, ep,
+ typeof(*csd));
+ } else {
+ struct fwnode_handle *phy_out, *phy_node, *phy_in, *sensor_ep;
+
+ phy_out = fwnode_graph_get_remote_endpoint(ep);
+ if (!phy_out)
+ continue;
+
+ phy_node = fwnode_graph_get_port_parent(phy_out);
+ fwnode_handle_put(phy_out);
+ if (!phy_node)
+ continue;
+
+ phy_in = fwnode_graph_get_endpoint_by_id(phy_node, 0, 0, 0);
+ fwnode_handle_put(phy_node);
+ if (!phy_in)
+ continue;
+
+ sensor_ep = fwnode_graph_get_remote_endpoint(phy_in);
+ fwnode_handle_put(phy_in);
+ if (!sensor_ep)
+ continue;
+
+ csd = v4l2_async_nf_add_fwnode(&camss->notifier, sensor_ep,
+ struct camss_async_subdev);
+ fwnode_handle_put(sensor_ep);
+ if (IS_ERR(csd)) {
+ ret = PTR_ERR(csd);
+ goto err_cleanup;
+ }
+ }
+
if (IS_ERR(csd)) {
ret = PTR_ERR(csd);
goto err_cleanup;
@@ -4819,6 +4854,29 @@ static int camss_parse_ports(struct camss *camss)
return ret;
}
+static void camss_detect_legacy_phy(struct camss *camss)
+{
+ struct device_node *remote;
+ struct device_node *ep;
+
+ camss->legacy_phy = true;
+
+ /* Find first remote-endpoint and determine if its a PHY */
+ for_each_endpoint_of_node(camss->dev->of_node, ep) {
+ remote = of_graph_get_remote_port_parent(ep);
+ if (!remote)
+ continue;
+
+ camss->legacy_phy = !of_node_name_eq(remote, "phy");
+ of_node_put(remote);
+ of_node_put(ep);
+ break;
+ }
+
+ dev_dbg(camss->dev, "legacy phy mode %s\n",
+ camss->legacy_phy ? "true" : "false");
+}
+
/*
* camss_init_subdevices - Initialize subdev structures and resources
* @camss: CAMSS device
@@ -4832,14 +4890,21 @@ static int camss_init_subdevices(struct camss *camss)
unsigned int i;
int ret;
+ camss_detect_legacy_phy(camss);
+
for (i = 0; i < camss->res->csiphy_num; i++) {
- ret = msm_csiphy_subdev_init(camss, &camss->csiphy[i],
- &res->csiphy_res[i],
- res->csiphy_res[i].csiphy.id);
+ if (!camss->legacy_phy) {
+ ret = msm_csiphy_subdev_init(camss, i);
+ } else {
+ ret = msm_csiphy_subdev_init_legacy(camss,
+ &camss->csiphy[i],
+ &res->csiphy_res[i],
+ res->csiphy_res[i].csiphy.id);
+ }
+
if (ret < 0) {
- dev_err(camss->dev,
- "Failed to init csiphy%d sub-device: %d\n",
- i, ret);
+ dev_err(camss->dev, "csiphy %d init fail\n",
+ res->csiphy_res[i].csiphy.id);
return ret;
}
}
@@ -4917,6 +4982,11 @@ inline void camss_link_err(struct camss *camss,
ret);
}
+static inline bool csiphy_enabled(struct camss *camss, struct csiphy_device *c)
+{
+ return camss->legacy_phy || c->phy;
+}
+
/*
* camss_link_entities - Register subdev nodes and create links
* @camss: CAMSS device
@@ -4930,6 +5000,9 @@ static int camss_link_entities(struct camss *camss)
for (i = 0; i < camss->res->csiphy_num; i++) {
for (j = 0; j < camss->res->csid_num; j++) {
+ if (!csiphy_enabled(camss, &camss->csiphy[i]))
+ continue;
+
ret = media_create_pad_link(&camss->csiphy[i].subdev.entity,
MSM_CSIPHY_PAD_SRC,
&camss->csid[j].subdev.entity,
@@ -5056,6 +5129,9 @@ static int camss_register_entities(struct camss *camss)
int ret;
for (i = 0; i < camss->res->csiphy_num; i++) {
+ if (!csiphy_enabled(camss, &camss->csiphy[i]))
+ continue;
+
ret = msm_csiphy_register_entity(&camss->csiphy[i],
&camss->v4l2_dev);
if (ret < 0) {
@@ -5131,8 +5207,10 @@ static int camss_register_entities(struct camss *camss)
i = camss->res->csiphy_num;
err_reg_csiphy:
- for (i--; i >= 0; i--)
- msm_csiphy_unregister_entity(&camss->csiphy[i]);
+ for (i--; i >= 0; i--) {
+ if (csiphy_enabled(camss, &camss->csiphy[i]))
+ msm_csiphy_unregister_entity(&camss->csiphy[i]);
+ }
return ret;
}
@@ -5147,8 +5225,10 @@ static void camss_unregister_entities(struct camss *camss)
{
unsigned int i;
- for (i = 0; i < camss->res->csiphy_num; i++)
- msm_csiphy_unregister_entity(&camss->csiphy[i]);
+ for (i = 0; i < camss->res->csiphy_num; i++) {
+ if (csiphy_enabled(camss, &camss->csiphy[i]))
+ msm_csiphy_unregister_entity(&camss->csiphy[i]);
+ }
if (camss->tpg) {
for (i = 0; i < camss->res->tpg_num; i++)
diff --git a/drivers/media/platform/qcom/camss/camss.h b/drivers/media/platform/qcom/camss/camss.h
index 93d691c8ac63b..ba3d51d9c0bf8 100644
--- a/drivers/media/platform/qcom/camss/camss.h
+++ b/drivers/media/platform/qcom/camss/camss.h
@@ -138,6 +138,7 @@ struct camss {
struct device_link *genpd_link;
struct icc_path *icc_path[ICC_SM8250_COUNT];
const struct camss_resources *res;
+ bool legacy_phy;
};
struct camss_camera_interface {
--
2.54.0
^ permalink raw reply related [flat|nested] 17+ messages in thread* Re: [PATCH v13 3/5] media: qcom: camss: Add support for PHY API devices
2026-07-28 9:35 ` [PATCH v13 3/5] media: qcom: camss: Add support for PHY API devices Bryan O'Donoghue
@ 2026-07-28 9:51 ` sashiko-bot
2026-07-28 10:48 ` Dmitry Baryshkov
2026-07-28 11:02 ` Loic Poulain
2 siblings, 0 replies; 17+ messages in thread
From: sashiko-bot @ 2026-07-28 9:51 UTC (permalink / raw)
To: Bryan O'Donoghue
Cc: vkoul, conor+dt, linux-phy, devicetree, media-ci, olteanv, robh,
neil.armstrong
Thank you for your contribution! Sashiko AI review found 4 potential issue(s) to consider:
New issues:
- [Medium] The Kconfig symbol VIDEO_QCOM_CAMSS selects a non-existent symbol PHY_QCOM_MIPI_CSI2.
- [Medium] Missing phy_exit() calls on probe error paths leak initialized PHY hardware states.
- [Medium] The return value of phy_mipi_dphy_get_default_config_for_hsclk() is ignored.
Pre-existing issues:
- [High] Dereferencing csiphy->cfg.csi2 without checking causes a NULL pointer dereference if no sensor is bound.
--
--- Patch [3]: [PATCH v13 3/5] media: qcom: camss: Add support for PHY API devices ---
commit 7ad9edf4c6cb1def82d912d6116e4eddc0da65e4
Author: Bryan O'Donoghue <bryan.odonoghue@linaro.org>
media: qcom: camss: Add support for PHY API devices
Add the ability to use a PHY pointer which interacts with the standard PHY
API. In the first instance the code will try to use the new PHY interface.
If no PHYs are present in the DT then the legacy method will be attempted.
> diff --git a/drivers/media/platform/qcom/camss/Kconfig b/drivers/media/platform/qcom/camss/Kconfig
> index 4eda48cb1adf0..1edc5e5a1829e 100644
> --- a/drivers/media/platform/qcom/camss/Kconfig
> +++ b/drivers/media/platform/qcom/camss/Kconfig
> @@ -7,3 +7,4 @@ config VIDEO_QCOM_CAMSS
> select VIDEO_V4L2_SUBDEV_API
> select VIDEOBUF2_DMA_SG
> select V4L2_FWNODE
> + select PHY_QCOM_MIPI_CSI2
[Severity: Medium]
Does the PHY_QCOM_MIPI_CSI2 config symbol exist in the tree?
It looks like VIDEO_QCOM_CAMSS selects a non-existent symbol here, which
could lead to unmet dependencies or silent configuration issues where the
feature remains disabled.
> diff --git a/drivers/media/platform/qcom/camss/camss-csiphy.c b/drivers/media/platform/qcom/camss/camss-csiphy.c
> index 539ac4888b608..e00748dd83b02 100644
> --- a/drivers/media/platform/qcom/camss/camss-csiphy.c
> +++ b/drivers/media/platform/qcom/camss/camss-csiphy.c
[ ... ]
> +static int csiphy_stream_on(struct csiphy_device *csiphy)
> +{
> + u8 bpp = csiphy_get_bpp(csiphy->res->formats->formats, csiphy->res->formats->nformats,
> + csiphy->fmt[MSM_CSIPHY_PAD_SINK].code);
> + struct csiphy_lanes_cfg *lncfg = &csiphy->cfg.csi2->lane_cfg;
[Severity: High]
This is a pre-existing issue, but can this dereference csiphy->cfg.csi2
while it is NULL if no remote sensor endpoint is defined in the Device Tree?
Since csiphy->cfg.csi2 is populated exclusively in the async notifier's
bound callback (camss_subdev_notifier_bound), if no sensor is bound, could
an unprivileged user trigger a NULL pointer dereference by calling the
VIDIOC_SUBDEV_S_STREAM ioctl on the /dev/v4l-subdevX node?
> + struct phy_configure_opts_mipi_dphy *dphy_cfg;
> + union phy_configure_opts dphy_opts = { 0 };
> + struct device *dev = csiphy->camss->dev;
> + u8 num_lanes = lncfg->num_data;
> + s64 link_freq;
> + int ret;
> +
> + dphy_cfg = &dphy_opts.mipi_dphy;
> +
> + link_freq = camss_get_link_freq(&csiphy->subdev.entity, bpp, num_lanes);
> +
> + if (link_freq < 0) {
> + dev_err(dev,
> + "Cannot get CSI2 transmitter's link frequency\n");
> + return -EINVAL;
> + }
> +
> + phy_mipi_dphy_get_default_config_for_hsclk(link_freq, num_lanes, dphy_cfg);
[Severity: Medium]
Does phy_mipi_dphy_get_default_config_for_hsclk() return an error code that
should be checked here?
If it fails, dphy_opts might remain zero-initialized when passed to
phy_configure() below.
> +
> + phy_set_mode(csiphy->phy, PHY_MODE_MIPI_DPHY);
> +
> + ret = phy_configure(csiphy->phy, &dphy_opts);
[ ... ]
> diff --git a/drivers/media/platform/qcom/camss/camss.c b/drivers/media/platform/qcom/camss/camss.c
> index 2123f6388e3d7..84097d82d99c9 100644
> --- a/drivers/media/platform/qcom/camss/camss.c
> +++ b/drivers/media/platform/qcom/camss/camss.c
[ ... ]
> @@ -5131,8 +5207,10 @@ static int camss_register_entities(struct camss *camss)
>
> i = camss->res->csiphy_num;
> err_reg_csiphy:
> - for (i--; i >= 0; i--)
> - msm_csiphy_unregister_entity(&camss->csiphy[i]);
> + for (i--; i >= 0; i--) {
> + if (csiphy_enabled(camss, &camss->csiphy[i]))
> + msm_csiphy_unregister_entity(&camss->csiphy[i]);
> + }
>
> return ret;
> }
[Severity: Medium]
Does this error path leak the PHY hardware states?
In camss_init_subdevices(), phy_init() is called for each CSIPHY port.
If camss_register_entities() fails on index 'i', this rollback loop starts
at 'i--', skipping the unregistration (and therefore phy_exit()) for the
failing index 'i' and any other initialized PHYs that hadn't been processed
yet.
Likewise, if probe fails later and jumps to err_genpd_cleanup in
camss_probe(), are the previously initialized PHY states properly cleaned up?
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260728-b4-linux-next-25-03-13-dtsi-x1e80100-camss-v13-0-ae811e2f0799@linaro.org?part=3
^ permalink raw reply [flat|nested] 17+ messages in thread* Re: [PATCH v13 3/5] media: qcom: camss: Add support for PHY API devices
2026-07-28 9:35 ` [PATCH v13 3/5] media: qcom: camss: Add support for PHY API devices Bryan O'Donoghue
2026-07-28 9:51 ` sashiko-bot
@ 2026-07-28 10:48 ` Dmitry Baryshkov
2026-07-28 11:02 ` Loic Poulain
2 siblings, 0 replies; 17+ messages in thread
From: Dmitry Baryshkov @ 2026-07-28 10:48 UTC (permalink / raw)
To: Bryan O'Donoghue
Cc: Bjorn Andersson, Michael Turquette, Stephen Boyd, Rob Herring,
Krzysztof Kozlowski, Conor Dooley, Robert Foss, Todor Tomov,
Mauro Carvalho Chehab, Konrad Dybcio, Vladimir Zapolskiy,
Bryan O'Donoghue, Loic Poulain, Vinod Koul, Neil Armstrong,
linux-arm-msm, linux-clk, devicetree, linux-kernel, linux-media,
linux-phy, Krzysztof Kozlowski
On Tue, Jul 28, 2026 at 10:35:34AM +0100, Bryan O'Donoghue wrote:
> Add the ability to use a PHY pointer which interacts with the standard PHY
> API.
>
> In the first instance the code will try to use the new PHY interface. If no
> PHYs are present in the DT then the legacy method will be attempted.
>
> Signed-off-by: Bryan O'Donoghue <bryan.odonoghue@linaro.org>
> ---
> drivers/media/platform/qcom/camss/Kconfig | 1 +
> drivers/media/platform/qcom/camss/camss-csiphy.c | 177 +++++++++++++++++++++--
> drivers/media/platform/qcom/camss/camss-csiphy.h | 11 +-
> drivers/media/platform/qcom/camss/camss.c | 104 +++++++++++--
> drivers/media/platform/qcom/camss/camss.h | 1 +
> 5 files changed, 263 insertions(+), 31 deletions(-)
>
This is nice
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
.
--
With best wishes
Dmitry
^ permalink raw reply [flat|nested] 17+ messages in thread
* Re: [PATCH v13 3/5] media: qcom: camss: Add support for PHY API devices
2026-07-28 9:35 ` [PATCH v13 3/5] media: qcom: camss: Add support for PHY API devices Bryan O'Donoghue
2026-07-28 9:51 ` sashiko-bot
2026-07-28 10:48 ` Dmitry Baryshkov
@ 2026-07-28 11:02 ` Loic Poulain
2 siblings, 0 replies; 17+ messages in thread
From: Loic Poulain @ 2026-07-28 11:02 UTC (permalink / raw)
To: Bryan O'Donoghue
Cc: Bjorn Andersson, Michael Turquette, Stephen Boyd, Rob Herring,
Krzysztof Kozlowski, Conor Dooley, Robert Foss, Todor Tomov,
Mauro Carvalho Chehab, Konrad Dybcio, Vladimir Zapolskiy,
Bryan O'Donoghue, Vinod Koul, Neil Armstrong, linux-arm-msm,
linux-clk, devicetree, linux-kernel, linux-media, linux-phy,
Krzysztof Kozlowski
On Tue, Jul 28, 2026 at 11:35 AM Bryan O'Donoghue
<bryan.odonoghue@linaro.org> wrote:
>
> Add the ability to use a PHY pointer which interacts with the standard PHY
> API.
>
> In the first instance the code will try to use the new PHY interface. If no
> PHYs are present in the DT then the legacy method will be attempted.
>
> Signed-off-by: Bryan O'Donoghue <bryan.odonoghue@linaro.org>
Reviewed-by: Loic Poulain <loic.poulain@oss.qualcomm.com>
> ---
> drivers/media/platform/qcom/camss/Kconfig | 1 +
> drivers/media/platform/qcom/camss/camss-csiphy.c | 177 +++++++++++++++++++++--
> drivers/media/platform/qcom/camss/camss-csiphy.h | 11 +-
> drivers/media/platform/qcom/camss/camss.c | 104 +++++++++++--
> drivers/media/platform/qcom/camss/camss.h | 1 +
> 5 files changed, 263 insertions(+), 31 deletions(-)
>
> diff --git a/drivers/media/platform/qcom/camss/Kconfig b/drivers/media/platform/qcom/camss/Kconfig
> index 4eda48cb1adf0..1edc5e5a1829e 100644
> --- a/drivers/media/platform/qcom/camss/Kconfig
> +++ b/drivers/media/platform/qcom/camss/Kconfig
> @@ -7,3 +7,4 @@ config VIDEO_QCOM_CAMSS
> select VIDEO_V4L2_SUBDEV_API
> select VIDEOBUF2_DMA_SG
> select V4L2_FWNODE
> + select PHY_QCOM_MIPI_CSI2
> diff --git a/drivers/media/platform/qcom/camss/camss-csiphy.c b/drivers/media/platform/qcom/camss/camss-csiphy.c
> index 539ac4888b608..e00748dd83b02 100644
> --- a/drivers/media/platform/qcom/camss/camss-csiphy.c
> +++ b/drivers/media/platform/qcom/camss/camss-csiphy.c
> @@ -13,6 +13,8 @@
> #include <linux/io.h>
> #include <linux/kernel.h>
> #include <linux/of.h>
> +#include <linux/of_graph.h>
> +#include <linux/phy/phy.h>
> #include <linux/platform_device.h>
> #include <linux/pm_runtime.h>
> #include <media/media-entity.h>
> @@ -131,10 +133,10 @@ static u8 csiphy_get_bpp(const struct csiphy_format_info *formats,
> }
>
> /*
> - * csiphy_set_clock_rates - Calculate and set clock rates on CSIPHY module
> + * csiphy_set_clock_rates_legacy - Calculate and set clock rates on CSIPHY module
> * @csiphy: CSIPHY device
> */
> -static int csiphy_set_clock_rates(struct csiphy_device *csiphy)
> +static int csiphy_set_clock_rates_legacy(struct csiphy_device *csiphy)
> {
> struct device *dev = csiphy->camss->dev;
> s64 link_freq;
> @@ -200,7 +202,7 @@ static int csiphy_set_clock_rates(struct csiphy_device *csiphy)
> *
> * Return 0 on success or a negative error code otherwise
> */
> -static int csiphy_set_power(struct v4l2_subdev *sd, int on)
> +static int csiphy_set_power_legacy(struct v4l2_subdev *sd, int on)
> {
> struct csiphy_device *csiphy = v4l2_get_subdevdata(sd);
> struct device *dev = csiphy->camss->dev;
> @@ -219,7 +221,7 @@ static int csiphy_set_power(struct v4l2_subdev *sd, int on)
> return ret;
> }
>
> - ret = csiphy_set_clock_rates(csiphy);
> + ret = csiphy_set_clock_rates_legacy(csiphy);
> if (ret < 0) {
> regulator_bulk_disable(csiphy->num_supplies,
> csiphy->supplies);
> @@ -254,7 +256,7 @@ static int csiphy_set_power(struct v4l2_subdev *sd, int on)
> }
>
> /*
> - * csiphy_stream_on - Enable streaming on CSIPHY module
> + * csiphy_stream_on_legacy - Enable streaming on CSIPHY module
> * @csiphy: CSIPHY device
> *
> * Helper function to enable streaming on CSIPHY module.
> @@ -262,7 +264,7 @@ static int csiphy_set_power(struct v4l2_subdev *sd, int on)
> *
> * Return 0 on success or a negative error code otherwise
> */
> -static int csiphy_stream_on(struct csiphy_device *csiphy)
> +static int csiphy_stream_on_legacy(struct csiphy_device *csiphy)
> {
> struct csiphy_config *cfg = &csiphy->cfg;
> s64 link_freq;
> @@ -306,11 +308,88 @@ static int csiphy_stream_on(struct csiphy_device *csiphy)
> *
> * Helper function to disable streaming on CSIPHY module
> */
> -static void csiphy_stream_off(struct csiphy_device *csiphy)
> +static void csiphy_stream_off_legacy(struct csiphy_device *csiphy)
> {
> csiphy->res->hw_ops->lanes_disable(csiphy, &csiphy->cfg);
> }
>
> +/*
> + * csiphy_stream_on - Enable streaming on CSIPHY module
> + * @csiphy: CSIPHY device
> + *
> + * Helper function to enable streaming on CSIPHY module.
> + * Main configuration of CSIPHY module is also done here.
> + *
> + * Return 0 on success or a negative error code otherwise
> + */
> +static int csiphy_stream_on(struct csiphy_device *csiphy)
> +{
> + u8 bpp = csiphy_get_bpp(csiphy->res->formats->formats, csiphy->res->formats->nformats,
> + csiphy->fmt[MSM_CSIPHY_PAD_SINK].code);
> + struct csiphy_lanes_cfg *lncfg = &csiphy->cfg.csi2->lane_cfg;
> + struct phy_configure_opts_mipi_dphy *dphy_cfg;
> + union phy_configure_opts dphy_opts = { 0 };
> + struct device *dev = csiphy->camss->dev;
> + u8 num_lanes = lncfg->num_data;
> + s64 link_freq;
> + int ret;
> +
> + dphy_cfg = &dphy_opts.mipi_dphy;
> +
> + link_freq = camss_get_link_freq(&csiphy->subdev.entity, bpp, num_lanes);
> +
> + if (link_freq < 0) {
> + dev_err(dev,
> + "Cannot get CSI2 transmitter's link frequency\n");
> + return -EINVAL;
> + }
> +
> + phy_mipi_dphy_get_default_config_for_hsclk(link_freq, num_lanes, dphy_cfg);
> +
> + phy_set_mode(csiphy->phy, PHY_MODE_MIPI_DPHY);
> +
> + ret = phy_configure(csiphy->phy, &dphy_opts);
> + if (ret) {
> + dev_err(dev, "failed to configure MIPI D-PHY\n");
> + goto error;
> + }
> +
> + return phy_power_on(csiphy->phy);
> +
> +error:
> + return ret;
> +}
> +
> +/*
> + * csiphy_stream_off - Disable streaming on CSIPHY module
> + * @csiphy: CSIPHY device
> + *
> + * Helper function to disable streaming on CSIPHY module
> + */
> +static void csiphy_stream_off(struct csiphy_device *csiphy)
> +{
> + phy_power_off(csiphy->phy);
> +}
> +
> +/*
> + * csiphy_set_stream - Enable/disable streaming on CSIPHY module
> + * @sd: CSIPHY V4L2 subdevice
> + * @enable: Requested streaming state
> + *
> + * Return 0 on success or a negative error code otherwise
> + */
> +static int csiphy_set_stream_legacy(struct v4l2_subdev *sd, int enable)
> +{
> + struct csiphy_device *csiphy = v4l2_get_subdevdata(sd);
> + int ret = 0;
> +
> + if (enable)
> + ret = csiphy_stream_on_legacy(csiphy);
> + else
> + csiphy_stream_off_legacy(csiphy);
> +
> + return ret;
> +}
>
> /*
> * csiphy_set_stream - Enable/disable streaming on CSIPHY module
> @@ -572,16 +651,16 @@ csiphy_match_clock_name(const char *clock_name, const char *format, ...)
> }
>
> /*
> - * msm_csiphy_subdev_init - Initialize CSIPHY device structure and resources
> + * msm_csiphy_subdev_init_legacy - Initialize CSIPHY device structure and resources
> * @csiphy: CSIPHY device
> * @res: CSIPHY module resources table
> * @id: CSIPHY module id
> *
> * Return 0 on success or a negative error code otherwise
> */
> -int msm_csiphy_subdev_init(struct camss *camss,
> - struct csiphy_device *csiphy,
> - const struct camss_subdev_resources *res, u8 id)
> +int msm_csiphy_subdev_init_legacy(struct camss *camss,
> + struct csiphy_device *csiphy,
> + const struct camss_subdev_resources *res, u8 id)
> {
> struct device *dev = camss->dev;
> struct platform_device *pdev = to_platform_device(dev);
> @@ -709,6 +788,56 @@ int msm_csiphy_subdev_init(struct camss *camss,
> return ret;
> }
>
> +/*
> + * msm_csiphy_subdev_init - Initialize CSIPHY device structure and resources
> + * @camss: CAMSS structure
> + * @port: DT port index
> + *
> + * Return 0 on success or absence of link, negative error code otherwise
> + */
> +int msm_csiphy_subdev_init(struct camss *camss, u8 port)
> +{
> + const struct camss_subdev_resources *res = &camss->res->csiphy_res[port];
> + struct csiphy_device *csiphy = &camss->csiphy[port];
> + struct device *dev = camss->dev;
> + struct device_node *ep, *remote;
> + int ret;
> +
> + ep = of_graph_get_endpoint_by_regs(dev->of_node, port, -1);
> + if (!ep)
> + return 0;
> +
> + remote = of_graph_get_remote_port_parent(ep);
> + of_node_put(ep);
> + if (!remote)
> + return 0;
> +
> + if (!of_device_is_available(remote)) {
> + of_node_put(remote);
> + return 0;
> + }
> +
> + csiphy->phy = devm_phy_get_by_of_node(dev, remote);
> + of_node_put(remote);
> + if (IS_ERR(csiphy->phy)) {
> + ret = PTR_ERR(csiphy->phy);
> + goto done;
> + }
> +
> + csiphy->camss = camss;
> + csiphy->id = res->csiphy.id;
> + csiphy->res = &res->csiphy;
> +
> + snprintf(csiphy->name, ARRAY_SIZE(csiphy->name), "csi%d", csiphy->id);
> +
> + ret = phy_init(csiphy->phy);
> + if (ret)
> + dev_err(dev, "%s init fail %d\n", csiphy->name, ret);
> +
> +done:
> + return ret;
> +}
> +
> /*
> * csiphy_link_setup - Setup CSIPHY connections
> * @entity: Pointer to media entity structure
> @@ -743,8 +872,12 @@ static int csiphy_link_setup(struct media_entity *entity,
> return 0;
> }
>
> -static const struct v4l2_subdev_core_ops csiphy_core_ops = {
> - .s_power = csiphy_set_power,
> +static const struct v4l2_subdev_core_ops csiphy_core_ops_legacy = {
> + .s_power = csiphy_set_power_legacy,
> +};
> +
> +static const struct v4l2_subdev_video_ops csiphy_video_ops_legacy = {
> + .s_stream = csiphy_set_stream_legacy,
> };
>
> static const struct v4l2_subdev_video_ops csiphy_video_ops = {
> @@ -758,8 +891,13 @@ static const struct v4l2_subdev_pad_ops csiphy_pad_ops = {
> .set_fmt = csiphy_set_format,
> };
>
> +static const struct v4l2_subdev_ops csiphy_v4l2_ops_legacy = {
> + .core = &csiphy_core_ops_legacy,
> + .video = &csiphy_video_ops_legacy,
> + .pad = &csiphy_pad_ops,
> +};
> +
> static const struct v4l2_subdev_ops csiphy_v4l2_ops = {
> - .core = &csiphy_core_ops,
> .video = &csiphy_video_ops,
> .pad = &csiphy_pad_ops,
> };
> @@ -785,10 +923,15 @@ int msm_csiphy_register_entity(struct csiphy_device *csiphy,
> {
> struct v4l2_subdev *sd = &csiphy->subdev;
> struct media_pad *pads = csiphy->pads;
> - struct device *dev = csiphy->camss->dev;
> + struct camss *camss = csiphy->camss;
> + struct device *dev = camss->dev;
> int ret;
>
> - v4l2_subdev_init(sd, &csiphy_v4l2_ops);
> + if (camss->legacy_phy)
> + v4l2_subdev_init(sd, &csiphy_v4l2_ops_legacy);
> + else
> + v4l2_subdev_init(sd, &csiphy_v4l2_ops);
> +
> sd->internal_ops = &csiphy_v4l2_internal_ops;
> sd->flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
> snprintf(sd->name, ARRAY_SIZE(sd->name), "%s%d",
> @@ -828,6 +971,8 @@ int msm_csiphy_register_entity(struct csiphy_device *csiphy,
> */
> void msm_csiphy_unregister_entity(struct csiphy_device *csiphy)
> {
> + if (!IS_ERR(csiphy->phy))
> + phy_exit(csiphy->phy);
> v4l2_device_unregister_subdev(&csiphy->subdev);
> media_entity_cleanup(&csiphy->subdev.entity);
> }
> diff --git a/drivers/media/platform/qcom/camss/camss-csiphy.h b/drivers/media/platform/qcom/camss/camss-csiphy.h
> index 9d9657b82f748..7a357044b9fdb 100644
> --- a/drivers/media/platform/qcom/camss/camss-csiphy.h
> +++ b/drivers/media/platform/qcom/camss/camss-csiphy.h
> @@ -12,6 +12,7 @@
>
> #include <linux/clk.h>
> #include <linux/interrupt.h>
> +#include <linux/phy/phy.h>
> #include <media/media-entity.h>
> #include <media/v4l2-device.h>
> #include <media/v4l2-mediabus.h>
> @@ -97,6 +98,7 @@ struct csiphy_device_regs {
>
> struct csiphy_device {
> struct camss *camss;
> + struct phy *phy;
> u8 id;
> struct v4l2_subdev subdev;
> struct media_pad pads[MSM_CSIPHY_PADS_NUM];
> @@ -104,6 +106,7 @@ struct csiphy_device {
> void __iomem *base_clk_mux;
> u32 irq;
> char irq_name[30];
> + char name[16];
> struct camss_clock *clock;
> bool *rate_set;
> int nclocks;
> @@ -118,9 +121,11 @@ struct csiphy_device {
>
> struct camss_subdev_resources;
>
> -int msm_csiphy_subdev_init(struct camss *camss,
> - struct csiphy_device *csiphy,
> - const struct camss_subdev_resources *res, u8 id);
> +int msm_csiphy_subdev_init_legacy(struct camss *camss,
> + struct csiphy_device *csiphy,
> + const struct camss_subdev_resources *res, u8 id);
> +
> +int msm_csiphy_subdev_init(struct camss *camss, u8 port);
>
> int msm_csiphy_register_entity(struct csiphy_device *csiphy,
> struct v4l2_device *v4l2_dev);
> diff --git a/drivers/media/platform/qcom/camss/camss.c b/drivers/media/platform/qcom/camss/camss.c
> index 2123f6388e3d7..84097d82d99c9 100644
> --- a/drivers/media/platform/qcom/camss/camss.c
> +++ b/drivers/media/platform/qcom/camss/camss.c
> @@ -4799,8 +4799,43 @@ static int camss_parse_ports(struct camss *camss)
> fwnode_graph_for_each_endpoint(fwnode, ep) {
> struct camss_async_subdev *csd;
>
> - csd = v4l2_async_nf_add_fwnode_remote(&camss->notifier, ep,
> - typeof(*csd));
> + if (!fwnode_device_is_available(ep))
> + continue;
> +
> + if (camss->legacy_phy) {
> + csd = v4l2_async_nf_add_fwnode_remote(&camss->notifier, ep,
> + typeof(*csd));
> + } else {
> + struct fwnode_handle *phy_out, *phy_node, *phy_in, *sensor_ep;
> +
> + phy_out = fwnode_graph_get_remote_endpoint(ep);
> + if (!phy_out)
> + continue;
> +
> + phy_node = fwnode_graph_get_port_parent(phy_out);
> + fwnode_handle_put(phy_out);
> + if (!phy_node)
> + continue;
> +
> + phy_in = fwnode_graph_get_endpoint_by_id(phy_node, 0, 0, 0);
> + fwnode_handle_put(phy_node);
> + if (!phy_in)
> + continue;
> +
> + sensor_ep = fwnode_graph_get_remote_endpoint(phy_in);
> + fwnode_handle_put(phy_in);
> + if (!sensor_ep)
> + continue;
> +
> + csd = v4l2_async_nf_add_fwnode(&camss->notifier, sensor_ep,
> + struct camss_async_subdev);
> + fwnode_handle_put(sensor_ep);
> + if (IS_ERR(csd)) {
> + ret = PTR_ERR(csd);
> + goto err_cleanup;
> + }
> + }
> +
> if (IS_ERR(csd)) {
> ret = PTR_ERR(csd);
> goto err_cleanup;
> @@ -4819,6 +4854,29 @@ static int camss_parse_ports(struct camss *camss)
> return ret;
> }
>
> +static void camss_detect_legacy_phy(struct camss *camss)
> +{
> + struct device_node *remote;
> + struct device_node *ep;
> +
> + camss->legacy_phy = true;
> +
> + /* Find first remote-endpoint and determine if its a PHY */
> + for_each_endpoint_of_node(camss->dev->of_node, ep) {
> + remote = of_graph_get_remote_port_parent(ep);
> + if (!remote)
> + continue;
> +
> + camss->legacy_phy = !of_node_name_eq(remote, "phy");
> + of_node_put(remote);
> + of_node_put(ep);
> + break;
> + }
> +
> + dev_dbg(camss->dev, "legacy phy mode %s\n",
> + camss->legacy_phy ? "true" : "false");
> +}
> +
> /*
> * camss_init_subdevices - Initialize subdev structures and resources
> * @camss: CAMSS device
> @@ -4832,14 +4890,21 @@ static int camss_init_subdevices(struct camss *camss)
> unsigned int i;
> int ret;
>
> + camss_detect_legacy_phy(camss);
> +
> for (i = 0; i < camss->res->csiphy_num; i++) {
> - ret = msm_csiphy_subdev_init(camss, &camss->csiphy[i],
> - &res->csiphy_res[i],
> - res->csiphy_res[i].csiphy.id);
> + if (!camss->legacy_phy) {
> + ret = msm_csiphy_subdev_init(camss, i);
> + } else {
> + ret = msm_csiphy_subdev_init_legacy(camss,
> + &camss->csiphy[i],
> + &res->csiphy_res[i],
> + res->csiphy_res[i].csiphy.id);
> + }
> +
> if (ret < 0) {
> - dev_err(camss->dev,
> - "Failed to init csiphy%d sub-device: %d\n",
> - i, ret);
> + dev_err(camss->dev, "csiphy %d init fail\n",
> + res->csiphy_res[i].csiphy.id);
> return ret;
> }
> }
> @@ -4917,6 +4982,11 @@ inline void camss_link_err(struct camss *camss,
> ret);
> }
>
> +static inline bool csiphy_enabled(struct camss *camss, struct csiphy_device *c)
> +{
> + return camss->legacy_phy || c->phy;
> +}
> +
> /*
> * camss_link_entities - Register subdev nodes and create links
> * @camss: CAMSS device
> @@ -4930,6 +5000,9 @@ static int camss_link_entities(struct camss *camss)
>
> for (i = 0; i < camss->res->csiphy_num; i++) {
> for (j = 0; j < camss->res->csid_num; j++) {
> + if (!csiphy_enabled(camss, &camss->csiphy[i]))
> + continue;
> +
> ret = media_create_pad_link(&camss->csiphy[i].subdev.entity,
> MSM_CSIPHY_PAD_SRC,
> &camss->csid[j].subdev.entity,
> @@ -5056,6 +5129,9 @@ static int camss_register_entities(struct camss *camss)
> int ret;
>
> for (i = 0; i < camss->res->csiphy_num; i++) {
> + if (!csiphy_enabled(camss, &camss->csiphy[i]))
> + continue;
> +
> ret = msm_csiphy_register_entity(&camss->csiphy[i],
> &camss->v4l2_dev);
> if (ret < 0) {
> @@ -5131,8 +5207,10 @@ static int camss_register_entities(struct camss *camss)
>
> i = camss->res->csiphy_num;
> err_reg_csiphy:
> - for (i--; i >= 0; i--)
> - msm_csiphy_unregister_entity(&camss->csiphy[i]);
> + for (i--; i >= 0; i--) {
> + if (csiphy_enabled(camss, &camss->csiphy[i]))
> + msm_csiphy_unregister_entity(&camss->csiphy[i]);
> + }
>
> return ret;
> }
> @@ -5147,8 +5225,10 @@ static void camss_unregister_entities(struct camss *camss)
> {
> unsigned int i;
>
> - for (i = 0; i < camss->res->csiphy_num; i++)
> - msm_csiphy_unregister_entity(&camss->csiphy[i]);
> + for (i = 0; i < camss->res->csiphy_num; i++) {
> + if (csiphy_enabled(camss, &camss->csiphy[i]))
> + msm_csiphy_unregister_entity(&camss->csiphy[i]);
> + }
>
> if (camss->tpg) {
> for (i = 0; i < camss->res->tpg_num; i++)
> diff --git a/drivers/media/platform/qcom/camss/camss.h b/drivers/media/platform/qcom/camss/camss.h
> index 93d691c8ac63b..ba3d51d9c0bf8 100644
> --- a/drivers/media/platform/qcom/camss/camss.h
> +++ b/drivers/media/platform/qcom/camss/camss.h
> @@ -138,6 +138,7 @@ struct camss {
> struct device_link *genpd_link;
> struct icc_path *icc_path[ICC_SM8250_COUNT];
> const struct camss_resources *res;
> + bool legacy_phy;
> };
>
> struct camss_camera_interface {
>
> --
> 2.54.0
>
^ permalink raw reply [flat|nested] 17+ messages in thread
* [PATCH v13 4/5] dt-bindings: media: qcom,x1e80100-camss: Describe iommu entries
2026-07-28 9:35 [PATCH v13 0/5] Add dt-bindings and PHY updates for CAMSS on x1e80100 silicon Bryan O'Donoghue
` (2 preceding siblings ...)
2026-07-28 9:35 ` [PATCH v13 3/5] media: qcom: camss: Add support for PHY API devices Bryan O'Donoghue
@ 2026-07-28 9:35 ` Bryan O'Donoghue
2026-07-28 9:35 ` [PATCH v13 5/5] dt-bindings: media: qcom,x1e80100-camss: Make vdd-csiphy supplies optional Bryan O'Donoghue
4 siblings, 0 replies; 17+ messages in thread
From: Bryan O'Donoghue @ 2026-07-28 9:35 UTC (permalink / raw)
To: Bjorn Andersson, Michael Turquette, Stephen Boyd, Rob Herring,
Krzysztof Kozlowski, Conor Dooley, Robert Foss, Todor Tomov,
Mauro Carvalho Chehab, Konrad Dybcio, Vladimir Zapolskiy,
Bryan O'Donoghue, Loic Poulain, Vinod Koul, Neil Armstrong
Cc: linux-arm-msm, linux-clk, devicetree, linux-kernel, linux-media,
linux-phy, Bryan O'Donoghue, Krzysztof Kozlowski
The original iommus list included entries for ICP and BPS/IPE S1
contexts. Only the five S1 HLOS stream IDs are required by the CAMSS
ISP hardware: IFE/IFE_LITE read and write, SFE read and write, and
CDM IFE. The remaining entries serve other hardware blocks which will
be described in their own nodes as support is added.
Signed-off-by: Bryan O'Donoghue <bryan.odonoghue@linaro.org>
---
.../bindings/media/qcom,x1e80100-camss.yaml | 26 ++++++++++++++++------
1 file changed, 19 insertions(+), 7 deletions(-)
diff --git a/Documentation/devicetree/bindings/media/qcom,x1e80100-camss.yaml b/Documentation/devicetree/bindings/media/qcom,x1e80100-camss.yaml
index 2d1662ef522b7..126400772d028 100644
--- a/Documentation/devicetree/bindings/media/qcom,x1e80100-camss.yaml
+++ b/Documentation/devicetree/bindings/media/qcom,x1e80100-camss.yaml
@@ -104,7 +104,22 @@ properties:
- const: sf_icp_mnoc
iommus:
- maxItems: 8
+ oneOf:
+ - items:
+ - description: S1 HLOS IFE and IFE_LITE non-protected read
+ - description: S1 HLOS IFE and IFE_LITE non-protected write
+ - description: S1 HLOS SFE non-protected read
+ - description: S1 HLOS SFE non-protected write
+ - description: S1 HLOS CDM IFE non-protected
+ - description: Legacy slot 0 - do not use
+ - description: Legacy slot 1 - do not use
+ - description: Legacy slot 2 - do not use
+ - items:
+ - description: S1 HLOS IFE and IFE_LITE non-protected read
+ - description: S1 HLOS IFE and IFE_LITE non-protected write
+ - description: S1 HLOS SFE non-protected read
+ - description: S1 HLOS SFE non-protected write
+ - description: S1 HLOS CDM IFE non-protected
power-domains:
items:
@@ -332,13 +347,10 @@ examples:
"sf_icp_mnoc";
iommus = <&apps_smmu 0x800 0x60>,
+ <&apps_smmu 0x820 0x60>,
+ <&apps_smmu 0x840 0x60>,
<&apps_smmu 0x860 0x60>,
- <&apps_smmu 0x1800 0x60>,
- <&apps_smmu 0x1860 0x60>,
- <&apps_smmu 0x18e0 0x00>,
- <&apps_smmu 0x1980 0x20>,
- <&apps_smmu 0x1900 0x00>,
- <&apps_smmu 0x19a0 0x20>;
+ <&apps_smmu 0x18a0 0x0>;
power-domains = <&camcc CAM_CC_IFE_0_GDSC>,
<&camcc CAM_CC_IFE_1_GDSC>,
--
2.54.0
^ permalink raw reply related [flat|nested] 17+ messages in thread* [PATCH v13 5/5] dt-bindings: media: qcom,x1e80100-camss: Make vdd-csiphy supplies optional
2026-07-28 9:35 [PATCH v13 0/5] Add dt-bindings and PHY updates for CAMSS on x1e80100 silicon Bryan O'Donoghue
` (3 preceding siblings ...)
2026-07-28 9:35 ` [PATCH v13 4/5] dt-bindings: media: qcom,x1e80100-camss: Describe iommu entries Bryan O'Donoghue
@ 2026-07-28 9:35 ` Bryan O'Donoghue
2026-07-28 9:42 ` sashiko-bot
4 siblings, 1 reply; 17+ messages in thread
From: Bryan O'Donoghue @ 2026-07-28 9:35 UTC (permalink / raw)
To: Bjorn Andersson, Michael Turquette, Stephen Boyd, Rob Herring,
Krzysztof Kozlowski, Conor Dooley, Robert Foss, Todor Tomov,
Mauro Carvalho Chehab, Konrad Dybcio, Vladimir Zapolskiy,
Bryan O'Donoghue, Loic Poulain, Vinod Koul, Neil Armstrong
Cc: linux-arm-msm, linux-clk, devicetree, linux-kernel, linux-media,
linux-phy, Bryan O'Donoghue, Krzysztof Kozlowski
Moving the csiphy to peer nodes means making the current supplies optional.
Optional since we still need to support the old way but, at the same time
separate nodes means having rails per phy which is a key benefit of having
separate nodes.
Signed-off-by: Bryan O'Donoghue <bryan.odonoghue@linaro.org>
---
Documentation/devicetree/bindings/media/qcom,x1e80100-camss.yaml | 2 --
1 file changed, 2 deletions(-)
diff --git a/Documentation/devicetree/bindings/media/qcom,x1e80100-camss.yaml b/Documentation/devicetree/bindings/media/qcom,x1e80100-camss.yaml
index 126400772d028..57a838fe2d229 100644
--- a/Documentation/devicetree/bindings/media/qcom,x1e80100-camss.yaml
+++ b/Documentation/devicetree/bindings/media/qcom,x1e80100-camss.yaml
@@ -186,8 +186,6 @@ required:
- iommus
- power-domains
- power-domain-names
- - vdd-csiphy-0p8-supply
- - vdd-csiphy-1p2-supply
- ports
additionalProperties: false
--
2.54.0
^ permalink raw reply related [flat|nested] 17+ messages in thread* Re: [PATCH v13 5/5] dt-bindings: media: qcom,x1e80100-camss: Make vdd-csiphy supplies optional
2026-07-28 9:35 ` [PATCH v13 5/5] dt-bindings: media: qcom,x1e80100-camss: Make vdd-csiphy supplies optional Bryan O'Donoghue
@ 2026-07-28 9:42 ` sashiko-bot
2026-07-28 10:06 ` Bryan O'Donoghue
0 siblings, 1 reply; 17+ messages in thread
From: sashiko-bot @ 2026-07-28 9:42 UTC (permalink / raw)
To: Bryan O'Donoghue
Cc: media-ci, neil.armstrong, robh, devicetree, olteanv, vkoul,
conor+dt, linux-phy
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Medium] Incomplete schema update for split PHY topology causes dt_binding_check failures and incorrect hardware descriptions.
--
--- Patch [5]: [PATCH v13 5/5] dt-bindings: media: qcom,x1e80100-camss: Make vdd-csiphy supplies optional ---
commit 8ca017ccca6ab80da696ef7ec19b3fc7494d6187
Author: Bryan O'Donoghue <bryan.odonoghue@linaro.org>
dt-bindings: media: qcom,x1e80100-camss: Make vdd-csiphy supplies optional
This commit removes the vdd-csiphy-0p8-supply and vdd-csiphy-1p2-supply from
the required list in the qcom,x1e80100-camss binding. This makes the supplies
optional to support moving the csiphy to peer nodes while maintaining
backwards compatibility.
> diff --git a/Documentation/devicetree/bindings/media/qcom,x1e80100-camss.yaml b/Documentation/devicetree/bindings/media/qcom,x1e80100-camss.yaml
> index 126400772d028..57a838fe2d229 100644
> --- a/Documentation/devicetree/bindings/media/qcom,x1e80100-camss.yaml
> +++ b/Documentation/devicetree/bindings/media/qcom,x1e80100-camss.yaml
> @@ -186,8 +186,6 @@ required:
> - iommus
> - power-domains
> - power-domain-names
> - - vdd-csiphy-0p8-supply
> - - vdd-csiphy-1p2-supply
[Severity: Medium]
Since the CSIPHY nodes are being moved out to peer nodes, do other properties
in this schema also need to be updated to prevent validation regressions?
For example, the reg-names, clock-names, and interrupt-names in this schema
are currently defined as strict, fixed-order arrays that expect csiphy elements
at specific indices. If those elements are removed from the CAMSS node to avoid
resource conflicts, won't the remaining elements shift and cause
dt_binding_check to fail?
Additionally, the ports schema mandates data-lanes on the CAMSS endpoints.
Is this requirement still correct for internal links between the CAMSS core
and a peer PHY, rather than physical lanes to the sensor?
> - ports
>
> additionalProperties: false
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260728-b4-linux-next-25-03-13-dtsi-x1e80100-camss-v13-0-ae811e2f0799@linaro.org?part=5
^ permalink raw reply [flat|nested] 17+ messages in thread
* Re: [PATCH v13 5/5] dt-bindings: media: qcom,x1e80100-camss: Make vdd-csiphy supplies optional
2026-07-28 9:42 ` sashiko-bot
@ 2026-07-28 10:06 ` Bryan O'Donoghue
0 siblings, 0 replies; 17+ messages in thread
From: Bryan O'Donoghue @ 2026-07-28 10:06 UTC (permalink / raw)
To: sashiko-reviews
Cc: media-ci, neil.armstrong, robh, devicetree, olteanv, vkoul,
conor+dt, linux-phy
On 28/07/2026 10:42, sashiko-bot@kernel.org wrote:
> [Severity: Medium]
> Since the CSIPHY nodes are being moved out to peer nodes, do other properties
> in this schema also need to be updated to prevent validation regressions?
>
> For example, the reg-names, clock-names, and interrupt-names in this schema
> are currently defined as strict, fixed-order arrays that expect csiphy elements
> at specific indices. If those elements are removed from the CAMSS node to avoid
> resource conflicts, won't the remaining elements shift and cause
> dt_binding_check to fail?
>
> Additionally, the ports schema mandates data-lanes on the CAMSS endpoints.
> Is this requirement still correct for internal links between the CAMSS core
> and a peer PHY, rather than physical lanes to the sensor?
A good guess but, no - illustrative of how LLMs "understand" stuff but
actually don't understand stuff.
If the graph lookup and probe succeeds then the legacy regs/clocks are
never mapped by camss - if that lookup _fails_ then you absolutely need
the legacy stuff.
"Dr Chandra will I dream" ?
"I don't know"
---
bod
^ permalink raw reply [flat|nested] 17+ messages in thread