[PATCH v9 0/9] lan966x pci device: Add support for SFPs, PCI part

[PATCH v9 0/9] lan966x pci device: Add support for SFPs, PCI part

[Herve Codina]

Hi,

Previously, I sent a big picture series adding support for SFP ports
available on the LAN966x PCI device [0].

In this series patches touch several parts and sub-system in the kernel.
Reviews have be done and it makes sense to split the series and send
parts separately.

This current series is the extraction of patches related to issues in
the PCI subsystem. It has to be seen as a continuation of the big
picture series but related to this specific core part.

Patches 1 to 6 introduce and use fw_devlink_set_device() in already
existing code. No functional change but the introduction of the
fw_devlink_set_device() wrapper.

Patch 7 avoid a dangling pointer.

Patches 8 and 9 fix fw_devlink issues specific to PCI and the
device-tree nodes created during enumeration.

[0] https://lore.kernel.org/all/20260325143555.451852-1-herve.codina@bootlin.com/

Best regards,
Hervé

Changes:

v8 -> v9
  v8: https://lore.kernel.org/all/20260630102804.413563-1-herve.codina@bootlin.com/

  - Patch 7 (new patch in v9)
    Clear fwnode->dev during root bridge node removal (avoid a dangling
    pointer).

  - Patch 8 (patch 7 in v8)
    Clear fwnode->dev during PCI device node removal.

v7 -> v8
  v7: https://lore.kernel.org/all/20260511155930.34604-1-herve.codina@bootlin.com/

  Rebase on top of v7.2-rc1

  - patches 4 and 5
    Add 'Reviewed-by: Andy Shevchenko'

  - Other Patches
    No other changes

v6 -> v7

  Rebase on top of v7.1-rc1

  - Patch 1
     Add Cc stable. Needed for patches 11 and 12

  - Patches 2 to 5
    No changes

  - Patch 6
     Add Cc stable. Needed for patch 13
     Add 'Acked-by: Bjorn Helgaas'

  - Patch 7
     Fix a typo in commit log
     Add Fixes tag + Cc stable
     Add 'Acked-by: Bjorn Helgaas'

  - Patch 8
     Add Fixes tag + Cc stable
     Add 'Acked-by: Bjorn Helgaas'
Older iterations:
  Patches 6 to 13 in the big picture series
  https://lore.kernel.org/all/20260325143555.451852-1-herve.codina@bootlin.com/

Herve Codina (9):
  driver core: fw_devlink: Introduce fw_devlink_set_device()
  drivers: core: Use fw_devlink_set_device()
  pinctrl: cs42l43: Use fw_devlink_set_device()
  cxl/test: Use device_set_node()
  cxl/test: Use fw_devlink_set_device()
  PCI: of: Use fw_devlink_set_device()
  PCI: of: Clear fwnode->dev during root bridge node removal
  PCI: of: Set fwnode device of newly created PCI device nodes
  PCI: of: Remove fwnode_dev_initialized() call for a PCI root bridge
    node

 drivers/base/core.c                      |  4 ++--
 drivers/pci/of.c                         | 12 ++++++++++--
 drivers/pinctrl/cirrus/pinctrl-cs42l43.c |  2 +-
 include/linux/fwnode.h                   |  6 ++++++
 tools/testing/cxl/test/cxl.c             |  4 ++--
 5 files changed, 21 insertions(+), 7 deletions(-)

-- 
2.54.0

[PATCH v9 1/9] driver core: fw_devlink: Introduce fw_devlink_set_device()

[Herve Codina]

Setting fwnode->dev is specific to fw_devlink.

In order to avoid having a direct 'fwnode->dev = dev;' in several
place in the kernel, introduce fw_devlink_set_device() helper to perform
this operation.

Having this helper allows to hide the fwnode devlink related stuff
behind the helper.

Cc: stable@vger.kernel.org
Signed-off-by: Herve Codina <herve.codina@bootlin.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Ulf Hansson <ulf.hansson@linaro.org>
Reviewed-by: Charles Keepax <ckeepax@opensource.cirrus.com>
---
Cc stable because used by other patches with Fixes + Cc stable
---
 include/linux/fwnode.h | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h
index 4e86e6990d28..31538f54b1ca 100644
--- a/include/linux/fwnode.h
+++ b/include/linux/fwnode.h
@@ -256,4 +256,10 @@ void fw_devlink_purge_absent_suppliers(struct fwnode_handle *fwnode);
 void fw_devlink_refresh_fwnode(struct fwnode_handle *fwnode);
 bool fw_devlink_is_strict(void);
 
+static inline void fw_devlink_set_device(struct fwnode_handle *fwnode,
+					 struct device *dev)
+{
+	fwnode->dev = dev;
+}
+
 #endif
-- 
2.54.0

Re: [PATCH v9 1/9] driver core: fw_devlink: Introduce fw_devlink_set_device()

[sashiko-bot]

> Setting fwnode->dev is specific to fw_devlink.
> 
> In order to avoid having a direct 'fwnode->dev = dev;' in several
> place in the kernel, introduce fw_devlink_set_device() helper to perform
> this operation.
> 
> Having this helper allows to hide the fwnode devlink related stuff
> behind the helper.
> 
> Cc: stable@vger.kernel.org
> Signed-off-by: Herve Codina <herve.codina@bootlin.com>

Sashiko has reviewed this patch and found no issues. It looks great!

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260708100302.517792-1-herve.codina@bootlin.com?part=1

[PATCH v9 2/9] drivers: core: Use fw_devlink_set_device()

[Herve Codina]

The code set directly fwnode->dev field.

Use the dedicated fw_devlink_set_device() helper to perform this
operation.

Signed-off-by: Herve Codina <herve.codina@bootlin.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/base/core.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/base/core.c b/drivers/base/core.c
index 4d026682944f..c205125344cf 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -3750,7 +3750,7 @@ int device_add(struct device *dev)
 	 * device and the driver sync_state callback is called for this device.
 	 */
 	if (dev->fwnode && !dev->fwnode->dev) {
-		dev->fwnode->dev = dev;
+		fw_devlink_set_device(dev->fwnode, dev);
 		fw_devlink_link_device(dev);
 	}
 
@@ -3925,7 +3925,7 @@ void device_del(struct device *dev)
 	device_unlock(dev);
 
 	if (dev->fwnode && dev->fwnode->dev == dev)
-		dev->fwnode->dev = NULL;
+		fw_devlink_set_device(dev->fwnode, NULL);
 
 	/* Notify clients of device removal.  This call must come
 	 * before dpm_sysfs_remove().
-- 
2.54.0

Re: [PATCH v9 2/9] drivers: core: Use fw_devlink_set_device()

[sashiko-bot]

> The code set directly fwnode->dev field.
> 
> Use the dedicated fw_devlink_set_device() helper to perform this
> operation.
> 
> Signed-off-by: Herve Codina <herve.codina@bootlin.com>

Sashiko has reviewed this patch and found no issues. It looks great!

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260708100302.517792-1-herve.codina@bootlin.com?part=2

[PATCH v9 3/9] pinctrl: cs42l43: Use fw_devlink_set_device()

[Herve Codina]

The code set directly fwnode->dev field.

Use the dedicated fw_devlink_set_device() helper to perform this
operation.

Signed-off-by: Herve Codina <herve.codina@bootlin.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Acked-by: Linus Walleij <linusw@kernel.org>
---
 drivers/pinctrl/cirrus/pinctrl-cs42l43.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pinctrl/cirrus/pinctrl-cs42l43.c b/drivers/pinctrl/cirrus/pinctrl-cs42l43.c
index 8990fab0446c..563070aba3d8 100644
--- a/drivers/pinctrl/cirrus/pinctrl-cs42l43.c
+++ b/drivers/pinctrl/cirrus/pinctrl-cs42l43.c
@@ -576,7 +576,7 @@ static int cs42l43_pin_probe(struct platform_device *pdev)
 				return ret;
 
 			if (!child->dev)
-				child->dev = priv->dev;
+				fw_devlink_set_device(child, priv->dev);
 			fwnode = child;
 		}
 	}
-- 
2.54.0

Re: [PATCH v9 3/9] pinctrl: cs42l43: Use fw_devlink_set_device()

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:

Pre-existing issues:
- [High] The driver overwrites the platform device's fwnode and devlink device pointer during probe, but fails to restore them on probe failure or driver unbind, leading to a Use-After-Free.
--

--- Patch [3]: [PATCH v9 3/9] pinctrl: cs42l43: Use fw_devlink_set_device() ---
commit 80d27bc87210331a635e646eedd21068256104a4
Author: Herve Codina <herve.codina@bootlin.com>

pinctrl: cs42l43: Use fw_devlink_set_device()

This patch updates the CS42L43 pinctrl driver to use the dedicated
fw_devlink_set_device() helper instead of directly modifying the fwnode->dev
field.

> diff --git a/drivers/pinctrl/cirrus/pinctrl-cs42l43.c b/drivers/pinctrl/cirrus/pinctrl-cs42l43.c
> index 8990fab0446cf..563070aba3d81 100644
> --- a/drivers/pinctrl/cirrus/pinctrl-cs42l43.c
> +++ b/drivers/pinctrl/cirrus/pinctrl-cs42l43.c
> @@ -576,7 +576,7 @@ static int cs42l43_pin_probe(struct platform_device *pdev)
>  				return ret;
>  
>  			if (!child->dev)
> -				child->dev = priv->dev;
> +				fw_devlink_set_device(child, priv->dev);

[Severity: High]
This isn't a bug introduced by this patch, but could this setup leave a dangling
pointer that leads to a use-after-free on unbind?

If the device is instantiated via a Device Tree overlay, the driver fetches the
child node, takes a reference to it, and registers a devres action
(cs42l43_fwnode_put) to drop this reference on teardown.

Later in cs42l43_pin_probe(), the driver calls:

    device_set_node(priv->dev, fwnode);

This overwrites the platform device's fwnode with the child node without taking
an additional reference.

If the driver is unbound manually via sysfs or fails probe, the devres action
drops the driver's reference to the child node, but pdev->dev.fwnode is left
pointing to it. If the DT overlay is then removed, the OF core detaches the
node, causing the child node to be freed.

Finally, the OF core notifier triggers platform device removal, and
device_del() attempts to access dev->fwnode->dev to clear the devlink,
dereferencing the freed child node. 

Does this require a cleanup action to restore the original fwnode and devlink
device pointer on teardown?

>  			fwnode = child;
>  		}
>  	}

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260708100302.517792-1-herve.codina@bootlin.com?part=3

[PATCH v9 4/9] cxl/test: Use device_set_node()

[Herve Codina]

The code set directly dev->fwnode.

Use the dedicated helper to perform this operation.

Signed-off-by: Herve Codina <herve.codina@bootlin.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 tools/testing/cxl/test/cxl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/cxl/test/cxl.c b/tools/testing/cxl/test/cxl.c
index ef92dd35e030..69da0727362b 100644
--- a/tools/testing/cxl/test/cxl.c
+++ b/tools/testing/cxl/test/cxl.c
@@ -1528,7 +1528,7 @@ static void mock_companion(struct acpi_device *adev, struct device *dev)
 {
 	device_initialize(&adev->dev);
 	fwnode_init(&adev->fwnode, NULL);
-	dev->fwnode = &adev->fwnode;
+	device_set_node(dev, &adev->fwnode);
 	adev->fwnode.dev = dev;
 }
 
-- 
2.54.0

Re: [PATCH v9 4/9] cxl/test: Use device_set_node()

[sashiko-bot]

> The code set directly dev->fwnode.
> 
> Use the dedicated helper to perform this operation.
> 
> Signed-off-by: Herve Codina <herve.codina@bootlin.com>

Sashiko has reviewed this patch and found no issues. It looks great!

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260708100302.517792-1-herve.codina@bootlin.com?part=4

[PATCH v9 5/9] cxl/test: Use fw_devlink_set_device()

[Herve Codina]

The code set directly fwnode.dev field.

Use the dedicated fw_devlink_set_device() helper to perform this
operation.

Signed-off-by: Herve Codina <herve.codina@bootlin.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 tools/testing/cxl/test/cxl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/cxl/test/cxl.c b/tools/testing/cxl/test/cxl.c
index 69da0727362b..95e39dfc6ec9 100644
--- a/tools/testing/cxl/test/cxl.c
+++ b/tools/testing/cxl/test/cxl.c
@@ -1529,7 +1529,7 @@ static void mock_companion(struct acpi_device *adev, struct device *dev)
 	device_initialize(&adev->dev);
 	fwnode_init(&adev->fwnode, NULL);
 	device_set_node(dev, &adev->fwnode);
-	adev->fwnode.dev = dev;
+	fw_devlink_set_device(&adev->fwnode, dev);
 }
 
 #ifndef SZ_64G
-- 
2.54.0

Re: [PATCH v9 5/9] cxl/test: Use fw_devlink_set_device()

[sashiko-bot]

> The code set directly fwnode.dev field.
> 
> Use the dedicated fw_devlink_set_device() helper to perform this
> operation.
> 
> Signed-off-by: Herve Codina <herve.codina@bootlin.com>

Sashiko has reviewed this patch and found no issues. It looks great!

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260708100302.517792-1-herve.codina@bootlin.com?part=5

[PATCH v9 6/9] PCI: of: Use fw_devlink_set_device()

[Herve Codina]

The code set directly fwnode.dev field.

Use the dedicated fw_devlink_set_device() helper to perform this
operation.

Cc: stable@vger.kernel.org
Signed-off-by: Herve Codina <herve.codina@bootlin.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
---
Cc stable because used by other patches with Fixes + Cc stable
---
 drivers/pci/of.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pci/of.c b/drivers/pci/of.c
index 8b18c4ba845c..ee9eb384b377 100644
--- a/drivers/pci/of.c
+++ b/drivers/pci/of.c
@@ -803,7 +803,7 @@ void of_pci_make_host_bridge_node(struct pci_host_bridge *bridge)
 	 * bus. Avoid any new device creation.
 	 */
 	of_node_set_flag(np, OF_POPULATED);
-	np->fwnode.dev = &bridge->dev;
+	fw_devlink_set_device(&np->fwnode, &bridge->dev);
 	fwnode_dev_initialized(&np->fwnode, true);
 
 	ret = of_changeset_apply(cset);
-- 
2.54.0

Re: [PATCH v9 6/9] PCI: of: Use fw_devlink_set_device()

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:

Pre-existing issues:
- [High] Dangling pointer in `np->fwnode.dev` on error paths and during bridge removal, leading to a potential use-after-free.
--

--- Patch [6]: [PATCH v9 6/9] PCI: of: Use fw_devlink_set_device() ---
commit e05d94ee3b1f4fa9d5ff1b29db6b40e43eca7313
Author: Herve Codina <herve.codina@bootlin.com>

PCI: of: Use fw_devlink_set_device()

The code directly set the fwnode.dev field. This commit updates the code
to use the dedicated fw_devlink_set_device() helper to perform this
operation.

> diff --git a/drivers/pci/of.c b/drivers/pci/of.c
> index 8b18c4ba845cf..ee9eb384b377a 100644
> --- a/drivers/pci/of.c
> +++ b/drivers/pci/of.c
> @@ -803,7 +803,7 @@ void of_pci_make_host_bridge_node(struct pci_host_bridge *bridge)
>  	 * bus. Avoid any new device creation.
>  	 */
>  	of_node_set_flag(np, OF_POPULATED);
> -	np->fwnode.dev = &bridge->dev;
> +	fw_devlink_set_device(&np->fwnode, &bridge->dev);

[Severity: High]
This isn't a bug introduced by this patch, but could this lead to a
use-after-free on error paths?

In of_pci_make_host_bridge_node(), if an error occurs after setting up the
fwnode (such as of_changeset_apply() or device_add_of_node() failing), the
error path removes the node from the tree and releases its reference, but
fails to clear the np->fwnode.dev pointer:

out_revert_cset:
	np->data = NULL;
	of_changeset_revert(cset);
out_free_node:
	of_node_put(np);

Because device_remove_of_node() only clears the forward pointer
(dev->fwnode) and not the backpointer, np->fwnode.dev remains dangling. If
another thread holds a reference to np, the node outlives the function.
When the bridge is later freed, any concurrent access via
get_dev_from_fwnode(&np->fwnode) could dereference freed memory.

The same dangling pointer issue appears to exist in
of_pci_remove_host_bridge_node() during teardown:

void of_pci_remove_host_bridge_node(struct pci_host_bridge *bridge)
{
...
	device_remove_of_node(&bridge->bus->dev);
	device_remove_of_node(&bridge->dev);
	of_changeset_revert(np->data);
	of_changeset_destroy(np->data);
	of_node_put(np);
}

>  	fwnode_dev_initialized(&np->fwnode, true);
>  
>  	ret = of_changeset_apply(cset);

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260708100302.517792-1-herve.codina@bootlin.com?part=6

[PATCH v9 7/9] PCI: of: Clear fwnode->dev during root bridge node removal

[Herve Codina]

During the of_pci_make_host_bridge_node() call, an OF node is created
dynamically and its fwnode device (fwnode->dev) is set to the PCI root
bridge device using the fw_devlink_set_device(&np->fwnode, &bridge->dev)
call.

On removal, of_pci_remove_host_bridge_node() is called and calls
device_remove_of_node() which in turn set to NULL the related
dev->fwnode.

Later in the removal sequence, device_del() is called and runs its
cleanup logic:

    if (dev->fwnode && dev->fwnode->dev == dev)
        fw_devlink_set_device(dev->fwnode, NULL);

Because dev->fwnode has been cleared earlier, fw_devlink_set_device()
is not called and leaves fwnode->dev unchanged. This fwnode device
(fwnode->dev) becomes an dangling pointer.

If any reference to the OF node is held after this removal, the pointer
is still accessible using the OF node (np->fwnode.dev) but points to a
freed area.

Avoid this dangling fwnode->dev pointer by clearing it in
of_pci_remove_host_bridge_node().

Fixes: 1f340724419e ("PCI: of: Create device tree PCI host bridge node")
Cc: stable@vger.kernel.org
Signed-off-by: Herve Codina <herve.codina@bootlin.com>
---
 drivers/pci/of.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/pci/of.c b/drivers/pci/of.c
index ee9eb384b377..8dd558a490bb 100644
--- a/drivers/pci/of.c
+++ b/drivers/pci/of.c
@@ -743,6 +743,7 @@ void of_pci_remove_host_bridge_node(struct pci_host_bridge *bridge)
 	if (!np || !of_node_check_flag(np, OF_DYNAMIC))
 		return;
 
+	fw_devlink_set_device(&np->fwnode, NULL);
 	device_remove_of_node(&bridge->bus->dev);
 	device_remove_of_node(&bridge->dev);
 	of_changeset_revert(np->data);
-- 
2.54.0

Re: [PATCH v9 7/9] PCI: of: Clear fwnode->dev during root bridge node removal

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:

Pre-existing issues:
- [High] Missing fw_devlink cleanup in the error path of of_pci_make_host_bridge_node(), leaving a dangling fwnode->dev pointer.
- [High] Kernel panic on removal of overlay-provided PCI host bridge nodes due to unsafe changeset revert.
--

--- Patch [7]: [PATCH v9 7/9] PCI: of: Clear fwnode->dev during root bridge node removal ---
commit 9e6873c21d6442ce4222fe6e9ac417348c8b3fbd
Author: Herve Codina <herve.codina@bootlin.com>

PCI: of: Clear fwnode->dev during root bridge node removal

This commit clears fwnode->dev during of_pci_remove_host_bridge_node() to
prevent a dangling pointer. It ensures fw_devlink_set_device() is called
with a NULL device before the fwnode is cleared.

> diff --git a/drivers/pci/of.c b/drivers/pci/of.c
> index ee9eb384b377a..8dd558a490bbd 100644
> --- a/drivers/pci/of.c
> +++ b/drivers/pci/of.c
> @@ -743,6 +743,7 @@ void of_pci_remove_host_bridge_node(struct pci_host_bridge *bridge)
>  	if (!np || !of_node_check_flag(np, OF_DYNAMIC))
>  		return;
>  
> +	fw_devlink_set_device(&np->fwnode, NULL);

[Severity: High]
This is a pre-existing issue, but does of_pci_make_host_bridge_node()
also need to clear the fwnode->dev pointer on its error path?

If device_add_of_node() fails in of_pci_make_host_bridge_node(), it jumps
to the error paths but leaves np->fwnode.dev pointing to the bridge device:

drivers/pci/of.c:of_pci_make_host_bridge_node() {
	...
	fw_devlink_set_device(&np->fwnode, &bridge->dev);
	...
	/* Add the of_node to host bridge and the root bus */
	ret = device_add_of_node(&bridge->dev, np);
	if (ret)
		goto out_revert_cset;

	ret = device_add_of_node(&bridge->bus->dev, np);
	if (ret)
		goto out_remove_bridge_dev_of_node;
	...
out_remove_bridge_dev_of_node:
	device_remove_of_node(&bridge->dev);
out_revert_cset:
	np->data = NULL;
	of_changeset_revert(cset);
out_free_node:
	of_node_put(np);
	...
}

If a concurrent thread acquired a reference to np, could the node outlive
the error path and result in a use-after-free where fwnode->dev points to
freed memory?

>  	device_remove_of_node(&bridge->bus->dev);
>  	device_remove_of_node(&bridge->dev);
>  	of_changeset_revert(np->data);

[Severity: High]
This isn't a bug introduced by this patch, but does calling
of_changeset_revert(np->data) unconditionally cause a crash when removing
an overlay-provided PCI host bridge node?

When an overlay provides the device tree node for a PCI host bridge, the
node inherently has the OF_DYNAMIC flag set. If the bridge is removed,
of_pci_remove_host_bridge_node() assumes the node was created by
of_pci_make_host_bridge_node() and executes of_changeset_revert(np->data).

Since np->data is NULL for standard overlay nodes, does this result in a
NULL pointer dereference in __of_changeset_revert_entries() when it tries
to evaluate &ocs->entries?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260708100302.517792-1-herve.codina@bootlin.com?part=7

[PATCH v9 8/9] PCI: of: Set fwnode device of newly created PCI device nodes

[Herve Codina]

Device-tree node can be created when CONFIG_PCI_DYNAMIC_OF_NODES. Those
nodes are created and filled based on PCI core information but the
fwnode device field is not set.

When later an overlay is applied, this confuses fw_devlink. Indeed,
without any device attached to the node, fw_devlink considers that this
node will never become a device. When this node is pointed as a
supplier, devlink looks at its ancestors in order to find a node with a
device that could be used as the supplier.

In the PCI use case, this leads to links that wrongly use the PCI root
bridge device as the supplier instead of the expected PCI device.

Setting the fwnode device to the device of the PCI device allows devlink
to use this device as a supplier and so, correct links are created.

Fixes: 407d1a51921e ("PCI: Create device tree node for bridge")
Cc: stable@vger.kernel.org
Signed-off-by: Herve Codina <herve.codina@bootlin.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/of.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/pci/of.c b/drivers/pci/of.c
index 8dd558a490bb..ca83006b7c7e 100644
--- a/drivers/pci/of.c
+++ b/drivers/pci/of.c
@@ -657,6 +657,7 @@ void of_pci_remove_node(struct pci_dev *pdev)
 	if (!np || !of_node_check_flag(np, OF_DYNAMIC))
 		return;
 
+	fw_devlink_set_device(&np->fwnode, NULL);
 	device_remove_of_node(&pdev->dev);
 	of_changeset_revert(np->data);
 	of_changeset_destroy(np->data);
@@ -709,6 +710,13 @@ void of_pci_make_dev_node(struct pci_dev *pdev)
 	if (ret)
 		goto out_free_node;
 
+	/*
+	 * Set the fwnode device in order to have fw_devlink creating links
+	 * pointing to this PCI device instead of walking up to the PCI host
+	 * bridge.
+	 */
+	fw_devlink_set_device(&np->fwnode, &pdev->dev);
+
 	ret = of_changeset_apply(cset);
 	if (ret)
 		goto out_free_node;
-- 
2.54.0

Re: [PATCH v9 8/9] PCI: of: Set fwnode device of newly created PCI device nodes

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [High] The `fwnode->dev` pointer is not cleared in the error paths of `of_pci_make_dev_node()` and `of_pci_make_host_bridge_node()`, potentially leaving a dangling pointer.
--

--- Patch [8]: [PATCH v9 8/9] PCI: of: Set fwnode device of newly created PCI device nodes ---
commit deed8a4ace1f4465ff17d82fc17dc458281c89a1
Author: Herve Codina <herve.codina@bootlin.com>

PCI: of: Set fwnode device of newly created PCI device nodes

This commit sets the fwnode device field for dynamically created PCI
device nodes to prevent fw_devlink from incorrectly using the PCI root
bridge as a supplier. It ensures proper links are created by pointing
devlink directly to the PCI device.

> diff --git a/drivers/pci/of.c b/drivers/pci/of.c
> index 8dd558a490bbd..ca83006b7c7e2 100644
> --- a/drivers/pci/of.c
> +++ b/drivers/pci/of.c

[ ... ]

> @@ -709,6 +710,13 @@ void of_pci_make_dev_node(struct pci_dev *pdev)
>  	if (ret)
>  		goto out_free_node;
>  
> +	/*
> +	 * Set the fwnode device in order to have fw_devlink creating links
> +	 * pointing to this PCI device instead of walking up to the PCI host
> +	 * bridge.
> +	 */
> +	fw_devlink_set_device(&np->fwnode, &pdev->dev);
> +
>  	ret = of_changeset_apply(cset);
>  	if (ret)
>  		goto out_free_node;

[Severity: High]
If of_changeset_apply() fails here, the code jumps to the out_free_node
error path in of_pci_make_dev_node() without clearing the fwnode.dev
pointer that was just set.

If the node survives due to an external reference acquired during partial
application (such as from an OF_RECONFIG_ATTACH_NODE listener), could this
leave np->fwnode.dev pointing to &pdev->dev?

When the PCI device is later freed, does this result in a dangling pointer
and a potential use-after-free?

Should fw_devlink_set_device(&np->fwnode, NULL) be called in the error
handling path to safely undo the assignment?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260708100302.517792-1-herve.codina@bootlin.com?part=8

[PATCH v9 9/9] PCI: of: Remove fwnode_dev_initialized() call for a PCI root bridge node

[Herve Codina]

During the instantiation of devices described by a device-tree overlay
applied on a PCI device, devlink displays the following kind of debug
messages instead of creating the expected links:
   'Not linking xxxx - might never become dev'

Without those expected links, the device removal order cannot be
correct.

Those debug traces are printed by fw_devlink_create_devlink(). In our
use case, they are all printed because the supplier of the link has at
least one of its ancestor with its fwnode flag FWNODE_FLAG_INITIALIZED
set.

The culprit ancestor is the PCI root bridge.

The fwnode related to the PCI root bridge is created dynamically by the
of_pci_make_host_bridge_node() function. During this creation
fwnode_dev_initialized() is called which set the FWNODE_FLAG_INITIALIZED
flag.

Calling fwnode_dev_initialized() tells devlink that the device related
to this node is handled out of the driver core. This is not correct in
our case. Indeed the device related to this firmware node is handled
using driver core mechanisms and is fully compliant devlink
expectations.

Simply remove the fwnode_dev_initialized() call. With that done, the
devlink debug messages are no more displayed and links that were missing
are correctly created.

Fixes: 1f340724419e ("PCI: of: Create device tree PCI host bridge node")
Cc: stable@vger.kernel.org
Signed-off-by: Herve Codina <herve.codina@bootlin.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/of.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/pci/of.c b/drivers/pci/of.c
index ca83006b7c7e..cb2470ca592f 100644
--- a/drivers/pci/of.c
+++ b/drivers/pci/of.c
@@ -813,7 +813,6 @@ void of_pci_make_host_bridge_node(struct pci_host_bridge *bridge)
 	 */
 	of_node_set_flag(np, OF_POPULATED);
 	fw_devlink_set_device(&np->fwnode, &bridge->dev);
-	fwnode_dev_initialized(&np->fwnode, true);
 
 	ret = of_changeset_apply(cset);
 	if (ret)
-- 
2.54.0

Re: [PATCH v9 9/9] PCI: of: Remove fwnode_dev_initialized() call for a PCI root bridge node

[sashiko-bot]

> During the instantiation of devices described by a device-tree overlay
> applied on a PCI device, devlink displays the following kind of debug
> messages instead of creating the expected links:
>    'Not linking xxxx - might never become dev'
> 
> Without those expected links, the device removal order cannot be
> correct.
> 
> Those debug traces are printed by fw_devlink_create_devlink(). In our
> use case, they are all printed because the supplier of the link has at
> least one of its ancestor with its fwnode flag FWNODE_FLAG_INITIALIZED
> set.
> 
> The culprit ancestor is the PCI root bridge.
> 
> [ ... ]
> are correctly created.
> 
> Fixes: 1f340724419e ("PCI: of: Create device tree PCI host bridge node")
> Cc: stable@vger.kernel.org
> Signed-off-by: Herve Codina <herve.codina@bootlin.com>

Sashiko has reviewed this patch and found no issues. It looks great!

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260708100302.517792-1-herve.codina@bootlin.com?part=9