Re: [PATCH] PCI: Restrict device disabled status check to DT

[Bjorn Helgaas]

[+cc Vitaly, Jesse, Tony, Andy, regressions, regarding reports of
hang or crash during boot in igb driver, some with AWS Xen]

On Wed, Apr 19, 2023 at 02:35:13PM -0500, Rob Herring wrote:
> Commit 6fffbc7ae137 ("PCI: Honor firmware's device disabled status")
> checked the firmware device status for both DT and ACPI devices. That
> caused a regression in some ACPI systems. The exact reason isn't clear.
> It's possibly a firmware bug. For now, at least, refactor the check to
> be for DT based systems only.
> 
> Note that the original implementation leaked a refcount which is now
> correctly handled.
> 
> Fixes: 6fffbc7ae137 ("PCI: Honor firmware's device disabled status")
> Link: https://lore.kernel.org/all/m2fs9lgndw.fsf@xxxxxxxxx/
> Reported-by: Donald Hunter <donald.hunter@xxxxxxxxx>
> Cc: Binbin Zhou <zhoubinbin@xxxxxxxxxxx>
> Cc: Liu Peibao <liupeibao@xxxxxxxxxxx>
> Cc: Huacai Chen <chenhuacai@xxxxxxxxxxx>
> Signed-off-by: Rob Herring <robh@xxxxxxxxxx>

Applied to for-linus for (hopefully) v6.3.  I added:

  [bhelgaas: Per ACPI r6.5, sec 6.3.7, for devices on an enumerable
  bus, _STA must return with bit[0] ("device is present") set]

  Link: https://bugzilla.kernel.org/show_bug.cgi?id=217317

It would be really great if anybody who has seen this issue could test
and report whether this patch solves it.

> ---
>  drivers/pci/of.c    | 30 ++++++++++++++++++++++++------
>  drivers/pci/pci.h   |  4 ++--
>  drivers/pci/probe.c |  8 ++++----
>  3 files changed, 30 insertions(+), 12 deletions(-)
> 
> diff --git a/drivers/pci/of.c b/drivers/pci/of.c
> index 196834ed44fe..4c2ef2e28fb5 100644
> --- a/drivers/pci/of.c
> +++ b/drivers/pci/of.c
> @@ -16,14 +16,32 @@
>  #include "pci.h"
>  
>  #ifdef CONFIG_PCI
> -void pci_set_of_node(struct pci_dev *dev)
> +/**
> + * pci_set_of_node - Find and set device's DT device_node
> + * @dev: the PCI device structure to fill
> + *
> + * Returns 0 on success with of_node set or when no device is described in the
> + * DT. Returns -ENODEV if the device is present, but disabled in the DT.
> + */
> +int pci_set_of_node(struct pci_dev *dev)
>  {
> +	struct device_node *node;
> +
>  	if (!dev->bus->dev.of_node)
> -		return;
> -	dev->dev.of_node = of_pci_find_child_device(dev->bus->dev.of_node,
> -						    dev->devfn);
> -	if (dev->dev.of_node)
> -		dev->dev.fwnode = &dev->dev.of_node->fwnode;
> +		return 0;
> +
> +	node = of_pci_find_child_device(dev->bus->dev.of_node, dev->devfn);
> +	if (!node)
> +		return 0;
> +
> +	if (!of_device_is_available(node)) {
> +		of_node_put(node);
> +		return -ENODEV;
> +	}
> +
> +	dev->dev.of_node = node;
> +	dev->dev.fwnode = &node->fwnode;
> +	return 0;
>  }
>  
>  void pci_release_of_node(struct pci_dev *dev)
> diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
> index d2c08670a20e..2b48a0aa8008 100644
> --- a/drivers/pci/pci.h
> +++ b/drivers/pci/pci.h
> @@ -624,7 +624,7 @@ int of_pci_get_max_link_speed(struct device_node *node);
>  u32 of_pci_get_slot_power_limit(struct device_node *node,
>  				u8 *slot_power_limit_value,
>  				u8 *slot_power_limit_scale);
> -void pci_set_of_node(struct pci_dev *dev);
> +int pci_set_of_node(struct pci_dev *dev);
>  void pci_release_of_node(struct pci_dev *dev);
>  void pci_set_bus_of_node(struct pci_bus *bus);
>  void pci_release_bus_of_node(struct pci_bus *bus);
> @@ -662,7 +662,7 @@ of_pci_get_slot_power_limit(struct device_node *node,
>  	return 0;
>  }
>  
> -static inline void pci_set_of_node(struct pci_dev *dev) { }
> +static inline int pci_set_of_node(struct pci_dev *dev) { return 0; }
>  static inline void pci_release_of_node(struct pci_dev *dev) { }
>  static inline void pci_set_bus_of_node(struct pci_bus *bus) { }
>  static inline void pci_release_bus_of_node(struct pci_bus *bus) { }
> diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
> index a3f68b6ba6ac..f96fa83f2627 100644
> --- a/drivers/pci/probe.c
> +++ b/drivers/pci/probe.c
> @@ -1826,7 +1826,7 @@ int pci_setup_device(struct pci_dev *dev)
>  	u32 class;
>  	u16 cmd;
>  	u8 hdr_type;
> -	int pos = 0;
> +	int err, pos = 0;
>  	struct pci_bus_region region;
>  	struct resource *res;
>  
> @@ -1840,10 +1840,10 @@ int pci_setup_device(struct pci_dev *dev)
>  	dev->error_state = pci_channel_io_normal;
>  	set_pcie_port_type(dev);
>  
> -	pci_set_of_node(dev);
> +	err = pci_set_of_node(dev);
> +	if (err)
> +		return err;
>  	pci_set_acpi_fwnode(dev);
> -	if (dev->dev.fwnode && !fwnode_device_is_available(dev->dev.fwnode))
> -		return -ENODEV;
>  
>  	pci_dev_assign_slot(dev);
>  
> -- 
> 2.39.2
>