[PATCH 5/5] PCI/powerpc/eeh: Add pcibios hooks for preparing to rescan

[Benjamin Herrenschmidt]

On Wed, 2018-09-05 at 18:40 +0300, Sergey Miroshnichenko wrote:
> Reading an empty slot returns all ones, which triggers a false
> EEH error event on PowerNV.
> 
> New callbacks pcibios_rescan_prepare/done are introduced to
> pause/resume the EEH during rescan.

This freaks me out a bit. EEH will still happen in HW, you will just
drop the notifications. Disabling the interrupt globally is not a great
idea either as it will affect other unrelated devices or busses.

Just marking the specific bus might work if we deal with unfreezing it
properly but you need some locking there, your code doesn't seem to
have any.

Ben.

> 
> Signed-off-by: Sergey Miroshnichenko <s.miroshnichenko at yadro.com>
> ---
>  arch/powerpc/include/asm/eeh.h               |  2 ++
>  arch/powerpc/kernel/eeh.c                    | 14 ++++++++++++++
>  arch/powerpc/platforms/powernv/eeh-powernv.c | 20 ++++++++++++++++++++
>  drivers/pci/probe.c                          | 14 ++++++++++++++
>  include/linux/pci.h                          |  2 ++
>  5 files changed, 52 insertions(+)
> 
> diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
> index 219637ea69a1..926c3e31df99 100644
> --- a/arch/powerpc/include/asm/eeh.h
> +++ b/arch/powerpc/include/asm/eeh.h
> @@ -219,6 +219,8 @@ struct eeh_ops {
>  	int (*next_error)(struct eeh_pe **pe);
>  	int (*restore_config)(struct pci_dn *pdn);
>  	int (*notify_resume)(struct pci_dn *pdn);
> +	int (*pause)(struct pci_bus *bus);
> +	int (*resume)(struct pci_bus *bus);
>  };
>  
>  extern int eeh_subsystem_flags;
> diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
> index 6ebba3e48b01..dce9b0978cb5 100644
> --- a/arch/powerpc/kernel/eeh.c
> +++ b/arch/powerpc/kernel/eeh.c
> @@ -1831,3 +1831,17 @@ static int __init eeh_init_proc(void)
>  	return 0;
>  }
>  __initcall(eeh_init_proc);
> +
> +void pcibios_rescan_prepare(struct pci_bus *bus)
> +{
> +	if (eeh_ops && eeh_ops->pause) {
> +		eeh_ops->pause(bus);
> +	}
> +}
> +
> +void pcibios_rescan_done(struct pci_bus *bus)
> +{
> +	if (eeh_ops && eeh_ops->resume) {
> +		eeh_ops->resume(bus);
> +	}
> +}
> diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
> index 3c1beae29f2d..9c9213d92550 100644
> --- a/arch/powerpc/platforms/powernv/eeh-powernv.c
> +++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
> @@ -59,6 +59,24 @@ void pnv_pcibios_bus_add_device(struct pci_dev *pdev)
>  	eeh_sysfs_add_device(pdev);
>  }
>  
> +static int pnv_eeh_pause(struct pci_bus *bus)
> +{
> +	struct pci_controller *hose = pci_bus_to_host(bus);
> +	struct pnv_phb *phb = hose->private_data;
> +	phb->flags &= ~PNV_PHB_FLAG_EEH;
> +	disable_irq(eeh_event_irq);
> +	return 0;
> +}
> +
> +static int pnv_eeh_resume(struct pci_bus *bus)
> +{
> +	struct pci_controller *hose = pci_bus_to_host(bus);
> +	struct pnv_phb *phb = hose->private_data;
> +	enable_irq(eeh_event_irq);
> +	phb->flags |= PNV_PHB_FLAG_EEH;
> +	return 0;
> +}
> +
>  static int pnv_eeh_init(void)
>  {
>  	struct pci_controller *hose;
> @@ -1710,6 +1728,8 @@ static struct eeh_ops pnv_eeh_ops = {
>  	.write_config           = pnv_eeh_write_config,
>  	.next_error		= pnv_eeh_next_error,
>  	.restore_config		= pnv_eeh_restore_config,
> +	.pause			= pnv_eeh_pause,
> +	.resume			= pnv_eeh_resume,
>  	.notify_resume		= NULL
>  };
>  
> diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
> index ec784009a36b..203368566896 100644
> --- a/drivers/pci/probe.c
> +++ b/drivers/pci/probe.c
> @@ -2893,6 +2893,14 @@ void __weak pcibios_remove_bus(struct pci_bus *bus)
>  {
>  }
>  
> +void __weak pcibios_rescan_prepare(struct pci_bus *bus)
> +{
> +}
> +
> +void __weak pcibios_rescan_done(struct pci_bus *bus)
> +{
> +}
> +
>  struct pci_bus *pci_create_root_bus(struct device *parent, int bus,
>  		struct pci_ops *ops, void *sysdata, struct list_head *resources)
>  {
> @@ -3147,9 +3155,15 @@ unsigned int pci_rescan_bus_bridge_resize(struct pci_dev *bridge)
>  unsigned int pci_rescan_bus(struct pci_bus *bus)
>  {
>  	unsigned int max;
> +	struct pci_bus *root = bus;
> +	while (!pci_is_root_bus(root)) {
> +		root = root->parent;
> +	}
>  
> +	pcibios_rescan_prepare(root);
>  	max = pci_scan_child_bus(bus);
>  	pci_assign_unassigned_bus_resources(bus);
> +	pcibios_rescan_done(root);
>  	pci_bus_add_devices(bus);
>  
>  	return max;
> diff --git a/include/linux/pci.h b/include/linux/pci.h
> index e72ca8dd6241..d7fe72aa53b3 100644
> --- a/include/linux/pci.h
> +++ b/include/linux/pci.h
> @@ -1952,6 +1952,8 @@ void pcibios_penalize_isa_irq(int irq, int active);
>  int pcibios_alloc_irq(struct pci_dev *dev);
>  void pcibios_free_irq(struct pci_dev *dev);
>  resource_size_t pcibios_default_alignment(void);
> +void pcibios_rescan_prepare(struct pci_bus *bus);
> +void pcibios_rescan_done(struct pci_bus *bus);
>  
>  #ifdef CONFIG_HIBERNATE_CALLBACKS
>  extern struct dev_pm_ops pcibios_pm_ops;