Re: [PATCH] PCI: pciehp: Fix system hang on resume after hot-unplug during suspend

From: Lukas Wunner
Date: Tue Oct 01 2024 - 07:04:51 EST


On Tue, Oct 01, 2024 at 01:02:46PM +0200, Lukas Wunner wrote:
> On Mon, Sep 30, 2024 at 09:31:53AM +0800, AceLan Kao wrote:
> > Lukas Wunner <lukas@xxxxxxxxx> 2024 9 28 8:51:
> > > - if (pci_get_dsn(pdev) != ctrl->dsn)
> > > + dsn = pci_get_dsn(pdev);
> > > + if (!PCI_POSSIBLE_ERROR(dsn) &&
> > > + dsn != ctrl->dsn)
> > > return true;
> >
> > In my case, the pciehp_device_replaced() returns true from this final check.
> > And these are the values I got
> > dsn = 0x00000000, ctrl->dsn = 0x7800AA00
> > dsn = 0x00000000, ctrl->dsn = 0x21B7D000
>
> Ah because pci_get_dsn() returns 0 if the device is gone.
> Below is a modified patch which returns false in that case.

Sorry, forgot to include the patch:

-- >8 --

diff --git a/drivers/pci/hotplug/pciehp_core.c b/drivers/pci/hotplug/pciehp_core.c
index ff458e6..957c320 100644
--- a/drivers/pci/hotplug/pciehp_core.c
+++ b/drivers/pci/hotplug/pciehp_core.c
@@ -287,24 +287,32 @@ static int pciehp_suspend(struct pcie_device *dev)
static bool pciehp_device_replaced(struct controller *ctrl)
{
struct pci_dev *pdev __free(pci_dev_put);
+ u64 dsn;
u32 reg;

pdev = pci_get_slot(ctrl->pcie->port->subordinate, PCI_DEVFN(0, 0));
if (!pdev)
+ return false;
+
+ if (pci_read_config_dword(pdev, PCI_VENDOR_ID, &reg) == 0 &&
+ !PCI_POSSIBLE_ERROR(reg) &&
+ reg != (pdev->vendor | (pdev->device << 16)))
return true;

- if (pci_read_config_dword(pdev, PCI_VENDOR_ID, &reg) ||
- reg != (pdev->vendor | (pdev->device << 16)) ||
- pci_read_config_dword(pdev, PCI_CLASS_REVISION, &reg) ||
+ if (pci_read_config_dword(pdev, PCI_CLASS_REVISION, &reg) == 0 &&
+ !PCI_POSSIBLE_ERROR(reg) &&
reg != (pdev->revision | (pdev->class << 8)))
return true;

if (pdev->hdr_type == PCI_HEADER_TYPE_NORMAL &&
- (pci_read_config_dword(pdev, PCI_SUBSYSTEM_VENDOR_ID, &reg) ||
- reg != (pdev->subsystem_vendor | (pdev->subsystem_device << 16))))
+ pci_read_config_dword(pdev, PCI_SUBSYSTEM_VENDOR_ID, &reg) == 0 &&
+ !PCI_POSSIBLE_ERROR(reg) &&
+ reg != (pdev->subsystem_vendor | (pdev->subsystem_device << 16)))
return true;

- if (pci_get_dsn(pdev) != ctrl->dsn)
+ if ((dsn = pci_get_dsn(pdev)) &&
+ !PCI_POSSIBLE_ERROR(dsn) &&
+ dsn != ctrl->dsn)
return true;

return false;