From 3489cdc417b20d929b33eff4d8312b4dd1f39ca1 Mon Sep 17 00:00:00 2001 From: Oliver O'Halloran Date: Mon, 15 Jul 2019 18:56:12 +1000 Subject: [PATCH] powerpc/eeh_sysfs: Make clearing EEH_DEV_SYSFS saner The eeh_sysfs_remove_device() function is supposed to clear the EEH_DEV_SYSFS flag since it indicates the EEH sysfs entries have been added for a pci_dev. When the sysfs files are removed eeh_remove_device() the eeh_dev and the pci_dev have already been de-associated. This then causes the pci_dev_to_eeh_dev() call in eeh_sysfs_remove_device() to return NULL so the flag can't be cleared from the still-live eeh_dev. This problem is worked around in the caller by clearing the flag manually. However, this behaviour doesn't make a whole lot of sense, so this patch fixes it by: a) Re-ordering eeh_remove_device() so that eeh_sysfs_remove_device() is called before de-associating the pci_dev and eeh_dev. b) Making eeh_sysfs_remove_device() emit a warning if there's no corresponding eeh_dev for a pci_dev. The paths where the sysfs files are only reachable if EEH was setup for the device for the device in the first place so hitting this warning indicates a programming error. Signed-off-by: Oliver O'Halloran Reviewed-by: Sam Bobroff Tested-by: Sam Bobroff Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20190715085612.8802-6-oohall@gmail.com --- arch/powerpc/kernel/eeh.c | 30 +++++++++++++++++------------- arch/powerpc/kernel/eeh_sysfs.c | 15 ++++++++------- 2 files changed, 25 insertions(+), 20 deletions(-) diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index bc8a551..daf9ff3 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -1191,7 +1191,6 @@ void eeh_add_device_late(struct pci_dev *dev) eeh_rmv_from_parent_pe(edev); eeh_addr_cache_rmv_dev(edev->pdev); eeh_sysfs_remove_device(edev->pdev); - edev->mode &= ~EEH_DEV_SYSFS; /* * We definitely should have the PCI device removed @@ -1296,17 +1295,11 @@ void eeh_remove_device(struct pci_dev *dev) edev->pdev = NULL; /* - * The flag "in_error" is used to trace EEH devices for VFs - * in error state or not. It's set in eeh_report_error(). If - * it's not set, eeh_report_{reset,resume}() won't be called - * for the VF EEH device. + * eeh_sysfs_remove_device() uses pci_dev_to_eeh_dev() so we need to + * remove the sysfs files before clearing dev.archdata.edev */ - edev->in_error = false; - dev->dev.archdata.edev = NULL; - if (!(edev->pe->state & EEH_PE_KEEP)) - eeh_rmv_from_parent_pe(edev); - else - edev->mode |= EEH_DEV_DISCONNECTED; + if (edev->mode & EEH_DEV_SYSFS) + eeh_sysfs_remove_device(dev); /* * We're removing from the PCI subsystem, that means @@ -1317,8 +1310,19 @@ void eeh_remove_device(struct pci_dev *dev) edev->mode |= EEH_DEV_NO_HANDLER; eeh_addr_cache_rmv_dev(dev); - eeh_sysfs_remove_device(dev); - edev->mode &= ~EEH_DEV_SYSFS; + + /* + * The flag "in_error" is used to trace EEH devices for VFs + * in error state or not. It's set in eeh_report_error(). If + * it's not set, eeh_report_{reset,resume}() won't be called + * for the VF EEH device. + */ + edev->in_error = false; + dev->dev.archdata.edev = NULL; + if (!(edev->pe->state & EEH_PE_KEEP)) + eeh_rmv_from_parent_pe(edev); + else + edev->mode |= EEH_DEV_DISCONNECTED; } int eeh_unfreeze_pe(struct eeh_pe *pe) diff --git a/arch/powerpc/kernel/eeh_sysfs.c b/arch/powerpc/kernel/eeh_sysfs.c index a6638ea..4fb0f1e 100644 --- a/arch/powerpc/kernel/eeh_sysfs.c +++ b/arch/powerpc/kernel/eeh_sysfs.c @@ -159,22 +159,23 @@ void eeh_sysfs_remove_device(struct pci_dev *pdev) { struct eeh_dev *edev = pci_dev_to_eeh_dev(pdev); + if (!edev) { + WARN_ON(eeh_enabled()); + return; + } + + edev->mode &= ~EEH_DEV_SYSFS; + /* * The parent directory might have been removed. We needn't * continue for that case. */ - if (!pdev->dev.kobj.sd) { - if (edev) - edev->mode &= ~EEH_DEV_SYSFS; + if (!pdev->dev.kobj.sd) return; - } device_remove_file(&pdev->dev, &dev_attr_eeh_mode); device_remove_file(&pdev->dev, &dev_attr_eeh_pe_config_addr); device_remove_file(&pdev->dev, &dev_attr_eeh_pe_state); eeh_notify_resume_remove(pdev); - - if (edev) - edev->mode &= ~EEH_DEV_SYSFS; } -- 2.7.4