From 91552f87853c6e50b3968f6514ddb9084acb9f10 Mon Sep 17 00:00:00 2001 From: Daniel Axtens Date: Fri, 14 Aug 2015 16:03:19 +1000 Subject: [PATCH] powerpc/eeh: Probe after unbalanced kref check commit e642d11bdbfe8eb10116ab3959a2b5d75efda832 upstream. In the complete hotplug case, EEH PEs are supposed to be released and set to NULL. Normally, this is done by eeh_remove_device(), which is called from pcibios_release_device(). However, if something is holding a kref to the device, it will not be released, and the PE will remain. eeh_add_device_late() has a check for this which will explictly destroy the PE in this case. This check in eeh_add_device_late() occurs after a call to eeh_ops->probe(). On PowerNV, probe is a pointer to pnv_eeh_probe(), which will exit without probing if there is an existing PE. This means that on PowerNV, devices with outstanding krefs will not be rediscovered by EEH correctly after a complete hotplug. This is affecting CXL (CAPI) devices in the field. Put the probe after the kref check so that the PE is destroyed and affected devices are correctly rediscovered by EEH. Fixes: d91dafc02f42 ("powerpc/eeh: Delay probing EEH device during hotplug") Cc: Gavin Shan Signed-off-by: Daniel Axtens Acked-by: Gavin Shan Signed-off-by: Michael Ellerman Signed-off-by: Greg Kroah-Hartman --- arch/powerpc/kernel/eeh.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index 9ee61d15653d..1d94bc2a1047 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -1118,9 +1118,6 @@ void eeh_add_device_late(struct pci_dev *dev) return; } - if (eeh_has_flag(EEH_PROBE_MODE_DEV)) - eeh_ops->probe(pdn, NULL); - /* * The EEH cache might not be removed correctly because of * unbalanced kref to the device during unplug time, which @@ -1144,6 +1141,9 @@ void eeh_add_device_late(struct pci_dev *dev) dev->dev.archdata.edev = NULL; } + if (eeh_has_flag(EEH_PROBE_MODE_DEV)) + eeh_ops->probe(pdn, NULL); + edev->pdev = dev; dev->dev.archdata.edev = edev; -- 2.50.1