This is a note to let you know that I've just added the patch titled powerpc/eeh: Small refactor of eeh_handle_normal_event() to the 5.4-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary The filename of the patch is: powerpc-eeh-small-refactor-of-eeh_handle_normal_even.patch and it can be found in the queue-5.4 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable@xxxxxxxxxxxxxxx> know about it. commit 7f050d95705dae24a07692957aad1c988aa8ef4b Author: Daniel Axtens <dja@xxxxxxxxxx> Date: Fri Oct 15 18:06:27 2021 +1100 powerpc/eeh: Small refactor of eeh_handle_normal_event() [ Upstream commit 10b34ece132ee46dc4e6459c765d180c422a09fa ] The control flow of eeh_handle_normal_event() is a bit tricky. Break out one of the error handling paths - rather than be in an else block, we'll make it part of the regular body of the function and put a 'goto out;' in the true limb of the if. Signed-off-by: Daniel Axtens <dja@xxxxxxxxxx> Signed-off-by: Michael Ellerman <mpe@xxxxxxxxxxxxxx> Link: https://lore.kernel.org/r/20211015070628.1331635-1-dja@xxxxxxxxxx Stable-dep-of: 9efcdaac36e1 ("powerpc/eeh: Set channel state after notifying the drivers") Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx> diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 4fd7efdf2a53a..ee12e335fed8f 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -1072,45 +1072,46 @@ void eeh_handle_normal_event(struct eeh_pe *pe) } pr_info("EEH: Recovery successful.\n"); - } else { - /* - * About 90% of all real-life EEH failures in the field - * are due to poorly seated PCI cards. Only 10% or so are - * due to actual, failed cards. - */ - pr_err("EEH: Unable to recover from failure from PHB#%x-PE#%x.\n" - "Please try reseating or replacing it\n", - pe->phb->global_number, pe->addr); + goto out; + } - eeh_slot_error_detail(pe, EEH_LOG_PERM); + /* + * About 90% of all real-life EEH failures in the field + * are due to poorly seated PCI cards. Only 10% or so are + * due to actual, failed cards. + */ + pr_err("EEH: Unable to recover from failure from PHB#%x-PE#%x.\n" + "Please try reseating or replacing it\n", + pe->phb->global_number, pe->addr); - /* Notify all devices that they're about to go down. */ - eeh_set_channel_state(pe, pci_channel_io_perm_failure); - eeh_set_irq_state(pe, false); - eeh_pe_report("error_detected(permanent failure)", pe, - eeh_report_failure, NULL); + eeh_slot_error_detail(pe, EEH_LOG_PERM); - /* Mark the PE to be removed permanently */ - eeh_pe_state_mark(pe, EEH_PE_REMOVED); + /* Notify all devices that they're about to go down. */ + eeh_set_channel_state(pe, pci_channel_io_perm_failure); + eeh_set_irq_state(pe, false); + eeh_pe_report("error_detected(permanent failure)", pe, + eeh_report_failure, NULL); - /* - * Shut down the device drivers for good. We mark - * all removed devices correctly to avoid access - * the their PCI config any more. - */ - if (pe->type & EEH_PE_VF) { - eeh_pe_dev_traverse(pe, eeh_rmv_device, NULL); - eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED); - } else { - eeh_pe_state_clear(pe, EEH_PE_PRI_BUS, true); - eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED); + /* Mark the PE to be removed permanently */ + eeh_pe_state_mark(pe, EEH_PE_REMOVED); - pci_lock_rescan_remove(); - pci_hp_remove_devices(bus); - pci_unlock_rescan_remove(); - /* The passed PE should no longer be used */ - return; - } + /* + * Shut down the device drivers for good. We mark + * all removed devices correctly to avoid access + * the their PCI config any more. + */ + if (pe->type & EEH_PE_VF) { + eeh_pe_dev_traverse(pe, eeh_rmv_device, NULL); + eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED); + } else { + eeh_pe_state_clear(pe, EEH_PE_PRI_BUS, true); + eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED); + + pci_lock_rescan_remove(); + pci_hp_remove_devices(bus); + pci_unlock_rescan_remove(); + /* The passed PE should no longer be used */ + return; } out: