Rajat Jain reported a deadlock when a hierarchical hot plug thread and aer recovery thread both run. https://lkml.org/lkml/2015/3/11/861 thread 1: pciehp_enable_slot() pciehp_configure_device() pci_bus_add_devices() device_attach(dev) device_lock(dev) //acquire device mutex successfully ... pciehp_probe(dev) __pci_hp_register() pci_create_slot() down_write(pci_bus_sem) //deadlock here thread 2: aer_isr_one_error() aer_process_err_device() do_recovery() broadcast_error_message() pci_walk_bus() down_read(&pci_bus_sem) //acquire pci_bus_sem successfully report_error_detected(dev) device_lock(dev) // deadlock here We use down_write(&pci_bus_sem) to protect the bus->slots list, because the bus->slots list is only accessed in drivers/pci/slot.c, we could introduce a new local mutex to protect bus->slots, and use down_read(&pci_bus_sem) instead of down_write(&pci_bus_sem) to protect the bus->devices list. Signed-off-by: Yijing Wang <wangyijing@xxxxxxxxxx> --- drivers/pci/slot.c | 15 ++++++++++----- include/linux/pci.h | 3 ++- 2 files changed, 12 insertions(+), 6 deletions(-) diff --git a/drivers/pci/slot.c b/drivers/pci/slot.c index 396c200..a9079d9 100644 --- a/drivers/pci/slot.c +++ b/drivers/pci/slot.c @@ -14,6 +14,7 @@ struct kset *pci_slots_kset; EXPORT_SYMBOL_GPL(pci_slots_kset); +static DEFINE_MUTEX(pci_slot_mutex); static ssize_t pci_slot_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) @@ -106,9 +107,11 @@ static void pci_slot_release(struct kobject *kobj) dev_dbg(&slot->bus->dev, "dev %02x, released physical slot %s\n", slot->number, pci_slot_name(slot)); + down_read(&pci_bus_sem); list_for_each_entry(dev, &slot->bus->devices, bus_list) if (PCI_SLOT(dev->devfn) == slot->number) dev->slot = NULL; + up_read(&pci_bus_sem); list_del(&slot->list); @@ -195,7 +198,7 @@ static struct pci_slot *get_slot(struct pci_bus *parent, int slot_nr) { struct pci_slot *slot; /* - * We already hold pci_bus_sem so don't worry + * We already hold pci_slot_mutex so don't worry */ list_for_each_entry(slot, &parent->slots, list) if (slot->number == slot_nr) { @@ -253,7 +256,7 @@ struct pci_slot *pci_create_slot(struct pci_bus *parent, int slot_nr, int err = 0; char *slot_name = NULL; - down_write(&pci_bus_sem); + mutex_lock(&pci_slot_mutex); if (slot_nr == -1) goto placeholder; @@ -301,16 +304,18 @@ placeholder: INIT_LIST_HEAD(&slot->list); list_add(&slot->list, &parent->slots); + down_read(&pci_bus_sem); list_for_each_entry(dev, &parent->devices, bus_list) if (PCI_SLOT(dev->devfn) == slot_nr) dev->slot = slot; + up_read(&pci_bus_sem); dev_dbg(&parent->dev, "dev %02x, created physical slot %s\n", slot_nr, pci_slot_name(slot)); out: kfree(slot_name); - up_write(&pci_bus_sem); + mutex_unlock(&pci_slot_mutex); return slot; err: kfree(slot); @@ -332,9 +337,9 @@ void pci_destroy_slot(struct pci_slot *slot) dev_dbg(&slot->bus->dev, "dev %02x, dec refcount to %d\n", slot->number, atomic_read(&slot->kobj.kref.refcount) - 1); - down_write(&pci_bus_sem); + mutex_lock(&pci_slot_mutex); kobject_put(&slot->kobj); - up_write(&pci_bus_sem); + mutex_unlock(&pci_slot_mutex); } EXPORT_SYMBOL_GPL(pci_destroy_slot); diff --git a/include/linux/pci.h b/include/linux/pci.h index 8a0321a..34cc95d 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -446,7 +446,8 @@ struct pci_bus { struct list_head children; /* list of child buses */ struct list_head devices; /* list of devices on this bus */ struct pci_dev *self; /* bridge device as seen by parent */ - struct list_head slots; /* list of slots on this bus */ + struct list_head slots; /* list of slots on this bus, we use a local pci_slot_mutex instead of + pci_bus_sem to protect this list to fix a potential ABBA deadlock */ struct resource *resource[PCI_BRIDGE_RESOURCE_NUM]; struct list_head resources; /* address space routed to this bus */ struct resource busn_res; /* bus numbers routed to this bus */ -- 1.7.1 -- To unsubscribe from this list: send the line "unsubscribe linux-pci" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
