[PATCH] try parent numa_node at first before using default For pci_device, pcibios_scan_root and pci_scan_root will call pci_device_add. pci_device_add will call device_initialize and set_dev_node(&dev->dev, pcibus_to_node(bus)). other device such as netdev, and usb_device, set_dev_node is never be used. So that field numa_node always is -1.
So for netdev, it will need to use dev->parent to get pci_device to use it's numa_node. esp in netdev_alloc_skb() not sure how other device such as infiniband do that. Actually before patch [PATCH 1/2] x86_64: get mp_bus_to_node as early there is a bug about squence of bus->sysdata and using pcibus_to_node. the numa_node of pci_dev->dev is never set correctly...always 0. So some device have to use pcibus_to_node(to_pci_dev(dev)->bus) directly such as dma_alloc_pages in arch/x86_64/kernel/pci-dma.c. or hwif_to_node in include/linux/ide.h According to Stefan Richter - Change all subsystems to set dev->parent before device_initialize(). *Document* that the device_initialize() API has this requirement. This is counter-intuitive, amounts to some work across the kernel, and could be gotten wrong again in future code because it's a counter-intuitive API. - Move your code from device_initialize() to device_add(). One minor drawback is that node-specific allocations based on the device's numa_node would not be optimized before device_add(), but there is probably no need for this. Driver probes come after device_add(). - Let subsystems explicitly call set_dev_node() on their own. this patch is using second method. Also we don't need call set_dev_node in pci_device_add anymore. but need to make sure every pci root bus's bridge device numa is set. with this patch, we could use device->numa_node direclty for all device. Signed-off-by: Yinghai Lu <[EMAIL PROTECTED]> diff --git a/drivers/base/core.c b/drivers/base/core.c index dd40d78..091c2b1 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -666,6 +666,11 @@ int device_add(struct device *dev) if (error) goto Error; + /* use parent numa_node */ + if (parent) { + set_dev_node(dev, dev_to_node(dev->parent)); + } + /* first, register with generic layer. */ kobject_set_name(&dev->kobj, "%s", dev->bus_id); error = kobject_add(&dev->kobj); @@ -1285,8 +1290,11 @@ int device_move(struct device *dev, struct device *new_parent) dev->parent = new_parent; if (old_parent) klist_remove(&dev->knode_parent); - if (new_parent) + if (new_parent) { klist_add_tail(&dev->knode_parent, &new_parent->klist_children); + set_dev_node(dev, dev_to_node(new_parent)); + } + if (!dev->class) goto out_put; error = device_move_class_links(dev, old_parent, new_parent); diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index e48fcf0..c029ffc 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -935,7 +938,6 @@ void pci_device_add(struct pci_dev *dev, struct pci_bus *bus) dev->dev.release = pci_release_dev; pci_dev_get(dev); - set_dev_node(&dev->dev, pcibus_to_node(bus)); dev->dev.dma_mask = &dev->dma_mask; dev->dev.coherent_dma_mask = 0xffffffffull; @@ -1096,6 +1098,9 @@ struct pci_bus * pci_create_bus(struct device *parent, goto dev_reg_err; b->bridge = get_device(dev); + if (!parent) + set_dev_node(b->bridge, pcibus_to_node(b)); + b->class_dev.class = &pcibus_class; sprintf(b->class_dev.class_id, "%04x:%02x", pci_domain_nr(b), bus); error = class_device_register(&b->class_dev); - To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html