From 12c3156f10c5d8c5f1fb3f0bbdb8c1ddb1d1f65c Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Mon, 18 Nov 2013 10:59:59 -0700 Subject: [PATCH] PCI: Avoid unnecessary CPU switch when calling driver .probe() method If we are already on a CPU local to the device, call the driver .probe() method directly without using work_on_cpu(). This is a workaround for a lockdep warning in the following scenario: pci_call_probe work_on_cpu(cpu, local_pci_probe, ...) driver .probe pci_enable_sriov ... pci_bus_add_device ... pci_call_probe work_on_cpu(cpu, local_pci_probe, ...) It would be better to fix PCI so we don't call VF driver .probe() methods from inside a PF driver .probe() method, but that's a bigger project. [bhelgaas: open bugzilla, rework comments & changelog] Link: https://bugzilla.kernel.org/show_bug.cgi?id=65071 Link: http://lkml.kernel.org/r/CAE9FiQXYQEAZ=0sG6+2OdffBqfLS9MpoN1xviRR9aDbxPxcKxQ@mail.gmail.com Link: http://lkml.kernel.org/r/20130624195942.40795.27292.stgit@ahduyck-cp1.jf.intel.com Tested-by: Yinghai Lu Signed-off-by: Alexander Duyck Signed-off-by: Bjorn Helgaas Acked-by: Tejun Heo Acked-by: Yinghai Lu --- drivers/pci/pci-driver.c | 26 +++++++++++++++++++++----- 1 file changed, 21 insertions(+), 5 deletions(-) diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index 9042fdb..7edd5c3 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -288,12 +288,27 @@ static int pci_call_probe(struct pci_driver *drv, struct pci_dev *dev, int error, node; struct drv_dev_and_id ddi = { drv, dev, id }; - /* Execute driver initialization on node where the device's - bus is attached to. This way the driver likely allocates - its local memory on the right node without any need to - change it. */ + /* + * Execute driver initialization on node where the device is + * attached. This way the driver likely allocates its local memory + * on the right node. + */ node = dev_to_node(&dev->dev); - if (node >= 0) { + + /* + * On NUMA systems, we are likely to call a PF probe function using + * work_on_cpu(). If that probe calls pci_enable_sriov() (which + * adds the VF devices via pci_bus_add_device()), we may re-enter + * this function to call the VF probe function. Calling + * work_on_cpu() again will cause a lockdep warning. Since VFs are + * always on the same node as the PF, we can work around this by + * avoiding work_on_cpu() when we're already on the correct node. + * + * Preemption is enabled, so it's theoretically unsafe to use + * numa_node_id(), but even if we run the probe function on the + * wrong node, it should be functionally correct. + */ + if (node >= 0 && node != numa_node_id()) { int cpu; get_online_cpus(); @@ -305,6 +320,7 @@ static int pci_call_probe(struct pci_driver *drv, struct pci_dev *dev, put_online_cpus(); } else error = local_pci_probe(&ddi); + return error; } -- 2.7.4