From 12c3156f10c5d8c5f1fb3f0bbdb8c1ddb1d1f65c Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Mon, 18 Nov 2013 10:59:59 -0700 Subject: 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(-) (limited to 'drivers/pci/pci-driver.c') diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index 9042fdbd7244..7edd5c307446 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; } -- cgit v1.2.3 From 4fc9bbf98fd66f879e628d8537ba7c240be2b58e Mon Sep 17 00:00:00 2001 From: Khalid Aziz Date: Wed, 27 Nov 2013 15:19:25 -0700 Subject: PCI: Disable Bus Master only on kexec reboot Add a flag to tell the PCI subsystem that kernel is shutting down in preparation to kexec a kernel. Add code in PCI subsystem to use this flag to clear Bus Master bit on PCI devices only in case of kexec reboot. This fixes a power-off problem on Acer Aspire V5-573G and likely other machines and avoids any other issues caused by clearing Bus Master bit on PCI devices in normal shutdown path. The problem was introduced by b566a22c2332 ("PCI: disable Bus Master on PCI device shutdown"). This patch is based on discussion at http://marc.info/?l=linux-pci&m=138425645204355&w=2 Link: https://bugzilla.kernel.org/show_bug.cgi?id=63861 Reported-by: Chang Liu Signed-off-by: Khalid Aziz Signed-off-by: Bjorn Helgaas Acked-by: Konstantin Khlebnikov Cc: stable@vger.kernel.org # v3.5+ --- drivers/pci/pci-driver.c | 12 +++++++++--- include/linux/kexec.h | 3 +++ kernel/kexec.c | 4 ++++ 3 files changed, 16 insertions(+), 3 deletions(-) (limited to 'drivers/pci/pci-driver.c') diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index 7edd5c307446..25f0bc659164 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -19,6 +19,7 @@ #include #include #include +#include #include "pci.h" struct pci_dynid { @@ -415,12 +416,17 @@ static void pci_device_shutdown(struct device *dev) pci_msi_shutdown(pci_dev); pci_msix_shutdown(pci_dev); +#ifdef CONFIG_KEXEC /* - * Turn off Bus Master bit on the device to tell it to not - * continue to do DMA. Don't touch devices in D3cold or unknown states. + * If this is a kexec reboot, turn off Bus Master bit on the + * device to tell it to not continue to do DMA. Don't touch + * devices in D3cold or unknown states. + * If it is not a kexec reboot, firmware will hit the PCI + * devices with big hammer and stop their DMA any way. */ - if (pci_dev->current_state <= PCI_D3hot) + if (kexec_in_progress && (pci_dev->current_state <= PCI_D3hot)) pci_clear_master(pci_dev); +#endif } #ifdef CONFIG_PM diff --git a/include/linux/kexec.h b/include/linux/kexec.h index d78d28a733b1..5fd33dc1fe3a 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -198,6 +198,9 @@ extern u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4]; extern size_t vmcoreinfo_size; extern size_t vmcoreinfo_max_size; +/* flag to track if kexec reboot is in progress */ +extern bool kexec_in_progress; + int __init parse_crashkernel(char *cmdline, unsigned long long system_ram, unsigned long long *crash_size, unsigned long long *crash_base); int parse_crashkernel_high(char *cmdline, unsigned long long system_ram, diff --git a/kernel/kexec.c b/kernel/kexec.c index 490afc03627e..d0d8fca54065 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -47,6 +47,9 @@ u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4]; size_t vmcoreinfo_size; size_t vmcoreinfo_max_size = sizeof(vmcoreinfo_data); +/* Flag to indicate we are going to kexec a new kernel */ +bool kexec_in_progress = false; + /* Location of the reserved area for the crash kernel */ struct resource crashk_res = { .name = "Crash kernel", @@ -1675,6 +1678,7 @@ int kernel_kexec(void) } else #endif { + kexec_in_progress = true; kernel_restart_prepare(NULL); printk(KERN_EMERG "Starting new kernel\n"); machine_shutdown(); -- cgit v1.2.3