Merge branch 'sched/urgent' into sched/core

Pick up the latest fixes before applying new changes.

Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 30 insertions, 8 deletions

diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index 9042fdb..25f0bc6 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -19,6 +19,7 @@
 #include <linux/cpu.h>
 #include <linux/pm_runtime.h>
 #include <linux/suspend.h>
+#include <linux/kexec.h>
 #include "pci.h"
 
 struct pci_dynid {
@@ -288,12 +289,27 @@ 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 +321,7 @@ static int pci_call_probe(struct pci_driver *drv, struct pci_dev *dev,
 		put_online_cpus();
 	} else
 		error = local_pci_probe(&ddi);
+
 	return error;
 }
 
@@ -399,12 +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