linux-stable/drivers/pci/remove.c
Hari Vyas 44bda4b7d2 PCI: Fix is_added/is_busmaster race condition
When a PCI device is detected, pdev->is_added is set to 1 and proc and
sysfs entries are created.

When the device is removed, pdev->is_added is checked for one and then
device is detached with clearing of proc and sys entries and at end,
pdev->is_added is set to 0.

is_added and is_busmaster are bit fields in pci_dev structure sharing same
memory location.

A strange issue was observed with multiple removal and rescan of a PCIe
NVMe device using sysfs commands where is_added flag was observed as zero
instead of one while removing device and proc,sys entries are not cleared.
This causes issue in later device addition with warning message
"proc_dir_entry" already registered.

Debugging revealed a race condition between the PCI core setting the
is_added bit in pci_bus_add_device() and the NVMe driver reset work-queue
setting the is_busmaster bit in pci_set_master().  As these fields are not
handled atomically, that clears the is_added bit.

Move the is_added bit to a separate private flag variable and use atomic
functions to set and retrieve the device addition state.  This avoids the
race because is_added no longer shares a memory location with is_busmaster.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=200283
Signed-off-by: Hari Vyas <hari.vyas@broadcom.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Lukas Wunner <lukas@wunner.de>
Acked-by: Michael Ellerman <mpe@ellerman.id.au>
2018-07-31 11:27:54 -05:00

168 lines
3.7 KiB
C

// SPDX-License-Identifier: GPL-2.0
#include <linux/pci.h>
#include <linux/module.h>
#include <linux/pci-aspm.h>
#include "pci.h"
static void pci_free_resources(struct pci_dev *dev)
{
int i;
for (i = 0; i < PCI_NUM_RESOURCES; i++) {
struct resource *res = dev->resource + i;
if (res->parent)
release_resource(res);
}
}
static void pci_stop_dev(struct pci_dev *dev)
{
pci_pme_active(dev, false);
if (pci_dev_is_added(dev)) {
device_release_driver(&dev->dev);
pci_proc_detach_device(dev);
pci_remove_sysfs_dev_files(dev);
pci_dev_assign_added(dev, false);
}
if (dev->bus->self)
pcie_aspm_exit_link_state(dev);
}
static void pci_destroy_dev(struct pci_dev *dev)
{
if (!dev->dev.kobj.parent)
return;
device_del(&dev->dev);
down_write(&pci_bus_sem);
list_del(&dev->bus_list);
up_write(&pci_bus_sem);
pci_bridge_d3_update(dev);
pci_free_resources(dev);
put_device(&dev->dev);
}
void pci_remove_bus(struct pci_bus *bus)
{
pci_proc_detach_bus(bus);
down_write(&pci_bus_sem);
list_del(&bus->node);
pci_bus_release_busn_res(bus);
up_write(&pci_bus_sem);
pci_remove_legacy_files(bus);
if (bus->ops->remove_bus)
bus->ops->remove_bus(bus);
pcibios_remove_bus(bus);
device_unregister(&bus->dev);
}
EXPORT_SYMBOL(pci_remove_bus);
static void pci_stop_bus_device(struct pci_dev *dev)
{
struct pci_bus *bus = dev->subordinate;
struct pci_dev *child, *tmp;
/*
* Stopping an SR-IOV PF device removes all the associated VFs,
* which will update the bus->devices list and confuse the
* iterator. Therefore, iterate in reverse so we remove the VFs
* first, then the PF.
*/
if (bus) {
list_for_each_entry_safe_reverse(child, tmp,
&bus->devices, bus_list)
pci_stop_bus_device(child);
}
pci_stop_dev(dev);
}
static void pci_remove_bus_device(struct pci_dev *dev)
{
struct pci_bus *bus = dev->subordinate;
struct pci_dev *child, *tmp;
if (bus) {
list_for_each_entry_safe(child, tmp,
&bus->devices, bus_list)
pci_remove_bus_device(child);
pci_remove_bus(bus);
dev->subordinate = NULL;
}
pci_destroy_dev(dev);
}
/**
* pci_stop_and_remove_bus_device - remove a PCI device and any children
* @dev: the device to remove
*
* Remove a PCI device from the device lists, informing the drivers
* that the device has been removed. We also remove any subordinate
* buses and children in a depth-first manner.
*
* For each device we remove, delete the device structure from the
* device lists, remove the /proc entry, and notify userspace
* (/sbin/hotplug).
*/
void pci_stop_and_remove_bus_device(struct pci_dev *dev)
{
pci_stop_bus_device(dev);
pci_remove_bus_device(dev);
}
EXPORT_SYMBOL(pci_stop_and_remove_bus_device);
void pci_stop_and_remove_bus_device_locked(struct pci_dev *dev)
{
pci_lock_rescan_remove();
pci_stop_and_remove_bus_device(dev);
pci_unlock_rescan_remove();
}
EXPORT_SYMBOL_GPL(pci_stop_and_remove_bus_device_locked);
void pci_stop_root_bus(struct pci_bus *bus)
{
struct pci_dev *child, *tmp;
struct pci_host_bridge *host_bridge;
if (!pci_is_root_bus(bus))
return;
host_bridge = to_pci_host_bridge(bus->bridge);
list_for_each_entry_safe_reverse(child, tmp,
&bus->devices, bus_list)
pci_stop_bus_device(child);
/* stop the host bridge */
device_release_driver(&host_bridge->dev);
}
EXPORT_SYMBOL_GPL(pci_stop_root_bus);
void pci_remove_root_bus(struct pci_bus *bus)
{
struct pci_dev *child, *tmp;
struct pci_host_bridge *host_bridge;
if (!pci_is_root_bus(bus))
return;
host_bridge = to_pci_host_bridge(bus->bridge);
list_for_each_entry_safe(child, tmp,
&bus->devices, bus_list)
pci_remove_bus_device(child);
pci_remove_bus(bus);
host_bridge->bus = NULL;
/* remove the host bridge */
device_unregister(&host_bridge->dev);
}
EXPORT_SYMBOL_GPL(pci_remove_root_bus);