linux_dsm_epyc7002/drivers/pci/hotplug/pciehp_pci.c
Mika Westerberg 499022396a PCI: pciehp: Fix race condition handling surprise link down
A surprise link down may retrain very quickly causing the same slot
generate a link up event before handling the link down event completes.

Since the link is active, the power off work queued from the first link
down will cause a second down event when power is disabled. However, the
link up event sets the slot state to POWERON_STATE before the event to
handle this is enqueued, making the second down event believe it needs to
do something.

This creates constant link up and down event cycle.

To prevent this it is better to handle each event at the time in order it
occurred, so change the driver to use ordered workqueue instead.

A normal device hotplug triggers two events (presense detect and link up)
that are already handled properly in the driver but we currently log an
error if we find an existing device in the slot. Since this is not an error
change the log level to be debug instead to avoid scaring users.

This is based on the original work by Ashok Raj.

Link: https://patchwork.kernel.org/patch/9469023
Suggested-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
2017-11-06 18:49:00 -06:00

138 lines
3.8 KiB
C

/*
* PCI Express Hot Plug Controller Driver
*
* Copyright (C) 1995,2001 Compaq Computer Corporation
* Copyright (C) 2001 Greg Kroah-Hartman (greg@kroah.com)
* Copyright (C) 2001 IBM Corp.
* Copyright (C) 2003-2004 Intel Corporation
*
* All rights reserved.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or (at
* your option) any later version.
*
* This program is distributed in the hope that it will be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
* NON INFRINGEMENT. See the GNU General Public License for more
* details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*
* Send feedback to <greg@kroah.com>, <kristen.c.accardi@intel.com>
*
*/
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/pci.h>
#include "../pci.h"
#include "pciehp.h"
int pciehp_configure_device(struct slot *p_slot)
{
struct pci_dev *dev;
struct pci_dev *bridge = p_slot->ctrl->pcie->port;
struct pci_bus *parent = bridge->subordinate;
int num, ret = 0;
struct controller *ctrl = p_slot->ctrl;
pci_lock_rescan_remove();
dev = pci_get_slot(parent, PCI_DEVFN(0, 0));
if (dev) {
/*
* The device is already there. Either configured by the
* boot firmware or a previous hotplug event.
*/
ctrl_dbg(ctrl, "Device %s already exists at %04x:%02x:00, skipping hot-add\n",
pci_name(dev), pci_domain_nr(parent), parent->number);
pci_dev_put(dev);
ret = -EEXIST;
goto out;
}
num = pci_scan_slot(parent, PCI_DEVFN(0, 0));
if (num == 0) {
ctrl_err(ctrl, "No new device found\n");
ret = -ENODEV;
goto out;
}
for_each_pci_bridge(dev, parent)
pci_hp_add_bridge(dev);
pci_assign_unassigned_bridge_resources(bridge);
pcie_bus_configure_settings(parent);
pci_bus_add_devices(parent);
out:
pci_unlock_rescan_remove();
return ret;
}
int pciehp_unconfigure_device(struct slot *p_slot)
{
int rc = 0;
u8 bctl = 0;
u8 presence = 0;
struct pci_dev *dev, *temp;
struct pci_bus *parent = p_slot->ctrl->pcie->port->subordinate;
u16 command;
struct controller *ctrl = p_slot->ctrl;
ctrl_dbg(ctrl, "%s: domain:bus:dev = %04x:%02x:00\n",
__func__, pci_domain_nr(parent), parent->number);
pciehp_get_adapter_status(p_slot, &presence);
pci_lock_rescan_remove();
/*
* 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. We do the same in pci_stop_bus_device().
*/
list_for_each_entry_safe_reverse(dev, temp, &parent->devices,
bus_list) {
pci_dev_get(dev);
if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE && presence) {
pci_read_config_byte(dev, PCI_BRIDGE_CONTROL, &bctl);
if (bctl & PCI_BRIDGE_CTL_VGA) {
ctrl_err(ctrl,
"Cannot remove display device %s\n",
pci_name(dev));
pci_dev_put(dev);
rc = -EINVAL;
break;
}
}
if (!presence) {
pci_dev_set_disconnected(dev, NULL);
if (pci_has_subordinate(dev))
pci_walk_bus(dev->subordinate,
pci_dev_set_disconnected, NULL);
}
pci_stop_and_remove_bus_device(dev);
/*
* Ensure that no new Requests will be generated from
* the device.
*/
if (presence) {
pci_read_config_word(dev, PCI_COMMAND, &command);
command &= ~(PCI_COMMAND_MASTER | PCI_COMMAND_SERR);
command |= PCI_COMMAND_INTX_DISABLE;
pci_write_config_word(dev, PCI_COMMAND, command);
}
pci_dev_put(dev);
}
pci_unlock_rescan_remove();
return rc;
}