OpenCloudOS-Kernel/drivers/pci/pci-driver.c

1660 lines
42 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* (C) Copyright 2002-2004, 2007 Greg Kroah-Hartman <greg@kroah.com>
* (C) Copyright 2007 Novell Inc.
*/
#include <linux/pci.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/device.h>
#include <linux/mempolicy.h>
#include <linux/string.h>
#include <linux/slab.h>
#include <linux/sched.h>
#include <linux/sched/isolation.h>
#include <linux/cpu.h>
#include <linux/pm_runtime.h>
#include <linux/suspend.h>
#include <linux/kexec.h>
#include <linux/of_device.h>
#include <linux/acpi.h>
#include <linux/dma-map-ops.h>
#include "pci.h"
#include "pcie/portdrv.h"
struct pci_dynid {
struct list_head node;
struct pci_device_id id;
};
/**
* pci_add_dynid - add a new PCI device ID to this driver and re-probe devices
* @drv: target pci driver
* @vendor: PCI vendor ID
* @device: PCI device ID
* @subvendor: PCI subvendor ID
* @subdevice: PCI subdevice ID
* @class: PCI class
* @class_mask: PCI class mask
* @driver_data: private driver data
*
* Adds a new dynamic pci device ID to this driver and causes the
* driver to probe for all devices again. @drv must have been
* registered prior to calling this function.
*
* CONTEXT:
* Does GFP_KERNEL allocation.
*
* RETURNS:
* 0 on success, -errno on failure.
*/
int pci_add_dynid(struct pci_driver *drv,
unsigned int vendor, unsigned int device,
unsigned int subvendor, unsigned int subdevice,
unsigned int class, unsigned int class_mask,
unsigned long driver_data)
{
struct pci_dynid *dynid;
dynid = kzalloc(sizeof(*dynid), GFP_KERNEL);
if (!dynid)
return -ENOMEM;
dynid->id.vendor = vendor;
dynid->id.device = device;
dynid->id.subvendor = subvendor;
dynid->id.subdevice = subdevice;
dynid->id.class = class;
dynid->id.class_mask = class_mask;
dynid->id.driver_data = driver_data;
spin_lock(&drv->dynids.lock);
list_add_tail(&dynid->node, &drv->dynids.list);
spin_unlock(&drv->dynids.lock);
return driver_attach(&drv->driver);
}
EXPORT_SYMBOL_GPL(pci_add_dynid);
static void pci_free_dynids(struct pci_driver *drv)
{
struct pci_dynid *dynid, *n;
spin_lock(&drv->dynids.lock);
list_for_each_entry_safe(dynid, n, &drv->dynids.list, node) {
list_del(&dynid->node);
kfree(dynid);
}
spin_unlock(&drv->dynids.lock);
}
/**
* store_new_id - sysfs frontend to pci_add_dynid()
* @driver: target device driver
* @buf: buffer for scanning device ID data
* @count: input size
*
* Allow PCI IDs to be added to an existing driver via sysfs.
*/
static ssize_t new_id_store(struct device_driver *driver, const char *buf,
size_t count)
{
struct pci_driver *pdrv = to_pci_driver(driver);
const struct pci_device_id *ids = pdrv->id_table;
u32 vendor, device, subvendor = PCI_ANY_ID,
subdevice = PCI_ANY_ID, class = 0, class_mask = 0;
unsigned long driver_data = 0;
int fields = 0;
int retval = 0;
fields = sscanf(buf, "%x %x %x %x %x %x %lx",
&vendor, &device, &subvendor, &subdevice,
&class, &class_mask, &driver_data);
if (fields < 2)
return -EINVAL;
if (fields != 7) {
struct pci_dev *pdev = kzalloc(sizeof(*pdev), GFP_KERNEL);
if (!pdev)
return -ENOMEM;
pdev->vendor = vendor;
pdev->device = device;
pdev->subsystem_vendor = subvendor;
pdev->subsystem_device = subdevice;
pdev->class = class;
if (pci_match_id(pdrv->id_table, pdev))
retval = -EEXIST;
kfree(pdev);
if (retval)
return retval;
}
/* Only accept driver_data values that match an existing id_table
entry */
if (ids) {
retval = -EINVAL;
while (ids->vendor || ids->subvendor || ids->class_mask) {
if (driver_data == ids->driver_data) {
retval = 0;
break;
}
ids++;
}
if (retval) /* No match */
return retval;
}
retval = pci_add_dynid(pdrv, vendor, device, subvendor, subdevice,
class, class_mask, driver_data);
if (retval)
return retval;
return count;
}
static DRIVER_ATTR_WO(new_id);
/**
* store_remove_id - remove a PCI device ID from this driver
* @driver: target device driver
* @buf: buffer for scanning device ID data
* @count: input size
*
* Removes a dynamic pci device ID to this driver.
*/
static ssize_t remove_id_store(struct device_driver *driver, const char *buf,
size_t count)
{
struct pci_dynid *dynid, *n;
struct pci_driver *pdrv = to_pci_driver(driver);
u32 vendor, device, subvendor = PCI_ANY_ID,
subdevice = PCI_ANY_ID, class = 0, class_mask = 0;
int fields = 0;
size_t retval = -ENODEV;
fields = sscanf(buf, "%x %x %x %x %x %x",
&vendor, &device, &subvendor, &subdevice,
&class, &class_mask);
if (fields < 2)
return -EINVAL;
spin_lock(&pdrv->dynids.lock);
list_for_each_entry_safe(dynid, n, &pdrv->dynids.list, node) {
struct pci_device_id *id = &dynid->id;
if ((id->vendor == vendor) &&
(id->device == device) &&
(subvendor == PCI_ANY_ID || id->subvendor == subvendor) &&
(subdevice == PCI_ANY_ID || id->subdevice == subdevice) &&
!((id->class ^ class) & class_mask)) {
list_del(&dynid->node);
kfree(dynid);
retval = count;
break;
}
}
spin_unlock(&pdrv->dynids.lock);
return retval;
}
static DRIVER_ATTR_WO(remove_id);
static struct attribute *pci_drv_attrs[] = {
&driver_attr_new_id.attr,
&driver_attr_remove_id.attr,
NULL,
};
ATTRIBUTE_GROUPS(pci_drv);
/**
* pci_match_id - See if a pci device matches a given pci_id table
* @ids: array of PCI device id structures to search in
* @dev: the PCI device structure to match against.
*
* Used by a driver to check whether a PCI device present in the
* system is in its list of supported devices. Returns the matching
* pci_device_id structure or %NULL if there is no match.
*
* Deprecated, don't use this as it will not catch any dynamic ids
* that a driver might want to check for.
*/
const struct pci_device_id *pci_match_id(const struct pci_device_id *ids,
struct pci_dev *dev)
{
if (ids) {
while (ids->vendor || ids->subvendor || ids->class_mask) {
if (pci_match_one_device(ids, dev))
return ids;
ids++;
}
}
return NULL;
}
EXPORT_SYMBOL(pci_match_id);
PCI: Introduce new device binding path using pci_dev.driver_override The driver_override field allows us to specify the driver for a device rather than relying on the driver to provide a positive match of the device. This shortcuts the existing process of looking up the vendor and device ID, adding them to the driver new_id, binding the device, then removing the ID, but it also provides a couple advantages. First, the above existing process allows the driver to bind to any device matching the new_id for the window where it's enabled. This is often not desired, such as the case of trying to bind a single device to a meta driver like pci-stub or vfio-pci. Using driver_override we can do this deterministically using: echo pci-stub > /sys/bus/pci/devices/0000:03:00.0/driver_override echo 0000:03:00.0 > /sys/bus/pci/devices/0000:03:00.0/driver/unbind echo 0000:03:00.0 > /sys/bus/pci/drivers_probe Previously we could not invoke drivers_probe after adding a device to new_id for a driver as we get non-deterministic behavior whether the driver we intend or the standard driver will claim the device. Now it becomes a deterministic process, only the driver matching driver_override will probe the device. To return the device to the standard driver, we simply clear the driver_override and reprobe the device: echo > /sys/bus/pci/devices/0000:03:00.0/driver_override echo 0000:03:00.0 > /sys/bus/pci/devices/0000:03:00.0/driver/unbind echo 0000:03:00.0 > /sys/bus/pci/drivers_probe Another advantage to this approach is that we can specify a driver override to force a specific binding or prevent any binding. For instance when an IOMMU group is exposed to userspace through VFIO we require that all devices within that group are owned by VFIO. However, devices can be hot-added into an IOMMU group, in which case we want to prevent the device from binding to any driver (override driver = "none") or perhaps have it automatically bind to vfio-pci. With driver_override it's a simple matter for this field to be set internally when the device is first discovered to prevent driver matches. Signed-off-by: Alex Williamson <alex.williamson@redhat.com> Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Reviewed-by: Alexander Graf <agraf@suse.de> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-05-20 22:53:21 +08:00
static const struct pci_device_id pci_device_id_any = {
.vendor = PCI_ANY_ID,
.device = PCI_ANY_ID,
.subvendor = PCI_ANY_ID,
.subdevice = PCI_ANY_ID,
};
/**
* pci_match_device - Tell if a PCI device structure has a matching PCI device id structure
* @drv: the PCI driver to match against
* @dev: the PCI device structure to match against
*
* Used by a driver to check whether a PCI device present in the
* system is in its list of supported devices. Returns the matching
* pci_device_id structure or %NULL if there is no match.
*/
static const struct pci_device_id *pci_match_device(struct pci_driver *drv,
struct pci_dev *dev)
{
struct pci_dynid *dynid;
PCI: Introduce new device binding path using pci_dev.driver_override The driver_override field allows us to specify the driver for a device rather than relying on the driver to provide a positive match of the device. This shortcuts the existing process of looking up the vendor and device ID, adding them to the driver new_id, binding the device, then removing the ID, but it also provides a couple advantages. First, the above existing process allows the driver to bind to any device matching the new_id for the window where it's enabled. This is often not desired, such as the case of trying to bind a single device to a meta driver like pci-stub or vfio-pci. Using driver_override we can do this deterministically using: echo pci-stub > /sys/bus/pci/devices/0000:03:00.0/driver_override echo 0000:03:00.0 > /sys/bus/pci/devices/0000:03:00.0/driver/unbind echo 0000:03:00.0 > /sys/bus/pci/drivers_probe Previously we could not invoke drivers_probe after adding a device to new_id for a driver as we get non-deterministic behavior whether the driver we intend or the standard driver will claim the device. Now it becomes a deterministic process, only the driver matching driver_override will probe the device. To return the device to the standard driver, we simply clear the driver_override and reprobe the device: echo > /sys/bus/pci/devices/0000:03:00.0/driver_override echo 0000:03:00.0 > /sys/bus/pci/devices/0000:03:00.0/driver/unbind echo 0000:03:00.0 > /sys/bus/pci/drivers_probe Another advantage to this approach is that we can specify a driver override to force a specific binding or prevent any binding. For instance when an IOMMU group is exposed to userspace through VFIO we require that all devices within that group are owned by VFIO. However, devices can be hot-added into an IOMMU group, in which case we want to prevent the device from binding to any driver (override driver = "none") or perhaps have it automatically bind to vfio-pci. With driver_override it's a simple matter for this field to be set internally when the device is first discovered to prevent driver matches. Signed-off-by: Alex Williamson <alex.williamson@redhat.com> Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Reviewed-by: Alexander Graf <agraf@suse.de> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-05-20 22:53:21 +08:00
const struct pci_device_id *found_id = NULL;
/* When driver_override is set, only bind to the matching driver */
if (dev->driver_override && strcmp(dev->driver_override, drv->name))
return NULL;
PCI: use /sys/bus/pci/drivers/<driver>/new_id first Unfortunately, the .../new_id feature does not work with the 8250_pci driver. The reason for this comes down to the way .../new_id is implemented. When PCI tries to match a driver to a device, it checks the modules static device ID tables _before_ checking the dynamic new_id tables. When a driver is capable of matching by ID, and falls back to matching by class (as 8250_pci does), this makes it absolutely impossible to specify a board by ID, and as such the correct driver_data value to use with it. Let's say you have a serial board with vendor 0x1234 and device 0x5678. It's class is set to PCI_CLASS_COMMUNICATION_SERIAL. On boot, this card is matched to the 8250_pci driver, which tries to probe it because it matched using the class entry. The driver finds that it is unable to automatically detect the correct settings to use, so it returns -ENODEV. You know that the information the driver needs is to match this card using a device_data value of '7'. So you echo 1234 5678 0 0 0 0 7 into new_id. The kernel attempts to re-bind 8250_pci to this device. However, because it scans the PCI driver tables, it _again_ matches the class entry which has the wrong device_data. It fails. End of story. You can't support the card without rebuilding the kernel (or writing a specific PCI probe module to support it.) So, can we make new_id override the driver-internal PCI ID tables? IOW, like this: From: Russell King <rmk@arm.linux.org.uk> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2006-11-30 05:18:04 +08:00
/* Look at the dynamic ids first, before the static ones */
spin_lock(&drv->dynids.lock);
list_for_each_entry(dynid, &drv->dynids.list, node) {
if (pci_match_one_device(&dynid->id, dev)) {
PCI: Introduce new device binding path using pci_dev.driver_override The driver_override field allows us to specify the driver for a device rather than relying on the driver to provide a positive match of the device. This shortcuts the existing process of looking up the vendor and device ID, adding them to the driver new_id, binding the device, then removing the ID, but it also provides a couple advantages. First, the above existing process allows the driver to bind to any device matching the new_id for the window where it's enabled. This is often not desired, such as the case of trying to bind a single device to a meta driver like pci-stub or vfio-pci. Using driver_override we can do this deterministically using: echo pci-stub > /sys/bus/pci/devices/0000:03:00.0/driver_override echo 0000:03:00.0 > /sys/bus/pci/devices/0000:03:00.0/driver/unbind echo 0000:03:00.0 > /sys/bus/pci/drivers_probe Previously we could not invoke drivers_probe after adding a device to new_id for a driver as we get non-deterministic behavior whether the driver we intend or the standard driver will claim the device. Now it becomes a deterministic process, only the driver matching driver_override will probe the device. To return the device to the standard driver, we simply clear the driver_override and reprobe the device: echo > /sys/bus/pci/devices/0000:03:00.0/driver_override echo 0000:03:00.0 > /sys/bus/pci/devices/0000:03:00.0/driver/unbind echo 0000:03:00.0 > /sys/bus/pci/drivers_probe Another advantage to this approach is that we can specify a driver override to force a specific binding or prevent any binding. For instance when an IOMMU group is exposed to userspace through VFIO we require that all devices within that group are owned by VFIO. However, devices can be hot-added into an IOMMU group, in which case we want to prevent the device from binding to any driver (override driver = "none") or perhaps have it automatically bind to vfio-pci. With driver_override it's a simple matter for this field to be set internally when the device is first discovered to prevent driver matches. Signed-off-by: Alex Williamson <alex.williamson@redhat.com> Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Reviewed-by: Alexander Graf <agraf@suse.de> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-05-20 22:53:21 +08:00
found_id = &dynid->id;
break;
}
}
spin_unlock(&drv->dynids.lock);
PCI: use /sys/bus/pci/drivers/<driver>/new_id first Unfortunately, the .../new_id feature does not work with the 8250_pci driver. The reason for this comes down to the way .../new_id is implemented. When PCI tries to match a driver to a device, it checks the modules static device ID tables _before_ checking the dynamic new_id tables. When a driver is capable of matching by ID, and falls back to matching by class (as 8250_pci does), this makes it absolutely impossible to specify a board by ID, and as such the correct driver_data value to use with it. Let's say you have a serial board with vendor 0x1234 and device 0x5678. It's class is set to PCI_CLASS_COMMUNICATION_SERIAL. On boot, this card is matched to the 8250_pci driver, which tries to probe it because it matched using the class entry. The driver finds that it is unable to automatically detect the correct settings to use, so it returns -ENODEV. You know that the information the driver needs is to match this card using a device_data value of '7'. So you echo 1234 5678 0 0 0 0 7 into new_id. The kernel attempts to re-bind 8250_pci to this device. However, because it scans the PCI driver tables, it _again_ matches the class entry which has the wrong device_data. It fails. End of story. You can't support the card without rebuilding the kernel (or writing a specific PCI probe module to support it.) So, can we make new_id override the driver-internal PCI ID tables? IOW, like this: From: Russell King <rmk@arm.linux.org.uk> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2006-11-30 05:18:04 +08:00
PCI: Introduce new device binding path using pci_dev.driver_override The driver_override field allows us to specify the driver for a device rather than relying on the driver to provide a positive match of the device. This shortcuts the existing process of looking up the vendor and device ID, adding them to the driver new_id, binding the device, then removing the ID, but it also provides a couple advantages. First, the above existing process allows the driver to bind to any device matching the new_id for the window where it's enabled. This is often not desired, such as the case of trying to bind a single device to a meta driver like pci-stub or vfio-pci. Using driver_override we can do this deterministically using: echo pci-stub > /sys/bus/pci/devices/0000:03:00.0/driver_override echo 0000:03:00.0 > /sys/bus/pci/devices/0000:03:00.0/driver/unbind echo 0000:03:00.0 > /sys/bus/pci/drivers_probe Previously we could not invoke drivers_probe after adding a device to new_id for a driver as we get non-deterministic behavior whether the driver we intend or the standard driver will claim the device. Now it becomes a deterministic process, only the driver matching driver_override will probe the device. To return the device to the standard driver, we simply clear the driver_override and reprobe the device: echo > /sys/bus/pci/devices/0000:03:00.0/driver_override echo 0000:03:00.0 > /sys/bus/pci/devices/0000:03:00.0/driver/unbind echo 0000:03:00.0 > /sys/bus/pci/drivers_probe Another advantage to this approach is that we can specify a driver override to force a specific binding or prevent any binding. For instance when an IOMMU group is exposed to userspace through VFIO we require that all devices within that group are owned by VFIO. However, devices can be hot-added into an IOMMU group, in which case we want to prevent the device from binding to any driver (override driver = "none") or perhaps have it automatically bind to vfio-pci. With driver_override it's a simple matter for this field to be set internally when the device is first discovered to prevent driver matches. Signed-off-by: Alex Williamson <alex.williamson@redhat.com> Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Reviewed-by: Alexander Graf <agraf@suse.de> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-05-20 22:53:21 +08:00
if (!found_id)
found_id = pci_match_id(drv->id_table, dev);
/* driver_override will always match, send a dummy id */
if (!found_id && dev->driver_override)
found_id = &pci_device_id_any;
return found_id;
}
struct drv_dev_and_id {
struct pci_driver *drv;
struct pci_dev *dev;
const struct pci_device_id *id;
};
static long local_pci_probe(void *_ddi)
{
struct drv_dev_and_id *ddi = _ddi;
struct pci_dev *pci_dev = ddi->dev;
struct pci_driver *pci_drv = ddi->drv;
struct device *dev = &pci_dev->dev;
int rc;
/*
* Unbound PCI devices are always put in D0, regardless of
* runtime PM status. During probe, the device is set to
* active and the usage count is incremented. If the driver
* supports runtime PM, it should call pm_runtime_put_noidle(),
* or any other runtime PM helper function decrementing the usage
* count, in its probe routine and pm_runtime_get_noresume() in
* its remove routine.
*/
pm_runtime_get_sync(dev);
pci_dev->driver = pci_drv;
rc = pci_drv->probe(pci_dev, ddi->id);
if (!rc)
return rc;
if (rc < 0) {
pci_dev->driver = NULL;
pm_runtime_put_sync(dev);
return rc;
}
/*
* Probe function should return < 0 for failure, 0 for success
* Treat values > 0 as success, but warn.
*/
pci_warn(pci_dev, "Driver probe function unexpectedly returned %d\n",
rc);
return 0;
}
PCI: Replace the racy recursion prevention pci_call_probe() can called recursively when a physcial function is probed and the probing creates virtual functions, which are populated via pci_bus_add_device() which in turn can end up calling pci_call_probe() again. The code has an interesting way to prevent recursing into the workqueue code. That's accomplished by a check whether the current task runs already on the numa node which is associated with the device. While that works to prevent the recursion into the workqueue code, it's racy versus normal execution as there is no guarantee that the node does not vanish after the check. There is another issue with this code. It dereferences cpumask_of_node() unconditionally without checking whether the node is available. Make the detection reliable by: - Mark a probed device as 'is_probed' in pci_call_probe() - Check in pci_call_probe for a virtual function. If it's a virtual function and the associated physical function device is marked 'is_probed' then this is a recursive call, so the call can be invoked in the calling context. - Add a check whether the node is online before dereferencing it. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ingo Molnar <mingo@kernel.org> Acked-by: Bjorn Helgaas <bhelgaas@google.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: linux-pci@vger.kernel.org Cc: Sebastian Siewior <bigeasy@linutronix.de> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/20170524081548.771457199@linutronix.de
2017-05-24 16:15:32 +08:00
static bool pci_physfn_is_probed(struct pci_dev *dev)
{
#ifdef CONFIG_PCI_IOV
return dev->is_virtfn && dev->physfn->is_probed;
#else
return false;
#endif
}
static int pci_call_probe(struct pci_driver *drv, struct pci_dev *dev,
const struct pci_device_id *id)
{
PCI: Replace the racy recursion prevention pci_call_probe() can called recursively when a physcial function is probed and the probing creates virtual functions, which are populated via pci_bus_add_device() which in turn can end up calling pci_call_probe() again. The code has an interesting way to prevent recursing into the workqueue code. That's accomplished by a check whether the current task runs already on the numa node which is associated with the device. While that works to prevent the recursion into the workqueue code, it's racy versus normal execution as there is no guarantee that the node does not vanish after the check. There is another issue with this code. It dereferences cpumask_of_node() unconditionally without checking whether the node is available. Make the detection reliable by: - Mark a probed device as 'is_probed' in pci_call_probe() - Check in pci_call_probe for a virtual function. If it's a virtual function and the associated physical function device is marked 'is_probed' then this is a recursive call, so the call can be invoked in the calling context. - Add a check whether the node is online before dereferencing it. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ingo Molnar <mingo@kernel.org> Acked-by: Bjorn Helgaas <bhelgaas@google.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: linux-pci@vger.kernel.org Cc: Sebastian Siewior <bigeasy@linutronix.de> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/20170524081548.771457199@linutronix.de
2017-05-24 16:15:32 +08:00
int error, node, cpu;
int hk_flags = HK_FLAG_DOMAIN | HK_FLAG_WQ;
struct drv_dev_and_id ddi = { drv, dev, id };
/*
* 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);
PCI: Replace the racy recursion prevention pci_call_probe() can called recursively when a physcial function is probed and the probing creates virtual functions, which are populated via pci_bus_add_device() which in turn can end up calling pci_call_probe() again. The code has an interesting way to prevent recursing into the workqueue code. That's accomplished by a check whether the current task runs already on the numa node which is associated with the device. While that works to prevent the recursion into the workqueue code, it's racy versus normal execution as there is no guarantee that the node does not vanish after the check. There is another issue with this code. It dereferences cpumask_of_node() unconditionally without checking whether the node is available. Make the detection reliable by: - Mark a probed device as 'is_probed' in pci_call_probe() - Check in pci_call_probe for a virtual function. If it's a virtual function and the associated physical function device is marked 'is_probed' then this is a recursive call, so the call can be invoked in the calling context. - Add a check whether the node is online before dereferencing it. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ingo Molnar <mingo@kernel.org> Acked-by: Bjorn Helgaas <bhelgaas@google.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: linux-pci@vger.kernel.org Cc: Sebastian Siewior <bigeasy@linutronix.de> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/20170524081548.771457199@linutronix.de
2017-05-24 16:15:32 +08:00
dev->is_probed = 1;
cpu_hotplug_disable();
/*
PCI: Replace the racy recursion prevention pci_call_probe() can called recursively when a physcial function is probed and the probing creates virtual functions, which are populated via pci_bus_add_device() which in turn can end up calling pci_call_probe() again. The code has an interesting way to prevent recursing into the workqueue code. That's accomplished by a check whether the current task runs already on the numa node which is associated with the device. While that works to prevent the recursion into the workqueue code, it's racy versus normal execution as there is no guarantee that the node does not vanish after the check. There is another issue with this code. It dereferences cpumask_of_node() unconditionally without checking whether the node is available. Make the detection reliable by: - Mark a probed device as 'is_probed' in pci_call_probe() - Check in pci_call_probe for a virtual function. If it's a virtual function and the associated physical function device is marked 'is_probed' then this is a recursive call, so the call can be invoked in the calling context. - Add a check whether the node is online before dereferencing it. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ingo Molnar <mingo@kernel.org> Acked-by: Bjorn Helgaas <bhelgaas@google.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: linux-pci@vger.kernel.org Cc: Sebastian Siewior <bigeasy@linutronix.de> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/20170524081548.771457199@linutronix.de
2017-05-24 16:15:32 +08:00
* Prevent nesting work_on_cpu() for the case where a Virtual Function
* device is probed from work_on_cpu() of the Physical device.
*/
PCI: Replace the racy recursion prevention pci_call_probe() can called recursively when a physcial function is probed and the probing creates virtual functions, which are populated via pci_bus_add_device() which in turn can end up calling pci_call_probe() again. The code has an interesting way to prevent recursing into the workqueue code. That's accomplished by a check whether the current task runs already on the numa node which is associated with the device. While that works to prevent the recursion into the workqueue code, it's racy versus normal execution as there is no guarantee that the node does not vanish after the check. There is another issue with this code. It dereferences cpumask_of_node() unconditionally without checking whether the node is available. Make the detection reliable by: - Mark a probed device as 'is_probed' in pci_call_probe() - Check in pci_call_probe for a virtual function. If it's a virtual function and the associated physical function device is marked 'is_probed' then this is a recursive call, so the call can be invoked in the calling context. - Add a check whether the node is online before dereferencing it. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ingo Molnar <mingo@kernel.org> Acked-by: Bjorn Helgaas <bhelgaas@google.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: linux-pci@vger.kernel.org Cc: Sebastian Siewior <bigeasy@linutronix.de> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/20170524081548.771457199@linutronix.de
2017-05-24 16:15:32 +08:00
if (node < 0 || node >= MAX_NUMNODES || !node_online(node) ||
pci_physfn_is_probed(dev))
cpu = nr_cpu_ids;
else
cpu = cpumask_any_and(cpumask_of_node(node),
housekeeping_cpumask(hk_flags));
PCI: Replace the racy recursion prevention pci_call_probe() can called recursively when a physcial function is probed and the probing creates virtual functions, which are populated via pci_bus_add_device() which in turn can end up calling pci_call_probe() again. The code has an interesting way to prevent recursing into the workqueue code. That's accomplished by a check whether the current task runs already on the numa node which is associated with the device. While that works to prevent the recursion into the workqueue code, it's racy versus normal execution as there is no guarantee that the node does not vanish after the check. There is another issue with this code. It dereferences cpumask_of_node() unconditionally without checking whether the node is available. Make the detection reliable by: - Mark a probed device as 'is_probed' in pci_call_probe() - Check in pci_call_probe for a virtual function. If it's a virtual function and the associated physical function device is marked 'is_probed' then this is a recursive call, so the call can be invoked in the calling context. - Add a check whether the node is online before dereferencing it. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ingo Molnar <mingo@kernel.org> Acked-by: Bjorn Helgaas <bhelgaas@google.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: linux-pci@vger.kernel.org Cc: Sebastian Siewior <bigeasy@linutronix.de> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/20170524081548.771457199@linutronix.de
2017-05-24 16:15:32 +08:00
if (cpu < nr_cpu_ids)
error = work_on_cpu(cpu, local_pci_probe, &ddi);
else
error = local_pci_probe(&ddi);
PCI: Replace the racy recursion prevention pci_call_probe() can called recursively when a physcial function is probed and the probing creates virtual functions, which are populated via pci_bus_add_device() which in turn can end up calling pci_call_probe() again. The code has an interesting way to prevent recursing into the workqueue code. That's accomplished by a check whether the current task runs already on the numa node which is associated with the device. While that works to prevent the recursion into the workqueue code, it's racy versus normal execution as there is no guarantee that the node does not vanish after the check. There is another issue with this code. It dereferences cpumask_of_node() unconditionally without checking whether the node is available. Make the detection reliable by: - Mark a probed device as 'is_probed' in pci_call_probe() - Check in pci_call_probe for a virtual function. If it's a virtual function and the associated physical function device is marked 'is_probed' then this is a recursive call, so the call can be invoked in the calling context. - Add a check whether the node is online before dereferencing it. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Ingo Molnar <mingo@kernel.org> Acked-by: Bjorn Helgaas <bhelgaas@google.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: linux-pci@vger.kernel.org Cc: Sebastian Siewior <bigeasy@linutronix.de> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/20170524081548.771457199@linutronix.de
2017-05-24 16:15:32 +08:00
dev->is_probed = 0;
cpu_hotplug_enable();
return error;
}
/**
* __pci_device_probe - check if a driver wants to claim a specific PCI device
* @drv: driver to call to check if it wants the PCI device
* @pci_dev: PCI device being probed
*
* returns 0 on success, else error.
* side-effect: pci_dev->driver is set to drv when drv claims pci_dev.
*/
static int __pci_device_probe(struct pci_driver *drv, struct pci_dev *pci_dev)
{
const struct pci_device_id *id;
int error = 0;
if (!pci_dev->driver && drv->probe) {
error = -ENODEV;
id = pci_match_device(drv, pci_dev);
if (id)
error = pci_call_probe(drv, pci_dev, id);
}
return error;
}
int __weak pcibios_alloc_irq(struct pci_dev *dev)
{
return 0;
}
void __weak pcibios_free_irq(struct pci_dev *dev)
{
}
#ifdef CONFIG_PCI_IOV
static inline bool pci_device_can_probe(struct pci_dev *pdev)
{
PCI: Always allow probing with driver_override Commit 0e7df22401a3 ("PCI: Add sysfs sriov_drivers_autoprobe to control VF driver binding") introduced the sriov_drivers_autoprobe attribute which allows users to prevent the kernel from automatically probing a driver for new VFs as they are created. This allows VFs to be spawned without automatically binding the new device to a host driver, such as in cases where the user intends to use the device only with a meta driver like vfio-pci. However, the current implementation prevents any use of drivers_probe with the VF while sriov_drivers_autoprobe=0. This blocks the now current general practice of setting driver_override followed by using drivers_probe to bind a device to a specified driver. The kernel never automatically sets a driver_override therefore it seems we can assume a driver_override reflects the intent of the user. Also, probing a device using a driver_override match seems outside the scope of the 'auto' part of sriov_drivers_autoprobe. Therefore, let's allow driver_override matches regardless of sriov_drivers_autoprobe, which we can do by simply testing if a driver_override is set for a device as a 'can probe' condition. Fixes: 0e7df22401a3 ("PCI: Add sysfs sriov_drivers_autoprobe to control VF driver binding") Link: https://lore.kernel.org/lkml/155742996741.21878.569845487290798703.stgit@gimli.home Link: https://lore.kernel.org/linux-pci/155672991496.20698.4279330795743262888.stgit@gimli.home/T/#u Signed-off-by: Alex Williamson <alex.williamson@redhat.com> Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
2019-05-10 03:27:22 +08:00
return (!pdev->is_virtfn || pdev->physfn->sriov->drivers_autoprobe ||
pdev->driver_override);
}
#else
static inline bool pci_device_can_probe(struct pci_dev *pdev)
{
return true;
}
#endif
static int pci_device_probe(struct device *dev)
{
int error;
struct pci_dev *pci_dev = to_pci_dev(dev);
struct pci_driver *drv = to_pci_driver(dev->driver);
if (!pci_device_can_probe(pci_dev))
return -ENODEV;
pci_assign_irq(pci_dev);
error = pcibios_alloc_irq(pci_dev);
if (error < 0)
return error;
pci_dev_get(pci_dev);
error = __pci_device_probe(drv, pci_dev);
if (error) {
pcibios_free_irq(pci_dev);
pci_dev_put(pci_dev);
}
return error;
}
static int pci_device_remove(struct device *dev)
{
struct pci_dev *pci_dev = to_pci_dev(dev);
struct pci_driver *drv = pci_dev->driver;
if (drv) {
if (drv->remove) {
pm_runtime_get_sync(dev);
drv->remove(pci_dev);
pm_runtime_put_noidle(dev);
}
pcibios_free_irq(pci_dev);
pci_dev->driver = NULL;
pci_iov_remove(pci_dev);
}
/* Undo the runtime PM settings in local_pci_probe() */
pm_runtime_put_sync(dev);
/*
* If the device is still on, set the power state as "unknown",
* since it might change by the next time we load the driver.
*/
if (pci_dev->current_state == PCI_D0)
pci_dev->current_state = PCI_UNKNOWN;
/*
* We would love to complain here if pci_dev->is_enabled is set, that
* the driver should have called pci_disable_device(), but the
* unfortunate fact is there are too many odd BIOS and bridge setups
* that don't like drivers doing that all of the time.
* Oh well, we can dream of sane hardware when we sleep, no matter how
* horrible the crap we have to deal with is when we are awake...
*/
pci_dev_put(pci_dev);
return 0;
}
static void pci_device_shutdown(struct device *dev)
{
struct pci_dev *pci_dev = to_pci_dev(dev);
struct pci_driver *drv = pci_dev->driver;
pm_runtime_resume(dev);
if (drv && drv->shutdown)
drv->shutdown(pci_dev);
/*
* 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 (kexec_in_progress && (pci_dev->current_state <= PCI_D3hot))
pci_clear_master(pci_dev);
}
#ifdef CONFIG_PM
/* Auxiliary functions used for system resume and run-time resume. */
/**
* pci_restore_standard_config - restore standard config registers of PCI device
* @pci_dev: PCI device to handle
*/
static int pci_restore_standard_config(struct pci_dev *pci_dev)
{
pci_update_current_state(pci_dev, PCI_UNKNOWN);
if (pci_dev->current_state != PCI_D0) {
int error = pci_set_power_state(pci_dev, PCI_D0);
if (error)
return error;
}
pci_restore_state(pci_dev);
pci_pme_restore(pci_dev);
return 0;
}
static void pci_pm_default_resume(struct pci_dev *pci_dev)
{
pci_fixup_device(pci_fixup_resume, pci_dev);
pci_enable_wake(pci_dev, PCI_D0, false);
}
#endif
#ifdef CONFIG_PM_SLEEP
static void pci_pm_default_resume_early(struct pci_dev *pci_dev)
{
pci_power_up(pci_dev);
pci_update_current_state(pci_dev, PCI_D0);
pci_restore_state(pci_dev);
pci_pme_restore(pci_dev);
}
/*
* Default "suspend" method for devices that have no driver provided suspend,
* or not even a driver at all (second part).
*/
static void pci_pm_set_unknown_state(struct pci_dev *pci_dev)
{
/*
* mark its power state as "unknown", since we don't know if
* e.g. the BIOS will change its device state when we suspend.
*/
if (pci_dev->current_state == PCI_D0)
pci_dev->current_state = PCI_UNKNOWN;
}
/*
* Default "resume" method for devices that have no driver provided resume,
* or not even a driver at all (second part).
*/
static int pci_pm_reenable_device(struct pci_dev *pci_dev)
{
int retval;
/* if the device was enabled before suspend, reenable */
retval = pci_reenable_device(pci_dev);
/*
* if the device was busmaster before the suspend, make it busmaster
* again
*/
if (pci_dev->is_busmaster)
pci_set_master(pci_dev);
return retval;
}
static int pci_legacy_suspend(struct device *dev, pm_message_t state)
{
struct pci_dev *pci_dev = to_pci_dev(dev);
struct pci_driver *drv = pci_dev->driver;
if (drv && drv->suspend) {
pci_power_t prev = pci_dev->current_state;
int error;
error = drv->suspend(pci_dev, state);
suspend_report_result(drv->suspend, error);
if (error)
return error;
if (!pci_dev->state_saved && pci_dev->current_state != PCI_D0
&& pci_dev->current_state != PCI_UNKNOWN) {
pci_WARN_ONCE(pci_dev, pci_dev->current_state != prev,
"PCI PM: Device state not saved by %pS\n",
drv->suspend);
}
}
pci_fixup_device(pci_fixup_suspend, pci_dev);
return 0;
}
static int pci_legacy_suspend_late(struct device *dev, pm_message_t state)
{
struct pci_dev *pci_dev = to_pci_dev(dev);
if (!pci_dev->state_saved)
pci_save_state(pci_dev);
pci_pm_set_unknown_state(pci_dev);
pci_fixup_device(pci_fixup_suspend_late, pci_dev);
return 0;
}
static int pci_legacy_resume(struct device *dev)
{
struct pci_dev *pci_dev = to_pci_dev(dev);
struct pci_driver *drv = pci_dev->driver;
pci_fixup_device(pci_fixup_resume, pci_dev);
return drv && drv->resume ?
drv->resume(pci_dev) : pci_pm_reenable_device(pci_dev);
}
/* Auxiliary functions used by the new power management framework */
PCI PM: make the PM core more careful with drivers using the new PM framework Currently, the PM core always attempts to manage devices with drivers that use the new PM framework. In particular, it attempts to disable the devices (which is unnecessary), to save their state (which may be undesirable if the driver has done that already) and to put them into low power states (again, this may be undesirable if the driver has already put the device into a low power state). That need not be the right thing to do, so make the core be more careful in this respect. Generally, there are the following categories of devices to consider: * bridge devices without drivers * non-bridge devices without drivers * bridge devices with drivers * non-bridge devices with drivers and each of them should be handled differently. For bridge devices without drivers the PCI PM core will save their state on suspend and restore it (early) during resume, after putting them into D0 if necessary. It will not attempt to do anything else to these devices. For non-bridge devices without drivers the PCI PM core will disable them and save their state on suspend. During resume, it will put them into D0, if necessary, restore their state (early) and reenable them. For bridge devices with drivers the PCI PM core will only save their state on suspend if the driver hasn't done that already. Still, the core will restore their state (early) during resume, after putting them into D0, if necessary. For non-bridge devices with drivers the PCI PM core will only save their state on suspend if the driver hasn't done that already. Also, if the state of the device hasn't been saved by the driver, the core will attempt to put the device into a low power state. During resume the core will restore the state of the device (early), after putting it into D0, if necessary. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2009-02-04 09:09:07 +08:00
static void pci_pm_default_suspend(struct pci_dev *pci_dev)
{
PCI PM: make the PM core more careful with drivers using the new PM framework Currently, the PM core always attempts to manage devices with drivers that use the new PM framework. In particular, it attempts to disable the devices (which is unnecessary), to save their state (which may be undesirable if the driver has done that already) and to put them into low power states (again, this may be undesirable if the driver has already put the device into a low power state). That need not be the right thing to do, so make the core be more careful in this respect. Generally, there are the following categories of devices to consider: * bridge devices without drivers * non-bridge devices without drivers * bridge devices with drivers * non-bridge devices with drivers and each of them should be handled differently. For bridge devices without drivers the PCI PM core will save their state on suspend and restore it (early) during resume, after putting them into D0 if necessary. It will not attempt to do anything else to these devices. For non-bridge devices without drivers the PCI PM core will disable them and save their state on suspend. During resume, it will put them into D0, if necessary, restore their state (early) and reenable them. For bridge devices with drivers the PCI PM core will only save their state on suspend if the driver hasn't done that already. Still, the core will restore their state (early) during resume, after putting them into D0, if necessary. For non-bridge devices with drivers the PCI PM core will only save their state on suspend if the driver hasn't done that already. Also, if the state of the device hasn't been saved by the driver, the core will attempt to put the device into a low power state. During resume the core will restore the state of the device (early), after putting it into D0, if necessary. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2009-02-04 09:09:07 +08:00
/* Disable non-bridge devices without PM support */
if (!pci_has_subordinate(pci_dev))
pci_disable_enabled_device(pci_dev);
}
static bool pci_has_legacy_pm_support(struct pci_dev *pci_dev)
{
struct pci_driver *drv = pci_dev->driver;
bool ret = drv && (drv->suspend || drv->resume);
/*
* Legacy PM support is used by default, so warn if the new framework is
* supported as well. Drivers are supposed to support either the
* former, or the latter, but not both at the same time.
*/
pci_WARN(pci_dev, ret && drv->driver.pm, "device %04x:%04x\n",
pci_dev->vendor, pci_dev->device);
return ret;
}
/* New power management framework */
static int pci_pm_prepare(struct device *dev)
{
struct pci_dev *pci_dev = to_pci_dev(dev);
const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
if (pm && pm->prepare) {
int error = pm->prepare(dev);
PM / core: Add NEVER_SKIP and SMART_PREPARE driver flags The motivation for this change is to provide a way to work around a problem with the direct-complete mechanism used for avoiding system suspend/resume handling for devices in runtime suspend. The problem is that some middle layer code (the PCI bus type and the ACPI PM domain in particular) returns positive values from its system suspend ->prepare callbacks regardless of whether the driver's ->prepare returns a positive value or 0, which effectively prevents drivers from being able to control the direct-complete feature. Some drivers need that control, however, and the PCI bus type has grown its own flag to deal with this issue, but since it is not limited to PCI, it is better to address it by adding driver flags at the core level. To that end, add a driver_flags field to struct dev_pm_info for flags that can be set by device drivers at the probe time to inform the PM core and/or bus types, PM domains and so on on the capabilities and/or preferences of device drivers. Also add two static inline helpers for setting that field and testing it against a given set of flags and make the driver core clear it automatically on driver remove and probe failures. Define and document two PM driver flags related to the direct- complete feature: NEVER_SKIP and SMART_PREPARE that can be used, respectively, to indicate to the PM core that the direct-complete mechanism should never be used for the device and to inform the middle layer code (bus types, PM domains etc) that it can only request the PM core to use the direct-complete mechanism for the device (by returning a positive value from its ->prepare callback) if it also has been requested by the driver. While at it, make the core check pm_runtime_suspended() when setting power.direct_complete so that it doesn't need to be checked by ->prepare callbacks. Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Acked-by: Bjorn Helgaas <bhelgaas@google.com> Reviewed-by: Ulf Hansson <ulf.hansson@linaro.org>
2017-10-25 20:12:29 +08:00
if (error < 0)
return error;
PM / core: Add NEVER_SKIP and SMART_PREPARE driver flags The motivation for this change is to provide a way to work around a problem with the direct-complete mechanism used for avoiding system suspend/resume handling for devices in runtime suspend. The problem is that some middle layer code (the PCI bus type and the ACPI PM domain in particular) returns positive values from its system suspend ->prepare callbacks regardless of whether the driver's ->prepare returns a positive value or 0, which effectively prevents drivers from being able to control the direct-complete feature. Some drivers need that control, however, and the PCI bus type has grown its own flag to deal with this issue, but since it is not limited to PCI, it is better to address it by adding driver flags at the core level. To that end, add a driver_flags field to struct dev_pm_info for flags that can be set by device drivers at the probe time to inform the PM core and/or bus types, PM domains and so on on the capabilities and/or preferences of device drivers. Also add two static inline helpers for setting that field and testing it against a given set of flags and make the driver core clear it automatically on driver remove and probe failures. Define and document two PM driver flags related to the direct- complete feature: NEVER_SKIP and SMART_PREPARE that can be used, respectively, to indicate to the PM core that the direct-complete mechanism should never be used for the device and to inform the middle layer code (bus types, PM domains etc) that it can only request the PM core to use the direct-complete mechanism for the device (by returning a positive value from its ->prepare callback) if it also has been requested by the driver. While at it, make the core check pm_runtime_suspended() when setting power.direct_complete so that it doesn't need to be checked by ->prepare callbacks. Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Acked-by: Bjorn Helgaas <bhelgaas@google.com> Reviewed-by: Ulf Hansson <ulf.hansson@linaro.org>
2017-10-25 20:12:29 +08:00
if (!error && dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_PREPARE))
return 0;
}
if (pci_dev_need_resume(pci_dev))
return 0;
/*
* The PME setting needs to be adjusted here in case the direct-complete
* optimization is used with respect to this device.
*/
pci_dev_adjust_pme(pci_dev);
return 1;
}
static void pci_pm_complete(struct device *dev)
{
struct pci_dev *pci_dev = to_pci_dev(dev);
pci_dev_complete_resume(pci_dev);
pm_generic_complete(dev);
/* Resume device if platform firmware has put it in reset-power-on */
if (pm_runtime_suspended(dev) && pm_resume_via_firmware()) {
pci_power_t pre_sleep_state = pci_dev->current_state;
pci_refresh_power_state(pci_dev);
/*
* On platforms with ACPI this check may also trigger for
* devices sharing power resources if one of those power
* resources has been activated as a result of a change of the
* power state of another device sharing it. However, in that
* case it is also better to resume the device, in general.
*/
if (pci_dev->current_state < pre_sleep_state)
pm_request_resume(dev);
}
}
#else /* !CONFIG_PM_SLEEP */
#define pci_pm_prepare NULL
#define pci_pm_complete NULL
#endif /* !CONFIG_PM_SLEEP */
#ifdef CONFIG_SUSPEND
static void pcie_pme_root_status_cleanup(struct pci_dev *pci_dev)
{
/*
* Some BIOSes forget to clear Root PME Status bits after system
* wakeup, which breaks ACPI-based runtime wakeup on PCI Express.
* Clear those bits now just in case (shouldn't hurt).
*/
if (pci_is_pcie(pci_dev) &&
(pci_pcie_type(pci_dev) == PCI_EXP_TYPE_ROOT_PORT ||
pci_pcie_type(pci_dev) == PCI_EXP_TYPE_RC_EC))
pcie_clear_root_pme_status(pci_dev);
}
static int pci_pm_suspend(struct device *dev)
{
struct pci_dev *pci_dev = to_pci_dev(dev);
const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
pci_dev->skip_bus_pm = false;
if (pci_has_legacy_pm_support(pci_dev))
return pci_legacy_suspend(dev, PMSG_SUSPEND);
PCI PM: make the PM core more careful with drivers using the new PM framework Currently, the PM core always attempts to manage devices with drivers that use the new PM framework. In particular, it attempts to disable the devices (which is unnecessary), to save their state (which may be undesirable if the driver has done that already) and to put them into low power states (again, this may be undesirable if the driver has already put the device into a low power state). That need not be the right thing to do, so make the core be more careful in this respect. Generally, there are the following categories of devices to consider: * bridge devices without drivers * non-bridge devices without drivers * bridge devices with drivers * non-bridge devices with drivers and each of them should be handled differently. For bridge devices without drivers the PCI PM core will save their state on suspend and restore it (early) during resume, after putting them into D0 if necessary. It will not attempt to do anything else to these devices. For non-bridge devices without drivers the PCI PM core will disable them and save their state on suspend. During resume, it will put them into D0, if necessary, restore their state (early) and reenable them. For bridge devices with drivers the PCI PM core will only save their state on suspend if the driver hasn't done that already. Still, the core will restore their state (early) during resume, after putting them into D0, if necessary. For non-bridge devices with drivers the PCI PM core will only save their state on suspend if the driver hasn't done that already. Also, if the state of the device hasn't been saved by the driver, the core will attempt to put the device into a low power state. During resume the core will restore the state of the device (early), after putting it into D0, if necessary. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2009-02-04 09:09:07 +08:00
if (!pm) {
pci_pm_default_suspend(pci_dev);
PCI / PM: Take SMART_SUSPEND driver flag into account Make the PCI bus type take DPM_FLAG_SMART_SUSPEND into account in its system-wide PM callbacks and make sure that all code that should not run in parallel with pci_pm_runtime_resume() is executed in the "late" phases of system suspend, freeze and poweroff transitions. [Note that the pm_runtime_suspended() check in pci_dev_keep_suspended() is an optimization, because if is not passed, all of the subsequent checks may be skipped and some of them are much more overhead in general.] Also use the observation that if the device is in runtime suspend at the beginning of the "late" phase of a system-wide suspend-like transition, its state cannot change going forward (runtime PM is disabled for it at that time) until the transition is over and the subsequent system-wide PM callbacks should be skipped for it (as they generally assume the device to not be suspended), so add checks for that in pci_pm_suspend_late/noirq(), pci_pm_freeze_late/noirq() and pci_pm_poweroff_late/noirq(). Moreover, if pci_pm_resume_noirq() or pci_pm_restore_noirq() is called during the subsequent system-wide resume transition and if the device was left in runtime suspend previously, its runtime PM status needs to be changed to "active" as it is going to be put into the full-power state, so add checks for that too to these functions. In turn, if pci_pm_thaw_noirq() runs after the device has been left in runtime suspend, the subsequent "thaw" callbacks need to be skipped for it (as they may not work correctly with a suspended device), so set the power.direct_complete flag for the device then to make the PM core skip those callbacks. In addition to the above add a core helper for checking if DPM_FLAG_SMART_SUSPEND is set and the device runtime PM status is "suspended" at the same time, which is done quite often in the new code (and will be done elsewhere going forward too). Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Acked-by: Bjorn Helgaas <bhelgaas@google.com>
2017-10-26 18:12:22 +08:00
return 0;
PCI PM: make the PM core more careful with drivers using the new PM framework Currently, the PM core always attempts to manage devices with drivers that use the new PM framework. In particular, it attempts to disable the devices (which is unnecessary), to save their state (which may be undesirable if the driver has done that already) and to put them into low power states (again, this may be undesirable if the driver has already put the device into a low power state). That need not be the right thing to do, so make the core be more careful in this respect. Generally, there are the following categories of devices to consider: * bridge devices without drivers * non-bridge devices without drivers * bridge devices with drivers * non-bridge devices with drivers and each of them should be handled differently. For bridge devices without drivers the PCI PM core will save their state on suspend and restore it (early) during resume, after putting them into D0 if necessary. It will not attempt to do anything else to these devices. For non-bridge devices without drivers the PCI PM core will disable them and save their state on suspend. During resume, it will put them into D0, if necessary, restore their state (early) and reenable them. For bridge devices with drivers the PCI PM core will only save their state on suspend if the driver hasn't done that already. Still, the core will restore their state (early) during resume, after putting them into D0, if necessary. For non-bridge devices with drivers the PCI PM core will only save their state on suspend if the driver hasn't done that already. Also, if the state of the device hasn't been saved by the driver, the core will attempt to put the device into a low power state. During resume the core will restore the state of the device (early), after putting it into D0, if necessary. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2009-02-04 09:09:07 +08:00
}
/*
PCI / PM: Take SMART_SUSPEND driver flag into account Make the PCI bus type take DPM_FLAG_SMART_SUSPEND into account in its system-wide PM callbacks and make sure that all code that should not run in parallel with pci_pm_runtime_resume() is executed in the "late" phases of system suspend, freeze and poweroff transitions. [Note that the pm_runtime_suspended() check in pci_dev_keep_suspended() is an optimization, because if is not passed, all of the subsequent checks may be skipped and some of them are much more overhead in general.] Also use the observation that if the device is in runtime suspend at the beginning of the "late" phase of a system-wide suspend-like transition, its state cannot change going forward (runtime PM is disabled for it at that time) until the transition is over and the subsequent system-wide PM callbacks should be skipped for it (as they generally assume the device to not be suspended), so add checks for that in pci_pm_suspend_late/noirq(), pci_pm_freeze_late/noirq() and pci_pm_poweroff_late/noirq(). Moreover, if pci_pm_resume_noirq() or pci_pm_restore_noirq() is called during the subsequent system-wide resume transition and if the device was left in runtime suspend previously, its runtime PM status needs to be changed to "active" as it is going to be put into the full-power state, so add checks for that too to these functions. In turn, if pci_pm_thaw_noirq() runs after the device has been left in runtime suspend, the subsequent "thaw" callbacks need to be skipped for it (as they may not work correctly with a suspended device), so set the power.direct_complete flag for the device then to make the PM core skip those callbacks. In addition to the above add a core helper for checking if DPM_FLAG_SMART_SUSPEND is set and the device runtime PM status is "suspended" at the same time, which is done quite often in the new code (and will be done elsewhere going forward too). Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Acked-by: Bjorn Helgaas <bhelgaas@google.com>
2017-10-26 18:12:22 +08:00
* PCI devices suspended at run time may need to be resumed at this
* point, because in general it may be necessary to reconfigure them for
* system suspend. Namely, if the device is expected to wake up the
* system from the sleep state, it may have to be reconfigured for this
* purpose, or if the device is not expected to wake up the system from
* the sleep state, it should be prevented from signaling wakeup events
* going forward.
*
* Also if the driver of the device does not indicate that its system
* suspend callbacks can cope with runtime-suspended devices, it is
* better to resume the device from runtime suspend here.
*/
PCI / PM: Take SMART_SUSPEND driver flag into account Make the PCI bus type take DPM_FLAG_SMART_SUSPEND into account in its system-wide PM callbacks and make sure that all code that should not run in parallel with pci_pm_runtime_resume() is executed in the "late" phases of system suspend, freeze and poweroff transitions. [Note that the pm_runtime_suspended() check in pci_dev_keep_suspended() is an optimization, because if is not passed, all of the subsequent checks may be skipped and some of them are much more overhead in general.] Also use the observation that if the device is in runtime suspend at the beginning of the "late" phase of a system-wide suspend-like transition, its state cannot change going forward (runtime PM is disabled for it at that time) until the transition is over and the subsequent system-wide PM callbacks should be skipped for it (as they generally assume the device to not be suspended), so add checks for that in pci_pm_suspend_late/noirq(), pci_pm_freeze_late/noirq() and pci_pm_poweroff_late/noirq(). Moreover, if pci_pm_resume_noirq() or pci_pm_restore_noirq() is called during the subsequent system-wide resume transition and if the device was left in runtime suspend previously, its runtime PM status needs to be changed to "active" as it is going to be put into the full-power state, so add checks for that too to these functions. In turn, if pci_pm_thaw_noirq() runs after the device has been left in runtime suspend, the subsequent "thaw" callbacks need to be skipped for it (as they may not work correctly with a suspended device), so set the power.direct_complete flag for the device then to make the PM core skip those callbacks. In addition to the above add a core helper for checking if DPM_FLAG_SMART_SUSPEND is set and the device runtime PM status is "suspended" at the same time, which is done quite often in the new code (and will be done elsewhere going forward too). Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Acked-by: Bjorn Helgaas <bhelgaas@google.com>
2017-10-26 18:12:22 +08:00
if (!dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND) ||
pci_dev_need_resume(pci_dev)) {
PCI / PM: Take SMART_SUSPEND driver flag into account Make the PCI bus type take DPM_FLAG_SMART_SUSPEND into account in its system-wide PM callbacks and make sure that all code that should not run in parallel with pci_pm_runtime_resume() is executed in the "late" phases of system suspend, freeze and poweroff transitions. [Note that the pm_runtime_suspended() check in pci_dev_keep_suspended() is an optimization, because if is not passed, all of the subsequent checks may be skipped and some of them are much more overhead in general.] Also use the observation that if the device is in runtime suspend at the beginning of the "late" phase of a system-wide suspend-like transition, its state cannot change going forward (runtime PM is disabled for it at that time) until the transition is over and the subsequent system-wide PM callbacks should be skipped for it (as they generally assume the device to not be suspended), so add checks for that in pci_pm_suspend_late/noirq(), pci_pm_freeze_late/noirq() and pci_pm_poweroff_late/noirq(). Moreover, if pci_pm_resume_noirq() or pci_pm_restore_noirq() is called during the subsequent system-wide resume transition and if the device was left in runtime suspend previously, its runtime PM status needs to be changed to "active" as it is going to be put into the full-power state, so add checks for that too to these functions. In turn, if pci_pm_thaw_noirq() runs after the device has been left in runtime suspend, the subsequent "thaw" callbacks need to be skipped for it (as they may not work correctly with a suspended device), so set the power.direct_complete flag for the device then to make the PM core skip those callbacks. In addition to the above add a core helper for checking if DPM_FLAG_SMART_SUSPEND is set and the device runtime PM status is "suspended" at the same time, which is done quite often in the new code (and will be done elsewhere going forward too). Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Acked-by: Bjorn Helgaas <bhelgaas@google.com>
2017-10-26 18:12:22 +08:00
pm_runtime_resume(dev);
pci_dev->state_saved = false;
} else {
pci_dev_adjust_pme(pci_dev);
}
PCI PM: make the PM core more careful with drivers using the new PM framework Currently, the PM core always attempts to manage devices with drivers that use the new PM framework. In particular, it attempts to disable the devices (which is unnecessary), to save their state (which may be undesirable if the driver has done that already) and to put them into low power states (again, this may be undesirable if the driver has already put the device into a low power state). That need not be the right thing to do, so make the core be more careful in this respect. Generally, there are the following categories of devices to consider: * bridge devices without drivers * non-bridge devices without drivers * bridge devices with drivers * non-bridge devices with drivers and each of them should be handled differently. For bridge devices without drivers the PCI PM core will save their state on suspend and restore it (early) during resume, after putting them into D0 if necessary. It will not attempt to do anything else to these devices. For non-bridge devices without drivers the PCI PM core will disable them and save their state on suspend. During resume, it will put them into D0, if necessary, restore their state (early) and reenable them. For bridge devices with drivers the PCI PM core will only save their state on suspend if the driver hasn't done that already. Still, the core will restore their state (early) during resume, after putting them into D0, if necessary. For non-bridge devices with drivers the PCI PM core will only save their state on suspend if the driver hasn't done that already. Also, if the state of the device hasn't been saved by the driver, the core will attempt to put the device into a low power state. During resume the core will restore the state of the device (early), after putting it into D0, if necessary. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2009-02-04 09:09:07 +08:00
if (pm->suspend) {
pci_power_t prev = pci_dev->current_state;
int error;
error = pm->suspend(dev);
suspend_report_result(pm->suspend, error);
PCI PM: make the PM core more careful with drivers using the new PM framework Currently, the PM core always attempts to manage devices with drivers that use the new PM framework. In particular, it attempts to disable the devices (which is unnecessary), to save their state (which may be undesirable if the driver has done that already) and to put them into low power states (again, this may be undesirable if the driver has already put the device into a low power state). That need not be the right thing to do, so make the core be more careful in this respect. Generally, there are the following categories of devices to consider: * bridge devices without drivers * non-bridge devices without drivers * bridge devices with drivers * non-bridge devices with drivers and each of them should be handled differently. For bridge devices without drivers the PCI PM core will save their state on suspend and restore it (early) during resume, after putting them into D0 if necessary. It will not attempt to do anything else to these devices. For non-bridge devices without drivers the PCI PM core will disable them and save their state on suspend. During resume, it will put them into D0, if necessary, restore their state (early) and reenable them. For bridge devices with drivers the PCI PM core will only save their state on suspend if the driver hasn't done that already. Still, the core will restore their state (early) during resume, after putting them into D0, if necessary. For non-bridge devices with drivers the PCI PM core will only save their state on suspend if the driver hasn't done that already. Also, if the state of the device hasn't been saved by the driver, the core will attempt to put the device into a low power state. During resume the core will restore the state of the device (early), after putting it into D0, if necessary. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2009-02-04 09:09:07 +08:00
if (error)
return error;
if (!pci_dev->state_saved && pci_dev->current_state != PCI_D0
PCI PM: make the PM core more careful with drivers using the new PM framework Currently, the PM core always attempts to manage devices with drivers that use the new PM framework. In particular, it attempts to disable the devices (which is unnecessary), to save their state (which may be undesirable if the driver has done that already) and to put them into low power states (again, this may be undesirable if the driver has already put the device into a low power state). That need not be the right thing to do, so make the core be more careful in this respect. Generally, there are the following categories of devices to consider: * bridge devices without drivers * non-bridge devices without drivers * bridge devices with drivers * non-bridge devices with drivers and each of them should be handled differently. For bridge devices without drivers the PCI PM core will save their state on suspend and restore it (early) during resume, after putting them into D0 if necessary. It will not attempt to do anything else to these devices. For non-bridge devices without drivers the PCI PM core will disable them and save their state on suspend. During resume, it will put them into D0, if necessary, restore their state (early) and reenable them. For bridge devices with drivers the PCI PM core will only save their state on suspend if the driver hasn't done that already. Still, the core will restore their state (early) during resume, after putting them into D0, if necessary. For non-bridge devices with drivers the PCI PM core will only save their state on suspend if the driver hasn't done that already. Also, if the state of the device hasn't been saved by the driver, the core will attempt to put the device into a low power state. During resume the core will restore the state of the device (early), after putting it into D0, if necessary. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2009-02-04 09:09:07 +08:00
&& pci_dev->current_state != PCI_UNKNOWN) {
pci_WARN_ONCE(pci_dev, pci_dev->current_state != prev,
"PCI PM: State of device not saved by %pS\n",
pm->suspend);
PCI PM: make the PM core more careful with drivers using the new PM framework Currently, the PM core always attempts to manage devices with drivers that use the new PM framework. In particular, it attempts to disable the devices (which is unnecessary), to save their state (which may be undesirable if the driver has done that already) and to put them into low power states (again, this may be undesirable if the driver has already put the device into a low power state). That need not be the right thing to do, so make the core be more careful in this respect. Generally, there are the following categories of devices to consider: * bridge devices without drivers * non-bridge devices without drivers * bridge devices with drivers * non-bridge devices with drivers and each of them should be handled differently. For bridge devices without drivers the PCI PM core will save their state on suspend and restore it (early) during resume, after putting them into D0 if necessary. It will not attempt to do anything else to these devices. For non-bridge devices without drivers the PCI PM core will disable them and save their state on suspend. During resume, it will put them into D0, if necessary, restore their state (early) and reenable them. For bridge devices with drivers the PCI PM core will only save their state on suspend if the driver hasn't done that already. Still, the core will restore their state (early) during resume, after putting them into D0, if necessary. For non-bridge devices with drivers the PCI PM core will only save their state on suspend if the driver hasn't done that already. Also, if the state of the device hasn't been saved by the driver, the core will attempt to put the device into a low power state. During resume the core will restore the state of the device (early), after putting it into D0, if necessary. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2009-02-04 09:09:07 +08:00
}
}
PCI PM: make the PM core more careful with drivers using the new PM framework Currently, the PM core always attempts to manage devices with drivers that use the new PM framework. In particular, it attempts to disable the devices (which is unnecessary), to save their state (which may be undesirable if the driver has done that already) and to put them into low power states (again, this may be undesirable if the driver has already put the device into a low power state). That need not be the right thing to do, so make the core be more careful in this respect. Generally, there are the following categories of devices to consider: * bridge devices without drivers * non-bridge devices without drivers * bridge devices with drivers * non-bridge devices with drivers and each of them should be handled differently. For bridge devices without drivers the PCI PM core will save their state on suspend and restore it (early) during resume, after putting them into D0 if necessary. It will not attempt to do anything else to these devices. For non-bridge devices without drivers the PCI PM core will disable them and save their state on suspend. During resume, it will put them into D0, if necessary, restore their state (early) and reenable them. For bridge devices with drivers the PCI PM core will only save their state on suspend if the driver hasn't done that already. Still, the core will restore their state (early) during resume, after putting them into D0, if necessary. For non-bridge devices with drivers the PCI PM core will only save their state on suspend if the driver hasn't done that already. Also, if the state of the device hasn't been saved by the driver, the core will attempt to put the device into a low power state. During resume the core will restore the state of the device (early), after putting it into D0, if necessary. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2009-02-04 09:09:07 +08:00
return 0;
}
PCI / PM: Take SMART_SUSPEND driver flag into account Make the PCI bus type take DPM_FLAG_SMART_SUSPEND into account in its system-wide PM callbacks and make sure that all code that should not run in parallel with pci_pm_runtime_resume() is executed in the "late" phases of system suspend, freeze and poweroff transitions. [Note that the pm_runtime_suspended() check in pci_dev_keep_suspended() is an optimization, because if is not passed, all of the subsequent checks may be skipped and some of them are much more overhead in general.] Also use the observation that if the device is in runtime suspend at the beginning of the "late" phase of a system-wide suspend-like transition, its state cannot change going forward (runtime PM is disabled for it at that time) until the transition is over and the subsequent system-wide PM callbacks should be skipped for it (as they generally assume the device to not be suspended), so add checks for that in pci_pm_suspend_late/noirq(), pci_pm_freeze_late/noirq() and pci_pm_poweroff_late/noirq(). Moreover, if pci_pm_resume_noirq() or pci_pm_restore_noirq() is called during the subsequent system-wide resume transition and if the device was left in runtime suspend previously, its runtime PM status needs to be changed to "active" as it is going to be put into the full-power state, so add checks for that too to these functions. In turn, if pci_pm_thaw_noirq() runs after the device has been left in runtime suspend, the subsequent "thaw" callbacks need to be skipped for it (as they may not work correctly with a suspended device), so set the power.direct_complete flag for the device then to make the PM core skip those callbacks. In addition to the above add a core helper for checking if DPM_FLAG_SMART_SUSPEND is set and the device runtime PM status is "suspended" at the same time, which is done quite often in the new code (and will be done elsewhere going forward too). Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Acked-by: Bjorn Helgaas <bhelgaas@google.com>
2017-10-26 18:12:22 +08:00
static int pci_pm_suspend_late(struct device *dev)
{
if (dev_pm_skip_suspend(dev))
PCI / PM: Take SMART_SUSPEND driver flag into account Make the PCI bus type take DPM_FLAG_SMART_SUSPEND into account in its system-wide PM callbacks and make sure that all code that should not run in parallel with pci_pm_runtime_resume() is executed in the "late" phases of system suspend, freeze and poweroff transitions. [Note that the pm_runtime_suspended() check in pci_dev_keep_suspended() is an optimization, because if is not passed, all of the subsequent checks may be skipped and some of them are much more overhead in general.] Also use the observation that if the device is in runtime suspend at the beginning of the "late" phase of a system-wide suspend-like transition, its state cannot change going forward (runtime PM is disabled for it at that time) until the transition is over and the subsequent system-wide PM callbacks should be skipped for it (as they generally assume the device to not be suspended), so add checks for that in pci_pm_suspend_late/noirq(), pci_pm_freeze_late/noirq() and pci_pm_poweroff_late/noirq(). Moreover, if pci_pm_resume_noirq() or pci_pm_restore_noirq() is called during the subsequent system-wide resume transition and if the device was left in runtime suspend previously, its runtime PM status needs to be changed to "active" as it is going to be put into the full-power state, so add checks for that too to these functions. In turn, if pci_pm_thaw_noirq() runs after the device has been left in runtime suspend, the subsequent "thaw" callbacks need to be skipped for it (as they may not work correctly with a suspended device), so set the power.direct_complete flag for the device then to make the PM core skip those callbacks. In addition to the above add a core helper for checking if DPM_FLAG_SMART_SUSPEND is set and the device runtime PM status is "suspended" at the same time, which is done quite often in the new code (and will be done elsewhere going forward too). Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Acked-by: Bjorn Helgaas <bhelgaas@google.com>
2017-10-26 18:12:22 +08:00
return 0;
pci_fixup_device(pci_fixup_suspend, to_pci_dev(dev));
return pm_generic_suspend_late(dev);
}
static int pci_pm_suspend_noirq(struct device *dev)
{
struct pci_dev *pci_dev = to_pci_dev(dev);
const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
if (dev_pm_skip_suspend(dev))
PCI / PM: Take SMART_SUSPEND driver flag into account Make the PCI bus type take DPM_FLAG_SMART_SUSPEND into account in its system-wide PM callbacks and make sure that all code that should not run in parallel with pci_pm_runtime_resume() is executed in the "late" phases of system suspend, freeze and poweroff transitions. [Note that the pm_runtime_suspended() check in pci_dev_keep_suspended() is an optimization, because if is not passed, all of the subsequent checks may be skipped and some of them are much more overhead in general.] Also use the observation that if the device is in runtime suspend at the beginning of the "late" phase of a system-wide suspend-like transition, its state cannot change going forward (runtime PM is disabled for it at that time) until the transition is over and the subsequent system-wide PM callbacks should be skipped for it (as they generally assume the device to not be suspended), so add checks for that in pci_pm_suspend_late/noirq(), pci_pm_freeze_late/noirq() and pci_pm_poweroff_late/noirq(). Moreover, if pci_pm_resume_noirq() or pci_pm_restore_noirq() is called during the subsequent system-wide resume transition and if the device was left in runtime suspend previously, its runtime PM status needs to be changed to "active" as it is going to be put into the full-power state, so add checks for that too to these functions. In turn, if pci_pm_thaw_noirq() runs after the device has been left in runtime suspend, the subsequent "thaw" callbacks need to be skipped for it (as they may not work correctly with a suspended device), so set the power.direct_complete flag for the device then to make the PM core skip those callbacks. In addition to the above add a core helper for checking if DPM_FLAG_SMART_SUSPEND is set and the device runtime PM status is "suspended" at the same time, which is done quite often in the new code (and will be done elsewhere going forward too). Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Acked-by: Bjorn Helgaas <bhelgaas@google.com>
2017-10-26 18:12:22 +08:00
return 0;
if (pci_has_legacy_pm_support(pci_dev))
return pci_legacy_suspend_late(dev, PMSG_SUSPEND);
if (!pm) {
pci_save_state(pci_dev);
goto Fixup;
}
if (pm->suspend_noirq) {
pci_power_t prev = pci_dev->current_state;
int error;
error = pm->suspend_noirq(dev);
suspend_report_result(pm->suspend_noirq, error);
if (error)
return error;
if (!pci_dev->state_saved && pci_dev->current_state != PCI_D0
&& pci_dev->current_state != PCI_UNKNOWN) {
pci_WARN_ONCE(pci_dev, pci_dev->current_state != prev,
"PCI PM: State of device not saved by %pS\n",
pm->suspend_noirq);
goto Fixup;
}
}
if (pci_dev->skip_bus_pm) {
/*
* Either the device is a bridge with a child in D0 below it, or
* the function is running for the second time in a row without
* going through full resume, which is possible only during
* suspend-to-idle in a spurious wakeup case. The device should
* be in D0 at this point, but if it is a bridge, it may be
* necessary to save its state.
*/
if (!pci_dev->state_saved)
pci_save_state(pci_dev);
} else if (!pci_dev->state_saved) {
pci_save_state(pci_dev);
PCI: Put PCIe ports into D3 during suspend Currently the Linux PCI core does not touch power state of PCI bridges and PCIe ports when system suspend is entered. Leaving them in D0 consumes power unnecessarily and may prevent the CPU from entering deeper C-states. With recent PCIe hardware we can power down the ports to save power given that we take into account few restrictions: - The PCIe port hardware is recent enough, starting from 2015. - Devices connected to PCIe ports are effectively in D3cold once the port is transitioned to D3 (the config space is not accessible anymore and the link may be powered down). - Devices behind the PCIe port need to be allowed to transition to D3cold and back. There is a way both drivers and userspace can forbid this. - If the device behind the PCIe port is capable of waking the system it needs to be able to do so from D3cold. This patch adds a new flag to struct pci_device called 'bridge_d3'. This flag is set and cleared by the PCI core whenever there is a change in power management state of any of the devices behind the PCIe port. When system later on is suspended we only need to check this flag and if it is true transition the port to D3 otherwise we leave it in D0. Also provide override mechanism via command line parameter "pcie_port_pm=[off|force]" that can be used to disable or enable the feature regardless of the BIOS manufacturing date. Tested-by: Lukas Wunner <lukas@wunner.de> Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com> Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2016-06-02 16:17:12 +08:00
if (pci_power_manageable(pci_dev))
pci_prepare_to_sleep(pci_dev);
}
pci_dbg(pci_dev, "PCI PM: Suspend power state: %s\n",
pci_power_name(pci_dev->current_state));
if (pci_dev->current_state == PCI_D0) {
pci_dev->skip_bus_pm = true;
/*
* Per PCI PM r1.2, table 6-1, a bridge must be in D0 if any
* downstream device is in D0, so avoid changing the power state
* of the parent bridge by setting the skip_bus_pm flag for it.
*/
if (pci_dev->bus->self)
pci_dev->bus->self->skip_bus_pm = true;
}
if (pci_dev->skip_bus_pm && pm_suspend_no_platform()) {
pci_dbg(pci_dev, "PCI PM: Skipped\n");
goto Fixup;
}
pci_pm_set_unknown_state(pci_dev);
PCI: EHCI: fix crash during suspend on ASUS computers Quite a few ASUS computers experience a nasty problem, related to the EHCI controllers, when going into system suspend. It was observed that the problem didn't occur if the controllers were not put into the D3 power state before starting the suspend, and commit 151b61284776be2d6f02d48c23c3625678960b97 (USB: EHCI: fix crash during suspend on ASUS computers) was created to do this. It turned out this approach messed up other computers that didn't have the problem -- it prevented USB wakeup from working. Consequently commit c2fb8a3fa25513de8fedb38509b1f15a5bbee47b (USB: add NO_D3_DURING_SLEEP flag and revert 151b61284776be2) was merged; it reverted the earlier commit and added a whitelist of known good board names. Now we know the actual cause of the problem. Thanks to AceLan Kao for tracking it down. According to him, an engineer at ASUS explained that some of their BIOSes contain a bug that was added in an attempt to work around a problem in early versions of Windows. When the computer goes into S3 suspend, the BIOS tries to verify that the EHCI controllers were first quiesced by the OS. Nothing's wrong with this, but the BIOS does it by checking that the PCI COMMAND registers contain 0 without checking the controllers' power state. If the register isn't 0, the BIOS assumes the controller needs to be quiesced and tries to do so. This involves making various MMIO accesses to the controller, which don't work very well if the controller is already in D3. The end result is a system hang or memory corruption. Since the value in the PCI COMMAND register doesn't matter once the controller has been suspended, and since the value will be restored anyway when the controller is resumed, we can work around the BIOS bug simply by setting the register to 0 during system suspend. This patch (as1590) does so and also reverts the second commit mentioned above, which is now unnecessary. In theory we could do this for every PCI device. However to avoid introducing new problems, the patch restricts itself to EHCI host controllers. Finally the affected systems can suspend with USB wakeup working properly. Reference: https://bugzilla.kernel.org/show_bug.cgi?id=37632 Reference: https://bugzilla.kernel.org/show_bug.cgi?id=42728 Based-on-patch-by: AceLan Kao <acelan.kao@canonical.com> Signed-off-by: Alan Stern <stern@rowland.harvard.edu> Tested-by: Dâniel Fraga <fragabr@gmail.com> Tested-by: Javier Marcet <jmarcet@gmail.com> Tested-by: Andrey Rahmatullin <wrar@wrar.name> Tested-by: Oleksij Rempel <bug-track@fisher-privat.net> Tested-by: Pavel Pisa <pisa@cmp.felk.cvut.cz> Cc: stable <stable@vger.kernel.org> Acked-by: Bjorn Helgaas <bhelgaas@google.com> Acked-by: Rafael J. Wysocki <rjw@sisk.pl> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2012-07-09 23:09:21 +08:00
/*
* Some BIOSes from ASUS have a bug: If a USB EHCI host controller's
* PCI COMMAND register isn't 0, the BIOS assumes that the controller
* hasn't been quiesced and tries to turn it off. If the controller
* is already in D3, this can hang or cause memory corruption.
*
* Since the value of the COMMAND register doesn't matter once the
* device has been suspended, we can safely set it to 0 here.
*/
if (pci_dev->class == PCI_CLASS_SERIAL_USB_EHCI)
pci_write_config_word(pci_dev, PCI_COMMAND, 0);
Fixup:
pci_fixup_device(pci_fixup_suspend_late, pci_dev);
/*
* If the target system sleep state is suspend-to-idle, it is sufficient
* to check whether or not the device's wakeup settings are good for
* runtime PM. Otherwise, the pm_resume_via_firmware() check will cause
* pci_pm_complete() to take care of fixing up the device's state
* anyway, if need be.
*/
if (device_can_wakeup(dev) && !device_may_wakeup(dev))
dev->power.may_skip_resume = false;
return 0;
}
static int pci_pm_resume_noirq(struct device *dev)
{
struct pci_dev *pci_dev = to_pci_dev(dev);
const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
PCI/PM: Add missing link delays required by the PCIe spec Currently Linux does not follow PCIe spec regarding the required delays after reset. A concrete example is a Thunderbolt add-in-card that consists of a PCIe switch and two PCIe endpoints: +-1b.0-[01-6b]----00.0-[02-6b]--+-00.0-[03]----00.0 TBT controller +-01.0-[04-36]-- DS hotplug port +-02.0-[37]----00.0 xHCI controller \-04.0-[38-6b]-- DS hotplug port The root port (1b.0) and the PCIe switch downstream ports are all PCIe Gen3 so they support 8GT/s link speeds. We wait for the PCIe hierarchy to enter D3cold (runtime): pcieport 0000:00:1b.0: power state changed by ACPI to D3cold When it wakes up from D3cold, according to the PCIe 5.0 section 5.8 the PCIe switch is put to reset and its power is re-applied. This means that we must follow the rules in PCIe 5.0 section 6.6.1. For the PCIe Gen3 ports we are dealing with here, the following applies: With a Downstream Port that supports Link speeds greater than 5.0 GT/s, software must wait a minimum of 100 ms after Link training completes before sending a Configuration Request to the device immediately below that Port. Software can determine when Link training completes by polling the Data Link Layer Link Active bit or by setting up an associated interrupt (see Section 6.7.3.3). Translating this into the above topology we would need to do this (DLLLA stands for Data Link Layer Link Active): 0000:00:1b.0: wait for 100 ms after DLLLA is set before access to 0000:01:00.0 0000:02:00.0: wait for 100 ms after DLLLA is set before access to 0000:03:00.0 0000:02:02.0: wait for 100 ms after DLLLA is set before access to 0000:37:00.0 I've instrumented the kernel with some additional logging so we can see the actual delays performed: pcieport 0000:00:1b.0: power state changed by ACPI to D0 pcieport 0000:00:1b.0: waiting for D3cold delay of 100 ms pcieport 0000:00:1b.0: waiting for D3hot delay of 10 ms pcieport 0000:02:01.0: waiting for D3hot delay of 10 ms pcieport 0000:02:04.0: waiting for D3hot delay of 10 ms For the switch upstream port (01:00.0 reachable through 00:1b.0 root port) we wait for 100 ms but not taking into account the DLLLA requirement. We then wait 10 ms for D3hot -> D0 transition of the root port and the two downstream hotplug ports. This means that we deviate from what the spec requires. Performing the same check for system sleep (s2idle) transitions it turns out to be even worse. None of the mandatory delays are performed. If this would be S3 instead of s2idle then according to PCI FW spec 3.2 section 4.6.8. there is a specific _DSM that allows the OS to skip the delays but this platform does not provide the _DSM and does not go to S3 anyway so no firmware is involved that could already handle these delays. On this particular platform these delays are not actually needed because there is an additional delay as part of the ACPI power resource that is used to turn on power to the hierarchy but since that additional delay is not required by any of standards (PCIe, ACPI) it is not present in the Intel Ice Lake, for example where missing the mandatory delays causes pciehp to start tearing down the stack too early (links are not yet trained). Below is an example how it looks like when this happens: pcieport 0000:83:04.0: pciehp: Slot(4): Card not present pcieport 0000:87:04.0: PME# disabled pcieport 0000:83:04.0: pciehp: pciehp_unconfigure_device: domain:bus:dev = 0000:86:00 pcieport 0000:86:00.0: Refused to change power state, currently in D3 pcieport 0000:86:00.0: restoring config space at offset 0x3c (was 0xffffffff, writing 0x201ff) pcieport 0000:86:00.0: restoring config space at offset 0x38 (was 0xffffffff, writing 0x0) ... There is also one reported case (see the bugzilla link below) where the missing delay causes xHCI on a Titan Ridge controller fail to runtime resume when USB-C dock is plugged. This does not involve pciehp but instead the PCI core fails to runtime resume the xHCI device: pcieport 0000:04:02.0: restoring config space at offset 0xc (was 0x10000, writing 0x10020) pcieport 0000:04:02.0: restoring config space at offset 0x4 (was 0x100000, writing 0x100406) xhci_hcd 0000:39:00.0: Refused to change power state, currently in D3 xhci_hcd 0000:39:00.0: restoring config space at offset 0x3c (was 0xffffffff, writing 0x1ff) xhci_hcd 0000:39:00.0: restoring config space at offset 0x38 (was 0xffffffff, writing 0x0) ... Add a new function pci_bridge_wait_for_secondary_bus() that is called on PCI core resume and runtime resume paths accordingly if the bridge entered D3cold (and thus went through reset). This is second attempt to add the missing delays. The previous solution in c2bf1fc212f7 ("PCI: Add missing link delays required by the PCIe spec") was reverted because of two issues it caused: 1. One system become unresponsive after S3 resume due to PME service spinning in pcie_pme_work_fn(). The root port in question reports that the xHCI sent PME but the xHCI device itself does not have PME status set. The PME status bit is never cleared in the root port resulting the indefinite loop in pcie_pme_work_fn(). 2. Slows down resume if the root/downstream port does not support Data Link Layer Active Reporting because pcie_wait_for_link_delay() waits 1100 ms in that case. This version should avoid the above issues because we restrict the delay to happen only if the port went into D3cold. Link: https://lore.kernel.org/linux-pci/SL2P216MB01878BBCD75F21D882AEEA2880C60@SL2P216MB0187.KORP216.PROD.OUTLOOK.COM/ Link: https://bugzilla.kernel.org/show_bug.cgi?id=203885 Link: https://lore.kernel.org/r/20191112091617.70282-3-mika.westerberg@linux.intel.com Reported-by: Kai-Heng Feng <kai.heng.feng@canonical.com> Tested-by: Kai-Heng Feng <kai.heng.feng@canonical.com> Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com> Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
2019-11-12 17:16:17 +08:00
pci_power_t prev_state = pci_dev->current_state;
bool skip_bus_pm = pci_dev->skip_bus_pm;
if (dev_pm_skip_resume(dev))
return 0;
/*
* In the suspend-to-idle case, devices left in D0 during suspend will
* stay in D0, so it is not necessary to restore or update their
* configuration here and attempting to put them into D0 again is
* pointless, so avoid doing that.
*/
PCI/PM: Add missing link delays required by the PCIe spec Currently Linux does not follow PCIe spec regarding the required delays after reset. A concrete example is a Thunderbolt add-in-card that consists of a PCIe switch and two PCIe endpoints: +-1b.0-[01-6b]----00.0-[02-6b]--+-00.0-[03]----00.0 TBT controller +-01.0-[04-36]-- DS hotplug port +-02.0-[37]----00.0 xHCI controller \-04.0-[38-6b]-- DS hotplug port The root port (1b.0) and the PCIe switch downstream ports are all PCIe Gen3 so they support 8GT/s link speeds. We wait for the PCIe hierarchy to enter D3cold (runtime): pcieport 0000:00:1b.0: power state changed by ACPI to D3cold When it wakes up from D3cold, according to the PCIe 5.0 section 5.8 the PCIe switch is put to reset and its power is re-applied. This means that we must follow the rules in PCIe 5.0 section 6.6.1. For the PCIe Gen3 ports we are dealing with here, the following applies: With a Downstream Port that supports Link speeds greater than 5.0 GT/s, software must wait a minimum of 100 ms after Link training completes before sending a Configuration Request to the device immediately below that Port. Software can determine when Link training completes by polling the Data Link Layer Link Active bit or by setting up an associated interrupt (see Section 6.7.3.3). Translating this into the above topology we would need to do this (DLLLA stands for Data Link Layer Link Active): 0000:00:1b.0: wait for 100 ms after DLLLA is set before access to 0000:01:00.0 0000:02:00.0: wait for 100 ms after DLLLA is set before access to 0000:03:00.0 0000:02:02.0: wait for 100 ms after DLLLA is set before access to 0000:37:00.0 I've instrumented the kernel with some additional logging so we can see the actual delays performed: pcieport 0000:00:1b.0: power state changed by ACPI to D0 pcieport 0000:00:1b.0: waiting for D3cold delay of 100 ms pcieport 0000:00:1b.0: waiting for D3hot delay of 10 ms pcieport 0000:02:01.0: waiting for D3hot delay of 10 ms pcieport 0000:02:04.0: waiting for D3hot delay of 10 ms For the switch upstream port (01:00.0 reachable through 00:1b.0 root port) we wait for 100 ms but not taking into account the DLLLA requirement. We then wait 10 ms for D3hot -> D0 transition of the root port and the two downstream hotplug ports. This means that we deviate from what the spec requires. Performing the same check for system sleep (s2idle) transitions it turns out to be even worse. None of the mandatory delays are performed. If this would be S3 instead of s2idle then according to PCI FW spec 3.2 section 4.6.8. there is a specific _DSM that allows the OS to skip the delays but this platform does not provide the _DSM and does not go to S3 anyway so no firmware is involved that could already handle these delays. On this particular platform these delays are not actually needed because there is an additional delay as part of the ACPI power resource that is used to turn on power to the hierarchy but since that additional delay is not required by any of standards (PCIe, ACPI) it is not present in the Intel Ice Lake, for example where missing the mandatory delays causes pciehp to start tearing down the stack too early (links are not yet trained). Below is an example how it looks like when this happens: pcieport 0000:83:04.0: pciehp: Slot(4): Card not present pcieport 0000:87:04.0: PME# disabled pcieport 0000:83:04.0: pciehp: pciehp_unconfigure_device: domain:bus:dev = 0000:86:00 pcieport 0000:86:00.0: Refused to change power state, currently in D3 pcieport 0000:86:00.0: restoring config space at offset 0x3c (was 0xffffffff, writing 0x201ff) pcieport 0000:86:00.0: restoring config space at offset 0x38 (was 0xffffffff, writing 0x0) ... There is also one reported case (see the bugzilla link below) where the missing delay causes xHCI on a Titan Ridge controller fail to runtime resume when USB-C dock is plugged. This does not involve pciehp but instead the PCI core fails to runtime resume the xHCI device: pcieport 0000:04:02.0: restoring config space at offset 0xc (was 0x10000, writing 0x10020) pcieport 0000:04:02.0: restoring config space at offset 0x4 (was 0x100000, writing 0x100406) xhci_hcd 0000:39:00.0: Refused to change power state, currently in D3 xhci_hcd 0000:39:00.0: restoring config space at offset 0x3c (was 0xffffffff, writing 0x1ff) xhci_hcd 0000:39:00.0: restoring config space at offset 0x38 (was 0xffffffff, writing 0x0) ... Add a new function pci_bridge_wait_for_secondary_bus() that is called on PCI core resume and runtime resume paths accordingly if the bridge entered D3cold (and thus went through reset). This is second attempt to add the missing delays. The previous solution in c2bf1fc212f7 ("PCI: Add missing link delays required by the PCIe spec") was reverted because of two issues it caused: 1. One system become unresponsive after S3 resume due to PME service spinning in pcie_pme_work_fn(). The root port in question reports that the xHCI sent PME but the xHCI device itself does not have PME status set. The PME status bit is never cleared in the root port resulting the indefinite loop in pcie_pme_work_fn(). 2. Slows down resume if the root/downstream port does not support Data Link Layer Active Reporting because pcie_wait_for_link_delay() waits 1100 ms in that case. This version should avoid the above issues because we restrict the delay to happen only if the port went into D3cold. Link: https://lore.kernel.org/linux-pci/SL2P216MB01878BBCD75F21D882AEEA2880C60@SL2P216MB0187.KORP216.PROD.OUTLOOK.COM/ Link: https://bugzilla.kernel.org/show_bug.cgi?id=203885 Link: https://lore.kernel.org/r/20191112091617.70282-3-mika.westerberg@linux.intel.com Reported-by: Kai-Heng Feng <kai.heng.feng@canonical.com> Tested-by: Kai-Heng Feng <kai.heng.feng@canonical.com> Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com> Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
2019-11-12 17:16:17 +08:00
if (!(skip_bus_pm && pm_suspend_no_platform()))
pci_pm_default_resume_early(pci_dev);
pci_fixup_device(pci_fixup_resume_early, pci_dev);
pcie_pme_root_status_cleanup(pci_dev);
PCI/PM: Add missing link delays required by the PCIe spec Currently Linux does not follow PCIe spec regarding the required delays after reset. A concrete example is a Thunderbolt add-in-card that consists of a PCIe switch and two PCIe endpoints: +-1b.0-[01-6b]----00.0-[02-6b]--+-00.0-[03]----00.0 TBT controller +-01.0-[04-36]-- DS hotplug port +-02.0-[37]----00.0 xHCI controller \-04.0-[38-6b]-- DS hotplug port The root port (1b.0) and the PCIe switch downstream ports are all PCIe Gen3 so they support 8GT/s link speeds. We wait for the PCIe hierarchy to enter D3cold (runtime): pcieport 0000:00:1b.0: power state changed by ACPI to D3cold When it wakes up from D3cold, according to the PCIe 5.0 section 5.8 the PCIe switch is put to reset and its power is re-applied. This means that we must follow the rules in PCIe 5.0 section 6.6.1. For the PCIe Gen3 ports we are dealing with here, the following applies: With a Downstream Port that supports Link speeds greater than 5.0 GT/s, software must wait a minimum of 100 ms after Link training completes before sending a Configuration Request to the device immediately below that Port. Software can determine when Link training completes by polling the Data Link Layer Link Active bit or by setting up an associated interrupt (see Section 6.7.3.3). Translating this into the above topology we would need to do this (DLLLA stands for Data Link Layer Link Active): 0000:00:1b.0: wait for 100 ms after DLLLA is set before access to 0000:01:00.0 0000:02:00.0: wait for 100 ms after DLLLA is set before access to 0000:03:00.0 0000:02:02.0: wait for 100 ms after DLLLA is set before access to 0000:37:00.0 I've instrumented the kernel with some additional logging so we can see the actual delays performed: pcieport 0000:00:1b.0: power state changed by ACPI to D0 pcieport 0000:00:1b.0: waiting for D3cold delay of 100 ms pcieport 0000:00:1b.0: waiting for D3hot delay of 10 ms pcieport 0000:02:01.0: waiting for D3hot delay of 10 ms pcieport 0000:02:04.0: waiting for D3hot delay of 10 ms For the switch upstream port (01:00.0 reachable through 00:1b.0 root port) we wait for 100 ms but not taking into account the DLLLA requirement. We then wait 10 ms for D3hot -> D0 transition of the root port and the two downstream hotplug ports. This means that we deviate from what the spec requires. Performing the same check for system sleep (s2idle) transitions it turns out to be even worse. None of the mandatory delays are performed. If this would be S3 instead of s2idle then according to PCI FW spec 3.2 section 4.6.8. there is a specific _DSM that allows the OS to skip the delays but this platform does not provide the _DSM and does not go to S3 anyway so no firmware is involved that could already handle these delays. On this particular platform these delays are not actually needed because there is an additional delay as part of the ACPI power resource that is used to turn on power to the hierarchy but since that additional delay is not required by any of standards (PCIe, ACPI) it is not present in the Intel Ice Lake, for example where missing the mandatory delays causes pciehp to start tearing down the stack too early (links are not yet trained). Below is an example how it looks like when this happens: pcieport 0000:83:04.0: pciehp: Slot(4): Card not present pcieport 0000:87:04.0: PME# disabled pcieport 0000:83:04.0: pciehp: pciehp_unconfigure_device: domain:bus:dev = 0000:86:00 pcieport 0000:86:00.0: Refused to change power state, currently in D3 pcieport 0000:86:00.0: restoring config space at offset 0x3c (was 0xffffffff, writing 0x201ff) pcieport 0000:86:00.0: restoring config space at offset 0x38 (was 0xffffffff, writing 0x0) ... There is also one reported case (see the bugzilla link below) where the missing delay causes xHCI on a Titan Ridge controller fail to runtime resume when USB-C dock is plugged. This does not involve pciehp but instead the PCI core fails to runtime resume the xHCI device: pcieport 0000:04:02.0: restoring config space at offset 0xc (was 0x10000, writing 0x10020) pcieport 0000:04:02.0: restoring config space at offset 0x4 (was 0x100000, writing 0x100406) xhci_hcd 0000:39:00.0: Refused to change power state, currently in D3 xhci_hcd 0000:39:00.0: restoring config space at offset 0x3c (was 0xffffffff, writing 0x1ff) xhci_hcd 0000:39:00.0: restoring config space at offset 0x38 (was 0xffffffff, writing 0x0) ... Add a new function pci_bridge_wait_for_secondary_bus() that is called on PCI core resume and runtime resume paths accordingly if the bridge entered D3cold (and thus went through reset). This is second attempt to add the missing delays. The previous solution in c2bf1fc212f7 ("PCI: Add missing link delays required by the PCIe spec") was reverted because of two issues it caused: 1. One system become unresponsive after S3 resume due to PME service spinning in pcie_pme_work_fn(). The root port in question reports that the xHCI sent PME but the xHCI device itself does not have PME status set. The PME status bit is never cleared in the root port resulting the indefinite loop in pcie_pme_work_fn(). 2. Slows down resume if the root/downstream port does not support Data Link Layer Active Reporting because pcie_wait_for_link_delay() waits 1100 ms in that case. This version should avoid the above issues because we restrict the delay to happen only if the port went into D3cold. Link: https://lore.kernel.org/linux-pci/SL2P216MB01878BBCD75F21D882AEEA2880C60@SL2P216MB0187.KORP216.PROD.OUTLOOK.COM/ Link: https://bugzilla.kernel.org/show_bug.cgi?id=203885 Link: https://lore.kernel.org/r/20191112091617.70282-3-mika.westerberg@linux.intel.com Reported-by: Kai-Heng Feng <kai.heng.feng@canonical.com> Tested-by: Kai-Heng Feng <kai.heng.feng@canonical.com> Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com> Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
2019-11-12 17:16:17 +08:00
if (!skip_bus_pm && prev_state == PCI_D3cold)
pci_bridge_wait_for_secondary_bus(pci_dev);
if (pci_has_legacy_pm_support(pci_dev))
return 0;
if (pm && pm->resume_noirq)
return pm->resume_noirq(dev);
return 0;
}
PM: sleep: core: Do not skip callbacks in the resume phase The current code in device_resume_noirq() causes the entire early resume and resume phases of device suspend to be skipped for devices for which the noirq resume phase have been skipped (due to the LEAVE_SUSPENDED flag being set) on the premise that those devices should stay in runtime-suspend after system-wide resume. However, that may not be correct in two situations. First, the middle layer (subsystem) noirq resume callback may be missing for a given device, but its early resume callback may be present and it may need to do something even if it decides to skip the driver callback. Second, if the device's wakeup settings were adjusted in the suspend phase without resuming the device (that was in runtime suspend at that time), they most likely need to be adjusted again in the resume phase and so the driver callback in that phase needs to be run. For the above reason, modify the core to allow the middle layer ->resume_late callback to run even if its ->resume_noirq callback is missing (and the core has skipped the driver-level callback in that phase) and to allow all device callbacks to run in the resume phase. Also make the core set the PM-runtime status of devices with SMART_SUSPEND set whose resume callbacks are not skipped to "active" in the "noirq" resume phase and update the affected subsystems (PCI and ACPI) accordingly. After this change, middle-layer (subsystem) callbacks will always be invoked in all phases of system suspend and resume and driver callbacks will always run in the prepare, suspend, resume, and complete phases for all devices. For devices with SMART_SUSPEND set, driver callbacks will be skipped in the late and noirq phases of system suspend if those devices remain in runtime suspend in __device_suspend_late(). Driver callbacks will also be skipped for them during the noirq and early phases of the "thaw" transition related to hibernation in that case. Setting LEAVE_SUSPENDED means that the driver allows its callbacks to be skipped in the noirq and early phases of system resume, but some additional conditions need to be met for that to happen (among other things, the power.may_skip_resume flag needs to be set for the device during system suspend for the driver callbacks to be skipped during the subsequent resume transition). For all devices with SMART_SUSPEND set whose driver callbacks are invoked during system resume, the PM-runtime status will be set to "active" (by the core). Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Alan Stern <stern@rowland.harvard.edu> Acked-by: Bjorn Helgaas <bhelgaas@google.com>
2020-04-19 00:52:08 +08:00
static int pci_pm_resume_early(struct device *dev)
{
if (dev_pm_skip_resume(dev))
PM: sleep: core: Do not skip callbacks in the resume phase The current code in device_resume_noirq() causes the entire early resume and resume phases of device suspend to be skipped for devices for which the noirq resume phase have been skipped (due to the LEAVE_SUSPENDED flag being set) on the premise that those devices should stay in runtime-suspend after system-wide resume. However, that may not be correct in two situations. First, the middle layer (subsystem) noirq resume callback may be missing for a given device, but its early resume callback may be present and it may need to do something even if it decides to skip the driver callback. Second, if the device's wakeup settings were adjusted in the suspend phase without resuming the device (that was in runtime suspend at that time), they most likely need to be adjusted again in the resume phase and so the driver callback in that phase needs to be run. For the above reason, modify the core to allow the middle layer ->resume_late callback to run even if its ->resume_noirq callback is missing (and the core has skipped the driver-level callback in that phase) and to allow all device callbacks to run in the resume phase. Also make the core set the PM-runtime status of devices with SMART_SUSPEND set whose resume callbacks are not skipped to "active" in the "noirq" resume phase and update the affected subsystems (PCI and ACPI) accordingly. After this change, middle-layer (subsystem) callbacks will always be invoked in all phases of system suspend and resume and driver callbacks will always run in the prepare, suspend, resume, and complete phases for all devices. For devices with SMART_SUSPEND set, driver callbacks will be skipped in the late and noirq phases of system suspend if those devices remain in runtime suspend in __device_suspend_late(). Driver callbacks will also be skipped for them during the noirq and early phases of the "thaw" transition related to hibernation in that case. Setting LEAVE_SUSPENDED means that the driver allows its callbacks to be skipped in the noirq and early phases of system resume, but some additional conditions need to be met for that to happen (among other things, the power.may_skip_resume flag needs to be set for the device during system suspend for the driver callbacks to be skipped during the subsequent resume transition). For all devices with SMART_SUSPEND set whose driver callbacks are invoked during system resume, the PM-runtime status will be set to "active" (by the core). Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Alan Stern <stern@rowland.harvard.edu> Acked-by: Bjorn Helgaas <bhelgaas@google.com>
2020-04-19 00:52:08 +08:00
return 0;
return pm_generic_resume_early(dev);
}
static int pci_pm_resume(struct device *dev)
{
struct pci_dev *pci_dev = to_pci_dev(dev);
const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
/*
* This is necessary for the suspend error path in which resume is
* called without restoring the standard config registers of the device.
*/
if (pci_dev->state_saved)
pci_restore_standard_config(pci_dev);
if (pci_has_legacy_pm_support(pci_dev))
return pci_legacy_resume(dev);
PCI PM: make the PM core more careful with drivers using the new PM framework Currently, the PM core always attempts to manage devices with drivers that use the new PM framework. In particular, it attempts to disable the devices (which is unnecessary), to save their state (which may be undesirable if the driver has done that already) and to put them into low power states (again, this may be undesirable if the driver has already put the device into a low power state). That need not be the right thing to do, so make the core be more careful in this respect. Generally, there are the following categories of devices to consider: * bridge devices without drivers * non-bridge devices without drivers * bridge devices with drivers * non-bridge devices with drivers and each of them should be handled differently. For bridge devices without drivers the PCI PM core will save their state on suspend and restore it (early) during resume, after putting them into D0 if necessary. It will not attempt to do anything else to these devices. For non-bridge devices without drivers the PCI PM core will disable them and save their state on suspend. During resume, it will put them into D0, if necessary, restore their state (early) and reenable them. For bridge devices with drivers the PCI PM core will only save their state on suspend if the driver hasn't done that already. Still, the core will restore their state (early) during resume, after putting them into D0, if necessary. For non-bridge devices with drivers the PCI PM core will only save their state on suspend if the driver hasn't done that already. Also, if the state of the device hasn't been saved by the driver, the core will attempt to put the device into a low power state. During resume the core will restore the state of the device (early), after putting it into D0, if necessary. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2009-02-04 09:09:07 +08:00
pci_pm_default_resume(pci_dev);
PCI PM: make the PM core more careful with drivers using the new PM framework Currently, the PM core always attempts to manage devices with drivers that use the new PM framework. In particular, it attempts to disable the devices (which is unnecessary), to save their state (which may be undesirable if the driver has done that already) and to put them into low power states (again, this may be undesirable if the driver has already put the device into a low power state). That need not be the right thing to do, so make the core be more careful in this respect. Generally, there are the following categories of devices to consider: * bridge devices without drivers * non-bridge devices without drivers * bridge devices with drivers * non-bridge devices with drivers and each of them should be handled differently. For bridge devices without drivers the PCI PM core will save their state on suspend and restore it (early) during resume, after putting them into D0 if necessary. It will not attempt to do anything else to these devices. For non-bridge devices without drivers the PCI PM core will disable them and save their state on suspend. During resume, it will put them into D0, if necessary, restore their state (early) and reenable them. For bridge devices with drivers the PCI PM core will only save their state on suspend if the driver hasn't done that already. Still, the core will restore their state (early) during resume, after putting them into D0, if necessary. For non-bridge devices with drivers the PCI PM core will only save their state on suspend if the driver hasn't done that already. Also, if the state of the device hasn't been saved by the driver, the core will attempt to put the device into a low power state. During resume the core will restore the state of the device (early), after putting it into D0, if necessary. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2009-02-04 09:09:07 +08:00
if (pm) {
if (pm->resume)
return pm->resume(dev);
PCI PM: make the PM core more careful with drivers using the new PM framework Currently, the PM core always attempts to manage devices with drivers that use the new PM framework. In particular, it attempts to disable the devices (which is unnecessary), to save their state (which may be undesirable if the driver has done that already) and to put them into low power states (again, this may be undesirable if the driver has already put the device into a low power state). That need not be the right thing to do, so make the core be more careful in this respect. Generally, there are the following categories of devices to consider: * bridge devices without drivers * non-bridge devices without drivers * bridge devices with drivers * non-bridge devices with drivers and each of them should be handled differently. For bridge devices without drivers the PCI PM core will save their state on suspend and restore it (early) during resume, after putting them into D0 if necessary. It will not attempt to do anything else to these devices. For non-bridge devices without drivers the PCI PM core will disable them and save their state on suspend. During resume, it will put them into D0, if necessary, restore their state (early) and reenable them. For bridge devices with drivers the PCI PM core will only save their state on suspend if the driver hasn't done that already. Still, the core will restore their state (early) during resume, after putting them into D0, if necessary. For non-bridge devices with drivers the PCI PM core will only save their state on suspend if the driver hasn't done that already. Also, if the state of the device hasn't been saved by the driver, the core will attempt to put the device into a low power state. During resume the core will restore the state of the device (early), after putting it into D0, if necessary. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2009-02-04 09:09:07 +08:00
} else {
pci_pm_reenable_device(pci_dev);
}
return 0;
}
#else /* !CONFIG_SUSPEND */
#define pci_pm_suspend NULL
PCI / PM: Take SMART_SUSPEND driver flag into account Make the PCI bus type take DPM_FLAG_SMART_SUSPEND into account in its system-wide PM callbacks and make sure that all code that should not run in parallel with pci_pm_runtime_resume() is executed in the "late" phases of system suspend, freeze and poweroff transitions. [Note that the pm_runtime_suspended() check in pci_dev_keep_suspended() is an optimization, because if is not passed, all of the subsequent checks may be skipped and some of them are much more overhead in general.] Also use the observation that if the device is in runtime suspend at the beginning of the "late" phase of a system-wide suspend-like transition, its state cannot change going forward (runtime PM is disabled for it at that time) until the transition is over and the subsequent system-wide PM callbacks should be skipped for it (as they generally assume the device to not be suspended), so add checks for that in pci_pm_suspend_late/noirq(), pci_pm_freeze_late/noirq() and pci_pm_poweroff_late/noirq(). Moreover, if pci_pm_resume_noirq() or pci_pm_restore_noirq() is called during the subsequent system-wide resume transition and if the device was left in runtime suspend previously, its runtime PM status needs to be changed to "active" as it is going to be put into the full-power state, so add checks for that too to these functions. In turn, if pci_pm_thaw_noirq() runs after the device has been left in runtime suspend, the subsequent "thaw" callbacks need to be skipped for it (as they may not work correctly with a suspended device), so set the power.direct_complete flag for the device then to make the PM core skip those callbacks. In addition to the above add a core helper for checking if DPM_FLAG_SMART_SUSPEND is set and the device runtime PM status is "suspended" at the same time, which is done quite often in the new code (and will be done elsewhere going forward too). Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Acked-by: Bjorn Helgaas <bhelgaas@google.com>
2017-10-26 18:12:22 +08:00
#define pci_pm_suspend_late NULL
#define pci_pm_suspend_noirq NULL
#define pci_pm_resume NULL
PM: sleep: core: Do not skip callbacks in the resume phase The current code in device_resume_noirq() causes the entire early resume and resume phases of device suspend to be skipped for devices for which the noirq resume phase have been skipped (due to the LEAVE_SUSPENDED flag being set) on the premise that those devices should stay in runtime-suspend after system-wide resume. However, that may not be correct in two situations. First, the middle layer (subsystem) noirq resume callback may be missing for a given device, but its early resume callback may be present and it may need to do something even if it decides to skip the driver callback. Second, if the device's wakeup settings were adjusted in the suspend phase without resuming the device (that was in runtime suspend at that time), they most likely need to be adjusted again in the resume phase and so the driver callback in that phase needs to be run. For the above reason, modify the core to allow the middle layer ->resume_late callback to run even if its ->resume_noirq callback is missing (and the core has skipped the driver-level callback in that phase) and to allow all device callbacks to run in the resume phase. Also make the core set the PM-runtime status of devices with SMART_SUSPEND set whose resume callbacks are not skipped to "active" in the "noirq" resume phase and update the affected subsystems (PCI and ACPI) accordingly. After this change, middle-layer (subsystem) callbacks will always be invoked in all phases of system suspend and resume and driver callbacks will always run in the prepare, suspend, resume, and complete phases for all devices. For devices with SMART_SUSPEND set, driver callbacks will be skipped in the late and noirq phases of system suspend if those devices remain in runtime suspend in __device_suspend_late(). Driver callbacks will also be skipped for them during the noirq and early phases of the "thaw" transition related to hibernation in that case. Setting LEAVE_SUSPENDED means that the driver allows its callbacks to be skipped in the noirq and early phases of system resume, but some additional conditions need to be met for that to happen (among other things, the power.may_skip_resume flag needs to be set for the device during system suspend for the driver callbacks to be skipped during the subsequent resume transition). For all devices with SMART_SUSPEND set whose driver callbacks are invoked during system resume, the PM-runtime status will be set to "active" (by the core). Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Alan Stern <stern@rowland.harvard.edu> Acked-by: Bjorn Helgaas <bhelgaas@google.com>
2020-04-19 00:52:08 +08:00
#define pci_pm_resume_early NULL
#define pci_pm_resume_noirq NULL
#endif /* !CONFIG_SUSPEND */
#ifdef CONFIG_HIBERNATE_CALLBACKS
static int pci_pm_freeze(struct device *dev)
{
struct pci_dev *pci_dev = to_pci_dev(dev);
const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
if (pci_has_legacy_pm_support(pci_dev))
return pci_legacy_suspend(dev, PMSG_FREEZE);
PCI PM: make the PM core more careful with drivers using the new PM framework Currently, the PM core always attempts to manage devices with drivers that use the new PM framework. In particular, it attempts to disable the devices (which is unnecessary), to save their state (which may be undesirable if the driver has done that already) and to put them into low power states (again, this may be undesirable if the driver has already put the device into a low power state). That need not be the right thing to do, so make the core be more careful in this respect. Generally, there are the following categories of devices to consider: * bridge devices without drivers * non-bridge devices without drivers * bridge devices with drivers * non-bridge devices with drivers and each of them should be handled differently. For bridge devices without drivers the PCI PM core will save their state on suspend and restore it (early) during resume, after putting them into D0 if necessary. It will not attempt to do anything else to these devices. For non-bridge devices without drivers the PCI PM core will disable them and save their state on suspend. During resume, it will put them into D0, if necessary, restore their state (early) and reenable them. For bridge devices with drivers the PCI PM core will only save their state on suspend if the driver hasn't done that already. Still, the core will restore their state (early) during resume, after putting them into D0, if necessary. For non-bridge devices with drivers the PCI PM core will only save their state on suspend if the driver hasn't done that already. Also, if the state of the device hasn't been saved by the driver, the core will attempt to put the device into a low power state. During resume the core will restore the state of the device (early), after putting it into D0, if necessary. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2009-02-04 09:09:07 +08:00
if (!pm) {
pci_pm_default_suspend(pci_dev);
return 0;
}
/*
* Resume all runtime-suspended devices before creating a snapshot
* image of system memory, because the restore kernel generally cannot
* be expected to always handle them consistently and they need to be
* put into the runtime-active metastate during system resume anyway,
* so it is better to ensure that the state saved in the image will be
* always consistent with that.
*/
pm_runtime_resume(dev);
pci_dev->state_saved = false;
PCI PM: make the PM core more careful with drivers using the new PM framework Currently, the PM core always attempts to manage devices with drivers that use the new PM framework. In particular, it attempts to disable the devices (which is unnecessary), to save their state (which may be undesirable if the driver has done that already) and to put them into low power states (again, this may be undesirable if the driver has already put the device into a low power state). That need not be the right thing to do, so make the core be more careful in this respect. Generally, there are the following categories of devices to consider: * bridge devices without drivers * non-bridge devices without drivers * bridge devices with drivers * non-bridge devices with drivers and each of them should be handled differently. For bridge devices without drivers the PCI PM core will save their state on suspend and restore it (early) during resume, after putting them into D0 if necessary. It will not attempt to do anything else to these devices. For non-bridge devices without drivers the PCI PM core will disable them and save their state on suspend. During resume, it will put them into D0, if necessary, restore their state (early) and reenable them. For bridge devices with drivers the PCI PM core will only save their state on suspend if the driver hasn't done that already. Still, the core will restore their state (early) during resume, after putting them into D0, if necessary. For non-bridge devices with drivers the PCI PM core will only save their state on suspend if the driver hasn't done that already. Also, if the state of the device hasn't been saved by the driver, the core will attempt to put the device into a low power state. During resume the core will restore the state of the device (early), after putting it into D0, if necessary. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2009-02-04 09:09:07 +08:00
if (pm->freeze) {
int error;
error = pm->freeze(dev);
suspend_report_result(pm->freeze, error);
if (error)
return error;
}
return 0;
}
static int pci_pm_freeze_noirq(struct device *dev)
{
struct pci_dev *pci_dev = to_pci_dev(dev);
const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
if (pci_has_legacy_pm_support(pci_dev))
return pci_legacy_suspend_late(dev, PMSG_FREEZE);
if (pm && pm->freeze_noirq) {
int error;
error = pm->freeze_noirq(dev);
suspend_report_result(pm->freeze_noirq, error);
if (error)
return error;
}
if (!pci_dev->state_saved)
pci_save_state(pci_dev);
pci_pm_set_unknown_state(pci_dev);
return 0;
}
static int pci_pm_thaw_noirq(struct device *dev)
{
struct pci_dev *pci_dev = to_pci_dev(dev);
const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
/*
* The pm->thaw_noirq() callback assumes the device has been
* returned to D0 and its config state has been restored.
PCI/PM: Always return devices to D0 when thawing pci_pm_thaw_noirq() is supposed to return the device to D0 and restore its configuration registers, but previously it only did that for devices whose drivers implemented the new power management ops. Hibernation, e.g., via "echo disk > /sys/power/state", involves freezing devices, creating a hibernation image, thawing devices, writing the image, and powering off. The fact that thawing did not return devices with legacy power management to D0 caused errors, e.g., in this path: pci_pm_thaw_noirq if (pci_has_legacy_pm_support(pci_dev)) # true for Mellanox VF driver return pci_legacy_resume_early(dev) # ... legacy PM skips the rest pci_set_power_state(pci_dev, PCI_D0) pci_restore_state(pci_dev) pci_pm_thaw if (pci_has_legacy_pm_support(pci_dev)) pci_legacy_resume drv->resume mlx4_resume ... pci_enable_msix_range ... if (dev->current_state != PCI_D0) # <--- return -EINVAL; which caused these warnings: mlx4_core a6d1:00:02.0: INTx is not supported in multi-function mode, aborting PM: dpm_run_callback(): pci_pm_thaw+0x0/0xd7 returns -95 PM: Device a6d1:00:02.0 failed to thaw: error -95 Return devices to D0 and restore config registers for all devices, not just those whose drivers support new power management. [bhelgaas: also call pci_restore_state() before pci_legacy_resume_early(), update comment, add stable tag, commit log] Link: https://lore.kernel.org/r/KU1P153MB016637CAEAD346F0AA8E3801BFAD0@KU1P153MB0166.APCP153.PROD.OUTLOOK.COM Signed-off-by: Dexuan Cui <decui@microsoft.com> Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> Reviewed-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Cc: stable@vger.kernel.org # v4.13+
2019-08-14 09:06:55 +08:00
*
* In addition, pci_restore_state() restores MSI-X state in MMIO
* space, which requires the device to be in D0, so return it to D0
* in case the driver's "freeze" callbacks put it into a low-power
* state.
*/
pci_set_power_state(pci_dev, PCI_D0);
PCI/PM: Restore the status of PCI devices across hibernation Currently we saw a lot of "No irq handler" errors during hibernation, which caused the system hang finally: ata4.00: qc timeout (cmd 0xec) ata4.00: failed to IDENTIFY (I/O error, err_mask=0x4) ata4.00: revalidation failed (errno=-5) ata4: SATA link up 6.0 Gbps (SStatus 133 SControl 300) do_IRQ: 31.151 No irq handler for vector According to above logs, there is an interrupt triggered and it is dispatched to CPU31 with a vector number 151, but there is no handler for it, thus this IRQ will not get acked and will cause an IRQ flood which kills the system. To be more specific, the 31.151 is an interrupt from the AHCI host controller. After some investigation, the reason why this issue is triggered is because the thaw_noirq() function does not restore the MSI/MSI-X settings across hibernation. The scenario is illustrated below: 1. Before hibernation, IRQ 34 is the handler for the AHCI device, which is bound to CPU31. 2. Hibernation starts, the AHCI device is put into low power state. 3. All the nonboot CPUs are put offline, so IRQ 34 has to be migrated to the last alive one - CPU0. 4. After the snapshot has been created, all the nonboot CPUs are brought up again; IRQ 34 remains bound to CPU0. 5. AHCI devices are put into D0. 6. The snapshot is written to the disk. The issue is triggered in step 6. The AHCI interrupt should be delivered to CPU0, however it is delivered to the original CPU31 instead, which causes the "No irq handler" issue. Ying Huang has provided a clue that, in step 3 it is possible that writing to the register might not take effect as the PCI devices have been suspended. In step 3, the IRQ 34 affinity should be modified from CPU31 to CPU0, but in fact it is not. In __pci_write_msi_msg(), if the device is already in low power state, the low level MSI message entry will not be updated but cached. During the device restore process after a normal suspend/resume, pci_restore_msi_state() writes the cached MSI back to the hardware. But this is not the case for hibernation. pci_restore_msi_state() is not currently called in pci_pm_thaw_noirq(), although pci_save_state() has saved the necessary PCI cached information in pci_pm_freeze_noirq(). Restore the PCI status for the device during hibernation. Otherwise the status might be lost across hibernation (for example, settings for MSI, MSI-X, ATS, ACS, IOV, etc.), which might cause problems during hibernation. Suggested-by: Ying Huang <ying.huang@intel.com> Suggested-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Signed-off-by: Chen Yu <yu.c.chen@intel.com> [bhelgaas: changelog] Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> Reviewed-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Cc: stable@vger.kernel.org Cc: Len Brown <len.brown@intel.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Rui Zhang <rui.zhang@intel.com> Cc: Ying Huang <ying.huang@intel.com>
2017-05-25 16:49:07 +08:00
pci_restore_state(pci_dev);
PCI/PM: Always return devices to D0 when thawing pci_pm_thaw_noirq() is supposed to return the device to D0 and restore its configuration registers, but previously it only did that for devices whose drivers implemented the new power management ops. Hibernation, e.g., via "echo disk > /sys/power/state", involves freezing devices, creating a hibernation image, thawing devices, writing the image, and powering off. The fact that thawing did not return devices with legacy power management to D0 caused errors, e.g., in this path: pci_pm_thaw_noirq if (pci_has_legacy_pm_support(pci_dev)) # true for Mellanox VF driver return pci_legacy_resume_early(dev) # ... legacy PM skips the rest pci_set_power_state(pci_dev, PCI_D0) pci_restore_state(pci_dev) pci_pm_thaw if (pci_has_legacy_pm_support(pci_dev)) pci_legacy_resume drv->resume mlx4_resume ... pci_enable_msix_range ... if (dev->current_state != PCI_D0) # <--- return -EINVAL; which caused these warnings: mlx4_core a6d1:00:02.0: INTx is not supported in multi-function mode, aborting PM: dpm_run_callback(): pci_pm_thaw+0x0/0xd7 returns -95 PM: Device a6d1:00:02.0 failed to thaw: error -95 Return devices to D0 and restore config registers for all devices, not just those whose drivers support new power management. [bhelgaas: also call pci_restore_state() before pci_legacy_resume_early(), update comment, add stable tag, commit log] Link: https://lore.kernel.org/r/KU1P153MB016637CAEAD346F0AA8E3801BFAD0@KU1P153MB0166.APCP153.PROD.OUTLOOK.COM Signed-off-by: Dexuan Cui <decui@microsoft.com> Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> Reviewed-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Cc: stable@vger.kernel.org # v4.13+
2019-08-14 09:06:55 +08:00
if (pci_has_legacy_pm_support(pci_dev))
return 0;
PCI/PM: Always return devices to D0 when thawing pci_pm_thaw_noirq() is supposed to return the device to D0 and restore its configuration registers, but previously it only did that for devices whose drivers implemented the new power management ops. Hibernation, e.g., via "echo disk > /sys/power/state", involves freezing devices, creating a hibernation image, thawing devices, writing the image, and powering off. The fact that thawing did not return devices with legacy power management to D0 caused errors, e.g., in this path: pci_pm_thaw_noirq if (pci_has_legacy_pm_support(pci_dev)) # true for Mellanox VF driver return pci_legacy_resume_early(dev) # ... legacy PM skips the rest pci_set_power_state(pci_dev, PCI_D0) pci_restore_state(pci_dev) pci_pm_thaw if (pci_has_legacy_pm_support(pci_dev)) pci_legacy_resume drv->resume mlx4_resume ... pci_enable_msix_range ... if (dev->current_state != PCI_D0) # <--- return -EINVAL; which caused these warnings: mlx4_core a6d1:00:02.0: INTx is not supported in multi-function mode, aborting PM: dpm_run_callback(): pci_pm_thaw+0x0/0xd7 returns -95 PM: Device a6d1:00:02.0 failed to thaw: error -95 Return devices to D0 and restore config registers for all devices, not just those whose drivers support new power management. [bhelgaas: also call pci_restore_state() before pci_legacy_resume_early(), update comment, add stable tag, commit log] Link: https://lore.kernel.org/r/KU1P153MB016637CAEAD346F0AA8E3801BFAD0@KU1P153MB0166.APCP153.PROD.OUTLOOK.COM Signed-off-by: Dexuan Cui <decui@microsoft.com> Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> Reviewed-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Cc: stable@vger.kernel.org # v4.13+
2019-08-14 09:06:55 +08:00
if (pm && pm->thaw_noirq)
return pm->thaw_noirq(dev);
return 0;
}
static int pci_pm_thaw(struct device *dev)
{
struct pci_dev *pci_dev = to_pci_dev(dev);
const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
int error = 0;
if (pci_has_legacy_pm_support(pci_dev))
return pci_legacy_resume(dev);
PCI PM: make the PM core more careful with drivers using the new PM framework Currently, the PM core always attempts to manage devices with drivers that use the new PM framework. In particular, it attempts to disable the devices (which is unnecessary), to save their state (which may be undesirable if the driver has done that already) and to put them into low power states (again, this may be undesirable if the driver has already put the device into a low power state). That need not be the right thing to do, so make the core be more careful in this respect. Generally, there are the following categories of devices to consider: * bridge devices without drivers * non-bridge devices without drivers * bridge devices with drivers * non-bridge devices with drivers and each of them should be handled differently. For bridge devices without drivers the PCI PM core will save their state on suspend and restore it (early) during resume, after putting them into D0 if necessary. It will not attempt to do anything else to these devices. For non-bridge devices without drivers the PCI PM core will disable them and save their state on suspend. During resume, it will put them into D0, if necessary, restore their state (early) and reenable them. For bridge devices with drivers the PCI PM core will only save their state on suspend if the driver hasn't done that already. Still, the core will restore their state (early) during resume, after putting them into D0, if necessary. For non-bridge devices with drivers the PCI PM core will only save their state on suspend if the driver hasn't done that already. Also, if the state of the device hasn't been saved by the driver, the core will attempt to put the device into a low power state. During resume the core will restore the state of the device (early), after putting it into D0, if necessary. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2009-02-04 09:09:07 +08:00
if (pm) {
if (pm->thaw)
error = pm->thaw(dev);
} else {
pci_pm_reenable_device(pci_dev);
}
pci_dev->state_saved = false;
return error;
}
static int pci_pm_poweroff(struct device *dev)
{
struct pci_dev *pci_dev = to_pci_dev(dev);
const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
if (pci_has_legacy_pm_support(pci_dev))
return pci_legacy_suspend(dev, PMSG_HIBERNATE);
PCI PM: make the PM core more careful with drivers using the new PM framework Currently, the PM core always attempts to manage devices with drivers that use the new PM framework. In particular, it attempts to disable the devices (which is unnecessary), to save their state (which may be undesirable if the driver has done that already) and to put them into low power states (again, this may be undesirable if the driver has already put the device into a low power state). That need not be the right thing to do, so make the core be more careful in this respect. Generally, there are the following categories of devices to consider: * bridge devices without drivers * non-bridge devices without drivers * bridge devices with drivers * non-bridge devices with drivers and each of them should be handled differently. For bridge devices without drivers the PCI PM core will save their state on suspend and restore it (early) during resume, after putting them into D0 if necessary. It will not attempt to do anything else to these devices. For non-bridge devices without drivers the PCI PM core will disable them and save their state on suspend. During resume, it will put them into D0, if necessary, restore their state (early) and reenable them. For bridge devices with drivers the PCI PM core will only save their state on suspend if the driver hasn't done that already. Still, the core will restore their state (early) during resume, after putting them into D0, if necessary. For non-bridge devices with drivers the PCI PM core will only save their state on suspend if the driver hasn't done that already. Also, if the state of the device hasn't been saved by the driver, the core will attempt to put the device into a low power state. During resume the core will restore the state of the device (early), after putting it into D0, if necessary. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2009-02-04 09:09:07 +08:00
if (!pm) {
pci_pm_default_suspend(pci_dev);
PCI / PM: Take SMART_SUSPEND driver flag into account Make the PCI bus type take DPM_FLAG_SMART_SUSPEND into account in its system-wide PM callbacks and make sure that all code that should not run in parallel with pci_pm_runtime_resume() is executed in the "late" phases of system suspend, freeze and poweroff transitions. [Note that the pm_runtime_suspended() check in pci_dev_keep_suspended() is an optimization, because if is not passed, all of the subsequent checks may be skipped and some of them are much more overhead in general.] Also use the observation that if the device is in runtime suspend at the beginning of the "late" phase of a system-wide suspend-like transition, its state cannot change going forward (runtime PM is disabled for it at that time) until the transition is over and the subsequent system-wide PM callbacks should be skipped for it (as they generally assume the device to not be suspended), so add checks for that in pci_pm_suspend_late/noirq(), pci_pm_freeze_late/noirq() and pci_pm_poweroff_late/noirq(). Moreover, if pci_pm_resume_noirq() or pci_pm_restore_noirq() is called during the subsequent system-wide resume transition and if the device was left in runtime suspend previously, its runtime PM status needs to be changed to "active" as it is going to be put into the full-power state, so add checks for that too to these functions. In turn, if pci_pm_thaw_noirq() runs after the device has been left in runtime suspend, the subsequent "thaw" callbacks need to be skipped for it (as they may not work correctly with a suspended device), so set the power.direct_complete flag for the device then to make the PM core skip those callbacks. In addition to the above add a core helper for checking if DPM_FLAG_SMART_SUSPEND is set and the device runtime PM status is "suspended" at the same time, which is done quite often in the new code (and will be done elsewhere going forward too). Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Acked-by: Bjorn Helgaas <bhelgaas@google.com>
2017-10-26 18:12:22 +08:00
return 0;
PCI PM: make the PM core more careful with drivers using the new PM framework Currently, the PM core always attempts to manage devices with drivers that use the new PM framework. In particular, it attempts to disable the devices (which is unnecessary), to save their state (which may be undesirable if the driver has done that already) and to put them into low power states (again, this may be undesirable if the driver has already put the device into a low power state). That need not be the right thing to do, so make the core be more careful in this respect. Generally, there are the following categories of devices to consider: * bridge devices without drivers * non-bridge devices without drivers * bridge devices with drivers * non-bridge devices with drivers and each of them should be handled differently. For bridge devices without drivers the PCI PM core will save their state on suspend and restore it (early) during resume, after putting them into D0 if necessary. It will not attempt to do anything else to these devices. For non-bridge devices without drivers the PCI PM core will disable them and save their state on suspend. During resume, it will put them into D0, if necessary, restore their state (early) and reenable them. For bridge devices with drivers the PCI PM core will only save their state on suspend if the driver hasn't done that already. Still, the core will restore their state (early) during resume, after putting them into D0, if necessary. For non-bridge devices with drivers the PCI PM core will only save their state on suspend if the driver hasn't done that already. Also, if the state of the device hasn't been saved by the driver, the core will attempt to put the device into a low power state. During resume the core will restore the state of the device (early), after putting it into D0, if necessary. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2009-02-04 09:09:07 +08:00
}
/* The reason to do that is the same as in pci_pm_suspend(). */
PCI / PM: Take SMART_SUSPEND driver flag into account Make the PCI bus type take DPM_FLAG_SMART_SUSPEND into account in its system-wide PM callbacks and make sure that all code that should not run in parallel with pci_pm_runtime_resume() is executed in the "late" phases of system suspend, freeze and poweroff transitions. [Note that the pm_runtime_suspended() check in pci_dev_keep_suspended() is an optimization, because if is not passed, all of the subsequent checks may be skipped and some of them are much more overhead in general.] Also use the observation that if the device is in runtime suspend at the beginning of the "late" phase of a system-wide suspend-like transition, its state cannot change going forward (runtime PM is disabled for it at that time) until the transition is over and the subsequent system-wide PM callbacks should be skipped for it (as they generally assume the device to not be suspended), so add checks for that in pci_pm_suspend_late/noirq(), pci_pm_freeze_late/noirq() and pci_pm_poweroff_late/noirq(). Moreover, if pci_pm_resume_noirq() or pci_pm_restore_noirq() is called during the subsequent system-wide resume transition and if the device was left in runtime suspend previously, its runtime PM status needs to be changed to "active" as it is going to be put into the full-power state, so add checks for that too to these functions. In turn, if pci_pm_thaw_noirq() runs after the device has been left in runtime suspend, the subsequent "thaw" callbacks need to be skipped for it (as they may not work correctly with a suspended device), so set the power.direct_complete flag for the device then to make the PM core skip those callbacks. In addition to the above add a core helper for checking if DPM_FLAG_SMART_SUSPEND is set and the device runtime PM status is "suspended" at the same time, which is done quite often in the new code (and will be done elsewhere going forward too). Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Acked-by: Bjorn Helgaas <bhelgaas@google.com>
2017-10-26 18:12:22 +08:00
if (!dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND) ||
pci_dev_need_resume(pci_dev)) {
PCI / PM: Take SMART_SUSPEND driver flag into account Make the PCI bus type take DPM_FLAG_SMART_SUSPEND into account in its system-wide PM callbacks and make sure that all code that should not run in parallel with pci_pm_runtime_resume() is executed in the "late" phases of system suspend, freeze and poweroff transitions. [Note that the pm_runtime_suspended() check in pci_dev_keep_suspended() is an optimization, because if is not passed, all of the subsequent checks may be skipped and some of them are much more overhead in general.] Also use the observation that if the device is in runtime suspend at the beginning of the "late" phase of a system-wide suspend-like transition, its state cannot change going forward (runtime PM is disabled for it at that time) until the transition is over and the subsequent system-wide PM callbacks should be skipped for it (as they generally assume the device to not be suspended), so add checks for that in pci_pm_suspend_late/noirq(), pci_pm_freeze_late/noirq() and pci_pm_poweroff_late/noirq(). Moreover, if pci_pm_resume_noirq() or pci_pm_restore_noirq() is called during the subsequent system-wide resume transition and if the device was left in runtime suspend previously, its runtime PM status needs to be changed to "active" as it is going to be put into the full-power state, so add checks for that too to these functions. In turn, if pci_pm_thaw_noirq() runs after the device has been left in runtime suspend, the subsequent "thaw" callbacks need to be skipped for it (as they may not work correctly with a suspended device), so set the power.direct_complete flag for the device then to make the PM core skip those callbacks. In addition to the above add a core helper for checking if DPM_FLAG_SMART_SUSPEND is set and the device runtime PM status is "suspended" at the same time, which is done quite often in the new code (and will be done elsewhere going forward too). Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Acked-by: Bjorn Helgaas <bhelgaas@google.com>
2017-10-26 18:12:22 +08:00
pm_runtime_resume(dev);
pci_dev->state_saved = false;
} else {
pci_dev_adjust_pme(pci_dev);
}
PCI PM: make the PM core more careful with drivers using the new PM framework Currently, the PM core always attempts to manage devices with drivers that use the new PM framework. In particular, it attempts to disable the devices (which is unnecessary), to save their state (which may be undesirable if the driver has done that already) and to put them into low power states (again, this may be undesirable if the driver has already put the device into a low power state). That need not be the right thing to do, so make the core be more careful in this respect. Generally, there are the following categories of devices to consider: * bridge devices without drivers * non-bridge devices without drivers * bridge devices with drivers * non-bridge devices with drivers and each of them should be handled differently. For bridge devices without drivers the PCI PM core will save their state on suspend and restore it (early) during resume, after putting them into D0 if necessary. It will not attempt to do anything else to these devices. For non-bridge devices without drivers the PCI PM core will disable them and save their state on suspend. During resume, it will put them into D0, if necessary, restore their state (early) and reenable them. For bridge devices with drivers the PCI PM core will only save their state on suspend if the driver hasn't done that already. Still, the core will restore their state (early) during resume, after putting them into D0, if necessary. For non-bridge devices with drivers the PCI PM core will only save their state on suspend if the driver hasn't done that already. Also, if the state of the device hasn't been saved by the driver, the core will attempt to put the device into a low power state. During resume the core will restore the state of the device (early), after putting it into D0, if necessary. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2009-02-04 09:09:07 +08:00
if (pm->poweroff) {
int error;
error = pm->poweroff(dev);
suspend_report_result(pm->poweroff, error);
if (error)
return error;
}
return 0;
}
PCI / PM: Take SMART_SUSPEND driver flag into account Make the PCI bus type take DPM_FLAG_SMART_SUSPEND into account in its system-wide PM callbacks and make sure that all code that should not run in parallel with pci_pm_runtime_resume() is executed in the "late" phases of system suspend, freeze and poweroff transitions. [Note that the pm_runtime_suspended() check in pci_dev_keep_suspended() is an optimization, because if is not passed, all of the subsequent checks may be skipped and some of them are much more overhead in general.] Also use the observation that if the device is in runtime suspend at the beginning of the "late" phase of a system-wide suspend-like transition, its state cannot change going forward (runtime PM is disabled for it at that time) until the transition is over and the subsequent system-wide PM callbacks should be skipped for it (as they generally assume the device to not be suspended), so add checks for that in pci_pm_suspend_late/noirq(), pci_pm_freeze_late/noirq() and pci_pm_poweroff_late/noirq(). Moreover, if pci_pm_resume_noirq() or pci_pm_restore_noirq() is called during the subsequent system-wide resume transition and if the device was left in runtime suspend previously, its runtime PM status needs to be changed to "active" as it is going to be put into the full-power state, so add checks for that too to these functions. In turn, if pci_pm_thaw_noirq() runs after the device has been left in runtime suspend, the subsequent "thaw" callbacks need to be skipped for it (as they may not work correctly with a suspended device), so set the power.direct_complete flag for the device then to make the PM core skip those callbacks. In addition to the above add a core helper for checking if DPM_FLAG_SMART_SUSPEND is set and the device runtime PM status is "suspended" at the same time, which is done quite often in the new code (and will be done elsewhere going forward too). Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Acked-by: Bjorn Helgaas <bhelgaas@google.com>
2017-10-26 18:12:22 +08:00
static int pci_pm_poweroff_late(struct device *dev)
{
if (dev_pm_skip_suspend(dev))
PCI / PM: Take SMART_SUSPEND driver flag into account Make the PCI bus type take DPM_FLAG_SMART_SUSPEND into account in its system-wide PM callbacks and make sure that all code that should not run in parallel with pci_pm_runtime_resume() is executed in the "late" phases of system suspend, freeze and poweroff transitions. [Note that the pm_runtime_suspended() check in pci_dev_keep_suspended() is an optimization, because if is not passed, all of the subsequent checks may be skipped and some of them are much more overhead in general.] Also use the observation that if the device is in runtime suspend at the beginning of the "late" phase of a system-wide suspend-like transition, its state cannot change going forward (runtime PM is disabled for it at that time) until the transition is over and the subsequent system-wide PM callbacks should be skipped for it (as they generally assume the device to not be suspended), so add checks for that in pci_pm_suspend_late/noirq(), pci_pm_freeze_late/noirq() and pci_pm_poweroff_late/noirq(). Moreover, if pci_pm_resume_noirq() or pci_pm_restore_noirq() is called during the subsequent system-wide resume transition and if the device was left in runtime suspend previously, its runtime PM status needs to be changed to "active" as it is going to be put into the full-power state, so add checks for that too to these functions. In turn, if pci_pm_thaw_noirq() runs after the device has been left in runtime suspend, the subsequent "thaw" callbacks need to be skipped for it (as they may not work correctly with a suspended device), so set the power.direct_complete flag for the device then to make the PM core skip those callbacks. In addition to the above add a core helper for checking if DPM_FLAG_SMART_SUSPEND is set and the device runtime PM status is "suspended" at the same time, which is done quite often in the new code (and will be done elsewhere going forward too). Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Acked-by: Bjorn Helgaas <bhelgaas@google.com>
2017-10-26 18:12:22 +08:00
return 0;
PCI / PM: Take SMART_SUSPEND driver flag into account Make the PCI bus type take DPM_FLAG_SMART_SUSPEND into account in its system-wide PM callbacks and make sure that all code that should not run in parallel with pci_pm_runtime_resume() is executed in the "late" phases of system suspend, freeze and poweroff transitions. [Note that the pm_runtime_suspended() check in pci_dev_keep_suspended() is an optimization, because if is not passed, all of the subsequent checks may be skipped and some of them are much more overhead in general.] Also use the observation that if the device is in runtime suspend at the beginning of the "late" phase of a system-wide suspend-like transition, its state cannot change going forward (runtime PM is disabled for it at that time) until the transition is over and the subsequent system-wide PM callbacks should be skipped for it (as they generally assume the device to not be suspended), so add checks for that in pci_pm_suspend_late/noirq(), pci_pm_freeze_late/noirq() and pci_pm_poweroff_late/noirq(). Moreover, if pci_pm_resume_noirq() or pci_pm_restore_noirq() is called during the subsequent system-wide resume transition and if the device was left in runtime suspend previously, its runtime PM status needs to be changed to "active" as it is going to be put into the full-power state, so add checks for that too to these functions. In turn, if pci_pm_thaw_noirq() runs after the device has been left in runtime suspend, the subsequent "thaw" callbacks need to be skipped for it (as they may not work correctly with a suspended device), so set the power.direct_complete flag for the device then to make the PM core skip those callbacks. In addition to the above add a core helper for checking if DPM_FLAG_SMART_SUSPEND is set and the device runtime PM status is "suspended" at the same time, which is done quite often in the new code (and will be done elsewhere going forward too). Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Acked-by: Bjorn Helgaas <bhelgaas@google.com>
2017-10-26 18:12:22 +08:00
pci_fixup_device(pci_fixup_suspend, to_pci_dev(dev));
return pm_generic_poweroff_late(dev);
}
static int pci_pm_poweroff_noirq(struct device *dev)
{
struct pci_dev *pci_dev = to_pci_dev(dev);
const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
if (dev_pm_skip_suspend(dev))
PCI / PM: Take SMART_SUSPEND driver flag into account Make the PCI bus type take DPM_FLAG_SMART_SUSPEND into account in its system-wide PM callbacks and make sure that all code that should not run in parallel with pci_pm_runtime_resume() is executed in the "late" phases of system suspend, freeze and poweroff transitions. [Note that the pm_runtime_suspended() check in pci_dev_keep_suspended() is an optimization, because if is not passed, all of the subsequent checks may be skipped and some of them are much more overhead in general.] Also use the observation that if the device is in runtime suspend at the beginning of the "late" phase of a system-wide suspend-like transition, its state cannot change going forward (runtime PM is disabled for it at that time) until the transition is over and the subsequent system-wide PM callbacks should be skipped for it (as they generally assume the device to not be suspended), so add checks for that in pci_pm_suspend_late/noirq(), pci_pm_freeze_late/noirq() and pci_pm_poweroff_late/noirq(). Moreover, if pci_pm_resume_noirq() or pci_pm_restore_noirq() is called during the subsequent system-wide resume transition and if the device was left in runtime suspend previously, its runtime PM status needs to be changed to "active" as it is going to be put into the full-power state, so add checks for that too to these functions. In turn, if pci_pm_thaw_noirq() runs after the device has been left in runtime suspend, the subsequent "thaw" callbacks need to be skipped for it (as they may not work correctly with a suspended device), so set the power.direct_complete flag for the device then to make the PM core skip those callbacks. In addition to the above add a core helper for checking if DPM_FLAG_SMART_SUSPEND is set and the device runtime PM status is "suspended" at the same time, which is done quite often in the new code (and will be done elsewhere going forward too). Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Acked-by: Bjorn Helgaas <bhelgaas@google.com>
2017-10-26 18:12:22 +08:00
return 0;
if (pci_has_legacy_pm_support(pci_dev))
return pci_legacy_suspend_late(dev, PMSG_HIBERNATE);
if (!pm) {
pci_fixup_device(pci_fixup_suspend_late, pci_dev);
return 0;
}
if (pm->poweroff_noirq) {
int error;
error = pm->poweroff_noirq(dev);
suspend_report_result(pm->poweroff_noirq, error);
if (error)
return error;
}
if (!pci_dev->state_saved && !pci_has_subordinate(pci_dev))
pci_prepare_to_sleep(pci_dev);
/*
* The reason for doing this here is the same as for the analogous code
* in pci_pm_suspend_noirq().
*/
if (pci_dev->class == PCI_CLASS_SERIAL_USB_EHCI)
pci_write_config_word(pci_dev, PCI_COMMAND, 0);
pci_fixup_device(pci_fixup_suspend_late, pci_dev);
return 0;
}
static int pci_pm_restore_noirq(struct device *dev)
{
struct pci_dev *pci_dev = to_pci_dev(dev);
const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
pci_pm_default_resume_early(pci_dev);
pci_fixup_device(pci_fixup_resume_early, pci_dev);
if (pci_has_legacy_pm_support(pci_dev))
return 0;
if (pm && pm->restore_noirq)
return pm->restore_noirq(dev);
return 0;
}
static int pci_pm_restore(struct device *dev)
{
struct pci_dev *pci_dev = to_pci_dev(dev);
const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
/*
* This is necessary for the hibernation error path in which restore is
* called without restoring the standard config registers of the device.
*/
if (pci_dev->state_saved)
pci_restore_standard_config(pci_dev);
if (pci_has_legacy_pm_support(pci_dev))
return pci_legacy_resume(dev);
PCI PM: make the PM core more careful with drivers using the new PM framework Currently, the PM core always attempts to manage devices with drivers that use the new PM framework. In particular, it attempts to disable the devices (which is unnecessary), to save their state (which may be undesirable if the driver has done that already) and to put them into low power states (again, this may be undesirable if the driver has already put the device into a low power state). That need not be the right thing to do, so make the core be more careful in this respect. Generally, there are the following categories of devices to consider: * bridge devices without drivers * non-bridge devices without drivers * bridge devices with drivers * non-bridge devices with drivers and each of them should be handled differently. For bridge devices without drivers the PCI PM core will save their state on suspend and restore it (early) during resume, after putting them into D0 if necessary. It will not attempt to do anything else to these devices. For non-bridge devices without drivers the PCI PM core will disable them and save their state on suspend. During resume, it will put them into D0, if necessary, restore their state (early) and reenable them. For bridge devices with drivers the PCI PM core will only save their state on suspend if the driver hasn't done that already. Still, the core will restore their state (early) during resume, after putting them into D0, if necessary. For non-bridge devices with drivers the PCI PM core will only save their state on suspend if the driver hasn't done that already. Also, if the state of the device hasn't been saved by the driver, the core will attempt to put the device into a low power state. During resume the core will restore the state of the device (early), after putting it into D0, if necessary. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2009-02-04 09:09:07 +08:00
pci_pm_default_resume(pci_dev);
PCI PM: make the PM core more careful with drivers using the new PM framework Currently, the PM core always attempts to manage devices with drivers that use the new PM framework. In particular, it attempts to disable the devices (which is unnecessary), to save their state (which may be undesirable if the driver has done that already) and to put them into low power states (again, this may be undesirable if the driver has already put the device into a low power state). That need not be the right thing to do, so make the core be more careful in this respect. Generally, there are the following categories of devices to consider: * bridge devices without drivers * non-bridge devices without drivers * bridge devices with drivers * non-bridge devices with drivers and each of them should be handled differently. For bridge devices without drivers the PCI PM core will save their state on suspend and restore it (early) during resume, after putting them into D0 if necessary. It will not attempt to do anything else to these devices. For non-bridge devices without drivers the PCI PM core will disable them and save their state on suspend. During resume, it will put them into D0, if necessary, restore their state (early) and reenable them. For bridge devices with drivers the PCI PM core will only save their state on suspend if the driver hasn't done that already. Still, the core will restore their state (early) during resume, after putting them into D0, if necessary. For non-bridge devices with drivers the PCI PM core will only save their state on suspend if the driver hasn't done that already. Also, if the state of the device hasn't been saved by the driver, the core will attempt to put the device into a low power state. During resume the core will restore the state of the device (early), after putting it into D0, if necessary. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2009-02-04 09:09:07 +08:00
if (pm) {
if (pm->restore)
return pm->restore(dev);
PCI PM: make the PM core more careful with drivers using the new PM framework Currently, the PM core always attempts to manage devices with drivers that use the new PM framework. In particular, it attempts to disable the devices (which is unnecessary), to save their state (which may be undesirable if the driver has done that already) and to put them into low power states (again, this may be undesirable if the driver has already put the device into a low power state). That need not be the right thing to do, so make the core be more careful in this respect. Generally, there are the following categories of devices to consider: * bridge devices without drivers * non-bridge devices without drivers * bridge devices with drivers * non-bridge devices with drivers and each of them should be handled differently. For bridge devices without drivers the PCI PM core will save their state on suspend and restore it (early) during resume, after putting them into D0 if necessary. It will not attempt to do anything else to these devices. For non-bridge devices without drivers the PCI PM core will disable them and save their state on suspend. During resume, it will put them into D0, if necessary, restore their state (early) and reenable them. For bridge devices with drivers the PCI PM core will only save their state on suspend if the driver hasn't done that already. Still, the core will restore their state (early) during resume, after putting them into D0, if necessary. For non-bridge devices with drivers the PCI PM core will only save their state on suspend if the driver hasn't done that already. Also, if the state of the device hasn't been saved by the driver, the core will attempt to put the device into a low power state. During resume the core will restore the state of the device (early), after putting it into D0, if necessary. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2009-02-04 09:09:07 +08:00
} else {
pci_pm_reenable_device(pci_dev);
}
return 0;
}
#else /* !CONFIG_HIBERNATE_CALLBACKS */
#define pci_pm_freeze NULL
#define pci_pm_freeze_noirq NULL
#define pci_pm_thaw NULL
#define pci_pm_thaw_noirq NULL
#define pci_pm_poweroff NULL
PCI / PM: Take SMART_SUSPEND driver flag into account Make the PCI bus type take DPM_FLAG_SMART_SUSPEND into account in its system-wide PM callbacks and make sure that all code that should not run in parallel with pci_pm_runtime_resume() is executed in the "late" phases of system suspend, freeze and poweroff transitions. [Note that the pm_runtime_suspended() check in pci_dev_keep_suspended() is an optimization, because if is not passed, all of the subsequent checks may be skipped and some of them are much more overhead in general.] Also use the observation that if the device is in runtime suspend at the beginning of the "late" phase of a system-wide suspend-like transition, its state cannot change going forward (runtime PM is disabled for it at that time) until the transition is over and the subsequent system-wide PM callbacks should be skipped for it (as they generally assume the device to not be suspended), so add checks for that in pci_pm_suspend_late/noirq(), pci_pm_freeze_late/noirq() and pci_pm_poweroff_late/noirq(). Moreover, if pci_pm_resume_noirq() or pci_pm_restore_noirq() is called during the subsequent system-wide resume transition and if the device was left in runtime suspend previously, its runtime PM status needs to be changed to "active" as it is going to be put into the full-power state, so add checks for that too to these functions. In turn, if pci_pm_thaw_noirq() runs after the device has been left in runtime suspend, the subsequent "thaw" callbacks need to be skipped for it (as they may not work correctly with a suspended device), so set the power.direct_complete flag for the device then to make the PM core skip those callbacks. In addition to the above add a core helper for checking if DPM_FLAG_SMART_SUSPEND is set and the device runtime PM status is "suspended" at the same time, which is done quite often in the new code (and will be done elsewhere going forward too). Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Acked-by: Bjorn Helgaas <bhelgaas@google.com>
2017-10-26 18:12:22 +08:00
#define pci_pm_poweroff_late NULL
#define pci_pm_poweroff_noirq NULL
#define pci_pm_restore NULL
#define pci_pm_restore_noirq NULL
#endif /* !CONFIG_HIBERNATE_CALLBACKS */
#ifdef CONFIG_PM
static int pci_pm_runtime_suspend(struct device *dev)
{
struct pci_dev *pci_dev = to_pci_dev(dev);
const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
pci_power_t prev = pci_dev->current_state;
int error;
/*
PCI: Restore config space on runtime resume despite being unbound We leave PCI devices not bound to a driver in D0 during runtime suspend. But they may have a parent which is bound and can be transitioned to D3cold at runtime. Once the parent goes to D3cold, the unbound child may go to D3cold as well. When the child goes to D3cold, its internal state, including configuration of BARs, MSI, ASPM, MPS, etc., is lost. One example are recent hybrid graphics laptops which cut power to the discrete GPU when the root port above it goes to ACPI power state D3. Users may provoke this by unbinding the GPU driver and allowing runtime PM on the GPU via sysfs: The PM core will then treat the GPU as "suspended", which in turn allows the root port to runtime suspend, causing the power resources listed in its _PR3 object to be powered off. The GPU's BARs will be uninitialized when a driver later probes it. Another example are hybrid graphics laptops where the GPU itself (rather than the root port) is capable of runtime suspending to D3cold. If the GPU's integrated HDA controller is not bound and the GPU's driver decides to runtime suspend to D3cold, the HDA controller's BARs will be uninitialized when a driver later probes it. Fix by saving and restoring config space over a runtime suspend cycle even if the device is not bound. Acked-by: Bjorn Helgaas <bhelgaas@google.com> Tested-by: Peter Wu <peter@lekensteyn.nl> # Nvidia Optimus Tested-by: Lukas Wunner <lukas@wunner.de> # MacBook Pro Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> [lukas: add commit message, bikeshed code comments for clarity] Signed-off-by: Lukas Wunner <lukas@wunner.de> Link: https://patchwork.freedesktop.org/patch/msgid/92fb6e6ae2730915eb733c08e2f76c6a313e3860.1520068884.git.lukas@wunner.de
2018-03-03 17:53:24 +08:00
* If pci_dev->driver is not set (unbound), we leave the device in D0,
* but it may go to D3cold when the bridge above it runtime suspends.
* Save its config space in case that happens.
*/
PCI: Restore config space on runtime resume despite being unbound We leave PCI devices not bound to a driver in D0 during runtime suspend. But they may have a parent which is bound and can be transitioned to D3cold at runtime. Once the parent goes to D3cold, the unbound child may go to D3cold as well. When the child goes to D3cold, its internal state, including configuration of BARs, MSI, ASPM, MPS, etc., is lost. One example are recent hybrid graphics laptops which cut power to the discrete GPU when the root port above it goes to ACPI power state D3. Users may provoke this by unbinding the GPU driver and allowing runtime PM on the GPU via sysfs: The PM core will then treat the GPU as "suspended", which in turn allows the root port to runtime suspend, causing the power resources listed in its _PR3 object to be powered off. The GPU's BARs will be uninitialized when a driver later probes it. Another example are hybrid graphics laptops where the GPU itself (rather than the root port) is capable of runtime suspending to D3cold. If the GPU's integrated HDA controller is not bound and the GPU's driver decides to runtime suspend to D3cold, the HDA controller's BARs will be uninitialized when a driver later probes it. Fix by saving and restoring config space over a runtime suspend cycle even if the device is not bound. Acked-by: Bjorn Helgaas <bhelgaas@google.com> Tested-by: Peter Wu <peter@lekensteyn.nl> # Nvidia Optimus Tested-by: Lukas Wunner <lukas@wunner.de> # MacBook Pro Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> [lukas: add commit message, bikeshed code comments for clarity] Signed-off-by: Lukas Wunner <lukas@wunner.de> Link: https://patchwork.freedesktop.org/patch/msgid/92fb6e6ae2730915eb733c08e2f76c6a313e3860.1520068884.git.lukas@wunner.de
2018-03-03 17:53:24 +08:00
if (!pci_dev->driver) {
pci_save_state(pci_dev);
return 0;
PCI: Restore config space on runtime resume despite being unbound We leave PCI devices not bound to a driver in D0 during runtime suspend. But they may have a parent which is bound and can be transitioned to D3cold at runtime. Once the parent goes to D3cold, the unbound child may go to D3cold as well. When the child goes to D3cold, its internal state, including configuration of BARs, MSI, ASPM, MPS, etc., is lost. One example are recent hybrid graphics laptops which cut power to the discrete GPU when the root port above it goes to ACPI power state D3. Users may provoke this by unbinding the GPU driver and allowing runtime PM on the GPU via sysfs: The PM core will then treat the GPU as "suspended", which in turn allows the root port to runtime suspend, causing the power resources listed in its _PR3 object to be powered off. The GPU's BARs will be uninitialized when a driver later probes it. Another example are hybrid graphics laptops where the GPU itself (rather than the root port) is capable of runtime suspending to D3cold. If the GPU's integrated HDA controller is not bound and the GPU's driver decides to runtime suspend to D3cold, the HDA controller's BARs will be uninitialized when a driver later probes it. Fix by saving and restoring config space over a runtime suspend cycle even if the device is not bound. Acked-by: Bjorn Helgaas <bhelgaas@google.com> Tested-by: Peter Wu <peter@lekensteyn.nl> # Nvidia Optimus Tested-by: Lukas Wunner <lukas@wunner.de> # MacBook Pro Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> [lukas: add commit message, bikeshed code comments for clarity] Signed-off-by: Lukas Wunner <lukas@wunner.de> Link: https://patchwork.freedesktop.org/patch/msgid/92fb6e6ae2730915eb733c08e2f76c6a313e3860.1520068884.git.lukas@wunner.de
2018-03-03 17:53:24 +08:00
}
pci_dev->state_saved = false;
PCI / PM: Allow runtime PM without callback functions a9c8088c7988 ("i2c: i801: Don't restore config registers on runtime PM") nullified the runtime PM suspend/resume callback pointers while keeping the runtime PM enabled. This caused the SMBus PCI device to stay in D0 with /sys/devices/.../power/runtime_status showing "error" when the runtime PM framework attempted to autosuspend the device. This is due to PCI bus runtime PM, which checks for driver runtime PM callbacks and returns -ENOSYS if they are not set. Since i2c-i801.c doesn't need to do anything device-specific for runtime PM, Jean Delvare proposed this be fixed in the PCI core rather than adding dummy runtime PM callback functions in the PCI drivers. Change pci_pm_runtime_suspend()/pci_pm_runtime_resume() so they allow changing the PCI device power state during runtime PM transitions even if the driver supplies no runtime PM callbacks. This fixes the runtime PM regression on i2c-i801.c. It is not obvious why the code previously required the runtime PM callbacks. The test has been there since the code was introduced by 6cbf82148ff2 ("PCI PM: Run-time callbacks for PCI bus type"). On the other hand, a similar change was done to generic runtime PM callbacks in 05aa55dddb9e ("PM / Runtime: Lenient generic runtime pm callbacks"). Fixes: a9c8088c7988 ("i2c: i801: Don't restore config registers on runtime PM") Reported-by: Mika Westerberg <mika.westerberg@linux.intel.com> Signed-off-by: Jarkko Nikula <jarkko.nikula@linux.intel.com> Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> Reviewed-by: Jean Delvare <jdelvare@suse.de> Reviewed-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Cc: stable@vger.kernel.org # v4.18+
2018-10-23 19:45:52 +08:00
if (pm && pm->runtime_suspend) {
error = pm->runtime_suspend(dev);
/*
* -EBUSY and -EAGAIN is used to request the runtime PM core
* to schedule a new suspend, so log the event only with debug
* log level.
*/
PCI / PM: Allow runtime PM without callback functions a9c8088c7988 ("i2c: i801: Don't restore config registers on runtime PM") nullified the runtime PM suspend/resume callback pointers while keeping the runtime PM enabled. This caused the SMBus PCI device to stay in D0 with /sys/devices/.../power/runtime_status showing "error" when the runtime PM framework attempted to autosuspend the device. This is due to PCI bus runtime PM, which checks for driver runtime PM callbacks and returns -ENOSYS if they are not set. Since i2c-i801.c doesn't need to do anything device-specific for runtime PM, Jean Delvare proposed this be fixed in the PCI core rather than adding dummy runtime PM callback functions in the PCI drivers. Change pci_pm_runtime_suspend()/pci_pm_runtime_resume() so they allow changing the PCI device power state during runtime PM transitions even if the driver supplies no runtime PM callbacks. This fixes the runtime PM regression on i2c-i801.c. It is not obvious why the code previously required the runtime PM callbacks. The test has been there since the code was introduced by 6cbf82148ff2 ("PCI PM: Run-time callbacks for PCI bus type"). On the other hand, a similar change was done to generic runtime PM callbacks in 05aa55dddb9e ("PM / Runtime: Lenient generic runtime pm callbacks"). Fixes: a9c8088c7988 ("i2c: i801: Don't restore config registers on runtime PM") Reported-by: Mika Westerberg <mika.westerberg@linux.intel.com> Signed-off-by: Jarkko Nikula <jarkko.nikula@linux.intel.com> Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> Reviewed-by: Jean Delvare <jdelvare@suse.de> Reviewed-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Cc: stable@vger.kernel.org # v4.18+
2018-10-23 19:45:52 +08:00
if (error == -EBUSY || error == -EAGAIN) {
pci_dbg(pci_dev, "can't suspend now (%ps returned %d)\n",
pm->runtime_suspend, error);
PCI / PM: Allow runtime PM without callback functions a9c8088c7988 ("i2c: i801: Don't restore config registers on runtime PM") nullified the runtime PM suspend/resume callback pointers while keeping the runtime PM enabled. This caused the SMBus PCI device to stay in D0 with /sys/devices/.../power/runtime_status showing "error" when the runtime PM framework attempted to autosuspend the device. This is due to PCI bus runtime PM, which checks for driver runtime PM callbacks and returns -ENOSYS if they are not set. Since i2c-i801.c doesn't need to do anything device-specific for runtime PM, Jean Delvare proposed this be fixed in the PCI core rather than adding dummy runtime PM callback functions in the PCI drivers. Change pci_pm_runtime_suspend()/pci_pm_runtime_resume() so they allow changing the PCI device power state during runtime PM transitions even if the driver supplies no runtime PM callbacks. This fixes the runtime PM regression on i2c-i801.c. It is not obvious why the code previously required the runtime PM callbacks. The test has been there since the code was introduced by 6cbf82148ff2 ("PCI PM: Run-time callbacks for PCI bus type"). On the other hand, a similar change was done to generic runtime PM callbacks in 05aa55dddb9e ("PM / Runtime: Lenient generic runtime pm callbacks"). Fixes: a9c8088c7988 ("i2c: i801: Don't restore config registers on runtime PM") Reported-by: Mika Westerberg <mika.westerberg@linux.intel.com> Signed-off-by: Jarkko Nikula <jarkko.nikula@linux.intel.com> Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> Reviewed-by: Jean Delvare <jdelvare@suse.de> Reviewed-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Cc: stable@vger.kernel.org # v4.18+
2018-10-23 19:45:52 +08:00
return error;
} else if (error) {
pci_err(pci_dev, "can't suspend (%ps returned %d)\n",
pm->runtime_suspend, error);
PCI / PM: Allow runtime PM without callback functions a9c8088c7988 ("i2c: i801: Don't restore config registers on runtime PM") nullified the runtime PM suspend/resume callback pointers while keeping the runtime PM enabled. This caused the SMBus PCI device to stay in D0 with /sys/devices/.../power/runtime_status showing "error" when the runtime PM framework attempted to autosuspend the device. This is due to PCI bus runtime PM, which checks for driver runtime PM callbacks and returns -ENOSYS if they are not set. Since i2c-i801.c doesn't need to do anything device-specific for runtime PM, Jean Delvare proposed this be fixed in the PCI core rather than adding dummy runtime PM callback functions in the PCI drivers. Change pci_pm_runtime_suspend()/pci_pm_runtime_resume() so they allow changing the PCI device power state during runtime PM transitions even if the driver supplies no runtime PM callbacks. This fixes the runtime PM regression on i2c-i801.c. It is not obvious why the code previously required the runtime PM callbacks. The test has been there since the code was introduced by 6cbf82148ff2 ("PCI PM: Run-time callbacks for PCI bus type"). On the other hand, a similar change was done to generic runtime PM callbacks in 05aa55dddb9e ("PM / Runtime: Lenient generic runtime pm callbacks"). Fixes: a9c8088c7988 ("i2c: i801: Don't restore config registers on runtime PM") Reported-by: Mika Westerberg <mika.westerberg@linux.intel.com> Signed-off-by: Jarkko Nikula <jarkko.nikula@linux.intel.com> Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> Reviewed-by: Jean Delvare <jdelvare@suse.de> Reviewed-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Cc: stable@vger.kernel.org # v4.18+
2018-10-23 19:45:52 +08:00
return error;
}
}
pci_fixup_device(pci_fixup_suspend, pci_dev);
PCI / PM: Allow runtime PM without callback functions a9c8088c7988 ("i2c: i801: Don't restore config registers on runtime PM") nullified the runtime PM suspend/resume callback pointers while keeping the runtime PM enabled. This caused the SMBus PCI device to stay in D0 with /sys/devices/.../power/runtime_status showing "error" when the runtime PM framework attempted to autosuspend the device. This is due to PCI bus runtime PM, which checks for driver runtime PM callbacks and returns -ENOSYS if they are not set. Since i2c-i801.c doesn't need to do anything device-specific for runtime PM, Jean Delvare proposed this be fixed in the PCI core rather than adding dummy runtime PM callback functions in the PCI drivers. Change pci_pm_runtime_suspend()/pci_pm_runtime_resume() so they allow changing the PCI device power state during runtime PM transitions even if the driver supplies no runtime PM callbacks. This fixes the runtime PM regression on i2c-i801.c. It is not obvious why the code previously required the runtime PM callbacks. The test has been there since the code was introduced by 6cbf82148ff2 ("PCI PM: Run-time callbacks for PCI bus type"). On the other hand, a similar change was done to generic runtime PM callbacks in 05aa55dddb9e ("PM / Runtime: Lenient generic runtime pm callbacks"). Fixes: a9c8088c7988 ("i2c: i801: Don't restore config registers on runtime PM") Reported-by: Mika Westerberg <mika.westerberg@linux.intel.com> Signed-off-by: Jarkko Nikula <jarkko.nikula@linux.intel.com> Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> Reviewed-by: Jean Delvare <jdelvare@suse.de> Reviewed-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Cc: stable@vger.kernel.org # v4.18+
2018-10-23 19:45:52 +08:00
if (pm && pm->runtime_suspend
&& !pci_dev->state_saved && pci_dev->current_state != PCI_D0
&& pci_dev->current_state != PCI_UNKNOWN) {
pci_WARN_ONCE(pci_dev, pci_dev->current_state != prev,
"PCI PM: State of device not saved by %pS\n",
pm->runtime_suspend);
return 0;
}
if (!pci_dev->state_saved) {
pci_save_state(pci_dev);
pci_finish_runtime_suspend(pci_dev);
}
return 0;
}
static int pci_pm_runtime_resume(struct device *dev)
{
struct pci_dev *pci_dev = to_pci_dev(dev);
const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
PCI/PM: Add missing link delays required by the PCIe spec Currently Linux does not follow PCIe spec regarding the required delays after reset. A concrete example is a Thunderbolt add-in-card that consists of a PCIe switch and two PCIe endpoints: +-1b.0-[01-6b]----00.0-[02-6b]--+-00.0-[03]----00.0 TBT controller +-01.0-[04-36]-- DS hotplug port +-02.0-[37]----00.0 xHCI controller \-04.0-[38-6b]-- DS hotplug port The root port (1b.0) and the PCIe switch downstream ports are all PCIe Gen3 so they support 8GT/s link speeds. We wait for the PCIe hierarchy to enter D3cold (runtime): pcieport 0000:00:1b.0: power state changed by ACPI to D3cold When it wakes up from D3cold, according to the PCIe 5.0 section 5.8 the PCIe switch is put to reset and its power is re-applied. This means that we must follow the rules in PCIe 5.0 section 6.6.1. For the PCIe Gen3 ports we are dealing with here, the following applies: With a Downstream Port that supports Link speeds greater than 5.0 GT/s, software must wait a minimum of 100 ms after Link training completes before sending a Configuration Request to the device immediately below that Port. Software can determine when Link training completes by polling the Data Link Layer Link Active bit or by setting up an associated interrupt (see Section 6.7.3.3). Translating this into the above topology we would need to do this (DLLLA stands for Data Link Layer Link Active): 0000:00:1b.0: wait for 100 ms after DLLLA is set before access to 0000:01:00.0 0000:02:00.0: wait for 100 ms after DLLLA is set before access to 0000:03:00.0 0000:02:02.0: wait for 100 ms after DLLLA is set before access to 0000:37:00.0 I've instrumented the kernel with some additional logging so we can see the actual delays performed: pcieport 0000:00:1b.0: power state changed by ACPI to D0 pcieport 0000:00:1b.0: waiting for D3cold delay of 100 ms pcieport 0000:00:1b.0: waiting for D3hot delay of 10 ms pcieport 0000:02:01.0: waiting for D3hot delay of 10 ms pcieport 0000:02:04.0: waiting for D3hot delay of 10 ms For the switch upstream port (01:00.0 reachable through 00:1b.0 root port) we wait for 100 ms but not taking into account the DLLLA requirement. We then wait 10 ms for D3hot -> D0 transition of the root port and the two downstream hotplug ports. This means that we deviate from what the spec requires. Performing the same check for system sleep (s2idle) transitions it turns out to be even worse. None of the mandatory delays are performed. If this would be S3 instead of s2idle then according to PCI FW spec 3.2 section 4.6.8. there is a specific _DSM that allows the OS to skip the delays but this platform does not provide the _DSM and does not go to S3 anyway so no firmware is involved that could already handle these delays. On this particular platform these delays are not actually needed because there is an additional delay as part of the ACPI power resource that is used to turn on power to the hierarchy but since that additional delay is not required by any of standards (PCIe, ACPI) it is not present in the Intel Ice Lake, for example where missing the mandatory delays causes pciehp to start tearing down the stack too early (links are not yet trained). Below is an example how it looks like when this happens: pcieport 0000:83:04.0: pciehp: Slot(4): Card not present pcieport 0000:87:04.0: PME# disabled pcieport 0000:83:04.0: pciehp: pciehp_unconfigure_device: domain:bus:dev = 0000:86:00 pcieport 0000:86:00.0: Refused to change power state, currently in D3 pcieport 0000:86:00.0: restoring config space at offset 0x3c (was 0xffffffff, writing 0x201ff) pcieport 0000:86:00.0: restoring config space at offset 0x38 (was 0xffffffff, writing 0x0) ... There is also one reported case (see the bugzilla link below) where the missing delay causes xHCI on a Titan Ridge controller fail to runtime resume when USB-C dock is plugged. This does not involve pciehp but instead the PCI core fails to runtime resume the xHCI device: pcieport 0000:04:02.0: restoring config space at offset 0xc (was 0x10000, writing 0x10020) pcieport 0000:04:02.0: restoring config space at offset 0x4 (was 0x100000, writing 0x100406) xhci_hcd 0000:39:00.0: Refused to change power state, currently in D3 xhci_hcd 0000:39:00.0: restoring config space at offset 0x3c (was 0xffffffff, writing 0x1ff) xhci_hcd 0000:39:00.0: restoring config space at offset 0x38 (was 0xffffffff, writing 0x0) ... Add a new function pci_bridge_wait_for_secondary_bus() that is called on PCI core resume and runtime resume paths accordingly if the bridge entered D3cold (and thus went through reset). This is second attempt to add the missing delays. The previous solution in c2bf1fc212f7 ("PCI: Add missing link delays required by the PCIe spec") was reverted because of two issues it caused: 1. One system become unresponsive after S3 resume due to PME service spinning in pcie_pme_work_fn(). The root port in question reports that the xHCI sent PME but the xHCI device itself does not have PME status set. The PME status bit is never cleared in the root port resulting the indefinite loop in pcie_pme_work_fn(). 2. Slows down resume if the root/downstream port does not support Data Link Layer Active Reporting because pcie_wait_for_link_delay() waits 1100 ms in that case. This version should avoid the above issues because we restrict the delay to happen only if the port went into D3cold. Link: https://lore.kernel.org/linux-pci/SL2P216MB01878BBCD75F21D882AEEA2880C60@SL2P216MB0187.KORP216.PROD.OUTLOOK.COM/ Link: https://bugzilla.kernel.org/show_bug.cgi?id=203885 Link: https://lore.kernel.org/r/20191112091617.70282-3-mika.westerberg@linux.intel.com Reported-by: Kai-Heng Feng <kai.heng.feng@canonical.com> Tested-by: Kai-Heng Feng <kai.heng.feng@canonical.com> Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com> Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
2019-11-12 17:16:17 +08:00
pci_power_t prev_state = pci_dev->current_state;
int error = 0;
/*
PCI: Restore config space on runtime resume despite being unbound We leave PCI devices not bound to a driver in D0 during runtime suspend. But they may have a parent which is bound and can be transitioned to D3cold at runtime. Once the parent goes to D3cold, the unbound child may go to D3cold as well. When the child goes to D3cold, its internal state, including configuration of BARs, MSI, ASPM, MPS, etc., is lost. One example are recent hybrid graphics laptops which cut power to the discrete GPU when the root port above it goes to ACPI power state D3. Users may provoke this by unbinding the GPU driver and allowing runtime PM on the GPU via sysfs: The PM core will then treat the GPU as "suspended", which in turn allows the root port to runtime suspend, causing the power resources listed in its _PR3 object to be powered off. The GPU's BARs will be uninitialized when a driver later probes it. Another example are hybrid graphics laptops where the GPU itself (rather than the root port) is capable of runtime suspending to D3cold. If the GPU's integrated HDA controller is not bound and the GPU's driver decides to runtime suspend to D3cold, the HDA controller's BARs will be uninitialized when a driver later probes it. Fix by saving and restoring config space over a runtime suspend cycle even if the device is not bound. Acked-by: Bjorn Helgaas <bhelgaas@google.com> Tested-by: Peter Wu <peter@lekensteyn.nl> # Nvidia Optimus Tested-by: Lukas Wunner <lukas@wunner.de> # MacBook Pro Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> [lukas: add commit message, bikeshed code comments for clarity] Signed-off-by: Lukas Wunner <lukas@wunner.de> Link: https://patchwork.freedesktop.org/patch/msgid/92fb6e6ae2730915eb733c08e2f76c6a313e3860.1520068884.git.lukas@wunner.de
2018-03-03 17:53:24 +08:00
* Restoring config space is necessary even if the device is not bound
* to a driver because although we left it in D0, it may have gone to
* D3cold when the bridge above it runtime suspended.
*/
PCI: Restore config space on runtime resume despite being unbound We leave PCI devices not bound to a driver in D0 during runtime suspend. But they may have a parent which is bound and can be transitioned to D3cold at runtime. Once the parent goes to D3cold, the unbound child may go to D3cold as well. When the child goes to D3cold, its internal state, including configuration of BARs, MSI, ASPM, MPS, etc., is lost. One example are recent hybrid graphics laptops which cut power to the discrete GPU when the root port above it goes to ACPI power state D3. Users may provoke this by unbinding the GPU driver and allowing runtime PM on the GPU via sysfs: The PM core will then treat the GPU as "suspended", which in turn allows the root port to runtime suspend, causing the power resources listed in its _PR3 object to be powered off. The GPU's BARs will be uninitialized when a driver later probes it. Another example are hybrid graphics laptops where the GPU itself (rather than the root port) is capable of runtime suspending to D3cold. If the GPU's integrated HDA controller is not bound and the GPU's driver decides to runtime suspend to D3cold, the HDA controller's BARs will be uninitialized when a driver later probes it. Fix by saving and restoring config space over a runtime suspend cycle even if the device is not bound. Acked-by: Bjorn Helgaas <bhelgaas@google.com> Tested-by: Peter Wu <peter@lekensteyn.nl> # Nvidia Optimus Tested-by: Lukas Wunner <lukas@wunner.de> # MacBook Pro Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> [lukas: add commit message, bikeshed code comments for clarity] Signed-off-by: Lukas Wunner <lukas@wunner.de> Link: https://patchwork.freedesktop.org/patch/msgid/92fb6e6ae2730915eb733c08e2f76c6a313e3860.1520068884.git.lukas@wunner.de
2018-03-03 17:53:24 +08:00
pci_restore_standard_config(pci_dev);
if (!pci_dev->driver)
return 0;
pci_fixup_device(pci_fixup_resume_early, pci_dev);
pci_pm_default_resume(pci_dev);
PCI/PM: Add missing link delays required by the PCIe spec Currently Linux does not follow PCIe spec regarding the required delays after reset. A concrete example is a Thunderbolt add-in-card that consists of a PCIe switch and two PCIe endpoints: +-1b.0-[01-6b]----00.0-[02-6b]--+-00.0-[03]----00.0 TBT controller +-01.0-[04-36]-- DS hotplug port +-02.0-[37]----00.0 xHCI controller \-04.0-[38-6b]-- DS hotplug port The root port (1b.0) and the PCIe switch downstream ports are all PCIe Gen3 so they support 8GT/s link speeds. We wait for the PCIe hierarchy to enter D3cold (runtime): pcieport 0000:00:1b.0: power state changed by ACPI to D3cold When it wakes up from D3cold, according to the PCIe 5.0 section 5.8 the PCIe switch is put to reset and its power is re-applied. This means that we must follow the rules in PCIe 5.0 section 6.6.1. For the PCIe Gen3 ports we are dealing with here, the following applies: With a Downstream Port that supports Link speeds greater than 5.0 GT/s, software must wait a minimum of 100 ms after Link training completes before sending a Configuration Request to the device immediately below that Port. Software can determine when Link training completes by polling the Data Link Layer Link Active bit or by setting up an associated interrupt (see Section 6.7.3.3). Translating this into the above topology we would need to do this (DLLLA stands for Data Link Layer Link Active): 0000:00:1b.0: wait for 100 ms after DLLLA is set before access to 0000:01:00.0 0000:02:00.0: wait for 100 ms after DLLLA is set before access to 0000:03:00.0 0000:02:02.0: wait for 100 ms after DLLLA is set before access to 0000:37:00.0 I've instrumented the kernel with some additional logging so we can see the actual delays performed: pcieport 0000:00:1b.0: power state changed by ACPI to D0 pcieport 0000:00:1b.0: waiting for D3cold delay of 100 ms pcieport 0000:00:1b.0: waiting for D3hot delay of 10 ms pcieport 0000:02:01.0: waiting for D3hot delay of 10 ms pcieport 0000:02:04.0: waiting for D3hot delay of 10 ms For the switch upstream port (01:00.0 reachable through 00:1b.0 root port) we wait for 100 ms but not taking into account the DLLLA requirement. We then wait 10 ms for D3hot -> D0 transition of the root port and the two downstream hotplug ports. This means that we deviate from what the spec requires. Performing the same check for system sleep (s2idle) transitions it turns out to be even worse. None of the mandatory delays are performed. If this would be S3 instead of s2idle then according to PCI FW spec 3.2 section 4.6.8. there is a specific _DSM that allows the OS to skip the delays but this platform does not provide the _DSM and does not go to S3 anyway so no firmware is involved that could already handle these delays. On this particular platform these delays are not actually needed because there is an additional delay as part of the ACPI power resource that is used to turn on power to the hierarchy but since that additional delay is not required by any of standards (PCIe, ACPI) it is not present in the Intel Ice Lake, for example where missing the mandatory delays causes pciehp to start tearing down the stack too early (links are not yet trained). Below is an example how it looks like when this happens: pcieport 0000:83:04.0: pciehp: Slot(4): Card not present pcieport 0000:87:04.0: PME# disabled pcieport 0000:83:04.0: pciehp: pciehp_unconfigure_device: domain:bus:dev = 0000:86:00 pcieport 0000:86:00.0: Refused to change power state, currently in D3 pcieport 0000:86:00.0: restoring config space at offset 0x3c (was 0xffffffff, writing 0x201ff) pcieport 0000:86:00.0: restoring config space at offset 0x38 (was 0xffffffff, writing 0x0) ... There is also one reported case (see the bugzilla link below) where the missing delay causes xHCI on a Titan Ridge controller fail to runtime resume when USB-C dock is plugged. This does not involve pciehp but instead the PCI core fails to runtime resume the xHCI device: pcieport 0000:04:02.0: restoring config space at offset 0xc (was 0x10000, writing 0x10020) pcieport 0000:04:02.0: restoring config space at offset 0x4 (was 0x100000, writing 0x100406) xhci_hcd 0000:39:00.0: Refused to change power state, currently in D3 xhci_hcd 0000:39:00.0: restoring config space at offset 0x3c (was 0xffffffff, writing 0x1ff) xhci_hcd 0000:39:00.0: restoring config space at offset 0x38 (was 0xffffffff, writing 0x0) ... Add a new function pci_bridge_wait_for_secondary_bus() that is called on PCI core resume and runtime resume paths accordingly if the bridge entered D3cold (and thus went through reset). This is second attempt to add the missing delays. The previous solution in c2bf1fc212f7 ("PCI: Add missing link delays required by the PCIe spec") was reverted because of two issues it caused: 1. One system become unresponsive after S3 resume due to PME service spinning in pcie_pme_work_fn(). The root port in question reports that the xHCI sent PME but the xHCI device itself does not have PME status set. The PME status bit is never cleared in the root port resulting the indefinite loop in pcie_pme_work_fn(). 2. Slows down resume if the root/downstream port does not support Data Link Layer Active Reporting because pcie_wait_for_link_delay() waits 1100 ms in that case. This version should avoid the above issues because we restrict the delay to happen only if the port went into D3cold. Link: https://lore.kernel.org/linux-pci/SL2P216MB01878BBCD75F21D882AEEA2880C60@SL2P216MB0187.KORP216.PROD.OUTLOOK.COM/ Link: https://bugzilla.kernel.org/show_bug.cgi?id=203885 Link: https://lore.kernel.org/r/20191112091617.70282-3-mika.westerberg@linux.intel.com Reported-by: Kai-Heng Feng <kai.heng.feng@canonical.com> Tested-by: Kai-Heng Feng <kai.heng.feng@canonical.com> Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com> Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
2019-11-12 17:16:17 +08:00
if (prev_state == PCI_D3cold)
pci_bridge_wait_for_secondary_bus(pci_dev);
PCI / PM: Allow runtime PM without callback functions a9c8088c7988 ("i2c: i801: Don't restore config registers on runtime PM") nullified the runtime PM suspend/resume callback pointers while keeping the runtime PM enabled. This caused the SMBus PCI device to stay in D0 with /sys/devices/.../power/runtime_status showing "error" when the runtime PM framework attempted to autosuspend the device. This is due to PCI bus runtime PM, which checks for driver runtime PM callbacks and returns -ENOSYS if they are not set. Since i2c-i801.c doesn't need to do anything device-specific for runtime PM, Jean Delvare proposed this be fixed in the PCI core rather than adding dummy runtime PM callback functions in the PCI drivers. Change pci_pm_runtime_suspend()/pci_pm_runtime_resume() so they allow changing the PCI device power state during runtime PM transitions even if the driver supplies no runtime PM callbacks. This fixes the runtime PM regression on i2c-i801.c. It is not obvious why the code previously required the runtime PM callbacks. The test has been there since the code was introduced by 6cbf82148ff2 ("PCI PM: Run-time callbacks for PCI bus type"). On the other hand, a similar change was done to generic runtime PM callbacks in 05aa55dddb9e ("PM / Runtime: Lenient generic runtime pm callbacks"). Fixes: a9c8088c7988 ("i2c: i801: Don't restore config registers on runtime PM") Reported-by: Mika Westerberg <mika.westerberg@linux.intel.com> Signed-off-by: Jarkko Nikula <jarkko.nikula@linux.intel.com> Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> Reviewed-by: Jean Delvare <jdelvare@suse.de> Reviewed-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Cc: stable@vger.kernel.org # v4.18+
2018-10-23 19:45:52 +08:00
if (pm && pm->runtime_resume)
error = pm->runtime_resume(dev);
PCI/PM: add PCIe runtime D3cold support This patch adds runtime D3cold support and corresponding ACPI platform support. This patch only enables runtime D3cold support; it does not enable D3cold support during system suspend/hibernate. D3cold is the deepest power saving state for a PCIe device, where its main power is removed. While it is in D3cold, you can't access the device at all, not even its configuration space (which is still accessible in D3hot). Therefore the PCI PM registers can not be used to transition into/out of the D3cold state; that must be done by platform logic such as ACPI _PR3. To support wakeup from D3cold, a system may provide auxiliary power, which allows a device to request wakeup using a Beacon or the sideband WAKE# signal. WAKE# is usually connected to platform logic such as ACPI GPE. This is quite different from other power saving states, where devices request wakeup via a PME message on the PCIe link. Some devices, such as those in plug-in slots, have no direct platform logic. For example, there is usually no ACPI _PR3 for them. D3cold support for these devices can be done via the PCIe Downstream Port leading to the device. When the PCIe port is powered on/off, the device is powered on/off too. Wakeup events from the device will be notified to the corresponding PCIe port. For more information about PCIe D3cold and corresponding ACPI support, please refer to: - PCI Express Base Specification Revision 2.0 - Advanced Configuration and Power Interface Specification Revision 5.0 [bhelgaas: changelog] Reviewed-by: Rafael J. Wysocki <rjw@sisk.pl> Originally-by: Zheng Yan <zheng.z.yan@intel.com> Signed-off-by: Huang Ying <ying.huang@intel.com> Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
2012-06-23 10:23:51 +08:00
pci_dev->runtime_d3cold = false;
return error;
}
static int pci_pm_runtime_idle(struct device *dev)
{
struct pci_dev *pci_dev = to_pci_dev(dev);
const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
/*
* If pci_dev->driver is not set (unbound), the device should
* always remain in D0 regardless of the runtime PM status
*/
if (!pci_dev->driver)
return 0;
if (!pm)
return -ENOSYS;
if (pm->runtime_idle)
return pm->runtime_idle(dev);
return 0;
}
static const struct dev_pm_ops pci_dev_pm_ops = {
.prepare = pci_pm_prepare,
.complete = pci_pm_complete,
.suspend = pci_pm_suspend,
PCI / PM: Take SMART_SUSPEND driver flag into account Make the PCI bus type take DPM_FLAG_SMART_SUSPEND into account in its system-wide PM callbacks and make sure that all code that should not run in parallel with pci_pm_runtime_resume() is executed in the "late" phases of system suspend, freeze and poweroff transitions. [Note that the pm_runtime_suspended() check in pci_dev_keep_suspended() is an optimization, because if is not passed, all of the subsequent checks may be skipped and some of them are much more overhead in general.] Also use the observation that if the device is in runtime suspend at the beginning of the "late" phase of a system-wide suspend-like transition, its state cannot change going forward (runtime PM is disabled for it at that time) until the transition is over and the subsequent system-wide PM callbacks should be skipped for it (as they generally assume the device to not be suspended), so add checks for that in pci_pm_suspend_late/noirq(), pci_pm_freeze_late/noirq() and pci_pm_poweroff_late/noirq(). Moreover, if pci_pm_resume_noirq() or pci_pm_restore_noirq() is called during the subsequent system-wide resume transition and if the device was left in runtime suspend previously, its runtime PM status needs to be changed to "active" as it is going to be put into the full-power state, so add checks for that too to these functions. In turn, if pci_pm_thaw_noirq() runs after the device has been left in runtime suspend, the subsequent "thaw" callbacks need to be skipped for it (as they may not work correctly with a suspended device), so set the power.direct_complete flag for the device then to make the PM core skip those callbacks. In addition to the above add a core helper for checking if DPM_FLAG_SMART_SUSPEND is set and the device runtime PM status is "suspended" at the same time, which is done quite often in the new code (and will be done elsewhere going forward too). Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Acked-by: Bjorn Helgaas <bhelgaas@google.com>
2017-10-26 18:12:22 +08:00
.suspend_late = pci_pm_suspend_late,
.resume = pci_pm_resume,
PM: sleep: core: Do not skip callbacks in the resume phase The current code in device_resume_noirq() causes the entire early resume and resume phases of device suspend to be skipped for devices for which the noirq resume phase have been skipped (due to the LEAVE_SUSPENDED flag being set) on the premise that those devices should stay in runtime-suspend after system-wide resume. However, that may not be correct in two situations. First, the middle layer (subsystem) noirq resume callback may be missing for a given device, but its early resume callback may be present and it may need to do something even if it decides to skip the driver callback. Second, if the device's wakeup settings were adjusted in the suspend phase without resuming the device (that was in runtime suspend at that time), they most likely need to be adjusted again in the resume phase and so the driver callback in that phase needs to be run. For the above reason, modify the core to allow the middle layer ->resume_late callback to run even if its ->resume_noirq callback is missing (and the core has skipped the driver-level callback in that phase) and to allow all device callbacks to run in the resume phase. Also make the core set the PM-runtime status of devices with SMART_SUSPEND set whose resume callbacks are not skipped to "active" in the "noirq" resume phase and update the affected subsystems (PCI and ACPI) accordingly. After this change, middle-layer (subsystem) callbacks will always be invoked in all phases of system suspend and resume and driver callbacks will always run in the prepare, suspend, resume, and complete phases for all devices. For devices with SMART_SUSPEND set, driver callbacks will be skipped in the late and noirq phases of system suspend if those devices remain in runtime suspend in __device_suspend_late(). Driver callbacks will also be skipped for them during the noirq and early phases of the "thaw" transition related to hibernation in that case. Setting LEAVE_SUSPENDED means that the driver allows its callbacks to be skipped in the noirq and early phases of system resume, but some additional conditions need to be met for that to happen (among other things, the power.may_skip_resume flag needs to be set for the device during system suspend for the driver callbacks to be skipped during the subsequent resume transition). For all devices with SMART_SUSPEND set whose driver callbacks are invoked during system resume, the PM-runtime status will be set to "active" (by the core). Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Alan Stern <stern@rowland.harvard.edu> Acked-by: Bjorn Helgaas <bhelgaas@google.com>
2020-04-19 00:52:08 +08:00
.resume_early = pci_pm_resume_early,
.freeze = pci_pm_freeze,
.thaw = pci_pm_thaw,
.poweroff = pci_pm_poweroff,
PCI / PM: Take SMART_SUSPEND driver flag into account Make the PCI bus type take DPM_FLAG_SMART_SUSPEND into account in its system-wide PM callbacks and make sure that all code that should not run in parallel with pci_pm_runtime_resume() is executed in the "late" phases of system suspend, freeze and poweroff transitions. [Note that the pm_runtime_suspended() check in pci_dev_keep_suspended() is an optimization, because if is not passed, all of the subsequent checks may be skipped and some of them are much more overhead in general.] Also use the observation that if the device is in runtime suspend at the beginning of the "late" phase of a system-wide suspend-like transition, its state cannot change going forward (runtime PM is disabled for it at that time) until the transition is over and the subsequent system-wide PM callbacks should be skipped for it (as they generally assume the device to not be suspended), so add checks for that in pci_pm_suspend_late/noirq(), pci_pm_freeze_late/noirq() and pci_pm_poweroff_late/noirq(). Moreover, if pci_pm_resume_noirq() or pci_pm_restore_noirq() is called during the subsequent system-wide resume transition and if the device was left in runtime suspend previously, its runtime PM status needs to be changed to "active" as it is going to be put into the full-power state, so add checks for that too to these functions. In turn, if pci_pm_thaw_noirq() runs after the device has been left in runtime suspend, the subsequent "thaw" callbacks need to be skipped for it (as they may not work correctly with a suspended device), so set the power.direct_complete flag for the device then to make the PM core skip those callbacks. In addition to the above add a core helper for checking if DPM_FLAG_SMART_SUSPEND is set and the device runtime PM status is "suspended" at the same time, which is done quite often in the new code (and will be done elsewhere going forward too). Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Acked-by: Bjorn Helgaas <bhelgaas@google.com>
2017-10-26 18:12:22 +08:00
.poweroff_late = pci_pm_poweroff_late,
.restore = pci_pm_restore,
.suspend_noirq = pci_pm_suspend_noirq,
.resume_noirq = pci_pm_resume_noirq,
.freeze_noirq = pci_pm_freeze_noirq,
.thaw_noirq = pci_pm_thaw_noirq,
.poweroff_noirq = pci_pm_poweroff_noirq,
.restore_noirq = pci_pm_restore_noirq,
.runtime_suspend = pci_pm_runtime_suspend,
.runtime_resume = pci_pm_runtime_resume,
.runtime_idle = pci_pm_runtime_idle,
};
#define PCI_PM_OPS_PTR (&pci_dev_pm_ops)
#else /* !CONFIG_PM */
#define pci_pm_runtime_suspend NULL
#define pci_pm_runtime_resume NULL
#define pci_pm_runtime_idle NULL
#define PCI_PM_OPS_PTR NULL
#endif /* !CONFIG_PM */
/**
* __pci_register_driver - register a new pci driver
* @drv: the driver structure to register
* @owner: owner module of drv
* @mod_name: module name string
*
* Adds the driver structure to the list of registered drivers.
* Returns a negative value on error, otherwise 0.
* If no error occurred, the driver remains registered even if
* no device was claimed during registration.
*/
int __pci_register_driver(struct pci_driver *drv, struct module *owner,
const char *mod_name)
{
/* initialize common driver fields */
drv->driver.name = drv->name;
drv->driver.bus = &pci_bus_type;
drv->driver.owner = owner;
drv->driver.mod_name = mod_name;
drv->driver.groups = drv->groups;
spin_lock_init(&drv->dynids.lock);
INIT_LIST_HEAD(&drv->dynids.list);
/* register with core */
return driver_register(&drv->driver);
}
EXPORT_SYMBOL(__pci_register_driver);
/**
* pci_unregister_driver - unregister a pci driver
* @drv: the driver structure to unregister
*
* Deletes the driver structure from the list of registered PCI drivers,
* gives it a chance to clean up by calling its remove() function for
* each device it was responsible for, and marks those devices as
* driverless.
*/
void pci_unregister_driver(struct pci_driver *drv)
{
driver_unregister(&drv->driver);
pci_free_dynids(drv);
}
EXPORT_SYMBOL(pci_unregister_driver);
static struct pci_driver pci_compat_driver = {
.name = "compat"
};
/**
* pci_dev_driver - get the pci_driver of a device
* @dev: the device to query
*
* Returns the appropriate pci_driver structure or %NULL if there is no
* registered driver for the device.
*/
struct pci_driver *pci_dev_driver(const struct pci_dev *dev)
{
if (dev->driver)
return dev->driver;
else {
int i;
for (i = 0; i <= PCI_ROM_RESOURCE; i++)
if (dev->resource[i].flags & IORESOURCE_BUSY)
return &pci_compat_driver;
}
return NULL;
}
EXPORT_SYMBOL(pci_dev_driver);
/**
* pci_bus_match - Tell if a PCI device structure has a matching PCI device id structure
* @dev: the PCI device structure to match against
* @drv: the device driver to search for matching PCI device id structures
*
* Used by a driver to check whether a PCI device present in the
* system is in its list of supported devices. Returns the matching
* pci_device_id structure or %NULL if there is no match.
*/
static int pci_bus_match(struct device *dev, struct device_driver *drv)
{
struct pci_dev *pci_dev = to_pci_dev(dev);
struct pci_driver *pci_drv;
const struct pci_device_id *found_id;
if (!pci_dev->match_driver)
return 0;
pci_drv = to_pci_driver(drv);
found_id = pci_match_device(pci_drv, pci_dev);
if (found_id)
return 1;
return 0;
}
/**
* pci_dev_get - increments the reference count of the pci device structure
* @dev: the device being referenced
*
* Each live reference to a device should be refcounted.
*
* Drivers for PCI devices should normally record such references in
* their probe() methods, when they bind to a device, and release
* them by calling pci_dev_put(), in their disconnect() methods.
*
* A pointer to the device with the incremented reference counter is returned.
*/
struct pci_dev *pci_dev_get(struct pci_dev *dev)
{
if (dev)
get_device(&dev->dev);
return dev;
}
EXPORT_SYMBOL(pci_dev_get);
/**
* pci_dev_put - release a use of the pci device structure
* @dev: device that's been disconnected
*
* Must be called when a user of a device is finished with it. When the last
* user of the device calls this function, the memory of the device is freed.
*/
void pci_dev_put(struct pci_dev *dev)
{
if (dev)
put_device(&dev->dev);
}
EXPORT_SYMBOL(pci_dev_put);
static int pci_uevent(struct device *dev, struct kobj_uevent_env *env)
{
struct pci_dev *pdev;
if (!dev)
return -ENODEV;
pdev = to_pci_dev(dev);
if (add_uevent_var(env, "PCI_CLASS=%04X", pdev->class))
return -ENOMEM;
if (add_uevent_var(env, "PCI_ID=%04X:%04X", pdev->vendor, pdev->device))
return -ENOMEM;
if (add_uevent_var(env, "PCI_SUBSYS_ID=%04X:%04X", pdev->subsystem_vendor,
pdev->subsystem_device))
return -ENOMEM;
if (add_uevent_var(env, "PCI_SLOT_NAME=%s", pci_name(pdev)))
return -ENOMEM;
if (add_uevent_var(env, "MODALIAS=pci:v%08Xd%08Xsv%08Xsd%08Xbc%02Xsc%02Xi%02X",
pdev->vendor, pdev->device,
pdev->subsystem_vendor, pdev->subsystem_device,
(u8)(pdev->class >> 16), (u8)(pdev->class >> 8),
(u8)(pdev->class)))
return -ENOMEM;
return 0;
}
#if defined(CONFIG_PCIEPORTBUS) || defined(CONFIG_EEH)
/**
* pci_uevent_ers - emit a uevent during recovery path of PCI device
* @pdev: PCI device undergoing error recovery
* @err_type: type of error event
*/
void pci_uevent_ers(struct pci_dev *pdev, enum pci_ers_result err_type)
{
int idx = 0;
char *envp[3];
switch (err_type) {
case PCI_ERS_RESULT_NONE:
case PCI_ERS_RESULT_CAN_RECOVER:
envp[idx++] = "ERROR_EVENT=BEGIN_RECOVERY";
envp[idx++] = "DEVICE_ONLINE=0";
break;
case PCI_ERS_RESULT_RECOVERED:
envp[idx++] = "ERROR_EVENT=SUCCESSFUL_RECOVERY";
envp[idx++] = "DEVICE_ONLINE=1";
break;
case PCI_ERS_RESULT_DISCONNECT:
envp[idx++] = "ERROR_EVENT=FAILED_RECOVERY";
envp[idx++] = "DEVICE_ONLINE=0";
break;
default:
break;
}
if (idx > 0) {
envp[idx++] = NULL;
kobject_uevent_env(&pdev->dev.kobj, KOBJ_CHANGE, envp);
}
}
#endif
static int pci_bus_num_vf(struct device *dev)
{
return pci_num_vf(to_pci_dev(dev));
}
/**
* pci_dma_configure - Setup DMA configuration
* @dev: ptr to dev structure
*
* Function to update PCI devices's DMA configuration using the same
* info from the OF node or ACPI node of host bridge's parent (if any).
*/
static int pci_dma_configure(struct device *dev)
{
struct device *bridge;
int ret = 0;
bridge = pci_get_host_bridge_device(to_pci_dev(dev));
if (IS_ENABLED(CONFIG_OF) && bridge->parent &&
bridge->parent->of_node) {
ret = of_dma_configure(dev, bridge->parent->of_node, true);
} else if (has_acpi_companion(bridge)) {
struct acpi_device *adev = to_acpi_device_node(bridge->fwnode);
ret = acpi_dma_configure(dev, acpi_get_dma_attr(adev));
}
pci_put_host_bridge_device(bridge);
return ret;
}
struct bus_type pci_bus_type = {
.name = "pci",
.match = pci_bus_match,
.uevent = pci_uevent,
.probe = pci_device_probe,
.remove = pci_device_remove,
.shutdown = pci_device_shutdown,
.dev_groups = pci_dev_groups,
.bus_groups = pci_bus_groups,
.drv_groups = pci_drv_groups,
.pm = PCI_PM_OPS_PTR,
.num_vf = pci_bus_num_vf,
.dma_configure = pci_dma_configure,
};
EXPORT_SYMBOL(pci_bus_type);
#ifdef CONFIG_PCIEPORTBUS
static int pcie_port_bus_match(struct device *dev, struct device_driver *drv)
{
struct pcie_device *pciedev;
struct pcie_port_service_driver *driver;
if (drv->bus != &pcie_port_bus_type || dev->bus != &pcie_port_bus_type)
return 0;
pciedev = to_pcie_device(dev);
driver = to_service_driver(drv);
if (driver->service != pciedev->service)
return 0;
if (driver->port_type != PCIE_ANY_PORT &&
driver->port_type != pci_pcie_type(pciedev->port))
return 0;
return 1;
}
struct bus_type pcie_port_bus_type = {
.name = "pci_express",
.match = pcie_port_bus_match,
};
EXPORT_SYMBOL_GPL(pcie_port_bus_type);
#endif
static int __init pci_driver_init(void)
{
int ret;
ret = bus_register(&pci_bus_type);
if (ret)
return ret;
#ifdef CONFIG_PCIEPORTBUS
ret = bus_register(&pcie_port_bus_type);
if (ret)
return ret;
#endif
dma_debug_add_bus(&pci_bus_type);
return 0;
}
postcore_initcall(pci_driver_init);