blob: 8abc843b1615ecf94a24a1fc1db03dfd00d03dc5 [file] [log] [blame]
// SPDX-License-Identifier: GPL-2.0
/*
* PCI Bus Services, see include/linux/pci.h for further explanation.
*
* Copyright 1993 -- 1997 Drew Eckhardt, Frederic Potter,
* David Mosberger-Tang
*
* Copyright 1997 -- 2000 Martin Mares <mj@ucw.cz>
*/
#include <linux/acpi.h>
#include <linux/kernel.h>
#include <linux/delay.h>
#include <linux/dmi.h>
#include <linux/init.h>
#include <linux/of.h>
#include <linux/of_pci.h>
#include <linux/pci.h>
#include <linux/pm.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/spinlock.h>
#include <linux/string.h>
#include <linux/log2.h>
#include <linux/logic_pio.h>
#include <linux/pm_wakeup.h>
#include <linux/interrupt.h>
#include <linux/device.h>
#include <linux/pm_runtime.h>
#include <linux/pci_hotplug.h>
#include <linux/vmalloc.h>
#include <linux/pci-ats.h>
#include <asm/setup.h>
#include <asm/dma.h>
#include <linux/aer.h>
#include "pci.h"
DEFINE_MUTEX(pci_slot_mutex);
const char *pci_power_names[] = {
"error", "D0", "D1", "D2", "D3hot", "D3cold", "unknown",
};
EXPORT_SYMBOL_GPL(pci_power_names);
int isa_dma_bridge_buggy;
EXPORT_SYMBOL(isa_dma_bridge_buggy);
int pci_pci_problems;
EXPORT_SYMBOL(pci_pci_problems);
unsigned int pci_pm_d3_delay;
static void pci_pme_list_scan(struct work_struct *work);
static LIST_HEAD(pci_pme_list);
static DEFINE_MUTEX(pci_pme_list_mutex);
static DECLARE_DELAYED_WORK(pci_pme_work, pci_pme_list_scan);
struct pci_pme_device {
struct list_head list;
struct pci_dev *dev;
};
#define PME_TIMEOUT 1000 /* How long between PME checks */
static void pci_dev_d3_sleep(struct pci_dev *dev)
{
unsigned int delay = dev->d3_delay;
if (delay < pci_pm_d3_delay)
delay = pci_pm_d3_delay;
if (delay)
msleep(delay);
}
#ifdef CONFIG_PCI_DOMAINS
int pci_domains_supported = 1;
#endif
#define DEFAULT_CARDBUS_IO_SIZE (256)
#define DEFAULT_CARDBUS_MEM_SIZE (64*1024*1024)
/* pci=cbmemsize=nnM,cbiosize=nn can override this */
unsigned long pci_cardbus_io_size = DEFAULT_CARDBUS_IO_SIZE;
unsigned long pci_cardbus_mem_size = DEFAULT_CARDBUS_MEM_SIZE;
#define DEFAULT_HOTPLUG_IO_SIZE (256)
#define DEFAULT_HOTPLUG_MEM_SIZE (2*1024*1024)
/* pci=hpmemsize=nnM,hpiosize=nn can override this */
unsigned long pci_hotplug_io_size = DEFAULT_HOTPLUG_IO_SIZE;
unsigned long pci_hotplug_mem_size = DEFAULT_HOTPLUG_MEM_SIZE;
#define DEFAULT_HOTPLUG_BUS_SIZE 1
unsigned long pci_hotplug_bus_size = DEFAULT_HOTPLUG_BUS_SIZE;
enum pcie_bus_config_types pcie_bus_config = PCIE_BUS_DEFAULT;
/*
* The default CLS is used if arch didn't set CLS explicitly and not
* all pci devices agree on the same value. Arch can override either
* the dfl or actual value as it sees fit. Don't forget this is
* measured in 32-bit words, not bytes.
*/
u8 pci_dfl_cache_line_size = L1_CACHE_BYTES >> 2;
u8 pci_cache_line_size;
/*
* If we set up a device for bus mastering, we need to check the latency
* timer as certain BIOSes forget to set it properly.
*/
unsigned int pcibios_max_latency = 255;
/* If set, the PCIe ARI capability will not be used. */
static bool pcie_ari_disabled;
/* If set, the PCIe ATS capability will not be used. */
static bool pcie_ats_disabled;
/* If set, the PCI config space of each device is printed during boot. */
bool pci_early_dump;
bool pci_ats_disabled(void)
{
return pcie_ats_disabled;
}
/* Disable bridge_d3 for all PCIe ports */
static bool pci_bridge_d3_disable;
/* Force bridge_d3 for all PCIe ports */
static bool pci_bridge_d3_force;
static int __init pcie_port_pm_setup(char *str)
{
if (!strcmp(str, "off"))
pci_bridge_d3_disable = true;
else if (!strcmp(str, "force"))
pci_bridge_d3_force = true;
return 1;
}
__setup("pcie_port_pm=", pcie_port_pm_setup);
/* Time to wait after a reset for device to become responsive */
#define PCIE_RESET_READY_POLL_MS 60000
/**
* pci_bus_max_busnr - returns maximum PCI bus number of given bus' children
* @bus: pointer to PCI bus structure to search
*
* Given a PCI bus, returns the highest PCI bus number present in the set
* including the given PCI bus and its list of child PCI buses.
*/
unsigned char pci_bus_max_busnr(struct pci_bus *bus)
{
struct pci_bus *tmp;
unsigned char max, n;
max = bus->busn_res.end;
list_for_each_entry(tmp, &bus->children, node) {
n = pci_bus_max_busnr(tmp);
if (n > max)
max = n;
}
return max;
}
EXPORT_SYMBOL_GPL(pci_bus_max_busnr);
#ifdef CONFIG_HAS_IOMEM
void __iomem *pci_ioremap_bar(struct pci_dev *pdev, int bar)
{
struct resource *res = &pdev->resource[bar];
/*
* Make sure the BAR is actually a memory resource, not an IO resource
*/
if (res->flags & IORESOURCE_UNSET || !(res->flags & IORESOURCE_MEM)) {
pci_warn(pdev, "can't ioremap BAR %d: %pR\n", bar, res);
return NULL;
}
return ioremap_nocache(res->start, resource_size(res));
}
EXPORT_SYMBOL_GPL(pci_ioremap_bar);
void __iomem *pci_ioremap_wc_bar(struct pci_dev *pdev, int bar)
{
/*
* Make sure the BAR is actually a memory resource, not an IO resource
*/
if (!(pci_resource_flags(pdev, bar) & IORESOURCE_MEM)) {
WARN_ON(1);
return NULL;
}
return ioremap_wc(pci_resource_start(pdev, bar),
pci_resource_len(pdev, bar));
}
EXPORT_SYMBOL_GPL(pci_ioremap_wc_bar);
#endif
/**
* pci_dev_str_match_path - test if a path string matches a device
* @dev: the PCI device to test
* @path: string to match the device against
* @endptr: pointer to the string after the match
*
* Test if a string (typically from a kernel parameter) formatted as a
* path of device/function addresses matches a PCI device. The string must
* be of the form:
*
* [<domain>:]<bus>:<device>.<func>[/<device>.<func>]*
*
* A path for a device can be obtained using 'lspci -t'. Using a path
* is more robust against bus renumbering than using only a single bus,
* device and function address.
*
* Returns 1 if the string matches the device, 0 if it does not and
* a negative error code if it fails to parse the string.
*/
static int pci_dev_str_match_path(struct pci_dev *dev, const char *path,
const char **endptr)
{
int ret;
int seg, bus, slot, func;
char *wpath, *p;
char end;
*endptr = strchrnul(path, ';');
wpath = kmemdup_nul(path, *endptr - path, GFP_KERNEL);
if (!wpath)
return -ENOMEM;
while (1) {
p = strrchr(wpath, '/');
if (!p)
break;
ret = sscanf(p, "/%x.%x%c", &slot, &func, &end);
if (ret != 2) {
ret = -EINVAL;
goto free_and_exit;
}
if (dev->devfn != PCI_DEVFN(slot, func)) {
ret = 0;
goto free_and_exit;
}
/*
* Note: we don't need to get a reference to the upstream
* bridge because we hold a reference to the top level
* device which should hold a reference to the bridge,
* and so on.
*/
dev = pci_upstream_bridge(dev);
if (!dev) {
ret = 0;
goto free_and_exit;
}
*p = 0;
}
ret = sscanf(wpath, "%x:%x:%x.%x%c", &seg, &bus, &slot,
&func, &end);
if (ret != 4) {
seg = 0;
ret = sscanf(wpath, "%x:%x.%x%c", &bus, &slot, &func, &end);
if (ret != 3) {
ret = -EINVAL;
goto free_and_exit;
}
}
ret = (seg == pci_domain_nr(dev->bus) &&
bus == dev->bus->number &&
dev->devfn == PCI_DEVFN(slot, func));
free_and_exit:
kfree(wpath);
return ret;
}
/**
* pci_dev_str_match - test if a string matches a device
* @dev: the PCI device to test
* @p: string to match the device against
* @endptr: pointer to the string after the match
*
* Test if a string (typically from a kernel parameter) matches a specified
* PCI device. The string may be of one of the following formats:
*
* [<domain>:]<bus>:<device>.<func>[/<device>.<func>]*
* pci:<vendor>:<device>[:<subvendor>:<subdevice>]
*
* The first format specifies a PCI bus/device/function address which
* may change if new hardware is inserted, if motherboard firmware changes,
* or due to changes caused in kernel parameters. If the domain is
* left unspecified, it is taken to be 0. In order to be robust against
* bus renumbering issues, a path of PCI device/function numbers may be used
* to address the specific device. The path for a device can be determined
* through the use of 'lspci -t'.
*
* The second format matches devices using IDs in the configuration
* space which may match multiple devices in the system. A value of 0
* for any field will match all devices. (Note: this differs from
* in-kernel code that uses PCI_ANY_ID which is ~0; this is for
* legacy reasons and convenience so users don't have to specify
* FFFFFFFFs on the command line.)
*
* Returns 1 if the string matches the device, 0 if it does not and
* a negative error code if the string cannot be parsed.
*/
static int pci_dev_str_match(struct pci_dev *dev, const char *p,
const char **endptr)
{
int ret;
int count;
unsigned short vendor, device, subsystem_vendor, subsystem_device;
if (strncmp(p, "pci:", 4) == 0) {
/* PCI vendor/device (subvendor/subdevice) IDs are specified */
p += 4;
ret = sscanf(p, "%hx:%hx:%hx:%hx%n", &vendor, &device,
&subsystem_vendor, &subsystem_device, &count);
if (ret != 4) {
ret = sscanf(p, "%hx:%hx%n", &vendor, &device, &count);
if (ret != 2)
return -EINVAL;
subsystem_vendor = 0;
subsystem_device = 0;
}
p += count;
if ((!vendor || vendor == dev->vendor) &&
(!device || device == dev->device) &&
(!subsystem_vendor ||
subsystem_vendor == dev->subsystem_vendor) &&
(!subsystem_device ||
subsystem_device == dev->subsystem_device))
goto found;
} else {
/*
* PCI Bus, Device, Function IDs are specified
* (optionally, may include a path of devfns following it)
*/
ret = pci_dev_str_match_path(dev, p, &p);
if (ret < 0)
return ret;
else if (ret)
goto found;
}
*endptr = p;
return 0;
found:
*endptr = p;
return 1;
}
static int __pci_find_next_cap_ttl(struct pci_bus *bus, unsigned int devfn,
u8 pos, int cap, int *ttl)
{
u8 id;
u16 ent;
pci_bus_read_config_byte(bus, devfn, pos, &pos);
while ((*ttl)--) {
if (pos < 0x40)
break;
pos &= ~3;
pci_bus_read_config_word(bus, devfn, pos, &ent);
id = ent & 0xff;
if (id == 0xff)
break;
if (id == cap)
return pos;
pos = (ent >> 8);
}
return 0;
}
static int __pci_find_next_cap(struct pci_bus *bus, unsigned int devfn,
u8 pos, int cap)
{
int ttl = PCI_FIND_CAP_TTL;
return __pci_find_next_cap_ttl(bus, devfn, pos, cap, &ttl);
}
int pci_find_next_capability(struct pci_dev *dev, u8 pos, int cap)
{
return __pci_find_next_cap(dev->bus, dev->devfn,
pos + PCI_CAP_LIST_NEXT, cap);
}
EXPORT_SYMBOL_GPL(pci_find_next_capability);
static int __pci_bus_find_cap_start(struct pci_bus *bus,
unsigned int devfn, u8 hdr_type)
{
u16 status;
pci_bus_read_config_word(bus, devfn, PCI_STATUS, &status);
if (!(status & PCI_STATUS_CAP_LIST))
return 0;
switch (hdr_type) {
case PCI_HEADER_TYPE_NORMAL:
case PCI_HEADER_TYPE_BRIDGE:
return PCI_CAPABILITY_LIST;
case PCI_HEADER_TYPE_CARDBUS:
return PCI_CB_CAPABILITY_LIST;
}
return 0;
}
/**
* pci_find_capability - query for devices' capabilities
* @dev: PCI device to query
* @cap: capability code
*
* Tell if a device supports a given PCI capability.
* Returns the address of the requested capability structure within the
* device's PCI configuration space or 0 in case the device does not
* support it. Possible values for @cap include:
*
* %PCI_CAP_ID_PM Power Management
* %PCI_CAP_ID_AGP Accelerated Graphics Port
* %PCI_CAP_ID_VPD Vital Product Data
* %PCI_CAP_ID_SLOTID Slot Identification
* %PCI_CAP_ID_MSI Message Signalled Interrupts
* %PCI_CAP_ID_CHSWP CompactPCI HotSwap
* %PCI_CAP_ID_PCIX PCI-X
* %PCI_CAP_ID_EXP PCI Express
*/
int pci_find_capability(struct pci_dev *dev, int cap)
{
int pos;
pos = __pci_bus_find_cap_start(dev->bus, dev->devfn, dev->hdr_type);
if (pos)
pos = __pci_find_next_cap(dev->bus, dev->devfn, pos, cap);
return pos;
}
EXPORT_SYMBOL(pci_find_capability);
/**
* pci_bus_find_capability - query for devices' capabilities
* @bus: the PCI bus to query
* @devfn: PCI device to query
* @cap: capability code
*
* Like pci_find_capability() but works for PCI devices that do not have a
* pci_dev structure set up yet.
*
* Returns the address of the requested capability structure within the
* device's PCI configuration space or 0 in case the device does not
* support it.
*/
int pci_bus_find_capability(struct pci_bus *bus, unsigned int devfn, int cap)
{
int pos;
u8 hdr_type;
pci_bus_read_config_byte(bus, devfn, PCI_HEADER_TYPE, &hdr_type);
pos = __pci_bus_find_cap_start(bus, devfn, hdr_type & 0x7f);
if (pos)
pos = __pci_find_next_cap(bus, devfn, pos, cap);
return pos;
}
EXPORT_SYMBOL(pci_bus_find_capability);
/**
* pci_find_next_ext_capability - Find an extended capability
* @dev: PCI device to query
* @start: address at which to start looking (0 to start at beginning of list)
* @cap: capability code
*
* Returns the address of the next matching extended capability structure
* within the device's PCI configuration space or 0 if the device does
* not support it. Some capabilities can occur several times, e.g., the
* vendor-specific capability, and this provides a way to find them all.
*/
int pci_find_next_ext_capability(struct pci_dev *dev, int start, int cap)
{
u32 header;
int ttl;
int pos = PCI_CFG_SPACE_SIZE;
/* minimum 8 bytes per capability */
ttl = (PCI_CFG_SPACE_EXP_SIZE - PCI_CFG_SPACE_SIZE) / 8;
if (dev->cfg_size <= PCI_CFG_SPACE_SIZE)
return 0;
if (start)
pos = start;
if (pci_read_config_dword(dev, pos, &header) != PCIBIOS_SUCCESSFUL)
return 0;
/*
* If we have no capabilities, this is indicated by cap ID,
* cap version and next pointer all being 0.
*/
if (header == 0)
return 0;
while (ttl-- > 0) {
if (PCI_EXT_CAP_ID(header) == cap && pos != start)
return pos;
pos = PCI_EXT_CAP_NEXT(header);
if (pos < PCI_CFG_SPACE_SIZE)
break;
if (pci_read_config_dword(dev, pos, &header) != PCIBIOS_SUCCESSFUL)
break;
}
return 0;
}
EXPORT_SYMBOL_GPL(pci_find_next_ext_capability);
/**
* pci_find_ext_capability - Find an extended capability
* @dev: PCI device to query
* @cap: capability code
*
* Returns the address of the requested extended capability structure
* within the device's PCI configuration space or 0 if the device does
* not support it. Possible values for @cap include:
*
* %PCI_EXT_CAP_ID_ERR Advanced Error Reporting
* %PCI_EXT_CAP_ID_VC Virtual Channel
* %PCI_EXT_CAP_ID_DSN Device Serial Number
* %PCI_EXT_CAP_ID_PWR Power Budgeting
*/
int pci_find_ext_capability(struct pci_dev *dev, int cap)
{
return pci_find_next_ext_capability(dev, 0, cap);
}
EXPORT_SYMBOL_GPL(pci_find_ext_capability);
static int __pci_find_next_ht_cap(struct pci_dev *dev, int pos, int ht_cap)
{
int rc, ttl = PCI_FIND_CAP_TTL;
u8 cap, mask;
if (ht_cap == HT_CAPTYPE_SLAVE || ht_cap == HT_CAPTYPE_HOST)
mask = HT_3BIT_CAP_MASK;
else
mask = HT_5BIT_CAP_MASK;
pos = __pci_find_next_cap_ttl(dev->bus, dev->devfn, pos,
PCI_CAP_ID_HT, &ttl);
while (pos) {
rc = pci_read_config_byte(dev, pos + 3, &cap);
if (rc != PCIBIOS_SUCCESSFUL)
return 0;
if ((cap & mask) == ht_cap)
return pos;
pos = __pci_find_next_cap_ttl(dev->bus, dev->devfn,
pos + PCI_CAP_LIST_NEXT,
PCI_CAP_ID_HT, &ttl);
}
return 0;
}
/**
* pci_find_next_ht_capability - query a device's Hypertransport capabilities
* @dev: PCI device to query
* @pos: Position from which to continue searching
* @ht_cap: Hypertransport capability code
*
* To be used in conjunction with pci_find_ht_capability() to search for
* all capabilities matching @ht_cap. @pos should always be a value returned
* from pci_find_ht_capability().
*
* NB. To be 100% safe against broken PCI devices, the caller should take
* steps to avoid an infinite loop.
*/
int pci_find_next_ht_capability(struct pci_dev *dev, int pos, int ht_cap)
{
return __pci_find_next_ht_cap(dev, pos + PCI_CAP_LIST_NEXT, ht_cap);
}
EXPORT_SYMBOL_GPL(pci_find_next_ht_capability);
/**
* pci_find_ht_capability - query a device's Hypertransport capabilities
* @dev: PCI device to query
* @ht_cap: Hypertransport capability code
*
* Tell if a device supports a given Hypertransport capability.
* Returns an address within the device's PCI configuration space
* or 0 in case the device does not support the request capability.
* The address points to the PCI capability, of type PCI_CAP_ID_HT,
* which has a Hypertransport capability matching @ht_cap.
*/
int pci_find_ht_capability(struct pci_dev *dev, int ht_cap)
{
int pos;
pos = __pci_bus_find_cap_start(dev->bus, dev->devfn, dev->hdr_type);
if (pos)
pos = __pci_find_next_ht_cap(dev, pos, ht_cap);
return pos;
}
EXPORT_SYMBOL_GPL(pci_find_ht_capability);
/**
* pci_find_parent_resource - return resource region of parent bus of given
* region
* @dev: PCI device structure contains resources to be searched
* @res: child resource record for which parent is sought
*
* For given resource region of given device, return the resource region of
* parent bus the given region is contained in.
*/
struct resource *pci_find_parent_resource(const struct pci_dev *dev,
struct resource *res)
{
const struct pci_bus *bus = dev->bus;
struct resource *r;
int i;
pci_bus_for_each_resource(bus, r, i) {
if (!r)
continue;
if (resource_contains(r, res)) {
/*
* If the window is prefetchable but the BAR is
* not, the allocator made a mistake.
*/
if (r->flags & IORESOURCE_PREFETCH &&
!(res->flags & IORESOURCE_PREFETCH))
return NULL;
/*
* If we're below a transparent bridge, there may
* be both a positively-decoded aperture and a
* subtractively-decoded region that contain the BAR.
* We want the positively-decoded one, so this depends
* on pci_bus_for_each_resource() giving us those
* first.
*/
return r;
}
}
return NULL;
}
EXPORT_SYMBOL(pci_find_parent_resource);
/**
* pci_find_resource - Return matching PCI device resource
* @dev: PCI device to query
* @res: Resource to look for
*
* Goes over standard PCI resources (BARs) and checks if the given resource
* is partially or fully contained in any of them. In that case the
* matching resource is returned, %NULL otherwise.
*/
struct resource *pci_find_resource(struct pci_dev *dev, struct resource *res)
{
int i;
for (i = 0; i < PCI_ROM_RESOURCE; i++) {
struct resource *r = &dev->resource[i];
if (r->start && resource_contains(r, res))
return r;
}
return NULL;
}
EXPORT_SYMBOL(pci_find_resource);
/**
* pci_find_pcie_root_port - return PCIe Root Port
* @dev: PCI device to query
*
* Traverse up the parent chain and return the PCIe Root Port PCI Device
* for a given PCI Device.
*/
struct pci_dev *pci_find_pcie_root_port(struct pci_dev *dev)
{
struct pci_dev *bridge, *highest_pcie_bridge = dev;
bridge = pci_upstream_bridge(dev);
while (bridge && pci_is_pcie(bridge)) {
highest_pcie_bridge = bridge;
bridge = pci_upstream_bridge(bridge);
}
if (pci_pcie_type(highest_pcie_bridge) != PCI_EXP_TYPE_ROOT_PORT)
return NULL;
return highest_pcie_bridge;
}
EXPORT_SYMBOL(pci_find_pcie_root_port);
/**
* pci_wait_for_pending - wait for @mask bit(s) to clear in status word @pos
* @dev: the PCI device to operate on
* @pos: config space offset of status word
* @mask: mask of bit(s) to care about in status word
*
* Return 1 when mask bit(s) in status word clear, 0 otherwise.
*/
int pci_wait_for_pending(struct pci_dev *dev, int pos, u16 mask)
{
int i;
/* Wait for Transaction Pending bit clean */
for (i = 0; i < 4; i++) {
u16 status;
if (i)
msleep((1 << (i - 1)) * 100);
pci_read_config_word(dev, pos, &status);
if (!(status & mask))
return 1;
}
return 0;
}
/**
* pci_restore_bars - restore a device's BAR values (e.g. after wake-up)
* @dev: PCI device to have its BARs restored
*
* Restore the BAR values for a given device, so as to make it
* accessible by its driver.
*/
static void pci_restore_bars(struct pci_dev *dev)
{
int i;
for (i = 0; i < PCI_BRIDGE_RESOURCES; i++)
pci_update_resource(dev, i);
}
static const struct pci_platform_pm_ops *pci_platform_pm;
int pci_set_platform_pm(const struct pci_platform_pm_ops *ops)
{
if (!ops->is_manageable || !ops->set_state || !ops->get_state ||
!ops->choose_state || !ops->set_wakeup || !ops->need_resume)
return -EINVAL;
pci_platform_pm = ops;
return 0;
}
static inline bool platform_pci_power_manageable(struct pci_dev *dev)
{
return pci_platform_pm ? pci_platform_pm->is_manageable(dev) : false;
}
static inline int platform_pci_set_power_state(struct pci_dev *dev,
pci_power_t t)
{
return pci_platform_pm ? pci_platform_pm->set_state(dev, t) : -ENOSYS;
}
static inline pci_power_t platform_pci_get_power_state(struct pci_dev *dev)
{
return pci_platform_pm ? pci_platform_pm->get_state(dev) : PCI_UNKNOWN;
}
static inline pci_power_t platform_pci_choose_state(struct pci_dev *dev)
{
return pci_platform_pm ?
pci_platform_pm->choose_state(dev) : PCI_POWER_ERROR;
}
static inline int platform_pci_set_wakeup(struct pci_dev *dev, bool enable)
{
return pci_platform_pm ?
pci_platform_pm->set_wakeup(dev, enable) : -ENODEV;
}
static inline bool platform_pci_need_resume(struct pci_dev *dev)
{
return pci_platform_pm ? pci_platform_pm->need_resume(dev) : false;
}
static inline bool platform_pci_bridge_d3(struct pci_dev *dev)
{
return pci_platform_pm ? pci_platform_pm->bridge_d3(dev) : false;
}
/**
* pci_raw_set_power_state - Use PCI PM registers to set the power state of
* given PCI device
* @dev: PCI device to handle.
* @state: PCI power state (D0, D1, D2, D3hot) to put the device into.
*
* RETURN VALUE:
* -EINVAL if the requested state is invalid.
* -EIO if device does not support PCI PM or its PM capabilities register has a
* wrong version, or device doesn't support the requested state.
* 0 if device already is in the requested state.
* 0 if device's power state has been successfully changed.
*/
static int pci_raw_set_power_state(struct pci_dev *dev, pci_power_t state)
{
u16 pmcsr;
bool need_restore = false;
/* Check if we're already there */
if (dev->current_state == state)
return 0;
if (!dev->pm_cap)
return -EIO;
if (state < PCI_D0 || state > PCI_D3hot)
return -EINVAL;
/*
* Validate current state:
* Can enter D0 from any state, but if we can only go deeper
* to sleep if we're already in a low power state
*/
if (state != PCI_D0 && dev->current_state <= PCI_D3cold
&& dev->current_state > state) {
pci_err(dev, "invalid power transition (from state %d to %d)\n",
dev->current_state, state);
return -EINVAL;
}
/* Check if this device supports the desired state */
if ((state == PCI_D1 && !dev->d1_support)
|| (state == PCI_D2 && !dev->d2_support))
return -EIO;
pci_read_config_word(dev, dev->pm_cap + PCI_PM_CTRL, &pmcsr);
/*
* If we're (effectively) in D3, force entire word to 0.
* This doesn't affect PME_Status, disables PME_En, and
* sets PowerState to 0.
*/
switch (dev->current_state) {
case PCI_D0:
case PCI_D1:
case PCI_D2:
pmcsr &= ~PCI_PM_CTRL_STATE_MASK;
pmcsr |= state;
break;
case PCI_D3hot:
case PCI_D3cold:
case PCI_UNKNOWN: /* Boot-up */
if ((pmcsr & PCI_PM_CTRL_STATE_MASK) == PCI_D3hot
&& !(pmcsr & PCI_PM_CTRL_NO_SOFT_RESET))
need_restore = true;
/* Fall-through - force to D0 */
default:
pmcsr = 0;
break;
}
/* Enter specified state */
pci_write_config_word(dev, dev->pm_cap + PCI_PM_CTRL, pmcsr);
/*
* Mandatory power management transition delays; see PCI PM 1.1
* 5.6.1 table 18
*/
if (state == PCI_D3hot || dev->current_state == PCI_D3hot)
pci_dev_d3_sleep(dev);
else if (state == PCI_D2 || dev->current_state == PCI_D2)
udelay(PCI_PM_D2_DELAY);
pci_read_config_word(dev, dev->pm_cap + PCI_PM_CTRL, &pmcsr);
dev->current_state = (pmcsr & PCI_PM_CTRL_STATE_MASK);
if (dev->current_state != state && printk_ratelimit())
pci_info(dev, "Refused to change power state, currently in D%d\n",
dev->current_state);
/*
* According to section 5.4.1 of the "PCI BUS POWER MANAGEMENT
* INTERFACE SPECIFICATION, REV. 1.2", a device transitioning
* from D3hot to D0 _may_ perform an internal reset, thereby
* going to "D0 Uninitialized" rather than "D0 Initialized".
* For example, at least some versions of the 3c905B and the
* 3c556B exhibit this behaviour.
*
* At least some laptop BIOSen (e.g. the Thinkpad T21) leave
* devices in a D3hot state at boot. Consequently, we need to
* restore at least the BARs so that the device will be
* accessible to its driver.
*/
if (need_restore)
pci_restore_bars(dev);
if (dev->bus->self)
pcie_aspm_pm_state_change(dev->bus->self);
return 0;
}
/**
* pci_update_current_state - Read power state of given device and cache it
* @dev: PCI device to handle.
* @state: State to cache in case the device doesn't have the PM capability
*
* The power state is read from the PMCSR register, which however is
* inaccessible in D3cold. The platform firmware is therefore queried first
* to detect accessibility of the register. In case the platform firmware
* reports an incorrect state or the device isn't power manageable by the
* platform at all, we try to detect D3cold by testing accessibility of the
* vendor ID in config space.
*/
void pci_update_current_state(struct pci_dev *dev, pci_power_t state)
{
if (platform_pci_get_power_state(dev) == PCI_D3cold ||
!pci_device_is_present(dev)) {
dev->current_state = PCI_D3cold;
} else if (dev->pm_cap) {
u16 pmcsr;
pci_read_config_word(dev, dev->pm_cap + PCI_PM_CTRL, &pmcsr);
dev->current_state = (pmcsr & PCI_PM_CTRL_STATE_MASK);
} else {
dev->current_state = state;
}
}
/**
* pci_power_up - Put the given device into D0 forcibly
* @dev: PCI device to power up
*/
void pci_power_up(struct pci_dev *dev)
{
if (platform_pci_power_manageable(dev))
platform_pci_set_power_state(dev, PCI_D0);
pci_raw_set_power_state(dev, PCI_D0);
pci_update_current_state(dev, PCI_D0);
}
/**
* pci_platform_power_transition - Use platform to change device power state
* @dev: PCI device to handle.
* @state: State to put the device into.
*/
static int pci_platform_power_transition(struct pci_dev *dev, pci_power_t state)
{
int error;
if (platform_pci_power_manageable(dev)) {
error = platform_pci_set_power_state(dev, state);
if (!error)
pci_update_current_state(dev, state);
} else
error = -ENODEV;
if (error && !dev->pm_cap) /* Fall back to PCI_D0 */
dev->current_state = PCI_D0;
return error;
}
/**
* pci_wakeup - Wake up a PCI device
* @pci_dev: Device to handle.
* @ign: ignored parameter
*/
static int pci_wakeup(struct pci_dev *pci_dev, void *ign)
{
pci_wakeup_event(pci_dev);
pm_request_resume(&pci_dev->dev);
return 0;
}
/**
* pci_wakeup_bus - Walk given bus and wake up devices on it
* @bus: Top bus of the subtree to walk.
*/
void pci_wakeup_bus(struct pci_bus *bus)
{
if (bus)
pci_walk_bus(bus, pci_wakeup, NULL);
}
/**
* __pci_start_power_transition - Start power transition of a PCI device
* @dev: PCI device to handle.
* @state: State to put the device into.
*/
static void __pci_start_power_transition(struct pci_dev *dev, pci_power_t state)
{
if (state == PCI_D0) {
pci_platform_power_transition(dev, PCI_D0);
/*
* Mandatory power management transition delays, see
* PCI Express Base Specification Revision 2.0 Section
* 6.6.1: Conventional Reset. Do not delay for
* devices powered on/off by corresponding bridge,
* because have already delayed for the bridge.
*/
if (dev->runtime_d3cold) {
if (dev->d3cold_delay && !dev->imm_ready)
msleep(dev->d3cold_delay);
/*
* When powering on a bridge from D3cold, the
* whole hierarchy may be powered on into
* D0uninitialized state, resume them to give
* them a chance to suspend again
*/
pci_wakeup_bus(dev->subordinate);
}
}
}
/**
* __pci_dev_set_current_state - Set current state of a PCI device
* @dev: Device to handle
* @data: pointer to state to be set
*/
static int __pci_dev_set_current_state(struct pci_dev *dev, void *data)
{
pci_power_t state = *(pci_power_t *)data;
dev->current_state = state;
return 0;
}
/**
* pci_bus_set_current_state - Walk given bus and set current state of devices
* @bus: Top bus of the subtree to walk.
* @state: state to be set
*/
void pci_bus_set_current_state(struct pci_bus *bus, pci_power_t state)
{
if (bus)
pci_walk_bus(bus, __pci_dev_set_current_state, &state);
}
/**
* __pci_complete_power_transition - Complete power transition of a PCI device
* @dev: PCI device to handle.
* @state: State to put the device into.
*
* This function should not be called directly by device drivers.
*/
int __pci_complete_power_transition(struct pci_dev *dev, pci_power_t state)
{
int ret;
if (state <= PCI_D0)
return -EINVAL;
ret = pci_platform_power_transition(dev, state);
/* Power off the bridge may power off the whole hierarchy */
if (!ret && state == PCI_D3cold)
pci_bus_set_current_state(dev->subordinate, PCI_D3cold);
return ret;
}
EXPORT_SYMBOL_GPL(__pci_complete_power_transition);
/**
* pci_set_power_state - Set the power state of a PCI device
* @dev: PCI device to handle.
* @state: PCI power state (D0, D1, D2, D3hot) to put the device into.
*
* Transition a device to a new power state, using the platform firmware and/or
* the device's PCI PM registers.
*
* RETURN VALUE:
* -EINVAL if the requested state is invalid.
* -EIO if device does not support PCI PM or its PM capabilities register has a
* wrong version, or device doesn't support the requested state.
* 0 if the transition is to D1 or D2 but D1 and D2 are not supported.
* 0 if device already is in the requested state.
* 0 if the transition is to D3 but D3 is not supported.
* 0 if device's power state has been successfully changed.
*/
int pci_set_power_state(struct pci_dev *dev, pci_power_t state)
{
int error;
/* Bound the state we're entering */
if (state > PCI_D3cold)
state = PCI_D3cold;
else if (state < PCI_D0)
state = PCI_D0;
else if ((state == PCI_D1 || state == PCI_D2) && pci_no_d1d2(dev))
/*
* If the device or the parent bridge do not support PCI
* PM, ignore the request if we're doing anything other
* than putting it into D0 (which would only happen on
* boot).
*/
return 0;
/* Check if we're already there */
if (dev->current_state == state)
return 0;
__pci_start_power_transition(dev, state);
/*
* This device is quirked not to be put into D3, so don't put it in
* D3
*/
if (state >= PCI_D3hot && (dev->dev_flags & PCI_DEV_FLAGS_NO_D3))
return 0;
/*
* To put device in D3cold, we put device into D3hot in native
* way, then put device into D3cold with platform ops
*/
error = pci_raw_set_power_state(dev, state > PCI_D3hot ?
PCI_D3hot : state);
if (!__pci_complete_power_transition(dev, state))
error = 0;
return error;
}
EXPORT_SYMBOL(pci_set_power_state);
/**
* pci_choose_state - Choose the power state of a PCI device
* @dev: PCI device to be suspended
* @state: target sleep state for the whole system. This is the value
* that is passed to suspend() function.
*
* Returns PCI power state suitable for given device and given system
* message.
*/
pci_power_t pci_choose_state(struct pci_dev *dev, pm_message_t state)
{
pci_power_t ret;
if (!dev->pm_cap)
return PCI_D0;
ret = platform_pci_choose_state(dev);
if (ret != PCI_POWER_ERROR)
return ret;
switch (state.event) {
case PM_EVENT_ON:
return PCI_D0;
case PM_EVENT_FREEZE:
case PM_EVENT_PRETHAW:
/* REVISIT both freeze and pre-thaw "should" use D0 */
case PM_EVENT_SUSPEND:
case PM_EVENT_HIBERNATE:
return PCI_D3hot;
default:
pci_info(dev, "unrecognized suspend event %d\n",
state.event);
BUG();
}
return PCI_D0;
}
EXPORT_SYMBOL(pci_choose_state);
#define PCI_EXP_SAVE_REGS 7
static struct pci_cap_saved_state *_pci_find_saved_cap(struct pci_dev *pci_dev,
u16 cap, bool extended)
{
struct pci_cap_saved_state *tmp;
hlist_for_each_entry(tmp, &pci_dev->saved_cap_space, next) {
if (tmp->cap.cap_extended == extended && tmp->cap.cap_nr == cap)
return tmp;
}
return NULL;
}
struct pci_cap_saved_state *pci_find_saved_cap(struct pci_dev *dev, char cap)
{
return _pci_find_saved_cap(dev, cap, false);
}
struct pci_cap_saved_state *pci_find_saved_ext_cap(struct pci_dev *dev, u16 cap)
{
return _pci_find_saved_cap(dev, cap, true);
}
static int pci_save_pcie_state(struct pci_dev *dev)
{
int i = 0;
struct pci_cap_saved_state *save_state;
u16 *cap;
if (!pci_is_pcie(dev))
return 0;
save_state = pci_find_saved_cap(dev, PCI_CAP_ID_EXP);
if (!save_state) {
pci_err(dev, "buffer not found in %s\n", __func__);
return -ENOMEM;
}
cap = (u16 *)&save_state->cap.data[0];
pcie_capability_read_word(dev, PCI_EXP_DEVCTL, &cap[i++]);
pcie_capability_read_word(dev, PCI_EXP_LNKCTL, &cap[i++]);
pcie_capability_read_word(dev, PCI_EXP_SLTCTL, &cap[i++]);
pcie_capability_read_word(dev, PCI_EXP_RTCTL, &cap[i++]);
pcie_capability_read_word(dev, PCI_EXP_DEVCTL2, &cap[i++]);
pcie_capability_read_word(dev, PCI_EXP_LNKCTL2, &cap[i++]);
pcie_capability_read_word(dev, PCI_EXP_SLTCTL2, &cap[i++]);
return 0;
}
static void pci_restore_pcie_state(struct pci_dev *dev)
{
int i = 0;
struct pci_cap_saved_state *save_state;
u16 *cap;
save_state = pci_find_saved_cap(dev, PCI_CAP_ID_EXP);
if (!save_state)
return;
cap = (u16 *)&save_state->cap.data[0];
pcie_capability_write_word(dev, PCI_EXP_DEVCTL, cap[i++]);
pcie_capability_write_word(dev, PCI_EXP_LNKCTL, cap[i++]);
pcie_capability_write_word(dev, PCI_EXP_SLTCTL, cap[i++]);
pcie_capability_write_word(dev, PCI_EXP_RTCTL, cap[i++]);
pcie_capability_write_word(dev, PCI_EXP_DEVCTL2, cap[i++]);
pcie_capability_write_word(dev, PCI_EXP_LNKCTL2, cap[i++]);
pcie_capability_write_word(dev, PCI_EXP_SLTCTL2, cap[i++]);
}
static int pci_save_pcix_state(struct pci_dev *dev)
{
int pos;
struct pci_cap_saved_state *save_state;
pos = pci_find_capability(dev, PCI_CAP_ID_PCIX);
if (!pos)
return 0;
save_state = pci_find_saved_cap(dev, PCI_CAP_ID_PCIX);
if (!save_state) {
pci_err(dev, "buffer not found in %s\n", __func__);
return -ENOMEM;
}
pci_read_config_word(dev, pos + PCI_X_CMD,
(u16 *)save_state->cap.data);
return 0;
}
static void pci_restore_pcix_state(struct pci_dev *dev)
{
int i = 0, pos;
struct pci_cap_saved_state *save_state;
u16 *cap;
save_state = pci_find_saved_cap(dev, PCI_CAP_ID_PCIX);
pos = pci_find_capability(dev, PCI_CAP_ID_PCIX);
if (!save_state || !pos)
return;
cap = (u16 *)&save_state->cap.data[0];
pci_write_config_word(dev, pos + PCI_X_CMD, cap[i++]);
}
static void pci_save_ltr_state(struct pci_dev *dev)
{
int ltr;
struct pci_cap_saved_state *save_state;
u16 *cap;
if (!pci_is_pcie(dev))
return;
ltr = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_LTR);
if (!ltr)
return;
save_state = pci_find_saved_ext_cap(dev, PCI_EXT_CAP_ID_LTR);
if (!save_state) {
pci_err(dev, "no suspend buffer for LTR; ASPM issues possible after resume\n");
return;
}
cap = (u16 *)&save_state->cap.data[0];
pci_read_config_word(dev, ltr + PCI_LTR_MAX_SNOOP_LAT, cap++);
pci_read_config_word(dev, ltr + PCI_LTR_MAX_NOSNOOP_LAT, cap++);
}
static void pci_restore_ltr_state(struct pci_dev *dev)
{
struct pci_cap_saved_state *save_state;
int ltr;
u16 *cap;
save_state = pci_find_saved_ext_cap(dev, PCI_EXT_CAP_ID_LTR);
ltr = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_LTR);
if (!save_state || !ltr)
return;
cap = (u16 *)&save_state->cap.data[0];
pci_write_config_word(dev, ltr + PCI_LTR_MAX_SNOOP_LAT, *cap++);
pci_write_config_word(dev, ltr + PCI_LTR_MAX_NOSNOOP_LAT, *cap++);
}
/**
* pci_save_state - save the PCI configuration space of a device before
* suspending
* @dev: PCI device that we're dealing with
*/
int pci_save_state(struct pci_dev *dev)
{
int i;
/* XXX: 100% dword access ok here? */
for (i = 0; i < 16; i++)
pci_read_config_dword(dev, i * 4, &dev->saved_config_space[i]);
dev->state_saved = true;
i = pci_save_pcie_state(dev);
if (i != 0)
return i;
i = pci_save_pcix_state(dev);
if (i != 0)
return i;
pci_save_ltr_state(dev);
pci_save_dpc_state(dev);
return pci_save_vc_state(dev);
}
EXPORT_SYMBOL(pci_save_state);
static void pci_restore_config_dword(struct pci_dev *pdev, int offset,
u32 saved_val, int retry, bool force)
{
u32 val;
pci_read_config_dword(pdev, offset, &val);
if (!force && val == saved_val)
return;
for (;;) {
pci_dbg(pdev, "restoring config space at offset %#x (was %#x, writing %#x)\n",
offset, val, saved_val);
pci_write_config_dword(pdev, offset, saved_val);
if (retry-- <= 0)
return;
pci_read_config_dword(pdev, offset, &val);
if (val == saved_val)
return;
mdelay(1);
}
}
static void pci_restore_config_space_range(struct pci_dev *pdev,
int start, int end, int retry,
bool force)
{
int index;
for (index = end; index >= start; index--)
pci_restore_config_dword(pdev, 4 * index,
pdev->saved_config_space[index],
retry, force);
}
static void pci_restore_config_space(struct pci_dev *pdev)
{
if (pdev->hdr_type == PCI_HEADER_TYPE_NORMAL) {
pci_restore_config_space_range(pdev, 10, 15, 0, false);
/* Restore BARs before the command register. */
pci_restore_config_space_range(pdev, 4, 9, 10, false);
pci_restore_config_space_range(pdev, 0, 3, 0, false);
} else if (pdev->hdr_type == PCI_HEADER_TYPE_BRIDGE) {
pci_restore_config_space_range(pdev, 12, 15, 0, false);
/*
* Force rewriting of prefetch registers to avoid S3 resume
* issues on Intel PCI bridges that occur when these
* registers are not explicitly written.
*/
pci_restore_config_space_range(pdev, 9, 11, 0, true);
pci_restore_config_space_range(pdev, 0, 8, 0, false);
} else {
pci_restore_config_space_range(pdev, 0, 15, 0, false);
}
}
static void pci_restore_rebar_state(struct pci_dev *pdev)
{
unsigned int pos, nbars, i;
u32 ctrl;
pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_REBAR);
if (!pos)
return;
pci_read_config_dword(pdev, pos + PCI_REBAR_CTRL, &ctrl);
nbars = (ctrl & PCI_REBAR_CTRL_NBAR_MASK) >>
PCI_REBAR_CTRL_NBAR_SHIFT;
for (i = 0; i < nbars; i++, pos += 8) {
struct resource *res;
int bar_idx, size;
pci_read_config_dword(pdev, pos + PCI_REBAR_CTRL, &ctrl);
bar_idx = ctrl & PCI_REBAR_CTRL_BAR_IDX;
res = pdev->resource + bar_idx;
size = order_base_2((resource_size(res) >> 20) | 1) - 1;
ctrl &= ~PCI_REBAR_CTRL_BAR_SIZE;
ctrl |= size << PCI_REBAR_CTRL_BAR_SHIFT;
pci_write_config_dword(pdev, pos + PCI_REBAR_CTRL, ctrl);
}
}
/**
* pci_restore_state - Restore the saved state of a PCI device
* @dev: PCI device that we're dealing with
*/
void pci_restore_state(struct pci_dev *dev)
{
if (!dev->state_saved)
return;
/*
* Restore max latencies (in the LTR capability) before enabling
* LTR itself (in the PCIe capability).
*/
pci_restore_ltr_state(dev);
pci_restore_pcie_state(dev);
pci_restore_pasid_state(dev);
pci_restore_pri_state(dev);
pci_restore_ats_state(dev);
pci_restore_vc_state(dev);
pci_restore_rebar_state(dev);
pci_restore_dpc_state(dev);
pci_cleanup_aer_error_status_regs(dev);
pci_restore_config_space(dev);
pci_restore_pcix_state(dev);
pci_restore_msi_state(dev);
/* Restore ACS and IOV configuration state */
pci_enable_acs(dev);
pci_restore_iov_state(dev);
dev->state_saved = false;
}
EXPORT_SYMBOL(pci_restore_state);
struct pci_saved_state {
u32 config_space[16];
struct pci_cap_saved_data cap[0];
};
/**
* pci_store_saved_state - Allocate and return an opaque struct containing
* the device saved state.
* @dev: PCI device that we're dealing with
*
* Return NULL if no state or error.
*/
struct pci_saved_state *pci_store_saved_state(struct pci_dev *dev)
{
struct pci_saved_state *state;
struct pci_cap_saved_state *tmp;
struct pci_cap_saved_data *cap;
size_t size;
if (!dev->state_saved)
return NULL;
size = sizeof(*state) + sizeof(struct pci_cap_saved_data);
hlist_for_each_entry(tmp, &dev->saved_cap_space, next)
size += sizeof(struct pci_cap_saved_data) + tmp->cap.size;
state = kzalloc(size, GFP_KERNEL);
if (!state)
return NULL;
memcpy(state->config_space, dev->saved_config_space,
sizeof(state->config_space));
cap = state->cap;
hlist_for_each_entry(tmp, &dev->saved_cap_space, next) {
size_t len = sizeof(struct pci_cap_saved_data) + tmp->cap.size;
memcpy(cap, &tmp->cap, len);
cap = (struct pci_cap_saved_data *)((u8 *)cap + len);
}
/* Empty cap_save terminates list */
return state;
}
EXPORT_SYMBOL_GPL(pci_store_saved_state);
/**
* pci_load_saved_state - Reload the provided save state into struct pci_dev.
* @dev: PCI device that we're dealing with
* @state: Saved state returned from pci_store_saved_state()
*/
int pci_load_saved_state(struct pci_dev *dev,
struct pci_saved_state *state)
{
struct pci_cap_saved_data *cap;
dev->state_saved = false;
if (!state)
return 0;
memcpy(dev->saved_config_space, state->config_space,
sizeof(state->config_space));
cap = state->cap;
while (cap->size) {
struct pci_cap_saved_state *tmp;
tmp = _pci_find_saved_cap(dev, cap->cap_nr, cap->cap_extended);
if (!tmp || tmp->cap.size != cap->size)
return -EINVAL;
memcpy(tmp->cap.data, cap->data, tmp->cap.size);
cap = (struct pci_cap_saved_data *)((u8 *)cap +
sizeof(struct pci_cap_saved_data) + cap->size);
}
dev->state_saved = true;
return 0;
}
EXPORT_SYMBOL_GPL(pci_load_saved_state);
/**
* pci_load_and_free_saved_state - Reload the save state pointed to by state,
* and free the memory allocated for it.
* @dev: PCI device that we're dealing with
* @state: Pointer to saved state returned from pci_store_saved_state()
*/
int pci_load_and_free_saved_state(struct pci_dev *dev,
struct pci_saved_state **state)
{
int ret = pci_load_saved_state(dev, *state);
kfree(*state);
*state = NULL;
return ret;
}
EXPORT_SYMBOL_GPL(pci_load_and_free_saved_state);
int __weak pcibios_enable_device(struct pci_dev *dev, int bars)
{
return pci_enable_resources(dev, bars);
}
static int do_pci_enable_device(struct pci_dev *dev, int bars)
{
int err;
struct pci_dev *bridge;
u16 cmd;
u8 pin;
err = pci_set_power_state(dev, PCI_D0);
if (err < 0 && err != -EIO)
return err;
bridge = pci_upstream_bridge(dev);
if (bridge)
pcie_aspm_powersave_config_link(bridge);
err = pcibios_enable_device(dev, bars);
if (err < 0)
return err;
pci_fixup_device(pci_fixup_enable, dev);
if (dev->msi_enabled || dev->msix_enabled)
return 0;
pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin);
if (pin) {
pci_read_config_word(dev, PCI_COMMAND, &cmd);
if (cmd & PCI_COMMAND_INTX_DISABLE)
pci_write_config_word(dev, PCI_COMMAND,
cmd & ~PCI_COMMAND_INTX_DISABLE);
}
return 0;
}
/**
* pci_reenable_device - Resume abandoned device
* @dev: PCI device to be resumed
*
* NOTE: This function is a backend of pci_default_resume() and is not supposed
* to be called by normal code, write proper resume handler and use it instead.
*/
int pci_reenable_device(struct pci_dev *dev)
{
if (pci_is_enabled(dev))
return do_pci_enable_device(dev, (1 << PCI_NUM_RESOURCES) - 1);
return 0;
}
EXPORT_SYMBOL(pci_reenable_device);
static void pci_enable_bridge(struct pci_dev *dev)
{
struct pci_dev *bridge;
int retval;
bridge = pci_upstream_bridge(dev);
if (bridge)
pci_enable_bridge(bridge);
if (pci_is_enabled(dev)) {
if (!dev->is_busmaster)
pci_set_master(dev);
return;
}
retval = pci_enable_device(dev);
if (retval)
pci_err(dev, "Error enabling bridge (%d), continuing\n",
retval);
pci_set_master(dev);
}
static int pci_enable_device_flags(struct pci_dev *dev, unsigned long flags)
{
struct pci_dev *bridge;
int err;
int i, bars = 0;
/*
* Power state could be unknown at this point, either due to a fresh
* boot or a device removal call. So get the current power state
* so that things like MSI message writing will behave as expected
* (e.g. if the device really is in D0 at enable time).
*/
if (dev->pm_cap) {
u16 pmcsr;
pci_read_config_word(dev, dev->pm_cap + PCI_PM_CTRL, &pmcsr);
dev->current_state = (pmcsr & PCI_PM_CTRL_STATE_MASK);
}
if (atomic_inc_return(&dev->enable_cnt) > 1)
return 0; /* already enabled */
bridge = pci_upstream_bridge(dev);
if (bridge)
pci_enable_bridge(bridge);
/* only skip sriov related */
for (i = 0; i <= PCI_ROM_RESOURCE; i++)
if (dev->resource[i].flags & flags)
bars |= (1 << i);
for (i = PCI_BRIDGE_RESOURCES; i < DEVICE_COUNT_RESOURCE; i++)
if (dev->resource[i].flags & flags)
bars |= (1 << i);
err = do_pci_enable_device(dev, bars);
if (err < 0)
atomic_dec(&dev->enable_cnt);
return err;
}
/**
* pci_enable_device_io - Initialize a device for use with IO space
* @dev: PCI device to be initialized
*
* Initialize device before it's used by a driver. Ask low-level code
* to enable I/O resources. Wake up the device if it was suspended.
* Beware, this function can fail.
*/
int pci_enable_device_io(struct pci_dev *dev)
{
return pci_enable_device_flags(dev, IORESOURCE_IO);
}
EXPORT_SYMBOL(pci_enable_device_io);
/**
* pci_enable_device_mem - Initialize a device for use with Memory space
* @dev: PCI device to be initialized
*
* Initialize device before it's used by a driver. Ask low-level code
* to enable Memory resources. Wake up the device if it was suspended.
* Beware, this function can fail.
*/
int pci_enable_device_mem(struct pci_dev *dev)
{
return pci_enable_device_flags(dev, IORESOURCE_MEM);
}
EXPORT_SYMBOL(pci_enable_device_mem);
/**
* pci_enable_device - Initialize device before it's used by a driver.
* @dev: PCI device to be initialized
*
* Initialize device before it's used by a driver. Ask low-level code
* to enable I/O and memory. Wake up the device if it was suspended.
* Beware, this function can fail.
*
* Note we don't actually enable the device many times if we call
* this function repeatedly (we just increment the count).
*/
int pci_enable_device(struct pci_dev *dev)
{
return pci_enable_device_flags(dev, IORESOURCE_MEM | IORESOURCE_IO);
}
EXPORT_SYMBOL(pci_enable_device);
/*
* Managed PCI resources. This manages device on/off, INTx/MSI/MSI-X
* on/off and BAR regions. pci_dev itself records MSI/MSI-X status, so
* there's no need to track it separately. pci_devres is initialized
* when a device is enabled using managed PCI device enable interface.
*/
struct pci_devres {
unsigned int enabled:1;
unsigned int pinned:1;
unsigned int orig_intx:1;
unsigned int restore_intx:1;
unsigned int mwi:1;
u32 region_mask;
};
static void pcim_release(struct device *gendev, void *res)
{
struct pci_dev *dev = to_pci_dev(gendev);
struct pci_devres *this = res;
int i;
if (dev->msi_enabled)
pci_disable_msi(dev);
if (dev->msix_enabled)
pci_disable_msix(dev);
for (i = 0; i < DEVICE_COUNT_RESOURCE; i++)
if (this->region_mask & (1 << i))
pci_release_region(dev, i);
if (this->mwi)
pci_clear_mwi(dev);
if (this->restore_intx)
pci_intx(dev, this->orig_intx);
if (this->enabled && !this->pinned)
pci_disable_device(dev);
}
static struct pci_devres *get_pci_dr(struct pci_dev *pdev)
{
struct pci_devres *dr, *new_dr;
dr = devres_find(&pdev->dev, pcim_release, NULL, NULL);
if (dr)
return dr;
new_dr = devres_alloc(pcim_release, sizeof(*new_dr), GFP_KERNEL);
if (!new_dr)
return NULL;
return devres_get(&pdev->dev, new_dr, NULL, NULL);
}
static struct pci_devres *find_pci_dr(struct pci_dev *pdev)
{
if (pci_is_managed(pdev))
return devres_find(&pdev->dev, pcim_release, NULL, NULL);
return NULL;
}
/**
* pcim_enable_device - Managed pci_enable_device()
* @pdev: PCI device to be initialized
*
* Managed pci_enable_device().
*/
int pcim_enable_device(struct pci_dev *pdev)
{
struct pci_devres *dr;
int rc;
dr = get_pci_dr(pdev);
if (unlikely(!dr))
return -ENOMEM;
if (dr->enabled)
return 0;
rc = pci_enable_device(pdev);
if (!rc) {
pdev->is_managed = 1;
dr->enabled = 1;
}
return rc;
}
EXPORT_SYMBOL(pcim_enable_device);
/**
* pcim_pin_device - Pin managed PCI device
* @pdev: PCI device to pin
*
* Pin managed PCI device @pdev. Pinned device won't be disabled on
* driver detach. @pdev must have been enabled with
* pcim_enable_device().
*/
void pcim_pin_device(struct pci_dev *pdev)
{
struct pci_devres *dr;
dr = find_pci_dr(pdev);
WARN_ON(!dr || !dr->enabled);
if (dr)
dr->pinned = 1;
}
EXPORT_SYMBOL(pcim_pin_device);
/*
* pcibios_add_device - provide arch specific hooks when adding device dev
* @dev: the PCI device being added
*
* Permits the platform to provide architecture specific functionality when
* devices are added. This is the default implementation. Architecture
* implementations can override this.
*/
int __weak pcibios_add_device(struct pci_dev *dev)
{
return 0;
}
/**
* pcibios_release_device - provide arch specific hooks when releasing
* device dev
* @dev: the PCI device being released
*
* Permits the platform to provide architecture specific functionality when
* devices are released. This is the default implementation. Architecture
* implementations can override this.
*/
void __weak pcibios_release_device(struct pci_dev *dev) {}
/**
* pcibios_disable_device - disable arch specific PCI resources for device dev
* @dev: the PCI device to disable
*
* Disables architecture specific PCI resources for the device. This
* is the default implementation. Architecture implementations can
* override this.
*/
void __weak pcibios_disable_device(struct pci_dev *dev) {}
/**
* pcibios_penalize_isa_irq - penalize an ISA IRQ
* @irq: ISA IRQ to penalize
* @active: IRQ active or not
*
* Permits the platform to provide architecture-specific functionality when
* penalizing ISA IRQs. This is the default implementation. Architecture
* implementations can override this.
*/
void __weak pcibios_penalize_isa_irq(int irq, int active) {}
static void do_pci_disable_device(struct pci_dev *dev)
{
u16 pci_command;
pci_read_config_word(dev, PCI_COMMAND, &pci_command);
if (pci_command & PCI_COMMAND_MASTER) {
pci_command &= ~PCI_COMMAND_MASTER;
pci_write_config_word(dev, PCI_COMMAND, pci_command);
}
pcibios_disable_device(dev);
}
/**
* pci_disable_enabled_device - Disable device without updating enable_cnt
* @dev: PCI device to disable
*
* NOTE: This function is a backend of PCI power management routines and is
* not supposed to be called drivers.
*/
void pci_disable_enabled_device(struct pci_dev *dev)
{
if (pci_is_enabled(dev))
do_pci_disable_device(dev);
}
/**
* pci_disable_device - Disable PCI device after use
* @dev: PCI device to be disabled
*
* Signal to the system that the PCI device is not in use by the system
* anymore. This only involves disabling PCI bus-mastering, if active.
*
* Note we don't actually disable the device until all callers of
* pci_enable_device() have called pci_disable_device().
*/
void pci_disable_device(struct pci_dev *dev)
{
struct pci_devres *dr;
dr = find_pci_dr(dev);
if (dr)
dr->enabled = 0;
dev_WARN_ONCE(&dev->dev, atomic_read(&dev->enable_cnt) <= 0,
"disabling already-disabled device");
if (atomic_dec_return(&dev->enable_cnt) != 0)
return;
do_pci_disable_device(dev);
dev->is_busmaster = 0;
}
EXPORT_SYMBOL(pci_disable_device);
/**
* pcibios_set_pcie_reset_state - set reset state for device dev
* @dev: the PCIe device reset
* @state: Reset state to enter into
*
* Set the PCIe reset state for the device. This is the default
* implementation. Architecture implementations can override this.
*/
int __weak pcibios_set_pcie_reset_state(struct pci_dev *dev,
enum pcie_reset_state state)
{
return -EINVAL;
}
/**
* pci_set_pcie_reset_state - set reset state for device dev
* @dev: the PCIe device reset
* @state: Reset state to enter into
*
* Sets the PCI reset state for the device.
*/
int pci_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state state)
{
return pcibios_set_pcie_reset_state(dev, state);
}
EXPORT_SYMBOL_GPL(pci_set_pcie_reset_state);
/**
* pcie_clear_root_pme_status - Clear root port PME interrupt status.
* @dev: PCIe root port or event collector.
*/
void pcie_clear_root_pme_status(struct pci_dev *dev)
{
pcie_capability_set_dword(dev, PCI_EXP_RTSTA, PCI_EXP_RTSTA_PME);
}
/**
* pci_check_pme_status - Check if given device has generated PME.
* @dev: Device to check.
*
* Check the PME status of the device and if set, clear it and clear PME enable
* (if set). Return 'true' if PME status and PME enable were both set or
* 'false' otherwise.
*/
bool pci_check_pme_status(struct pci_dev *dev)
{
int pmcsr_pos;
u16 pmcsr;
bool ret = false;
if (!dev->pm_cap)
return false;
pmcsr_pos = dev->pm_cap + PCI_PM_CTRL;
pci_read_config_word(dev, pmcsr_pos, &pmcsr);
if (!(pmcsr & PCI_PM_CTRL_PME_STATUS))
return false;
/* Clear PME status. */
pmcsr |= PCI_PM_CTRL_PME_STATUS;
if (pmcsr & PCI_PM_CTRL_PME_ENABLE) {
/* Disable PME to avoid interrupt flood. */
pmcsr &= ~PCI_PM_CTRL_PME_ENABLE;
ret = true;
}
pci_write_config_word(dev, pmcsr_pos, pmcsr);
return ret;
}
/**
* pci_pme_wakeup - Wake up a PCI device if its PME Status bit is set.
* @dev: Device to handle.
* @pme_poll_reset: Whether or not to reset the device's pme_poll flag.
*
* Check if @dev has generated PME and queue a resume request for it in that
* case.
*/
static int pci_pme_wakeup(struct pci_dev *dev, void *pme_poll_reset)
{
if (pme_poll_reset && dev->pme_poll)
dev->pme_poll = false;
if (pci_check_pme_status(dev)) {
pci_wakeup_event(dev);
pm_request_resume(&dev->dev);
}
return 0;
}
/**
* pci_pme_wakeup_bus - Walk given bus and wake up devices on it, if necessary.
* @bus: Top bus of the subtree to walk.
*/
void pci_pme_wakeup_bus(struct pci_bus *bus)
{
if (bus)
pci_walk_bus(bus, pci_pme_wakeup, (void *)true);
}
/**
* pci_pme_capable - check the capability of PCI device to generate PME#
* @dev: PCI device to handle.
* @state: PCI state from which device will issue PME#.
*/
bool pci_pme_capable(struct pci_dev *dev, pci_power_t state)
{
if (!dev->pm_cap)
return false;
return !!(dev->pme_support & (1 << state));
}
EXPORT_SYMBOL(pci_pme_capable);
static void pci_pme_list_scan(struct work_struct *work)
{
struct pci_pme_device *pme_dev, *n;
mutex_lock(&pci_pme_list_mutex);
list_for_each_entry_safe(pme_dev, n, &pci_pme_list, list) {
if (pme_dev->dev->pme_poll) {
struct pci_dev *bridge;
bridge = pme_dev->dev->bus->self;
/*
* If bridge is in low power state, the
* configuration space of subordinate devices
* may be not accessible
*/
if (bridge && bridge->current_state != PCI_D0)
continue;
pci_pme_wakeup(pme_dev->dev, NULL);
} else {
list_del(&pme_dev->list);
kfree(pme_dev);
}
}
if (!list_empty(&pci_pme_list))
queue_delayed_work(system_freezable_wq, &pci_pme_work,
msecs_to_jiffies(PME_TIMEOUT));
mutex_unlock(&pci_pme_list_mutex);
}
static void __pci_pme_active(struct pci_dev *dev, bool enable)
{
u16 pmcsr;
if (!dev->pme_support)
return;
pci_read_config_word(dev, dev->pm_cap + PCI_PM_CTRL, &pmcsr);
/* Clear PME_Status by writing 1 to it and enable PME# */
pmcsr |= PCI_PM_CTRL_PME_STATUS | PCI_PM_CTRL_PME_ENABLE;
if (!enable)
pmcsr &= ~PCI_PM_CTRL_PME_ENABLE;
pci_write_config_word(dev, dev->pm_cap + PCI_PM_CTRL, pmcsr);
}
/**
* pci_pme_restore - Restore PME configuration after config space restore.
* @dev: PCI device to update.
*/
void pci_pme_restore(struct pci_dev *dev)
{
u16 pmcsr;
if (!dev->pme_support)
return;
pci_read_config_word(dev, dev->pm_cap + PCI_PM_CTRL, &pmcsr);
if (dev->wakeup_prepared) {
pmcsr |= PCI_PM_CTRL_PME_ENABLE;
pmcsr &= ~PCI_PM_CTRL_PME_STATUS;
} else {
pmcsr &= ~PCI_PM_CTRL_PME_ENABLE;
pmcsr |= PCI_PM_CTRL_PME_STATUS;
}
pci_write_config_word(dev, dev->pm_cap + PCI_PM_CTRL, pmcsr);
}
/**
* pci_pme_active - enable or disable PCI device's PME# function
* @dev: PCI device to handle.
* @enable: 'true' to enable PME# generation; 'false' to disable it.
*
* The caller must verify that the device is capable of generating PME# before
* calling this function with @enable equal to 'true'.
*/
void pci_pme_active(struct pci_dev *dev, bool enable)
{
__pci_pme_active(dev, enable);
/*
* PCI (as opposed to PCIe) PME requires that the device have
* its PME# line hooked up correctly. Not all hardware vendors
* do this, so the PME never gets delivered and the device
* remains asleep. The easiest way around this is to
* periodically walk the list of suspended devices and check
* whether any have their PME flag set. The assumption is that
* we'll wake up often enough anyway that this won't be a huge
* hit, and the power savings from the devices will still be a
* win.
*
* Although PCIe uses in-band PME message instead of PME# line
* to report PME, PME does not work for some PCIe devices in
* reality. For example, there are devices that set their PME
* status bits, but don't really bother to send a PME message;
* there are PCI Express Root Ports that don't bother to
* trigger interrupts when they receive PME messages from the
* devices below. So PME poll is used for PCIe devices too.
*/
if (dev->pme_poll) {
struct pci_pme_device *pme_dev;
if (enable) {
pme_dev = kmalloc(sizeof(struct pci_pme_device),
GFP_KERNEL);
if (!pme_dev) {
pci_warn(dev, "can't enable PME#\n");
return;
}
pme_dev->dev = dev;
mutex_lock(&pci_pme_list_mutex);
list_add(&pme_dev->list, &pci_pme_list);
if (list_is_singular(&pci_pme_list))
queue_delayed_work(system_freezable_wq,
&pci_pme_work,
msecs_to_jiffies(PME_TIMEOUT));
mutex_unlock(&pci_pme_list_mutex);
} else {
mutex_lock(&pci_pme_list_mutex);
list_for_each_entry(pme_dev, &pci_pme_list, list) {
if (pme_dev->dev == dev) {
list_del(&pme_dev->list);
kfree(pme_dev);
break;
}
}
mutex_unlock(&pci_pme_list_mutex);
}
}
pci_dbg(dev, "PME# %s\n", enable ? "enabled" : "disabled");
}
EXPORT_SYMBOL(pci_pme_active);
/**
* __pci_enable_wake - enable PCI device as wakeup event source
* @dev: PCI device affected
* @state: PCI state from which device will issue wakeup events
* @enable: True to enable event generation; false to disable
*
* This enables the device as a wakeup event source, or disables it.
* When such events involves platform-specific hooks, those hooks are
* called automatically by this routine.
*
* Devices with legacy power management (no standard PCI PM capabilities)
* always require such platform hooks.
*
* RETURN VALUE:
* 0 is returned on success
* -EINVAL is returned if device is not supposed to wake up the system
* Error code depending on the platform is returned if both the platform and
* the native mechanism fail to enable the generation of wake-up events
*/
static int __pci_enable_wake(struct pci_dev *dev, pci_power_t state, bool enable)
{
int ret = 0;
/*
* Bridges that are not power-manageable directly only signal
* wakeup on behalf of subordinate devices which is set up
* elsewhere, so skip them. However, bridges that are
* power-manageable may signal wakeup for themselves (for example,
* on a hotplug event) and they need to be covered here.
*/
if (!pci_power_manageable(dev))
return 0;
/* Don't do the same thing twice in a row for one device. */
if (!!enable == !!dev->wakeup_prepared)
return 0;
/*
* According to "PCI System Architecture" 4th ed. by Tom Shanley & Don
* Anderson we should be doing PME# wake enable followed by ACPI wake
* enable. To disable wake-up we call the platform first, for symmetry.
*/
if (enable) {
int error;
if (pci_pme_capable(dev, state))
pci_pme_active(dev, true);
else
ret = 1;
error = platform_pci_set_wakeup(dev, true);
if (ret)
ret = error;
if (!ret)
dev->wakeup_prepared = true;
} else {
platform_pci_set_wakeup(dev, false);
pci_pme_active(dev, false);
dev->wakeup_prepared = false;
}
return ret;
}
/**
* pci_enable_wake - change wakeup settings for a PCI device
* @pci_dev: Target device
* @state: PCI state from which device will issue wakeup events
* @enable: Whether or not to enable event generation
*
* If @enable is set, check device_may_wakeup() for the device before calling
* __pci_enable_wake() for it.
*/
int pci_enable_wake(struct pci_dev *pci_dev, pci_power_t state, bool enable)
{
if (enable && !device_may_wakeup(&pci_dev->dev))
return -EINVAL;
return __pci_enable_wake(pci_dev, state, enable);
}
EXPORT_SYMBOL(pci_enable_wake);
/**
* pci_wake_from_d3 - enable/disable device to wake up from D3_hot or D3_cold
* @dev: PCI device to prepare
* @enable: True to enable wake-up event generation; false to disable
*
* Many drivers want the device to wake up the system from D3_hot or D3_cold
* and this function allows them to set that up cleanly - pci_enable_wake()
* should not be called twice in a row to enable wake-up due to PCI PM vs ACPI
* ordering constraints.
*
* This function only returns error code if the device is not allowed to wake
* up the system from sleep or it is not capable of generating PME# from both
* D3_hot and D3_cold and the platform is unable to enable wake-up power for it.
*/
int pci_wake_from_d3(struct pci_dev *dev, bool enable)
{
return pci_pme_capable(dev, PCI_D3cold) ?
pci_enable_wake(dev, PCI_D3cold, enable) :
pci_enable_wake(dev, PCI_D3hot, enable);
}
EXPORT_SYMBOL(pci_wake_from_d3);
/**
* pci_target_state - find an appropriate low power state for a given PCI dev
* @dev: PCI device
* @wakeup: Whether or not wakeup functionality will be enabled for the device.
*
* Use underlying platform code to find a supported low power state for @dev.
* If the platform can't manage @dev, return the deepest state from which it
* can generate wake events, based on any available PME info.
*/
static pci_power_t pci_target_state(struct pci_dev *dev, bool wakeup)
{
pci_power_t target_state = PCI_D3hot;
if (platform_pci_power_manageable(dev)) {
/*
* Call the platform to find the target state for the device.
*/
pci_power_t state = platform_pci_choose_state(dev);
switch (state) {
case PCI_POWER_ERROR:
case PCI_UNKNOWN:
break;
case PCI_D1:
case PCI_D2:
if (pci_no_d1d2(dev))
break;
/* else, fall through */
default:
target_state = state;
}
return target_state;
}
if (!dev->pm_cap)
target_state = PCI_D0;
/*
* If the device is in D3cold even though it's not power-manageable by
* the platform, it may have been powered down by non-standard means.
* Best to let it slumber.
*/
if (dev->current_state == PCI_D3cold)
target_state = PCI_D3cold;
if (wakeup) {
/*
* Find the deepest state from which the device can generate
* PME#.
*/
if (dev->pme_support) {
while (target_state
&& !(dev->pme_support & (1 << target_state)))
target_state--;
}
}
return target_state;
}
/**
* pci_prepare_to_sleep - prepare PCI device for system-wide transition
* into a sleep state
* @dev: Device to handle.
*
* Choose the power state appropriate for the device depending on whether
* it can wake up the system and/or is power manageable by the platform
* (PCI_D3hot is the default) and put the device into that state.
*/
int pci_prepare_to_sleep(struct pci_dev *dev)
{
bool wakeup = device_may_wakeup(&dev->dev);
pci_power_t target_state = pci_target_state(dev, wakeup);
int error;
if (target_state == PCI_POWER_ERROR)
return -EIO;
pci_enable_wake(dev, target_state, wakeup);
error = pci_set_power_state(dev, target_state);
if (error)
pci_enable_wake(dev, target_state, false);
return error;
}
EXPORT_SYMBOL(pci_prepare_to_sleep);
/**
* pci_back_from_sleep - turn PCI device on during system-wide transition
* into working state
* @dev: Device to handle.
*
* Disable device's system wake-up capability and put it into D0.
*/
int pci_back_from_sleep(struct pci_dev *dev)
{
pci_enable_wake(dev, PCI_D0, false);
return pci_set_power_state(dev, PCI_D0);
}
EXPORT_SYMBOL(pci_back_from_sleep);
/**
* pci_finish_runtime_suspend - Carry out PCI-specific part of runtime suspend.
* @dev: PCI device being suspended.
*
* Prepare @dev to generate wake-up events at run time and put it into a low
* power state.
*/
int pci_finish_runtime_suspend(struct pci_dev *dev)
{
pci_power_t target_state;
int error;
target_state = pci_target_state(dev, device_can_wakeup(&dev->dev));
if (target_state == PCI_POWER_ERROR)
return -EIO;
dev->runtime_d3cold = target_state == PCI_D3cold;
__pci_enable_wake(dev, target_state, pci_dev_run_wake(dev));
error = pci_set_power_state(dev, target_state);
if (error) {
pci_enable_wake(dev, target_state, false);
dev->runtime_d3cold = false;
}
return error;
}
/**
* pci_dev_run_wake - Check if device can generate run-time wake-up events.
* @dev: Device to check.
*
* Return true if the device itself is capable of generating wake-up events
* (through the platform or using the native PCIe PME) or if the device supports
* PME and one of its upstream bridges can generate wake-up events.
*/
bool pci_dev_run_wake(struct pci_dev *dev)
{
struct pci_bus *bus = dev->bus;
if (!dev->pme_support)
return false;
/* PME-capable in principle, but not from the target power state */
if (!pci_pme_capable(dev, pci_target_state(dev, true)))
return false;
if (device_can_wakeup(&dev->dev))
return true;
while (bus->parent) {
struct pci_dev *bridge = bus->self;
if (device_can_wakeup(&bridge->dev))
return true;
bus = bus->parent;
}
/* We have reached the root bus. */
if (bus->bridge)
return device_can_wakeup(bus->bridge);
return false;
}
EXPORT_SYMBOL_GPL(pci_dev_run_wake);
/**
* pci_dev_keep_suspended - Check if the device can stay in the suspended state.
* @pci_dev: Device to check.
*
* Return 'true' if the device is runtime-suspended, it doesn't have to be
* reconfigured due to wakeup settings difference between system and runtime
* suspend and the current power state of it is suitable for the upcoming
* (system) transition.
*
* If the device is not configured for system wakeup, disable PME for it before
* returning 'true' to prevent it from waking up the system unnecessarily.
*/
bool pci_dev_keep_suspended(struct pci_dev *pci_dev)
{
struct device *dev = &pci_dev->dev;
bool wakeup = device_may_wakeup(dev);
if (!pm_runtime_suspended(dev)
|| pci_target_state(pci_dev, wakeup) != pci_dev->current_state
|| platform_pci_need_resume(pci_dev))
return false;
/*
* At this point the device is good to go unless it's been configured
* to generate PME at the runtime suspend time, but it is not supposed
* to wake up the system. In that case, simply disable PME for it
* (it will have to be re-enabled on exit from system resume).
*
* If the device's power state is D3cold and the platform check above
* hasn't triggered, the device's configuration is suitable and we don't
* need to manipulate it at all.
*/
spin_lock_irq(&dev->power.lock);
if (pm_runtime_suspended(dev) && pci_dev->current_state < PCI_D3cold &&
!wakeup)
__pci_pme_active(pci_dev, false);
spin_unlock_irq(&dev->power.lock);
return true;
}
/**
* pci_dev_complete_resume - Finalize resume from system sleep for a device.
* @pci_dev: Device to handle.
*
* If the device is runtime suspended and wakeup-capable, enable PME for it as
* it might have been disabled during the prepare phase of system suspend if
* the device was not configured for system wakeup.
*/
void pci_dev_complete_resume(struct pci_dev *pci_dev)
{
struct device *dev = &pci_dev->dev;
if (!pci_dev_run_wake(pci_dev))
return;
spin_lock_irq(&dev->power.lock);
if (pm_runtime_suspended(dev) && pci_dev->current_state < PCI_D3cold)
__pci_pme_active(pci_dev, true);
spin_unlock_irq(&dev->power.lock);
}
void pci_config_pm_runtime_get(struct pci_dev *pdev)
{
struct device *dev = &pdev->dev;
struct device *parent = dev->parent;
if (parent)
pm_runtime_get_sync(parent);
pm_runtime_get_noresume(dev);
/*
* pdev->current_state is set to PCI_D3cold during suspending,
* so wait until suspending completes
*/
pm_runtime_barrier(dev);
/*
* Only need to resume devices in D3cold, because config
* registers are still accessible for devices suspended but
* not in D3cold.
*/
if (pdev->current_state == PCI_D3cold)
pm_runtime_resume(dev);
}
void pci_config_pm_runtime_put(struct pci_dev *pdev)
{
struct device *dev = &pdev->dev;
struct device *parent = dev->parent;
pm_runtime_put(dev);
if (parent)
pm_runtime_put_sync(parent);
}
static const struct dmi_system_id bridge_d3_blacklist[] = {
#ifdef CONFIG_X86
{
/*
* Gigabyte X299 root port is not marked as hotplug capable
* which allows Linux to power manage it. However, this
* confuses the BIOS SMI handler so don't power manage root
* ports on that system.
*/
.ident = "X299 DESIGNARE EX-CF",
.matches = {
DMI_MATCH(DMI_BOARD_VENDOR, "Gigabyte Technology Co., Ltd."),
DMI_MATCH(DMI_BOARD_NAME, "X299 DESIGNARE EX-CF"),
},
},
#endif
{ }
};
/**
* pci_bridge_d3_possible - Is it possible to put the bridge into D3
* @bridge: Bridge to check
*
* This function checks if it is possible to move the bridge to D3.
* Currently we only allow D3 for recent enough PCIe ports and Thunderbolt.
*/
bool pci_bridge_d3_possible(struct pci_dev *bridge)
{
if (!pci_is_pcie(bridge))
return false;
switch (pci_pcie_type(bridge)) {
case PCI_EXP_TYPE_ROOT_PORT:
case PCI_EXP_TYPE_UPSTREAM:
case PCI_EXP_TYPE_DOWNSTREAM:
if (pci_bridge_d3_disable)
return false;
/*
* Hotplug ports handled by firmware in System Management Mode
* may not be put into D3 by the OS (Thunderbolt on non-Macs).
*/
if (bridge->is_hotplug_bridge && !pciehp_is_native(bridge))
return false;
if (pci_bridge_d3_force)
return true;
/* Even the oldest 2010 Thunderbolt controller supports D3. */
if (bridge->is_thunderbolt)
return true;
/* Platform might know better if the bridge supports D3 */
if (platform_pci_bridge_d3(bridge))
return true;
/*
* Hotplug ports handled natively by the OS were not validated
* by vendors for runtime D3 at least until 2018 because there
* was no OS support.
*/
if (bridge->is_hotplug_bridge)
return false;
if (dmi_check_system(bridge_d3_blacklist))
return false;
/*
* It should be safe to put PCIe ports from 2015 or newer
* to D3.
*/
if (dmi_get_bios_year() >= 2015)
return true;
break;
}
return false;
}
static int pci_dev_check_d3cold(struct pci_dev *dev, void *data)
{
bool *d3cold_ok = data;
if (/* The device needs to be allowed to go D3cold ... */
dev->no_d3cold || !dev->d3cold_allowed ||
/* ... and if it is wakeup capable to do so from D3cold. */
(device_may_wakeup(&dev->dev) &&
!pci_pme_capable(dev, PCI_D3cold)) ||
/* If it is a bridge it must be allowed to go to D3. */
!pci_power_manageable(dev))
*d3cold_ok = false;
return !*d3cold_ok;
}
/*
* pci_bridge_d3_update - Update bridge D3 capabilities
* @dev: PCI device which is changed
*
* Update upstream bridge PM capabilities accordingly depending on if the
* device PM configuration was changed or the device is being removed. The
* change is also propagated upstream.
*/
void pci_bridge_d3_update(struct pci_dev *dev)
{
bool remove = !device_is_registered(&dev->dev);
struct pci_dev *bridge;
bool d3cold_ok = true;
bridge = pci_upstream_bridge(dev);
if (!bridge || !pci_bridge_d3_possible(bridge))
return;
/*
* If D3 is currently allowed for the bridge, removing one of its
* children won't change that.
*/
if (remove && bridge->bridge_d3)
return;
/*
* If D3 is currently allowed for the bridge and a child is added or
* changed, disallowance of D3 can only be caused by that child, so
* we only need to check that single device, not any of its siblings.
*
* If D3 is currently not allowed for the bridge, checking the device
* first may allow us to skip checking its siblings.
*/
if (!remove)
pci_dev_check_d3cold(dev, &d3cold_ok);
/*
* If D3 is currently not allowed for the bridge, this may be caused
* either by the device being changed/removed or any of its siblings,
* so we need to go through all children to find out if one of them
* continues to block D3.
*/
if (d3cold_ok && !bridge->bridge_d3)
pci_walk_bus(bridge->subordinate, pci_dev_check_d3cold,
&d3cold_ok);
if (bridge->bridge_d3 != d3cold_ok) {
bridge->bridge_d3 = d3cold_ok;
/* Propagate change to upstream bridges */
pci_bridge_d3_update(bridge);
}
}
/**
* pci_d3cold_enable - Enable D3cold for device
* @dev: PCI device to handle
*
* This function can be used in drivers to enable D3cold from the device
* they handle. It also updates upstream PCI bridge PM capabilities
* accordingly.
*/
void pci_d3cold_enable(struct pci_dev *dev)
{
if (dev->no_d3cold) {
dev->no_d3cold = false;
pci_bridge_d3_update(dev);
}
}
EXPORT_SYMBOL_GPL(pci_d3cold_enable);
/**
* pci_d3cold_disable - Disable D3cold for device
* @dev: PCI device to handle
*
* This function can be used in drivers to disable D3cold from the device
* they handle. It also updates upstream PCI bridge PM capabilities
* accordingly.
*/
void pci_d3cold_disable(struct pci_dev *dev)
{
if (!dev->no_d3cold) {
dev->no_d3cold = true;
pci_bridge_d3_update(dev);
}
}
EXPORT_SYMBOL_GPL(pci_d3cold_disable);
/**
* pci_pm_init - Initialize PM functions of given PCI device
* @dev: PCI device to handle.
*/
void pci_pm_init(struct pci_dev *dev)
{
int pm;
u16 status;
u16 pmc;
pm_runtime_forbid(&dev->dev);
pm_runtime_set_active(&dev->dev);
pm_runtime_enable(&dev->dev);
device_enable_async_suspend(&dev->dev);
dev->wakeup_prepared = false;
dev->pm_cap = 0;
dev->pme_support = 0;
/* find PCI PM capability in list */
pm = pci_find_capability(dev, PCI_CAP_ID_PM);
if (!pm)
return;
/* Check device's ability to generate PME# */
pci_read_config_word(dev, pm + PCI_PM_PMC, &pmc);
if ((pmc & PCI_PM_CAP_VER_MASK) > 3) {
pci_err(dev, "unsupported PM cap regs version (%u)\n",
pmc & PCI_PM_CAP_VER_MASK);
return;
}
dev->pm_cap = pm;
dev->d3_delay = PCI_PM_D3_WAIT;
dev->d3cold_delay = PCI_PM_D3COLD_WAIT;
dev->bridge_d3 = pci_bridge_d3_possible(dev);
dev->d3cold_allowed = true;
dev->d1_support = false;
dev->d2_support = false;
if (!pci_no_d1d2(dev)) {
if (pmc & PCI_PM_CAP_D1)
dev->d1_support = true;
if (pmc & PCI_PM_CAP_D2)
dev->d2_support = true;
if (dev->d1_support || dev->d2_support)
pci_info(dev, "supports%s%s\n",
dev->d1_support ? " D1" : "",
dev->d2_support ? " D2" : "");
}
pmc &= PCI_PM_CAP_PME_MASK;
if (pmc) {
pci_info(dev, "PME# supported from%s%s%s%s%s\n",
(pmc & PCI_PM_CAP_PME_D0) ? " D0" : "",
(pmc & PCI_PM_CAP_PME_D1) ? " D1" : "",
(pmc & PCI_PM_CAP_PME_D2) ? " D2" : "",
(pmc & PCI_PM_CAP_PME_D3) ? " D3hot" : "",
(pmc & PCI_PM_CAP_PME_D3cold) ? " D3cold" : "");
dev->pme_support = pmc >> PCI_PM_CAP_PME_SHIFT;
dev->pme_poll = true;
/*
* Make device's PM flags reflect the wake-up capability, but
* let the user space enable it to wake up the system as needed.
*/
device_set_wakeup_capable(&dev->dev, true);
/* Disable the PME# generation functionality */
pci_pme_active(dev, false);
}
pci_read_config_word(dev, PCI_STATUS, &status);
if (status & PCI_STATUS_IMM_READY)
dev->imm_ready = 1;
}
static unsigned long pci_ea_flags(struct pci_dev *dev, u8 prop)
{
unsigned long flags = IORESOURCE_PCI_FIXED | IORESOURCE_PCI_EA_BEI;
switch (prop) {
case PCI_EA_P_MEM:
case PCI_EA_P_VF_MEM:
flags |= IORESOURCE_MEM;
break;
case PCI_EA_P_MEM_PREFETCH:
case PCI_EA_P_VF_MEM_PREFETCH:
flags |= IORESOURCE_MEM | IORESOURCE_PREFETCH;
break;
case PCI_EA_P_IO:
flags |= IORESOURCE_IO;
break;
default:
return 0;
}
return flags;
}
static struct resource *pci_ea_get_resource(struct pci_dev *dev, u8 bei,
u8 prop)
{
if (bei <= PCI_EA_BEI_BAR5 && prop <= PCI_EA_P_IO)
return &dev->resource[bei];
#ifdef CONFIG_PCI_IOV
else if (bei >= PCI_EA_BEI_VF_BAR0 && bei <= PCI_EA_BEI_VF_BAR5 &&
(prop == PCI_EA_P_VF_MEM || prop == PCI_EA_P_VF_MEM_PREFETCH))
return &dev->resource[PCI_IOV_RESOURCES +
bei - PCI_EA_BEI_VF_BAR0];
#endif
else if (bei == PCI_EA_BEI_ROM)
return &dev->resource[PCI_ROM_RESOURCE];
else
return NULL;
}
/* Read an Enhanced Allocation (EA) entry */
static int pci_ea_read(struct pci_dev *dev, int offset)
{
struct resource *res;
int ent_size, ent_offset = offset;
resource_size_t start, end;
unsigned long flags;
u32 dw0, bei, base, max_offset;
u8 prop;
bool support_64 = (sizeof(resource_size_t) >= 8);
pci_read_config_dword(dev, ent_offset, &dw0);
ent_offset += 4;
/* Entry size field indicates DWORDs after 1st */
ent_size = ((dw0 & PCI_EA_ES) + 1) << 2;
if (!(dw0 & PCI_EA_ENABLE)) /* Entry not enabled */
goto out;
bei = (dw0 & PCI_EA_BEI) >> 4;
prop = (dw0 & PCI_EA_PP) >> 8;
/*
* If the Property is in the reserved range, try the Secondary
* Property instead.
*/
if (prop > PCI_EA_P_BRIDGE_IO && prop < PCI_EA_P_MEM_RESERVED)
prop = (dw0 & PCI_EA_SP) >> 16;
if (prop > PCI_EA_P_BRIDGE_IO)
goto out;
res = pci_ea_get_resource(dev, bei, prop);
if (!res) {
pci_err(dev, "Unsupported EA entry BEI: %u\n", bei);
goto out;
}
flags = pci_ea_flags(dev, prop);
if (!flags) {
pci_err(dev, "Unsupported EA properties: %#x\n", prop);
goto out;
}
/* Read Base */
pci_read_config_dword(dev, ent_offset, &base);
start = (base & PCI_EA_FIELD_MASK);
ent_offset += 4;
/* Read MaxOffset */
pci_read_config_dword(dev, ent_offset, &max_offset);
ent_offset += 4;
/* Read Base MSBs (if 64-bit entry) */
if (base & PCI_EA_IS_64) {
u32 base_upper;
pci_read_config_dword(dev, ent_offset, &base_upper);
ent_offset += 4;
flags |= IORESOURCE_MEM_64;
/* entry starts above 32-bit boundary, can't use */
if (!support_64 && base_upper)
goto out;
if (support_64)
start |= ((u64)base_upper << 32);
}
end = start + (max_offset | 0x03);
/* Read MaxOffset MSBs (if 64-bit entry) */
if (max_offset & PCI_EA_IS_64) {
u32 max_offset_upper;
pci_read_config_dword(dev, ent_offset, &max_offset_upper);
ent_offset += 4;
flags |= IORESOURCE_MEM_64;
/* entry too big, can't use */
if (!support_64 && max_offset_upper)
goto out;
if (support_64)
end += ((u64)max_offset_upper << 32);
}
if (end < start) {
pci_err(dev, "EA Entry crosses address boundary\n");
goto out;
}
if (ent_size != ent_offset - offset) {
pci_err(dev, "EA Entry Size (%d) does not match length read (%d)\n",
ent_size, ent_offset - offset);
goto out;
}
res->name = pci_name(dev);
res->start = start;
res->end = end;
res->flags = flags;
if (bei <= PCI_EA_BEI_BAR5)
pci_info(dev, "BAR %d: %pR (from Enhanced Allocation, properties %#02x)\n",
bei, res, prop);
else if (bei == PCI_EA_BEI_ROM)
pci_info(dev,