pci.c

/*
 *	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/kernel.h>
#include <linux/delay.h>
#include <linux/init.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/pci-aspm.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 <asm-generic/pci-bridge.h>
#include <asm/setup.h>
#include "pci.h"

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;

	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;

enum pcie_bus_config_types pcie_bus_config = PCIE_BUS_TUNE_OFF;

/*
 * 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;

/**
 * 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 list_head *tmp;
	unsigned char max, n;

	max = bus->busn_res.end;
	list_for_each(tmp, &bus->children) {
		n = pci_bus_max_busnr(pci_bus_b(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)
{
	/*
	 * 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_nocache(pci_resource_start(pdev, bar),
				     pci_resource_len(pdev, bar));
}
EXPORT_SYMBOL_GPL(pci_ioremap_bar);
#endif

#define PCI_FIND_CAP_TTL	48

static int __pci_find_next_cap_ttl(struct pci_bus *bus, unsigned int devfn,
				   u8 pos, int cap, int *ttl)
{
	u8 id;

	while ((*ttl)--) {
		pci_bus_read_config_byte(bus, devfn, pos, &pos);
		if (pos < 0x40)
			break;
		pos &= ~3;
		pci_bus_read_config_byte(bus, devfn, pos + PCI_CAP_LIST_ID,
					 &id);
		if (id == 0xff)
			break;
		if (id == cap)
			return pos;
		pos += PCI_CAP_LIST_NEXT;
	}
	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;
	default:
		return 0;
	}

	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:
 *
 *  %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;
}

/**
 * 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;
}

/**
 * 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:
 *
 *  %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 or where
 *  it should be allocated from.
 */
struct resource *
pci_find_parent_resource(const struct pci_dev *dev, struct resource *res)
{
	const struct pci_bus *bus = dev->bus;
	int i;
	struct resource *best = NULL, *r;

	pci_bus_for_each_resource(bus, r, i) {
		if (!r)
			continue;
		if (res->start && !(res->start >= r->start && res->end <= r->end))
			continue;	/* Not contained */
		if ((res->flags ^ r->flags) & (IORESOURCE_IO | IORESOURCE_MEM))
			continue;	/* Wrong type */
		if (!((res->flags ^ r->flags) & IORESOURCE_PREFETCH))
			return r;	/* Exact match */
		/* We can't insert a non-prefetch resource inside a prefetchable parent .. */
		if (r->flags & IORESOURCE_PREFETCH)
			continue;
		/* .. but we can put a prefetchable resource inside a non-prefetchable one */
		if (!best)
			best = r;
	}
	return best;
}

/**
 * pci_restore_bars - restore a devices 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 struct pci_platform_pm_ops *pci_platform_pm;

int pci_set_platform_pm(struct pci_platform_pm_ops *ops)
{
	if (!ops->is_manageable || !ops->set_state || !ops->choose_state
	    || !ops->sleep_wake)
		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_choose_state(struct pci_dev *dev)
{
	return pci_platform_pm ?
			pci_platform_pm->choose_state(dev) : PCI_POWER_ERROR;
}

static inline int platform_pci_sleep_wake(struct pci_dev *dev, bool enable)
{
	return pci_platform_pm ?
			pci_platform_pm->sleep_wake(dev, enable) : -ENODEV;
}

static inline int platform_pci_run_wake(struct pci_dev *dev, bool enable)
{
	return pci_platform_pm ?
			pci_platform_pm->run_wake(dev, enable) : -ENODEV;
}

/**
 * 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) {
		dev_err(&dev->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())
		dev_info(&dev->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 PCI power state of given device from its
 *                            PCI PM registers and cache it
 * @dev: PCI device to handle.
 * @state: State to cache in case the device doesn't have the PM capability
 */
void pci_update_current_state(struct pci_dev *dev, pci_power_t state)
{
	if (dev->pm_cap) {
		u16 pmcsr;

		/*
		 * Configuration space is not accessible for device in
		 * D3cold, so just keep or set D3cold for safety
		 */
		if (dev->current_state == PCI_D3cold)
			return;
		if (state == PCI_D3cold) {
			dev->current_state = PCI_D3cold;
			return;
		}
		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.
 */
static 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) {
			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
 */
static 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 device already is in the requested state.
 * 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;
	/*
	 * When aspm_policy is "powersave" this call ensures
	 * that ASPM is configured.
	 */
	if (!error && dev->bus->self)
		pcie_aspm_powersave_config_link(dev->bus->self);

	return error;
}

/**
 * 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:
		dev_info(&dev->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,
						      char cap)
{
	struct pci_cap_saved_state *tmp;

	hlist_for_each_entry(tmp, &pci_dev->saved_cap_space, next) {
		if (tmp->cap.cap_nr == cap)
			return tmp;
	}
	return NULL;
}

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) {
		dev_err(&dev->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 <= 0)
		return 0;

	save_state = pci_find_saved_cap(dev, PCI_CAP_ID_PCIX);
	if (!save_state) {
		dev_err(&dev->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 <= 0)
		return;
	cap = (u16 *)&save_state->cap.data[0];

	pci_write_config_word(dev, pos + PCI_X_CMD, cap[i++]);
}


/**
 * 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;
	if ((i = pci_save_pcie_state(dev)) != 0)
		return i;
	if ((i = pci_save_pcix_state(dev)) != 0)
		return i;
	return 0;
}

static void pci_restore_config_dword(struct pci_dev *pdev, int offset,
				     u32 saved_val, int retry)
{
	u32 val;

	pci_read_config_dword(pdev, offset, &val);
	if (val == saved_val)
		return;

	for (;;) {
		dev_dbg(&pdev->dev, "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,