[muen/linux.git] / drivers / pci / pci.c

// 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/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 <linux/vmalloc.h>
#include <linux/pci-ats.h>
#include <asm/setup.h>
#include <asm/dma.h>
#include <linux/aer.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;

        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;

/* 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


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:
 *
 *  %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:
 *
 *  %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;
}

/**
 * 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.
 */
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) {
                        if (dev->d3cold_delay)
                                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 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++]);
}


/**
 * 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;

        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)
{
        u32 val;

        pci_read_config_dword(pdev, offset, &val);
        if (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)
{
        int index;

        for (index = end; index >= start; index--)
                pci_restore_config_dword(pdev, 4 * index,
                                         pdev->saved_config_space[index],
                                         retry);
}

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);
                /* Restore BARs before the command register. */
                pci_restore_config_space_range(pdev, 4, 9, 10);
                pci_restore_config_space_range(pdev, 0, 3, 0);
        } else {
                pci_restore_config_space_range(pdev, 0, 15, 0);
        }
}

/**
 * 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;

        /* PCI Express register must be restored first */
        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_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/msix
 * on/off and BAR regions.  pci_dev itself records msi/msix 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
 *
 *
 * Sets 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
 */
int pci_enable_wake(struct pci_dev *dev, pci_power_t state, bool enable)
{
        int ret = 0;

        /*
         * Bridges can only signal wakeup on behalf of subordinate devices,
         * but that is set up elsewhere, so skip them.
         */
        if (pci_has_subordinate(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;
}
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 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 choose the target state of the device
                 * and enable wake-up from this state if supported.
                 */
                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;
                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
                 * wake-up events, make it the target state and enable device
                 * to 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 (device_can_wakeup(&dev->dev))
                return true;

        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, false)))
                return false;

        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);
}

/**
 * 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.
 */
bool pci_bridge_d3_possible(struct pci_dev *bridge)
{
        unsigned int year;

        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 interrupts cannot be delivered if the link is down,
                 * so parents of a hotplug port must stay awake. In addition,
                 * hotplug ports handled by firmware in System Management Mode
                 * may not be put into D3 by the OS (Thunderbolt on non-Macs).
                 * For simplicity, disallow in general for now.
                 */
                if (bridge->is_hotplug_bridge)
                        return false;

                if (pci_bridge_d3_force)
                        return true;

                /*
                 * It should be safe to put PCIe ports from 2015 or newer
                 * to D3.
                 */
                if (dmi_get_date(DMI_BIOS_DATE, &year, NULL, NULL) &&
                    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 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_printk(KERN_DEBUG, dev, "supports%s%s\n",
                                   dev->d1_support ? " D1" : "",
                                   dev->d2_support ? " D2" : "");
        }

        pmc &= PCI_PM_CAP_PME_MASK;
        if (pmc) {
                pci_printk(KERN_DEBUG, 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);
        }
}

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_printk(KERN_DEBUG, dev, "BAR %d: %pR (from Enhanced Allocation, properties %#02x)\n",
                           bei, res, prop);
        else if (bei == PCI_EA_BEI_ROM)
                pci_printk(KERN_DEBUG, dev, "ROM: %pR (from Enhanced Allocation, properties %#02x)\n",
                           res, prop);
        else if (bei >= PCI_EA_BEI_VF_BAR0 && bei <= PCI_EA_BEI_VF_BAR5)
                pci_printk(KERN_DEBUG, dev, "VF BAR %d: %pR (from Enhanced Allocation, properties %#02x)\n",
                           bei - PCI_EA_BEI_VF_BAR0, res, prop);
        else
                pci_printk(KERN_DEBUG, dev, "BEI %d res: %pR (from Enhanced Allocation, properties %#02x)\n",
                           bei, res, prop);

out:
        return offset + ent_size;
}

/* Enhanced Allocation Initialization */
void pci_ea_init(struct pci_dev *dev)
{
        int ea;
        u8 num_ent;
        int offset;
        int i;

        /* find PCI EA capability in list */
        ea = pci_find_capability(dev, PCI_CAP_ID_EA);
        if (!ea)
                return;

        /* determine the number of entries */
        pci_bus_read_config_byte(dev->bus, dev->devfn, ea + PCI_EA_NUM_ENT,
                                        &num_ent);
        num_ent &= PCI_EA_NUM_ENT_MASK;

        offset = ea + PCI_EA_FIRST_ENT;

        /* Skip DWORD 2 for type 1 functions */
        if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE)
                offset += 4;

        /* parse each EA entry */
        for (i = 0; i < num_ent; ++i)
                offset = pci_ea_read(dev, offset);
}

static void pci_add_saved_cap(struct pci_dev *pci_dev,
        struct pci_cap_saved_state *new_cap)
{
        hlist_add_head(&new_cap->next, &pci_dev->saved_cap_space);
}

/**
 * _pci_add_cap_save_buffer - allocate buffer for saving given
 *                            capability registers
 * @dev: the PCI device
 * @cap: the capability to allocate the buffer for
 * @extended: Standard or Extended capability ID
 * @size: requested size of the buffer
 */
static int _pci_add_cap_save_buffer(struct pci_dev *dev, u16 cap,
                                    bool extended, unsigned int size)
{
        int pos;
        struct pci_cap_saved_state *save_state;

        if (extended)
                pos = pci_find_ext_capability(dev, cap);
        else
                pos = pci_find_capability(dev, cap);

        if (!pos)
                return 0;

        save_state = kzalloc(sizeof(*save_state) + size, GFP_KERNEL);
        if (!save_state)
                return -ENOMEM;

        save_state->cap.cap_nr = cap;
        save_state->cap.cap_extended = extended;
        save_state->cap.size = size;
        pci_add_saved_cap(dev, save_state);

        return 0;
}

int pci_add_cap_save_buffer(struct pci_dev *dev, char cap, unsigned int size)
{
        return _pci_add_cap_save_buffer(dev, cap, false, size);
}

int pci_add_ext_cap_save_buffer(struct pci_dev *dev, u16 cap, unsigned int size)
{
        return _pci_add_cap_save_buffer(dev, cap, true, size);
}

/**
 * pci_allocate_cap_save_buffers - allocate buffers for saving capabilities
 * @dev: the PCI device
 */
void pci_allocate_cap_save_buffers(struct pci_dev *dev)
{
        int error;

        error = pci_add_cap_save_buffer(dev, PCI_CAP_ID_EXP,
                                        PCI_EXP_SAVE_REGS * sizeof(u16));
        if (error)
                pci_err(dev, "unable to preallocate PCI Express save buffer\n");

        error = pci_add_cap_save_buffer(dev, PCI_CAP_ID_PCIX, sizeof(u16));
        if (error)
                pci_err(dev, "unable to preallocate PCI-X save buffer\n");

        pci_allocate_vc_save_buffers(dev);
}

void pci_free_cap_save_buffers(struct pci_dev *dev)
{
        struct pci_cap_saved_state *tmp;
        struct hlist_node *n;

        hlist_for_each_entry_safe(tmp, n, &dev->saved_cap_space, next)
                kfree(tmp);
}

/**
 * pci_configure_ari - enable or disable ARI forwarding
 * @dev: the PCI device
 *
 * If @dev and its upstream bridge both support ARI, enable ARI in the
 * bridge.  Otherwise, disable ARI in the bridge.
 */
void pci_configure_ari(struct pci_dev *dev)
{
        u32 cap;
        struct pci_dev *bridge;

        if (pcie_ari_disabled || !pci_is_pcie(dev) || dev->devfn)
                return;

        bridge = dev->bus->self;
        if (!bridge)
                return;

        pcie_capability_read_dword(bridge, PCI_EXP_DEVCAP2, &cap);
        if (!(cap & PCI_EXP_DEVCAP2_ARI))
                return;

        if (pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ARI)) {
                pcie_capability_set_word(bridge, PCI_EXP_DEVCTL2,
                                         PCI_EXP_DEVCTL2_ARI);
                bridge->ari_enabled = 1;
        } else {
                pcie_capability_clear_word(bridge, PCI_EXP_DEVCTL2,
                                           PCI_EXP_DEVCTL2_ARI);
                bridge->ari_enabled = 0;
        }
}

static int pci_acs_enable;

/**
 * pci_request_acs - ask for ACS to be enabled if supported
 */
void pci_request_acs(void)
{
        pci_acs_enable = 1;
}

/**
 * pci_std_enable_acs - enable ACS on devices using standard ACS capabilites
 * @dev: the PCI device
 */
static void pci_std_enable_acs(struct pci_dev *dev)
{
        int pos;
        u16 cap;
        u16 ctrl;

        pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ACS);
        if (!pos)
                return;

        pci_read_config_word(dev, pos + PCI_ACS_CAP, &cap);
        pci_read_config_word(dev, pos + PCI_ACS_CTRL, &ctrl);

        /* Source Validation */
        ctrl |= (cap & PCI_ACS_SV);

        /* P2P Request Redirect */
        ctrl |= (cap & PCI_ACS_RR);

        /* P2P Completion Redirect */
        ctrl |= (cap & PCI_ACS_CR);

        /* Upstream Forwarding */
        ctrl |= (cap & PCI_ACS_UF);

        pci_write_config_word(dev, pos + PCI_ACS_CTRL, ctrl);
}

/**
 * pci_enable_acs - enable ACS if hardware support it
 * @dev: the PCI device
 */
void pci_enable_acs(struct pci_dev *dev)
{
        if (!pci_acs_enable)
                return;

        if (!pci_dev_specific_enable_acs(dev))
                return;

        pci_std_enable_acs(dev);
}

static bool pci_acs_flags_enabled(struct pci_dev *pdev, u16 acs_flags)
{
        int pos;
        u16 cap, ctrl;

        pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ACS);
        if (!pos)
                return false;

        /*
         * Except for egress control, capabilities are either required
         * or only required if controllable.  Features missing from the
         * capability field can therefore be assumed as hard-wired enabled.
         */
        pci_read_config_word(pdev, pos + PCI_ACS_CAP, &cap);
        acs_flags &= (cap | PCI_ACS_EC);

        pci_read_config_word(pdev, pos + PCI_ACS_CTRL, &ctrl);
        return (ctrl & acs_flags) == acs_flags;
}

/**
 * pci_acs_enabled - test ACS against required flags for a given device
 * @pdev: device to test
 * @acs_flags: required PCI ACS flags
 *
 * Return true if the device supports the provided flags.  Automatically
 * filters out flags that are not implemented on multifunction devices.
 *
 * Note that this interface checks the effective ACS capabilities of the
 * device rather than the actual capabilities.  For instance, most single
 * function endpoints are not required to support ACS because they have no
 * opportunity for peer-to-peer access.  We therefore return 'true'
 * regardless of whether the device exposes an ACS capability.  This makes
 * it much easier for callers of this function to ignore the actual type
 * or topology of the device when testing ACS support.
 */
bool pci_acs_enabled(struct pci_dev *pdev, u16 acs_flags)
{
        int ret;

        ret = pci_dev_specific_acs_enabled(pdev, acs_flags);
        if (ret >= 0)
                return ret > 0;

        /*
         * Conventional PCI and PCI-X devices never support ACS, either
         * effectively or actually.  The shared bus topology implies that
         * any device on the bus can receive or snoop DMA.
         */
        if (!pci_is_pcie(pdev))
                return false;

        switch (pci_pcie_type(pdev)) {
        /*
         * PCI/X-to-PCIe bridges are not specifically mentioned by the spec,
         * but since their primary interface is PCI/X, we conservatively
         * handle them as we would a non-PCIe device.
         */
        case PCI_EXP_TYPE_PCIE_BRIDGE:
        /*
         * PCIe 3.0, 6.12.1 excludes ACS on these devices.  "ACS is never
         * applicable... must never implement an ACS Extended Capability...".
         * This seems arbitrary, but we take a conservative interpretation
         * of this statement.
         */
        case PCI_EXP_TYPE_PCI_BRIDGE:
        case PCI_EXP_TYPE_RC_EC:
                return false;
        /*
         * PCIe 3.0, 6.12.1.1 specifies that downstream and root ports should
         * implement ACS in order to indicate their peer-to-peer capabilities,
         * regardless of whether they are single- or multi-function devices.
         */
        case PCI_EXP_TYPE_DOWNSTREAM:
        case PCI_EXP_TYPE_ROOT_PORT:
                return pci_acs_flags_enabled(pdev, acs_flags);
        /*
         * PCIe 3.0, 6.12.1.2 specifies ACS capabilities that should be
         * implemented by the remaining PCIe types to indicate peer-to-peer
         * capabilities, but only when they are part of a multifunction
         * device.  The footnote for section 6.12 indicates the specific
         * PCIe types included here.
         */
        case PCI_EXP_TYPE_ENDPOINT:
        case PCI_EXP_TYPE_UPSTREAM:
        case PCI_EXP_TYPE_LEG_END:
        case PCI_EXP_TYPE_RC_END:
                if (!pdev->multifunction)
                        break;

                return pci_acs_flags_enabled(pdev, acs_flags);
        }

        /*
         * PCIe 3.0, 6.12.1.3 specifies no ACS capabilities are applicable
         * to single function devices with the exception of downstream ports.
         */
        return true;
}

/**
 * pci_acs_path_enable - test ACS flags from start to end in a hierarchy
 * @start: starting downstream device
 * @end: ending upstream device or NULL to search to the root bus
 * @acs_flags: required flags
 *
 * Walk up a device tree from start to end testing PCI ACS support.  If
 * any step along the way does not support the required flags, return false.
 */
bool pci_acs_path_enabled(struct pci_dev *start,
                          struct pci_dev *end, u16 acs_flags)
{
        struct pci_dev *pdev, *parent = start;

        do {
                pdev = parent;

                if (!pci_acs_enabled(pdev, acs_flags))
                        return false;

                if (pci_is_root_bus(pdev->bus))
                        return (end == NULL);

                parent = pdev->bus->self;
        } while (pdev != end);

        return true;
}

/**
 * pci_rebar_find_pos - find position of resize ctrl reg for BAR
 * @pdev: PCI device
 * @bar: BAR to find
 *
 * Helper to find the position of the ctrl register for a BAR.
 * Returns -ENOTSUPP if resizable BARs are not supported at all.
 * Returns -ENOENT if no ctrl register for the BAR could be found.
 */
static int pci_rebar_find_pos(struct pci_dev *pdev, int bar)
{
        unsigned int pos, nbars, i;
        u32 ctrl;

        pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_REBAR);
        if (!pos)
                return -ENOTSUPP;

        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) {
                int bar_idx;

                pci_read_config_dword(pdev, pos + PCI_REBAR_CTRL, &ctrl);
                bar_idx = ctrl & PCI_REBAR_CTRL_BAR_IDX;
                if (bar_idx == bar)
                        return pos;
        }

        return -ENOENT;
}

/**
 * pci_rebar_get_possible_sizes - get possible sizes for BAR
 * @pdev: PCI device
 * @bar: BAR to query
 *
 * Get the possible sizes of a resizable BAR as bitmask defined in the spec
 * (bit 0=1MB, bit 19=512GB). Returns 0 if BAR isn't resizable.
 */
u32 pci_rebar_get_possible_sizes(struct pci_dev *pdev, int bar)
{
        int pos;
        u32 cap;

        pos = pci_rebar_find_pos(pdev, bar);
        if (pos < 0)
                return 0;

        pci_read_config_dword(pdev, pos + PCI_REBAR_CAP, &cap);
        return (cap & PCI_REBAR_CAP_SIZES) >> 4;
}

/**
 * pci_rebar_get_current_size - get the current size of a BAR
 * @pdev: PCI device
 * @bar: BAR to set size to
 *
 * Read the size of a BAR from the resizable BAR config.
 * Returns size if found or negative error code.
 */
int pci_rebar_get_current_size(struct pci_dev *pdev, int bar)
{
        int pos;
        u32 ctrl;

        pos = pci_rebar_find_pos(pdev, bar);
        if (pos < 0)
                return pos;

        pci_read_config_dword(pdev, pos + PCI_REBAR_CTRL, &ctrl);
        return (ctrl & PCI_REBAR_CTRL_BAR_SIZE) >> 8;
}

/**
 * pci_rebar_set_size - set a new size for a BAR
 * @pdev: PCI device
 * @bar: BAR to set size to
 * @size: new size as defined in the spec (0=1MB, 19=512GB)
 *
 * Set the new size of a BAR as defined in the spec.
 * Returns zero if resizing was successful, error code otherwise.
 */
int pci_rebar_set_size(struct pci_dev *pdev, int bar, int size)
{
        int pos;
        u32 ctrl;

        pos = pci_rebar_find_pos(pdev, bar);
        if (pos < 0)
                return pos;

        pci_read_config_dword(pdev, pos + PCI_REBAR_CTRL, &ctrl);
        ctrl &= ~PCI_REBAR_CTRL_BAR_SIZE;
        ctrl |= size << 8;
        pci_write_config_dword(pdev, pos + PCI_REBAR_CTRL, ctrl);
        return 0;
}

/**
 * pci_enable_atomic_ops_to_root - enable AtomicOp requests to root port
 * @dev: the PCI device
 * @cap_mask: mask of desired AtomicOp sizes, including one or more of:
 *      PCI_EXP_DEVCAP2_ATOMIC_COMP32
 *      PCI_EXP_DEVCAP2_ATOMIC_COMP64
 *      PCI_EXP_DEVCAP2_ATOMIC_COMP128
 *
 * Return 0 if all upstream bridges support AtomicOp routing, egress
 * blocking is disabled on all upstream ports, and the root port supports
 * the requested completion capabilities (32-bit, 64-bit and/or 128-bit
 * AtomicOp completion), or negative otherwise.
 */
int pci_enable_atomic_ops_to_root(struct pci_dev *dev, u32 cap_mask)
{
        struct pci_bus *bus = dev->bus;
        struct pci_dev *bridge;
        u32 cap, ctl2;

        if (!pci_is_pcie(dev))
                return -EINVAL;

        /*
         * Per PCIe r4.0, sec 6.15, endpoints and root ports may be
         * AtomicOp requesters.  For now, we only support endpoints as
         * requesters and root ports as completers.  No endpoints as
         * completers, and no peer-to-peer.
         */

        switch (pci_pcie_type(dev)) {
        case PCI_EXP_TYPE_ENDPOINT:
        case PCI_EXP_TYPE_LEG_END:
        case PCI_EXP_TYPE_RC_END:
                break;
        default:
                return -EINVAL;
        }

        while (bus->parent) {
                bridge = bus->self;

                pcie_capability_read_dword(bridge, PCI_EXP_DEVCAP2, &cap);

                switch (pci_pcie_type(bridge)) {
                /* Ensure switch ports support AtomicOp routing */
                case PCI_EXP_TYPE_UPSTREAM:
                case PCI_EXP_TYPE_DOWNSTREAM:
                        if (!(cap & PCI_EXP_DEVCAP2_ATOMIC_ROUTE))
                                return -EINVAL;
                        break;

                /* Ensure root port supports all the sizes we care about */
                case PCI_EXP_TYPE_ROOT_PORT:
                        if ((cap & cap_mask) != cap_mask)
                                return -EINVAL;
                        break;
                }

                /* Ensure upstream ports don't block AtomicOps on egress */
                if (!bridge->has_secondary_link) {
                        pcie_capability_read_dword(bridge, PCI_EXP_DEVCTL2,
                                                   &ctl2);
                        if (ctl2 & PCI_EXP_DEVCTL2_ATOMIC_EGRESS_BLOCK)
                                return -EINVAL;
                }

                bus = bus->parent;
        }

        pcie_capability_set_word(dev, PCI_EXP_DEVCTL2,
                                 PCI_EXP_DEVCTL2_ATOMIC_REQ);
        return 0;
}
EXPORT_SYMBOL(pci_enable_atomic_ops_to_root);

/**
 * pci_swizzle_interrupt_pin - swizzle INTx for device behind bridge
 * @dev: the PCI device
 * @pin: the INTx pin (1=INTA, 2=INTB, 3=INTC, 4=INTD)
 *
 * Perform INTx swizzling for a device behind one level of bridge.  This is
 * required by section 9.1 of the PCI-to-PCI bridge specification for devices
 * behind bridges on add-in cards.  For devices with ARI enabled, the slot
 * number is always 0 (see the Implementation Note in section 2.2.8.1 of
 * the PCI Express Base Specification, Revision 2.1)
 */
u8 pci_swizzle_interrupt_pin(const struct pci_dev *dev, u8 pin)
{
        int slot;

        if (pci_ari_enabled(dev->bus))
                slot = 0;
        else
                slot = PCI_SLOT(dev->devfn);

        return (((pin - 1) + slot) % 4) + 1;
}

int pci_get_interrupt_pin(struct pci_dev *dev, struct pci_dev **bridge)
{
        u8 pin;

        pin = dev->pin;
        if (!pin)
                return -1;

        while (!pci_is_root_bus(dev->bus)) {
                pin = pci_swizzle_interrupt_pin(dev, pin);
                dev = dev->bus->self;
        }
        *bridge = dev;
        return pin;
}

/**
 * pci_common_swizzle - swizzle INTx all the way to root bridge
 * @dev: the PCI device
 * @pinp: pointer to the INTx pin value (1=INTA, 2=INTB, 3=INTD, 4=INTD)
 *
 * Perform INTx swizzling for a device.  This traverses through all PCI-to-PCI
 * bridges all the way up to a PCI root bus.
 */
u8 pci_common_swizzle(struct pci_dev *dev, u8 *pinp)
{
        u8 pin = *pinp;

        while (!pci_is_root_bus(dev->bus)) {
                pin = pci_swizzle_interrupt_pin(dev, pin);
                dev = dev->bus->self;
        }
        *pinp = pin;
        return PCI_SLOT(dev->devfn);
}
EXPORT_SYMBOL_GPL(pci_common_swizzle);

/**
 *      pci_release_region - Release a PCI bar
 *      @pdev: PCI device whose resources were previously reserved by pci_request_region
 *      @bar: BAR to release
 *
 *      Releases the PCI I/O and memory resources previously reserved by a
 *      successful call to pci_request_region.  Call this function only
 *      after all use of the PCI regions has ceased.
 */
void pci_release_region(struct pci_dev *pdev, int bar)
{
        struct pci_devres *dr;

        if (pci_resource_len(pdev, bar) == 0)
                return;
        if (pci_resource_flags(pdev, bar) & IORESOURCE_IO)
                release_region(pci_resource_start(pdev, bar),
                                pci_resource_len(pdev, bar));
        else if (pci_resource_flags(pdev, bar) & IORESOURCE_MEM)
                release_mem_region(pci_resource_start(pdev, bar),
                                pci_resource_len(pdev, bar));

        dr = find_pci_dr(pdev);
        if (dr)
                dr->region_mask &= ~(1 << bar);
}
EXPORT_SYMBOL(pci_release_region);

/**
 *      __pci_request_region - Reserved PCI I/O and memory resource
 *      @pdev: PCI device whose resources are to be reserved
 *      @bar: BAR to be reserved
 *      @res_name: Name to be associated with resource.
 *      @exclusive: whether the region access is exclusive or not
 *
 *      Mark the PCI region associated with PCI device @pdev BR @bar as
 *      being reserved by owner @res_name.  Do not access any
 *      address inside the PCI regions unless this call returns
 *      successfully.
 *
 *      If @exclusive is set, then the region is marked so that userspace
 *      is explicitly not allowed to map the resource via /dev/mem or
 *      sysfs MMIO access.
 *
 *      Returns 0 on success, or %EBUSY on error.  A warning
 *      message is also printed on failure.
 */
static int __pci_request_region(struct pci_dev *pdev, int bar,
                                const char *res_name, int exclusive)
{
        struct pci_devres *dr;

        if (pci_resource_len(pdev, bar) == 0)
                return 0;

        if (pci_resource_flags(pdev, bar) & IORESOURCE_IO) {
                if (!request_region(pci_resource_start(pdev, bar),
                            pci_resource_len(pdev, bar), res_name))
                        goto err_out;
        } else if (pci_resource_flags(pdev, bar) & IORESOURCE_MEM) {
                if (!__request_mem_region(pci_resource_start(pdev, bar),
                                        pci_resource_len(pdev, bar), res_name,
                                        exclusive))
                        goto err_out;
        }

        dr = find_pci_dr(pdev);
        if (dr)
                dr->region_mask |= 1 << bar;

        return 0;

err_out:
        pci_warn(pdev, "BAR %d: can't reserve %pR\n", bar,
                 &pdev->resource[bar]);
        return -EBUSY;
}

/**
 *      pci_request_region - Reserve PCI I/O and memory resource
 *      @pdev: PCI device whose resources are to be reserved
 *      @bar: BAR to be reserved
 *      @res_name: Name to be associated with resource
 *
 *      Mark the PCI region associated with PCI device @pdev BAR @bar as
 *      being reserved by owner @res_name.  Do not access any
 *      address inside the PCI regions unless this call returns
 *      successfully.
 *
 *      Returns 0 on success, or %EBUSY on error.  A warning
 *      message is also printed on failure.
 */
int pci_request_region(struct pci_dev *pdev, int bar, const char *res_name)
{
        return __pci_request_region(pdev, bar, res_name, 0);
}
EXPORT_SYMBOL(pci_request_region);

/**
 *      pci_request_region_exclusive - Reserved PCI I/O and memory resource
 *      @pdev: PCI device whose resources are to be reserved
 *      @bar: BAR to be reserved
 *      @res_name: Name to be associated with resource.
 *
 *      Mark the PCI region associated with PCI device @pdev BR @bar as
 *      being reserved by owner @res_name.  Do not access any
 *      address inside the PCI regions unless this call returns
 *      successfully.
 *
 *      Returns 0 on success, or %EBUSY on error.  A warning
 *      message is also printed on failure.
 *
 *      The key difference that _exclusive makes it that userspace is
 *      explicitly not allowed to map the resource via /dev/mem or
 *      sysfs.
 */
int pci_request_region_exclusive(struct pci_dev *pdev, int bar,
                                 const char *res_name)
{
        return __pci_request_region(pdev, bar, res_name, IORESOURCE_EXCLUSIVE);
}
EXPORT_SYMBOL(pci_request_region_exclusive);

/**
 * pci_release_selected_regions - Release selected PCI I/O and memory resources
 * @pdev: PCI device whose resources were previously reserved
 * @bars: Bitmask of BARs to be released
 *
 * Release selected PCI I/O and memory resources previously reserved.
 * Call this function only after all use of the PCI regions has ceased.
 */
void pci_release_selected_regions(struct pci_dev *pdev, int bars)
{
        int i;

        for (i = 0; i < 6; i++)
                if (bars & (1 << i))
                        pci_release_region(pdev, i);
}
EXPORT_SYMBOL(pci_release_selected_regions);

static int __pci_request_selected_regions(struct pci_dev *pdev, int bars,
                                          const char *res_name, int excl)
{
        int i;

        for (i = 0; i < 6; i++)
                if (bars & (1 << i))
                        if (__pci_request_region(pdev, i, res_name, excl))
                                goto err_out;
        return 0;

err_out:
        while (--i >= 0)
                if (bars & (1 << i))
                        pci_release_region(pdev, i);

        return -EBUSY;
}


/**
 * pci_request_selected_regions - Reserve selected PCI I/O and memory resources
 * @pdev: PCI device whose resources are to be reserved
 * @bars: Bitmask of BARs to be requested
 * @res_name: Name to be associated with resource
 */
int pci_request_selected_regions(struct pci_dev *pdev, int bars,
                                 const char *res_name)
{
        return __pci_request_selected_regions(pdev, bars, res_name, 0);
}
EXPORT_SYMBOL(pci_request_selected_regions);

int pci_request_selected_regions_exclusive(struct pci_dev *pdev, int bars,
                                           const char *res_name)
{
        return __pci_request_selected_regions(pdev, bars, res_name,
                        IORESOURCE_EXCLUSIVE);
}
EXPORT_SYMBOL(pci_request_selected_regions_exclusive);

/**
 *      pci_release_regions - Release reserved PCI I/O and memory resources
 *      @pdev: PCI device whose resources were previously reserved by pci_request_regions
 *
 *      Releases all PCI I/O and memory resources previously reserved by a
 *      successful call to pci_request_regions.  Call this function only
 *      after all use of the PCI regions has ceased.
 */

void pci_release_regions(struct pci_dev *pdev)
{
        pci_release_selected_regions(pdev, (1 << 6) - 1);
}
EXPORT_SYMBOL(pci_release_regions);

/**
 *      pci_request_regions - Reserved PCI I/O and memory resources
 *      @pdev: PCI device whose resources are to be reserved
 *      @res_name: Name to be associated with resource.
 *
 *      Mark all PCI regions associated with PCI device @pdev as
 *      being reserved by owner @res_name.  Do not access any
 *      address inside the PCI regions unless this call returns
 *      successfully.
 *
 *      Returns 0 on success, or %EBUSY on error.  A warning
 *      message is also printed on failure.
 */
int pci_request_regions(struct pci_dev *pdev, const char *res_name)
{
        return pci_request_selected_regions(pdev, ((1 << 6) - 1), res_name);
}
EXPORT_SYMBOL(pci_request_regions);

/**
 *      pci_request_regions_exclusive - Reserved PCI I/O and memory resources
 *      @pdev: PCI device whose resources are to be reserved
 *      @res_name: Name to be associated with resource.
 *
 *      Mark all PCI regions associated with PCI device @pdev as
 *      being reserved by owner @res_name.  Do not access any
 *      address inside the PCI regions unless this call returns
 *      successfully.
 *
 *      pci_request_regions_exclusive() will mark the region so that
 *      /dev/mem and the sysfs MMIO access will not be allowed.
 *
 *      Returns 0 on success, or %EBUSY on error.  A warning
 *      message is also printed on failure.
 */
int pci_request_regions_exclusive(struct pci_dev *pdev, const char *res_name)
{
        return pci_request_selected_regions_exclusive(pdev,
                                        ((1 << 6) - 1), res_name);
}
EXPORT_SYMBOL(pci_request_regions_exclusive);

/*
 * Record the PCI IO range (expressed as CPU physical address + size).
 * Return a negative value if an error has occured, zero otherwise
 */
int pci_register_io_range(struct fwnode_handle *fwnode, phys_addr_t addr,
                        resource_size_t size)
{
        int ret = 0;
#ifdef PCI_IOBASE
        struct logic_pio_hwaddr *range;

        if (!size || addr + size < addr)
                return -EINVAL;

        range = kzalloc(sizeof(*range), GFP_ATOMIC);
        if (!range)
                return -ENOMEM;

        range->fwnode = fwnode;
        range->size = size;
        range->hw_start = addr;
        range->flags = LOGIC_PIO_CPU_MMIO;

        ret = logic_pio_register_range(range);
        if (ret)
                kfree(range);
#endif

        return ret;
}

phys_addr_t pci_pio_to_address(unsigned long pio)
{
        phys_addr_t address = (phys_addr_t)OF_BAD_ADDR;

#ifdef PCI_IOBASE
        if (pio >= MMIO_UPPER_LIMIT)
                return address;

        address = logic_pio_to_hwaddr(pio);
#endif

        return address;
}

unsigned long __weak pci_address_to_pio(phys_addr_t address)
{
#ifdef PCI_IOBASE
        return logic_pio_trans_cpuaddr(address);
#else
        if (address > IO_SPACE_LIMIT)
                return (unsigned long)-1;

        return (unsigned long) address;
#endif
}

/**
 *      pci_remap_iospace - Remap the memory mapped I/O space
 *      @res: Resource describing the I/O space
 *      @phys_addr: physical address of range to be mapped
 *
 *      Remap the memory mapped I/O space described by the @res
 *      and the CPU physical address @phys_addr into virtual address space.
 *      Only architectures that have memory mapped IO functions defined
 *      (and the PCI_IOBASE value defined) should call this function.
 */
int pci_remap_iospace(const struct resource *res, phys_addr_t phys_addr)
{
#if defined(PCI_IOBASE) && defined(CONFIG_MMU)
        unsigned long vaddr = (unsigned long)PCI_IOBASE + res->start;

        if (!(res->flags & IORESOURCE_IO))
                return -EINVAL;

        if (res->end > IO_SPACE_LIMIT)
                return -EINVAL;

        return ioremap_page_range(vaddr, vaddr + resource_size(res), phys_addr,
                                  pgprot_device(PAGE_KERNEL));
#else
        /* this architecture does not have memory mapped I/O space,
           so this function should never be called */
        WARN_ONCE(1, "This architecture does not support memory mapped I/O\n");
        return -ENODEV;
#endif
}
EXPORT_SYMBOL(pci_remap_iospace);

/**
 *      pci_unmap_iospace - Unmap the memory mapped I/O space
 *      @res: resource to be unmapped
 *
 *      Unmap the CPU virtual address @res from virtual address space.
 *      Only architectures that have memory mapped IO functions defined
 *      (and the PCI_IOBASE value defined) should call this function.
 */
void pci_unmap_iospace(struct resource *res)
{
#if defined(PCI_IOBASE) && defined(CONFIG_MMU)
        unsigned long vaddr = (unsigned long)PCI_IOBASE + res->start;

        unmap_kernel_range(vaddr, resource_size(res));
#endif
}
EXPORT_SYMBOL(pci_unmap_iospace);

/**
 * devm_pci_remap_cfgspace - Managed pci_remap_cfgspace()
 * @dev: Generic device to remap IO address for
 * @offset: Resource address to map
 * @size: Size of map
 *
 * Managed pci_remap_cfgspace().  Map is automatically unmapped on driver
 * detach.
 */
void __iomem *devm_pci_remap_cfgspace(struct device *dev,
                                      resource_size_t offset,
                                      resource_size_t size)
{
        void __iomem **ptr, *addr;

        ptr = devres_alloc(devm_ioremap_release, sizeof(*ptr), GFP_KERNEL);
        if (!ptr)
                return NULL;

        addr = pci_remap_cfgspace(offset, size);
        if (addr) {
                *ptr = addr;
                devres_add(dev, ptr);
        } else
                devres_free(ptr);

        return addr;
}
EXPORT_SYMBOL(devm_pci_remap_cfgspace);

/**
 * devm_pci_remap_cfg_resource - check, request region and ioremap cfg resource
 * @dev: generic device to handle the resource for
 * @res: configuration space resource to be handled
 *
 * Checks that a resource is a valid memory region, requests the memory
 * region and ioremaps with pci_remap_cfgspace() API that ensures the
 * proper PCI configuration space memory attributes are guaranteed.
 *
 * All operations are managed and will be undone on driver detach.
 *
 * Returns a pointer to the remapped memory or an ERR_PTR() encoded error code
 * on failure. Usage example::
 *
 *      res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 *      base = devm_pci_remap_cfg_resource(&pdev->dev, res);
 *      if (IS_ERR(base))
 *              return PTR_ERR(base);
 */
void __iomem *devm_pci_remap_cfg_resource(struct device *dev,
                                          struct resource *res)
{
        resource_size_t size;
        const char *name;
        void __iomem *dest_ptr;

        BUG_ON(!dev);

        if (!res || resource_type(res) != IORESOURCE_MEM) {
                dev_err(dev, "invalid resource\n");
                return IOMEM_ERR_PTR(-EINVAL);
        }

        size = resource_size(res);
        name = res->name ?: dev_name(dev);

        if (!devm_request_mem_region(dev, res->start, size, name)) {
                dev_err(dev, "can't request region for resource %pR\n", res);
                return IOMEM_ERR_PTR(-EBUSY);
        }

        dest_ptr = devm_pci_remap_cfgspace(dev, res->start, size);
        if (!dest_ptr) {
                dev_err(dev, "ioremap failed for resource %pR\n", res);
                devm_release_mem_region(dev, res->start, size);
                dest_ptr = IOMEM_ERR_PTR(-ENOMEM);
        }

        return dest_ptr;
}
EXPORT_SYMBOL(devm_pci_remap_cfg_resource);

static void __pci_set_master(struct pci_dev *dev, bool enable)
{
        u16 old_cmd, cmd;

        pci_read_config_word(dev, PCI_COMMAND, &old_cmd);
        if (enable)
                cmd = old_cmd | PCI_COMMAND_MASTER;
        else
                cmd = old_cmd & ~PCI_COMMAND_MASTER;
        if (cmd != old_cmd) {
                pci_dbg(dev, "%s bus mastering\n",
                        enable ? "enabling" : "disabling");
                pci_write_config_word(dev, PCI_COMMAND, cmd);
        }
        dev->is_busmaster = enable;
}

/**
 * pcibios_setup - process "pci=" kernel boot arguments
 * @str: string used to pass in "pci=" kernel boot arguments
 *
 * Process kernel boot arguments.  This is the default implementation.
 * Architecture specific implementations can override this as necessary.
 */
char * __weak __init pcibios_setup(char *str)
{
        return str;
}