diff options
Diffstat (limited to 'drivers/pci/pci.c')
| -rw-r--r-- | drivers/pci/pci.c | 3752 |
1 files changed, 3261 insertions, 491 deletions
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index a4445b7210b..1c8592b0e14 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -1,6 +1,4 @@ /* - * $Id: pci.c,v 1.91 1999/01/21 13:34:01 davem Exp $ - * * PCI Bus Services, see include/linux/pci.h for further explanation. * * Copyright 1993 -- 1997 Drew Eckhardt, Frederic Potter, @@ -14,14 +12,56 @@ #include <linux/init.h> #include <linux/pci.h> #include <linux/pm.h> +#include <linux/slab.h> #include <linux/module.h> #include <linux/spinlock.h> #include <linux/string.h> #include <linux/log2.h> -#include <asm/dma.h> /* isa_dma_bridge_buggy */ +#include <linux/pci-aspm.h> +#include <linux/pm_wakeup.h> +#include <linux/interrupt.h> +#include <linux/device.h> +#include <linux/pm_runtime.h> +#include <linux/pci_hotplug.h> +#include <asm-generic/pci-bridge.h> +#include <asm/setup.h> #include "pci.h" -unsigned int pci_pm_d3_delay = 10; +const char *pci_power_names[] = { + "error", "D0", "D1", "D2", "D3hot", "D3cold", "unknown", +}; +EXPORT_SYMBOL_GPL(pci_power_names); + +int isa_dma_bridge_buggy; +EXPORT_SYMBOL(isa_dma_bridge_buggy); + +int pci_pci_problems; +EXPORT_SYMBOL(pci_pci_problems); + +unsigned int pci_pm_d3_delay; + +static void pci_pme_list_scan(struct work_struct *work); + +static LIST_HEAD(pci_pme_list); +static DEFINE_MUTEX(pci_pme_list_mutex); +static DECLARE_DELAYED_WORK(pci_pme_work, pci_pme_list_scan); + +struct pci_pme_device { + struct list_head list; + struct pci_dev *dev; +}; + +#define PME_TIMEOUT 1000 /* How long between PME checks */ + +static void pci_dev_d3_sleep(struct pci_dev *dev) +{ + unsigned int delay = dev->d3_delay; + + if (delay < pci_pm_d3_delay) + delay = pci_pm_d3_delay; + + msleep(delay); +} #ifdef CONFIG_PCI_DOMAINS int pci_domains_supported = 1; @@ -33,6 +73,32 @@ int pci_domains_supported = 1; unsigned long pci_cardbus_io_size = DEFAULT_CARDBUS_IO_SIZE; unsigned long pci_cardbus_mem_size = DEFAULT_CARDBUS_MEM_SIZE; +#define DEFAULT_HOTPLUG_IO_SIZE (256) +#define DEFAULT_HOTPLUG_MEM_SIZE (2*1024*1024) +/* pci=hpmemsize=nnM,hpiosize=nn can override this */ +unsigned long pci_hotplug_io_size = DEFAULT_HOTPLUG_IO_SIZE; +unsigned long pci_hotplug_mem_size = DEFAULT_HOTPLUG_MEM_SIZE; + +enum pcie_bus_config_types pcie_bus_config = PCIE_BUS_TUNE_OFF; + +/* + * The default CLS is used if arch didn't set CLS explicitly and not + * all pci devices agree on the same value. Arch can override either + * the dfl or actual value as it sees fit. Don't forget this is + * measured in 32-bit words, not bytes. + */ +u8 pci_dfl_cache_line_size = L1_CACHE_BYTES >> 2; +u8 pci_cache_line_size; + +/* + * If we set up a device for bus mastering, we need to check the latency + * timer as certain BIOSes forget to set it properly. + */ +unsigned int pcibios_max_latency = 255; + +/* If set, the PCIe ARI capability will not be used. */ +static bool pcie_ari_disabled; + /** * pci_bus_max_busnr - returns maximum PCI bus number of given bus' children * @bus: pointer to PCI bus structure to search @@ -40,44 +106,36 @@ unsigned long pci_cardbus_mem_size = DEFAULT_CARDBUS_MEM_SIZE; * 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) +unsigned char pci_bus_max_busnr(struct pci_bus *bus) { - struct list_head *tmp; + struct pci_bus *tmp; unsigned char max, n; - max = bus->subordinate; - list_for_each(tmp, &bus->children) { - n = pci_bus_max_busnr(pci_bus_b(tmp)); - if(n > max) + 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); -#if 0 -/** - * pci_max_busnr - returns maximum PCI bus number - * - * Returns the highest PCI bus number present in the system global list of - * PCI buses. - */ -unsigned char __devinit -pci_max_busnr(void) +#ifdef CONFIG_HAS_IOMEM +void __iomem *pci_ioremap_bar(struct pci_dev *pdev, int bar) { - struct pci_bus *bus = NULL; - unsigned char max, n; - - max = 0; - while ((bus = pci_find_next_bus(bus)) != NULL) { - n = pci_bus_max_busnr(bus); - if(n > max) - max = n; + /* + * 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 max; + return ioremap_nocache(pci_resource_start(pdev, bar), + pci_resource_len(pdev, bar)); } - -#endif /* 0 */ +EXPORT_SYMBOL_GPL(pci_ioremap_bar); +#endif #define PCI_FIND_CAP_TTL 48 @@ -140,7 +198,7 @@ static int __pci_bus_find_cap_start(struct pci_bus *bus, } /** - * pci_find_capability - query for devices' capabilities + * pci_find_capability - query for devices' capabilities * @dev: PCI device to query * @cap: capability code * @@ -149,12 +207,12 @@ static int __pci_bus_find_cap_start(struct pci_bus *bus, * 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_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_CHSWP CompactPCI HotSwap * %PCI_CAP_ID_PCIX PCI-X * %PCI_CAP_ID_EXP PCI Express */ @@ -168,15 +226,16 @@ int pci_find_capability(struct pci_dev *dev, int cap) return pos; } +EXPORT_SYMBOL(pci_find_capability); /** - * pci_bus_find_capability - query for devices' capabilities + * 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. + * 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 @@ -195,30 +254,34 @@ int pci_bus_find_capability(struct pci_bus *bus, unsigned int devfn, int cap) return pos; } +EXPORT_SYMBOL(pci_bus_find_capability); /** - * pci_find_ext_capability - Find an extended 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 requested extended capability structure + * 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. 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 + * 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_ext_capability(struct pci_dev *dev, int cap) +int pci_find_next_ext_capability(struct pci_dev *dev, int start, int cap) { u32 header; - int ttl = 480; /* 3840 bytes, minimum 8 bytes per capability */ - int pos = 0x100; + 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 <= 256) + 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; @@ -230,11 +293,11 @@ int pci_find_ext_capability(struct pci_dev *dev, int cap) return 0; while (ttl-- > 0) { - if (PCI_EXT_CAP_ID(header) == cap) + if (PCI_EXT_CAP_ID(header) == cap && pos != start) return pos; pos = PCI_EXT_CAP_NEXT(header); - if (pos < 0x100) + if (pos < PCI_CFG_SPACE_SIZE) break; if (pci_read_config_dword(dev, pos, &header) != PCIBIOS_SUCCESSFUL) @@ -243,6 +306,26 @@ int pci_find_ext_capability(struct pci_dev *dev, int cap) 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) @@ -320,30 +403,67 @@ EXPORT_SYMBOL_GPL(pci_find_ht_capability); * @res: child resource record for which parent is sought * * For given resource region of given device, return the resource - * region of parent bus the given region is contained in or where - * it should be allocated from. + * region of parent bus the given region is contained in. */ -struct resource * -pci_find_parent_resource(const struct pci_dev *dev, struct resource *res) +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; - struct resource *best = NULL; - for(i = 0; i < PCI_BUS_NUM_RESOURCES; i++) { - struct resource *r = bus->resource[i]; + pci_bus_for_each_resource(bus, r, i) { if (!r) continue; - if (res->start && !(res->start >= r->start && res->end <= r->end)) - continue; /* Not contained */ - if ((res->flags ^ r->flags) & (IORESOURCE_IO | IORESOURCE_MEM)) - continue; /* Wrong type */ - if (!((res->flags ^ r->flags) & IORESOURCE_PREFETCH)) - return r; /* Exact match */ - if ((res->flags & IORESOURCE_PREFETCH) && !(r->flags & IORESOURCE_PREFETCH)) - best = r; /* Approximating prefetchable by non-prefetchable */ + if (res->start && 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_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 best; + + return 0; } /** @@ -353,98 +473,99 @@ pci_find_parent_resource(const struct pci_dev *dev, struct resource *res) * 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) +static void pci_restore_bars(struct pci_dev *dev) { - int i, numres; + int i; - switch (dev->hdr_type) { - case PCI_HEADER_TYPE_NORMAL: - numres = 6; - break; - case PCI_HEADER_TYPE_BRIDGE: - numres = 2; - break; - case PCI_HEADER_TYPE_CARDBUS: - numres = 1; - break; - default: - /* Should never get here, but just in case... */ - return; - } + for (i = 0; i < PCI_BRIDGE_RESOURCES; i++) + pci_update_resource(dev, i); +} + +static struct pci_platform_pm_ops *pci_platform_pm; + +int pci_set_platform_pm(struct pci_platform_pm_ops *ops) +{ + if (!ops->is_manageable || !ops->set_state || !ops->choose_state + || !ops->sleep_wake) + return -EINVAL; + pci_platform_pm = ops; + return 0; +} - for (i = 0; i < numres; i ++) - pci_update_resource(dev, &dev->resource[i], i); +static inline bool platform_pci_power_manageable(struct pci_dev *dev) +{ + return pci_platform_pm ? pci_platform_pm->is_manageable(dev) : false; } -int (*platform_pci_set_power_state)(struct pci_dev *dev, pci_power_t t); +static inline int platform_pci_set_power_state(struct pci_dev *dev, + pci_power_t t) +{ + return pci_platform_pm ? pci_platform_pm->set_state(dev, t) : -ENOSYS; +} + +static inline pci_power_t platform_pci_choose_state(struct pci_dev *dev) +{ + return pci_platform_pm ? + pci_platform_pm->choose_state(dev) : PCI_POWER_ERROR; +} + +static inline int platform_pci_sleep_wake(struct pci_dev *dev, bool enable) +{ + return pci_platform_pm ? + pci_platform_pm->sleep_wake(dev, enable) : -ENODEV; +} + +static inline int platform_pci_run_wake(struct pci_dev *dev, bool enable) +{ + return pci_platform_pm ? + pci_platform_pm->run_wake(dev, enable) : -ENODEV; +} /** - * pci_set_power_state - Set the power state of a PCI device - * @dev: PCI device to be suspended - * @state: PCI power state (D0, D1, D2, D3hot, D3cold) we're entering - * - * Transition a device to a new power state, using the Power Management - * Capabilities in the device's config space. + * 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 trying to enter a lower state than we're already in. - * 0 if we're already in the requested state. - * -EIO if device does not support PCI PM. - * 0 if we can successfully change the power state. + * RETURN VALUE: + * -EINVAL if the requested state is invalid. + * -EIO if device does not support PCI PM or its PM capabilities register has a + * wrong version, or device doesn't support the requested state. + * 0 if device already is in the requested state. + * 0 if device's power state has been successfully changed. */ -int -pci_set_power_state(struct pci_dev *dev, pci_power_t state) +static int pci_raw_set_power_state(struct pci_dev *dev, pci_power_t state) { - int pm, need_restore = 0; - u16 pmcsr, pmc; + u16 pmcsr; + bool need_restore = false; - /* bound the state we're entering */ - if (state > PCI_D3hot) - state = PCI_D3hot; - - /* - * If the device or the parent bridge can't support PCI PM, ignore - * the request if we're doing anything besides putting it into D0 - * (which would only happen on boot). - */ - if ((state == PCI_D1 || state == PCI_D2) && pci_no_d1d2(dev)) + /* Check if we're already there */ + if (dev->current_state == state) return 0; - /* find PCI PM capability in list */ - pm = pci_find_capability(dev, PCI_CAP_ID_PM); - - /* abort if the device doesn't support PM capabilities */ - if (!pm) + 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 + * 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 > state) { - printk(KERN_ERR "%s(): %s: state=%d, current state=%d\n", - __FUNCTION__, pci_name(dev), state, dev->current_state); + if (state != PCI_D0 && dev->current_state <= PCI_D3cold + && dev->current_state > state) { + dev_err(&dev->dev, "invalid power transition (from state %d to %d)\n", + dev->current_state, state); return -EINVAL; - } else if (dev->current_state == state) - return 0; /* we're already there */ - - - pci_read_config_word(dev,pm + PCI_PM_PMC,&pmc); - if ((pmc & PCI_PM_CAP_VER_MASK) > 3) { - printk(KERN_DEBUG - "PCI: %s has unsupported PM cap regs version (%u)\n", - pci_name(dev), pmc & PCI_PM_CAP_VER_MASK); - return -EIO; } /* check if this device supports the desired state */ - if (state == PCI_D1 && !(pmc & PCI_PM_CAP_D1)) - return -EIO; - else if (state == PCI_D2 && !(pmc & PCI_PM_CAP_D2)) + if ((state == PCI_D1 && !dev->d1_support) + || (state == PCI_D2 && !dev->d2_support)) return -EIO; - pci_read_config_word(dev, pm + PCI_PM_CTRL, &pmcsr); + 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 @@ -457,10 +578,12 @@ pci_set_power_state(struct pci_dev *dev, pci_power_t state) 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 = 1; + need_restore = true; /* Fall-through: force to D0 */ default: pmcsr = 0; @@ -468,25 +591,23 @@ pci_set_power_state(struct pci_dev *dev, pci_power_t state) } /* enter specified state */ - pci_write_config_word(dev, pm + PCI_PM_CTRL, pmcsr); + 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) - msleep(pci_pm_d3_delay); + pci_dev_d3_sleep(dev); else if (state == PCI_D2 || dev->current_state == PCI_D2) - udelay(200); + udelay(PCI_PM_D2_DELAY); - /* - * Give firmware a chance to be called, such as ACPI _PRx, _PSx - * Firmware method after native method ? - */ - if (platform_pci_set_power_state) - platform_pci_set_power_state(dev, state); + pci_read_config_word(dev, dev->pm_cap + PCI_PM_CTRL, &pmcsr); + dev->current_state = (pmcsr & PCI_PM_CTRL_STATE_MASK); + if (dev->current_state != state && printk_ratelimit()) + dev_info(&dev->dev, "Refused to change power state, currently in D%d\n", + dev->current_state); - dev->current_state = state; - - /* According to section 5.4.1 of the "PCI BUS POWER MANAGEMENT + /* + * 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". @@ -501,11 +622,234 @@ pci_set_power_state(struct pci_dev *dev, pci_power_t state) if (need_restore) pci_restore_bars(dev); + if (dev->bus->self) + pcie_aspm_pm_state_change(dev->bus->self); + + return 0; +} + +/** + * pci_update_current_state - Read PCI power state of given device from its + * PCI PM registers and cache it + * @dev: PCI device to handle. + * @state: State to cache in case the device doesn't have the PM capability + */ +void pci_update_current_state(struct pci_dev *dev, pci_power_t state) +{ + if (dev->pm_cap) { + u16 pmcsr; + + /* + * Configuration space is not accessible for device in + * D3cold, so just keep or set D3cold for safety + */ + if (dev->current_state == PCI_D3cold) + return; + if (state == PCI_D3cold) { + dev->current_state = PCI_D3cold; + return; + } + pci_read_config_word(dev, dev->pm_cap + PCI_PM_CTRL, &pmcsr); + dev->current_state = (pmcsr & PCI_PM_CTRL_STATE_MASK); + } else { + dev->current_state = state; + } +} + +/** + * pci_power_up - Put the given device into D0 forcibly + * @dev: PCI device to power up + */ +void pci_power_up(struct pci_dev *dev) +{ + if (platform_pci_power_manageable(dev)) + platform_pci_set_power_state(dev, PCI_D0); + + pci_raw_set_power_state(dev, PCI_D0); + pci_update_current_state(dev, PCI_D0); +} + +/** + * pci_platform_power_transition - Use platform to change device power state + * @dev: PCI device to handle. + * @state: State to put the device into. + */ +static int pci_platform_power_transition(struct pci_dev *dev, pci_power_t state) +{ + int error; + + if (platform_pci_power_manageable(dev)) { + error = platform_pci_set_power_state(dev, state); + if (!error) + pci_update_current_state(dev, state); + } else + error = -ENODEV; + + if (error && !dev->pm_cap) /* Fall back to PCI_D0 */ + dev->current_state = PCI_D0; + + return error; +} + +/** + * pci_wakeup - Wake up a PCI device + * @pci_dev: Device to handle. + * @ign: ignored parameter + */ +static int pci_wakeup(struct pci_dev *pci_dev, void *ign) +{ + pci_wakeup_event(pci_dev); + pm_request_resume(&pci_dev->dev); return 0; } -pci_power_t (*platform_pci_choose_state)(struct pci_dev *dev, pm_message_t state); - +/** + * pci_wakeup_bus - Walk given bus and wake up devices on it + * @bus: Top bus of the subtree to walk. + */ +static void pci_wakeup_bus(struct pci_bus *bus) +{ + if (bus) + pci_walk_bus(bus, pci_wakeup, NULL); +} + +/** + * __pci_start_power_transition - Start power transition of a PCI device + * @dev: PCI device to handle. + * @state: State to put the device into. + */ +static void __pci_start_power_transition(struct pci_dev *dev, pci_power_t state) +{ + if (state == PCI_D0) { + pci_platform_power_transition(dev, PCI_D0); + /* + * Mandatory power management transition delays, see + * PCI Express Base Specification Revision 2.0 Section + * 6.6.1: Conventional Reset. Do not delay for + * devices powered on/off by corresponding bridge, + * because have already delayed for the bridge. + */ + if (dev->runtime_d3cold) { + msleep(dev->d3cold_delay); + /* + * When powering on a bridge from D3cold, the + * whole hierarchy may be powered on into + * D0uninitialized state, resume them to give + * them a chance to suspend again + */ + pci_wakeup_bus(dev->subordinate); + } + } +} + +/** + * __pci_dev_set_current_state - Set current state of a PCI device + * @dev: Device to handle + * @data: pointer to state to be set + */ +static int __pci_dev_set_current_state(struct pci_dev *dev, void *data) +{ + pci_power_t state = *(pci_power_t *)data; + + dev->current_state = state; + return 0; +} + +/** + * __pci_bus_set_current_state - Walk given bus and set current state of devices + * @bus: Top bus of the subtree to walk. + * @state: state to be set + */ +static void __pci_bus_set_current_state(struct pci_bus *bus, pci_power_t state) +{ + if (bus) + pci_walk_bus(bus, __pci_dev_set_current_state, &state); +} + +/** + * __pci_complete_power_transition - Complete power transition of a PCI device + * @dev: PCI device to handle. + * @state: State to put the device into. + * + * This function should not be called directly by device drivers. + */ +int __pci_complete_power_transition(struct pci_dev *dev, pci_power_t state) +{ + int ret; + + if (state <= PCI_D0) + return -EINVAL; + ret = pci_platform_power_transition(dev, state); + /* Power off the bridge may power off the whole hierarchy */ + if (!ret && state == PCI_D3cold) + __pci_bus_set_current_state(dev->subordinate, PCI_D3cold); + return ret; +} +EXPORT_SYMBOL_GPL(__pci_complete_power_transition); + +/** + * pci_set_power_state - Set the power state of a PCI device + * @dev: PCI device to handle. + * @state: PCI power state (D0, D1, D2, D3hot) to put the device into. + * + * Transition a device to a new power state, using the platform firmware and/or + * the device's PCI PM registers. + * + * RETURN VALUE: + * -EINVAL if the requested state is invalid. + * -EIO if device does not support PCI PM or its PM capabilities register has a + * wrong version, or device doesn't support the requested state. + * 0 if device already is in the requested state. + * 0 if device's power state has been successfully changed. + */ +int pci_set_power_state(struct pci_dev *dev, pci_power_t state) +{ + int error; + + /* bound the state we're entering */ + if (state > PCI_D3cold) + state = PCI_D3cold; + else if (state < PCI_D0) + state = PCI_D0; + else if ((state == PCI_D1 || state == PCI_D2) && pci_no_d1d2(dev)) + /* + * If the device or the parent bridge do not support PCI PM, + * ignore the request if we're doing anything other than putting + * it into D0 (which would only happen on boot). + */ + return 0; + + /* Check if we're already there */ + if (dev->current_state == state) + return 0; + + __pci_start_power_transition(dev, state); + + /* This device is quirked not to be put into D3, so + don't put it in D3 */ + if (state >= PCI_D3hot && (dev->dev_flags & PCI_DEV_FLAGS_NO_D3)) + return 0; + + /* + * To put device in D3cold, we put device into D3hot in native + * way, then put device into D3cold with platform ops + */ + error = pci_raw_set_power_state(dev, state > PCI_D3hot ? + PCI_D3hot : state); + + if (!__pci_complete_power_transition(dev, state)) + error = 0; + /* + * When aspm_policy is "powersave" this call ensures + * that ASPM is configured. + */ + if (!error && dev->bus->self) + pcie_aspm_powersave_config_link(dev->bus->self); + + return error; +} +EXPORT_SYMBOL(pci_set_power_state); + /** * pci_choose_state - Choose the power state of a PCI device * @dev: PCI device to be suspended @@ -520,14 +864,12 @@ pci_power_t pci_choose_state(struct pci_dev *dev, pm_message_t state) { pci_power_t ret; - if (!pci_find_capability(dev, PCI_CAP_ID_PM)) + if (!dev->pm_cap) return PCI_D0; - if (platform_pci_choose_state) { - ret = platform_pci_choose_state(dev, state); - if (ret != PCI_POWER_ERROR) - return ret; - } + ret = platform_pci_choose_state(dev); + if (ret != PCI_POWER_ERROR) + return ret; switch (state.event) { case PM_EVENT_ON: @@ -539,91 +881,104 @@ pci_power_t pci_choose_state(struct pci_dev *dev, pm_message_t state) case PM_EVENT_HIBERNATE: return PCI_D3hot; default: - printk("Unrecognized suspend event %d\n", state.event); + dev_info(&dev->dev, "unrecognized suspend event %d\n", + state.event); BUG(); } return PCI_D0; } - EXPORT_SYMBOL(pci_choose_state); +#define PCI_EXP_SAVE_REGS 7 + +static struct pci_cap_saved_state *_pci_find_saved_cap(struct pci_dev *pci_dev, + 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 pos, i = 0; + int i = 0; struct pci_cap_saved_state *save_state; u16 *cap; - int found = 0; - pos = pci_find_capability(dev, PCI_CAP_ID_EXP); - if (pos <= 0) + if (!pci_is_pcie(dev)) return 0; save_state = pci_find_saved_cap(dev, PCI_CAP_ID_EXP); - if (!save_state) - save_state = kzalloc(sizeof(*save_state) + sizeof(u16) * 4, GFP_KERNEL); - else - found = 1; if (!save_state) { - dev_err(&dev->dev, "Out of memory in pci_save_pcie_state\n"); + dev_err(&dev->dev, "buffer not found in %s\n", __func__); return -ENOMEM; } - cap = (u16 *)&save_state->data[0]; - pci_read_config_word(dev, pos + PCI_EXP_DEVCTL, &cap[i++]); - pci_read_config_word(dev, pos + PCI_EXP_LNKCTL, &cap[i++]); - pci_read_config_word(dev, pos + PCI_EXP_SLTCTL, &cap[i++]); - pci_read_config_word(dev, pos + PCI_EXP_RTCTL, &cap[i++]); - save_state->cap_nr = PCI_CAP_ID_EXP; - if (!found) - pci_add_saved_cap(dev, save_state); + 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, pos; + int i = 0; struct pci_cap_saved_state *save_state; u16 *cap; save_state = pci_find_saved_cap(dev, PCI_CAP_ID_EXP); - pos = pci_find_capability(dev, PCI_CAP_ID_EXP); - if (!save_state || pos <= 0) + if (!save_state) return; - cap = (u16 *)&save_state->data[0]; - pci_write_config_word(dev, pos + PCI_EXP_DEVCTL, cap[i++]); - pci_write_config_word(dev, pos + PCI_EXP_LNKCTL, cap[i++]); - pci_write_config_word(dev, pos + PCI_EXP_SLTCTL, cap[i++]); - pci_write_config_word(dev, pos + PCI_EXP_RTCTL, cap[i++]); + 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, i = 0; + int pos; struct pci_cap_saved_state *save_state; - u16 *cap; - int found = 0; pos = pci_find_capability(dev, PCI_CAP_ID_PCIX); if (pos <= 0) return 0; save_state = pci_find_saved_cap(dev, PCI_CAP_ID_PCIX); - if (!save_state) - save_state = kzalloc(sizeof(*save_state) + sizeof(u16), GFP_KERNEL); - else - found = 1; if (!save_state) { - dev_err(&dev->dev, "Out of memory in pci_save_pcie_state\n"); + dev_err(&dev->dev, "buffer not found in %s\n", __func__); return -ENOMEM; } - cap = (u16 *)&save_state->data[0]; - pci_read_config_word(dev, pos + PCI_X_CMD, &cap[i++]); - save_state->cap_nr = PCI_CAP_ID_PCIX; - if (!found) - pci_add_saved_cap(dev, save_state); + pci_read_config_word(dev, pos + PCI_X_CMD, + (u16 *)save_state->cap.data); + return 0; } @@ -637,7 +992,7 @@ static void pci_restore_pcix_state(struct pci_dev *dev) pos = pci_find_capability(dev, PCI_CAP_ID_PCIX); if (!save_state || pos <= 0) return; - cap = (u16 *)&save_state->data[0]; + cap = (u16 *)&save_state->cap.data[0]; pci_write_config_word(dev, pos + PCI_X_CMD, cap[i++]); } @@ -647,57 +1002,201 @@ static void pci_restore_pcix_state(struct pci_dev *dev) * 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 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]); + pci_read_config_dword(dev, i * 4, &dev->saved_config_space[i]); + dev->state_saved = true; if ((i = pci_save_pcie_state(dev)) != 0) return i; if ((i = pci_save_pcix_state(dev)) != 0) return i; + if ((i = pci_save_vc_state(dev)) != 0) + return i; return 0; } +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 (;;) { + dev_dbg(&pdev->dev, "restoring config space at offset %#x (was %#x, writing %#x)\n", + offset, val, saved_val); + pci_write_config_dword(pdev, offset, saved_val); + if (retry-- <= 0) + return; + + pci_read_config_dword(pdev, offset, &val); + if (val == saved_val) + return; + + mdelay(1); + } +} + +static void pci_restore_config_space_range(struct pci_dev *pdev, + 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 */ -int -pci_restore_state(struct pci_dev *dev) +void pci_restore_state(struct pci_dev *dev) { - int i; - u32 val; + if (!dev->state_saved) + return; /* PCI Express register must be restored first */ pci_restore_pcie_state(dev); + pci_restore_ats_state(dev); + pci_restore_vc_state(dev); + + pci_restore_config_space(dev); - /* - * The Base Address register should be programmed before the command - * register(s) - */ - for (i = 15; i >= 0; i--) { - pci_read_config_dword(dev, i * 4, &val); - if (val != dev->saved_config_space[i]) { - printk(KERN_DEBUG "PM: Writing back config space on " - "device %s at offset %x (was %x, writing %x)\n", - pci_name(dev), i, - val, (int)dev->saved_config_space[i]); - pci_write_config_dword(dev,i * 4, - dev->saved_config_space[i]); - } - } pci_restore_pcix_state(dev); pci_restore_msi_state(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() + */ +static 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; } +/** + * 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; + u16 cmd; + u8 pin; err = pci_set_power_state(dev, PCI_D0); if (err < 0 && err != -EIO) @@ -707,6 +1206,17 @@ static int do_pci_enable_device(struct pci_dev *dev, int bars) 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; } @@ -719,21 +1229,64 @@ static int do_pci_enable_device(struct pci_dev *dev, int bars) */ int pci_reenable_device(struct pci_dev *dev) { - if (atomic_read(&dev->enable_cnt)) + if (pci_is_enabled(dev)) return do_pci_enable_device(dev, (1 << PCI_NUM_RESOURCES) - 1); return 0; } +EXPORT_SYMBOL(pci_reenable_device); -static int __pci_enable_device_flags(struct pci_dev *dev, - resource_size_t flags) +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) + dev_err(&dev->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; - if (atomic_add_return(1, &dev->enable_cnt) > 1) + /* + * 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 */ - for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) + 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); @@ -753,8 +1306,9 @@ static int __pci_enable_device_flags(struct pci_dev *dev, */ int pci_enable_device_io(struct pci_dev *dev) { - return __pci_enable_device_flags(dev, IORESOURCE_IO); + 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 @@ -766,8 +1320,9 @@ int pci_enable_device_io(struct pci_dev *dev) */ int pci_enable_device_mem(struct pci_dev *dev) { - return __pci_enable_device_flags(dev, IORESOURCE_MEM); + 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. @@ -782,8 +1337,9 @@ int pci_enable_device_mem(struct pci_dev *dev) */ int pci_enable_device(struct pci_dev *dev) { - return __pci_enable_device_flags(dev, IORESOURCE_MEM | IORESOURCE_IO); + 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 @@ -821,7 +1377,7 @@ static void pcim_release(struct device *gendev, void *res) pci_disable_device(dev); } -static struct pci_devres * get_pci_dr(struct pci_dev *pdev) +static struct pci_devres *get_pci_dr(struct pci_dev *pdev) { struct pci_devres *dr, *new_dr; @@ -835,7 +1391,7 @@ static struct pci_devres * get_pci_dr(struct pci_dev *pdev) return devres_get(&pdev->dev, new_dr, NULL, NULL); } -static struct pci_devres * find_pci_dr(struct pci_dev *pdev) +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); @@ -866,6 +1422,7 @@ int pcim_enable_device(struct pci_dev *pdev) } return rc; } +EXPORT_SYMBOL(pcim_enable_device); /** * pcim_pin_device - Pin managed PCI device @@ -884,6 +1441,30 @@ void pcim_pin_device(struct pci_dev *pdev) 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 @@ -893,7 +1474,44 @@ void pcim_pin_device(struct pci_dev *pdev) * is the default implementation. Architecture implementations can * override this. */ -void __attribute__ ((weak)) pcibios_disable_device (struct pci_dev *dev) {} +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 @@ -903,49 +1521,46 @@ void __attribute__ ((weak)) pcibios_disable_device (struct pci_dev *dev) {} * anymore. This only involves disabling PCI bus-mastering, if active. * * Note we don't actually disable the device until all callers of - * pci_device_enable() have called pci_device_disable(). + * pci_enable_device() have called pci_disable_device(). */ -void -pci_disable_device(struct pci_dev *dev) +void pci_disable_device(struct pci_dev *dev) { struct pci_devres *dr; - u16 pci_command; dr = find_pci_dr(dev); if (dr) dr->enabled = 0; - if (atomic_sub_return(1, &dev->enable_cnt) != 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; - 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); - } - dev->is_busmaster = 0; + do_pci_disable_device(dev); - pcibios_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 PCI-E device reset + * @dev: the PCIe device reset * @state: Reset state to enter into * * - * Sets the PCI-E reset state for the device. This is the default + * Sets the PCIe reset state for the device. This is the default * implementation. Architecture implementations can override this. */ -int __attribute__ ((weak)) pcibios_set_pcie_reset_state(struct pci_dev *dev, - enum pcie_reset_state state) +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 PCI-E device reset + * @dev: the PCIe device reset * @state: Reset state to enter into * * @@ -955,11 +1570,198 @@ 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); + +/** + * 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)) + schedule_delayed_work(&pci_pme_work, + msecs_to_jiffies(PME_TIMEOUT)); + mutex_unlock(&pci_pme_list_mutex); +} + +/** + * 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) +{ + 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 (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) { + dev_warn(&dev->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)) + schedule_delayed_work(&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); + } + } + + dev_dbg(&dev->dev, "PME# %s\n", enable ? "enabled" : "disabled"); +} +EXPORT_SYMBOL(pci_pme_active); /** - * pci_enable_wake - enable PCI device as wakeup event source + * __pci_enable_wake - enable PCI device as wakeup event source * @dev: PCI device affected * @state: PCI state from which device will issue wakeup events + * @runtime: True if the events are to be generated at run time * @enable: True to enable event generation; false to disable * * This enables the device as a wakeup event source, or disables it. @@ -967,79 +1769,676 @@ int pci_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state state) * called automatically by this routine. * * Devices with legacy power management (no standard PCI PM capabilities) - * always require such platform hooks. Depending on the platform, devices - * supporting the standard PCI PME# signal may require such platform hooks; - * they always update bits in config space to allow PME# generation. + * always require such platform hooks. * - * -EIO is returned if the device can't ever be a wakeup event source. - * -EINVAL is returned if the device can't generate wakeup events from - * the specified PCI state. Returns zero if the operation is successful. + * 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, int enable) +int __pci_enable_wake(struct pci_dev *dev, pci_power_t state, + bool runtime, bool enable) { - int pm; - int status; - u16 value; - - /* Note that drivers should verify device_may_wakeup(&dev->dev) - * before calling this function. Platform code should report - * errors when drivers try to enable wakeup on devices that - * can't issue wakeups, or on which wakeups were disabled by - * userspace updating the /sys/devices.../power/wakeup file. + int ret = 0; + + if (enable && !runtime && !device_may_wakeup(&dev->dev)) + return -EINVAL; + + /* 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. */ - status = call_platform_enable_wakeup(&dev->dev, enable); + if (enable) { + int error; + + if (pci_pme_capable(dev, state)) + pci_pme_active(dev, true); + else + ret = 1; + error = runtime ? platform_pci_run_wake(dev, true) : + platform_pci_sleep_wake(dev, true); + if (ret) + ret = error; + if (!ret) + dev->wakeup_prepared = true; + } else { + if (runtime) + platform_pci_run_wake(dev, false); + else + platform_pci_sleep_wake(dev, false); + pci_pme_active(dev, false); + dev->wakeup_prepared = false; + } - /* find PCI PM capability in list */ - pm = pci_find_capability(dev, PCI_CAP_ID_PM); + 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 + * + * 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) +{ + 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; + } + } else if (!dev->pm_cap) { + target_state = PCI_D0; + } else if (device_may_wakeup(&dev->dev)) { + /* + * 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--; + } + } - /* If device doesn't support PM Capabilities, but caller wants to - * disable wake events, it's a NOP. Otherwise fail unless the - * platform hooks handled this legacy device already. + 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) +{ + pci_power_t target_state = pci_target_state(dev); + int error; + + if (target_state == PCI_POWER_ERROR) + return -EIO; + + /* D3cold during system suspend/hibernate is not supported */ + if (target_state > PCI_D3hot) + target_state = PCI_D3hot; + + pci_enable_wake(dev, target_state, device_may_wakeup(&dev->dev)); + + 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 = pci_target_state(dev); + int error; + + if (target_state == PCI_POWER_ERROR) + return -EIO; + + dev->runtime_d3cold = target_state == PCI_D3cold; + + __pci_enable_wake(dev, target_state, true, pci_dev_run_wake(dev)); + + error = pci_set_power_state(dev, target_state); + + if (error) { + __pci_enable_wake(dev, target_state, true, 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_run_wake(&dev->dev)) + return true; + + if (!dev->pme_support) + return false; + + while (bus->parent) { + struct pci_dev *bridge = bus->self; + + if (device_run_wake(&bridge->dev)) + return true; + + bus = bus->parent; + } + + /* We have reached the root bus. */ + if (bus->bridge) + return device_run_wake(bus->bridge); + + return false; +} +EXPORT_SYMBOL_GPL(pci_dev_run_wake); + +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 */ - if (!pm) - return enable ? status : 0; + 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_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,&value); + pci_read_config_word(dev, pm + PCI_PM_PMC, &pmc); - value &= PCI_PM_CAP_PME_MASK; - value >>= ffs(PCI_PM_CAP_PME_MASK) - 1; /* First bit of mask */ + if ((pmc & PCI_PM_CAP_VER_MASK) > 3) { + dev_err(&dev->dev, "unsupported PM cap regs version (%u)\n", + pmc & PCI_PM_CAP_VER_MASK); + return; + } - /* Check if it can generate PME# from requested state. */ - if (!value || !(value & (1 << state))) { - /* if it can't, revert what the platform hook changed, - * always reporting the base "EINVAL, can't PME#" error + dev->pm_cap = pm; + dev->d3_delay = PCI_PM_D3_WAIT; + dev->d3cold_delay = PCI_PM_D3COLD_WAIT; + 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) + dev_printk(KERN_DEBUG, &dev->dev, "supports%s%s\n", + dev->d1_support ? " D1" : "", + dev->d2_support ? " D2" : ""); + } + + pmc &= PCI_PM_CAP_PME_MASK; + if (pmc) { + dev_printk(KERN_DEBUG, &dev->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. */ - if (enable) - call_platform_enable_wakeup(&dev->dev, 0); - return enable ? -EINVAL : 0; + device_set_wakeup_capable(&dev->dev, true); + /* Disable the PME# generation functionality */ + pci_pme_active(dev, false); } +} - pci_read_config_word(dev, pm + PCI_PM_CTRL, &value); +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); +} - /* Clear PME_Status by writing 1 to it and enable PME# */ - value |= PCI_PM_CTRL_PME_STATUS | PCI_PM_CTRL_PME_ENABLE; +/** + * _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 (!enable) - value &= ~PCI_PM_CTRL_PME_ENABLE; + if (extended) + pos = pci_find_ext_capability(dev, cap); + else + pos = pci_find_capability(dev, cap); + + if (pos <= 0) + 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) + dev_err(&dev->dev, + "unable to preallocate PCI Express save buffer\n"); + + error = pci_add_cap_save_buffer(dev, PCI_CAP_ID_PCIX, sizeof(u16)); + if (error) + dev_err(&dev->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_write_config_word(dev, pm + PCI_PM_CTRL, value); +/** + * pci_std_enable_acs - enable ACS on devices using standard ACS capabilites + * @dev: the PCI device + */ +static int 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 -ENODEV; + + 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); return 0; } -int -pci_get_interrupt_pin(struct pci_dev *dev, struct pci_dev **bridge) +/** + * 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_std_enable_acs(dev)) + return; + + pci_dev_specific_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_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; - pin--; - while (dev->bus->self) { - pin = (pin + PCI_SLOT(dev->devfn)) % 4; + + while (!pci_is_root_bus(dev->bus)) { + pin = pci_swizzle_interrupt_pin(dev, pin); dev = dev->bus->self; } *bridge = dev; @@ -1047,6 +2446,26 @@ pci_get_interrupt_pin(struct pci_dev *dev, struct pci_dev **bridge) } /** + * 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); +} + +/** * pci_release_region - Release a PCI bar * @pdev: PCI device whose resources were previously reserved by pci_request_region * @bar: BAR to release @@ -1072,36 +2491,43 @@ void pci_release_region(struct pci_dev *pdev, int bar) if (dr) dr->region_mask &= ~(1 << bar); } +EXPORT_SYMBOL(pci_release_region); /** - * pci_request_region - Reserved PCI I/O and memory resource + * __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. */ -int pci_request_region(struct pci_dev *pdev, int bar, const char *res_name) +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)) + } 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; } @@ -1112,17 +2538,57 @@ int pci_request_region(struct pci_dev *pdev, int bar, const char *res_name) return 0; err_out: - printk (KERN_WARNING "PCI: Unable to reserve %s region #%d:%llx@%llx " - "for device %s\n", - pci_resource_flags(pdev, bar) & IORESOURCE_IO ? "I/O" : "mem", - bar + 1, /* PCI BAR # */ - (unsigned long long)pci_resource_len(pdev, bar), - (unsigned long long)pci_resource_start(pdev, bar), - pci_name(pdev)); + dev_warn(&pdev->dev, "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 @@ -1138,32 +2604,49 @@ void pci_release_selected_regions(struct pci_dev *pdev, int bars) if (bars & (1 << i)) pci_release_region(pdev, i); } +EXPORT_SYMBOL(pci_release_selected_regions); -/** - * 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) +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)) + if (__pci_request_region(pdev, i, res_name, excl)) goto err_out; return 0; err_out: - while(--i >= 0) + 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 @@ -1177,6 +2660,7 @@ 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 @@ -1195,53 +2679,110 @@ 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_set_master - enables bus-mastering for device dev - * @dev: the PCI device to enable + * 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. * - * Enables bus-mastering on the device and calls pcibios_set_master() - * to do the needed arch specific settings. + * 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. */ -void -pci_set_master(struct pci_dev *dev) +int pci_request_regions_exclusive(struct pci_dev *pdev, const char *res_name) { - u16 cmd; + return pci_request_selected_regions_exclusive(pdev, + ((1 << 6) - 1), res_name); +} +EXPORT_SYMBOL(pci_request_regions_exclusive); - pci_read_config_word(dev, PCI_COMMAND, &cmd); - if (! (cmd & PCI_COMMAND_MASTER)) { - pr_debug("PCI: Enabling bus mastering for device %s\n", pci_name(dev)); - cmd |= PCI_COMMAND_MASTER; +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) { + dev_dbg(&dev->dev, "%s bus mastering\n", + enable ? "enabling" : "disabling"); pci_write_config_word(dev, PCI_COMMAND, cmd); } - dev->is_busmaster = 1; - pcibios_set_master(dev); + dev->is_busmaster = enable; } -#ifdef PCI_DISABLE_MWI -int pci_set_mwi(struct pci_dev *dev) +/** + * 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 0; + return str; } -int pci_try_set_mwi(struct pci_dev *dev) +/** + * pcibios_set_master - enable PCI bus-mastering for device dev + * @dev: the PCI device to enable + * + * Enables PCI bus-mastering for the device. This is the default + * implementation. Architecture specific implementations can override + * this if necessary. + */ +void __weak pcibios_set_master(struct pci_dev *dev) { - return 0; + u8 lat; + + /* The latency timer doesn't apply to PCIe (either Type 0 or Type 1) */ + if (pci_is_pcie(dev)) + return; + + pci_read_config_byte(dev, PCI_LATENCY_TIMER, &lat); + if (lat < 16) + lat = (64 <= pcibios_max_latency) ? 64 : pcibios_max_latency; + else if (lat > pcibios_max_latency) + lat = pcibios_max_latency; + else + return; + + pci_write_config_byte(dev, PCI_LATENCY_TIMER, lat); } -void pci_clear_mwi(struct pci_dev *dev) +/** + * pci_set_master - enables bus-mastering for device dev + * @dev: the PCI device to enable + * + * Enables bus-mastering on the device and calls pcibios_set_master() + * to do the needed arch specific settings. + */ +void pci_set_master(struct pci_dev *dev) { + __pci_set_master(dev, true); + pcibios_set_master(dev); } +EXPORT_SYMBOL(pci_set_master); -#else - -#ifndef PCI_CACHE_LINE_BYTES -#define PCI_CACHE_LINE_BYTES L1_CACHE_BYTES -#endif - -/* This can be overridden by arch code. */ -/* Don't forget this is measured in 32-bit words, not bytes */ -u8 pci_cache_line_size = PCI_CACHE_LINE_BYTES / 4; +/** + * pci_clear_master - disables bus-mastering for device dev + * @dev: the PCI device to disable + */ +void pci_clear_master(struct pci_dev *dev) +{ + __pci_set_master(dev, false); +} +EXPORT_SYMBOL(pci_clear_master); /** * pci_set_cacheline_size - ensure the CACHE_LINE_SIZE register is programmed @@ -1253,13 +2794,12 @@ u8 pci_cache_line_size = PCI_CACHE_LINE_BYTES / 4; * * RETURNS: An appropriate -ERRNO error value on error, or zero for success. */ -static int -pci_set_cacheline_size(struct pci_dev *dev) +int pci_set_cacheline_size(struct pci_dev *dev) { u8 cacheline_size; if (!pci_cache_line_size) - return -EINVAL; /* The system doesn't support MWI. */ + return -EINVAL; /* Validate current setting: the PCI_CACHE_LINE_SIZE must be equal to or multiple of the right value. */ @@ -1275,11 +2815,12 @@ pci_set_cacheline_size(struct pci_dev *dev) if (cacheline_size == pci_cache_line_size) return 0; - printk(KERN_DEBUG "PCI: cache line size of %d is not supported " - "by device %s\n", pci_cache_line_size << 2, pci_name(dev)); + dev_printk(KERN_DEBUG, &dev->dev, "cache line size of %d is not supported\n", + pci_cache_line_size << 2); return -EINVAL; } +EXPORT_SYMBOL_GPL(pci_set_cacheline_size); /** * pci_set_mwi - enables memory-write-invalidate PCI transaction @@ -1289,9 +2830,11 @@ pci_set_cacheline_size(struct pci_dev *dev) * * RETURNS: An appropriate -ERRNO error value on error, or zero for success. */ -int -pci_set_mwi(struct pci_dev *dev) +int pci_set_mwi(struct pci_dev *dev) { +#ifdef PCI_DISABLE_MWI + return 0; +#else int rc; u16 cmd; @@ -1300,15 +2843,15 @@ pci_set_mwi(struct pci_dev *dev) return rc; pci_read_config_word(dev, PCI_COMMAND, &cmd); - if (! (cmd & PCI_COMMAND_INVALIDATE)) { - pr_debug("PCI: Enabling Mem-Wr-Inval for device %s\n", - pci_name(dev)); + if (!(cmd & PCI_COMMAND_INVALIDATE)) { + dev_dbg(&dev->dev, "enabling Mem-Wr-Inval\n"); cmd |= PCI_COMMAND_INVALIDATE; pci_write_config_word(dev, PCI_COMMAND, cmd); } - return 0; +#endif } +EXPORT_SYMBOL(pci_set_mwi); /** * pci_try_set_mwi - enables memory-write-invalidate PCI transaction @@ -1321,9 +2864,13 @@ pci_set_mwi(struct pci_dev *dev) */ int pci_try_set_mwi(struct pci_dev *dev) { - int rc = pci_set_mwi(dev); - return rc; +#ifdef PCI_DISABLE_MWI + return 0; +#else + return pci_set_mwi(dev); +#endif } +EXPORT_SYMBOL(pci_try_set_mwi); /** * pci_clear_mwi - disables Memory-Write-Invalidate for device dev @@ -1331,9 +2878,9 @@ int pci_try_set_mwi(struct pci_dev *dev) * * Disables PCI Memory-Write-Invalidate transaction on the device */ -void -pci_clear_mwi(struct pci_dev *dev) +void pci_clear_mwi(struct pci_dev *dev) { +#ifndef PCI_DISABLE_MWI u16 cmd; pci_read_config_word(dev, PCI_COMMAND, &cmd); @@ -1341,8 +2888,9 @@ pci_clear_mwi(struct pci_dev *dev) cmd &= ~PCI_COMMAND_INVALIDATE; pci_write_config_word(dev, PCI_COMMAND, cmd); } +#endif } -#endif /* ! PCI_DISABLE_MWI */ +EXPORT_SYMBOL(pci_clear_mwi); /** * pci_intx - enables/disables PCI INTx for device dev @@ -1351,18 +2899,16 @@ pci_clear_mwi(struct pci_dev *dev) * * Enables/disables PCI INTx for device dev */ -void -pci_intx(struct pci_dev *pdev, int enable) +void pci_intx(struct pci_dev *pdev, int enable) { u16 pci_command, new; pci_read_config_word(pdev, PCI_COMMAND, &pci_command); - if (enable) { + if (enable) new = pci_command & ~PCI_COMMAND_INTX_DISABLE; - } else { + else new = pci_command | PCI_COMMAND_INTX_DISABLE; - } if (new != pci_command) { struct pci_devres *dr; @@ -1376,20 +2922,139 @@ pci_intx(struct pci_dev *pdev, int enable) } } } +EXPORT_SYMBOL_GPL(pci_intx); /** - * pci_msi_off - disables any msi or msix capabilities + * pci_intx_mask_supported - probe for INTx masking support * @dev: the PCI device to operate on * - * If you want to use msi see pci_enable_msi and friends. - * This is a lower level primitive that allows us to disable - * msi operation at the device level. + * Check if the device dev support INTx masking via the config space + * command word. + */ +bool pci_intx_mask_supported(struct pci_dev *dev) +{ + bool mask_supported = false; + u16 orig, new; + + if (dev->broken_intx_masking) + return false; + + pci_cfg_access_lock(dev); + + pci_read_config_word(dev, PCI_COMMAND, &orig); + pci_write_config_word(dev, PCI_COMMAND, + orig ^ PCI_COMMAND_INTX_DISABLE); + pci_read_config_word(dev, PCI_COMMAND, &new); + + /* + * There's no way to protect against hardware bugs or detect them + * reliably, but as long as we know what the value should be, let's + * go ahead and check it. + */ + if ((new ^ orig) & ~PCI_COMMAND_INTX_DISABLE) { + dev_err(&dev->dev, "Command register changed from 0x%x to 0x%x: driver or hardware bug?\n", + orig, new); + } else if ((new ^ orig) & PCI_COMMAND_INTX_DISABLE) { + mask_supported = true; + pci_write_config_word(dev, PCI_COMMAND, orig); + } + + pci_cfg_access_unlock(dev); + return mask_supported; +} +EXPORT_SYMBOL_GPL(pci_intx_mask_supported); + +static bool pci_check_and_set_intx_mask(struct pci_dev *dev, bool mask) +{ + struct pci_bus *bus = dev->bus; + bool mask_updated = true; + u32 cmd_status_dword; + u16 origcmd, newcmd; + unsigned long flags; + bool irq_pending; + + /* + * We do a single dword read to retrieve both command and status. + * Document assumptions that make this possible. + */ + BUILD_BUG_ON(PCI_COMMAND % 4); + BUILD_BUG_ON(PCI_COMMAND + 2 != PCI_STATUS); + + raw_spin_lock_irqsave(&pci_lock, flags); + + bus->ops->read(bus, dev->devfn, PCI_COMMAND, 4, &cmd_status_dword); + + irq_pending = (cmd_status_dword >> 16) & PCI_STATUS_INTERRUPT; + + /* + * Check interrupt status register to see whether our device + * triggered the interrupt (when masking) or the next IRQ is + * already pending (when unmasking). + */ + if (mask != irq_pending) { + mask_updated = false; + goto done; + } + + origcmd = cmd_status_dword; + newcmd = origcmd & ~PCI_COMMAND_INTX_DISABLE; + if (mask) + newcmd |= PCI_COMMAND_INTX_DISABLE; + if (newcmd != origcmd) + bus->ops->write(bus, dev->devfn, PCI_COMMAND, 2, newcmd); + +done: + raw_spin_unlock_irqrestore(&pci_lock, flags); + + return mask_updated; +} + +/** + * pci_check_and_mask_intx - mask INTx on pending interrupt + * @dev: the PCI device to operate on + * + * Check if the device dev has its INTx line asserted, mask it and + * return true in that case. False is returned if not interrupt was + * pending. + */ +bool pci_check_and_mask_intx(struct pci_dev *dev) +{ + return pci_check_and_set_intx_mask(dev, true); +} +EXPORT_SYMBOL_GPL(pci_check_and_mask_intx); + +/** + * pci_check_and_unmask_intx - unmask INTx if no interrupt is pending + * @dev: the PCI device to operate on + * + * Check if the device dev has its INTx line asserted, unmask it if not + * and return true. False is returned and the mask remains active if + * there was still an interrupt pending. + */ +bool pci_check_and_unmask_intx(struct pci_dev *dev) +{ + return pci_check_and_set_intx_mask(dev, false); +} +EXPORT_SYMBOL_GPL(pci_check_and_unmask_intx); + +/** + * pci_msi_off - disables any MSI or MSI-X capabilities + * @dev: the PCI device to operate on + * + * If you want to use MSI, see pci_enable_msi() and friends. + * This is a lower-level primitive that allows us to disable + * MSI operation at the device level. */ void pci_msi_off(struct pci_dev *dev) { int pos; u16 control; + /* + * This looks like it could go in msi.c, but we need it even when + * CONFIG_PCI_MSI=n. For the same reason, we can't use + * dev->msi_cap or dev->msix_cap here. + */ pos = pci_find_capability(dev, PCI_CAP_ID_MSI); if (pos) { pci_read_config_word(dev, pos + PCI_MSI_FLAGS, &control); @@ -1403,49 +3068,812 @@ void pci_msi_off(struct pci_dev *dev) pci_write_config_word(dev, pos + PCI_MSIX_FLAGS, control); } } +EXPORT_SYMBOL_GPL(pci_msi_off); -#ifndef HAVE_ARCH_PCI_SET_DMA_MASK -/* - * These can be overridden by arch-specific implementations +int pci_set_dma_max_seg_size(struct pci_dev *dev, unsigned int size) +{ + return dma_set_max_seg_size(&dev->dev, size); +} +EXPORT_SYMBOL(pci_set_dma_max_seg_size); + +int pci_set_dma_seg_boundary(struct pci_dev *dev, unsigned long mask) +{ + return dma_set_seg_boundary(&dev->dev, mask); +} +EXPORT_SYMBOL(pci_set_dma_seg_boundary); + +/** + * pci_wait_for_pending_transaction - waits for pending transaction + * @dev: the PCI device to operate on + * + * Return 0 if transaction is pending 1 otherwise. */ -int -pci_set_dma_mask(struct pci_dev *dev, u64 mask) +int pci_wait_for_pending_transaction(struct pci_dev *dev) { - if (!pci_dma_supported(dev, mask)) - return -EIO; + if (!pci_is_pcie(dev)) + return 1; + + return pci_wait_for_pending(dev, pci_pcie_cap(dev) + PCI_EXP_DEVSTA, + PCI_EXP_DEVSTA_TRPND); +} +EXPORT_SYMBOL(pci_wait_for_pending_transaction); + +static int pcie_flr(struct pci_dev *dev, int probe) +{ + u32 cap; + + pcie_capability_read_dword(dev, PCI_EXP_DEVCAP, &cap); + if (!(cap & PCI_EXP_DEVCAP_FLR)) + return -ENOTTY; + + if (probe) + return 0; - dev->dma_mask = mask; + if (!pci_wait_for_pending_transaction(dev)) + dev_err(&dev->dev, "transaction is not cleared; proceeding with reset anyway\n"); + + pcie_capability_set_word(dev, PCI_EXP_DEVCTL, PCI_EXP_DEVCTL_BCR_FLR); + + msleep(100); return 0; } - -int -pci_set_consistent_dma_mask(struct pci_dev *dev, u64 mask) + +static int pci_af_flr(struct pci_dev *dev, int probe) { - if (!pci_dma_supported(dev, mask)) - return -EIO; + int pos; + u8 cap; + + pos = pci_find_capability(dev, PCI_CAP_ID_AF); + if (!pos) + return -ENOTTY; + + pci_read_config_byte(dev, pos + PCI_AF_CAP, &cap); + if (!(cap & PCI_AF_CAP_TP) || !(cap & PCI_AF_CAP_FLR)) + return -ENOTTY; + + if (probe) + return 0; + + /* + * Wait for Transaction Pending bit to clear. A word-aligned test + * is used, so we use the conrol offset rather than status and shift + * the test bit to match. + */ + if (pci_wait_for_pending(dev, pos + PCI_AF_CTRL, + PCI_AF_STATUS_TP << 8)) + goto clear; + + dev_err(&dev->dev, "transaction is not cleared; proceeding with reset anyway\n"); - dev->dev.coherent_dma_mask = mask; +clear: + pci_write_config_byte(dev, pos + PCI_AF_CTRL, PCI_AF_CTRL_FLR); + msleep(100); return 0; } -#endif -#ifndef HAVE_ARCH_PCI_SET_DMA_MAX_SEGMENT_SIZE -int pci_set_dma_max_seg_size(struct pci_dev *dev, unsigned int size) +/** + * pci_pm_reset - Put device into PCI_D3 and back into PCI_D0. + * @dev: Device to reset. + * @probe: If set, only check if the device can be reset this way. + * + * If @dev supports native PCI PM and its PCI_PM_CTRL_NO_SOFT_RESET flag is + * unset, it will be reinitialized internally when going from PCI_D3hot to + * PCI_D0. If that's the case and the device is not in a low-power state + * already, force it into PCI_D3hot and back to PCI_D0, causing it to be reset. + * + * NOTE: This causes the caller to sleep for twice the device power transition + * cooldown period, which for the D0->D3hot and D3hot->D0 transitions is 10 ms + * by default (i.e. unless the @dev's d3_delay field has a different value). + * Moreover, only devices in D0 can be reset by this function. + */ +static int pci_pm_reset(struct pci_dev *dev, int probe) { - return dma_set_max_seg_size(&dev->dev, size); + u16 csr; + + if (!dev->pm_cap) + return -ENOTTY; + + pci_read_config_word(dev, dev->pm_cap + PCI_PM_CTRL, &csr); + if (csr & PCI_PM_CTRL_NO_SOFT_RESET) + return -ENOTTY; + + if (probe) + return 0; + + if (dev->current_state != PCI_D0) + return -EINVAL; + + csr &= ~PCI_PM_CTRL_STATE_MASK; + csr |= PCI_D3hot; + pci_write_config_word(dev, dev->pm_cap + PCI_PM_CTRL, csr); + pci_dev_d3_sleep(dev); + + csr &= ~PCI_PM_CTRL_STATE_MASK; + csr |= PCI_D0; + pci_write_config_word(dev, dev->pm_cap + PCI_PM_CTRL, csr); + pci_dev_d3_sleep(dev); + + return 0; } -EXPORT_SYMBOL(pci_set_dma_max_seg_size); -#endif -#ifndef HAVE_ARCH_PCI_SET_DMA_SEGMENT_BOUNDARY -int pci_set_dma_seg_boundary(struct pci_dev *dev, unsigned long mask) +void __weak pcibios_reset_secondary_bus(struct pci_dev *dev) { - return dma_set_seg_boundary(&dev->dev, mask); + u16 ctrl; + + pci_read_config_word(dev, PCI_BRIDGE_CONTROL, &ctrl); + ctrl |= PCI_BRIDGE_CTL_BUS_RESET; + pci_write_config_word(dev, PCI_BRIDGE_CONTROL, ctrl); + /* + * PCI spec v3.0 7.6.4.2 requires minimum Trst of 1ms. Double + * this to 2ms to ensure that we meet the minimum requirement. + */ + msleep(2); + + ctrl &= ~PCI_BRIDGE_CTL_BUS_RESET; + pci_write_config_word(dev, PCI_BRIDGE_CONTROL, ctrl); + + /* + * Trhfa for conventional PCI is 2^25 clock cycles. + * Assuming a minimum 33MHz clock this results in a 1s + * delay before we can consider subordinate devices to + * be re-initialized. PCIe has some ways to shorten this, + * but we don't make use of them yet. + */ + ssleep(1); } -EXPORT_SYMBOL(pci_set_dma_seg_boundary); -#endif + +/** + * pci_reset_bridge_secondary_bus - Reset the secondary bus on a PCI bridge. + * @dev: Bridge device + * + * Use the bridge control register to assert reset on the secondary bus. + * Devices on the secondary bus are left in power-on state. + */ +void pci_reset_bridge_secondary_bus(struct pci_dev *dev) +{ + pcibios_reset_secondary_bus(dev); +} +EXPORT_SYMBOL_GPL(pci_reset_bridge_secondary_bus); + +static int pci_parent_bus_reset(struct pci_dev *dev, int probe) +{ + struct pci_dev *pdev; + + if (pci_is_root_bus(dev->bus) || dev->subordinate || !dev->bus->self) + return -ENOTTY; + + list_for_each_entry(pdev, &dev->bus->devices, bus_list) + if (pdev != dev) + return -ENOTTY; + + if (probe) + return 0; + + pci_reset_bridge_secondary_bus(dev->bus->self); + + return 0; +} + +static int pci_reset_hotplug_slot(struct hotplug_slot *hotplug, int probe) +{ + int rc = -ENOTTY; + + if (!hotplug || !try_module_get(hotplug->ops->owner)) + return rc; + + if (hotplug->ops->reset_slot) + rc = hotplug->ops->reset_slot(hotplug, probe); + + module_put(hotplug->ops->owner); + + return rc; +} + +static int pci_dev_reset_slot_function(struct pci_dev *dev, int probe) +{ + struct pci_dev *pdev; + + if (dev->subordinate || !dev->slot) + return -ENOTTY; + + list_for_each_entry(pdev, &dev->bus->devices, bus_list) + if (pdev != dev && pdev->slot == dev->slot) + return -ENOTTY; + + return pci_reset_hotplug_slot(dev->slot->hotplug, probe); +} + +static int __pci_dev_reset(struct pci_dev *dev, int probe) +{ + int rc; + + might_sleep(); + + rc = pci_dev_specific_reset(dev, probe); + if (rc != -ENOTTY) + goto done; + + rc = pcie_flr(dev, probe); + if (rc != -ENOTTY) + goto done; + + rc = pci_af_flr(dev, probe); + if (rc != -ENOTTY) + goto done; + + rc = pci_pm_reset(dev, probe); + if (rc != -ENOTTY) + goto done; + + rc = pci_dev_reset_slot_function(dev, probe); + if (rc != -ENOTTY) + goto done; + + rc = pci_parent_bus_reset(dev, probe); +done: + return rc; +} + +static void pci_dev_lock(struct pci_dev *dev) +{ + pci_cfg_access_lock(dev); + /* block PM suspend, driver probe, etc. */ + device_lock(&dev->dev); +} + +/* Return 1 on successful lock, 0 on contention */ +static int pci_dev_trylock(struct pci_dev *dev) +{ + if (pci_cfg_access_trylock(dev)) { + if (device_trylock(&dev->dev)) + return 1; + pci_cfg_access_unlock(dev); + } + + return 0; +} + +static void pci_dev_unlock(struct pci_dev *dev) +{ + device_unlock(&dev->dev); + pci_cfg_access_unlock(dev); +} + +/** + * pci_reset_notify - notify device driver of reset + * @dev: device to be notified of reset + * @prepare: 'true' if device is about to be reset; 'false' if reset attempt + * completed + * + * Must be called prior to device access being disabled and after device + * access is restored. + */ +static void pci_reset_notify(struct pci_dev *dev, bool prepare) +{ + const struct pci_error_handlers *err_handler = + dev->driver ? dev->driver->err_handler : NULL; + if (err_handler && err_handler->reset_notify) + err_handler->reset_notify(dev, prepare); +} + +static void pci_dev_save_and_disable(struct pci_dev *dev) +{ + pci_reset_notify(dev, true); + + /* + * Wake-up device prior to save. PM registers default to D0 after + * reset and a simple register restore doesn't reliably return + * to a non-D0 state anyway. + */ + pci_set_power_state(dev, PCI_D0); + + pci_save_state(dev); + /* + * Disable the device by clearing the Command register, except for + * INTx-disable which is set. This not only disables MMIO and I/O port + * BARs, but also prevents the device from being Bus Master, preventing + * DMA from the device including MSI/MSI-X interrupts. For PCI 2.3 + * compliant devices, INTx-disable prevents legacy interrupts. + */ + pci_write_config_word(dev, PCI_COMMAND, PCI_COMMAND_INTX_DISABLE); +} + +static void pci_dev_restore(struct pci_dev *dev) +{ + pci_restore_state(dev); + pci_reset_notify(dev, false); +} + +static int pci_dev_reset(struct pci_dev *dev, int probe) +{ + int rc; + + if (!probe) + pci_dev_lock(dev); + + rc = __pci_dev_reset(dev, probe); + + if (!probe) + pci_dev_unlock(dev); + + return rc; +} + +/** + * __pci_reset_function - reset a PCI device function + * @dev: PCI device to reset + * + * Some devices allow an individual function to be reset without affecting + * other functions in the same device. The PCI device must be responsive + * to PCI config space in order to use this function. + * + * The device function is presumed to be unused when this function is called. + * Resetting the device will make the contents of PCI configuration space + * random, so any caller of this must be prepared to reinitialise the + * device including MSI, bus mastering, BARs, decoding IO and memory spaces, + * etc. + * + * Returns 0 if the device function was successfully reset or negative if the + * device doesn't support resetting a single function. + */ +int __pci_reset_function(struct pci_dev *dev) +{ + return pci_dev_reset(dev, 0); +} +EXPORT_SYMBOL_GPL(__pci_reset_function); + +/** + * __pci_reset_function_locked - reset a PCI device function while holding + * the @dev mutex lock. + * @dev: PCI device to reset + * + * Some devices allow an individual function to be reset without affecting + * other functions in the same device. The PCI device must be responsive + * to PCI config space in order to use this function. + * + * The device function is presumed to be unused and the caller is holding + * the device mutex lock when this function is called. + * Resetting the device will make the contents of PCI configuration space + * random, so any caller of this must be prepared to reinitialise the + * device including MSI, bus mastering, BARs, decoding IO and memory spaces, + * etc. + * + * Returns 0 if the device function was successfully reset or negative if the + * device doesn't support resetting a single function. + */ +int __pci_reset_function_locked(struct pci_dev *dev) +{ + return __pci_dev_reset(dev, 0); +} +EXPORT_SYMBOL_GPL(__pci_reset_function_locked); + +/** + * pci_probe_reset_function - check whether the device can be safely reset + * @dev: PCI device to reset + * + * Some devices allow an individual function to be reset without affecting + * other functions in the same device. The PCI device must be responsive + * to PCI config space in order to use this function. + * + * Returns 0 if the device function can be reset or negative if the + * device doesn't support resetting a single function. + */ +int pci_probe_reset_function(struct pci_dev *dev) +{ + return pci_dev_reset(dev, 1); +} + +/** + * pci_reset_function - quiesce and reset a PCI device function + * @dev: PCI device to reset + * + * Some devices allow an individual function to be reset without affecting + * other functions in the same device. The PCI device must be responsive + * to PCI config space in order to use this function. + * + * This function does not just reset the PCI portion of a device, but + * clears all the state associated with the device. This function differs + * from __pci_reset_function in that it saves and restores device state + * over the reset. + * + * Returns 0 if the device function was successfully reset or negative if the + * device doesn't support resetting a single function. + */ +int pci_reset_function(struct pci_dev *dev) +{ + int rc; + + rc = pci_dev_reset(dev, 1); + if (rc) + return rc; + + pci_dev_save_and_disable(dev); + + rc = pci_dev_reset(dev, 0); + + pci_dev_restore(dev); + + return rc; +} +EXPORT_SYMBOL_GPL(pci_reset_function); + +/** + * pci_try_reset_function - quiesce and reset a PCI device function + * @dev: PCI device to reset + * + * Same as above, except return -EAGAIN if unable to lock device. + */ +int pci_try_reset_function(struct pci_dev *dev) +{ + int rc; + + rc = pci_dev_reset(dev, 1); + if (rc) + return rc; + + pci_dev_save_and_disable(dev); + + if (pci_dev_trylock(dev)) { + rc = __pci_dev_reset(dev, 0); + pci_dev_unlock(dev); + } else + rc = -EAGAIN; + + pci_dev_restore(dev); + + return rc; +} +EXPORT_SYMBOL_GPL(pci_try_reset_function); + +/* Lock devices from the top of the tree down */ +static void pci_bus_lock(struct pci_bus *bus) +{ + struct pci_dev *dev; + + list_for_each_entry(dev, &bus->devices, bus_list) { + pci_dev_lock(dev); + if (dev->subordinate) + pci_bus_lock(dev->subordinate); + } +} + +/* Unlock devices from the bottom of the tree up */ +static void pci_bus_unlock(struct pci_bus *bus) +{ + struct pci_dev *dev; + + list_for_each_entry(dev, &bus->devices, bus_list) { + if (dev->subordinate) + pci_bus_unlock(dev->subordinate); + pci_dev_unlock(dev); + } +} + +/* Return 1 on successful lock, 0 on contention */ +static int pci_bus_trylock(struct pci_bus *bus) +{ + struct pci_dev *dev; + + list_for_each_entry(dev, &bus->devices, bus_list) { + if (!pci_dev_trylock(dev)) + goto unlock; + if (dev->subordinate) { + if (!pci_bus_trylock(dev->subordinate)) { + pci_dev_unlock(dev); + goto unlock; + } + } + } + return 1; + +unlock: + list_for_each_entry_continue_reverse(dev, &bus->devices, bus_list) { + if (dev->subordinate) + pci_bus_unlock(dev->subordinate); + pci_dev_unlock(dev); + } + return 0; +} + +/* Lock devices from the top of the tree down */ +static void pci_slot_lock(struct pci_slot *slot) +{ + struct pci_dev *dev; + + list_for_each_entry(dev, &slot->bus->devices, bus_list) { + if (!dev->slot || dev->slot != slot) + continue; + pci_dev_lock(dev); + if (dev->subordinate) + pci_bus_lock(dev->subordinate); + } +} + +/* Unlock devices from the bottom of the tree up */ +static void pci_slot_unlock(struct pci_slot *slot) +{ + struct pci_dev *dev; + + list_for_each_entry(dev, &slot->bus->devices, bus_list) { + if (!dev->slot || dev->slot != slot) + continue; + if (dev->subordinate) + pci_bus_unlock(dev->subordinate); + pci_dev_unlock(dev); + } +} + +/* Return 1 on successful lock, 0 on contention */ +static int pci_slot_trylock(struct pci_slot *slot) +{ + struct pci_dev *dev; + + list_for_each_entry(dev, &slot->bus->devices, bus_list) { + if (!dev->slot || dev->slot != slot) + continue; + if (!pci_dev_trylock(dev)) + goto unlock; + if (dev->subordinate) { + if (!pci_bus_trylock(dev->subordinate)) { + pci_dev_unlock(dev); + goto unlock; + } + } + } + return 1; + +unlock: + list_for_each_entry_continue_reverse(dev, + &slot->bus->devices, bus_list) { + if (!dev->slot || dev->slot != slot) + continue; + if (dev->subordinate) + pci_bus_unlock(dev->subordinate); + pci_dev_unlock(dev); + } + return 0; +} + +/* Save and disable devices from the top of the tree down */ +static void pci_bus_save_and_disable(struct pci_bus *bus) +{ + struct pci_dev *dev; + + list_for_each_entry(dev, &bus->devices, bus_list) { + pci_dev_save_and_disable(dev); + if (dev->subordinate) + pci_bus_save_and_disable(dev->subordinate); + } +} + +/* + * Restore devices from top of the tree down - parent bridges need to be + * restored before we can get to subordinate devices. + */ +static void pci_bus_restore(struct pci_bus *bus) +{ + struct pci_dev *dev; + + list_for_each_entry(dev, &bus->devices, bus_list) { + pci_dev_restore(dev); + if (dev->subordinate) + pci_bus_restore(dev->subordinate); + } +} + +/* Save and disable devices from the top of the tree down */ +static void pci_slot_save_and_disable(struct pci_slot *slot) +{ + struct pci_dev *dev; + + list_for_each_entry(dev, &slot->bus->devices, bus_list) { + if (!dev->slot || dev->slot != slot) + continue; + pci_dev_save_and_disable(dev); + if (dev->subordinate) + pci_bus_save_and_disable(dev->subordinate); + } +} + +/* + * Restore devices from top of the tree down - parent bridges need to be + * restored before we can get to subordinate devices. + */ +static void pci_slot_restore(struct pci_slot *slot) +{ + struct pci_dev *dev; + + list_for_each_entry(dev, &slot->bus->devices, bus_list) { + if (!dev->slot || dev->slot != slot) + continue; + pci_dev_restore(dev); + if (dev->subordinate) + pci_bus_restore(dev->subordinate); + } +} + +static int pci_slot_reset(struct pci_slot *slot, int probe) +{ + int rc; + + if (!slot) + return -ENOTTY; + + if (!probe) + pci_slot_lock(slot); + + might_sleep(); + + rc = pci_reset_hotplug_slot(slot->hotplug, probe); + + if (!probe) + pci_slot_unlock(slot); + + return rc; +} + +/** + * pci_probe_reset_slot - probe whether a PCI slot can be reset + * @slot: PCI slot to probe + * + * Return 0 if slot can be reset, negative if a slot reset is not supported. + */ +int pci_probe_reset_slot(struct pci_slot *slot) +{ + return pci_slot_reset(slot, 1); +} +EXPORT_SYMBOL_GPL(pci_probe_reset_slot); + +/** + * pci_reset_slot - reset a PCI slot + * @slot: PCI slot to reset + * + * A PCI bus may host multiple slots, each slot may support a reset mechanism + * independent of other slots. For instance, some slots may support slot power + * control. In the case of a 1:1 bus to slot architecture, this function may + * wrap the bus reset to avoid spurious slot related events such as hotplug. + * Generally a slot reset should be attempted before a bus reset. All of the + * function of the slot and any subordinate buses behind the slot are reset + * through this function. PCI config space of all devices in the slot and + * behind the slot is saved before and restored after reset. + * + * Return 0 on success, non-zero on error. + */ +int pci_reset_slot(struct pci_slot *slot) +{ + int rc; + + rc = pci_slot_reset(slot, 1); + if (rc) + return rc; + + pci_slot_save_and_disable(slot); + + rc = pci_slot_reset(slot, 0); + + pci_slot_restore(slot); + + return rc; +} +EXPORT_SYMBOL_GPL(pci_reset_slot); + +/** + * pci_try_reset_slot - Try to reset a PCI slot + * @slot: PCI slot to reset + * + * Same as above except return -EAGAIN if the slot cannot be locked + */ +int pci_try_reset_slot(struct pci_slot *slot) +{ + int rc; + + rc = pci_slot_reset(slot, 1); + if (rc) + return rc; + + pci_slot_save_and_disable(slot); + + if (pci_slot_trylock(slot)) { + might_sleep(); + rc = pci_reset_hotplug_slot(slot->hotplug, 0); + pci_slot_unlock(slot); + } else + rc = -EAGAIN; + + pci_slot_restore(slot); + + return rc; +} +EXPORT_SYMBOL_GPL(pci_try_reset_slot); + +static int pci_bus_reset(struct pci_bus *bus, int probe) +{ + if (!bus->self) + return -ENOTTY; + + if (probe) + return 0; + + pci_bus_lock(bus); + + might_sleep(); + + pci_reset_bridge_secondary_bus(bus->self); + + pci_bus_unlock(bus); + + return 0; +} + +/** + * pci_probe_reset_bus - probe whether a PCI bus can be reset + * @bus: PCI bus to probe + * + * Return 0 if bus can be reset, negative if a bus reset is not supported. + */ +int pci_probe_reset_bus(struct pci_bus *bus) +{ + return pci_bus_reset(bus, 1); +} +EXPORT_SYMBOL_GPL(pci_probe_reset_bus); + +/** + * pci_reset_bus - reset a PCI bus + * @bus: top level PCI bus to reset + * + * Do a bus reset on the given bus and any subordinate buses, saving + * and restoring state of all devices. + * + * Return 0 on success, non-zero on error. + */ +int pci_reset_bus(struct pci_bus *bus) +{ + int rc; + + rc = pci_bus_reset(bus, 1); + if (rc) + return rc; + + pci_bus_save_and_disable(bus); + + rc = pci_bus_reset(bus, 0); + + pci_bus_restore(bus); + + return rc; +} +EXPORT_SYMBOL_GPL(pci_reset_bus); + +/** + * pci_try_reset_bus - Try to reset a PCI bus + * @bus: top level PCI bus to reset + * + * Same as above except return -EAGAIN if the bus cannot be locked + */ +int pci_try_reset_bus(struct pci_bus *bus) +{ + int rc; + + rc = pci_bus_reset(bus, 1); + if (rc) + return rc; + + pci_bus_save_and_disable(bus); + + if (pci_bus_trylock(bus)) { + might_sleep(); + pci_reset_bridge_secondary_bus(bus->self); + pci_bus_unlock(bus); + } else + rc = -EAGAIN; + + pci_bus_restore(bus); + + return rc; +} +EXPORT_SYMBOL_GPL(pci_try_reset_bus); /** * pcix_get_max_mmrbc - get PCI-X maximum designed memory read byte count @@ -1456,18 +3884,17 @@ EXPORT_SYMBOL(pci_set_dma_seg_boundary); */ int pcix_get_max_mmrbc(struct pci_dev *dev) { - int err, cap; + int cap; u32 stat; cap = pci_find_capability(dev, PCI_CAP_ID_PCIX); if (!cap) return -EINVAL; - err = pci_read_config_dword(dev, cap + PCI_X_STATUS, &stat); - if (err) + if (pci_read_config_dword(dev, cap + PCI_X_STATUS, &stat)) return -EINVAL; - return (stat & PCI_X_STATUS_MAX_READ) >> 12; + return 512 << ((stat & PCI_X_STATUS_MAX_READ) >> 21); } EXPORT_SYMBOL(pcix_get_max_mmrbc); @@ -1480,18 +3907,17 @@ EXPORT_SYMBOL(pcix_get_max_mmrbc); */ int pcix_get_mmrbc(struct pci_dev *dev) { - int ret, cap; - u32 cmd; + int cap; + u16 cmd; cap = pci_find_capability(dev, PCI_CAP_ID_PCIX); if (!cap) return -EINVAL; - ret = pci_read_config_dword(dev, cap + PCI_X_CMD, &cmd); - if (!ret) - ret = 512 << ((cmd & PCI_X_CMD_MAX_READ) >> 2); + if (pci_read_config_word(dev, cap + PCI_X_CMD, &cmd)) + return -EINVAL; - return ret; + return 512 << ((cmd & PCI_X_CMD_MAX_READ) >> 2); } EXPORT_SYMBOL(pcix_get_mmrbc); @@ -1506,41 +3932,39 @@ EXPORT_SYMBOL(pcix_get_mmrbc); */ int pcix_set_mmrbc(struct pci_dev *dev, int mmrbc) { - int cap, err = -EINVAL; - u32 stat, cmd, v, o; + int cap; + u32 stat, v, o; + u16 cmd; if (mmrbc < 512 || mmrbc > 4096 || !is_power_of_2(mmrbc)) - goto out; + return -EINVAL; v = ffs(mmrbc) - 10; cap = pci_find_capability(dev, PCI_CAP_ID_PCIX); if (!cap) - goto out; + return -EINVAL; - err = pci_read_config_dword(dev, cap + PCI_X_STATUS, &stat); - if (err) - goto out; + if (pci_read_config_dword(dev, cap + PCI_X_STATUS, &stat)) + return -EINVAL; if (v > (stat & PCI_X_STATUS_MAX_READ) >> 21) return -E2BIG; - err = pci_read_config_dword(dev, cap + PCI_X_CMD, &cmd); - if (err) - goto out; + if (pci_read_config_word(dev, cap + PCI_X_CMD, &cmd)) + return -EINVAL; o = (cmd & PCI_X_CMD_MAX_READ) >> 2; if (o != v) { - if (v > o && dev->bus && - (dev->bus->bus_flags & PCI_BUS_FLAGS_NO_MMRBC)) + if (v > o && (dev->bus->bus_flags & PCI_BUS_FLAGS_NO_MMRBC)) return -EIO; cmd &= ~PCI_X_CMD_MAX_READ; cmd |= v << 2; - err = pci_write_config_dword(dev, cap + PCI_X_CMD, cmd); + if (pci_write_config_word(dev, cap + PCI_X_CMD, cmd)) + return -EIO; } -out: - return err; + return 0; } EXPORT_SYMBOL(pcix_set_mmrbc); @@ -1553,18 +3977,11 @@ EXPORT_SYMBOL(pcix_set_mmrbc); */ int pcie_get_readrq(struct pci_dev *dev) { - int ret, cap; u16 ctl; - cap = pci_find_capability(dev, PCI_CAP_ID_EXP); - if (!cap) - return -EINVAL; - - ret = pci_read_config_word(dev, cap + PCI_EXP_DEVCTL, &ctl); - if (!ret) - ret = 128 << ((ctl & PCI_EXP_DEVCTL_READRQ) >> 12); + pcie_capability_read_word(dev, PCI_EXP_DEVCTL, &ctl); - return ret; + return 128 << ((ctl & PCI_EXP_DEVCTL_READRQ) >> 12); } EXPORT_SYMBOL(pcie_get_readrq); @@ -1574,36 +3991,118 @@ EXPORT_SYMBOL(pcie_get_readrq); * @rq: maximum memory read count in bytes * valid values are 128, 256, 512, 1024, 2048, 4096 * - * If possible sets maximum read byte count + * If possible sets maximum memory read request in bytes */ int pcie_set_readrq(struct pci_dev *dev, int rq) { - int cap, err = -EINVAL; - u16 ctl, v; + u16 v; if (rq < 128 || rq > 4096 || !is_power_of_2(rq)) - goto out; + return -EINVAL; + + /* + * If using the "performance" PCIe config, we clamp the + * read rq size to the max packet size to prevent the + * host bridge generating requests larger than we can + * cope with + */ + if (pcie_bus_config == PCIE_BUS_PERFORMANCE) { + int mps = pcie_get_mps(dev); + + if (mps < rq) + rq = mps; + } v = (ffs(rq) - 8) << 12; - cap = pci_find_capability(dev, PCI_CAP_ID_EXP); - if (!cap) - goto out; + return pcie_capability_clear_and_set_word(dev, PCI_EXP_DEVCTL, + PCI_EXP_DEVCTL_READRQ, v); +} +EXPORT_SYMBOL(pcie_set_readrq); + +/** + * pcie_get_mps - get PCI Express maximum payload size + * @dev: PCI device to query + * + * Returns maximum payload size in bytes + */ +int pcie_get_mps(struct pci_dev *dev) +{ + u16 ctl; + + pcie_capability_read_word(dev, PCI_EXP_DEVCTL, &ctl); + + return 128 << ((ctl & PCI_EXP_DEVCTL_PAYLOAD) >> 5); +} +EXPORT_SYMBOL(pcie_get_mps); + +/** + * pcie_set_mps - set PCI Express maximum payload size + * @dev: PCI device to query + * @mps: maximum payload size in bytes + * valid values are 128, 256, 512, 1024, 2048, 4096 + * + * If possible sets maximum payload size + */ +int pcie_set_mps(struct pci_dev *dev, int mps) +{ + u16 v; + + if (mps < 128 || mps > 4096 || !is_power_of_2(mps)) + return -EINVAL; + + v = ffs(mps) - 8; + if (v > dev->pcie_mpss) + return -EINVAL; + v <<= 5; + + return pcie_capability_clear_and_set_word(dev, PCI_EXP_DEVCTL, + PCI_EXP_DEVCTL_PAYLOAD, v); +} +EXPORT_SYMBOL(pcie_set_mps); + +/** + * pcie_get_minimum_link - determine minimum link settings of a PCI device + * @dev: PCI device to query + * @speed: storage for minimum speed + * @width: storage for minimum width + * + * This function will walk up the PCI device chain and determine the minimum + * link width and speed of the device. + */ +int pcie_get_minimum_link(struct pci_dev *dev, enum pci_bus_speed *speed, + enum pcie_link_width *width) +{ + int ret; + + *speed = PCI_SPEED_UNKNOWN; + *width = PCIE_LNK_WIDTH_UNKNOWN; + + while (dev) { + u16 lnksta; + enum pci_bus_speed next_speed; + enum pcie_link_width next_width; - err = pci_read_config_word(dev, cap + PCI_EXP_DEVCTL, &ctl); - if (err) - goto out; + ret = pcie_capability_read_word(dev, PCI_EXP_LNKSTA, &lnksta); + if (ret) + return ret; + + next_speed = pcie_link_speed[lnksta & PCI_EXP_LNKSTA_CLS]; + next_width = (lnksta & PCI_EXP_LNKSTA_NLW) >> + PCI_EXP_LNKSTA_NLW_SHIFT; + + if (next_speed < *speed) + *speed = next_speed; - if ((ctl & PCI_EXP_DEVCTL_READRQ) != v) { - ctl &= ~PCI_EXP_DEVCTL_READRQ; - ctl |= v; - err = pci_write_config_dword(dev, cap + PCI_EXP_DEVCTL, ctl); + if (next_width < *width) + *width = next_width; + + dev = dev->bus->self; } -out: - return err; + return 0; } -EXPORT_SYMBOL(pcie_set_readrq); +EXPORT_SYMBOL(pcie_get_minimum_link); /** * pci_select_bars - Make BAR mask from the type of resource @@ -1620,25 +4119,306 @@ int pci_select_bars(struct pci_dev *dev, unsigned long flags) bars |= (1 << i); return bars; } +EXPORT_SYMBOL(pci_select_bars); + +/** + * pci_resource_bar - get position of the BAR associated with a resource + * @dev: the PCI device + * @resno: the resource number + * @type: the BAR type to be filled in + * + * Returns BAR position in config space, or 0 if the BAR is invalid. + */ +int pci_resource_bar(struct pci_dev *dev, int resno, enum pci_bar_type *type) +{ + int reg; + + if (resno < PCI_ROM_RESOURCE) { + *type = pci_bar_unknown; + return PCI_BASE_ADDRESS_0 + 4 * resno; + } else if (resno == PCI_ROM_RESOURCE) { + *type = pci_bar_mem32; + return dev->rom_base_reg; + } else if (resno < PCI_BRIDGE_RESOURCES) { + /* device specific resource */ + reg = pci_iov_resource_bar(dev, resno, type); + if (reg) + return reg; + } + + dev_err(&dev->dev, "BAR %d: invalid resource\n", resno); + return 0; +} + +/* Some architectures require additional programming to enable VGA */ +static arch_set_vga_state_t arch_set_vga_state; + +void __init pci_register_set_vga_state(arch_set_vga_state_t func) +{ + arch_set_vga_state = func; /* NULL disables */ +} + +static int pci_set_vga_state_arch(struct pci_dev *dev, bool decode, + unsigned int command_bits, u32 flags) +{ + if (arch_set_vga_state) + return arch_set_vga_state(dev, decode, command_bits, + flags); + return 0; +} + +/** + * pci_set_vga_state - set VGA decode state on device and parents if requested + * @dev: the PCI device + * @decode: true = enable decoding, false = disable decoding + * @command_bits: PCI_COMMAND_IO and/or PCI_COMMAND_MEMORY + * @flags: traverse ancestors and change bridges + * CHANGE_BRIDGE_ONLY / CHANGE_BRIDGE + */ +int pci_set_vga_state(struct pci_dev *dev, bool decode, + unsigned int command_bits, u32 flags) +{ + struct pci_bus *bus; + struct pci_dev *bridge; + u16 cmd; + int rc; + + WARN_ON((flags & PCI_VGA_STATE_CHANGE_DECODES) && (command_bits & ~(PCI_COMMAND_IO|PCI_COMMAND_MEMORY))); + + /* ARCH specific VGA enables */ + rc = pci_set_vga_state_arch(dev, decode, command_bits, flags); + if (rc) + return rc; + + if (flags & PCI_VGA_STATE_CHANGE_DECODES) { + pci_read_config_word(dev, PCI_COMMAND, &cmd); + if (decode == true) + cmd |= command_bits; + else + cmd &= ~command_bits; + pci_write_config_word(dev, PCI_COMMAND, cmd); + } + + if (!(flags & PCI_VGA_STATE_CHANGE_BRIDGE)) + return 0; + + bus = dev->bus; + while (bus) { + bridge = bus->self; + if (bridge) { + pci_read_config_word(bridge, PCI_BRIDGE_CONTROL, + &cmd); + if (decode == true) + cmd |= PCI_BRIDGE_CTL_VGA; + else + cmd &= ~PCI_BRIDGE_CTL_VGA; + pci_write_config_word(bridge, PCI_BRIDGE_CONTROL, + cmd); + } + bus = bus->parent; + } + return 0; +} -static void __devinit pci_no_domains(void) +bool pci_device_is_present(struct pci_dev *pdev) +{ + u32 v; + + return pci_bus_read_dev_vendor_id(pdev->bus, pdev->devfn, &v, 0); +} +EXPORT_SYMBOL_GPL(pci_device_is_present); + +#define RESOURCE_ALIGNMENT_PARAM_SIZE COMMAND_LINE_SIZE +static char resource_alignment_param[RESOURCE_ALIGNMENT_PARAM_SIZE] = {0}; +static DEFINE_SPINLOCK(resource_alignment_lock); + +/** + * pci_specified_resource_alignment - get resource alignment specified by user. + * @dev: the PCI device to get + * + * RETURNS: Resource alignment if it is specified. + * Zero if it is not specified. + */ +static resource_size_t pci_specified_resource_alignment(struct pci_dev *dev) +{ + int seg, bus, slot, func, align_order, count; + resource_size_t align = 0; + char *p; + + spin_lock(&resource_alignment_lock); + p = resource_alignment_param; + while (*p) { + count = 0; + if (sscanf(p, "%d%n", &align_order, &count) == 1 && + p[count] == '@') { + p += count + 1; + } else { + align_order = -1; + } + if (sscanf(p, "%x:%x:%x.%x%n", + &seg, &bus, &slot, &func, &count) != 4) { + seg = 0; + if (sscanf(p, "%x:%x.%x%n", + &bus, &slot, &func, &count) != 3) { + /* Invalid format */ + printk(KERN_ERR "PCI: Can't parse resource_alignment parameter: %s\n", + p); + break; + } + } + p += count; + if (seg == pci_domain_nr(dev->bus) && + bus == dev->bus->number && + slot == PCI_SLOT(dev->devfn) && + func == PCI_FUNC(dev->devfn)) { + if (align_order == -1) + align = PAGE_SIZE; + else + align = 1 << align_order; + /* Found */ + break; + } + if (*p != ';' && *p != ',') { + /* End of param or invalid format */ + break; + } + p++; + } + spin_unlock(&resource_alignment_lock); + return align; +} + +/* + * This function disables memory decoding and releases memory resources + * of the device specified by kernel's boot parameter 'pci=resource_alignment='. + * It also rounds up size to specified alignment. + * Later on, the kernel will assign page-aligned memory resource back + * to the device. + */ +void pci_reassigndev_resource_alignment(struct pci_dev *dev) +{ + int i; + struct resource *r; + resource_size_t align, size; + u16 command; + + /* check if specified PCI is target device to reassign */ + align = pci_specified_resource_alignment(dev); + if (!align) + return; + + if (dev->hdr_type == PCI_HEADER_TYPE_NORMAL && + (dev->class >> 8) == PCI_CLASS_BRIDGE_HOST) { + dev_warn(&dev->dev, + "Can't reassign resources to host bridge.\n"); + return; + } + + dev_info(&dev->dev, + "Disabling memory decoding and releasing memory resources.\n"); + pci_read_config_word(dev, PCI_COMMAND, &command); + command &= ~PCI_COMMAND_MEMORY; + pci_write_config_word(dev, PCI_COMMAND, command); + + for (i = 0; i < PCI_BRIDGE_RESOURCES; i++) { + r = &dev->resource[i]; + if (!(r->flags & IORESOURCE_MEM)) + continue; + size = resource_size(r); + if (size < align) { + size = align; + dev_info(&dev->dev, + "Rounding up size of resource #%d to %#llx.\n", + i, (unsigned long long)size); + } + r->flags |= IORESOURCE_UNSET; + r->end = size - 1; + r->start = 0; + } + /* Need to disable bridge's resource window, + * to enable the kernel to reassign new resource + * window later on. + */ + if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE && + (dev->class >> 8) == PCI_CLASS_BRIDGE_PCI) { + for (i = PCI_BRIDGE_RESOURCES; i < PCI_NUM_RESOURCES; i++) { + r = &dev->resource[i]; + if (!(r->flags & IORESOURCE_MEM)) + continue; + r->flags |= IORESOURCE_UNSET; + r->end = resource_size(r) - 1; + r->start = 0; + } + pci_disable_bridge_window(dev); + } +} + +static ssize_t pci_set_resource_alignment_param(const char *buf, size_t count) +{ + if (count > RESOURCE_ALIGNMENT_PARAM_SIZE - 1) + count = RESOURCE_ALIGNMENT_PARAM_SIZE - 1; + spin_lock(&resource_alignment_lock); + strncpy(resource_alignment_param, buf, count); + resource_alignment_param[count] = '\0'; + spin_unlock(&resource_alignment_lock); + return count; +} + +static ssize_t pci_get_resource_alignment_param(char *buf, size_t size) +{ + size_t count; + spin_lock(&resource_alignment_lock); + count = snprintf(buf, size, "%s", resource_alignment_param); + spin_unlock(&resource_alignment_lock); + return count; +} + +static ssize_t pci_resource_alignment_show(struct bus_type *bus, char *buf) +{ + return pci_get_resource_alignment_param(buf, PAGE_SIZE); +} + +static ssize_t pci_resource_alignment_store(struct bus_type *bus, + const char *buf, size_t count) +{ + return pci_set_resource_alignment_param(buf, count); +} + +BUS_ATTR(resource_alignment, 0644, pci_resource_alignment_show, + pci_resource_alignment_store); + +static int __init pci_resource_alignment_sysfs_init(void) +{ + return bus_create_file(&pci_bus_type, + &bus_attr_resource_alignment); +} +late_initcall(pci_resource_alignment_sysfs_init); + +static void pci_no_domains(void) { #ifdef CONFIG_PCI_DOMAINS pci_domains_supported = 0; #endif } -static int __devinit pci_init(void) +/** + * pci_ext_cfg_avail - can we access extended PCI config space? + * + * Returns 1 if we can access PCI extended config space (offsets + * greater than 0xff). This is the default implementation. Architecture + * implementations can override this. + */ +int __weak pci_ext_cfg_avail(void) { - struct pci_dev *dev = NULL; + return 1; +} - while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) { - pci_fixup_device(pci_fixup_final, dev); - } - return 0; +void __weak pci_fixup_cardbus(struct pci_bus *bus) +{ } +EXPORT_SYMBOL(pci_fixup_cardbus); -static int __devinit pci_setup(char *str) +static int __init pci_setup(char *str) { while (str) { char *k = strchr(str, ','); @@ -1649,12 +4429,37 @@ static int __devinit pci_setup(char *str) pci_no_msi(); } else if (!strcmp(str, "noaer")) { pci_no_aer(); + } else if (!strncmp(str, "realloc=", 8)) { + pci_realloc_get_opt(str + 8); + } else if (!strncmp(str, "realloc", 7)) { + pci_realloc_get_opt("on"); } else if (!strcmp(str, "nodomains")) { pci_no_domains(); + } else if (!strncmp(str, "noari", 5)) { + pcie_ari_disabled = true; } else if (!strncmp(str, "cbiosize=", 9)) { pci_cardbus_io_size = memparse(str + 9, &str); } else if (!strncmp(str, "cbmemsize=", 10)) { pci_cardbus_mem_size = memparse(str + 10, &str); + } else if (!strncmp(str, "resource_alignment=", 19)) { + pci_set_resource_alignment_param(str + 19, + strlen(str + 19)); + } else if (!strncmp(str, "ecrc=", 5)) { + pcie_ecrc_get_policy(str + 5); + } else if (!strncmp(str, "hpiosize=", 9)) { + pci_hotplug_io_size = memparse(str + 9, &str); + } else if (!strncmp(str, "hpmemsize=", 10)) { + pci_hotplug_mem_size = memparse(str + 10, &str); + } else if (!strncmp(str, "pcie_bus_tune_off", 17)) { + pcie_bus_config = PCIE_BUS_TUNE_OFF; + } else if (!strncmp(str, "pcie_bus_safe", 13)) { + pcie_bus_config = PCIE_BUS_SAFE; + } else if (!strncmp(str, "pcie_bus_perf", 13)) { + pcie_bus_config = PCIE_BUS_PERFORMANCE; + } else if (!strncmp(str, "pcie_bus_peer2peer", 18)) { + pcie_bus_config = PCIE_BUS_PEER2PEER; + } else if (!strncmp(str, "pcie_scan_all", 13)) { + pci_add_flags(PCI_SCAN_ALL_PCIE_DEVS); } else { printk(KERN_ERR "PCI: Unknown option `%s'\n", str); @@ -1665,38 +4470,3 @@ static int __devinit pci_setup(char *str) return 0; } early_param("pci", pci_setup); - -device_initcall(pci_init); - -EXPORT_SYMBOL(pci_reenable_device); -EXPORT_SYMBOL(pci_enable_device_io); -EXPORT_SYMBOL(pci_enable_device_mem); -EXPORT_SYMBOL(pci_enable_device); -EXPORT_SYMBOL(pcim_enable_device); -EXPORT_SYMBOL(pcim_pin_device); -EXPORT_SYMBOL(pci_disable_device); -EXPORT_SYMBOL(pci_find_capability); -EXPORT_SYMBOL(pci_bus_find_capability); -EXPORT_SYMBOL(pci_release_regions); -EXPORT_SYMBOL(pci_request_regions); -EXPORT_SYMBOL(pci_release_region); -EXPORT_SYMBOL(pci_request_region); -EXPORT_SYMBOL(pci_release_selected_regions); -EXPORT_SYMBOL(pci_request_selected_regions); -EXPORT_SYMBOL(pci_set_master); -EXPORT_SYMBOL(pci_set_mwi); -EXPORT_SYMBOL(pci_try_set_mwi); -EXPORT_SYMBOL(pci_clear_mwi); -EXPORT_SYMBOL_GPL(pci_intx); -EXPORT_SYMBOL(pci_set_dma_mask); -EXPORT_SYMBOL(pci_set_consistent_dma_mask); -EXPORT_SYMBOL(pci_assign_resource); -EXPORT_SYMBOL(pci_find_parent_resource); -EXPORT_SYMBOL(pci_select_bars); - -EXPORT_SYMBOL(pci_set_power_state); -EXPORT_SYMBOL(pci_save_state); -EXPORT_SYMBOL(pci_restore_state); -EXPORT_SYMBOL(pci_enable_wake); -EXPORT_SYMBOL_GPL(pci_set_pcie_reset_state); - |