tmp_suning_uos_patched/include/linux/pci.h

1075 lines
35 KiB
C
Raw Normal View History

/*
* pci.h
*
* PCI defines and function prototypes
* Copyright 1994, Drew Eckhardt
* Copyright 1997--1999 Martin Mares <mj@ucw.cz>
*
* For more information, please consult the following manuals (look at
* http://www.pcisig.com/ for how to get them):
*
* PCI BIOS Specification
* PCI Local Bus Specification
* PCI to PCI Bridge Specification
* PCI System Design Guide
*/
#ifndef LINUX_PCI_H
#define LINUX_PCI_H
/* Include the pci register defines */
#include <linux/pci_regs.h>
/*
* The PCI interface treats multi-function devices as independent
* devices. The slot/function address of each device is encoded
* in a single byte as follows:
*
* 7:3 = slot
* 2:0 = function
*/
#define PCI_DEVFN(slot, func) ((((slot) & 0x1f) << 3) | ((func) & 0x07))
#define PCI_SLOT(devfn) (((devfn) >> 3) & 0x1f)
#define PCI_FUNC(devfn) ((devfn) & 0x07)
/* Ioctls for /proc/bus/pci/X/Y nodes. */
#define PCIIOC_BASE ('P' << 24 | 'C' << 16 | 'I' << 8)
#define PCIIOC_CONTROLLER (PCIIOC_BASE | 0x00) /* Get controller for PCI device. */
#define PCIIOC_MMAP_IS_IO (PCIIOC_BASE | 0x01) /* Set mmap state to I/O space. */
#define PCIIOC_MMAP_IS_MEM (PCIIOC_BASE | 0x02) /* Set mmap state to MEM space. */
#define PCIIOC_WRITE_COMBINE (PCIIOC_BASE | 0x03) /* Enable/disable write-combining. */
#ifdef __KERNEL__
#include <linux/mod_devicetable.h>
#include <linux/types.h>
#include <linux/init.h>
#include <linux/ioport.h>
#include <linux/list.h>
#include <linux/compiler.h>
#include <linux/errno.h>
PCI: switch pci_{enable,disable}_device() to be nestable Changes the pci_{enable,disable}_device() functions to work in a nested basis, so that eg, three calls to enable_device() require three calls to disable_device(). The reason for this is to simplify PCI drivers for multi-interface/capability devices. These are devices that cram more than one interface in a single function. A relevant example of that is the Wireless [USB] Host Controller Interface (similar to EHCI) [see http://www.intel.com/technology/comms/wusb/whci.htm]. In these kind of devices, multiple interfaces are accessed through a single bar and IRQ line. For that, the drivers map only the smallest area of the bar to access their register banks and use shared IRQ handlers. However, because the order at which those drivers load cannot be known ahead of time, the sequence in which the calls to pci_enable_device() and pci_disable_device() cannot be predicted. Thus: 1. driverA starts pci_enable_device() 2. driverB starts pci_enable_device() 3. driverA shutdown pci_disable_device() 4. driverB shutdown pci_disable_device() between steps 3 and 4, driver B would loose access to it's device, even if it didn't intend to. By using this modification, the device won't be disabled until all the callers to enable() have called disable(). This is implemented by replacing 'struct pci_dev->is_enabled' from a bitfield to an atomic use count. Each caller to enable increments it, each caller to disable decrements it. When the count increments from 0 to 1, __pci_enable_device() is called to actually enable the device. When it drops to zero, pci_disable_device() actually does the disabling. We keep the backend __pci_enable_device() for pci_default_resume() to use and also change the sysfs method implementation, so that userspace enabling/disabling the device doesn't disable it one time too much. Signed-off-by: Inaky Perez-Gonzalez <inaky@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2006-11-23 04:40:31 +08:00
#include <asm/atomic.h>
#include <linux/device.h>
/* Include the ID list */
#include <linux/pci_ids.h>
/* File state for mmap()s on /proc/bus/pci/X/Y */
enum pci_mmap_state {
pci_mmap_io,
pci_mmap_mem
};
/* This defines the direction arg to the DMA mapping routines. */
#define PCI_DMA_BIDIRECTIONAL 0
#define PCI_DMA_TODEVICE 1
#define PCI_DMA_FROMDEVICE 2
#define PCI_DMA_NONE 3
#define DEVICE_COUNT_RESOURCE 12
typedef int __bitwise pci_power_t;
#define PCI_D0 ((pci_power_t __force) 0)
#define PCI_D1 ((pci_power_t __force) 1)
#define PCI_D2 ((pci_power_t __force) 2)
#define PCI_D3hot ((pci_power_t __force) 3)
#define PCI_D3cold ((pci_power_t __force) 4)
#define PCI_UNKNOWN ((pci_power_t __force) 5)
#define PCI_POWER_ERROR ((pci_power_t __force) -1)
/** The pci_channel state describes connectivity between the CPU and
* the pci device. If some PCI bus between here and the pci device
* has crashed or locked up, this info is reflected here.
*/
typedef unsigned int __bitwise pci_channel_state_t;
enum pci_channel_state {
/* I/O channel is in normal state */
pci_channel_io_normal = (__force pci_channel_state_t) 1,
/* I/O to channel is blocked */
pci_channel_io_frozen = (__force pci_channel_state_t) 2,
/* PCI card is dead */
pci_channel_io_perm_failure = (__force pci_channel_state_t) 3,
};
typedef unsigned int __bitwise pcie_reset_state_t;
enum pcie_reset_state {
/* Reset is NOT asserted (Use to deassert reset) */
pcie_deassert_reset = (__force pcie_reset_state_t) 1,
/* Use #PERST to reset PCI-E device */
pcie_warm_reset = (__force pcie_reset_state_t) 2,
/* Use PCI-E Hot Reset to reset device */
pcie_hot_reset = (__force pcie_reset_state_t) 3
};
typedef unsigned short __bitwise pci_dev_flags_t;
enum pci_dev_flags {
/* INTX_DISABLE in PCI_COMMAND register disables MSI
* generation too.
*/
PCI_DEV_FLAGS_MSI_INTX_DISABLE_BUG = (__force pci_dev_flags_t) 1,
};
typedef unsigned short __bitwise pci_bus_flags_t;
enum pci_bus_flags {
PCI_BUS_FLAGS_NO_MSI = (__force pci_bus_flags_t) 1,
PCI_BUS_FLAGS_NO_MMRBC = (__force pci_bus_flags_t) 2,
};
struct pci_cap_saved_state {
struct hlist_node next;
char cap_nr;
u32 data[0];
};
struct pcie_link_state;
struct pci_vpd;
/*
* The pci_dev structure is used to describe PCI devices.
*/
struct pci_dev {
struct list_head bus_list; /* node in per-bus list */
struct pci_bus *bus; /* bus this device is on */
struct pci_bus *subordinate; /* bus this device bridges to */
void *sysdata; /* hook for sys-specific extension */
struct proc_dir_entry *procent; /* device entry in /proc/bus/pci */
unsigned int devfn; /* encoded device & function index */
unsigned short vendor;
unsigned short device;
unsigned short subsystem_vendor;
unsigned short subsystem_device;
unsigned int class; /* 3 bytes: (base,sub,prog-if) */
u8 revision; /* PCI revision, low byte of class word */
u8 hdr_type; /* PCI header type (`multi' flag masked out) */
u8 pcie_type; /* PCI-E device/port type */
u8 rom_base_reg; /* which config register controls the ROM */
u8 pin; /* which interrupt pin this device uses */
struct pci_driver *driver; /* which driver has allocated this device */
u64 dma_mask; /* Mask of the bits of bus address this
device implements. Normally this is
0xffffffff. You only need to change
this if your device has broken DMA
or supports 64-bit transfers. */
struct device_dma_parameters dma_parms;
pci_power_t current_state; /* Current operating state. In ACPI-speak,
this is D0-D3, D0 being fully functional,
and D3 being off. */
#ifdef CONFIG_PCIEASPM
struct pcie_link_state *link_state; /* ASPM link state. */
#endif
pci_channel_state_t error_state; /* current connectivity state */
struct device dev; /* Generic device interface */
int cfg_size; /* Size of configuration space */
/*
* Instead of touching interrupt line and base address registers
* directly, use the values stored here. They might be different!
*/
unsigned int irq;
struct resource resource[DEVICE_COUNT_RESOURCE]; /* I/O and memory regions + expansion ROMs */
/* These fields are used by common fixups */
unsigned int transparent:1; /* Transparent PCI bridge */
unsigned int multifunction:1;/* Part of multi-function device */
/* keep track of device state */
unsigned int is_added:1;
unsigned int is_busmaster:1; /* device is busmaster */
unsigned int no_msi:1; /* device may not use msi */
unsigned int no_d1d2:1; /* only allow d0 or d3 */
unsigned int block_ucfg_access:1; /* userspace config space access is blocked */
[PATCH] PCI Bus Parity Status-broken hardware attribute, EDAC foundation Currently, the EDAC (error detection and correction) modules that are in the kernel contain some features that need to be moved. After some good feedback on the PCI Parity detection code and interface (http://www.ussg.iu.edu/hypermail/linux/kernel/0603.1/0897.html) this patch ADDs an new attribute to the pci_dev structure: Namely the 'broken_parity_status' bit. When set this indicates that the respective hardware generates false positives of Parity errors. The EDAC "blacklist" solution was inferior and will be removed in a future patch. Also in this patch is a PCI quirk.c entry for an Infiniband PCI-X card which generates false positive parity errors. I am requesting comments on this AND on the possibility of a exposing this 'broken_parity_status' bit to userland via the PCI device sysfs directory for devices. This access would allow for enabling of this feature on new devices and for old devices that have their drivers updated. (SLES 9 SP3 did this on an ATI motherboard video device). There is a need to update such a PCI attribute between kernel releases. This patch just adds a storage place for the attribute and a quirk entry for a known bad PCI device. PCI Parity reaper/harvestor operations are in EDAC itself and will be refactored to use this PCI attribute instead of its own mechanisms (which are currently disabled) in the future. Signed-off-by: Doug Thompson <norsk5@xmission.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2006-05-09 08:06:09 +08:00
unsigned int broken_parity_status:1; /* Device generates false positive parity */
unsigned int msi_enabled:1;
unsigned int msix_enabled:1;
unsigned int is_managed:1;
unsigned int is_pcie:1;
pci_dev_flags_t dev_flags;
PCI: switch pci_{enable,disable}_device() to be nestable Changes the pci_{enable,disable}_device() functions to work in a nested basis, so that eg, three calls to enable_device() require three calls to disable_device(). The reason for this is to simplify PCI drivers for multi-interface/capability devices. These are devices that cram more than one interface in a single function. A relevant example of that is the Wireless [USB] Host Controller Interface (similar to EHCI) [see http://www.intel.com/technology/comms/wusb/whci.htm]. In these kind of devices, multiple interfaces are accessed through a single bar and IRQ line. For that, the drivers map only the smallest area of the bar to access their register banks and use shared IRQ handlers. However, because the order at which those drivers load cannot be known ahead of time, the sequence in which the calls to pci_enable_device() and pci_disable_device() cannot be predicted. Thus: 1. driverA starts pci_enable_device() 2. driverB starts pci_enable_device() 3. driverA shutdown pci_disable_device() 4. driverB shutdown pci_disable_device() between steps 3 and 4, driver B would loose access to it's device, even if it didn't intend to. By using this modification, the device won't be disabled until all the callers to enable() have called disable(). This is implemented by replacing 'struct pci_dev->is_enabled' from a bitfield to an atomic use count. Each caller to enable increments it, each caller to disable decrements it. When the count increments from 0 to 1, __pci_enable_device() is called to actually enable the device. When it drops to zero, pci_disable_device() actually does the disabling. We keep the backend __pci_enable_device() for pci_default_resume() to use and also change the sysfs method implementation, so that userspace enabling/disabling the device doesn't disable it one time too much. Signed-off-by: Inaky Perez-Gonzalez <inaky@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2006-11-23 04:40:31 +08:00
atomic_t enable_cnt; /* pci_enable_device has been called */
u32 saved_config_space[16]; /* config space saved at suspend time */
struct hlist_head saved_cap_space;
struct bin_attribute *rom_attr; /* attribute descriptor for sysfs ROM entry */
int rom_attr_enabled; /* has display of the rom attribute been enabled? */
struct bin_attribute *res_attr[DEVICE_COUNT_RESOURCE]; /* sysfs file for resources */
struct bin_attribute *res_attr_wc[DEVICE_COUNT_RESOURCE]; /* sysfs file for WC mapping of resources */
#ifdef CONFIG_PCI_MSI
struct list_head msi_list;
#endif
struct pci_vpd *vpd;
};
extern struct pci_dev *alloc_pci_dev(void);
#define pci_dev_b(n) list_entry(n, struct pci_dev, bus_list)
#define to_pci_dev(n) container_of(n, struct pci_dev, dev)
#define for_each_pci_dev(d) while ((d = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, d)) != NULL)
static inline int pci_channel_offline(struct pci_dev *pdev)
{
return (pdev->error_state != pci_channel_io_normal);
}
static inline struct pci_cap_saved_state *pci_find_saved_cap(
struct pci_dev *pci_dev, char cap)
{
struct pci_cap_saved_state *tmp;
struct hlist_node *pos;
hlist_for_each_entry(tmp, pos, &pci_dev->saved_cap_space, next) {
if (tmp->cap_nr == cap)
return tmp;
}
return NULL;
}
static inline 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);
}
/*
* For PCI devices, the region numbers are assigned this way:
*
* 0-5 standard PCI regions
* 6 expansion ROM
* 7-10 bridges: address space assigned to buses behind the bridge
*/
#define PCI_ROM_RESOURCE 6
#define PCI_BRIDGE_RESOURCES 7
#define PCI_NUM_RESOURCES 11
#ifndef PCI_BUS_NUM_RESOURCES
#define PCI_BUS_NUM_RESOURCES 16
#endif
#define PCI_REGION_FLAG_MASK 0x0fU /* These bits of resource flags tell us the PCI region flags */
struct pci_bus {
struct list_head node; /* node in list of buses */
struct pci_bus *parent; /* parent bus this bridge is on */
struct list_head children; /* list of child buses */
struct list_head devices; /* list of devices on this bus */
struct pci_dev *self; /* bridge device as seen by parent */
struct resource *resource[PCI_BUS_NUM_RESOURCES];
/* address space routed to this bus */
struct pci_ops *ops; /* configuration access functions */
void *sysdata; /* hook for sys-specific extension */
struct proc_dir_entry *procdir; /* directory entry in /proc/bus/pci */
unsigned char number; /* bus number */
unsigned char primary; /* number of primary bridge */
unsigned char secondary; /* number of secondary bridge */
unsigned char subordinate; /* max number of subordinate buses */
char name[48];
unsigned short bridge_ctl; /* manage NO_ISA/FBB/et al behaviors */
pci_bus_flags_t bus_flags; /* Inherited by child busses */
struct device *bridge;
struct device dev;
struct bin_attribute *legacy_io; /* legacy I/O for this bus */
struct bin_attribute *legacy_mem; /* legacy mem */
unsigned int is_added:1;
};
#define pci_bus_b(n) list_entry(n, struct pci_bus, node)
#define to_pci_bus(n) container_of(n, struct pci_bus, dev)
/*
* Error values that may be returned by PCI functions.
*/
#define PCIBIOS_SUCCESSFUL 0x00
#define PCIBIOS_FUNC_NOT_SUPPORTED 0x81
#define PCIBIOS_BAD_VENDOR_ID 0x83
#define PCIBIOS_DEVICE_NOT_FOUND 0x86
#define PCIBIOS_BAD_REGISTER_NUMBER 0x87
#define PCIBIOS_SET_FAILED 0x88
#define PCIBIOS_BUFFER_TOO_SMALL 0x89
/* Low-level architecture-dependent routines */
struct pci_ops {
int (*read)(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 *val);
int (*write)(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 val);
};
/*
* ACPI needs to be able to access PCI config space before we've done a
* PCI bus scan and created pci_bus structures.
*/
extern int raw_pci_read(unsigned int domain, unsigned int bus,
unsigned int devfn, int reg, int len, u32 *val);
extern int raw_pci_write(unsigned int domain, unsigned int bus,
unsigned int devfn, int reg, int len, u32 val);
struct pci_bus_region {
resource_size_t start;
resource_size_t end;
};
struct pci_dynids {
spinlock_t lock; /* protects list, index */
struct list_head list; /* for IDs added at runtime */
unsigned int use_driver_data:1; /* pci_driver->driver_data is used */
};
/* ---------------------------------------------------------------- */
/** PCI Error Recovery System (PCI-ERS). If a PCI device driver provides
* a set of callbacks in struct pci_error_handlers, then that device driver
* will be notified of PCI bus errors, and will be driven to recovery
* when an error occurs.
*/
typedef unsigned int __bitwise pci_ers_result_t;
enum pci_ers_result {
/* no result/none/not supported in device driver */
PCI_ERS_RESULT_NONE = (__force pci_ers_result_t) 1,
/* Device driver can recover without slot reset */
PCI_ERS_RESULT_CAN_RECOVER = (__force pci_ers_result_t) 2,
/* Device driver wants slot to be reset. */
PCI_ERS_RESULT_NEED_RESET = (__force pci_ers_result_t) 3,
/* Device has completely failed, is unrecoverable */
PCI_ERS_RESULT_DISCONNECT = (__force pci_ers_result_t) 4,
/* Device driver is fully recovered and operational */
PCI_ERS_RESULT_RECOVERED = (__force pci_ers_result_t) 5,
};
/* PCI bus error event callbacks */
struct pci_error_handlers {
/* PCI bus error detected on this device */
pci_ers_result_t (*error_detected)(struct pci_dev *dev,
enum pci_channel_state error);
/* MMIO has been re-enabled, but not DMA */
pci_ers_result_t (*mmio_enabled)(struct pci_dev *dev);
/* PCI Express link has been reset */
pci_ers_result_t (*link_reset)(struct pci_dev *dev);
/* PCI slot has been reset */
pci_ers_result_t (*slot_reset)(struct pci_dev *dev);
/* Device driver may resume normal operations */
void (*resume)(struct pci_dev *dev);
};
/* ---------------------------------------------------------------- */
struct module;
struct pci_driver {
struct list_head node;
char *name;
const struct pci_device_id *id_table; /* must be non-NULL for probe to be called */
int (*probe) (struct pci_dev *dev, const struct pci_device_id *id); /* New device inserted */
void (*remove) (struct pci_dev *dev); /* Device removed (NULL if not a hot-plug capable driver) */
int (*suspend) (struct pci_dev *dev, pm_message_t state); /* Device suspended */
int (*suspend_late) (struct pci_dev *dev, pm_message_t state);
int (*resume_early) (struct pci_dev *dev);
int (*resume) (struct pci_dev *dev); /* Device woken up */
void (*shutdown) (struct pci_dev *dev);
struct pci_error_handlers *err_handler;
struct device_driver driver;
struct pci_dynids dynids;
};
#define to_pci_driver(drv) container_of(drv, struct pci_driver, driver)
/**
* DEFINE_PCI_DEVICE_TABLE - macro used to describe a pci device table
* @_table: device table name
*
* This macro is used to create a struct pci_device_id array (a device table)
* in a generic manner.
*/
#define DEFINE_PCI_DEVICE_TABLE(_table) \
const struct pci_device_id _table[] __devinitconst
/**
* PCI_DEVICE - macro used to describe a specific pci device
* @vend: the 16 bit PCI Vendor ID
* @dev: the 16 bit PCI Device ID
*
* This macro is used to create a struct pci_device_id that matches a
* specific device. The subvendor and subdevice fields will be set to
* PCI_ANY_ID.
*/
#define PCI_DEVICE(vend,dev) \
.vendor = (vend), .device = (dev), \
.subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID
/**
* PCI_DEVICE_CLASS - macro used to describe a specific pci device class
* @dev_class: the class, subclass, prog-if triple for this device
* @dev_class_mask: the class mask for this device
*
* This macro is used to create a struct pci_device_id that matches a
* specific PCI class. The vendor, device, subvendor, and subdevice
* fields will be set to PCI_ANY_ID.
*/
#define PCI_DEVICE_CLASS(dev_class,dev_class_mask) \
.class = (dev_class), .class_mask = (dev_class_mask), \
.vendor = PCI_ANY_ID, .device = PCI_ANY_ID, \
.subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID
/**
* PCI_VDEVICE - macro used to describe a specific pci device in short form
* @vend: the vendor name
* @dev: the 16 bit PCI Device ID
*
* This macro is used to create a struct pci_device_id that matches a
* specific PCI device. The subvendor, and subdevice fields will be set
* to PCI_ANY_ID. The macro allows the next field to follow as the device
* private data.
*/
#define PCI_VDEVICE(vendor, device) \
PCI_VENDOR_ID_##vendor, (device), \
PCI_ANY_ID, PCI_ANY_ID, 0, 0
/* these external functions are only available when PCI support is enabled */
#ifdef CONFIG_PCI
extern struct bus_type pci_bus_type;
/* Do NOT directly access these two variables, unless you are arch specific pci
* code, or pci core code. */
extern struct list_head pci_root_buses; /* list of all known PCI buses */
/* Some device drivers need know if pci is initiated */
extern int no_pci_devices(void);
void pcibios_fixup_bus(struct pci_bus *);
int __must_check pcibios_enable_device(struct pci_dev *, int mask);
char *pcibios_setup(char *str);
/* Used only when drivers/pci/setup.c is used */
void pcibios_align_resource(void *, struct resource *, resource_size_t,
resource_size_t);
void pcibios_update_irq(struct pci_dev *, int irq);
/* Generic PCI functions used internally */
extern struct pci_bus *pci_find_bus(int domain, int busnr);
void pci_bus_add_devices(struct pci_bus *bus);
struct pci_bus *pci_scan_bus_parented(struct device *parent, int bus,
struct pci_ops *ops, void *sysdata);
static inline struct pci_bus * __devinit pci_scan_bus(int bus, struct pci_ops *ops,
void *sysdata)
{
struct pci_bus *root_bus;
root_bus = pci_scan_bus_parented(NULL, bus, ops, sysdata);
if (root_bus)
pci_bus_add_devices(root_bus);
return root_bus;
}
struct pci_bus *pci_create_bus(struct device *parent, int bus,
struct pci_ops *ops, void *sysdata);
struct pci_bus *pci_add_new_bus(struct pci_bus *parent, struct pci_dev *dev,
int busnr);
int pci_scan_slot(struct pci_bus *bus, int devfn);
struct pci_dev *pci_scan_single_device(struct pci_bus *bus, int devfn);
void pci_device_add(struct pci_dev *dev, struct pci_bus *bus);
unsigned int pci_scan_child_bus(struct pci_bus *bus);
int __must_check pci_bus_add_device(struct pci_dev *dev);
void pci_read_bridge_bases(struct pci_bus *child);
struct resource *pci_find_parent_resource(const struct pci_dev *dev,
struct resource *res);
int pci_get_interrupt_pin(struct pci_dev *dev, struct pci_dev **bridge);
extern struct pci_dev *pci_dev_get(struct pci_dev *dev);
extern void pci_dev_put(struct pci_dev *dev);
extern void pci_remove_bus(struct pci_bus *b);
extern void pci_remove_bus_device(struct pci_dev *dev);
extern void pci_stop_bus_device(struct pci_dev *dev);
void pci_setup_cardbus(struct pci_bus *bus);
PCI: optionally sort device lists breadth-first Problem: New Dell PowerEdge servers have 2 embedded ethernet ports, which are labeled NIC1 and NIC2 on the chassis, in the BIOS setup screens, and in the printed documentation. Assuming no other add-in ethernet ports in the system, Linux 2.4 kernels name these eth0 and eth1 respectively. Many people have come to expect this naming. Linux 2.6 kernels name these eth1 and eth0 respectively (backwards from expectations). I also have reports that various Sun and HP servers have similar behavior. Root cause: Linux 2.4 kernels walk the pci_devices list, which happens to be sorted in breadth-first order (or pcbios_find_device order on i386, which most often is breadth-first also). 2.6 kernels have both the pci_devices list and the pci_bus_type.klist_devices list, the latter is what is walked at driver load time to match the pci_id tables; this klist happens to be in depth-first order. On systems where, for physical routing reasons, NIC1 appears on a lower bus number than NIC2, but NIC2's bridge is discovered first in the depth-first ordering, NIC2 will be discovered before NIC1. If the list were sorted breadth-first, NIC1 would be discovered before NIC2. A PowerEdge 1955 system has the following topology which easily exhibits the difference between depth-first and breadth-first device lists. -[0000:00]-+-00.0 Intel Corporation 5000P Chipset Memory Controller Hub +-02.0-[0000:03-08]--+-00.0-[0000:04-07]--+-00.0-[0000:05-06]----00.0-[0000:06]----00.0 Broadcom Corporation NetXtreme II BCM5708S Gigabit Ethernet (labeled NIC2, 2.4 kernel name eth1, 2.6 kernel name eth0) +-1c.0-[0000:01-02]----00.0-[0000:02]----00.0 Broadcom Corporation NetXtreme II BCM5708S Gigabit Ethernet (labeled NIC1, 2.4 kernel name eth0, 2.6 kernel name eth1) Other factors, such as device driver load order and the presence of PCI slots at various points in the bus hierarchy further complicate this problem; I'm not trying to solve those here, just restore the device order, and thus basic behavior, that 2.4 kernels had. Solution: The solution can come in multiple steps. Suggested fix #1: kernel Patch below optionally sorts the two device lists into breadth-first ordering to maintain compatibility with 2.4 kernels. It adds two new command line options: pci=bfsort pci=nobfsort to force the sort order, or not, as you wish. It also adds DMI checks for the specific Dell systems which exhibit "backwards" ordering, to make them "right". Suggested fix #2: udev rules from userland Many people also have the expectation that embedded NICs are always discovered before add-in NICs (which this patch does not try to do). Using the PCI IRQ Routing Table provided by system BIOS, it's easy to determine which PCI devices are embedded, or if add-in, which PCI slot they're in. I'm working on a tool that would allow udev to name ethernet devices in ascending embedded, slot 1 .. slot N order, subsort by PCI bus/dev/fn breadth-first. It'll be possible to use it independent of udev as well for those distributions that don't use udev in their installers. Suggested fix #3: system board routing rules One can constrain the system board layout to put NIC1 ahead of NIC2 regardless of breadth-first or depth-first discovery order. This adds a significant level of complexity to board routing, and may not be possible in all instances (witness the above systems from several major manufacturers). I don't want to encourage this particular train of thought too far, at the expense of not doing #1 or #2 above. Feedback appreciated. Patch tested on a Dell PowerEdge 1955 blade with 2.6.18. You'll also note I took some liberty and temporarily break the klist abstraction to simplify and speed up the sort algorithm. I think that's both safe and appropriate in this instance. Signed-off-by: Matt Domsch <Matt_Domsch@dell.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2006-09-30 04:23:23 +08:00
extern void pci_sort_breadthfirst(void);
/* Generic PCI functions exported to card drivers */
#ifdef CONFIG_PCI_LEGACY
struct pci_dev __deprecated *pci_find_device(unsigned int vendor,
unsigned int device,
const struct pci_dev *from);
struct pci_dev __deprecated *pci_find_slot(unsigned int bus,
unsigned int devfn);
#endif /* CONFIG_PCI_LEGACY */
int pci_find_capability(struct pci_dev *dev, int cap);
int pci_find_next_capability(struct pci_dev *dev, u8 pos, int cap);
int pci_find_ext_capability(struct pci_dev *dev, int cap);
int pci_find_ht_capability(struct pci_dev *dev, int ht_cap);
int pci_find_next_ht_capability(struct pci_dev *dev, int pos, int ht_cap);
struct pci_bus *pci_find_next_bus(const struct pci_bus *from);
struct pci_dev *pci_get_device(unsigned int vendor, unsigned int device,
struct pci_dev *from);
struct pci_dev *pci_get_subsys(unsigned int vendor, unsigned int device,
unsigned int ss_vendor, unsigned int ss_device,
const struct pci_dev *from);
struct pci_dev *pci_get_slot(struct pci_bus *bus, unsigned int devfn);
struct pci_dev *pci_get_bus_and_slot(unsigned int bus, unsigned int devfn);
struct pci_dev *pci_get_class(unsigned int class, struct pci_dev *from);
int pci_dev_present(const struct pci_device_id *ids);
int pci_bus_read_config_byte(struct pci_bus *bus, unsigned int devfn,
int where, u8 *val);
int pci_bus_read_config_word(struct pci_bus *bus, unsigned int devfn,
int where, u16 *val);
int pci_bus_read_config_dword(struct pci_bus *bus, unsigned int devfn,
int where, u32 *val);
int pci_bus_write_config_byte(struct pci_bus *bus, unsigned int devfn,
int where, u8 val);
int pci_bus_write_config_word(struct pci_bus *bus, unsigned int devfn,
int where, u16 val);
int pci_bus_write_config_dword(struct pci_bus *bus, unsigned int devfn,
int where, u32 val);
static inline int pci_read_config_byte(struct pci_dev *dev, int where, u8 *val)
{
return pci_bus_read_config_byte(dev->bus, dev->devfn, where, val);
}
static inline int pci_read_config_word(struct pci_dev *dev, int where, u16 *val)
{
return pci_bus_read_config_word(dev->bus, dev->devfn, where, val);
}
static inline int pci_read_config_dword(struct pci_dev *dev, int where,
u32 *val)
{
return pci_bus_read_config_dword(dev->bus, dev->devfn, where, val);
}
static inline int pci_write_config_byte(struct pci_dev *dev, int where, u8 val)
{
return pci_bus_write_config_byte(dev->bus, dev->devfn, where, val);
}
static inline int pci_write_config_word(struct pci_dev *dev, int where, u16 val)
{
return pci_bus_write_config_word(dev->bus, dev->devfn, where, val);
}
static inline int pci_write_config_dword(struct pci_dev *dev, int where,
u32 val)
{
return pci_bus_write_config_dword(dev->bus, dev->devfn, where, val);
}
int __must_check pci_enable_device(struct pci_dev *dev);
int __must_check pci_enable_device_io(struct pci_dev *dev);
int __must_check pci_enable_device_mem(struct pci_dev *dev);
int __must_check pci_reenable_device(struct pci_dev *);
int __must_check pcim_enable_device(struct pci_dev *pdev);
void pcim_pin_device(struct pci_dev *pdev);
static inline int pci_is_managed(struct pci_dev *pdev)
{
return pdev->is_managed;
}
void pci_disable_device(struct pci_dev *dev);
void pci_set_master(struct pci_dev *dev);
int pci_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state state);
#define HAVE_PCI_SET_MWI
int __must_check pci_set_mwi(struct pci_dev *dev);
int pci_try_set_mwi(struct pci_dev *dev);
void pci_clear_mwi(struct pci_dev *dev);
void pci_intx(struct pci_dev *dev, int enable);
void pci_msi_off(struct pci_dev *dev);
int pci_set_dma_mask(struct pci_dev *dev, u64 mask);
int pci_set_consistent_dma_mask(struct pci_dev *dev, u64 mask);
int pci_set_dma_max_seg_size(struct pci_dev *dev, unsigned int size);
int pci_set_dma_seg_boundary(struct pci_dev *dev, unsigned long mask);
int pcix_get_max_mmrbc(struct pci_dev *dev);
int pcix_get_mmrbc(struct pci_dev *dev);
int pcix_set_mmrbc(struct pci_dev *dev, int mmrbc);
int pcie_get_readrq(struct pci_dev *dev);
int pcie_set_readrq(struct pci_dev *dev, int rq);
[PATCH] PCI: restore BAR values after D3hot->D0 for devices that need it Some PCI devices (e.g. 3c905B, 3c556B) lose all configuration (including BARs) when transitioning from D3hot->D0. This leaves such a device in an inaccessible state. The patch below causes the BARs to be restored when enabling such a device, so that its driver will be able to access it. The patch also adds pci_restore_bars as a new global symbol, and adds a correpsonding EXPORT_SYMBOL_GPL for that. Some firmware (e.g. Thinkpad T21) leaves devices in D3hot after a (re)boot. Most drivers call pci_enable_device very early, so devices left in D3hot that lose configuration during the D3hot->D0 transition will be inaccessible to their drivers. Drivers could be modified to account for this, but it would be difficult to know which drivers need modification. This is especially true since often many devices are covered by the same driver. It likely would be necessary to replicate code across dozens of drivers. The patch below should trigger only when transitioning from D3hot->D0 (or at boot), and only for devices that have the "no soft reset" bit cleared in the PM control register. I believe it is safe to include this patch as part of the PCI infrastructure. The cleanest implementation of pci_restore_bars was to call pci_update_resource. Unfortunately, that does not currently exist for the sparc64 architecture. The patch below includes a null implemenation of pci_update_resource for sparc64. Some have expressed interest in making general use of the the pci_restore_bars function, so that has been exported to GPL licensed modules. Signed-off-by: John W. Linville <linville@tuxdriver.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2005-07-27 22:19:44 +08:00
void pci_update_resource(struct pci_dev *dev, struct resource *res, int resno);
int __must_check pci_assign_resource(struct pci_dev *dev, int i);
int pci_select_bars(struct pci_dev *dev, unsigned long flags);
/* ROM control related routines */
void __iomem __must_check *pci_map_rom(struct pci_dev *pdev, size_t *size);
void pci_unmap_rom(struct pci_dev *pdev, void __iomem *rom);
size_t pci_get_rom_size(void __iomem *rom, size_t size);
/* Power management related routines */
int pci_save_state(struct pci_dev *dev);
int pci_restore_state(struct pci_dev *dev);
int pci_set_power_state(struct pci_dev *dev, pci_power_t state);
pci_power_t pci_choose_state(struct pci_dev *dev, pm_message_t state);
int pci_enable_wake(struct pci_dev *dev, pci_power_t state, int enable);
/* Functions for PCI Hotplug drivers to use */
int pci_bus_find_capability(struct pci_bus *bus, unsigned int devfn, int cap);
/* Helper functions for low-level code (drivers/pci/setup-[bus,res].c) */
void pci_bus_assign_resources(struct pci_bus *bus);
void pci_bus_size_bridges(struct pci_bus *bus);
int pci_claim_resource(struct pci_dev *, int);
void pci_assign_unassigned_resources(void);
void pdev_enable_device(struct pci_dev *);
void pdev_sort_resources(struct pci_dev *, struct resource_list *);
int pci_enable_resources(struct pci_dev *, int mask);
void pci_fixup_irqs(u8 (*)(struct pci_dev *, u8 *),
int (*)(struct pci_dev *, u8, u8));
#define HAVE_PCI_REQ_REGIONS 2
int __must_check pci_request_regions(struct pci_dev *, const char *);
void pci_release_regions(struct pci_dev *);
int __must_check pci_request_region(struct pci_dev *, int, const char *);
void pci_release_region(struct pci_dev *, int);
int pci_request_selected_regions(struct pci_dev *, int, const char *);
void pci_release_selected_regions(struct pci_dev *, int);
/* drivers/pci/bus.c */
int __must_check pci_bus_alloc_resource(struct pci_bus *bus,
struct resource *res, resource_size_t size,
resource_size_t align, resource_size_t min,
unsigned int type_mask,
void (*alignf)(void *, struct resource *,
resource_size_t, resource_size_t),
void *alignf_data);
void pci_enable_bridges(struct pci_bus *bus);
/* Proper probing supporting hot-pluggable devices */
int __must_check __pci_register_driver(struct pci_driver *, struct module *,
const char *mod_name);
static inline int __must_check pci_register_driver(struct pci_driver *driver)
{
return __pci_register_driver(driver, THIS_MODULE, KBUILD_MODNAME);
}
void pci_unregister_driver(struct pci_driver *dev);
void pci_remove_behind_bridge(struct pci_dev *dev);
struct pci_driver *pci_dev_driver(const struct pci_dev *dev);
const struct pci_device_id *pci_match_id(const struct pci_device_id *ids,
struct pci_dev *dev);
int pci_scan_bridge(struct pci_bus *bus, struct pci_dev *dev, int max,
int pass);
void pci_walk_bus(struct pci_bus *top, void (*cb)(struct pci_dev *, void *),
void *userdata);
int pci_cfg_space_size_ext(struct pci_dev *dev);
int pci_cfg_space_size(struct pci_dev *dev);
unsigned char pci_bus_max_busnr(struct pci_bus *bus);
/* kmem_cache style wrapper around pci_alloc_consistent() */
#include <linux/dmapool.h>
#define pci_pool dma_pool
#define pci_pool_create(name, pdev, size, align, allocation) \
dma_pool_create(name, &pdev->dev, size, align, allocation)
#define pci_pool_destroy(pool) dma_pool_destroy(pool)
#define pci_pool_alloc(pool, flags, handle) dma_pool_alloc(pool, flags, handle)
#define pci_pool_free(pool, vaddr, addr) dma_pool_free(pool, vaddr, addr)
enum pci_dma_burst_strategy {
PCI_DMA_BURST_INFINITY, /* make bursts as large as possible,
strategy_parameter is N/A */
PCI_DMA_BURST_BOUNDARY, /* disconnect at every strategy_parameter
byte boundaries */
PCI_DMA_BURST_MULTIPLE, /* disconnect at some multiple of
strategy_parameter byte boundaries */
};
struct msix_entry {
u16 vector; /* kernel uses to write allocated vector */
u16 entry; /* driver uses to specify entry, OS writes */
};
#ifndef CONFIG_PCI_MSI
static inline int pci_enable_msi(struct pci_dev *dev)
{
return -1;
}
static inline void pci_msi_shutdown(struct pci_dev *dev)
{ }
static inline void pci_disable_msi(struct pci_dev *dev)
{ }
static inline int pci_enable_msix(struct pci_dev *dev,
struct msix_entry *entries, int nvec)
{
return -1;
}
static inline void pci_msix_shutdown(struct pci_dev *dev)
{ }
static inline void pci_disable_msix(struct pci_dev *dev)
{ }
static inline void msi_remove_pci_irq_vectors(struct pci_dev *dev)
{ }
static inline void pci_restore_msi_state(struct pci_dev *dev)
{ }
#else
extern int pci_enable_msi(struct pci_dev *dev);
extern void pci_msi_shutdown(struct pci_dev *dev);
extern void pci_disable_msi(struct pci_dev *dev);
extern int pci_enable_msix(struct pci_dev *dev,
struct msix_entry *entries, int nvec);
extern void pci_msix_shutdown(struct pci_dev *dev);
extern void pci_disable_msix(struct pci_dev *dev);
extern void msi_remove_pci_irq_vectors(struct pci_dev *dev);
extern void pci_restore_msi_state(struct pci_dev *dev);
#endif
#ifdef CONFIG_HT_IRQ
/* The functions a driver should call */
int ht_create_irq(struct pci_dev *dev, int idx);
void ht_destroy_irq(unsigned int irq);
#endif /* CONFIG_HT_IRQ */
extern void pci_block_user_cfg_access(struct pci_dev *dev);
extern void pci_unblock_user_cfg_access(struct pci_dev *dev);
/*
* PCI domain support. Sometimes called PCI segment (eg by ACPI),
* a PCI domain is defined to be a set of PCI busses which share
* configuration space.
*/
#ifdef CONFIG_PCI_DOMAINS
extern int pci_domains_supported;
#else
enum { pci_domains_supported = 0 };
static inline int pci_domain_nr(struct pci_bus *bus)
{
return 0;
}
static inline int pci_proc_domain(struct pci_bus *bus)
{
return 0;
}
#endif /* CONFIG_PCI_DOMAINS */
#else /* CONFIG_PCI is not enabled */
/*
* If the system does not have PCI, clearly these return errors. Define
* these as simple inline functions to avoid hair in drivers.
*/
#define _PCI_NOP(o, s, t) \
static inline int pci_##o##_config_##s(struct pci_dev *dev, \
int where, t val) \
{ return PCIBIOS_FUNC_NOT_SUPPORTED; }
#define _PCI_NOP_ALL(o, x) _PCI_NOP(o, byte, u8 x) \
_PCI_NOP(o, word, u16 x) \
_PCI_NOP(o, dword, u32 x)
_PCI_NOP_ALL(read, *)
_PCI_NOP_ALL(write,)
static inline struct pci_dev *pci_find_device(unsigned int vendor,
unsigned int device,
const struct pci_dev *from)
{
return NULL;
}
static inline struct pci_dev *pci_find_slot(unsigned int bus,
unsigned int devfn)
{
return NULL;
}
static inline struct pci_dev *pci_get_device(unsigned int vendor,
unsigned int device,
struct pci_dev *from)
{
return NULL;
}
static inline struct pci_dev *pci_get_subsys(unsigned int vendor,
unsigned int device,
unsigned int ss_vendor,
unsigned int ss_device,
const struct pci_dev *from)
{
return NULL;
}
static inline struct pci_dev *pci_get_class(unsigned int class,
struct pci_dev *from)
{
return NULL;
}
#define pci_dev_present(ids) (0)
#define no_pci_devices() (1)
#define pci_dev_put(dev) do { } while (0)
static inline void pci_set_master(struct pci_dev *dev)
{ }
static inline int pci_enable_device(struct pci_dev *dev)
{
return -EIO;
}
static inline void pci_disable_device(struct pci_dev *dev)
{ }
static inline int pci_set_dma_mask(struct pci_dev *dev, u64 mask)
{
return -EIO;
}
static inline int pci_set_dma_max_seg_size(struct pci_dev *dev,
unsigned int size)
{
return -EIO;
}
static inline int pci_set_dma_seg_boundary(struct pci_dev *dev,
unsigned long mask)
{
return -EIO;
}
static inline int pci_assign_resource(struct pci_dev *dev, int i)
{
return -EBUSY;
}
static inline int __pci_register_driver(struct pci_driver *drv,
struct module *owner)
{
return 0;
}
static inline int pci_register_driver(struct pci_driver *drv)
{
return 0;
}
static inline void pci_unregister_driver(struct pci_driver *drv)
{ }
static inline int pci_find_capability(struct pci_dev *dev, int cap)
{
return 0;
}
static inline int pci_find_next_capability(struct pci_dev *dev, u8 post,
int cap)
{
return 0;
}
static inline int pci_find_ext_capability(struct pci_dev *dev, int cap)
{
return 0;
}
/* Power management related routines */
static inline int pci_save_state(struct pci_dev *dev)
{
return 0;
}
static inline int pci_restore_state(struct pci_dev *dev)
{
return 0;
}
static inline int pci_set_power_state(struct pci_dev *dev, pci_power_t state)
{
return 0;
}
static inline pci_power_t pci_choose_state(struct pci_dev *dev,
pm_message_t state)
{
return PCI_D0;
}
static inline int pci_enable_wake(struct pci_dev *dev, pci_power_t state,
int enable)
{
return 0;
}
static inline int pci_request_regions(struct pci_dev *dev, const char *res_name)
{
return -EIO;
}
static inline void pci_release_regions(struct pci_dev *dev)
{ }
#define pci_dma_burst_advice(pdev, strat, strategy_parameter) do { } while (0)
static inline void pci_block_user_cfg_access(struct pci_dev *dev)
{ }
static inline void pci_unblock_user_cfg_access(struct pci_dev *dev)
{ }
static inline struct pci_bus *pci_find_next_bus(const struct pci_bus *from)
{ return NULL; }
static inline struct pci_dev *pci_get_slot(struct pci_bus *bus,
unsigned int devfn)
{ return NULL; }
static inline struct pci_dev *pci_get_bus_and_slot(unsigned int bus,
unsigned int devfn)
{ return NULL; }
#endif /* CONFIG_PCI */
/* Include architecture-dependent settings and functions */
#include <asm/pci.h>
/* these helpers provide future and backwards compatibility
* for accessing popular PCI BAR info */
#define pci_resource_start(dev, bar) ((dev)->resource[(bar)].start)
#define pci_resource_end(dev, bar) ((dev)->resource[(bar)].end)
#define pci_resource_flags(dev, bar) ((dev)->resource[(bar)].flags)
#define pci_resource_len(dev,bar) \
((pci_resource_start((dev), (bar)) == 0 && \
pci_resource_end((dev), (bar)) == \
pci_resource_start((dev), (bar))) ? 0 : \
\
(pci_resource_end((dev), (bar)) - \
pci_resource_start((dev), (bar)) + 1))
/* Similar to the helpers above, these manipulate per-pci_dev
* driver-specific data. They are really just a wrapper around
* the generic device structure functions of these calls.
*/
static inline void *pci_get_drvdata(struct pci_dev *pdev)
{
return dev_get_drvdata(&pdev->dev);
}
static inline void pci_set_drvdata(struct pci_dev *pdev, void *data)
{
dev_set_drvdata(&pdev->dev, data);
}
/* If you want to know what to call your pci_dev, ask this function.
* Again, it's a wrapper around the generic device.
*/
static inline char *pci_name(struct pci_dev *pdev)
{
return pdev->dev.bus_id;
}
/* Some archs don't want to expose struct resource to userland as-is
* in sysfs and /proc
*/
#ifndef HAVE_ARCH_PCI_RESOURCE_TO_USER
static inline void pci_resource_to_user(const struct pci_dev *dev, int bar,
const struct resource *rsrc, resource_size_t *start,
resource_size_t *end)
{
*start = rsrc->start;
*end = rsrc->end;
}
#endif /* HAVE_ARCH_PCI_RESOURCE_TO_USER */
/*
* The world is not perfect and supplies us with broken PCI devices.
* For at least a part of these bugs we need a work-around, so both
* generic (drivers/pci/quirks.c) and per-architecture code can define
* fixup hooks to be called for particular buggy devices.
*/
struct pci_fixup {
u16 vendor, device; /* You can use PCI_ANY_ID here of course */
void (*hook)(struct pci_dev *dev);
};
enum pci_fixup_pass {
pci_fixup_early, /* Before probing BARs */
pci_fixup_header, /* After reading configuration header */
pci_fixup_final, /* Final phase of device fixups */
pci_fixup_enable, /* pci_enable_device() time */
pci_fixup_resume, /* pci_enable_device() time */
};
/* Anonymous variables would be nice... */
#define DECLARE_PCI_FIXUP_SECTION(section, name, vendor, device, hook) \
static const struct pci_fixup __pci_fixup_##name __used \
__attribute__((__section__(#section))) = { vendor, device, hook };
#define DECLARE_PCI_FIXUP_EARLY(vendor, device, hook) \
DECLARE_PCI_FIXUP_SECTION(.pci_fixup_early, \
vendor##device##hook, vendor, device, hook)
#define DECLARE_PCI_FIXUP_HEADER(vendor, device, hook) \
DECLARE_PCI_FIXUP_SECTION(.pci_fixup_header, \
vendor##device##hook, vendor, device, hook)
#define DECLARE_PCI_FIXUP_FINAL(vendor, device, hook) \
DECLARE_PCI_FIXUP_SECTION(.pci_fixup_final, \
vendor##device##hook, vendor, device, hook)
#define DECLARE_PCI_FIXUP_ENABLE(vendor, device, hook) \
DECLARE_PCI_FIXUP_SECTION(.pci_fixup_enable, \
vendor##device##hook, vendor, device, hook)
#define DECLARE_PCI_FIXUP_RESUME(vendor, device, hook) \
DECLARE_PCI_FIXUP_SECTION(.pci_fixup_resume, \
resume##vendor##device##hook, vendor, device, hook)
void pci_fixup_device(enum pci_fixup_pass pass, struct pci_dev *dev);
void __iomem *pcim_iomap(struct pci_dev *pdev, int bar, unsigned long maxlen);
void pcim_iounmap(struct pci_dev *pdev, void __iomem *addr);
void __iomem * const *pcim_iomap_table(struct pci_dev *pdev);
int pcim_iomap_regions(struct pci_dev *pdev, u16 mask, const char *name);
int pcim_iomap_regions_request_all(struct pci_dev *pdev, u16 mask,
const char *name);
void pcim_iounmap_regions(struct pci_dev *pdev, u16 mask);
extern int pci_pci_problems;
#define PCIPCI_FAIL 1 /* No PCI PCI DMA */
#define PCIPCI_TRITON 2
#define PCIPCI_NATOMA 4
#define PCIPCI_VIAETBF 8
#define PCIPCI_VSFX 16
#define PCIPCI_ALIMAGIK 32 /* Need low latency setting */
#define PCIAGP_FAIL 64 /* No PCI to AGP DMA */
extern unsigned long pci_cardbus_io_size;
extern unsigned long pci_cardbus_mem_size;
extern int pcibios_add_platform_entries(struct pci_dev *dev);
x86: validate against acpi motherboard resources This path adds validation of the MMCONFIG table against the ACPI reserved motherboard resources. If the MMCONFIG table is found to be reserved in ACPI, we don't bother checking the E820 table. The PCI Express firmware spec apparently tells BIOS developers that reservation in ACPI is required and E820 reservation is optional, so checking against ACPI first makes sense. Many BIOSes don't reserve the MMCONFIG region in E820 even though it is perfectly functional, the existing check needlessly disables MMCONFIG in these cases. In order to do this, MMCONFIG setup has been split into two phases. If PCI configuration type 1 is not available then MMCONFIG is enabled early as before. Otherwise, it is enabled later after the ACPI interpreter is enabled, since we need to be able to execute control methods in order to check the ACPI reserved resources. Presently this is just triggered off the end of ACPI interpreter initialization. There are a few other behavioral changes here: - Validate all MMCONFIG configurations provided, not just the first one. - Validate the entire required length of each configuration according to the provided ending bus number is reserved, not just the minimum required allocation. - Validate that the area is reserved even if we read it from the chipset directly and not from the MCFG table. This catches the case where the BIOS didn't set the location properly in the chipset and has mapped it over other things it shouldn't have. This also cleans up the MMCONFIG initialization functions so that they simply do nothing if MMCONFIG is not compiled in. Based on an original patch by Rajesh Shah from Intel. [akpm@linux-foundation.org: many fixes and cleanups] Signed-off-by: Robert Hancock <hancockr@shaw.ca> Signed-off-by: Andi Kleen <ak@suse.de> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Greg KH <greg@kroah.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Tested-by: Andi Kleen <ak@suse.de> Cc: Rajesh Shah <rajesh.shah@intel.com> Cc: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andi Kleen <ak@suse.de> Cc: Greg KH <greg@kroah.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-02-15 17:27:20 +08:00
#ifdef CONFIG_PCI_MMCONFIG
extern void __init pci_mmcfg_early_init(void);
x86: validate against acpi motherboard resources This path adds validation of the MMCONFIG table against the ACPI reserved motherboard resources. If the MMCONFIG table is found to be reserved in ACPI, we don't bother checking the E820 table. The PCI Express firmware spec apparently tells BIOS developers that reservation in ACPI is required and E820 reservation is optional, so checking against ACPI first makes sense. Many BIOSes don't reserve the MMCONFIG region in E820 even though it is perfectly functional, the existing check needlessly disables MMCONFIG in these cases. In order to do this, MMCONFIG setup has been split into two phases. If PCI configuration type 1 is not available then MMCONFIG is enabled early as before. Otherwise, it is enabled later after the ACPI interpreter is enabled, since we need to be able to execute control methods in order to check the ACPI reserved resources. Presently this is just triggered off the end of ACPI interpreter initialization. There are a few other behavioral changes here: - Validate all MMCONFIG configurations provided, not just the first one. - Validate the entire required length of each configuration according to the provided ending bus number is reserved, not just the minimum required allocation. - Validate that the area is reserved even if we read it from the chipset directly and not from the MCFG table. This catches the case where the BIOS didn't set the location properly in the chipset and has mapped it over other things it shouldn't have. This also cleans up the MMCONFIG initialization functions so that they simply do nothing if MMCONFIG is not compiled in. Based on an original patch by Rajesh Shah from Intel. [akpm@linux-foundation.org: many fixes and cleanups] Signed-off-by: Robert Hancock <hancockr@shaw.ca> Signed-off-by: Andi Kleen <ak@suse.de> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Greg KH <greg@kroah.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Tested-by: Andi Kleen <ak@suse.de> Cc: Rajesh Shah <rajesh.shah@intel.com> Cc: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andi Kleen <ak@suse.de> Cc: Greg KH <greg@kroah.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-02-15 17:27:20 +08:00
extern void __init pci_mmcfg_late_init(void);
#else
static inline void pci_mmcfg_early_init(void) { }
x86: validate against acpi motherboard resources This path adds validation of the MMCONFIG table against the ACPI reserved motherboard resources. If the MMCONFIG table is found to be reserved in ACPI, we don't bother checking the E820 table. The PCI Express firmware spec apparently tells BIOS developers that reservation in ACPI is required and E820 reservation is optional, so checking against ACPI first makes sense. Many BIOSes don't reserve the MMCONFIG region in E820 even though it is perfectly functional, the existing check needlessly disables MMCONFIG in these cases. In order to do this, MMCONFIG setup has been split into two phases. If PCI configuration type 1 is not available then MMCONFIG is enabled early as before. Otherwise, it is enabled later after the ACPI interpreter is enabled, since we need to be able to execute control methods in order to check the ACPI reserved resources. Presently this is just triggered off the end of ACPI interpreter initialization. There are a few other behavioral changes here: - Validate all MMCONFIG configurations provided, not just the first one. - Validate the entire required length of each configuration according to the provided ending bus number is reserved, not just the minimum required allocation. - Validate that the area is reserved even if we read it from the chipset directly and not from the MCFG table. This catches the case where the BIOS didn't set the location properly in the chipset and has mapped it over other things it shouldn't have. This also cleans up the MMCONFIG initialization functions so that they simply do nothing if MMCONFIG is not compiled in. Based on an original patch by Rajesh Shah from Intel. [akpm@linux-foundation.org: many fixes and cleanups] Signed-off-by: Robert Hancock <hancockr@shaw.ca> Signed-off-by: Andi Kleen <ak@suse.de> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Greg KH <greg@kroah.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Tested-by: Andi Kleen <ak@suse.de> Cc: Rajesh Shah <rajesh.shah@intel.com> Cc: Jesse Barnes <jbarnes@virtuousgeek.org> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andi Kleen <ak@suse.de> Cc: Greg KH <greg@kroah.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-02-15 17:27:20 +08:00
static inline void pci_mmcfg_late_init(void) { }
#endif
#endif /* __KERNEL__ */
#endif /* LINUX_PCI_H */