dect
/
linux-2.6
Archived
13
0
Fork 0
This repository has been archived on 2022-02-17. You can view files and clone it, but cannot push or open issues or pull requests.
linux-2.6/include/linux/pci.h

1845 lines
61 KiB
C
Raw Permalink 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 <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: introduce pci_slot Currently, /sys/bus/pci/slots/ only exposes hotplug attributes when a hotplug driver is loaded, but PCI slots have attributes such as address, speed, width, etc. that are not related to hotplug at all. Introduce pci_slot as the primary data structure and kobject model. Hotplug attributes described in hotplug_slot become a secondary structure associated with the pci_slot. This patch only creates the infrastructure that allows the separation of PCI slot attributes and hotplug attributes. In this patch, the PCI hotplug core remains the only user of this infrastructure, and thus, /sys/bus/pci/slots/ will still only become populated when a hotplug driver is loaded. A later patch in this series will add a second user of this new infrastructure and demonstrate splitting the task of exposing pci_slot attributes from hotplug_slot attributes. - Make pci_slot the primary sysfs entity. hotplug_slot becomes a subsidiary structure. o pci_create_slot() creates and registers a slot with the PCI core o pci_slot_add_hotplug() gives it hotplug capability - Change the prototype of pci_hp_register() to take the bus and slot number (on parent bus) as parameters. - Remove all the ->get_address methods since this functionality is now handled by pci_slot directly. [achiang@hp.com: rpaphp-correctly-pci_hp_register-for-empty-pci-slots] Tested-by: Badari Pulavarty <pbadari@us.ibm.com> Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: make headers_check happy] [akpm@linux-foundation.org: nuther build fix] [akpm@linux-foundation.org: fix typo in #include] Signed-off-by: Alex Chiang <achiang@hp.com> Signed-off-by: Matthew Wilcox <matthew@wil.cx> Cc: Greg KH <greg@kroah.com> Cc: Kristen Carlson Accardi <kristen.c.accardi@intel.com> Cc: Len Brown <lenb@kernel.org> Acked-by: Kenji Kaneshige <kaneshige.kenji@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2008-06-10 21:28:50 +00:00
#include <linux/kobject.h>
#include <linux/atomic.h>
#include <linux/device.h>
#include <linux/io.h>
#include <linux/irqreturn.h>
#include <uapi/linux/pci.h>
/* Include the ID list */
#include <linux/pci_ids.h>
PCI: introduce pci_slot Currently, /sys/bus/pci/slots/ only exposes hotplug attributes when a hotplug driver is loaded, but PCI slots have attributes such as address, speed, width, etc. that are not related to hotplug at all. Introduce pci_slot as the primary data structure and kobject model. Hotplug attributes described in hotplug_slot become a secondary structure associated with the pci_slot. This patch only creates the infrastructure that allows the separation of PCI slot attributes and hotplug attributes. In this patch, the PCI hotplug core remains the only user of this infrastructure, and thus, /sys/bus/pci/slots/ will still only become populated when a hotplug driver is loaded. A later patch in this series will add a second user of this new infrastructure and demonstrate splitting the task of exposing pci_slot attributes from hotplug_slot attributes. - Make pci_slot the primary sysfs entity. hotplug_slot becomes a subsidiary structure. o pci_create_slot() creates and registers a slot with the PCI core o pci_slot_add_hotplug() gives it hotplug capability - Change the prototype of pci_hp_register() to take the bus and slot number (on parent bus) as parameters. - Remove all the ->get_address methods since this functionality is now handled by pci_slot directly. [achiang@hp.com: rpaphp-correctly-pci_hp_register-for-empty-pci-slots] Tested-by: Badari Pulavarty <pbadari@us.ibm.com> Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: make headers_check happy] [akpm@linux-foundation.org: nuther build fix] [akpm@linux-foundation.org: fix typo in #include] Signed-off-by: Alex Chiang <achiang@hp.com> Signed-off-by: Matthew Wilcox <matthew@wil.cx> Cc: Greg KH <greg@kroah.com> Cc: Kristen Carlson Accardi <kristen.c.accardi@intel.com> Cc: Len Brown <lenb@kernel.org> Acked-by: Kenji Kaneshige <kaneshige.kenji@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2008-06-10 21:28:50 +00:00
/* pci_slot represents a physical slot */
struct pci_slot {
struct pci_bus *bus; /* The bus this slot is on */
struct list_head list; /* node in list of slots on this bus */
struct hotplug_slot *hotplug; /* Hotplug info (migrate over time) */
unsigned char number; /* PCI_SLOT(pci_dev->devfn) */
struct kobject kobj;
};
static inline const char *pci_slot_name(const struct pci_slot *slot)
{
return kobject_name(&slot->kobj);
}
/* 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
/*
* For PCI devices, the region numbers are assigned this way:
*/
enum {
/* #0-5: standard PCI resources */
PCI_STD_RESOURCES,
PCI_STD_RESOURCE_END = 5,
/* #6: expansion ROM resource */
PCI_ROM_RESOURCE,
/* device specific resources */
#ifdef CONFIG_PCI_IOV
PCI_IOV_RESOURCES,
PCI_IOV_RESOURCE_END = PCI_IOV_RESOURCES + PCI_SRIOV_NUM_BARS - 1,
#endif
/* resources assigned to buses behind the bridge */
#define PCI_BRIDGE_RESOURCE_NUM 4
PCI_BRIDGE_RESOURCES,
PCI_BRIDGE_RESOURCE_END = PCI_BRIDGE_RESOURCES +
PCI_BRIDGE_RESOURCE_NUM - 1,
/* total resources associated with a PCI device */
PCI_NUM_RESOURCES,
/* preserve this for compatibility */
DEVICE_COUNT_RESOURCE = PCI_NUM_RESOURCES,
};
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)
/* Remember to update this when the list above changes! */
extern const char *pci_power_names[];
static inline const char *pci_power_name(pci_power_t state)
{
return pci_power_names[1 + (int) state];
}
PCI/PM: add PCIe runtime D3cold support This patch adds runtime D3cold support and corresponding ACPI platform support. This patch only enables runtime D3cold support; it does not enable D3cold support during system suspend/hibernate. D3cold is the deepest power saving state for a PCIe device, where its main power is removed. While it is in D3cold, you can't access the device at all, not even its configuration space (which is still accessible in D3hot). Therefore the PCI PM registers can not be used to transition into/out of the D3cold state; that must be done by platform logic such as ACPI _PR3. To support wakeup from D3cold, a system may provide auxiliary power, which allows a device to request wakeup using a Beacon or the sideband WAKE# signal. WAKE# is usually connected to platform logic such as ACPI GPE. This is quite different from other power saving states, where devices request wakeup via a PME message on the PCIe link. Some devices, such as those in plug-in slots, have no direct platform logic. For example, there is usually no ACPI _PR3 for them. D3cold support for these devices can be done via the PCIe Downstream Port leading to the device. When the PCIe port is powered on/off, the device is powered on/off too. Wakeup events from the device will be notified to the corresponding PCIe port. For more information about PCIe D3cold and corresponding ACPI support, please refer to: - PCI Express Base Specification Revision 2.0 - Advanced Configuration and Power Interface Specification Revision 5.0 [bhelgaas: changelog] Reviewed-by: Rafael J. Wysocki <rjw@sisk.pl> Originally-by: Zheng Yan <zheng.z.yan@intel.com> Signed-off-by: Huang Ying <ying.huang@intel.com> Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
2012-06-23 02:23:51 +00:00
#define PCI_PM_D2_DELAY 200
#define PCI_PM_D3_WAIT 10
#define PCI_PM_D3COLD_WAIT 100
#define PCI_PM_BUS_WAIT 50
/** 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,
/* Device configuration is irrevocably lost if disabled into D3 */
PCI_DEV_FLAGS_NO_D3 = (__force pci_dev_flags_t) 2,
/* Provide indication device is assigned by a Virtual Machine Manager */
PCI_DEV_FLAGS_ASSIGNED = (__force pci_dev_flags_t) 4,
};
enum pci_irq_reroute_variant {
INTEL_IRQ_REROUTE_VARIANT = 1,
MAX_IRQ_REROUTE_VARIANTS = 3
};
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,
};
/* Based on the PCI Hotplug Spec, but some values are made up by us */
enum pci_bus_speed {
PCI_SPEED_33MHz = 0x00,
PCI_SPEED_66MHz = 0x01,
PCI_SPEED_66MHz_PCIX = 0x02,
PCI_SPEED_100MHz_PCIX = 0x03,
PCI_SPEED_133MHz_PCIX = 0x04,
PCI_SPEED_66MHz_PCIX_ECC = 0x05,
PCI_SPEED_100MHz_PCIX_ECC = 0x06,
PCI_SPEED_133MHz_PCIX_ECC = 0x07,
PCI_SPEED_66MHz_PCIX_266 = 0x09,
PCI_SPEED_100MHz_PCIX_266 = 0x0a,
PCI_SPEED_133MHz_PCIX_266 = 0x0b,
AGP_UNKNOWN = 0x0c,
AGP_1X = 0x0d,
AGP_2X = 0x0e,
AGP_4X = 0x0f,
AGP_8X = 0x10,
PCI_SPEED_66MHz_PCIX_533 = 0x11,
PCI_SPEED_100MHz_PCIX_533 = 0x12,
PCI_SPEED_133MHz_PCIX_533 = 0x13,
PCIE_SPEED_2_5GT = 0x14,
PCIE_SPEED_5_0GT = 0x15,
PCIE_SPEED_8_0GT = 0x16,
PCI_SPEED_UNKNOWN = 0xff,
};
struct pci_cap_saved_data {
char cap_nr;
unsigned int size;
u32 data[0];
};
struct pci_cap_saved_state {
struct hlist_node next;
struct pci_cap_saved_data cap;
};
struct pcie_link_state;
struct pci_vpd;
struct pci_sriov;
struct pci_ats;
/*
* 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 */
PCI: introduce pci_slot Currently, /sys/bus/pci/slots/ only exposes hotplug attributes when a hotplug driver is loaded, but PCI slots have attributes such as address, speed, width, etc. that are not related to hotplug at all. Introduce pci_slot as the primary data structure and kobject model. Hotplug attributes described in hotplug_slot become a secondary structure associated with the pci_slot. This patch only creates the infrastructure that allows the separation of PCI slot attributes and hotplug attributes. In this patch, the PCI hotplug core remains the only user of this infrastructure, and thus, /sys/bus/pci/slots/ will still only become populated when a hotplug driver is loaded. A later patch in this series will add a second user of this new infrastructure and demonstrate splitting the task of exposing pci_slot attributes from hotplug_slot attributes. - Make pci_slot the primary sysfs entity. hotplug_slot becomes a subsidiary structure. o pci_create_slot() creates and registers a slot with the PCI core o pci_slot_add_hotplug() gives it hotplug capability - Change the prototype of pci_hp_register() to take the bus and slot number (on parent bus) as parameters. - Remove all the ->get_address methods since this functionality is now handled by pci_slot directly. [achiang@hp.com: rpaphp-correctly-pci_hp_register-for-empty-pci-slots] Tested-by: Badari Pulavarty <pbadari@us.ibm.com> Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: make headers_check happy] [akpm@linux-foundation.org: nuther build fix] [akpm@linux-foundation.org: fix typo in #include] Signed-off-by: Alex Chiang <achiang@hp.com> Signed-off-by: Matthew Wilcox <matthew@wil.cx> Cc: Greg KH <greg@kroah.com> Cc: Kristen Carlson Accardi <kristen.c.accardi@intel.com> Cc: Len Brown <lenb@kernel.org> Acked-by: Kenji Kaneshige <kaneshige.kenji@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2008-06-10 21:28:50 +00:00
struct pci_slot *slot; /* Physical slot this device is in */
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_cap; /* PCI-E capability offset */
PCI: Set PCI-E Max Payload Size on fabric On a given PCI-E fabric, each device, bridge, and root port can have a different PCI-E maximum payload size. There is a sizable performance boost for having the largest possible maximum payload size on each PCI-E device. However, if improperly configured, fatal bus errors can occur. Thus, it is important to ensure that PCI-E payloads sends by a device are never larger than the MPS setting of all devices on the way to the destination. This can be achieved two ways: - A conservative approach is to use the smallest common denominator of the entire tree below a root complex for every device on that fabric. This means for example that having a 128 bytes MPS USB controller on one leg of a switch will dramatically reduce performances of a video card or 10GE adapter on another leg of that same switch. It also means that any hierarchy supporting hotplug slots (including expresscard or thunderbolt I suppose, dbl check that) will have to be entirely clamped to 128 bytes since we cannot predict what will be plugged into those slots, and we cannot change the MPS on a "live" system. - A more optimal way is possible, if it falls within a couple of constraints: * The top-level host bridge will never generate packets larger than the smallest TLP (or if it can be controlled independently from its MPS at least) * The device will never generate packets larger than MPS (which can be configured via MRRS) * No support of direct PCI-E <-> PCI-E transfers between devices without some additional code to specifically deal with that case Then we can use an approach that basically ignores downstream requests and focuses exclusively on upstream requests. In that case, all we need to care about is that a device MPS is no larger than its parent MPS, which allows us to keep all switches/bridges to the max MPS supported by their parent and eventually the PHB. In this case, your USB controller would no longer "starve" your 10GE Ethernet and your hotplug slots won't affect your global MPS. Additionally, the hotplugged devices themselves can be configured to a larger MPS up to the value configured in the hotplug bridge. To choose between the two available options, two PCI kernel boot args have been added to the PCI calls. "pcie_bus_safe" will provide the former behavior, while "pcie_bus_perf" will perform the latter behavior. By default, the latter behavior is used. NOTE: due to the location of the enablement, each arch will need to add calls to this function. This patch only enables x86. This patch includes a number of changes recommended by Benjamin Herrenschmidt. Tested-by: Jordan_Hargrave@dell.com Signed-off-by: Jon Mason <mason@myri.com> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2011-07-20 20:20:54 +00:00
u8 pcie_mpss:3; /* PCI-E Max Payload Size Supported */
u8 rom_base_reg; /* which config register controls the ROM */
u8 pin; /* which interrupt pin this device uses */
u16 pcie_flags_reg; /* cached PCI-E Capabilities Register */
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. */
int pm_cap; /* PM capability offset in the
configuration space */
unsigned int pme_support:5; /* Bitmask of states from which PME#
can be generated */
unsigned int pme_interrupt:1;
PCI / PM: Extend PME polling to all PCI devices The land of PCI power management is a land of sorrow and ugliness, especially in the area of signaling events by devices. There are devices that set their PME Status bits, but don't really bother to send a PME message or assert PME#. There are hardware vendors who don't connect PME# lines to the system core logic (they know who they are). There are PCI Express Root Ports that don't bother to trigger interrupts when they receive PME messages from the devices below. There are ACPI BIOSes that forget to provide _PRW methods for devices capable of signaling wakeup. Finally, there are BIOSes that do provide _PRW methods for such devices, but then don't bother to call Notify() for those devices from the corresponding _Lxx/_Exx GPE-handling methods. In all of these cases the kernel doesn't have a chance to receive a proper notification that it should wake up a device, so devices stay in low-power states forever. Worse yet, in some cases they continuously send PME Messages that are silently ignored, because the kernel simply doesn't know that it should clear the device's PME Status bit. This problem was first observed for "parallel" (non-Express) PCI devices on add-on cards and Matthew Garrett addressed it by adding code that polls PME Status bits of such devices, if they are enabled to signal PME, to the kernel. Recently, however, it has turned out that PCI Express devices are also affected by this issue and that it is not limited to add-on devices, so it seems necessary to extend the PME polling to all PCI devices, including PCI Express and planar ones. Still, it would be wasteful to poll the PME Status bits of devices that are known to receive proper PME notifications, so make the kernel (1) poll the PME Status bits of all PCI and PCIe devices enabled to signal PME and (2) disable the PME Status polling for devices for which correct PME notifications are received. Tested-by: Sarah Sharp <sarah.a.sharp@linux.intel.com> Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2011-10-03 21:16:33 +00:00
unsigned int pme_poll:1; /* Poll device's PME status bit */
unsigned int d1_support:1; /* Low power state D1 is supported */
unsigned int d2_support:1; /* Low power state D2 is supported */
PCI/PM: add PCIe runtime D3cold support This patch adds runtime D3cold support and corresponding ACPI platform support. This patch only enables runtime D3cold support; it does not enable D3cold support during system suspend/hibernate. D3cold is the deepest power saving state for a PCIe device, where its main power is removed. While it is in D3cold, you can't access the device at all, not even its configuration space (which is still accessible in D3hot). Therefore the PCI PM registers can not be used to transition into/out of the D3cold state; that must be done by platform logic such as ACPI _PR3. To support wakeup from D3cold, a system may provide auxiliary power, which allows a device to request wakeup using a Beacon or the sideband WAKE# signal. WAKE# is usually connected to platform logic such as ACPI GPE. This is quite different from other power saving states, where devices request wakeup via a PME message on the PCIe link. Some devices, such as those in plug-in slots, have no direct platform logic. For example, there is usually no ACPI _PR3 for them. D3cold support for these devices can be done via the PCIe Downstream Port leading to the device. When the PCIe port is powered on/off, the device is powered on/off too. Wakeup events from the device will be notified to the corresponding PCIe port. For more information about PCIe D3cold and corresponding ACPI support, please refer to: - PCI Express Base Specification Revision 2.0 - Advanced Configuration and Power Interface Specification Revision 5.0 [bhelgaas: changelog] Reviewed-by: Rafael J. Wysocki <rjw@sisk.pl> Originally-by: Zheng Yan <zheng.z.yan@intel.com> Signed-off-by: Huang Ying <ying.huang@intel.com> Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
2012-06-23 02:23:51 +00:00
unsigned int no_d1d2:1; /* D1 and D2 are forbidden */
unsigned int no_d3cold:1; /* D3cold is forbidden */
unsigned int d3cold_allowed:1; /* D3cold is allowed by user */
unsigned int mmio_always_on:1; /* disallow turning off io/mem
decoding during bar sizing */
unsigned int wakeup_prepared:1;
PCI/PM: add PCIe runtime D3cold support This patch adds runtime D3cold support and corresponding ACPI platform support. This patch only enables runtime D3cold support; it does not enable D3cold support during system suspend/hibernate. D3cold is the deepest power saving state for a PCIe device, where its main power is removed. While it is in D3cold, you can't access the device at all, not even its configuration space (which is still accessible in D3hot). Therefore the PCI PM registers can not be used to transition into/out of the D3cold state; that must be done by platform logic such as ACPI _PR3. To support wakeup from D3cold, a system may provide auxiliary power, which allows a device to request wakeup using a Beacon or the sideband WAKE# signal. WAKE# is usually connected to platform logic such as ACPI GPE. This is quite different from other power saving states, where devices request wakeup via a PME message on the PCIe link. Some devices, such as those in plug-in slots, have no direct platform logic. For example, there is usually no ACPI _PR3 for them. D3cold support for these devices can be done via the PCIe Downstream Port leading to the device. When the PCIe port is powered on/off, the device is powered on/off too. Wakeup events from the device will be notified to the corresponding PCIe port. For more information about PCIe D3cold and corresponding ACPI support, please refer to: - PCI Express Base Specification Revision 2.0 - Advanced Configuration and Power Interface Specification Revision 5.0 [bhelgaas: changelog] Reviewed-by: Rafael J. Wysocki <rjw@sisk.pl> Originally-by: Zheng Yan <zheng.z.yan@intel.com> Signed-off-by: Huang Ying <ying.huang@intel.com> Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
2012-06-23 02:23:51 +00:00
unsigned int runtime_d3cold:1; /* whether go through runtime
D3cold, not set for devices
powered on/off by the
corresponding bridge */
unsigned int d3_delay; /* D3->D0 transition time in ms */
PCI/PM: add PCIe runtime D3cold support This patch adds runtime D3cold support and corresponding ACPI platform support. This patch only enables runtime D3cold support; it does not enable D3cold support during system suspend/hibernate. D3cold is the deepest power saving state for a PCIe device, where its main power is removed. While it is in D3cold, you can't access the device at all, not even its configuration space (which is still accessible in D3hot). Therefore the PCI PM registers can not be used to transition into/out of the D3cold state; that must be done by platform logic such as ACPI _PR3. To support wakeup from D3cold, a system may provide auxiliary power, which allows a device to request wakeup using a Beacon or the sideband WAKE# signal. WAKE# is usually connected to platform logic such as ACPI GPE. This is quite different from other power saving states, where devices request wakeup via a PME message on the PCIe link. Some devices, such as those in plug-in slots, have no direct platform logic. For example, there is usually no ACPI _PR3 for them. D3cold support for these devices can be done via the PCIe Downstream Port leading to the device. When the PCIe port is powered on/off, the device is powered on/off too. Wakeup events from the device will be notified to the corresponding PCIe port. For more information about PCIe D3cold and corresponding ACPI support, please refer to: - PCI Express Base Specification Revision 2.0 - Advanced Configuration and Power Interface Specification Revision 5.0 [bhelgaas: changelog] Reviewed-by: Rafael J. Wysocki <rjw@sisk.pl> Originally-by: Zheng Yan <zheng.z.yan@intel.com> Signed-off-by: Huang Ying <ying.huang@intel.com> Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
2012-06-23 02:23:51 +00:00
unsigned int d3cold_delay; /* D3cold->D0 transition time in ms */
#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 block_cfg_access:1; /* 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 00:06:09 +00:00
unsigned int broken_parity_status:1; /* Device generates false positive parity */
unsigned int irq_reroute_variant:2; /* device needs IRQ rerouting variant */
unsigned int msi_enabled:1;
unsigned int msix_enabled:1;
unsigned int ari_enabled:1; /* ARI forwarding */
unsigned int is_managed:1;
unsigned int is_pcie:1; /* Obsolete. Will be removed.
Use pci_is_pcie() instead */
unsigned int needs_freset:1; /* Dev requires fundamental reset */
unsigned int state_saved:1;
unsigned int is_physfn:1;
unsigned int is_virtfn:1;
unsigned int reset_fn:1;
unsigned int is_hotplug_bridge:1;
unsigned int __aer_firmware_first_valid:1;
unsigned int __aer_firmware_first:1;
unsigned int broken_intx_masking:1;
unsigned int io_window_1k:1; /* Intel P2P bridge 1K I/O windows */
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>
2006-11-22 20:40:31 +00:00
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;
struct kset *msi_kset;
#endif
struct pci_vpd *vpd;
#ifdef CONFIG_PCI_ATS
union {
struct pci_sriov *sriov; /* SR-IOV capability related */
struct pci_dev *physfn; /* the PF this VF is associated with */
};
struct pci_ats *ats; /* Address Translation Service */
#endif
phys_addr_t rom; /* Physical address of ROM if it's not from the BAR */
size_t romlen; /* Length of ROM if it's not from the BAR */
};
static inline struct pci_dev *pci_physfn(struct pci_dev *dev)
{
#ifdef CONFIG_PCI_IOV
if (dev->is_virtfn)
dev = dev->physfn;
#endif
return dev;
}
extern struct pci_dev *alloc_pci_dev(void);
#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);
}
extern struct resource busn_resource;
struct pci_host_bridge_window {
struct list_head list;
struct resource *res; /* host bridge aperture (CPU address) */
resource_size_t offset; /* bus address + offset = CPU address */
};
struct pci_host_bridge {
struct device dev;
struct pci_bus *bus; /* root bus */
struct list_head windows; /* pci_host_bridge_windows */
void (*release_fn)(struct pci_host_bridge *);
void *release_data;
};
#define to_pci_host_bridge(n) container_of(n, struct pci_host_bridge, dev)
void pci_set_host_bridge_release(struct pci_host_bridge *bridge,
void (*release_fn)(struct pci_host_bridge *),
void *release_data);
/*
* The first PCI_BRIDGE_RESOURCE_NUM PCI bus resources (those that correspond
* to P2P or CardBus bridge windows) go in a table. Additional ones (for
* buses below host bridges or subtractive decode bridges) go in the list.
* Use pci_bus_for_each_resource() to iterate through all the resources.
*/
/*
* PCI_SUBTRACTIVE_DECODE means the bridge forwards the window implicitly
* and there's no way to program the bridge with the details of the window.
* This does not apply to ACPI _CRS windows, even with the _DEC subtractive-
* decode bit set, because they are explicit and can be programmed with _SRS.
*/
#define PCI_SUBTRACTIVE_DECODE 0x1
struct pci_bus_resource {
struct list_head list;
struct resource *res;
unsigned int flags;
};
#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 */
PCI: introduce pci_slot Currently, /sys/bus/pci/slots/ only exposes hotplug attributes when a hotplug driver is loaded, but PCI slots have attributes such as address, speed, width, etc. that are not related to hotplug at all. Introduce pci_slot as the primary data structure and kobject model. Hotplug attributes described in hotplug_slot become a secondary structure associated with the pci_slot. This patch only creates the infrastructure that allows the separation of PCI slot attributes and hotplug attributes. In this patch, the PCI hotplug core remains the only user of this infrastructure, and thus, /sys/bus/pci/slots/ will still only become populated when a hotplug driver is loaded. A later patch in this series will add a second user of this new infrastructure and demonstrate splitting the task of exposing pci_slot attributes from hotplug_slot attributes. - Make pci_slot the primary sysfs entity. hotplug_slot becomes a subsidiary structure. o pci_create_slot() creates and registers a slot with the PCI core o pci_slot_add_hotplug() gives it hotplug capability - Change the prototype of pci_hp_register() to take the bus and slot number (on parent bus) as parameters. - Remove all the ->get_address methods since this functionality is now handled by pci_slot directly. [achiang@hp.com: rpaphp-correctly-pci_hp_register-for-empty-pci-slots] Tested-by: Badari Pulavarty <pbadari@us.ibm.com> Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: make headers_check happy] [akpm@linux-foundation.org: nuther build fix] [akpm@linux-foundation.org: fix typo in #include] Signed-off-by: Alex Chiang <achiang@hp.com> Signed-off-by: Matthew Wilcox <matthew@wil.cx> Cc: Greg KH <greg@kroah.com> Cc: Kristen Carlson Accardi <kristen.c.accardi@intel.com> Cc: Len Brown <lenb@kernel.org> Acked-by: Kenji Kaneshige <kaneshige.kenji@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2008-06-10 21:28:50 +00:00
struct list_head slots; /* list of slots on this bus */
struct resource *resource[PCI_BRIDGE_RESOURCE_NUM];
struct list_head resources; /* address space routed to this bus */
struct resource busn_res; /* bus numbers 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 max_bus_speed; /* enum pci_bus_speed */
unsigned char cur_bus_speed; /* enum pci_bus_speed */
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)
/*
* Returns true if the pci bus is root (behind host-pci bridge),
* false otherwise
*/
static inline bool pci_is_root_bus(struct pci_bus *pbus)
{
return !(pbus->parent);
}
#ifdef CONFIG_PCI_MSI
static inline bool pci_dev_msi_enabled(struct pci_dev *pci_dev)
{
return pci_dev->msi_enabled || pci_dev->msix_enabled;
}
#else
static inline bool pci_dev_msi_enabled(struct pci_dev *pci_dev) { return false; }
#endif
/*
* 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
/*
* Translate above to generic errno for passing back through non-pci.
*/
static inline int pcibios_err_to_errno(int err)
{
if (err <= PCIBIOS_SUCCESSFUL)
return err; /* Assume already errno */
switch (err) {
case PCIBIOS_FUNC_NOT_SUPPORTED:
return -ENOENT;
case PCIBIOS_BAD_VENDOR_ID:
return -EINVAL;
case PCIBIOS_DEVICE_NOT_FOUND:
return -ENODEV;
case PCIBIOS_BAD_REGISTER_NUMBER:
return -EFAULT;
case PCIBIOS_SET_FAILED:
return -EIO;
case PCIBIOS_BUFFER_TOO_SMALL:
return -ENOSPC;
}
return -ENOTTY;
}
/* 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 */
};
/* ---------------------------------------------------------------- */
/** 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/AER: Report success only when every device has AER-aware driver When an error is detected on a PCIe device which does not have an AER-aware driver, prevent AER infrastructure from reporting successful error recovery. This is because the report_error_detected() function that gets called in the first phase of recovery process allows forward progress even when the driver for the device does not have AER capabilities. It seems that all callbacks (in pci_error_handlers structure) registered by drivers that gets called during error recovery are not mandatory. So the intention of the infrastructure design seems to be to allow forward progress even when a specific callback has not been registered by a driver. However, if error handler structure itself has not been registered, it doesn't make sense to allow forward progress. As a result of the current design, in the case of a single device having an AER-unaware driver or in the case of any function in a multi-function card having an AER-unaware driver, a successful recovery is reported. Typical scenario this happens is when a PCI device is detached from a KVM host and the pci-stub driver on the host claims the device. The pci-stub driver does not have error handling capabilities but the AER infrastructure still reports that the device recovered successfully. The changes proposed here leaves the device(s)in an unrecovered state if the driver for the device or for any device in the subtree does not have error handler structure registered. This reflects the true state of the device and prevents any partial recovery (or no recovery at all) reported as successful. [bhelgaas: changelog] Signed-off-by: Vijay Mohan Pandarathil <vijaymohan.pandarathil@hp.com> Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> Reviewed-by: Linas Vepstas <linasvepstas@gmail.com> Reviewed-by: Myron Stowe <myron.stowe@redhat.com>
2012-11-17 11:47:18 +00:00
/* No AER capabilities registered for the driver */
PCI_ERS_RESULT_NO_AER_DRIVER = (__force pci_ers_result_t) 6,
};
/* 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;
const 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);
int (*sriov_configure) (struct pci_dev *dev, int num_vfs); /* PF pdev */
const 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[]
/**
* 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_SUB - macro used to describe a specific pci device with subsystem
* @vend: the 16 bit PCI Vendor ID
* @dev: the 16 bit PCI Device ID
* @subvend: the 16 bit PCI Subvendor ID
* @subdev: the 16 bit PCI Subdevice ID
*
* This macro is used to create a struct pci_device_id that matches a
* specific device with subsystem information.
*/
#define PCI_DEVICE_SUB(vend, dev, subvend, subdev) \
.vendor = (vend), .device = (dev), \
.subvendor = (subvend), .subdevice = (subdev)
/**
* 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
* @vendor: the vendor name
* @device: 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
PCI: Set PCI-E Max Payload Size on fabric On a given PCI-E fabric, each device, bridge, and root port can have a different PCI-E maximum payload size. There is a sizable performance boost for having the largest possible maximum payload size on each PCI-E device. However, if improperly configured, fatal bus errors can occur. Thus, it is important to ensure that PCI-E payloads sends by a device are never larger than the MPS setting of all devices on the way to the destination. This can be achieved two ways: - A conservative approach is to use the smallest common denominator of the entire tree below a root complex for every device on that fabric. This means for example that having a 128 bytes MPS USB controller on one leg of a switch will dramatically reduce performances of a video card or 10GE adapter on another leg of that same switch. It also means that any hierarchy supporting hotplug slots (including expresscard or thunderbolt I suppose, dbl check that) will have to be entirely clamped to 128 bytes since we cannot predict what will be plugged into those slots, and we cannot change the MPS on a "live" system. - A more optimal way is possible, if it falls within a couple of constraints: * The top-level host bridge will never generate packets larger than the smallest TLP (or if it can be controlled independently from its MPS at least) * The device will never generate packets larger than MPS (which can be configured via MRRS) * No support of direct PCI-E <-> PCI-E transfers between devices without some additional code to specifically deal with that case Then we can use an approach that basically ignores downstream requests and focuses exclusively on upstream requests. In that case, all we need to care about is that a device MPS is no larger than its parent MPS, which allows us to keep all switches/bridges to the max MPS supported by their parent and eventually the PHB. In this case, your USB controller would no longer "starve" your 10GE Ethernet and your hotplug slots won't affect your global MPS. Additionally, the hotplugged devices themselves can be configured to a larger MPS up to the value configured in the hotplug bridge. To choose between the two available options, two PCI kernel boot args have been added to the PCI calls. "pcie_bus_safe" will provide the former behavior, while "pcie_bus_perf" will perform the latter behavior. By default, the latter behavior is used. NOTE: due to the location of the enablement, each arch will need to add calls to this function. This patch only enables x86. This patch includes a number of changes recommended by Benjamin Herrenschmidt. Tested-by: Jordan_Hargrave@dell.com Signed-off-by: Jon Mason <mason@myri.com> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2011-07-20 20:20:54 +00:00
extern void pcie_bus_configure_settings(struct pci_bus *bus, u8 smpss);
enum pcie_bus_config_types {
PCIE_BUS_TUNE_OFF,
PCI: Set PCI-E Max Payload Size on fabric On a given PCI-E fabric, each device, bridge, and root port can have a different PCI-E maximum payload size. There is a sizable performance boost for having the largest possible maximum payload size on each PCI-E device. However, if improperly configured, fatal bus errors can occur. Thus, it is important to ensure that PCI-E payloads sends by a device are never larger than the MPS setting of all devices on the way to the destination. This can be achieved two ways: - A conservative approach is to use the smallest common denominator of the entire tree below a root complex for every device on that fabric. This means for example that having a 128 bytes MPS USB controller on one leg of a switch will dramatically reduce performances of a video card or 10GE adapter on another leg of that same switch. It also means that any hierarchy supporting hotplug slots (including expresscard or thunderbolt I suppose, dbl check that) will have to be entirely clamped to 128 bytes since we cannot predict what will be plugged into those slots, and we cannot change the MPS on a "live" system. - A more optimal way is possible, if it falls within a couple of constraints: * The top-level host bridge will never generate packets larger than the smallest TLP (or if it can be controlled independently from its MPS at least) * The device will never generate packets larger than MPS (which can be configured via MRRS) * No support of direct PCI-E <-> PCI-E transfers between devices without some additional code to specifically deal with that case Then we can use an approach that basically ignores downstream requests and focuses exclusively on upstream requests. In that case, all we need to care about is that a device MPS is no larger than its parent MPS, which allows us to keep all switches/bridges to the max MPS supported by their parent and eventually the PHB. In this case, your USB controller would no longer "starve" your 10GE Ethernet and your hotplug slots won't affect your global MPS. Additionally, the hotplugged devices themselves can be configured to a larger MPS up to the value configured in the hotplug bridge. To choose between the two available options, two PCI kernel boot args have been added to the PCI calls. "pcie_bus_safe" will provide the former behavior, while "pcie_bus_perf" will perform the latter behavior. By default, the latter behavior is used. NOTE: due to the location of the enablement, each arch will need to add calls to this function. This patch only enables x86. This patch includes a number of changes recommended by Benjamin Herrenschmidt. Tested-by: Jordan_Hargrave@dell.com Signed-off-by: Jon Mason <mason@myri.com> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2011-07-20 20:20:54 +00:00
PCIE_BUS_SAFE,
PCIE_BUS_PERFORMANCE,
PCI: Set PCI-E Max Payload Size on fabric On a given PCI-E fabric, each device, bridge, and root port can have a different PCI-E maximum payload size. There is a sizable performance boost for having the largest possible maximum payload size on each PCI-E device. However, if improperly configured, fatal bus errors can occur. Thus, it is important to ensure that PCI-E payloads sends by a device are never larger than the MPS setting of all devices on the way to the destination. This can be achieved two ways: - A conservative approach is to use the smallest common denominator of the entire tree below a root complex for every device on that fabric. This means for example that having a 128 bytes MPS USB controller on one leg of a switch will dramatically reduce performances of a video card or 10GE adapter on another leg of that same switch. It also means that any hierarchy supporting hotplug slots (including expresscard or thunderbolt I suppose, dbl check that) will have to be entirely clamped to 128 bytes since we cannot predict what will be plugged into those slots, and we cannot change the MPS on a "live" system. - A more optimal way is possible, if it falls within a couple of constraints: * The top-level host bridge will never generate packets larger than the smallest TLP (or if it can be controlled independently from its MPS at least) * The device will never generate packets larger than MPS (which can be configured via MRRS) * No support of direct PCI-E <-> PCI-E transfers between devices without some additional code to specifically deal with that case Then we can use an approach that basically ignores downstream requests and focuses exclusively on upstream requests. In that case, all we need to care about is that a device MPS is no larger than its parent MPS, which allows us to keep all switches/bridges to the max MPS supported by their parent and eventually the PHB. In this case, your USB controller would no longer "starve" your 10GE Ethernet and your hotplug slots won't affect your global MPS. Additionally, the hotplugged devices themselves can be configured to a larger MPS up to the value configured in the hotplug bridge. To choose between the two available options, two PCI kernel boot args have been added to the PCI calls. "pcie_bus_safe" will provide the former behavior, while "pcie_bus_perf" will perform the latter behavior. By default, the latter behavior is used. NOTE: due to the location of the enablement, each arch will need to add calls to this function. This patch only enables x86. This patch includes a number of changes recommended by Benjamin Herrenschmidt. Tested-by: Jordan_Hargrave@dell.com Signed-off-by: Jon Mason <mason@myri.com> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2011-07-20 20:20:54 +00:00
PCIE_BUS_PEER2PEER,
};
extern enum pcie_bus_config_types pcie_bus_config;
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);
/* Architecture specific versions may override this (weak) */
char *pcibios_setup(char *str);
/* Used only when drivers/pci/setup.c is used */
resource_size_t pcibios_align_resource(void *, const struct resource *,
resource_size_t,
resource_size_t);
void pcibios_update_irq(struct pci_dev *, int irq);
/* Weak but can be overriden by arch */
void pci_fixup_cardbus(struct pci_bus *);
/* Generic PCI functions used internally */
void pcibios_resource_to_bus(struct pci_dev *dev, struct pci_bus_region *region,
struct resource *res);
void pcibios_bus_to_resource(struct pci_dev *dev, struct resource *res,
struct pci_bus_region *region);
void pcibios_scan_specific_bus(int busn);
extern struct pci_bus *pci_find_bus(int domain, int busnr);
void pci_bus_add_devices(const struct pci_bus *bus);
struct pci_bus *pci_scan_bus_parented(struct device *parent, int bus,
struct pci_ops *ops, void *sysdata);
struct pci_bus *pci_scan_bus(int bus, struct pci_ops *ops, void *sysdata);
struct pci_bus *pci_create_root_bus(struct device *parent, int bus,
struct pci_ops *ops, void *sysdata,
struct list_head *resources);
int pci_bus_insert_busn_res(struct pci_bus *b, int bus, int busmax);
int pci_bus_update_busn_res_end(struct pci_bus *b, int busmax);
void pci_bus_release_busn_res(struct pci_bus *b);
struct pci_bus *pci_scan_root_bus(struct device *parent, int bus,
struct pci_ops *ops, void *sysdata,
struct list_head *resources);
struct pci_bus *pci_add_new_bus(struct pci_bus *parent, struct pci_dev *dev,
int busnr);
void pcie_update_link_speed(struct pci_bus *bus, u16 link_status);
PCI: introduce pci_slot Currently, /sys/bus/pci/slots/ only exposes hotplug attributes when a hotplug driver is loaded, but PCI slots have attributes such as address, speed, width, etc. that are not related to hotplug at all. Introduce pci_slot as the primary data structure and kobject model. Hotplug attributes described in hotplug_slot become a secondary structure associated with the pci_slot. This patch only creates the infrastructure that allows the separation of PCI slot attributes and hotplug attributes. In this patch, the PCI hotplug core remains the only user of this infrastructure, and thus, /sys/bus/pci/slots/ will still only become populated when a hotplug driver is loaded. A later patch in this series will add a second user of this new infrastructure and demonstrate splitting the task of exposing pci_slot attributes from hotplug_slot attributes. - Make pci_slot the primary sysfs entity. hotplug_slot becomes a subsidiary structure. o pci_create_slot() creates and registers a slot with the PCI core o pci_slot_add_hotplug() gives it hotplug capability - Change the prototype of pci_hp_register() to take the bus and slot number (on parent bus) as parameters. - Remove all the ->get_address methods since this functionality is now handled by pci_slot directly. [achiang@hp.com: rpaphp-correctly-pci_hp_register-for-empty-pci-slots] Tested-by: Badari Pulavarty <pbadari@us.ibm.com> Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: make headers_check happy] [akpm@linux-foundation.org: nuther build fix] [akpm@linux-foundation.org: fix typo in #include] Signed-off-by: Alex Chiang <achiang@hp.com> Signed-off-by: Matthew Wilcox <matthew@wil.cx> Cc: Greg KH <greg@kroah.com> Cc: Kristen Carlson Accardi <kristen.c.accardi@intel.com> Cc: Len Brown <lenb@kernel.org> Acked-by: Kenji Kaneshige <kaneshige.kenji@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2008-06-10 21:28:50 +00:00
struct pci_slot *pci_create_slot(struct pci_bus *parent, int slot_nr,
const char *name,
struct hotplug_slot *hotplug);
PCI: introduce pci_slot Currently, /sys/bus/pci/slots/ only exposes hotplug attributes when a hotplug driver is loaded, but PCI slots have attributes such as address, speed, width, etc. that are not related to hotplug at all. Introduce pci_slot as the primary data structure and kobject model. Hotplug attributes described in hotplug_slot become a secondary structure associated with the pci_slot. This patch only creates the infrastructure that allows the separation of PCI slot attributes and hotplug attributes. In this patch, the PCI hotplug core remains the only user of this infrastructure, and thus, /sys/bus/pci/slots/ will still only become populated when a hotplug driver is loaded. A later patch in this series will add a second user of this new infrastructure and demonstrate splitting the task of exposing pci_slot attributes from hotplug_slot attributes. - Make pci_slot the primary sysfs entity. hotplug_slot becomes a subsidiary structure. o pci_create_slot() creates and registers a slot with the PCI core o pci_slot_add_hotplug() gives it hotplug capability - Change the prototype of pci_hp_register() to take the bus and slot number (on parent bus) as parameters. - Remove all the ->get_address methods since this functionality is now handled by pci_slot directly. [achiang@hp.com: rpaphp-correctly-pci_hp_register-for-empty-pci-slots] Tested-by: Badari Pulavarty <pbadari@us.ibm.com> Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: make headers_check happy] [akpm@linux-foundation.org: nuther build fix] [akpm@linux-foundation.org: fix typo in #include] Signed-off-by: Alex Chiang <achiang@hp.com> Signed-off-by: Matthew Wilcox <matthew@wil.cx> Cc: Greg KH <greg@kroah.com> Cc: Kristen Carlson Accardi <kristen.c.accardi@intel.com> Cc: Len Brown <lenb@kernel.org> Acked-by: Kenji Kaneshige <kaneshige.kenji@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2008-06-10 21:28:50 +00:00
void pci_destroy_slot(struct pci_slot *slot);
void pci_renumber_slot(struct pci_slot *slot, int slot_nr);
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);
u8 pci_swizzle_interrupt_pin(const struct pci_dev *dev, u8 pin);
int pci_get_interrupt_pin(struct pci_dev *dev, struct pci_dev **bridge);
u8 pci_common_swizzle(struct pci_dev *dev, u8 *pinp);
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_stop_and_remove_bus_device(struct pci_dev *dev);
void pci_stop_root_bus(struct pci_bus *bus);
void pci_remove_root_bus(struct pci_bus *bus);
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>
2006-09-29 20:23:23 +00:00
extern void pci_sort_breadthfirst(void);
#define dev_is_pci(d) ((d)->bus == &pci_bus_type)
#define dev_is_pf(d) ((dev_is_pci(d) ? to_pci_dev(d)->is_physfn : false))
#define dev_num_vf(d) ((dev_is_pci(d) ? pci_num_vf(to_pci_dev(d)) : 0))
/* Generic PCI functions exported to card drivers */
enum pci_lost_interrupt_reason {
PCI_LOST_IRQ_NO_INFORMATION = 0,
PCI_LOST_IRQ_DISABLE_MSI,
PCI_LOST_IRQ_DISABLE_MSIX,
PCI_LOST_IRQ_DISABLE_ACPI,
};
enum pci_lost_interrupt_reason pci_lost_interrupt(struct pci_dev *dev);
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_next_ext_capability(struct pci_dev *dev, int pos, 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,
struct pci_dev *from);
struct pci_dev *pci_get_slot(struct pci_bus *bus, unsigned int devfn);
struct pci_dev *pci_get_domain_bus_and_slot(int domain, unsigned int bus,
unsigned int devfn);
static inline struct pci_dev *pci_get_bus_and_slot(unsigned int bus,
unsigned int devfn)
{
return pci_get_domain_bus_and_slot(0, bus, 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);
struct pci_ops *pci_bus_set_ops(struct pci_bus *bus, struct pci_ops *ops);
static inline int pci_read_config_byte(const 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(const 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(const 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(const 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(const 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(const struct pci_dev *dev, int where,
u32 val)
{
return pci_bus_write_config_dword(dev->bus, dev->devfn, where, val);
}
int pcie_capability_read_word(struct pci_dev *dev, int pos, u16 *val);
int pcie_capability_read_dword(struct pci_dev *dev, int pos, u32 *val);
int pcie_capability_write_word(struct pci_dev *dev, int pos, u16 val);
int pcie_capability_write_dword(struct pci_dev *dev, int pos, u32 val);
int pcie_capability_clear_and_set_word(struct pci_dev *dev, int pos,
u16 clear, u16 set);
int pcie_capability_clear_and_set_dword(struct pci_dev *dev, int pos,
u32 clear, u32 set);
static inline int pcie_capability_set_word(struct pci_dev *dev, int pos,
u16 set)
{
return pcie_capability_clear_and_set_word(dev, pos, 0, set);
}
static inline int pcie_capability_set_dword(struct pci_dev *dev, int pos,
u32 set)
{
return pcie_capability_clear_and_set_dword(dev, pos, 0, set);
}
static inline int pcie_capability_clear_word(struct pci_dev *dev, int pos,
u16 clear)
{
return pcie_capability_clear_and_set_word(dev, pos, clear, 0);
}
static inline int pcie_capability_clear_dword(struct pci_dev *dev, int pos,
u32 clear)
{
return pcie_capability_clear_and_set_dword(dev, pos, clear, 0);
}
/* user-space driven config access */
int pci_user_read_config_byte(struct pci_dev *dev, int where, u8 *val);
int pci_user_read_config_word(struct pci_dev *dev, int where, u16 *val);
int pci_user_read_config_dword(struct pci_dev *dev, int where, u32 *val);
int pci_user_write_config_byte(struct pci_dev *dev, int where, u8 val);
int pci_user_write_config_word(struct pci_dev *dev, int where, u16 val);
int pci_user_write_config_dword(struct pci_dev *dev, int where, u32 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_enabled(struct pci_dev *pdev)
{
return (atomic_read(&pdev->enable_cnt) > 0);
}
static inline int pci_is_managed(struct pci_dev *pdev)
{
return pdev->is_managed;
}
void pci_disable_device(struct pci_dev *dev);
extern unsigned int pcibios_max_latency;
void pci_set_master(struct pci_dev *dev);
void pci_clear_master(struct pci_dev *dev);
int pci_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state state);
int pci_set_cacheline_size(struct pci_dev *dev);
#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);
bool pci_intx_mask_supported(struct pci_dev *dev);
bool pci_check_and_mask_intx(struct pci_dev *dev);
bool pci_check_and_unmask_intx(struct pci_dev *dev);
void pci_msi_off(struct pci_dev *dev);
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);
PCI: Set PCI-E Max Payload Size on fabric On a given PCI-E fabric, each device, bridge, and root port can have a different PCI-E maximum payload size. There is a sizable performance boost for having the largest possible maximum payload size on each PCI-E device. However, if improperly configured, fatal bus errors can occur. Thus, it is important to ensure that PCI-E payloads sends by a device are never larger than the MPS setting of all devices on the way to the destination. This can be achieved two ways: - A conservative approach is to use the smallest common denominator of the entire tree below a root complex for every device on that fabric. This means for example that having a 128 bytes MPS USB controller on one leg of a switch will dramatically reduce performances of a video card or 10GE adapter on another leg of that same switch. It also means that any hierarchy supporting hotplug slots (including expresscard or thunderbolt I suppose, dbl check that) will have to be entirely clamped to 128 bytes since we cannot predict what will be plugged into those slots, and we cannot change the MPS on a "live" system. - A more optimal way is possible, if it falls within a couple of constraints: * The top-level host bridge will never generate packets larger than the smallest TLP (or if it can be controlled independently from its MPS at least) * The device will never generate packets larger than MPS (which can be configured via MRRS) * No support of direct PCI-E <-> PCI-E transfers between devices without some additional code to specifically deal with that case Then we can use an approach that basically ignores downstream requests and focuses exclusively on upstream requests. In that case, all we need to care about is that a device MPS is no larger than its parent MPS, which allows us to keep all switches/bridges to the max MPS supported by their parent and eventually the PHB. In this case, your USB controller would no longer "starve" your 10GE Ethernet and your hotplug slots won't affect your global MPS. Additionally, the hotplugged devices themselves can be configured to a larger MPS up to the value configured in the hotplug bridge. To choose between the two available options, two PCI kernel boot args have been added to the PCI calls. "pcie_bus_safe" will provide the former behavior, while "pcie_bus_perf" will perform the latter behavior. By default, the latter behavior is used. NOTE: due to the location of the enablement, each arch will need to add calls to this function. This patch only enables x86. This patch includes a number of changes recommended by Benjamin Herrenschmidt. Tested-by: Jordan_Hargrave@dell.com Signed-off-by: Jon Mason <mason@myri.com> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2011-07-20 20:20:54 +00:00
int pcie_get_mps(struct pci_dev *dev);
int pcie_set_mps(struct pci_dev *dev, int mps);
int __pci_reset_function(struct pci_dev *dev);
int __pci_reset_function_locked(struct pci_dev *dev);
int pci_reset_function(struct pci_dev *dev);
void pci_update_resource(struct pci_dev *dev, int resno);
int __must_check pci_assign_resource(struct pci_dev *dev, int i);
int __must_check pci_reassign_resource(struct pci_dev *dev, int i, resource_size_t add_size, resource_size_t align);
int pci_select_bars(struct pci_dev *dev, unsigned long flags);
/* ROM control related routines */
int pci_enable_rom(struct pci_dev *pdev);
void pci_disable_rom(struct pci_dev *pdev);
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(struct pci_dev *pdev, void __iomem *rom, size_t size);
/* Power management related routines */
int pci_save_state(struct pci_dev *dev);
void pci_restore_state(struct pci_dev *dev);
struct pci_saved_state *pci_store_saved_state(struct pci_dev *dev);
int pci_load_saved_state(struct pci_dev *dev, struct pci_saved_state *state);
int pci_load_and_free_saved_state(struct pci_dev *dev,
struct pci_saved_state **state);
int __pci_complete_power_transition(struct pci_dev *dev, pci_power_t state);
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);
bool pci_pme_capable(struct pci_dev *dev, pci_power_t state);
void pci_pme_active(struct pci_dev *dev, bool enable);
int __pci_enable_wake(struct pci_dev *dev, pci_power_t state,
bool runtime, bool enable);
int pci_wake_from_d3(struct pci_dev *dev, bool enable);
pci_power_t pci_target_state(struct pci_dev *dev);
int pci_prepare_to_sleep(struct pci_dev *dev);
int pci_back_from_sleep(struct pci_dev *dev);
PCI / ACPI / PM: Platform support for PCI PME wake-up Although the majority of PCI devices can generate PMEs that in principle may be used to wake up devices suspended at run time, platform support is generally necessary to convert PMEs into wake-up events that can be delivered to the kernel. If ACPI is used for this purpose, PME signals generated by a PCI device will trigger the ACPI GPE associated with the device to generate an ACPI wake-up event that we can set up a handler for, provided that everything is configured correctly. Unfortunately, the subset of PCI devices that have GPEs associated with them is quite limited. The devices without dedicated GPEs have to rely on the GPEs associated with other devices (in the majority of cases their upstream bridges and, possibly, the root bridge) to generate ACPI wake-up events in response to PME signals from them. Add ACPI platform support for PCI PME wake-up: o Add a framework making is possible to use ACPI system notify handlers for run-time PM. o Add new PCI platform callback ->run_wake() to struct pci_platform_pm_ops allowing us to enable/disable the platform to generate wake-up events for given device. Implemet this callback for the ACPI platform. o Define ACPI wake-up handlers for PCI devices and PCI root buses and make the PCI-ACPI binding code register wake-up notifiers for all PCI devices present in the ACPI tables. o Add function pci_dev_run_wake() which can be used by PCI drivers to check if given device is capable of generating wake-up events at run time. Developed in cooperation with Matthew Garrett <mjg@redhat.com>. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2010-02-17 22:44:09 +00:00
bool pci_dev_run_wake(struct pci_dev *dev);
bool pci_check_pme_status(struct pci_dev *dev);
void pci_pme_wakeup_bus(struct pci_bus *bus);
static inline int pci_enable_wake(struct pci_dev *dev, pci_power_t state,
bool enable)
{
return __pci_enable_wake(dev, state, false, enable);
}
#define PCI_EXP_IDO_REQUEST (1<<0)
#define PCI_EXP_IDO_COMPLETION (1<<1)
void pci_enable_ido(struct pci_dev *dev, unsigned long type);
void pci_disable_ido(struct pci_dev *dev, unsigned long type);
enum pci_obff_signal_type {
PCI_EXP_OBFF_SIGNAL_L0 = 0,
PCI_EXP_OBFF_SIGNAL_ALWAYS = 1,
};
int pci_enable_obff(struct pci_dev *dev, enum pci_obff_signal_type);
void pci_disable_obff(struct pci_dev *dev);
int pci_enable_ltr(struct pci_dev *dev);
void pci_disable_ltr(struct pci_dev *dev);
int pci_set_ltr(struct pci_dev *dev, int snoop_lat_ns, int nosnoop_lat_ns);
/* For use by arch with custom probe code */
void set_pcie_port_type(struct pci_dev *pdev);
void set_pcie_hotplug_bridge(struct pci_dev *pdev);
/* Functions for PCI Hotplug drivers to use */
int pci_bus_find_capability(struct pci_bus *bus, unsigned int devfn, int cap);
unsigned int pci_rescan_bus_bridge_resize(struct pci_dev *bridge);
unsigned int pci_rescan_bus(struct pci_bus *bus);
/* Vital product data routines */
ssize_t pci_read_vpd(struct pci_dev *dev, loff_t pos, size_t count, void *buf);
ssize_t pci_write_vpd(struct pci_dev *dev, loff_t pos, size_t count, const void *buf);
int pci_vpd_truncate(struct pci_dev *dev, size_t size);
/* Helper functions for low-level code (drivers/pci/setup-[bus,res].c) */
resource_size_t pcibios_retrieve_fw_addr(struct pci_dev *dev, int idx);
void pci_bus_assign_resources(const 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 pci_assign_unassigned_bridge_resources(struct pci_dev *bridge);
void pci_assign_unassigned_bus_resources(struct pci_bus *bus);
void pdev_enable_device(struct pci_dev *);
int pci_enable_resources(struct pci_dev *, int mask);
void pci_fixup_irqs(u8 (*)(struct pci_dev *, u8 *),
PCI: Make the struct pci_dev * argument of pci_fixup_irqs const. Aside of the usual motivation for constification, this function has a history of being abused a hook for interrupt and other fixups so I turned this function const ages ago in the MIPS code but it should be done treewide. Due to function pointer passing in varous places a few other functions had to be constified as well. Signed-off-by: Ralf Baechle <ralf@linux-mips.org> To: Anton Vorontsov <avorontsov@mvista.com> To: Chris Metcalf <cmetcalf@tilera.com> To: Colin Cross <ccross@android.com> Acked-by: "David S. Miller" <davem@davemloft.net> To: Eric Miao <eric.y.miao@gmail.com> To: Erik Gilling <konkers@android.com> Acked-by: Guan Xuetao <gxt@mprc.pku.edu.cn> To: "H. Peter Anvin" <hpa@zytor.com> To: Imre Kaloz <kaloz@openwrt.org> To: Ingo Molnar <mingo@redhat.com> To: Ivan Kokshaysky <ink@jurassic.park.msu.ru> To: Jesse Barnes <jbarnes@virtuousgeek.org> To: Krzysztof Halasa <khc@pm.waw.pl> To: Lennert Buytenhek <kernel@wantstofly.org> To: Matt Turner <mattst88@gmail.com> To: Nicolas Pitre <nico@fluxnic.net> To: Olof Johansson <olof@lixom.net> Acked-by: Paul Mundt <lethal@linux-sh.org> To: Richard Henderson <rth@twiddle.net> To: Russell King <linux@arm.linux.org.uk> To: Thomas Gleixner <tglx@linutronix.de> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: linux-alpha@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-kernel@vger.kernel.org Cc: linux-mips@linux-mips.org Cc: linux-pci@vger.kernel.org Cc: linux-sh@vger.kernel.org Cc: linux-tegra@vger.kernel.org Cc: sparclinux@vger.kernel.org Cc: x86@kernel.org Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2011-06-10 14:30:21 +00:00
int (*)(const struct pci_dev *, u8, u8));
#define HAVE_PCI_REQ_REGIONS 2
int __must_check pci_request_regions(struct pci_dev *, const char *);
int __must_check pci_request_regions_exclusive(struct pci_dev *, const char *);
void pci_release_regions(struct pci_dev *);
int __must_check pci_request_region(struct pci_dev *, int, const char *);
int __must_check pci_request_region_exclusive(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 *);
int pci_request_selected_regions_exclusive(struct pci_dev *, int, const char *);
void pci_release_selected_regions(struct pci_dev *, int);
/* drivers/pci/bus.c */
void pci_add_resource(struct list_head *resources, struct resource *res);
void pci_add_resource_offset(struct list_head *resources, struct resource *res,
resource_size_t offset);
void pci_free_resource_list(struct list_head *resources);
void pci_bus_add_resource(struct pci_bus *bus, struct resource *res, unsigned int flags);
struct resource *pci_bus_resource_n(const struct pci_bus *bus, int n);
void pci_bus_remove_resources(struct pci_bus *bus);
#define pci_bus_for_each_resource(bus, res, i) \
for (i = 0; \
(res = pci_bus_resource_n(bus, i)) || i < PCI_BRIDGE_RESOURCE_NUM; \
i++)
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,
resource_size_t (*alignf)(void *,
const 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);
2008-07-30 19:07:04 +00:00
/*
* pci_register_driver must be a macro so that KBUILD_MODNAME can be expanded
*/
#define pci_register_driver(driver) \
__pci_register_driver(driver, THIS_MODULE, KBUILD_MODNAME)
void pci_unregister_driver(struct pci_driver *dev);
/**
* module_pci_driver() - Helper macro for registering a PCI driver
* @__pci_driver: pci_driver struct
*
* Helper macro for PCI drivers which do not do anything special in module
* init/exit. This eliminates a lot of boilerplate. Each module may only
* use this macro once, and calling it replaces module_init() and module_exit()
*/
#define module_pci_driver(__pci_driver) \
module_driver(__pci_driver, pci_register_driver, \
pci_unregister_driver)
struct pci_driver *pci_dev_driver(const struct pci_dev *dev);
int pci_add_dynid(struct pci_driver *drv,
unsigned int vendor, unsigned int device,
unsigned int subvendor, unsigned int subdevice,
unsigned int class, unsigned int class_mask,
unsigned long driver_data);
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, int (*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);
void pci_setup_bridge(struct pci_bus *bus);
resource_size_t pcibios_window_alignment(struct pci_bus *bus,
unsigned long type);
#define PCI_VGA_STATE_CHANGE_BRIDGE (1 << 0)
#define PCI_VGA_STATE_CHANGE_DECODES (1 << 1)
int pci_set_vga_state(struct pci_dev *pdev, bool decode,
unsigned int command_bits, u32 flags);
/* kmem_cache style wrapper around pci_alloc_consistent() */
#include <linux/pci-dma.h>
#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 {
u32 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_block(struct pci_dev *dev, unsigned int nvec)
{
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_msix_table_size(struct pci_dev *dev)
{
return 0;
}
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)
{ }
static inline int pci_msi_enabled(void)
{
return 0;
}
#else
extern int pci_enable_msi_block(struct pci_dev *dev, unsigned int nvec);
extern void pci_msi_shutdown(struct pci_dev *dev);
extern void pci_disable_msi(struct pci_dev *dev);
extern int pci_msix_table_size(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);
extern int pci_msi_enabled(void);
#endif
#ifdef CONFIG_PCIEPORTBUS
extern bool pcie_ports_disabled;
extern bool pcie_ports_auto;
#else
#define pcie_ports_disabled true
#define pcie_ports_auto false
#endif
#ifndef CONFIG_PCIEASPM
static inline int pcie_aspm_enabled(void) { return 0; }
static inline bool pcie_aspm_support_enabled(void) { return false; }
#else
extern int pcie_aspm_enabled(void);
extern bool pcie_aspm_support_enabled(void);
#endif
#ifdef CONFIG_PCIEAER
void pci_no_aer(void);
bool pci_aer_available(void);
#else
static inline void pci_no_aer(void) { }
static inline bool pci_aer_available(void) { return false; }
#endif
#ifndef CONFIG_PCIE_ECRC
static inline void pcie_set_ecrc_checking(struct pci_dev *dev)
{
return;
}
static inline void pcie_ecrc_get_policy(char *str) {};
#else
extern void pcie_set_ecrc_checking(struct pci_dev *dev);
extern void pcie_ecrc_get_policy(char *str);
#endif
#define pci_enable_msi(pdev) pci_enable_msi_block(pdev, 1)
#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_cfg_access_lock(struct pci_dev *dev);
extern bool pci_cfg_access_trylock(struct pci_dev *dev);
extern void pci_cfg_access_unlock(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 */
/* some architectures require additional setup to direct VGA traffic */
typedef int (*arch_set_vga_state_t)(struct pci_dev *pdev, bool decode,
unsigned int command_bits, u32 flags);
extern void pci_register_set_vga_state(arch_set_vga_state_t func);
#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_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,
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_consistent_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 void pci_restore_state(struct pci_dev *dev)
{ }
static inline int pci_set_power_state(struct pci_dev *dev, pci_power_t state)
{
return 0;
}
static inline int pci_wake_from_d3(struct pci_dev *dev, bool enable)
{
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 void pci_enable_ido(struct pci_dev *dev, unsigned long type)
{
}
static inline void pci_disable_ido(struct pci_dev *dev, unsigned long type)
{
}
static inline int pci_enable_obff(struct pci_dev *dev, unsigned long type)
{
return 0;
}
static inline void pci_disable_obff(struct pci_dev *dev)
{
}
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_cfg_access(struct pci_dev *dev)
{ }
static inline int pci_block_cfg_access_in_atomic(struct pci_dev *dev)
{ return 0; }
static inline void pci_unblock_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; }
static inline int pci_domain_nr(struct pci_bus *bus)
{ return 0; }
static inline struct pci_dev *pci_dev_get(struct pci_dev *dev)
{ return NULL; }
#define dev_is_pci(d) (false)
#define dev_is_pf(d) (false)
#define dev_num_vf(d) (0)
#endif /* CONFIG_PCI */
/* Include architecture-dependent settings and functions */
#include <asm/pci.h>
#ifndef PCIBIOS_MAX_MEM_32
#define PCIBIOS_MAX_MEM_32 (-1)
#endif
/* 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 const char *pci_name(const struct pci_dev *pdev)
{
return dev_name(&pdev->dev);
}
/* 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; /* You can use PCI_ANY_ID here of course */
u16 device; /* You can use PCI_ANY_ID here of course */
u32 class; /* You can use PCI_ANY_ID here too */
unsigned int class_shift; /* should be 0, 8, 16 */
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_device_resume() */
pci_fixup_suspend, /* pci_device_suspend */
pci_fixup_resume_early, /* pci_device_resume_early() */
};
/* Anonymous variables would be nice... */
#define DECLARE_PCI_FIXUP_SECTION(section, name, vendor, device, class, \
class_shift, hook) \
static const struct pci_fixup __pci_fixup_##name __used \
__attribute__((__section__(#section), aligned((sizeof(void *))))) \
= { vendor, device, class, class_shift, hook };
#define DECLARE_PCI_FIXUP_CLASS_EARLY(vendor, device, class, \
class_shift, hook) \
DECLARE_PCI_FIXUP_SECTION(.pci_fixup_early, \
vendor##device##hook, vendor, device, class, class_shift, hook)
#define DECLARE_PCI_FIXUP_CLASS_HEADER(vendor, device, class, \
class_shift, hook) \
DECLARE_PCI_FIXUP_SECTION(.pci_fixup_header, \
vendor##device##hook, vendor, device, class, class_shift, hook)
#define DECLARE_PCI_FIXUP_CLASS_FINAL(vendor, device, class, \
class_shift, hook) \
DECLARE_PCI_FIXUP_SECTION(.pci_fixup_final, \
vendor##device##hook, vendor, device, class, class_shift, hook)
#define DECLARE_PCI_FIXUP_CLASS_ENABLE(vendor, device, class, \
class_shift, hook) \
DECLARE_PCI_FIXUP_SECTION(.pci_fixup_enable, \
vendor##device##hook, vendor, device, class, class_shift, hook)
#define DECLARE_PCI_FIXUP_CLASS_RESUME(vendor, device, class, \
class_shift, hook) \
DECLARE_PCI_FIXUP_SECTION(.pci_fixup_resume, \
resume##vendor##device##hook, vendor, device, class, \
class_shift, hook)
#define DECLARE_PCI_FIXUP_CLASS_RESUME_EARLY(vendor, device, class, \
class_shift, hook) \
DECLARE_PCI_FIXUP_SECTION(.pci_fixup_resume_early, \
resume_early##vendor##device##hook, vendor, device, \
class, class_shift, hook)
#define DECLARE_PCI_FIXUP_CLASS_SUSPEND(vendor, device, class, \
class_shift, hook) \
DECLARE_PCI_FIXUP_SECTION(.pci_fixup_suspend, \
suspend##vendor##device##hook, vendor, device, class, \
class_shift, hook)
#define DECLARE_PCI_FIXUP_EARLY(vendor, device, hook) \
DECLARE_PCI_FIXUP_SECTION(.pci_fixup_early, \
vendor##device##hook, vendor, device, PCI_ANY_ID, 0, hook)
#define DECLARE_PCI_FIXUP_HEADER(vendor, device, hook) \
DECLARE_PCI_FIXUP_SECTION(.pci_fixup_header, \
vendor##device##hook, vendor, device, PCI_ANY_ID, 0, hook)
#define DECLARE_PCI_FIXUP_FINAL(vendor, device, hook) \
DECLARE_PCI_FIXUP_SECTION(.pci_fixup_final, \
vendor##device##hook, vendor, device, PCI_ANY_ID, 0, hook)
#define DECLARE_PCI_FIXUP_ENABLE(vendor, device, hook) \
DECLARE_PCI_FIXUP_SECTION(.pci_fixup_enable, \
vendor##device##hook, vendor, device, PCI_ANY_ID, 0, hook)
#define DECLARE_PCI_FIXUP_RESUME(vendor, device, hook) \
DECLARE_PCI_FIXUP_SECTION(.pci_fixup_resume, \
resume##vendor##device##hook, vendor, device, \
PCI_ANY_ID, 0, hook)
#define DECLARE_PCI_FIXUP_RESUME_EARLY(vendor, device, hook) \
DECLARE_PCI_FIXUP_SECTION(.pci_fixup_resume_early, \
resume_early##vendor##device##hook, vendor, device, \
PCI_ANY_ID, 0, hook)
#define DECLARE_PCI_FIXUP_SUSPEND(vendor, device, hook) \
DECLARE_PCI_FIXUP_SECTION(.pci_fixup_suspend, \
suspend##vendor##device##hook, vendor, device, \
PCI_ANY_ID, 0, hook)
#ifdef CONFIG_PCI_QUIRKS
void pci_fixup_device(enum pci_fixup_pass pass, struct pci_dev *dev);
struct pci_dev *pci_get_dma_source(struct pci_dev *dev);
int pci_dev_specific_acs_enabled(struct pci_dev *dev, u16 acs_flags);
#else
static inline void pci_fixup_device(enum pci_fixup_pass pass,
struct pci_dev *dev) {}
static inline struct pci_dev *pci_get_dma_source(struct pci_dev *dev)
{
return pci_dev_get(dev);
}
static inline int pci_dev_specific_acs_enabled(struct pci_dev *dev,
u16 acs_flags)
{
return -ENOTTY;
}
#endif
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, int mask, const char *name);
int pcim_iomap_regions_request_all(struct pci_dev *pdev, int mask,
const char *name);
void pcim_iounmap_regions(struct pci_dev *pdev, int 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 u8 pci_dfl_cache_line_size;
extern u8 pci_cache_line_size;
extern unsigned long pci_hotplug_io_size;
extern unsigned long pci_hotplug_mem_size;
/* Architecture specific versions may override these (weak) */
int pcibios_add_platform_entries(struct pci_dev *dev);
void pcibios_disable_device(struct pci_dev *dev);
void pcibios_set_master(struct pci_dev *dev);
int pcibios_set_pcie_reset_state(struct pci_dev *dev,
enum pcie_reset_state state);
int pcibios_add_device(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 09:27:20 +00:00
#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 09:27:20 +00:00
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 09:27:20 +00:00
static inline void pci_mmcfg_late_init(void) { }
#endif
int pci_ext_cfg_avail(void);
void __iomem *pci_ioremap_bar(struct pci_dev *pdev, int bar);
#ifdef CONFIG_PCI_IOV
extern int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn);
extern void pci_disable_sriov(struct pci_dev *dev);
extern irqreturn_t pci_sriov_migration(struct pci_dev *dev);
extern int pci_num_vf(struct pci_dev *dev);
extern int pci_sriov_set_totalvfs(struct pci_dev *dev, u16 numvfs);
extern int pci_sriov_get_totalvfs(struct pci_dev *dev);
#else
static inline int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn)
{
return -ENODEV;
}
static inline void pci_disable_sriov(struct pci_dev *dev)
{
}
static inline irqreturn_t pci_sriov_migration(struct pci_dev *dev)
{
return IRQ_NONE;
}
static inline int pci_num_vf(struct pci_dev *dev)
{
return 0;
}
static inline int pci_sriov_set_totalvfs(struct pci_dev *dev, u16 numvfs)
{
return 0;
}
static inline int pci_sriov_get_totalvfs(struct pci_dev *dev)
{
return 0;
}
#endif
#if defined(CONFIG_HOTPLUG_PCI) || defined(CONFIG_HOTPLUG_PCI_MODULE)
extern void pci_hp_create_module_link(struct pci_slot *pci_slot);
extern void pci_hp_remove_module_link(struct pci_slot *pci_slot);
#endif
/**
* pci_pcie_cap - get the saved PCIe capability offset
* @dev: PCI device
*
* PCIe capability offset is calculated at PCI device initialization
* time and saved in the data structure. This function returns saved
* PCIe capability offset. Using this instead of pci_find_capability()
* reduces unnecessary search in the PCI configuration space. If you
* need to calculate PCIe capability offset from raw device for some
* reasons, please use pci_find_capability() instead.
*/
static inline int pci_pcie_cap(struct pci_dev *dev)
{
return dev->pcie_cap;
}
/**
* pci_is_pcie - check if the PCI device is PCI Express capable
* @dev: PCI device
*
* Retrun true if the PCI device is PCI Express capable, false otherwise.
*/
static inline bool pci_is_pcie(struct pci_dev *dev)
{
return !!pci_pcie_cap(dev);
}
/**
* pci_pcie_type - get the PCIe device/port type
* @dev: PCI device
*/
static inline int pci_pcie_type(const struct pci_dev *dev)
{
return (dev->pcie_flags_reg & PCI_EXP_FLAGS_TYPE) >> 4;
}
void pci_request_acs(void);
bool pci_acs_enabled(struct pci_dev *pdev, u16 acs_flags);
bool pci_acs_path_enabled(struct pci_dev *start,
struct pci_dev *end, u16 acs_flags);
#define PCI_VPD_LRDT 0x80 /* Large Resource Data Type */
#define PCI_VPD_LRDT_ID(x) (x | PCI_VPD_LRDT)
/* Large Resource Data Type Tag Item Names */
#define PCI_VPD_LTIN_ID_STRING 0x02 /* Identifier String */
#define PCI_VPD_LTIN_RO_DATA 0x10 /* Read-Only Data */
#define PCI_VPD_LTIN_RW_DATA 0x11 /* Read-Write Data */
#define PCI_VPD_LRDT_ID_STRING PCI_VPD_LRDT_ID(PCI_VPD_LTIN_ID_STRING)
#define PCI_VPD_LRDT_RO_DATA PCI_VPD_LRDT_ID(PCI_VPD_LTIN_RO_DATA)
#define PCI_VPD_LRDT_RW_DATA PCI_VPD_LRDT_ID(PCI_VPD_LTIN_RW_DATA)
/* Small Resource Data Type Tag Item Names */
#define PCI_VPD_STIN_END 0x78 /* End */
#define PCI_VPD_SRDT_END PCI_VPD_STIN_END
#define PCI_VPD_SRDT_TIN_MASK 0x78
#define PCI_VPD_SRDT_LEN_MASK 0x07
#define PCI_VPD_LRDT_TAG_SIZE 3
#define PCI_VPD_SRDT_TAG_SIZE 1
#define PCI_VPD_INFO_FLD_HDR_SIZE 3
#define PCI_VPD_RO_KEYWORD_PARTNO "PN"
#define PCI_VPD_RO_KEYWORD_MFR_ID "MN"
#define PCI_VPD_RO_KEYWORD_VENDOR0 "V0"
#define PCI_VPD_RO_KEYWORD_CHKSUM "RV"
/**
* pci_vpd_lrdt_size - Extracts the Large Resource Data Type length
* @lrdt: Pointer to the beginning of the Large Resource Data Type tag
*
* Returns the extracted Large Resource Data Type length.
*/
static inline u16 pci_vpd_lrdt_size(const u8 *lrdt)
{
return (u16)lrdt[1] + ((u16)lrdt[2] << 8);
}
/**
* pci_vpd_srdt_size - Extracts the Small Resource Data Type length
* @lrdt: Pointer to the beginning of the Small Resource Data Type tag
*
* Returns the extracted Small Resource Data Type length.
*/
static inline u8 pci_vpd_srdt_size(const u8 *srdt)
{
return (*srdt) & PCI_VPD_SRDT_LEN_MASK;
}
/**
* pci_vpd_info_field_size - Extracts the information field length
* @lrdt: Pointer to the beginning of an information field header
*
* Returns the extracted information field length.
*/
static inline u8 pci_vpd_info_field_size(const u8 *info_field)
{
return info_field[2];
}
/**
* pci_vpd_find_tag - Locates the Resource Data Type tag provided
* @buf: Pointer to buffered vpd data
* @off: The offset into the buffer at which to begin the search
* @len: The length of the vpd buffer
* @rdt: The Resource Data Type to search for
*
* Returns the index where the Resource Data Type was found or
* -ENOENT otherwise.
*/
int pci_vpd_find_tag(const u8 *buf, unsigned int off, unsigned int len, u8 rdt);
/**
* pci_vpd_find_info_keyword - Locates an information field keyword in the VPD
* @buf: Pointer to buffered vpd data
* @off: The offset into the buffer at which to begin the search
* @len: The length of the buffer area, relative to off, in which to search
* @kw: The keyword to search for
*
* Returns the index where the information field keyword was found or
* -ENOENT otherwise.
*/
int pci_vpd_find_info_keyword(const u8 *buf, unsigned int off,
unsigned int len, const char *kw);
/* PCI <-> OF binding helpers */
#ifdef CONFIG_OF
struct device_node;
extern void pci_set_of_node(struct pci_dev *dev);
extern void pci_release_of_node(struct pci_dev *dev);
extern void pci_set_bus_of_node(struct pci_bus *bus);
extern void pci_release_bus_of_node(struct pci_bus *bus);
/* Arch may override this (weak) */
extern struct device_node * __weak pcibios_get_phb_of_node(struct pci_bus *bus);
static inline struct device_node *
pci_device_to_OF_node(const struct pci_dev *pdev)
{
return pdev ? pdev->dev.of_node : NULL;
}
static inline struct device_node *pci_bus_to_OF_node(struct pci_bus *bus)
{
return bus ? bus->dev.of_node : NULL;
}
#else /* CONFIG_OF */
static inline void pci_set_of_node(struct pci_dev *dev) { }
static inline void pci_release_of_node(struct pci_dev *dev) { }
static inline void pci_set_bus_of_node(struct pci_bus *bus) { }
static inline void pci_release_bus_of_node(struct pci_bus *bus) { }
#endif /* CONFIG_OF */
#ifdef CONFIG_EEH
static inline struct eeh_dev *pci_dev_to_eeh_dev(struct pci_dev *pdev)
{
return pdev->dev.archdata.edev;
}
#endif
/**
* pci_find_upstream_pcie_bridge - find upstream PCIe-to-PCI bridge of a device
* @pdev: the PCI device
*
* if the device is PCIE, return NULL
* if the device isn't connected to a PCIe bridge (that is its parent is a
* legacy PCI bridge and the bridge is directly connected to bus 0), return its
* parent
*/
struct pci_dev *pci_find_upstream_pcie_bridge(struct pci_dev *pdev);
#endif /* LINUX_PCI_H */