Platforms may want to provide architecture-specific functionality during
PCI enumeration. Add a pcibios_add_device() call that architectures can
override to do so.
Signed-off-by: NMatthew Garrett <mjg@redhat.com>
Signed-off-by: NBjorn Helgaas <bhelgaas@google.com>
Tested-by: NSeth Forshee <seth.forshee@canonical.com>

For unbound PCI devices, what we need is:

 - Always in D0 state, because some devices do not work again after
   being put into D3 by the PCI bus.

 - In SUSPENDED state if allowed, so that the parent devices can still
   be put into low power state.

To satisfy these requirements, the runtime PM for the unbound PCI
devices are disabled and set to SUSPENDED state.  One issue of this
solution is that the PCI devices will be put into SUSPENDED state even
if the SUSPENDED state is forbidden via the sysfs interface
(.../power/control) of the device.  This is not an issue for most
devices, because most PCI devices are not used at all if unbound.
But there are exceptions.  For example, unbound VGA card can be used
for display, but suspending its parents makes it stop working.

To fix the issue, we keep the runtime PM enabled when the PCI devices
are unbound.  But the runtime PM callbacks will do nothing if the PCI
devices are unbound.  This way, we can put the PCI devices into
SUSPENDED state without putting the PCI devices into D3 state.

Reference: https://bugzilla.kernel.org/show_bug.cgi?id=48201Signed-off-by: NHuang Ying <ying.huang@intel.com>
Signed-off-by: NBjorn Helgaas <bhelgaas@google.com>
Acked-by: NAlan Stern <stern@rowland.harvard.edu>
Acked-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>
CC: stable@vger.kernel.org          # v3.6+

CONFIG_HOTPLUG is going away as an option so __devexit_p, __devint,
__devinitdata, __devinitconst, and _devexit are no longer needed.
Signed-off-by: NBill Pemberton <wfp5p@virginia.edu>
Acked-by: NBjorn Helgaas <bhelgaas@google.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

There are comments on why PME poll support is necessary for PCI
devices, but not for PCIe devices.  That may lead to misunderstanding
that PME poll is only necessary for PCI devices.  So add comments
related to PCIe PME poll to make it more clear.

The content of comments comes from the changelog of commit:

379021d5Signed-off-by: NHuang Ying <ying.huang@intel.com>
Signed-off-by: NBjorn Helgaas <bhelgaas@google.com>
Acked-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

pci_ext_cfg_avail() doesn't use the "struct pci_dev *" passed to
it, and there's no requirement that a host bridge even be represented
by a pci_dev.  This drops the pci_ext_cfg_avail() parameter.

[bhelgaas: changelog]
Signed-off-by: NTaku Izumi <izumi.taku@jp.fujitsu.com>
Signed-off-by: NBjorn Helgaas <bhelgaas@google.com>

In https://bugzilla.kernel.org/show_bug.cgi?id=48981
Peter reported that /proc/bus/pci/??/??.? does not work for 3.6.
This is because the device configuration space registers are
not accessible if the corresponding parent bridge is suspended or
the device is put into D3cold state.

This is the same as /sys/bus/pci/devices/0000:??:??.?/config access
issue.  So the function used to solve sysfs issue is used to solve
this issue.

This patch moves pci_config_pm_runtime_get()/_put() from pci/pci-sysfs.c
to pci/pci.c and makes them extern so they can be used by both the
sysfs and proc paths.

[bhelgaas: changelog, references, reporters]
Reference: https://bugzilla.kernel.org/show_bug.cgi?id=48981
Reference: https://bugzilla.kernel.org/show_bug.cgi?id=49031Reported-by: NForrest Loomis <cybercyst@gmail.com>
Reported-by: NPeter <lekensteyn@gmail.com>
Reported-by: NMicael Dias <kam1kaz3@gmail.com>
Signed-off-by: NHuang Ying <ying.huang@intel.com>
Signed-off-by: NBjorn Helgaas <bhelgaas@google.com>
Acked-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>
CC: stable@vger.kernel.org		# v3.6+

Use PCI Express Capability access functions to simplify core.
Signed-off-by: NJiang Liu <jiang.liu@huawei.com>
Signed-off-by: NYijing Wang <wangyijing@huawei.com>
Signed-off-by: NBjorn Helgaas <bhelgaas@google.com>

Introduce an inline function pci_pcie_type(dev) to extract PCIe
device type from pci_dev->pcie_flags_reg field, and prepare for
removing pci_dev->pcie_type.
Signed-off-by: NYijing Wang <wangyijing@huawei.com>
Signed-off-by: NJiang Liu <jiang.liu@huawei.com>
Signed-off-by: NBjorn Helgaas <bhelgaas@google.com>

Some extended capabilities, e.g., the vendor-specific capability, can
occur several times.  The existing pci_find_ext_capability() only finds
the first occurrence.  This adds pci_find_next_ext_capability(), which
can iterate through all of them.
Signed-off-by: NBjorn Helgaas <bhelgaas@google.com>

Fix kernel-doc warnings in drivers/pci/pci.c:

Warning(drivers/pci/pci.c:1550): No description found for parameter 'pci_dev'
Warning(drivers/pci/pci.c:1550): Excess function parameter 'dev' description in 'pci_wakeup'
Signed-off-by: NRandy Dunlap <rdunlap@xenotime.net>
Signed-off-by: NBjorn Helgaas <bhelgaas@google.com>

This patch fixes the following bug:

http://marc.info/?l=linux-usb&m=134318961120825&w=2

Originally, device lower power states include D1, D2, D3.  After that,
D3 is further divided into D3hot and D3cold.  To support both scenario
safely, original D3 is mapped to D3cold.

When adding D3cold support, because worry about some device may have
broken D3cold support, D3cold is disabled by default.  This disable D3
on original platform too.  But some original platform may only have
working D3, but no working D1, D2.  The root cause of the above bug is
it too.

To deal with this, this patch enables D3/D3cold by default for most
devices.  This restores the original behavior.  For some devices that
suspected to have broken D3cold support, such as PCIe port, D3cold is
disabled by default.
Reported-by: NBjorn Mork <bjorn@mork.no>
Signed-off-by: NHuang Ying <ying.huang@intel.com>
Signed-off-by: NBjorn Helgaas <bhelgaas@google.com>
Reviewed-by: NRafael J. Wysocki <rjw@sisk.pl>

Quite a few ASUS computers experience a nasty problem, related to the
EHCI controllers, when going into system suspend.  It was observed
that the problem didn't occur if the controllers were not put into the
D3 power state before starting the suspend, and commit
151b6128 (USB: EHCI: fix crash during
suspend on ASUS computers) was created to do this.

It turned out this approach messed up other computers that didn't have
the problem -- it prevented USB wakeup from working.  Consequently
commit c2fb8a3f (USB: add
NO_D3_DURING_SLEEP flag and revert 151b6128) was merged; it
reverted the earlier commit and added a whitelist of known good board
names.

Now we know the actual cause of the problem.  Thanks to AceLan Kao for
tracking it down.

According to him, an engineer at ASUS explained that some of their
BIOSes contain a bug that was added in an attempt to work around a
problem in early versions of Windows.  When the computer goes into S3
suspend, the BIOS tries to verify that the EHCI controllers were first
quiesced by the OS.  Nothing's wrong with this, but the BIOS does it
by checking that the PCI COMMAND registers contain 0 without checking
the controllers' power state.  If the register isn't 0, the BIOS
assumes the controller needs to be quiesced and tries to do so.  This
involves making various MMIO accesses to the controller, which don't
work very well if the controller is already in D3.  The end result is
a system hang or memory corruption.

Since the value in the PCI COMMAND register doesn't matter once the
controller has been suspended, and since the value will be restored
anyway when the controller is resumed, we can work around the BIOS bug
simply by setting the register to 0 during system suspend.  This patch
(as1590) does so and also reverts the second commit mentioned above,
which is now unnecessary.

In theory we could do this for every PCI device.  However to avoid
introducing new problems, the patch restricts itself to EHCI host
controllers.

Finally the affected systems can suspend with USB wakeup working
properly.

Reference: https://bugzilla.kernel.org/show_bug.cgi?id=37632
Reference: https://bugzilla.kernel.org/show_bug.cgi?id=42728Based-on-patch-by: NAceLan Kao <acelan.kao@canonical.com>
Signed-off-by: NAlan Stern <stern@rowland.harvard.edu>
Tested-by: NDâniel Fraga <fragabr@gmail.com>
Tested-by: NJavier Marcet <jmarcet@gmail.com>
Tested-by: NAndrey Rahmatullin <wrar@wrar.name>
Tested-by: NOleksij Rempel <bug-track@fisher-privat.net>
Tested-by: NPavel Pisa <pisa@cmp.felk.cvut.cz>
Cc: stable <stable@vger.kernel.org>
Acked-by: NBjorn Helgaas <bhelgaas@google.com>
Acked-by: NRafael J. Wysocki <rjw@sisk.pl>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

Commit cc2893b6 (PCI: Ensure we re-enable devices on resume)
addressed the problem with USB not being powered after resume on
recent Lenovo machines, but it did that in a suboptimal way.
Namely, it should have changed the relevant code paths only,
which are pci_pm_resume_noirq() and pci_pm_restore_noirq() supposed
to restore the device's power and standard configuration registers
after system resume from suspend or hibernation.  Instead, however,
it modified pci_set_power_state() which is executed in several
other situations too.  That resulted in some undesirable effects,
like attempting to change a device's power state in the same way
multiple times in a row (up to as many as 4 times in a row in the
snd_hda_intel driver).

Fix the bug addressed by commit cc2893b6 in an alternative way,
by forcibly powering up all devices in pci_pm_default_resume_early(),
which is called by pci_pm_resume_noirq() and pci_pm_restore_noirq()
to restore the device's power and standard configuration registers,
and modifying pci_pm_runtime_resume() to avoid the forcible power-up
if not necessary.  Then, revert the changes made by commit cc2893b6
to make the confusion introduced by it go away.
Acked-by: NMatthew Garrett <mjg@redhat.com>
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>
Signed-off-by: NBjorn Helgaas <bhelgaas@google.com>

Currently, all of the architectures implement their own pcibios_setup()
routine.  Most of the implementations do nothing so this patch introduces
a generic (__weak) routine in the core that can be used by all
architectures as a default.  If necessary, it can be overridden by
architecture-specific code.
Signed-off-by: NMyron Stowe <myron.stowe@redhat.com>
Signed-off-by: NBjorn Helgaas <bhelgaas@google.com>

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: NRafael J. Wysocki <rjw@sisk.pl>
Originally-by: NZheng Yan <zheng.z.yan@intel.com>
Signed-off-by: NHuang Ying <ying.huang@intel.com>
Signed-off-by: NBjorn Helgaas <bhelgaas@google.com>

This patch adds runtime PM support to PCIe port.  This is needed by
PCIe D3cold support, where PCIe device without ACPI node may be
powered on/off by PCIe port.

Because runtime suspend is broken for some chipsets, a black list is
used to disable runtime PM support for these chipsets.
Reviewed-by: NRafael J. Wysocki <rjw@sisk.pl>
Signed-off-by: NZheng Yan <zheng.z.yan@intel.com>
Signed-off-by: NHuang Ying <ying.huang@intel.com>
Signed-off-by: NBjorn Helgaas <bhelgaas@google.com>

For a valid pci_dev, dev->bus != NULL always, so remove this
unnecessary test.

Found by Coverity (CID 101680).
Signed-off-by: NBjorn Helgaas <bhelgaas@google.com>

pci_enable_obff() and pci_enable_ltr() incorrectly check "dev->bus" instead
of "dev->bus->self" to determine whether the upstream device is a P2P
bridge or a host bridge.  For devices on the root bus, the upstream device
is a host bridge, "dev->bus != NULL" and "dev->bus->self == NULL", and we
panic with a null pointer dereference.

These functions should previously have panicked when called on devices
supporting OBFF or LTR, so they should be regarded as untested.

Found by Coverity (CID 143038 and CID 143039).
Signed-off-by: NBjorn Helgaas <bhelgaas@google.com>

Use "__weak" instead of the gcc-specific "__attribute__ ((weak))"
Signed-off-by: NBjorn Helgaas <bhelgaas@google.com>

pci_intx_mask_supported() assumes INTx masking is supported if the
PCI_COMMAND_INTX_DISABLE bit is writable.  But when that bit is set,
some devices don't actually mask INTx or update PCI_STATUS_INTERRUPT
as we expect.

This patch adds a way for quirks to identify these broken devices.

[bhelgaas: split out from Chelsio quirk addition]
Signed-off-by: NJan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: NBjorn Helgaas <bhelgaas@google.com>

Replace the struct pci_bus secondary/subordinate members with the
struct resource busn_res.  Later we'll build a resource tree of these
bus numbers.

[bhelgaas: changelog]
Signed-off-by: NYinghai Lu <yinghai@kernel.org>
Signed-off-by: NBjorn Helgaas <bhelgaas@google.com>

This patch (as1558) fixes a problem affecting several ASUS computers:
The machine crashes or corrupts memory when going into suspend if the
ehci-hcd driver is bound to any controllers.  Users have been forced
to unbind or unload ehci-hcd before putting their systems to sleep.

After extensive testing, it was determined that the machines don't
like going into suspend when any EHCI controllers are in the PCI D3
power state.  Presumably this is a firmware bug, but there's nothing
we can do about it except to avoid putting the controllers in D3
during system sleep.

The patch adds a new flag to indicate whether the problem is present,
and avoids changing the controller's power state if the flag is set.
Runtime suspend is unaffected; this matters only for system suspend.
However as a side effect, the controller will not respond to remote
wakeup requests while the system is asleep.  Hence USB wakeup is not
functional -- but of course, this is already true in the current state
of affairs.

A similar patch has already been applied as commit
151b6128 (USB: EHCI: fix crash during
suspend on ASUS computers).  The patch supersedes that one and reverts
it.  There are two differences:

	The old patch added the flag at the USB level; this patch
	adds it at the PCI level.

	The old patch applied to all chipsets with the same vendor,
	subsystem vendor, and product IDs; this patch makes an
	exception for a known-good system (based on DMI information).
Signed-off-by: NAlan Stern <stern@rowland.harvard.edu>
Tested-by: NDâniel Fraga <fragabr@gmail.com>
Tested-by: NAndrey Rahmatullin <wrar@wrar.name>
Tested-by: NSteven Rostedt <rostedt@goodmis.org>
Cc: stable <stable@vger.kernel.org>
Reviewed-by: NRafael J. Wysocki <rjw@sisk.pl>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

In a PCI environment, transactions aren't always required to reach
the root bus before being re-routed.  Intermediate switches between
an endpoint and the root bus can redirect DMA back downstream before
things like IOMMUs have a chance to intervene.  Legacy PCI is always
susceptible to this as it operates on a shared bus.  PCIe added a
new capability to describe and control this behavior, Access Control
Services, or ACS.

The utility function pci_acs_enabled() allows us to test the ACS
capabilities of an individual devices against a set of flags while
pci_acs_path_enabled() tests a complete path from a given downstream
device up to the specified upstream device.  We also include the
ability to add device specific tests as it's likely we'll see
devices that do not implement ACS, but want to indicate support
for various capabilities in this space.
Signed-off-by: NAlex Williamson <alex.williamson@redhat.com>
Signed-off-by: NBjorn Helgaas <bhelgaas@google.com>

Unlike PCI Express v1's Capabilities Structure, v2's requires the entire
structure to be implemented.  In v2 structures, register fields that
are not implemented are present but hardwired to 0x0.  These may
include: Link Capabilities, Status, and Control; Slot Capabilities,
Status, and Control; Root Capabilities, Status, and Control; and all of
the '2' (Device, Link, and Slot) Capabilities, Status, and Control
registers.

This patch removes the redundant capability checks corresponding to the
Link 2's and Slot 2's, Capabilities, Status, and Control registers as they
will be present if Device Capabilities 2's registers are (which explains
why the macros for each of the three are identical).
Signed-off-by: NMyron Stowe <myron.stowe@redhat.com>
Signed-off-by: NBjorn Helgaas <bhelgaas@google.com>

This patch resolves potential issues when accessing PCI Express
Capability structures.  The makeup of the capability varies
substantially between v1 and v2:

    Version 1 of the PCI Express Capability (defined by PCI Express
    1.0 and 1.1 base) neither requires the endpoint to implement the
    entire PCIe capability structure nor specifies default values of
    registers that are not implemented by the device.

    Version 2 of the PCI Express Capability (defined by PCIe 1.1
    Capability Structure Expansion ECN, PCIe 2.0, 2.1, and 3.0) added
    additional registers to the structure and requires all registers
    to be either implemented or hardwired to 0.

Due to the differences in the capability structures, code dealing with
capability features must be careful not to access the additional
registers introduced with v2 unless the device is specifically known to
be a v2 capable device.  Otherwise, attempts to access non-existant
registers will occur.  This is a subtle issue that is hard to track down
when it occurs (and it has - see commit 864d296c).

To try and help mitigate such occurrences, this patch introduces
pci_pcie_cap2() which is similar to pci_pcie_cap() but also checks
that the PCIe capability version is >= 2.  pci_pcie_cap2() should be
used for qualifying PCIe capability features introduced after v1.

Suggested by Don Dutile.
Acked-by: NDonald Dutile <ddutile@redhat.com>
Signed-off-by: NMyron Stowe <myron.stowe@redhat.com>
Signed-off-by: NBjorn Helgaas <bhelgaas@google.com>

There are a number of redundant pci_is_pcie() checks in various PCI
Express capabilities related routines like the following:

    if (!pci_is_pcie(dev))
	return false;

    pos = pci_pcie_cap(dev);
    if (!pos)
	return false;

The current pci_is_pcie() implementation is merely:

    static inline bool pci_is_pcie(struct pci_dev *dev)
    {
        return !!pci_pcie_cap(dev);
    }

so we can just drop the pci_is_pcie() test in such cases.
Acked-by: NDonald Dutile <ddutile@redhat.com>
Signed-off-by: NMyron Stowe <myron.stowe@redhat.com>
Signed-off-by: NBjorn Helgaas <bhelgaas@google.com>

The PCI Express Latency Tolerance Reporting (LTR) feature's
pci_ltr_supported() routine is currently only used within
drivers/pci/pci.c so make it static.
Acked-by: NDonald Dutile <ddutile@redhat.com>
Signed-off-by: NMyron Stowe <myron.stowe@redhat.com>
Signed-off-by: NBjorn Helgaas <bhelgaas@google.com>

pci_max_busnr() has been commented out for years (since 54c762fe), and
this patch removes it completely.
Signed-off-by: NBjorn Helgaas <bhelgaas@google.com>

pci_bus_find_ext_capability() is unused, and this patch removes it.
Signed-off-by: NBjorn Helgaas <bhelgaas@google.com>

On MIPS we want to call of_irq_map_pci from inside

arch/mips/include/asm/pci.h:extern int pcibios_map_irq(
				const struct pci_dev *dev, u8 slot, u8 pin);
For this to work we need to change several functions to const usage.
Signed-off-by: NJohn Crispin <blogic@openwrt.org>
Cc: linux-pci@vger.kernel.org
Cc: devicetree-discuss@lists.ozlabs.org
Cc: linux-mips@linux-mips.org
Acked-by: NBjorn Helgaas <bhelgaas@google.com>
Acked-by: NGrant Likely <grant.likely@secretlab.ca>
Patchwork: https://patchwork.linux-mips.org/patch/3710/Signed-off-by: NRalf Baechle <ralf@linux-mips.org>

The intent of git commit 6fbf9e7a
"PCI: Introduce __pci_reset_function_locked to be used when holding
device_lock." was to have a non-locking function that would call
pci_dev_reset function.

But it fell short of that by just probing and not actually reseting
the device. To make that work we need a way to move the lock
around device_lock to not be in pci_dev_reset (as the caller of
__pci_reset_function_locked already holds said lock). We do this by
renaming pci_dev_reset to __pci_dev_reset and bubbling said mutex out
of __pci_dev_reset to pci_dev_reset (a wrapper around __pci_dev_reset).
The __pci_reset_function_locked  can now call __pci_dev_reset without
having to worry about the dead-lock.
Signed-off-by: NKonrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: NBjorn Helgaas <bhelgaas@google.com>

A PCIe downstream port is a P2P bridge.  Its secondary interface is
a link that should lead only to device 0 (unless ARI is enabled)[1], so
we don't probe for non-zero device numbers.

Some Stratus ftServer systems have a PCIe downstream port (02:00.0) that
leads to both an upstream port (03:00.0) and a downstream port (03:01.0),
and 03:01.0 has important devices below it:

  [0000:02]-+-00.0-[03-3c]--+-00.0-[04-09]--...
                            \-01.0-[0a-0d]--+-[USB]
                                            +-[NIC]
                                            +-...

Previously, we didn't enumerate device 03:01.0, so USB and the network
didn't work.  This patch adds a DMI quirk to scan all device numbers,
not just 0, below a downstream port.

Based on a patch by Prarit Bhargava.

[1] PCIe spec r3.0, sec 7.3.1

CC: Myron Stowe <mstowe@redhat.com>
CC: Don Dutile <ddutile@redhat.com>
CC: James Paradis <james.paradis@stratus.com>
CC: Matthew Wilcox <matthew.r.wilcox@intel.com>
CC: Jesse Barnes <jbarnes@virtuousgeek.org>
CC: Prarit Bhargava <prarit@redhat.com>
Signed-off-by: NBjorn Helgaas <bhelgaas@google.com>

Some shortcomings introduced into pci_restore_state() by commit
26f41062 ("PCI: check for pci bar restore completion and retry")
have been fixed by recent commit ebfc5b80 ("PCI: Fix regression in
pci_restore_state(), v3"), but that commit treats all PCI devices as
those with Type 0 configuration headers.

That is not entirely correct, because Type 1 and Type 2 headers have
different layouts.  In particular, the area occupied by BARs in Type 0
config headers contains the secondary status register in Type 1 ones and
it doesn't make sense to retry the restoration of that register even if
the value read back from it after a write is not the same as the written
one (it very well may be different).

For this reason, make pci_restore_state() only retry the restoration
of BARs for Type 0 config headers.  This effectively makes it behave
as before commit 26f41062 for all header types except for Type 0.
Tested-by: NMikko Vinni <mmvinni@yahoo.com>
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Commit 26f41062 ("PCI: check for pci bar restore completion and
retry") attempted to address problems with PCI BAR restoration on
systems where FLR had not been completed before pci_restore_state() was
called, but it did that in an utterly wrong way.

First off, instead of retrying the writes for the BAR registers only, it
did that for all of the PCI config space of the device, including the
status register (whose value after the write quite obviously need not be
the same as the written one).  Second, it added arbitrary delay to
pci_restore_state() even for systems where the PCI config space
restoration was successful at first attempt.  Finally, the mdelay(10) it
added to every iteration of the writing loop was way too much of a delay
for any reasonable device.

All of this actually caused resume failures for some devices on Mikko's
system.

To fix the regression, make pci_restore_state() only retry the writes
for BAR registers and only wait if the first read from the register
doesn't return the written value.  Additionaly, make it wait for 1 ms,
instead of 10 ms, after every failing attempt to write into config
space.
Reported-by: NMikko Vinni <mmvinni@yahoo.com>
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

There are PCIe devices on the market that report ARI support but
then fail to initialize correctly when ARI is actually used.  This
leads to situations in which kernels 2.6.34 and newer fail to handle
systems where the previous kernels worked without any apparent
problems.  Unfortunately, it is currently unknown how many such
devices are there.

For this reason, introduce a new kernel command line option,
pci=noari, allowing users to disable PCIe ARI altogether if they
see problems with PCIe device initialization.
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>

This isn't really a quirk; calling it directly from pci_add_device makes
more sense.
Signed-off-by: NYinghai Lu <yinghai@kernel.org>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>

Let the user could enable and disable with pci=realloc=on or pci=realloc=off

Also
1. move variable and functions near the place they are used.
2. change macro to function
3. change related functions and variable to static and _init
4. update parameter description accordingly.

This will let us add a config option to control default behavior, and
still allow the user to turn off automatic reallocation if it fails on
their platform until a permanent solution is found.

-v2: still honor pci=realloc, and treat it as pci=realloc=on
     also use enum instead of ...
-v3: update kernel-paramenters.txt according to Jesse.
Signed-off-by: NYinghai Lu <yinghai@kernel.org>
Acked-by: NJesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>

Only one user in driver/pci/pci.c, so we don't need to put it in global
pci.h
Reviewed-by: NBjorn Helgaas <bhelgaas@google.com>
Signed-off-by: NYinghai Lu <yinghai@kernel.org>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>

unreferenced object 0xffff880276d17700 (size 64):
  comm "swapper/0", pid 1, jiffies 4294897182 (age 3976.028s)
  hex dump (first 32 bytes):
    00 00 00 00 00 00 00 00 18 f9 de 76 02 88 ff ff  ...........v....
    10 00 00 00 0e 00 00 00 0f 28 40 00 00 00 00 00  .........(@.....
  backtrace:
    [<ffffffff81c8aede>] kmemleak_alloc+0x26/0x43
    [<ffffffff811385f0>] __kmalloc+0x121/0x183
    [<ffffffff813cf821>] pci_add_cap_save_buffer+0x35/0x7c
    [<ffffffff813d12b7>] pci_allocate_cap_save_buffers+0x1d/0x65
    [<ffffffff813cdb52>] pci_device_add+0x92/0xf1
    [<ffffffff81c8afe6>] pci_scan_single_device+0x9f/0xa1
    [<ffffffff813cdbd2>] pci_scan_slot.part.20+0x21/0x106
    [<ffffffff813cdce2>] pci_scan_slot+0x2b/0x35
    [<ffffffff81c8dae4>] __pci_scan_child_bus+0x51/0x107
    [<ffffffff81c8d75b>] pci_scan_bridge+0x376/0x6ae
    [<ffffffff81c8db60>] __pci_scan_child_bus+0xcd/0x107
    [<ffffffff81c8dbab>] pci_scan_child_bus+0x11/0x2a
    [<ffffffff81cca58c>] pci_acpi_scan_root+0x18b/0x21c
    [<ffffffff81c916be>] acpi_pci_root_add+0x1e1/0x42a
    [<ffffffff81406210>] acpi_device_probe+0x50/0x190
    [<ffffffff814a0227>] really_probe+0x99/0x126

Need to free saved_buffer for capabilities.
Signed-off-by: NYinghai Lu <yinghai@kernel.org>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>

On some OEM systems, pci_restore_state() is called while FLR has not yet
completed.  As a result, PCI BAR register restore is not successful.  This fix
reads back the restored value and compares it with saved value and re-tries 10
times before giving up.
Signed-off-by: NJean Guyader <jean.guyader@eu.citrix.com>
Signed-off-by: NEric Chanudet <eric.chanudet@citrix.com>
Signed-off-by: NAllen Kay <allen.m.kay@intel.com>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>