The Moorestown platform only has a few devices that actually support
PCI config cycles.  The rest of the devices use an in-RAM MCFG space
for the purposes of device enumeration and initialization.

There are a few uglies in the fake support, like BAR sizes that aren't
a power of two, sizing detection, and writes to the real devices, but
other than that it's pretty straightforward.

Another way to think of this is not really as PCI at all, but just a
table in RAM describing which devices are present, their capabilities
and their offsets in MMIO space.  This could have been done with a
special new firmware table on this platform, but given that we do have
some real PCI devices too, simply describing things in an MCFG type
space was pretty simple.
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>
LKML-Reference: <43F901BD926A4E43B106BF17856F07559FB80D08@orsmsx508.amr.corp.intel.com>
Signed-off-by: NJacob Pan <jacob.jun.pan@intel.com>
Signed-off-by: NH. Peter Anvin <hpa@zytor.com>

Platforms like Moorestown want to override the pcibios_fixup_irqs
default function. Add it to x86_init.pci.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
LKML-Reference: <43F901BD926A4E43B106BF17856F07559FB80D00@orsmsx508.amr.corp.intel.com>
Acked-by: NJesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: NJacob Pan <jacob.jun.pan@intel.com>
Signed-off-by: NH. Peter Anvin <hpa@zytor.com>

Moorestown wants to reuse pcibios_init_irq but needs to provide its
own implementation of pci_enable_irq. After we distangled the init we
can move the init_irq call to x86_init and remove the pci_enable_irq
!= NULL check in pcibios_init_irq. pci_enable_irq is compile time
initialized to pirq_enable_irq and the special cases which override it
(visws and acpi) set the x86_init function pointer to noop. That
allows MSRT to override pci_enable_irq and otherwise run
pcibios_init_irq unmodified.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
LKML-Reference: <43F901BD926A4E43B106BF17856F07559FB80CFF@orsmsx508.amr.corp.intel.com>
Acked-by: NJesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: NJacob Pan <jacob.jun.pan@intel.com>
Signed-off-by: NH. Peter Anvin <hpa@zytor.com>

The PCI initialization in pci_subsys_init() is a mess. pci_numaq_init,
pci_acpi_init, pci_visws_init and pci_legacy_init are called and each
implementation checks and eventually modifies the global variable
pcibios_scanned.

x86_init functions allow us to do this more elegant. The pci.init
function pointer is preset to pci_legacy_init. numaq, acpi and visws
can modify the pointer in their early setup functions. The functions
return 0 when they did the full initialization including bus scan. A
non zero return value indicates that pci_legacy_init needs to be
called either because the selected function failed or wants the
generic bus scan in pci_legacy_init to happen (e.g. visws).
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
LKML-Reference: <43F901BD926A4E43B106BF17856F07559FB80CFE@orsmsx508.amr.corp.intel.com>
Acked-by: NJesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: NJacob Pan <jacob.jun.pan@intel.com>
Signed-off-by: NH. Peter Anvin <hpa@zytor.com>

Turned out to cause trouble on single IOH machines, and is superceded by
_CRS on multi-IOH machines with production BIOSes.
Signed-off-by: NJeff Garrett <jeff@jgarrett.org>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>

It is above 0x100 (PCI-Express extended register space), so if mmconf
is not enable, we can't access it.

[ hpa: changed the bound from 0x200 to 0x120, which is the tight
  bound. ]
Reported-by: NJens Axboe <jens.axboe@oracle.com>
Signed-off-by: NYinghai Lu <yinghai@kernel.org>
LKML-Reference: <1261525263-13763-3-git-send-email-yinghai@kernel.org>
Signed-off-by: NH. Peter Anvin <hpa@zytor.com>

Remark update_res from __init to __devinit as it is called also
from __devinit functions.

This patch removes the following warning message:

  WARNING: vmlinux.o(.devinit.text+0x774a): Section mismatch
  in reference from the function pci_root_bus_res() to the
  function .init.text:update_res()
  The function __devinit pci_root_bus_res() references
  a function __init update_res().
  If update_res is only used by pci_root_bus_res then
  annotate update_res with a matching annotation.
Signed-off-by: NJiri Slaby <jslaby@suse.cz>
Cc: Aristeu Sergio <arozansk@redhat.com>
Cc: Jesse Barnes <jbarnes@virtuousgeek.org>
Cc: linux-pci@vger.kernel.org
Cc: x86@kernel.org
Signed-off-by: NHidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>

This allows us to use the BIOS SR-IOV allocations rather than assigning
our own later on.
Signed-off-by: NYinghai Lu <yinghai@kernel.org>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>

This patch factors out the search for an MMCONFIG region, which was
previously implemented in both mmconfig_32 and mmconfig_64.  No functional
change.
Reviewed-by: NYinghai Lu <yinghai@kernel.org>
Signed-off-by: NBjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>

No functional change; just tidy up printks and make them more consistent
with the rest of PCI.
Reviewed-by: NYinghai Lu <yinghai@kernel.org>
Signed-off-by: NBjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>

This is only used internally now, but eventually will be used in the
hot-remove path to remove the MMCONFIG region associated with a host bridge.
Reviewed-by: NYinghai Lu <yinghai@kernel.org>
Signed-off-by: NBjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>

This changes pci_mmcfg_region from a table to a list, to make it easier
to add and remove MMCONFIG regions for PCI host bridge hotplug.
Reviewed-by: NYinghai Lu <yinghai@kernel.org>
Signed-off-by: NBjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>

This replaces "typeof(pci_mmcfg_config[0])" with the actual type because
I plan to convert pci_mmcfg_config to a list, and then "pci_mmcfg_config[0]"
won't mean anything.
Reviewed-by: NYinghai Lu <yinghai@kernel.org>
Signed-off-by: NBjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>

The virtual address is only used for x86_64, but it's so much simpler
to manage it as part of the pci_mmcfg_region that I think it's worth
wasting a pointer per MMCONFIG region on x86_32.
Reviewed-by: NYinghai Lu <yinghai@kernel.org>
Signed-off-by: NBjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>

Since pci_mmcfg_region contains the struct resource, no need to pass the
pci_mmcfg_region *and* the resource start/size.
Reviewed-by: NYinghai Lu <yinghai@kernel.org>
Signed-off-by: NBjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>

This patch adds a resource and corresponding name to the MMCONFIG
structure.  This makes allocation simpler (we can allocate the
resource and name at the same time we allocate the pci_mmcfg_region),
and gives us a way to hang onto the resource after inserting it.
This will be needed so we can release and free it when hot-removing
a host bridge.
Reviewed-by: NYinghai Lu <yinghai@kernel.org>
Signed-off-by: NBjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>

No functional change, but simplifies a future patch to convert the table
to a list.
Reviewed-by: NYinghai Lu <yinghai@kernel.org>
Signed-off-by: NBjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>

This only renames the struct pci_mmcfg_region members; no functional change.
Reviewed-by: NYinghai Lu <yinghai@kernel.org>
Signed-off-by: NBjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>

This adds a struct pci_mmcfg_region with a little more information
than the struct acpi_mcfg_allocation used previously.  The acpi_mcfg
structure is defined by the spec, so we can't change it.

To begin with, struct pci_mmcfg_region is basically the same as the
ACPI MCFG version, but future patches will add more information.
Reviewed-by: NYinghai Lu <yinghai@kernel.org>
Signed-off-by: NBjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>

This factors out the common "bus << 20" expression used when computing the
MMCONFIG address.
Reviewed-by: NYinghai Lu <yinghai@kernel.org>
Signed-off-by: NBjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>

Since all MMCONFIG regions go through pci_mmconfig_add(), we can test the
address once there.  If the caller supplies an address of zero, we never
insert it in the pci_mmcfg_config[] table, so no need to test it elsewhere.
Reviewed-by: NYinghai Lu <yinghai@kernel.org>
Signed-off-by: NBjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>

We never set pci_mmcfg_config unless we increment pci_mmcfg_config_num,
so there's no need to test both pci_mmcfg_config_num and pci_mmcfg_config.
Reviewed-by: NYinghai Lu <yinghai@kernel.org>
Signed-off-by: NBjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>

This patch encapsulate pci_mmcfg_config[] updates.  All alloc/free is now
done in pci_mmconfig_add() and free_all_mcfg(), so all updates to
pci_mmcfg_config[] and pci_mmcfg_config_num are in those two functions.

This replaces the previous sequence of extend_mmcfg(), fill_one_mmcfg()
with the single pci_mmconfig_add() interface.  This interface is currently
static but will eventually be used in the host bridge hot-add path.
Reviewed-by: NYinghai Lu <yinghai@kernel.org>
Signed-off-by: NBjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>

Step through the ACPI MCFG table, not pci_mmcfg_config[].  No functional
change, but simplifies future patches that encapsulate pci_mmcfg_config[].
Reviewed-by: NYinghai Lu <yinghai@kernel.org>
Signed-off-by: NBjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>

Use a local variable, not pci_mmcfg_config_num, to count MCFG entries.
No functional change, but simplifies future changes.
Reviewed-by: NYinghai Lu <yinghai@kernel.org>
Signed-off-by: NBjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>

Reviewed-by: NYinghai Lu <yinghai@kernel.org>
Signed-off-by: NBjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>

Those functions are used by intel_bus.c so seperate them to another file. and
make amd_bus a bit smaller.
Signed-off-by: NYinghai Lu <yinghai@kernel.org>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>

Signed-off-by: NAndré Goddard Rosa <andre.goddard@gmail.com>
Signed-off-by: NJiri Kosina <jkosina@suse.cz>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>

commit db635adc turned -DDEBUG for x86/pci on when CONFIG_PCI_DEBUG
is set. In general, I agree with that change.

However, it exposes a bunch of very low level PCI debugging in the
early x86 path, such as:

	0 reading 2 from a: ffff
	1 reading 2 from a: ffff
	2 reading 2 from a: ffff
	3 reading 2 from a: 300
	3 reading 2 from 0: 1002
	3 reading 2 from 2: 515e

These statements add a lot of noise to the boot and aren't likely to
be necessary even when handling random upstream bug reports.

[In contrast, statements such as these:

	pci 0000:02:04.0: found [14e4:164a] class 000200 header type 00
	pci 0000:02:04.0: reg 10: [mem 0xf8000000-0xf9ffffff 64bit]
	pci 0000:02:04.0: reg 30: [mem 0x00000000-0x0001ffff pref]

are indeed useful when remote debugging users' machines]

Remove the noisy printks and save electrons everywhere.

Cc: Bjorn Helgaas <bjorn.helgaas@hp.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: NAlex Chiang <achiang@hp.com>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>

The roundup() caused a build error (undefined reference to `__udivdi3').
We're aligning to power-of-two boundaries, so it's simpler to just use
ALIGN() anyway, which avoids the division.
Signed-off-by: NBjorn Helgaas <bjorn.helgaas@hp.com>
Acked-by: NRandy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>

PCI device BARs are guaranteed to start and end on at least a four-byte
(I/O) or a sixteen-byte (MMIO) boundary because they're aligned on their
size and the low BAR bits are reserved.  PCI-to-PCI bridge apertures
have even larger alignment restrictions.

However, some BIOSes (e.g., HP DL360 BIOS P31) report host bridge windows
like "[io  0x0000-0x2cfe]".  This is wrong because it excludes the last
port at 0x2cff: it's impossible for a downstream device to claim 0x2cfe
without also claiming 0x2cff.  In fact, this BIOS configures a device
behind the bridge to "[io  0x2c00-0x2cff]", so we know the window actually
does include 0x2cff.

This patch rounds the start and end of apertures to the appropriate
boundary.  I experimentally determined that Windows contains a similar
workaround; details here:

    http://bugzilla.kernel.org/show_bug.cgi?id=14337Signed-off-by: NBjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>

We have occasional problems with PCI resource allocation, and sometimes
they could be avoided by paying attention to what ACPI tells us about
the host bridges.  This patch doesn't change the behavior, but it prints
window information that should make debugging easier.
Signed-off-by: NBjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>

This makes PCI resource management messages more consistent and adds a few
new messages to aid debugging.

Whenever we assign resources to a device, update a BAR, or change a
bridge aperture, it's worth noting it.
Signed-off-by: NBjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>

Use the dev_printk-like "%04x:%02x" format for printing PCI bus numbers.
Signed-off-by: NBjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>

Jesse accidentally applied v1 [1] of the patchset instead of v2 [2].  This
is the diff between v1 and v2.

The changes in this patch are:
    - tidied vsprintf stack buffer to shrink and compute size more
      accurately
    - use %pR for decoding and %pr for "raw" (with type and flags) instead
      of adding %pRt and %pRf

[1] http://lkml.org/lkml/2009/10/6/491
[2] http://lkml.org/lkml/2009/10/13/441Signed-off-by: NBjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>

We use dev_dbg() in arch/x86/pci, but there's no easy way to turn it
on.  Add -DDEBUG when CONFIG_PCI_DEBUG=y, just like we do in drivers/pci.
Signed-off-by: NBjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>

The current whitelist requires a kernel change for every machine that has
MMCONFIG regions above 4GB, even if BIOS provides a correct MCFG table.

This patch expands the whitelist to include machines with a rev 1 or newer
MCFG table and a DMI_BIOS_DATE of 2010 or later.  That way, we only need
kernel changes for new machines that provide incorrect MCFG tables.
Signed-off-by: NBjorn Helgaas <bjorn.helgaas@hp.com>
CC: Matthew Wilcox <willy@linux.intel.com>
CC: John Keller <jpk@sgi.com>
CC: Yinghai Lu <yhlu.kernel@gmail.com>
CC: Kenji Kaneshige <kaneshige.kenji@jp.fujitsu.com>
CC: Andi Kleen <andi@firstfloor.org>
Acked-by: NIngo Molnar <mingo@elte.hu>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>

Thomas Schlichter reported:
> X.org uses libpciaccess which tries to mmap with write combining enabled via
> /sys/bus/pci/devices/*/resource0_wc. Currently, when PAT is not enabled, the
> kernel does fall back to uncached mmap. Then libpciaccess thinks it succeeded
> mapping with write combining enabled and does not set up suited MTRR entries.
> ;-(

Instead of silently mapping pci mmap region as UC minus in the case
of !pat_enabled and wc request, we can return error. Eric Anholt mentioned
that caller (like X) typically follows up with UC minus pci mmap request and
if there is a free mtrr slot, caller will manage adding WC mtrr.

Jesse Barnes says:
> Older versions of libpciaccess will behave better if we do it that way
> (iirc it only allocates an MTRR if the resource_wc file doesn't exist or
> fails to get mapped).
Reported-by: NThomas Schlichter <thomas.schlichter@web.de>
Signed-off-by: NThomas Schlichter <thomas.schlichter@web.de>
Signed-off-by: NSuresh Siddha <suresh.b.siddha@intel.com>
Acked-by: NEric Anholt <eric@anholt.net>
Acked-by: NJesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>

This uses %pRt to print additional resource information (type, size,
prefetchability, etc.) consistently.
Signed-off-by: NBjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>

Instead of the PCI code needing to have code to determine the
cacheline size of each processor, use the data the cpu identification
code should have already determined during early boot.

(The vendor checks are also incomplete, and don't take into account
 modern CPUs)

I've been carrying a variant of this code in Fedora for a while,
that prints debug information.  There are a number of cases where we
are currently setting the PCI cacheline size to 32 bytes, when the CPU
cacheline size is 64 bytes.  With this patch, we set them both the same.
Signed-off-by: NDave Jones <davej@redhat.com>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>