Commit ae21ee65 "PCI: acs p2p upsteram
forwarding enabling" doesn't actually enable ACS.

Add a function to pci core to allow an IOMMU to request that ACS
be enabled.  The existing mechanism of using iommu_found() in the pci
core to know when ACS should be enabled doesn't actually work due to
initialization order;  iommu has only been detected not initialized.

Have Intel and AMD IOMMUs request ACS, and Xen does as well during early
init of dom0.

Cc: Allen Kay <allen.m.kay@intel.com>
Cc: David Woodhouse <dwmw2@infradead.org>
Cc: Jeremy Fitzhardinge <jeremy@goop.org>
Cc: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: NChris Wright <chrisw@sous-sol.org>
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>

This patch fixes the following compilation error introduced by a PCI related
features.

The change set of 5dd1af9f84c79bedd589db89e71ca733f3bf0ebd moves some
xen related definitions from the arch header file
(x86/include/asm/xen/hypervisor.h) to the common header file
(include/xen/xen.h).  So ia64/xen also follows it.

In file included from linux-next/include/xen/grant_table.h:41,
                 from linux-next/drivers/block/xen-blkfront.c:48:
linux-next/arch/ia64/include/asm/xen/hypervisor.h:43: error: nested redefinition of 'enum xen_domain_type'
linux-next/arch/ia64/include/asm/xen/hypervisor.h:43: error: redeclaration of 'enum xen_domain_type'
linux-next/arch/ia64/include/asm/xen/hypervisor.h:44: error: redeclaration of enumerator 'XEN_NATIVE'
linux-next/include/xen/xen.h:5: error: previous definition of 'XEN_NATIVE' was here
linux-next/arch/ia64/include/asm/xen/hypervisor.h:45: error: redeclaration of enumerator 'XEN_PV_DOMAIN'
linux-next/include/xen/xen.h:6: error: previous definition of 'XEN_PV_DOMAIN' was here
linux-next/arch/ia64/include/asm/xen/hypervisor.h:46: error: redeclaration of enumerator 'XEN_HVM_DOMAIN'
linux-next/include/xen/xen.h:7: error: previous definition of 'XEN_HVM_DOMAIN' was here
Signed-off-by: NIsaku Yamahata <yamahata@valinux.co.jp>
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>

Move xen_domain and related tests out of asm-x86 to xen/xen.h so they
can be included whenever they are necessary.
Signed-off-by: NJeremy Fitzhardinge <jeremy.fitzhardinge@citrix.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>

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>

sparc64 is now the only user of PCI_CACHE_LINE_BYTES.  Drop it and set
pci_dfl_cache_line_size from pcibios_init() instead and drop
PCI_CACHE_LINE_BYTES handling from generic pci code.

Orignally-From: David Miller <davem@davemloft.net>
Signed-off-by: NTejun Heo <tj@kernel.org>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>

Till now, CLS has been determined either by arch code or as
L1_CACHE_BYTES.  Only x86 and ia64 set CLS explicitly and x86 doesn't
always get it right.  On most configurations, the chance is that
firmware configures the correct value during boot.

This patch makes pci_init() determine CLS by looking at what firmware
has configured.  It scans all devices and if all non-zero values
agree, the value is used.  If none is configured or there is a
disagreement, pci_dfl_cache_line_size is used.  arch can set the dfl
value (via PCI_CACHE_LINE_BYTES or pci_dfl_cache_line_size) or
override the actual one.

ia64, x86 and sparc64 updated to set the default cls instead of the
actual one.

While at it, declare pci_cache_line_size and pci_dfl_cache_line_size
in pci.h and drop private declarations from arch code.
Signed-off-by: NTejun Heo <tj@kernel.org>
Acked-by: NDavid Miller <davem@davemloft.net>
Acked-by: NGreg KH <gregkh@suse.de>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tony Luck <tony.luck@intel.com>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>

For intel systems with multi IOH, we should read peer root resources
directly from PCI config space, and don't trust _CRS.
Signed-off-by: NYinghai Lu <yinghai.lu@sun.com>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>