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>

We had assumed that SAL firmware would return an error if it didn't
understand extended config space.  Unfortunately, the SAL on the SGI 750
doesn't do that, it panics the machine.  So, condition the extended PCI
config space accesses on SAL revision 3.2.
Signed-off-by: NMatthew Wilcox <willy@linux.intel.com>
Tested-by: NBrad Spengler <spender@grsecurity.net>
Signed-off-by: NTony Luck <tony.luck@intel.com>

Should be __init.
Acked-by: NTony Luck <tony.luck@intel.com>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>

ia64 was assigning resources to root busses after allocations had
been made for child busses.  Calling pcibios_setup_root_windows() from
pcibios_fixup_bus() solves this problem by assigning the resources to
the root bus before child busses are scanned.
Signed-off-by: NMatthew Wilcox <willy@linux.intel.com>
Tested-by: NAndrew Patterson <andrew.patterson@hp.com>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

It is generally agreed that it would be beneficial for u64 to be an
unsigned long long on all architectures.  ia64 (in common with several
other 64-bit architectures) currently uses unsigned long.  Migrating
piecemeal is too painful; this giant patch fixes all compilation warnings
and errors that come as a result of switching to use int-ll64.h.

Note that userspace will still see __u64 defined as unsigned long.  This
is important as it affects C++ name mangling.

[Updated by Tony Luck to change efi.h:efi_freemem_callback_t to use
 u64 for start/end rather than unsigned long]
Signed-off-by: NMatthew Wilcox <willy@linux.intel.com>
Signed-off-by: NTony Luck <tony.luck@intel.com>

Create a platform specific version of dma_get_required_mask()
for ia64 SN Altix. All SN Altix platforms support 64 bit DMA
addressing regardless of the size of system memory.
Create an ia64 machvec for dma_get_required_mask, with the
SN version unconditionally returning DMA_64BIT_MASK.
Signed-off-by: NJohn Keller <jpk@sgi.com>
Signed-off-by: NTony Luck <tony.luck@intel.com>

This adds the ability to mmap legacy IO space to the legacy_io files
in sysfs on platforms that support it. This will allow to clean up
X to use this instead of /dev/mem for legacy IO accesses such as
those performed by Int10.

While at it I moved pci_create/remove_legacy_files() to pci-sysfs.c
where I think they belong, thus making more things statis in there
and cleaned up some spurrious prototypes in the ia64 pci.h file
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>

The code walks all the acpi _CRS methods to see how many windows
to allocate.  It then scans them all again to insert_resource()
for each *even if the first scan found that there were none*.

Move the second scan inside the "if (windows)" clause.
Signed-off-by: NTony Luck <tony.luck@intel.com>

Use the generic pci_enable_resources() instead of the arch-specific code.

Unlike this arch-specific code, the generic version:
    - does not check for a NULL dev pointer
    - skips resources that have neither IORESOURCE_IO nor IORESOURCE_MEM set
Signed-off-by: NBjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

http://bugzilla.kernel.org/show_bug.cgi?id=10124

this change:

      commit 08f1c192
      Author: Muli Ben-Yehuda <muli@il.ibm.com>
      Date:   Sun Jul 22 00:23:39 2007 +0300

         x86-64: introduce struct pci_sysdata to facilitate sharing of ->sysdata

         This patch introduces struct pci_sysdata to x86 and x86-64, and
         converts the existing two users (NUMA, Calgary) to use it.

         This lays the groundwork for having other users of sysdata, such as
         the PCI domains work.

         The Calgary bits are tested, the NUMA bits just look ok.

replaces pcibios_scan_root by pci_scan_bus_parented...

but in pcibios_scan_root we have a check about scanned busses.

Cc: <yakui.zhao@intel.com>
Cc: Stian Jordet <stian@jordet.net>
Cc: Len Brown <lenb@kernel.org>
Cc: Greg KH <greg@kroah.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: "Yinghai Lu" <yhlu.kernel@gmail.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

__FUNCTION__ is gcc-specific, use __func__

Long lines have been kept where they exist, some small spacing changes
have been done.
Signed-off-by: NHarvey Harrison <harvey.harrison@gmail.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NTony Luck <tony.luck@intel.com>

We want to allow different implementations of pci_raw_ops for standard
and extended config space on x86.  Rather than clutter generic code with
knowledge of this, we make pci_raw_ops private to x86 and use it to
implement the new raw interface -- raw_pci_read() and raw_pci_write().
Signed-off-by: NMatthew Wilcox <willy@linux.intel.com>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

pcibios_setup (between 'pci_setup' and 'quirk_mellanox_tavor')
setup_profiling_timer (between 'write_profile' and 'delayed_put_task_struct')
Signed-off-by: NTony Luck <tony.luck@intel.com>

Example memory map (HP rx7640 with 'default' acpiconfig setting, VGA disabled):
   0x00000000 - 0x3FFFBFFF  supports only WB (cacheable) access

If a user attempts to perform an MMIO mmap (using the PCIIOC_MMAP_IS_MEM ioctl)
to PCI config space (like mmap'ing and accessing memory at 0xA0000),
we will MCA because the kernel will attempt to use a mapping with the UC
attribute.

So check the memory attribute in kern_mmap and the EFI memmap. If WC is
requested, and WC or UC access is supported for the region, allow it.
Otherwise, use the same attribute the kernel uses.

Updates documentation and test cases as well.
Signed-off-by: NAlex Chiang <achiang@hp.com>
Signed-off-by: NBjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: NTony Luck <tony.luck@intel.com>

Hiroyuki Kamezawa reported the problem that pci_acpi_scan_root() of
ia64 might call kmalloc_node() with zero size.

Currently ia64's pci_acpi_scan_root() assumes that _CRS method of root
bridge has at least one resource window. But, the root bridges that
has no resource window must be taken into account.
Signed-off-by: NKenji Kaneshige <kaneshige.kenji@jp.fujitsu.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NTony Luck <tony.luck@intel.com>

Remove includes of <linux/smp_lock.h> where it is not used/needed.
Suggested by Al Viro.

Builds cleanly on x86_64, i386, alpha, ia64, powerpc, sparc,
sparc64, and arm (all 59 defconfigs).
Signed-off-by: NRandy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Allow cacheable mmaps of legacy_mem if WB access is supported for the region.
The "legacy_mem" file often contains a shadow option ROM, and some versions of
X depend on this.

Tim Yamin <plasm@roo.me.uk> reported that this change fixes X on a Dell
PowerEdge 3250.
Signed-off-by: NBjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: NTony Luck <tony.luck@intel.com>

Typo/thinko in bba6f6fcSigned-off-by: NTony Luck <tony.luck@intel.com>

So I think the right solution is to simply make pci_enable_device just
flip enable bits and move the rest of the work someplace else.

However a thorough cleanup is a little extreme for this point in the
release cycle, so I think a quick hack that makes the code not stomp the
irq when msi irq's are enabled should be the first fix.  Then we can
later make the code not change the irqs at all.
Signed-off-by: NEric W. Biederman <ebiederm@xmission.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Replace kmalloc+memset with kzalloc
Signed-off-by: NYan Burman <burman.yan@gmail.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NTony Luck <tony.luck@intel.com>

The recent change to convert the is_enabled flag in the PCI device to an
atomic count broke the IA64 compilation.

As pcibios_disable_device is only ever called if the reference count
is zero, convert the if to a BUG_ON.
Signed-off-by: NPeter Chubb <peterc@gelato.unsw.edu.au>
Signed-off-by: NTony Luck <tony.luck@intel.com>

First phase in introducing ACPI support to SN.
In this phase, when running with an ACPI capable PROM,
the DSDT will define the root busses and all SN nodes
(SGIHUB, SGITIO). An ACPI bus driver will be registered
for the node devices, with the acpi_pci_root_driver being
used for the root busses. An ACPI vendor descriptor is
now used to pass platform specific information for both
nodes and busses, eliminating the need for the current
SAL calls. Also, with ACPI support, SN fixup code is no longer
needed to initiate the PCI bus scans, as the acpi_pci_root_driver
does that.

However, to maintain backward compatibility with non-ACPI capable
PROMs, none of the current 'fixup' code can been deleted, though
much restructuring has been done. For example, the bulk of the code
in io_common.c is relocated code that is now common regardless
of what PROM is running, while io_acpi_init.c and io_init.c contain
routines specific to an ACPI or non ACPI capable PROM respectively.

A new pci bus fixup platform vector has been created to provide
a hook for invoking platform specific bus fixup from pcibios_fixup_bus().

The size of io_space[] has been increased to support systems with
large IO configurations.
Signed-off-by: NJohn Keller <jpk@sgi.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

The pci_generic_prep_mwi() code does everything that pcibios_prep_mwi()
does on ia64.  All we need to do is be sure that pci_cache_line_size
is set appropriately, and we can delete pcibios_prep_mwi().

Using SMP_CACHE_BYTES as the default was wrong on uniprocessor machines
as it is only 8 bytes.  The default in the generic code of L1_CACHE_BYTES
is at least as good.
Signed-off-by: NMatthew Wilcox <matthew@wil.cx>
Acked-by: NJeff Garzik <jeff@garzik.org>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Currently we attempt to predict how many irqs we will be able to allocate with
msi using pci_vector_resources and some complicated accounting, and then we
only allow each device as many irqs as we think are available on average.

Only the s2io driver even takes advantage of this feature all other drivers
have a fixed number of irqs they need and bail if they can't get them.

pci_vector_resources is inaccurate if anyone ever frees an irq.  The whole
implmentation is racy.  The current irq limit policy does not appear to make
sense with current drivers.  So I have simplified things.  We can revisit this
we we need a more sophisticated policy.
Signed-off-by: NEric W. Biederman <ebiederm@xmission.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Rajesh Shah <rajesh.shah@intel.com>
Cc: Andi Kleen <ak@muc.de>
Cc: "Protasevich, Natalie" <Natalie.Protasevich@UNISYS.com>
Cc: "Luck, Tony" <tony.luck@intel.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

This patch prevents pcibios_disable_device() from disabling interrupts
of devices which is not enabled.
Signed-off-by: NKenji Kaneshige <kaneshige.kenji@jp.fujitsu.com>
Signed-off-by: NMUNEDA Takahiro <muneda.takahiro@jp.fujitsu.com>
Signed-off-by: NSatoru Takeuchi <takeuchi_satoru@jp.fujitsu.com>
Signed-off-by: NKristen Carlson Accardi <kristen.c.accardi@intel.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Newer ARMs have a 40 bit physical address space, but mapping physical
memory above 4G needs a special page table format which we (currently?) do
not use for userspace mappings, so what happens instead is that mapping an
address >= 4G will happily discard the upper bits and wrap.

There is a valid_mmap_phys_addr_range() arch hook where we could check for
>= 4G addresses and deny the mapping, but this hook takes an unsigned long
address:

	static inline int valid_mmap_phys_addr_range(unsigned long addr, size_t size);

And drivers/char/mem.c:mmap_mem() calls it like this:

	static int mmap_mem(struct file * file, struct vm_area_struct * vma)
	{
		size_t size = vma->vm_end - vma->vm_start;

		if (!valid_mmap_phys_addr_range(vma->vm_pgoff << PAGE_SHIFT, size))

So that's not much help either.

This patch makes the hook take a pfn instead of a phys address.
Signed-off-by: NLennert Buytenhek <buytenh@wantstofly.org>
Cc: Bjorn Helgaas <bjorn.helgaas@hp.com>
Cc: "Luck, Tony" <tony.luck@intel.com>
Cc: Russell King <rmk@arm.linux.org.uk>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Signed-off-by: NJörn Engel <joern@wohnheim.fh-wedel.de>
Signed-off-by: NAdrian Bunk <bunk@stusta.de>

Based on a patch series originally from Vivek Goyal <vgoyal@in.ibm.com>

Cc: Vivek Goyal <vgoyal@in.ibm.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Remove VM_LOCKED before remap_pfn range from device drivers and get rid of
VM_SHM.

remap_pfn_range() already sets VM_IO.  There is no need to set VM_SHM since
it does nothing.  VM_LOCKED is of no use since the remap_pfn_range does not
place pages on the LRU.  The pages are therefore never subject to swap
anyways.  Remove all the vm_flags settings before calling remap_pfn_range.

After removing all the vm_flag settings no use of VM_SHM is left.  Drop it.
Signed-off-by: NChristoph Lameter <clameter@sgi.com>
Acked-by: NHugh Dickins <hugh@veritas.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Consolidate the various arch-specific implementations of pxm_to_node() and
node_to_pxm() into a single generic version.
Signed-off-by: NYasunori Goto <y-goto@jp.fujitsu.com>
Cc: "Luck, Tony" <tony.luck@intel.com>
Cc: Andi Kleen <ak@muc.de>
Cc: Dave Hansen <haveblue@us.ibm.com>
Cc: "Brown, Len" <len.brown@intel.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

This closes a couple holes in our attribute aliasing avoidance scheme:

  - The current kernel fails mmaps of some /dev/mem MMIO regions because
    they don't appear in the EFI memory map.  This keeps X from working
    on the Intel Tiger box.

  - The current kernel allows UC mmap of the 0-1MB region of
    /sys/.../legacy_mem even when the chipset doesn't support UC
    access.  This causes an MCA when starting X on HP rx7620 and rx8620
    boxes in the default configuration.

There's more detail in the Documentation/ia64/aliasing.txt file this
adds, but the general idea is that if a region might be covered by
a granule-sized kernel identity mapping, any access via /dev/mem or
mmap must use the same attribute as the identity mapping.

Otherwise, we fall back to using an attribute that is supported
according to the EFI memory map, or to using UC if the EFI memory
map doesn't mention the region.
Signed-off-by: NBjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: NTony Luck <tony.luck@intel.com>

This patch removes following compile time warnings:

drivers/pci/pci-sysfs.c: In function `pci_read_legacy_io':
drivers/pci/pci-sysfs.c:257: warning: implicit declaration of function `ia64_pci_legacy_read'
drivers/pci/pci-sysfs.c: In function `pci_write_legacy_io':
drivers/pci/pci-sysfs.c:280: warning: implicit declaration of function `ia64_pci_legacy_write'

It also fixes wrong definition of ia64_pci_legacy_write (type of `bus' is not
`pci_dev', but `pci_bus').
Signed-Off-By: NSatoru Takeuchi <takeuchi_satoru@jp.fujitsu.com>
Signed-off-by: NTony Luck <tony.luck@intel.com>

pcibios_setup() should return NULL if it handled a parameter.  Since ia64
handles no parameters, it should return the string that was passed in,
not NULL.  This brings ia64 into line with all other architectures that
handle no parameters.
Signed-off-by: NMatthew Wilcox <matthew@wil.cx>
Signed-off-by: NTony Luck <tony.luck@intel.com>

This patch fixes the bug that pci_claim_resource() is called multiple
times for the same P2P bridge's resource structures if P2P bridges
require their own PCI I/O resources.
Signed-off-by: NKenji Kaneshige <kaneshige.kenji@jp.fujitsu.com>
Signed-off-by: NTony Luck <tony.luck@intel.com>

The function ia64_pci_legacy_write() returns 0 for everything
except errors.  This return value gets sent back to the user from
pci_write_legacy_io(), making it look like every write fails.  The trivial
patch below copies the behavior of the SGI sn machvec and does what
would be expected from something implementing a write() function.
Signed-off-by: NAlex Williamson <alex.williamson@hp.com>
Signed-off-by: NTony Luck <tony.luck@intel.com>

Implemented support for the EM64T and other x86_64
processors. This essentially entails recognizing
that these processors support non-aligned memory
transfers. Previously, all 64-bit processors were assumed
to lack hardware support for non-aligned transfers.

Completed conversion of the Resource Manager to nearly
full table-driven operation. Specifically, the resource
conversion code (convert AML to internal format and the
reverse) and the debug code to dump internal resource
descriptors are fully table-driven, reducing code and data
size and improving maintainability.

The OSL interfaces for Acquire and Release Lock now use a
64-bit flag word on 64-bit processors instead of a fixed
32-bit word. (Alexey Starikovskiy)

Implemented support within the resource conversion code
for the Type-Specific byte within the various ACPI 3.0
*WordSpace macros.

Fixed some issues within the resource conversion code for
the type-specific flags for both Memory and I/O address
resource descriptors. For Memory, implemented support
for the MTP and TTP flags. For I/O, split the TRS and TTP
flags into two separate fields.
Signed-off-by: NBob Moore <robert.moore@intel.com>
Signed-off-by: NLen Brown <len.brown@intel.com>

Completed a major overhaul of the Resource Manager code -
specifically, optimizations in the area of the AML/internal
resource conversion code. The code has been optimized to
simplify and eliminate duplicated code, CPU stack use has
been decreased by optimizing function parameters and local
variables, and naming conventions across the manager have
been standardized for clarity and ease of maintenance (this
includes function, parameter, variable, and struct/typedef
names.)

All Resource Manager dispatch and information tables have
been moved to a single location for clarity and ease of
maintenance. One new file was created, named "rsinfo.c".

The ACPI return macros (return_ACPI_STATUS, etc.) have
been modified to guarantee that the argument is
not evaluated twice, making them less prone to macro
side-effects. However, since there exists the possibility
of additional stack use if a particular compiler cannot
optimize them (such as in the debug generation case),
the original macros are optionally available.  Note that
some invocations of the return_VALUE macro may now cause
size mismatch warnings; the return_UINT8 and return_UINT32
macros are provided to eliminate these. (From Randy Dunlap)

Implemented a new mechanism to enable debug tracing for
individual control methods. A new external interface,
acpi_debug_trace(), is provided to enable this mechanism. The
intent is to allow the host OS to easily enable and disable
tracing for problematic control methods. This interface
can be easily exposed to a user or debugger interface if
desired. See the file psxface.c for details.

acpi_ut_callocate() will now return a valid pointer if a
length of zero is specified - a length of one is used
and a warning is issued. This matches the behavior of
acpi_ut_allocate().
Signed-off-by: NBob Moore <robert.moore@intel.com>
Signed-off-by: NLen Brown <len.brown@intel.com>

ia64 translates normal loads and stores to special MMIO regions into I/O port
accesses.  Reserve these special MMIO regions in /proc/iomem.

Sample /proc/iomem:
    f8100000000-f81003fffff : PCI Bus 0000:80 I/O Ports 00000000-00000fff
    f8100400000-f81007fffff : PCI Bus 0000:8e I/O Ports 00001000-00001fff
    f8100800000-f8100ffffff : PCI Bus 0000:9c I/O Ports 00002000-00003fff
    f8101000000-f81017fffff : PCI Bus 0000:aa I/O Ports 00004000-00005fff

and corresponding /proc/ioports:
    00000000-00000fff : PCI Bus 0000:80
    00001000-00001fff : PCI Bus 0000:8e
    00002000-00003fff : PCI Bus 0000:9c
    00004000-00005fff : PCI Bus 0000:aa
Signed-off-by: NBjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: NTony Luck <tony.luck@intel.com>

Address space resources for ACPI devices have a producer/consumer
flag.  All devices "consume" the indicated address space.  If the
resource is marked as a "producer", the range is also passed on
to child devices.

We currently ignore this flag when setting up MMIO and I/O port
windows for PCI root bridges, so we could mistakenly interpret
a "consumed-only" range, like CSR space for the device itself,
as a window that is routed to children.
Signed-off-by: NBjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: NTony Luck <tony.luck@intel.com>

Move acpi_map_iosapics() from pci.c to acpi.c, since it doesn't
have anything to do with PCI.
Signed-off-by: NBjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: NTony Luck <tony.luck@intel.com>