commit ff097ddd4 (x86/PCI: MMCONFIG: manage pci_mmcfg_region as a
list, not a table) introduced a nasty memory corruption when
pci_mmcfg_list is empty.
pci_mmcfg_check_end_bus_number() dereferences pci_mmcfg_list.prev even
when the list is empty. The following write hits some variable near to
pci_mmcfg_list.
Further down a similar problem exists, where cfg->list.next is
dereferenced unconditionally and a comparison with some variable near
to pci_mmcfg_list happens.
Add a check for the last element into the for_each_entry() loop and
remove all the other crappy logic which is just a leftover of the old
array based code which was replaced by the list conversion.
Reported-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Bjorn Helgaas <bjorn.helgaas@hp.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: stable@kernel.org
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
The main benefit of using ACPI host bridge window information is that
we can do better resource allocation in systems with multiple host bridges,
e.g., http://bugzilla.kernel.org/show_bug.cgi?id=14183
Sometimes we need _CRS information even if we only have one host bridge,
e.g., https://bugs.launchpad.net/ubuntu/+source/linux/+bug/341681
Most of these systems are relatively new, so this patch turns on
"pci=use_crs" only on machines with a BIOS date of 2008 or newer.
Signed-off-by: Bjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Previously we used a table of size PCI_BUS_NUM_RESOURCES (16) for resources
forwarded to a bus by its upstream bridge. We've increased this size
several times when the table overflowed.
But there's no good limit on the number of resources because host bridges
and subtractive decode bridges can forward any number of ranges to their
secondary buses.
This patch reduces the table to only PCI_BRIDGE_RESOURCE_NUM (4) entries,
which corresponds to the number of windows a PCI-to-PCI (3) or CardBus (4)
bridge can positively decode. Any additional resources, e.g., PCI host
bridge windows or subtractively-decoded regions, are kept in a list.
I'd prefer a single list rather than this split table/list approach, but
that requires simultaneous changes to every architecture. This approach
only requires immediate changes where we set up (a) host bridges with more
than four windows and (b) subtractive-decode P2P bridges, and we can
incrementally change other architectures to use the list.
Signed-off-by: Bjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Now that we return the new resource start position, there is no
need to update "struct resource" inside the align function.
Therefore, mark the struct resource as const.
Cc: Bjorn Helgaas <bjorn.helgaas@hp.com>
Cc: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
As suggested by Linus, align functions should return the start
of a resource, not void. An update of "res->start" is no longer
necessary.
Cc: Bjorn Helgaas <bjorn.helgaas@hp.com>
Cc: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
The XQUAD stuff is part of the NUMAQ architecture, so move it there.
Signed-off-by: Brian Gerst <brgerst@gmail.com>
LKML-Reference: <1265380629-3212-2-git-send-email-brgerst@gmail.com>
Signed-off-by: H. 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: Jeff Garrett <jeff@jgarrett.org>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
* 'x86-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/x86/linux-2.6-tip:
x86, irq: Check move_in_progress before freeing the vector mapping
x86: copy_from_user() should not return -EFAULT
Revert "x86: Side-step lguest problem by only building cmpxchg8b_emu for pre-Pentium"
x86/pci: Intel ioh bus num reg accessing fix
x86: Fix size for ex trampoline with 32bit
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: Jens Axboe <jens.axboe@oracle.com>
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
LKML-Reference: <1261525263-13763-3-git-send-email-yinghai@kernel.org>
Signed-off-by: H. 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: Jiri 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: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
This allows us to use the BIOS SR-IOV allocations rather than assigning
our own later on.
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Jesse 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: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Bjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
No functional change; just tidy up printks and make them more consistent
with the rest of PCI.
Reviewed-by: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Bjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: Jesse 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: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Bjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: Jesse 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: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Bjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: Jesse 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: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Bjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: Jesse 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: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Bjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: Jesse 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: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Bjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: Jesse 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: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Bjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
No functional change, but simplifies a future patch to convert the table
to a list.
Reviewed-by: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Bjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
This only renames the struct pci_mmcfg_region members; no functional change.
Reviewed-by: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Bjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: Jesse 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: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Bjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
This factors out the common "bus << 20" expression used when computing the
MMCONFIG address.
Reviewed-by: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Bjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: Jesse 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: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Bjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: Jesse 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: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Bjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: Jesse 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: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Bjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: Jesse 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: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Bjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: Jesse 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: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Bjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: Jesse 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: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Jesse 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: Alex Chiang <achiang@hp.com>
Signed-off-by: Jesse 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: Bjorn Helgaas <bjorn.helgaas@hp.com>
Acked-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: Jesse 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=14337
Signed-off-by: Bjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: Jesse 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: Bjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: Jesse 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: Bjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Use the dev_printk-like "%04x:%02x" format for printing PCI bus numbers.
Signed-off-by: Bjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: Jesse 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/2009/10/13/441
Signed-off-by: Bjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: Jesse 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: Bjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: Jesse 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: Bjorn 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: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Jesse 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: Thomas Schlichter <thomas.schlichter@web.de>
Signed-off-by: Thomas Schlichter <thomas.schlichter@web.de>
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Acked-by: Eric Anholt <eric@anholt.net>
Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Jesse 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: Dave Jones <davej@redhat.com>
Signed-off-by: Jesse 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: Tejun Heo <tj@kernel.org>
Acked-by: David Miller <davem@davemloft.net>
Acked-by: Greg 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: Jesse 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: Yinghai Lu <yinghai.lu@sun.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
* mark struct vm_area_struct::vm_ops as const
* mark vm_ops in AGP code
But leave TTM code alone, something is fishy there with global vm_ops
being used.
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Linus Torvalds