fix non-APIC UP build:

 arch/x86/kernel/built-in.o: In function `setup_arch':
 : undefined reference to `pin_map_size'
 arch/x86/kernel/built-in.o: In function `setup_arch':
 : undefined reference to `first_free_entry'
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Signed-off-by: NYinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Portions of the ACPI code needs to know if a system is a UV system prior
to genapic initialization. This patch adds a call early_acpi_boot_init()
so that the apic type is discovered earlier.

V2 of the patch adding fixes from Yinghai Lu.
Much cleaner and smaller.
Signed-off-by: NJack Steiner <steiner@sgi.com>
Acked-by: NYinghai Lu <yinghai@kernel.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

The remappings in setup.c are all just ordinary memory, so use
early_memremap() rather than early_ioremap().
Signed-off-by: NJeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

DMI tables need a blank NULL tail.

fixes the crash on Ingo's test box.
Signed-off-by: NYinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

The bad_bios_dmi_table() quirk never triggered because we do DMI setup
too late. Move it a bit earlier.

Also change the CONFIG_X86_RESERVE_LOW_64K quirk to operate on the e820
table directly instead of messing with early reservations - this handles
overlaps (which do occur in this low range of RAM) more gracefully.
Signed-off-by: NIngo Molnar <mingo@elte.hu>

the exact timing of the corruption check isn't too important (it's once a
minute timer), use round_jiffies() to align it and avoid extra wakeups.
Signed-off-by: NArjan van de Ven <arjan@linux.intel.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

This bugzilla:

  http://bugzilla.kernel.org/show_bug.cgi?id=11237

Documents a wide range of systems where the BIOS utilizes the first
64K of physical memory during suspend/resume and other hardware events.

Currently we reserve this memory on all AMI and Phoenix BIOS systems.
Life is too short to hunt subtle memory corruption problems like this,
so we try to be robust by default.

Still, allow this to be overriden: allow users who want that first 64K
of memory to be available to the kernel disable the quirk, via
CONFIG_X86_RESERVE_LOW_64K=n.

Also, allow the early reservation to overlap with other
early reservations.
Signed-off-by: NIngo Molnar <mingo@elte.hu>

there's multiple reports about suspend/resume related low memory
corruption in this bugzilla:

  http://bugzilla.kernel.org/show_bug.cgi?id=11237

the common pattern is that the corruption is caused by the BIOS,
and that it affects some portion of the first 64K of physical RAM.

So add a DMI quirk

This will waste 64K RAM on 'good' systems too, but without knowing
the exact nature of this BIOS memory corruption this is the safest
approach.

This might as well solve a wide range of suspend/resume breakages
under Linux.
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Alan Jenkins and Andy Wettstein reported a suspend/resume memory
corruption bug and extensively documented it here:

   http://bugzilla.kernel.org/show_bug.cgi?id=11237

The bug is that the BIOS overwrites 1K of memory at 0xc000 physical,
without registering it in e820 as reserved or giving the kernel any
idea about this.

Detect AMI BIOSen and reserve that 1K.

We paint this bug around with a very broad brush (reserving that 1K on all
AMI BIOS systems), as the bug was extremely hard to find and needed several
weeks and lots of debugging and patching.

The bug was found via the CONFIG_X86_CHECK_BIOS_CORRUPTION=y debug feature,
if similar bugs are suspected then this feature can be enabled on other
systems as well to scan low memory for corrupted memory.
Reported-by: NAlan Jenkins <alan-jenkins@tuffmail.co.uk>
Reported-by: NAndy Wettstein <ajw1980@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Russ Anderson reported a boot crash with EFI and latest mainline:

 BIOS-e820: 00000000fffa0000 - 00000000fffac000 (reserved)
Pid: 0, comm: swapper Not tainted 2.6.27-rc5-00100-gec0c15af-dirty #5

Call Trace:
 [<ffffffff80849195>] early_idt_handler+0x55/0x69
 [<ffffffff80313e52>] __memcpy+0x12/0xa4
 [<ffffffff80859015>] efi_init+0xce/0x932
 [<ffffffff80869c83>] setup_early_serial8250_console+0x2d/0x36a
 [<ffffffff80238688>] __insert_resource+0x18/0xc8
 [<ffffffff8084f6de>] setup_arch+0x3a7/0x632
 [<ffffffff808499ed>] start_kernel+0x91/0x367
 [<ffffffff80849393>] x86_64_start_kernel+0xe3/0xe7
 [<ffffffff808492b0>] x86_64_start_kernel+0x0/0xe7

 RIP 0x10

Such a crash is possible if the CPU in this system is a 64-bit
processor which doesn't support NX (ie, old Intel P4 -based64-bit
processors).

Certainly, if we support such processors, then we should start with
_PAGE_NX initially clear in __supported_pte_flags, and then set it once
we've established that the processor does indeed support NX.  That will
prevent early_ioremap - or anything else - from trying to set it.

The simple fix is to simply call check_efer() earlier.
Reported-by: NRuss Anderson <rja@sgi.com>
Signed-off-by: NJeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Default the low memory corruption check to off, but make the default setting of
the memory_corruption_check kernel parameter a config parameter.
Signed-off-by: NJeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

The corruption check is enabled in Kconfig by default, but disabled at runtime.

This patch adds several kernel parameters to control the corruption
check's behaviour; these are documented in kernel-parameters.txt.
Signed-off-by: NJeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Perodically check for corruption in low phusical memory.  Don't bother
checking at fault time, since it won't show anything useful.
Signed-off-by: NHugh Dickins <hugh@veritas.com>
Signed-off-by: NJeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Some BIOSes have been observed to corrupt memory in the low 64k.  This
change:
 - Reserves all memory which does not have to be in that area, to
   prevent it from being used as general memory by the kernel.  Things
   like the SMP trampoline are still in the memory, however.
 - Clears the reserved memory so we can observe changes to it.
 - Adds a function check_for_bios_corruption() which checks and reports on
   memory becoming unexpectedly non-zero.  Currently it's called in the
   x86 fault handler, and the powermanagement debug output.
Signed-off-by: NJeremy Fitzhardinge <jeremy@goop.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

while fixing a different bug i moved the call to vmi_init before
early params could be parsed.

This broke the vmi specific commandline parameters.
Fix that, by moving vmi initialization after kernel has got a chance to
parse early parameters.
Signed-off-by: NAlok N Kataria <akataria@vmware.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Allow x86 to support a built-in kernel command line.  The built-in
command line can override the one provided by the boot loader, for
those cases where the boot loader is broken or it is difficult
to change the command line in the the boot loader.

H. Peter Anvin wrote:
> Ingo Molnar wrote:
>> Best would be to make it really apparent in the code that nothing
>> changes if this config option is not set. Preferably there should be
>> no extra code at all in that case.
>>
>
> I would like to see this:
[...Nested ifdefs...]

OK. This version changes absolutely nothing if CONFIG_CMDLINE_BOOL is not
set (the default).  Also, no space is appended even when CONFIG_CMDLINE_BOOL
is set, but the builtin string is empty.  This is less sloppy all the way
around, IMHO.

Note that I use the same option names as on other arches for
this feature.

[ mingo@elte.hu: build fix ]
Signed-off-by: NTim Bird <tim.bird@am.sony.com>
Cc: Matt Mackall <mpm@selenic.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

WARNING: vmlinux.o(.text+0xcd1f): Section mismatch in reference from the function find_and_reserve_crashkernel() to the function .init.text:find_e820_area()
The function find_and_reserve_crashkernel() references
the function __init find_e820_area().
This is often because find_and_reserve_crashkernel lacks a __init
annotation or the annotation of find_e820_area is wrong.

WARNING: vmlinux.o(.text+0xcd38): Section mismatch in reference from the function find_and_reserve_crashkernel() to the function .init.text:reserve_bootmem_generic()
The function find_and_reserve_crashkernel() references
the function __init reserve_bootmem_generic().
This is often because find_and_reserve_crashkernel lacks a __init
annotation or the annotation of reserve_bootmem_generic is wrong.

find_and_reserve_crashkernel is called from __init function (reserve_crashkernel)
and calls 2 __init functions (find_e820_area, reserve_bootmem_generic),
so mark it __init
Signed-off-by: NMarcin Slusarz <marcin.slusarz@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Jeff Chua reported that booting a !bigsmp kernel on a 16-way box
hangs silently.

this is a long-standing issue, smp start AP cpu could check the
apic id >=8 etc before trying to start it.

achieve this by moving the def_to_bigsmp check later and skip the
apicid id > 8

[ mingo@elte.hu: clean up the message that is printed. ]
Reported-by: N"Jeff Chua" <jeff.chua.linux@gmail.com>
Signed-off-by: NYinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

 arch/x86/kernel/setup.c   |    6 ------
 arch/x86/kernel/smpboot.c |   10 ++++++++++
 2 files changed, 10 insertions(+), 6 deletions(-)

The lowmem mapping table created by VMI need not depend on max_low_pfn
at all.  Instead we now create an extra large mapping which covers all
possible lowmem instead of the physical ram that is actually available.

This allows the vmi initialization to be done before max_low_pfn could
be computed. We also move the vmi_init code very early in the boot process
so that nobody accidentally breaks the fixmap dependancy.
Signed-off-by: NAlok N Kataria <akataria@vmware.com>
Acked-by: NZachary Amsden <zach@vmware.com>
Signed-off-by: NH. Peter Anvin <hpa@zytor.com>

Call early_cpu_init() at the same (early) point in setup_arch().
The x86_64 code was calling it relatively late, after when other arch
code need to do cpu-related setup which depends on it.
Signed-off-by: NJeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Cc: Mark McLoughlin <markmc@redhat.com>
Cc: Eduardo Habkost <ehabkost@redhat.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

beauty fix: /proc/cpuinfo will still show apic feature even if
we booted up with it disabled.
Signed-off-by: NYinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

so NUMAQ can use that to call numaq_pre_time_init()

This allows us to remove a NUMAQ special from arch/x86/kernel/setup.c.

(and paves the way to remove the NUMAQ subarch)
Signed-off-by: NYinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

introduce x86_quirks array of boot-time quirk methods.

No change in functionality intended.
Signed-off-by: NYinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

On a x86-64 machine (nothing special I could encounter) I had the problem that
crashkernel reservation with the usual "64M@16M" failed. While debugging that,
I encountered that dma32_reserve_bootmem() reserves a memory region which is in
that area.

Because dma32_reserve_bootmem() does not rely on a specific offset but
crashkernel does, it makes sense to move the dma32_reserve_bootmem()
reservation down a bit. I tested that patch and it works without problems. I
don't see any negative effects of that move, but maybe I oversaw something ...

While we strictly don't need that patch in 2.6.27 because we have the
automatic, dynamic offset detection, it makes sense to also include it here
because:

  - it's easier to get it in -stable then,
  - many people are still used to the 'crashkernel=...@16M' syntax,
  - not everybody may be using a reloatable kernel.
Signed-off-by: NBernhard Walle <bwalle@suse.de>
Cc: kexec@lists.infradead.org
Cc: vgoyal@redhat.com
Cc: akpm@linux-foundation.org
Cc: Bernhard Walle <bwalle@suse.de>
Cc: yhlu.kernel@gmail.com
Signed-off-by: NIngo Molnar <mingo@elte.hu>

x86: remove double includes in setup.c
Signed-off-by: NAlexander Beregalov <a.beregalov@gmail.com>
Cc: yhlu.kernel@gmail.com
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Signed-off-by: NEduardo Habkost <ehabkost@redhat.com>
Signed-off-by: NJeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Cc: Stephen Tweedie <sct@redhat.com>
Cc: Mark McLoughlin <markmc@redhat.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Call paravirt_pagetable_setup_{start,done}

These paravirt_ops functions were not being called on x86_64.
Signed-off-by: NEduardo Habkost <ehabkost@redhat.com>
Signed-off-by: NJeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Cc: Stephen Tweedie <sct@redhat.com>
Cc: Mark McLoughlin <markmc@redhat.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

got this on a test-system:

 calling  numaq_tsc_disable+0x0/0x39
 NUMAQ: disabling TSC
 initcall numaq_tsc_disable+0x0/0x39 returned 0 after 0 msecs

that's because we should not be using arch_initcall to call numaq_tsc_disable.

need to call it in setup_arch before time_init()/tsc_init()
and call it in init_intel() to make the cpu feature bits right.
Signed-off-by: NYinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

x2apic support.  Interrupt-remapping must be enabled before enabling x2apic,
this is needed to ensure that IO interrupts continue to work properly after the
cpu mode is changed to x2apic(which uses 32bit extended physical/cluster
apic id).

On systems where apicid's are > 255, BIOS can handover the control to OS in
x2apic mode. Or if the OS handover was in legacy xapic mode, check
if it is capable of x2apic mode. And if we succeed in enabling
Interrupt-remapping, then we can enable x2apic mode in the CPU.
Signed-off-by: NSuresh Siddha <suresh.b.siddha@intel.com>
Cc: akpm@linux-foundation.org
Cc: arjan@linux.intel.com
Cc: andi@firstfloor.org
Cc: ebiederm@xmission.com
Cc: jbarnes@virtuousgeek.org
Cc: steiner@sgi.com
Signed-off-by: NIngo Molnar <mingo@elte.hu>

gart.h has only GART-specific stuff. Only GART code needs it. Other
IOMMU stuff should include iommu.h instead of gart.h.
Signed-off-by: NFUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Acked-by: NMuli Ben-Yehuda <muli@il.ibm.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

when more than 4g memory is installed, don't map the big hole below 4g.
Signed-off-by: NYinghai Lu <yhlu.kernel@gmail.com>
Cc: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Add early quirks support.

In preparation of enabling the generic architecture to boot on a VISWS.

This will allow us to remove the VISWS subarch and all its complications.
Signed-off-by: NIngo Molnar <mingo@elte.hu>

When system have 4g less ram installed, and acpi table sit
near end of ram, make max_pfn cover them too,
so 64bit kernel don't need to mess up fixmap.
Signed-off-by: NYinghai Lu <yhlu.kernel@gmail.com>
Cc: "Suresh Siddha" <suresh.b.siddha@intel.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

seperate reserve_setup_data into e820_reserved_setup_data,
and reserve_early_setup_data.

So could use e820_reserved_setup_data to backup e820 with setup_data.
Signed-off-by: NYinghai Lu <yhlu.kernel@gmail.com>
Cc: Bernhard Walle <bwalle@suse.de>
Cc: Ying Huang <ying.huang@intel.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

call it right after we are done with MADT/mptable handling, instead of
doing that in setup_per_cpu_areas() later on...

this way for_possible_cpu() can be used early.
Signed-off-by: NYinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

when acpi=off, cpu_to_apicid is ready after get_smp_config
so need to move init_cpu_to_node after it.

otherwise, we will get wrong cpu->node mapping, and it will rely on
amd_detect_cmp() to correct it - but that is too late as
setup_per_cpu_data is already called before that so  we will get
per_cpu_data on the wrong node.
Signed-off-by: NYinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

move out e820_register_active_regions from non numa zones_sizes_init()
and remove numa version zones_sizes_init().

and let 32 bit call remove_all_active_ranges() in setup_arch() directly
like 64-bit
Signed-off-by: NYinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Signed-off-by: NYinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

This patch removes the need of the crashkernel=...@offset parameter to define
a fixed offset for crashkernel reservation. That feature can be used together
with a relocatable kernel where the kexec-tools relocate the kernel and
get the actual offset from /proc/iomem.

The use case is a kernel where the .text+.data+.bss is after 16M physical
memory (debug kernel with lockdep on x86_64 can cause that) which caused a
major pain in autoconfiguration in our distribution.

Also, that patch unifies crashdump architectures a bit since IA64 has
that semantics from the very beginning of the kdump port.
Signed-off-by: NBernhard Walle <bwalle@suse.de>
Cc: vgoyal@redhat.com
Cc: Bernhard Walle <bwalle@suse.de>
Cc: kexec@lists.infradead.org
Signed-off-by: NIngo Molnar <mingo@elte.hu>