After updating several machines to 2.6.20, I can't boot  anymore the single
one of them that supports the NX bit and is configured as a 32-bit system.

My understanding is that the VDSO changes in 2.6.20-rc7 were not fully
cooked, in that with that config option enabled VDSO_SYM(x) now equals
x, meaning that an address in the fixmap area is now being passed to
apps via AT_SYSINFO. However, the page is mapped with PAGE_READONLY
rather than PAGE_READONLY_EXEC.

I'm not certain whether having app code go through the fixmap area is
intended, but in case it is here is the simple patch that makes things work
again.
Signed-off-by: NJan Beulich <jbeulich@novell.com>
Signed-off-by: NAndi Kleen <ak@suse.de>

[MTRR] fix 32-bit ioctls on x64_32
Signed-off-by: NGiuliano Procida <giuliano.procida@googlemail.com>
Signed-off-by: NAndi Kleen <ak@suse.de>

Trivial cleanup.

Only change is that it is always compiled in now on x86-64 like on i386.
Signed-off-by: NAndi Kleen <ak@suse.de>

Extern declarations belong in headers.  Times, they are a'changin.
Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>
Signed-off-by: NAndi Kleen <ak@suse.de>

===================================================================

When I implemented the DECLARE_PER_CPU(var) macros, I was careful that
people couldn't use "var" in a non-percpu context, by prepending
percpu__.  I never considered that this would allow them to overload
the same name for a per-cpu and a non-percpu variable.

It is only one of many horrors in the i386 boot code, but let's rename
the non-perpcu cpu_gdt_descr to early_gdt_descr (not boot_gdt_descr,
that's something else...)
Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>
Signed-off-by: NAndi Kleen <ak@suse.de>

===================================================================

Allows external actors to disable mce.
Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>
Signed-off-by: NAndi Kleen <ak@suse.de>

===================================================================

The current code simply calls "start_kernel" directly if we're under a
hypervisor and no paravirt_ops backend wants us, because paravirt.c
registers that as a backend.

This was always a vain hope; start_kernel won't get far without setup.
It's also impossible for paravirt_ops backends which don't sit in the
arch/i386/kernel directory: they can't link before paravirt.o anyway.

Keep it simple: if we pass all the registered paravirt probes, BUG().
Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>
Signed-off-by: NAndi Kleen <ak@suse.de>

> Which remembers me that I think that MIPS is using the non-compat version
> of sys_epoll_pwait for compat syscalls. But maybe MIPS doesn't need a compat
> syscall for some reason. Dunno.

Which reminds me that x86_64 i386 compat doesn't wire up sys_epoll_pwait ;-)
Signed-off-by: NRalf Baechle <ralf@linux-mips.org>
Signed-off-by: NAndi Kleen <ak@suse.de>

and in other strange binfmts. vDSO is not necessarily mapped there.
Signed-off-by: NAndi Kleen <ak@suse.de>

The old Cyrix 5520 CPU detection code relied upon the PCI layer setup being
done earlier than the CPU setup, which is no longer true.  Fortunately we
know that if the processor is a MediaGX we can do type 1 pci config
accesses to check the companion chip.  We thus do those directly and from
this find the 5520 and implement the workarounds for the timer problem

Original report from takada@mbf.nifty.com, I sent a proposed patch which
Takara then corrected, tested and sent back to the list on 10th January.

Submitting for merging as it seems to have been missed

AK: Changed to use pci-direct.h and fix warning for !CONFIG_PCI (later
AK: originally from akpm)
Signed-off-by: NAlan Cox <alan@redhat.com>
Signed-off-by: NAndi Kleen <ak@suse.de>
Cc: Andi Kleen <ak@suse.de>
Cc: <takada@mbf.nifty.com>
Cc: Jordan Crouse <jordan.crouse@amd.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>

Fix bogus warning

linux/arch/i386/kernel/cpu/transmeta.c:12: warning: ‘cpu_freq’ may be used uninitialized in this function
Signed-off-by: NAndi Kleen <ak@suse.de>

Fix bogus gcc warning

linux/arch/i386/kernel/microcode.c:387: warning: ‘new_mc’ may be used uninitialized in this function
Signed-off-by: NAndi Kleen <ak@suse.de>

For i386/x86-64.

Straight forward -- just reuse the Family 0xf code.
Signed-off-by: NAndi Kleen <ak@suse.de>

Just various new acronyms. The new popcnt bit is in the middle
of Intel space. This looks a little weird, but I've been assured
it's ok.

Also I fixed RDTSCP for i386 which was at the wrong place.

For i386 and x86-64.
Signed-off-by: NAndi Kleen <ak@suse.de>

Not needed because fastcall is always default now
Signed-off-by: NAndi Kleen <ak@suse.de>

gcc 5.0 will likely not have the constraint problem
Signed-off-by: NAndi Kleen <ak@suse.de>

Occasionally the kernel has bugs that result in no irq being found for a
given cpu vector.  If we acknowledge the irq the system has a good chance
of continuing even though we dropped an irq message.  If we continue to
simply print a message and not acknowledge the irq the system is likely to
become non-responsive shortly there after.

AK: Fixed compilation for UP kernels
Signed-off-by: NEric W. Biederman <ebiederm@xmission.com>
Signed-off-by: NAndi Kleen <ak@suse.de>
Cc: "Luigi Genoni" <luigi.genoni@pirelli.com>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>

Original code doesn't write back to CCR4 register.  This patch reflects a
value of a register.

Cc: Jordan Crouse <jordan.crouse@amd.com>
Acked-by: NAlan Cox <alan@lxorguk.ukuu.org.uk>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NAndi Kleen <ak@suse.de>

Sometimes developers need to see more object code in an oops report,
e.g. when kernel may be corrupted at runtime.

Add the "code_bytes" option for this.
Signed-off-by: NChuck Ebbert <cebbert@redhat.com>
Signed-off-by: NAndi Kleen <ak@suse.de>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>

If DEBUG_SIG is enbaled in source code, ia32_signal.c compiles with warning
due to wrong format string.  Attached patch fixes that.  It is quite minor
update, since by default DEBUG_SIG is not enabled and can not be turned on
without code modification.
Signed-off-by: NEvgeniy Polyakov <johnpol@2ka.mipt.ru>
Signed-off-by: NAndi Kleen <ak@suse.de>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>

I've seen my box paralyzed by an endless spew of

    rtc: lost some interrupts at 1024Hz.

messages on the serial console.  What seems to be happening is that
something real causes an interrupt to be lost and triggers the
message.  But then printing the message to the serial console (from
the hpet interrupt handler) takes more than 1/1024th of a second, and
then some more interrupts are lost, so the message triggers again....

Fix this by adding a printk_ratelimit() before printing the warning.
Signed-off-by: NRoland Dreier <rolandd@cisco.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NAndi Kleen <ak@suse.de>

On the Unisys ES7000/ONE system, we encountered a problem where performing
a kexec reboot or dump on any cell other than cell 0 causes the system
timer to stop working, resulting in a hang during timer calibration in the
new kernel.

We traced the problem to one line of code in disable_IO_APIC(), which needs
to restore the timer's IO-APIC configuration before rebooting.  The code is
currently using the 4-bit physical destination field, rather than using the
8-bit logical destination field, and it cuts off the upper 4 bits of the
timer's APIC ID.  If we change this to use the logical destination field,
the timer works and we can kexec on the upper cells.  This was tested on
two different cells (0 and 2) in an ES7000/ONE system.

For reference, the relevant Intel xAPIC spec is kept at
ftp://download.intel.com/design/chipsets/e8501/datashts/30962001.pdf,
specifically on page 334.
Signed-off-by: NBenjamin M Romer <benjamin.romer@unisys.com>
Signed-off-by: NAndi Kleen <ak@suse.de>
Cc: Andi Kleen <ak@suse.de>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Vivek Goyal <vgoyal@in.ibm.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>

Remove the unused kernel config option X86_XADD, which is unused in any
source or header file.
Signed-off-by: NRobert P. J. Day <rpjday@mindspring.com>
Signed-off-by: NAndi Kleen <ak@suse.de>
Cc: Andi Kleen <ak@muc.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>

Eliminate arch specific memory_present call x86_64 NUMA by utilizing
sparse_memory_present_with_active_regions.
Acked-by: NMel Gorman <mel@csn.ul.ie>
Signed-off-by: NBob Picco <bob.picco@hp.com>
Signed-off-by: NAndi Kleen <ak@suse.de>
Cc: Andi Kleen <ak@muc.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>

Annotate i386/kernel/entry.S with END/ENDPROC to assist disassemblers and
other analysis tools.
Signed-off-by: NJan Beulich <jbeulich@novell.com>
Signed-off-by: NAndi Kleen <ak@suse.de>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>

I hope to support "classic" MediaGXm in kernel.

The DIR1 register of MediaGXm( or Geode) shows the following values for
identify CPU.  For example, My MediaGXm shows 0x42.

We can read National Semiconductor's datasheet without any NDAs.
  http://www.national.com/pf/GX/GXLV.html

from datasheets:
DIR1
0x30 - 0x33 GXm rev. 1.0 - 2.3
0x34 - 0x4f GXm rev. 2.4 - 3.x
0x5x        GXm rev. 5.0 - 5.4
0x6x        GXLV
0x7x         (unknow)
0x8x	    Gx1

In nsc driver of X, accept 0x30 through 0x82. What will 0x7x mean?

Cc: Jordan Crouse <jordan.crouse@amd.com>
Cc: Andi Kleen <ak@suse.de>
Cc: Alan Cox <alan@lxorguk.ukuu.org.uk>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NAndi Kleen <ak@suse.de>

setcc() in math-emu is written as a gcc extension statement expression
macro that returns a value.  However, it's not used that way and it's not
needed like that, so just make it a inline function so that we
don't use an extension when it's not needed.
Signed-off-by: NRandy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: NAndi Kleen <ak@suse.de>
Cc: Andi Kleen <ak@suse.de>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Segher Boessenkool <segher@kernel.crashing.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>

All Transmeta CPUs ever produced have constant-rate TSCs.
Signed-off-by: NH. Peter Anvin <hpa@zytor.com>
Signed-off-by: NAndi Kleen <ak@suse.de>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>

During kernel bootup, a new T60 laptop (CoreDuo, 32-bit) hangs about
10%-20% of the time in acpi_init():

 Calling initcall 0xc055ce1a: topology_init+0x0/0x2f()
 Calling initcall 0xc055d75e: mtrr_init_finialize+0x0/0x2c()
 Calling initcall 0xc05664f3: param_sysfs_init+0x0/0x175()
 Calling initcall 0xc014cb65: pm_sysrq_init+0x0/0x17()
 Calling initcall 0xc0569f99: init_bio+0x0/0xf4()
 Calling initcall 0xc056b865: genhd_device_init+0x0/0x50()
 Calling initcall 0xc056c4bd: fbmem_init+0x0/0x87()
 Calling initcall 0xc056dd74: acpi_init+0x0/0x1ee()

It's a hard hang that not even an NMI could punch through!  Frustratingly,
adding printks or function tracing to the ACPI code made the hangs go away
...

After some time an additional detail emerged: disabling the NMI watchdog
made these occasional hangs go away.

So i spent the better part of today trying to debug this and trying out
various theories when i finally found the likely reason for the hang: if
acpi_ns_initialize_devices() executes an _INI AML method and an NMI
happens to hit that AML execution in the wrong moment, the machine would
hang.  (my theory is that this must be some sort of chipset setup method
doing stores to chipset mmio registers?)

Unfortunately given the characteristics of the hang it was sheer
impossible to figure out which of the numerous AML methods is impacted
by this problem.

As a workaround i wrote an interface to disable chipset-based NMIs while
executing _INI sections - and indeed this fixed the hang.  I did a
boot-loop of 100 separate reboots and none hung - while without the patch
it would hang every 5-10 attempts.  Out of caution i did not touch the
nmi_watchdog=2 case (it's not related to the chipset anyway and didnt
hang).

I implemented this for both x86_64 and i686, tested the i686 laptop both
with nmi_watchdog=1 [which triggered the hangs] and nmi_watchdog=2, and
tested an Athlon64 box with the 64-bit kernel as well. Everything builds
and works with the patch applied.
Signed-off-by: NIngo Molnar <mingo@elte.hu>
Signed-off-by: NAndi Kleen <ak@suse.de>
Cc: Andi Kleen <ak@suse.de>
Cc: Len Brown <lenb@kernel.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>

- set bad_dma_address explicitly to 0x0
- reserve 32 pages from bad_dma_address and up
- WARN_ON() a driver feeding us bad_dma_address

Thanks to Leo Duran <leo.duran@amd.com> for the suggestion.
Signed-off-by: NMuli Ben-Yehuda <muli@il.ibm.com>
Signed-off-by: NAndi Kleen <ak@suse.de>
Cc: Leo Duran <leo.duran@amd.com>
Cc: Job Mason <jdmason@kudzu.us>

x86-64 is missing these:
Signed-off-by: NJeff Garzik <jeff@garzik.org>
Signed-off-by: NAndi Kleen <ak@suse.de>

We trust the e820 table, so explicitely reserving ROMs shouldn't
be needed.
Signed-off-by: NAndi Kleen <ak@suse.de>

Should be harmless because there is normally no memory there, but
technically it was incorrect.

Pointed out by Leo Duran
Signed-off-by: NAndi Kleen <ak@suse.de>

Initialize FS and GS to __KERNEL_DS as well.  The actual value of them is not
important, but it is important to reload them in protected mode.  At this time,
they still retain the real mode values from initial boot.  VT disallows
execution of code under such conditions, which means hardware virtualization
can not be used to boot the kernel on Intel platforms, making the boot time
painfully slow.

This requires moving the GS load before the load of GS_BASE, so just move
all the segments loads there to keep them together in the code.
Signed-off-by: NZachary Amsden <zach@vmware.com>
Signed-off-by: NAndi Kleen <ak@suse.de>

The symbol is needed to manipulate page tables, and modules shouldn't
do that.

Leftover from 2.4, but no in tree module should need it now.
Signed-off-by: NAndi Kleen <ak@suse.de>

This means if an illegal value is set for the segment registers there
ptrace will error out now with an errno instead of silently ignoring
it.
Signed-off-by: NAndi Kleen <ak@suse.de>

Add failsafe mechanism to HPET/TSC clock calibration.
Signed-off-by: NJack Steiner <steiner@sgi.com>

Updated to include failsafe mechanism & additional community feedback.
Patch built on latest 2.6.20-rc4-mm1 tree.
Signed-off-by: NAndi Kleen <ak@suse.de>

mtrr: fix size_or_mask and size_and_mask

This fixes two bugs in /proc/mtrr interface:
o If physical address size crosses the 44 bit boundary
  size_or_mask is evaluated wrong.
o size_and_mask limits width of physical base
  address for an MTRR to be less than 44 bits.

TBD: later patch had one more change, but I think that was bogus.
TBD: need to double check
Signed-off-by: NAndreas Herrmann <andreas.herrmann3@amd.com>
Signed-off-by: NAndi Kleen <ak@suse.de>

Byte-to-byte identical /proc/apm here.
Signed-off-by: NAlexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: NAndi Kleen <ak@suse.de>

Old code was legal standard C, but apparently not sparse-C.
Signed-off-by: NJosef 'Jeff' Sipek <jsipek@cs.sunysb.edu>
Signed-off-by: NAndi Kleen <ak@suse.de>