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: Alan Jenkins <alan-jenkins@tuffmail.co.uk>
Reported-by: Andy Wettstein <ajw1980@gmail.com>
Signed-off-by: Ingo 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: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Ingo 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: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Ingo 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: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Ingo 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: Jeremy Fitzhardinge <jeremy@goop.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
* 'x86-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
x86: cpu_init(): fix memory leak when using CPU hotplug
x86: pda_init(): fix memory leak when using CPU hotplug
x86, xen: Use native_pte_flags instead of native_pte_val for .pte_flags
x86: move mtrr cpu cap setting early in early_init_xxxx
x86: delay early cpu initialization until cpuid is done
x86: use X86_FEATURE_NOPL in alternatives
x86: add NOPL as a synthetic CPU feature bit
x86: boot: stub out unimplemented CPU feature words
Exception stacks are allocated each time a CPU is set online.
But the allocated space is never freed. Thus with one CPU hotplug
offline/online cycle there is a memory leak of 24K (6 pages) for
a CPU.
Fix is to allocate exception stacks only once -- when the CPU is
set online for the first time.
Signed-off-by: Andreas Herrmann <andreas.herrmann3@amd.com>
Cc: akpm@linux-foundation.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
pda->irqstackptr is allocated whenever a CPU is set online.
But it is never freed. This results in a memory leak of 16K
for each CPU offline/online cycle.
Fix is to allocate pda->irqstackptr only once.
Signed-off-by: Andreas Herrmann <andreas.herrmann3@amd.com>
Cc: akpm@linux-foundation.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Krzysztof Helt found MTRR is not detected on k6-2
root cause:
we moved mtrr_bp_init() early for mtrr trimming,
and in early_detect we only read the CPU capability from cpuid,
so some cpu doesn't have that bit in cpuid.
So we need to add early_init_xxxx to preset those bit before mtrr_bp_init
for those earlier cpus.
this patch is for v2.6.27
Reported-by: Krzysztof Helt <krzysztof.h1@wp.pl>
Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Move early cpu initialization after cpu early get cap so the
early cpu initialization can fix up cpu caps.
Signed-off-by: Krzysztof Helt <krzysztof.h1@wp.pl>
Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
After fixing the u32 thinko I sill had occasional hickups on ATI chipsets
with small deltas. There seems to be a delay between writing the compare
register and the transffer to the internal register which triggers the
interrupt. Reading back the value makes sure, that it hit the internal
match register befor we compare against the counter value.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
We use the HPET only in 32bit mode because:
1) some HPETs are 32bit only
2) on i386 there is no way to read/write the HPET atomic 64bit wide
The HPET code unification done by the "moron of the year" did
not take into account that unsigned long is different on 32 and
64 bit.
This thinko results in a possible endless loop in the clockevents
code, when the return comparison fails due to the 64bit/332bit
unawareness.
unsigned long cnt = (u32) hpet_read() + delta can wrap over 32bit.
but the final compare will fail and return -ETIME causing endless
loops.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Use X86_FEATURE_NOPL to determine if it is safe to use P6 NOPs in
alternatives. Also, replace table and loop with simple if statement.
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
The long noops ("NOPL") are supposed to be detected by family >= 6.
Unfortunately, several non-Intel x86 implementations, both hardware
and software, don't obey this dictum. Instead, probe for NOPL
directly by executing a NOPL instruction and see if we get #UD.
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
The minimum reprogramming delta was hardcoded in HPET ticks,
which is stupid as it does not work with faster running HPETs.
The C1E idle patches made this prominent on AMD/RS690 chipsets,
where the HPET runs with 25MHz. Set it to 5us which seems to be
a reasonable value and fixes the problems on the bug reporters
machines. We have a further sanity check now in the clock events,
which increases the delta when it is not sufficient.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Luiz Fernando N. Capitulino <lcapitulino@mandriva.com.br>
Tested-by: Dmitry Nezhevenko <dion@inhex.net>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
When calibration against PIT fails, the warning that we print is misleading.
In a virtualized environment the VM may get descheduled while calibration
or, the check in PIT calibration may fail due to other virtualization
overheads.
The warning message explicitly assumes that calibration failed due to SMI's
which may not be the case. Change that to something proper.
Signed-off-by: Alok N Kataria <akataria@vmware.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Manually adding "io_delay=0xed" fixes system lockups in ioapic
mode on this machine.
System Information
Manufacturer: Hewlett-Packard
Product Name: Presario F700 (KA695EA#ABF)
Base Board Information
Manufacturer: Quanta
Product Name: 30D3
Reference:
https://bugzilla.redhat.com/show_bug.cgi?id=459546
Signed-off-by: Chuck Ebbert <cebbert@redhat.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
The TSC calibration function is still very complicated, but this makes
it at least a little bit less so by moving the PIT part out into a
helper function of its own.
Tested-by: Larry Finger <Larry.Finger@lwfinger.net>
Signed-of-by: Linus Torvalds <torvalds@linux-foundation.org>
Larry Finger reported at http://lkml.org/lkml/2008/9/1/90:
An ancient laptop of mine started throwing errors from b43legacy when
I started using 2.6.27 on it. This has been bisected to commit bfc0f59
"x86: merge tsc calibration".
The unification of the TSC code adopted mostly the 64bit code, which
prefers PMTIMER/HPET over the PIT calibration.
Larrys system has an AMD K6 CPU. Such systems are known to have
PMTIMER incarnations which run at double speed. This results in a
miscalibration of the TSC by factor 0.5. So the resulting calibrated
CPU/TSC speed is half of the real CPU speed, which means that the TSC
based delay loop will run half the time it should run. That might
explain why the b43legacy driver went berserk.
On the other hand we know about systems, where the PIT based
calibration results in random crap due to heavy SMI/SMM
disturbance. On those systems the PMTIMER/HPET based calibration logic
with SMI detection shows better results.
According to Alok also virtualized systems suffer from the PIT
calibration method.
The solution is to use a more wreckage aware aproach than the current
either/or decision.
1) reimplement the retry loop which was dropped from the 32bit code
during the merge. It repeats the calibration and selects the lowest
frequency value as this is probably the closest estimate to the real
frequency
2) Monitor the delta of the TSC values in the delay loop which waits
for the PIT counter to reach zero. If the maximum value is
significantly different from the minimum, then we have a pretty safe
indicator that the loop was disturbed by an SMI.
3) keep the pmtimer/hpet reference as a backup solution for systems
where the SMI disturbance is a permanent point of failure for PIT
based calibration
4) do the loop iteration for both methods, record the lowest value and
decide after all iterations finished.
5) Set a clear preference to PIT based calibration when the result
makes sense.
The implementation does the reference calibration based on
HPET/PMTIMER around the delay, which is necessary for the PIT anyway,
but keeps separate TSC values to ensure the "independency" of the
resulting calibration values.
Tested on various 32bit/64bit machines including Geode 266Mhz, AMD K6
(affected machine with a double speed pmtimer which I grabbed out of
the dump), Pentium class machines and AMD/Intel 64 bit boxen.
Bisected-by: Larry Finger <Larry.Finger@lwfinger.net>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Larry Finger <Larry.Finger@lwfinger.net>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Return the correct return value when the CPUID driver partially
completes a request (we should return the number of bytes actually
read or written, instead of the error code.)
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Return the correct return value when the MSR driver partially
completes a request (we should return the number of bytes actually
read or written, instead of the error code.)
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Propagate error (-ENXIO) from smp_call_function_single() in the CPUID
driver. This can happen when a CPU is unplugged while the CPUID
driver is open.
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Propagate error (-ENXIO) from smp_call_function_single(). These
errors can happen when a CPU is unplugged while the MSR driver is
open.
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
I noticed that my sched_clock() was slow on a number of machine, so I
started looking at cpufreq.
The below seems to fix the problem for me.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Impact: crash on non-TSC-equipped CPUs
Don't enable the TSC notifier if we *either*:
1. don't have a CPU, or
2. have a CPU with constant TSC.
In either of those cases, the notifier is either damaging (1) or useless(2).
From: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
During CPU hot-remove the sysfs directory created by
threshold_create_bank(), defined in
arch/x86/kernel/cpu/mcheck/mce_amd_64.c, has to be removed before
its parent directory, created by mce_create_device(), defined in
arch/x86/kernel/cpu/mcheck/mce_64.c . Moreover, when the CPU in
question is hotplugged again, obviously the latter has to be created
before the former. At present, the right ordering is not enforced,
because all of these operations are carried out by CPU hotplug
notifiers which are not appropriately ordered with respect to each
other. This leads to serious problems on systems with two or more
multicore AMD CPUs, among other things during suspend and hibernation.
Fix the problem by placing threshold bank CPU hotplug callbacks in
mce_cpu_callback(), so that they are invoked at the right places,
if defined. Additionally, use kobject_del() to remove the sysfs
directory associated with the kobject created by
kobject_create_and_add() in threshold_create_bank(), to prevent the
kernel from crashing during CPU hotplug operations on systems with
two or more multicore AMD CPUs.
This patch fixes bug #11337.
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Acked-by: Andi Kleen <andi@firstfloor.org>
Tested-by: Mark Langsdorf <mark.langsdorf@amd.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
* 'x86-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
x86: work around MTRR mask setting, v2
x86: fix section mismatch warning - uv_cpu_init
x86: fix VMI for early params
x86: fix two modpost warnings in mm/init_64.c
x86: fix 1:1 mapping init on 64-bit (memory hotplug case)
x86: work around MTRR mask setting
x86: PAT Update validate_pat_support for intel CPUs
devmem, x86: PAT Change /dev/mem mmap with O_SYNC to use UC_MINUS
x86: PAT proper tracking of set_memory_uc and friends
x86: fix BUG: unable to handle kernel paging request (numaq_tsc_disable)
x86: export pv_lock_ops non-GPL
x86, mmiotrace: silence section mismatch warning - leave_uniprocessor
x86: use WARN() in arch/x86/kernel
x86: use WARN() in arch/x86/mm/ioremap.c
werror: fix pci calgary
x86: fix oprofile + hibernation badness
x86, SGI UV: hardcode the TLB flush interrupt system vector
x86: fix Xorg startup/shutdown slowdown with PAT
x86: fix "kernel won't boot on a Cyrix MediaGXm (Geode)"
x86 iommu: remove unneeded parenthesis
improve the debug printout:
- make it actually display something
- print it only once
would be nice to have a WARN_ONCE() facility, to feed such things to
kerneloops.org.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
WARNING: vmlinux.o(.cpuinit.text+0x3cc4): Section mismatch in reference from the function uv_cpu_init() to the function .init.text:uv_system_init()
The function __cpuinit uv_cpu_init() references
a function __init uv_system_init().
If uv_system_init is only used by uv_cpu_init then
annotate uv_system_init with a matching annotation.
uv_system_init was ment to be called only once, so do it from codepath
(native_smp_prepare_cpus) which is called once, right before activation
of other cpus (smp_init).
Note: old code relied on uv_node_to_blade being initialized to 0,
but it'a not initialized from anywhere.
Signed-off-by: Marcin Slusarz <marcin.slusarz@gmail.com>
Acked-by: Jack Steiner <steiner@sgi.com>
Signed-off-by: Ingo 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: Alok N Kataria <akataria@vmware.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Joshua Hoblitt reported that only 3 GB of his 16 GB of RAM is
usable. Booting with mtrr_show showed us the BIOS-initialized
MTRR settings - which are all wrong.
So the root cause is that the BIOS has not set the mask correctly:
> [ 0.429971] MSR00000200: 00000000d0000000
> [ 0.433305] MSR00000201: 0000000ff0000800
> should be ==> [ 0.433305] MSR00000201: 0000003ff0000800
>
> [ 0.436638] MSR00000202: 00000000e0000000
> [ 0.439971] MSR00000203: 0000000fe0000800
> should be ==> [ 0.439971] MSR00000203: 0000003fe0000800
>
> [ 0.443304] MSR00000204: 0000000000000006
> [ 0.446637] MSR00000205: 0000000c00000800
> should be ==> [ 0.446637] MSR00000205: 0000003c00000800
>
> [ 0.449970] MSR00000206: 0000000400000006
> [ 0.453303] MSR00000207: 0000000fe0000800
> should be ==> [ 0.453303] MSR00000207: 0000003fe0000800
>
> [ 0.456636] MSR00000208: 0000000420000006
> [ 0.459970] MSR00000209: 0000000ff0000800
> should be ==> [ 0.459970] MSR00000209: 0000003ff0000800
So detect this borkage and add the prefix 111.
Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Cc: <stable@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Pentium III and Core Solo/Duo CPUs have an erratum
" Page with PAT set to WC while associated MTRR is UC may consolidate to UC "
which can result in WC setting in PAT to be ineffective. We will disable
PAT on such CPUs, so that we can continue to use MTRR WC setting.
Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This section mismatch:
>> Seems to be a section mismatch; init_intel() is __cpuinit while
>> numaq_tsc_disable() is __init. Seems to be introduced in:
>>
>> commit 64898a8bad
>> Author: Yinghai Lu <yhlu.kernel@gmail.com>
>> Date: Sat Jul 19 18:01:16 2008 -0700
>>
>> x86: extend and use x86_quirks to clean up NUMAQ code
>
> Oops, I am wrong about numaq_tsc_disable() being __init. Still, I
> believe that Yinghai might be able to say what's really wrong :-)
Would lead to this crash:
BUG: unable to handle kernel paging request at c08a45f0
IP: [<c08a45f0>] numaq_tsc_disable+0x0/0x40
Fixed by the patch below.
Signed-off-by: Vegard Nossum <vegardno@ifi.uio.no>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
None of the spinlock API is exported GPL, so there's no reason for
pv_lock_ops to be.
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Cc: drago01 <drago01@gmail.com>
Use WARN() instead of a printk+WARN_ON() pair; this way the message
becomes part of the warning section for better reporting/collection.
This also allowed the folding of some if()'s into the WARN()
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: akpm@linux-foundation.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Fix an integer comparison always false warning in the PCI Calgary 64 driver.
A u8 is being compared to something that's 512 by default, resulting in the
following warning:
arch/x86/kernel/pci-calgary_64.c:1285: warning: comparison is always false due to limited range of data type
This was introduced by patch b34e90b8f0.
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
The UV TLB shootdown mechanism needs a system interrupt vector.
Its vector had been hardcoded as 200, but needs to moved to the reserved
system vector range so that it does not collide with some device vector.
This is still temporary until dynamic system IRQ allocation is provided.
But it will be needed when real UV hardware becomes available and runs 2.6.27.
Signed-off-by: Cliff Wickman <cpw@sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Cyrix MediaGXm/Cx5530 Unicorn Revision 1.19.3B has stopped
booting starting at v2.6.22.
The reason is this commit:
> commit f25f64ed5b
> Author: Juergen Beisert <juergen@kreuzholzen.de>
> Date: Sun Jul 22 11:12:38 2007 +0200
>
> x86: Replace NSC/Cyrix specific chipset access macros by inlined functions.
this commit activated a macro which was dormant before due to (buggy)
macro side-effects.
I've looked through various datasheets and found that the GXm and GXLV
Geode processors don't have an incrementor.
Remove the incrementor setup entirely. As the incrementor value
differs according to clock speed and we would hope that the BIOS
configures it correctly, it is probably the right solution.
Cc: <stable@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This reverts commit 34ae7f35a2, which has
been reported to cause a number of problems. During suspend and resume,
it apparently causes a crash in a CPU hotplug notifier to happen,
although the exact details are sketchy because of the inability to get
good traces during the suspend sequence.
See buzilla entries
http://bugzilla.kernel.org/show_bug.cgi?id=11296http://bugzilla.kernel.org/show_bug.cgi?id=11339
for more examples and details.
[ Mark: "Revert the patch for now. I'm still looking into getting a
reliable reproduction and I do not have a fix at this time." ]
Requested-by: Rafael J. Wysocki <rjw@sisk.pl>
Acked-by: Mark Langsdorf <mark.langsdorf@amd.com>
Acked-by: Dave Jones <davej@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@inux-foundation.org>
The parenthesis in __iommu_queue_command() are not needed when assigning
into 'target' variable.
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
WARNING: vmlinux.o(.text+0x27032): Section mismatch in reference from the function get_tce_space_from_tar() to the function .init.text:calgary_bus_has_devices()
The function get_tce_space_from_tar() references
the function __init calgary_bus_has_devices().
This is often because get_tce_space_from_tar lacks a __init
annotation or the annotation of calgary_bus_has_devices is wrong.
get_tce_space_from_tar is called only from __init function (calgary_init)
and calls __init function (calgary_bus_has_devices).
So annotate it properly.
Signed-off-by: Marcin Slusarz <marcin.slusarz@gmail.com>
Cc: Chandru Siddalingappa <chandru@in.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Take out part of get_local_pda referencing __init function (free_bootmem)
to new (static) function marked as __ref. It's safe to do because free_bootmem
is called before __init sections are dropped.
WARNING: vmlinux.o(.cpuinit.text+0x3cd7): Section mismatch in reference from the function get_local_pda() to the function .init.text:free_bootmem()
The function __cpuinit get_local_pda() references
a function __init free_bootmem().
If free_bootmem is only used by get_local_pda then
annotate free_bootmem with a matching annotation.
Signed-off-by: Marcin Slusarz <marcin.slusarz@gmail.com>
Cc: Mike Travis <travis@sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
arch/x86/power/cpu_32.c __save_processor_state calls read_cr4()
only a i486 CPU doesn't have the CR4 register. Trying to read it
produces an invalid opcode oops during suspend to disk.
Use the safe rc4 reading op instead. If the value to be written is
zero the write is skipped.
arch/x86/power/hibernate_asm_32.S
done: swapped the use of %eax and %ecx to use jecxz for
the zero test and jump over store to %cr4.
restore_image: s/%ecx/%eax/ to be consistent with done:
In addition to __save_processor_state, acpi_save_state_mem,
efi_call_phys_prelog, and efi_call_phys_epilog had checks added
(acpi restore was in assembly and already had a check for
non-zero). There were other reads and writes of CR4, but MCE and
virtualization shouldn't be executed on a i486 anyway.
Signed-off-by: David Fries <david@fries.net>
Acked-by: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
