Introduce a fast TSC-calibration method on sane hardware.
It only uses 17920 PIT timer ticks to calibrate the TSC, plus 256 ticks on
each side to make sure the TSC values were very close to the tick, so the
whole calibration takes 15ms. Yet, despite only takign 15ms,
we can actually give pretty stringent guarantees of accuracy:
- the code requires that we hit each 256-counter block at least 50 times,
so the TSC error is basically at *MOST* just a few PIT cycles off in
any direction. In practice, it's going to be about one microseconds
off (which is how long it takes to read the counter)
- so over 17920 PIT cycles, we can pretty much guarantee that the
calibration error is less than one half of a percent.
My testing bears this out: on my machine, the quick-calibration reports
2934.085kHz, while the slow one reports 2933.415.
Yes, the slower calibration is still more precise. For me, the slow
calibration is stable to within about one hundreth of a percent, so it's
(at a guess) roughly an order-and-a-half of magnitude more precise. The
longer you wait, the more precise you can be.
However, the nice thing about the fast TSC PIT synchronization is that
it's pretty much _guaranteed_ to give that 0.5% precision, and fail
gracefully (and very quickly) if it doesn't get it. And it really is
fairly simple (even if there's a lot of _details_ there, and I didn't get
all of those right ont he first try or even the second ;)
The patch says "110 insertions", but 63 of those new lines are actually
comments.
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
arch/x86/kernel/tsc.c | 111 ++++++++++++++++++++++++++++++++++++++++++++++++-
1 files changed, 110 insertions(+), 1 deletions(-)
Impact: aestetic
Capitalize function call interrupts consistently.
All other descriptions in /proc/interrupts are capitalized except
for "function call interrupts". Capitalize it too for consistency.
While that's technically a published ABI I think the risk of anyone
relying on that text to stay the same is negligible.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
The last changes made the calibration loop 250ms long which is far
too much. Try to do that more clever.
Experiments have shown that using a 10ms delay for the PIT based calibration
gives us a good enough value. If we have a reference (HPET/PMTIMER) and the
result of the PIT and the reference is close enough, then we can break out of
the calibration loop on a match right away and use the reference value.
Otherwise we just loop 3 times and decide then, which value to take.
One caveat is that for virtualized environments the PIT calibration often does
not work at all and I found out that 10us is a bit too short as well for the
reference to give a sane result. The solution here is to make the last loop
longer when the first two PIT calibrations failed.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
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>
Breaking lines due to some imaginary problem with a long line length is
often stupid and wrong, but never more so when it splits a string that
is printed out into multiple lines. This really ended up making it much
harder to find where some error strings were printed out, because a
simple 'grep' didn't work.
I'm sure there is tons more of this particular idiocy hiding in other
places, but this particular case hit me once more last week. So fix it.
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This reverts commit a2bd7274b4.
It wasn't really right to begin with (there's a better fix for the
problem with e820 reservations clashing with PCI BAR's pending), but it
also actually causes more regressions, so it should be reverted even
before the better fix is finalized.
Rafael reports that this commit broke AHCI detection, and thus causes
the kernel to not boot on his quad core test box.
Reported-and-bisected-by: Rafael J. Wysocki <rjw@sisk.pl>
Cc: Yinghai Lu <yhlu.kernel@gmail.com>
Cc: David Witbrodt <dawitbro@sbcglobal.net>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
From NHM processor onward, Intel processors can support hardware accelerated
CRC32c algorithm with the new CRC32 instruction in SSE 4.2 instruction set.
The patch detects the availability of the feature, and chooses the most proper
way to calculate CRC32c checksum.
Byte code instructions are used for compiler compatibility.
No MMX / XMM registers is involved in the implementation.
Signed-off-by: Austin Zhang <austin.zhang@intel.com>
Signed-off-by: Kent Liu <kent.liu@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Make poll_idle() behave more like the other idle methods.
Currently, poll_idle() returns immediately. The other
idle methods all wait indefinately for some condition
to come true before returning. poll_idle should emulate
these other methods and also wait for a return condition,
in this case, for need_resched() to become 'true'.
Without this delay the idle loop spends all of its time
in the outer loop that calls poll_idle. This outer loop,
these days, does real work, some of it under rcu locks.
That work should only be done when idle is entered and
when idle exits, not continuously while idle is spinning.
Signed-off-by: Joe Korty <joe.korty@ccur.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
acpi_mcfg_64bit_base_addr is used when CONFIG_PCI_MMCONFIG is enabled.
Signed-off-by: Hiroshi Shimamoto <h-shimamoto@ct.jp.nec.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Enable some option commonly used by testers in defconfig, including
some very common device drivers and network boot support. defconfig
is still not meant to be a kitchen-sink configuration.
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Remove an unnecessary level of abstraction in the msr-on-cpu library.
Although this duplicates some code, the duplicated code is less than
the additional code, and this way should be faster.
Additionally, change the order of the functions to make the regular
structure of this file more obvious.
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
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>
This fixes a regression that was indirectly caused by commit
1184dc2ffe ("x86: modify Kconfig to allow
up to 4096 cpus").
Allowing 4k CPU's is not practical at this time, because we still have a
number of places that have several 'cpumask_t's on the stack, and a
4k-bit cpumask is 512 bytes of stack-space for each such variable. This
literally caused functions like 'smp_call_function_mask' to have a 2.5kB
stack frame, and several functions to have 2kB stackframes.
With an 8kB stack total, smashing the stack was simply much too likely.
At least bugzilla entry
http://bugzilla.kernel.org/show_bug.cgi?id=11342
was due to this.
The earlier commit to not inline load_module() into sys_init_module()
fixed the particular symptoms of this that Alan Brunelle saw in that
bugzilla entry, but the huge stack waste by cpumask_t's was the more
direct cause.
Some day we'll have allocation helpers that allocate large CPU masks
dynamically, but in the meantime we simply cannot allow cpumasks this
large.
Cc: Alan D. Brunelle <Alan.Brunelle@hp.com>
Cc: Mike Travis <travis@sgi.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* 'x86-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
x86: add X86_FEATURE_XMM4_2 definitions
x86: fix cpufreq + sched_clock() regression
x86: fix HPET regression in 2.6.26 versus 2.6.25, check hpet against BAR, v3
x86: do not enable TSC notifier if we don't need it
x86 MCE: Fix CPU hotplug problem with multiple multicore AMD CPUs
x86: fix: make PCI ECS for AMD CPUs hotplug capable
x86: fix: do not run code in amd_bus.c on non-AMD CPUs
The shadow code assigns a pte directly in one place, which is nonatomic on
i386 can can cause random memory references. Fix by using an atomic setter.
Signed-off-by: Avi Kivity <avi@qumranet.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>
Triple-fault and keyboard reset may assert INIT instead of RESET; however
INIT is blocked when Intel VT is enabled. This leads to a partially reset
machine when invoking emergency_restart via sysrq-b: the processor is still
working but other parts of the system are dead.
Default to rebooting via ACPI, which correctly asserts RESET and reboots the
machine.
This is safe since we will fall back to keyboard reset and triple fault if
acpi is not enabled or if the reset is not successful.
Signed-off-by: Avi Kivity <avi@qumranet.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
David Witbrodt tracked down (and bisected) a hpet bootup hang on his
system to the following problem: a BIOS bug made the hpet device
visible as a generic PCI device. If e820 reserved entries happen to
be registered first in the resource tree [which v2.6.26 started doing],
then the PCI code will reallocate that device's BAR to some other
address - breaking timer IRQs and hanging the system.
( Normally hpet devices are hidden by the BIOS from the OS's PCI
discovery via chipset magic. Sometimes the hpet is not a PCI device
at all. )
Solve this fundamental fragility by making non-PCI platform drivers
insert resources into the resource tree even if it overlaps the e820
reserved entry, to keep the resource manager from updating the BAR.
Also do these checks for the ioapic and mmconfig addresses, and emit
a warning if this happens.
Bisected-by: David Witbrodt <dawitbro@sbcglobal.net>
Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Tested-by: David Witbrodt <dawitbro@sbcglobal.net>
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>
This patch lets the files using linux/version.h match the files that
#include it.
Signed-off-by: Adrian Bunk <bunk@kernel.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
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>
Jan Beulich wrote:
> Even worse - this would even try to access the MSR on non-AMD CPUs
> (currently probably prevented just by the fact that only AMD ones use
> family values of 0x10 or higher).
This patch adds cpu vendor check to the postcore_initcalls.
Reported-by: Jan Beulich <jbeulich@novell.com>
Signed-off-by: Robert Richter <robert.richter@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>
early_io{re,un}map() are __init and hence can't be called from __meminit
functions.
Signed-off-by: Jan Beulich <jbeulich@novell.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
While I don't have a hotplug capable system at hand, I think two issues need
fixing:
- pud_phys (in kernel_physical_ampping_init()) would remain uninitialized in
the after_bootmem case
- the locking done just around phys_pmd_{init,update}() would leave out pgd
updates, and it was needlessly covering code portions that do allocations
(perhaps using a more friendly gfp value in alloc_low_page() would then be
possible)
Signed-off-by: Jan Beulich <jbeulich@novell.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>
This patch changes the pfn args from 'u32' to 'unsigned long'
on alloc_p*() functions on paravirt_ops, and the corresponding
implementations for Xen and VMI. The prototypes for CONFIG_PARAVIRT=n
are already using unsigned long, so paravirt.h now matches the prototypes
on asm-x86/pgalloc.h.
It shouldn't result in any changes on generated code on 32-bit, with
or without CONFIG_PARAVIRT. On both cases, 'codiff -f' didn't show any
change after applying this patch.
On 64-bit, there are (expected) binary changes only when CONFIG_PARAVIRT
is enabled, as the patch is really supposed to change the size of the
pfn args.
[ v2: KVM_GUEST: use the right parameter type on kvm_release_pt() ]
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
Acked-by: Jeremy Fitzhardinge <jeremy@goop.org>
Acked-by: Zachary Amsden <zach@vmware.com>
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>
All kernel mappings like ioremap(), etc uses UC_MINUS as the type. /dev/mem
mappings with /dev/mem being opened with O_SYNC however was using UC,
resulting in a conflict with /dev/mem mmap failing. This seems to be
affecting some apps (one being flashrom) which are using O_SYNC and which were
working before.
Switch /dev/mem with O_SYNC also to UC_MINUS.
Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Big thinko in pat memtype tracking code. reserve_memtype should be called
with physical address and not virtual address.
Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: Suresh Siddha <suresh.b.siddha@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>
WARNING: vmlinux.o(.text+0x180af): Section mismatch in reference from the function leave_uniprocessor() to the function .cpuinit.text:cpu_up()
The function leave_uniprocessor() references
the function __cpuinit cpu_up().
This is often because leave_uniprocessor lacks a __cpuinit
annotation or the annotation of cpu_up is wrong.
leave_uniprocessor calls cpu_up only when CONFIG_HOTPLUG_CPU is set,
so it can be safely annotated as __ref
Signed-off-by: Marcin Slusarz <marcin.slusarz@gmail.com>
Cc: Pekka Paalanen <pq@iki.fi>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Pekka Paalanen <pq@iki.fi>
Booting kernel with vmalloc=[any size<=16m] will oops on my pc (i386/1G memory).
BUG_ON in arch/x86/mm/init_32.c triggered:
BUG_ON((unsigned long)high_memory > VMALLOC_START);
It's due to the vm area hole.
In include/asm-x86/pgtable_32.h:
#define VMALLOC_OFFSET (8 * 1024 * 1024)
#define VMALLOC_START (((unsigned long)high_memory + 2 * VMALLOC_OFFSET - 1) \
& ~(VMALLOC_OFFSET - 1))
There's several related point:
1. MAXMEM :
(-__PAGE_OFFSET - __VMALLOC_RESERVE).
The space after VMALLOC_END is included as well, I set it to
(VMALLOC_END - PAGE_OFFSET - __VMALLOC_RESERVE)
2. VMALLOC_OFFSET is not considered in __VMALLOC_RESERVE
fixed by adding VMALLOC_OFFSET to it.
3. VMALLOC_START :
(((unsigned long)high_memory + 2 * VMALLOC_OFFSET - 1) & ~(VMALLOC_OFFSET - 1))
So it's not always 8M, bigger than 8M possible.
I set it to ((unsigned long)high_memory + VMALLOC_OFFSET)
4. the VMALLOC_RESERVE is an unused macro, so remove it here.
Signed-off-by: Dave Young <hidave.darkstar@gmail.com>
Cc: akpm@linux-foundation.org
Cc: hidave.darkstar@gmail.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
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>
Use WARN() instead of a printk+WARN_ON() pair; this way the message
becomes part of the warning section for better reporting/collection.
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>
Vegard Nossum reported oprofile + hibernation problems:
> Now some warnings:
>
> ------------[ cut here ]------------
> WARNING: at /uio/arkimedes/s29/vegardno/git-working/linux-2.6/kernel/smp.c:328 s
> mp_call_function_mask+0x194/0x1a0()
The usual problem: the suspend function when interrupts are
already disabled calls smp_call_function which is not allowed with
interrupt off. But at this point all the other CPUs should be already
down anyways, so it should be enough to just drop that.
This patch should fix that problem at least by fixing cpu hotplug&
suspend support.
[ mingo@elte.hu: fixed 5 coding style errors. ]
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Tested-by: Vegard Nossum <vegard.nossum@gmail.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>
Use savesegment and loadsegment consistently in ia32 compat code.
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Rene Herman reported significant Xorg startup/shutdown slowdown due
to PAT. It turns out that the memtype list has thousands of entries.
Add cached_entry to list add routine, in order to speed up the
lookup for sequential reserve_memtype calls.
Reported-by: Rene Herman <rene.herman@keyaccess.nl>
Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.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>
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jbarnes/pci-2.6:
PCI: add acpi_find_root_bridge_handle
PCI: acpi_pcihp: run _OSC on a root bridge
x86/PCI: irq and pci_ids patch for Intel Ibex Peak PCHs
x86/PCI: allow scanning of 255 PCI busses
x86, pci: detect end_bus_number according to acpi/e820 reserved, v2
pci: debug extra pci bus resources
pci: debug extra pci resources range
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>
This recent patch
commit c3965bd151
Author: Paul Jackson <pj@sgi.com>
Date: Wed May 14 08:15:34 2008 -0700
x86 boot: proper use of ARRAY_SIZE instead of repeated E820MAX constant
caused these new warnings during a normal build:
In file included from linux-2.6/arch/x86/boot/memory.c:17:
linux-2.6/include/linux/log2.h: In function '__ilog2_u32':
linux-2.6/include/linux/log2.h:34: warning: implicit declaration of function 'fls'
linux-2.6/include/linux/log2.h: In function '__ilog2_u64':
linux-2.6/include/linux/log2.h:42: warning: implicit declaration of function 'fls64'
linux-2.6/include/linux/log2.h: In function '__roundup_pow_of_two ':
linux-2.6/include/linux/log2.h:63: warning: implicit declaration of function 'fls_long'
I tried to fix them in log2.h, but it's difficult because the real mode
environment is completely different from a normal kernel environment. Instead
define an own ARRAY_SIZE macro in boot.h, similar to the other private
macros there.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
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>
WARNING: vmlinux.o(.text+0x118f7): Section mismatch in reference from the function construct_ioapic_table() to the function .init.text:MP_bus_info()
The function construct_ioapic_table() references
the function __init MP_bus_info().
This is often because construct_ioapic_table lacks a __init
annotation or the annotation of MP_bus_info is wrong.
construct_ioapic_table is called only from construct_default_ISA_mptable which is __init
Signed-off-by: Marcin Slusarz <marcin.slusarz@gmail.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
WARNING: arch/x86/kernel/built-in.o(.cpuinit.text+0x1591): Section mismatch in reference from the function init_amd() to the function .init.text:check_enable_amd_mmconf_dmi()
The function __cpuinit init_amd() references
a function __init check_enable_amd_mmconf_dmi().
If check_enable_amd_mmconf_dmi is only used by init_amd then
annotate check_enable_amd_mmconf_dmi with a matching annotation.
check_enable_amd_mmconf_dmi is only called from init_amd which is __cpuinit
Signed-off-by: Marcin Slusarz <marcin.slusarz@gmail.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
WARNING: arch/x86/kernel/built-in.o(.cpuinit.text+0x1fe7): Section mismatch in reference from the function MP_processor_info() to the variable .init.data:x86_quirks
The function __cpuinit MP_processor_info() references
a variable __initdata x86_quirks.
If x86_quirks is only used by MP_processor_info then
annotate x86_quirks with a matching annotation.
MP_processor_info uses x86_quirks which is __init and is used only from
smp_read_mpc and construct_default_ISA_mptable which are __init
Signed-off-by: Marcin Slusarz <marcin.slusarz@gmail.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
WARNING: vmlinux.o(.text+0x7950): Section mismatch in reference from the function native_calibrate_tsc() to the function .init.text:tsc_read_refs()
The function native_calibrate_tsc() references
the function __init tsc_read_refs().
This is often because native_calibrate_tsc lacks a __init
annotation or the annotation of tsc_read_refs is wrong.
tsc_read_refs is called from native_calibrate_tsc which is not __init
and native_calibrate_tsc cannot be marked __init
Signed-off-by: Marcin Slusarz <marcin.slusarz@gmail.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This patch changes GART IOMMU to return a size aligned address wrt
dma_alloc_coherent, as DMA-mapping.txt defines:
The cpu return address and the DMA bus master address are both
guaranteed to be aligned to the smallest PAGE_SIZE order which
is greater than or equal to the requested size. This invariant
exists (for example) to guarantee that if you allocate a chunk
which is smaller than or equal to 64 kilobytes, the extent of the
buffer you receive will not cross a 64K boundary.
Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
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: (32 commits)
x86: add MAP_STACK mmap flag
x86: fix section mismatch warning - spp_getpage()
x86: change init_gdt to update the gdt via write_gdt, rather than a direct write.
x86-64: fix overlap of modules and fixmap areas
x86, geode-mfgpt: check IRQ before using MFGPT as clocksource
x86, acpi: cleanup, temp_stack is used only when CONFIG_SMP is set
x86: fix spin_is_contended()
x86, nmi: clean UP NMI watchdog failure message
x86, NMI: fix watchdog failure message
x86: fix /proc/meminfo DirectMap
x86: fix readb() et al compile error with gcc-3.2.3
arch/x86/Kconfig: clean up, experimental adjustement
x86: invalidate caches before going into suspend
x86, perfctr: don't use CCCR_OVF_PMI1 on Pentium 4Ds
x86, AMD IOMMU: initialize dma_ops after sysfs registration
x86m AMD IOMMU: cleanup: replace LOW_U32 macro with generic lower_32_bits
x86, AMD IOMMU: initialize device table properly
x86, AMD IOMMU: use status bit instead of memory write-back for completion wait
x86: silence mmconfig printk
x86, msr: fix NULL pointer deref due to msr_open on nonexistent CPUs
...
* 'release-2.6.27' of git://git.kernel.org/pub/scm/linux/kernel/git/ak/linux-acpi-2.6:
cpuidle: Make ladder governor honor latency requirements fully
cpuidle: Menu governor fix wrong usage of measured_us
cpuidle: Do not use poll_idle unless user asks for it
x86: Fix ioremap off by one BUG
If a kernel thread is preempted in single-cpu mode right after the NOP (nop
about to be turned into a lock prefix), then we CPU hotplug a CPU, and then the
thread is scheduled back again, a SMP-unsafe atomic operation will be used on
shared SMP variables, leading to corruption. No corruption would happen in the
reverse case : going from SMP to UP is ok because we split a bit instruction
into tiny pieces, which does not present this condition.
Changing the 0x90 (single-byte nop) currently used into a 0x3E DS segment
override prefix should fix this issue. Since the default of the atomic
instructions is to use the DS segment anyway, it should not affect the
behavior.
The exception to this are references that use ESP/RSP and EBP/RBP as
the base register (they will use the SS segment), however, in Linux
(a) DS == SS at all times, and (b) we do not distinguish between
segment violations reported as #SS as opposed to #GP, so there is no
need to disassemble the instruction to figure out the suitable segment.
This patch assumes that the 0x3E prefix will leave atomic operations as-is (thus
assuming they normally touch data in the DS segment). Since there seem to be no
obvious ill-use of other segment override prefixes for atomic operations, it
should be safe. It can be verified with a quick
grep -r LOCK_PREFIX include/asm-x86/
grep -A 1 -r LOCK_PREFIX arch/x86/
Taken from
This source :
AMD64 Architecture Programmer's Manual Volume 3: General-Purpose and System
Instructions
States
"Instructions that Reference a Non-Stack Segment—If an instruction encoding
references any base register other than rBP or rSP, or if an instruction
contains an immediate offset, the default segment is the data segment (DS).
These instructions can use the segment-override prefix to select one of the
non-default segments, as shown in Table 1-5."
Therefore, forcing the DS segment on the atomic operations, which already use
the DS segment, should not change.
This source :
http://wiki.osdev.org/X86_Instruction_Encoding
States
"In 64-bit the CS, SS, DS and ES segment overrides are ignored."
Confirmed by "AMD 64-Bit Technology" A.7
http://www.amd.com/us-en/assets/content_type/white_papers_and_tech_docs/x86-64_overview.pdf
"In 64-bit mode, the DS, ES, SS and CS segment-override prefixes have no effect.
These four prefixes are no longer treated as segment-override prefixes in the
context of multipleprefix rules. Instead, they are treated as null prefixes."
This patch applies to 2.6.27-rc2, but would also have to be applied to earlier
kernels (2.6.26, 2.6.25, ...).
Performance impact of the fix : tests done on "xaddq" and "xaddl" shows it
actually improves performances on Intel Xeon, AMD64, Pentium M. It does not
change the performance on Pentium II, Pentium 3 and Pentium 4.
Xeon E5405 2.0GHz :
NR_TESTS 10000000
test empty cycles : 162207948
test test 1-byte nop xadd cycles : 170755422
test test DS override prefix xadd cycles : 170000118 *
test test LOCK xadd cycles : 472012134
AMD64 2.0GHz :
NR_TESTS 10000000
test empty cycles : 146674549
test test 1-byte nop xadd cycles : 150273860
test test DS override prefix xadd cycles : 149982382 *
test test LOCK xadd cycles : 270000690
Pentium 4 3.0GHz
NR_TESTS 10000000
test empty cycles : 290001195
test test 1-byte nop xadd cycles : 310000560
test test DS override prefix xadd cycles : 310000575 *
test test LOCK xadd cycles : 1050103740
Pentium M 2.0GHz
NR_TESTS 10000000
test empty cycles : 180000523
test test 1-byte nop xadd cycles : 320000345
test test DS override prefix xadd cycles : 310000374 *
test test LOCK xadd cycles : 480000357
Pentium 3 550MHz
NR_TESTS 10000000
test empty cycles : 510000231
test test 1-byte nop xadd cycles : 620000128
test test DS override prefix xadd cycles : 620000110 *
test test LOCK xadd cycles : 800000088
Pentium II 350MHz
NR_TESTS 10000000
test empty cycles : 200833494
test test 1-byte nop xadd cycles : 340000130
test test DS override prefix xadd cycles : 340000126 *
test test LOCK xadd cycles : 530000078
Speed test modules can be found at
http://ltt.polymtl.ca/svn/trunk/tests/kernel/test-prefix-speed-32.chttp://ltt.polymtl.ca/svn/trunk/tests/kernel/test-prefix-speed.c
Macro-benchmarks
2.0GHz E5405 Core 2 dual Quad-Core Xeon
Summary
* replace smp lock prefixes with DS segment selector prefixes
no lock prefix (s) with lock prefix (s) Speedup
make -j1 kernel/ 33.94 +/- 0.07 34.91 +/- 0.27 2.8 %
hackbench 50 2.99 +/- 0.01 3.74 +/- 0.01 25.1 %
* replace smp lock prefixes with 0x90 nops
no lock prefix (s) with lock prefix (s) Speedup
make -j1 kernel/ 34.16 +/- 0.32 34.91 +/- 0.27 2.2 %
hackbench 50 3.00 +/- 0.01 3.74 +/- 0.01 24.7 %
Detail :
1 CPU, replace smp lock prefixes with DS segment selector prefixes
make -j1 kernel/
real 0m34.067s
user 0m30.630s
sys 0m2.980s
real 0m33.867s
user 0m30.582s
sys 0m3.024s
real 0m33.939s
user 0m30.738s
sys 0m2.876s
real 0m33.913s
user 0m30.806s
sys 0m2.808s
avg : 33.94s
std. dev. : 0.07s
hackbench 50
Time: 2.978
Time: 2.982
Time: 3.010
Time: 2.984
Time: 2.982
avg : 2.99
std. dev. : 0.01
1 CPU, noreplace-smp
make -j1 kernel/
real 0m35.326s
user 0m30.630s
sys 0m3.260s
real 0m34.325s
user 0m30.802s
sys 0m3.084s
real 0m35.568s
user 0m30.722s
sys 0m3.168s
real 0m34.435s
user 0m30.886s
sys 0m2.996s
avg.: 34.91s
std. dev. : 0.27s
hackbench 50
Time: 3.733
Time: 3.750
Time: 3.761
Time: 3.737
Time: 3.741
avg : 3.74
std. dev. : 0.01
1 CPU, replace smp lock prefixes with 0x90 nops
make -j1 kernel/
real 0m34.139s
user 0m30.782s
sys 0m2.820s
real 0m34.010s
user 0m30.630s
sys 0m2.976s
real 0m34.777s
user 0m30.658s
sys 0m2.916s
real 0m33.924s
user 0m30.634s
sys 0m2.924s
real 0m33.962s
user 0m30.774s
sys 0m2.800s
real 0m34.141s
user 0m30.770s
sys 0m2.828s
avg : 34.16
std. dev. : 0.32
hackbench 50
Time: 2.999
Time: 2.994
Time: 3.004
Time: 2.991
Time: 2.988
avg : 3.00
std. dev. : 0.01
I did more runs (20 runs of each) to compare the nop case to the DS
prefix case. Results in seconds. They actually does not seems to show a
significant difference.
NOP
34.155
33.955
34.012
35.299
35.679
34.141
33.995
35.016
34.254
33.957
33.957
34.008
35.013
34.494
33.893
34.295
34.314
34.854
33.991
34.132
DS
34.080
34.304
34.374
35.095
34.291
34.135
33.940
34.208
35.276
34.288
33.861
33.898
34.610
34.709
33.851
34.256
35.161
34.283
33.865
35.078
Used http://www.graphpad.com/quickcalcs/ttest1.cfm?Format=C to do the
T-test (yeah, I'm lazy) :
Group Group One (DS prefix) Group Two (nops)
Mean 34.37815 34.37070
SD 0.46108 0.51905
SEM 0.10310 0.11606
N 20 20
P value and statistical significance:
The two-tailed P value equals 0.9620
By conventional criteria, this difference is considered to be not statistically significant.
Confidence interval:
The mean of Group One minus Group Two equals 0.00745
95% confidence interval of this difference: From -0.30682 to 0.32172
Intermediate values used in calculations:
t = 0.0480
df = 38
standard error of difference = 0.155
So, unless these calculus are completely bogus, the difference between the nop
and the DS case seems not to be statistically significant.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Acked-by: H. Peter Anvin <hpa@zytor.com>
CC: Linus Torvalds <torvalds@linux-foundation.org>
CC: Jeremy Fitzhardinge <jeremy@goop.org>
CC: Roland McGrath <roland@redhat.com>
CC: Ingo Molnar <mingo@elte.hu>
Cc: Steven Rostedt <rostedt@goodmis.org>
CC: Steven Rostedt <srostedt@redhat.com>
CC: Thomas Gleixner <tglx@linutronix.de>
CC: Peter Zijlstra <peterz@infradead.org>
CC: Andrew Morton <akpm@linux-foundation.org>
CC: David Miller <davem@davemloft.net>
CC: Ulrich Drepper <drepper@redhat.com>
CC: Rusty Russell <rusty@rustcorp.com.au>
CC: Gregory Haskins <ghaskins@novell.com>
CC: Arnaldo Carvalho de Melo <acme@redhat.com>
CC: "Luis Claudio R. Goncalves" <lclaudio@uudg.org>
CC: Clark Williams <williams@redhat.com>
CC: Christoph Lameter <cl@linux-foundation.org>
CC: Andi Kleen <andi@firstfloor.org>
CC: Harvey Harrison <harvey.harrison@gmail.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
WARNING: vmlinux.o(.text+0x17a3e): Section mismatch in reference from the function set_pte_vaddr_pud() to the function .init.text:spp_getpage()
The function set_pte_vaddr_pud() references
the function __init spp_getpage().
This is often because set_pte_vaddr_pud lacks a __init
annotation or the annotation of spp_getpage is wrong.
spp_getpage is called from __init (__init_extra_mapping) and
non __init (set_pte_vaddr_pud) functions, so it can't be __init.
Unfortunately it calls alloc_bootmem_pages which is __init,
but does it only when bootmem allocator is available (after_bootmem == 0).
So annotate it accordingly.
Signed-off-by: Marcin Slusarz <marcin.slusarz@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Cc: H. Peter Anvin <hpa@zytor.com>
By writing directly, a memory access violation can occur whilst
hotplugging a CPU if the entry was previously marked read-only.
Signed-off-by: Alex Nixon <alex.nixon@citrix.com>
Cc: Jeremy Fitzhardinge <Jeremy.Fitzhardinge@citrix.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Jean Delvare's machine triggered this BUG
acpi_os_map_memory phys ffff0000 size 65535
------------[ cut here ]------------
kernel BUG at arch/x86/mm/pat.c:233!
with ACPI in the backtrace.
Adding some debugging output showed that ACPI calls
acpi_os_map_memory phys ffff0000 size 65535
And ioremap/PAT does this check in 32bit, so addr+size wraps and the BUG
in reserve_memtype() triggers incorrectly.
BUG_ON(start >= end); /* end is exclusive */
But reserve_memtype already uses u64:
int reserve_memtype(u64 start, u64 end,
so the 32bit truncation must happen in the caller. Presumably in ioremap
when it passes this information to reserve_memtype().
This patch does this computation in 64bit.
http://bugzilla.kernel.org/show_bug.cgi?id=11346
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Fix coding style of traps_64.c with improvements suggested by Ingo.
Signed-off-by: Gustavo F. Padovan <gustavo@las.ic.unicamp.br>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Ftrace depends on some processor state that we destroyed during kexec and
restored by restore_processor_state(). So save_processor_state() and
restore_processor_state() are moved into machine_kexec() and ftrace is
restored after restore_processor_state().
Signed-off-by: Huang Ying <ying.huang@intel.com>
Cc: Pavel Machek <pavel@ucw.cz>
Cc: "Rafael J. Wysocki" <rjw@sisk.pl>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Kexec/Kexec-jump require code size in control page is less than
PAGE_SIZE/2. This patch add link-time checking for this.
ASSERT() of ld link script is used as the link-time checking mechanism.
[akpm@linux-foundation.org: build fix]
Signed-off-by: Huang Ying <ying.huang@intel.com>
Cc: Pavel Machek <pavel@ucw.cz>
Cc: "Rafael J. Wysocki" <rjw@sisk.pl>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Acked-by: Vivek Goyal <vgoyal@redhat.com>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Rename KEXEC_CONTROL_CODE_SIZE to KEXEC_CONTROL_PAGE_SIZE, because control
page is used for not only code on some platform. For example in kexec
jump, it is used for data and stack too.
[akpm@linux-foundation.org: unbreak powerpc and arm, finish conversion]
Signed-off-by: Huang Ying <ying.huang@intel.com>
Cc: Pavel Machek <pavel@ucw.cz>
Cc: "Rafael J. Wysocki" <rjw@sisk.pl>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Russell King <rmk@arm.linux.org.uk>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Plus add a build time check so this doesn't go unnoticed again.
Signed-off-by: Jan Beulich <jbeulich@novell.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Adds a simple IRQ autodetection to the AMD Geode MFGPT driver, and more
importantly, adds some checks, if IRQs can actually be received on the
chosen line. This fixes cases where MFGPT is selected as clocksource
though not producing any ticks, so the kernel simply starves during
boot.
Signed-off-by: Jens Rottmann <JRottmann@LiPPERTEmbedded.de>
Cc: Andres Salomon <dilinger@debian.org>
Cc: linux-geode@bombadil.infradead.org
Cc: Jordan Crouse <jordan.crouse@amd.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
fix:
arch/x86/kernel/acpi/sleep.c:24: warning: 'temp_stack' defined but not used
[ Sven Wegener <sven.wegener@stealer.net>: fix build bug ]
Signed-off-by: Marcin Slusarz <marcin.slusarz@gmail.com>
Acked-by: Pavel Machek <pavel@suse.cz>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
prefill_possible_map() is defined inside CONFIG_HOTPLUG_CPU,
so the nesting CONFIG_HOTPLUG_CPU is just redundant.
Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>
Signed-off-by: Ingo 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: Tim Bird <tim.bird@am.sony.com>
Cc: Matt Mackall <mpm@selenic.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Do we actually want these DirectMap lines in the x86 /proc/meminfo?
I can see they're interesting to CPA developers and TLB optimizers,
but they don't fit its usual "where has all my memory gone?" usage.
If they are to stay, here are some fixes.
1. On x86_32 without PAE, they're not 2M but 4M pages: no need to
mess with the internal enum, but show the right name to users.
2. Many machines can never show anything but 0 for DirectMap1G,
so suppress that line unless direct_gbpages are really enabled.
3. The unit in /proc/meminfo is kB not number of pages: HugePages
messed that up, but they're an example to regret not to follow.
4. Once we use kB, it's easy to see that 1GB has gone missing (which
explains why CONFIG_CPA_DEBUG=y soon wraps DirectMap2M negative):
because head_64.S's level2_ident_pgt entries were not counted.
My fix is not ideal, but works for more and for less than 1G,
and avoids interfering with early bootup pagetable contortions.
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Cc: Andi Kleen <andi@firstfloor.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Adjust experimental tags in Kconfig, update config to notice that
i386/x86_64 is now single architecture.
Signed-off-by: Pavel Machek <pavel@suse.cz>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
When a CPU core is shut down, all of its caches need to be flushed
to prevent stale data from causing errors if the core is resumed.
Current Linux suspend code performs an assignment after the flush,
which can add dirty data back to the cache. On some AMD platforms,
additional speculative reads have caused crashes on resume because
of this dirty data.
Relocate the cache flush to be the very last thing done before
halting. Tie into an assembly line so the compile will not
reorder it. Add some documentation explaining what is going
on and why we're doing this.
Signed-off-by: Mark Langsdorf <mark.langsdorf@amd.com>
Acked-by: Mark Borden <mark.borden@amd.com>
Acked-by: Michael Hohmuth <michael.hohmuth@amd.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Currently, setup_p4_watchdog() use CCCR_OVF_PMI1 to enable the counter
overflow interrupts to the second logical core. But this bit doesn't work
on Pentium 4 Ds (model 4, stepping 4) and this patch avoids its use on
these processors. Tested on 4 different machines that have this
specific model with success.
Signed-off-by: Aristeu Rozanski <aris@redhat.com>
Cc: jvillalovos@redhat.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
If sysfs registration fails all memory used by IOMMU is freed. This
happens after dma_ops initialization and the functions will access the
freed memory then.
Fix this by initializing dma_ops after the sysfs registration.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This patch adds device table initializations which forbids memory accesses
for devices per default and disables all page faults.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
There's so much broken mmconfig hardware/bios'es out there,
that classing this as an error seems a little extreme.
Lower its priority to KERN_INFO so that it isn't so noisy
when booting with 'quiet'
Signed-off-by: Dave Jones <davej@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
msr_open tests for someone trying to open a device for a nonexistent CPU.
However, the function always returns 0, not ret like it should, hence
userspace can BUG the kernel trivially. This bug was introduced by the
cdev lock_kernel pushdown patch last May.
The BUG can be reproduced with these commands:
# mknod fubar c 202 8 <-- pick a number less than NR_CPUS that is not
the number of an online CPU
# cat fubar
Signed-off-by: Darrick J. Wong <djwong@us.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
AMD SB700 based systems with spread spectrum enabled use a SMM based
HPET emulation to provide proper frequency setting. The SMM code is
initialized with the first HPET register access and takes some time to
complete. During this time the config register reads 0xffffffff. We
check for max. 1000 loops whether the config register reads a non
0xffffffff value to make sure that HPET is up and running before we go
further. A counting loop is safe, as the HPET access takes thousands
of CPU cycles. On non SB700 based machines this check is only done
once and has no side effects.
Based on a quirk patch from: crane cai <crane.cai@amd.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
clear bits for cpu nr > 8.
This allows us to boot the full range of possible CPUs that the
supported APIC model will allow. Previously we'd hang or boot up
with less than 8 CPUs.
Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Tested-by: Jeff Chua <jeff.chua.linux@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
so we don't get warning on 32bit system with 64g RAM or more
Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
For some reason we had two parsers registered for maxcpus=. One in init/main.c
and another in arch/x86/smpboot.c. So I nuked the one in arch/x86.
Also 64-bit kernels used to handle maxcpus= as documented in
Documentation/cpu-hotplug.txt. CPUs with 'id > maxcpus' are initialized
but not booted. 32-bit version for some reason ignored them even though
all the infrastructure for booting them later is there.
In the current mainline both 64 and 32 bit versions are broken.
This patch restores the correct behaviour. I've tested x86_64 version on
4- and 8- way Core2 and 2-way Opteron based machines. Various config
combinations SMP, !SMP, CPU_HOTPLUG, !CPU_HOTPLUG.
Booted with maxcpus=1 and maxcpus=4, etc. Everything is working as expected.
So far we've received two reports from different people confirming that 32-bit
version also works fine, both on dual core laptops and 16way server machines.
[v2: This version fixes visws breakage pointed out by Ingo.]
Signed-off-by: Max Krasnyansky <maxk@qualcomm.com>
Cc: lizf@cn.fujitsu.com
Cc: jeff.chua.linux@gmail.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Clean up the code for crashes during SpeedStep probing on older
machines.
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Use WARN() instead of a printk+WARN_ON() pair; this way the message becomes
part of the warning section for better reporting/collection.
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Acked-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: akpm@linux-foundation.org
Cc: arjan@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
SGI UV will have MMCFG base addresses that are greater than 4GB (32 bits).
v2: Use CONFIG_RESOURCES_64BIT instead of CONFIG_X86_64.
v3: Create a flag, that is set by platform specific code,
to disable the > 4GB check.
Signed-off-by: John Keller <jpk@sgi.com>
Cc: jpk@sgi.com
Signed-off-by: Ingo 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: Marcin Slusarz <marcin.slusarz@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
WARNING: vmlinux.o(.text+0x14cf8): Section mismatch in reference from the function map_high() to the function .init.text:init_extra_mapping_uc()
The function map_high() references
the function __init init_extra_mapping_uc().
This is often because map_high lacks a __init
annotation or the annotation of init_extra_mapping_uc is wrong.
WARNING: vmlinux.o(.text+0x14d05): Section mismatch in reference from the function map_high() to the function .init.text:init_extra_mapping_wb()
The function map_high() references
the function __init init_extra_mapping_wb().
This is often because map_high lacks a __init
annotation or the annotation of init_extra_mapping_wb is wrong.
map_high is called only from __init functions (map_*_high)
and calls 2 __init_functions (init_extra_mapping_*)
Signed-off-by: Marcin Slusarz <marcin.slusarz@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
yesterday I tried to reactivate my old 486 box and wanted to install a
current Linux with latest kernel on it. But it turned out that the
latest kernel does not boot because the machine crashes early in the
setup code.
After some debugging it turned out that the problem is the query_ist()
function. If this interrupt with that function is called the machine
simply locks up. It looks like a BIOS bug. Looking for a workaround for
this problem I wrote the attached patch. It checks for the CPUID
instruction and if it is not implemented it does not call the speedstep
BIOS function. As far as I know speedstep should be available since some
Pentium earliest.
Alan Cox observed that it's available since the Pentium II, so cpuid
levels 4 and 5 can be excluded altogether.
H. Peter Anvin cleaned up the code some more:
> Right in concept, but I dislike the implementation (duplication of the
> CPU detect code we already have). Could you try this patch and see if
> it works for you?
which, with a small modification to fix a build error with it the
resulting kernel boots on my machine.
Signed-off-by: Joerg Roedel <joro@8bytes.org>
Signed-off-by: "H. Peter Anvin" <hpa@zytor.com>
Cc: <stable@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
* git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux-2.6-for-linus:
fix spinlock recursion in hvc_console
stop_machine: remove unused variable
modules: extend initcall_debug functionality to the module loader
export virtio_rng.h
lguest: use get_user_pages_fast() instead of get_user_pages()
mm: Make generic weak get_user_pages_fast and EXPORT_GPL it
lguest: don't set MAC address for guest unless specified
Out of line get_user_pages_fast fallback implementation, make it a weak
symbol, get rid of CONFIG_HAVE_GET_USER_PAGES_FAST.
Export the symbol to modules so lguest can use it.
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
* 'x86-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
x86: fix 2.6.27rc1 cannot boot more than 8CPUs
x86: make "apic" an early_param() on 32-bit, NULL check
EFI, x86: fix function prototype
x86, pci-calgary: fix function declaration
x86: work around gcc 3.4.x bug
x86: make "apic" an early_param() on 32-bit
x86, debug: tone down arch/x86/kernel/mpparse.c debugging printk
x86_64: restore the proper NR_IRQS define so larger systems work.
x86: Restore proper vector locking during cpu hotplug
x86: Fix broken VMI in 2.6.27-rc..
x86: fdiv bug detection fix
Fix an old off by one error in the legacy PCI bus check. 0xff
is a valid bus.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
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: "Jeff Chua" <jeff.chua.linux@gmail.com>
Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
arch/x86/kernel/setup.c | 6 ------
arch/x86/kernel/smpboot.c | 10 ++++++++++
2 files changed, 10 insertions(+), 6 deletions(-)
With CONFIG_X86_PC, I can set CONFIG_SPARSEMEM=y.
With CONFIG_X86_GENERICARCH, CONFIG_SPARSEMEM depends on CONFIG_NUMA.
I'm using the patch below to enable sparsemem instead of flatmem.
System booted and is running.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Comments in arch/x86/boot/compressed/head_32.S erroneously refer to the
real mode pointer as the second and the heap area as the third argument
to decompress_kernel(). In fact, these have been the first and second
argument, respectively, since v2.6.20.
This patch corrects the comments. It introduces no code changes.
Signed-off-by: Philipp Kohlbecher <xt28@gmx.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Cyrill Gorcunov observed:
> you turned it into early_param so now it's NULL injecting vulnerabled.
> Could you please add checking for NULL str param?
fix that.
Also, change the name of 'str' into 'arg', to make it more apparent
that this is an optional argument that can be NULL, not a string
parameter that is empty when unset.
Reported-by: Cyrill Gorcunov <gorcunov@gmail.com>
Signed-off-by: Rene Herman <rene.herman@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Fix function declaration:
linux-next-20080807/arch/x86/kernel/pci-calgary_64.c:1353:36: warning: non-ANSI function declaration of function 'get_tce_space_from_tar'
Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com>
Acked-by: Acked-by: Muli Ben-Yehuda <muli@il.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Simon Horman reported that gcc-3.4.x crashes when compiling
pgd_prepopulate_pmd() when PREALLOCATED_PMDS == 0 and CONFIG_DEBUG_INFO
is enabled.
Adding an extra check for PREALLOCATED_PMDS == 0 [which is compiled out
by gcc] seems to avoid the problem.
Reported-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Acked-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
On 32-bit, "apic" is a __setup() param meaning it is parsed rather
late in the game. Make it an early_param() for apic_printk() use
by arch/x86/kernel/mpparse.c.
On 64-bit, it already is an early_param().
Signed-off-by: Rene Herman <rene.herman@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
commit 11a62a0560 turns some formerly
nopped debugging printks in arch/x86/kernel/mppparse.c into regular
ones. The one at the top of smp_scan_config() in particular also
prints on !CONFIG_SMP/CONFIG_X86_LOCAL_APIC kernels and UP machines
without anything resembling MP tables which makes their lowly UP
owners wonder...
Turn the former Dprintk()s into apic_printk()s instead meaning that
their printing is dependent on passing the apic=verbose (or =debug)
command line param.
On 32-bit, "apic" is a __setup() param which isn't early enough
for this code and therefore needs a followup changing it into an
early_param(). On 64-bit, it already is.
Signed-off-by: Rene Herman <rene.herman@gmail.com>
Cc: Andrew Morton <akpm@osdl.org>
Cc: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This removes the EXPERIMENTAL restriction from CONFIG_HOTPLUG_CPU
on the x86 architecture.
Signed-off-by: Dimitri Sivanich <sivanich@sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
