Xiaohui Xin and some other folks at Intel have been looking into what's
behind the performance hit of paravirt_ops when running native.
It appears that the hit is entirely due to the paravirtualized
spinlocks introduced by:
| commit 8efcbab674
| Date: Mon Jul 7 12:07:51 2008 -0700
|
| paravirt: introduce a "lock-byte" spinlock implementation
The extra call/return in the spinlock path is somehow
causing an increase in the cycles/instruction of somewhere around 2-7%
(seems to vary quite a lot from test to test). The working theory is
that the CPU's pipeline is getting upset about the
call->call->locked-op->return->return, and seems to be failing to
speculate (though I haven't seen anything definitive about the precise
reasons). This doesn't entirely make sense, because the performance
hit is also visible on unlock and other operations which don't involve
locked instructions. But spinlock operations clearly swamp all the
other pvops operations, even though I can't imagine that they're
nearly as common (there's only a .05% increase in instructions
executed).
If I disable just the pv-spinlock calls, my tests show that pvops is
identical to non-pvops performance on native (my measurements show that
it is actually about .1% faster, but Xiaohui shows a .05% slowdown).
Summary of results, averaging 10 runs of the "mmperf" test, using a
no-pvops build as baseline:
nopv Pv-nospin Pv-spin
CPU cycles 100.00% 99.89% 102.18%
instructions 100.00% 100.10% 100.15%
CPI 100.00% 99.79% 102.03%
cache ref 100.00% 100.84% 100.28%
cache miss 100.00% 90.47% 88.56%
cache miss rate 100.00% 89.72% 88.31%
branches 100.00% 99.93% 100.04%
branch miss 100.00% 103.66% 107.72%
branch miss rt 100.00% 103.73% 107.67%
wallclock 100.00% 99.90% 102.20%
The clear effect here is that the 2% increase in CPI is
directly reflected in the final wallclock time.
(The other interesting effect is that the more ops are
out of line calls via pvops, the lower the cache access
and miss rates. Not too surprising, but it suggests that
the non-pvops kernel is over-inlined. On the flipside,
the branch misses go up correspondingly...)
So, what's the fix?
Paravirt patching turns all the pvops calls into direct calls, so
_spin_lock etc do end up having direct calls. For example, the compiler
generated code for paravirtualized _spin_lock is:
<_spin_lock+0>: mov %gs:0xb4c8,%rax
<_spin_lock+9>: incl 0xffffffffffffe044(%rax)
<_spin_lock+15>: callq *0xffffffff805a5b30
<_spin_lock+22>: retq
The indirect call will get patched to:
<_spin_lock+0>: mov %gs:0xb4c8,%rax
<_spin_lock+9>: incl 0xffffffffffffe044(%rax)
<_spin_lock+15>: callq <__ticket_spin_lock>
<_spin_lock+20>: nop; nop /* or whatever 2-byte nop */
<_spin_lock+22>: retq
One possibility is to inline _spin_lock, etc, when building an
optimised kernel (ie, when there's no spinlock/preempt
instrumentation/debugging enabled). That will remove the outer
call/return pair, returning the instruction stream to a single
call/return, which will presumably execute the same as the non-pvops
case. The downsides arel 1) it will replicate the
preempt_disable/enable code at eack lock/unlock callsite; this code is
fairly small, but not nothing; and 2) the spinlock definitions are
already a very heavily tangled mass of #ifdefs and other preprocessor
magic, and making any changes will be non-trivial.
The other obvious answer is to disable pv-spinlocks. Making them a
separate config option is fairly easy, and it would be trivial to
enable them only when Xen is enabled (as the only non-default user).
But it doesn't really address the common case of a distro build which
is going to have Xen support enabled, and leaves the open question of
whether the native performance cost of pv-spinlocks is worth the
performance improvement on a loaded Xen system (10% saving of overall
system CPU when guests block rather than spin). Still it is a
reasonable short-term workaround.
[ Impact: fix pvops performance regression when running native ]
Analysed-by: "Xin Xiaohui" <xiaohui.xin@intel.com>
Analysed-by: "Li Xin" <xin.li@intel.com>
Analysed-by: "Nakajima Jun" <jun.nakajima@intel.com>
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Acked-by: H. Peter Anvin <hpa@zytor.com>
Cc: Nick Piggin <npiggin@suse.de>
Cc: Xen-devel <xen-devel@lists.xensource.com>
LKML-Reference: <4A0B62F7.5030802@goop.org>
[ fixed the help text ]
Signed-off-by: Ingo Molnar <mingo@elte.hu>
mmu.c needs to #include module.h to prevent these warnings:
arch/x86/xen/mmu.c:239: warning: data definition has no type or storage class
arch/x86/xen/mmu.c:239: warning: type defaults to 'int' in declaration of 'EXPORT_SYMBOL_GPL'
arch/x86/xen/mmu.c:239: warning: parameter names (without types) in function declaration
[ Impact: cleanup ]
Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com>
Acked-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Use ®s->sp instead of regs for getting the top of stack in kernel mode.
(on x86-64, regs->sp always points the top of stack)
[ Impact: Oprofile decodes only stack for backtracing on i386 ]
Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com>
[ v2: rename the API to kernel_stack_pointer(), move variable inside ]
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: systemtap@sources.redhat.com
Cc: Harvey Harrison <harvey.harrison@gmail.com>
Cc: Jan Blunck <jblunck@suse.de>
Cc: Christoph Hellwig <hch@infradead.org>
LKML-Reference: <20090511210300.17332.67549.stgit@localhost.localdomain>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
- the byte operand constraints were wrong for 32-bit
- the to-op's input operands weren't properly parenthesized
[ Impact: fix possible miscompilation or build failure ]
Signed-off-by: Jan Beulich <jbeulich@novell.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
found one system where cpu address line is 44bits, mtrr printout
is not right:
[ 0.000000] MTRR variable ranges enabled:
[ 0.000000] 0 base 0 00000000 mask FF0 00000000 write-back
[ 0.000000] 1 base 10 00000000 mask FFF 80000000 write-back
[ 0.000000] 2 base 0 80000000 mask FFF 80000000 uncachable
[ 0.000000] 3 base 0 7F800000 mask FFF FF800000 uncachable
Li Zefan and Frederic pointed out the high_width could be -4 some how.
It turns out when phys_addr is 44bit, size_or_mask will be
ffffffff,00000000 so ffs(size_or_mask) will be 0.
Try to check low 32 bit, to get correct high_width.
Signed-off-by: Yinghai Lu <yinghai@kerne.org>
Also-analyzed-by: Frederic Weisbecker <fweisbec@gmail.com>
Also-analyzed-by: Li Zefan <lizf@cn.fujitsu.com>
Cc: Jeremy Fitzhardinge <jeremy@goop.org>
Cc: Zhaolei <zhaolei@cn.fujitsu.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Vegard Nossum <vegard.nossum@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
LKML-Reference: <4A026540.8060504@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Lockdep reports the warning below when Li tries to offline one cpu:
[ 110.835487] =================================
[ 110.835616] [ INFO: inconsistent lock state ]
[ 110.835688] 2.6.30-rc4-00336-g8c9ed89 #52
[ 110.835757] ---------------------------------
[ 110.835828] inconsistent {HARDIRQ-ON-W} -> {IN-HARDIRQ-W} usage.
[ 110.835908] swapper/0 [HC1[1]:SC0[0]:HE0:SE1] takes:
[ 110.835982] (cmci_discover_lock){?.+...}, at: [<ffffffff80236dc0>] cmci_clear+0x30/0x9b
cmci_clear() can be called via smp_call_function_single().
It is better to disable interrupt while holding cmci_discover_lock,
to turn it into an irq-safe lock - we can deadlock otherwise.
[ Impact: fix possible deadlock in the MCE code ]
Reported-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
LKML-Reference: <4A03ED38.8000700@jp.fujitsu.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Reported-by: Shaohua Li<shaohua.li@intel.com>
The Xen pagetables are no longer implicitly reserved as part of the other
i386_start_kernel reservations, so make sure we explicitly reserve them.
This prevents them from being released into the general kernel free page
pool and reused.
[ Impact: fix Xen guest crash ]
Also-Bisected-by: Bryan Donlan <bdonlan@gmail.com>
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Cc: Xen-devel <xen-devel@lists.xensource.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
LKML-Reference: <4A032EEC.30509@goop.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Tim Starling reported that crashdump will panic with kernel compiled
with CONFIG_KEXEC_JUMP due to null pointer deference in
machine_kexec_32.c: machine_kexec(), when deferencing
kexec_image. Refering to:
http://bugzilla.kernel.org/show_bug.cgi?id=13265
This patch fixes the BUG via replacing global variable reference:
kexec_image in machine_kexec() with local variable reference: image,
which is more appropriate, and will not be null.
Same BUG is in machine_kexec_64.c too, so fixed too in the same way.
[ Impact: fix crash on kexec ]
Reported-by: Tim Starling <tstarling@wikimedia.org>
Signed-off-by: Huang Ying <ying.huang@intel.com>
LKML-Reference: <1241751101.6259.85.camel@yhuang-dev.sh.intel.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
With the introduction of the .brk section, special care must be taken
that no unused page table entries remain if _brk_end and _end are
separated by a 2M page boundary. cleanup_highmap() runs very early and
hence cannot take care of that, hence potential entries needing to be
removed past _brk_end must be cleared once the brk allocator has done
its job.
[ Impact: avoids undesirable TLB aliases ]
Signed-off-by: Jan Beulich <jbeulich@novell.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
If the first non-reserved (sub-)range doesn't fit the size requested,
an endless loop will be entered. If a range returned from
find_e820_area_size() turns out insufficient in size, the range must
be skipped before calling the function again.
[ Impact: fixes boot hang on some platforms ]
Signed-off-by: Jan Beulich <jbeulich@novell.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
The mem= option will truncate the memory map at a specified address so
it's not possible to register nodes with memory beyond the e820 upper
bound.
unparse_node() is only called when then node had memory associated with
it, although with the mem= option it is no longer addressable.
[ Impact: fix boot hang on certain (large) systems ]
Reported-by: "Zhang, Yanmin" <yanmin_zhang@linux.intel.com>
Signed-off-by: David Rientjes <rientjes@google.com>
Acked-by: Jack Steiner <steiner@sgi.com>
LKML-Reference: <alpine.DEB.2.00.0905051248150.20021@chino.kir.corp.google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
* 'tracing-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
tracing: x86, mmiotrace: fix range test
tracing: fix ref count in splice pages
* 'x86-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
x86: show number of core_siblings instead of thread_siblings in /proc/cpuinfo
amd-iommu: fix iommu flag masks
x86: initialize io_bitmap_base on 32bit
x86: gettimeofday() vDSO: fix segfault when tv == NULL
Commit 7ad728f981
(cpumask: x86: convert cpu_sibling_map/cpu_core_map to cpumask_var_t)
changed the output of /proc/cpuinfo for siblings:
Example on an AMD Phenom:
physical id : 0
siblings : 1
core id : 3
cpu cores : 4
Before that commit it was:
physical id : 0
siblings : 4
core id : 3
cpu cores : 4
Instead of cpu_core_mask it now uses cpu_sibling_mask to count siblings.
This is due to the following hunk of above commit:
| --- a/arch/x86/kernel/cpu/proc.c
| +++ b/arch/x86/kernel/cpu/proc.c
| @@ -14,7 +14,7 @@ static void show_cpuinfo_core(struct seq_file *m, struct cpuinf
| if (c->x86_max_cores * smp_num_siblings > 1) {
| seq_printf(m, "physical id\t: %d\n", c->phys_proc_id);
| seq_printf(m, "siblings\t: %d\n",
| - cpus_weight(per_cpu(cpu_core_map, cpu)));
| + cpumask_weight(cpu_sibling_mask(cpu)));
| seq_printf(m, "core id\t\t: %d\n", c->cpu_core_id);
| seq_printf(m, "cpu cores\t: %d\n", c->booted_cores);
| seq_printf(m, "apicid\t\t: %d\n", c->apicid);
This was a mistake, because the impact line shows that this side-effect
was not anticipated:
Impact: reduce per-cpu size for CONFIG_CPUMASK_OFFSTACK=y
So revert the respective hunk to restore the old behavior.
[ Impact: fix sibling-info regression in /proc/cpuinfo ]
Signed-off-by: Andreas Herrmann <andreas.herrmann3@amd.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
LKML-Reference: <20090504182859.GA29045@alberich.amd.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
The feature bits should be set via bitmasks, not via feature IDs.
[ Impact: fix feature enabling in newer IOMMU versions ]
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
LKML-Reference: <20090504102028.GA30307@amd.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
* 'x86-mce-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/x86/linux-2.6-tip:
x86, mce: fix boot logging logic
x86, mce: make polling timer interval per CPU
commit db949bba3c (x86-32: use non-lazy
io bitmap context switching) broke ioperm for 32bit because it removed
the lazy initialization of io_bitmap_base and did not set it to the
real bitmap offset.
[ Impact: fix non-working sys_ioperm() on 32-bit kernels ]
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
According to the gettimeofday(2) manual:
If either tv or tz is NULL, the corresponding structure is not
set or returned.
Since it is legal to give NULL as the tv argument, the code should make
sure tv is not NULL before trying to dereference it.
This issue manifests itself on x86_64 when vdso=0 is not on the kernel
command-line and libc uses the vDSO for gettimeofday() (e.g. glibc >=
2.7). A simple reproducer:
#include <stdio.h>
#include <sys/time.h>
int main(void)
{
struct timezone tz;
gettimeofday(NULL, &tz);
return 0;
}
See http://bugs.debian.org/466491 for more details.
[ Impact: fix gettimeofday(NULL, &tz) segfault ]
Signed-off-by: John Wright <john.wright@hp.com>
Cc: Andi Kleen <ak@suse.de>
Cc: John Wright <john.wright@hp.com>
LKML-Reference: <1241037121-14805-1-git-send-email-john.wright@hp.com>
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: only save/restore existent registers in the PCIe capability
x86/PCI: don't bother with root quirks if _CRS is used
docbooks: add/fix PCI kernel-doc
PCI: cleanup debug output resources
x86/PCI: set_pci_bus_resources_arch_default cleanups
x86/PCI: Move set_pci_bus_resources_arch_default into arch/x86
x86/PCI: don't call e820_all_mapped with -1 in the mmconfig case
PCI quirk: disable MSI on VIA VT3364 chipsets
* 'x86-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
x86, hpet: Stop soliciting hpet=force users on ICH4M
x86: check boundary in setup_node_bootmem()
uv_time: add parameter to uv_read_rtc()
x86: hpet: fix periodic mode programming on AMD 81xx
x86: more than 8 32-bit CPUs requires X86_BIGSMP
x86: avoid theoretical spurious NMI backtraces with CONFIG_CPUMASK_OFFSTACK=y
x86: fix boot crash in NMI watchdog with CONFIG_CPUMASK_OFFSTACK=y and flat APIC
x86-64: fix FPU corruption with signals and preemption
x86/uv: fix for no memory at paddr 0
docs, x86: add nox2apic back to kernel-parameters.txt
x86: mm/numa_32.c calculate_numa_remap_pages should use __init
x86, kbuild: make "make install" not depend on vmlinux
x86/uv: fix init of cpu-less nodes
x86/uv: fix init of memory-less nodes
* 'irq-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
x86/irq: mark NUMA_MIGRATE_IRQ_DESC broken
x86, irq: Remove IRQ_DISABLED check in process context IRQ move
* 'release' of git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux-acpi-2.6: (34 commits)
ACPI, i915: Register ACPI video even when not modesetting
Revert "ACPICA: delete check for AML access to port 0x81-83"
I/O port protection: update for windows compatibility.
sony-laptop: always try to unblock rfkill on load
sony-laptop: fix bogus error message display on resume
ACPI: EC: Fix ACPI EC resume non-query interrupt message
sony-laptop: SNC input event 38 fix
sony-laptop: SNC 127 Initialization Fix
sony-laptop: Duplicate SNC 127 Event Fix
ACPI: prevent processor.max_cstate=0 boot crash
ACPI/hpet: prevent boot hang when hpet=force used on ICH-4M
ACPI: delete obsolete "bus master activity" proc field
ACPI: idle: mark_tsc_unstable() at init-time, not run-time
ACPI: add /sys/firmware/acpi/interrupts/sci_not counter
ACPI video: fix an error when the brightness levels on AC and on Battery are same
acpi-cpufreq: Do not let get_measured perf depend on internal variable
acpi-cpufreq: style-only: add parens to math expression
acpi-cpufreq: Cleanup: Use printk_once
x86, acpi_cpufreq: Fix the NULL pointer dereference in get_measured_perf
thinkpad-acpi: bump up version to 0.23
...
The HPET in the ICH4M is not documented in the data sheet
because it was not officially validated.
While it is fine for hackers to continue to use "hpet=force"
to enable the hardware that they have, it is not prudent to
solicit additional "hpet=force" users on this hardware.
[ Impact: remove hpet=force syslog message on old-ICH systems ]
Signed-off-by: Len Brown <len.brown@intel.com>
Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
LKML-Reference: <alpine.LFD.2.00.0904231918510.15843@localhost.localdomain>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Commit dc09855 ("x86/uv: fix init of memory-less nodes") causes a
two sockets system (where node-1 doesn't have RAM installed) to crash.
That commit makes node_possible include cpu nodes that do not have memory.
So check boundary in setup_node_bootmem().
[ Impact: fix boot crash on RAM-less NUMA node system ]
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Cc: Jack Steiner <steiner@sgi.com>
LKML-Reference: <49EF89DF.9090404@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
It will be overwriten later if _CRS is used, so don't bother to set it.
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Rename set_pci_bus_resources_arch_default to x86_pci_root_bus_res_quirks, move
the weak version from common.c to i386.c, and before calling, make sure it's a
root bus.
Reviewed-by: Matthew Wilcox <willy@linux.intel.com>
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Commit 30a18d6c3f introduced a new
function to set the PCI bus resources. Unfortunately, neither the
author, nor the committers seemed to know that we already have somewhere
to do that -- pcibios_fixup_bus(). This patch moves the hook (used only
by the K8 code) into x86-specific code where it should have been in the
first place.
Cc: Yinghai Lu <yinghai.lu@sun.com>
Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
Acked-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
The earlier patch to change the poller to a separate function subtly
broke the boot logging logic. This could lead to machine checks
getting logged at boot even when disabled or defaulting to off
on some systems. Fix that.
[ Impact: bug fix - avoid spurious MCE in log ]
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Reviewed-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
The polling timer while running per CPU still uses a global next_interval
variable, which lead to some CPUs either polling too fast or too slow.
This was not a serious problem because all errors get picked up eventually,
but it's still better to avoid it. Turn next_interval into a per cpu variable.
v2: Fix check_interval == 0 case (Hidetoshi Seto)
[ Impact: minor bug fix ]
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Reviewed-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
uv_read_rtc() is referenced by read member of struct clocksource clocksource_uv.
In include/linux/clocksource.h, read of struct clocksource is declared as:
cycle_t (*read)(struct clocksource *cs)
This got introduced recently in:
8e19608: clocksource: pass clocksource to read() callback
But arch/x86/kernel/uv_time.c was not properly converted by that pach.
This patch adds a dummy parameter (struct clocksource type) to uv_read_rtc() to
fix the incompatible reference in clocksource_uv, and add a NULL parameter in
all places where uv_read_rtc() gets called.
[ Impact: cleanup, address compiler warning ]
Signed-off-by: Coly Li <coly.li@suse.de>
Cc: Dimitri Sivanich <sivanich@sgi.com>
Cc: Magnus Damm <damm@igel.co.jp>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Hugh Dickins <hugh@veritas.com>
LKML-Reference: <49EF3614.1050806@suse.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Cc: Dimitri Sivanich <sivanich@sgi.com>
(See http://bugzilla.kernel.org/show_bug.cgi?id=12961)
It partially reverts commit c23e253e67
(x86: hpet: stop HPET_COUNTER when programming periodic mode)
HPET on AMD 81xx chipset needs a second write (with HPET_TN_SETVAL
cleared) to T0_CMP register to set the period in periodic mode.
With this patch HPET_COUNTER is still stopped but not reset when HPET
is programmed in periodic mode. This should help to avoid races when
HPET is programmed in periodic mode and fixes a boot time hang that
I've observed on a machine when using 1000HZ.
[ Impact: fix boot time hang on machines with AMD 81xx chipset ]
Reported-by: Jeff Mahoney <jeffm@suse.com>
Signed-off-by: Andreas Herrmann <andreas.herrmann3@amd.com>
Tested-by: Jeff Mahoney <jeffm@suse.com>
LKML-Reference: <20090421180037.GA2763@alberich.amd.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Properly unregister cpufreq notifier on onload if it was registered
during init.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
Not releasing the time_page causes a leak of that page or the compound
page it is situated in.
Cc: stable@kernel.org
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
In non-SMP mode, the variable section attribute specified by DECLARE_PER_CPU()
does not agree with that specified by DEFINE_PER_CPU(). This means that
architectures that have a small data section references relative to a base
register may throw up linkage errors due to too great a displacement between
where the base register points and the per-CPU variable.
On FRV, the .h declaration says that the variable is in the .sdata section, but
the .c definition says it's actually in the .data section. The linker throws
up the following errors:
kernel/built-in.o: In function `release_task':
kernel/exit.c:78: relocation truncated to fit: R_FRV_GPREL12 against symbol `per_cpu__process_counts' defined in .data section in kernel/built-in.o
kernel/exit.c:78: relocation truncated to fit: R_FRV_GPREL12 against symbol `per_cpu__process_counts' defined in .data section in kernel/built-in.o
To fix this, DECLARE_PER_CPU() should simply apply the same section attribute
as does DEFINE_PER_CPU(). However, this is made slightly more complex by
virtue of the fact that there are several variants on DEFINE, so these need to
be matched by variants on DECLARE.
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
$ cat x86-more-than-8-cpus-requires-bigsmp.patch
Enforce NR_CPUS <= 8 limitation if X86_BIGSMP not set
Configuring more than 8 logical CPUs on 32-bit x86 requires
X86_BIGSMP to be set in order to boot successfully, if more than 8
logical CPUs are actually found at boot time. The X86_BIGSMP help
text describes that it is required to be set if more than 8 CPUs
are configured, but this was previously not enforced.
This configuration error has affected multiple distributions:
https://bugzilla.redhat.com/show_bug.cgi?id=480844https://issues.rpath.com/browse/RPL-3022
Signed-off-by: Michael K Johnson <johnsonm@rpath.com>
LKML-Reference: <20090422014448.GB32541@logo.rdu.rpath.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Pass clocksource pointer to the read() callback for clocksources. This
allows us to share the callback between multiple instances.
[hugh@veritas.com: fix powerpc build of clocksource pass clocksource mods]
[akpm@linux-foundation.org: cleanup]
Signed-off-by: Magnus Damm <damm@igel.co.jp>
Acked-by: John Stultz <johnstul@us.ibm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
In theory (though not shown in practice) alloc_cpumask_var() doesn't zero
memory, so CPUs might print an "NMI backtrace for cpu %d" once on boot.
(Bug introduced in fcef8576d8).
[ Impact: avoid theoretical syslog noise in rare configs ]
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Cc: Steven Rostedt <rostedt@goodmis.org>
LKML-Reference: <alpine.DEB.2.00.0904202113520.10097@gandalf.stny.rr.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
fcef8576d8 converted backtrace_mask to a
cpumask_var_t, and assumed check_nmi_watchdog was called before
nmi_watchdog_tick was ever called. Steven's oops shows I was wrong.
This is something of a bandaid: I'm not sure we *should* be calling
nmi_watchdog_tick before check_nmi_watchdog. Note that gcc eliminates
this test for the CONFIG_CPUMASK_OFFSTACK=n case.
[ Impact: fix boot crash in rare configs ]
Reported-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
LKML-Reference: <alpine.DEB.2.00.0904202113520.10097@gandalf.stny.rr.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This is a version incorporating Christoph's suggestion.
Separate out common *fstatat functionality into a single function
instead of duplicating it all over the code.
Signed-off-by: Oleg Drokin <green@linuxhacker.ru>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
In 64bit signal delivery path, clear_used_math() was happening before saving
the current active FPU state on to the user stack for signal handling. Between
clear_used_math() and the state store on to the user stack, potentially we
can get a page fault for the user address and can block. Infact, while testing
we were hitting the might_fault() in __clear_user() which can do a schedule().
At a later point in time, we will schedule back into this process and
resume the save state (using "xsave/fxsave" instruction) which can lead
to DNA fault. And as used_math was cleared before, we will reinit the FP state
in the DNA fault and continue. This reinit will result in loosing the
FPU state of the process.
Move clear_used_math() to a point after the FPU state has been stored
onto the user stack.
This issue is present from a long time (even before the xsave changes
and the x86 merge). But it can easily be exposed in 2.6.28.x and 2.6.29.x
series because of the __clear_user() in this path, which has an explicit
__cond_resched() leading to a context switch with CONFIG_PREEMPT_VOLUNTARY.
[ Impact: fix FPU state corruption ]
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Cc: <stable@kernel.org> [2.6.28.x, 2.6.29.x]
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Fix endcase where the memory at physical address 0 does not really
exist AND one of the sockets on blade 0 has no active cpus.
The memory that _appears_ to be at physical address 0 is actually
memory that located at a different address but has been remapped by
the chipset so that it appears to be at physical address 0.
When determining the UV pnode, the algorithm for determining the pnode
incorrectly used the relocated physical address instead of the actual
(global) address.
[ Impact: boot failure on partitioned systems ]
Signed-off-by: Jack Steiner <steiner@sgi.com>
LKML-Reference: <20090420132530.GA23156@sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
