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>
* '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
$ 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>
It causes crash on system with lots of cards with MSI-X
when irq_balancer enabled...
The patches fixing it were both complex and fragile, according
to Eric they were also doing quite dangerous things to the
hardware.
Instead we now have patches that solve this problem via static
NUMA node mappings - not dynamic allocation and balancing.
The patches are much simpler than this method but are still too
large outside of the merge window, so we mark the dynamic balancer
as broken for now, and queue up the new approach for v2.6.31.
[ Impact: deactivate broken kernel feature ]
Reported-by: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
LKML-Reference: <49E68C41.4020801@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
* 'x86/uv' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
x86: UV BAU distribution and payload MMRs
x86: UV: BAU partition-relative distribution map
x86, uv: add Kconfig dependency on NUMA for UV systems
x86: prevent /sys/firmware/sgi_uv from being created on non-uv systems
x86, UV: Fix for nodes with memory and no cpus
x86, UV: system table in bios accessed after unmap
x86: UV BAU messaging timeouts
x86: UV BAU and nodes with no memory
Impact: build fix
Add Kconfig dependency on NUMA for enabling UV. Although it might
be possible to configure non-NUMA UV systems, they are unsupported
and not interesting. Much of the infrastructure for UV requires
NUMA support.
Signed-off-by: Jack Steiner <steiner@sgi.com>
LKML-Reference: <20090403203942.GA20137@sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This build failure:
| drivers/pci/dmar.c:47: error: expected ‘=’, ‘,’, ‘;’, ‘asm’ or ‘__attribute__’ before ‘dmar_tbl_size’
| drivers/pci/dmar.c:62: warning: ‘struct acpi_dmar_device_scope’ declared inside parameter list
| drivers/pci/dmar.c:62: warning: its scope is only this definition or declaration, which is probably not what you want
Triggers due to this commit:
d0b03bd: x2apic/intr-remap: decouple interrupt remapping from x2apic
Which exposed a pre-existing but dormant fragility of the 'select X86_X2APIC'
it moved around and turned that fragility into a build failure.
Replace it with a proper 'depends on' construct.
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
LKML-Reference: <1239084280.22733.404.camel@macbook.infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
* 'tracing-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (413 commits)
tracing, net: fix net tree and tracing tree merge interaction
tracing, powerpc: fix powerpc tree and tracing tree interaction
ring-buffer: do not remove reader page from list on ring buffer free
function-graph: allow unregistering twice
trace: make argument 'mem' of trace_seq_putmem() const
tracing: add missing 'extern' keywords to trace_output.h
tracing: provide trace_seq_reserve()
blktrace: print out BLK_TN_MESSAGE properly
blktrace: extract duplidate code
blktrace: fix memory leak when freeing struct blk_io_trace
blktrace: fix blk_probes_ref chaos
blktrace: make classic output more classic
blktrace: fix off-by-one bug
blktrace: fix the original blktrace
blktrace: fix a race when creating blk_tree_root in debugfs
blktrace: fix timestamp in binary output
tracing, Text Edit Lock: cleanup
tracing: filter fix for TRACE_EVENT_FORMAT events
ftrace: Using FTRACE_WARN_ON() to check "freed record" in ftrace_release()
x86: kretprobe-booster interrupt emulation code fix
...
Fix up trivial conflicts in
arch/parisc/include/asm/ftrace.h
include/linux/memory.h
kernel/extable.c
kernel/module.c
interrupt remapping must be enabled before enabling x2apic, but
interrupt remapping doesn't depend on x2apic, it can be used
separately. Enable interrupt remapping in init_dmars even x2apic
is not supported.
[dwmw2: Update Kconfig accordingly, fix build with INTR_REMAP && !X2APIC]
Signed-off-by: Weidong Han <weidong.han@intel.com>
Acked-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jikos/trivial: (28 commits)
trivial: Update my email address
trivial: NULL noise: drivers/mtd/tests/mtd_*test.c
trivial: NULL noise: drivers/media/dvb/frontends/drx397xD_fw.h
trivial: Fix misspelling of "Celsius".
trivial: remove unused variable 'path' in alloc_file()
trivial: fix a pdlfush -> pdflush typo in comment
trivial: jbd header comment typo fix for JBD_PARANOID_IOFAIL
trivial: wusb: Storage class should be before const qualifier
trivial: drivers/char/bsr.c: Storage class should be before const qualifier
trivial: h8300: Storage class should be before const qualifier
trivial: fix where cgroup documentation is not correctly referred to
trivial: Give the right path in Documentation example
trivial: MTD: remove EOL from MODULE_DESCRIPTION
trivial: Fix typo in bio_split()'s documentation
trivial: PWM: fix of #endif comment
trivial: fix typos/grammar errors in Kconfig texts
trivial: Fix misspelling of firmware
trivial: cgroups: documentation typo and spelling corrections
trivial: Update contact info for Jochen Hein
trivial: fix typo "resgister" -> "register"
...
* git://git.infradead.org/iommu-2.6:
intel-iommu: Fix address wrap on 32-bit kernel.
intel-iommu: Enable DMAR on 32-bit kernel.
intel-iommu: fix PCI device detach from virtual machine
intel-iommu: VT-d page table to support snooping control bit
iommu: Add domain_has_cap iommu_ops
intel-iommu: Snooping control support
Fixed trivial conflicts in arch/x86/Kconfig and drivers/pci/intel-iommu.c
CONFIG_DEBUG_PAGEALLOC is now supported by x86, powerpc, sparc64, and
s390. This patch implements it for the rest of the architectures by
filling the pages with poison byte patterns after free_pages() and
verifying the poison patterns before alloc_pages().
This generic one cannot detect invalid page accesses immediately but
invalid read access may cause invalid dereference by poisoned memory and
invalid write access can be detected after a long delay.
Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Cc: <linux-arch@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* 'iommu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (60 commits)
dma-debug: make memory range checks more consistent
dma-debug: warn of unmapping an invalid dma address
dma-debug: fix dma_debug_add_bus() definition for !CONFIG_DMA_API_DEBUG
dma-debug/x86: register pci bus for dma-debug leak detection
dma-debug: add a check dma memory leaks
dma-debug: add checks for kernel text and rodata
dma-debug: print stacktrace of mapping path on unmap error
dma-debug: Documentation update
dma-debug: x86 architecture bindings
dma-debug: add function to dump dma mappings
dma-debug: add checks for sync_single_sg_*
dma-debug: add checks for sync_single_range_*
dma-debug: add checks for sync_single_*
dma-debug: add checking for [alloc|free]_coherent
dma-debug: add add checking for map/unmap_sg
dma-debug: add checking for map/unmap_page/single
dma-debug: add core checking functions
dma-debug: add debugfs interface
dma-debug: add kernel command line parameters
dma-debug: add initialization code
...
Fix trivial conflicts due to whitespace changes in arch/x86/kernel/pci-nommu.c
Impact: disable unused code
x86 is fully converted to flow handlers. No need to keep the
deprecated __do_IRQ() support active.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
If we fix a few highmem-related thinkos and a couple of printk format
warnings, the Intel IOMMU driver works fine in a 32-bit kernel.
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Impact: disable unused code
x86 is fully converted to flow handlers. No need to keep the
deprecated __do_IRQ() support active.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Provide the x86 trace callbacks to trace syscalls.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Lai Jiangshan <laijs@cn.fujitsu.com>
LKML-Reference: <1236401580-5758-3-git-send-email-fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Impact: configuration bug fix
Just like for x86-64, the range of widths valid for NODE_SHIFT is not
unbounded. The upper bound 64-bit uses is definitely also an upper
bound for 32-bit.
Signed-off-by: Jan Beulich <jbeulich@novell.com>
LKML-Reference: <49B90F12.76E4.0078.0@novell.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Impact: New major feature
This patch add kexec jump support for x86_64. More information about
kexec jump can be found in corresponding x86_32 support patch.
Signed-off-by: Huang Ying <ying.huang@intel.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Introduce:
cat /sys/kernel/debug/x86/cpu/*
for Intel and AMD processors to view / debug the state of each CPU.
By using this we can debug whole range of registers and other
cpu information for debugging purpose and monitor how things
are changing.
This can be useful for developers as well as for users.
Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
LKML-Reference: <1236701373.3387.4.camel@localhost.localdomain>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Now that the obvious bugs have been worked out, specifically
the iwlagn issue, and the write buffer errata, DMAR should be safe
to turn back on by default. (We've had it on since those patches were
first written a few weeks ago, without any noticeable bug reports
(most have been due to the dma-api debug patchset.))
Signed-off-by: Kyle McMartin <kyle@redhat.com>
Acked-by: David Woodhouse <David.Woodhouse@intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Impact: cleanup; preparation for feature
The mce_amd_64 code has an own private MC threshold vector with an own
interrupt handler. Since Intel needs a similar handler
it makes sense to share the vector because both can not
be active at the same time.
I factored the common APIC handler code into a separate file which can
be used by both the Intel or AMD MC code.
This is needed for the next patch which adds an Intel specific
CMCI handler.
This patch should be a nop for AMD, it just moves some code
around.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Impact: cleaner and consistent bootmem wrapping
By setting CONFIG_HAVE_ARCH_BOOTMEM_NODE, archs can define
arch-specific wrappers for bootmem allocation. However, this is done
a bit strangely in that only the high level convenience macros can be
changed while lower level, but still exported, interface functions
can't be wrapped. This not only is messy but also leads to strange
situation where alloc_bootmem() does what the arch wants it to do but
the equivalent __alloc_bootmem() call doesn't although they should be
able to be used interchangeably.
This patch updates bootmem such that archs can override / wrap the
backend function - alloc_bootmem_core() instead of the highlevel
interface functions to allow simpler and consistent wrapping. Also,
HAVE_ARCH_BOOTMEM_NODE is renamed to HAVE_ARCH_BOOTMEM.
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Johannes Weiner <hannes@saeurebad.de>
Impact: remove unused/broken code
The Voyager subarch last built successfully on the v2.6.26 kernel
and has been stale since then and does not build on the v2.6.27,
v2.6.28 and v2.6.29-rc5 kernels.
No actual users beyond the maintainer reported this breakage.
Patches were sent and most of the fixes were accepted but the
discussion around how to do a few remaining issues cleanly
fizzled out with no resolution and the code remained broken.
In the v2.6.30 x86 tree development cycle 32-bit subarch support
has been reworked and removed - and the Voyager code, beyond the
build problems already known, needs serious and significant
changes and probably a rewrite to support it.
CONFIG_X86_VOYAGER has been marked BROKEN then. The maintainer has
been notified but no patches have been sent so far to fix it.
While all other subarchs have been converted to the new scheme,
voyager is still broken. We'd prefer to receive patches which
clean up the current situation in a constructive way, but even in
case of removal there is no obstacle to add that support back
after the issues have been sorted out in a mutually acceptable
fashion.
So remove this inactive code for now.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Change the CONFIG_X86_EXTENDED_PLATFORM help text to display the
32bit/64bit extended platform list. This is as suggested by Ingo.
Signed-off-by: Ravikiran Thirumalai <kiran@scalex86.org>
Cc: shai@scalex86.org
Cc: "Benzi Galili (Benzi@ScaleMP.com)" <benzi@scalemp.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Impact: use new dynamic allocator, unified access to static/dynamic
percpu memory
Convert to the new dynamic percpu allocator.
* implement populate_extra_pte() for both 32 and 64
* update setup_per_cpu_areas() to use pcpu_setup_static()
* define __addr_to_pcpu_ptr() and __pcpu_ptr_to_addr()
* define config HAVE_DYNAMIC_PER_CPU_AREA
Signed-off-by: Tejun Heo <tj@kernel.org>
- make oprofile build
- select X86_X2APIC from X86_UV - it relies on it
- export genapic for oprofile modular build
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Impact: cleanup
so could deselect x2apic
and INTR_REMAP will select x2apic
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Jeremy Fitzhardinge