commit 26e61e8939 upstream.
Vince "Super Tester" Weaver reported a new round of syscall fuzzing (Trinity) failures,
with perf WARN_ON()s triggering. He also provided traces of the failures.
This is I think the relevant bit:
> pec_1076_warn-2804 [000] d... 147.926153: x86_pmu_disable: x86_pmu_disable
> pec_1076_warn-2804 [000] d... 147.926153: x86_pmu_state: Events: {
> pec_1076_warn-2804 [000] d... 147.926156: x86_pmu_state: 0: state: .R config: ffffffffffffffff ( (null))
> pec_1076_warn-2804 [000] d... 147.926158: x86_pmu_state: 33: state: AR config: 0 (ffff88011ac99800)
> pec_1076_warn-2804 [000] d... 147.926159: x86_pmu_state: }
> pec_1076_warn-2804 [000] d... 147.926160: x86_pmu_state: n_events: 1, n_added: 0, n_txn: 1
> pec_1076_warn-2804 [000] d... 147.926161: x86_pmu_state: Assignment: {
> pec_1076_warn-2804 [000] d... 147.926162: x86_pmu_state: 0->33 tag: 1 config: 0 (ffff88011ac99800)
> pec_1076_warn-2804 [000] d... 147.926163: x86_pmu_state: }
> pec_1076_warn-2804 [000] d... 147.926166: collect_events: Adding event: 1 (ffff880119ec8800)
So we add the insn:p event (fd[23]).
At this point we should have:
n_events = 2, n_added = 1, n_txn = 1
> pec_1076_warn-2804 [000] d... 147.926170: collect_events: Adding event: 0 (ffff8800c9e01800)
> pec_1076_warn-2804 [000] d... 147.926172: collect_events: Adding event: 4 (ffff8800cbab2c00)
We try and add the {BP,cycles,br_insn} group (fd[3], fd[4], fd[15]).
These events are 0:cycles and 4:br_insn, the BP event isn't x86_pmu so
that's not visible.
group_sched_in()
pmu->start_txn() /* nop - BP pmu */
event_sched_in()
event->pmu->add()
So here we should end up with:
0: n_events = 3, n_added = 2, n_txn = 2
4: n_events = 4, n_added = 3, n_txn = 3
But seeing the below state on x86_pmu_enable(), the must have failed,
because the 0 and 4 events aren't there anymore.
Looking at group_sched_in(), since the BP is the leader, its
event_sched_in() must have succeeded, for otherwise we would not have
seen the sibling adds.
But since neither 0 or 4 are in the below state; their event_sched_in()
must have failed; but I don't see why, the complete state: 0,0,1:p,4
fits perfectly fine on a core2.
However, since we try and schedule 4 it means the 0 event must have
succeeded! Therefore the 4 event must have failed, its failure will
have put group_sched_in() into the fail path, which will call:
event_sched_out()
event->pmu->del()
on 0 and the BP event.
Now x86_pmu_del() will reduce n_events; but it will not reduce n_added;
giving what we see below:
n_event = 2, n_added = 2, n_txn = 2
> pec_1076_warn-2804 [000] d... 147.926177: x86_pmu_enable: x86_pmu_enable
> pec_1076_warn-2804 [000] d... 147.926177: x86_pmu_state: Events: {
> pec_1076_warn-2804 [000] d... 147.926179: x86_pmu_state: 0: state: .R config: ffffffffffffffff ( (null))
> pec_1076_warn-2804 [000] d... 147.926181: x86_pmu_state: 33: state: AR config: 0 (ffff88011ac99800)
> pec_1076_warn-2804 [000] d... 147.926182: x86_pmu_state: }
> pec_1076_warn-2804 [000] d... 147.926184: x86_pmu_state: n_events: 2, n_added: 2, n_txn: 2
> pec_1076_warn-2804 [000] d... 147.926184: x86_pmu_state: Assignment: {
> pec_1076_warn-2804 [000] d... 147.926186: x86_pmu_state: 0->33 tag: 1 config: 0 (ffff88011ac99800)
> pec_1076_warn-2804 [000] d... 147.926188: x86_pmu_state: 1->0 tag: 1 config: 1 (ffff880119ec8800)
> pec_1076_warn-2804 [000] d... 147.926188: x86_pmu_state: }
> pec_1076_warn-2804 [000] d... 147.926190: x86_pmu_enable: S0: hwc->idx: 33, hwc->last_cpu: 0, hwc->last_tag: 1 hwc->state: 0
So the problem is that x86_pmu_del(), when called from a
group_sched_in() that fails (for whatever reason), and without x86_pmu
TXN support (because the leader is !x86_pmu), will corrupt the n_added
state.
Reported-and-Tested-by: Vince Weaver <vincent.weaver@maine.edu>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Dave Jones <davej@redhat.com>
Link: http://lkml.kernel.org/r/20140221150312.GF3104@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit f98b7a772a upstream.
There was a large performance regression that was bisected to
commit 611ae8e3 ("x86/tlb: enable tlb flush range support for
x86"). This patch simply changes the default balance point
between a local and global flush for IvyBridge.
In the interest of allowing the tests to be reproduced, this
patch was tested using mmtests 0.15 with the following
configurations
configs/config-global-dhp__tlbflush-performance
configs/config-global-dhp__scheduler-performance
configs/config-global-dhp__network-performance
Results are from two machines
Ivybridge 4 threads: Intel(R) Core(TM) i3-3240 CPU @ 3.40GHz
Ivybridge 8 threads: Intel(R) Core(TM) i7-3770 CPU @ 3.40GHz
Page fault microbenchmark showed nothing interesting.
Ebizzy was configured to run multiple iterations and threads.
Thread counts ranged from 1 to NR_CPUS*2. For each thread count,
it ran 100 iterations and each iteration lasted 10 seconds.
Ivybridge 4 threads
3.13.0-rc7 3.13.0-rc7
vanilla altshift-v3
Mean 1 6395.44 ( 0.00%) 6789.09 ( 6.16%)
Mean 2 7012.85 ( 0.00%) 8052.16 ( 14.82%)
Mean 3 6403.04 ( 0.00%) 6973.74 ( 8.91%)
Mean 4 6135.32 ( 0.00%) 6582.33 ( 7.29%)
Mean 5 6095.69 ( 0.00%) 6526.68 ( 7.07%)
Mean 6 6114.33 ( 0.00%) 6416.64 ( 4.94%)
Mean 7 6085.10 ( 0.00%) 6448.51 ( 5.97%)
Mean 8 6120.62 ( 0.00%) 6462.97 ( 5.59%)
Ivybridge 8 threads
3.13.0-rc7 3.13.0-rc7
vanilla altshift-v3
Mean 1 7336.65 ( 0.00%) 7787.02 ( 6.14%)
Mean 2 8218.41 ( 0.00%) 9484.13 ( 15.40%)
Mean 3 7973.62 ( 0.00%) 8922.01 ( 11.89%)
Mean 4 7798.33 ( 0.00%) 8567.03 ( 9.86%)
Mean 5 7158.72 ( 0.00%) 8214.23 ( 14.74%)
Mean 6 6852.27 ( 0.00%) 7952.45 ( 16.06%)
Mean 7 6774.65 ( 0.00%) 7536.35 ( 11.24%)
Mean 8 6510.50 ( 0.00%) 6894.05 ( 5.89%)
Mean 12 6182.90 ( 0.00%) 6661.29 ( 7.74%)
Mean 16 6100.09 ( 0.00%) 6608.69 ( 8.34%)
Ebizzy hits the worst case scenario for TLB range flushing every
time and it shows for these Ivybridge CPUs at least that the
default choice is a poor on. The patch addresses the problem.
Next was a tlbflush microbenchmark written by Alex Shi at
http://marc.info/?l=linux-kernel&m=133727348217113 . It
measures access costs while the TLB is being flushed. The
expectation is that if there are always full TLB flushes that
the benchmark would suffer and it benefits from range flushing
There are 320 iterations of the test per thread count. The
number of entries is randomly selected with a min of 1 and max
of 512. To ensure a reasonably even spread of entries, the full
range is broken up into 8 sections and a random number selected
within that section.
iteration 1, random number between 0-64
iteration 2, random number between 64-128 etc
This is still a very weak methodology. When you do not know
what are typical ranges, random is a reasonable choice but it
can be easily argued that the opimisation was for smaller ranges
and an even spread is not representative of any workload that
matters. To improve this, we'd need to know the probability
distribution of TLB flush range sizes for a set of workloads
that are considered "common", build a synthetic trace and feed
that into this benchmark. Even that is not perfect because it
would not account for the time between flushes but there are
limits of what can be reasonably done and still be doing
something useful. If a representative synthetic trace is
provided then this benchmark could be revisited and the shift values retuned.
Ivybridge 4 threads
3.13.0-rc7 3.13.0-rc7
vanilla altshift-v3
Mean 1 10.50 ( 0.00%) 10.50 ( 0.03%)
Mean 2 17.59 ( 0.00%) 17.18 ( 2.34%)
Mean 3 22.98 ( 0.00%) 21.74 ( 5.41%)
Mean 5 47.13 ( 0.00%) 46.23 ( 1.92%)
Mean 8 43.30 ( 0.00%) 42.56 ( 1.72%)
Ivybridge 8 threads
3.13.0-rc7 3.13.0-rc7
vanilla altshift-v3
Mean 1 9.45 ( 0.00%) 9.36 ( 0.93%)
Mean 2 9.37 ( 0.00%) 9.70 ( -3.54%)
Mean 3 9.36 ( 0.00%) 9.29 ( 0.70%)
Mean 5 14.49 ( 0.00%) 15.04 ( -3.75%)
Mean 8 41.08 ( 0.00%) 38.73 ( 5.71%)
Mean 13 32.04 ( 0.00%) 31.24 ( 2.49%)
Mean 16 40.05 ( 0.00%) 39.04 ( 2.51%)
For both CPUs, average access time is reduced which is good as
this is the benchmark that was used to tune the shift values in
the first place albeit it is now known *how* the benchmark was
used.
The scheduler benchmarks were somewhat inconclusive. They
showed gains and losses and makes me reconsider how stable those
benchmarks really are or if something else might be interfering
with the test results recently.
Network benchmarks were inconclusive. Almost all results were
flat except for netperf-udp tests on the 4 thread machine.
These results were unstable and showed large variations between
reboots. It is unknown if this is a recent problems but I've
noticed before that netperf-udp results tend to vary.
Based on these results, changing the default for Ivybridge seems
like a logical choice.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Tested-by: Davidlohr Bueso <davidlohr@hp.com>
Reviewed-by: Alex Shi <alex.shi@linaro.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/n/tip-cqnadffh1tiqrshthRj3Esge@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 3b56496865 upstream.
This adds the workaround for erratum 793 as a precaution in case not
every BIOS implements it. This addresses CVE-2013-6885.
Erratum text:
[Revision Guide for AMD Family 16h Models 00h-0Fh Processors,
document 51810 Rev. 3.04 November 2013]
793 Specific Combination of Writes to Write Combined Memory Types and
Locked Instructions May Cause Core Hang
Description
Under a highly specific and detailed set of internal timing
conditions, a locked instruction may trigger a timing sequence whereby
the write to a write combined memory type is not flushed, causing the
locked instruction to stall indefinitely.
Potential Effect on System
Processor core hang.
Suggested Workaround
BIOS should set MSR
C001_1020[15] = 1b.
Fix Planned
No fix planned
[ hpa: updated description, fixed typo in MSR name ]
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: http://lkml.kernel.org/r/20140114230711.GS29865@pd.tnic
Tested-by: Aravind Gopalakrishnan <aravind.gopalakrishnan@amd.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
On AMD family 10h we see following error messages while waking up from
S3 for all non-boot CPUs leading to a failed IBS initialization:
Enabling non-boot CPUs ...
smpboot: Booting Node 0 Processor 1 APIC 0x1
[Firmware Bug]: cpu 1, try to use APIC500 (LVT offset 0) for vector 0x400, but the register is already in use for vector 0xf9 on another cpu
perf: IBS APIC setup failed on cpu #1
process: Switch to broadcast mode on CPU1
CPU1 is up
...
ACPI: Waking up from system sleep state S3
Reason for this is that during suspend the LVT offset for the IBS
vector gets lost and needs to be reinialized while resuming.
The offset is read from the IBSCTL msr. On family 10h the offset needs
to be 1 as offset 0 is used for the MCE threshold interrupt, but
firmware assings it for IBS to 0 too. The kernel needs to reprogram
the vector. The msr is a readonly node msr, but a new value can be
written via pci config space access. The reinitialization is
implemented for family 10h in setup_ibs_ctl() which is forced during
IBS setup.
This patch fixes IBS setup after waking up from S3 by adding
resume/supend hooks for the boot cpu which does the offset
reinitialization.
Marking it as stable to let distros pick up this fix.
Signed-off-by: Robert Richter <rric@kernel.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: <stable@vger.kernel.org> v3.2..
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1389797849-5565-1-git-send-email-rric.net@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Pull x86 fixes from Peter Anvin:
"There is a small EFI fix and a big power regression fix in this batch.
My queue also had a fix for downing a CPU when there are insufficient
number of IRQ vectors available, but I'm holding that one for now due
to recent bug reports"
* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/efi: Don't select EFI from certain special ACPI drivers
x86 idle: Repair large-server 50-watt idle-power regression
Linux 3.10 changed the timing of how thread_info->flags is touched:
x86: Use generic idle loop
(7d1a941731)
This caused Intel NHM-EX and WSM-EX servers to experience a large number
of immediate MONITOR/MWAIT break wakeups, which caused cpuidle to demote
from deep C-states to shallow C-states, which caused these platforms
to experience a significant increase in idle power.
Note that this issue was already present before the commit above,
however, it wasn't seen often enough to be noticed in power measurements.
Here we extend an errata workaround from the Core2 EX "Dunnington"
to extend to NHM-EX and WSM-EX, to prevent these immediate
returns from MWAIT, reducing idle power on these platforms.
While only acpi_idle ran on Dunnington, intel_idle
may also run on these two newer systems.
As of today, there are no other models that are known
to need this tweak.
Link: http://lkml.kernel.org/r/CAJvTdK=%2BaNN66mYpCGgbHGCHhYQAKx-vB0kJSWjVpsNb_hOAtQ@mail.gmail.com
Signed-off-by: Len Brown <len.brown@intel.com>
Link: http://lkml.kernel.org/r/baff264285f6e585df757d58b17788feabc68918.1387403066.git.len.brown@intel.com
Cc: <stable@vger.kernel.org> # 3.12.x, 3.11.x, 3.10.x
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
The EVENT_CONSTRAINT_END() macro defines the end marker as
a constraint with a weight of zero. This was all fine
until we blacklisted the corrupting memory events on
Intel IvyBridge. These events are blacklisted by using
a counter bitmask of zero. Thus, they also get a constraint
weight of zero.
The iteration macro: for_each_constraint tests the weight==0.
Therefore, it was stopping at the first blacklisted event, i.e.,
0xd0. The corrupting events were therefore considered as
unconstrained and were scheduled on any of the generic counters.
This patch fixes the end marker to have a weight of -1. With
this, the blacklisted events get an empty constraint and cannot
be scheduled which is what we want for now.
Signed-off-by: Maria Dimakopoulou <maria.n.dimakopoulou@gmail.com>
Reviewed-by: Stephane Eranian <eranian@google.com>
Cc: peterz@infradead.org
Cc: ak@linux.intel.com
Cc: jolsa@redhat.com
Cc: zheng.z.yan@intel.com
Link: http://lkml.kernel.org/r/20131204232437.GA10689@starlight
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Pull trivial tree updates from Jiri Kosina:
"Usual earth-shaking, news-breaking, rocket science pile from
trivial.git"
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jikos/trivial: (23 commits)
doc: usb: Fix typo in Documentation/usb/gadget_configs.txt
doc: add missing files to timers/00-INDEX
timekeeping: Fix some trivial typos in comments
mm: Fix some trivial typos in comments
irq: Fix some trivial typos in comments
NUMA: fix typos in Kconfig help text
mm: update 00-INDEX
doc: Documentation/DMA-attributes.txt fix typo
DRM: comment: `halve' -> `half'
Docs: Kconfig: `devlopers' -> `developers'
doc: typo on word accounting in kprobes.c in mutliple architectures
treewide: fix "usefull" typo
treewide: fix "distingush" typo
mm/Kconfig: Grammar s/an/a/
kexec: Typo s/the/then/
Documentation/kvm: Update cpuid documentation for steal time and pv eoi
treewide: Fix common typo in "identify"
__page_to_pfn: Fix typo in comment
Correct some typos for word frequency
clk: fixed-factor: Fix a trivial typo
...
Pull x86 RAS changes from Ingo Molnar:
"The biggest change adds support for Intel 'CPER' (UEFI Common Platform
Error Record) error logging, which builds upon an enhanced error
logging mechanism available on Xeon processors.
Full description is here:
http://www.intel.com/content/www/us/en/architecture-and-technology/enhanced-mca-logging-xeon-paper.html
This change provides a module (and support code) to check for an
extended error log and prints extra details about the error on the
console"
* 'x86-mce-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
ACPI, x86: Fix extended error log driver to depend on CONFIG_X86_LOCAL_APIC
dmi: Avoid unaligned memory access in save_mem_devices()
Move cper.c from drivers/acpi/apei to drivers/firmware/efi
EDAC, GHES: Update ghes error record info
ACPI, APEI, CPER: Cleanup CPER memory error output format
ACPI, APEI, CPER: Enhance memory reporting capability
ACPI, APEI, CPER: Add UEFI 2.4 support for memory error
DMI: Parse memory device (type 17) in SMBIOS
ACPI, x86: Extended error log driver for x86 platform
bitops: Introduce a more generic BITMASK macro
ACPI, CPER: Update cper info
ACPI, APEI, CPER: Fix status check during error printing
Pull x86/hyperv changes from Ingo Molnar:
"These changes enable Linux guests to boot as 'Modern VM' guest kernels
on MS-Hyperv hosts"
* 'x86-hyperv-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86, hyperv: Move a variable to avoid an unused variable warning
x86, hyperv: Fix build error due to missing <asm/apic.h> include
x86, hyperv: Correctly guard the local APIC calibration code
x86, hyperv: Get the local APIC timer frequency from the hypervisor
Pull x86 cpu changes from Ingo Molnar:
"The biggest change that stands out is the increase of the
CONFIG_NR_CPUS range from 4096 to 8192 - as real hardware out there
already went beyond 4k CPUs ...
We only allow more than 512 CPUs if offstack cpumasks are enabled.
CONFIG_MAXSMP=y remains to be the 'you are nuts!' extreme testcase,
which now means a max of 8192 CPUs"
* 'x86-cpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/cpu: Increase max CPU count to 8192
x86/cpu: Allow higher NR_CPUS values
x86/cpu: Always print SMP information in /proc/cpuinfo
x86/cpu: Track legacy CPU model data only on 32-bit kernels
Pull scheduler changes from Ingo Molnar:
"The main changes in this cycle are:
- (much) improved CONFIG_NUMA_BALANCING support from Mel Gorman, Rik
van Riel, Peter Zijlstra et al. Yay!
- optimize preemption counter handling: merge the NEED_RESCHED flag
into the preempt_count variable, by Peter Zijlstra.
- wait.h fixes and code reorganization from Peter Zijlstra
- cfs_bandwidth fixes from Ben Segall
- SMP load-balancer cleanups from Peter Zijstra
- idle balancer improvements from Jason Low
- other fixes and cleanups"
* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (129 commits)
ftrace, sched: Add TRACE_FLAG_PREEMPT_RESCHED
stop_machine: Fix race between stop_two_cpus() and stop_cpus()
sched: Remove unnecessary iteration over sched domains to update nr_busy_cpus
sched: Fix asymmetric scheduling for POWER7
sched: Move completion code from core.c to completion.c
sched: Move wait code from core.c to wait.c
sched: Move wait.c into kernel/sched/
sched/wait: Fix __wait_event_interruptible_lock_irq_timeout()
sched: Avoid throttle_cfs_rq() racing with period_timer stopping
sched: Guarantee new group-entities always have weight
sched: Fix hrtimer_cancel()/rq->lock deadlock
sched: Fix cfs_bandwidth misuse of hrtimer_expires_remaining
sched: Fix race on toggling cfs_bandwidth_used
sched: Remove extra put_online_cpus() inside sched_setaffinity()
sched/rt: Fix task_tick_rt() comment
sched/wait: Fix build breakage
sched/wait: Introduce prepare_to_wait_event()
sched/wait: Add ___wait_cond_timeout() to wait_event*_timeout() too
sched: Remove get_online_cpus() usage
sched: Fix race in migrate_swap_stop()
...
The arch_perf_output_copy_user() default of
__copy_from_user_inatomic() returns bytes not copied, while all other
argument functions given DEFINE_OUTPUT_COPY() return bytes copied.
Since copy_from_user_nmi() is the odd duck out by returning bytes
copied where all other *copy_{to,from}* functions return bytes not
copied, change it over and ammend DEFINE_OUTPUT_COPY() to expect bytes
not copied.
Oddly enough DEFINE_OUTPUT_COPY() already returned bytes not copied
while expecting its worker functions to return bytes copied.
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Acked-by: will.deacon@arm.com
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Link: http://lkml.kernel.org/r/20131030201622.GR16117@laptop.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Currently show_cpuinfo_core() displays cpu core information only if
the number of threads per a whole cores is 2 or larger.
However, this condition doesn't care about the number of
sockets. For example, this condition doesn't hold on systems
with two logical cpus consisting of two sockets and a single
core on each socket - yet the topology information would be
interesting to see in that case as well.
I don't know whether or not there are processors in real world
by which such configurations are possible, but at least on
vitual machine environments, such configuration can occur,
typically when no explicit SMP information is provided in
advance.
For example, on qemu/KVM, SMP information is specified via -smp
command-line option, more specifically, its syntax is:
-smp n[,cores=cores][,threads=threads][,sockets=sockets][,maxcpus=maxcpus]
If this is not specified, qemu tells configuration with
n-sockets, 1-core and 1-thread to the guest machine, on which
guest, MP information is not displayed in /proc/cpuinfo.
I saw this situation on VMWare guest environment, too.
To fix this issue, this patch simply removes the condition
because this information is useful even if there's only 1
thread.
Signed-off-by: HATAYAMA Daisuke <d.hatayama@jp.fujitsu.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: H. Peter Anvin <hpa@linux.intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/5277D644.4090707@jp.fujitsu.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
9e7827b5ea ("x86, hyperv: Get the local APIC timer frequency from the
hypervisor") breaks the build with some configs because apic.h isn't
directly included:
arch/x86/kernel/cpu/mshyperv.c: In function 'ms_hyperv_init_platform':
arch/x86/kernel/cpu/mshyperv.c:90:3: error: 'lapic_timer_frequency' undeclared (first use in this function)
arch/x86/kernel/cpu/mshyperv.c:90:3: note: each undeclared identifier is reported only once for each function it appears in
Fix it by including asm/apic.h.
Signed-off-by: David Rientjes <rientjes@google.com>
Link: http://lkml.kernel.org/r/alpine.DEB.2.02.1310111604160.31170@chino.kir.corp.google.com
Acked-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
OK, so what I'm actually seeing on my WSM is that sched/clock.c is
'broken' for the purpose we're using it for.
What triggered it is that my WSM-EP is broken :-(
[ 0.001000] tsc: Fast TSC calibration using PIT
[ 0.002000] tsc: Detected 2533.715 MHz processor
[ 0.500180] TSC synchronization [CPU#0 -> CPU#6]:
[ 0.505197] Measured 3 cycles TSC warp between CPUs, turning off TSC clock.
[ 0.004000] tsc: Marking TSC unstable due to check_tsc_sync_source failed
For some reason it consistently detects TSC skew, even though NHM+
should have a single clock domain for 'reasonable' systems.
This marks sched_clock_stable=0, which means that we do fancy stuff to
try and get a 'sane' clock. Part of this fancy stuff relies on the tick,
clearly that's gone when NOHZ=y. So for idle cpus time gets stuck, until
it either wakes up or gets kicked by another cpu.
While this is perfectly fine for the scheduler -- it only cares about
actually running stuff, and when we're running stuff we're obviously not
idle. This does somewhat break down for perf which can trigger events
just fine on an otherwise idle cpu.
So I've got NMIs get get 'measured' as taking ~1ms, which actually
don't last nearly that long:
<idle>-0 [013] d.h. 886.311970: rcu_nmi_enter <-do_nmi
...
<idle>-0 [013] d.h. 886.311997: perf_sample_event_took: HERE!!! : 1040990
So ftrace (which uses sched_clock(), not the fancy bits) only sees
~27us, but we measure ~1ms !!
Now since all this measurement stuff lives in x86 code, we can actually
fix it.
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: mingo@kernel.org
Cc: dave.hansen@linux.intel.com
Cc: eranian@google.com
Cc: Don Zickus <dzickus@redhat.com>
Cc: jmario@redhat.com
Cc: acme@infradead.org
Link: http://lkml.kernel.org/r/20131017133350.GG3364@laptop.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
struct cpu_dev's c_models is only ever set inside CONFIG_X86_32
conditionals (or code that's being built for 32-bit only), so
there's no use of reserving the (empty) space for the model
names in a 64-bit kernel.
Similarly, c_size_cache is only used in the #else of a
CONFIG_X86_64 conditional, so reserving space for (and in one
case even initializing) that field is pointless for 64-bit
kernels too.
While moving both fields to the end of the structure, I also
noticed that:
- the c_models array size was one too small, potentially causing
table_lookup_model() to return garbage on Intel CPUs (intel.c's
instance was lacking the sentinel with family being zero), so the
patch bumps that by one,
- c_models' vendor sub-field was unused (and anyway redundant
with the base structure's c_x86_vendor field), so the patch deletes it.
Also rename the legacy fields so that their legacy nature stands out
and comment their declarations.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Link: http://lkml.kernel.org/r/5265036802000078000FC4DB@nat28.tlf.novell.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
In latest UEFI spec(by now it is 2.4) memory error definition
for CPER (UEFI 2.4 Appendix N Common Platform Error Record)
adds some new fields. These fields help people to locate
memory error to an actual DIMM location.
Original-author: Tony Luck <tony.luck@intel.com>
Signed-off-by: Chen, Gong <gong.chen@linux.intel.com>
Reviewed-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
Acked-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
There's been reports of high NMI handler overhead, highlighted by
such kernel messages:
[ 3697.380195] perf samples too long (10009 > 10000), lowering kernel.perf_event_max_sample_rate to 13000
[ 3697.389509] INFO: NMI handler (perf_event_nmi_handler) took too long to run: 9.331 msecs
Don Zickus analyzed the source of the overhead and reported:
> While there are a few places that are causing latencies, for now I focused on
> the longest one first. It seems to be 'copy_user_from_nmi'
>
> intel_pmu_handle_irq ->
> intel_pmu_drain_pebs_nhm ->
> __intel_pmu_drain_pebs_nhm ->
> __intel_pmu_pebs_event ->
> intel_pmu_pebs_fixup_ip ->
> copy_from_user_nmi
>
> In intel_pmu_pebs_fixup_ip(), if the while-loop goes over 50, the sum of
> all the copy_from_user_nmi latencies seems to go over 1,000,000 cycles
> (there are some cases where only 10 iterations are needed to go that high
> too, but in generall over 50 or so). At this point copy_user_from_nmi
> seems to account for over 90% of the nmi latency.
The solution to that is to avoid having to call copy_from_user_nmi() for
every instruction.
Since we already limit the max basic block size, we can easily
pre-allocate a piece of memory to copy the entire thing into in one
go.
Don reported this test result:
> Your patch made a huge difference in improvement. The
> copy_from_user_nmi() no longer hits the million of cycles. I still
> have a batch of 100,000-300,000 cycles. My longest NMI paths used
> to be dominated by copy_from_user_nmi, now it is not (I have to dig
> up the new hot path).
Reported-and-tested-by: Don Zickus <dzickus@redhat.com>
Cc: jmario@redhat.com
Cc: acme@infradead.org
Cc: dave.hansen@linux.intel.com
Cc: eranian@google.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20131016105755.GX10651@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Correct common misspelling of "identify" as "indentify" throughout
the kernel
Signed-off-by: Maxime Jayat <maxime@artisandeveloppeur.fr>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Hyper-V supports a mechanism for retrieving the local APIC frequency.
Use this and bypass the calibration code in the kernel . This would
allow us to boot the Linux kernel as a "modern VM" on Hyper-V where
many of the legacy devices (such as PIT) are not emulated.
I would like to thank Olaf Hering <olaf@aepfle.de>, Jan Beulich <JBeulich@suse.com> and
H. Peter Anvin <h.peter.anvin@intel.com> for their help in this effort.
In this version of the patch, I have addressed Jan's comments.
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Link: http://lkml.kernel.org/r/1380554932-9888-1-git-send-email-olaf@aepfle.de
Tested-by: Olaf Hering <olaf@aepfle.de>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Merge Linux v3.12-rc4 to fix a conflict and also to refresh the tree
before applying more scheduler patches.
Conflicts:
arch/avr32/include/asm/Kbuild
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Currently the cap_user_time_zero capability has different tests than
cap_user_time; even though they expose the exact same data.
Switch from CONSTANT && NONSTOP to sched_clock_stable to also deal
with multi cabinet machines and drop the tsc_disabled() check.. non of
this will work sanely without tsc anyway.
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/n/tip-nmgn0j0muo1r4c94vlfh23xy@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Pull perf fixes from Ingo Molnar:
"A couple of tooling fixlets and a PMU detection printout fix"
* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
perf/x86: Fix PMU detection printout when no PMU is detected
perf symbols: Demangle cloned functions
perf machine: Fix path unpopulated in machine__create_modules()
perf tools: Explicitly add libdl dependency
perf probe: Fix probing symbols with optimization suffix
perf trace: Add mmap2 handler
perf kmem: Make it work again on non NUMA machines
Ran into this cryptic PMU bootup log recently:
[ 0.124047] Performance Events:
[ 0.125000] smpboot: ...
Turns out we print this if no PMU is detected. Fall back to
the right condition so that the following is printed:
[ 0.122381] Performance Events: no PMU driver, software events only.
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Link: http://lkml.kernel.org/n/tip-u2fwaUffakjp0qkpRfqljgsn@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Pull perf fixes from Ingo Molnar:
"Assorted standalone fixes"
* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
perf/x86/intel: Add model number for Avoton Silvermont
perf: Fix capabilities bitfield compatibility in 'struct perf_event_mmap_page'
perf/x86/intel/uncore: Don't use smp_processor_id() in validate_group()
perf: Update ABI comment
tools lib lk: Uninclude linux/magic.h in debugfs.c
perf tools: Fix old GCC build error in trace-event-parse.c:parse_proc_kallsyms()
perf probe: Fix finder to find lines of given function
perf session: Check for SIGINT in more loops
perf tools: Fix compile with libelf without get_phdrnum
perf tools: Fix buildid cache handling of kallsyms with kcore
perf annotate: Fix objdump line parsing offset validation
perf tools: Fill in new definitions for madvise()/mmap() flags
perf tools: Sharpen the libaudit dependencies test
Convert x86 to use a per-cpu preemption count. The reason for doing so
is that accessing per-cpu variables is a lot cheaper than accessing
thread_info variables.
We still need to save/restore the actual preemption count due to
PREEMPT_ACTIVE so we place the per-cpu __preempt_count variable in the
same cache-line as the other hot __switch_to() variables such as
current_task.
NOTE: this save/restore is required even for !PREEMPT kernels as
cond_resched() also relies on preempt_count's PREEMPT_ACTIVE to ignore
task_struct::state.
Also rename thread_info::preempt_count to ensure nobody is
'accidentally' still poking at it.
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/n/tip-gzn5rfsf8trgjoqx8hyayy3q@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Fengguang Wu reported this build warning:
arch/x86/kernel/cpu/perf_event_intel_ds.c: In function 'intel_pmu_drain_pebs_nhm':
arch/x86/kernel/cpu/perf_event_intel_ds.c:964:2: warning: format '%ld' expects argument of type 'long int', but argument 4 has type 'int'
Because pointer arithmetics result type is bitness dependent there's no natural
type to use here, cast it to long.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/n/tip-jbpauwxJqtf24luewcsdFith@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Solve the problems around the broken definition of perf_event_mmap_page::
cap_usr_time and cap_usr_rdpmc fields which used to overlap, partially
fixed by:
860f085b74 ("perf: Fix broken union in 'struct perf_event_mmap_page'")
The problem with the fix (merged in v3.12-rc1 and not yet released
officially), noticed by Vince Weaver is that the new behavior is
not detectable by new user-space, and that due to the reuse of the
field names it's easy to mis-compile a binary if old headers are used
on a new kernel or new headers are used on an old kernel.
To solve all that make this change explicit, detectable and self-contained,
by iterating the ABI the following way:
- Always clear bit 0, and rename it to usrpage->cap_bit0, to at least not
confuse old user-space binaries. RDPMC will be marked as unavailable
to old binaries but that's within the ABI, this is a capability bit.
- Rename bit 1 to ->cap_bit0_is_deprecated and always set it to 1, so new
libraries can reliably detect that bit 0 is deprecated and perma-zero
without having to check the kernel version.
- Use bits 2, 3, 4 for the newly defined, correct functionality:
cap_user_rdpmc : 1, /* The RDPMC instruction can be used to read counts */
cap_user_time : 1, /* The time_* fields are used */
cap_user_time_zero : 1, /* The time_zero field is used */
- Rename all the bitfield names in perf_event.h to be different from the
old names, to make sure it's not possible to mis-compile it
accidentally with old assumptions.
The 'size' field can then be used in the future to add new fields and it
will act as a natural ABI version indicator as well.
Also adjust tools/perf/ userspace for the new definitions, noticed by
Adrian Hunter.
Reported-by: Vince Weaver <vincent.weaver@maine.edu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Also-Fixed-by: Adrian Hunter <adrian.hunter@intel.com>
Link: http://lkml.kernel.org/n/tip-zr03yxjrpXesOzzupszqglbv@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Pull x86 fixes from Ingo Molnar:
"Misc fixes"
* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/intel/lpss: Add pin control support to Intel low power subsystem
perf/x86/intel: Mark MEM_LOAD_UOPS_MISS_RETIRED as precise on SNB
x86: Remove now-unused save_rest()
x86/smpboot: Fix announce_cpu() to printk() the last "OK" properly
Pull perf fixes from Ingo Molnar:
"Various fixes.
The -g perf report lockup you reported is only partially addressed,
patches that fix the excessive runtime are still being worked on"
* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
perf/x86: Fix uncore PCI fixed counter handling
uprobes: Fix utask->depth accounting in handle_trampoline()
perf/x86: Add constraint for IVB CYCLE_ACTIVITY:CYCLES_LDM_PENDING
perf: Fix up MMAP2 buffer space reservation
perf tools: Add attr->mmap2 support
perf kvm: Fix sample_type manipulation
perf evlist: Fix id pos in perf_evlist__open()
perf trace: Handle perf.data files with no tracepoints
perf session: Separate progress bar update when processing events
perf trace: Check if MAP_32BIT is defined
perf hists: Fix formatting of long symbol names
perf evlist: Fix parsing with no sample_id_all bit set
perf tools: Add test for parsing with no sample_id_all bit
perf trace: Check control+C more often
