Pull timer and time updates from Thomas Gleixner:
"A rather large update of timers, timekeeping & co
- Core timekeeping code is year-2038 safe now for 32bit machines.
Now we just need to fix all in kernel users and the gazillion of
user space interfaces which rely on timespec/timeval :)
- Better cache layout for the timekeeping internal data structures.
- Proper nanosecond based interfaces for in kernel users.
- Tree wide cleanup of code which wants nanoseconds but does hoops
and loops to convert back and forth from timespecs. Some of it
definitely belongs into the ugly code museum.
- Consolidation of the timekeeping interface zoo.
- A fast NMI safe accessor to clock monotonic for tracing. This is a
long standing request to support correlated user/kernel space
traces. With proper NTP frequency correction it's also suitable
for correlation of traces accross separate machines.
- Checkpoint/restart support for timerfd.
- A few NOHZ[_FULL] improvements in the [hr]timer code.
- Code move from kernel to kernel/time of all time* related code.
- New clocksource/event drivers from the ARM universe. I'm really
impressed that despite an architected timer in the newer chips SoC
manufacturers insist on inventing new and differently broken SoC
specific timers.
[ Ed. "Impressed"? I don't think that word means what you think it means ]
- Another round of code move from arch to drivers. Looks like most
of the legacy mess in ARM regarding timers is sorted out except for
a few obnoxious strongholds.
- The usual updates and fixlets all over the place"
* 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (114 commits)
timekeeping: Fixup typo in update_vsyscall_old definition
clocksource: document some basic timekeeping concepts
timekeeping: Use cached ntp_tick_length when accumulating error
timekeeping: Rework frequency adjustments to work better w/ nohz
timekeeping: Minor fixup for timespec64->timespec assignment
ftrace: Provide trace clocks monotonic
timekeeping: Provide fast and NMI safe access to CLOCK_MONOTONIC
seqcount: Add raw_write_seqcount_latch()
seqcount: Provide raw_read_seqcount()
timekeeping: Use tk_read_base as argument for timekeeping_get_ns()
timekeeping: Create struct tk_read_base and use it in struct timekeeper
timekeeping: Restructure the timekeeper some more
clocksource: Get rid of cycle_last
clocksource: Move cycle_last validation to core code
clocksource: Make delta calculation a function
wireless: ath9k: Get rid of timespec conversions
drm: vmwgfx: Use nsec based interfaces
drm: i915: Use nsec based interfaces
timekeeping: Provide ktime_get_raw()
hangcheck-timer: Use ktime_get_ns()
...
Pull x86 build/cleanup/debug updates from Ingo Molnar:
"Robustify the build process with a quirk to avoid GCC reordering
related bugs.
Two code cleanups.
Simplify entry_64.S CFI annotations, by Jan Beulich"
* 'x86-build-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86, build: Change code16gcc.h from a C header to an assembly header
* 'x86-cleanups-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86: Simplify __HAVE_ARCH_CMPXCHG tests
x86/tsc: Get rid of custom DIV_ROUND() macro
* 'x86-debug-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/debug: Drop several unnecessary CFI annotations
The only user of the cycle_last validation is the x86 TSC. In order to
provide NMI safe accessor functions for clock monotonic and
monotonic_raw we need to do that in the core.
We can't do the TSC specific
if (now < cycle_last)
now = cycle_last;
for the other wrapping around clocksources, but TSC has
CLOCKSOURCE_MASK(64) which actually does not mask out anything so if
now is less than cycle_last the subtraction will give a negative
result. So we can check for that in clocksource_delta() and return 0
for that case.
Implement and enable it for x86
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: John Stultz <john.stultz@linaro.org>
Mauro reported that his AMD X2 using the powernow-k8 cpufreq driver
locked up when doing cpu hotplug.
Because we called set_cyc2ns_scale() from the time_cpufreq_notifier()
unconditionally, it gets called multiple times for each freq change,
instead of only the once, when the tsc_khz value actually changes.
Because it gets called more than once, we run out of cyc2ns data slots
and stall, waiting for a free one, but because we're half way offline,
there's no consumers to free slots.
By placing the call inside the condition that actually changes tsc_khz
we avoid superfluous calls and avoid the problem.
Reported-by: Mauro <registosites@hotmail.com>
Tested-by: Mauro <registosites@hotmail.com>
Fixes: 20d1c86a57 ("sched/clock, x86: Rewrite cyc2ns() to avoid the need to disable IRQs")
Cc: <stable@vger.kernel.org>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Viresh Kumar <viresh.kumar@linaro.org>
Cc: Bin Gao <bin.gao@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mika Westerberg <mika.westerberg@linux.intel.com>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
Cc: Stefani Seibold <stefani@seibold.net>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
When invoced for positive values, DIV_ROUND macro defined in
arch/x86/kernel/tsc.c behaves exactly like DIV_ROUND_CLOSEST from
include/linux/kernel.h file, so remove the custom macro in favour
of the shared one.
[ hpa: changed line breaks ]
Signed-off-by: Michal Nazarewicz <mina86@mina86.com>
Link: http://lkml.kernel.org/r/1403143116-21755-1-git-send-email-mina86@mina86.com
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Pull x86 vdso changes from Peter Anvin:
"This is the revamp of the 32-bit vdso and the associated cleanups.
This adds timekeeping support to the 32-bit vdso that we already have
in the 64-bit vdso. Although 32-bit x86 is legacy, it is likely to
remain in the embedded space for a very long time to come.
This removes the traditional COMPAT_VDSO support; the configuration
variable is reused for simply removing the 32-bit vdso, which will
produce correct results but obviously suffer a performance penalty.
Only one beta version of glibc was affected, but that version was
unfortunately included in one OpenSUSE release.
This is not the end of the vdso cleanups. Stefani and Andy have
agreed to continue work for the next kernel cycle; in fact Andy has
already produced another set of cleanups that came too late for this
cycle.
An incidental, but arguably important, change is that this ensures
that unused space in the VVAR page is properly zeroed. It wasn't
before, and would contain whatever garbage was left in memory by BIOS
or the bootloader. Since the VVAR page is accessible to user space
this had the potential of information leaks"
* 'x86-vdso-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (23 commits)
x86, vdso: Fix the symbol versions on the 32-bit vDSO
x86, vdso, build: Don't rebuild 32-bit vdsos on every make
x86, vdso: Actually discard the .discard sections
x86, vdso: Fix size of get_unmapped_area()
x86, vdso: Finish removing VDSO32_PRELINK
x86, vdso: Move more vdso definitions into vdso.h
x86: Load the 32-bit vdso in place, just like the 64-bit vdsos
x86, vdso32: handle 32 bit vDSO larger one page
x86, vdso32: Disable stack protector, adjust optimizations
x86, vdso: Zero-pad the VVAR page
x86, vdso: Add 32 bit VDSO time support for 64 bit kernel
x86, vdso: Add 32 bit VDSO time support for 32 bit kernel
x86, vdso: Patch alternatives in the 32-bit VDSO
x86, vdso: Introduce VVAR marco for vdso32
x86, vdso: Cleanup __vdso_gettimeofday()
x86, vdso: Replace VVAR(vsyscall_gtod_data) by gtod macro
x86, vdso: __vdso_clock_gettime() cleanup
x86, vdso: Revamp vclock_gettime.c
mm: Add new func _install_special_mapping() to mmap.c
x86, vdso: Make vsyscall_gtod_data handling x86 generic
...
Two cpufreq notifiers CPUFREQ_RESUMECHANGE and CPUFREQ_SUSPENDCHANGE have
not been used for some time, so remove them to clean up code a bit.
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
[rjw: Changelog]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
This patch move the vsyscall_gtod_data handling out of vsyscall_64.c
into an additonal file vsyscall_gtod.c to make the functionality
available for x86 32 bit kernel.
It also adds a new vsyscall_32.c which setup the VVAR page.
Reviewed-by: Andy Lutomirski <luto@amacapital.net>
Signed-off-by: Stefani Seibold <stefani@seibold.net>
Link: http://lkml.kernel.org/r/1395094933-14252-2-git-send-email-stefani@seibold.net
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
If we cannot calibrate TSC via MSR based calibration
try_msr_calibrate_tsc() stores zero to fast_calibrate and returns that
to the caller. This value gets then propagated further to clockevents
code resulting division by zero oops like the one below:
divide error: 0000 [#1] PREEMPT SMP
Modules linked in:
CPU: 0 PID: 1 Comm: swapper/0 Tainted: G W 3.13.0+ #47
task: ffff880075508000 ti: ffff880075506000 task.ti: ffff880075506000
RIP: 0010:[<ffffffff810aec14>] [<ffffffff810aec14>] clockevents_config.part.3+0x24/0xa0
RSP: 0000:ffff880075507e58 EFLAGS: 00010246
RAX: ffffffffffffffff RBX: ffff880079c0cd80 RCX: 0000000000000000
RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffffffffffffffff
RBP: ffff880075507e70 R08: 0000000000000001 R09: 00000000000000be
R10: 00000000000000bd R11: 0000000000000003 R12: 000000000000b008
R13: 0000000000000008 R14: 000000000000b010 R15: 0000000000000000
FS: 0000000000000000(0000) GS:ffff880079c00000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b
CR2: ffff880079fff000 CR3: 0000000001c0b000 CR4: 00000000001006f0
Stack:
ffff880079c0cd80 000000000000b008 0000000000000008 ffff880075507e88
ffffffff810aecb0 ffff880079c0cd80 ffff880075507e98 ffffffff81030168
ffff880075507ed8 ffffffff81d1104f 00000000000000c3 0000000000000000
Call Trace:
[<ffffffff810aecb0>] clockevents_config_and_register+0x20/0x30
[<ffffffff81030168>] setup_APIC_timer+0xc8/0xd0
[<ffffffff81d1104f>] setup_boot_APIC_clock+0x4cc/0x4d8
[<ffffffff81d0f5de>] native_smp_prepare_cpus+0x3dd/0x3f0
[<ffffffff81d02ee9>] kernel_init_freeable+0xc3/0x205
[<ffffffff8177c910>] ? rest_init+0x90/0x90
[<ffffffff8177c91e>] kernel_init+0xe/0x120
[<ffffffff8178deec>] ret_from_fork+0x7c/0xb0
[<ffffffff8177c910>] ? rest_init+0x90/0x90
Prevent this from happening by:
1) Modifying try_msr_calibrate_tsc() to return calibration value or zero
if it fails.
2) Check this return value in native_calibrate_tsc() and in case of zero
fallback to use normal non-MSR based calibration.
[mw: Added subject and changelog]
Reported-and-tested-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Bin Gao <bin.gao@linux.intel.com>
Cc: One Thousand Gnomes <gnomes@lxorguk.ukuu.org.uk>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Link: http://lkml.kernel.org/r/1392810750-18660-1-git-send-email-mika.westerberg@linux.intel.com
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
When debug preempt is enabled, preempt_disable() can be traced by
function and function graph tracing.
There's a place in the function graph tracer that calls trace_clock()
which eventually calls cycles_2_ns() outside of the recursion
protection. When cycles_2_ns() calls preempt_disable() it gets traced
and the graph tracer will go into a recursive loop causing a crash or
worse, a triple fault.
Simple fix is to use preempt_disable_notrace() in cycles_2_ns, which
makes sense because the preempt_disable() tracing may use that code
too, and it tracing it, even with recursion protection is rather
pointless.
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20140204141315.2a968a72@gandalf.local.home
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Since we keep the clock value linearly continuous on frequency change,
make sure the initial multiplier is 0, such that our initial value is 0.
Without this we compute the initial value at whatever the TSC has
managed to reach since power-on.
Reported-and-Tested-by: Markus Trippelsdorf <markus@trippelsdorf.de>
Fixes: 20d1c86a57 ("sched/clock, x86: Rewrite cyc2ns() to avoid the need to disable IRQs")
Cc: lenb@kernel.org
Cc: rjw@rjwysocki.net
Cc: Eliezer Tamir <eliezer.tamir@linux.intel.com>
Cc: rui.zhang@intel.com
Cc: jacob.jun.pan@linux.intel.com
Cc: Mike Galbraith <bitbucket@online.de>
Cc: hpa@zytor.com
Cc: paulmck@linux.vnet.ibm.com
Cc: John Stultz <john.stultz@linaro.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: Sasha Levin <sasha.levin@oracle.com>
Cc: dyoung@redhat.com
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20140123094804.GP30183@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
On SoCs that have the calibration MSRs available, either there is no
PIT, HPET or PMTIMER to calibrate against, or the PIT/HPET/PMTIMER is
driven from the same clock as the TSC, so calibration is redundant and
just slows down the boot.
TSC rate is caculated by this formula:
<maximum core-clock to bus-clock ratio> * <maximum resolved frequency>
The ratio and the resolved frequency ID can be obtained from MSR.
See Intel 64 and IA-32 System Programming Guid section 16.12 and 30.11.5
for details.
Signed-off-by: Bin Gao <bin.gao@intel.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Link: http://lkml.kernel.org/n/tip-rgm7xmg7k6qnjlw3ynkcjsmh@git.kernel.org
Use a ring-buffer like multi-version object structure which allows
always having a coherent object; we use this to avoid having to
disable IRQs while reading sched_clock() and avoids a problem when
getting an NMI while changing the cyc2ns data.
MAINLINE PRE POST
sched_clock_stable: 1 1 1
(cold) sched_clock: 329841 331312 257223
(cold) local_clock: 301773 310296 309889
(warm) sched_clock: 38375 38247 25280
(warm) local_clock: 100371 102713 85268
(warm) rdtsc: 27340 27289 24247
sched_clock_stable: 0 0 0
(cold) sched_clock: 382634 372706 301224
(cold) local_clock: 396890 399275 399870
(warm) sched_clock: 38194 38124 25630
(warm) local_clock: 143452 148698 129629
(warm) rdtsc: 27345 27365 24307
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/n/tip-s567in1e5ekq2nlyhn8f987r@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
There are no __cycles_2_ns() users outside of arch/x86/kernel/tsc.c,
so move it there.
There are no cycles_2_ns() users.
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/n/tip-01lslnavfgo3kmbo4532zlcj@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
For modern CPUs, perf clock is directly related to TSC. TSC
can be calculated from perf clock and vice versa using a simple
calculation. Two of the three componenets of that calculation
are already exported in struct perf_event_mmap_page. This patch
exports the third.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Link: http://lkml.kernel.org/r/1372425741-1676-3-git-send-email-adrian.hunter@intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The __cpuinit type of throwaway sections might have made sense
some time ago when RAM was more constrained, but now the savings
do not offset the cost and complications. For example, the fix in
commit 5e427ec2d0 ("x86: Fix bit corruption at CPU resume time")
is a good example of the nasty type of bugs that can be created
with improper use of the various __init prefixes.
After a discussion on LKML[1] it was decided that cpuinit should go
the way of devinit and be phased out. Once all the users are gone,
we can then finally remove the macros themselves from linux/init.h.
Note that some harmless section mismatch warnings may result, since
notify_cpu_starting() and cpu_up() are arch independent (kernel/cpu.c)
are flagged as __cpuinit -- so if we remove the __cpuinit from
arch specific callers, we will also get section mismatch warnings.
As an intermediate step, we intend to turn the linux/init.h cpuinit
content into no-ops as early as possible, since that will get rid
of these warnings. In any case, they are temporary and harmless.
This removes all the arch/x86 uses of the __cpuinit macros from
all C files. x86 only had the one __CPUINIT used in assembly files,
and it wasn't paired off with a .previous or a __FINIT, so we can
delete it directly w/o any corresponding additional change there.
[1] https://lkml.org/lkml/2013/5/20/589
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: x86@kernel.org
Acked-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: H. Peter Anvin <hpa@linux.intel.com>
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
During some experiments with an external clock (in a FPGA), we saw that
the TSC clock drifted approx. 2.5ms per second.
This drift was caused by the current way of calculating the scale.
In our case cpu_khz had a value of 3292725. This resulted in a scale
value of 310. But when doing the calculation by hand it shows that the
actual value is 310.9886188491, so a value of 311 would be more precise.
With this change the value is rounded.
Signed-off-by: Bernd Faust <berndfaust@gmail.com>
Signed-off-by: John Stultz <john.stultz@linaro.org>
Move native_read_tsc() to tsc.c to allow profiling to be
re-enabled for rtc.c.
Signed-off-by: David Vrabel <david.vrabel@citrix.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1349698050-6560-1-git-send-email-david.vrabel@citrix.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Use a more current logging style:
- Bare printks should have a KERN_<LEVEL> for consistency's sake
- Add pr_fmt where appropriate
- Neaten some macro definitions
- Convert some Ok output to OK
- Use "%s: ", __func__ in pr_fmt for summit
- Convert some printks to pr_<level>
Message output is not identical in all cases.
Signed-off-by: Joe Perches <joe@perches.com>
Cc: levinsasha928@gmail.com
Link: http://lkml.kernel.org/r/1337655007.24226.10.camel@joe2Laptop
[ merged two similar patches, tidied up the changelog ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Pull timer core updates from Thomas Gleixner.
* 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
ia64: vsyscall: Add missing paranthesis
alarmtimer: Don't call rtc_timer_init() when CONFIG_RTC_CLASS=n
x86: vdso: Put declaration before code
x86-64: Inline vdso clock_gettime helpers
x86-64: Simplify and optimize vdso clock_gettime monotonic variants
kernel-time: fix s/then/than/ spelling errors
time: remove no_sync_cmos_clock
time: Avoid scary backtraces when warning of > 11% adj
alarmtimer: Make sure we initialize the rtctimer
ntp: Fix leap-second hrtimer livelock
x86, tsc: Skip refined tsc calibration on systems with reliable TSC
rtc: Provide flag for rtc devices that don't support UIE
ia64: vsyscall: Use seqcount instead of seqlock
x86: vdso: Use seqcount instead of seqlock
x86: vdso: Remove bogus locking in update_vsyscall_tz()
time: Remove bogus comments
time: Fix change_clocksource locking
time: x86: Fix race switching from vsyscall to non-vsyscall clock
Pull kvm updates from Avi Kivity:
"Changes include timekeeping improvements, support for assigning host
PCI devices that share interrupt lines, s390 user-controlled guests, a
large ppc update, and random fixes."
This is with the sign-off's fixed, hopefully next merge window we won't
have rebased commits.
* 'kvm-updates/3.4' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (130 commits)
KVM: Convert intx_mask_lock to spin lock
KVM: x86: fix kvm_write_tsc() TSC matching thinko
x86: kvmclock: abstract save/restore sched_clock_state
KVM: nVMX: Fix erroneous exception bitmap check
KVM: Ignore the writes to MSR_K7_HWCR(3)
KVM: MMU: make use of ->root_level in reset_rsvds_bits_mask
KVM: PMU: add proper support for fixed counter 2
KVM: PMU: Fix raw event check
KVM: PMU: warn when pin control is set in eventsel msr
KVM: VMX: Fix delayed load of shared MSRs
KVM: use correct tlbs dirty type in cmpxchg
KVM: Allow host IRQ sharing for assigned PCI 2.3 devices
KVM: Ensure all vcpus are consistent with in-kernel irqchip settings
KVM: x86 emulator: Allow PM/VM86 switch during task switch
KVM: SVM: Fix CPL updates
KVM: x86 emulator: VM86 segments must have DPL 3
KVM: x86 emulator: Fix task switch privilege checks
arch/powerpc/kvm/book3s_hv.c: included linux/sched.h twice
KVM: x86 emulator: correctly mask pmc index bits in RDPMC instruction emulation
KVM: mmu_notifier: Flush TLBs before releasing mmu_lock
...
Upon resume from hibernation, CPU 0's hvclock area contains the old
values for system_time and tsc_timestamp. It is necessary for the
hypervisor to update these values with uptodate ones before the CPU uses
them.
Abstract TSC's save/restore sched_clock_state functions and use
restore_state to write to KVM_SYSTEM_TIME MSR, forcing an update.
Also move restore_sched_clock_state before __restore_processor_state,
since the later calls CONFIG_LOCK_STAT's lockstat_clock (also for TSC).
Thanks to Igor Mammedov for tracking it down.
Fixes suspend-to-disk with kvmclock.
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
While running the latest Linux as guest under VMware in highly
over-committed situations, we have seen cases when the refined TSC
algorithm fails to get a valid tsc_start value in
tsc_refine_calibration_work from multiple attempts. As a result the
kernel keeps on scheduling the tsc_irqwork task for later. Subsequently
after several attempts when it gets a valid start value it goes through
the refined calibration and either bails out or uses the new results.
Given that the kernel originally read the TSC frequency from the
platform, which is the best it can get, I don't think there is much
value in refining it.
So for systems which get the TSC frequency from the platform we
should skip the refined tsc algorithm.
We can use the TSC_RELIABLE cpu cap flag to detect this, right now it is
set only on VMware and for Moorestown Penwell both of which have there
own TSC calibration methods.
Signed-off-by: Alok N Kataria <akataria@vmware.com>
Cc: John Stultz <johnstul@us.ibm.com>
Cc: Dirk Brandewie <dirk.brandewie@gmail.com>
Cc: Alan Cox <alan@linux.intel.com>
Cc: stable@kernel.org
[jstultz: Reworked to simply not schedule the refining work,
rather then scheduling the work and bombing out later]
Signed-off-by: John Stultz <john.stultz@linaro.org>
When a machine boots up, the TSC generally gets reset. However,
when kexec is used to boot into a kernel, the TSC value would be
carried over from the previous kernel. The computation of
cycns_offset in set_cyc2ns_scale is prone to an overflow, if the
machine has been up more than 208 days prior to the kexec. The
overflow happens when we multiply *scale, even though there is
enough room to store the final answer.
We fix this issue by decomposing tsc_now into the quotient and
remainder of division by CYC2NS_SCALE_FACTOR and then performing
the multiplication separately on the two components.
Refactor code to share the calculation with the previous
fix in __cycles_2_ns().
Signed-off-by: Salman Qazi <sqazi@google.com>
Acked-by: John Stultz <john.stultz@linaro.org>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Turner <pjt@google.com>
Cc: john stultz <johnstul@us.ibm.com>
Link: http://lkml.kernel.org/r/20120310004027.19291.88460.stgit@dungbeetle.mtv.corp.google.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
pit_expect_msb() returns success wrongly in the below SMI scenario:
a. pit_verify_msb() has not yet seen the MSB transition.
b. we are close to the MSB transition though and got a SMI immediately after
returning from pit_verify_msb() which didn't see the MSB transition. PIT MSB
transition has happened somewhere during SMI execution.
c. returned from SMI and we noted down the 'tsc', saw the pit MSB change now and
exited the loop to calculate 'deltatsc'. Instead of noting the TSC at the MSB
transition, we are way off because of the SMI. And as the SMI happened
between the pit_verify_msb() and before the 'tsc' is recorded in the
for loop, 'delattsc' (d1/d2 in quick_pit_calibrate()) will be small and
quick_pit_calibrate() will not notice this error.
Depending on whether SMI disturbance happens while computing d1 or d2, we will
see the TSC calibrated value smaller or bigger than the expected value. As a
result, in a cluster we were seeing a variation of approximately +/- 20MHz in
the calibrated values, resulting in NTP failures.
[ As far as the SMI source is concerned, this is a periodic SMI that gets
disabled after ACPI is enabled by the OS. But the TSC calibration happens
before the ACPI is enabled. ]
To address this, change pit_expect_msb() so that
- the 'tsc' is the TSC in between the two reads that read the MSB
change from the PIT (same as before)
- the 'delta' is the difference in TSC from *before* the MSB changed
to *after* the MSB changed.
Now the delta is twice as big as before (it covers four PIT accesses,
roughly 4us) and quick_pit_calibrate() will loop a bit longer to get
the calibrated value with in the 500ppm precision. As the delta (d1/d2)
covers four PIT accesses, actual calibrated result might be closer to
250ppm precision.
As the loop now takes longer to stabilize, double MAX_QUICK_PIT_MS to 50.
SMI disturbance will showup as much larger delta's and the loop will take
longer than usual for the result to be with in the accepted precision. Or will
fallback to slow PIT calibration if it takes more than 50msec.
Also while we are at this, remove the calibration correction that aims to
get the result to the middle of the error bars. We really don't know which
direction to correct into, so remove it.
Reported-and-tested-by: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Link: http://lkml.kernel.org/r/1326843337.5291.4.camel@sbsiddha-mobl2
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
* 'x86-platform-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/intel config: Fix the APB_TIMER selection
x86/mrst: Add additional debug prints for pb_keys
x86/intel config: Revamp configuration to allow for Moorestown and Medfield
x86/intel/scu/ipc: Match the changes in the x86 configuration
x86/apb: Fix configuration constraints
x86: Fix INTEL_MID silly
x86/Kconfig: Cyclone-timer depends on x86-summit
x86: Reduce clock calibration time during slave cpu startup
x86/config: Revamp configuration for MID devices
x86/sfi: Kill the IRQ as id hack
tsc=reliable boot parameter is supposed to skip all the TSC
stablility checks during boot time.
On a 8-socket system where we want to run an experiment with the
"tsc=reliable" boot option, TSC synchronization checks are not
getting skipped and marking the TSC as not stable.
Check for tsc_clocksource_reliable (which is set via
tsc=reliable or for platforms supporting synthetic TSC_RELIABLE
feature bit etc) and when set, skip the TSC synchronization
tests during boot.
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Acked-by: John Stultz <johnstul@us.ibm.com>
Tested-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/1320446537.15071.14.camel@sbsiddha-desk.sc.intel.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Reduce the startup time for slave cpus.
Adds hooks for an arch-specific function for clock calibration.
These hooks are used on x86. If a newly started cpu has the
same phys_proc_id as a core already active, uses the TSC for the
delay loop and has a CONSTANT_TSC, use the already-calculated
value of loops_per_jiffy.
This patch reduces the time required to start slave cpus on a
4096 cpu system from: 465 sec OLD 62 sec NEW
This reduces boot time on a 4096p system by almost 7 minutes.
Nice...
Signed-off-by: Jack Steiner <steiner@sgi.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: John Stultz <john.stultz@linaro.org>
[fix CONFIG_SMP=n build]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
The tsc code uses CLOCK_TICK_RATE which on x86
is defined to just be the same as PIT_TICK_RATE.
This patch updates the code use the later
as we want to depecrate and remove the global
CLOCK_TICK_RATE symbol.
Signed-off-by: Deepak Saxena <dsaxena@linaro.org>
Signed-off-by: John Stultz <john.stultz@linaro.org>
* 'x86-detect-hyper-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
x86, hyper: Change hypervisor detection order
* 'x86-fpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
x86-32, fpu: Fix DNA exception during check_fpu()
* 'x86-kexec-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
kexec, x86: Fix incorrect jump back address if not preserving context
* 'x86-platform-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
x86, config: Introduce an INTEL_MID configuration
* 'x86-quirks-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
x86, quirks: Use pci_dev->revision
* 'x86-tsc-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
x86: tsc: Remove unneeded DMI-based blacklisting
* 'x86-smpboot-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
x86, boot: Wait for boot cpu to show up if nr_cpus limit is about to hit
The vread field was bloating struct clocksource everywhere except
x86_64, and I want to change the way this works on x86_64, so let's
split it out into per-arch data.
Cc: x86@kernel.org
Cc: Clemens Ladisch <clemens@ladisch.de>
Cc: linux-ia64@vger.kernel.org
Cc: Tony Luck <tony.luck@intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: John Stultz <johnstul@us.ibm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andy Lutomirski <luto@mit.edu>
Link: http://lkml.kernel.org/r/3ae5ec76a168eaaae63f08a2a1060b91aa0b7759.1310563276.git.luto@mit.edu
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
The blacklist was added in response to my bug report
(http://lkml.org/lkml/2006/1/19/362) and has never
contained more than the one entry describing my old
now dead ThinkPad 380XD laptop. As found out later
(http://lkml.org/lkml/2007/11/29/50), this special
treatment has been unnecessary for a long time, so
it can be removed.
Signed-off-by: Tero Roponen <tero.roponen@gmail.com>
Signed-off-by: John Stultz <john.stultz@linaro.org>
vread_tsc is short and hot, and it's userspace code so the usual
reasons to enable -pg and turn off sibling calls don't apply.
(OK, turning off sibling calls has no effect. But it might
someday...)
As an added benefit, tsc.c is profilable now.
Signed-off-by: Andy Lutomirski <luto@mit.edu>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Borislav Petkov <bp@amd64.org>
Link: http://lkml.kernel.org/r/%3C99c6d7f5efa3ccb65b4ac6eb443e1ab7bad47d7b.1306156808.git.luto%40mit.edu%3E
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
vread_tsc checks whether rdtsc returns something less than
cycle_last, which is an extremely predictable branch. GCC likes
to generate a cmov anyway, which is several cycles slower than
a predicted branch. This saves a couple of nanoseconds.
Signed-off-by: Andy Lutomirski <luto@mit.edu>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Borislav Petkov <bp@amd64.org>
Link: http://lkml.kernel.org/r/%3C561280649519de41352fcb620684dfb22bad6bac.1306156808.git.luto%40mit.edu%3E
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
RDTSC is completely unordered on modern Intel and AMD CPUs. The
Intel manual says that lfence;rdtsc causes all previous instructions
to complete before the tsc is read, and the AMD manual says to use
mfence;rdtsc to do the same thing.
From a decent amount of testing [1] this is enough to make rdtsc
be ordered with respect to subsequent loads across a wide variety
of CPUs.
On Sandy Bridge (i7-2600), this improves a loop of
clock_gettime(CLOCK_MONOTONIC) by more than 5 ns/iter.
[1] https://lkml.org/lkml/2011/4/18/350
Signed-off-by: Andy Lutomirski <luto@mit.edu>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Borislav Petkov <bp@amd64.org>
Link: http://lkml.kernel.org/r/%3C1c158b9d74338aa5361f96dd473d0e6a58235302.1306156808.git.luto%40mit.edu%3E
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Variables that are shared between the vdso and the kernel are
currently a bit of a mess. They are each defined with their own
magic, they are accessed differently in the kernel, the vsyscall page,
and the vdso, and one of them (vsyscall_clock) doesn't even really
exist.
This changes them all to use a common mechanism. All of them are
delcared in vvar.h with a fixed address (validated by the linker
script). In the kernel (as before), they look like ordinary
read-write variables. In the vsyscall page and the vdso, they are
accessed through a new macro VVAR, which gives read-only access.
The vdso is now loaded verbatim into memory without any fixups. As a
side bonus, access from the vdso is faster because a level of
indirection is removed.
While we're at it, pack jiffies and vgetcpu_mode into the same
cacheline.
Signed-off-by: Andy Lutomirski <luto@mit.edu>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Borislav Petkov <bp@amd64.org>
Link: http://lkml.kernel.org/r/%3C7357882fbb51fa30491636a7b6528747301b7ee9.1306156808.git.luto%40mit.edu%3E
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
They were generated by 'codespell' and then manually reviewed.
Signed-off-by: Lucas De Marchi <lucas.demarchi@profusion.mobi>
Cc: trivial@kernel.org
LKML-Reference: <1300389856-1099-3-git-send-email-lucas.demarchi@profusion.mobi>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
* 'core-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
rcu: avoid pointless blocked-task warnings
rcu: demote SRCU_SYNCHRONIZE_DELAY from kernel-parameter status
rtmutex: Fix comment about why new_owner can be NULL in wake_futex_pi()
* 'x86-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
x86, olpc: Add missing Kconfig dependencies
x86, mrst: Set correct APB timer IRQ affinity for secondary cpu
x86: tsc: Fix calibration refinement conditionals to avoid divide by zero
x86, ia64, acpi: Clean up x86-ism in drivers/acpi/numa.c
* 'timers-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
timekeeping: Make local variables static
time: Rename misnamed minsec argument of clocks_calc_mult_shift()
* 'perf-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
tracing: Remove syscall_exit_fields
tracing: Only process module tracepoints once
perf record: Add "nodelay" mode, disabled by default
perf sched: Fix list of events, dropping unsupported ':r' modifier
Revert "perf tools: Emit clearer message for sys_perf_event_open ENOENT return"
perf top: Fix annotate segv
perf evsel: Fix order of event list deletion
Konrad Wilk reported that the new delayed calibration crashes with a
divide by zero on Xen. The reason is that Xen sets the pmtimer
address, but reading from it returns 0xffffff. That results in the
ref_start and ref_stop value being the same, so the delta is zero
which causes the divide by zero later in the calculation.
The conditional (!hpet && !ref_start && !ref_stop) which sanity checks
the calibration reference values doesn't really make sense. If the
refs are null, but hpet is on, we still want to break out.
The div by zero would be possible to trigger by chance if both reads
from the hardware provided the exact same value (due to hardware
wrapping).
So checking if both the ref values are the same should handle if we
don't have hardware (both null) or if they are the same value (either by
invalid hardware, or by chance), avoiding the div by zero issue.
[ tglx: Applied the same fix to native_calibrate_tsc() where this
check was copied from ]
Reported-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Tested-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: John Stultz <johnstul@us.ibm.com>
LKML-Reference: <1295024788-15619-1-git-send-email-johnstul@us.ibm.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
x86: Fix Moorestown VRTC fixmap placement
x86/gpio: Implement x86 gpio_to_irq convert function
x86, UV: Fix APICID shift for Westmere processors
x86: Use PCI method for enabling AMD extended config space before MSR method
x86: tsc: Prevent delayed init if initial tsc calibration failed
x86, lapic-timer: Increase the max_delta to 31 bits
x86: Fix sparse non-ANSI function warnings in smpboot.c
x86, numa: Fix CONFIG_DEBUG_PER_CPU_MAPS without NUMA emulation
x86, AMD, PCI: Add AMD northbridge PCI device id for CPU families 12h and 14h
x86, numa: Fix cpu to node mapping for sparse node ids
x86, numa: Fake node-to-cpumask for NUMA emulation
x86, numa: Fake apicid and pxm mappings for NUMA emulation
x86, numa: Avoid compiling NUMA emulation functions without CONFIG_NUMA_EMU
x86, numa: Reduce minimum fake node size to 32M
Fix up trivial conflict in arch/x86/kernel/apic/x2apic_uv_x.c
commit a8760ec (x86: Check tsc available/disabled in the delayed init
function) missed to prevent the setup of the delayed init function in
case the initial tsc calibration failed. This results in the same
divide by zero bug as we have seen without the tsc disabled check.
Skip the delayed work setup when tsc_khz (the initial calibration
value) is 0.
Bisected-and-tested-by: Kirill A. Shutemov <kas@openvz.org>
Cc: John Stultz <john.stultz@linaro.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* 'for-2.6.38' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu: (30 commits)
gameport: use this_cpu_read instead of lookup
x86: udelay: Use this_cpu_read to avoid address calculation
x86: Use this_cpu_inc_return for nmi counter
x86: Replace uses of current_cpu_data with this_cpu ops
x86: Use this_cpu_ops to optimize code
vmstat: User per cpu atomics to avoid interrupt disable / enable
irq_work: Use per cpu atomics instead of regular atomics
cpuops: Use cmpxchg for xchg to avoid lock semantics
x86: this_cpu_cmpxchg and this_cpu_xchg operations
percpu: Generic this_cpu_cmpxchg() and this_cpu_xchg support
percpu,x86: relocate this_cpu_add_return() and friends
connector: Use this_cpu operations
xen: Use this_cpu_inc_return
taskstats: Use this_cpu_ops
random: Use this_cpu_inc_return
fs: Use this_cpu_inc_return in buffer.c
highmem: Use this_cpu_xx_return() operations
vmstat: Use this_cpu_inc_return for vm statistics
x86: Support for this_cpu_add, sub, dec, inc_return
percpu: Generic support for this_cpu_add, sub, dec, inc_return
...
Fixed up conflicts: in arch/x86/kernel/{apic/nmi.c, apic/x2apic_uv_x.c, process.c}
as per Tejun.
