This patch reverts commit 75437bb304 (locking/pvqspinlock: Don't
wait if vCPU is preempted). A large performance regression was caused
by this commit. on over-subscription scenarios.
The test was run on a Xeon Skylake box, 2 sockets, 40 cores, 80 threads,
with three VMs of 80 vCPUs each. The score of ebizzy -M is reduced from
13000-14000 records/s to 1700-1800 records/s:
Host Guest score
vanilla w/o kvm optimizations upstream 1700-1800 records/s
vanilla w/o kvm optimizations revert 13000-14000 records/s
vanilla w/ kvm optimizations upstream 4500-5000 records/s
vanilla w/ kvm optimizations revert 14000-15500 records/s
Exit from aggressive wait-early mechanism can result in premature yield
and extra scheduling latency.
Actually, only 6% of wait_early events are caused by vcpu_is_preempted()
being true. However, when one vCPU voluntarily releases its vCPU, all
the subsequently waiters in the queue will do the same and the cascading
effect leads to bad performance.
kvm optimizations:
[1] commit d73eb57b80 (KVM: Boost vCPUs that are delivering interrupts)
[2] commit 266e85a5ec (KVM: X86: Boost queue head vCPU to mitigate lock waiter preemption)
Tested-by: loobinliu@tencent.com
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Waiman Long <longman@redhat.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: loobinliu@tencent.com
Cc: stable@vger.kernel.org
Fixes: 75437bb304 (locking/pvqspinlock: Don't wait if vCPU is preempted)
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
The percpu event counts used by qspinlock code can be useful for
other locking code as well. So a new set of lockevent_* counting APIs
is introduced with the lock event names extracted out into the new
lock_events_list.h header file for easier addition in the future.
The existing qstat_inc() calls are replaced by either lockevent_inc() or
lockevent_cond_inc() calls.
The qstat_hop() call is renamed to lockevent_pv_hop(). The "reset_counters"
debugfs file is also renamed to ".reset_counts".
Signed-off-by: Waiman Long <longman@redhat.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Davidlohr Bueso <dbueso@suse.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Will Deacon <will.deacon@arm.com>
Link: http://lkml.kernel.org/r/20190404174320.22416-8-longman@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Move remaining definitions and declarations from include/linux/bootmem.h
into include/linux/memblock.h and remove the redundant header.
The includes were replaced with the semantic patch below and then
semi-automated removal of duplicated '#include <linux/memblock.h>
@@
@@
- #include <linux/bootmem.h>
+ #include <linux/memblock.h>
[sfr@canb.auug.org.au: dma-direct: fix up for the removal of linux/bootmem.h]
Link: http://lkml.kernel.org/r/20181002185342.133d1680@canb.auug.org.au
[sfr@canb.auug.org.au: powerpc: fix up for removal of linux/bootmem.h]
Link: http://lkml.kernel.org/r/20181005161406.73ef8727@canb.auug.org.au
[sfr@canb.auug.org.au: x86/kaslr, ACPI/NUMA: fix for linux/bootmem.h removal]
Link: http://lkml.kernel.org/r/20181008190341.5e396491@canb.auug.org.au
Link: http://lkml.kernel.org/r/1536927045-23536-30-git-send-email-rppt@linux.vnet.ibm.com
Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chris Zankel <chris@zankel.net>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Greentime Hu <green.hu@gmail.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Guan Xuetao <gxt@pku.edu.cn>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "James E.J. Bottomley" <jejb@parisc-linux.org>
Cc: Jonas Bonn <jonas@southpole.se>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Ley Foon Tan <lftan@altera.com>
Cc: Mark Salter <msalter@redhat.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Michal Simek <monstr@monstr.eu>
Cc: Palmer Dabbelt <palmer@sifive.com>
Cc: Paul Burton <paul.burton@mips.com>
Cc: Richard Kuo <rkuo@codeaurora.org>
Cc: Richard Weinberger <richard@nod.at>
Cc: Rich Felker <dalias@libc.org>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Serge Semin <fancer.lancer@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Vineet Gupta <vgupta@synopsys.com>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The qspinlock code supports up to 4 levels of slowpath nesting using
four per-CPU mcs_spinlock structures. For 64-bit architectures, they
fit nicely in one 64-byte cacheline.
For para-virtualized (PV) qspinlocks it needs to store more information
in the per-CPU node structure than there is space for. It uses a trick
to use a second cacheline to hold the extra information that it needs.
So PV qspinlock needs to access two extra cachelines for its information
whereas the native qspinlock code only needs one extra cacheline.
Freshly added counter profiling of the qspinlock code, however, revealed
that it was very rare to use more than two levels of slowpath nesting.
So it doesn't make sense to penalize PV qspinlock code in order to have
four mcs_spinlock structures in the same cacheline to optimize for a case
in the native qspinlock code that rarely happens.
Extend the per-CPU node structure to have two more long words when PV
qspinlock locks are configured to hold the extra data that it needs.
As a result, the PV qspinlock code will enjoy the same benefit of using
just one extra cacheline like the native counterpart, for most cases.
[ mingo: Minor changelog edits. ]
Signed-off-by: Waiman Long <longman@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will.deacon@arm.com>
Link: http://lkml.kernel.org/r/1539697507-28084-2-git-send-email-longman@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The native clear_pending() function is identical to the PV version, so the
latter can simply be removed.
This fixes the build for systems with >= 16K CPUs using the PV lock implementation.
Reported-by: Waiman Long <longman@redhat.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: boqun.feng@gmail.com
Cc: linux-arm-kernel@lists.infradead.org
Cc: paulmck@linux.vnet.ibm.com
Link: http://lkml.kernel.org/r/20180427101619.GB21705@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Currently, the qspinlock_stat code tracks only statistical counts in the
PV qspinlock code. However, it may also be useful to track the number
of locking operations done via the pending code vs. the MCS lock queue
slowpath for the non-PV case.
The qspinlock stat code is modified to do that. The stat counter
pv_lock_slowpath is renamed to lock_slowpath so that it can be used by
both the PV and non-PV cases.
Signed-off-by: Waiman Long <longman@redhat.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Waiman Long <longman@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: boqun.feng@gmail.com
Cc: linux-arm-kernel@lists.infradead.org
Cc: paulmck@linux.vnet.ibm.com
Cc: will.deacon@arm.com
Link: http://lkml.kernel.org/r/1524738868-31318-14-git-send-email-will.deacon@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The qspinlock locking slowpath utilises a "pending" bit as a simple form
of an embedded test-and-set lock that can avoid the overhead of explicit
queuing in cases where the lock is held but uncontended. This bit is
managed using a cmpxchg() loop which tries to transition the uncontended
lock word from (0,0,0) -> (0,0,1) or (0,0,1) -> (0,1,1).
Unfortunately, the cmpxchg() loop is unbounded and lockers can be starved
indefinitely if the lock word is seen to oscillate between unlocked
(0,0,0) and locked (0,0,1). This could happen if concurrent lockers are
able to take the lock in the cmpxchg() loop without queuing and pass it
around amongst themselves.
This patch fixes the problem by unconditionally setting _Q_PENDING_VAL
using atomic_fetch_or, and then inspecting the old value to see whether
we need to spin on the current lock owner, or whether we now effectively
hold the lock. The tricky scenario is when concurrent lockers end up
queuing on the lock and the lock becomes available, causing us to see
a lockword of (n,0,0). With pending now set, simply queuing could lead
to deadlock as the head of the queue may not have observed the pending
flag being cleared. Conversely, if the head of the queue did observe
pending being cleared, then it could transition the lock from (n,0,0) ->
(0,0,1) meaning that any attempt to "undo" our setting of the pending
bit could race with a concurrent locker trying to set it.
We handle this race by preserving the pending bit when taking the lock
after reaching the head of the queue and leaving the tail entry intact
if we saw pending set, because we know that the tail is going to be
updated shortly.
Signed-off-by: Will Deacon <will.deacon@arm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Waiman Long <longman@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: boqun.feng@gmail.com
Cc: linux-arm-kernel@lists.infradead.org
Cc: paulmck@linux.vnet.ibm.com
Link: http://lkml.kernel.org/r/1524738868-31318-6-git-send-email-will.deacon@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
'struct __qspinlock' provides a handy union of fields so that
subcomponents of the lockword can be accessed by name, without having to
manage shifts and masks explicitly and take endianness into account.
This is useful in qspinlock.h and also potentially in arch headers, so
move the 'struct __qspinlock' into 'struct qspinlock' and kill the extra
definition.
Signed-off-by: Will Deacon <will.deacon@arm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Waiman Long <longman@redhat.com>
Acked-by: Boqun Feng <boqun.feng@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-arm-kernel@lists.infradead.org
Cc: paulmck@linux.vnet.ibm.com
Link: http://lkml.kernel.org/r/1524738868-31318-3-git-send-email-will.deacon@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Currently, all the lock waiters entering the slowpath will do one
lock stealing attempt to acquire the lock. That helps performance,
especially in VMs with over-committed vCPUs. However, the current
pvqspinlocks still don't perform as good as unfair locks in many cases.
On the other hands, unfair locks do have the problem of lock starvation
that pvqspinlocks don't have.
This patch combines the best attributes of an unfair lock and a
pvqspinlock into a hybrid lock with 2 modes - queued mode & unfair
mode. A lock waiter goes into the unfair mode when there are waiters
in the wait queue but the pending bit isn't set. Otherwise, it will
go into the queued mode waiting in the queue for its turn.
On a 2-socket 36-core E5-2699 v3 system (HT off), a kernel build
(make -j<n>) was done in a VM with unpinned vCPUs 3 times with the
best time selected and <n> is the number of vCPUs available. The build
times of the original pvqspinlock, hybrid pvqspinlock and unfair lock
with various number of vCPUs are as follows:
vCPUs pvqlock hybrid pvqlock unfair lock
----- ------- -------------- -----------
30 342.1s 329.1s 329.1s
36 314.1s 305.3s 307.3s
45 345.0s 302.1s 306.6s
54 365.4s 308.6s 307.8s
72 358.9s 293.6s 303.9s
108 343.0s 285.9s 304.2s
The hybrid pvqspinlock performs better or comparable to the unfair
lock.
By turning on QUEUED_LOCK_STAT, the table below showed the number
of lock acquisitions in unfair mode and queue mode after a kernel
build with various number of vCPUs.
vCPUs queued mode unfair mode
----- ----------- -----------
30 9,130,518 294,954
36 10,856,614 386,809
45 8,467,264 11,475,373
54 6,409,987 19,670,855
72 4,782,063 25,712,180
It can be seen that as the VM became more and more over-committed,
the ratio of locks acquired in unfair mode increases. This is all
done automatically to get the best overall performance as possible.
Using a kernel locking microbenchmark with number of locking
threads equals to the number of vCPUs available on the same machine,
the minimum, average and maximum (min/avg/max) numbers of locking
operations done per thread in a 5-second testing interval are shown
below:
vCPUs hybrid pvqlock unfair lock
----- -------------- -----------
36 822,135/881,063/950,363 75,570/313,496/ 690,465
54 542,435/581,664/625,937 35,460/204,280/ 457,172
72 397,500/428,177/499,299 17,933/150,679/ 708,001
108 257,898/288,150/340,871 3,085/181,176/1,257,109
It can be seen that the hybrid pvqspinlocks are more fair and
performant than the unfair locks in this test.
The table below shows the kernel build times on a smaller 2-socket
16-core 32-thread E5-2620 v4 system.
vCPUs pvqlock hybrid pvqlock unfair lock
----- ------- -------------- -----------
16 436.8s 433.4s 435.6s
36 366.2s 364.8s 364.5s
48 423.6s 376.3s 370.2s
64 433.1s 376.6s 376.8s
Again, the performance of the hybrid pvqspinlock was comparable to
that of the unfair lock.
Signed-off-by: Waiman Long <longman@redhat.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Eduardo Valentin <eduval@amazon.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1510089486-3466-1-git-send-email-longman@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Many source files in the tree are missing licensing information, which
makes it harder for compliance tools to determine the correct license.
By default all files without license information are under the default
license of the kernel, which is GPL version 2.
Update the files which contain no license information with the 'GPL-2.0'
SPDX license identifier. The SPDX identifier is a legally binding
shorthand, which can be used instead of the full boiler plate text.
This patch is based on work done by Thomas Gleixner and Kate Stewart and
Philippe Ombredanne.
How this work was done:
Patches were generated and checked against linux-4.14-rc6 for a subset of
the use cases:
- file had no licensing information it it.
- file was a */uapi/* one with no licensing information in it,
- file was a */uapi/* one with existing licensing information,
Further patches will be generated in subsequent months to fix up cases
where non-standard license headers were used, and references to license
had to be inferred by heuristics based on keywords.
The analysis to determine which SPDX License Identifier to be applied to
a file was done in a spreadsheet of side by side results from of the
output of two independent scanners (ScanCode & Windriver) producing SPDX
tag:value files created by Philippe Ombredanne. Philippe prepared the
base worksheet, and did an initial spot review of a few 1000 files.
The 4.13 kernel was the starting point of the analysis with 60,537 files
assessed. Kate Stewart did a file by file comparison of the scanner
results in the spreadsheet to determine which SPDX license identifier(s)
to be applied to the file. She confirmed any determination that was not
immediately clear with lawyers working with the Linux Foundation.
Criteria used to select files for SPDX license identifier tagging was:
- Files considered eligible had to be source code files.
- Make and config files were included as candidates if they contained >5
lines of source
- File already had some variant of a license header in it (even if <5
lines).
All documentation files were explicitly excluded.
The following heuristics were used to determine which SPDX license
identifiers to apply.
- when both scanners couldn't find any license traces, file was
considered to have no license information in it, and the top level
COPYING file license applied.
For non */uapi/* files that summary was:
SPDX license identifier # files
---------------------------------------------------|-------
GPL-2.0 11139
and resulted in the first patch in this series.
If that file was a */uapi/* path one, it was "GPL-2.0 WITH
Linux-syscall-note" otherwise it was "GPL-2.0". Results of that was:
SPDX license identifier # files
---------------------------------------------------|-------
GPL-2.0 WITH Linux-syscall-note 930
and resulted in the second patch in this series.
- if a file had some form of licensing information in it, and was one
of the */uapi/* ones, it was denoted with the Linux-syscall-note if
any GPL family license was found in the file or had no licensing in
it (per prior point). Results summary:
SPDX license identifier # files
---------------------------------------------------|------
GPL-2.0 WITH Linux-syscall-note 270
GPL-2.0+ WITH Linux-syscall-note 169
((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) 21
((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) 17
LGPL-2.1+ WITH Linux-syscall-note 15
GPL-1.0+ WITH Linux-syscall-note 14
((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause) 5
LGPL-2.0+ WITH Linux-syscall-note 4
LGPL-2.1 WITH Linux-syscall-note 3
((GPL-2.0 WITH Linux-syscall-note) OR MIT) 3
((GPL-2.0 WITH Linux-syscall-note) AND MIT) 1
and that resulted in the third patch in this series.
- when the two scanners agreed on the detected license(s), that became
the concluded license(s).
- when there was disagreement between the two scanners (one detected a
license but the other didn't, or they both detected different
licenses) a manual inspection of the file occurred.
- In most cases a manual inspection of the information in the file
resulted in a clear resolution of the license that should apply (and
which scanner probably needed to revisit its heuristics).
- When it was not immediately clear, the license identifier was
confirmed with lawyers working with the Linux Foundation.
- If there was any question as to the appropriate license identifier,
the file was flagged for further research and to be revisited later
in time.
In total, over 70 hours of logged manual review was done on the
spreadsheet to determine the SPDX license identifiers to apply to the
source files by Kate, Philippe, Thomas and, in some cases, confirmation
by lawyers working with the Linux Foundation.
Kate also obtained a third independent scan of the 4.13 code base from
FOSSology, and compared selected files where the other two scanners
disagreed against that SPDX file, to see if there was new insights. The
Windriver scanner is based on an older version of FOSSology in part, so
they are related.
Thomas did random spot checks in about 500 files from the spreadsheets
for the uapi headers and agreed with SPDX license identifier in the
files he inspected. For the non-uapi files Thomas did random spot checks
in about 15000 files.
In initial set of patches against 4.14-rc6, 3 files were found to have
copy/paste license identifier errors, and have been fixed to reflect the
correct identifier.
Additionally Philippe spent 10 hours this week doing a detailed manual
inspection and review of the 12,461 patched files from the initial patch
version early this week with:
- a full scancode scan run, collecting the matched texts, detected
license ids and scores
- reviewing anything where there was a license detected (about 500+
files) to ensure that the applied SPDX license was correct
- reviewing anything where there was no detection but the patch license
was not GPL-2.0 WITH Linux-syscall-note to ensure that the applied
SPDX license was correct
This produced a worksheet with 20 files needing minor correction. This
worksheet was then exported into 3 different .csv files for the
different types of files to be modified.
These .csv files were then reviewed by Greg. Thomas wrote a script to
parse the csv files and add the proper SPDX tag to the file, in the
format that the file expected. This script was further refined by Greg
based on the output to detect more types of files automatically and to
distinguish between header and source .c files (which need different
comment types.) Finally Greg ran the script using the .csv files to
generate the patches.
Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org>
Reviewed-by: Philippe Ombredanne <pombredanne@nexb.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
All the locking related cmpxchg's in the following functions are
replaced with the _acquire variants:
- pv_queued_spin_steal_lock()
- trylock_clear_pending()
This change should help performance on architectures that use LL/SC.
The cmpxchg in pv_kick_node() is replaced with a relaxed version
with explicit memory barrier to make sure that it is fully ordered
in the writing of next->lock and the reading of pn->state whether
the cmpxchg is a success or failure without affecting performance in
non-LL/SC architectures.
On a 2-socket 12-core 96-thread Power8 system with pvqspinlock
explicitly enabled, the performance of a locking microbenchmark
with and without this patch on a 4.13-rc4 kernel with Xinhui's PPC
qspinlock patch were as follows:
# of thread w/o patch with patch % Change
----------- --------- ---------- --------
8 5054.8 Mop/s 5209.4 Mop/s +3.1%
16 3985.0 Mop/s 4015.0 Mop/s +0.8%
32 2378.2 Mop/s 2396.0 Mop/s +0.7%
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrea Parri <parri.andrea@gmail.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Pan Xinhui <xinhui@linux.vnet.ibm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will.deacon@arm.com>
Link: http://lkml.kernel.org/r/1502741222-24360-1-git-send-email-longman@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
If prev node is not in running state or its vCPU is preempted, we can give
up our vCPU slices in pv_wait_node() ASAP.
Signed-off-by: Pan Xinhui <xinhui.pan@linux.vnet.ibm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: longman@redhat.com
Link: http://lkml.kernel.org/r/1484035006-6787-1-git-send-email-xinhui.pan@linux.vnet.ibm.com
[ Fixed typos in the changelog, removed ugly linebreak from the code. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Currently there are overlap in the pvqspinlock wait_again and
spurious_wakeup stat counters. Because of lock stealing, it is
no longer possible to accurately determine if spurious wakeup has
happened in the queue head. As they track both the queue node and
queue head status, it is also hard to tell how many of those comes
from the queue head and how many from the queue node.
This patch changes the accounting rules so that spurious wakeup is
only tracked in the queue node. The wait_again count, however, is
only tracked in the queue head when the vCPU failed to acquire the
lock after a vCPU kick. This should give a much better indication of
the wait-kick dynamics in the queue node and the queue head.
Signed-off-by: Waiman Long <Waiman.Long@hpe.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Douglas Hatch <doug.hatch@hpe.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Pan Xinhui <xinhui@linux.vnet.ibm.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Scott J Norton <scott.norton@hpe.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1464713631-1066-2-git-send-email-Waiman.Long@hpe.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Restructure pv_queued_spin_steal_lock() as I found it hard to read.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Waiman Long <waiman.long@hpe.com
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
When the lock holder vCPU is racing with the queue head:
CPU 0 (lock holder) CPU1 (queue head)
=================== =================
spin_lock(); spin_lock();
pv_kick_node(): pv_wait_head_or_lock():
if (!lp) {
lp = pv_hash(lock, pn);
xchg(&l->locked, _Q_SLOW_VAL);
}
WRITE_ONCE(pn->state, vcpu_halted);
cmpxchg(&pn->state,
vcpu_halted, vcpu_hashed);
WRITE_ONCE(l->locked, _Q_SLOW_VAL);
(void)pv_hash(lock, pn);
In this case, lock holder inserts the pv_node of queue head into the
hash table and set _Q_SLOW_VAL unnecessary. This patch avoids it by
restoring/setting vcpu_hashed state after failing adaptive locking
spinning.
Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Pan Xinhui <xinhui.pan@linux.vnet.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Waiman Long <Waiman.Long@hpe.com>
Link: http://lkml.kernel.org/r/1468484156-4521-1-git-send-email-wanpeng.li@hotmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
These functions have been deprecated for a while and there is only the
one user left, convert and kill.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will.deacon@arm.com>
Cc: linux-arch@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This patch enables the tracking of the number of slowpath locking
operations performed. This can be used to compare against the number
of lock stealing operations to see what percentage of locks are stolen
versus acquired via the regular slowpath.
Signed-off-by: Waiman Long <Waiman.Long@hpe.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Douglas Hatch <doug.hatch@hpe.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Scott J Norton <scott.norton@hpe.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1449778666-13593-2-git-send-email-Waiman.Long@hpe.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This patch moves the lock stealing count tracking code into
pv_queued_spin_steal_lock() instead of via a jacket function simplifying
the code.
Signed-off-by: Waiman Long <Waiman.Long@hpe.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Douglas Hatch <doug.hatch@hpe.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Scott J Norton <scott.norton@hpe.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1449778666-13593-3-git-send-email-Waiman.Long@hpe.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
In an overcommitted guest where some vCPUs have to be halted to make
forward progress in other areas, it is highly likely that a vCPU later
in the spinlock queue will be spinning while the ones earlier in the
queue would have been halted. The spinning in the later vCPUs is then
just a waste of precious CPU cycles because they are not going to
get the lock soon as the earlier ones have to be woken up and take
their turn to get the lock.
This patch implements an adaptive spinning mechanism where the vCPU
will call pv_wait() if the previous vCPU is not running.
Linux kernel builds were run in KVM guest on an 8-socket, 4
cores/socket Westmere-EX system and a 4-socket, 8 cores/socket
Haswell-EX system. Both systems are configured to have 32 physical
CPUs. The kernel build times before and after the patch were:
Westmere Haswell
Patch 32 vCPUs 48 vCPUs 32 vCPUs 48 vCPUs
----- -------- -------- -------- --------
Before patch 3m02.3s 5m00.2s 1m43.7s 3m03.5s
After patch 3m03.0s 4m37.5s 1m43.0s 2m47.2s
For 32 vCPUs, this patch doesn't cause any noticeable change in
performance. For 48 vCPUs (over-committed), there is about 8%
performance improvement.
Signed-off-by: Waiman Long <Waiman.Long@hpe.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Douglas Hatch <doug.hatch@hpe.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Scott J Norton <scott.norton@hpe.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1447114167-47185-8-git-send-email-Waiman.Long@hpe.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This patch allows one attempt for the lock waiter to steal the lock
when entering the PV slowpath. To prevent lock starvation, the pending
bit will be set by the queue head vCPU when it is in the active lock
spinning loop to disable any lock stealing attempt. This helps to
reduce the performance penalty caused by lock waiter preemption while
not having much of the downsides of a real unfair lock.
The pv_wait_head() function was renamed as pv_wait_head_or_lock()
as it was modified to acquire the lock before returning. This is
necessary because of possible lock stealing attempts from other tasks.
Linux kernel builds were run in KVM guest on an 8-socket, 4
cores/socket Westmere-EX system and a 4-socket, 8 cores/socket
Haswell-EX system. Both systems are configured to have 32 physical
CPUs. The kernel build times before and after the patch were:
Westmere Haswell
Patch 32 vCPUs 48 vCPUs 32 vCPUs 48 vCPUs
----- -------- -------- -------- --------
Before patch 3m15.6s 10m56.1s 1m44.1s 5m29.1s
After patch 3m02.3s 5m00.2s 1m43.7s 3m03.5s
For the overcommited case (48 vCPUs), this patch is able to reduce
kernel build time by more than 54% for Westmere and 44% for Haswell.
Signed-off-by: Waiman Long <Waiman.Long@hpe.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Douglas Hatch <doug.hatch@hpe.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Scott J Norton <scott.norton@hpe.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1447190336-53317-1-git-send-email-Waiman.Long@hpe.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This patch enables the accumulation of kicking and waiting related
PV qspinlock statistics when the new QUEUED_LOCK_STAT configuration
option is selected. It also enables the collection of data which
enable us to calculate the kicking and wakeup latencies which have
a heavy dependency on the CPUs being used.
The statistical counters are per-cpu variables to minimize the
performance overhead in their updates. These counters are exported
via the debugfs filesystem under the qlockstat directory. When the
corresponding debugfs files are read, summation and computing of the
required data are then performed.
The measured latencies for different CPUs are:
CPU Wakeup Kicking
--- ------ -------
Haswell-EX 63.6us 7.4us
Westmere-EX 67.6us 9.3us
The measured latencies varied a bit from run-to-run. The wakeup
latency is much higher than the kicking latency.
A sample of statistical counters after system bootup (with vCPU
overcommit) was:
pv_hash_hops=1.00
pv_kick_unlock=1148
pv_kick_wake=1146
pv_latency_kick=11040
pv_latency_wake=194840
pv_spurious_wakeup=7
pv_wait_again=4
pv_wait_head=23
pv_wait_node=1129
Signed-off-by: Waiman Long <Waiman.Long@hpe.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Douglas Hatch <doug.hatch@hpe.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Scott J Norton <scott.norton@hpe.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1447114167-47185-6-git-send-email-Waiman.Long@hpe.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The unlock function in queued spinlocks was optimized for better
performance on bare metal systems at the expense of virtualized guests.
For x86-64 systems, the unlock call needs to go through a
PV_CALLEE_SAVE_REGS_THUNK() which saves and restores 8 64-bit
registers before calling the real __pv_queued_spin_unlock()
function. The thunk code may also be in a separate cacheline from
__pv_queued_spin_unlock().
This patch optimizes the PV unlock code path by:
1) Moving the unlock slowpath code from the fastpath into a separate
__pv_queued_spin_unlock_slowpath() function to make the fastpath
as simple as possible..
2) For x86-64, hand-coded an assembly function to combine the register
saving thunk code with the fastpath code. Only registers that
are used in the fastpath will be saved and restored. If the
fastpath fails, the slowpath function will be called via another
PV_CALLEE_SAVE_REGS_THUNK(). For 32-bit, it falls back to the C
__pv_queued_spin_unlock() code as the thunk saves and restores
only one 32-bit register.
With a microbenchmark of 5M lock-unlock loop, the table below shows
the execution times before and after the patch with different number
of threads in a VM running on a 32-core Westmere-EX box with x86-64
4.2-rc1 based kernels:
Threads Before patch After patch % Change
------- ------------ ----------- --------
1 134.1 ms 119.3 ms -11%
2 1286 ms 953 ms -26%
3 3715 ms 3480 ms -6.3%
4 4092 ms 3764 ms -8.0%
Signed-off-by: Waiman Long <Waiman.Long@hpe.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Douglas Hatch <doug.hatch@hpe.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Scott J Norton <scott.norton@hpe.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1447114167-47185-5-git-send-email-Waiman.Long@hpe.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
If _Q_SLOW_VAL has been set, the vCPU state must have been vcpu_hashed.
The extra check at the end of __pv_queued_spin_unlock() is unnecessary
and can be removed.
Signed-off-by: Waiman Long <Waiman.Long@hpe.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Davidlohr Bueso <dave@stgolabs.net>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Douglas Hatch <doug.hatch@hp.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Scott J Norton <scott.norton@hp.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1441996658-62854-3-git-send-email-Waiman.Long@hpe.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
For an over-committed guest with more vCPUs than physical CPUs
available, it is possible that a vCPU may be kicked twice before
getting the lock - once before it becomes queue head and once again
before it gets the lock. All these CPU kicking and halting (VMEXIT)
can be expensive and slow down system performance.
This patch adds a new vCPU state (vcpu_hashed) which enables the code
to delay CPU kicking until at unlock time. Once this state is set,
the new lock holder will set _Q_SLOW_VAL and fill in the hash table
on behalf of the halted queue head vCPU. The original vcpu_halted
state will be used by pv_wait_node() only to differentiate other
queue nodes from the qeue head.
Signed-off-by: Waiman Long <Waiman.Long@hp.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Douglas Hatch <doug.hatch@hp.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Scott J Norton <scott.norton@hp.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1436647018-49734-2-git-send-email-Waiman.Long@hp.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
When we unlock in __pv_queued_spin_unlock(), a failed cmpxchg() on the lock
value indicates that we need to take the slow-path and unhash the
corresponding node blocked on the lock.
Since a failed cmpxchg() does not provide any memory-ordering guarantees,
it is possible that the node data could be read before the cmpxchg() on
weakly-ordered architectures and therefore return a stale value, leading
to hash corruption and/or a BUG().
This patch adds an smb_rmb() following the failed cmpxchg operation, so
that the unhashing is ordered after the lock has been checked.
Reported-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
[ Added more comments]
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Waiman Long <Waiman.Long@hp.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Paul McKenney <paulmck@linux.vnet.ibm.com>
Cc: Steve Capper <Steve.Capper@arm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20150713155830.GL2632@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
- Rename the on-stack variable to match the datastructure variable,
- place the cmpxchg back under the comment that explains it,
- clean up the WARN() statement to avoid superfluous conditionals
and line-breaks.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Waiman Long <Waiman.Long@hp.com>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Enabling locking-selftest in a VM guest may cause the following
kernel panic:
kernel BUG at .../kernel/locking/qspinlock_paravirt.h:137!
This is due to the fact that the pvqspinlock unlock function is
expecting either a _Q_LOCKED_VAL or _Q_SLOW_VAL in the lock
byte. This patch prevents that bug report by ignoring it when
debug_locks_silent is set. Otherwise, a warning will be printed
if it contains an unexpected value.
With this patch applied, the kernel locking-selftest completed
without any noise.
Tested-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Signed-off-by: Waiman Long <Waiman.Long@hp.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1436663959-53092-1-git-send-email-Waiman.Long@hp.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Since set_mb() is really about an smp_mb() -- not a IO/DMA barrier
like mb() rename it to match the recent smp_load_acquire() and
smp_store_release().
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The xchg() function was used in pv_wait_node() to set a certain
value and provide a memory barrier which is what the set_mb()
function is for. This patch replaces the xchg() call by
set_mb().
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Waiman Long <Waiman.Long@hp.com>
Cc: Douglas Hatch <doug.hatch@hp.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Scott J Norton <scott.norton@hp.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Provide a separate (second) version of the spin_lock_slowpath for
paravirt along with a special unlock path.
The second slowpath is generated by adding a few pv hooks to the
normal slowpath, but where those will compile away for the native
case, they expand into special wait/wake code for the pv version.
The actual MCS queue can use extra storage in the mcs_nodes[] array to
keep track of state and therefore uses directed wakeups.
The head contender has no such storage directly visible to the
unlocker. So the unlocker searches a hash table with open addressing
using a simple binary Galois linear feedback shift register.
Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Waiman Long <Waiman.Long@hp.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Daniel J Blueman <daniel@numascale.com>
Cc: David Vrabel <david.vrabel@citrix.com>
Cc: Douglas Hatch <doug.hatch@hp.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Paolo Bonzini <paolo.bonzini@gmail.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Scott J Norton <scott.norton@hp.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1429901803-29771-9-git-send-email-Waiman.Long@hp.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
