From patchwork Fri Jun 18 04:48:17 2021
ContentType: text/plain; charset="utf8"
MIMEVersion: 1.0
ContentTransferEncoding: 7bit
XPatchworkSubmitter: Jing Zhang
XPatchworkId: 12330115
ReturnPath:
XSpamCheckerVersion: SpamAssassin 3.4.0 (20140207) on
awsuswest2korglkml1.web.codeaurora.org
XSpamLevel:
XSpamStatus: No, score=26.3 required=3.0 tests=BAYES_00,DKIMWL_WL_MED,
DKIM_SIGNED,DKIM_VALID,DKIM_VALID_AU,HEADER_FROM_DIFFERENT_DOMAINS,
INCLUDES_CR_TRAILER,INCLUDES_PATCH,MAILING_LIST_MULTI,SPF_HELO_NONE,SPF_PASS,
USER_AGENT_GIT,USER_IN_DEF_DKIM_WL autolearn=unavailable autolearn_force=no
version=3.4.0
Received: from mail.kernel.org (mail.kernel.org [198.145.29.99])
by smtp.lore.kernel.org (Postfix) with ESMTP id 1328EC49EA2
for ; Fri, 18 Jun 2021 04:48:41 +0000 (UTC)
Received: from vger.kernel.org (vger.kernel.org [23.128.96.18])
by mail.kernel.org (Postfix) with ESMTP id E3247611CE
for ; Fri, 18 Jun 2021 04:48:40 +0000 (UTC)
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
id S232359AbhFREus (ORCPT );
Fri, 18 Jun 2021 00:50:48 0400
Received: from lindbergh.monkeyblade.net ([23.128.96.19]:56272 "EHLO
lindbergh.monkeyblade.net" rhostflagsOKOKOKOK) by vger.kernel.org
with ESMTP id S232357AbhFREun (ORCPT );
Fri, 18 Jun 2021 00:50:43 0400
Received: from mailpg1x549.google.com (mailpg1x549.google.com
[IPv6:2607:f8b0:4864:20::549])
by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 05FB9C061283
for ; Thu, 17 Jun 2021 21:48:32 0700 (PDT)
Received: by mailpg1x549.google.com with SMTP id
v18620020a632fc30000b029022192d6757dso5192370pgv.22
for ; Thu, 17 Jun 2021 21:48:32 0700 (PDT)
DKIMSignature: v=1; a=rsasha256; c=relaxed/relaxed;
d=google.com; s=20161025;
h=date:inreplyto:messageid:mimeversion:references:subject:from:to
:cc;
bh=ACDlgMuXCZDsetX7KRhrcOX3+jjuxXZRreYDTT75YTU=;
b=JCC/DbH8et+zeP3tBTw3UT+39oOBrX/FGV9hMQ2NwQkQNp1Uur1QpgQfJ8QnvjuJEz
XCSk32Gua/LrNCyC01iwzIygcv1uUSWLJStfqCtBcgrxj78PosE3yB2K1P09lRTAcPiC
kPZb+ar3PsVVvQQonl5zP/IIFpM1Pes+3CKHK/0poH7MOZSENcd+43zX3m7JF/LuylXK
XVyp3av2emtCJpsjrV22r/1QGgInxeNpmvDiP9CQyRVeLYosnOUjUStt7LzqEDroRQHD
fGpXFDW1QIW2ThjvzoMerJinwtYfLgQgQxbyOTz56g9g9EkmE38016p15WuEvJq3Qkgf
j4tg==
XGoogleDKIMSignature: v=1; a=rsasha256; c=relaxed/relaxed;
d=1e100.net; s=20161025;
h=xgmmessagestate:date:inreplyto:messageid:mimeversion
:references:subject:from:to:cc;
bh=ACDlgMuXCZDsetX7KRhrcOX3+jjuxXZRreYDTT75YTU=;
b=ZDEhIfRzVJL3rEu3lhiKtCAoUFgHz2Fh8gnibmkMh62Q09LLfvtSA8TcLoEjkGAZee
NbNUAWzG445iSGWLeMINwvTqT80jl7qA2ieY+A8OWrWIGW7ovJayDXu/q33rP3yWdku8
OjF67MBWSBt68UmKIR2cFJ0RS4M7AhSC1efB2nC63vUoiIExeFeM2Z0YRoQ9wrfIQZZg
9kQ9AxrdeiByqLOm0gE4kHOfE40DO7t1BjBcu06mi64jyKn8oQ1iYrNDU4vrif1YiTYE
xVt2v3AUBJSJM6SV8a9+aim0W4hJr36q+iBnr6bbRs7D/1W9BnVfqG0/hRhcLQgfoyDe
vTIg==
XGmMessageState: AOAM532D/AaAr2quC5jJosbL2mO6AIuY4wp8xXlOXCCUYjfCryYeu9AT
knugoLLL30U7U7z94mQiDxoFzBQDpgSY0X8MbdF/0jNJ15Ll83Hc6eXIZCJNZCDdHa5aXQxh6Ma
dj48IlVCyf9tGEvYeUmM4ifO75DRXZV53LoKOsZLRUabWaEN6nvxCYXlfnawwSVcWcQ4hwvM=
XGoogleSmtpSource:
ABdhPJxjP7eUjIDRktqIzAkQNpt7aF6od26SEO+/ze1THLepoxd/AqNiFwUQ5wP1PcwM1RyWisRVUZGmqDu+Lc1EnA==
XReceived: from jgzg.c.googlers.com ([fda3:e722:ac3:10:7f:e700:c0a8:1acf])
(user=jingzhangos job=sendgmr) by 2002:a62:6490:0:b029:2f7:2fba:4d79 with
SMTP id y13820020a6264900000b02902f72fba4d79mr3204154pfb.29.1623991711344;
Thu, 17 Jun 2021 21:48:31 0700 (PDT)
Date: Fri, 18 Jun 2021 04:48:17 +0000
InReplyTo: <20210618044819.36901661jingzhangos@google.com>
MessageId: <20210618044819.36901666jingzhangos@google.com>
MimeVersion: 1.0
References: <20210618044819.36901661jingzhangos@google.com>
XMailer: gitsendemail 2.32.0.288.g62a8d224e6goog
Subject: [PATCH v11 5/7] KVM: stats: Add documentation for binary statistics
interface
From: Jing Zhang
To: KVM , KVMARM ,
LinuxMIPS ,
KVMPPC ,
LinuxS390 ,
Linuxkselftest ,
Paolo Bonzini ,
Marc Zyngier ,
James Morse ,
Julien Thierry ,
Suzuki K Poulose ,
Will Deacon ,
Huacai Chen ,
Aleksandar Markovic ,
Thomas Bogendoerfer ,
Paul Mackerras ,
Christian Borntraeger ,
Janosch Frank ,
David Hildenbrand ,
Cornelia Huck ,
Claudio Imbrenda ,
Sean Christopherson ,
Vitaly Kuznetsov ,
Jim Mattson ,
Peter Shier ,
Oliver Upton ,
David Rientjes ,
Emanuele Giuseppe Esposito ,
David Matlack ,
Ricardo Koller ,
Krish Sadhukhan ,
Fuad Tabba ,
Greg KH
Cc: Jing Zhang
Precedence: bulk
ListID:
XMailingList: kvm@vger.kernel.org
This new API provides a file descriptor for every VM and VCPU to read
KVM statistics data in binary format.
It is meant to provide a lightweight, flexible, scalable and efficient
lockfree solution for user space telemetry applications to pull the
statistics data periodically for large scale systems. The pulling
frequency could be as high as a few times per second.
The statistics descriptors are defined by KVM in kernel and can be
by userspace to discover VM/VCPU statistics during the onetime setup
stage.
The statistics data itself could be read out by userspace telemetry
periodically without any extra parsing or setup effort.
There are a few existed interface protocols and definitions, but no
one can fulfil all the requirements this interface implemented as
below:
1. During high frequency periodic stats reading, there should be no
extra efforts except the stats data read itself.
2. Support stats annotation, like type (cumulative, instantaneous,
peak, histogram, etc) and unit (counter, time, size, cycles, etc).
3. The stats data reading should be free of lock/synchronization. We
don't care about the consistency between all the stats data. All
stats data can not be read out at exactly the same time. We really
care about the change or trend of the stats data. The lockfree
solution is not just for efficiency and scalability, also for the
stats data accuracy and usability. For example, in the situation
that all the stats data readings are protected by a global lock,
if one VCPU died somehow with that lock held, then all stats data
reading would be blocked, then we have no way from stats data that
which VCPU has died.
4. The stats data reading workload can be handed over to other
unprivileged process.
Reviewedby: David Matlack
Reviewedby: Ricardo Koller
Reviewedby: Krish Sadhukhan
Reviewedby: Fuad Tabba
Signedoffby: Jing Zhang

Documentation/virt/kvm/api.rst  176 ++++++++++++++++++++++++++++++++
1 file changed, 175 insertions(+), 1 deletion()
diff git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index e328caa35d6c..7ca1c8d190c0 100644
 a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ 5034,7 +5034,6 @@ see KVM_XEN_VCPU_SET_ATTR above.
The KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST type may not be used
with the KVM_XEN_VCPU_GET_ATTR ioctl.

4.131 KVM_GET_SREGS2

@@ 5081,6 +5080,173 @@ Writes special registers into the vcpu.
See KVM_GET_SREGS2 for the data structures.
This ioctl (when supported) replaces the KVM_SET_SREGS.
+4.133 KVM_GET_STATS_FD
+
+
+:Capability: KVM_CAP_STATS_BINARY_FD
+:Architectures: all
+:Type: vm ioctl, vcpu ioctl
+:Parameters: none
+:Returns: statistics file descriptor on success, < 0 on error
+
+Errors:
+
+ ====== ======================================================
+ ENOMEM if the fd could not be created due to lack of memory
+ EMFILE if the number of opened files exceeds the limit
+ ====== ======================================================
+
+The file descriptor can be used to read VM/vCPU statistics data in binary
+format. The file data is organized into three blocks as below:
+++
+ Header 
+++
+ Descriptors 
+++
+ Stats Data 
+++
+
+The Header block is always at the start of the file. It is only needed to be
+read one time for the lifetime of the file descriptor.
+It is in the form of ``struct kvm_stats_header`` as below::
+
+ #define KVM_STATS_ID_MAXLEN 64
+
+ struct kvm_stats_header {
+ __u32 name_size;
+ __u32 count;
+ __u32 desc_offset;
+ __u32 data_offset;
+ char id[];
+ };
+
+The ``id`` field is a '\0' terminated string which identifies the corresponding
+KVM statistics. For VM statistics, it is in the form of "kvm{kvm pid}", like
+"kvm12345". For VCPU statistics, it is in the form of
+"kvm{kvm pid}/vcpu{vcpu id}", like "kvm12345/vcpu12".
+
+The ``name_size`` field is the size (in byte) of the statistics name string
+(including trailing '\0') appended to the end of every statistics descriptor.
+
+The ``count`` field is the number of statistics.
+
+The ``desc_offset`` field is the offset of the Descriptors block from the start
+of the file indicated by the file descriptor.
+
+The ``data_offset`` field is the offset of the Stats Data block from the start
+of the file indicated by the file descriptor.
+
+The Descriptors block is only needed to be read once for the lifetime of the
+file descriptor. It is an array of ``struct kvm_stats_desc`` as shown in
+below code block::
+
+ #define KVM_STATS_TYPE_SHIFT 0
+ #define KVM_STATS_TYPE_MASK (0xF << KVM_STATS_TYPE_SHIFT)
+ #define KVM_STATS_TYPE_CUMULATIVE (0x0 << KVM_STATS_TYPE_SHIFT)
+ #define KVM_STATS_TYPE_INSTANT (0x1 << KVM_STATS_TYPE_SHIFT)
+ #define KVM_STATS_TYPE_MAX KVM_STATS_TYPE_INSTANT
+
+ #define KVM_STATS_UNIT_SHIFT 4
+ #define KVM_STATS_UNIT_MASK (0xF << KVM_STATS_UNIT_SHIFT)
+ #define KVM_STATS_UNIT_NONE (0x0 << KVM_STATS_UNIT_SHIFT)
+ #define KVM_STATS_UNIT_BYTES (0x1 << KVM_STATS_UNIT_SHIFT)
+ #define KVM_STATS_UNIT_SECONDS (0x2 << KVM_STATS_UNIT_SHIFT)
+ #define KVM_STATS_UNIT_CYCLES (0x3 << KVM_STATS_UNIT_SHIFT)
+ #define KVM_STATS_UNIT_MAX KVM_STATS_UNIT_CYCLES
+
+ #define KVM_STATS_BASE_SHIFT 8
+ #define KVM_STATS_BASE_MASK (0xF << KVM_STATS_BASE_SHIFT)
+ #define KVM_STATS_BASE_POW10 (0x0 << KVM_STATS_BASE_SHIFT)
+ #define KVM_STATS_BASE_POW2 (0x1 << KVM_STATS_BASE_SHIFT)
+ #define KVM_STATS_BASE_MAX KVM_STATS_BASE_POW2
+
+ struct kvm_stats_desc {
+ __u32 flags;
+ __s16 exponent;
+ __u16 size;
+ __u32 offset;
+ __u32 unused;
+ char name[];
+ };
+
+The ``flags`` field contains the type and unit of the statistics data described
+by this descriptor. Its endianness is CPU native.
+The following flags are supported:
+
+Bits 03 of ``flags`` encode the type:
+ * ``KVM_STATS_TYPE_CUMULATIVE``
+ The statistics data is cumulative. The value of data can only be increased.
+ Most of the counters used in KVM are of this type.
+ The corresponding ``count`` field for this type is always 1.
+ * ``KVM_STATS_TYPE_INSTANT``
+ The statistics data is instantaneous. Its value can be increased or
+ decreased. This type is usually used as a measurement of some resources,
+ like the number of dirty pages, the number of large pages, etc.
+ The corresponding ``count`` field for this type is always 1.
+
+Bits 47 of ``flags`` encode the unit:
+ * ``KVM_STATS_UNIT_NONE``
+ There is no unit for the value of statistics data. This usually means that
+ the value is a simple counter of an event.
+ * ``KVM_STATS_UNIT_BYTES``
+ It indicates that the statistics data is used to measure memory size, in the
+ unit of Byte, KiByte, MiByte, GiByte, etc. The unit of the data is
+ determined by the ``exponent`` field in the descriptor. The
+ ``KVM_STATS_BASE_POW2`` flag is valid in this case. The unit of the data is
+ determined by ``pow(2, exponent)``. For example, if value is 10,
+ ``exponent`` is 20, which means the unit of statistics data is MiByte, we
+ can get the statistics data in the unit of Byte by
+ ``value * pow(2, exponent) = 10 * pow(2, 20) = 10 MiByte`` which is
+ 10 * 1024 * 1024 Bytes.
+ * ``KVM_STATS_UNIT_SECONDS``
+ It indicates that the statistics data is used to measure time/latency, in
+ the unit of nanosecond, microsecond, millisecond and second. The unit of the
+ data is determined by the ``exponent`` field in the descriptor. The
+ ``KVM_STATS_BASE_POW10`` flag is valid in this case. The unit of the data
+ is determined by ``pow(10, exponent)``. For example, if value is 2000000,
+ ``exponent`` is 6, which means the unit of statistics data is microsecond,
+ we can get the statistics data in the unit of second by
+ ``value * pow(10, exponent) = 2000000 * pow(10, 6) = 2 seconds``.
+ * ``KVM_STATS_UNIT_CYCLES``
+ It indicates that the statistics data is used to measure CPU clock cycles.
+ The ``KVM_STATS_BASE_POW10`` flag is valid in this case. For example, if
+ value is 200, ``exponent`` is 4, we can get the number of CPU clock cycles
+ by ``value * pow(10, exponent) = 200 * pow(10, 4) = 2000000``.
+
+Bits 811 of ``flags`` encode the base:
+ * ``KVM_STATS_BASE_POW10``
+ The scale is based on power of 10. It is used for measurement of time and
+ CPU clock cycles.
+ * ``KVM_STATS_BASE_POW2``
+ The scale is based on power of 2. It is used for measurement of memory size.
+
+The ``exponent`` field is the scale of corresponding statistics data. For
+example, if the unit is ``KVM_STATS_UNIT_BYTES``, the base is
+``KVM_STATS_BASE_POW2``, the ``exponent`` is 10, then we know that the real
+unit of the statistics data is KBytes a.k.a pow(2, 10) = 1024 bytes.
+If the unit is ``KVM_STATS_UNIT_SECONDS``, the base is ``KVM_STATS_BASE_POW10``,
+the ``exponent`` is 6, then we know that the real unit of the statistics data
+is microsecond a.k.a 1 second * pow(10, 6) = 1 microsecond.
+
+The ``size`` field is the number of values of this statistics data. Its
+value is usually 1 for most of simple statistics. 1 means it contains an
+unsigned 64bit data.
+
+The ``offset`` field is the offset from the start of Data Block to the start of
+the corresponding statistics data.
+
+The ``unused`` fields are reserved for future support for other types of
+statistics data, like log/linear histogram. Its current value is always 0.
+
+The ``name`` field is the name string of the statistics data. The name string
+starts at the end of ``struct kvm_stats_desc``.
+The maximum length (including trailing '\0') is indicated by ``name_size``
+in ``struct kvm_stats_header``.
+
+The Stats Data block contains an array of statistics data whose type is __u64.
+It would be read out by userspace periodically.
+The order of data value in Stats Data block is the same as the order of
+descriptors in Descriptors block.
5. The kvm_run structure
========================
@@ 6969,3 +7135,11 @@ The argument to KVM_ENABLE_CAP is also a bitmask, and must be a subset
of the result of KVM_CHECK_EXTENSION. KVM will forward to userspace
the hypercalls whose corresponding bit is in the argument, and return
ENOSYS for the others.
+
+8.35 KVM_CAP_STATS_BINARY_FD
+
+
+:Architectures: all
+
+This capability indicates the feature that userspace can create get a file
+descriptor for every VM and VCPU to read statistics data in binary format.