Message-ID: <20090409155200.32740.19358.stgit@dev.haskins.net>
Date:	Thu, 09 Apr 2009 12:30:41 -0400
From:	Gregory Haskins <ghaskins@...ell.com>
To:	linux-kernel@...r.kernel.org
Cc:	agraf@...e.de, pmullaney@...ell.com, pmorreale@...ell.com,
	anthony@...emonkey.ws, rusty@...tcorp.com.au,
	netdev@...r.kernel.org, kvm@...r.kernel.org, avi@...hat.com,
	bhutchings@...arflare.com, andi@...stfloor.org, gregkh@...e.de,
	herber@...dor.apana.org.au, chrisw@...s-sol.org,
	shemminger@...tta.com
Subject: [RFC PATCH v2 00/19] virtual-bus

This is release v2.  Changes since v1:

*) Incorporated review feedback from Stephen Hemminger on vbus-enet driver
*) Added support for connecting to vbus devices from userspace
*) Added support for a virtio-vbus transport to allow virtio drivers to
   work with vbus (needs testing and backend models).

(Avi, I know I still owe you a reply re the PCI debate)

Todo:
*) Develop some kind of hypercall registration mechanism for KVM so that
   we can use that as an integration point instead of directly hooking
   kvm hypercalls
*) Beef up the userspace event channel ABI to support different event types
*) Add memory-registration support
*) Integrate with qemu PCI device model to render vbus objects as PCI
*) Develop some virtio backend devices.
*) Support ethtool_ops for venet.

---------------------------------------

RFC: Virtual-bus

applies to v2.6.29 (will port to git HEAD soon)

FIRST OFF: Let me state that this is _not_ a KVM or networking specific
technology.  Virtual-Bus is a mechanism for defining and deploying
software “devices” directly in a Linux kernel.  These devices are designed
to be directly accessed from a variety of environments in an arbitrarly nested
fashion.  The goal is provide for the potential for maxium IO performance by
providing the shortest and most efficient path to the "bare metal" kernel, and
thus the actual IO resources.  For instance, an application can be written to
run the same on baremetal as it does in guest userspace nested 10 levels deep,
all the while providing direct access to the resource, thus reducing latency
and boosting throughput.  A good way to think of this is perhaps like software
based SR-IOV that supports nesting of the pass-through.

Due to its design as an in-kernel resource, it also provides very strong
notions of protection and isolation so as to not introduce a security
compromise when compared to traditional/alternative models where such
guarantees are provided by something like userspace or hardware.

The example use-case we have provided supports a “virtual-ethernet” device
being utilized in a KVM guest environment, so comparisons to virtio-net will
be natural. However, please note that this is but one use-case, of many we have
planned for the future (such as userspace bypass and RT guest support).
The goal for right now is to describe what a virual-bus is and why we
believe it is useful.

We are intent to get this core technology merged, even if the networking
components are not accepted as is.  It should be noted that, in many ways,
virtio could be considered complimentary to the technology.  We could
in fact, have implemented the virtual-ethernet using a virtio-ring, but
it would have required ABI changes that we didn't want to yet propose
without having the concept in general vetted and accepted by the community.

[Update: this release includes a virtio-vbus transport, so virtio-net and
other such drivers can now run over vbus in addition to the venet system
provided]

To cut to the chase, we recently measured our virtual-ethernet on 
v2.6.29 on two 8-core x86_64 boxes with Chelsio T3 10GE connected back
to back via cross over.  We measured bare-metal performance, as well
as a kvm guest (running the same kernel) connected to the T3 via
a linux-bridge+tap configuration with a 1500 MTU.  The results are as
follows:

Bare metal: tput = 4078Mb/s, round-trip = 25593pps (39us rtt)
Virtio-net: tput = 4003Mb/s, round-trip = 320pps (3125us rtt)
Venet: tput = 4050Mb/s, round-trip = 15255 (65us rtt)

As you can see, all three technologies can achieve (MTU limited) line-rate,
but the virtio-net solution is severely limited on the latency front (by a
factor of 48:1)

Note that the 320pps is technically artificially low in virtio-net, caused by a
a known design limitation to use a timer for tx-mitigation.  However, note that
even when removing the timer from the path the best we could achieve was
350us-450us of latency, and doing so causes the tput to drop to 1300Mb/s.
So even in this case, I think the in-kernel results presents a compelling
argument for the new model presented.

[Update: Anthony Ligouri is working on this userspace implementation problem
currently and has obtained significant performance gains by utilizing some of
the techniques we use in this patch set as well.  More details to come.]

When we jump to 9000 byte MTU, the situation looks similar

Bare metal: tput = 9717Mb/s, round-trip = 30396pps (33us rtt)
Virtio-net: tput = 4578Mb/s, round-trip = 249pps (4016us rtt)
Venet: tput = 5802Mb/s, round-trip = 15127 (66us rtt)

Note that even the throughput was slightly better in this test for venet, though
neither venet nor virtio-net could achieve line-rate.  I suspect some tuning may
allow these numbers to improve, TBD.

So with that said, lets jump into the description:

Virtual-Bus: What is it?
--------------------

Virtual-Bus is a kernel based IO resource container technology.  It is modeled
on a concept similar to the Linux Device-Model (LDM), where we have buses,
devices, and drivers as the primary actors.  However, VBUS has several
distinctions when contrasted with LDM:

  1) "Busses" in LDM are relatively static and global to the kernel (e.g.
     "PCI", "USB", etc).  VBUS buses are arbitrarily created and destroyed
     dynamically, and are not globally visible.  Instead they are defined as
     visible only to a specific subset of the system (the contained context).
  2) "Devices" in LDM are typically tangible physical (or sometimes logical)
     devices.  VBUS devices are purely software abstractions (which may or
     may not have one or more physical devices behind them).  Devices may
     also be arbitrarily created or destroyed by software/administrative action
     as opposed to by a hardware discovery mechanism.
  3) "Drivers" in LDM sit within the same kernel context as the busses and
     devices they interact with.  VBUS drivers live in a foreign
     context (such as userspace, or a virtual-machine guest).

The idea is that a vbus is created to contain access to some IO services.
Virtual devices are then instantiated and linked to a bus to grant access to
drivers actively present on the bus.  Drivers will only have visibility to
devices present on their respective bus, and nothing else.

Virtual devices are defined by modules which register a deviceclass with the
system.  A deviceclass simply represents a type of device that _may_ be
instantiated into a device, should an administrator wish to do so.  Once
this has happened, the device may be associated with one or more buses where
it will become visible to all clients of those respective buses.

Why do we need this?
----------------------

There are various reasons why such a construct may be useful.  One of the
most interesting use cases is for virtualization, such as KVM.  Hypervisors
today provide virtualized IO resources to a guest, but this is often at a cost
in both latency and throughput compared to bare metal performance.  Utilizing
para-virtual resources instead of emulated devices helps to mitigate this
penalty, but even these techniques to date have not fully realized the
potential of the underlying bare-metal hardware.

Some of the performance differential is unavoidable just given the extra
processing that occurs due to the deeper stack (guest+host).  However, some of
this overhead is a direct result of the rather indirect path most hypervisors
use to route IO.  For instance, KVM uses PIO faults from the guest to trigger
a guest->host-kernel->host-userspace->host-kernel sequence of events.
Contrast this to a typical userspace application on the host which must only
traverse app->kernel for most IO.

The fact is that the linux kernel is already great at managing access to IO
resources.  Therefore, if you have a hypervisor that is based on the linux
kernel, is there some way that we can allow the hypervisor to manage IO
directly instead of forcing this convoluted path?

The short answer is: "not yet" ;)

In order to use such a concept, we need some new facilties.  For one, we
need to be able to define containers with their corresponding access-control so
that guests do not have unmitigated access to anything they wish.  Second,
we also need to define some forms of memory access that is uniform in the face
of various clients (e.g. "copy_to_user()" cannot be assumed to work for, say,
a KVM vcpu context).  Lastly, we need to provide access to these resources in
a way that makes sense for the application, such as asynchronous communication
paths and minimizing context switches.

For more details, please visit our wiki at:

http://developer.novell.com/wiki/index.php/Virtual-bus

Regards,
-Greg

---

Gregory Haskins (19):
      virtio: add a vbus transport
      vbus: add a userspace connector
      kvm: Add guest-side support for VBUS
      kvm: Add VBUS support to the host
      kvm: add dynamic IRQ support
      kvm: add a reset capability
      x86: allow the irq->vector translation to be determined outside of ioapic
      venettap: add scatter-gather support
      venet: add scatter-gather support
      venet-tap: Adds a "venet" compatible "tap" device to VBUS
      net: Add vbus_enet driver
      venet: add the ABI definitions for an 802.x packet interface
      ioq: add vbus helpers
      ioq: Add basic definitions for a shared-memory, lockless queue
      vbus: add a "vbus-proxy" bus model for vbus_driver objects
      vbus: add bus-registration notifiers
      vbus: add connection-client helper infrastructure
      vbus: add virtual-bus definitions
      shm-signal: shared-memory signals


 Documentation/vbus.txt           |  386 +++++++++
 arch/x86/Kconfig                 |   16 
 arch/x86/Makefile                |    3 
 arch/x86/include/asm/irq.h       |    6 
 arch/x86/include/asm/kvm_host.h  |    9 
 arch/x86/include/asm/kvm_para.h  |   12 
 arch/x86/kernel/io_apic.c        |   25 +
 arch/x86/kvm/Kconfig             |    9 
 arch/x86/kvm/Makefile            |    6 
 arch/x86/kvm/dynirq.c            |  329 ++++++++
 arch/x86/kvm/guest/Makefile      |    2 
 arch/x86/kvm/guest/dynirq.c      |   95 ++
 arch/x86/kvm/x86.c               |   13 
 arch/x86/kvm/x86.h               |   12 
 drivers/Makefile                 |    2 
 drivers/net/Kconfig              |   13 
 drivers/net/Makefile             |    1 
 drivers/net/vbus-enet.c          |  907 +++++++++++++++++++++
 drivers/vbus/devices/Kconfig     |   17 
 drivers/vbus/devices/Makefile    |    1 
 drivers/vbus/devices/venet-tap.c | 1609 ++++++++++++++++++++++++++++++++++++++
 drivers/vbus/proxy/Makefile      |    2 
 drivers/vbus/proxy/kvm.c         |  726 +++++++++++++++++
 drivers/virtio/Kconfig           |   15 
 drivers/virtio/Makefile          |    1 
 drivers/virtio/virtio_vbus.c     |  496 ++++++++++++
 fs/proc/base.c                   |   96 ++
 include/linux/ioq.h              |  410 ++++++++++
 include/linux/kvm.h              |    4 
 include/linux/kvm_guest.h        |    7 
 include/linux/kvm_host.h         |   27 +
 include/linux/kvm_para.h         |   60 +
 include/linux/sched.h            |    4 
 include/linux/shm_signal.h       |  188 ++++
 include/linux/vbus.h             |  166 ++++
 include/linux/vbus_client.h      |  115 +++
 include/linux/vbus_device.h      |  424 ++++++++++
 include/linux/vbus_driver.h      |   80 ++
 include/linux/vbus_userspace.h   |   48 +
 include/linux/venet.h            |   82 ++
 include/linux/virtio_vbus.h      |  163 ++++
 kernel/Makefile                  |    1 
 kernel/exit.c                    |    2 
 kernel/fork.c                    |    2 
 kernel/vbus/Kconfig              |   55 +
 kernel/vbus/Makefile             |   11 
 kernel/vbus/attribute.c          |   52 +
 kernel/vbus/client.c             |  543 +++++++++++++
 kernel/vbus/config.c             |  275 ++++++
 kernel/vbus/core.c               |  626 +++++++++++++++
 kernel/vbus/devclass.c           |  124 +++
 kernel/vbus/map.c                |   72 ++
 kernel/vbus/map.h                |   41 +
 kernel/vbus/proxy.c              |  216 +++++
 kernel/vbus/shm-ioq.c            |   89 ++
 kernel/vbus/userspace-client.c   |  485 +++++++++++
 kernel/vbus/vbus.h               |  117 +++
 kernel/vbus/virtio.c             |  628 +++++++++++++++
 lib/Kconfig                      |   22 +
 lib/Makefile                     |    2 
 lib/ioq.c                        |  298 +++++++
 lib/shm_signal.c                 |  186 ++++
 virt/kvm/kvm_main.c              |   37 +
 virt/kvm/vbus.c                  | 1307 +++++++++++++++++++++++++++++++
 64 files changed, 11777 insertions(+), 1 deletions(-)
 create mode 100644 Documentation/vbus.txt
 create mode 100644 arch/x86/kvm/dynirq.c
 create mode 100644 arch/x86/kvm/guest/Makefile
 create mode 100644 arch/x86/kvm/guest/dynirq.c
 create mode 100644 drivers/net/vbus-enet.c
 create mode 100644 drivers/vbus/devices/Kconfig
 create mode 100644 drivers/vbus/devices/Makefile
 create mode 100644 drivers/vbus/devices/venet-tap.c
 create mode 100644 drivers/vbus/proxy/Makefile
 create mode 100644 drivers/vbus/proxy/kvm.c
 create mode 100644 drivers/virtio/virtio_vbus.c
 create mode 100644 include/linux/ioq.h
 create mode 100644 include/linux/kvm_guest.h
 create mode 100644 include/linux/shm_signal.h
 create mode 100644 include/linux/vbus.h
 create mode 100644 include/linux/vbus_client.h
 create mode 100644 include/linux/vbus_device.h
 create mode 100644 include/linux/vbus_driver.h
 create mode 100644 include/linux/vbus_userspace.h
 create mode 100644 include/linux/venet.h
 create mode 100644 include/linux/virtio_vbus.h
 create mode 100644 kernel/vbus/Kconfig
 create mode 100644 kernel/vbus/Makefile
 create mode 100644 kernel/vbus/attribute.c
 create mode 100644 kernel/vbus/client.c
 create mode 100644 kernel/vbus/config.c
 create mode 100644 kernel/vbus/core.c
 create mode 100644 kernel/vbus/devclass.c
 create mode 100644 kernel/vbus/map.c
 create mode 100644 kernel/vbus/map.h
 create mode 100644 kernel/vbus/proxy.c
 create mode 100644 kernel/vbus/shm-ioq.c
 create mode 100644 kernel/vbus/userspace-client.c
 create mode 100644 kernel/vbus/vbus.h
 create mode 100644 kernel/vbus/virtio.c
 create mode 100644 lib/ioq.c
 create mode 100644 lib/shm_signal.c
 create mode 100644 virt/kvm/vbus.c

-- 

--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Powered by blists - more mailing lists