vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
/* Copyright (C) 2009 Red Hat, Inc.
|
|
|
|
* Author: Michael S. Tsirkin <mst@redhat.com>
|
|
|
|
*
|
|
|
|
* This work is licensed under the terms of the GNU GPL, version 2.
|
|
|
|
*
|
|
|
|
* virtio-net server in host kernel.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include <linux/compat.h>
|
|
|
|
#include <linux/eventfd.h>
|
|
|
|
#include <linux/vhost.h>
|
|
|
|
#include <linux/virtio_net.h>
|
|
|
|
#include <linux/mmu_context.h>
|
|
|
|
#include <linux/miscdevice.h>
|
|
|
|
#include <linux/module.h>
|
|
|
|
#include <linux/mutex.h>
|
|
|
|
#include <linux/workqueue.h>
|
|
|
|
#include <linux/rcupdate.h>
|
|
|
|
#include <linux/file.h>
|
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files. percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.
percpu.h -> slab.h dependency is about to be removed. Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability. As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.
http://userweb.kernel.org/~tj/misc/slabh-sweep.py
The script does the followings.
* Scan files for gfp and slab usages and update includes such that
only the necessary includes are there. ie. if only gfp is used,
gfp.h, if slab is used, slab.h.
* When the script inserts a new include, it looks at the include
blocks and try to put the new include such that its order conforms
to its surrounding. It's put in the include block which contains
core kernel includes, in the same order that the rest are ordered -
alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
doesn't seem to be any matching order.
* If the script can't find a place to put a new include (mostly
because the file doesn't have fitting include block), it prints out
an error message indicating which .h file needs to be added to the
file.
The conversion was done in the following steps.
1. The initial automatic conversion of all .c files updated slightly
over 4000 files, deleting around 700 includes and adding ~480 gfp.h
and ~3000 slab.h inclusions. The script emitted errors for ~400
files.
2. Each error was manually checked. Some didn't need the inclusion,
some needed manual addition while adding it to implementation .h or
embedding .c file was more appropriate for others. This step added
inclusions to around 150 files.
3. The script was run again and the output was compared to the edits
from #2 to make sure no file was left behind.
4. Several build tests were done and a couple of problems were fixed.
e.g. lib/decompress_*.c used malloc/free() wrappers around slab
APIs requiring slab.h to be added manually.
5. The script was run on all .h files but without automatically
editing them as sprinkling gfp.h and slab.h inclusions around .h
files could easily lead to inclusion dependency hell. Most gfp.h
inclusion directives were ignored as stuff from gfp.h was usually
wildly available and often used in preprocessor macros. Each
slab.h inclusion directive was examined and added manually as
necessary.
6. percpu.h was updated not to include slab.h.
7. Build test were done on the following configurations and failures
were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my
distributed build env didn't work with gcov compiles) and a few
more options had to be turned off depending on archs to make things
build (like ipr on powerpc/64 which failed due to missing writeq).
* x86 and x86_64 UP and SMP allmodconfig and a custom test config.
* powerpc and powerpc64 SMP allmodconfig
* sparc and sparc64 SMP allmodconfig
* ia64 SMP allmodconfig
* s390 SMP allmodconfig
* alpha SMP allmodconfig
* um on x86_64 SMP allmodconfig
8. percpu.h modifications were reverted so that it could be applied as
a separate patch and serve as bisection point.
Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.
Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 01:04:11 -07:00
|
|
|
#include <linux/slab.h>
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
|
|
|
|
#include <linux/net.h>
|
|
|
|
#include <linux/if_packet.h>
|
|
|
|
#include <linux/if_arp.h>
|
|
|
|
#include <linux/if_tun.h>
|
2010-02-17 22:46:50 -07:00
|
|
|
#include <linux/if_macvlan.h>
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
|
|
|
|
#include <net/sock.h>
|
|
|
|
|
|
|
|
#include "vhost.h"
|
|
|
|
|
|
|
|
/* Max number of bytes transferred before requeueing the job.
|
|
|
|
* Using this limit prevents one virtqueue from starving others. */
|
|
|
|
#define VHOST_NET_WEIGHT 0x80000
|
|
|
|
|
|
|
|
enum {
|
|
|
|
VHOST_NET_VQ_RX = 0,
|
|
|
|
VHOST_NET_VQ_TX = 1,
|
|
|
|
VHOST_NET_VQ_MAX = 2,
|
|
|
|
};
|
|
|
|
|
|
|
|
enum vhost_net_poll_state {
|
|
|
|
VHOST_NET_POLL_DISABLED = 0,
|
|
|
|
VHOST_NET_POLL_STARTED = 1,
|
|
|
|
VHOST_NET_POLL_STOPPED = 2,
|
|
|
|
};
|
|
|
|
|
|
|
|
struct vhost_net {
|
|
|
|
struct vhost_dev dev;
|
|
|
|
struct vhost_virtqueue vqs[VHOST_NET_VQ_MAX];
|
|
|
|
struct vhost_poll poll[VHOST_NET_VQ_MAX];
|
|
|
|
/* Tells us whether we are polling a socket for TX.
|
|
|
|
* We only do this when socket buffer fills up.
|
|
|
|
* Protected by tx vq lock. */
|
|
|
|
enum vhost_net_poll_state tx_poll_state;
|
|
|
|
};
|
|
|
|
|
|
|
|
/* Pop first len bytes from iovec. Return number of segments used. */
|
|
|
|
static int move_iovec_hdr(struct iovec *from, struct iovec *to,
|
|
|
|
size_t len, int iov_count)
|
|
|
|
{
|
|
|
|
int seg = 0;
|
|
|
|
size_t size;
|
|
|
|
while (len && seg < iov_count) {
|
|
|
|
size = min(from->iov_len, len);
|
|
|
|
to->iov_base = from->iov_base;
|
|
|
|
to->iov_len = size;
|
|
|
|
from->iov_len -= size;
|
|
|
|
from->iov_base += size;
|
|
|
|
len -= size;
|
|
|
|
++from;
|
|
|
|
++to;
|
|
|
|
++seg;
|
|
|
|
}
|
|
|
|
return seg;
|
|
|
|
}
|
2010-07-27 08:52:21 -07:00
|
|
|
/* Copy iovec entries for len bytes from iovec. */
|
|
|
|
static void copy_iovec_hdr(const struct iovec *from, struct iovec *to,
|
|
|
|
size_t len, int iovcount)
|
|
|
|
{
|
|
|
|
int seg = 0;
|
|
|
|
size_t size;
|
|
|
|
while (len && seg < iovcount) {
|
|
|
|
size = min(from->iov_len, len);
|
|
|
|
to->iov_base = from->iov_base;
|
|
|
|
to->iov_len = size;
|
|
|
|
len -= size;
|
|
|
|
++from;
|
|
|
|
++to;
|
|
|
|
++seg;
|
|
|
|
}
|
|
|
|
}
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
|
|
|
|
/* Caller must have TX VQ lock */
|
|
|
|
static void tx_poll_stop(struct vhost_net *net)
|
|
|
|
{
|
|
|
|
if (likely(net->tx_poll_state != VHOST_NET_POLL_STARTED))
|
|
|
|
return;
|
|
|
|
vhost_poll_stop(net->poll + VHOST_NET_VQ_TX);
|
|
|
|
net->tx_poll_state = VHOST_NET_POLL_STOPPED;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Caller must have TX VQ lock */
|
|
|
|
static void tx_poll_start(struct vhost_net *net, struct socket *sock)
|
|
|
|
{
|
|
|
|
if (unlikely(net->tx_poll_state != VHOST_NET_POLL_STOPPED))
|
|
|
|
return;
|
|
|
|
vhost_poll_start(net->poll + VHOST_NET_VQ_TX, sock->file);
|
|
|
|
net->tx_poll_state = VHOST_NET_POLL_STARTED;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Expects to be always run from workqueue - which acts as
|
|
|
|
* read-size critical section for our kind of RCU. */
|
|
|
|
static void handle_tx(struct vhost_net *net)
|
|
|
|
{
|
|
|
|
struct vhost_virtqueue *vq = &net->dev.vqs[VHOST_NET_VQ_TX];
|
2010-06-24 06:59:59 -07:00
|
|
|
unsigned out, in, s;
|
|
|
|
int head;
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
struct msghdr msg = {
|
|
|
|
.msg_name = NULL,
|
|
|
|
.msg_namelen = 0,
|
|
|
|
.msg_control = NULL,
|
|
|
|
.msg_controllen = 0,
|
|
|
|
.msg_iov = vq->iov,
|
|
|
|
.msg_flags = MSG_DONTWAIT,
|
|
|
|
};
|
|
|
|
size_t len, total_len = 0;
|
|
|
|
int err, wmem;
|
|
|
|
size_t hdr_size;
|
|
|
|
struct socket *sock = rcu_dereference(vq->private_data);
|
|
|
|
if (!sock)
|
|
|
|
return;
|
|
|
|
|
|
|
|
wmem = atomic_read(&sock->sk->sk_wmem_alloc);
|
2010-02-28 10:39:16 -07:00
|
|
|
if (wmem >= sock->sk->sk_sndbuf) {
|
|
|
|
mutex_lock(&vq->mutex);
|
|
|
|
tx_poll_start(net, sock);
|
|
|
|
mutex_unlock(&vq->mutex);
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
return;
|
2010-02-28 10:39:16 -07:00
|
|
|
}
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
|
|
|
|
use_mm(net->dev.mm);
|
|
|
|
mutex_lock(&vq->mutex);
|
|
|
|
vhost_disable_notify(vq);
|
|
|
|
|
2010-03-08 14:24:22 -07:00
|
|
|
if (wmem < sock->sk->sk_sndbuf / 2)
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
tx_poll_stop(net);
|
2010-07-27 08:52:21 -07:00
|
|
|
hdr_size = vq->vhost_hlen;
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
|
|
|
|
for (;;) {
|
|
|
|
head = vhost_get_vq_desc(&net->dev, vq, vq->iov,
|
|
|
|
ARRAY_SIZE(vq->iov),
|
|
|
|
&out, &in,
|
|
|
|
NULL, NULL);
|
2010-06-24 06:59:59 -07:00
|
|
|
/* On error, stop handling until the next kick. */
|
2010-07-01 08:40:12 -07:00
|
|
|
if (unlikely(head < 0))
|
2010-06-24 06:59:59 -07:00
|
|
|
break;
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
/* Nothing new? Wait for eventfd to tell us they refilled. */
|
|
|
|
if (head == vq->num) {
|
|
|
|
wmem = atomic_read(&sock->sk->sk_wmem_alloc);
|
|
|
|
if (wmem >= sock->sk->sk_sndbuf * 3 / 4) {
|
|
|
|
tx_poll_start(net, sock);
|
|
|
|
set_bit(SOCK_ASYNC_NOSPACE, &sock->flags);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
if (unlikely(vhost_enable_notify(vq))) {
|
|
|
|
vhost_disable_notify(vq);
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
if (in) {
|
|
|
|
vq_err(vq, "Unexpected descriptor format for TX: "
|
|
|
|
"out %d, int %d\n", out, in);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
/* Skip header. TODO: support TSO. */
|
|
|
|
s = move_iovec_hdr(vq->iov, vq->hdr, hdr_size, out);
|
|
|
|
msg.msg_iovlen = out;
|
|
|
|
len = iov_length(vq->iov, out);
|
|
|
|
/* Sanity check */
|
|
|
|
if (!len) {
|
|
|
|
vq_err(vq, "Unexpected header len for TX: "
|
|
|
|
"%zd expected %zd\n",
|
|
|
|
iov_length(vq->hdr, s), hdr_size);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
/* TODO: Check specific error and bomb out unless ENOBUFS? */
|
|
|
|
err = sock->ops->sendmsg(NULL, sock, &msg, len);
|
|
|
|
if (unlikely(err < 0)) {
|
2010-07-27 08:52:21 -07:00
|
|
|
vhost_discard_vq_desc(vq, 1);
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
tx_poll_start(net, sock);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
if (err != len)
|
2010-06-24 07:10:25 -07:00
|
|
|
pr_debug("Truncated TX packet: "
|
|
|
|
" len %d != %zd\n", err, len);
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
vhost_add_used_and_signal(&net->dev, vq, head, 0);
|
|
|
|
total_len += len;
|
|
|
|
if (unlikely(total_len >= VHOST_NET_WEIGHT)) {
|
|
|
|
vhost_poll_queue(&vq->poll);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
mutex_unlock(&vq->mutex);
|
|
|
|
unuse_mm(net->dev.mm);
|
|
|
|
}
|
|
|
|
|
2010-07-27 08:52:21 -07:00
|
|
|
static int peek_head_len(struct sock *sk)
|
|
|
|
{
|
|
|
|
struct sk_buff *head;
|
|
|
|
int len = 0;
|
|
|
|
|
|
|
|
lock_sock(sk);
|
|
|
|
head = skb_peek(&sk->sk_receive_queue);
|
|
|
|
if (head)
|
|
|
|
len = head->len;
|
|
|
|
release_sock(sk);
|
|
|
|
return len;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* This is a multi-buffer version of vhost_get_desc, that works if
|
|
|
|
* vq has read descriptors only.
|
|
|
|
* @vq - the relevant virtqueue
|
|
|
|
* @datalen - data length we'll be reading
|
|
|
|
* @iovcount - returned count of io vectors we fill
|
|
|
|
* @log - vhost log
|
|
|
|
* @log_num - log offset
|
|
|
|
* returns number of buffer heads allocated, negative on error
|
|
|
|
*/
|
|
|
|
static int get_rx_bufs(struct vhost_virtqueue *vq,
|
|
|
|
struct vring_used_elem *heads,
|
|
|
|
int datalen,
|
|
|
|
unsigned *iovcount,
|
|
|
|
struct vhost_log *log,
|
|
|
|
unsigned *log_num)
|
|
|
|
{
|
|
|
|
unsigned int out, in;
|
|
|
|
int seg = 0;
|
|
|
|
int headcount = 0;
|
|
|
|
unsigned d;
|
|
|
|
int r, nlogs = 0;
|
|
|
|
|
|
|
|
while (datalen > 0) {
|
|
|
|
if (unlikely(headcount >= VHOST_NET_MAX_SG)) {
|
|
|
|
r = -ENOBUFS;
|
|
|
|
goto err;
|
|
|
|
}
|
|
|
|
d = vhost_get_vq_desc(vq->dev, vq, vq->iov + seg,
|
|
|
|
ARRAY_SIZE(vq->iov) - seg, &out,
|
|
|
|
&in, log, log_num);
|
|
|
|
if (d == vq->num) {
|
|
|
|
r = 0;
|
|
|
|
goto err;
|
|
|
|
}
|
|
|
|
if (unlikely(out || in <= 0)) {
|
|
|
|
vq_err(vq, "unexpected descriptor format for RX: "
|
|
|
|
"out %d, in %d\n", out, in);
|
|
|
|
r = -EINVAL;
|
|
|
|
goto err;
|
|
|
|
}
|
|
|
|
if (unlikely(log)) {
|
|
|
|
nlogs += *log_num;
|
|
|
|
log += *log_num;
|
|
|
|
}
|
|
|
|
heads[headcount].id = d;
|
|
|
|
heads[headcount].len = iov_length(vq->iov + seg, in);
|
|
|
|
datalen -= heads[headcount].len;
|
|
|
|
++headcount;
|
|
|
|
seg += in;
|
|
|
|
}
|
|
|
|
heads[headcount - 1].len += datalen;
|
|
|
|
*iovcount = seg;
|
|
|
|
if (unlikely(log))
|
|
|
|
*log_num = nlogs;
|
|
|
|
return headcount;
|
|
|
|
err:
|
|
|
|
vhost_discard_vq_desc(vq, headcount);
|
|
|
|
return r;
|
|
|
|
}
|
|
|
|
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
/* Expects to be always run from workqueue - which acts as
|
|
|
|
* read-size critical section for our kind of RCU. */
|
2010-07-27 08:52:21 -07:00
|
|
|
static void handle_rx_big(struct vhost_net *net)
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
{
|
|
|
|
struct vhost_virtqueue *vq = &net->dev.vqs[VHOST_NET_VQ_RX];
|
2010-06-24 06:59:59 -07:00
|
|
|
unsigned out, in, log, s;
|
|
|
|
int head;
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
struct vhost_log *vq_log;
|
|
|
|
struct msghdr msg = {
|
|
|
|
.msg_name = NULL,
|
|
|
|
.msg_namelen = 0,
|
|
|
|
.msg_control = NULL, /* FIXME: get and handle RX aux data. */
|
|
|
|
.msg_controllen = 0,
|
|
|
|
.msg_iov = vq->iov,
|
|
|
|
.msg_flags = MSG_DONTWAIT,
|
|
|
|
};
|
|
|
|
|
|
|
|
struct virtio_net_hdr hdr = {
|
|
|
|
.flags = 0,
|
|
|
|
.gso_type = VIRTIO_NET_HDR_GSO_NONE
|
|
|
|
};
|
|
|
|
|
|
|
|
size_t len, total_len = 0;
|
|
|
|
int err;
|
|
|
|
size_t hdr_size;
|
|
|
|
struct socket *sock = rcu_dereference(vq->private_data);
|
|
|
|
if (!sock || skb_queue_empty(&sock->sk->sk_receive_queue))
|
|
|
|
return;
|
|
|
|
|
|
|
|
use_mm(net->dev.mm);
|
|
|
|
mutex_lock(&vq->mutex);
|
|
|
|
vhost_disable_notify(vq);
|
2010-07-27 08:52:21 -07:00
|
|
|
hdr_size = vq->vhost_hlen;
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
|
|
|
|
vq_log = unlikely(vhost_has_feature(&net->dev, VHOST_F_LOG_ALL)) ?
|
|
|
|
vq->log : NULL;
|
|
|
|
|
|
|
|
for (;;) {
|
|
|
|
head = vhost_get_vq_desc(&net->dev, vq, vq->iov,
|
|
|
|
ARRAY_SIZE(vq->iov),
|
|
|
|
&out, &in,
|
|
|
|
vq_log, &log);
|
2010-06-24 06:59:59 -07:00
|
|
|
/* On error, stop handling until the next kick. */
|
2010-07-01 08:40:12 -07:00
|
|
|
if (unlikely(head < 0))
|
2010-06-24 06:59:59 -07:00
|
|
|
break;
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
/* OK, now we need to know about added descriptors. */
|
|
|
|
if (head == vq->num) {
|
|
|
|
if (unlikely(vhost_enable_notify(vq))) {
|
|
|
|
/* They have slipped one in as we were
|
|
|
|
* doing that: check again. */
|
|
|
|
vhost_disable_notify(vq);
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
/* Nothing new? Wait for eventfd to tell us
|
|
|
|
* they refilled. */
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
/* We don't need to be notified again. */
|
|
|
|
if (out) {
|
|
|
|
vq_err(vq, "Unexpected descriptor format for RX: "
|
|
|
|
"out %d, int %d\n",
|
|
|
|
out, in);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
/* Skip header. TODO: support TSO/mergeable rx buffers. */
|
|
|
|
s = move_iovec_hdr(vq->iov, vq->hdr, hdr_size, in);
|
|
|
|
msg.msg_iovlen = in;
|
|
|
|
len = iov_length(vq->iov, in);
|
|
|
|
/* Sanity check */
|
|
|
|
if (!len) {
|
|
|
|
vq_err(vq, "Unexpected header len for RX: "
|
|
|
|
"%zd expected %zd\n",
|
|
|
|
iov_length(vq->hdr, s), hdr_size);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
err = sock->ops->recvmsg(NULL, sock, &msg,
|
|
|
|
len, MSG_DONTWAIT | MSG_TRUNC);
|
|
|
|
/* TODO: Check specific error and bomb out unless EAGAIN? */
|
|
|
|
if (err < 0) {
|
2010-07-27 08:52:21 -07:00
|
|
|
vhost_discard_vq_desc(vq, 1);
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
break;
|
|
|
|
}
|
|
|
|
/* TODO: Should check and handle checksum. */
|
|
|
|
if (err > len) {
|
2010-06-24 07:10:25 -07:00
|
|
|
pr_debug("Discarded truncated rx packet: "
|
|
|
|
" len %d > %zd\n", err, len);
|
2010-07-27 08:52:21 -07:00
|
|
|
vhost_discard_vq_desc(vq, 1);
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
continue;
|
|
|
|
}
|
|
|
|
len = err;
|
|
|
|
err = memcpy_toiovec(vq->hdr, (unsigned char *)&hdr, hdr_size);
|
|
|
|
if (err) {
|
|
|
|
vq_err(vq, "Unable to write vnet_hdr at addr %p: %d\n",
|
|
|
|
vq->iov->iov_base, err);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
len += hdr_size;
|
|
|
|
vhost_add_used_and_signal(&net->dev, vq, head, len);
|
|
|
|
if (unlikely(vq_log))
|
|
|
|
vhost_log_write(vq, vq_log, log, len);
|
|
|
|
total_len += len;
|
|
|
|
if (unlikely(total_len >= VHOST_NET_WEIGHT)) {
|
|
|
|
vhost_poll_queue(&vq->poll);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
mutex_unlock(&vq->mutex);
|
|
|
|
unuse_mm(net->dev.mm);
|
|
|
|
}
|
|
|
|
|
2010-07-27 08:52:21 -07:00
|
|
|
/* Expects to be always run from workqueue - which acts as
|
|
|
|
* read-size critical section for our kind of RCU. */
|
|
|
|
static void handle_rx_mergeable(struct vhost_net *net)
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
{
|
2010-07-27 08:52:21 -07:00
|
|
|
struct vhost_virtqueue *vq = &net->dev.vqs[VHOST_NET_VQ_RX];
|
|
|
|
unsigned uninitialized_var(in), log;
|
|
|
|
struct vhost_log *vq_log;
|
|
|
|
struct msghdr msg = {
|
|
|
|
.msg_name = NULL,
|
|
|
|
.msg_namelen = 0,
|
|
|
|
.msg_control = NULL, /* FIXME: get and handle RX aux data. */
|
|
|
|
.msg_controllen = 0,
|
|
|
|
.msg_iov = vq->iov,
|
|
|
|
.msg_flags = MSG_DONTWAIT,
|
|
|
|
};
|
|
|
|
|
|
|
|
struct virtio_net_hdr_mrg_rxbuf hdr = {
|
|
|
|
.hdr.flags = 0,
|
|
|
|
.hdr.gso_type = VIRTIO_NET_HDR_GSO_NONE
|
|
|
|
};
|
|
|
|
|
|
|
|
size_t total_len = 0;
|
|
|
|
int err, headcount;
|
|
|
|
size_t vhost_hlen, sock_hlen;
|
|
|
|
size_t vhost_len, sock_len;
|
|
|
|
struct socket *sock = rcu_dereference(vq->private_data);
|
|
|
|
if (!sock || skb_queue_empty(&sock->sk->sk_receive_queue))
|
|
|
|
return;
|
|
|
|
|
|
|
|
use_mm(net->dev.mm);
|
|
|
|
mutex_lock(&vq->mutex);
|
|
|
|
vhost_disable_notify(vq);
|
|
|
|
vhost_hlen = vq->vhost_hlen;
|
|
|
|
sock_hlen = vq->sock_hlen;
|
|
|
|
|
|
|
|
vq_log = unlikely(vhost_has_feature(&net->dev, VHOST_F_LOG_ALL)) ?
|
|
|
|
vq->log : NULL;
|
|
|
|
|
|
|
|
while ((sock_len = peek_head_len(sock->sk))) {
|
|
|
|
sock_len += sock_hlen;
|
|
|
|
vhost_len = sock_len + vhost_hlen;
|
|
|
|
headcount = get_rx_bufs(vq, vq->heads, vhost_len,
|
|
|
|
&in, vq_log, &log);
|
|
|
|
/* On error, stop handling until the next kick. */
|
|
|
|
if (unlikely(headcount < 0))
|
|
|
|
break;
|
|
|
|
/* OK, now we need to know about added descriptors. */
|
|
|
|
if (!headcount) {
|
|
|
|
if (unlikely(vhost_enable_notify(vq))) {
|
|
|
|
/* They have slipped one in as we were
|
|
|
|
* doing that: check again. */
|
|
|
|
vhost_disable_notify(vq);
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
/* Nothing new? Wait for eventfd to tell us
|
|
|
|
* they refilled. */
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
/* We don't need to be notified again. */
|
|
|
|
if (unlikely((vhost_hlen)))
|
|
|
|
/* Skip header. TODO: support TSO. */
|
|
|
|
move_iovec_hdr(vq->iov, vq->hdr, vhost_hlen, in);
|
|
|
|
else
|
|
|
|
/* Copy the header for use in VIRTIO_NET_F_MRG_RXBUF:
|
|
|
|
* needed because sendmsg can modify msg_iov. */
|
|
|
|
copy_iovec_hdr(vq->iov, vq->hdr, sock_hlen, in);
|
|
|
|
msg.msg_iovlen = in;
|
|
|
|
err = sock->ops->recvmsg(NULL, sock, &msg,
|
|
|
|
sock_len, MSG_DONTWAIT | MSG_TRUNC);
|
|
|
|
/* Userspace might have consumed the packet meanwhile:
|
|
|
|
* it's not supposed to do this usually, but might be hard
|
|
|
|
* to prevent. Discard data we got (if any) and keep going. */
|
|
|
|
if (unlikely(err != sock_len)) {
|
|
|
|
pr_debug("Discarded rx packet: "
|
|
|
|
" len %d, expected %zd\n", err, sock_len);
|
|
|
|
vhost_discard_vq_desc(vq, headcount);
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
if (unlikely(vhost_hlen) &&
|
|
|
|
memcpy_toiovecend(vq->hdr, (unsigned char *)&hdr, 0,
|
|
|
|
vhost_hlen)) {
|
|
|
|
vq_err(vq, "Unable to write vnet_hdr at addr %p\n",
|
|
|
|
vq->iov->iov_base);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
/* TODO: Should check and handle checksum. */
|
|
|
|
if (vhost_has_feature(&net->dev, VIRTIO_NET_F_MRG_RXBUF) &&
|
|
|
|
memcpy_toiovecend(vq->hdr, (unsigned char *)&headcount,
|
|
|
|
offsetof(typeof(hdr), num_buffers),
|
|
|
|
sizeof hdr.num_buffers)) {
|
|
|
|
vq_err(vq, "Failed num_buffers write");
|
|
|
|
vhost_discard_vq_desc(vq, headcount);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
vhost_add_used_and_signal_n(&net->dev, vq, vq->heads,
|
|
|
|
headcount);
|
|
|
|
if (unlikely(vq_log))
|
|
|
|
vhost_log_write(vq, vq_log, log, vhost_len);
|
|
|
|
total_len += vhost_len;
|
|
|
|
if (unlikely(total_len >= VHOST_NET_WEIGHT)) {
|
|
|
|
vhost_poll_queue(&vq->poll);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
mutex_unlock(&vq->mutex);
|
|
|
|
unuse_mm(net->dev.mm);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void handle_rx(struct vhost_net *net)
|
|
|
|
{
|
|
|
|
if (vhost_has_feature(&net->dev, VIRTIO_NET_F_MRG_RXBUF))
|
|
|
|
handle_rx_mergeable(net);
|
|
|
|
else
|
|
|
|
handle_rx_big(net);
|
|
|
|
}
|
|
|
|
|
2010-06-02 11:40:00 -07:00
|
|
|
static void handle_tx_kick(struct vhost_work *work)
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
{
|
2010-06-02 11:40:00 -07:00
|
|
|
struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue,
|
|
|
|
poll.work);
|
|
|
|
struct vhost_net *net = container_of(vq->dev, struct vhost_net, dev);
|
|
|
|
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
handle_tx(net);
|
|
|
|
}
|
|
|
|
|
2010-06-02 11:40:00 -07:00
|
|
|
static void handle_rx_kick(struct vhost_work *work)
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
{
|
2010-06-02 11:40:00 -07:00
|
|
|
struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue,
|
|
|
|
poll.work);
|
|
|
|
struct vhost_net *net = container_of(vq->dev, struct vhost_net, dev);
|
|
|
|
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
handle_rx(net);
|
|
|
|
}
|
|
|
|
|
2010-06-02 11:40:00 -07:00
|
|
|
static void handle_tx_net(struct vhost_work *work)
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
{
|
2010-06-02 11:40:00 -07:00
|
|
|
struct vhost_net *net = container_of(work, struct vhost_net,
|
|
|
|
poll[VHOST_NET_VQ_TX].work);
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
handle_tx(net);
|
|
|
|
}
|
|
|
|
|
2010-06-02 11:40:00 -07:00
|
|
|
static void handle_rx_net(struct vhost_work *work)
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
{
|
2010-06-02 11:40:00 -07:00
|
|
|
struct vhost_net *net = container_of(work, struct vhost_net,
|
|
|
|
poll[VHOST_NET_VQ_RX].work);
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
handle_rx(net);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int vhost_net_open(struct inode *inode, struct file *f)
|
|
|
|
{
|
|
|
|
struct vhost_net *n = kmalloc(sizeof *n, GFP_KERNEL);
|
2010-06-02 11:40:00 -07:00
|
|
|
struct vhost_dev *dev;
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
int r;
|
2010-06-02 11:40:00 -07:00
|
|
|
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
if (!n)
|
|
|
|
return -ENOMEM;
|
2010-06-02 11:40:00 -07:00
|
|
|
|
|
|
|
dev = &n->dev;
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
n->vqs[VHOST_NET_VQ_TX].handle_kick = handle_tx_kick;
|
|
|
|
n->vqs[VHOST_NET_VQ_RX].handle_kick = handle_rx_kick;
|
2010-06-02 11:40:00 -07:00
|
|
|
r = vhost_dev_init(dev, n->vqs, VHOST_NET_VQ_MAX);
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
if (r < 0) {
|
|
|
|
kfree(n);
|
|
|
|
return r;
|
|
|
|
}
|
|
|
|
|
2010-06-02 11:40:00 -07:00
|
|
|
vhost_poll_init(n->poll + VHOST_NET_VQ_TX, handle_tx_net, POLLOUT, dev);
|
|
|
|
vhost_poll_init(n->poll + VHOST_NET_VQ_RX, handle_rx_net, POLLIN, dev);
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
n->tx_poll_state = VHOST_NET_POLL_DISABLED;
|
|
|
|
|
|
|
|
f->private_data = n;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void vhost_net_disable_vq(struct vhost_net *n,
|
|
|
|
struct vhost_virtqueue *vq)
|
|
|
|
{
|
|
|
|
if (!vq->private_data)
|
|
|
|
return;
|
|
|
|
if (vq == n->vqs + VHOST_NET_VQ_TX) {
|
|
|
|
tx_poll_stop(n);
|
|
|
|
n->tx_poll_state = VHOST_NET_POLL_DISABLED;
|
|
|
|
} else
|
|
|
|
vhost_poll_stop(n->poll + VHOST_NET_VQ_RX);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void vhost_net_enable_vq(struct vhost_net *n,
|
|
|
|
struct vhost_virtqueue *vq)
|
|
|
|
{
|
|
|
|
struct socket *sock = vq->private_data;
|
|
|
|
if (!sock)
|
|
|
|
return;
|
|
|
|
if (vq == n->vqs + VHOST_NET_VQ_TX) {
|
|
|
|
n->tx_poll_state = VHOST_NET_POLL_STOPPED;
|
|
|
|
tx_poll_start(n, sock);
|
|
|
|
} else
|
|
|
|
vhost_poll_start(n->poll + VHOST_NET_VQ_RX, sock->file);
|
|
|
|
}
|
|
|
|
|
|
|
|
static struct socket *vhost_net_stop_vq(struct vhost_net *n,
|
|
|
|
struct vhost_virtqueue *vq)
|
|
|
|
{
|
|
|
|
struct socket *sock;
|
|
|
|
|
|
|
|
mutex_lock(&vq->mutex);
|
|
|
|
sock = vq->private_data;
|
|
|
|
vhost_net_disable_vq(n, vq);
|
|
|
|
rcu_assign_pointer(vq->private_data, NULL);
|
|
|
|
mutex_unlock(&vq->mutex);
|
|
|
|
return sock;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void vhost_net_stop(struct vhost_net *n, struct socket **tx_sock,
|
|
|
|
struct socket **rx_sock)
|
|
|
|
{
|
|
|
|
*tx_sock = vhost_net_stop_vq(n, n->vqs + VHOST_NET_VQ_TX);
|
|
|
|
*rx_sock = vhost_net_stop_vq(n, n->vqs + VHOST_NET_VQ_RX);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void vhost_net_flush_vq(struct vhost_net *n, int index)
|
|
|
|
{
|
|
|
|
vhost_poll_flush(n->poll + index);
|
|
|
|
vhost_poll_flush(&n->dev.vqs[index].poll);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void vhost_net_flush(struct vhost_net *n)
|
|
|
|
{
|
|
|
|
vhost_net_flush_vq(n, VHOST_NET_VQ_TX);
|
|
|
|
vhost_net_flush_vq(n, VHOST_NET_VQ_RX);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int vhost_net_release(struct inode *inode, struct file *f)
|
|
|
|
{
|
|
|
|
struct vhost_net *n = f->private_data;
|
|
|
|
struct socket *tx_sock;
|
|
|
|
struct socket *rx_sock;
|
|
|
|
|
|
|
|
vhost_net_stop(n, &tx_sock, &rx_sock);
|
|
|
|
vhost_net_flush(n);
|
|
|
|
vhost_dev_cleanup(&n->dev);
|
|
|
|
if (tx_sock)
|
|
|
|
fput(tx_sock->file);
|
|
|
|
if (rx_sock)
|
|
|
|
fput(rx_sock->file);
|
|
|
|
/* We do an extra flush before freeing memory,
|
|
|
|
* since jobs can re-queue themselves. */
|
|
|
|
vhost_net_flush(n);
|
|
|
|
kfree(n);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static struct socket *get_raw_socket(int fd)
|
|
|
|
{
|
|
|
|
struct {
|
|
|
|
struct sockaddr_ll sa;
|
|
|
|
char buf[MAX_ADDR_LEN];
|
|
|
|
} uaddr;
|
|
|
|
int uaddr_len = sizeof uaddr, r;
|
|
|
|
struct socket *sock = sockfd_lookup(fd, &r);
|
|
|
|
if (!sock)
|
|
|
|
return ERR_PTR(-ENOTSOCK);
|
|
|
|
|
|
|
|
/* Parameter checking */
|
|
|
|
if (sock->sk->sk_type != SOCK_RAW) {
|
|
|
|
r = -ESOCKTNOSUPPORT;
|
|
|
|
goto err;
|
|
|
|
}
|
|
|
|
|
|
|
|
r = sock->ops->getname(sock, (struct sockaddr *)&uaddr.sa,
|
|
|
|
&uaddr_len, 0);
|
|
|
|
if (r)
|
|
|
|
goto err;
|
|
|
|
|
|
|
|
if (uaddr.sa.sll_family != AF_PACKET) {
|
|
|
|
r = -EPFNOSUPPORT;
|
|
|
|
goto err;
|
|
|
|
}
|
|
|
|
return sock;
|
|
|
|
err:
|
|
|
|
fput(sock->file);
|
|
|
|
return ERR_PTR(r);
|
|
|
|
}
|
|
|
|
|
2010-02-17 22:46:50 -07:00
|
|
|
static struct socket *get_tap_socket(int fd)
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
{
|
|
|
|
struct file *file = fget(fd);
|
|
|
|
struct socket *sock;
|
|
|
|
if (!file)
|
|
|
|
return ERR_PTR(-EBADF);
|
|
|
|
sock = tun_get_socket(file);
|
2010-02-17 22:46:50 -07:00
|
|
|
if (!IS_ERR(sock))
|
|
|
|
return sock;
|
|
|
|
sock = macvtap_get_socket(file);
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
if (IS_ERR(sock))
|
|
|
|
fput(file);
|
|
|
|
return sock;
|
|
|
|
}
|
|
|
|
|
|
|
|
static struct socket *get_socket(int fd)
|
|
|
|
{
|
|
|
|
struct socket *sock;
|
|
|
|
/* special case to disable backend */
|
|
|
|
if (fd == -1)
|
|
|
|
return NULL;
|
|
|
|
sock = get_raw_socket(fd);
|
|
|
|
if (!IS_ERR(sock))
|
|
|
|
return sock;
|
2010-02-17 22:46:50 -07:00
|
|
|
sock = get_tap_socket(fd);
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
if (!IS_ERR(sock))
|
|
|
|
return sock;
|
|
|
|
return ERR_PTR(-ENOTSOCK);
|
|
|
|
}
|
|
|
|
|
|
|
|
static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd)
|
|
|
|
{
|
|
|
|
struct socket *sock, *oldsock;
|
|
|
|
struct vhost_virtqueue *vq;
|
|
|
|
int r;
|
|
|
|
|
|
|
|
mutex_lock(&n->dev.mutex);
|
|
|
|
r = vhost_dev_check_owner(&n->dev);
|
|
|
|
if (r)
|
|
|
|
goto err;
|
|
|
|
|
|
|
|
if (index >= VHOST_NET_VQ_MAX) {
|
|
|
|
r = -ENOBUFS;
|
|
|
|
goto err;
|
|
|
|
}
|
|
|
|
vq = n->vqs + index;
|
|
|
|
mutex_lock(&vq->mutex);
|
|
|
|
|
|
|
|
/* Verify that ring has been setup correctly. */
|
|
|
|
if (!vhost_vq_access_ok(vq)) {
|
|
|
|
r = -EFAULT;
|
2010-03-04 14:10:14 -07:00
|
|
|
goto err_vq;
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
}
|
|
|
|
sock = get_socket(fd);
|
|
|
|
if (IS_ERR(sock)) {
|
|
|
|
r = PTR_ERR(sock);
|
2010-03-04 14:10:14 -07:00
|
|
|
goto err_vq;
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
}
|
|
|
|
|
|
|
|
/* start polling new socket */
|
|
|
|
oldsock = vq->private_data;
|
2010-07-20 18:25:24 -07:00
|
|
|
if (sock != oldsock) {
|
2010-03-04 14:10:14 -07:00
|
|
|
vhost_net_disable_vq(n, vq);
|
|
|
|
rcu_assign_pointer(vq->private_data, sock);
|
|
|
|
vhost_net_enable_vq(n, vq);
|
|
|
|
}
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
|
2010-07-15 05:19:12 -07:00
|
|
|
mutex_unlock(&vq->mutex);
|
|
|
|
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
if (oldsock) {
|
|
|
|
vhost_net_flush_vq(n, index);
|
|
|
|
fput(oldsock->file);
|
|
|
|
}
|
2010-03-04 14:10:14 -07:00
|
|
|
|
2010-07-15 05:19:12 -07:00
|
|
|
mutex_unlock(&n->dev.mutex);
|
|
|
|
return 0;
|
|
|
|
|
2010-03-04 14:10:14 -07:00
|
|
|
err_vq:
|
|
|
|
mutex_unlock(&vq->mutex);
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
err:
|
|
|
|
mutex_unlock(&n->dev.mutex);
|
|
|
|
return r;
|
|
|
|
}
|
|
|
|
|
|
|
|
static long vhost_net_reset_owner(struct vhost_net *n)
|
|
|
|
{
|
|
|
|
struct socket *tx_sock = NULL;
|
|
|
|
struct socket *rx_sock = NULL;
|
|
|
|
long err;
|
|
|
|
mutex_lock(&n->dev.mutex);
|
|
|
|
err = vhost_dev_check_owner(&n->dev);
|
|
|
|
if (err)
|
|
|
|
goto done;
|
|
|
|
vhost_net_stop(n, &tx_sock, &rx_sock);
|
|
|
|
vhost_net_flush(n);
|
|
|
|
err = vhost_dev_reset_owner(&n->dev);
|
|
|
|
done:
|
|
|
|
mutex_unlock(&n->dev.mutex);
|
|
|
|
if (tx_sock)
|
|
|
|
fput(tx_sock->file);
|
|
|
|
if (rx_sock)
|
|
|
|
fput(rx_sock->file);
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int vhost_net_set_features(struct vhost_net *n, u64 features)
|
|
|
|
{
|
2010-07-27 08:52:21 -07:00
|
|
|
size_t vhost_hlen, sock_hlen, hdr_len;
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
int i;
|
2010-07-27 08:52:21 -07:00
|
|
|
|
|
|
|
hdr_len = (features & (1 << VIRTIO_NET_F_MRG_RXBUF)) ?
|
|
|
|
sizeof(struct virtio_net_hdr_mrg_rxbuf) :
|
|
|
|
sizeof(struct virtio_net_hdr);
|
|
|
|
if (features & (1 << VHOST_NET_F_VIRTIO_NET_HDR)) {
|
|
|
|
/* vhost provides vnet_hdr */
|
|
|
|
vhost_hlen = hdr_len;
|
|
|
|
sock_hlen = 0;
|
|
|
|
} else {
|
|
|
|
/* socket provides vnet_hdr */
|
|
|
|
vhost_hlen = 0;
|
|
|
|
sock_hlen = hdr_len;
|
|
|
|
}
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
mutex_lock(&n->dev.mutex);
|
|
|
|
if ((features & (1 << VHOST_F_LOG_ALL)) &&
|
|
|
|
!vhost_log_access_ok(&n->dev)) {
|
|
|
|
mutex_unlock(&n->dev.mutex);
|
|
|
|
return -EFAULT;
|
|
|
|
}
|
|
|
|
n->dev.acked_features = features;
|
|
|
|
smp_wmb();
|
|
|
|
for (i = 0; i < VHOST_NET_VQ_MAX; ++i) {
|
|
|
|
mutex_lock(&n->vqs[i].mutex);
|
2010-07-27 08:52:21 -07:00
|
|
|
n->vqs[i].vhost_hlen = vhost_hlen;
|
|
|
|
n->vqs[i].sock_hlen = sock_hlen;
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
mutex_unlock(&n->vqs[i].mutex);
|
|
|
|
}
|
|
|
|
vhost_net_flush(n);
|
|
|
|
mutex_unlock(&n->dev.mutex);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static long vhost_net_ioctl(struct file *f, unsigned int ioctl,
|
|
|
|
unsigned long arg)
|
|
|
|
{
|
|
|
|
struct vhost_net *n = f->private_data;
|
|
|
|
void __user *argp = (void __user *)arg;
|
|
|
|
u64 __user *featurep = argp;
|
|
|
|
struct vhost_vring_file backend;
|
|
|
|
u64 features;
|
|
|
|
int r;
|
|
|
|
switch (ioctl) {
|
|
|
|
case VHOST_NET_SET_BACKEND:
|
2010-05-27 03:01:58 -07:00
|
|
|
if (copy_from_user(&backend, argp, sizeof backend))
|
|
|
|
return -EFAULT;
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
return vhost_net_set_backend(n, backend.index, backend.fd);
|
|
|
|
case VHOST_GET_FEATURES:
|
|
|
|
features = VHOST_FEATURES;
|
2010-05-27 03:01:58 -07:00
|
|
|
if (copy_to_user(featurep, &features, sizeof features))
|
|
|
|
return -EFAULT;
|
|
|
|
return 0;
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
case VHOST_SET_FEATURES:
|
2010-05-27 03:01:58 -07:00
|
|
|
if (copy_from_user(&features, featurep, sizeof features))
|
|
|
|
return -EFAULT;
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
if (features & ~VHOST_FEATURES)
|
|
|
|
return -EOPNOTSUPP;
|
|
|
|
return vhost_net_set_features(n, features);
|
|
|
|
case VHOST_RESET_OWNER:
|
|
|
|
return vhost_net_reset_owner(n);
|
|
|
|
default:
|
|
|
|
mutex_lock(&n->dev.mutex);
|
|
|
|
r = vhost_dev_ioctl(&n->dev, ioctl, arg);
|
|
|
|
vhost_net_flush(n);
|
|
|
|
mutex_unlock(&n->dev.mutex);
|
|
|
|
return r;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
#ifdef CONFIG_COMPAT
|
|
|
|
static long vhost_net_compat_ioctl(struct file *f, unsigned int ioctl,
|
|
|
|
unsigned long arg)
|
|
|
|
{
|
|
|
|
return vhost_net_ioctl(f, ioctl, (unsigned long)compat_ptr(arg));
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
2010-05-17 06:12:49 -07:00
|
|
|
static const struct file_operations vhost_net_fops = {
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
.owner = THIS_MODULE,
|
|
|
|
.release = vhost_net_release,
|
|
|
|
.unlocked_ioctl = vhost_net_ioctl,
|
|
|
|
#ifdef CONFIG_COMPAT
|
|
|
|
.compat_ioctl = vhost_net_compat_ioctl,
|
|
|
|
#endif
|
|
|
|
.open = vhost_net_open,
|
|
|
|
};
|
|
|
|
|
|
|
|
static struct miscdevice vhost_net_misc = {
|
2010-06-09 01:39:49 -07:00
|
|
|
MISC_DYNAMIC_MINOR,
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
"vhost-net",
|
|
|
|
&vhost_net_fops,
|
|
|
|
};
|
|
|
|
|
2010-04-13 11:11:25 -07:00
|
|
|
static int vhost_net_init(void)
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
{
|
2010-06-02 11:40:00 -07:00
|
|
|
return misc_register(&vhost_net_misc);
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
}
|
|
|
|
module_init(vhost_net_init);
|
|
|
|
|
2010-04-13 11:11:25 -07:00
|
|
|
static void vhost_net_exit(void)
|
vhost_net: a kernel-level virtio server
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-01-13 23:17:27 -07:00
|
|
|
{
|
|
|
|
misc_deregister(&vhost_net_misc);
|
|
|
|
}
|
|
|
|
module_exit(vhost_net_exit);
|
|
|
|
|
|
|
|
MODULE_VERSION("0.0.1");
|
|
|
|
MODULE_LICENSE("GPL v2");
|
|
|
|
MODULE_AUTHOR("Michael S. Tsirkin");
|
|
|
|
MODULE_DESCRIPTION("Host kernel accelerator for virtio net");
|