This patch tries to implement an device IOTLB for vhost. This could be
used with userspace(qemu) implementation of DMA remapping
to emulate an IOMMU for the guest.

The idea is simple, cache the translation in a software device IOTLB
(which is implemented as an interval tree) in vhost and use vhost_net
file descriptor for reporting IOTLB miss and IOTLB
update/invalidation. When vhost meets an IOTLB miss, the fault
address, size and access can be read from the file. After userspace
finishes the translation, it writes the translated address to the
vhost_net file to update the device IOTLB.

When device IOTLB is enabled by setting VIRTIO_F_IOMMU_PLATFORM all vq
addresses set by ioctl are treated as iova instead of virtual address and
the accessing can only be done through IOTLB instead of direct userspace
memory access. Before each round or vq processing, all vq metadata is
prefetched in device IOTLB to make sure no translation fault happens
during vq processing.

In most cases, virtqueues are contiguous even in virtual address space.
The IOTLB translation for virtqueue itself may make it a little
slower. We might add fast path cache on top of this patch.
Signed-off-by: NJason Wang <jasowang@redhat.com>
[mst: use virtio feature bit: VHOST_F_DEVICE_IOTLB -> VIRTIO_F_IOMMU_PLATFORM ]
[mst: fix build warnings ]
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
[ weiyj.lk: missing unlock on error ]
Signed-off-by: NWei Yongjun <weiyj.lk@gmail.com>

Current pre-sorted memory region array has some limitations for future
device IOTLB conversion:

1) need extra work for adding and removing a single region, and it's
   expected to be slow because of sorting or memory re-allocation.
2) need extra work of removing a large range which may intersect
   several regions with different size.
3) need trick for a replacement policy like LRU

To overcome the above shortcomings, this patch convert it to interval
tree which can easily address the above issue with almost no extra
work.

The patch could be used for:

- Extend the current API and only let the userspace to send diffs of
  memory table.
- Simplify Device IOTLB implementation.
Signed-off-by: NJason Wang <jasowang@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

This patch tries to poll for new added tx buffer or socket receive
queue for a while at the end of tx/rx processing. The maximum time
spent on polling were specified through a new kind of vring ioctl.
Signed-off-by: NJason Wang <jasowang@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

Looking at how callers use this, maybe we should just rename init_used
to vhost_vq_init_access. The _used suffix was a hint that we
access the vq used ring. But maybe what callers care about is
that it must be called after access_ok.

Also, this function manipulates the vq->is_le field which isn't related
to the vq used ring.

This patch simply renames vhost_init_used() to vhost_vq_init_access() as
suggested by Michael.

No behaviour change.
Signed-off-by: NGreg Kurz <gkurz@linux.vnet.ibm.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

virtio 1 and any layout are core features, move them
there. This fixes vhost test.
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

convert open-coded instances
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

After TIPC doesn't depend on iocb argument in its internal
implementations of sendmsg() and recvmsg() hooks defined in proto
structure, no any user is using iocb argument in them at all now.
Then we can drop the redundant iocb argument completely from kinds of
implementations of both sendmsg() and recvmsg() in the entire
networking stack.

Cc: Christoph Hellwig <hch@lst.de>
Suggested-by: NAl Viro <viro@ZenIV.linux.org.uk>
Signed-off-by: NYing Xue <ying.xue@windriver.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The 2 that we use for copy_to_iter comes from sizeof(u16),
it used to be that way before the iov iter update.
Fix it up, making it obvious the size of stack access
is right.
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Recent iterator-related changes in vhost made it
harder to follow the logic fixing up the header.
In fact, the fixup always happens at the same
offset: sizeof(virtio_net_hdr): sometimes the
fixup iterator is updated by copy_to_iter,
sometimes-by iov_iter_advance.

Rearrange code to make this obvious.
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In commit ba7438ae ("vhost: don't bother copying iovecs in
handle_rx(), kill memcpy_toiovecend()"), we advance iov iter fixup
sizeof(struct virtio_net_hdr) bytes and fill the number of buffers
after doing the socket recvmsg(). This work well but was broken after
commit 6e03f896 ("Merge
git://git.kernel.org/pub/scm/linux/kernel/git/davem/net") which tries
to advance sizeof(struct virtio_net_hdr_mrg_rxbuf). It will fill the
number of buffers at the wrong place. This patch fixes this.

Fixes 6e03f896
("Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net")
Cc: David S. Miller <davem@davemloft.net>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: NJason Wang <jasowang@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In virtio 1.0 mode, when mergeable buffers are enabled on a big-endian
host, num_buffers wasn't byte-swapped correctly, so large incoming
packets got corrupted.

To fix, fill it in within hdr - this also makes sure it gets
the correct type.
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: kvm@vger.kernel.org
Cc: virtualization@lists.linux-foundation.org
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

just advance the msg.msg_iter and be done with that.

Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: kvm@vger.kernel.org
Cc: virtualization@lists.linux-foundation.org
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

The same macros are used for rx as well. So rename it.
Signed-off-by: NJiri Pirko <jiri@resnulli.us>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

commit 8b38694a
    vhost/net: virtio 1.0 byte swap
had this chunk:
-       heads[headcount - 1].len += datalen;
+       heads[headcount - 1].len = cpu_to_vhost32(vq, len - datalen);

This adds datalen with the wrong sign, causing guest panics.

Fixes: 8b38694aReported-by: NAlex Williamson <alex.williamson@redhat.com>
Suggested-by: NGreg Kurz <gkurz@linux.vnet.ibm.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

Note that the code _using_ ->msg_iter at that point will be very
unhappy with anything other than unshifted iovec-backed iov_iter.
We still need to convert users to proper primitives.
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Reviewed-by: NJason Wang <jasowang@redhat.com>
Reviewed-by: NCornelia Huck <cornelia.huck@de.ibm.com>

I had to add an explicit tag to suppress compiler warning:
gcc isn't smart enough to notice that
len is always initialized since function is called with size > 0.
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Reviewed-by: NCornelia Huck <cornelia.huck@de.ibm.com>

vhost/net keeps a copy of the used ring in host memory but (ab)uses
the length field for internal house-keeping. This works because the
length in the used ring for tx is always 0. In order to suppress sparse
warnings, we force native endianness here.
Note that these values are never exposed to guests.
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Reviewed-by: NJason Wang <jasowang@redhat.com>

Commit 23cc5a99 ("vhost-net: extend device allocation to vmalloc")
added another open-coded version of kvfree (which is available since
v3.15-rc5), nuke it.
Signed-off-by: NRomain Francoise <romain@orebokech.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

commit 2ae76693b8bcabf370b981cd00c36cd41d33fabc
    vhost: replace rcu with mutex
replaced rcu sync for memory accesses with VQ mutex locl/unlock.
This is correct since all accesses are under VQ mutex, but incomplete:
we still do useless rcu lock/unlock operations, someone might copy this
code into some other context where this won't be right.
This use of RCU is also non standard and hard to understand.
Let's copy the pointer to each VQ structure, this way
the access rules become straight-forward, and there's
no need for RCU anymore.
Reported-by: NEric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

Refactor code to make sure features are only accessed
under VQ mutex. This makes everything simpler, no need
for RCU here anymore.
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

Michael Mueller provided a patch to reduce the size of
vhost-net structure as some allocations could fail under
memory pressure/fragmentation. We are still left with
high order allocations though.

This patch is handling the problem at the core level, allowing
vhost structures to use vmalloc() if kmalloc() failed.

As vmalloc() adds overhead on a critical network path, add __GFP_REPEAT
to kzalloc() flags to do this fallback only when really needed.

People are still looking at cleaner ways to handle the problem
at the API level, probably passing in multiple iovecs.
This hack seems consistent with approaches
taken since then by drivers/vhost/scsi.c and net/core/dev.c

Based on patch by Romain Francoise.

Cc: Michael Mueller <mimu@linux.vnet.ibm.com>
Signed-off-by: NRomain Francoise <romain@orebokech.com>
Acked-by: NMichael S. Tsirkin <mst@redhat.com>

Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

vhost fails to validate negative error code
from vhost_get_vq_desc causing
a crash: we are using -EFAULT which is 0xfffffff2
as vector size, which exceeds the allocated size.

The code in question was introduced in commit
8dd014ad
    vhost-net: mergeable buffers support

CVE-2014-0055
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When mergeable buffers are disabled, and the
incoming packet is too large for the rx buffer,
get_rx_bufs returns success.

This was intentional in order for make recvmsg
truncate the packet and then handle_rx would
detect err != sock_len and drop it.

Unfortunately we pass the original sock_len to
recvmsg - which means we use parts of iov not fully
validated.

Fix this up by detecting this overrun and doing packet drop
immediately.

CVE-2014-0077
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

vhost_zerocopy_callback accesses VQ right after it drops a ubuf
reference.  In theory, this could race with device removal which waits
on the ubuf kref, and crash on use after free.

Do all accesses within rcu read side critical section, and synchronize
on release.

Since callbacks are always invoked from bh, synchronize_rcu_bh seems
enough and will help release complete a bit faster.
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Acked-by: NJason Wang <jasowang@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

vhost checked the counter within the refcnt before decrementing.  It
really wanted to know that it is the one that has the last reference, as
a way to batch freeing resources a bit more efficiently.

Note: we only let refcount go to 0 on device release.

This works well but we now access the ref counter twice so there's a
race: all users might see a high count and decide to defer freeing
resources.
In the end no one initiates freeing resources until the last reference
is gone (which is on VM shotdown so might happen after a looooong time).

Let's do what we probably should have done straight away:
switch from kref to plain atomic, documenting the
semantics, return the refcount value atomically after decrement,
then use that to avoid the deadlock.
Reported-by: NQin Chuanyu <qinchuanyu@huawei.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Acked-by: NJason Wang <jasowang@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Since vhost_dev_init() forever return 0, some branches are never run,
therefore need to be removed.
Signed-off-by: NZhi Yong Wu <wuzhy@linux.vnet.ibm.com>
Acked-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

As Michael point out, We used to limit the max pending DMAs to get better cache
utilization. But it was not done correctly since it was one done when there's no
new buffers submitted from guest. Guest can easily exceeds the limitation by
keeping sending packets.

So this patch moves the check into main loop. Tests shows about 5%-10%
improvement on per cpu throughput for guest tx.
Signed-off-by: NJason Wang <jasowang@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

We used to poll vhost queue before making DMA is done, this is racy if vhost
thread were waked up before marking DMA is done which can result the signal to
be missed. Fix this by always polling the vhost thread before DMA is done.
Signed-off-by: NJason Wang <jasowang@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Currently, even if the packet length is smaller than VHOST_GOODCOPY_LEN, if
upend_idx != done_idx we still set zcopy_used to true and rollback this choice
later. This could be avoided by determining zerocopy once by checking all
conditions at one time before.
Signed-off-by: NJason Wang <jasowang@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

We tend to batch the used adding and signaling in vhost_zerocopy_callback()
which may result more than 100 used buffers to be updated in
vhost_zerocopy_signal_used() in some cases. So switch to use
vhost_add_used_and_signal_n() to avoid multiple calls to
vhost_add_used_and_signal(). Which means much less times of used index
updating and memory barriers.

2% performance improvement were seen on netperf TCP_RR test.
Signed-off-by: NJason Wang <jasowang@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

None of its caller use its return value, so let it return void.
Signed-off-by: NJason Wang <jasowang@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Now, vq->private_data is always accessed under vq mutex. No need to play
the vhost rcu trick.
Signed-off-by: NAsias He <asias@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

Signed-off-by: NAsias He <asias@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

vhost_net_ubuf_put_and_wait has a confusing name:
it will actually also free it's argument.
Thus since commit 1280c27f
    "vhost-net: flush outstanding DMAs on memory change"
vhost_net_flush tries to use the argument after passing it
to vhost_net_ubuf_put_and_wait, this results
in use after free.
To fix, don't free the argument in vhost_net_ubuf_put_and_wait,
add an new API for callers that want to free ubufs.
Acked-by: NAsias He <asias@redhat.com>
Acked-by: NJason Wang <jasowang@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

$ make C=1 M=drivers/vhost

drivers/vhost/net.c:168:5: warning: symbol 'vhost_net_set_ubuf_info' was not declared. Should it be static?
drivers/vhost/net.c:194:6: warning: symbol 'vhost_net_vq_reset' was not declared. Should it be static?
drivers/vhost/scsi.c:219:6: warning: symbol 'tcm_vhost_done_inflight' was not declared. Should it be static?
Signed-off-by: NAsias He <asias@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

vhost_net_ubuf_put_and_wait has a confusing name:
it will actually also free it's argument.
Thus since commit 1280c27f
    "vhost-net: flush outstanding DMAs on memory change"
vhost_net_flush tries to use the argument after passing it
to vhost_net_ubuf_put_and_wait, this results
in use after free.
To fix, don't free the argument in vhost_net_ubuf_put_and_wait,
add an new API for callers that want to free ubufs.
Acked-by: NAsias He <asias@redhat.com>
Acked-by: NJason Wang <jasowang@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>