This patch introduces to a new tun/tap specific msg_control:
#define TUN_MSG_UBUF 1
#define TUN_MSG_PTR 2
struct tun_msg_ctl {
int type;
void *ptr;
};
This allows us to pass different kinds of msg_control through
sendmsg(). The first supported type is ubuf (TUN_MSG_UBUF) which will
be used by the existed vhost_net zerocopy code. The second is XDP
buff, which allows vhost_net to pass XDP buff to TUN. This could be
used to implement accepting an array of XDP buffs from vhost_net in
the following patches.
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The tuntap driver invented it's own driver specific way of queuing
XDP packets, by storing the xdp_buff information in the top of
the XDP frame data.
Convert it over to use the more generic xdp_frame structure. The
main problem with the in-driver method is that the xdp_rxq_info pointer
cannot be trused/used when dequeueing the frame.
V3: Remove check based on feedback from Jason
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
After commit fc72d1d54d ("tuntap: XDP transmission"), we can
actually queueing XDP pointers in the pointer ring, so we should
examine the pointer type before freeing the pointer.
Fixes: fc72d1d54d ("tuntap: XDP transmission")
Reported-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Fixes: fc72d1d54d ("tuntap: XDP transmission")
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch implements XDP transmission for TAP. Since we can't create
new queues for TAP during XDP set, exist ptr_ring was reused for
queuing XDP buffers. To differ xdp_buff from sk_buff, TUN_XDP_FLAG
(0x1UL) was encoded into lowest bit of xpd_buff pointer during
ptr_ring_produce, and was decoded during consuming. XDP metadata was
stored in the headroom of the packet which should work in most of
cases since driver usually reserve enough headroom. Very minor changes
were done for vhost_net: it just need to peek the length depends on
the type of pointer.
Tests were done on two Intel E5-2630 2.40GHz machines connected back
to back through two 82599ES. Traffic were generated/received through
MoonGen/testpmd(rxonly). It reports ~20% improvements when
xdp_redirect_map is doing redirection from ixgbe to TAP (from 2.50Mpps
to 3.05Mpps)
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch switches to use ptr_ring instead of skb_array. This will be
used to enqueue different types of pointers by encoding type into
lower bits.
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch exports skb_array through tun_get_skb_array(). Caller can
then manipulate skb array directly.
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Michael Kerrisk <mtk.manpages@gmail.com>
Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Dave Jones <davej@redhat.com>
virtio added mergeable buffers mode where 2 bytes of extra info is put
after vnet header but before actual data (tun does not need this data).
In hindsight, it would have been better to add the new info *before* the
packet: as it is, users need a lot of tricky code to skip the extra 2
bytes in the middle of the iovec, and in fact applications seem to get
it wrong, and only work with specific iovec layout. The fact we might
need to split iovec also means we might in theory overflow iovec max
size.
This patch adds a simpler way for applications to handle this,
and future proofs the interface against further extensions,
by making the size of the virtio net header configurable
from userspace. As a result, tun driver will simply
skip the extra 2 bytes on both input and output.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: David S. Miller <davem@davemloft.net>
This patch adds Linux Socket Filter support to
tun driver.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Tun device looks similar to a packet socket
in that both pass complete frames from/to userspace.
This patch fills in enough fields in the socket underlying tun driver
to support sendmsg/recvmsg operations, and message flags
MSG_TRUNC and MSG_DONTWAIT, and exports access to this socket
to modules. Regular read/write behaviour is unchanged.
This way, code using raw sockets to inject packets
into a physical device, can support injecting
packets into host network stack almost without modification.
First user of this interface will be vhost virtualization
accelerator.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
- Allow setting UFO on tap device and handle UFO packets.
Signed-off-by: Sridhar Samudrala <sri@us.ibm.com>
---------------------------------------------------------
Signed-off-by: David S. Miller <davem@davemloft.net>
When creating a certain types of VPN, NetworkManager will first attempt
to find an available tun device by iterating through 'vpn%d' until it
finds one that isn't already busy. Then it'll set that to be persistent
and owned by the otherwise unprivileged user that the VPN dæmon itself
runs as.
There's a race condition here -- during the period where the vpn%d
device is created and we're waiting for the VPN dæmon to actually
connect and use it, if we try to create _another_ device we could end up
re-using the same one -- because trying to open it again doesn't get
-EBUSY as it would while it's _actually_ busy.
So solve this, we add an IFF_TUN_EXCL flag which causes tun_set_iff() to
fail if it would be opening an existing persistent tundevice -- so that
we can make sure we're getting an entirely _new_ device.
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Unlike a normal socket path, the tuntap device send path does
not have any accounting. This means that the user-space sender
may be able to pin down arbitrary amounts of kernel memory by
continuing to send data to an end-point that is congested.
Even when this isn't an issue because of limited queueing at
most end points, this can also be a problem because its only
response to congestion is packet loss. That is, when those
local queues at the end-point fills up, the tuntap device will
start wasting system time because it will continue to send
data there which simply gets dropped straight away.
Of course one could argue that everybody should do congestion
control end-to-end, unfortunately there are people in this world
still hooked on UDP, and they don't appear to be going away
anywhere fast. In fact, we've always helped them by performing
accounting in our UDP code, the sole purpose of which is to
provide congestion feedback other than through packet loss.
This patch attempts to apply the same bandaid to the tuntap device.
It creates a pseudo-socket object which is used to account our
packets just as a normal socket does for UDP. Of course things
are a little complex because we're actually reinjecting traffic
back into the stack rather than out of the stack.
The stack complexities however should have been resolved by preceding
patches. So this one can simply start using skb_set_owner_w.
For now the accounting is essentially disabled by default for
backwards compatibility. In particular, we set the cap to INT_MAX.
This is so that existing applications don't get confused by the
sudden arrival EAGAIN errors.
In future we may wish (or be forced to) do this by default.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add a TUNGETIFF interface so that userspace can query a
tun/tap descriptor for its name and flags.
This is needed because it is common for one app to create
a tap interface, exec another app and pass it the file
descriptor for the interface. Without TUNGETIFF the spawned
app has no way of detecting wheter the interface has e.g.
IFF_VNET_HDR set.
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
Acked-by: Max Krasnyansky <maxk@qualcomm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Please see the following thread to get some context on this
http://marc.info/?l=linux-netdev&m=121564433018903&w=2
Basically the issue is that current multi-cast filtering stuff in
the TUN/TAP driver is seriously broken.
Original patch went in without proper review and ACK. It was broken and
confusing to start with and subsequent patches broke it completely.
To give you an idea of what's broken here are some of the issues:
- Very confusing comments throughout the code that imply that the
character device is a network interface in its own right, and that packets
are passed between the two nics. Which is completely wrong.
- Wrong set of ioctls is used for setting up filters. They look like
shortcuts for manipulating state of the tun/tap network interface but
in reality manipulate the state of the TX filter.
- ioctls that were originally used for setting address of the the TX filter
got "fixed" and now set the address of the network interface itself. Which
made filter totaly useless.
- Filtering is done too late. Instead of filtering early on, to avoid
unnecessary wakeups, filtering is done in the read() call.
The list goes on and on :)
So the patch cleans all that up. It introduces simple and clean interface for
setting up TX filters (TUNSETTXFILTER + tun_filter spec) and does filtering
before enqueuing the packets.
TX filtering is useful in the scenarios where TAP is part of a bridge, in
which case it gets all broadcast, multicast and potentially other packets when
the bridge is learning. So for example Ethernet tunnelling app may want to
setup TX filters to avoid tunnelling multicast traffic. QEMU and other
hypervisors can push RX filtering that is currently done in the guest into the
host context therefore saving wakeups and unnecessary data transfer.
Signed-off-by: Max Krasnyansky <maxk@qualcomm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add a IFF_VNET_HDR flag. This uses the same ABI as virtio_net
(ie. prepending struct virtio_net_hdr to packets) to indicate GSO and
checksum information.
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Max Krasnyansky <maxk@qualcomm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
ethtool is useful for setting (some) device fields, but it's
root-only. Finer feature control is available through a tun-specific
ioctl.
(Includes Mark McLoughlin <markmc@redhat.com>'s fix to hold rtnl sem).
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Max Krasnyansky <maxk@qualcomm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The problem with introducing checksum offload and gso to tun is they
need to set dev->features to enable GSO and/or checksumming, which is
supposed to be done before register_netdevice(), ie. as part of
TUNSETIFF.
Unfortunately, TUNSETIFF has always just ignored flags it doesn't
understand, so there's no good way of detecting whether the kernel
supports new IFF_ flags.
This patch implements a TUNGETFEATURES ioctl which returns all the valid IFF
flags. It could be extended later to include other features.
Here's an example program which uses it:
#include <linux/if_tun.h>
#include <sys/types.h>
#include <sys/ioctl.h>
#include <sys/stat.h>
#include <fcntl.h>
#include <err.h>
#include <stdio.h>
static struct {
unsigned int flag;
const char *name;
} known_flags[] = {
{ IFF_TUN, "TUN" },
{ IFF_TAP, "TAP" },
{ IFF_NO_PI, "NO_PI" },
{ IFF_ONE_QUEUE, "ONE_QUEUE" },
};
int main()
{
unsigned int features, i;
int netfd = open("/dev/net/tun", O_RDWR);
if (netfd < 0)
err(1, "Opening /dev/net/tun");
if (ioctl(netfd, TUNGETFEATURES, &features) != 0) {
printf("Kernel does not support TUNGETFEATURES, guessing\n");
features = (IFF_TUN|IFF_TAP|IFF_NO_PI|IFF_ONE_QUEUE);
}
printf("Available features are: ");
for (i = 0; i < sizeof(known_flags)/sizeof(known_flags[0]); i++) {
if (features & known_flags[i].flag) {
features &= ~known_flags[i].flag;
printf("%s ", known_flags[i].name);
}
}
if (features)
printf("(UNKNOWN %#x)", features);
printf("\n");
return 0;
}
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Max Krasnyansky <maxk@qualcomm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch removes CVS keywords that weren't updated for a long time
from comments.
Signed-off-by: Adrian Bunk <bunk@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
There's no reason for this to be in the header, and it just hurts
recompile time.
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Max Krasnyanskiy <maxk@qualcomm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We now have struct net_device_stats embedded in struct net_device,
and the default ->get_stats() hook does the obvious thing for us.
Run through drivers/net/* and remove the driver-local storage of
statistics, and driver-local ->get_stats() hook where applicable.
This was just the low-hanging fruit in drivers/net; plenty more drivers
remain to be updated.
[ Resolved conflicts with napi_struct changes and fix sunqe build
regression... -DaveM ]
Signed-off-by: Jeff Garzik <jeff@garzik.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Introduce a new syscall TUNSETGROUP for group ownership setting of tap
devices. The user now is allowed to send packages if either his euid or
his egid matches the one specified via tunctl (via -u or -g
respecitvely). If both, gid and uid, are set via tunctl, both have to
match.
Signed-off-by: Guido Guenther <agx@sigxcpu.org>
Signed-off-by: Jeff Dike <jdike@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently tun/tap only supports the EN10MB ARP type. For use with
wireless and other networking types it should be possible to set the
ARP type via an ioctl.
Patch v2: Included check that the tap interface is down before changing the
link type out from underneath it
Signed-off-by: Mike Kershaw <dragorn@kismetwireless.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Initial git repository build. I'm not bothering with the full history,
even though we have it. We can create a separate "historical" git
archive of that later if we want to, and in the meantime it's about
3.2GB when imported into git - space that would just make the early
git days unnecessarily complicated, when we don't have a lot of good
infrastructure for it.
Let it rip!
Jason Wang