OpenCloudOS-Kernel/include/linux/if_tun.h

88 lines
2.8 KiB
C
Raw Normal View History

/*
* Universal TUN/TAP device driver.
* Copyright (C) 1999-2000 Maxim Krasnyansky <max_mk@yahoo.com>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*/
#ifndef __IF_TUN_H
#define __IF_TUN_H
#include <linux/types.h>
tun: Fix/rewrite packet filtering logic 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>
2008-07-15 13:18:19 +08:00
#include <linux/if_ether.h>
/* Read queue size */
#define TUN_READQ_SIZE 500
/* TUN device flags */
#define TUN_TUN_DEV 0x0001
#define TUN_TAP_DEV 0x0002
#define TUN_TYPE_MASK 0x000f
#define TUN_FASYNC 0x0010
#define TUN_NOCHECKSUM 0x0020
#define TUN_NO_PI 0x0040
#define TUN_ONE_QUEUE 0x0080
#define TUN_PERSIST 0x0100
#define TUN_VNET_HDR 0x0200
/* Ioctl defines */
#define TUNSETNOCSUM _IOW('T', 200, int)
#define TUNSETDEBUG _IOW('T', 201, int)
#define TUNSETIFF _IOW('T', 202, int)
#define TUNSETPERSIST _IOW('T', 203, int)
#define TUNSETOWNER _IOW('T', 204, int)
#define TUNSETLINK _IOW('T', 205, int)
#define TUNSETGROUP _IOW('T', 206, int)
tun: Interface to query tun/tap features. 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>
2008-07-03 18:45:32 +08:00
#define TUNGETFEATURES _IOR('T', 207, unsigned int)
tun: Fix/rewrite packet filtering logic 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>
2008-07-15 13:18:19 +08:00
#define TUNSETOFFLOAD _IOW('T', 208, unsigned int)
#define TUNSETTXFILTER _IOW('T', 209, unsigned int)
#define TUNGETIFF _IOR('T', 210, unsigned int)
tun: Limit amount of queued packets per device 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>
2009-02-06 13:25:32 +08:00
#define TUNGETSNDBUF _IOR('T', 211, int)
#define TUNSETSNDBUF _IOW('T', 212, int)
/* TUNSETIFF ifr flags */
#define IFF_TUN 0x0001
#define IFF_TAP 0x0002
#define IFF_NO_PI 0x1000
#define IFF_ONE_QUEUE 0x2000
#define IFF_VNET_HDR 0x4000
/* Features for GSO (TUNSETOFFLOAD). */
#define TUN_F_CSUM 0x01 /* You can hand me unchecksummed packets. */
#define TUN_F_TSO4 0x02 /* I can handle TSO for IPv4 packets */
#define TUN_F_TSO6 0x04 /* I can handle TSO for IPv6 packets */
#define TUN_F_TSO_ECN 0x08 /* I can handle TSO with ECN bits. */
tun: Fix/rewrite packet filtering logic 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>
2008-07-15 13:18:19 +08:00
/* Protocol info prepended to the packets (when IFF_NO_PI is not set) */
#define TUN_PKT_STRIP 0x0001
struct tun_pi {
tun: Fix/rewrite packet filtering logic 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>
2008-07-15 13:18:19 +08:00
__u16 flags;
__be16 proto;
};
tun: Fix/rewrite packet filtering logic 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>
2008-07-15 13:18:19 +08:00
/*
* Filter spec (used for SETXXFILTER ioctls)
* This stuff is applicable only to the TAP (Ethernet) devices.
* If the count is zero the filter is disabled and the driver accepts
* all packets (promisc mode).
* If the filter is enabled in order to accept broadcast packets
* broadcast addr must be explicitly included in the addr list.
*/
#define TUN_FLT_ALLMULTI 0x0001 /* Accept all multicast packets */
struct tun_filter {
__u16 flags; /* TUN_FLT_ flags see above */
__u16 count; /* Number of addresses */
__u8 addr[0][ETH_ALEN];
};
#endif /* __IF_TUN_H */