linux-stable/net
Willem de Bruijn 104ba78c98 packet: on direct_xmit, limit tso and csum to supported devices
When transmitting on a packet socket with PACKET_VNET_HDR and
PACKET_QDISC_BYPASS, validate device support for features requested
in vnet_hdr.

Drop TSO packets sent to devices that do not support TSO or have the
feature disabled. Note that the latter currently do process those
packets correctly, regardless of not advertising the feature.

Because of SKB_GSO_DODGY, it is not sufficient to test device features
with netif_needs_gso. Full validate_xmit_skb is needed.

Switch to software checksum for non-TSO packets that request checksum
offload if that device feature is unsupported or disabled. Note that
similar to the TSO case, device drivers may perform checksum offload
correctly even when not advertising it.

When switching to software checksum, packets hit skb_checksum_help,
which has two BUG_ON checksum not in linear segment. Packet sockets
always allocate at least up to csum_start + csum_off + 2 as linear.

Tested by running github.com/wdebruij/kerneltools/psock_txring_vnet.c

  ethtool -K eth0 tso off tx on
  psock_txring_vnet -d $dst -s $src -i eth0 -l 2000 -n 1 -q -v
  psock_txring_vnet -d $dst -s $src -i eth0 -l 2000 -n 1 -q -v -N

  ethtool -K eth0 tx off
  psock_txring_vnet -d $dst -s $src -i eth0 -l 1000 -n 1 -q -v -G
  psock_txring_vnet -d $dst -s $src -i eth0 -l 1000 -n 1 -q -v -G -N

v2:
  - add EXPORT_SYMBOL_GPL(validate_xmit_skb_list)

Fixes: d346a3fae3 ("packet: introduce PACKET_QDISC_BYPASS socket option")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-29 15:02:15 -04:00
..
6lowpan 6lowpan: ndisc: no overreact if no short address is available 2016-09-19 20:19:34 +02:00
9p IB/core: add support to create a unsafe global rkey to ib_create_pd 2016-09-23 13:47:44 -04:00
802
8021q net: add recursion limit to GRO 2016-10-20 14:32:22 -04:00
appletalk
atm
ax25
batman-adv treewide: remove redundant #include <linux/kconfig.h> 2016-10-11 15:06:33 -07:00
bluetooth Bluetooth: Fix append max 11 bytes of name to scan rsp data 2016-10-19 18:42:37 +02:00
bridge bridge: multicast: restore perm router ports on multicast enable 2016-10-18 13:52:13 -04:00
caif
can
ceph crush: remove redundant local variable 2016-10-05 23:02:10 +02:00
core packet: on direct_xmit, limit tso and csum to supported devices 2016-10-29 15:02:15 -04:00
dcb
dccp
decnet
dns_resolver
dsa net: dsa: add port fast ageing 2016-09-23 08:38:50 -04:00
ethernet net: add recursion limit to GRO 2016-10-20 14:32:22 -04:00
hsr net/hsr: Remove unused but set variable 2016-10-18 10:28:18 -04:00
ieee802154
ipv4 udp: fix IP_CHECKSUM handling 2016-10-26 17:33:22 -04:00
ipv6 ip6_tunnel: Update skb->protocol to ETH_P_IPV6 in ip6_tnl_xmit() 2016-10-29 14:49:31 -04:00
ipx
irda Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net 2016-09-23 06:46:57 -04:00
iucv
kcm Merge branch 'work.splice_read' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs 2016-10-07 15:36:58 -07:00
key
l2tp udp: must lock the socket in udp_disconnect() 2016-10-20 14:45:52 -04:00
l3mdev
lapb
llc llc: switch type to bool as the timeout is only tested versus 0 2016-09-17 10:05:05 -04:00
mac80211 mac80211: move struct aead_req off the stack 2016-10-17 16:14:04 +02:00
mac802154 mac802154: use rate limited warnings for malformed frames 2016-09-19 20:19:34 +02:00
mpls mpls: move mpls_hdr to a common location 2016-10-03 02:00:21 -04:00
ncsi net/ncsi: Improve HNCDSC AEN handler 2016-10-20 11:23:08 -04:00
netfilter netfilter: fix nf_queue handling 2016-10-20 19:59:59 +02:00
netlabel
netlink netlink: do not enter direct reclaim from netlink_dump() 2016-10-06 20:53:13 -04:00
netrom
nfc
openvswitch openvswitch: add NETIF_F_HW_VLAN_STAG_TX to internal dev 2016-10-13 10:03:23 -04:00
packet packet: on direct_xmit, limit tso and csum to supported devices 2016-10-29 15:02:15 -04:00
phonet
qrtr
rds IB/core: add support to create a unsafe global rkey to ib_create_pd 2016-09-23 13:47:44 -04:00
rfkill
rose
rxrpc rxrpc: Fix checking of error from ip6_route_output() 2016-10-13 08:43:17 +01:00
sched net_sched actions: use nla_parse_nested() 2016-10-29 15:01:01 -04:00
sctp sctp: validate chunk len before actually using it 2016-10-29 12:00:10 -04:00
strparser strparser: Propagate correct error code in strp_recv() 2016-10-12 01:51:49 -04:00
sunrpc NFS client updates for Linux 4.9 2016-10-13 21:28:20 -07:00
switchdev switchdev: Execute bridge ndos only for bridge ports 2016-10-19 10:58:04 -04:00
tipc tipc: info leak in __tipc_nl_add_udp_addr() 2016-10-13 12:10:01 -04:00
unix skb_splice_bits(): get rid of callback 2016-10-03 20:40:56 -04:00
vmw_vsock VSOCK: Don't dec ack backlog twice for rejected connections 2016-09-27 07:59:25 -04:00
wimax
wireless cfg80211: add ability to check DA/SA in A-MSDU decapsulation 2016-10-12 09:19:10 +02:00
x25
xfrm proc: Reduce cache miss in xfrm_statistics_seq_show 2016-09-30 01:50:45 -04:00
compat.c
Kconfig
Makefile
socket.c vfs: Remove {get,set,remove}xattr inode operations 2016-10-07 21:48:36 -04:00
sysctl_net.c Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace 2016-10-06 09:52:23 -07:00