John Fastabend
9e8ce79cd7
net: sched: cls_u32 add bit to specify software only rules ...
In the initial implementation the only way to stop a rule from being
inserted into the hardware table was via the device feature flag.
However this doesn't work well when working on an end host system
where packets are expect to hit both the hardware and software
datapaths.
For example we can imagine a rule that will match an IP address and
increment a field. If we install this rule in both hardware and
software we may increment the field twice. To date we have only
added support for the drop action so we have been able to ignore
these cases. But as we extend the action support we will hit this
example plus more such cases. Arguably these are not even corner
cases in many working systems these cases will be common.
To avoid forcing the driver to always abort (i.e. the above example)
this patch adds a flag to add a rule in software only. A careful
user can use this flag to build software and hardware datapaths
that work together. One example we have found particularly useful
is to use hardware resources to set the skb->mark on the skb when
the match may be expensive to run in software but a mark lookup
in a hash table is cheap. The idea here is hardware can do in one
lookup what the u32 classifier may need to traverse multiple lists
and hash tables to compute. The flag is only passed down on inserts.
On deletion to avoid stale references in hardware we always try
to remove a rule if it exists.
The flags field is part of the classifier specific options. Although
it is tempting to lift this into the generic structure doing this
proves difficult do to how the tc netlink attributes are implemented
along with how the dump/change routines are called. There is also
precedence for putting seemingly generic pieces in the specific
classifier options such as TCA_U32_POLICE, TCA_U32_ACT, etc. So
although not ideal I've left FLAGS in the u32 options as well as it
simplifies the code greatly and user space has already learned how
to manage these bits ala 'tc' tool.
Another thing if trying to update a rule we require the flags to
be unchanged. This is to force user space, software u32 and
the hardware u32 to keep in sync. Thanks to Simon Horman for
catching this case.
Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2016-03-01 16:05:39 -05:00
9p: switch p9_client_read() to passing struct iov_iter *
2015-04-11 22:28:27 -04:00
Bluetooth: L2CAP: Introduce proper defines for PSM ranges
2016-01-29 11:47:24 +01:00
caif: fix a signedness bug in cfpkt_iterate()
2015-02-20 17:35:14 -05:00
irda: Convert function pointer arrays and uses to const
2014-12-10 15:33:16 -05:00
s390/iucv: do not use arrays as argument
2015-09-21 16:03:04 -07:00
netfilter: nf_conntrack: use safer way to lock all buckets
2016-01-20 14:15:31 +01:00
ipv4: namespacify ip_early_demux sysctl knob
2016-02-16 20:42:54 -05:00
nfc: netlink: HCI event connectivity implementation
2015-12-29 19:06:20 +01:00
sock: struct proto hash function may error
2016-02-11 03:54:14 -05:00
sctp: remove the unused sctp_datamsg_free()
2016-02-17 15:41:54 -05:00
net: tc: helper functions to query action types
2016-02-17 09:47:36 -05:00
6lowpan: add debugfs support
2015-12-10 01:25:25 +01:00
net_sched: add network namespace support for tc actions
2016-02-25 14:16:21 -05:00
inet: refactor inet[6]_lookup functions to take skb
2016-02-11 03:54:14 -05:00
ieee802154: af_ieee802154: fix typo in comment.
2015-09-17 13:20:05 +02:00
unix: correctly track in-flight fds in sending process user_struct
2016-02-08 10:30:42 -05:00
Revert "Merge branch 'vsock-virtio'"
2015-12-08 21:55:49 -05:00
neigh: Factor out ___neigh_lookup_noref
2015-03-04 00:23:23 -05:00
ax25: Stop using sock->sk_protinfo.
2015-06-28 16:55:44 -07:00
bonding: 3ad: apply ad_actor settings changes immediately
2016-02-09 04:45:49 -05:00
bonding: convert num_grat_arp to the new bonding option API
2015-07-27 01:05:24 -07:00
bonding: implement lower state change propagation
2015-12-03 11:49:27 -05:00
net: un-inline sk_busy_loop()
2015-11-18 16:17:38 -05:00
cfg80211: Add support for aborting an ongoing scan
2015-12-04 14:43:32 +01:00
nl802154: add support for security layer
2015-09-30 13:16:44 +02:00
rco: Clean up casting errors
2015-12-13 23:57:45 -05:00
cipso: don't use IPCB() to locate the CIPSO IP option
2015-02-11 14:46:37 -05:00
net: wrap sock->sk_cgrp_prioidx and ->sk_classid inside a struct
2015-12-08 22:02:33 -05:00
net_sched: update hierarchical backlog too
2016-02-29 17:02:33 -05:00
net: switch importing msghdr from userland to {compat_,}import_iovec()
2015-04-09 00:02:26 -04:00
net/dcb: Add IEEE QCN attribute
2015-03-06 21:50:02 -05:00
netfilter: Pass net into okfn
2015-09-17 17:18:37 -07:00
net: dsa: drop vlan_getnext
2016-02-25 15:20:21 -05:00
net: fix IP early demux races
2015-12-14 23:52:00 -05:00
net: add dst_cache support
2016-02-16 20:21:48 -05:00
net: add dst_cache to ovs vxlan lwtunnel
2016-02-16 20:21:48 -05:00
ipv4, ipv6: Pass net into __ip_local_out and __ip6_local_out
2015-10-08 04:27:02 -07:00
net/ethoc: support big-endian register layout
2015-09-23 15:33:15 -07:00
net: ipv6: use common fib_default_rule_pref
2015-09-09 14:19:50 -07:00
net: Rename FLOWI_FLAG_VRFSRC to FLOWI_FLAG_L3MDEV_SRC
2015-10-07 04:27:42 -07:00
flow_dissector: Don't use bit fields.
2015-09-01 16:46:08 -07:00
Revert "genl: Add genlmsg_new_unicast() for unicast message allocation"
2016-02-18 11:42:19 -05:00
geneve: Add geneve_get_rx_port support
2015-12-16 10:58:56 -05:00
gre: Remove support for sharing GRE protocol hook.
2015-08-10 14:03:54 -07:00
gro_cells: remove spinlock protecting receive queues
2015-08-31 15:17:17 -07:00
mac802154: constify ieee802154_llsec_ops structure
2016-01-04 20:40:41 +01:00
ipv6: do retries on stable privacy addresses
2015-03-23 22:12:09 -04:00
ila: Add generic ILA translation facility
2015-12-15 23:25:20 -05:00
ipv6: remove obsolete inet6 functions
2015-10-03 04:32:42 -07:00
inet: refactor inet[6]_lookup functions to take skb
2016-02-11 03:54:14 -05:00
net: avoid NULL deref in inet_ctl_sock_destroy()
2015-11-02 22:46:09 -05:00
tcp/dccp: fix another race at listener dismantle
2016-02-18 11:35:51 -05:00
ipv6: update skb->csum when CE mark is propagated
2016-01-15 15:07:23 -05:00
ipv4: namespacify ip fragment max dist sysctl knob
2016-02-16 20:42:54 -05:00
soreuseport: fast reuseport TCP socket selection
2016-02-11 03:54:15 -05:00
net: Allow accepted sockets to be bound to l3mdev domain
2015-12-18 14:43:38 -05:00
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
2015-10-20 06:08:27 -07:00
inet: tcp: fix inetpeer_set_addr_v4()
2015-12-16 00:14:12 -05:00
ipv4: namespacify ip_early_demux sysctl knob
2016-02-16 20:42:54 -05:00
ipv6: Check rt->dst.from for the DST_NOCACHE route
2015-11-15 17:12:37 -05:00
ipv6: enforce flowi6_oif usage in ip6_dst_lookup_tail()
2016-01-29 20:31:26 -08:00
net: replace dst_cache ip6_tunnel implementation with the generic one
2016-02-16 20:21:48 -05:00
route: check and remove route cache when we get route
2016-02-18 11:31:36 -05:00
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
2016-02-23 00:09:14 -05:00
ipvs: Remove skb_sknet
2015-09-24 09:34:43 +09:00
ipv6: Annotate change of locking mechanism for np->opt
2016-02-18 15:27:25 -05:00
wext: add checked wrappers for adding events/points to streams
2015-02-28 21:31:12 +01:00
net: l3mdev: address selection should only consider devices in L3 domain
2016-02-26 14:22:26 -05:00
llc: Make llc_conn_ev_qfyr_t function pointer arrays const
2014-12-10 15:21:24 -05:00
net: Pass kern from net_proto_family.create to sk_alloc
2015-05-11 10:50:17 -04:00
llc: Make llc_sap_action_t function pointer arrays const
2014-12-10 15:21:24 -05:00
lwtunnel: autoload of lwt modules
2016-02-21 22:00:28 -05:00
mac80211: add new IEEE80211_VIF_GET_NOA_UPDATE flag
2015-12-04 14:43:32 +01:00
6lowpan: cleanup lowpan_header_decompress
2015-10-21 00:49:24 +02:00
mpls: multipath route support
2015-10-23 06:26:42 -07:00
Revert "ipv6: ndisc: inherit metadata dst when creating ndisc requests"
2015-12-01 15:07:59 -05:00
net: add explicit logging and stat for neighbour table overflow
2015-08-10 13:46:21 -07:00
netfilter: cttimeout: add netns support
2015-12-14 12:48:58 +01:00
netlink: add nla_get for le32 and le64
2015-09-30 13:16:44 +02:00
net: wrap sock->sk_cgrp_prioidx and ->sk_classid inside a struct
2015-12-08 22:02:33 -05:00
nl802154: add support for security layer
2015-09-30 13:16:44 +02:00
sock: struct proto hash function may error
2016-02-11 03:54:14 -05:00
net: sched: cls_u32 add bit to specify software only rules
2016-03-01 16:05:39 -05:00
net: sched: consolidate tc_classify{,_compat}
2015-08-27 14:18:48 -07:00
udp: restrict offloads to one namespace
2016-01-10 17:28:24 -05:00
sock: struct proto hash function may error
2016-02-11 03:54:14 -05:00
cfg80211: allow wiphy specific regdomain management
2014-12-17 11:49:55 +01:00
net: add inet_sk_transparent() helper
2015-12-22 17:03:05 -05:00
ipv4: Namespaceify ip_default_ttl sysctl knob
2016-02-16 20:42:54 -05:00
netlink: Rightsize IFLA_AF_SPEC size calculation
2015-10-21 19:15:20 -07:00
net_sched: update hierarchical backlog too
2016-02-29 17:02:33 -05:00
unix: correctly track in-flight fds in sending process user_struct
2016-02-08 10:30:42 -05:00
sock: struct proto hash function may error
2016-02-11 03:54:14 -05:00
soreuseport: fix NULL ptr dereference SO_REUSEPORT after bind
2016-01-19 14:44:23 -05:00
switchdev: Adding MDB entry offload
2016-01-10 16:50:20 -05:00
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
2016-02-23 00:09:14 -05:00
inet: add TCP_NEW_SYN_RECV state
2015-03-12 22:58:12 -04:00
inet: remove BUG_ON() in twsk_destructor()
2015-07-09 15:12:20 -07:00
net: tso: add support for IPv6
2015-10-26 22:24:22 -07:00
sock: struct proto hash function may error
2016-02-11 03:54:14 -05:00
net: ip_tunnel: remove 'csum_help' argument to iptunnel_handle_offloads
2016-02-12 05:52:16 -05:00
net: switch memcpy_fromiovec()/memcpy_fromiovecend() users to copy_from_iter()
2015-02-04 01:34:15 -05:00
VXLAN: Support outer IPv4 Tx checksums by default
2016-02-21 22:05:50 -05:00
xfrm: add rcu protection to sk->sk_policy[]
2015-12-11 19:22:06 -05:00
9e8ce79cd7