This change is meant to add an ntuple data extensions to the rx network flow
classification specifiers. The idea is to allow ntuple to be displayed via
the network flow classification interface.
The first patch had some left over stuff from the original flow extension
flags I had added. That bit is removed in this patch.
The second had some left over comments that stated we ignored bits in the
masks when we actually match them.
This work is based on input from Ben Hutchings.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Reviewed-by: Ben Hutchings <bhutchings@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This change is meant to prevent a possible null pointer dereference if
NETIF_F_NTUPLE is defined but the set_rx_ntuple function pointer is not.
The main motivation behind this patch is to eventually replace the ntuple
interfaces entirely with the network flow classifier interfaces. This
allows the device drivers to maintain the ntuple check internally while
using the network flow classifier interface for setting up and displaying
rules.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The reverse path filter interferes with IPsec subnet-to-subnet tunnels,
especially when the link to the IPsec peer is on an interface other than
the one hosting the default route.
With dynamic routing, where the peer might be reachable through eth0
today and eth1 tomorrow, it's difficult to keep rp_filter enabled unless
fake routes to the remote subnets are configured on the interface
currently used to reach the peer.
IPsec provides a much stronger anti-spoofing policy than rp_filter, so
this patch disables the rp_filter for packets with a security path.
Signed-off-by: Michael Smith <msmith@cbnco.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This makes sk_buff available for other use in fib_validate_source().
Signed-off-by: Michael Smith <msmith@cbnco.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit 1018b5c016 ("Set rt->rt_iif more
sanely on output routes.") breaks rt_is_{output,input}_route.
This became the cause to return "IP_PKTINFO's ->ipi_ifindex == 0".
To fix it, this does:
1) Add "int rt_route_iif;" to struct rtable
2) For input routes, always set rt_route_iif to same value as rt_iif
3) For output routes, always set rt_route_iif to zero. Set rt_iif
as it is done currently.
4) Change rt_is_{output,input}_route() to test rt_route_iif
Signed-off-by: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp>
Signed-off-by: David S. Miller <davem@davemloft.net>
The mv88e6085 is identical to the mv88e6095, except that all ports are
10/100 Mb/s, so use the existing setup code except for the cpu/dsa speed
selection in _setup_port().
Signed-off-by: Peter Korsgaard <jacmet@sunsite.dk>
Acked-by: Lennert Buytenhek <buytenh@wantstofly.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
properly record sk_rxhash in ipv6 sockets (v2)
Noticed while working on another project that flows to sockets which I had open
on a test systems weren't getting steered properly when I had RFS enabled.
Looking more closely I found that:
1) The affected sockets were all ipv6
2) They weren't getting steered because sk->sk_rxhash was never set from the
incomming skbs on that socket.
This was occuring because there are several points in the IPv4 tcp and udp code
which save the rxhash value when a new connection is established. Those calls
to sock_rps_save_rxhash were never added to the corresponding ipv6 code paths.
This patch adds those calls. Tested by myself to properly enable RFS
functionalty on ipv6.
Change notes:
v2:
Filtered UDP to only arm RFS on bound sockets (Eric Dumazet)
Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch removes spin_locks at CAN socket creation time by using RCU.
Inspired by the discussion with Kurt van Dijck and Eric Dumazet the RCU code
was partly derived from af_phonet.c
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Reviewed-by: Eric Dumazet <eric.dumazet@gmail.com>
Acked-by: Kurt Van Dijck <kurt.van.dijck@eia.be>
Signed-off-by: David S. Miller <davem@davemloft.net>
The ethtool ETHTOOL_PHYS_ID command runs for an arbitrarily long
period of time, holding the RTNL lock. This blocks routing updates,
device enumeration, and various important operations that one might
want to keep running while hunting for the flashing LED.
We need to drop the RTNL lock during this operation, but currently the
core implementation is a thin wrapper around a driver operation and
drivers may well depend upon holding the lock.
Define a new driver operation 'set_phys_id' with an argument that sets
the ID indicator on/off/inactive/active (the last optional, for any
driver or firmware that prefers to handle blinking asynchronously).
When this is defined, the ethtool core drops the lock while waiting
and only acquires it around calls to this operation.
Deprecate the 'phys_id' operation in favour of this. It can be
removed once all in-tree drivers are converted.
Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
This patch uses __copy_from_user_nocache on transmit to bypass data
cache for a performance improvement. skb_add_data_nocache and
skb_copy_to_page_nocache can be called by sendmsg functions to use
this feature, initial support is in tcp_sendmsg. This functionality is
configurable per device using ethtool.
Presumably, this feature would only be useful when the driver does
not touch the data. The feature is turned on by default if a device
indicates that it does some form of checksum offload; it is off by
default for devices that do no checksum offload or indicate no checksum
is necessary. For the former case copy-checksum is probably done
anyway, in the latter case the device is likely loopback in which case
the no cache copy is probably not beneficial.
This patch was tested using 200 instances of netperf TCP_RR with
1400 byte request and one byte reply. Platform is 16 core AMD x86.
No-cache copy disabled:
672703 tps, 97.13% utilization
50/90/99% latency:244.31 484.205 1028.41
No-cache copy enabled:
702113 tps, 96.16% utilization,
50/90/99% latency 238.56 467.56 956.955
Using 14000 byte request and response sizes demonstrate the
effects more dramatically:
No-cache copy disabled:
79571 tps, 34.34 %utlization
50/90/95% latency 1584.46 2319.59 5001.76
No-cache copy enabled:
83856 tps, 34.81% utilization
50/90/95% latency 2508.42 2622.62 2735.88
Note especially the effect on latency tail (95th percentile).
This seems to provide a nice performance improvement and is
consistent in the tests I ran. Presumably, this would provide
the greatest benfits in the presence of an application workload
stressing the cache and a lot of transmit data happening.
Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Apply restrictions on STP parameters based 802.1D 1998 standard.
* Fixes missing locking in set path cost ioctl
* Uses common code for both ioctl and sysfs
This is based on an earlier patch Sasikanth V but with overhaul.
Note:
1. It does NOT enforce the restriction on the relationship max_age and
forward delay or hello time because in existing implementation these are
set as independant operations.
2. If STP is disabled, there is no restriction on forward delay
3. No restriction on holding time because users use Linux code to act
as hub or be sticky.
4. Although standard allow 0-255, Linux only allows 0-63 for port priority
because more bits are reserved for port number.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add netlink device ops to allow creating bridge device via netlink.
This works in a manner similar to vlan, macvlan and bonding.
Example:
# ip link add link dev br0 type bridge
# ip link del dev br0
The change required rearranging initializtion code to deal with
being called by create link. Most of the initialization happens
in br_dev_setup, but allocation of stats is done in ndo_init callback
to deal with allocation failure. Sysfs setup has to wait until
after the network device kobject is registered.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use RTM_NEWNEIGH and RTM_DELNEIGH to allow updating of entries
in bridge forwarding table. This allows manipulating static entries
which is not possible with existing tools.
Example (using bridge extensions to iproute2)
# br fdb add 00:02:03:04:05:06 dev eth0
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This allows applications to query and monitor bridge forwarding
table in the same method used for neighbor table. The forward table
entries are returned in same structure format as used by the ioctl.
If more information is desired in future, the netlink method is
extensible.
Example (using bridge extensions to iproute2)
# br monitor
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In some cases, look up of forward database entry is done with RCU;
and for others no RCU is needed because of locking. Split the two
cases into two differnt loops (and take off inline).
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Adds tracking the last used time in forwarding table.
Rename ageing_timer to updated to better describe it.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Later patch provides ability to create non-local static entry.
To make this easier move the updating of the flag values to
after the code that creates entry.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Make sure dst_release() is not called with error pointer. This is
similar to commit 4910ac6c52 ("ipv4:
Don't ip_rt_put() an error pointer in RAW sockets.").
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@amd.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Cleaning the ieee80211_rx_data.flags field here is wrong, instead the
flags should be valid accross processing the frame on different
interfaces. Fix this by removing the incorrect flags=0 assignment.
Introduced in commit 554891e63a
(mac80211: move packet flags into packet).
Signed-off-by: Helmut Schaa <helmut.schaa@googlemail.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
This is an implementation of the Quick Fair Queue scheduler developed
by Fabio Checconi. The same algorithm is already implemented in ipfw
in FreeBSD. Fabio had an earlier version developed on Linux, I just
cleaned it up. Thanks to Eric Dumazet for testing this under load.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This avoids pulling in the ipv6 module when using (ipv4-only) iptables
-m addrtype.
Signed-off-by: Florian Westphal <fw@strlen.de>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Patrick McHardy <kaber@trash.net>
ipv6 fib lookup can set RT6_LOOKUP_F_IFACE flag to restrict search
to an interface, but this flag cannot be set via struct flowi.
Also, it cannot be set via ip6_route_output: this function uses the
passed sock struct to determine if this flag is required
(by testing for nonzero sk_bound_dev_if).
Work around this by passing in an artificial struct sk in case
'strict' argument is true.
This is required to replace the rt6_lookup call in xt_addrtype.c with
nf_afinfo->route().
Signed-off-by: Florian Westphal <fw@strlen.de>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Patrick McHardy <kaber@trash.net>
This is required to eventually replace the rt6_lookup call in
xt_addrtype.c with nf_afinfo->route().
Signed-off-by: Florian Westphal <fw@strlen.de>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Patrick McHardy <kaber@trash.net>
ipvsadm -ln --daemon will trigger a Null pointer exception because
ip_vs_genl_dump_daemons() uses skb_net() instead of skb_sknet().
To prevent others from NULL ptr a check is made in ip_vs.h skb_net().
Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Patrick McHardy <kaber@trash.net>
Static analyzer of clang found a dead store which appears to be a bug in
reading count of items in SEQOF field, only the lower byte of word is
stored. This may lead to corrupted read and communication shutdown.
The bug has been in the module since it's first inclusion into linux
kernel.
[Patrick: the bug is real, but without practical consequence since the
largest amount of sequence-of members we parse is 30.]
Signed-off-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Patrick McHardy <kaber@trash.net>
The timeout variant of the list:set type must reference the member sets.
However, its garbage collector runs at timer interrupt so the mutex
protection of the references is a no go. Therefore the reference protection
is converted to rwlock.
Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Signed-off-by: Patrick McHardy <kaber@trash.net>
- the timeout value was actually not set
- the garbage collector was broken
The variant is fixed, the tests to the ipset testsuite are added.
Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Signed-off-by: Patrick McHardy <kaber@trash.net>
Note: get_flags was actually broken, because it should return the
flags capped with vlan_features. This is now done implicitly by
limiting netdev->hw_features.
RX checksumming offload control is (and was) broken, as there was no way
before to say whether it's done for tagged packets.
Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
Issue FEAT_CHANGE notification when features are changed by
netdev_update_features(). This will allow changes made by extra constraints
on e.g. MTU change to be properly propagated like changes via ethtool.
Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
All callers are prepared for alloc failures anyway, so this error
can safely be boomeranged to the callers domain without super
bad consequences. ...At worst the connection might go into a state
where each RTO tries to (unsuccessfully) re-fragment with such
a mis-sized value and eventually dies.
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit 60d9f461a2 ("appletalk: remove
the BKL") added a dereference of "sk" before checking for NULL in
atalk_release().
Guard the code block completely, rather than partially, with the
NULL check.
Reported-by: Dave Jones <davej@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add __rcu annotations and lockdep checks.
Add const qualifiers
node_parent() and node_parent_rcu() can use
rcu_dereference_index_check()
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Like DCCP and other similar pieces of code, there are mechanisms
here to try allocating smaller hash tables if the allocation
fails. So pass in __GFP_NOWARN like the others do instead of
emitting a scary message.
Reported-by: Dave Jones <davej@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Daniel J Blueman reported a lockdep splat in trie_firstleaf(), caused by
RTNL being not locked before a call to fib_table_flush()
Reported-by: Daniel J Blueman <daniel.blueman@gmail.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Don't flap VCs when carrier state changes; higher-level protocols
can detect loss of connectivity and act accordingly. This is more
consistent with how other network interfaces work.
We no longer use release_vccs() so we can delete it.
release_vccs() was duplicated from net/atm/common.c; make the
corresponding function exported, since other code duplicates it
and could leverage it if it were public.
Signed-off-by: Philip A. Prindeville <philipp@redfish-solutions.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In case the device where is coming from the packet has TSO enabled,
we should not check the mtu size value as this one could be bigger
than the expected value.
This is the case for the macvlan driver when the lower device has
TSO enabled. The macvlan inherit this feature and forward the packets
without fragmenting them. Then the packets go through dev_forward_skb
and are dropped. This patch fix this by checking TSO is not enabled
when we want to check the mtu size.
Signed-off-by: Daniel Lezcano <daniel.lezcano@free.fr>
Acked-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
"len = ntohs(ip6h->payload_len)" does not include the length of the ipv6
header itself, which the rest of this function assumes, though.
This leads to a length check less restrictive as it should be in the
following line for one thing. For another, it very likely leads to an
integer underrun when substracting the offset and therefore to a very
high new value of 'len' due to its unsignedness. This will ultimately
lead to the pskb_trim_rcsum() practically never being called, even in
the cases where it should.
Signed-off-by: Linus Lüssing <linus.luessing@web.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
