First, make callers pass on-stack flowi4 to ip_route_output_gre()
so they can get at the fully resolved flow key.

Next, use that in ipgre_tunnel_xmit() to avoid the need to use
rt->rt_{dst,src}.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This eliminates the need to use rt->rt_{src,dst}.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Instead of rt->rt_{dst,src}

The only tricky part is source route option handling.

If the source route option is enabled we can't just use plain 'daddr',
we have to use opt->opt.faddr.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Instead of rt->rt_{dst,src}
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Instead of rt->rt_{src,dst}
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Instead of rt->rt_{src,dst}
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NDavid S. Miller <davem@davemloft.net>

To more accurately reflect that it is purely a routing
cache lookup key and is used in no other context.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Use information from the skb as much as possible, currently
this means daddr, saddr, and TOS.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Four years ago, Patrick made a change to hold rtnl mutex during netlink
dump callbacks.

I believe it was a wrong move. This slows down concurrent dumps, making
good old /proc/net/ files faster than rtnetlink in some situations.

This occurred to me because one "ip link show dev ..." was _very_ slow
on a workload adding/removing network devices in background.

All dump callbacks are able to use RCU locking now, so this patch does
roughly a revert of commits :

1c2d670f : [RTNETLINK]: Hold rtnl_mutex during netlink dump callbacks
6313c1e0 : [RTNETLINK]: Remove unnecessary locking in dump callbacks

This let writers fight for rtnl mutex and readers going full speed.

It also takes care of phonet : phonet_route_get() is now called from rcu
read section. I renamed it to phonet_route_get_rcu()
Signed-off-by: NEric Dumazet <eric.dumazet@gmail.com>
Cc: Patrick McHardy <kaber@trash.net>
Cc: Remi Denis-Courmont <remi.denis-courmont@nokia.com>
Acked-by: NStephen Hemminger <shemminger@vyatta.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Slow path output route resolution always makes sure that
->{saddr,daddr} are set, and also if we trigger into IPSEC resolution
we initialize them as well, because xfrm_lookup() expects them to be
fully resolved.

But if we hit the fast path and flowi4->flowi4_proto is zero, we won't
do this initialization.

Therefore, move the IPSEC path initialization to the route cache
lookup fast path to make sure these are always set.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The rcu protected macros rcu_dereference() and rcu_assign_pointer()
for the bat_priv->primary_if need to be used, as well as spin/rcu locking.

Otherwise we might end up using a primary_if pointer pointing to already
freed memory.
Signed-off-by: NMarek Lindner <lindner_marek@yahoo.de>
Signed-off-by: NSven Eckelmann <sven@narfation.org>

This is a regression from c4aac1ab

- gw_node_update() doesn't add a new gw_node in case of empty curr_gw.
This means that at the beginning no gw_node is added, leading to an
empty gateway list.

- gw_election() is terminating in case of curr_gw == NULL. It has to
terminate in case of curr_gw != NULL
Signed-off-by: NAntonio Quartulli <ordex@autistici.org>
Signed-off-by: NSven Eckelmann <sven@narfation.org>

atomic_dec_not_zero() is very useful and it is currently defined
multiple times. So it is possible to move it in main.h
Signed-off-by: NAntonio Quartulli <ordex@autistici.org>
Signed-off-by: NSven Eckelmann <sven@narfation.org>

orig_hash_find() manages rcu_lock/unlock internally and doesn't need to
be surrounded by rcu_read_lock() / rcu_read_unlock() anymore
Signed-off-by: NAntonio Quartulli <ordex@autistici.org>
Acked-by: NMarek Lindner <lindner_marek@yahoo.de>
Signed-off-by: NSven Eckelmann <sven@narfation.org>

This updates the network drivers so that they don't access the
ethtool_cmd::speed field directly, but use ethtool_cmd_speed()
instead.

For most of the drivers, these changes are purely cosmetic and don't
fix any problem, such as for those 1GbE/10GbE drivers that indirectly
call their own ethtool get_settings()/mii_ethtool_gset(). The changes
are meant to enforce code consistency and provide robustness with
future larger throughputs, at the expense of a few CPU cycles for each
ethtool operation.

All drivers compiled with make allyesconfig ion x86_64 have been
updated.

Tested: make allyesconfig on x86_64 + e1000e/bnx2x work
Signed-off-by: NDavid Decotigny <decot@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This makes sure the ethtool's set_settings() callback of network
drivers don't ignore the 16 most significant bits when ethtool calls
their set_settings().

All drivers compiled with make allyesconfig on x86_64 have been
updated.
Signed-off-by: NDavid Decotigny <decot@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This makes sure that when a driver calls the ethtool's
get/set_settings() callback of another driver, the data passed to it
is clean. This guarantees that speed_hi will be zeroed correctly if
the called callback doesn't explicitely set it: we are sure we don't
get a corrupted speed from the underlying driver. We also take care of
setting the cmd field appropriately (ETHTOOL_GSET/SSET).

This applies to dev_ethtool_get_settings(), which now makes sure it
sets up that ethtool command parameter correctly before passing it to
drivers. This also means that whoever calls dev_ethtool_get_settings()
does not have to clean the ethtool command parameter. This function
also becomes an exported symbol instead of an inline.

All drivers visible to make allyesconfig under x86_64 have been
updated.
Signed-off-by: NDavid Decotigny <decot@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

For backward compatibility, we should retain the module parameters and
sysfs attributes to control the number of peer notifications
(gratuitous ARPs and unsolicited NAs) sent after bonding failover.
Also, it is possible for failover to take place even though the new
active slave does not have link up, and in that case the peer
notification should be deferred until it does.

Change ipv4 and ipv6 so they do not automatically send peer
notifications on bonding failover.

Change the bonding driver to send separate NETDEV_NOTIFY_PEERS
notifications when the link is up, as many times as requested.  Since
it does not directly control which protocols send notifications, make
num_grat_arp and num_unsol_na aliases for a single parameter.  Bump
the bonding version number and update its documentation.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>
Signed-off-by: NJay Vosburgh <fubar@us.ibm.com>
Acked-by: NBrian Haley <brian.haley@hp.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Pktgen doesn't generate number of frags requested.
Divide packet size by number of frags and fill that in every frags.

Example:
With packet size 1470, it generate only 11 frags. Initial frags
get lenght 706, 353, 177....so on. Last frag get divided by 2.

Now with this fix, each frags will get 78 bytes.
Signed-off-by: NAmit Kumar Salecha <amit.salecha@qlogic.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

module_alloc() and module_free() are available only if CONFIG_MODULES=y
Reported-by: NRandy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: NEric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Now that output route lookups update the flow with
destination address selection, we can fetch it from
fl4->daddr instead of rt->rt_dst
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Now that output route lookups update the flow with
destination address selection, we can fetch it from
fl4->daddr instead of rt->rt_dst
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Now that output route lookups update the flow with
destination address selection, we can fetch it from
fl4->daddr instead of rt->rt_dst
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Now that output route lookups update the flow with
destination address selection, we can fetch it from
fl4->daddr instead of rt->rt_dst
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Now that output route lookups update the flow with
destination address selection, we can fetch it from
fl4->daddr instead of rt->rt_dst
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Now that output route lookups update the flow with
source address selection, we can fetch it from
fl4->saddr instead of rt->rt_src
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Now that output route lookups update the flow with
source address selection, we can fetch it from
fl4->saddr instead of rt->rt_src
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Now that output route lookups update the flow with
source address selection, we can fetch it from
fl4->saddr instead of rt->rt_src
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Now that output route lookups update the flow with
source address selection, we can fetch it from
fl4->saddr instead of rt->rt_src
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Make dst_alloc() and it's users explicitly initialize the entire
entry.

The zero'ing done by kmem_cache_zalloc() was almost entirely
redundant.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Now the dst->dev, dev->obsolete, and dst->flags values can
be specified as well.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

We don't actually hold the socket lock at this point, so the
rcu_dereference_protected() isn't' correct.  Thanks to Eric
Dumazet for pointing this out.

Thankfully, we're only interested in fetching the faddr value
if srr is enabled, so we can simply make this an RCU sequence
and use plain rcu_dereference().
Reported-by: NEric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Note: netdev_update_features() needs only rtnl_lock as br->port_list
is only changed while holding it.
Signed-off-by: NMichał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Simplify and fix netdev_increment_features() to conform to what is
stated in netdevice.h comments about NETIF_F_ONE_FOR_ALL.
Include FCoE segmentation and VLAN-challedged flags in computation.
Signed-off-by: NMichał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Although these are equivalent, but the skb_checksum_start_offset() is more readable.
Signed-off-by: NShan Wei <shanwei@cn.fujitsu.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

We lack proper synchronization to manipulate inet->opt ip_options

Problem is ip_make_skb() calls ip_setup_cork() and
ip_setup_cork() possibly makes a copy of ipc->opt (struct ip_options),
without any protection against another thread manipulating inet->opt.

Another thread can change inet->opt pointer and free old one under us.

Use RCU to protect inet->opt (changed to inet->inet_opt).

Instead of handling atomic refcounts, just copy ip_options when
necessary, to avoid cache line dirtying.

We cant insert an rcu_head in struct ip_options since its included in
skb->cb[], so this patch is large because I had to introduce a new
ip_options_rcu structure.
Signed-off-by: NEric Dumazet <eric.dumazet@gmail.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In order to speedup packet filtering, here is an implementation of a
JIT compiler for x86_64

It is disabled by default, and must be enabled by the admin.

echo 1 >/proc/sys/net/core/bpf_jit_enable

It uses module_alloc() and module_free() to get memory in the 2GB text
kernel range since we call helpers functions from the generated code.

EAX : BPF A accumulator
EBX : BPF X accumulator
RDI : pointer to skb   (first argument given to JIT function)
RBP : frame pointer (even if CONFIG_FRAME_POINTER=n)
r9d : skb->len - skb->data_len (headlen)
r8  : skb->data

To get a trace of generated code, use :

echo 2 >/proc/sys/net/core/bpf_jit_enable

Example of generated code :

# tcpdump -p -n -s 0 -i eth1 host 192.168.20.0/24

flen=18 proglen=147 pass=3 image=ffffffffa00b5000
JIT code: ffffffffa00b5000: 55 48 89 e5 48 83 ec 60 48 89 5d f8 44 8b 4f 60
JIT code: ffffffffa00b5010: 44 2b 4f 64 4c 8b 87 b8 00 00 00 be 0c 00 00 00
JIT code: ffffffffa00b5020: e8 24 7b f7 e0 3d 00 08 00 00 75 28 be 1a 00 00
JIT code: ffffffffa00b5030: 00 e8 fe 7a f7 e0 24 00 3d 00 14 a8 c0 74 49 be
JIT code: ffffffffa00b5040: 1e 00 00 00 e8 eb 7a f7 e0 24 00 3d 00 14 a8 c0
JIT code: ffffffffa00b5050: 74 36 eb 3b 3d 06 08 00 00 74 07 3d 35 80 00 00
JIT code: ffffffffa00b5060: 75 2d be 1c 00 00 00 e8 c8 7a f7 e0 24 00 3d 00
JIT code: ffffffffa00b5070: 14 a8 c0 74 13 be 26 00 00 00 e8 b5 7a f7 e0 24
JIT code: ffffffffa00b5080: 00 3d 00 14 a8 c0 75 07 b8 ff ff 00 00 eb 02 31
JIT code: ffffffffa00b5090: c0 c9 c3

BPF program is 144 bytes long, so native program is almost same size ;)

(000) ldh      [12]
(001) jeq      #0x800           jt 2    jf 8
(002) ld       [26]
(003) and      #0xffffff00
(004) jeq      #0xc0a81400      jt 16   jf 5
(005) ld       [30]
(006) and      #0xffffff00
(007) jeq      #0xc0a81400      jt 16   jf 17
(008) jeq      #0x806           jt 10   jf 9
(009) jeq      #0x8035          jt 10   jf 17
(010) ld       [28]
(011) and      #0xffffff00
(012) jeq      #0xc0a81400      jt 16   jf 13
(013) ld       [38]
(014) and      #0xffffff00
(015) jeq      #0xc0a81400      jt 16   jf 17
(016) ret      #65535
(017) ret      #0
Signed-off-by: NEric Dumazet <eric.dumazet@gmail.com>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: Ben Hutchings <bhutchings@solarflare.com>
Cc: Hagen Paul Pfeifer <hagen@jauu.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>