linux-toradex.git/include/net/ipv6.h, branch v3.10.54

inetpeer: get rid of ip_id_count

2014-08-14T01:24:15+00:00

[ Upstream commit 73f156a6e8c1074ac6327e0abd1169e95eb66463 ]

Ideally, we would need to generate IP ID using a per destination IP
generator.

linux kernels used inet_peer cache for this purpose, but this had a huge
cost on servers disabling MTU discovery.

1) each inet_peer struct consumes 192 bytes

2) inetpeer cache uses a binary tree of inet_peer structs,
   with a nominal size of ~66000 elements under load.

3) lookups in this tree are hitting a lot of cache lines, as tree depth
   is about 20.

4) If server deals with many tcp flows, we have a high probability of
   not finding the inet_peer, allocating a fresh one, inserting it in
   the tree with same initial ip_id_count, (cf secure_ip_id())

5) We garbage collect inet_peer aggressively.

IP ID generation do not have to be 'perfect'

Goal is trying to avoid duplicates in a short period of time,
so that reassembly units have a chance to complete reassembly of
fragments belonging to one message before receiving other fragments
with a recycled ID.

We simply use an array of generators, and a Jenkin hash using the dst IP
as a key.

ipv6_select_ident() is put back into net/ipv6/ip6_output.c where it
belongs (it is only used from this file)

secure_ip_id() and secure_ipv6_id() no longer are needed.

Rename ip_select_ident_more() to ip_select_ident_segs() to avoid
unnecessary decrement/increment of the number of segments.

Signed-off-by: Eric Dumazet 
Signed-off-by: David S. Miller 
Signed-off-by: Greg Kroah-Hartman

inet: fix addr_len/msg->msg_namelen assignment in recv_error and rxpmtu functions

2013-12-08T15:29:25+00:00

[ Upstream commit 85fbaa75037d0b6b786ff18658ddf0b4014ce2a4 ]

Commit bceaa90240b6019ed73b49965eac7d167610be69 ("inet: prevent leakage
of uninitialized memory to user in recv syscalls") conditionally updated
addr_len if the msg_name is written to. The recv_error and rxpmtu
functions relied on the recvmsg functions to set up addr_len before.

As this does not happen any more we have to pass addr_len to those
functions as well and set it to the size of the corresponding sockaddr
length.

This broke traceroute and such.

Fixes: bceaa90240b6 ("inet: prevent leakage of uninitialized memory to user in recv syscalls")
Reported-by: Brad Spengler 
Reported-by: Tom Labanowski
Cc: mpb 
Cc: David S. Miller 
Cc: Eric Dumazet 
Signed-off-by: Hannes Frederic Sowa 
Signed-off-by: David S. Miller 
Signed-off-by: Greg Kroah-Hartman

ipv6: implement RFC3168 5.3 (ecn protection) for ipv6 fragmentation handling

2013-03-24T21:16:30+00:00

Hello!

After patch 1 got accepted to net-next I will also send a patch to
netfilter-devel to make the corresponding changes to the netfilter
reassembly logic.

Thanks,

  Hannes

-- >8 --
[PATCH 2/2] ipv6: implement RFC3168 5.3 (ecn protection) for ipv6 fragmentation handling

This patch also ensures that INET_ECN_CE is propagated if one fragment
had the codepoint set.

Cc: Eric Dumazet 
Cc: Jesper Dangaard Brouer 
Cc: YOSHIFUJI Hideaki 
Signed-off-by: Hannes Frederic Sowa 
Acked-by: YOSHIFUJI Hideaki 
Signed-off-by: David S. Miller

ipv6: introdcue __ipv6_addr_needs_scope_id and ipv6_iface_scope_id helper functions

2013-03-08T17:29:22+00:00

__ipv6_addr_needs_scope_id checks if an ipv6 address needs to supply
a 'sin6_scope_id != 0'. 'sin6_scope_id != 0' was enforced in case
of link-local addresses. To support interface-local multicast these
checks had to be enhanced and are now consolidated into these new helper
functions.

v2:
a) migrated to struct ipv6_addr_props

v3:
a) reverted changes for ipv6_addr_props
b) test for address type instead of comparing scope

v4:
a) unchanged

Suggested-by: YOSHIFUJI Hideaki 
Cc: YOSHIFUJI Hideaki 
Acked-by: YOSHIFUJI Hideaki 
Signed-off-by: Hannes Frederic Sowa 
Acked-by: YOSHIFUJI Hideaki 
Signed-off-by: David S. Miller

ipv6 flowlabel: add __rcu annotations

2013-03-07T21:33:10+00:00

Commit 18367681a10b (ipv6 flowlabel: Convert np->ipv6_fl_list to RCU.)
omitted proper __rcu annotations.

Signed-off-by: Eric Dumazet 
Cc: YOSHIFUJI Hideaki 
Signed-off-by: David S. Miller

ipv6: use a stronger hash for tcp

2013-02-21T23:15:58+00:00

It looks like its possible to open thousands of TCP IPv6
sessions on a server, all landing in a single slot of TCP hash
table. Incoming packets have to lookup sockets in a very
long list.

We should hash all bits from foreign IPv6 addresses, using
a salt and hash mix, not a simple XOR.

inet6_ehashfn() can also separately use the ports, instead
of xoring them.

Reported-by: Neal Cardwell 
Signed-off-by: Eric Dumazet 
Cc: Yuchung Cheng 
Signed-off-by: David S. Miller

ipv6 flowlabel: Convert np->ipv6_fl_list to RCU.

2013-01-31T03:41:13+00:00

Signed-off-by: YOSHIFUJI Hideaki 
Signed-off-by: David S. Miller

ipv6 flowlabel: Convert hash list to RCU.

2013-01-31T03:41:13+00:00

Signed-off-by: YOSHIFUJI Hideaki 
Signed-off-by: David S. Miller

net: frag helper functions for mem limit tracking

2013-01-29T18:36:24+00:00

This change is primarily a preparation to ease the extension of memory
limit tracking.

The change does reduce the number atomic operation, during freeing of
a frag queue.  This does introduce a some performance improvement, as
these atomic operations are at the core of the performance problems
seen on NUMA systems.

Signed-off-by: Jesper Dangaard Brouer 
Signed-off-by: David S. Miller

ipv6: Unshare ip6_nd_hdr() and change return type to void.

2013-01-21T18:33:15+00:00

- move ip6_nd_hdr() to its users' source files.
  In net/ipv6/mcast.c, it will be called ip6_mc_hdr().
- make return type to void since this function never fails.

Signed-off-by: YOSHIFUJI Hideaki 
Signed-off-by: David S. Miller