proto_ops->getname implies copying protocol specific data
into storage unit (particulary to __kernel_sockaddr_storage).
So when we implement new protocol support we should keep such
a detail in mind (which is easy to forget about).
Lets introduce DECLARE_SOCKADDR helper which check if
storage unit is not overfowed at build time.
Eventually inet_getname is switched to use DECLARE_SOCKADDR
(to show example of usage).
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
optlen is unsigned so the `< 0' test is never true.
Signed-off-by: Roel Kluin <roel.kluin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add and use no DSCAK bit in the features field.
Signed-off-by: Gilad Ben-Yossef <gilad@codefidence.com>
Sigend-off-by: Ori Finkelman <ori@comsleep.com>
Sigend-off-by: Yony Amit <yony@comsleep.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add and use no window scale bit in the features field.
Note that this is not the same as setting a window scale of 0
as would happen with window limit on route.
Signed-off-by: Gilad Ben-Yossef <gilad@codefidence.com>
Sigend-off-by: Ori Finkelman <ori@comsleep.com>
Sigend-off-by: Yony Amit <yony@comsleep.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Implement querying and acting upon the no timestamp bit in the feature
field.
Signed-off-by: Gilad Ben-Yossef <gilad@codefidence.com>
Sigend-off-by: Ori Finkelman <ori@comsleep.com>
Sigend-off-by: Yony Amit <yony@comsleep.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Implement querying and acting upon the no sack bit in the features
field.
Signed-off-by: Gilad Ben-Yossef <gilad@codefidence.com>
Sigend-off-by: Ori Finkelman <ori@comsleep.com>
Sigend-off-by: Yony Amit <yony@comsleep.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We need tcp_parse_options to be aware of dst_entry to
take into account per dst_entry TCP options settings
Signed-off-by: Gilad Ben-Yossef <gilad@codefidence.com>
Sigend-off-by: Ori Finkelman <ori@comsleep.com>
Sigend-off-by: Yony Amit <yony@comsleep.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since we only use tcp_parse_options here to check for the exietence
of TCP timestamp option in the header, it is better to call with
the "established" flag on.
Signed-off-by: Gilad Ben-Yossef <gilad@codefidence.com>
Signed-off-by: Ori Finkelman <ori@comsleep.com>
Signed-off-by: Yony Amit <yony@comsleep.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Speedup module unloading by factorizing synchronize_rcu() calls
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Augment raw_send_hdrinc to correct for incorrect ip header length values
A series of oopses was reported to me recently. Apparently when using AF_RAW
sockets to send data to peers that were reachable via ipsec encapsulation,
people could panic or BUG halt their systems.
I've tracked the problem down to user space sending an invalid ip header over an
AF_RAW socket with IP_HDRINCL set to 1.
Basically what happens is that userspace sends down an ip frame that includes
only the header (no data), but sets the ip header ihl value to a large number,
one that is larger than the total amount of data passed to the sendmsg call. In
raw_send_hdrincl, we allocate an skb based on the size of the data in the msghdr
that was passed in, but assume the data is all valid. Later during ipsec
encapsulation, xfrm4_tranport_output moves the entire frame back in the skbuff
to provide headroom for the ipsec headers. During this operation, the
skb->transport_header is repointed to a spot computed by
skb->network_header + the ip header length (ihl). Since so little data was
passed in relative to the value of ihl provided by the raw socket, we point
transport header to an unknown location, resulting in various crashes.
This fix for this is pretty straightforward, simply validate the value of of
iph->ihl when sending over a raw socket. If (iph->ihl*4U) > user data buffer
size, drop the frame and return -EINVAL. I just confirmed this fixes the
reported crashes.
Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Corrected a spelling error in a function name.
Signed-off-by: Andreas Petlund <apetlund@simula.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
Speedup module unloading by factorizing synchronize_rcu() calls
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Speedup module unloading by factorizing synchronize_rcu() calls
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
GRE tunnels use one rwlock to protect their hash tables.
This locking scheme can be converted to RCU for free, since netdevice
already must wait for a RCU grace period at dismantle time.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
IPIP tunnels use one rwlock to protect their hash tables.
This locking scheme can be converted to RCU for free, since netdevice
already must wait for a RCU grace period at dismantle time.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit b6b39e8f3f (tcp: Try to catch MSG_PEEK bug) added a printk()
to the WARN_ON() that's in tcp.c. This patch changes this combination
to WARN(); the advantage of WARN() is that the printk message shows up
inside the message, so that kerneloops.org will collect the message.
In addition, this gets rid of an extra if() statement.
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
dst_negative_advice() should check for changed dst and reset
sk_tx_queue_mapping accordingly. Pass sock to the callers of
dst_negative_advice.
(sk_reset_txq is defined just for use by dst_negative_advice. The
only way I could find to get around this is to move dst_negative_()
from dst.h to dst.c, include sock.h in dst.c, etc)
Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch tries to print out more information when we hit the
MSG_PEEK bug in tcp_recvmsg. It's been around since at least
2005 and it's about time that we finally fix it.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use symbols instead of magic constants while checking PMTU discovery
setsockopt.
Remove redundant test in ip_rt_frag_needed() (done by caller).
Signed-off-by: John Dykstra <john.dykstra1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
ipv4/ipv6 setsockopt(IP_MULTICAST_IF) have dubious __dev_get_by_index() calls.
This function should be called only with RTNL or dev_base_lock held, or reader
could see a corrupt hash chain and eventually enter an endless loop.
Fix is to call dev_get_by_index()/dev_put().
If this happens to be performance critical, we could define a new dev_exist_by_index()
function to avoid touching dev refcount.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Fix TCP_DEFER_ACCEPT conversion between seconds and
retransmission to match the TCP SYN-ACK retransmission periods
because the time is converted to such retransmissions. The old
algorithm selects one more retransmission in some cases. Allow
up to 255 retransmissions.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Change SYN-ACK retransmitting code for the TCP_DEFER_ACCEPT
users to not retransmit SYN-ACKs during the deferring period if
ACK from client was received. The goal is to reduce traffic
during the deferring period. When the period is finished
we continue with sending SYN-ACKs (at least one) but this time
any traffic from client will change the request to established
socket allowing application to terminate it properly.
Also, do not drop acked request if sending of SYN-ACK fails.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Willy Tarreau and many other folks in recent years
were concerned what happens when the TCP_DEFER_ACCEPT period
expires for clients which sent ACK packet. They prefer clients
that actively resend ACK on our SYN-ACK retransmissions to be
converted from open requests to sockets and queued to the
listener for accepting after the deferring period is finished.
Then application server can decide to wait longer for data
or to properly terminate the connection with FIN if read()
returns EAGAIN which is an indication for accepting after
the deferring period. This change still can have side effects
for applications that expect always to see data on the accepted
socket. Others can be prepared to work in both modes (with or
without TCP_DEFER_ACCEPT period) and their data processing can
ignore the read=EAGAIN notification and to allocate resources for
clients which proved to have no data to send during the deferring
period. OTOH, servers that use TCP_DEFER_ACCEPT=1 as flag (not
as a timeout) to wait for data will notice clients that didn't
send data for 3 seconds but that still resend ACKs.
Thanks to Willy Tarreau for the initial idea and to
Eric Dumazet for the review and testing the change.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This reverts commit 6d01a026b7.
Julian Anastasov, Willy Tarreau and Eric Dumazet have come up
with a more correct way to deal with this.
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch converts ah4 to the new ahash interface.
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
- skb_kill_datagram() can increment sk->sk_drops itself, not callers.
- UDP on IPV4 & IPV6 dropped frames (because of bad checksum or policy checks) increment sk_drops
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In order to have better cache layouts of struct sock (separate zones
for rx/tx paths), we need this preliminary patch.
Goal is to transfert fields used at lookup time in the first
read-mostly cache line (inside struct sock_common) and move sk_refcnt
to a separate cache line (only written by rx path)
This patch adds inet_ prefix to daddr, rcv_saddr, dport, num, saddr,
sport and id fields. This allows a future patch to define these
fields as macros, like sk_refcnt, without name clashes.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
sock_queue_rcv_skb() can update sk_drops itself, removing need for
callers to take care of it. This is more consistent since
sock_queue_rcv_skb() also reads sk_drops when queueing a skb.
This adds sk_drops managment to many protocols that not cared yet.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Storing the mask (size - 1) instead of the size allows fast path to be
a bit faster.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
udp_poll() can in some circumstances drop frames with incorrect checksums.
Problem is we now have to lock the socket while dropping frames, or risk
sk_forward corruption.
This bug is present since commit 95766fff6b
([UDP]: Add memory accounting.)
While we are at it, we can correct ioctl(SIOCINQ) to also drop bad frames.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
I was trying to use TCP_DEFER_ACCEPT and noticed that if the
client does not talk, the connection is never accepted and
remains in SYN_RECV state until the retransmits expire, where
it finally is deleted. This is bad when some firewall such as
netfilter sits between the client and the server because the
firewall sees the connection in ESTABLISHED state while the
server will finally silently drop it without sending an RST.
This behaviour contradicts the man page which says it should
wait only for some time :
TCP_DEFER_ACCEPT (since Linux 2.4)
Allows a listener to be awakened only when data arrives
on the socket. Takes an integer value (seconds), this
can bound the maximum number of attempts TCP will
make to complete the connection. This option should not
be used in code intended to be portable.
Also, looking at ipv4/tcp.c, a retransmit counter is correctly
computed :
case TCP_DEFER_ACCEPT:
icsk->icsk_accept_queue.rskq_defer_accept = 0;
if (val > 0) {
/* Translate value in seconds to number of
* retransmits */
while (icsk->icsk_accept_queue.rskq_defer_accept < 32 &&
val > ((TCP_TIMEOUT_INIT / HZ) <<
icsk->icsk_accept_queue.rskq_defer_accept))
icsk->icsk_accept_queue.rskq_defer_accept++;
icsk->icsk_accept_queue.rskq_defer_accept++;
}
break;
==> rskq_defer_accept is used as a counter of retransmits.
But in tcp_minisocks.c, this counter is only checked. And in
fact, I have found no location which updates it. So I think
that what was intended was to decrease it in tcp_minisocks
whenever it is checked, which the trivial patch below does.
Signed-off-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
Create a new socket level option to report number of queue overflows
Recently I augmented the AF_PACKET protocol to report the number of frames lost
on the socket receive queue between any two enqueued frames. This value was
exported via a SOL_PACKET level cmsg. AFter I completed that work it was
requested that this feature be generalized so that any datagram oriented socket
could make use of this option. As such I've created this patch, It creates a
new SOL_SOCKET level option called SO_RXQ_OVFL, which when enabled exports a
SOL_SOCKET level cmsg that reports the nubmer of times the sk_receive_queue
overflowed between any two given frames. It also augments the AF_PACKET
protocol to take advantage of this new feature (as it previously did not touch
sk->sk_drops, which this patch uses to record the overflow count). Tested
successfully by me.
Notes:
1) Unlike my previous patch, this patch simply records the sk_drops value, which
is not a number of drops between packets, but rather a total number of drops.
Deltas must be computed in user space.
2) While this patch currently works with datagram oriented protocols, it will
also be accepted by non-datagram oriented protocols. I'm not sure if thats
agreeable to everyone, but my argument in favor of doing so is that, for those
protocols which aren't applicable to this option, sk_drops will always be zero,
and reporting no drops on a receive queue that isn't used for those
non-participating protocols seems reasonable to me. This also saves us having
to code in a per-protocol opt in mechanism.
3) This applies cleanly to net-next assuming that commit
977750076d (my af packet cmsg patch) is reverted
Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
UDP_HTABLE_SIZE was initialy defined to 128, which is a bit small for
several setups.
4000 active UDP sockets -> 32 sockets per chain in average. An
incoming frame has to lookup all sockets to find best match, so long
chains hurt latency.
Instead of a fixed size hash table that cant be perfect for every
needs, let UDP stack choose its table size at boot time like tcp/ip
route, using alloc_large_system_hash() helper
Add an optional boot parameter, uhash_entries=x so that an admin can
force a size between 256 and 65536 if needed, like thash_entries and
rhash_entries.
dmesg logs two new lines :
[ 0.647039] UDP hash table entries: 512 (order: 0, 4096 bytes)
[ 0.647099] UDP Lite hash table entries: 512 (order: 0, 4096 bytes)
Maximal size on 64bit arches would be 65536 slots, ie 1 MBytes for non
debugging spinlocks.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There is no reason that cipso_v4_delopt() is not
defined as a static function.
Signed-off-by: Hagen Paul Pfeifer <hagen@jauu.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add support for route lookup using sk_mark on IPv4 listening sockets.
Signed-off-by: Atis Elsts <atis@mikrotik.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This fixes a bug with arp_notify.
If arp_notify is enabled, kernel will crash if address is changed
and no IP address is assigned.
http://bugzilla.kernel.org/show_bug.cgi?id=14330
Reported-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
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>
All usages of structure net_proto_ops should be declared const.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When routing daemon wants to enable forwarding of multicast traffic it
performs something like:
struct vifctl vc = {
.vifc_vifi = 1,
.vifc_flags = 0,
.vifc_threshold = 1,
.vifc_rate_limit = 0,
.vifc_lcl_addr = ip, /* <--- ip address of physical
interface, e.g. eth0 */
.vifc_rmt_addr.s_addr = htonl(INADDR_ANY),
};
setsockopt(fd, IPPROTO_IP, MRT_ADD_VIF, &vc, sizeof(vc));
This leads (in the kernel) to calling vif_add() function call which
search the (physical) device using assigned IP address:
dev = ip_dev_find(net, vifc->vifc_lcl_addr.s_addr);
The current API (struct vifctl) does not allow to specify an
interface other way than using it's IP, and if there are more than a
single interface with specified IP only the first one will be found.
The attached patch (against 2.6.30.4) allows to specify an interface
by its index, instead of IP address:
struct vifctl vc = {
.vifc_vifi = 1,
.vifc_flags = VIFF_USE_IFINDEX, /* NEW */
.vifc_threshold = 1,
.vifc_rate_limit = 0,
.vifc_lcl_ifindex = if_nametoindex("eth0"), /* NEW */
.vifc_rmt_addr.s_addr = htonl(INADDR_ANY),
};
setsockopt(fd, IPPROTO_IP, MRT_ADD_VIF, &vc, sizeof(vc));
Signed-off-by: Ilia K. <mail4ilia@gmail.com>
=== modified file 'include/linux/mroute.h'
Signed-off-by: David S. Miller <davem@davemloft.net>
We currently dirty a cache line to update tunnel device stats
(tx_packets/tx_bytes). We better use the txq->tx_bytes/tx_packets
counters that already are present in cpu cache, in the cache
line shared with txq->_xmit_lock
This patch extends IPTUNNEL_XMIT() macro to use txq pointer
provided by the caller.
Also &tunnel->dev->stats can be replaced by &dev->stats
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The FIB algorithim for IPV4 is set at compile time, but kernel goes through
the overhead of function call indirection at runtime. Save some
cycles by turning the indirect calls to direct calls to either
hash or trie code.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We can make icmp messages tx completion callback a litle bit faster.
Setting SOCK_USE_WRITE_QUEUE sk flag tells sock_wfree() to
not call sk_write_space() on a socket we know no thread is posssibly
waiting for write space. (on per cpu kernel internal icmp sockets only)
This avoids the sock_def_write_space() call and
read_lock(&sk->sk_callback_lock)/read_unlock(&sk->sk_callback_lock) calls
as well.
We avoid three atomic ops.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
tcp_splice_read() doesnt take into account socket's O_NONBLOCK flag
Before this patch :
splice(socket,0,pipe,0,128*1024,SPLICE_F_MOVE);
causes a random endless block (if pipe is full) and
splice(socket,0,pipe,0,128*1024,SPLICE_F_MOVE | SPLICE_F_NONBLOCK);
will return 0 immediately if the TCP buffer is empty.
User application has no way to instruct splice() that socket should be in blocking mode
but pipe in nonblock more.
Many projects cannot use splice(tcp -> pipe) because of this flaw.
http://git.samba.org/?p=samba.git;a=history;f=source3/lib/recvfile.c;h=ea0159642137390a0f7e57a123684e6e63e47581;hb=HEADhttp://lkml.indiana.edu/hypermail/linux/kernel/0807.2/0687.html
Linus introduced SPLICE_F_NONBLOCK in commit 29e350944f
(splice: add SPLICE_F_NONBLOCK flag )
It doesn't make the splice itself necessarily nonblocking (because the
actual file descriptors that are spliced from/to may block unless they
have the O_NONBLOCK flag set), but it makes the splice pipe operations
nonblocking.
Linus intention was clear : let SPLICE_F_NONBLOCK control the splice pipe mode only
This patch instruct tcp_splice_read() to use the underlying file O_NONBLOCK
flag, as other socket operations do.
Users will then call :
splice(socket,0,pipe,0,128*1024,SPLICE_F_MOVE | SPLICE_F_NONBLOCK );
to block on data coming from socket (if file is in blocking mode),
and not block on pipe output (to avoid deadlock)
First version of this patch was submitted by Octavian Purdila
Reported-by: Volker Lendecke <vl@samba.org>
Reported-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Octavian Purdila <opurdila@ixiacom.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Acked-by: Jens Axboe <jens.axboe@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch against v2.6.31 adds support for route lookup using sk_mark in some
more places. The benefits from this patch are the following.
First, SO_MARK option now has effect on UDP sockets too.
Second, ip_queue_xmit() and inet_sk_rebuild_header() could fail to do routing
lookup correctly if TCP sockets with SO_MARK were used.
Signed-off-by: Atis Elsts <atis@mikrotik.com>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
Acknowledge TCP window scale support by inserting the proper option in SYN/ACK
and SYN headers even if our window scale is zero.
This fixes the following observed behavior:
1. Client sends a SYN with TCP window scaling option and non zero window scale
value to a Linux box.
2. Linux box notes large receive window from client.
3. Linux decides on a zero value of window scale for its part.
4. Due to compare against requested window scale size option, Linux does not to
send windows scale TCP option header on SYN/ACK at all.
With the following result:
Client box thinks TCP window scaling is not supported, since SYN/ACK had no
TCP window scale option, while Linux thinks that TCP window scaling is
supported (and scale might be non zero), since SYN had TCP window scale
option and we have a mismatched idea between the client and server
regarding window sizes.
Probably it also fixes up the following bug (not observed in practice):
1. Linux box opens TCP connection to some server.
2. Linux decides on zero value of window scale.
3. Due to compare against computed window scale size option, Linux does
not to set windows scale TCP option header on SYN.
With the expected result that the server OS does not use window scale option
due to not receiving such an option in the SYN headers, leading to suboptimal
performance.
Signed-off-by: Gilad Ben-Yossef <gilad@codefidence.com>
Signed-off-by: Ori Finkelman <ori@comsleep.com>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
net/ipv4/tcp.c: In function 'do_tcp_setsockopt':
net/ipv4/tcp.c:2050: warning: comparison of distinct pointer types lacks a cast
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
This provides safety against negative optlen at the type
level instead of depending upon (sometimes non-trivial)
checks against this sprinkled all over the the place, in
each and every implementation.
Based upon work done by Arjan van de Ven and feedback
from Linus Torvalds.
Signed-off-by: David S. Miller <davem@davemloft.net>
