Corey Minyard found a race added in commit 271b72c7fa
(udp: RCU handling for Unicast packets.)
"If the socket is moved from one list to another list in-between the
time the hash is calculated and the next field is accessed, and the
socket has moved to the end of the new list, the traversal will not
complete properly on the list it should have, since the socket will
be on the end of the new list and there's not a way to tell it's on a
new list and restart the list traversal. I think that this can be
solved by pre-fetching the "next" field (with proper barriers) before
checking the hash."
This patch corrects this problem, introducing a new
sk_for_each_rcu_safenext() macro.
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Goals are :
1) Optimizing handling of incoming Unicast UDP frames, so that no memory
writes should happen in the fast path.
Note: Multicasts and broadcasts still will need to take a lock,
because doing a full lockless lookup in this case is difficult.
2) No expensive operations in the socket bind/unhash phases :
- No expensive synchronize_rcu() calls.
- No added rcu_head in socket structure, increasing memory needs,
but more important, forcing us to use call_rcu() calls,
that have the bad property of making sockets structure cold.
(rcu grace period between socket freeing and its potential reuse
make this socket being cold in CPU cache).
David did a previous patch using call_rcu() and noticed a 20%
impact on TCP connection rates.
Quoting Cristopher Lameter :
"Right. That results in cacheline cooldown. You'd want to recycle
the object as they are cache hot on a per cpu basis. That is screwed
up by the delayed regular rcu processing. We have seen multiple
regressions due to cacheline cooldown.
The only choice in cacheline hot sensitive areas is to deal with the
complexity that comes with SLAB_DESTROY_BY_RCU or give up on RCU."
- Because udp sockets are allocated from dedicated kmem_cache,
use of SLAB_DESTROY_BY_RCU can help here.
Theory of operation :
---------------------
As the lookup is lockfree (using rcu_read_lock()/rcu_read_unlock()),
special attention must be taken by readers and writers.
Use of SLAB_DESTROY_BY_RCU is tricky too, because a socket can be freed,
reused, inserted in a different chain or in worst case in the same chain
while readers could do lookups in the same time.
In order to avoid loops, a reader must check each socket found in a chain
really belongs to the chain the reader was traversing. If it finds a
mismatch, lookup must start again at the begining. This *restart* loop
is the reason we had to use rdlock for the multicast case, because
we dont want to send same message several times to the same socket.
We use RCU only for fast path.
Thus, /proc/net/udp still takes spinlocks.
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
UDP sockets are hashed in a 128 slots hash table.
This hash table is protected by *one* rwlock.
This rwlock is readlocked each time an incoming UDP message is handled.
This rwlock is writelocked each time a socket must be inserted in
hash table (bind time), or deleted from this table (close time)
This is not scalable on SMP machines :
1) Even in read mode, lock() and unlock() are atomic operations and
must dirty a contended cache line, shared by all cpus.
2) A writer might be starved if many readers are 'in flight'. This can
happen on a machine with some NIC receiving many UDP messages. User
process can be delayed a long time at socket creation/dismantle time.
This patch prepares RCU migration, by introducing 'struct udp_table
and struct udp_hslot', and using one spinlock per chain, to reduce
contention on central rwlock.
Introducing one spinlock per chain reduces latencies, for port
randomization on heavily loaded UDP servers. This also speedup
bindings to specific ports.
udp_lib_unhash() was uninlined, becoming to big.
Some cleanups were done to ease review of following patch
(RCUification of UDP Unicast lookups)
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This is a patch to provide on demand route cache rebuilding. Currently, our
route cache is rebulid periodically regardless of need. This introduced
unneeded periodic latency. This patch offers a better approach. Using code
provided by Eric Dumazet, we compute the standard deviation of the average hash
bucket chain length while running rt_check_expire. Should any given chain
length grow to larger that average plus 4 standard deviations, we trigger an
emergency hash table rebuild for that net namespace. This allows for the common
case in which chains are well behaved and do not grow unevenly to not incur any
latency at all, while those systems (which may be being maliciously attacked),
only rebuild when the attack is detected. This patch take 2 other factors into
account:
1) chains with multiple entries that differ by attributes that do not affect the
hash value are only counted once, so as not to unduly bias system to rebuilding
if features like QOS are heavily used
2) if rebuilding crosses a certain threshold (which is adjustable via the added
sysctl in this patch), route caching is disabled entirely for that net
namespace, since constant rebuilding is less efficient that no caching at all
Tested successfully by me.
Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This fixes an OOPS in hard_header if a Phonet address is assigned to a
non-Phonet network interface.
Signed-off-by: Remi Denis-Courmont <remi.denis-courmont@nokia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6: (29 commits)
tcp: Restore ordering of TCP options for the sake of inter-operability
net: Fix disjunct computation of netdev features
sctp: Fix to handle SHUTDOWN in SHUTDOWN_RECEIVED state
sctp: Fix to handle SHUTDOWN in SHUTDOWN-PENDING state
sctp: Add check for the TSN field of the SHUTDOWN chunk
sctp: Drop ICMP packet too big message with MTU larger than current PMTU
p54: enable 2.4/5GHz spectrum by eeprom bits.
orinoco: reduce stack usage in firmware download path
ath5k: fix suspend-related oops on rmmod
[netdrvr] fec_mpc52xx: Implement polling, to make netconsole work.
qlge: Fix MSI/legacy single interrupt bug.
smc911x: Make the driver safer on SMP
smc911x: Add IRQ polarity configuration
smc911x: Allow Kconfig dependency on ARM
sis190: add identifier for Atheros AR8021 PHY
8139x: reduce message severity on driver overlap
igb: add IGB_DCA instead of selecting INTEL_IOATDMA
igb: fix tx data corruption with transition to L0s on 82575
ehea: Fix memory hotplug support
netdev: DM9000: remove BLACKFIN hacking in DM9000 netdev driver
...
Once an endpoint has reached the SHUTDOWN-RECEIVED state,
it MUST NOT send a SHUTDOWN in response to a ULP request.
The Cumulative TSN Ack of the received SHUTDOWN chunk
MUST be processed.
This patch fix to process Cumulative TSN Ack of the received
SHUTDOWN chunk in SHUTDOWN_RECEIVED state.
Signed-off-by: Wei Yongjun <yjwei@cn.fujitsu.com>
Signed-off-by: Vlad Yasevich <vladislav.yasevich@hp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Several sparse warnings were introduced by patches accepted during the merge
window which weren't caught. This patch fixes those warnings.
Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
This patch implements the RDMA transport provider for 9P. It allows
mounts to be performed over iWARP and IB capable network interfaces.
Signed-off-by: Tom Tucker <tom@opengridcomputing.com>
Signed-off-by: Latchesar Ionkov <lionkov@lanl.gov>
Fixes build problem with 9p when building with debug disabled.
Also contains some fixes for warnings which pop up when
CONFIG_NET_9P_DEBUG is disabled.
Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
* 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/ericvh/v9fs: (26 commits)
9p: add more conservative locking
9p: fix oops in protocol stat parsing error path.
9p: fix device file handling
9p: Improve debug support
9p: eliminate depricated conv functions
9p: rework client code to use new protocol support functions
9p: remove unnecessary tag field from p9_req_t structure
9p: remove 9p fcall debug prints
9p: add new protocol support code
9p: encapsulate version function
9p: move dirread to fs layer
9p: adjust 9p vfs write operation
9p: move readn meta-function from client to fs layer
9p: consolidate read/write functions
9p: drop broken unused error path from p9_conn_create()
9p: make rpc code common and rework flush code
9p: use the rcall structure passed in the request in trans_fd read_work
9p: apply common request code to trans_fd
9p: apply common tagpool handling to trans_fd
9p: move request management to client code
...
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6:
netfilter: replace old NF_ARP calls with NFPROTO_ARP
netfilter: fix compilation error with NAT=n
netfilter: xt_recent: use proc_create_data()
netfilter: snmp nat leaks memory in case of failure
netfilter: xt_iprange: fix range inversion match
netfilter: netns: use NFPROTO_NUMPROTO instead of NUMPROTO for tables array
netfilter: ctnetlink: remove obsolete NAT dependency from Kconfig
pkt_sched: sch_generic: Fix oops in sch_teql
dccp: Port redirection support for DCCP
tcp: Fix IPv6 fallout from 'Port redirection support for TCP'
netdev: change name dropping error codes
ipvs: Update CONFIG_IP_VS_IPV6 description and help text
The netfilter families have been decoupled from regular protocol families.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
The new debug support lacks some of the information that the previous fcprint
code provided -- this patch focuses on better presentation of debug data along
with more helpful debug along error paths.
Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
Remove depricated conv functions which have been replaced with new
protocol routines.
This patch also reworks the one instance of the file-system code which
directly calls conversion routines (to accomplish unpacking dirreads).
Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
Now that the new protocol functions are in place, this patch switches
the client code to using the new support code.
Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
One of the current debug options allows users to get a verbose dump of fcalls.
This isn't really necessary as correctly parsed protocol frames can be printed
as part of the code in the client functions. The consolidated printfcalls
structure would require new entries to be added for every extension. This
patch removes the debug print methods and their use.
Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
This adds a new protocol processing support code based on Anthony Liguori's
9p library code. This code performs protocol marshalling/unmarshalling using
printf like strings to represent protocol elements. It is my intent to use
them to replace the current functions in conv.c as well as the
p9_create_* functions.
This should make the client implementation much more clear, and also make it
much easier to add new protocol extensions by limiting the number of places
in which changes need to be made.
Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
Currently reading a directory is implemented in the client code.
This function is not actually a wire operation, but a meta operation
which calls read operations and processes the results.
This patch moves this functionality to the fs layer and calls component
wire operations instead of constructing their packets. This provides a
cleaner separation and will help when we reorganize the client functions
and protocol processing methods.
Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
There are a couple of methods in the client code which aren't actually
wire operations. To keep things organized cleaner, these operations are
being moved to the fs layer.
This patch moves the readn meta-function (which executes multiple wire
reads until a buffer is full) to the fs layer.
Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
