When __inet_inherit_port() is called on a tproxy connection the wrong locks are
held for the inet_bind_bucket it is added to. __inet_inherit_port() made an
implicit assumption that the listener's port number (and thus its bind bucket).
Unfortunately, if you're using the TPROXY target to redirect skbs to a
transparent proxy that assumption is not true anymore and things break.
This patch adds code to __inet_inherit_port() so that it can handle this case
by looking up or creating a new bind bucket for the child socket and updates
callers of __inet_inherit_port() to gracefully handle __inet_inherit_port()
failing.
Reported by and original patch from Stephen Buck <stephen.buck@exinda.com>.
See http://marc.info/?t=128169268200001&r=1&w=2 for the original discussion.
Signed-off-by: KOVACS Krisztian <hidden@balabit.hu>
Signed-off-by: Patrick McHardy <kaber@trash.net>
First patch changes __inet_hash_nolisten() and __inet6_hash()
to get a timewait parameter to be able to unhash it from ehash
at same time the new socket is inserted in hash.
This makes sure timewait socket wont be found by a concurrent
writer in __inet_check_established()
Reported-by: kapil dakhane <kdakhane@gmail.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The first "node" is supposed to be the cursor used in the for_each.
The second "node" is ment literally and should not be macro expanded:
it's the name of the hlist_node field from the inet_bind_bucket.
This currently works because when inet_bind_bucket_for_each is called
it's argument is still "node".
Signed-off-by: Lucian Adrian Grijincu <lgrijincu@ixiacom.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>
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>
Define three accessors to get/set dst attached to a skb
struct dst_entry *skb_dst(const struct sk_buff *skb)
void skb_dst_set(struct sk_buff *skb, struct dst_entry *dst)
void skb_dst_drop(struct sk_buff *skb)
This one should replace occurrences of :
dst_release(skb->dst)
skb->dst = NULL;
Delete skb->dst field
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
And switch bsockets to atomic_t since it might be changed in parallel.
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Acked-by: Evgeniy Polyakov <zbr@ioremap.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
In commit 9db66bdcc8 (net: convert
TCP/DCCP ehash rwlocks to spinlocks), I forgot to change one
occurrence of rwlock_t to spinlock_t
I believe sizeof(raw_spinlock_t) might be > 0 on !CONFIG_SMP if
CONFIG_DEBUG_SPINLOCK while sizeof(raw_rwlock_t) should be 0 in this
case.
Fortunatly, CONFIG_DEBUG_SPINLOCK adds fields to both spinlock_t and
rwlock_t, but at this might change in the future (being able to debug
spinlocks but not rwlocks for example), better to be safe.
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
With simple extension to the binding mechanism, which allows to bind more
than 64k sockets (or smaller amount, depending on sysctl parameters),
we have to traverse the whole bind hash table to find out empty bucket.
And while it is not a problem for example for 32k connections, bind()
completion time grows exponentially (since after each successful binding
we have to traverse one bucket more to find empty one) even if we start
each time from random offset inside the hash table.
So, when hash table is full, and we want to add another socket, we have
to traverse the whole table no matter what, so effectivelly this will be
the worst case performance and it will be constant.
Attached picture shows bind() time depending on number of already bound
sockets.
Green area corresponds to the usual binding to zero port process, which
turns on kernel port selection as described above. Red area is the bind
process, when number of reuse-bound sockets is not limited by 64k (or
sysctl parameters). The same exponential growth (hidden by the green
area) before number of ports reaches sysctl limit.
At this time bind hash table has exactly one reuse-enbaled socket in a
bucket, but it is possible that they have different addresses. Actually
kernel selects the first port to try randomly, so at the beginning bind
will take roughly constant time, but with time number of port to check
after random start will increase. And that will have exponential growth,
but because of above random selection, not every next port selection
will necessary take longer time than previous. So we have to consider
the area below in the graph (if you could zoom it, you could find, that
there are many different times placed there), so area can hide another.
Blue area corresponds to the port selection optimization.
This is rather simple design approach: hashtable now maintains (unprecise
and racely updated) number of currently bound sockets, and when number
of such sockets becomes greater than predefined value (I use maximum
port range defined by sysctls), we stop traversing the whole bind hash
table and just stop at first matching bucket after random start. Above
limit roughly corresponds to the case, when bind hash table is full and
we turned on mechanism of allowing to bind more reuse-enabled sockets,
so it does not change behaviour of other sockets.
Signed-off-by: Evgeniy Polyakov <zbr@ioremap.net>
Tested-by: Denys Fedoryschenko <denys@visp.net.lb>
Signed-off-by: David S. Miller <davem@davemloft.net>
This is the last step to be able to perform full RCU lookups
in __inet_lookup() : After established/timewait tables, we
add RCU lookups to listening hash table.
The only trick here is that a socket of a given type (TCP ipv4,
TCP ipv6, ...) can now flight between two different tables
(established and listening) during a RCU grace period, so we
must use different 'nulls' end-of-chain values for two tables.
We define a large value :
#define LISTENING_NULLS_BASE (1U << 29)
So that slots in listening table are guaranteed to have different
end-of-chain values than slots in established table. A reader can
still detect it finished its lookup in the right chain.
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We can avoid some useless instructions if !CONFIG_NET_NS
Because of RCU, we use INET_MATCH or INET_TW_MATCH twice for the found
socket, so thats six instructions less per incoming TCP packet.
Yet another tbench speedup :)
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Now TCP & DCCP use RCU lookups, we can convert ehash rwlocks to spinlocks.
/proc/net/tcp and other seq_file 'readers' can safely be converted to 'writers'.
This should speedup writers, since spin_lock()/spin_unlock()
only use one atomic operation instead of two for write_lock()/write_unlock()
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch prepares RCU migration of listening_hash table for
TCP/DCCP protocols.
listening_hash table being small (32 slots per protocol), we add
a spinlock for each slot, instead of a single rwlock for whole table.
This should reduce hold time of readers, and writers concurrency.
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
RCU was added to UDP lookups, using a fast infrastructure :
- sockets kmem_cache use SLAB_DESTROY_BY_RCU and dont pay the
price of call_rcu() at freeing time.
- hlist_nulls permits to use few memory barriers.
This patch uses same infrastructure for TCP/DCCP established
and timewait sockets.
Thanks to SLAB_DESTROY_BY_RCU, no slowdown for applications
using short lived TCP connections. A followup patch, converting
rwlocks to spinlocks will even speedup this case.
__inet_lookup_established() is pretty fast now we dont have to
dirty a contended cache line (read_lock/read_unlock)
Only established and timewait hashtable are converted to RCU
(bind table and listen table are still using traditional locking)
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We can shrink size of "struct inet_bind_bucket" by 50%, using
read_pnet() and write_pnet()
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use the socket cached in the skb if it's present.
Signed-off-by: KOVACS Krisztian <hidden@sch.bme.hu>
Acked-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
To be able to use the cached socket reference in the skb during input
processing we add a new set of lookup functions that receive the skb on
their argument list.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: KOVACS Krisztian <hidden@sch.bme.hu>
Signed-off-by: David S. Miller <davem@davemloft.net>
There are many possible ways to add this "salt", thus I made this
patch to be the last in the series to change it if required.
Currently I propose to use the struct net pointer itself as this
salt, but since this pointer is most often cache-line aligned, shift
this right to eliminate the bits, that are most often zeroed.
After this, simply add this mix to prepared hashfn-s.
For CONFIG_NET_NS=n case this salt is 0 and no changes in hashfn
appear.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Listening-on-one-port sockets in many namespaces produce long
chains in the listening_hash-es, so prepare the inet_lhashfn to
take struct net into account.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Binding to some port in many namespaces may create too long
chains in bhash-es, so prepare the hashfn to take struct net
into account.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
This deblats ~200 bytes when ipv6 and dccp are 'y'.
Besides, this will ease compilation issues for patches
I'm working on to make inet hash tables more scalable
wrt net namespaces.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
As I can see from the code, two places (tcp_v6_syn_recv_sock and
dccp_v6_request_recv_sock) that call this one already run with
BHs disabled, so it's safe to call __inet_inherit_port there.
Besides (in case I missed smth with code review) the calltrace
tcp_v6_syn_recv_sock
`- tcp_v4_syn_recv_sock
`- __inet_inherit_port
and the similar for DCCP are valid, but assumes BHs to be disabled.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Introduce per-sock inlines: sock_net(), sock_net_set()
and per-inet_timewait_sock inlines: twsk_net(), twsk_net_set().
Without CONFIG_NET_NS, no namespace other than &init_net exists.
Let's explicitly define them to help compiler optimizations.
Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
