2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2007-02-09 23:24:49 +09:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2007-02-09 23:24:49 +09:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-12-11 11:30:32 -08:00
|
|
|
|
2005-12-13 23:16:37 -08:00
|
|
|
|
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files. percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.
percpu.h -> slab.h dependency is about to be removed. Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability. As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.
http://userweb.kernel.org/~tj/misc/slabh-sweep.py
The script does the followings.
* Scan files for gfp and slab usages and update includes such that
only the necessary includes are there. ie. if only gfp is used,
gfp.h, if slab is used, slab.h.
* When the script inserts a new include, it looks at the include
blocks and try to put the new include such that its order conforms
to its surrounding. It's put in the include block which contains
core kernel includes, in the same order that the rest are ordered -
alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
doesn't seem to be any matching order.
* If the script can't find a place to put a new include (mostly
because the file doesn't have fitting include block), it prints out
an error message indicating which .h file needs to be added to the
file.
The conversion was done in the following steps.
1. The initial automatic conversion of all .c files updated slightly
over 4000 files, deleting around 700 includes and adding ~480 gfp.h
and ~3000 slab.h inclusions. The script emitted errors for ~400
files.
2. Each error was manually checked. Some didn't need the inclusion,
some needed manual addition while adding it to implementation .h or
embedding .c file was more appropriate for others. This step added
inclusions to around 150 files.
3. The script was run again and the output was compared to the edits
from #2 to make sure no file was left behind.
4. Several build tests were done and a couple of problems were fixed.
e.g. lib/decompress_*.c used malloc/free() wrappers around slab
APIs requiring slab.h to be added manually.
5. The script was run on all .h files but without automatically
editing them as sprinkling gfp.h and slab.h inclusions around .h
files could easily lead to inclusion dependency hell. Most gfp.h
inclusion directives were ignored as stuff from gfp.h was usually
wildly available and often used in preprocessor macros. Each
slab.h inclusion directive was examined and added manually as
necessary.
6. percpu.h was updated not to include slab.h.
7. Build test were done on the following configurations and failures
were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my
distributed build env didn't work with gcov compiles) and a few
more options had to be turned off depending on archs to make things
build (like ipr on powerpc/64 which failed due to missing writeq).
* x86 and x86_64 UP and SMP allmodconfig and a custom test config.
* powerpc and powerpc64 SMP allmodconfig
* sparc and sparc64 SMP allmodconfig
* ia64 SMP allmodconfig
* s390 SMP allmodconfig
* alpha SMP allmodconfig
* um on x86_64 SMP allmodconfig
8. percpu.h modifications were reverted so that it could be applied as
a separate patch and serve as bisection point.
Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.
Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 17:04:11 +09:00
|
|
|
|
2016-12-24 11:46:01 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2016-02-10 11:50:36 -05:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-08-09 20:08:28 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2017-04-18 11:39:41 -06:00
|
|
|
|
2013-01-22 09:50:44 +00:00
|
|
|
|
2013-07-10 17:13:17 +03:00
|
|
|
|
2016-01-04 17:41:46 -05:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-06-27 00:23:44 +00:00
|
|
|
|
2006-11-27 11:10:57 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2017-01-26 18:02:24 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-03-18 14:05:33 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-10-19 21:48:52 +02:00
|
|
|
|
2013-10-19 21:48:57 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-10-19 21:48:52 +02:00
|
|
|
|
2013-10-19 21:48:57 +02:00
|
|
|
|
2013-10-19 21:48:52 +02:00
|
|
|
|
|
|
|
|
|
2015-03-18 14:05:33 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-11-08 10:17:30 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-11-09 12:05:53 +00:00
|
|
|
|
2010-04-20 19:06:52 -07:00
|
|
|
|
2009-11-08 10:17:30 +00:00
|
|
|
|
2010-04-20 19:06:52 -07:00
|
|
|
|
2009-11-08 10:17:30 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-03-22 16:51:21 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2009-11-09 05:26:33 +00:00
|
|
|
|
|
|
|
|
|
2012-05-19 01:45:21 +00:00
|
|
|
|
ipv6: make lookups simpler and faster
TCP listener refactoring, part 4 :
To speed up inet lookups, we moved IPv4 addresses from inet to struct
sock_common
Now is time to do the same for IPv6, because it permits us to have fast
lookups for all kind of sockets, including upcoming SYN_RECV.
Getting IPv6 addresses in TCP lookups currently requires two extra cache
lines, plus a dereference (and memory stall).
inet6_sk(sk) does the dereference of inet_sk(__sk)->pinet6
This patch is way bigger than its IPv4 counter part, because for IPv4,
we could add aliases (inet_daddr, inet_rcv_saddr), while on IPv6,
it's not doable easily.
inet6_sk(sk)->daddr becomes sk->sk_v6_daddr
inet6_sk(sk)->rcv_saddr becomes sk->sk_v6_rcv_saddr
And timewait socket also have tw->tw_v6_daddr & tw->tw_v6_rcv_saddr
at the same offset.
We get rid of INET6_TW_MATCH() as INET6_MATCH() is now the generic
macro.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-03 15:42:29 -07:00
|
|
|
|
2009-11-09 05:26:33 +00:00
|
|
|
|
2009-11-08 10:17:30 +00:00
|
|
|
|
2009-11-09 05:26:33 +00:00
|
|
|
|
2017-01-17 07:51:01 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
udp: add rehash on connect()
commit 30fff923 introduced in linux-2.6.33 (udp: bind() optimisation)
added a secondary hash on UDP, hashed on (local addr, local port).
Problem is that following sequence :
fd = socket(...)
connect(fd, &remote, ...)
not only selects remote end point (address and port), but also sets
local address, while UDP stack stored in secondary hash table the socket
while its local address was INADDR_ANY (or ipv6 equivalent)
Sequence is :
- autobind() : choose a random local port, insert socket in hash tables
[while local address is INADDR_ANY]
- connect() : set remote address and port, change local address to IP
given by a route lookup.
When an incoming UDP frame comes, if more than 10 sockets are found in
primary hash table, we switch to secondary table, and fail to find
socket because its local address changed.
One solution to this problem is to rehash datagram socket if needed.
We add a new rehash(struct socket *) method in "struct proto", and
implement this method for UDP v4 & v6, using a common helper.
This rehashing only takes care of secondary hash table, since primary
hash (based on local port only) is not changed.
Reported-by: Krzysztof Piotr Oledzki <ole@ans.pl>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Tested-by: Krzysztof Piotr Oledzki <ole@ans.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-09-08 05:08:44 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
ipv6: make lookups simpler and faster
TCP listener refactoring, part 4 :
To speed up inet lookups, we moved IPv4 addresses from inet to struct
sock_common
Now is time to do the same for IPv6, because it permits us to have fast
lookups for all kind of sockets, including upcoming SYN_RECV.
Getting IPv6 addresses in TCP lookups currently requires two extra cache
lines, plus a dereference (and memory stall).
inet6_sk(sk) does the dereference of inet_sk(__sk)->pinet6
This patch is way bigger than its IPv4 counter part, because for IPv4,
we could add aliases (inet_daddr, inet_rcv_saddr), while on IPv6,
it's not doable easily.
inet6_sk(sk)->daddr becomes sk->sk_v6_daddr
inet6_sk(sk)->rcv_saddr becomes sk->sk_v6_rcv_saddr
And timewait socket also have tw->tw_v6_daddr & tw->tw_v6_rcv_saddr
at the same offset.
We get rid of INET6_TW_MATCH() as INET6_MATCH() is now the generic
macro.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-03 15:42:29 -07:00
|
|
|
|
udp: add rehash on connect()
commit 30fff923 introduced in linux-2.6.33 (udp: bind() optimisation)
added a secondary hash on UDP, hashed on (local addr, local port).
Problem is that following sequence :
fd = socket(...)
connect(fd, &remote, ...)
not only selects remote end point (address and port), but also sets
local address, while UDP stack stored in secondary hash table the socket
while its local address was INADDR_ANY (or ipv6 equivalent)
Sequence is :
- autobind() : choose a random local port, insert socket in hash tables
[while local address is INADDR_ANY]
- connect() : set remote address and port, change local address to IP
given by a route lookup.
When an incoming UDP frame comes, if more than 10 sockets are found in
primary hash table, we switch to secondary table, and fail to find
socket because its local address changed.
One solution to this problem is to rehash datagram socket if needed.
We add a new rehash(struct socket *) method in "struct proto", and
implement this method for UDP v4 & v6, using a common helper.
This rehashing only takes care of secondary hash table, since primary
hash (based on local port only) is not changed.
Reported-by: Krzysztof Piotr Oledzki <ole@ans.pl>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Tested-by: Krzysztof Piotr Oledzki <ole@ans.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-09-08 05:08:44 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
udp reuseport: fix packet of same flow hashed to different socket
There is a corner case in which udp packets belonging to a same
flow are hashed to different socket when hslot->count changes from 10
to 11:
1) When hslot->count <= 10, __udp_lib_lookup() searches udp_table->hash,
and always passes 'daddr' to udp_ehashfn().
2) When hslot->count > 10, __udp_lib_lookup() searches udp_table->hash2,
but may pass 'INADDR_ANY' to udp_ehashfn() if the sockets are bound to
INADDR_ANY instead of some specific addr.
That means when hslot->count changes from 10 to 11, the hash calculated by
udp_ehashfn() is also changed, and the udp packets belonging to a same
flow will be hashed to different socket.
This is easily reproduced:
1) Create 10 udp sockets and bind all of them to 0.0.0.0:40000.
2) From the same host send udp packets to 127.0.0.1:40000, record the
socket index which receives the packets.
3) Create 1 more udp socket and bind it to 0.0.0.0:44096. The number 44096
is 40000 + UDP_HASH_SIZE(4096), this makes the new socket put into the
same hslot as the aformentioned 10 sockets, and makes the hslot->count
change from 10 to 11.
4) From the same host send udp packets to 127.0.0.1:40000, and the socket
index which receives the packets will be different from the one received
in step 2.
This should not happen as the socket bound to 0.0.0.0:44096 should not
change the behavior of the sockets bound to 0.0.0.0:40000.
It's the same case for IPv6, and this patch also fixes that.
Signed-off-by: Su, Xuemin <suxm@chinanetcenter.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-13 11:02:50 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-08-07 08:44:20 -07:00
|
|
|
|
2008-10-29 01:41:45 -07:00
|
|
|
|
2014-12-01 20:29:06 -08:00
|
|
|
|
|
|
|
|
|
2008-10-29 01:41:45 -07:00
|
|
|
|
2014-12-01 20:29:06 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-10-29 01:41:45 -07:00
|
|
|
|
2014-12-01 20:29:06 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-10-29 01:41:45 -07:00
|
|
|
|
2014-12-01 20:29:06 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-01-26 18:02:24 +00:00
|
|
|
|
2017-08-07 08:44:20 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-12-01 20:29:06 -08:00
|
|
|
|
2017-08-07 08:44:20 -07:00
|
|
|
|
|
|
|
|
|
2014-12-01 20:29:06 -08:00
|
|
|
|
|
|
|
|
|
2015-10-08 19:33:21 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-10-29 01:41:45 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
udp reuseport: fix packet of same flow hashed to different socket
There is a corner case in which udp packets belonging to a same
flow are hashed to different socket when hslot->count changes from 10
to 11:
1) When hslot->count <= 10, __udp_lib_lookup() searches udp_table->hash,
and always passes 'daddr' to udp_ehashfn().
2) When hslot->count > 10, __udp_lib_lookup() searches udp_table->hash2,
but may pass 'INADDR_ANY' to udp_ehashfn() if the sockets are bound to
INADDR_ANY instead of some specific addr.
That means when hslot->count changes from 10 to 11, the hash calculated by
udp_ehashfn() is also changed, and the udp packets belonging to a same
flow will be hashed to different socket.
This is easily reproduced:
1) Create 10 udp sockets and bind all of them to 0.0.0.0:40000.
2) From the same host send udp packets to 127.0.0.1:40000, record the
socket index which receives the packets.
3) Create 1 more udp socket and bind it to 0.0.0.0:44096. The number 44096
is 40000 + UDP_HASH_SIZE(4096), this makes the new socket put into the
same hslot as the aformentioned 10 sockets, and makes the hslot->count
change from 10 to 11.
4) From the same host send udp packets to 127.0.0.1:40000, and the socket
index which receives the packets will be different from the one received
in step 2.
This should not happen as the socket bound to 0.0.0.0:44096 should not
change the behavior of the sockets bound to 0.0.0.0:40000.
It's the same case for IPv6, and this patch also fixes that.
Signed-off-by: Su, Xuemin <suxm@chinanetcenter.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-13 11:02:50 +08:00
|
|
|
|
ipv6: udp: optimize unicast RX path
We first locate the (local port) hash chain head
If few sockets are in this chain, we proceed with previous lookup algo.
If too many sockets are listed, we take a look at the secondary
(port, address) hash chain.
We choose the shortest chain and proceed with a RCU lookup on the elected chain.
But, if we chose (port, address) chain, and fail to find a socket on given address,
we must try another lookup on (port, in6addr_any) chain to find sockets not bound
to a particular IP.
-> No extra cost for typical setups, where the first lookup will probabbly
be performed.
RCU lookups everywhere, we dont acquire spinlock.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-08 10:18:30 +00:00
|
|
|
|
|
|
|
|
|
2017-08-07 08:44:20 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
ipv6: udp: optimize unicast RX path
We first locate the (local port) hash chain head
If few sockets are in this chain, we proceed with previous lookup algo.
If too many sockets are listed, we take a look at the secondary
(port, address) hash chain.
We choose the shortest chain and proceed with a RCU lookup on the elected chain.
But, if we chose (port, address) chain, and fail to find a socket on given address,
we must try another lookup on (port, in6addr_any) chain to find sockets not bound
to a particular IP.
-> No extra cost for typical setups, where the first lookup will probabbly
be performed.
RCU lookups everywhere, we dont acquire spinlock.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-08 10:18:30 +00:00
|
|
|
|
|
|
|
|
|
2013-01-22 09:50:44 +00:00
|
|
|
|
|
|
|
|
|
ipv6: udp: optimize unicast RX path
We first locate the (local port) hash chain head
If few sockets are in this chain, we proceed with previous lookup algo.
If too many sockets are listed, we take a look at the secondary
(port, address) hash chain.
We choose the shortest chain and proceed with a RCU lookup on the elected chain.
But, if we chose (port, address) chain, and fail to find a socket on given address,
we must try another lookup on (port, in6addr_any) chain to find sockets not bound
to a particular IP.
-> No extra cost for typical setups, where the first lookup will probabbly
be performed.
RCU lookups everywhere, we dont acquire spinlock.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-08 10:18:30 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-04-01 08:52:13 -07:00
|
|
|
|
udp reuseport: fix packet of same flow hashed to different socket
There is a corner case in which udp packets belonging to a same
flow are hashed to different socket when hslot->count changes from 10
to 11:
1) When hslot->count <= 10, __udp_lib_lookup() searches udp_table->hash,
and always passes 'daddr' to udp_ehashfn().
2) When hslot->count > 10, __udp_lib_lookup() searches udp_table->hash2,
but may pass 'INADDR_ANY' to udp_ehashfn() if the sockets are bound to
INADDR_ANY instead of some specific addr.
That means when hslot->count changes from 10 to 11, the hash calculated by
udp_ehashfn() is also changed, and the udp packets belonging to a same
flow will be hashed to different socket.
This is easily reproduced:
1) Create 10 udp sockets and bind all of them to 0.0.0.0:40000.
2) From the same host send udp packets to 127.0.0.1:40000, record the
socket index which receives the packets.
3) Create 1 more udp socket and bind it to 0.0.0.0:44096. The number 44096
is 40000 + UDP_HASH_SIZE(4096), this makes the new socket put into the
same hslot as the aformentioned 10 sockets, and makes the hslot->count
change from 10 to 11.
4) From the same host send udp packets to 127.0.0.1:40000, and the socket
index which receives the packets will be different from the one received
in step 2.
This should not happen as the socket bound to 0.0.0.0:44096 should not
change the behavior of the sockets bound to 0.0.0.0:40000.
It's the same case for IPv6, and this patch also fixes that.
Signed-off-by: Su, Xuemin <suxm@chinanetcenter.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-13 11:02:50 +08:00
|
|
|
|
2017-08-07 08:44:20 -07:00
|
|
|
|
ipv6: udp: optimize unicast RX path
We first locate the (local port) hash chain head
If few sockets are in this chain, we proceed with previous lookup algo.
If too many sockets are listed, we take a look at the secondary
(port, address) hash chain.
We choose the shortest chain and proceed with a RCU lookup on the elected chain.
But, if we chose (port, address) chain, and fail to find a socket on given address,
we must try another lookup on (port, in6addr_any) chain to find sockets not bound
to a particular IP.
-> No extra cost for typical setups, where the first lookup will probabbly
be performed.
RCU lookups everywhere, we dont acquire spinlock.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-08 10:18:30 +00:00
|
|
|
|
2013-01-22 09:50:44 +00:00
|
|
|
|
|
|
|
|
|
2013-10-19 21:48:52 +02:00
|
|
|
|
|
|
|
|
|
udp: fix potential infinite loop in SO_REUSEPORT logic
Using a combination of connected and un-connected sockets, Dmitry
was able to trigger soft lockups with his fuzzer.
The problem is that sockets in the SO_REUSEPORT array might have
different scores.
Right after sk2=socket(), setsockopt(sk2,...,SO_REUSEPORT, on) and
bind(sk2, ...), but _before_ the connect(sk2) is done, sk2 is added into
the soreuseport array, with a score which is smaller than the score of
first socket sk1 found in hash table (I am speaking of the regular UDP
hash table), if sk1 had the connect() done, giving a +8 to its score.
hash bucket [X] -> sk1 -> sk2 -> NULL
sk1 score = 14 (because it did a connect())
sk2 score = 6
SO_REUSEPORT fast selection is an optimization. If it turns out the
score of the selected socket does not match score of first socket, just
fallback to old SO_REUSEPORT logic instead of trying to be too smart.
Normal SO_REUSEPORT users do not mix different kind of sockets, as this
mechanism is used for load balance traffic.
Fixes: e32ea7e74727 ("soreuseport: fast reuseport UDP socket selection")
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Craig Gallek <kraigatgoog@gmail.com>
Acked-by: Craig Gallek <kraig@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2016-01-19 08:36:43 -08:00
|
|
|
|
2016-04-01 08:52:13 -07:00
|
|
|
|
udp: fix potential infinite loop in SO_REUSEPORT logic
Using a combination of connected and un-connected sockets, Dmitry
was able to trigger soft lockups with his fuzzer.
The problem is that sockets in the SO_REUSEPORT array might have
different scores.
Right after sk2=socket(), setsockopt(sk2,...,SO_REUSEPORT, on) and
bind(sk2, ...), but _before_ the connect(sk2) is done, sk2 is added into
the soreuseport array, with a score which is smaller than the score of
first socket sk1 found in hash table (I am speaking of the regular UDP
hash table), if sk1 had the connect() done, giving a +8 to its score.
hash bucket [X] -> sk1 -> sk2 -> NULL
sk1 score = 14 (because it did a connect())
sk2 score = 6
SO_REUSEPORT fast selection is an optimization. If it turns out the
score of the selected socket does not match score of first socket, just
fallback to old SO_REUSEPORT logic instead of trying to be too smart.
Normal SO_REUSEPORT users do not mix different kind of sockets, as this
mechanism is used for load balance traffic.
Fixes: e32ea7e74727 ("soreuseport: fast reuseport UDP socket selection")
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Craig Gallek <kraigatgoog@gmail.com>
Acked-by: Craig Gallek <kraig@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2016-01-19 08:36:43 -08:00
|
|
|
|
2016-04-01 08:52:13 -07:00
|
|
|
|
|
|
|
|
|
2013-01-22 09:50:44 +00:00
|
|
|
|
2015-10-08 19:33:21 -07:00
|
|
|
|
2016-04-01 08:52:13 -07:00
|
|
|
|
|
|
|
|
|
2013-01-22 09:50:44 +00:00
|
|
|
|
|
|
|
|
|
2014-08-23 20:58:54 +02:00
|
|
|
|
2013-01-22 09:50:44 +00:00
|
|
|
|
|
|
|
|
|
ipv6: udp: optimize unicast RX path
We first locate the (local port) hash chain head
If few sockets are in this chain, we proceed with previous lookup algo.
If too many sockets are listed, we take a look at the secondary
(port, address) hash chain.
We choose the shortest chain and proceed with a RCU lookup on the elected chain.
But, if we chose (port, address) chain, and fail to find a socket on given address,
we must try another lookup on (port, in6addr_any) chain to find sockets not bound
to a particular IP.
-> No extra cost for typical setups, where the first lookup will probabbly
be performed.
RCU lookups everywhere, we dont acquire spinlock.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-08 10:18:30 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-04-01 08:52:13 -07:00
|
|
|
|
2011-12-09 06:23:34 +00:00
|
|
|
|
2017-08-07 08:44:20 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
udp: RCU handling for Unicast packets.
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>
2008-10-29 02:11:14 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
ipv6: udp: optimize unicast RX path
We first locate the (local port) hash chain head
If few sockets are in this chain, we proceed with previous lookup algo.
If too many sockets are listed, we take a look at the secondary
(port, address) hash chain.
We choose the shortest chain and proceed with a RCU lookup on the elected chain.
But, if we chose (port, address) chain, and fail to find a socket on given address,
we must try another lookup on (port, in6addr_any) chain to find sockets not bound
to a particular IP.
-> No extra cost for typical setups, where the first lookup will probabbly
be performed.
RCU lookups everywhere, we dont acquire spinlock.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-08 10:18:30 +00:00
|
|
|
|
|
|
|
|
|
2017-01-26 18:02:24 +00:00
|
|
|
|
2013-01-22 09:50:44 +00:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
ipv6: udp: optimize unicast RX path
We first locate the (local port) hash chain head
If few sockets are in this chain, we proceed with previous lookup algo.
If too many sockets are listed, we take a look at the secondary
(port, address) hash chain.
We choose the shortest chain and proceed with a RCU lookup on the elected chain.
But, if we chose (port, address) chain, and fail to find a socket on given address,
we must try another lookup on (port, in6addr_any) chain to find sockets not bound
to a particular IP.
-> No extra cost for typical setups, where the first lookup will probabbly
be performed.
RCU lookups everywhere, we dont acquire spinlock.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-08 10:18:30 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-08-07 08:44:20 -07:00
|
|
|
|
udp reuseport: fix packet of same flow hashed to different socket
There is a corner case in which udp packets belonging to a same
flow are hashed to different socket when hslot->count changes from 10
to 11:
1) When hslot->count <= 10, __udp_lib_lookup() searches udp_table->hash,
and always passes 'daddr' to udp_ehashfn().
2) When hslot->count > 10, __udp_lib_lookup() searches udp_table->hash2,
but may pass 'INADDR_ANY' to udp_ehashfn() if the sockets are bound to
INADDR_ANY instead of some specific addr.
That means when hslot->count changes from 10 to 11, the hash calculated by
udp_ehashfn() is also changed, and the udp packets belonging to a same
flow will be hashed to different socket.
This is easily reproduced:
1) Create 10 udp sockets and bind all of them to 0.0.0.0:40000.
2) From the same host send udp packets to 127.0.0.1:40000, record the
socket index which receives the packets.
3) Create 1 more udp socket and bind it to 0.0.0.0:44096. The number 44096
is 40000 + UDP_HASH_SIZE(4096), this makes the new socket put into the
same hslot as the aformentioned 10 sockets, and makes the hslot->count
change from 10 to 11.
4) From the same host send udp packets to 127.0.0.1:40000, and the socket
index which receives the packets will be different from the one received
in step 2.
This should not happen as the socket bound to 0.0.0.0:44096 should not
change the behavior of the sockets bound to 0.0.0.0:40000.
It's the same case for IPv6, and this patch also fixes that.
Signed-off-by: Su, Xuemin <suxm@chinanetcenter.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-13 11:02:50 +08:00
|
|
|
|
ipv6: udp: optimize unicast RX path
We first locate the (local port) hash chain head
If few sockets are in this chain, we proceed with previous lookup algo.
If too many sockets are listed, we take a look at the secondary
(port, address) hash chain.
We choose the shortest chain and proceed with a RCU lookup on the elected chain.
But, if we chose (port, address) chain, and fail to find a socket on given address,
we must try another lookup on (port, in6addr_any) chain to find sockets not bound
to a particular IP.
-> No extra cost for typical setups, where the first lookup will probabbly
be performed.
RCU lookups everywhere, we dont acquire spinlock.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-08 10:18:30 +00:00
|
|
|
|
udp reuseport: fix packet of same flow hashed to different socket
There is a corner case in which udp packets belonging to a same
flow are hashed to different socket when hslot->count changes from 10
to 11:
1) When hslot->count <= 10, __udp_lib_lookup() searches udp_table->hash,
and always passes 'daddr' to udp_ehashfn().
2) When hslot->count > 10, __udp_lib_lookup() searches udp_table->hash2,
but may pass 'INADDR_ANY' to udp_ehashfn() if the sockets are bound to
INADDR_ANY instead of some specific addr.
That means when hslot->count changes from 10 to 11, the hash calculated by
udp_ehashfn() is also changed, and the udp packets belonging to a same
flow will be hashed to different socket.
This is easily reproduced:
1) Create 10 udp sockets and bind all of them to 0.0.0.0:40000.
2) From the same host send udp packets to 127.0.0.1:40000, record the
socket index which receives the packets.
3) Create 1 more udp socket and bind it to 0.0.0.0:44096. The number 44096
is 40000 + UDP_HASH_SIZE(4096), this makes the new socket put into the
same hslot as the aformentioned 10 sockets, and makes the hslot->count
change from 10 to 11.
4) From the same host send udp packets to 127.0.0.1:40000, and the socket
index which receives the packets will be different from the one received
in step 2.
This should not happen as the socket bound to 0.0.0.0:44096 should not
change the behavior of the sockets bound to 0.0.0.0:40000.
It's the same case for IPv6, and this patch also fixes that.
Signed-off-by: Su, Xuemin <suxm@chinanetcenter.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-13 11:02:50 +08:00
|
|
|
|
ipv6: udp: optimize unicast RX path
We first locate the (local port) hash chain head
If few sockets are in this chain, we proceed with previous lookup algo.
If too many sockets are listed, we take a look at the secondary
(port, address) hash chain.
We choose the shortest chain and proceed with a RCU lookup on the elected chain.
But, if we chose (port, address) chain, and fail to find a socket on given address,
we must try another lookup on (port, in6addr_any) chain to find sockets not bound
to a particular IP.
-> No extra cost for typical setups, where the first lookup will probabbly
be performed.
RCU lookups everywhere, we dont acquire spinlock.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-08 10:18:30 +00:00
|
|
|
|
|
|
|
|
|
udp reuseport: fix packet of same flow hashed to different socket
There is a corner case in which udp packets belonging to a same
flow are hashed to different socket when hslot->count changes from 10
to 11:
1) When hslot->count <= 10, __udp_lib_lookup() searches udp_table->hash,
and always passes 'daddr' to udp_ehashfn().
2) When hslot->count > 10, __udp_lib_lookup() searches udp_table->hash2,
but may pass 'INADDR_ANY' to udp_ehashfn() if the sockets are bound to
INADDR_ANY instead of some specific addr.
That means when hslot->count changes from 10 to 11, the hash calculated by
udp_ehashfn() is also changed, and the udp packets belonging to a same
flow will be hashed to different socket.
This is easily reproduced:
1) Create 10 udp sockets and bind all of them to 0.0.0.0:40000.
2) From the same host send udp packets to 127.0.0.1:40000, record the
socket index which receives the packets.
3) Create 1 more udp socket and bind it to 0.0.0.0:44096. The number 44096
is 40000 + UDP_HASH_SIZE(4096), this makes the new socket put into the
same hslot as the aformentioned 10 sockets, and makes the hslot->count
change from 10 to 11.
4) From the same host send udp packets to 127.0.0.1:40000, and the socket
index which receives the packets will be different from the one received
in step 2.
This should not happen as the socket bound to 0.0.0.0:44096 should not
change the behavior of the sockets bound to 0.0.0.0:40000.
It's the same case for IPv6, and this patch also fixes that.
Signed-off-by: Su, Xuemin <suxm@chinanetcenter.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-13 11:02:50 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
ipv6: udp: optimize unicast RX path
We first locate the (local port) hash chain head
If few sockets are in this chain, we proceed with previous lookup algo.
If too many sockets are listed, we take a look at the secondary
(port, address) hash chain.
We choose the shortest chain and proceed with a RCU lookup on the elected chain.
But, if we chose (port, address) chain, and fail to find a socket on given address,
we must try another lookup on (port, in6addr_any) chain to find sockets not bound
to a particular IP.
-> No extra cost for typical setups, where the first lookup will probabbly
be performed.
RCU lookups everywhere, we dont acquire spinlock.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-08 10:18:30 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-04-08 04:56:48 +00:00
|
|
|
|
2017-08-07 08:44:20 -07:00
|
|
|
|
2017-01-26 18:02:24 +00:00
|
|
|
|
|
|
|
|
|
ipv6: udp: optimize unicast RX path
We first locate the (local port) hash chain head
If few sockets are in this chain, we proceed with previous lookup algo.
If too many sockets are listed, we take a look at the secondary
(port, address) hash chain.
We choose the shortest chain and proceed with a RCU lookup on the elected chain.
But, if we chose (port, address) chain, and fail to find a socket on given address,
we must try another lookup on (port, in6addr_any) chain to find sockets not bound
to a particular IP.
-> No extra cost for typical setups, where the first lookup will probabbly
be performed.
RCU lookups everywhere, we dont acquire spinlock.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-08 10:18:30 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
udp: RCU handling for Unicast packets.
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>
2008-10-29 02:11:14 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-04-01 08:52:13 -07:00
|
|
|
|
2017-01-26 18:02:24 +00:00
|
|
|
|
2017-08-07 08:44:20 -07:00
|
|
|
|
2008-10-29 01:41:45 -07:00
|
|
|
|
2013-01-22 09:50:44 +00:00
|
|
|
|
|
|
|
|
|
2013-10-19 21:48:52 +02:00
|
|
|
|
|
|
|
|
|
2016-04-01 08:52:13 -07:00
|
|
|
|
2016-01-04 17:41:47 -05:00
|
|
|
|
2016-04-01 08:52:13 -07:00
|
|
|
|
|
|
|
|
|
2013-01-22 09:50:44 +00:00
|
|
|
|
|
|
|
|
|
2016-04-01 08:52:13 -07:00
|
|
|
|
|
|
|
|
|
2013-01-22 09:50:44 +00:00
|
|
|
|
|
|
|
|
|
2014-08-23 20:58:54 +02:00
|
|
|
|
2013-01-22 09:50:44 +00:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-12-09 06:23:34 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2008-10-07 12:38:32 -07:00
|
|
|
|
|
|
|
|
|
2008-10-29 01:41:45 -07:00
|
|
|
|
2008-10-07 12:38:32 -07:00
|
|
|
|
2011-04-22 04:53:02 +00:00
|
|
|
|
2008-10-07 12:38:32 -07:00
|
|
|
|
2016-05-12 16:23:44 -07:00
|
|
|
|
2009-06-02 05:19:30 +00:00
|
|
|
|
2017-08-07 08:44:20 -07:00
|
|
|
|
2008-10-07 12:38:32 -07:00
|
|
|
|
|
|
|
|
|
2016-04-05 08:22:50 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-05-12 16:23:44 -07:00
|
|
|
|
2016-04-05 08:22:50 -07:00
|
|
|
|
2017-08-07 08:44:20 -07:00
|
|
|
|
2016-04-05 08:22:50 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-04-01 08:52:13 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-11-08 14:28:18 +01:00
|
|
|
|
|
|
|
|
|
2010-10-21 16:05:41 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-04-01 08:52:13 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-08-07 08:44:20 -07:00
|
|
|
|
2017-06-30 13:08:01 +03:00
|
|
|
|
2016-04-01 08:52:13 -07:00
|
|
|
|
|
|
|
|
|
2010-10-21 16:05:41 +02:00
|
|
|
|
|
|
|
|
|
2016-04-01 08:52:13 -07:00
|
|
|
|
2010-10-21 16:05:41 +02:00
|
|
|
|
2017-07-31 16:52:36 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2014-08-24 21:53:10 +01:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2015-03-02 15:37:48 +08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-02-09 23:24:49 +09:00
|
|
|
|
2011-12-01 14:12:55 -05:00
|
|
|
|
2016-04-05 12:41:16 -04:00
|
|
|
|
2007-03-25 20:10:56 -07:00
|
|
|
|
|
|
|
|
|
udp: properly support MSG_PEEK with truncated buffers
Backport of this upstream commit into stable kernels :
89c22d8c3b27 ("net: Fix skb csum races when peeking")
exposed a bug in udp stack vs MSG_PEEK support, when user provides
a buffer smaller than skb payload.
In this case,
skb_copy_and_csum_datagram_iovec(skb, sizeof(struct udphdr),
msg->msg_iov);
returns -EFAULT.
This bug does not happen in upstream kernels since Al Viro did a great
job to replace this into :
skb_copy_and_csum_datagram_msg(skb, sizeof(struct udphdr), msg);
This variant is safe vs short buffers.
For the time being, instead reverting Herbert Xu patch and add back
skb->ip_summed invalid changes, simply store the result of
udp_lib_checksum_complete() so that we avoid computing the checksum a
second time, and avoid the problematic
skb_copy_and_csum_datagram_iovec() call.
This patch can be applied on recent kernels as it avoids a double
checksumming, then backported to stable kernels as a bug fix.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-12-30 08:51:12 -05:00
|
|
|
|
2008-11-02 16:11:01 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2013-11-23 00:46:12 +01:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2010-04-23 11:26:09 +00:00
|
|
|
|
2013-11-23 00:46:12 +01:00
|
|
|
|
2010-04-23 11:26:09 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
datagram: When peeking datagrams with offset < 0 don't skip empty skbs
Due to commit e6afc8ace6dd5cef5e812f26c72579da8806f5ac ("udp: remove
headers from UDP packets before queueing"), when udp packets are being
peeked the requested extra offset is always 0 as there is no need to skip
the udp header. However, when the offset is 0 and the next skb is
of length 0, it is only returned once. The behaviour can be seen with
the following python script:
from socket import *;
f=socket(AF_INET6, SOCK_DGRAM | SOCK_NONBLOCK, 0);
g=socket(AF_INET6, SOCK_DGRAM | SOCK_NONBLOCK, 0);
f.bind(('::', 0));
addr=('::1', f.getsockname()[1]);
g.sendto(b'', addr)
g.sendto(b'b', addr)
print(f.recvfrom(10, MSG_PEEK));
print(f.recvfrom(10, MSG_PEEK));
Where the expected output should be the empty string twice.
Instead, make sk_peek_offset return negative values, and pass those values
to __skb_try_recv_datagram/__skb_try_recv_from_queue. If the passed offset
to __skb_try_recv_from_queue is negative, the checked skb is never skipped.
__skb_try_recv_from_queue will then ensure the offset is reset back to 0
if a peek is requested without an offset, unless no packets are found.
Also simplify the if condition in __skb_try_recv_from_queue. If _off is
greater then 0, and off is greater then or equal to skb->len, then
(_off || skb->len) must always be true assuming skb->len >= 0 is always
true.
Also remove a redundant check around a call to sk_peek_offset in af_unix.c,
as it double checked if MSG_PEEK was set in the flags.
V2:
- Moved the negative fixup into __skb_try_recv_from_queue, and remove now
redundant checks
- Fix peeking in udp{,v6}_recvmsg to report the right value when the
offset is 0
V3:
- Marked new branch in __skb_try_recv_from_queue as unlikely.
Signed-off-by: Matthew Dawson <matthew@mjdsystems.ca>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-18 15:04:54 -04:00
|
|
|
|
|
|
|
|
|
2016-11-04 11:28:59 +01:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2016-04-05 12:41:16 -04:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2017-07-31 16:52:36 +02:00
|
|
|
|
2011-12-01 14:12:55 -05:00
|
|
|
|
2016-04-05 12:41:16 -04:00
|
|
|
|
|
|
|
|
|
2011-12-01 14:12:55 -05:00
|
|
|
|
2007-02-09 23:24:49 +09:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2008-11-02 16:11:01 +00:00
|
|
|
|
|
|
|
|
|
2006-11-27 11:10:57 -08:00
|
|
|
|
2007-03-25 20:10:56 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2006-11-27 11:10:57 -08:00
|
|
|
|
|
|
|
|
|
2016-11-18 17:18:03 -08:00
|
|
|
|
|
|
|
|
|
2017-06-26 19:01:51 +02:00
|
|
|
|
|
|
|
|
|
udp: properly support MSG_PEEK with truncated buffers
Backport of this upstream commit into stable kernels :
89c22d8c3b27 ("net: Fix skb csum races when peeking")
exposed a bug in udp stack vs MSG_PEEK support, when user provides
a buffer smaller than skb payload.
In this case,
skb_copy_and_csum_datagram_iovec(skb, sizeof(struct udphdr),
msg->msg_iov);
returns -EFAULT.
This bug does not happen in upstream kernels since Al Viro did a great
job to replace this into :
skb_copy_and_csum_datagram_msg(skb, sizeof(struct udphdr), msg);
This variant is safe vs short buffers.
For the time being, instead reverting Herbert Xu patch and add back
skb->ip_summed invalid changes, simply store the result of
udp_lib_checksum_complete() so that we avoid computing the checksum a
second time, and avoid the problematic
skb_copy_and_csum_datagram_iovec() call.
This patch can be applied on recent kernels as it avoids a double
checksumming, then backported to stable kernels as a bug fix.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-12-30 08:51:12 -05:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2006-11-27 11:10:57 -08:00
|
|
|
|
|
|
|
|
|
2017-06-26 19:01:51 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-04-05 12:41:16 -04:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-06-27 00:23:44 +00:00
|
|
|
|
2012-09-05 23:34:44 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
net: snmp: kill various STATS_USER() helpers
In the old days (before linux-3.0), SNMP counters were duplicated,
one for user context, and one for BH context.
After commit 8f0ea0fe3a03 ("snmp: reduce percpu needs by 50%")
we have a single copy, and what really matters is preemption being
enabled or disabled, since we use this_cpu_inc() or __this_cpu_inc()
respectively.
We therefore kill SNMP_INC_STATS_USER(), SNMP_ADD_STATS_USER(),
NET_INC_STATS_USER(), NET_ADD_STATS_USER(), SCTP_INC_STATS_USER(),
SNMP_INC_STATS64_USER(), SNMP_ADD_STATS64_USER(), TCP_ADD_STATS_USER(),
UDP_INC_STATS_USER(), UDP6_INC_STATS_USER(), and XFRM_INC_STATS_USER()
Following patches will rename __BH helpers to make clear their
usage is not tied to BH being disabled.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-27 16:44:27 -07:00
|
|
|
|
|
|
|
|
|
2012-09-05 23:34:44 +00:00
|
|
|
|
net: snmp: kill various STATS_USER() helpers
In the old days (before linux-3.0), SNMP counters were duplicated,
one for user context, and one for BH context.
After commit 8f0ea0fe3a03 ("snmp: reduce percpu needs by 50%")
we have a single copy, and what really matters is preemption being
enabled or disabled, since we use this_cpu_inc() or __this_cpu_inc()
respectively.
We therefore kill SNMP_INC_STATS_USER(), SNMP_ADD_STATS_USER(),
NET_INC_STATS_USER(), NET_ADD_STATS_USER(), SCTP_INC_STATS_USER(),
SNMP_INC_STATS64_USER(), SNMP_ADD_STATS64_USER(), TCP_ADD_STATS_USER(),
UDP_INC_STATS_USER(), UDP6_INC_STATS_USER(), and XFRM_INC_STATS_USER()
Following patches will rename __BH helpers to make clear their
usage is not tied to BH being disabled.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-27 16:44:27 -07:00
|
|
|
|
|
|
|
|
|
2012-09-05 23:34:44 +00:00
|
|
|
|
2016-10-21 13:55:47 +02:00
|
|
|
|
2016-04-05 12:41:16 -04:00
|
|
|
|
2012-06-27 00:23:44 +00:00
|
|
|
|
2008-11-02 16:11:01 +00:00
|
|
|
|
|
|
|
|
|
net: snmp: kill various STATS_USER() helpers
In the old days (before linux-3.0), SNMP counters were duplicated,
one for user context, and one for BH context.
After commit 8f0ea0fe3a03 ("snmp: reduce percpu needs by 50%")
we have a single copy, and what really matters is preemption being
enabled or disabled, since we use this_cpu_inc() or __this_cpu_inc()
respectively.
We therefore kill SNMP_INC_STATS_USER(), SNMP_ADD_STATS_USER(),
NET_INC_STATS_USER(), NET_ADD_STATS_USER(), SCTP_INC_STATS_USER(),
SNMP_INC_STATS64_USER(), SNMP_ADD_STATS64_USER(), TCP_ADD_STATS_USER(),
UDP_INC_STATS_USER(), UDP6_INC_STATS_USER(), and XFRM_INC_STATS_USER()
Following patches will rename __BH helpers to make clear their
usage is not tied to BH being disabled.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-27 16:44:27 -07:00
|
|
|
|
|
|
|
|
|
2008-11-02 16:11:01 +00:00
|
|
|
|
net: snmp: kill various STATS_USER() helpers
In the old days (before linux-3.0), SNMP counters were duplicated,
one for user context, and one for BH context.
After commit 8f0ea0fe3a03 ("snmp: reduce percpu needs by 50%")
we have a single copy, and what really matters is preemption being
enabled or disabled, since we use this_cpu_inc() or __this_cpu_inc()
respectively.
We therefore kill SNMP_INC_STATS_USER(), SNMP_ADD_STATS_USER(),
NET_INC_STATS_USER(), NET_ADD_STATS_USER(), SCTP_INC_STATS_USER(),
SNMP_INC_STATS64_USER(), SNMP_ADD_STATS64_USER(), TCP_ADD_STATS_USER(),
UDP_INC_STATS_USER(), UDP6_INC_STATS_USER(), and XFRM_INC_STATS_USER()
Following patches will rename __BH helpers to make clear their
usage is not tied to BH being disabled.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-27 16:44:27 -07:00
|
|
|
|
|
|
|
|
|
2008-11-02 16:11:01 +00:00
|
|
|
|
2007-12-03 22:33:28 +11:00
|
|
|
|
net: Generalize socket rx gap / receive queue overflow cmsg
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
977750076d98c7ff6cbda51858bb5a5894a9d9ab (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>
2009-10-12 13:26:31 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-01-17 22:53:15 +01:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-03-13 14:28:48 -03:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2013-03-08 02:07:19 +00:00
|
|
|
|
2009-10-07 13:58:25 -07:00
|
|
|
|
|
|
|
|
|
2013-03-08 02:07:19 +00:00
|
|
|
|
|
|
|
|
|
2011-11-21 03:39:03 +00:00
|
|
|
|
2013-03-08 02:07:19 +00:00
|
|
|
|
|
|
|
|
|
2014-08-01 09:52:58 +08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2013-11-18 04:20:45 +01:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2014-01-20 03:43:08 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-11-02 16:11:01 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2016-11-04 11:28:58 +01:00
|
|
|
|
2016-10-23 18:03:06 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2014-01-20 03:43:08 +01:00
|
|
|
|
2007-02-09 23:24:49 +09:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2011-12-01 14:12:55 -05:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-03-25 20:10:56 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2016-10-21 13:55:47 +02:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-05-16 11:20:14 +02:00
|
|
|
|
|
|
|
|
|
2013-04-29 08:39:56 +00:00
|
|
|
|
net: snmp: kill various STATS_USER() helpers
In the old days (before linux-3.0), SNMP counters were duplicated,
one for user context, and one for BH context.
After commit 8f0ea0fe3a03 ("snmp: reduce percpu needs by 50%")
we have a single copy, and what really matters is preemption being
enabled or disabled, since we use this_cpu_inc() or __this_cpu_inc()
respectively.
We therefore kill SNMP_INC_STATS_USER(), SNMP_ADD_STATS_USER(),
NET_INC_STATS_USER(), NET_ADD_STATS_USER(), SCTP_INC_STATS_USER(),
SNMP_INC_STATS64_USER(), SNMP_ADD_STATS64_USER(), TCP_ADD_STATS_USER(),
UDP_INC_STATS_USER(), UDP6_INC_STATS_USER(), and XFRM_INC_STATS_USER()
Following patches will rename __BH helpers to make clear their
usage is not tied to BH being disabled.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-27 16:44:27 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-04-29 08:39:56 +00:00
|
|
|
|
net: snmp: kill various STATS_USER() helpers
In the old days (before linux-3.0), SNMP counters were duplicated,
one for user context, and one for BH context.
After commit 8f0ea0fe3a03 ("snmp: reduce percpu needs by 50%")
we have a single copy, and what really matters is preemption being
enabled or disabled, since we use this_cpu_inc() or __this_cpu_inc()
respectively.
We therefore kill SNMP_INC_STATS_USER(), SNMP_ADD_STATS_USER(),
NET_INC_STATS_USER(), NET_ADD_STATS_USER(), SCTP_INC_STATS_USER(),
SNMP_INC_STATS64_USER(), SNMP_ADD_STATS64_USER(), TCP_ADD_STATS_USER(),
UDP_INC_STATS_USER(), UDP6_INC_STATS_USER(), and XFRM_INC_STATS_USER()
Following patches will rename __BH helpers to make clear their
usage is not tied to BH being disabled.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-27 16:44:27 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-04-29 08:39:56 +00:00
|
|
|
|
2008-11-02 16:14:27 +00:00
|
|
|
|
2016-10-21 13:55:47 +02:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2015-05-30 09:16:53 -07:00
|
|
|
|
|
|
|
|
|
2011-06-21 10:43:40 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2006-11-27 11:10:57 -08:00
|
|
|
|
2009-06-23 04:31:07 -07:00
|
|
|
|
2008-10-29 01:41:45 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2011-04-22 04:53:02 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-08-24 21:53:10 +01:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2016-02-17 13:58:22 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2014-07-31 17:54:32 +08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2016-01-04 17:41:46 -05:00
|
|
|
|
2017-08-07 08:44:20 -07:00
|
|
|
|
2015-03-29 14:00:04 +01:00
|
|
|
|
2016-04-27 16:44:36 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2014-07-31 17:54:32 +08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2016-02-17 13:58:22 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-12-15 03:41:14 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-06-15 14:54:11 -07:00
|
|
|
|
2016-02-17 13:58:22 -08:00
|
|
|
|
|
|
|
|
|
2013-12-15 03:41:14 +01:00
|
|
|
|
2013-09-20 18:20:28 +08:00
|
|
|
|
2012-07-12 00:25:15 -07:00
|
|
|
|
2013-09-20 18:20:28 +08:00
|
|
|
|
|
|
|
|
|
2012-06-15 14:54:11 -07:00
|
|
|
|
2016-02-17 13:58:22 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2016-02-17 13:58:22 -08:00
|
|
|
|
2010-05-31 23:44:05 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-04-01 08:52:13 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2017-05-17 14:52:16 +02:00
|
|
|
|
2012-04-27 08:23:21 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
ipv6: make lookups simpler and faster
TCP listener refactoring, part 4 :
To speed up inet lookups, we moved IPv4 addresses from inet to struct
sock_common
Now is time to do the same for IPv6, because it permits us to have fast
lookups for all kind of sockets, including upcoming SYN_RECV.
Getting IPv6 addresses in TCP lookups currently requires two extra cache
lines, plus a dereference (and memory stall).
inet6_sk(sk) does the dereference of inet_sk(__sk)->pinet6
This patch is way bigger than its IPv4 counter part, because for IPv4,
we could add aliases (inet_daddr, inet_rcv_saddr), while on IPv6,
it's not doable easily.
inet6_sk(sk)->daddr becomes sk->sk_v6_daddr
inet6_sk(sk)->rcv_saddr becomes sk->sk_v6_rcv_saddr
And timewait socket also have tw->tw_v6_daddr & tw->tw_v6_rcv_saddr
at the same offset.
We get rid of INET6_TW_MATCH() as INET6_MATCH() is now the generic
macro.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-03 15:42:29 -07:00
|
|
|
|
2012-04-27 08:23:21 +00:00
|
|
|
|
2013-10-07 11:01:38 -05:00
|
|
|
|
net: introduce SO_INCOMING_CPU
Alternative to RPS/RFS is to use hardware support for multiple
queues.
Then split a set of million of sockets into worker threads, each
one using epoll() to manage events on its own socket pool.
Ideally, we want one thread per RX/TX queue/cpu, but we have no way to
know after accept() or connect() on which queue/cpu a socket is managed.
We normally use one cpu per RX queue (IRQ smp_affinity being properly
set), so remembering on socket structure which cpu delivered last packet
is enough to solve the problem.
After accept(), connect(), or even file descriptor passing around
processes, applications can use :
int cpu;
socklen_t len = sizeof(cpu);
getsockopt(fd, SOL_SOCKET, SO_INCOMING_CPU, &cpu, &len);
And use this information to put the socket into the right silo
for optimal performance, as all networking stack should run
on the appropriate cpu, without need to send IPI (RPS/RFS).
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-11-11 05:54:28 -08:00
|
|
|
|
2016-11-16 09:10:42 -08:00
|
|
|
|
|
|
|
|
|
2013-10-07 11:01:38 -05:00
|
|
|
|
2012-04-27 08:23:21 +00:00
|
|
|
|
2016-10-21 13:55:47 +02:00
|
|
|
|
2012-04-27 08:23:21 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-04-29 14:16:50 -07:00
|
|
|
|
2016-04-27 16:44:30 -07:00
|
|
|
|
2016-04-29 14:16:50 -07:00
|
|
|
|
2012-04-27 08:23:21 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-10-21 13:55:47 +02:00
|
|
|
|
2012-04-27 08:23:21 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2006-11-27 11:10:57 -08:00
|
|
|
|
2009-06-23 04:31:07 -07:00
|
|
|
|
2014-08-24 21:53:10 +01:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2008-10-29 01:41:45 -07:00
|
|
|
|
2006-11-27 11:10:57 -08:00
|
|
|
|
|
|
|
|
|
2012-04-27 08:24:08 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-08-01 17:24:05 +02:00
|
|
|
|
2012-04-27 08:24:08 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-05-17 14:52:16 +02:00
|
|
|
|
2006-11-27 11:10:57 -08:00
|
|
|
|
|
|
|
|
|
2007-12-03 22:34:16 +11:00
|
|
|
|
2006-08-15 00:00:09 -07:00
|
|
|
|
2006-11-27 11:10:57 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-04-27 08:24:08 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-05-19 15:58:33 +02:00
|
|
|
|
2012-04-27 08:24:08 +00:00
|
|
|
|
|
|
|
|
|
2014-05-07 16:52:39 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-04-27 08:24:08 +00:00
|
|
|
|
|
|
|
|
|
2016-04-27 16:44:30 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-04-27 08:24:08 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2006-11-27 11:10:57 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-12-03 22:34:16 +11:00
|
|
|
|
2006-11-27 11:10:57 -08:00
|
|
|
|
|
|
|
|
|
2014-11-11 10:59:17 -08:00
|
|
|
|
|
|
|
|
|
2006-11-27 11:10:57 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-11-11 10:59:17 -08:00
|
|
|
|
|
|
|
|
|
2006-11-27 11:10:57 -08:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2017-06-22 15:01:22 +02:00
|
|
|
|
2016-06-02 14:52:43 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-07-25 18:06:12 +02:00
|
|
|
|
2016-07-08 17:52:33 +02:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2016-04-05 12:41:15 -04:00
|
|
|
|
2012-04-27 08:23:59 +00:00
|
|
|
|
ipv4: PKTINFO doesnt need dst reference
Le lundi 07 novembre 2011 à 15:33 +0100, Eric Dumazet a écrit :
> At least, in recent kernels we dont change dst->refcnt in forwarding
> patch (usinf NOREF skb->dst)
>
> One particular point is the atomic_inc(dst->refcnt) we have to perform
> when queuing an UDP packet if socket asked PKTINFO stuff (for example a
> typical DNS server has to setup this option)
>
> I have one patch somewhere that stores the information in skb->cb[] and
> avoid the atomic_{inc|dec}(dst->refcnt).
>
OK I found it, I did some extra tests and believe its ready.
[PATCH net-next] ipv4: IP_PKTINFO doesnt need dst reference
When a socket uses IP_PKTINFO notifications, we currently force a dst
reference for each received skb. Reader has to access dst to get needed
information (rt_iif & rt_spec_dst) and must release dst reference.
We also forced a dst reference if skb was put in socket backlog, even
without IP_PKTINFO handling. This happens under stress/load.
We can instead store the needed information in skb->cb[], so that only
softirq handler really access dst, improving cache hit ratios.
This removes two atomic operations per packet, and false sharing as
well.
On a benchmark using a mono threaded receiver (doing only recvmsg()
calls), I can reach 720.000 pps instead of 570.000 pps.
IP_PKTINFO is typically used by DNS servers, and any multihomed aware
UDP application.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-11-09 07:24:35 +00:00
|
|
|
|
2007-12-03 22:33:28 +11:00
|
|
|
|
2016-10-21 13:55:47 +02:00
|
|
|
|
2014-06-25 17:38:13 -04:00
|
|
|
|
2013-04-29 08:39:56 +00:00
|
|
|
|
2016-04-27 16:44:30 -07:00
|
|
|
|
2006-11-27 11:10:57 -08:00
|
|
|
|
2016-04-27 16:44:30 -07:00
|
|
|
|
2012-04-27 08:23:59 +00:00
|
|
|
|
2006-11-27 11:10:57 -08:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2014-07-15 23:28:31 -04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2014-07-15 23:28:31 -04:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2014-07-15 23:28:31 -04:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2014-07-15 23:28:31 -04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-05-18 21:08:49 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-07-15 23:28:31 -04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2014-05-02 16:29:58 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-11-11 10:59:17 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-05-02 16:29:58 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-06-16 17:12:11 -07:00
|
|
|
|
2011-04-22 04:53:02 +00:00
|
|
|
|
2014-11-06 10:37:54 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2016-04-01 08:52:13 -07:00
|
|
|
|
2007-03-13 14:28:48 -03:00
|
|
|
|
2014-07-15 23:28:31 -04:00
|
|
|
|
|
|
|
|
|
2016-04-01 08:52:13 -07:00
|
|
|
|
2014-07-15 23:28:32 -04:00
|
|
|
|
2016-04-01 08:52:13 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-07-15 23:28:32 -04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-11-14 23:40:30 +01:00
|
|
|
|
|
|
|
|
|
2014-07-15 23:28:32 -04:00
|
|
|
|
2016-11-14 23:40:30 +01:00
|
|
|
|
2014-07-15 23:28:32 -04:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2016-04-01 08:52:13 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-04-27 16:44:30 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-04-01 08:52:13 -07:00
|
|
|
|
2007-12-31 00:29:24 -08:00
|
|
|
|
2009-11-08 10:18:52 +00:00
|
|
|
|
2016-04-01 08:52:13 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-11-08 10:18:52 +00:00
|
|
|
|
2014-07-15 23:28:32 -04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-04-01 08:52:13 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-11-08 10:18:52 +00:00
|
|
|
|
2016-04-01 08:52:13 -07:00
|
|
|
|
2016-04-27 16:44:30 -07:00
|
|
|
|
|
|
|
|
|
2009-11-08 10:18:52 +00:00
|
|
|
|
2006-11-27 11:10:57 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2017-08-25 14:31:01 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-10-29 01:41:45 -07:00
|
|
|
|
2007-03-25 20:10:56 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2011-04-22 04:53:02 +00:00
|
|
|
|
2016-04-01 08:52:13 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-05-06 03:44:35 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-04-25 17:54:47 -07:00
|
|
|
|
|
|
|
|
|
2007-03-13 14:28:48 -03:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2006-11-27 11:10:57 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2007-03-25 20:10:56 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2006-11-27 11:10:57 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-04-25 17:54:47 -07:00
|
|
|
|
|
|
|
|
|
2007-03-13 14:28:48 -03:00
|
|
|
|
2006-11-27 11:10:57 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2007-03-25 20:10:56 -07:00
|
|
|
|
2013-04-29 08:39:56 +00:00
|
|
|
|
2007-03-25 20:10:56 -07:00
|
|
|
|
2017-07-27 14:45:09 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-08-25 14:31:01 +02:00
|
|
|
|
2017-07-27 14:45:09 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-02-09 23:24:49 +09:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2006-11-27 11:10:57 -08:00
|
|
|
|
2008-06-16 17:12:11 -07:00
|
|
|
|
2014-11-06 10:37:54 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2008-10-07 12:38:32 -07:00
|
|
|
|
2015-03-29 14:00:05 +01:00
|
|
|
|
2013-06-10 11:40:00 +03:00
|
|
|
|
|
|
|
|
|
2014-05-23 08:47:32 -07:00
|
|
|
|
2014-05-02 16:29:58 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-01-05 13:56:14 -08:00
|
|
|
|
2014-08-31 15:12:43 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-06-10 11:40:00 +03:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2016-03-04 14:47:21 -08:00
|
|
|
|
2012-04-27 08:23:59 +00:00
|
|
|
|
2016-03-04 14:47:21 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-03-08 20:42:35 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-02-09 23:24:49 +09:00
|
|
|
|
2014-05-02 16:29:58 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-04-27 08:23:59 +00:00
|
|
|
|
|
|
|
|
|
2007-02-09 23:24:49 +09:00
|
|
|
|
2012-04-27 08:23:59 +00:00
|
|
|
|
2013-04-29 08:39:56 +00:00
|
|
|
|
2012-04-27 08:23:59 +00:00
|
|
|
|
2016-04-27 16:44:30 -07:00
|
|
|
|
2012-04-27 08:23:59 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-03-08 20:42:35 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-02-09 23:24:49 +09:00
|
|
|
|
2014-11-11 10:59:17 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-04-29 08:39:56 +00:00
|
|
|
|
|
|
|
|
|
2016-04-27 16:44:30 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2016-04-27 16:44:30 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-03-08 20:42:35 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2006-11-27 11:10:57 -08:00
|
|
|
|
2017-04-18 11:39:41 -06:00
|
|
|
|
2017-03-08 16:36:49 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-08-07 08:44:21 -07:00
|
|
|
|
2017-03-08 16:36:49 -07:00
|
|
|
|
2017-04-18 11:39:41 -06:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-03-08 16:36:49 -07:00
|
|
|
|
|
|
|
|
|
2017-04-18 11:39:41 -06:00
|
|
|
|
2017-06-23 15:25:37 -07:00
|
|
|
|
2017-08-07 08:44:21 -07:00
|
|
|
|
2017-04-18 11:39:41 -06:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-03-08 16:36:49 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-08-07 08:44:21 -07:00
|
|
|
|
2017-03-08 16:36:49 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-08-07 08:44:21 -07:00
|
|
|
|
2017-03-08 16:36:49 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-06-30 13:08:01 +03:00
|
|
|
|
2017-03-08 16:36:49 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-06-17 10:42:25 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-03-08 16:36:49 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-10-15 12:50:28 -07:00
|
|
|
|
2006-11-27 11:10:57 -08:00
|
|
|
|
2008-10-29 01:41:45 -07:00
|
|
|
|
2006-11-27 11:10:57 -08:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-06-04 15:49:07 +04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-02-09 23:24:49 +09:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2009-07-09 08:09:54 +00:00
|
|
|
|
2014-08-24 21:53:10 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-07-09 08:09:54 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-01-31 10:40:16 -05:00
|
|
|
|
2009-07-09 08:09:54 +00:00
|
|
|
|
|
|
|
|
|
2015-01-31 10:40:16 -05:00
|
|
|
|
2009-07-09 08:09:54 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-09-13 19:30:51 -06:00
|
|
|
|
2009-07-09 08:09:54 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-01-31 10:40:16 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-07-09 08:09:54 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-01-31 10:40:16 -05:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2015-01-31 10:40:16 -05:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2007-12-03 22:34:16 +11:00
|
|
|
|
2006-11-14 21:35:48 -08:00
|
|
|
|
2015-01-31 10:40:16 -05:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-03-13 14:28:48 -03:00
|
|
|
|
2011-03-12 16:36:19 -05:00
|
|
|
|
|
|
|
|
|
2015-01-31 10:40:16 -05:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2007-12-03 22:34:16 +11:00
|
|
|
|
2015-01-31 10:40:16 -05:00
|
|
|
|
|
|
|
|
|
2014-05-02 16:29:58 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-01-31 10:40:16 -05:00
|
|
|
|
2009-07-09 08:09:54 +00:00
|
|
|
|
|
|
|
|
|
2015-01-31 10:40:16 -05:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2006-11-27 11:10:57 -08:00
|
|
|
|
2011-03-12 16:22:43 -05:00
|
|
|
|
2015-01-31 10:40:16 -05:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2006-11-16 02:36:50 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2009-07-09 08:09:54 +00:00
|
|
|
|
2015-01-31 10:40:16 -05:00
|
|
|
|
ip: Report qdisc packet drops
Christoph Lameter pointed out that packet drops at qdisc level where not
accounted in SNMP counters. Only if application sets IP_RECVERR, drops
are reported to user (-ENOBUFS errors) and SNMP counters updated.
IP_RECVERR is used to enable extended reliable error message passing,
but these are not needed to update system wide SNMP stats.
This patch changes things a bit to allow SNMP counters to be updated,
regardless of IP_RECVERR being set or not on the socket.
Example after an UDP tx flood
# netstat -s
...
IP:
1487048 outgoing packets dropped
...
Udp:
...
SndbufErrors: 1487048
send() syscalls, do however still return an OK status, to not
break applications.
Note : send() manual page explicitly says for -ENOBUFS error :
"The output queue for a network interface was full.
This generally indicates that the interface has stopped sending,
but may be caused by transient congestion.
(Normally, this does not occur in Linux. Packets are just silently
dropped when a device queue overflows.) "
This is not true for IP_RECVERR enabled sockets : a send() syscall
that hit a qdisc drop returns an ENOBUFS error.
Many thanks to Christoph, David, and last but not least, Alexey !
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-09-02 18:05:33 -07:00
|
|
|
|
|
|
|
|
|
net: snmp: kill various STATS_USER() helpers
In the old days (before linux-3.0), SNMP counters were duplicated,
one for user context, and one for BH context.
After commit 8f0ea0fe3a03 ("snmp: reduce percpu needs by 50%")
we have a single copy, and what really matters is preemption being
enabled or disabled, since we use this_cpu_inc() or __this_cpu_inc()
respectively.
We therefore kill SNMP_INC_STATS_USER(), SNMP_ADD_STATS_USER(),
NET_INC_STATS_USER(), NET_ADD_STATS_USER(), SCTP_INC_STATS_USER(),
SNMP_INC_STATS64_USER(), SNMP_ADD_STATS64_USER(), TCP_ADD_STATS_USER(),
UDP_INC_STATS_USER(), UDP6_INC_STATS_USER(), and XFRM_INC_STATS_USER()
Following patches will rename __BH helpers to make clear their
usage is not tied to BH being disabled.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-27 16:44:27 -07:00
|
|
|
|
|
|
|
|
|
ip: Report qdisc packet drops
Christoph Lameter pointed out that packet drops at qdisc level where not
accounted in SNMP counters. Only if application sets IP_RECVERR, drops
are reported to user (-ENOBUFS errors) and SNMP counters updated.
IP_RECVERR is used to enable extended reliable error message passing,
but these are not needed to update system wide SNMP stats.
This patch changes things a bit to allow SNMP counters to be updated,
regardless of IP_RECVERR being set or not on the socket.
Example after an UDP tx flood
# netstat -s
...
IP:
1487048 outgoing packets dropped
...
Udp:
...
SndbufErrors: 1487048
send() syscalls, do however still return an OK status, to not
break applications.
Note : send() manual page explicitly says for -ENOBUFS error :
"The output queue for a network interface was full.
This generally indicates that the interface has stopped sending,
but may be caused by transient congestion.
(Normally, this does not occur in Linux. Packets are just silently
dropped when a device queue overflows.) "
This is not true for IP_RECVERR enabled sockets : a send() syscall
that hit a qdisc drop returns an ENOBUFS error.
Many thanks to Christoph, David, and last but not least, Alexey !
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-09-02 18:05:33 -07:00
|
|
|
|
|
|
|
|
|
net: snmp: kill various STATS_USER() helpers
In the old days (before linux-3.0), SNMP counters were duplicated,
one for user context, and one for BH context.
After commit 8f0ea0fe3a03 ("snmp: reduce percpu needs by 50%")
we have a single copy, and what really matters is preemption being
enabled or disabled, since we use this_cpu_inc() or __this_cpu_inc()
respectively.
We therefore kill SNMP_INC_STATS_USER(), SNMP_ADD_STATS_USER(),
NET_INC_STATS_USER(), NET_ADD_STATS_USER(), SCTP_INC_STATS_USER(),
SNMP_INC_STATS64_USER(), SNMP_ADD_STATS64_USER(), TCP_ADD_STATS_USER(),
UDP_INC_STATS_USER(), UDP6_INC_STATS_USER(), and XFRM_INC_STATS_USER()
Following patches will rename __BH helpers to make clear their
usage is not tied to BH being disabled.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-27 16:44:27 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-01-31 10:40:16 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-03-02 15:37:48 +08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-01-17 22:53:15 +01:00
|
|
|
|
2010-06-01 21:35:01 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2015-11-29 19:37:57 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2011-03-12 16:22:43 -05:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2016-05-02 21:40:07 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-09-18 00:30:08 -07:00
|
|
|
|
2007-12-03 22:34:16 +11:00
|
|
|
|
2006-11-27 11:10:57 -08:00
|
|
|
|
2016-04-02 23:08:11 -04:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2016-05-02 21:40:07 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-03-21 17:14:27 +01:00
|
|
|
|
2016-05-02 21:40:07 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-02-12 17:26:07 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
ipv6: make lookups simpler and faster
TCP listener refactoring, part 4 :
To speed up inet lookups, we moved IPv4 addresses from inet to struct
sock_common
Now is time to do the same for IPv6, because it permits us to have fast
lookups for all kind of sockets, including upcoming SYN_RECV.
Getting IPv6 addresses in TCP lookups currently requires two extra cache
lines, plus a dereference (and memory stall).
inet6_sk(sk) does the dereference of inet_sk(__sk)->pinet6
This patch is way bigger than its IPv4 counter part, because for IPv4,
we could add aliases (inet_daddr, inet_rcv_saddr), while on IPv6,
it's not doable easily.
inet6_sk(sk)->daddr becomes sk->sk_v6_daddr
inet6_sk(sk)->rcv_saddr becomes sk->sk_v6_rcv_saddr
And timewait socket also have tw->tw_v6_daddr & tw->tw_v6_rcv_saddr
at the same offset.
We get rid of INET6_TW_MATCH() as INET6_MATCH() is now the generic
macro.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-03 15:42:29 -07:00
|
|
|
|
2007-02-09 23:24:49 +09:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-08-24 23:16:08 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2009-10-15 06:30:45 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-03-02 15:37:48 +08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-03-02 15:37:48 +08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
[IPv6]: Fix incorrect length check in rawv6_sendmsg()
In article <20070329.142644.70222545.davem@davemloft.net> (at Thu, 29 Mar 2007 14:26:44 -0700 (PDT)), David Miller <davem@davemloft.net> says:
> From: Sridhar Samudrala <sri@us.ibm.com>
> Date: Thu, 29 Mar 2007 14:17:28 -0700
>
> > The check for length in rawv6_sendmsg() is incorrect.
> > As len is an unsigned int, (len < 0) will never be TRUE.
> > I think checking for IPV6_MAXPLEN(65535) is better.
> >
> > Is it possible to send ipv6 jumbo packets using raw
> > sockets? If so, we can remove this check.
>
> I don't see why such a limitation against jumbo would exist,
> does anyone else?
>
> Thanks for catching this Sridhar. A good compiler should simply
> fail to compile "if (x < 0)" when 'x' is an unsigned type, don't
> you think :-)
Dave, we use "int" for returning value,
so we should fix this anyway, IMHO;
we should not allow len > INT_MAX.
Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Acked-by: Sridhar Samudrala <sri@us.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-03-30 14:45:35 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-02-09 23:24:49 +09:00
|
|
|
|
2015-01-31 10:40:17 -05:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-03-12 16:22:43 -05:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-03-12 16:36:19 -05:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-03-12 16:22:43 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-03-29 14:00:04 +01:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
ipv6: make lookups simpler and faster
TCP listener refactoring, part 4 :
To speed up inet lookups, we moved IPv4 addresses from inet to struct
sock_common
Now is time to do the same for IPv6, because it permits us to have fast
lookups for all kind of sockets, including upcoming SYN_RECV.
Getting IPv6 addresses in TCP lookups currently requires two extra cache
lines, plus a dereference (and memory stall).
inet6_sk(sk) does the dereference of inet_sk(__sk)->pinet6
This patch is way bigger than its IPv4 counter part, because for IPv4,
we could add aliases (inet_daddr, inet_rcv_saddr), while on IPv6,
it's not doable easily.
inet6_sk(sk)->daddr becomes sk->sk_v6_daddr
inet6_sk(sk)->rcv_saddr becomes sk->sk_v6_rcv_saddr
And timewait socket also have tw->tw_v6_daddr & tw->tw_v6_rcv_saddr
at the same offset.
We get rid of INET6_TW_MATCH() as INET6_MATCH() is now the generic
macro.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-03 15:42:29 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-03-08 02:07:19 +00:00
|
|
|
|
2011-03-12 16:22:43 -05:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-03-12 16:36:19 -05:00
|
|
|
|
ipv6: make lookups simpler and faster
TCP listener refactoring, part 4 :
To speed up inet lookups, we moved IPv4 addresses from inet to struct
sock_common
Now is time to do the same for IPv6, because it permits us to have fast
lookups for all kind of sockets, including upcoming SYN_RECV.
Getting IPv6 addresses in TCP lookups currently requires two extra cache
lines, plus a dereference (and memory stall).
inet6_sk(sk) does the dereference of inet_sk(__sk)->pinet6
This patch is way bigger than its IPv4 counter part, because for IPv4,
we could add aliases (inet_daddr, inet_rcv_saddr), while on IPv6,
it's not doable easily.
inet6_sk(sk)->daddr becomes sk->sk_v6_daddr
inet6_sk(sk)->rcv_saddr becomes sk->sk_v6_rcv_saddr
And timewait socket also have tw->tw_v6_daddr & tw->tw_v6_rcv_saddr
at the same offset.
We get rid of INET6_TW_MATCH() as INET6_MATCH() is now the generic
macro.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-03 15:42:29 -07:00
|
|
|
|
2011-03-12 16:22:43 -05:00
|
|
|
|
2005-09-18 00:30:08 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2011-03-12 16:22:43 -05:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2011-03-12 16:22:43 -05:00
|
|
|
|
|
|
|
|
|
2008-12-16 02:08:29 -08:00
|
|
|
|
2011-03-12 16:22:43 -05:00
|
|
|
|
2016-11-04 02:23:43 +09:00
|
|
|
|
2009-10-05 08:24:16 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-05-02 21:40:07 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2016-05-02 21:40:07 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-03-12 16:22:43 -05:00
|
|
|
|
|
|
|
|
|
2015-03-29 14:00:04 +01:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-09-18 00:30:08 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2015-11-29 19:37:57 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-11-20 12:23:18 +09:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-05-02 21:40:07 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2011-03-12 16:22:43 -05:00
|
|
|
|
2008-04-11 00:38:24 -04:00
|
|
|
|
2011-11-21 03:39:03 +00:00
|
|
|
|
2008-04-11 00:38:24 -04:00
|
|
|
|
2011-03-12 16:22:43 -05:00
|
|
|
|
|
|
|
|
|
2011-11-21 03:39:03 +00:00
|
|
|
|
2011-03-12 16:36:19 -05:00
|
|
|
|
2007-02-09 23:24:49 +09:00
|
|
|
|
2011-03-12 16:22:43 -05:00
|
|
|
|
2010-06-01 21:35:01 +00:00
|
|
|
|
2005-09-18 00:30:08 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2011-03-12 16:22:43 -05:00
|
|
|
|
|
|
|
|
|
2005-09-18 00:30:08 -07:00
|
|
|
|
2012-02-08 09:11:08 +00:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2011-03-12 16:22:43 -05:00
|
|
|
|
2006-08-04 23:12:42 -07:00
|
|
|
|
2016-06-11 20:08:19 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-08-28 08:04:14 +02:00
|
|
|
|
2011-03-01 13:19:07 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-05-24 18:17:54 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2016-05-02 21:40:07 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-01-31 10:40:17 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-05-02 21:40:07 -07:00
|
|
|
|
2015-01-31 10:40:17 -05:00
|
|
|
|
2016-05-02 21:40:07 -07:00
|
|
|
|
2015-01-31 10:40:17 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-11-11 10:59:17 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-05-02 21:40:07 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2016-05-02 21:40:07 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2006-11-27 09:29:59 -08:00
|
|
|
|
2006-10-03 14:35:49 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2015-01-31 10:40:17 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-10-03 14:21:58 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
ipv6: make lookups simpler and faster
TCP listener refactoring, part 4 :
To speed up inet lookups, we moved IPv4 addresses from inet to struct
sock_common
Now is time to do the same for IPv6, because it permits us to have fast
lookups for all kind of sockets, including upcoming SYN_RECV.
Getting IPv6 addresses in TCP lookups currently requires two extra cache
lines, plus a dereference (and memory stall).
inet6_sk(sk) does the dereference of inet_sk(__sk)->pinet6
This patch is way bigger than its IPv4 counter part, because for IPv4,
we could add aliases (inet_daddr, inet_rcv_saddr), while on IPv6,
it's not doable easily.
inet6_sk(sk)->daddr becomes sk->sk_v6_daddr
inet6_sk(sk)->rcv_saddr becomes sk->sk_v6_rcv_saddr
And timewait socket also have tw->tw_v6_daddr & tw->tw_v6_rcv_saddr
at the same offset.
We get rid of INET6_TW_MATCH() as INET6_MATCH() is now the generic
macro.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-03 15:42:29 -07:00
|
|
|
|
|
|
|
|
|
2006-08-29 17:15:09 -07:00
|
|
|
|
2011-03-12 16:22:43 -05:00
|
|
|
|
2006-08-29 17:15:09 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-10-03 14:21:58 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-06-04 01:30:25 +09:00
|
|
|
|
2005-10-03 14:21:58 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2008-06-04 01:30:25 +09:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2015-11-29 19:37:57 -08:00
|
|
|
|
2007-09-14 17:15:01 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2006-08-15 00:00:09 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
net: snmp: kill various STATS_USER() helpers
In the old days (before linux-3.0), SNMP counters were duplicated,
one for user context, and one for BH context.
After commit 8f0ea0fe3a03 ("snmp: reduce percpu needs by 50%")
we have a single copy, and what really matters is preemption being
enabled or disabled, since we use this_cpu_inc() or __this_cpu_inc()
respectively.
We therefore kill SNMP_INC_STATS_USER(), SNMP_ADD_STATS_USER(),
NET_INC_STATS_USER(), NET_ADD_STATS_USER(), SCTP_INC_STATS_USER(),
SNMP_INC_STATS64_USER(), SNMP_ADD_STATS64_USER(), TCP_ADD_STATS_USER(),
UDP_INC_STATS_USER(), UDP6_INC_STATS_USER(), and XFRM_INC_STATS_USER()
Following patches will rename __BH helpers to make clear their
usage is not tied to BH being disabled.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-27 16:44:27 -07:00
|
|
|
|
|
|
|
|
|
2006-08-15 00:00:09 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-02-06 23:14:16 +02:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-06-14 17:04:49 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2013-03-19 06:11:12 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-03-19 06:11:12 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2006-11-27 11:10:57 -08:00
|
|
|
|
2009-09-30 16:12:20 -07:00
|
|
|
|
2006-03-20 22:45:21 -08:00
|
|
|
|
2008-03-06 16:22:02 -08:00
|
|
|
|
2006-11-27 09:29:59 -08:00
|
|
|
|
|
|
|
|
|
2006-11-27 11:10:57 -08:00
|
|
|
|
2006-03-20 22:45:21 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2006-11-27 11:10:57 -08:00
|
|
|
|
2009-09-30 16:12:20 -07:00
|
|
|
|
2006-03-20 22:45:21 -08:00
|
|
|
|
2008-03-06 16:22:02 -08:00
|
|
|
|
2006-11-27 09:29:59 -08:00
|
|
|
|
|
|
|
|
|
2006-11-27 11:10:57 -08:00
|
|
|
|
2006-03-20 22:45:21 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2006-11-27 11:10:57 -08:00
|
|
|
|
|
|
|
|
|
2006-03-20 22:45:21 -08:00
|
|
|
|
2008-03-06 16:22:02 -08:00
|
|
|
|
2006-11-27 09:29:59 -08:00
|
|
|
|
2006-11-27 11:10:57 -08:00
|
|
|
|
2006-03-20 22:45:21 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2006-11-27 11:10:57 -08:00
|
|
|
|
|
|
|
|
|
2006-03-20 22:45:21 -08:00
|
|
|
|
2008-03-06 16:22:02 -08:00
|
|
|
|
2006-11-27 09:29:59 -08:00
|
|
|
|
2006-11-27 11:10:57 -08:00
|
|
|
|
2006-03-20 22:45:21 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-08-28 15:14:20 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-03-23 13:34:16 -06:00
|
|
|
|
2017-03-08 16:36:49 -07:00
|
|
|
|
2017-03-23 13:34:16 -06:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2006-11-27 11:10:57 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2013-05-31 15:05:48 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-10-30 06:46:30 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-10-29 01:41:45 -07:00
|
|
|
|
2011-10-30 06:46:30 +00:00
|
|
|
|
2008-03-28 18:24:26 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2010-01-17 03:35:32 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2008-03-21 04:14:17 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2015-08-14 22:43:38 +01:00
|
|
|
|
|
|
|
|
|
2008-03-21 04:14:17 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2006-03-20 22:48:35 -08:00
|
|
|
|
|
|
|
|
|
2006-11-27 11:10:57 -08:00
|
|
|
|
2006-03-20 22:48:35 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-10-21 13:55:47 +02:00
|
|
|
|
2006-03-20 22:48:35 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-04-11 15:29:37 -07:00
|
|
|
|
2006-11-27 11:10:57 -08:00
|
|
|
|
|
|
|
|
|
udp: add rehash on connect()
commit 30fff923 introduced in linux-2.6.33 (udp: bind() optimisation)
added a secondary hash on UDP, hashed on (local addr, local port).
Problem is that following sequence :
fd = socket(...)
connect(fd, &remote, ...)
not only selects remote end point (address and port), but also sets
local address, while UDP stack stored in secondary hash table the socket
while its local address was INADDR_ANY (or ipv6 equivalent)
Sequence is :
- autobind() : choose a random local port, insert socket in hash tables
[while local address is INADDR_ANY]
- connect() : set remote address and port, change local address to IP
given by a route lookup.
When an incoming UDP frame comes, if more than 10 sockets are found in
primary hash table, we switch to secondary table, and fail to find
socket because its local address changed.
One solution to this problem is to rehash datagram socket if needed.
We add a new rehash(struct socket *) method in "struct proto", and
implement this method for UDP v4 & v6, using a common helper.
This rehashing only takes care of secondary hash table, since primary
hash (based on local port only) is not changed.
Reported-by: Krzysztof Piotr Oledzki <ole@ans.pl>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Tested-by: Krzysztof Piotr Oledzki <ole@ans.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-09-08 05:08:44 +00:00
|
|
|
|
2006-03-20 22:48:35 -08:00
|
|
|
|
2007-12-31 00:29:24 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2006-03-20 22:48:35 -08:00
|
|
|
|
2008-10-29 01:41:45 -07:00
|
|
|
|
2006-03-20 22:45:21 -08:00
|
|
|
|
2006-03-20 22:48:35 -08:00
|
|
|
|
|
|
|
|
|
2006-03-20 22:45:21 -08:00
|
|
|
|
2016-08-23 21:06:33 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-12-11 02:25:35 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-12-11 02:25:35 -08:00
|
|
|
|
|
|
|
|
|
2012-11-15 08:49:15 +00:00
|
|
|
|
|
|
|
|
|
2012-11-15 08:49:22 +00:00
|
|
|
|
2012-11-15 08:49:15 +00:00
|
|
|
|
2007-12-11 02:25:35 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-12-13 05:34:58 -08:00
|
|
|
|
2007-12-11 02:25:35 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|