2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-05-05 16:16:16 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-02-09 23:24:47 +09:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-02-09 23:24:47 +09:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-07-05 15:00:32 -07:00
|
|
|
|
2006-03-25 01:38:55 -08:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-03-12 07:03:32 +00:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2016-12-24 11:46:01 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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
|
|
|
|
inetpeer: get rid of ip_id_count
Ideally, we would need to generate IP ID using a per destination IP
generator.
linux kernels used inet_peer cache for this purpose, but this had a huge
cost on servers disabling MTU discovery.
1) each inet_peer struct consumes 192 bytes
2) inetpeer cache uses a binary tree of inet_peer structs,
with a nominal size of ~66000 elements under load.
3) lookups in this tree are hitting a lot of cache lines, as tree depth
is about 20.
4) If server deals with many tcp flows, we have a high probability of
not finding the inet_peer, allocating a fresh one, inserting it in
the tree with same initial ip_id_count, (cf secure_ip_id())
5) We garbage collect inet_peer aggressively.
IP ID generation do not have to be 'perfect'
Goal is trying to avoid duplicates in a short period of time,
so that reassembly units have a chance to complete reassembly of
fragments belonging to one message before receiving other fragments
with a recycled ID.
We simply use an array of generators, and a Jenkin hash using the dst IP
as a key.
ipv6_select_ident() is put back into net/ipv6/ip6_output.c where it
belongs (it is only used from this file)
secure_ip_id() and secure_ipv6_id() no longer are needed.
Rename ip_select_ident_more() to ip_select_ident_segs() to avoid
unnecessary decrement/increment of the number of segments.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-06-02 05:26:03 -07:00
|
|
|
|
2007-11-13 21:34:06 -08:00
|
|
|
|
2015-07-21 10:43:59 +02:00
|
|
|
|
2007-09-12 12:01:34 +02:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-07-21 10:43:47 +02:00
|
|
|
|
2006-07-30 20:43:36 -07:00
|
|
|
|
2007-03-22 11:55:17 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2012-04-18 18:05:46 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2011-08-03 20:50:44 -07:00
|
|
|
|
2015-07-21 10:43:59 +02:00
|
|
|
|
2015-09-29 20:07:13 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2017-05-25 10:42:39 -07:00
|
|
|
|
|
|
|
|
|
2011-03-11 20:07:33 -05:00
|
|
|
|
2011-12-02 11:39:42 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-03-22 17:43:59 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-12-21 15:47:16 -05:00
|
|
|
|
2016-02-18 21:21:19 +08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-12-13 12:52:14 -08:00
|
|
|
|
2011-11-23 02:12:51 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2012-07-17 03:29:28 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-31 15:06:50 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
net: Implement read-only protection and COW'ing of metrics.
Routing metrics are now copy-on-write.
Initially a route entry points it's metrics at a read-only location.
If a routing table entry exists, it will point there. Else it will
point at the all zero metric place-holder called 'dst_default_metrics'.
The writeability state of the metrics is stored in the low bits of the
metrics pointer, we have two bits left to spare if we want to store
more states.
For the initial implementation, COW is implemented simply via kmalloc.
However future enhancements will change this to place the writable
metrics somewhere else, in order to increase sharing. Very likely
this "somewhere else" will be the inetpeer cache.
Note also that this means that metrics updates may transiently fail
if we cannot COW the metrics successfully.
But even by itself, this patch should decrease memory usage and
increase cache locality especially for routing workloads. In those
cases the read-only metric copies stay in place and never get written
to.
TCP workloads where metrics get updated, and those rare cases where
PMTU triggers occur, will take a very slight performance hit. But
that hit will be alleviated when the long-term writable metrics
move to a more sharable location.
Since the metrics storage went from a u32 array of RTAX_MAX entries to
what is essentially a pointer, some retooling of the dst_entry layout
was necessary.
Most importantly, we need to preserve the alignment of the reference
count so that it doesn't share cache lines with the read-mostly state,
as per Eric Dumazet's alignment assertion checks.
The only non-trivial bit here is the move of the 'flags' member into
the writeable cacheline. This is OK since we are always accessing the
flags around the same moment when we made a modification to the
reference count.
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-01-26 20:51:05 -08:00
|
|
|
|
|
|
|
|
|
2012-07-10 07:08:18 -07:00
|
|
|
|
|
|
|
|
|
net: Implement read-only protection and COW'ing of metrics.
Routing metrics are now copy-on-write.
Initially a route entry points it's metrics at a read-only location.
If a routing table entry exists, it will point there. Else it will
point at the all zero metric place-holder called 'dst_default_metrics'.
The writeability state of the metrics is stored in the low bits of the
metrics pointer, we have two bits left to spare if we want to store
more states.
For the initial implementation, COW is implemented simply via kmalloc.
However future enhancements will change this to place the writable
metrics somewhere else, in order to increase sharing. Very likely
this "somewhere else" will be the inetpeer cache.
Note also that this means that metrics updates may transiently fail
if we cannot COW the metrics successfully.
But even by itself, this patch should decrease memory usage and
increase cache locality especially for routing workloads. In those
cases the read-only metric copies stay in place and never get written
to.
TCP workloads where metrics get updated, and those rare cases where
PMTU triggers occur, will take a very slight performance hit. But
that hit will be alleviated when the long-term writable metrics
move to a more sharable location.
Since the metrics storage went from a u32 array of RTAX_MAX entries to
what is essentially a pointer, some retooling of the dst_entry layout
was necessary.
Most importantly, we need to preserve the alignment of the reference
count so that it doesn't share cache lines with the read-mostly state,
as per Eric Dumazet's alignment assertion checks.
The only non-trivial bit here is the move of the 'flags' member into
the writeable cacheline. This is OK since we are always accessing the
flags around the same moment when we made a modification to the
reference count.
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-01-26 20:51:05 -08:00
|
|
|
|
|
|
|
|
|
2012-07-02 21:52:24 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-02-06 23:14:15 +02:00
|
|
|
|
2011-07-18 00:40:17 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-12-13 12:52:14 -08:00
|
|
|
|
2011-11-23 02:12:51 +00:00
|
|
|
|
net: Implement read-only protection and COW'ing of metrics.
Routing metrics are now copy-on-write.
Initially a route entry points it's metrics at a read-only location.
If a routing table entry exists, it will point there. Else it will
point at the all zero metric place-holder called 'dst_default_metrics'.
The writeability state of the metrics is stored in the low bits of the
metrics pointer, we have two bits left to spare if we want to store
more states.
For the initial implementation, COW is implemented simply via kmalloc.
However future enhancements will change this to place the writable
metrics somewhere else, in order to increase sharing. Very likely
this "somewhere else" will be the inetpeer cache.
Note also that this means that metrics updates may transiently fail
if we cannot COW the metrics successfully.
But even by itself, this patch should decrease memory usage and
increase cache locality especially for routing workloads. In those
cases the read-only metric copies stay in place and never get written
to.
TCP workloads where metrics get updated, and those rare cases where
PMTU triggers occur, will take a very slight performance hit. But
that hit will be alleviated when the long-term writable metrics
move to a more sharable location.
Since the metrics storage went from a u32 array of RTAX_MAX entries to
what is essentially a pointer, some retooling of the dst_entry layout
was necessary.
Most importantly, we need to preserve the alignment of the reference
count so that it doesn't share cache lines with the read-mostly state,
as per Eric Dumazet's alignment assertion checks.
The only non-trivial bit here is the move of the 'flags' member into
the writeable cacheline. This is OK since we are always accessing the
flags around the same moment when we made a modification to the
reference count.
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-01-26 20:51:05 -08:00
|
|
|
|
2012-07-31 15:06:50 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-11 20:55:47 -07:00
|
|
|
|
2015-10-07 16:48:37 -05:00
|
|
|
|
2011-07-18 00:40:17 -07:00
|
|
|
|
2017-02-06 23:14:15 +02:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-07-09 15:32:57 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2011-03-15 13:56:07 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-04-04 21:33:28 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
[IPV4]: rt_cache_stat can be statically defined
Using __get_cpu_var(obj) is slightly faster than per_cpu_ptr(obj,
raw_smp_processor_id()).
1) Smaller code and memory use
For static and small objects, DEFINE_PER_CPU(type, object) is preferred over a
alloc_percpu() : Better and smaller code to access them, and no extra memory
(storing the pointer, and the percpu array of pointers)
x86_64 code before patch
mov 1237577(%rip),%rax # ffffffff803e5990 <rt_cache_stat>
not %rax # part of per_cpu machinery
mov %gs:0x3c,%edx # get cpu number
movslq %edx,%rdx # extend 32 bits cpu number to 64 bits
mov (%rax,%rdx,8),%rax # get the pointer for this cpu
incl 0x38(%rax)
x86_64 code after patch
mov $per_cpu__rt_cache_stat,%rdx
mov %gs:0x48,%rax # get percpu data offset
incl 0x38(%rax,%rdx,1)
2) False sharing avoidance for SMP :
For a small NR_CPUS, the array of per cpu pointers allocated in alloc_percpu()
can be <= 32 bytes. This let slab code gives a part of a cache line. If the
other part of this 64 bytes (or 128 bytes) cache line is used by a mostly
written object, we can have false sharing and expensive per_cpu_ptr() operations.
Size of rt_cache_stat is 64 bytes, so this patch is not a danger of a too big
increase of bss (in UP mode) or static per_cpu data for SMP
(PERCPU_ENOUGH_ROOM is currently 32768 bytes)
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2006-01-17 02:54:36 -08:00
|
|
|
|
2014-04-07 15:39:40 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
[IPV4] route cache: Introduce rt_genid for smooth cache invalidation
Current ip route cache implementation is not suited to large caches.
We can consume a lot of CPU when cache must be invalidated, since we
currently need to evict all cache entries, and this eviction is
sometimes asynchronous. min_delay & max_delay can somewhat control this
asynchronism behavior, but whole thing is a kludge, regularly triggering
infamous soft lockup messages. When entries are still in use, this also
consumes a lot of ram, filling dst_garbage.list.
A better scheme is to use a generation identifier on each entry,
so that cache invalidation can be performed by changing the table
identifier, without having to scan all entries.
No more delayed flushing, no more stalling when secret_interval expires.
Invalidated entries will then be freed at GC time (controled by
ip_rt_gc_timeout or stress), or when an invalidated entry is found
in a chain when an insert is done.
Thus we keep a normal equilibrium.
This patch :
- renames rt_hash_rnd to rt_genid (and makes it an atomic_t)
- Adds a new rt_genid field to 'struct rtable' (filling a hole on 64bit)
- Checks entry->rt_genid at appropriate places :
2008-01-31 17:05:09 -08:00
|
|
|
|
2012-07-17 11:00:09 -07:00
|
|
|
|
[IPV4] route cache: Introduce rt_genid for smooth cache invalidation
Current ip route cache implementation is not suited to large caches.
We can consume a lot of CPU when cache must be invalidated, since we
currently need to evict all cache entries, and this eviction is
sometimes asynchronous. min_delay & max_delay can somewhat control this
asynchronism behavior, but whole thing is a kludge, regularly triggering
infamous soft lockup messages. When entries are still in use, this also
consumes a lot of ram, filling dst_garbage.list.
A better scheme is to use a generation identifier on each entry,
so that cache invalidation can be performed by changing the table
identifier, without having to scan all entries.
No more delayed flushing, no more stalling when secret_interval expires.
Invalidated entries will then be freed at GC time (controled by
ip_rt_gc_timeout or stress), or when an invalidated entry is found
in a chain when an insert is done.
Thus we keep a normal equilibrium.
This patch :
- renames rt_hash_rnd to rt_genid (and makes it an atomic_t)
- Adds a new rt_genid field to 'struct rtable' (filling a hole on 64bit)
- Checks entry->rt_genid at appropriate places :
2008-01-31 17:05:09 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-17 11:00:09 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-02-09 23:24:47 +09:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2007-03-12 14:34:29 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-17 11:00:09 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2007-02-12 00:55:35 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-17 11:00:09 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-12-29 12:23:42 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
[IPV4]: rt_cache_stat can be statically defined
Using __get_cpu_var(obj) is slightly faster than per_cpu_ptr(obj,
raw_smp_processor_id()).
1) Smaller code and memory use
For static and small objects, DEFINE_PER_CPU(type, object) is preferred over a
alloc_percpu() : Better and smaller code to access them, and no extra memory
(storing the pointer, and the percpu array of pointers)
x86_64 code before patch
mov 1237577(%rip),%rax # ffffffff803e5990 <rt_cache_stat>
not %rax # part of per_cpu machinery
mov %gs:0x3c,%edx # get cpu number
movslq %edx,%rdx # extend 32 bits cpu number to 64 bits
mov (%rax,%rdx,8),%rax # get the pointer for this cpu
incl 0x38(%rax)
x86_64 code after patch
mov $per_cpu__rt_cache_stat,%rdx
mov %gs:0x48,%rax # get percpu data offset
incl 0x38(%rax,%rdx,1)
2) False sharing avoidance for SMP :
For a small NR_CPUS, the array of per cpu pointers allocated in alloc_percpu()
can be <= 32 bytes. This let slab code gives a part of a cache line. If the
other part of this 64 bytes (or 128 bytes) cache line is used by a mostly
written object, we can have false sharing and expensive per_cpu_ptr() operations.
Size of rt_cache_stat is 64 bytes, so this patch is not a danger of a too big
increase of bss (in UP mode) or static per_cpu data for SMP
(PERCPU_ENOUGH_ROOM is currently 32768 bytes)
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2006-01-17 02:54:36 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-12-29 12:23:42 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
[IPV4]: rt_cache_stat can be statically defined
Using __get_cpu_var(obj) is slightly faster than per_cpu_ptr(obj,
raw_smp_processor_id()).
1) Smaller code and memory use
For static and small objects, DEFINE_PER_CPU(type, object) is preferred over a
alloc_percpu() : Better and smaller code to access them, and no extra memory
(storing the pointer, and the percpu array of pointers)
x86_64 code before patch
mov 1237577(%rip),%rax # ffffffff803e5990 <rt_cache_stat>
not %rax # part of per_cpu machinery
mov %gs:0x3c,%edx # get cpu number
movslq %edx,%rdx # extend 32 bits cpu number to 64 bits
mov (%rax,%rdx,8),%rax # get the pointer for this cpu
incl 0x38(%rax)
x86_64 code after patch
mov $per_cpu__rt_cache_stat,%rdx
mov %gs:0x48,%rax # get percpu data offset
incl 0x38(%rax,%rdx,1)
2) False sharing avoidance for SMP :
For a small NR_CPUS, the array of per cpu pointers allocated in alloc_percpu()
can be <= 32 bytes. This let slab code gives a part of a cache line. If the
other part of this 64 bytes (or 128 bytes) cache line is used by a mostly
written object, we can have false sharing and expensive per_cpu_ptr() operations.
Size of rt_cache_stat is 64 bytes, so this patch is not a danger of a too big
increase of bss (in UP mode) or static per_cpu data for SMP
(PERCPU_ENOUGH_ROOM is currently 32768 bytes)
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2006-01-17 02:54:36 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2007-02-09 23:24:47 +09:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-28 12:16:08 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2007-02-09 23:24:47 +09:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2010-10-08 06:37:34 +00:00
|
|
|
|
2013-10-16 02:49:04 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-10-16 02:49:04 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-02-09 23:24:47 +09:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2013-10-16 02:49:04 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-03-12 14:34:29 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-02-12 00:55:35 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-01-14 13:36:42 +01:00
|
|
|
|
2009-11-25 15:40:35 -08:00
|
|
|
|
2007-12-05 21:13:48 -08:00
|
|
|
|
2009-11-25 15:40:35 -08:00
|
|
|
|
|
|
|
|
|
2007-12-05 21:13:48 -08:00
|
|
|
|
2009-11-25 15:40:35 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-12-05 21:13:48 -08:00
|
|
|
|
2009-11-25 15:40:35 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-12-05 21:13:48 -08:00
|
|
|
|
|
|
|
|
|
2009-11-25 15:40:35 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-12-05 21:13:48 -08:00
|
|
|
|
2009-11-25 15:40:35 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-12-05 21:13:48 -08:00
|
|
|
|
2007-12-05 21:14:28 -08:00
|
|
|
|
2008-02-28 20:51:18 -08:00
|
|
|
|
2007-12-05 21:14:28 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-02-18 01:34:54 +00:00
|
|
|
|
|
|
|
|
|
2007-12-05 21:14:28 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-02-28 14:14:25 -08:00
|
|
|
|
|
|
|
|
|
2007-12-05 21:14:28 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-01-14 13:36:42 +01:00
|
|
|
|
2009-11-25 15:40:35 -08:00
|
|
|
|
2007-12-05 21:14:28 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-01-14 13:36:42 +01:00
|
|
|
|
2007-12-05 21:14:28 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-02-28 20:51:18 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-01-14 13:36:42 +01:00
|
|
|
|
2008-02-28 20:51:18 -08:00
|
|
|
|
2010-01-17 03:32:50 +00:00
|
|
|
|
2008-02-28 20:51:18 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-12-05 21:14:28 -08:00
|
|
|
|
2008-02-28 20:51:18 -08:00
|
|
|
|
2007-12-05 21:14:28 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-02-09 23:24:47 +09:00
|
|
|
|
2012-07-25 05:11:23 +00:00
|
|
|
|
2008-07-05 19:04:32 -07:00
|
|
|
|
2013-07-30 08:33:53 +08:00
|
|
|
|
2008-07-05 19:04:32 -07:00
|
|
|
|
|
|
|
|
|
2012-09-07 00:45:29 +00:00
|
|
|
|
[IPV4] route cache: Introduce rt_genid for smooth cache invalidation
Current ip route cache implementation is not suited to large caches.
We can consume a lot of CPU when cache must be invalidated, since we
currently need to evict all cache entries, and this eviction is
sometimes asynchronous. min_delay & max_delay can somewhat control this
asynchronism behavior, but whole thing is a kludge, regularly triggering
infamous soft lockup messages. When entries are still in use, this also
consumes a lot of ram, filling dst_garbage.list.
A better scheme is to use a generation identifier on each entry,
so that cache invalidation can be performed by changing the table
identifier, without having to scan all entries.
No more delayed flushing, no more stalling when secret_interval expires.
Invalidated entries will then be freed at GC time (controled by
ip_rt_gc_timeout or stress), or when an invalidated entry is found
in a chain when an insert is done.
Thus we keep a normal equilibrium.
This patch :
- renames rt_hash_rnd to rt_genid (and makes it an atomic_t)
- Adds a new rt_genid field to 'struct rtable' (filling a hole on 64bit)
- Checks entry->rt_genid at appropriate places :
2008-01-31 17:05:09 -08:00
|
|
|
|
2013-07-30 08:33:53 +08:00
|
|
|
|
2010-03-08 03:20:00 +00:00
|
|
|
|
|
|
|
|
|
2012-07-02 21:52:24 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-07-11 22:44:24 +00:00
|
|
|
|
2011-07-18 00:40:17 -07:00
|
|
|
|
|
|
|
|
|
2012-01-26 15:22:32 -05:00
|
|
|
|
2011-07-11 22:44:24 +00:00
|
|
|
|
|
|
|
|
|
2012-01-26 15:22:32 -05:00
|
|
|
|
2012-07-02 02:02:15 -07:00
|
|
|
|
2012-01-26 15:22:32 -05:00
|
|
|
|
2012-07-02 21:52:24 -07:00
|
|
|
|
|
|
|
|
|
2011-07-18 00:40:17 -07:00
|
|
|
|
2012-02-15 17:48:35 -05:00
|
|
|
|
2011-07-18 00:40:17 -07:00
|
|
|
|
|
|
|
|
|
2011-07-25 00:01:41 +00:00
|
|
|
|
2011-07-18 00:40:17 -07:00
|
|
|
|
|
|
|
|
|
2017-02-06 23:14:15 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
ip: make IP identifiers less predictable
In "Counting Packets Sent Between Arbitrary Internet Hosts", Jeffrey and
Jedidiah describe ways exploiting linux IP identifier generation to
infer whether two machines are exchanging packets.
With commit 73f156a6e8c1 ("inetpeer: get rid of ip_id_count"), we
changed IP id generation, but this does not really prevent this
side-channel technique.
This patch adds a random amount of perturbation so that IP identifiers
for a given destination [1] are no longer monotonically increasing after
an idle period.
Note that prandom_u32_max(1) returns 0, so if generator is used at most
once per jiffy, this patch inserts no hole in the ID suite and do not
increase collision probability.
This is jiffies based, so in the worst case (HZ=1000), the id can
rollover after ~65 seconds of idle time, which should be fine.
We also change the hash used in __ip_select_ident() to not only hash
on daddr, but also saddr and protocol, so that ICMP probes can not be
used to infer information for other protocols.
For IPv6, adds saddr into the hash as well, but not nexthdr.
If I ping the patched target, we can see ID are now hard to predict.
21:57:11.008086 IP (...)
A > target: ICMP echo request, seq 1, length 64
21:57:11.010752 IP (... id 2081 ...)
target > A: ICMP echo reply, seq 1, length 64
21:57:12.013133 IP (...)
A > target: ICMP echo request, seq 2, length 64
21:57:12.015737 IP (... id 3039 ...)
target > A: ICMP echo reply, seq 2, length 64
21:57:13.016580 IP (...)
A > target: ICMP echo request, seq 3, length 64
21:57:13.019251 IP (... id 3437 ...)
target > A: ICMP echo reply, seq 3, length 64
[1] TCP sessions uses a per flow ID generator not changed by this patch.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Jeffrey Knockel <jeffk@cs.unm.edu>
Reported-by: Jedidiah R. Crandall <crandall@cs.unm.edu>
Cc: Willy Tarreau <w@1wt.eu>
Cc: Hannes Frederic Sowa <hannes@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-26 08:58:10 +02:00
|
|
|
|
|
|
|
|
|
2015-05-01 10:37:49 -07:00
|
|
|
|
|
|
|
|
|
ip: make IP identifiers less predictable
In "Counting Packets Sent Between Arbitrary Internet Hosts", Jeffrey and
Jedidiah describe ways exploiting linux IP identifier generation to
infer whether two machines are exchanging packets.
With commit 73f156a6e8c1 ("inetpeer: get rid of ip_id_count"), we
changed IP id generation, but this does not really prevent this
side-channel technique.
This patch adds a random amount of perturbation so that IP identifiers
for a given destination [1] are no longer monotonically increasing after
an idle period.
Note that prandom_u32_max(1) returns 0, so if generator is used at most
once per jiffy, this patch inserts no hole in the ID suite and do not
increase collision probability.
This is jiffies based, so in the worst case (HZ=1000), the id can
rollover after ~65 seconds of idle time, which should be fine.
We also change the hash used in __ip_select_ident() to not only hash
on daddr, but also saddr and protocol, so that ICMP probes can not be
used to infer information for other protocols.
For IPv6, adds saddr into the hash as well, but not nexthdr.
If I ping the patched target, we can see ID are now hard to predict.
21:57:11.008086 IP (...)
A > target: ICMP echo request, seq 1, length 64
21:57:11.010752 IP (... id 2081 ...)
target > A: ICMP echo reply, seq 1, length 64
21:57:12.013133 IP (...)
A > target: ICMP echo request, seq 2, length 64
21:57:12.015737 IP (... id 3039 ...)
target > A: ICMP echo reply, seq 2, length 64
21:57:13.016580 IP (...)
A > target: ICMP echo request, seq 3, length 64
21:57:13.019251 IP (... id 3437 ...)
target > A: ICMP echo reply, seq 3, length 64
[1] TCP sessions uses a per flow ID generator not changed by this patch.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Jeffrey Knockel <jeffk@cs.unm.edu>
Reported-by: Jedidiah R. Crandall <crandall@cs.unm.edu>
Cc: Willy Tarreau <w@1wt.eu>
Cc: Hannes Frederic Sowa <hannes@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-26 08:58:10 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-05-01 10:37:49 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
ip: make IP identifiers less predictable
In "Counting Packets Sent Between Arbitrary Internet Hosts", Jeffrey and
Jedidiah describe ways exploiting linux IP identifier generation to
infer whether two machines are exchanging packets.
With commit 73f156a6e8c1 ("inetpeer: get rid of ip_id_count"), we
changed IP id generation, but this does not really prevent this
side-channel technique.
This patch adds a random amount of perturbation so that IP identifiers
for a given destination [1] are no longer monotonically increasing after
an idle period.
Note that prandom_u32_max(1) returns 0, so if generator is used at most
once per jiffy, this patch inserts no hole in the ID suite and do not
increase collision probability.
This is jiffies based, so in the worst case (HZ=1000), the id can
rollover after ~65 seconds of idle time, which should be fine.
We also change the hash used in __ip_select_ident() to not only hash
on daddr, but also saddr and protocol, so that ICMP probes can not be
used to infer information for other protocols.
For IPv6, adds saddr into the hash as well, but not nexthdr.
If I ping the patched target, we can see ID are now hard to predict.
21:57:11.008086 IP (...)
A > target: ICMP echo request, seq 1, length 64
21:57:11.010752 IP (... id 2081 ...)
target > A: ICMP echo reply, seq 1, length 64
21:57:12.013133 IP (...)
A > target: ICMP echo request, seq 2, length 64
21:57:12.015737 IP (... id 3039 ...)
target > A: ICMP echo reply, seq 2, length 64
21:57:13.016580 IP (...)
A > target: ICMP echo request, seq 3, length 64
21:57:13.019251 IP (... id 3437 ...)
target > A: ICMP echo reply, seq 3, length 64
[1] TCP sessions uses a per flow ID generator not changed by this patch.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Jeffrey Knockel <jeffk@cs.unm.edu>
Reported-by: Jedidiah R. Crandall <crandall@cs.unm.edu>
Cc: Willy Tarreau <w@1wt.eu>
Cc: Hannes Frederic Sowa <hannes@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-26 08:58:10 +02:00
|
|
|
|
2016-09-20 18:06:17 -07:00
|
|
|
|
ip: make IP identifiers less predictable
In "Counting Packets Sent Between Arbitrary Internet Hosts", Jeffrey and
Jedidiah describe ways exploiting linux IP identifier generation to
infer whether two machines are exchanging packets.
With commit 73f156a6e8c1 ("inetpeer: get rid of ip_id_count"), we
changed IP id generation, but this does not really prevent this
side-channel technique.
This patch adds a random amount of perturbation so that IP identifiers
for a given destination [1] are no longer monotonically increasing after
an idle period.
Note that prandom_u32_max(1) returns 0, so if generator is used at most
once per jiffy, this patch inserts no hole in the ID suite and do not
increase collision probability.
This is jiffies based, so in the worst case (HZ=1000), the id can
rollover after ~65 seconds of idle time, which should be fine.
We also change the hash used in __ip_select_ident() to not only hash
on daddr, but also saddr and protocol, so that ICMP probes can not be
used to infer information for other protocols.
For IPv6, adds saddr into the hash as well, but not nexthdr.
If I ping the patched target, we can see ID are now hard to predict.
21:57:11.008086 IP (...)
A > target: ICMP echo request, seq 1, length 64
21:57:11.010752 IP (... id 2081 ...)
target > A: ICMP echo reply, seq 1, length 64
21:57:12.013133 IP (...)
A > target: ICMP echo request, seq 2, length 64
21:57:12.015737 IP (... id 3039 ...)
target > A: ICMP echo reply, seq 2, length 64
21:57:13.016580 IP (...)
A > target: ICMP echo request, seq 3, length 64
21:57:13.019251 IP (... id 3437 ...)
target > A: ICMP echo reply, seq 3, length 64
[1] TCP sessions uses a per flow ID generator not changed by this patch.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Jeffrey Knockel <jeffk@cs.unm.edu>
Reported-by: Jedidiah R. Crandall <crandall@cs.unm.edu>
Cc: Willy Tarreau <w@1wt.eu>
Cc: Hannes Frederic Sowa <hannes@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-26 08:58:10 +02:00
|
|
|
|
2015-05-01 10:37:49 -07:00
|
|
|
|
ip: make IP identifiers less predictable
In "Counting Packets Sent Between Arbitrary Internet Hosts", Jeffrey and
Jedidiah describe ways exploiting linux IP identifier generation to
infer whether two machines are exchanging packets.
With commit 73f156a6e8c1 ("inetpeer: get rid of ip_id_count"), we
changed IP id generation, but this does not really prevent this
side-channel technique.
This patch adds a random amount of perturbation so that IP identifiers
for a given destination [1] are no longer monotonically increasing after
an idle period.
Note that prandom_u32_max(1) returns 0, so if generator is used at most
once per jiffy, this patch inserts no hole in the ID suite and do not
increase collision probability.
This is jiffies based, so in the worst case (HZ=1000), the id can
rollover after ~65 seconds of idle time, which should be fine.
We also change the hash used in __ip_select_ident() to not only hash
on daddr, but also saddr and protocol, so that ICMP probes can not be
used to infer information for other protocols.
For IPv6, adds saddr into the hash as well, but not nexthdr.
If I ping the patched target, we can see ID are now hard to predict.
21:57:11.008086 IP (...)
A > target: ICMP echo request, seq 1, length 64
21:57:11.010752 IP (... id 2081 ...)
target > A: ICMP echo reply, seq 1, length 64
21:57:12.013133 IP (...)
A > target: ICMP echo request, seq 2, length 64
21:57:12.015737 IP (... id 3039 ...)
target > A: ICMP echo reply, seq 2, length 64
21:57:13.016580 IP (...)
A > target: ICMP echo request, seq 3, length 64
21:57:13.019251 IP (... id 3437 ...)
target > A: ICMP echo reply, seq 3, length 64
[1] TCP sessions uses a per flow ID generator not changed by this patch.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Jeffrey Knockel <jeffk@cs.unm.edu>
Reported-by: Jedidiah R. Crandall <crandall@cs.unm.edu>
Cc: Willy Tarreau <w@1wt.eu>
Cc: Hannes Frederic Sowa <hannes@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-26 08:58:10 +02:00
|
|
|
|
|
|
|
|
|
2016-09-20 18:06:17 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
ip: make IP identifiers less predictable
In "Counting Packets Sent Between Arbitrary Internet Hosts", Jeffrey and
Jedidiah describe ways exploiting linux IP identifier generation to
infer whether two machines are exchanging packets.
With commit 73f156a6e8c1 ("inetpeer: get rid of ip_id_count"), we
changed IP id generation, but this does not really prevent this
side-channel technique.
This patch adds a random amount of perturbation so that IP identifiers
for a given destination [1] are no longer monotonically increasing after
an idle period.
Note that prandom_u32_max(1) returns 0, so if generator is used at most
once per jiffy, this patch inserts no hole in the ID suite and do not
increase collision probability.
This is jiffies based, so in the worst case (HZ=1000), the id can
rollover after ~65 seconds of idle time, which should be fine.
We also change the hash used in __ip_select_ident() to not only hash
on daddr, but also saddr and protocol, so that ICMP probes can not be
used to infer information for other protocols.
For IPv6, adds saddr into the hash as well, but not nexthdr.
If I ping the patched target, we can see ID are now hard to predict.
21:57:11.008086 IP (...)
A > target: ICMP echo request, seq 1, length 64
21:57:11.010752 IP (... id 2081 ...)
target > A: ICMP echo reply, seq 1, length 64
21:57:12.013133 IP (...)
A > target: ICMP echo request, seq 2, length 64
21:57:12.015737 IP (... id 3039 ...)
target > A: ICMP echo reply, seq 2, length 64
21:57:13.016580 IP (...)
A > target: ICMP echo request, seq 3, length 64
21:57:13.019251 IP (... id 3437 ...)
target > A: ICMP echo reply, seq 3, length 64
[1] TCP sessions uses a per flow ID generator not changed by this patch.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Jeffrey Knockel <jeffk@cs.unm.edu>
Reported-by: Jedidiah R. Crandall <crandall@cs.unm.edu>
Cc: Willy Tarreau <w@1wt.eu>
Cc: Hannes Frederic Sowa <hannes@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-26 08:58:10 +02:00
|
|
|
|
|
|
|
|
|
inetpeer: get rid of ip_id_count
Ideally, we would need to generate IP ID using a per destination IP
generator.
linux kernels used inet_peer cache for this purpose, but this had a huge
cost on servers disabling MTU discovery.
1) each inet_peer struct consumes 192 bytes
2) inetpeer cache uses a binary tree of inet_peer structs,
with a nominal size of ~66000 elements under load.
3) lookups in this tree are hitting a lot of cache lines, as tree depth
is about 20.
4) If server deals with many tcp flows, we have a high probability of
not finding the inet_peer, allocating a fresh one, inserting it in
the tree with same initial ip_id_count, (cf secure_ip_id())
5) We garbage collect inet_peer aggressively.
IP ID generation do not have to be 'perfect'
Goal is trying to avoid duplicates in a short period of time,
so that reassembly units have a chance to complete reassembly of
fragments belonging to one message before receiving other fragments
with a recycled ID.
We simply use an array of generators, and a Jenkin hash using the dst IP
as a key.
ipv6_select_ident() is put back into net/ipv6/ip6_output.c where it
belongs (it is only used from this file)
secure_ip_id() and secure_ipv6_id() no longer are needed.
Rename ip_select_ident_more() to ip_select_ident_segs() to avoid
unnecessary decrement/increment of the number of segments.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-06-02 05:26:03 -07:00
|
|
|
|
2015-03-25 17:07:44 +01:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
inetpeer: get rid of ip_id_count
Ideally, we would need to generate IP ID using a per destination IP
generator.
linux kernels used inet_peer cache for this purpose, but this had a huge
cost on servers disabling MTU discovery.
1) each inet_peer struct consumes 192 bytes
2) inetpeer cache uses a binary tree of inet_peer structs,
with a nominal size of ~66000 elements under load.
3) lookups in this tree are hitting a lot of cache lines, as tree depth
is about 20.
4) If server deals with many tcp flows, we have a high probability of
not finding the inet_peer, allocating a fresh one, inserting it in
the tree with same initial ip_id_count, (cf secure_ip_id())
5) We garbage collect inet_peer aggressively.
IP ID generation do not have to be 'perfect'
Goal is trying to avoid duplicates in a short period of time,
so that reassembly units have a chance to complete reassembly of
fragments belonging to one message before receiving other fragments
with a recycled ID.
We simply use an array of generators, and a Jenkin hash using the dst IP
as a key.
ipv6_select_ident() is put back into net/ipv6/ip6_output.c where it
belongs (it is only used from this file)
secure_ip_id() and secure_ipv6_id() no longer are needed.
Rename ip_select_ident_more() to ip_select_ident_segs() to avoid
unnecessary decrement/increment of the number of segments.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-06-02 05:26:03 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
inetpeer: get rid of ip_id_count
Ideally, we would need to generate IP ID using a per destination IP
generator.
linux kernels used inet_peer cache for this purpose, but this had a huge
cost on servers disabling MTU discovery.
1) each inet_peer struct consumes 192 bytes
2) inetpeer cache uses a binary tree of inet_peer structs,
with a nominal size of ~66000 elements under load.
3) lookups in this tree are hitting a lot of cache lines, as tree depth
is about 20.
4) If server deals with many tcp flows, we have a high probability of
not finding the inet_peer, allocating a fresh one, inserting it in
the tree with same initial ip_id_count, (cf secure_ip_id())
5) We garbage collect inet_peer aggressively.
IP ID generation do not have to be 'perfect'
Goal is trying to avoid duplicates in a short period of time,
so that reassembly units have a chance to complete reassembly of
fragments belonging to one message before receiving other fragments
with a recycled ID.
We simply use an array of generators, and a Jenkin hash using the dst IP
as a key.
ipv6_select_ident() is put back into net/ipv6/ip6_output.c where it
belongs (it is only used from this file)
secure_ip_id() and secure_ipv6_id() no longer are needed.
Rename ip_select_ident_more() to ip_select_ident_segs() to avoid
unnecessary decrement/increment of the number of segments.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-06-02 05:26:03 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
ip: make IP identifiers less predictable
In "Counting Packets Sent Between Arbitrary Internet Hosts", Jeffrey and
Jedidiah describe ways exploiting linux IP identifier generation to
infer whether two machines are exchanging packets.
With commit 73f156a6e8c1 ("inetpeer: get rid of ip_id_count"), we
changed IP id generation, but this does not really prevent this
side-channel technique.
This patch adds a random amount of perturbation so that IP identifiers
for a given destination [1] are no longer monotonically increasing after
an idle period.
Note that prandom_u32_max(1) returns 0, so if generator is used at most
once per jiffy, this patch inserts no hole in the ID suite and do not
increase collision probability.
This is jiffies based, so in the worst case (HZ=1000), the id can
rollover after ~65 seconds of idle time, which should be fine.
We also change the hash used in __ip_select_ident() to not only hash
on daddr, but also saddr and protocol, so that ICMP probes can not be
used to infer information for other protocols.
For IPv6, adds saddr into the hash as well, but not nexthdr.
If I ping the patched target, we can see ID are now hard to predict.
21:57:11.008086 IP (...)
A > target: ICMP echo request, seq 1, length 64
21:57:11.010752 IP (... id 2081 ...)
target > A: ICMP echo reply, seq 1, length 64
21:57:12.013133 IP (...)
A > target: ICMP echo request, seq 2, length 64
21:57:12.015737 IP (... id 3039 ...)
target > A: ICMP echo reply, seq 2, length 64
21:57:13.016580 IP (...)
A > target: ICMP echo request, seq 3, length 64
21:57:13.019251 IP (... id 3437 ...)
target > A: ICMP echo reply, seq 3, length 64
[1] TCP sessions uses a per flow ID generator not changed by this patch.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Jeffrey Knockel <jeffk@cs.unm.edu>
Reported-by: Jedidiah R. Crandall <crandall@cs.unm.edu>
Cc: Willy Tarreau <w@1wt.eu>
Cc: Hannes Frederic Sowa <hannes@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-26 08:58:10 +02:00
|
|
|
|
|
|
|
|
|
2015-03-25 17:07:44 +01:00
|
|
|
|
ip: make IP identifiers less predictable
In "Counting Packets Sent Between Arbitrary Internet Hosts", Jeffrey and
Jedidiah describe ways exploiting linux IP identifier generation to
infer whether two machines are exchanging packets.
With commit 73f156a6e8c1 ("inetpeer: get rid of ip_id_count"), we
changed IP id generation, but this does not really prevent this
side-channel technique.
This patch adds a random amount of perturbation so that IP identifiers
for a given destination [1] are no longer monotonically increasing after
an idle period.
Note that prandom_u32_max(1) returns 0, so if generator is used at most
once per jiffy, this patch inserts no hole in the ID suite and do not
increase collision probability.
This is jiffies based, so in the worst case (HZ=1000), the id can
rollover after ~65 seconds of idle time, which should be fine.
We also change the hash used in __ip_select_ident() to not only hash
on daddr, but also saddr and protocol, so that ICMP probes can not be
used to infer information for other protocols.
For IPv6, adds saddr into the hash as well, but not nexthdr.
If I ping the patched target, we can see ID are now hard to predict.
21:57:11.008086 IP (...)
A > target: ICMP echo request, seq 1, length 64
21:57:11.010752 IP (... id 2081 ...)
target > A: ICMP echo reply, seq 1, length 64
21:57:12.013133 IP (...)
A > target: ICMP echo request, seq 2, length 64
21:57:12.015737 IP (... id 3039 ...)
target > A: ICMP echo reply, seq 2, length 64
21:57:13.016580 IP (...)
A > target: ICMP echo request, seq 3, length 64
21:57:13.019251 IP (... id 3437 ...)
target > A: ICMP echo reply, seq 3, length 64
[1] TCP sessions uses a per flow ID generator not changed by this patch.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Jeffrey Knockel <jeffk@cs.unm.edu>
Reported-by: Jedidiah R. Crandall <crandall@cs.unm.edu>
Cc: Willy Tarreau <w@1wt.eu>
Cc: Hannes Frederic Sowa <hannes@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-26 08:58:10 +02:00
|
|
|
|
inetpeer: get rid of ip_id_count
Ideally, we would need to generate IP ID using a per destination IP
generator.
linux kernels used inet_peer cache for this purpose, but this had a huge
cost on servers disabling MTU discovery.
1) each inet_peer struct consumes 192 bytes
2) inetpeer cache uses a binary tree of inet_peer structs,
with a nominal size of ~66000 elements under load.
3) lookups in this tree are hitting a lot of cache lines, as tree depth
is about 20.
4) If server deals with many tcp flows, we have a high probability of
not finding the inet_peer, allocating a fresh one, inserting it in
the tree with same initial ip_id_count, (cf secure_ip_id())
5) We garbage collect inet_peer aggressively.
IP ID generation do not have to be 'perfect'
Goal is trying to avoid duplicates in a short period of time,
so that reassembly units have a chance to complete reassembly of
fragments belonging to one message before receiving other fragments
with a recycled ID.
We simply use an array of generators, and a Jenkin hash using the dst IP
as a key.
ipv6_select_ident() is put back into net/ipv6/ip6_output.c where it
belongs (it is only used from this file)
secure_ip_id() and secure_ipv6_id() no longer are needed.
Rename ip_select_ident_more() to ip_select_ident_segs() to avoid
unnecessary decrement/increment of the number of segments.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-06-02 05:26:03 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2010-07-09 21:22:10 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2016-11-04 02:23:43 +09:00
|
|
|
|
|
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-11-04 02:23:43 +09:00
|
|
|
|
|
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
|
|
|
|
|
2012-07-17 22:42:13 +02:00
|
|
|
|
|
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
2016-11-30 02:56:47 +09:00
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-11-30 02:56:47 +09:00
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
|
|
|
|
|
2012-07-17 22:42:13 +02:00
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
|
|
|
|
|
2012-07-17 22:42:13 +02:00
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-11-04 02:23:43 +09:00
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-17 22:42:13 +02:00
|
|
|
|
|
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-31 15:02:02 -07:00
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
2013-06-27 10:27:05 +03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-06-17 10:42:30 -07:00
|
|
|
|
2017-06-17 10:42:29 -07:00
|
|
|
|
2013-06-27 10:27:05 +03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-06-17 10:42:30 -07:00
|
|
|
|
2017-06-17 10:42:29 -07:00
|
|
|
|
2013-06-27 10:27:05 +03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-18 10:15:35 +00:00
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-06-27 10:27:05 +03:00
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-17 13:23:08 -07:00
|
|
|
|
|
|
|
|
|
2014-09-04 08:21:31 -07:00
|
|
|
|
2012-07-17 13:23:08 -07:00
|
|
|
|
|
|
|
|
|
2014-09-04 08:21:31 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-17 13:23:08 -07:00
|
|
|
|
|
|
|
|
|
2013-05-27 20:46:31 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-18 10:15:35 +00:00
|
|
|
|
|
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
2012-07-18 10:15:35 +00:00
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
2013-05-27 20:46:31 +00:00
|
|
|
|
2017-11-17 14:27:18 +08:00
|
|
|
|
2013-05-27 20:46:31 +00:00
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
2017-11-17 14:27:18 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
2012-07-31 15:02:02 -07:00
|
|
|
|
2012-07-18 10:15:35 +00:00
|
|
|
|
2014-09-03 22:21:56 -07:00
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
2012-07-18 10:15:35 +00:00
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
2012-07-18 10:15:35 +00:00
|
|
|
|
2014-09-03 22:21:56 -07:00
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-18 10:15:35 +00:00
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-18 10:15:35 +00:00
|
|
|
|
2017-11-17 14:27:18 +08:00
|
|
|
|
|
|
|
|
|
2012-07-18 10:15:35 +00:00
|
|
|
|
|
|
|
|
|
2017-11-17 14:27:06 +08:00
|
|
|
|
2012-07-18 10:15:35 +00:00
|
|
|
|
2017-11-17 14:27:06 +08:00
|
|
|
|
2013-05-27 20:46:31 +00:00
|
|
|
|
2013-06-27 10:27:05 +03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-05-27 20:46:31 +00:00
|
|
|
|
|
|
|
|
|
2012-07-18 10:15:35 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-11-17 14:27:18 +08:00
|
|
|
|
2012-07-18 10:15:35 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-05-27 20:46:31 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-06-27 10:27:05 +03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-05-27 20:46:31 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-18 10:15:35 +00:00
|
|
|
|
|
|
|
|
|
2012-07-31 15:02:02 -07:00
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
|
|
|
|
|
2012-07-17 11:31:28 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2012-07-11 20:55:47 -07:00
|
|
|
|
2012-07-11 20:38:08 -07:00
|
|
|
|
2012-07-11 20:55:47 -07:00
|
|
|
|
|
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
2012-07-11 20:55:47 -07:00
|
|
|
|
2008-02-28 20:50:06 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2012-07-11 20:38:08 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-11 20:55:47 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-03-25 21:47:49 +09:00
|
|
|
|
2009-11-23 10:41:23 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-02-28 20:50:06 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-11-10 11:16:15 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-09-24 17:07:53 -07:00
|
|
|
|
2012-07-11 20:55:47 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-06-23 13:45:37 -04:00
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
|
|
|
|
|
2012-07-18 10:15:35 +00:00
|
|
|
|
2016-02-18 21:21:19 +08:00
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
2012-07-17 11:31:28 -07:00
|
|
|
|
|
|
|
|
|
2012-07-11 20:55:47 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-12 07:40:05 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-11 20:55:47 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-12 07:40:05 -07:00
|
|
|
|
2012-07-11 20:55:47 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-05-28 08:26:49 +02:00
|
|
|
|
2016-12-23 00:33:57 +09:00
|
|
|
|
2013-05-28 08:26:49 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-12-23 00:33:57 +09:00
|
|
|
|
2012-07-17 11:31:28 -07:00
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2008-03-05 18:30:47 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-03-18 23:20:20 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2012-07-10 06:58:42 -07:00
|
|
|
|
|
|
|
|
|
2012-07-17 11:00:09 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-06-02 05:14:27 +00:00
|
|
|
|
2009-08-28 23:52:01 -07:00
|
|
|
|
2011-02-04 15:55:25 -08:00
|
|
|
|
2012-07-10 03:58:16 -07:00
|
|
|
|
2009-08-28 23:52:01 -07:00
|
|
|
|
2015-08-27 16:07:03 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2009-08-28 23:52:01 -07:00
|
|
|
|
2010-06-10 23:31:35 -07:00
|
|
|
|
2009-08-28 23:52:01 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2009-08-28 23:52:01 -07:00
|
|
|
|
|
|
|
|
|
2015-09-29 20:07:13 -07:00
|
|
|
|
2009-08-28 23:52:01 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2012-07-10 03:58:16 -07:00
|
|
|
|
2015-08-27 16:07:03 -07:00
|
|
|
|
2011-02-04 15:55:25 -08:00
|
|
|
|
2012-10-08 11:41:15 +00:00
|
|
|
|
|
|
|
|
|
2011-02-04 15:55:25 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-02-04 15:55:25 -08:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2010-06-10 23:31:35 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2011-02-04 15:55:25 -08:00
|
|
|
|
|
|
|
|
|
2012-07-10 03:58:16 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-02-04 15:55:25 -08:00
|
|
|
|
2006-12-18 00:26:35 -08:00
|
|
|
|
2011-02-04 15:55:25 -08:00
|
|
|
|
|
|
|
|
|
2012-10-08 11:41:15 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-02-04 15:55:25 -08:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2009-08-28 23:52:01 -07:00
|
|
|
|
2012-05-13 21:56:26 +00:00
|
|
|
|
|
|
|
|
|
2012-07-23 16:29:00 -07:00
|
|
|
|
2012-10-08 11:41:15 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2012-07-10 03:58:16 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-06-26 16:27:09 -07:00
|
|
|
|
2009-06-02 05:14:27 +00:00
|
|
|
|
2011-02-04 15:55:25 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2012-06-26 16:27:09 -07:00
|
|
|
|
2011-02-04 15:55:25 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2015-05-22 04:58:12 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-06-26 16:27:09 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-04-27 16:44:35 -07:00
|
|
|
|
2012-06-26 16:27:09 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-04-27 16:44:35 -07:00
|
|
|
|
2012-06-26 16:27:09 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-06-10 23:31:35 -07:00
|
|
|
|
2011-07-01 09:43:07 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-04-27 16:44:35 -07:00
|
|
|
|
2011-07-01 09:43:07 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2015-08-27 16:07:03 -07:00
|
|
|
|
2015-09-29 20:07:13 -07:00
|
|
|
|
2011-02-04 15:55:25 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-10 03:58:16 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2011-02-04 15:55:25 -08:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-02-09 23:24:47 +09:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2012-10-07 22:47:25 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2012-10-07 22:47:25 +00:00
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
2011-02-09 20:42:07 -08:00
|
|
|
|
2013-01-16 20:58:10 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-04-28 11:43:15 +08:00
|
|
|
|
2015-01-29 16:09:03 +08:00
|
|
|
|
|
|
|
|
|
2012-07-10 06:58:42 -07:00
|
|
|
|
|
|
|
|
|
2011-06-08 06:07:07 +00:00
|
|
|
|
2013-05-27 20:46:32 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-08-28 12:33:07 +00:00
|
|
|
|
2015-06-23 13:45:37 -04:00
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
|
|
|
|
|
2012-07-18 10:15:35 +00:00
|
|
|
|
|
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
2012-08-28 12:33:07 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-10-07 22:47:25 +00:00
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
|
|
|
|
|
2012-06-14 22:21:46 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
2012-06-14 22:21:46 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-05-13 10:17:34 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-11-04 02:23:43 +09:00
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
2012-06-14 22:21:46 -07:00
|
|
|
|
|
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
2012-06-14 22:21:46 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-01-21 01:59:11 +00:00
|
|
|
|
2012-06-14 22:21:46 -07:00
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-06-14 22:21:46 -07:00
|
|
|
|
2016-11-04 02:23:43 +09:00
|
|
|
|
2014-05-13 10:17:34 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-06-14 22:21:46 -07:00
|
|
|
|
2013-01-21 01:59:11 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-06-30 01:26:23 -07:00
|
|
|
|
2013-01-22 00:01:28 +00:00
|
|
|
|
2016-11-04 02:23:43 +09:00
|
|
|
|
2013-01-21 01:59:11 +00:00
|
|
|
|
|
|
|
|
|
2013-11-05 02:24:17 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-06-30 01:26:23 -07:00
|
|
|
|
2013-01-21 01:59:11 +00:00
|
|
|
|
2014-06-30 01:26:23 -07:00
|
|
|
|
2013-01-21 01:59:11 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-11-04 02:23:43 +09:00
|
|
|
|
2013-01-21 01:59:11 +00:00
|
|
|
|
2014-06-30 01:26:23 -07:00
|
|
|
|
2015-04-03 09:17:26 +01:00
|
|
|
|
2013-01-21 01:59:11 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-01-22 00:01:28 +00:00
|
|
|
|
|
|
|
|
|
2013-01-21 01:59:11 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-06-30 01:26:23 -07:00
|
|
|
|
2013-01-22 00:01:28 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-01-21 01:59:11 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-01-22 00:01:28 +00:00
|
|
|
|
2013-01-21 01:59:11 +00:00
|
|
|
|
|
|
|
|
|
2013-01-22 00:01:28 +00:00
|
|
|
|
2014-06-30 01:26:23 -07:00
|
|
|
|
2013-01-21 01:59:11 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-06-30 01:26:23 -07:00
|
|
|
|
2013-01-21 01:59:11 +00:00
|
|
|
|
2012-06-14 22:21:46 -07:00
|
|
|
|
2011-02-09 22:00:16 -08:00
|
|
|
|
2012-07-11 21:25:45 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
2012-07-11 21:25:45 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-11-04 02:23:43 +09:00
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
2012-07-11 21:25:45 -07:00
|
|
|
|
|
|
|
|
|
2012-07-17 11:31:28 -07:00
|
|
|
|
2012-07-11 21:25:45 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-11-04 02:23:43 +09:00
|
|
|
|
2012-07-11 21:25:45 -07:00
|
|
|
|
2016-11-04 02:23:43 +09:00
|
|
|
|
|
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
2012-07-17 11:31:28 -07:00
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
|
|
|
|
|
2012-07-11 21:25:45 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-12-01 13:38:59 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-17 11:31:28 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-05-27 20:46:31 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-17 11:31:28 -07:00
|
|
|
|
2013-05-27 20:46:31 +00:00
|
|
|
|
2011-12-01 13:38:59 -05:00
|
|
|
|
2010-03-18 23:20:20 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-06-02 05:14:27 +00:00
|
|
|
|
2012-07-10 06:58:42 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2015-10-07 16:48:47 -05:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2012-05-15 14:11:54 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2011-05-21 07:16:42 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-05-13 17:29:41 -04:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2006-09-26 21:27:54 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2010-11-11 17:07:48 -08:00
|
|
|
|
2011-05-13 18:01:21 -04:00
|
|
|
|
2010-10-05 10:41:36 +00:00
|
|
|
|
2011-05-13 17:29:41 -04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-07-23 02:00:41 +00:00
|
|
|
|
2011-05-13 17:29:41 -04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-03-04 21:47:09 -08:00
|
|
|
|
2010-10-05 10:41:36 +00:00
|
|
|
|
2015-06-23 13:45:37 -04:00
|
|
|
|
2011-03-24 17:42:21 -07:00
|
|
|
|
2010-10-05 10:41:36 +00:00
|
|
|
|
2012-07-13 05:03:45 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-10-05 10:41:36 +00:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-01-14 13:36:42 +01:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2010-06-10 23:31:35 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-12-13 12:52:14 -08:00
|
|
|
|
|
|
|
|
|
2017-04-12 12:34:03 +08:00
|
|
|
|
2017-10-18 17:02:03 -07:00
|
|
|
|
2017-04-12 12:34:03 +08:00
|
|
|
|
2010-12-13 12:52:14 -08:00
|
|
|
|
2017-04-12 12:34:03 +08:00
|
|
|
|
2010-12-13 12:52:14 -08:00
|
|
|
|
|
|
|
|
|
2011-11-23 02:12:51 +00:00
|
|
|
|
2010-12-14 13:01:14 -08:00
|
|
|
|
2011-11-23 02:14:50 +00:00
|
|
|
|
2012-07-10 06:58:42 -07:00
|
|
|
|
|
|
|
|
|
2012-08-27 06:30:01 +00:00
|
|
|
|
2012-07-10 06:58:42 -07:00
|
|
|
|
2011-11-23 02:13:31 +00:00
|
|
|
|
2013-01-16 20:55:01 +00:00
|
|
|
|
2011-11-23 02:13:31 +00:00
|
|
|
|
|
|
|
|
|
2017-08-16 11:09:12 -07:00
|
|
|
|
2010-12-14 13:01:14 -08:00
|
|
|
|
|
|
|
|
|
2012-10-08 11:41:18 +00:00
|
|
|
|
2010-12-14 13:01:14 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-08-24 20:10:43 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-12-14 13:01:14 -08:00
|
|
|
|
|
|
|
|
|
2012-07-17 12:20:47 -07:00
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
2014-09-03 22:21:56 -07:00
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-17 12:20:47 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-17 13:23:08 -07:00
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-17 12:20:47 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
2012-07-31 15:06:50 -07:00
|
|
|
|
2017-06-17 10:42:42 -07:00
|
|
|
|
2012-07-17 12:20:47 -07:00
|
|
|
|
2012-07-31 15:06:50 -07:00
|
|
|
|
|
|
|
|
|
2012-07-31 15:02:02 -07:00
|
|
|
|
2012-07-18 10:15:35 +00:00
|
|
|
|
2012-07-31 15:02:02 -07:00
|
|
|
|
2013-06-27 10:27:05 +03:00
|
|
|
|
|
|
|
|
|
2013-05-27 20:46:33 +00:00
|
|
|
|
2013-06-27 10:27:05 +03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-05-27 20:46:33 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-10-17 21:17:44 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-06-27 10:27:05 +03:00
|
|
|
|
|
|
|
|
|
2012-10-17 21:17:44 +00:00
|
|
|
|
2013-05-27 20:46:31 +00:00
|
|
|
|
|
|
|
|
|
2012-10-08 11:41:18 +00:00
|
|
|
|
2012-07-17 12:20:47 -07:00
|
|
|
|
2017-06-17 10:42:42 -07:00
|
|
|
|
2017-06-17 10:42:29 -07:00
|
|
|
|
2013-06-27 10:27:05 +03:00
|
|
|
|
2017-06-17 10:42:29 -07:00
|
|
|
|
2017-06-17 10:42:30 -07:00
|
|
|
|
2017-06-17 10:42:29 -07:00
|
|
|
|
|
|
|
|
|
2013-06-27 10:27:05 +03:00
|
|
|
|
|
|
|
|
|
2012-07-31 15:02:02 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-31 15:06:50 -07:00
|
|
|
|
|
|
|
|
|
2012-07-31 01:08:23 +00:00
|
|
|
|
|
|
|
|
|
2012-07-31 15:06:50 -07:00
|
|
|
|
2012-07-17 12:20:47 -07:00
|
|
|
|
2012-07-31 05:45:30 +00:00
|
|
|
|
2012-07-31 15:06:50 -07:00
|
|
|
|
2012-07-17 12:20:47 -07:00
|
|
|
|
2012-07-31 05:45:30 +00:00
|
|
|
|
2012-07-31 01:08:23 +00:00
|
|
|
|
2012-07-31 05:45:30 +00:00
|
|
|
|
2014-08-17 12:30:35 -05:00
|
|
|
|
2012-07-31 05:45:30 +00:00
|
|
|
|
2012-07-17 12:20:47 -07:00
|
|
|
|
|
|
|
|
|
2017-06-17 10:42:29 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-17 12:20:47 -07:00
|
|
|
|
|
|
|
|
|
2017-06-17 10:42:29 -07:00
|
|
|
|
2017-06-17 10:42:30 -07:00
|
|
|
|
2017-06-17 10:42:29 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-31 15:06:50 -07:00
|
|
|
|
2017-06-17 10:42:29 -07:00
|
|
|
|
2012-07-31 15:06:50 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-01-14 15:17:06 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-31 15:06:50 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-01-14 15:17:06 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-31 15:06:50 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-05-25 14:27:35 -07:00
|
|
|
|
2012-07-31 15:06:50 -07:00
|
|
|
|
|
|
|
|
|
2017-08-18 12:08:07 -07:00
|
|
|
|
2017-05-25 14:27:35 -07:00
|
|
|
|
|
|
|
|
|
2012-08-24 05:40:47 +00:00
|
|
|
|
2015-01-14 15:17:06 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-31 15:06:50 -07:00
|
|
|
|
2015-01-14 15:17:06 -08:00
|
|
|
|
2012-07-31 15:06:50 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-01-14 15:17:06 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-31 15:06:50 -07:00
|
|
|
|
2015-01-14 15:17:06 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-31 15:06:50 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-01-14 15:17:06 -08:00
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-25 05:11:23 +00:00
|
|
|
|
2012-07-17 12:58:50 -07:00
|
|
|
|
2012-07-25 05:11:23 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-17 12:58:50 -07:00
|
|
|
|
|
|
|
|
|
2012-07-17 12:20:47 -07:00
|
|
|
|
2011-03-04 21:47:09 -08:00
|
|
|
|
2012-07-17 12:20:47 -07:00
|
|
|
|
2017-06-17 10:42:42 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2012-07-31 15:06:50 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
|
|
|
|
|
2012-10-08 11:41:18 +00:00
|
|
|
|
2012-07-17 04:19:00 -07:00
|
|
|
|
2012-10-08 11:41:18 +00:00
|
|
|
|
|
|
|
|
|
2017-05-25 14:27:35 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-08-18 12:08:07 -07:00
|
|
|
|
2017-05-25 14:27:35 -07:00
|
|
|
|
2011-01-14 13:36:42 +01:00
|
|
|
|
2012-07-17 12:20:47 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2015-08-20 13:56:25 +02:00
|
|
|
|
2012-07-31 15:02:02 -07:00
|
|
|
|
2017-06-17 10:42:42 -07:00
|
|
|
|
|
|
|
|
|
2012-07-31 15:06:50 -07:00
|
|
|
|
2012-10-08 11:41:18 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-31 15:06:50 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2011-01-14 13:36:42 +01:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2012-07-13 08:21:29 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-04-07 11:10:06 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-02-17 15:42:37 -08:00
|
|
|
|
2015-09-02 13:58:34 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-06-17 10:42:42 -07:00
|
|
|
|
2015-09-02 13:58:34 -07:00
|
|
|
|
2017-06-17 10:42:41 -07:00
|
|
|
|
2015-09-02 13:58:34 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-09-02 13:58:35 -07:00
|
|
|
|
2015-09-02 13:58:34 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-02-17 15:42:37 -08:00
|
|
|
|
2016-04-07 11:10:06 -07:00
|
|
|
|
2011-02-17 15:42:37 -08:00
|
|
|
|
2010-06-02 19:21:31 +00:00
|
|
|
|
2017-09-28 15:51:37 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2010-06-02 12:05:27 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2015-04-03 09:17:26 +01:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2008-01-21 03:18:08 -08:00
|
|
|
|
2012-06-12 00:44:01 +00:00
|
|
|
|
2017-09-28 15:51:37 +02:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2015-09-28 11:10:38 -07:00
|
|
|
|
2017-09-28 15:51:37 +02:00
|
|
|
|
2012-06-12 00:44:01 +00:00
|
|
|
|
2007-12-16 13:45:43 -08:00
|
|
|
|
|
|
|
|
|
2017-09-28 15:51:37 +02:00
|
|
|
|
2010-06-02 12:05:27 +00:00
|
|
|
|
2012-06-28 18:54:02 -07:00
|
|
|
|
2017-09-28 15:51:37 +02:00
|
|
|
|
2010-06-02 12:05:27 +00:00
|
|
|
|
2017-09-28 15:51:37 +02:00
|
|
|
|
2010-06-02 12:05:27 +00:00
|
|
|
|
2017-09-28 15:51:37 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-09-02 13:58:34 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-17 12:20:47 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2017-09-28 15:51:37 +02:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2011-01-14 13:36:42 +01:00
|
|
|
|
2010-06-10 23:31:35 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2011-04-28 14:31:47 -07:00
|
|
|
|
2012-07-17 14:44:26 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2007-12-16 13:45:43 -08:00
|
|
|
|
2010-06-10 23:31:35 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-17 11:00:09 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2006-09-26 21:25:20 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-03-11 18:36:11 +00:00
|
|
|
|
2008-10-31 00:53:57 -07:00
|
|
|
|
2007-03-19 15:33:04 -07:00
|
|
|
|
2012-03-11 18:36:11 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-02-18 21:21:19 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-11-30 17:10:09 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-06-03 04:13:21 +00:00
|
|
|
|
2008-04-10 01:52:09 -07:00
|
|
|
|
2011-02-16 21:44:24 -08:00
|
|
|
|
2008-04-10 01:52:09 -07:00
|
|
|
|
2012-07-26 11:14:38 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2013-06-27 10:27:05 +03:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-17 12:58:50 -07:00
|
|
|
|
2014-05-22 16:36:55 +08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2010-06-03 04:13:21 +00:00
|
|
|
|
2015-04-03 09:17:26 +01:00
|
|
|
|
2012-05-13 21:56:26 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-04-07 04:51:50 +00:00
|
|
|
|
2012-06-28 18:54:02 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-02-09 23:24:47 +09:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-02-09 23:24:47 +09:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-10-08 11:41:15 +00:00
|
|
|
|
|
|
|
|
|
2015-01-23 12:01:26 +01:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2015-01-23 12:01:26 +01:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-01-05 05:50:47 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2010-01-05 05:50:47 +00:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-06-27 10:27:05 +03:00
|
|
|
|
2012-10-08 11:41:15 +00:00
|
|
|
|
2016-02-18 21:21:19 +08:00
|
|
|
|
2013-06-27 10:27:05 +03:00
|
|
|
|
2016-02-18 21:21:19 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-06-27 10:27:05 +03:00
|
|
|
|
2016-02-18 21:21:19 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-10-08 11:41:15 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-17 12:58:50 -07:00
|
|
|
|
|
|
|
|
|
2012-07-17 12:20:47 -07:00
|
|
|
|
2015-09-02 13:58:34 -07:00
|
|
|
|
2011-04-28 14:13:38 -07:00
|
|
|
|
2012-07-17 12:58:50 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-17 14:44:26 -07:00
|
|
|
|
2015-09-02 13:58:35 -07:00
|
|
|
|
|
|
|
|
|
2014-02-17 15:23:43 +08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2010-06-10 23:31:35 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2017-06-17 10:42:42 -07:00
|
|
|
|
|
|
|
|
|
2016-11-30 17:10:09 +01:00
|
|
|
|
2012-07-26 11:14:38 +00:00
|
|
|
|
2012-07-17 12:58:50 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-02-09 23:24:47 +09:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2015-09-30 10:12:22 +02:00
|
|
|
|
|
|
|
|
|
2017-03-16 15:28:00 +02:00
|
|
|
|
2015-09-30 10:12:22 +02:00
|
|
|
|
2017-03-16 15:28:00 +02:00
|
|
|
|
|
|
|
|
|
2015-09-30 10:12:22 +02:00
|
|
|
|
|
|
|
|
|
2017-03-16 15:28:00 +02:00
|
|
|
|
2015-09-30 10:12:22 +02:00
|
|
|
|
|
|
|
|
|
2017-03-16 15:28:00 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-09-30 10:12:22 +02:00
|
|
|
|
|
|
|
|
|
2017-03-16 15:28:00 +02:00
|
|
|
|
2015-09-30 10:12:22 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-03-16 15:28:00 +02:00
|
|
|
|
2015-09-30 10:12:22 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-03-16 15:28:00 +02:00
|
|
|
|
|
|
|
|
|
2015-09-30 10:12:22 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-03-16 15:28:00 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-09-30 10:12:22 +02:00
|
|
|
|
|
|
|
|
|
2017-03-16 15:28:00 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-09-30 10:12:22 +02:00
|
|
|
|
|
|
|
|
|
2008-04-10 01:52:09 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2015-09-30 10:12:21 +02:00
|
|
|
|
2017-03-16 15:28:00 +02:00
|
|
|
|
2015-09-30 10:12:21 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-26 11:14:38 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-10-05 10:41:36 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2006-09-26 21:25:20 -07:00
|
|
|
|
2017-05-25 10:42:34 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2010-06-02 19:21:31 +00:00
|
|
|
|
2015-07-21 10:43:59 +02:00
|
|
|
|
2011-03-11 20:07:33 -05:00
|
|
|
|
2012-04-15 05:58:06 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2012-04-15 05:58:06 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2012-04-15 01:34:41 +00:00
|
|
|
|
2012-07-17 12:58:50 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-08-20 13:56:25 +02:00
|
|
|
|
2015-08-28 20:48:19 +02:00
|
|
|
|
2015-07-21 10:43:59 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-07-21 10:43:56 +02:00
|
|
|
|
|
|
|
|
|
2012-06-12 00:44:01 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2017-05-25 10:42:34 -07:00
|
|
|
|
|
|
|
|
|
2010-10-17 15:11:22 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-12-16 13:45:43 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2012-06-12 00:44:01 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2012-08-03 21:27:25 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-06-12 00:44:01 +00:00
|
|
|
|
2012-08-03 21:27:25 +00:00
|
|
|
|
|
|
|
|
|
2012-06-12 00:44:01 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-03-11 20:07:33 -05:00
|
|
|
|
2016-09-10 12:09:57 -07:00
|
|
|
|
2011-03-11 20:07:33 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-09-29 19:07:07 -07:00
|
|
|
|
2011-03-11 20:07:33 -05:00
|
|
|
|
|
|
|
|
|
2017-02-26 15:50:52 +02:00
|
|
|
|
2017-05-25 10:42:34 -07:00
|
|
|
|
2014-02-14 18:26:22 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2014-02-14 18:26:22 +08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2017-05-25 10:42:34 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2017-05-25 10:42:34 -07:00
|
|
|
|
2011-04-07 04:51:50 +00:00
|
|
|
|
2014-04-15 16:25:35 -07:00
|
|
|
|
2010-06-02 12:05:27 +00:00
|
|
|
|
2015-09-28 11:10:44 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-02-14 18:26:22 +08:00
|
|
|
|
|
|
|
|
|
2012-06-26 16:27:09 -07:00
|
|
|
|
2014-02-14 18:26:22 +08:00
|
|
|
|
2017-05-25 10:42:34 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2017-05-25 10:42:34 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-06-28 04:05:27 -07:00
|
|
|
|
2012-06-28 18:54:02 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2015-09-28 11:10:44 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2017-05-25 10:42:34 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-17 12:58:50 -07:00
|
|
|
|
2017-05-25 10:42:34 -07:00
|
|
|
|
2012-07-23 13:22:20 -07:00
|
|
|
|
2017-05-25 10:42:34 -07:00
|
|
|
|
2012-07-17 12:58:50 -07:00
|
|
|
|
2012-07-26 11:14:38 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-17 12:58:50 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-12-29 15:29:03 -08:00
|
|
|
|
2017-05-25 10:42:34 -07:00
|
|
|
|
2012-07-17 12:58:50 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-06-10 23:31:35 -07:00
|
|
|
|
2011-04-28 14:31:47 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-17 14:44:26 -07:00
|
|
|
|
2017-05-25 10:42:34 -07:00
|
|
|
|
|
|
|
|
|
2015-07-21 10:43:47 +02:00
|
|
|
|
2014-02-17 15:23:43 +08:00
|
|
|
|
2017-05-25 10:42:34 -07:00
|
|
|
|
2010-06-10 23:31:35 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2016-11-30 17:10:09 +01:00
|
|
|
|
2013-11-19 19:12:34 -08:00
|
|
|
|
2017-05-25 10:42:34 -07:00
|
|
|
|
2016-11-30 17:10:09 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-06-17 10:42:42 -07:00
|
|
|
|
2013-11-19 19:12:34 -08:00
|
|
|
|
|
|
|
|
|
2012-07-17 11:00:09 -07:00
|
|
|
|
2011-03-02 14:31:35 -08:00
|
|
|
|
2010-10-05 10:41:36 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-05-25 10:42:34 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-05-13 21:56:26 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2005-06-28 13:06:23 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2010-10-05 10:41:36 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-10-05 10:41:36 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-10-05 10:41:36 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2012-07-26 11:14:38 +00:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2017-05-25 10:42:34 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2017-02-26 17:14:35 +02:00
|
|
|
|
2010-06-02 19:21:31 +00:00
|
|
|
|
2017-05-25 10:42:34 -07:00
|
|
|
|
|
|
|
|
|
2010-06-02 19:21:31 +00:00
|
|
|
|
2017-05-25 10:42:34 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-12-16 13:45:43 -08:00
|
|
|
|
2010-06-02 19:21:31 +00:00
|
|
|
|
2016-10-31 15:54:00 -07:00
|
|
|
|
2017-05-25 10:42:34 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2016-10-31 15:54:00 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2016-10-31 15:54:00 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2016-10-31 15:54:00 -07:00
|
|
|
|
2017-05-25 10:42:34 -07:00
|
|
|
|
2016-10-31 15:54:00 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2017-05-25 10:42:34 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2017-05-25 10:42:34 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2010-10-05 10:41:36 +00:00
|
|
|
|
2011-02-16 21:44:24 -08:00
|
|
|
|
2012-07-01 02:02:56 +00:00
|
|
|
|
2011-12-02 11:39:42 +00:00
|
|
|
|
2011-02-17 15:29:00 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2011-02-16 21:44:24 -08:00
|
|
|
|
2012-07-17 12:20:47 -07:00
|
|
|
|
2011-02-17 15:29:00 -08:00
|
|
|
|
2011-02-16 21:44:24 -08:00
|
|
|
|
2011-02-17 15:29:00 -08:00
|
|
|
|
2012-10-08 11:41:19 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2012-06-12 00:44:01 +00:00
|
|
|
|
|
|
|
|
|
2011-02-17 15:29:00 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2012-06-12 00:44:01 +00:00
|
|
|
|
2016-09-10 12:09:54 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-06-12 00:44:01 +00:00
|
|
|
|
|
|
|
|
|
2011-03-11 20:07:33 -05:00
|
|
|
|
2011-02-16 21:44:24 -08:00
|
|
|
|
2011-03-11 20:07:33 -05:00
|
|
|
|
2011-02-16 21:44:24 -08:00
|
|
|
|
2011-03-11 20:07:33 -05:00
|
|
|
|
2011-02-17 15:29:00 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-11-22 23:04:14 +02:00
|
|
|
|
2011-02-16 21:44:24 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2011-02-16 21:44:24 -08:00
|
|
|
|
|
|
|
|
|
2010-09-29 11:53:50 +00:00
|
|
|
|
2011-04-28 14:48:42 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2012-11-22 23:04:14 +02:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2010-09-29 11:53:50 +00:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2011-02-16 21:44:24 -08:00
|
|
|
|
|
|
|
|
|
2016-04-08 15:21:30 -06:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2012-07-17 12:20:47 -07:00
|
|
|
|
2012-11-22 23:04:14 +02:00
|
|
|
|
|
|
|
|
|
2012-07-31 15:02:02 -07:00
|
|
|
|
2012-10-08 11:41:19 +00:00
|
|
|
|
2012-07-31 05:45:30 +00:00
|
|
|
|
2012-10-08 11:41:19 +00:00
|
|
|
|
2016-02-18 21:21:19 +08:00
|
|
|
|
2013-06-27 10:27:05 +03:00
|
|
|
|
2016-02-18 21:21:19 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-10-08 11:41:19 +00:00
|
|
|
|
|
|
|
|
|
2016-02-18 21:21:19 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-31 15:02:02 -07:00
|
|
|
|
2016-02-18 21:21:19 +08:00
|
|
|
|
|
|
|
|
|
2017-06-17 10:42:31 -07:00
|
|
|
|
2012-07-31 15:02:02 -07:00
|
|
|
|
2012-07-17 12:20:47 -07:00
|
|
|
|
2012-10-08 11:41:19 +00:00
|
|
|
|
|
|
|
|
|
2015-09-02 13:58:34 -07:00
|
|
|
|
2011-04-28 14:13:38 -07:00
|
|
|
|
2012-07-17 12:20:47 -07:00
|
|
|
|
2012-10-08 11:41:19 +00:00
|
|
|
|
2010-10-07 14:48:38 +00:00
|
|
|
|
2011-02-17 15:29:00 -08:00
|
|
|
|
2010-10-07 14:48:38 +00:00
|
|
|
|
2017-08-11 17:02:02 -07:00
|
|
|
|
2015-09-02 13:58:35 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-02-09 23:24:47 +09:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2010-06-10 23:31:35 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-02-16 21:44:24 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2011-04-28 14:48:42 -07:00
|
|
|
|
2010-06-10 23:31:35 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-06-17 10:42:42 -07:00
|
|
|
|
2016-11-30 17:10:09 +01:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2011-02-17 15:29:00 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-05-25 10:42:33 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2011-12-02 11:39:42 +00:00
|
|
|
|
2011-04-28 14:48:42 -07:00
|
|
|
|
2011-02-17 15:29:00 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2012-07-13 08:21:29 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2012-06-11 02:01:56 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2012-08-08 21:53:36 +00:00
|
|
|
|
2011-04-28 14:48:42 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
ipv4: Optimize flow initialization in output route lookup.
We burn a lot of useless cycles, cpu store buffer traffic, and
memory operations memset()'ing the on-stack flow used to perform
output route lookups in __ip_route_output_key().
Only the first half of the flow object members even matter for
output route lookups in this context, specifically:
FIB rules matching cares about:
dst, src, tos, iif, oif, mark
FIB trie lookup cares about:
dst
FIB semantic match cares about:
tos, scope, oif
Therefore only initialize these specific members and elide the
memset entirely.
On Niagara2 this kills about ~300 cycles from the output route
lookup path.
Likely, we can take things further, since all callers of output
route lookups essentially throw away the on-stack flow they use.
So they don't care if we use it as a scratch-pad to compute the
final flow key.
Signed-off-by: David S. Miller <davem@davemloft.net>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
2011-03-04 21:24:47 -08:00
|
|
|
|
2011-02-17 15:37:09 -08:00
|
|
|
|
2017-05-25 10:42:33 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-04-28 14:48:42 -07:00
|
|
|
|
2011-03-02 14:31:35 -08:00
|
|
|
|
2011-04-28 14:48:42 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-01-22 22:04:30 -08:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-04-28 14:48:42 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-10-01 07:28:28 -07:00
|
|
|
|
2011-04-28 14:48:42 -07:00
|
|
|
|
2015-04-03 09:17:26 +01:00
|
|
|
|
2008-10-01 07:28:28 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-04-28 14:48:42 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2008-10-01 07:28:28 -07:00
|
|
|
|
2011-04-28 14:48:42 -07:00
|
|
|
|
2008-10-01 07:28:28 -07:00
|
|
|
|
2011-04-28 14:48:42 -07:00
|
|
|
|
2008-10-01 07:28:28 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-04-28 14:48:42 -07:00
|
|
|
|
|
|
|
|
|
2011-03-02 14:31:35 -08:00
|
|
|
|
2015-04-03 09:17:26 +01:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2005-10-03 14:35:55 -07:00
|
|
|
|
|
|
|
|
|
2010-12-22 04:39:39 +00:00
|
|
|
|
2011-03-02 14:31:35 -08:00
|
|
|
|
2010-12-22 04:39:39 +00:00
|
|
|
|
|
|
|
|
|
2011-04-28 14:48:42 -07:00
|
|
|
|
2015-05-01 16:39:54 +02:00
|
|
|
|
|
|
|
|
|
2011-04-28 14:48:42 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2013-10-04 17:04:48 +02:00
|
|
|
|
2011-04-28 14:48:42 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-04-28 14:48:42 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-01-22 22:06:19 -08:00
|
|
|
|
2012-08-08 21:53:36 +00:00
|
|
|
|
2017-05-25 10:42:33 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-05-25 10:42:33 -07:00
|
|
|
|
2015-09-17 16:01:32 +02:00
|
|
|
|
2017-05-25 10:42:33 -07:00
|
|
|
|
|
|
|
|
|
2016-10-12 13:20:11 -07:00
|
|
|
|
2016-10-31 15:54:00 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-04-28 14:48:42 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-05-25 10:42:33 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2015-09-17 16:01:32 +02:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-05-25 10:42:33 -07:00
|
|
|
|
2011-04-28 14:48:42 -07:00
|
|
|
|
2017-05-25 10:42:33 -07:00
|
|
|
|
|
|
|
|
|
2011-01-03 20:24:20 +00:00
|
|
|
|
2011-04-28 14:48:42 -07:00
|
|
|
|
2011-01-03 20:24:20 +00:00
|
|
|
|
2016-09-10 12:09:54 -07:00
|
|
|
|
|
|
|
|
|
2017-05-25 10:42:33 -07:00
|
|
|
|
2017-04-21 21:34:59 +01:00
|
|
|
|
2017-08-10 13:49:10 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-04-28 14:48:42 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-05-25 10:42:33 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2017-05-25 10:42:33 -07:00
|
|
|
|
2011-04-28 14:48:42 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-05-25 10:42:33 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2011-02-17 15:37:09 -08:00
|
|
|
|
2011-03-02 14:31:35 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2005-08-09 20:12:12 -07:00
|
|
|
|
2010-09-08 14:35:43 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-11-23 02:12:51 +00:00
|
|
|
|
2011-01-31 13:16:00 -08:00
|
|
|
|
2011-11-23 02:13:31 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-01-31 13:16:00 -08:00
|
|
|
|
|
|
|
|
|
2012-07-17 03:29:28 -07:00
|
|
|
|
|
|
|
|
|
2007-05-24 18:17:54 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-17 03:29:28 -07:00
|
|
|
|
|
|
|
|
|
2012-07-12 00:39:24 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-04-24 22:07:32 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-24 18:17:54 -07:00
|
|
|
|
|
|
|
|
|
2010-09-08 14:35:43 -07:00
|
|
|
|
2011-11-23 02:12:51 +00:00
|
|
|
|
2011-02-18 11:39:01 -08:00
|
|
|
|
2007-05-24 18:17:54 -07:00
|
|
|
|
2012-07-12 00:39:24 -07:00
|
|
|
|
2011-04-24 22:07:32 +00:00
|
|
|
|
2011-07-18 00:40:17 -07:00
|
|
|
|
2007-05-24 18:17:54 -07:00
|
|
|
|
|
|
|
|
|
2011-03-01 14:59:04 -08:00
|
|
|
|
2007-05-24 18:17:54 -07:00
|
|
|
|
2011-03-01 14:59:04 -08:00
|
|
|
|
2012-07-19 12:31:33 -07:00
|
|
|
|
2007-05-24 18:17:54 -07:00
|
|
|
|
2017-10-09 08:43:55 +02:00
|
|
|
|
2007-05-24 18:17:54 -07:00
|
|
|
|
2010-06-10 23:31:35 -07:00
|
|
|
|
2007-05-24 18:17:54 -07:00
|
|
|
|
|
|
|
|
|
2007-11-13 21:34:06 -08:00
|
|
|
|
2015-10-07 16:48:47 -05:00
|
|
|
|
2007-05-24 18:17:54 -07:00
|
|
|
|
2017-06-17 10:42:26 -07:00
|
|
|
|
2007-05-24 18:17:54 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-17 14:44:26 -07:00
|
|
|
|
2011-03-04 21:47:09 -08:00
|
|
|
|
2012-07-10 06:58:42 -07:00
|
|
|
|
2007-05-24 18:17:54 -07:00
|
|
|
|
2013-07-30 08:33:53 +08:00
|
|
|
|
2007-05-24 18:17:54 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-10-08 11:41:18 +00:00
|
|
|
|
2007-05-24 18:17:54 -07:00
|
|
|
|
2012-07-31 15:06:50 -07:00
|
|
|
|
2007-05-24 18:17:54 -07:00
|
|
|
|
|
|
|
|
|
2011-03-01 14:59:04 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-24 18:17:54 -07:00
|
|
|
|
|
|
|
|
|
2011-03-12 01:12:47 -05:00
|
|
|
|
2015-09-25 07:39:10 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2011-03-12 01:12:47 -05:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2011-03-02 14:31:35 -08:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2011-05-02 14:37:45 -07:00
|
|
|
|
2014-09-16 10:08:40 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2011-03-02 14:31:35 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2005-08-09 20:12:12 -07:00
|
|
|
|
|
|
|
|
|
2017-05-25 10:42:36 -07:00
|
|
|
|
2015-09-02 13:58:36 -07:00
|
|
|
|
2012-09-07 20:12:54 +00:00
|
|
|
|
2017-05-31 22:53:25 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2017-05-31 22:53:25 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2006-08-17 18:15:17 -07:00
|
|
|
|
2011-10-11 01:12:02 +00:00
|
|
|
|
2012-07-10 07:26:01 -07:00
|
|
|
|
2012-07-20 12:02:08 +03:00
|
|
|
|
2006-08-17 18:15:17 -07:00
|
|
|
|
2017-05-25 10:42:35 -07:00
|
|
|
|
2015-04-03 09:17:26 +01:00
|
|
|
|
2007-01-31 23:16:40 -08:00
|
|
|
|
2006-08-17 18:15:17 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-01 02:02:59 +00:00
|
|
|
|
2017-01-11 15:42:17 -08:00
|
|
|
|
2015-09-02 13:58:36 -07:00
|
|
|
|
2012-04-01 20:39:02 -04:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-01-23 12:01:26 +01:00
|
|
|
|
|
|
|
|
|
2006-08-17 18:15:17 -07:00
|
|
|
|
2015-03-29 16:59:25 +02:00
|
|
|
|
2012-04-01 20:39:02 -04:00
|
|
|
|
2012-07-01 02:02:56 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2015-03-29 16:59:25 +02:00
|
|
|
|
2012-04-01 20:39:02 -04:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2012-04-01 20:39:02 -04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-01-14 13:36:42 +01:00
|
|
|
|
2012-04-01 20:39:02 -04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2012-06-28 04:05:27 -07:00
|
|
|
|
2012-07-01 02:02:59 +00:00
|
|
|
|
2015-03-29 16:59:25 +02:00
|
|
|
|
2012-04-01 20:39:02 -04:00
|
|
|
|
|
|
|
|
|
2012-10-08 11:41:18 +00:00
|
|
|
|
2015-03-29 16:59:25 +02:00
|
|
|
|
2012-04-01 20:39:02 -04:00
|
|
|
|
2006-08-17 18:15:17 -07:00
|
|
|
|
2012-10-08 00:56:54 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-20 12:02:08 +03:00
|
|
|
|
2012-10-08 00:56:54 +00:00
|
|
|
|
2012-07-20 12:02:08 +03:00
|
|
|
|
|
|
|
|
|
2006-08-17 18:15:17 -07:00
|
|
|
|
|
|
|
|
|
2012-07-01 02:03:01 +00:00
|
|
|
|
2012-10-10 08:27:25 +00:00
|
|
|
|
2012-04-01 20:39:02 -04:00
|
|
|
|
2010-07-20 22:03:14 +00:00
|
|
|
|
2016-11-04 02:23:42 +09:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-06-10 23:31:35 -07:00
|
|
|
|
2006-08-17 18:15:17 -07:00
|
|
|
|
2010-11-11 17:07:48 -08:00
|
|
|
|
2012-12-04 01:03:07 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-01-06 17:39:06 -08:00
|
|
|
|
2016-09-25 23:08:31 +02:00
|
|
|
|
2012-12-04 01:03:07 +00:00
|
|
|
|
2017-01-05 19:32:46 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-12-04 01:03:07 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-04-13 18:08:02 +03:00
|
|
|
|
2012-12-04 01:03:07 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2012-07-10 07:26:01 -07:00
|
|
|
|
2006-11-27 09:27:07 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2015-01-16 22:09:00 +01:00
|
|
|
|
|
|
|
|
|
2006-08-17 18:15:17 -07:00
|
|
|
|
|
|
|
|
|
2007-01-31 23:16:40 -08:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2017-04-16 09:48:24 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2008-03-26 02:26:21 +09:00
|
|
|
|
2006-08-17 18:15:44 -07:00
|
|
|
|
|
|
|
|
|
2017-05-25 10:42:36 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2012-07-01 02:02:59 +00:00
|
|
|
|
2006-09-26 21:25:20 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2006-08-17 18:15:44 -07:00
|
|
|
|
2010-07-20 22:03:14 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2015-09-02 13:58:36 -07:00
|
|
|
|
2016-11-04 02:23:42 +09:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2017-04-12 14:34:07 +02:00
|
|
|
|
2017-04-16 09:48:24 -07:00
|
|
|
|
2006-08-17 18:15:44 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2015-04-03 09:17:26 +01:00
|
|
|
|
2006-08-17 18:15:44 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-03-19 15:30:44 -07:00
|
|
|
|
2007-04-10 20:45:18 -07:00
|
|
|
|
2006-04-17 17:27:11 -07:00
|
|
|
|
2015-03-29 16:59:26 +02:00
|
|
|
|
|
|
|
|
|
2006-08-17 18:15:44 -07:00
|
|
|
|
2010-07-20 22:03:14 +00:00
|
|
|
|
2016-11-04 02:23:42 +09:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2017-04-07 14:42:20 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-01 02:02:59 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-11-04 02:23:42 +09:00
|
|
|
|
2012-07-01 02:02:59 +00:00
|
|
|
|
2017-05-25 10:42:36 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2006-08-17 18:15:44 -07:00
|
|
|
|
|
|
|
|
|
2017-05-25 10:42:36 -07:00
|
|
|
|
2015-04-03 09:17:26 +01:00
|
|
|
|
2006-08-17 18:15:44 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2010-07-20 22:03:14 +00:00
|
|
|
|
2017-05-25 10:42:36 -07:00
|
|
|
|
|
|
|
|
|
2006-08-17 18:15:44 -07:00
|
|
|
|
2009-06-02 05:14:27 +00:00
|
|
|
|
2010-06-10 23:31:35 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2018-01-11 18:36:26 +09:00
|
|
|
|
2017-05-25 10:42:36 -07:00
|
|
|
|
2011-03-02 14:31:35 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-08-14 00:52:58 +02:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2006-08-17 18:15:44 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2006-08-17 18:15:44 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-09-02 13:58:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-08-16 12:38:52 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-05-25 10:42:39 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-08-16 12:38:52 -07:00
|
|
|
|
2017-05-25 10:42:39 -07:00
|
|
|
|
2017-05-31 22:53:25 -07:00
|
|
|
|
2017-08-16 12:38:52 -07:00
|
|
|
|
2015-01-18 23:36:08 -05:00
|
|
|
|
2006-08-17 18:15:44 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2017-05-25 10:42:36 -07:00
|
|
|
|
|
|
|
|
|
2012-09-07 20:12:54 +00:00
|
|
|
|
2006-08-17 18:15:44 -07:00
|
|
|
|
2006-08-15 00:30:25 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2006-08-17 18:15:44 -07:00
|
|
|
|
2017-05-25 10:42:36 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2006-08-17 18:15:44 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-09-07 00:45:29 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-02-19 00:43:12 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-06-11 23:04:25 -07:00
|
|
|
|
2009-09-23 15:57:19 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2013-05-27 20:46:33 +00:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2013-05-27 20:46:33 +00:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-02-09 23:24:47 +09:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-06-11 23:04:25 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-11-03 18:21:05 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-11-03 18:21:05 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-02-09 23:24:47 +09:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-11-03 18:21:05 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-11-03 18:21:05 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-11-03 18:21:05 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2011-12-21 15:47:16 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-11-03 18:21:05 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-11-03 18:21:05 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-11-03 18:21:05 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-11-03 18:21:05 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-11-03 18:21:05 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-11-03 18:21:05 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-11-03 18:21:05 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-11-03 18:21:05 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-11-03 18:21:05 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2009-11-05 13:32:03 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2008-07-05 19:02:33 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-11-03 18:21:05 -08:00
|
|
|
|
2008-07-05 19:02:33 -07:00
|
|
|
|
2009-11-05 13:32:03 -08:00
|
|
|
|
2008-07-05 19:02:33 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-11-25 15:14:13 -08:00
|
|
|
|
2008-07-05 19:02:33 -07:00
|
|
|
|
2015-04-03 09:17:26 +01:00
|
|
|
|
2008-07-05 19:02:33 -07:00
|
|
|
|
2012-11-16 03:02:59 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-07-05 19:02:33 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-04-19 13:44:49 +00:00
|
|
|
|
2015-04-03 09:17:26 +01:00
|
|
|
|
2008-07-05 19:02:33 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2010-05-08 01:57:52 -07:00
|
|
|
|
2008-07-05 19:02:59 -07:00
|
|
|
|
2013-07-30 08:33:53 +08:00
|
|
|
|
2013-05-27 20:46:33 +00:00
|
|
|
|
2017-06-07 23:01:20 -04:00
|
|
|
|
2008-07-05 19:02:59 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-05-08 01:57:52 -07:00
|
|
|
|
|
|
|
|
|
2008-07-05 19:02:59 -07:00
|
|
|
|
|
|
|
|
|
2012-06-09 16:27:05 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-06-09 16:32:41 -07:00
|
|
|
|
2012-06-09 16:27:05 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-07-05 19:02:59 -07:00
|
|
|
|
2011-01-14 13:36:42 +01:00
|
|
|
|
2010-02-16 15:20:26 +00:00
|
|
|
|
2011-01-14 13:36:42 +01:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-07-05 14:58:19 -07:00
|
|
|
|
2015-01-14 15:17:06 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
inetpeer: get rid of ip_id_count
Ideally, we would need to generate IP ID using a per destination IP
generator.
linux kernels used inet_peer cache for this purpose, but this had a huge
cost on servers disabling MTU discovery.
1) each inet_peer struct consumes 192 bytes
2) inetpeer cache uses a binary tree of inet_peer structs,
with a nominal size of ~66000 elements under load.
3) lookups in this tree are hitting a lot of cache lines, as tree depth
is about 20.
4) If server deals with many tcp flows, we have a high probability of
not finding the inet_peer, allocating a fresh one, inserting it in
the tree with same initial ip_id_count, (cf secure_ip_id())
5) We garbage collect inet_peer aggressively.
IP ID generation do not have to be 'perfect'
Goal is trying to avoid duplicates in a short period of time,
so that reassembly units have a chance to complete reassembly of
fragments belonging to one message before receiving other fragments
with a recycled ID.
We simply use an array of generators, and a Jenkin hash using the dst IP
as a key.
ipv6_select_ident() is put back into net/ipv6/ip6_output.c where it
belongs (it is only used from this file)
secure_ip_id() and secure_ipv6_id() no longer are needed.
Rename ip_select_ident_more() to ip_select_ident_segs() to avoid
unnecessary decrement/increment of the number of segments.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-06-02 05:26:03 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-05-01 10:37:49 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2015-01-14 15:17:06 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-01-14 13:36:42 +01:00
|
|
|
|
2009-02-25 14:07:33 +01:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2006-08-26 19:25:52 -07:00
|
|
|
|
|
|
|
|
|
2007-07-20 10:11:58 +09:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-05-24 18:17:54 -07:00
|
|
|
|
|
|
|
|
|
2010-10-08 06:37:34 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-07-17 11:00:09 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-02-28 20:51:18 -08:00
|
|
|
|
2012-03-11 18:36:11 +00:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2012-11-13 08:52:24 +01:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2017-08-15 16:34:44 +02:00
|
|
|
|
|
|
|
|
|
2007-03-22 11:55:17 -07:00
|
|
|
|
2008-07-05 19:02:33 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-05-08 01:57:52 -07:00
|
|
|
|
2012-06-09 16:27:05 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-07-30 06:32:52 -04:00
|
|
|
|
2008-07-27 08:59:33 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-04-19 13:32:39 +00:00
|
|
|
|
2008-07-27 08:59:33 +01:00
|
|
|
|
2008-07-30 06:32:52 -04:00
|
|
|
|
