linux.git/net/core/flow.c, branch v2.6.35 Linux kernel source tree flow: delayed deletion of flow cache entries 2010-04-07T10:43:20+00:00 Timo Teräs timo.teras@iki.fi 2010-04-07T00:30:07+00:00 8e4795605d1e1b39113818ad7c147b8a867a1f6a Speed up lookups by freeing flow cache entries later. After virtualizing flow cache entry operations, the flow cache may now end up calling policy or bundle destructor which can be slowish. As gc_list is more effective with double linked list, the flow cache is converted to use common hlist and list macroes where appropriate. Signed-off-by: Timo Teras <timo.teras@iki.fi> Signed-off-by: David S. Miller <davem@davemloft.net> 
Speed up lookups by freeing flow cache entries later. After
virtualizing flow cache entry operations, the flow cache may now
end up calling policy or bundle destructor which can be slowish.

As gc_list is more effective with double linked list, the flow cache
is converted to use common hlist and list macroes where appropriate.

Signed-off-by: Timo Teras <timo.teras@iki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
flow: virtualize flow cache entry methods 2010-04-07T10:43:18+00:00 Timo Teräs timo.teras@iki.fi 2010-04-07T00:30:04+00:00 fe1a5f031e76bd8761a7803d75b95ee96e84a574 This allows to validate the cached object before returning it. It also allows to destruct object properly, if the last reference was held in flow cache. This is also a prepartion for caching bundles in the flow cache. In return for virtualizing the methods, we save on: - not having to regenerate the whole flow cache on policy removal: each flow matching a killed policy gets refreshed as the getter function notices it smartly. - we do not have to call flow_cache_flush from policy gc, since the flow cache now properly deletes the object if it had any references Signed-off-by: Timo Teras <timo.teras@iki.fi> Acked-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net> 
This allows to validate the cached object before returning it.
It also allows to destruct object properly, if the last reference
was held in flow cache. This is also a prepartion for caching
bundles in the flow cache.

In return for virtualizing the methods, we save on:
- not having to regenerate the whole flow cache on policy removal:
  each flow matching a killed policy gets refreshed as the getter
  function notices it smartly.
- we do not have to call flow_cache_flush from policy gc, since the
  flow cache now properly deletes the object if it had any references

Signed-off-by: Timo Teras <timo.teras@iki.fi>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
flow: structurize flow cache 2010-04-02T02:41:36+00:00 Timo Teräs timo.teras@iki.fi 2010-03-31T00:17:06+00:00 d7997fe1f4584da12e9c29fb682c18e9bdc13b73 Group all per-cpu data to one structure instead of having many globals. Also prepare the internals so that we can have multiple instances of the flow cache if needed. Only the kmem_cache is left as a global as all flow caches share the same element size, and benefit from using a common cache. Signed-off-by: Timo Teras <timo.teras@iki.fi> Acked-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net> 
Group all per-cpu data to one structure instead of having many
globals. Also prepare the internals so that we can have multiple
instances of the flow cache if needed.

Only the kmem_cache is left as a global as all flow caches share
the same element size, and benefit from using a common cache.

Signed-off-by: Timo Teras <timo.teras@iki.fi>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
netns xfrm: lookup in netns 2008-11-26T01:35:18+00:00 Alexey Dobriyan adobriyan@gmail.com 2008-11-26T01:35:18+00:00 52479b623d3d41df84c499325b6a8c7915413032 Pass netns to xfrm_lookup()/__xfrm_lookup(). For that pass netns to flow_cache_lookup() and resolver callback. Take it from socket or netdevice. Stub DECnet to init_net. Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
Pass netns to xfrm_lookup()/__xfrm_lookup(). For that pass netns
to flow_cache_lookup() and resolver callback.

Take it from socket or netdevice. Stub DECnet to init_net.

Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
net: mark flow_cache_cpu_prepare() as __init 2008-11-07T07:06:44+00:00 Alexey Dobriyan adobriyan@gmail.com 2008-11-07T07:06:44+00:00 76acfdb9b78acf73023307974f6d38a269e9967a It's called from __init code only. And__devinit in generic networking code is pretty strange :^) Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
It's called from __init code only. And__devinit in generic networking code
is pretty strange :^)

Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
smp_call_function: get rid of the unused nonatomic/retry argument 2008-06-26T09:24:35+00:00 Jens Axboe jens.axboe@oracle.com 2008-06-06T09:18:06+00:00 8691e5a8f691cc2a4fda0651e8d307aaba0e7d68 It's never used and the comments refer to nonatomic and retry interchangably. So get rid of it. Acked-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com> 
It's never used and the comments refer to nonatomic and retry
interchangably. So get rid of it.

Acked-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
net: Remove unnecessary inclusions of asm/semaphore.h 2008-04-19T02:15:50+00:00 Matthew Wilcox matthew@wil.cx 2008-04-19T02:15:50+00:00 5f090dcb4d4fff373ce7165bce4ba5e87534d50a None of these files use any of the functionality promised by asm/semaphore.h. It's possible that they rely on it dragging in some unrelated header file, but I can't build all these files, so we'll have fix any build failures as they come up. Signed-off-by: Matthew Wilcox <willy@linux.intel.com> 
None of these files use any of the functionality promised by
asm/semaphore.h.  It's possible that they rely on it dragging in some
unrelated header file, but I can't build all these files, so we'll have
fix any build failures as they come up.

Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
[IPSEC] flow: reorder "struct flow_cache_entry" and remove SLAB_HWCACHE_ALIGN 2008-02-08T07:30:42+00:00 Eric Dumazet dada1@cosmosbay.com 2008-02-08T07:30:42+00:00 dd5a1843d566911dbb077c4022c4936697495af6 1) We can shrink sizeof(struct flow_cache_entry) by 8 bytes on 64bit arches. 2) No need to align these structures to hardware cache lines, this only waste ram for very litle gain. Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
1) We can shrink sizeof(struct flow_cache_entry) by 8 bytes on 64bit arches.
2) No need to align these structures to hardware cache lines, this only waste 
   ram for very litle gain.

Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
[IPSEC] flow: Remove an unnecessary ____cacheline_aligned 2008-02-08T02:03:18+00:00 Eric Dumazet dada1@cosmosbay.com 2008-02-08T02:03:18+00:00 5f58a5c8725b48f3e32851f9748527c8d1ff71b2 We use a percpu variable named flow_hash_info, which holds 12 bytes. It is currently marked as ____cacheline_aligned, which makes linker skip space to properly align this variable. Before : c065cc90 D per_cpu__softnet_data c065cd00 d per_cpu__flow_tables <Here, hole of 124 bytes> c065cd80 d per_cpu__flow_hash_info <Here, hole of 116 bytes> c065ce00 d per_cpu__flow_flush_tasklets c065ce14 d per_cpu__rt_cache_stat This alignement is quite unproductive, and removing it reduces the size of percpu data (by 240 bytes on my x86 machine), and improves performance (flow_tables & flow_hash_info can share a single cache line) After patch : c065cc04 D per_cpu__softnet_data c065cc4c d per_cpu__flow_tables c065cc50 d per_cpu__flow_hash_info c065cc5c d per_cpu__flow_flush_tasklets c065cc70 d per_cpu__rt_cache_stat Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
We use a percpu variable named flow_hash_info, which holds 12 bytes.

It is currently marked as ____cacheline_aligned, which makes linker
skip space to properly align this variable.

Before :
c065cc90 D per_cpu__softnet_data
c065cd00 d per_cpu__flow_tables
<Here, hole of 124 bytes>
c065cd80 d per_cpu__flow_hash_info
<Here, hole of 116 bytes>
c065ce00 d per_cpu__flow_flush_tasklets
c065ce14 d per_cpu__rt_cache_stat


This alignement is quite unproductive, and removing it reduces the
size of percpu data (by 240 bytes on my x86 machine), and improves
performance (flow_tables & flow_hash_info can share a single cache
line)

After patch :
c065cc04 D per_cpu__softnet_data
c065cc4c d per_cpu__flow_tables
c065cc50 d per_cpu__flow_hash_info
c065cc5c d per_cpu__flow_flush_tasklets
c065cc70 d per_cpu__rt_cache_stat

Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
[NET]: Convert init_timer into setup_timer 2008-01-28T22:53:35+00:00 Pavel Emelyanov xemul@openvz.org 2008-01-24T05:20:07+00:00 b24b8a247ff65c01b252025926fe564209fae4fc Many-many code in the kernel initialized the timer->function and timer->data together with calling init_timer(timer). There is already a helper for this. Use it for networking code. The patch is HUGE, but makes the code 130 lines shorter (98 insertions(+), 228 deletions(-)). Signed-off-by: Pavel Emelyanov <xemul@openvz.org> Acked-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
Many-many code in the kernel initialized the timer->function
and  timer->data together with calling init_timer(timer). There
is already a helper for this. Use it for networking code.

The patch is HUGE, but makes the code 130 lines shorter
(98 insertions(+), 228 deletions(-)).

Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Acked-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>