Commits · 04128f233f2b344f3438cde09723e9946463a573 · Kirill Smelkov / linux

15 Oct, 2007 40 commits

[INET]: Collect common frag sysctl variables together · 04128f23

Pavel Emelyanov authored Oct 15, 2007

Some sysctl variables are used to tune the frag queues
management and it will be useful to work with them in
a common way in the future, so move them into one
structure, moreover they are the same for all the frag
management codes.

I don't place them in the existing inet_frags object,
introduced in the previous patch for two reasons:

 1. to keep them in the __read_mostly section;
 2. not to export the whole inet_frags objects outside.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

04128f23

[INET]: Collect frag queues management objects together · 7eb95156

Pavel Emelyanov authored Oct 15, 2007

There are some objects that are common in all the places
which are used to keep track of frag queues, they are:

 * hash table
 * LRU list
 * rw lock
 * rnd number for hash function
 * the number of queues
 * the amount of memory occupied by queues
 * secret timer

Move all this stuff into one structure (struct inet_frags)
to make it possible use them uniformly in the future. Like
with the previous patch this mostly consists of hunks like

-    write_lock(&ipfrag_lock);
+    write_lock(&ip4_frags.lock);

To address the issue with exporting the number of queues and
the amount of memory occupied by queues outside the .c file
they are declared in, I introduce a couple of helpers.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

7eb95156

[INET]: Move common fields from frag_queues in one place. · 5ab11c98

Pavel Emelyanov authored Oct 15, 2007

Introduce the struct inet_frag_queue in include/net/inet_frag.h
file and place there all the common fields from three structs:

 * struct ipq in ipv4/ip_fragment.c
 * struct nf_ct_frag6_queue in nf_conntrack_reasm.c
 * struct frag_queue in ipv6/reassembly.c

After this, replace these fields on appropriate structures with
this structure instance and fix the users to use correct names
i.e. hunks like

-    atomic_dec(&fq->refcnt);
+    atomic_dec(&fq->q.refcnt);

(these occupy most of the patch)
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

5ab11c98

[TG3]: Fix performance regression on 5705. · 114342f2

Michael Chan authored Oct 15, 2007

A performance regression was introduced by the following commit:

    commit ee6a99b5
    Author: Michael Chan <mchan@broadcom.com>
    Date:   Wed Jul 18 21:49:10 2007 -0700

    [TG3]: Fix msi issue with kexec/kdump.

In making that change, the PCI latency timer and cache line size
registers were not restored after chip reset.  On the 5705, the
latency timer gets reset to 0 during chip reset and this causes
very poor performance.

Update version to 3.84.
Signed-off-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

114342f2

[ISDN]: Remove local copy of device name to make sure renames work. · faca94ff
Karsten Keil authored Oct 15, 2007
```
Signed-off-by: Karsten Keil <kkeil@suse.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
```
faca94ff
[TCP]: high_seq parameter removed (all callers use tp->high_seq) · f885c5b0
Ilpo Järvinen authored Oct 15, 2007
```
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
```
f885c5b0

[IPV6]: Uninline netfilter okfns · ad643a79

Patrick McHardy authored Oct 15, 2007

Uninline netfilter okfns for those cases where gcc can generate tail-calls.

Before:
   text    data     bss     dec     hex filename
8994153 1016524  524652 10535329         a0c1a1 vmlinux

After:
   text    data     bss     dec     hex filename
8992761 1016524  524652 10533937         a0bc31 vmlinux
-------------------------------------------------------
  -1392

All cases have been verified to generate tail-calls with and without netfilter.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

ad643a79

[BRIDGE]: Remove SKB share checks in br_nf_pre_routing(). · 9c2842bd
Patrick McHardy authored Oct 15, 2007
```
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
```
9c2842bd

[IPV4]: Uninline netfilter okfns · 861d0486

Patrick McHardy authored Oct 15, 2007

Now that we don't pass double skb pointers to nf_hook_slow anymore, gcc
can generate tail calls for some of the netfilter hook okfn invocations,
so there is no need to inline the functions anymore. This caused huge
code bloat since we ended up with one inlined version and one out-of-line
version since we pass the address to nf_hook_slow.

Before:
   text    data     bss     dec     hex filename
8997385 1016524  524652 10538561         a0ce41 vmlinux

After:
   text    data     bss     dec     hex filename
8994009 1016524  524652 10535185         a0c111 vmlinux
-------------------------------------------------------
  -3376

All cases have been verified to generate tail-calls with and without
netfilter. The okfns in ipmr and xfrm4_input still remain inline because
gcc can't generate tail-calls for them.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

861d0486

[NET]: Avoid copying TCP packets unnecessarily · a030847e

Herbert Xu authored Oct 15, 2007

TCP packets all have writable heads, that is, even though it's cloned, it is
writable up to the end of the TCP header. This patch makes skb_checksum_help
aware of this fact by using skb_clone_writable and avoiding a copy for TCP.

I've also modified the BUG_ON tests to be unsigned. The only case where this
makes a difference is if csum_start points to a location before skb->data.
Since skb->data should always include the header where the checksum field
is (and all currently callers adhere to that), this change is safe and may
uncover bugs later.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>

a030847e

[NET]: Fix csum_start update in pskb_expand_head · 172a863f

Herbert Xu authored Oct 15, 2007

I got confused by the dual nature of the off variable in the
function pskb_expand_head.  The csum_start offset should use
nhead instead of off which can change depending on whether we
are using offsets or pointers.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>

172a863f

[NIU]: getting rid of __ucmpdi2 in niu.o · a9d41192

Al Viro authored Oct 15, 2007

	By the time we get to that switch by PHY type, we have 8bit
value.  No need to keep it in u64 when u8 would do.
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>

a9d41192

[NETLINK]: Don't leak 'listeners' in netlink_kernel_create() · f937f1f4

Jesper Juhl authored Oct 15, 2007

The Coverity checker spotted that we'll leak the storage allocated
to 'listeners' in netlink_kernel_create() when the
  if (!nl_table[unit].registered)
check is false.

This patch avoids the leak.
Signed-off-by: Jesper Juhl <jesper.juhl@gmail.com>
Acked-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

f937f1f4

[IPV6] __inet6_csk_dst_store(): fix check-after-use · 1dff92e0

Adrian Bunk authored Oct 15, 2007

The Coverity checker spotted that we have already oops'ed if "dst" was
NULL.

Since "dst" being NULL doesn't seem to be possible at this point this
patch removes the NULL check.
Signed-off-by: Adrian Bunk <bunk@stusta.de>
Acked-by: Masahide NAKAMURA <nakam@linux-ipv6.org>
Acked-by: Noriaki TAKAMIYA <takamiya@po.ntts.co.jp>
Signed-off-by: David S. Miller <davem@davemloft.net>

1dff92e0

[NIU]: Fix write past end of array in niu_pci_probe_sprom(). · e6a5fdf5
David S. Miller authored Oct 15, 2007
```
Noticed by Coverity checker and reported by Adrian Bunk.
Signed-off-by: David S. Miller <davem@davemloft.net>
```
e6a5fdf5

[IPV6]: Avoid skb_copy/pskb_copy/skb_realloc_headroom on input · 65c88466

Herbert Xu authored Oct 15, 2007

This patch replaces unnecessary uses of skb_copy by pskb_expand_head
on the IPv6 input path.

This allows us to remove the double pointers later.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>

65c88466

[IPV6]: Make ipv6_frag_rcv return the same packet · f61944ef

Herbert Xu authored Oct 15, 2007

This patch implements the same change taht was done to ip_defrag.  It
makes ipv6_frag_rcv return the last packet received of a train of fragments
rather than the head of that sequence.

This allows us to get rid of the sk_buff ** argument later.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>

f61944ef

[NETFILTER]: Replace sk_buff ** with sk_buff * · 3db05fea

Herbert Xu authored Oct 15, 2007

With all the users of the double pointers removed, this patch mops up by
finally replacing all occurances of sk_buff ** in the netfilter API by
sk_buff *.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>

3db05fea

[NETFILTER]: Avoid skb_copy/pskb_copy/skb_realloc_headroom · 2ca7b0ac