<feed xmlns='http://www.w3.org/2005/Atom'>
<title>kernel/linux.git/drivers/net/loopback.c, branch linux-2.6.22.y</title>
<subtitle>Linux kernel stable tree (mirror)</subtitle>
<id>https://git.radix-linux.su/kernel/linux.git/atom?h=linux-2.6.22.y</id>
<link rel='self' href='https://git.radix-linux.su/kernel/linux.git/atom?h=linux-2.6.22.y'/>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/'/>
<updated>2007-04-26T05:28:52+00:00</updated>
<entry>
<title>[NET]: loopback driver can use loopback_dev integrated net_device_stats</title>
<updated>2007-04-26T05:28:52+00:00</updated>
<author>
<name>Eric Dumazet</name>
<email>dada1@cosmosbay.com</email>
</author>
<published>2007-04-10T20:25:40+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=33036807b32d5ed1f4fdfe2d5e6bab2bb260b9f7'/>
<id>urn:sha1:33036807b32d5ed1f4fdfe2d5e6bab2bb260b9f7</id>
<content type='text'>
Rusty added a new 'stats' field to struct net_device.

loopback driver can use it instead of declaring another struct
net_device_stats This saves some memory.

Signed-off-by: Eric Dumazet &lt;dada1@cosmosbay.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</content>
</entry>
<entry>
<title>[SK_BUFF]: Introduce skb_copy_to_linear_data{_offset}</title>
<updated>2007-04-26T05:28:29+00:00</updated>
<author>
<name>Arnaldo Carvalho de Melo</name>
<email>acme@ghostprotocols.net</email>
</author>
<published>2007-03-31T14:55:19+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=27d7ff46a3498d3debc6ba68fb8014c702b81170'/>
<id>urn:sha1:27d7ff46a3498d3debc6ba68fb8014c702b81170</id>
<content type='text'>
To clearly state the intent of copying to linear sk_buffs, _offset being a
overly long variant but interesting for the sake of saving some bytes.

Signed-off-by: Arnaldo Carvalho de Melo &lt;acme@ghostprotocols.net&gt;
</content>
</entry>
<entry>
<title>[SK_BUFF]: Introduce ip_hdr(), remove skb-&gt;nh.iph</title>
<updated>2007-04-26T05:25:10+00:00</updated>
<author>
<name>Arnaldo Carvalho de Melo</name>
<email>acme@redhat.com</email>
</author>
<published>2007-04-21T05:47:35+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=eddc9ec53be2ecdbf4efe0efd4a83052594f0ac0'/>
<id>urn:sha1:eddc9ec53be2ecdbf4efe0efd4a83052594f0ac0</id>
<content type='text'>
Signed-off-by: Arnaldo Carvalho de Melo &lt;acme@redhat.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</content>
</entry>
<entry>
<title>[SK_BUFF]: Introduce skb_network_header()</title>
<updated>2007-04-26T05:24:59+00:00</updated>
<author>
<name>Arnaldo Carvalho de Melo</name>
<email>acme@redhat.com</email>
</author>
<published>2007-04-11T03:50:43+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=d56f90a7c96da5187f0cdf07ee7434fe6aa78bbc'/>
<id>urn:sha1:d56f90a7c96da5187f0cdf07ee7434fe6aa78bbc</id>
<content type='text'>
For the places where we need a pointer to the network header, it is still legal
to touch skb-&gt;nh.raw directly if just adding to, subtracting from or setting it
to another layer header.

Signed-off-by: Arnaldo Carvalho de Melo &lt;acme@redhat.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</content>
</entry>
<entry>
<title>[SK_BUFF]: Introduce skb_reset_network_header(skb)</title>
<updated>2007-04-26T05:24:46+00:00</updated>
<author>
<name>Arnaldo Carvalho de Melo</name>
<email>acme@redhat.com</email>
</author>
<published>2007-04-11T03:45:18+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=c1d2bbe1cd6c7bbdc6d532cefebb66c7efb789ce'/>
<id>urn:sha1:c1d2bbe1cd6c7bbdc6d532cefebb66c7efb789ce</id>
<content type='text'>
For the common, open coded 'skb-&gt;nh.raw = skb-&gt;data' operation, so that we can
later turn skb-&gt;nh.raw into a offset, reducing the size of struct sk_buff in
64bit land while possibly keeping it as a pointer on 32bit.

This one touches just the most simple case, next will handle the slightly more
"complex" cases.

Signed-off-by: Arnaldo Carvalho de Melo &lt;acme@redhat.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</content>
</entry>
<entry>
<title>[SK_BUFF]: Introduce skb_set_mac_header()</title>
<updated>2007-04-26T05:24:37+00:00</updated>
<author>
<name>Arnaldo Carvalho de Melo</name>
<email>acme@redhat.com</email>
</author>
<published>2007-03-10T15:30:58+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=48d49d0ccdaa9caff4636ef9c3410973d28131b5'/>
<id>urn:sha1:48d49d0ccdaa9caff4636ef9c3410973d28131b5</id>
<content type='text'>
For the cases where we want to set skb-&gt;mac.raw to an offset from skb-&gt;data.

Simple cases first, the memmove ones and specially pktgen will be left for later.

Signed-off-by: Arnaldo Carvalho de Melo &lt;acme@redhat.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</content>
</entry>
<entry>
<title>[ETH]: Make eth_type_trans set skb-&gt;dev like the other *_type_trans</title>
<updated>2007-04-26T05:24:30+00:00</updated>
<author>
<name>Arnaldo Carvalho de Melo</name>
<email>acme@redhat.com</email>
</author>
<published>2007-04-26T00:40:23+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=4c13eb6657fe9ef7b4dc8f1a405c902e9e5234e0'/>
<id>urn:sha1:4c13eb6657fe9ef7b4dc8f1a405c902e9e5234e0</id>
<content type='text'>
One less thing for drivers writers to worry about.

Signed-off-by: Arnaldo Carvalho de Melo &lt;acme@redhat.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</content>
</entry>
<entry>
<title>[NET] drivers/net/loopback.c: convert to module_init()</title>
<updated>2007-01-04T02:38:10+00:00</updated>
<author>
<name>Adrian Bunk</name>
<email>bunk@stusta.de</email>
</author>
<published>2007-01-02T08:35:48+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=60903f2c6616939afd0335b49697beeb7219657e'/>
<id>urn:sha1:60903f2c6616939afd0335b49697beeb7219657e</id>
<content type='text'>
This patch converts drivers/net/loopback.c to using module_init().

Signed-off-by: Adrian Bunk &lt;bunk@stusta.de&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</content>
</entry>
<entry>
<title>[NET]: Can use __get_cpu_var() instead of per_cpu() in loopback driver.</title>
<updated>2006-10-20T07:32:41+00:00</updated>
<author>
<name>Eric Dumazet</name>
<email>dada1@cosmosbay.com</email>
</author>
<published>2006-10-20T07:32:41+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=58f539740b1ccfc5ef4e509ec2efe82621b546e3'/>
<id>urn:sha1:58f539740b1ccfc5ef4e509ec2efe82621b546e3</id>
<content type='text'>
As BHs are off in loopback_xmit(), preemption cannot occurs, so we can
use __get_cpu_var() instead of per_cpu() (and avoid a
preempt_enable()/preempt_disable() pair)

Signed-off-by: Eric Dumazet &lt;dada1@cosmosbay.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</content>
</entry>
<entry>
<title>[NET]: reduce per cpu ram used for loopback stats</title>
<updated>2006-10-19T03:51:57+00:00</updated>
<author>
<name>Eric Dumazet</name>
<email>dada1@cosmosbay.com</email>
</author>
<published>2006-10-19T03:51:57+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=5175c3786c244f8b689854db24c9e79b1c6a084f'/>
<id>urn:sha1:5175c3786c244f8b689854db24c9e79b1c6a084f</id>
<content type='text'>
We dont need a full struct net_device_stats (currently 23 long : 184 bytes on 
x86_64) per possible CPU, but only two counters : bytes and packets

We save few CPU cycles too in loopback_xmit() not updating 4 fields, but 2. 

Signed-off-by: Eric Dumazet &lt;dada1@cosmosbay.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</content>
</entry>
</feed>
