<feed xmlns='http://www.w3.org/2005/Atom'>
<title>linux-toradex.git/drivers/net/xen-netback/common.h, branch v4.16</title>
<subtitle>Linux kernel for Apalis and Colibri modules</subtitle>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/'/>
<entry>
<title>net/xen-netback: Convert timers to use timer_setup()</title>
<updated>2017-10-18T11:40:27+00:00</updated>
<author>
<name>Kees Cook</name>
<email>keescook@chromium.org</email>
</author>
<published>2017-10-17T00:29:38+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=cac6a8f9017b532b39ecb9a9b040eadf26895035'/>
<id>cac6a8f9017b532b39ecb9a9b040eadf26895035</id>
<content type='text'>
In preparation for unconditionally passing the struct timer_list pointer to
all timer callbacks, switch to using the new timer_setup() and from_timer()
to pass the timer pointer explicitly.

Cc: Wei Liu &lt;wei.liu2@citrix.com&gt;
Cc: Paul Durrant &lt;paul.durrant@citrix.com&gt;
Cc: xen-devel@lists.xenproject.org
Cc: netdev@vger.kernel.org
Signed-off-by: Kees Cook &lt;keescook@chromium.org&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
In preparation for unconditionally passing the struct timer_list pointer to
all timer callbacks, switch to using the new timer_setup() and from_timer()
to pass the timer pointer explicitly.

Cc: Wei Liu &lt;wei.liu2@citrix.com&gt;
Cc: Paul Durrant &lt;paul.durrant@citrix.com&gt;
Cc: xen-devel@lists.xenproject.org
Cc: netdev@vger.kernel.org
Signed-off-by: Kees Cook &lt;keescook@chromium.org&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>xen-netback: correctly schedule rate-limited queues</title>
<updated>2017-06-22T15:15:42+00:00</updated>
<author>
<name>Wei Liu</name>
<email>wei.liu2@citrix.com</email>
</author>
<published>2017-06-21T09:21:22+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=dfa523ae9f2542bee4cddaea37b3be3e157f6e6b'/>
<id>dfa523ae9f2542bee4cddaea37b3be3e157f6e6b</id>
<content type='text'>
Add a flag to indicate if a queue is rate-limited. Test the flag in
NAPI poll handler and avoid rescheduling the queue if true, otherwise
we risk locking up the host. The rescheduling will be done in the
timer callback function.

Reported-by: Jean-Louis Dupond &lt;jean-louis@dupond.be&gt;
Signed-off-by: Wei Liu &lt;wei.liu2@citrix.com&gt;
Tested-by: Jean-Louis Dupond &lt;jean-louis@dupond.be&gt;
Reviewed-by: Paul Durrant &lt;paul.durrant@citrix.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Add a flag to indicate if a queue is rate-limited. Test the flag in
NAPI poll handler and avoid rescheduling the queue if true, otherwise
we risk locking up the host. The rescheduling will be done in the
timer callback function.

Reported-by: Jean-Louis Dupond &lt;jean-louis@dupond.be&gt;
Signed-off-by: Wei Liu &lt;wei.liu2@citrix.com&gt;
Tested-by: Jean-Louis Dupond &lt;jean-louis@dupond.be&gt;
Reviewed-by: Paul Durrant &lt;paul.durrant@citrix.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>xen-netback: vif counters from int/long to u64</title>
<updated>2017-02-14T02:49:53+00:00</updated>
<author>
<name>Mart van Santen</name>
<email>mart@greenhost.nl</email>
</author>
<published>2017-02-10T12:02:18+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=ebf692f85ff78092cd238166d8d7ec51419f9c02'/>
<id>ebf692f85ff78092cd238166d8d7ec51419f9c02</id>
<content type='text'>
This patch fixes an issue where the type of counters in the queue(s)
and interface are not in sync (queue counters are int, interface
counters are long), causing incorrect reporting of tx/rx values
of the vif interface and unclear counter overflows.
This patch sets both counters to the u64 type.

Signed-off-by: Mart van Santen &lt;mart@greenhost.nl&gt;
Reviewed-by: Paul Durrant &lt;paul.durrant@citrix.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
This patch fixes an issue where the type of counters in the queue(s)
and interface are not in sync (queue counters are int, interface
counters are long), causing incorrect reporting of tx/rx values
of the vif interface and unclear counter overflows.
This patch sets both counters to the u64 type.

Signed-off-by: Mart van Santen &lt;mart@greenhost.nl&gt;
Reviewed-by: Paul Durrant &lt;paul.durrant@citrix.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>xen-netback: (re-)create a debugfs node for hash information</title>
<updated>2016-10-13T13:53:09+00:00</updated>
<author>
<name>Paul Durrant</name>
<email>Paul.Durrant@citrix.com</email>
</author>
<published>2016-10-10T08:30:53+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=a9339b8e138d81b6ee928d0de3372c551cbd3d34'/>
<id>a9339b8e138d81b6ee928d0de3372c551cbd3d34</id>
<content type='text'>
It is useful to be able to see the hash configuration when running tests.
This patch adds a debugfs node for that purpose.

The original version of this patch (commit c0c64c152389) was reverted due
to build failures caused by a conflict with commit 0364a8824c02
("xen-netback: switch to threaded irq for control ring"). This new version
of the patch is nearly identical to the original, the only difference
being that creation of the debugfs node is predicated on 'ctrl_irq' being
non-zero rather then the now non-existent 'ctrl_task'.

Signed-off-by: Paul Durrant &lt;paul.durrant@citrix.com&gt;
Cc: Wei Liu &lt;wei.liu2@citrix.com&gt;
Cc: David S. Miller &lt;davem@davemloft.net&gt;
Acked-by: Wei Liu &lt;wei.liu2@citrix.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
It is useful to be able to see the hash configuration when running tests.
This patch adds a debugfs node for that purpose.

The original version of this patch (commit c0c64c152389) was reverted due
to build failures caused by a conflict with commit 0364a8824c02
("xen-netback: switch to threaded irq for control ring"). This new version
of the patch is nearly identical to the original, the only difference
being that creation of the debugfs node is predicated on 'ctrl_irq' being
non-zero rather then the now non-existent 'ctrl_task'.

Signed-off-by: Paul Durrant &lt;paul.durrant@citrix.com&gt;
Cc: Wei Liu &lt;wei.liu2@citrix.com&gt;
Cc: David S. Miller &lt;davem@davemloft.net&gt;
Acked-by: Wei Liu &lt;wei.liu2@citrix.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>xen-netback: batch copies for multiple to-guest rx packets</title>
<updated>2016-10-07T00:37:36+00:00</updated>
<author>
<name>David Vrabel</name>
<email>david.vrabel@citrix.com</email>
</author>
<published>2016-10-04T09:29:17+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=a37f12298c251a48bc74d4012e07bf0d78175f46'/>
<id>a37f12298c251a48bc74d4012e07bf0d78175f46</id>
<content type='text'>
Instead of flushing the copy ops when an packet is complete, complete
packets when their copy ops are done.  This improves performance by
reducing the number of grant copy hypercalls.

Latency is still limited by the relatively small size of the copy
batch.

Signed-off-by: David Vrabel &lt;david.vrabel@citrix.com&gt;
[re-based]
Signed-off-by: Paul Durrant &lt;paul.durrant@citrix.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Instead of flushing the copy ops when an packet is complete, complete
packets when their copy ops are done.  This improves performance by
reducing the number of grant copy hypercalls.

Latency is still limited by the relatively small size of the copy
batch.

Signed-off-by: David Vrabel &lt;david.vrabel@citrix.com&gt;
[re-based]
Signed-off-by: Paul Durrant &lt;paul.durrant@citrix.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>xen-netback: refactor guest rx</title>
<updated>2016-10-07T00:37:35+00:00</updated>
<author>
<name>David Vrabel</name>
<email>david.vrabel@citrix.com</email>
</author>
<published>2016-10-04T09:29:14+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=eb1723a29b9a75dd787510a39096a68dba6cc200'/>
<id>eb1723a29b9a75dd787510a39096a68dba6cc200</id>
<content type='text'>
Refactor the to-guest (rx) path to:

1. Push responses for completed skbs earlier, reducing latency.

2. Reduce the per-queue memory overhead by greatly reducing the
   maximum number of grant copy ops in each hypercall (from 4352 to
   64).  Each struct xenvif_queue is now only 44 kB instead of 220 kB.

3. Make the code more maintainable.

Signed-off-by: David Vrabel &lt;david.vrabel@citrix.com&gt;
[re-based]
Signed-off-by: Paul Durrant &lt;paul.durrant@citrix.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Refactor the to-guest (rx) path to:

1. Push responses for completed skbs earlier, reducing latency.

2. Reduce the per-queue memory overhead by greatly reducing the
   maximum number of grant copy ops in each hypercall (from 4352 to
   64).  Each struct xenvif_queue is now only 44 kB instead of 220 kB.

3. Make the code more maintainable.

Signed-off-by: David Vrabel &lt;david.vrabel@citrix.com&gt;
[re-based]
Signed-off-by: Paul Durrant &lt;paul.durrant@citrix.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>xen-netback: retire guest rx side prefix GSO feature</title>
<updated>2016-10-07T00:37:35+00:00</updated>
<author>
<name>Paul Durrant</name>
<email>Paul.Durrant@citrix.com</email>
</author>
<published>2016-10-04T09:29:13+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=fedbc8c132bcf836358103195d8b6df6c03d9daf'/>
<id>fedbc8c132bcf836358103195d8b6df6c03d9daf</id>
<content type='text'>
As far as I am aware only very old Windows network frontends make use of
this style of passing GSO packets from backend to frontend. These
frontends can easily be replaced by the freely available Xen Project
Windows PV network frontend, which uses the 'default' mechanism for
passing GSO packets, which is also used by all Linux frontends.

NOTE: Removal of this feature will not cause breakage in old Windows
      frontends. They simply will no longer receive GSO packets - the
      packets instead being fragmented in the backend.

Signed-off-by: Paul Durrant &lt;paul.durrant@citrix.com&gt;
Reviewed-by: David Vrabel &lt;david.vrabel@citrix.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
As far as I am aware only very old Windows network frontends make use of
this style of passing GSO packets from backend to frontend. These
frontends can easily be replaced by the freely available Xen Project
Windows PV network frontend, which uses the 'default' mechanism for
passing GSO packets, which is also used by all Linux frontends.

NOTE: Removal of this feature will not cause breakage in old Windows
      frontends. They simply will no longer receive GSO packets - the
      packets instead being fragmented in the backend.

Signed-off-by: Paul Durrant &lt;paul.durrant@citrix.com&gt;
Reviewed-by: David Vrabel &lt;david.vrabel@citrix.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>Revert "xen-netback: create a debugfs node for hash information"</title>
<updated>2016-09-23T13:09:31+00:00</updated>
<author>
<name>David S. Miller</name>
<email>davem@davemloft.net</email>
</author>
<published>2016-09-23T13:09:31+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=fb2a3d5c7c85cb6e8bc88192be919b4ef8d6e630'/>
<id>fb2a3d5c7c85cb6e8bc88192be919b4ef8d6e630</id>
<content type='text'>
This reverts commit c0c64c152389ad73306b9b0796357210ec6d32ee.

There is no vif-&gt;ctrl_task member, so this change broke
the build.

Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
This reverts commit c0c64c152389ad73306b9b0796357210ec6d32ee.

There is no vif-&gt;ctrl_task member, so this change broke
the build.

Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>xen-netback: switch to threaded irq for control ring</title>
<updated>2016-09-22T12:26:24+00:00</updated>
<author>
<name>Juergen Gross</name>
<email>jgross@suse.com</email>
</author>
<published>2016-09-22T09:06:25+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=0364a8824c020f12e2d5e9fad963685b58f7574e'/>
<id>0364a8824c020f12e2d5e9fad963685b58f7574e</id>
<content type='text'>
Instead of open coding it use the threaded irq mechanism in
xen-netback.

Signed-off-by: Juergen Gross &lt;jgross@suse.com&gt;
Acked-by: Wei Liu &lt;wei.liu2@citrix.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Instead of open coding it use the threaded irq mechanism in
xen-netback.

Signed-off-by: Juergen Gross &lt;jgross@suse.com&gt;
Acked-by: Wei Liu &lt;wei.liu2@citrix.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>xen-netback: create a debugfs node for hash information</title>
<updated>2016-08-19T06:29:09+00:00</updated>
<author>
<name>Paul Durrant</name>
<email>Paul.Durrant@citrix.com</email>
</author>
<published>2016-08-17T15:13:29+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=c0c64c152389ad73306b9b0796357210ec6d32ee'/>
<id>c0c64c152389ad73306b9b0796357210ec6d32ee</id>
<content type='text'>
It is useful to be able to see the hash configuration when running tests.
This patch adds a debugfs node for that purpose.

Signed-off-by: Paul Durrant &lt;paul.durrant@citrix.com&gt;
Cc: Wei Liu &lt;wei.liu2@citrix.com&gt;
Acked-by: Wei Liu &lt;wei.liu2@citrix.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
It is useful to be able to see the hash configuration when running tests.
This patch adds a debugfs node for that purpose.

Signed-off-by: Paul Durrant &lt;paul.durrant@citrix.com&gt;
Cc: Wei Liu &lt;wei.liu2@citrix.com&gt;
Acked-by: Wei Liu &lt;wei.liu2@citrix.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</pre>
</div>
</content>
</entry>
</feed>
