<feed xmlns='http://www.w3.org/2005/Atom'>
<title>linux.git/drivers/infiniband/ulp, branch v2.6.14</title>
<subtitle>Linux kernel source tree</subtitle>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/'/>
<entry>
<title>[IPoIB] Rename IPoIB's path_lookup() to avoid name clashes</title>
<updated>2005-09-29T02:56:57+00:00</updated>
<author>
<name>Roland Dreier</name>
<email>rolandd@cisco.com</email>
</author>
<published>2005-09-29T02:56:57+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=d70ed6075f15bdbb0548d162394bf10332769c88'/>
<id>d70ed6075f15bdbb0548d162394bf10332769c88</id>
<content type='text'>
Rename IPoIB driver's path_lookup() to ipoib_path_lookup() to avoid a
clashes with the kernel global path_lookup().  We don't hit this with
the current kernel source, but some external patches seem to trigger
this, and it's cleaner to avoid clashing with global names anyway.

Signed-off-by: Roland Dreier &lt;rolandd@cisco.com&gt;
refs/heads/for-linus
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Rename IPoIB driver's path_lookup() to ipoib_path_lookup() to avoid a
clashes with the kernel global path_lookup().  We don't hit this with
the current kernel source, but some external patches seem to trigger
this, and it's cleaner to avoid clashing with global names anyway.

Signed-off-by: Roland Dreier &lt;rolandd@cisco.com&gt;
refs/heads/for-linus
</pre>
</div>
</content>
</entry>
<entry>
<title>[PATCH] IPoIB: Don't flush workqueue from within workqueue</title>
<updated>2005-09-20T17:52:04+00:00</updated>
<author>
<name>Roland Dreier</name>
<email>rolandd@cisco.com</email>
</author>
<published>2005-09-20T17:52:04+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=8d2cae0651502028bf64844508ab18528bbd65c2'/>
<id>8d2cae0651502028bf64844508ab18528bbd65c2</id>
<content type='text'>
ipoib_mcast_restart_task() is always called from within the
single-threaded IPoIB workqueue, so flushing the workqueue from within
the function can lead to a recursion overflow.  But since we're
running in a single-threaded workqueue, we're already synchronized
against other items in the workqueue, so just get rid of the flush in
ipoib_mcast_restart_task().

Signed-off-by: Roland Dreier &lt;rolandd@cisco.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
ipoib_mcast_restart_task() is always called from within the
single-threaded IPoIB workqueue, so flushing the workqueue from within
the function can lead to a recursion overflow.  But since we're
running in a single-threaded workqueue, we're already synchronized
against other items in the workqueue, so just get rid of the flush in
ipoib_mcast_restart_task().

Signed-off-by: Roland Dreier &lt;rolandd@cisco.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>[PATCH] IPoIB: Fix SA client retransmission strategy</title>
<updated>2005-09-19T05:02:38+00:00</updated>
<author>
<name>Hal Rosenstock</name>
<email>halr@voltaire.com</email>
</author>
<published>2005-09-18T20:47:53+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=ce5b65cc9626feac0d4ffb96f798407e50c45575'/>
<id>ce5b65cc9626feac0d4ffb96f798407e50c45575</id>
<content type='text'>
We got a little mixed up with what the backoff member holds in the
IPoIB multicast group structure: sometimes it was used as a number of
seconds, and sometimes it was used as a number of jiffies.  Fix the
code so that backoff is always in seconds.

Signed-off-by: Hal Rosenstock &lt;halr@voltaire.com&gt;
Signed-off-by: Roland Dreier &lt;rolandd@cisco.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
We got a little mixed up with what the backoff member holds in the
IPoIB multicast group structure: sometimes it was used as a number of
seconds, and sometimes it was used as a number of jiffies.  Fix the
code so that backoff is always in seconds.

Signed-off-by: Hal Rosenstock &lt;halr@voltaire.com&gt;
Signed-off-by: Roland Dreier &lt;rolandd@cisco.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>[PATCH] IPoIB: fix module removal race</title>
<updated>2005-09-19T05:02:37+00:00</updated>
<author>
<name>Michael S. Tsirkin</name>
<email>mst@mellanox.co.il</email>
</author>
<published>2005-09-12T16:52:28+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=51574e0398a2d93cbf7f26e36b673cd919062268'/>
<id>51574e0398a2d93cbf7f26e36b673cd919062268</id>
<content type='text'>
Since ipoib uses queue_delayed_work to run flush task on port state events,
it must flush scheduled work after unregistering the event handler.

Signed-off-by: Michael S. Tsirkin &lt;mst@mellanox.co.il&gt;
Signed-off-by: Roland Dreier &lt;rolandd@cisco.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Since ipoib uses queue_delayed_work to run flush task on port state events,
it must flush scheduled work after unregistering the event handler.

Signed-off-by: Michael S. Tsirkin &lt;mst@mellanox.co.il&gt;
Signed-off-by: Roland Dreier &lt;rolandd@cisco.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>[PATCH] IPoIB: fix memory leak</title>
<updated>2005-09-07T16:48:52+00:00</updated>
<author>
<name>Michael S. Tsirkin</name>
<email>mst@mellanox.co.il</email>
</author>
<published>2005-09-01T16:19:02+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=06c56e44f3e32a859420ecac97996cc6f12827bb'/>
<id>06c56e44f3e32a859420ecac97996cc6f12827bb</id>
<content type='text'>
Fix IPoIB memory leak on device removal.

Signed-off-by: Michael S. Tsirkin &lt;mst@mellanox.co.il&gt;
Signed-off-by: Roland Dreier &lt;rolandd@cisco.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Fix IPoIB memory leak on device removal.

Signed-off-by: Michael S. Tsirkin &lt;mst@mellanox.co.il&gt;
Signed-off-by: Roland Dreier &lt;rolandd@cisco.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>[PATCH] IB: move include files to include/rdma</title>
<updated>2005-08-27T03:37:38+00:00</updated>
<author>
<name>Roland Dreier</name>
<email>roland@eddore.topspincom.com</email>
</author>
<published>2005-08-25T20:40:04+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=a4d61e84804f3b14cc35c5e2af768a07c0f64ef6'/>
<id>a4d61e84804f3b14cc35c5e2af768a07c0f64ef6</id>
<content type='text'>
Move the InfiniBand headers from drivers/infiniband/include to include/rdma.
This allows InfiniBand-using code to live elsewhere, and lets us remove the
ugly EXTRA_CFLAGS include path from the InfiniBand Makefiles.

Signed-off-by: Roland Dreier &lt;rolandd@cisco.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Move the InfiniBand headers from drivers/infiniband/include to include/rdma.
This allows InfiniBand-using code to live elsewhere, and lets us remove the
ugly EXTRA_CFLAGS include path from the InfiniBand Makefiles.

Signed-off-by: Roland Dreier &lt;rolandd@cisco.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>[PATCH] IPoIB: Fix device removal race</title>
<updated>2005-08-27T03:37:38+00:00</updated>
<author>
<name>Michael S. Tsirkin</name>
<email>mst@mellanox.co.il</email>
</author>
<published>2005-08-24T21:41:51+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=1ad62a19f177e61d4dde111ba35fb4badd0c2106'/>
<id>1ad62a19f177e61d4dde111ba35fb4badd0c2106</id>
<content type='text'>
Currently we may have work scheduled in default kernel workqueue when
the device is going down.  The device could get freed before this
workqueue gets serviced.  I am actually seeing this causing system
hangs.

The following patch fixes this by using ipoib_workqueue which gets
flushed when the device is going down.

Signed-off-by: Michael S. Tsirkin &lt;mst@mellanox.co.il&gt;
Signed-off-by: Roland Dreier &lt;rolandd@cisco.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Currently we may have work scheduled in default kernel workqueue when
the device is going down.  The device could get freed before this
workqueue gets serviced.  I am actually seeing this causing system
hangs.

The following patch fixes this by using ipoib_workqueue which gets
flushed when the device is going down.

Signed-off-by: Michael S. Tsirkin &lt;mst@mellanox.co.il&gt;
Signed-off-by: Roland Dreier &lt;rolandd@cisco.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>[PATCH] IPoIB: Set full membership bit in P_Keys</title>
<updated>2005-08-27T03:37:37+00:00</updated>
<author>
<name>Roland Dreier</name>
<email>roland@eddore.topspincom.com</email>
</author>
<published>2005-08-19T19:03:17+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=4ce059378c04b40c2e9f658b1c6a2e9078b85c7c'/>
<id>4ce059378c04b40c2e9f658b1c6a2e9078b85c7c</id>
<content type='text'>
Always make sure that the full membership bit is set in the P_Keys
that IPoIB uses.  This makes sure that all hosts join the correct
multicast groups so that hosts that are partial partition members
can talk to the rest of the network.

Signed-off-by: Roland Dreier &lt;rolandd@cisco.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Always make sure that the full membership bit is set in the P_Keys
that IPoIB uses.  This makes sure that all hosts join the correct
multicast groups so that hosts that are partial partition members
can talk to the rest of the network.

Signed-off-by: Roland Dreier &lt;rolandd@cisco.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>[PATCH] IB: Remove unnecessary includes of &lt;linux/version.h&gt;</title>
<updated>2005-08-27T03:37:36+00:00</updated>
<author>
<name>Olaf Hering</name>
<email>olh@suse.de</email>
</author>
<published>2005-08-15T21:29:03+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=2aeba9a03b0d249fc710b9939fc089ce53d8cd30'/>
<id>2aeba9a03b0d249fc710b9939fc089ce53d8cd30</id>
<content type='text'>
changing CONFIG_LOCALVERSION rebuilds too much, for no appearent reason.
Remove unneeded includes of &lt;linux/version.h&gt;.

Signed-off-by: Olaf Hering &lt;olh@suse.de&gt;
Signed-off-by: Roland Dreier &lt;rolandd@cisco.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
changing CONFIG_LOCALVERSION rebuilds too much, for no appearent reason.
Remove unneeded includes of &lt;linux/version.h&gt;.

Signed-off-by: Olaf Hering &lt;olh@suse.de&gt;
Signed-off-by: Roland Dreier &lt;rolandd@cisco.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>[PATCH] IB: sparse endianness cleanup</title>
<updated>2005-08-27T03:37:35+00:00</updated>
<author>
<name>Sean Hefty</name>
<email>sean.hefty@intel.com</email>
</author>
<published>2005-08-14T04:05:57+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=97f52eb438be7caebe026421545619d8a0c1398a'/>
<id>97f52eb438be7caebe026421545619d8a0c1398a</id>
<content type='text'>
Fix sparse warnings.  Use __be* where appropriate.

Signed-off-by: Sean Hefty &lt;sean.hefty@intel.com&gt;
Signed-off-by: Roland Dreier &lt;rolandd@cisco.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Fix sparse warnings.  Use __be* where appropriate.

Signed-off-by: Sean Hefty &lt;sean.hefty@intel.com&gt;
Signed-off-by: Roland Dreier &lt;rolandd@cisco.com&gt;
</pre>
</div>
</content>
</entry>
</feed>
