<feed xmlns='http://www.w3.org/2005/Atom'>
<title>linux-stable.git/drivers/infiniband, branch v3.5</title>
<subtitle>Linux kernel stable tree</subtitle>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux-stable.git/'/>
<entry>
<title>IPoIB: fix skb truesize underestimatiom</title>
<updated>2012-07-11T06:33:12+00:00</updated>
<author>
<name>Eric Dumazet</name>
<email>edumazet@google.com</email>
</author>
<published>2012-07-10T10:03:41+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux-stable.git/commit/?id=b28ba72665356438e3a6e3be365c3c3071496840'/>
<id>b28ba72665356438e3a6e3be365c3c3071496840</id>
<content type='text'>
Or Gerlitz reported triggering of WARN_ON_ONCE(delta &lt; len); in
skb_try_coalesce()
This warning tracks drivers that incorrectly set skb-&gt;truesize

IPoIB indeed allocates a full page to store a fragment, but only
accounts in skb-&gt;truesize the used part of the page (frame length)

This patch fixes skb truesize underestimation, and
also fixes a performance issue, because RX skbs have not enough tailroom
to allow IP and TCP stacks to pull their header in skb linear part
without an expensive call to pskb_expand_head()

Signed-off-by: Eric Dumazet &lt;edumazet@google.com&gt;
Reported-by: Or Gerlitz &lt;ogerlitz@mellanox.com&gt;
Cc: Erez Shitrit &lt;erezsh@mellanox.com&gt;
Cc: Shlomo Pongartz &lt;shlomop@mellanox.com&gt;
Cc: Roland Dreier &lt;roland@purestorage.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>
Or Gerlitz reported triggering of WARN_ON_ONCE(delta &lt; len); in
skb_try_coalesce()
This warning tracks drivers that incorrectly set skb-&gt;truesize

IPoIB indeed allocates a full page to store a fragment, but only
accounts in skb-&gt;truesize the used part of the page (frame length)

This patch fixes skb truesize underestimation, and
also fixes a performance issue, because RX skbs have not enough tailroom
to allow IP and TCP stacks to pull their header in skb linear part
without an expensive call to pskb_expand_head()

Signed-off-by: Eric Dumazet &lt;edumazet@google.com&gt;
Reported-by: Or Gerlitz &lt;ogerlitz@mellanox.com&gt;
Cc: Erez Shitrit &lt;erezsh@mellanox.com&gt;
Cc: Shlomo Pongartz &lt;shlomop@mellanox.com&gt;
Cc: Roland Dreier &lt;roland@purestorage.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>Merge branches 'cma' and 'ocrdma' into for-linus</title>
<updated>2012-06-24T11:59:59+00:00</updated>
<author>
<name>Roland Dreier</name>
<email>roland@purestorage.com</email>
</author>
<published>2012-06-24T11:59:59+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux-stable.git/commit/?id=2e51fd3c13e330d9364a211ddcd3e38771eeb4b4'/>
<id>2e51fd3c13e330d9364a211ddcd3e38771eeb4b4</id>
<content type='text'>
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
</pre>
</div>
</content>
</entry>
<entry>
<title>RDMA/cma: QP type check on received REQs should be AND not OR</title>
<updated>2012-06-20T03:04:04+00:00</updated>
<author>
<name>Sean Hefty</name>
<email>sean.hefty@intel.com</email>
</author>
<published>2012-06-14T20:49:09+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux-stable.git/commit/?id=4dd81e895655c59bd19d7a8f03a5de1310f4aeb6'/>
<id>4dd81e895655c59bd19d7a8f03a5de1310f4aeb6</id>
<content type='text'>
Change || check to the intended &amp;&amp; when checking the QP type in a
received connection request against the listening endpoint.

Signed-off-by: Sean Hefty &lt;sean.hefty@intel.com&gt;
Signed-off-by: Roland Dreier &lt;roland@purestorage.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Change || check to the intended &amp;&amp; when checking the QP type in a
received connection request against the listening endpoint.

Signed-off-by: Sean Hefty &lt;sean.hefty@intel.com&gt;
Signed-off-by: Roland Dreier &lt;roland@purestorage.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>RDMA/ocrdma: Fix off by one in ocrdma_query_gid()</title>
<updated>2012-06-14T20:30:41+00:00</updated>
<author>
<name>Dan Carpenter</name>
<email>dan.carpenter@oracle.com</email>
</author>
<published>2012-06-14T18:36:09+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux-stable.git/commit/?id=7b33dc2b050b71de0e202885a26caffbc864d072'/>
<id>7b33dc2b050b71de0e202885a26caffbc864d072</id>
<content type='text'>
The dev-&gt;sgid_tbl[] array is allocated in ocrdma_alloc_resources().
It has OCRDMA_MAX_SGID elements so the test here is off by one.

Signed-off-by: Dan Carpenter &lt;dan.carpenter@oracle.com&gt;
Signed-off-by: Roland Dreier &lt;roland@purestorage.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
The dev-&gt;sgid_tbl[] array is allocated in ocrdma_alloc_resources().
It has OCRDMA_MAX_SGID elements so the test here is off by one.

Signed-off-by: Dan Carpenter &lt;dan.carpenter@oracle.com&gt;
Signed-off-by: Roland Dreier &lt;roland@purestorage.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>RDMA/ocrdma: Fixed RQ error CQE polling</title>
<updated>2012-06-11T16:38:36+00:00</updated>
<author>
<name>Parav Pandit</name>
<email>parav.pandit@emulex.com</email>
</author>
<published>2012-06-11T11:09:20+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux-stable.git/commit/?id=a3698a9b919d2a54e3348be48ab65d102b2f105d'/>
<id>a3698a9b919d2a54e3348be48ab65d102b2f105d</id>
<content type='text'>
Fix RQ/SRQ error CQE polling.  Return error CQE to consumer for error
case which was not returned previously.

Signed-off-by: Parav Pandit &lt;parav.pandit@emulex.com&gt;
Signed-off-by: Roland Dreier &lt;roland@purestorage.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Fix RQ/SRQ error CQE polling.  Return error CQE to consumer for error
case which was not returned previously.

Signed-off-by: Parav Pandit &lt;parav.pandit@emulex.com&gt;
Signed-off-by: Roland Dreier &lt;roland@purestorage.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>RDMA/ocrdma: Correct queue SGE calculation</title>
<updated>2012-06-11T16:38:35+00:00</updated>
<author>
<name>Mahesh Vardhamanaiah</name>
<email>mahesh.vardhamanaiah@emulex.com</email>
</author>
<published>2012-06-08T15:56:11+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux-stable.git/commit/?id=634c5796a5c60964faf9d51892571ffe36ad24d5'/>
<id>634c5796a5c60964faf9d51892571ffe36ad24d5</id>
<content type='text'>
Fix max sge calculation for sq, rq, srq for all hardware types.

Signed-off-by: Mahesh Vardhamanaiah &lt;mahesh.vardhamanaiah@emulex.com&gt;
Signed-off-by: Roland Dreier &lt;roland@purestorage.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Fix max sge calculation for sq, rq, srq for all hardware types.

Signed-off-by: Mahesh Vardhamanaiah &lt;mahesh.vardhamanaiah@emulex.com&gt;
Signed-off-by: Roland Dreier &lt;roland@purestorage.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>RDMA/ocrdma: Correct reported max queue sizes</title>
<updated>2012-06-11T16:38:34+00:00</updated>
<author>
<name>Mahesh Vardhamanaiah</name>
<email>mahesh.vardhamanaiah@emulex.com</email>
</author>
<published>2012-06-08T15:55:52+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux-stable.git/commit/?id=07bb54244e466f1517357f47a498574f97c31e08'/>
<id>07bb54244e466f1517357f47a498574f97c31e08</id>
<content type='text'>
Fix code to read the max wqe and max rqe values from mailbox response.

Signed-off-by: Mahesh Vardhamanaiah &lt;mahesh.vardhamanaiah@emulex.com&gt;
Signed-off-by: Roland Dreier &lt;roland@purestorage.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Fix code to read the max wqe and max rqe values from mailbox response.

Signed-off-by: Mahesh Vardhamanaiah &lt;mahesh.vardhamanaiah@emulex.com&gt;
Signed-off-by: Roland Dreier &lt;roland@purestorage.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>RDMA/ocrdma: Fixed GID table for vlan and events</title>
<updated>2012-06-11T16:38:32+00:00</updated>
<author>
<name>Parav Pandit</name>
<email>parav.pandit@emulex.com</email>
</author>
<published>2012-06-08T15:55:25+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux-stable.git/commit/?id=6ab6827ee99937834cc268298ee4eab1a651569e'/>
<id>6ab6827ee99937834cc268298ee4eab1a651569e</id>
<content type='text'>
1. Fix reporting GID table addition events.
2. Enable vlan based GID entries only when VLAN is enabled at compile
   time (test CONFIG_VLAN_8021Q / CONFIG_VLAN_8021Q_MODULE).

Signed-off-by: Parav Pandit &lt;parav.pandit@emulex.com&gt;
Signed-off-by: Roland Dreier &lt;roland@purestorage.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
1. Fix reporting GID table addition events.
2. Enable vlan based GID entries only when VLAN is enabled at compile
   time (test CONFIG_VLAN_8021Q / CONFIG_VLAN_8021Q_MODULE).

Signed-off-by: Parav Pandit &lt;parav.pandit@emulex.com&gt;
Signed-off-by: Roland Dreier &lt;roland@purestorage.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>Merge branches 'cxgb4', 'mlx4' and 'ocrdma' into for-linus</title>
<updated>2012-06-06T17:08:11+00:00</updated>
<author>
<name>Roland Dreier</name>
<email>roland@purestorage.com</email>
</author>
<published>2012-06-06T17:08:11+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux-stable.git/commit/?id=20952cdd8e79945245be29f8f5ecac5abc99b4ae'/>
<id>20952cdd8e79945245be29f8f5ecac5abc99b4ae</id>
<content type='text'>
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
</pre>
</div>
</content>
</entry>
<entry>
<title>IB/mlx4: Fix max_wqe capacity reported from query device</title>
<updated>2012-06-06T17:08:03+00:00</updated>
<author>
<name>Sagi Grimberg</name>
<email>sagig@mellanox.co.il</email>
</author>
<published>2012-05-24T13:08:08+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux-stable.git/commit/?id=fc2d004419abebcfd740f46c32dd8201ce1b33c9'/>
<id>fc2d004419abebcfd740f46c32dd8201ce1b33c9</id>
<content type='text'>
1. Limit the max number of WQEs per QP reported when querying the
   device, so that ib_create_qp() will not fail for a QP size that the
   device claimed to support due to additional headroom WQEs being
   allocated.

2. Limit qp resources accepted for ib_create_qp() to the limits
   reported in ib_query_device().  In kernel space, make sure that the
   limits returned to the caller following qp creation also lie within
   the reported device limits. For userspace, report as before, and do
   adjustment in libmlx4 (so as not to break ABI).

Signed-off-by: Jack Morgenstein &lt;jackm@dev.mellanox.co.il&gt;
Signed-off-by: Sagi Grimberg &lt;sagig@mellanox.co.il&gt;
Signed-off-by: Or Gerlitz &lt;ogerlitz@mellanox.com&gt;
Signed-off-by: Roland Dreier &lt;roland@purestorage.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
1. Limit the max number of WQEs per QP reported when querying the
   device, so that ib_create_qp() will not fail for a QP size that the
   device claimed to support due to additional headroom WQEs being
   allocated.

2. Limit qp resources accepted for ib_create_qp() to the limits
   reported in ib_query_device().  In kernel space, make sure that the
   limits returned to the caller following qp creation also lie within
   the reported device limits. For userspace, report as before, and do
   adjustment in libmlx4 (so as not to break ABI).

Signed-off-by: Jack Morgenstein &lt;jackm@dev.mellanox.co.il&gt;
Signed-off-by: Sagi Grimberg &lt;sagig@mellanox.co.il&gt;
Signed-off-by: Or Gerlitz &lt;ogerlitz@mellanox.com&gt;
Signed-off-by: Roland Dreier &lt;roland@purestorage.com&gt;
</pre>
</div>
</content>
</entry>
</feed>
