<feed xmlns='http://www.w3.org/2005/Atom'>
<title>linux/drivers/infiniband/ulp/iser, branch v3.2.38</title>
<subtitle>Linux kernel source tree</subtitle>
<id>https://git.amat.us/linux/atom/drivers/infiniband/ulp/iser?h=v3.2.38</id>
<link rel='self' href='https://git.amat.us/linux/atom/drivers/infiniband/ulp/iser?h=v3.2.38'/>
<link rel='alternate' type='text/html' href='https://git.amat.us/linux/'/>
<updated>2012-04-02T16:52:36Z</updated>
<entry>
<title>IB/iser: Post initial receive buffers before sending the final login request</title>
<updated>2012-04-02T16:52:36Z</updated>
<author>
<name>Or Gerlitz</name>
<email>ogerlitz@mellanox.com</email>
</author>
<published>2012-03-05T16:21:44Z</published>
<link rel='alternate' type='text/html' href='https://git.amat.us/linux/commit/?id=9af865fc7d42e347f679405000fc22ecbfbf2653'/>
<id>urn:sha1:9af865fc7d42e347f679405000fc22ecbfbf2653</id>
<content type='text'>
commit 89e984e2c2cd14f77ccb26c47726ac7f13b70ae8 upstream.

An iser target may send iscsi NO-OP PDUs as soon as it marks the iSER
iSCSI session as fully operative.  This means that there is window
where there are no posted receive buffers on the initiator side, so
it's possible for the iSER RC connection to break because of RNR NAK /
retry errors.  To fix this, rely on the flags bits in the login
request to have FFP (0x3) in the lower nibble as a marker for the
final login request, and post an initial chunk of receive buffers
before sending that login request instead of after getting the login
response.

Signed-off-by: Or Gerlitz &lt;ogerlitz@mellanox.com&gt;
Signed-off-by: Roland Dreier &lt;roland@purestorage.com&gt;
Signed-off-by: Greg Kroah-Hartman &lt;gregkh@linuxfoundation.org&gt;

</content>
</entry>
<entry>
<title>Merge branch 'modsplit-Oct31_2011' of git://git.kernel.org/pub/scm/linux/kernel/git/paulg/linux</title>
<updated>2011-11-07T03:44:47Z</updated>
<author>
<name>Linus Torvalds</name>
<email>torvalds@linux-foundation.org</email>
</author>
<published>2011-11-07T03:44:47Z</published>
<link rel='alternate' type='text/html' href='https://git.amat.us/linux/commit/?id=32aaeffbd4a7457bf2f7448b33b5946ff2a960eb'/>
<id>urn:sha1:32aaeffbd4a7457bf2f7448b33b5946ff2a960eb</id>
<content type='text'>
* 'modsplit-Oct31_2011' of git://git.kernel.org/pub/scm/linux/kernel/git/paulg/linux: (230 commits)
  Revert "tracing: Include module.h in define_trace.h"
  irq: don't put module.h into irq.h for tracking irqgen modules.
  bluetooth: macroize two small inlines to avoid module.h
  ip_vs.h: fix implicit use of module_get/module_put from module.h
  nf_conntrack.h: fix up fallout from implicit moduleparam.h presence
  include: replace linux/module.h with "struct module" wherever possible
  include: convert various register fcns to macros to avoid include chaining
  crypto.h: remove unused crypto_tfm_alg_modname() inline
  uwb.h: fix implicit use of asm/page.h for PAGE_SIZE
  pm_runtime.h: explicitly requires notifier.h
  linux/dmaengine.h: fix implicit use of bitmap.h and asm/page.h
  miscdevice.h: fix up implicit use of lists and types
  stop_machine.h: fix implicit use of smp.h for smp_processor_id
  of: fix implicit use of errno.h in include/linux/of.h
  of_platform.h: delete needless include &lt;linux/module.h&gt;
  acpi: remove module.h include from platform/aclinux.h
  miscdevice.h: delete unnecessary inclusion of module.h
  device_cgroup.h: delete needless include &lt;linux/module.h&gt;
  net: sch_generic remove redundant use of &lt;linux/module.h&gt;
  net: inet_timewait_sock doesnt need &lt;linux/module.h&gt;
  ...

Fix up trivial conflicts (other header files, and  removal of the ab3550 mfd driver) in
 - drivers/media/dvb/frontends/dibx000_common.c
 - drivers/media/video/{mt9m111.c,ov6650.c}
 - drivers/mfd/ab3550-core.c
 - include/linux/dmaengine.h
</content>
</entry>
<entry>
<title>IB/iser: DMA unmap TX bufs used for iSCSI/iSER headers</title>
<updated>2011-11-04T16:32:44Z</updated>
<author>
<name>Or Gerlitz</name>
<email>ogerlitz@mellanox.com</email>
</author>
<published>2011-11-03T22:21:27Z</published>
<link rel='alternate' type='text/html' href='https://git.amat.us/linux/commit/?id=52439540ea30396982b69662dd21aede6b336288'/>
<id>urn:sha1:52439540ea30396982b69662dd21aede6b336288</id>
<content type='text'>
The current driver never does DMA unmapping on these buffers.  Fix that
by adding DMA unmapping to the task cleanup callback, and DMA mapping to
the task init function (drop the headers_initialized micro-optimization).

Signed-off-by: Or Gerlitz &lt;ogerlitz@mellanox.com&gt;
Signed-off-by: Roland Dreier &lt;roland@purestorage.com&gt;
</content>
</entry>
<entry>
<title>IB/iser: Use separate buffers for the login request/response</title>
<updated>2011-11-04T16:30:52Z</updated>
<author>
<name>Or Gerlitz</name>
<email>ogerlitz@mellanox.com</email>
</author>
<published>2011-11-03T22:19:46Z</published>
<link rel='alternate' type='text/html' href='https://git.amat.us/linux/commit/?id=2c4ce609347f2a45792c8d9ebb5af11217766cb6'/>
<id>urn:sha1:2c4ce609347f2a45792c8d9ebb5af11217766cb6</id>
<content type='text'>
The driver counted on the transactional nature of iSCSI login/text
flows and used the same buffer for both the request and the response.
We also went further and did DMA mapping only once, with
DMA_FROM_DEVICE, which violates the DMA mapping API.  Fix that by
using different buffers, one for requests and one for responses, and
use the correct DMA mapping direction for each.

Signed-off-by: Or Gerlitz &lt;ogerlitz@mellanox.com&gt;
Signed-off-by: Roland Dreier &lt;roland@purestorage.com&gt;
</content>
</entry>
<entry>
<title>infiniband: Fix up module files that need to include module.h</title>
<updated>2011-10-31T23:31:35Z</updated>
<author>
<name>Paul Gortmaker</name>
<email>paul.gortmaker@windriver.com</email>
</author>
<published>2011-05-27T19:35:46Z</published>
<link rel='alternate' type='text/html' href='https://git.amat.us/linux/commit/?id=e4dd23d753c3cb0d8533d353069e8b2e8a666360'/>
<id>urn:sha1:e4dd23d753c3cb0d8533d353069e8b2e8a666360</id>
<content type='text'>
They had been getting it implicitly via device.h but we can't
rely on that for the future, due to a pending cleanup so fix
it now.

Signed-off-by: Paul Gortmaker &lt;paul.gortmaker@windriver.com&gt;
</content>
</entry>
<entry>
<title>[SCSI] iscsi class: sysfs group is_visible callout for iscsi host attrs</title>
<updated>2011-08-27T14:36:14Z</updated>
<author>
<name>Mike Christie</name>
<email>michaelc@cs.wisc.edu</email>
</author>
<published>2011-07-25T18:48:45Z</published>
<link rel='alternate' type='text/html' href='https://git.amat.us/linux/commit/?id=f27fb2ef7bd88c9c5f67befe4d85e2155aa0e1a8'/>
<id>urn:sha1:f27fb2ef7bd88c9c5f67befe4d85e2155aa0e1a8</id>
<content type='text'>
The iscsi class currently does not support writable sysfs
attrs for LLD sysfs settings. This patch converts the
iscsi class and driver's host attrs to use the attribute
container sysfs group and the sysfs group's is_visible callout
to be able to support readable or writable sysfs attrs.

Signed-off-by: Mike Christie &lt;michaelc@cs.wisc.edu&gt;
Signed-off-by: James Bottomley &lt;JBottomley@Parallels.com&gt;
</content>
</entry>
<entry>
<title>[SCSI] iscsi class: sysfs group is_visible callout for session attrs</title>
<updated>2011-08-27T14:36:06Z</updated>
<author>
<name>Mike Christie</name>
<email>michaelc@cs.wisc.edu</email>
</author>
<published>2011-07-25T18:48:43Z</published>
<link rel='alternate' type='text/html' href='https://git.amat.us/linux/commit/?id=1d063c17298d7cd26cfe350f1e93e1727b4aa53f'/>
<id>urn:sha1:1d063c17298d7cd26cfe350f1e93e1727b4aa53f</id>
<content type='text'>
The iscsi class currently does not support writable sysfs
attrs for LLD sysfs settings. This patch converts the
iscsi class and driver's session attrs to use the attribute
container sysfs group and the sysfs group's is_visible callout
to be able to support readable or writable sysfs attrs.

Signed-off-by: Mike Christie &lt;michaelc@cs.wisc.edu&gt;
Signed-off-by: James Bottomley &lt;JBottomley@Parallels.com&gt;
</content>
</entry>
<entry>
<title>[SCSI] iscsi cls: sysfs group is_visible callout for conn attrs</title>
<updated>2011-08-27T14:36:03Z</updated>
<author>
<name>Mike Christie</name>
<email>michaelc@cs.wisc.edu</email>
</author>
<published>2011-07-25T18:48:42Z</published>
<link rel='alternate' type='text/html' href='https://git.amat.us/linux/commit/?id=3128c6c73cdf3df92c3165bfb785ae50114d18bf'/>
<id>urn:sha1:3128c6c73cdf3df92c3165bfb785ae50114d18bf</id>
<content type='text'>
The iscsi class currently does not support writable sysfs
attrs for LLD sysfs settings. This patch converts the
iscsi class and drivers to use the attribute container
sysfs group and the sysfs group's is_visible callout
to be able to support readable or writable sysfs attrs.

Signed-off-by: Mike Christie &lt;michaelc@cs.wisc.edu&gt;
Signed-off-by: James Bottomley &lt;JBottomley@Parallels.com&gt;
</content>
</entry>
<entry>
<title>IB/iser: Support iSCSI PDU padding</title>
<updated>2011-08-17T16:45:07Z</updated>
<author>
<name>Or Gerlitz</name>
<email>ogerlitz@mellanox.com</email>
</author>
<published>2011-08-01T21:14:09Z</published>
<link rel='alternate' type='text/html' href='https://git.amat.us/linux/commit/?id=200ae1a08bec8f3fedfcfe94c892d9a024db4e46'/>
<id>urn:sha1:200ae1a08bec8f3fedfcfe94c892d9a024db4e46</id>
<content type='text'>
RFC3270 mandates that iSCSI PDUs are padded to the closest integer
number of four byte words.  Fix the iser code to support that on both
the TX/RX flows.

Signed-off-by: Or Gerlitz &lt;ogerlitz@mellanox.co.il&gt;
Signed-off-by: Roland Dreier &lt;roland@purestorage.com&gt;
</content>
</entry>
<entry>
<title>IBiser: Fix wrong mask when sizeof (dma_addr_t) &gt; sizeof (unsigned long)</title>
<updated>2011-08-17T16:40:55Z</updated>
<author>
<name>Or Gerlitz</name>
<email>ogerlitz@mellanox.com</email>
</author>
<published>2011-08-01T21:12:09Z</published>
<link rel='alternate' type='text/html' href='https://git.amat.us/linux/commit/?id=0ace64b85ea7b90e3bffe408b9d7c3364692bfa4'/>
<id>urn:sha1:0ace64b85ea7b90e3bffe408b9d7c3364692bfa4</id>
<content type='text'>
The code that prepares the SG associated with SCSI command for FMR was
buggy for systems with DMA addresses that don't fit in unsigned long,
e.g under the 32-bit based XenServer dom0 sizeof(dma_addr_t) is 8.

Fix that by casting to unsigned long long a masking constant used by
the code. This resolves a crash in iser_sg_to_page_vec on this system.

Signed-off-by: Or Gerlitz &lt;ogerlitz@mellanox.co.il&gt;
Signed-off-by: Roland Dreier &lt;roland@purestorage.com&gt;
</content>
</entry>
</feed>
