<feed xmlns='http://www.w3.org/2005/Atom'>
<title>BMC/Intel-BMC/linux.git/drivers/block/xen-blkback/blkback.c, branch dev</title>
<subtitle>Intel OpenBMC Linux kernel source tree (mirror)</subtitle>
<id>https://git.radix-linux.su/BMC/Intel-BMC/linux.git/atom?h=dev</id>
<link rel='self' href='https://git.radix-linux.su/BMC/Intel-BMC/linux.git/atom?h=dev'/>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/BMC/Intel-BMC/linux.git/'/>
<updated>2015-07-27T17:58:41+00:00</updated>
<entry>
<title>Merge branch 'stable/for-jens-4.2' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen into for-linus</title>
<updated>2015-07-27T17:58:41+00:00</updated>
<author>
<name>Jens Axboe</name>
<email>axboe@fb.com</email>
</author>
<published>2015-07-27T17:58:41+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/BMC/Intel-BMC/linux.git/commit/?id=e162b219ae6a64be353f254bd4ba1c9627c67749'/>
<id>urn:sha1:e162b219ae6a64be353f254bd4ba1c9627c67749</id>
<content type='text'>
Konrad writes:

"There are three bugs that have been found in the xen-blkfront (and
backend). Two of them have the stable tree CC-ed. They have been found
where an guest is migrating to a host that is missing
'feature-persistent' support (from one that has it enabled). We end up
hitting an BUG() in the driver code."
</content>
</entry>
<entry>
<title>xen-blkback: replace work_pending with work_busy in purge_persistent_gnt()</title>
<updated>2015-07-24T13:09:49+00:00</updated>
<author>
<name>Bob Liu</name>
<email>bob.liu@oracle.com</email>
</author>
<published>2015-07-22T06:40:10+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/BMC/Intel-BMC/linux.git/commit/?id=53bc7dc004fecf39e0ba70f2f8d120a1444315d3'/>
<id>urn:sha1:53bc7dc004fecf39e0ba70f2f8d120a1444315d3</id>
<content type='text'>
The BUG_ON() in purge_persistent_gnt() will be triggered when previous purge
work haven't finished.

There is a work_pending() before this BUG_ON, but it doesn't account if the work
is still currently running.

CC: stable@vger.kernel.org
Acked-by: Roger Pau Monné &lt;roger.pau@citrix.com&gt;
Signed-off-by: Bob Liu &lt;bob.liu@oracle.com&gt;
Signed-off-by: Konrad Rzeszutek Wilk &lt;konrad.wilk@oracle.com&gt;
</content>
</entry>
<entry>
<title>Merge tag 'for-linus-4.2-rc0-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip</title>
<updated>2015-07-01T18:53:46+00:00</updated>
<author>
<name>Linus Torvalds</name>
<email>torvalds@linux-foundation.org</email>
</author>
<published>2015-07-01T18:53:46+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/BMC/Intel-BMC/linux.git/commit/?id=7adf12b87f45a77d364464018fb8e9e1ac875152'/>
<id>urn:sha1:7adf12b87f45a77d364464018fb8e9e1ac875152</id>
<content type='text'>
Pull xen updates from David Vrabel:
 "Xen features and cleanups for 4.2-rc0:

   - add "make xenconfig" to assist in generating configs for Xen guests

   - preparatory cleanups necessary for supporting 64 KiB pages in ARM
     guests

   - automatically use hvc0 as the default console in ARM guests"

* tag 'for-linus-4.2-rc0-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
  block/xen-blkback: s/nr_pages/nr_segs/
  block/xen-blkfront: Remove invalid comment
  block/xen-blkfront: Remove unused macro MAXIMUM_OUTSTANDING_BLOCK_REQS
  arm/xen: Drop duplicate define mfn_to_virt
  xen/grant-table: Remove unused macro SPP
  xen/xenbus: client: Fix call of virt_to_mfn in xenbus_grant_ring
  xen: Include xen/page.h rather than asm/xen/page.h
  kconfig: add xenconfig defconfig helper
  kconfig: clarify kvmconfig is for kvm
  xen/pcifront: Remove usage of struct timeval
  xen/tmem: use BUILD_BUG_ON() in favor of BUG_ON()
  hvc_xen: avoid uninitialized variable warning
  xenbus: avoid uninitialized variable warning
  xen/arm: allow console=hvc0 to be omitted for guests
  arm,arm64/xen: move Xen initialization earlier
  arm/xen: Correctly check if the event channel interrupt is present
</content>
</entry>
<entry>
<title>Merge branch 'stable/for-jens-4.2' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen into for-linus</title>
<updated>2015-06-27T17:47:07+00:00</updated>
<author>
<name>Jens Axboe</name>
<email>axboe@fb.com</email>
</author>
<published>2015-06-27T17:47:07+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/BMC/Intel-BMC/linux.git/commit/?id=6443af9855dad721375349af036449becc62b632'/>
<id>urn:sha1:6443af9855dad721375349af036449becc62b632</id>
<content type='text'>
</content>
</entry>
<entry>
<title>block/xen-blkback: s/nr_pages/nr_segs/</title>
<updated>2015-06-17T15:35:19+00:00</updated>
<author>
<name>Julien Grall</name>
<email>julien.grall@linaro.org</email>
</author>
<published>2015-06-17T14:28:08+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/BMC/Intel-BMC/linux.git/commit/?id=6684fa1cdb1ebe804e9707f389255d461b2e95b0'/>
<id>urn:sha1:6684fa1cdb1ebe804e9707f389255d461b2e95b0</id>
<content type='text'>
Make the code less confusing to read now that Linux may not have the
same page size as Xen.

Signed-off-by: Julien Grall &lt;julien.grall@citrix.com&gt;
Acked-by: Roger Pau Monné &lt;roger.pau@citrix.com&gt;
Cc: Konrad Rzeszutek Wilk &lt;konrad.wilk@oracle.com&gt;
Signed-off-by: David Vrabel &lt;david.vrabel@citrix.com&gt;
</content>
</entry>
<entry>
<title>xen/block: add multi-page ring support</title>
<updated>2015-06-06T01:14:05+00:00</updated>
<author>
<name>Bob Liu</name>
<email>bob.liu@oracle.com</email>
</author>
<published>2015-06-03T05:40:03+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/BMC/Intel-BMC/linux.git/commit/?id=86839c56dee28c315a4c19b7bfee450ccd84cd25'/>
<id>urn:sha1:86839c56dee28c315a4c19b7bfee450ccd84cd25</id>
<content type='text'>
Extend xen/block to support multi-page ring, so that more requests can be
issued by using more than one pages as the request ring between blkfront
and backend.
As a result, the performance can get improved significantly.

We got some impressive improvements on our highend iscsi storage cluster
backend. If using 64 pages as the ring, the IOPS increased about 15 times
for the throughput testing and above doubled for the latency testing.

The reason was the limit on outstanding requests is 32 if use only one-page
ring, but in our case the iscsi lun was spread across about 100 physical
drives, 32 was really not enough to keep them busy.

Changes in v2:
 - Rebased to 4.0-rc6.
 - Document on how multi-page ring feature working to linux io/blkif.h.

Changes in v3:
 - Remove changes to linux io/blkif.h and follow the protocol defined
   in io/blkif.h of XEN tree.
 - Rebased to 4.1-rc3

Changes in v4:
 - Turn to use 'ring-page-order' and 'max-ring-page-order'.
 - A few comments from Roger.

Changes in v5:
 - Clarify with 4k granularity to comment
 - Address more comments from Roger

Signed-off-by: Bob Liu &lt;bob.liu@oracle.com&gt;
Signed-off-by: Konrad Rzeszutek Wilk &lt;konrad.wilk@oracle.com&gt;
</content>
</entry>
<entry>
<title>xen/grant: introduce func gnttab_unmap_refs_sync()</title>
<updated>2015-04-27T10:41:12+00:00</updated>
<author>
<name>Bob Liu</name>
<email>bob.liu@oracle.com</email>
</author>
<published>2015-04-03T06:42:59+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/BMC/Intel-BMC/linux.git/commit/?id=b44166cd46e28dd608d5baa5873047a40f32919c'/>
<id>urn:sha1:b44166cd46e28dd608d5baa5873047a40f32919c</id>
<content type='text'>
There are several place using gnttab async unmap and wait for
completion, so move the common code to a function
gnttab_unmap_refs_sync().

Signed-off-by: Bob Liu &lt;bob.liu@oracle.com&gt;
Acked-by: Roger Pau Monné &lt;roger.pau@citrix.com&gt;
Acked-by: Konrad Rzeszutek Wilk &lt;konrad.wilk@oracle.com&gt;
Signed-off-by: David Vrabel &lt;david.vrabel@citrix.com&gt;
</content>
</entry>
<entry>
<title>xen/blkback: safely unmap purge persistent grants</title>
<updated>2015-04-27T10:40:10+00:00</updated>
<author>
<name>Bob Liu</name>
<email>bob.liu@oracle.com</email>
</author>
<published>2015-04-03T06:42:58+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/BMC/Intel-BMC/linux.git/commit/?id=325d73bf8fea8af2227240b7305253fb052d3a68'/>
<id>urn:sha1:325d73bf8fea8af2227240b7305253fb052d3a68</id>
<content type='text'>
Commit c43cf3ea8385 ("xen-blkback: safely unmap grants in case they
are still in use") use gnttab_unmap_refs_async() to wait until the
mapped pages are no longer in use before unmapping them, but that
commit missed the persistent case.  Purge persistent pages can't be
unmapped either unless no longer in use.

Signed-off-by: Bob Liu &lt;bob.liu@oracle.com&gt;
Acked-by: Roger Pau Monné &lt;roger.pau@citrix.com&gt;
Signed-off-by: David Vrabel &lt;david.vrabel@citrix.com&gt;
</content>
</entry>
<entry>
<title>xen-blkback: define pr_fmt macro to avoid the duplication of DRV_PFX</title>
<updated>2015-04-07T14:32:43+00:00</updated>
<author>
<name>Tao Chen</name>
<email>boby.chen@huawei.com</email>
</author>
<published>2015-04-01T15:04:22+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/BMC/Intel-BMC/linux.git/commit/?id=77387b82d1b2bada25a7b566ab7716408fedc5e9'/>
<id>urn:sha1:77387b82d1b2bada25a7b566ab7716408fedc5e9</id>
<content type='text'>
Define pr_fmt macro with {xen-blkback: } prefix, then remove all use
of DRV_PFX in the pr sentences. Replace all DPRINTK with pr sentences,
and get rid of DPRINTK macro. It will simplify the code.

And if the pr sentences miss a \n, add it in the end. If the DPRINTK
sentences have redundant \n, remove it. It will format the code.

These all make the readability of the code become better.

Signed-off-by: Tao Chen &lt;boby.chen@huawei.com&gt;
Signed-off-by: Konrad Rzeszutek Wilk &lt;konrad.wilk@oracle.com&gt;
Acked-by: Roger Pau Monné &lt;roger.pau@citrix.com&gt;
</content>
</entry>
<entry>
<title>xen-blkback: safely unmap grants in case they are still in use</title>
<updated>2015-01-28T14:03:16+00:00</updated>
<author>
<name>Jennifer Herbert</name>
<email>jennifer.herbert@citrix.com</email>
</author>
<published>2015-01-05T16:49:22+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/BMC/Intel-BMC/linux.git/commit/?id=c43cf3ea838541ea9f066f4f1aa7b197cba6276e'/>
<id>urn:sha1:c43cf3ea838541ea9f066f4f1aa7b197cba6276e</id>
<content type='text'>
Use gnttab_unmap_refs_async() to wait until the mapped pages are no
longer in use before unmapping them.

This allows blkback to use network storage which may retain refs to
pages in queued skbs after the block I/O has completed.

Signed-off-by: Jennifer Herbert &lt;jennifer.herbert@citrix.com&gt;
Acked-by: Roger Pau Monné &lt;roger.pau@citrix.com&gt;
Acked-by: Jens Axboe &lt;axboe@kernel.de&gt;
Signed-off-by: David Vrabel &lt;david.vrabel@citrix.com&gt;
</content>
</entry>
</feed>
