<feed xmlns='http://www.w3.org/2005/Atom'>
<title>linux/drivers/hv, branch v4.4</title>
<subtitle>Mirror of https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/
</subtitle>
<id>https://git.shady.money/linux/atom?h=v4.4</id>
<link rel='self' href='https://git.shady.money/linux/atom?h=v4.4'/>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/'/>
<updated>2015-11-04T15:24:33Z</updated>
<entry>
<title>drivers/hv: share Hyper-V SynIC constants with userspace</title>
<updated>2015-11-04T15:24:33Z</updated>
<author>
<name>Andrey Smetanin</name>
<email>asmetanin@virtuozzo.com</email>
</author>
<published>2015-10-16T07:07:50Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=c75efa974e013640496620f26f0b532cb5cb17f9'/>
<id>urn:sha1:c75efa974e013640496620f26f0b532cb5cb17f9</id>
<content type='text'>
Moved Hyper-V synic contants from guest Hyper-V drivers private
header into x86 arch uapi Hyper-V header.

Added Hyper-V synic msr's flags into x86 arch uapi Hyper-V header.

Signed-off-by: Andrey Smetanin &lt;asmetanin@virtuozzo.com&gt;
Reviewed-by: Roman Kagan &lt;rkagan@virtuozzo.com&gt;
Signed-off-by: Denis V. Lunev &lt;den@openvz.org&gt;
CC: Vitaly Kuznetsov &lt;vkuznets@redhat.com&gt;
CC: "K. Y. Srinivasan" &lt;kys@microsoft.com&gt;
CC: Gleb Natapov &lt;gleb@kernel.org&gt;
CC: Paolo Bonzini &lt;pbonzini@redhat.com&gt;
Signed-off-by: Paolo Bonzini &lt;pbonzini@redhat.com&gt;
</content>
</entry>
<entry>
<title>Drivers: hv: vmbus: fix init_vp_index() for reloading hv_netvsc</title>
<updated>2015-09-21T05:44:51Z</updated>
<author>
<name>Dexuan Cui</name>
<email>decui@microsoft.com</email>
</author>
<published>2015-08-14T00:07:03Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=ca1c4b745779e20711322b3338f3a942a3c1224a'/>
<id>urn:sha1:ca1c4b745779e20711322b3338f3a942a3c1224a</id>
<content type='text'>
This fixes the recent commit 3b71107d73b16074afa7658f3f0fcf837aabfe24:
Drivers: hv: vmbus: Further improve CPU affiliation logic

Without the fix, reloading hv_netvsc hangs the guest.

Signed-off-by: Dexuan Cui &lt;decui@microsoft.com&gt;
Signed-off-by: K. Y. Srinivasan &lt;kys@microsoft.com&gt;
Signed-off-by: Greg Kroah-Hartman &lt;gregkh@linuxfoundation.org&gt;
</content>
</entry>
<entry>
<title>Drivers: hv: vmbus: use cpu_hotplug_enable/disable</title>
<updated>2015-08-05T18:46:44Z</updated>
<author>
<name>Vitaly Kuznetsov</name>
<email>vkuznets@redhat.com</email>
</author>
<published>2015-08-05T07:52:48Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=f39c4280a3872b0e6c7b01076132c12ad7a90392'/>
<id>urn:sha1:f39c4280a3872b0e6c7b01076132c12ad7a90392</id>
<content type='text'>
Commit e513229b4c38 ("Drivers: hv: vmbus: prevent cpu offlining on newer
hypervisors") was altering smp_ops.cpu_disable to prevent CPU offlining.
We can bo better by using cpu_hotplug_enable/disable functions instead of
such hard-coding.

Reported-by: Radim Kr.má  &lt;rkrcmar@redhat.com&gt;
Signed-off-by: Vitaly Kuznetsov &lt;vkuznets@redhat.com&gt;
Signed-off-by: K. Y. Srinivasan &lt;kys@microsoft.com&gt;
Signed-off-by: Greg Kroah-Hartman &lt;gregkh@linuxfoundation.org&gt;
</content>
</entry>
<entry>
<title>Drivers: hv: vmbus: add a sysfs attr to show the binding of channel/VP</title>
<updated>2015-08-05T18:44:29Z</updated>
<author>
<name>Dexuan Cui</name>
<email>decui@microsoft.com</email>
</author>
<published>2015-08-05T07:52:43Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=042ab0313bbb7e776e9510da3f07fb300d08a8ba'/>
<id>urn:sha1:042ab0313bbb7e776e9510da3f07fb300d08a8ba</id>
<content type='text'>
This is useful to analyze performance issue.

Signed-off-by: Dexuan Cui &lt;decui@microsoft.com&gt;
Signed-off-by: K. Y. Srinivasan &lt;kys@microsoft.com&gt;
Signed-off-by: Greg Kroah-Hartman &lt;gregkh@linuxfoundation.org&gt;
</content>
</entry>
<entry>
<title>Drivers: hv: vmbus: Implement a clocksource based on the TSC page</title>
<updated>2015-08-05T18:44:29Z</updated>
<author>
<name>K. Y. Srinivasan</name>
<email>kys@microsoft.com</email>
</author>
<published>2015-08-05T07:52:42Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=ca9357bd26c2f8e7b909321eedd651f52cc30d04'/>
<id>urn:sha1:ca9357bd26c2f8e7b909321eedd651f52cc30d04</id>
<content type='text'>
The current Hyper-V clock source is based on the per-partition reference counter
and this counter is being accessed via s synthetic MSR - HV_X64_MSR_TIME_REF_COUNT.
Hyper-V has a more efficient way of computing the per-partition reference
counter value that does not involve reading a synthetic MSR. We implement
a time source based on this mechanism.

Tested-by: Vivek Yadav &lt;vyadav@microsoft.com&gt;
Signed-off-by: K. Y. Srinivasan &lt;kys@microsoft.com&gt;
Signed-off-by: Greg Kroah-Hartman &lt;gregkh@linuxfoundation.org&gt;
</content>
</entry>
<entry>
<title>drivers/hv: Migrate to new 'set-state' interface</title>
<updated>2015-08-05T18:44:29Z</updated>
<author>
<name>Viresh Kumar</name>
<email>viresh.kumar@linaro.org</email>
</author>
<published>2015-08-05T07:52:41Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=bc609cb47fb2e74654e23cef0a1d4db38b6570a3'/>
<id>urn:sha1:bc609cb47fb2e74654e23cef0a1d4db38b6570a3</id>
<content type='text'>
Migrate hv driver to the new 'set-state' interface provided by
clockevents core, the earlier 'set-mode' interface is marked obsolete
now.

This also enables us to implement callbacks for new states of clockevent
devices, for example: ONESHOT_STOPPED.

Cc: "K. Y. Srinivasan" &lt;kys@microsoft.com&gt;
Cc: Haiyang Zhang &lt;haiyangz@microsoft.com&gt;
Cc: devel@linuxdriverproject.org
Signed-off-by: Viresh Kumar &lt;viresh.kumar@linaro.org&gt;
Signed-off-by: K. Y. Srinivasan &lt;kys@microsoft.com&gt;
Signed-off-by: Greg Kroah-Hartman &lt;gregkh@linuxfoundation.org&gt;
</content>
</entry>
<entry>
<title>Drivers: hv_vmbus: Fix signal to host condition</title>
<updated>2015-08-05T18:44:29Z</updated>
<author>
<name>Christopher Oo</name>
<email>t-chriso@microsoft.com</email>
</author>
<published>2015-08-05T07:52:40Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=a5cca686ce0ef4909deaee4ed46dd991e3a9ece4'/>
<id>urn:sha1:a5cca686ce0ef4909deaee4ed46dd991e3a9ece4</id>
<content type='text'>
Fixes a bug where previously hv_ringbuffer_read would pass in the old
number of bytes available to read instead of the expected old read index
when calculating when to signal to the host that the ringbuffer is empty.
Since the previous write size is already saved, also changes the
hv_need_to_signal_on_read to use the previously read value rather than
recalculating it.

Signed-off-by: Christopher Oo &lt;t-chriso@microsoft.com&gt;
Signed-off-by: K. Y. Srinivasan &lt;kys@microsoft.com&gt;
Signed-off-by: Greg Kroah-Hartman &lt;gregkh@linuxfoundation.org&gt;
</content>
</entry>
<entry>
<title>Drivers: hv: vmbus: Further improve CPU affiliation logic</title>
<updated>2015-08-05T18:44:28Z</updated>
<author>
<name>Dexuan Cui</name>
<email>decui@microsoft.com</email>
</author>
<published>2015-08-05T07:52:39Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=3b71107d73b16074afa7658f3f0fcf837aabfe24'/>
<id>urn:sha1:3b71107d73b16074afa7658f3f0fcf837aabfe24</id>
<content type='text'>
Keep track of CPU affiliations of sub-channels within the scope of the primary
channel. This will allow us to better distribute the load amongst available
CPUs.

Signed-off-by: Dexuan Cui &lt;decui@microsoft.com&gt;
Signed-off-by: K. Y. Srinivasan &lt;kys@microsoft.com&gt;
Signed-off-by: Greg Kroah-Hartman &lt;gregkh@linuxfoundation.org&gt;
</content>
</entry>
<entry>
<title>Drivers: hv: vmbus: Improve the CPU affiliation for channels</title>
<updated>2015-08-05T18:41:31Z</updated>
<author>
<name>K. Y. Srinivasan</name>
<email>kys@microsoft.com</email>
</author>
<published>2015-08-05T07:52:38Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=9f01ec53458d9e9b68f1c555e773b5d1a1f66e94'/>
<id>urn:sha1:9f01ec53458d9e9b68f1c555e773b5d1a1f66e94</id>
<content type='text'>
The current code tracks the assigned CPUs within a NUMA node in the context of
the primary channel. So, if we have a VM with a single NUMA node with 8 VCPUs, we may
end up unevenly distributing the channel load. Fix the issue by tracking affiliations
globally.

Signed-off-by: K. Y. Srinivasan &lt;kys@microsoft.com&gt;
Signed-off-by: Greg Kroah-Hartman &lt;gregkh@linuxfoundation.org&gt;
</content>
</entry>
<entry>
<title>drivers:hv: Move MMIO range picking from hyper_fb to hv_vmbus</title>
<updated>2015-08-05T18:41:31Z</updated>
<author>
<name>Jake Oshins</name>
<email>jakeo@microsoft.com</email>
</author>
<published>2015-08-05T07:52:37Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=3546448338e76a52d4f86eb3680cb2934e22d89b'/>
<id>urn:sha1:3546448338e76a52d4f86eb3680cb2934e22d89b</id>
<content type='text'>
This patch deletes the logic from hyperv_fb which picked a range of MMIO space
for the frame buffer and adds new logic to hv_vmbus which picks ranges for
child drivers.  The new logic isn't quite the same as the old, as it considers
more possible ranges.

Signed-off-by: Jake Oshins &lt;jakeo@microsoft.com&gt;
Signed-off-by: K. Y. Srinivasan &lt;kys@microsoft.com&gt;
Signed-off-by: Greg Kroah-Hartman &lt;gregkh@linuxfoundation.org&gt;
</content>
</entry>
</feed>
