<feed xmlns='http://www.w3.org/2005/Atom'>
<title>pm24.git/kernel/rcu/tree_plugin.h, branch v4.3-rc6</title>
<subtitle>Unnamed repository; edit this file 'description' to name the repository.
</subtitle>
<id>https://git.kobert.dev/pm24.git/atom?h=v4.3-rc6</id>
<link rel='self' href='https://git.kobert.dev/pm24.git/atom?h=v4.3-rc6'/>
<link rel='alternate' type='text/html' href='https://git.kobert.dev/pm24.git/'/>
<updated>2015-08-04T15:40:58Z</updated>
<entry>
<title>Merge branches 'fixes.2015.07.22a' and 'initexp.2015.08.04a' into HEAD</title>
<updated>2015-08-04T15:40:58Z</updated>
<author>
<name>Paul E. McKenney</name>
<email>paulmck@linux.vnet.ibm.com</email>
</author>
<published>2015-08-04T15:40:58Z</published>
<link rel='alternate' type='text/html' href='https://git.kobert.dev/pm24.git/commit/?id=8ff4fbfd69a6c7b9598f8c1f2df34f89bac02c1a'/>
<id>urn:sha1:8ff4fbfd69a6c7b9598f8c1f2df34f89bac02c1a</id>
<content type='text'>
fixes.2015.07.22a: Miscellaneous fixes.
initexp.2015.08.04a: Initialization and expedited updates.
	(Single branch due to conflicts.)
</content>
</entry>
<entry>
<title>rcu: Don't disable CPU hotplug during OOM notifiers</title>
<updated>2015-07-22T22:27:43Z</updated>
<author>
<name>Paul E. McKenney</name>
<email>paulmck@linux.vnet.ibm.com</email>
</author>
<published>2015-07-14T23:24:14Z</published>
<link rel='alternate' type='text/html' href='https://git.kobert.dev/pm24.git/commit/?id=9a54f98e341d09793247a6e598012edefb5ae7cb'/>
<id>urn:sha1:9a54f98e341d09793247a6e598012edefb5ae7cb</id>
<content type='text'>
RCU's rcu_oom_notify() disables CPU hotplug in order to stabilize the
list of online CPUs, which it traverses.  However, this is completely
pointless because smp_call_function_single() will quietly fail if invoked
on an offline CPU.  Because the count of requests is incremented in the
rcu_oom_notify_cpu() function that is remotely invoked, everything works
nicely even in the face of concurrent CPU-hotplug operations.

Furthermore, in recent kernels, invoking get_online_cpus() from an OOM
notifier can result in deadlock.  This commit therefore removes the
call to get_online_cpus() and put_online_cpus() from rcu_oom_notify().

Reported-by: Marcin Ślusarz &lt;marcin.slusarz@gmail.com&gt;
Reported-by: David Rientjes &lt;rientjes@google.com&gt;
Signed-off-by: Paul E. McKenney &lt;paulmck@linux.vnet.ibm.com&gt;
Acked-by: David Rientjes &lt;rientjes@google.com&gt;
Tested-by: Marcin Ślusarz &lt;marcin.slusarz@gmail.com&gt;
</content>
</entry>
<entry>
<title>rcu: Rename rcu_lockdep_assert() to RCU_LOCKDEP_WARN()</title>
<updated>2015-07-22T22:27:32Z</updated>
<author>
<name>Paul E. McKenney</name>
<email>paulmck@linux.vnet.ibm.com</email>
</author>
<published>2015-06-18T22:50:02Z</published>
<link rel='alternate' type='text/html' href='https://git.kobert.dev/pm24.git/commit/?id=f78f5b90c4ffa559e400c3919a02236101f29f3f'/>
<id>urn:sha1:f78f5b90c4ffa559e400c3919a02236101f29f3f</id>
<content type='text'>
This commit renames rcu_lockdep_assert() to RCU_LOCKDEP_WARN() for
consistency with the WARN() series of macros.  This also requires
inverting the sense of the conditional, which this commit also does.

Reported-by: Ingo Molnar &lt;mingo@kernel.org&gt;
Signed-off-by: Paul E. McKenney &lt;paulmck@linux.vnet.ibm.com&gt;
Reviewed-by: Ingo Molnar &lt;mingo@kernel.org&gt;
</content>
</entry>
<entry>
<title>rcu: Fix obsolete priority-boosting comment</title>
<updated>2015-07-22T22:27:28Z</updated>
<author>
<name>Paul E. McKenney</name>
<email>paulmck@linux.vnet.ibm.com</email>
</author>
<published>2015-06-06T15:11:43Z</published>
<link rel='alternate' type='text/html' href='https://git.kobert.dev/pm24.git/commit/?id=bc17ea1092c48227334a311a130c1a41966333fe'/>
<id>urn:sha1:bc17ea1092c48227334a311a130c1a41966333fe</id>
<content type='text'>
Tasks are no longer migrated to the root rcu_node, so there is no
longer any need for a boost kthread for the root rcu_node, and there no
longer is such a kthread.  This commit therefore fixes the comment in
rcu_boost_kthread()'s header to reflect this new reality.

Signed-off-by: Paul E. McKenney &lt;paulmck@linux.vnet.ibm.com&gt;
</content>
</entry>
<entry>
<title>rcu: Consolidate last open-coded expedited memory barrier</title>
<updated>2015-07-17T21:58:59Z</updated>
<author>
<name>Paul E. McKenney</name>
<email>paulmck@linux.vnet.ibm.com</email>
</author>
<published>2015-06-27T16:36:29Z</published>
<link rel='alternate' type='text/html' href='https://git.kobert.dev/pm24.git/commit/?id=704dd435ac7eaefa89fcd82fd2876b8330e00ff3'/>
<id>urn:sha1:704dd435ac7eaefa89fcd82fd2876b8330e00ff3</id>
<content type='text'>
One of the requirements on RCU grace periods is that if there is a
causal chain of operations that starts after one grace period and
ends before another grace period, then the two grace periods must
be serialized.  There has been (and might still be) code that relies
on this, for example, certain types of reference-counting code that
does a call_rcu() within an RCU callback function.

This requirement is why there is an smp_mb() at the end of both
synchronize_sched_expedited() and synchronize_rcu_expedited().
However, this is the only smp_mb() in these functions, so it would
be nicer to consolidate it into rcu_exp_gp_seq_end().  This commit
does just that.

Signed-off-by: Paul E. McKenney &lt;paulmck@linux.vnet.ibm.com&gt;
</content>
</entry>
<entry>
<title>rcu: Use funnel locking for synchronize_rcu_expedited()'s polling loop</title>
<updated>2015-07-17T21:58:56Z</updated>
<author>
<name>Paul E. McKenney</name>
<email>paulmck@linux.vnet.ibm.com</email>
</author>
<published>2015-06-26T02:03:16Z</published>
<link rel='alternate' type='text/html' href='https://git.kobert.dev/pm24.git/commit/?id=29fd930940193a9a035a75a3847457160d65559a'/>
<id>urn:sha1:29fd930940193a9a035a75a3847457160d65559a</id>
<content type='text'>
This commit gets rid of synchronize_rcu_expedited()'s mutex_trylock()
polling loop in favor of the funnel-locking scheme that was abstracted
from synchronize_sched_expedited().

Signed-off-by: Paul E. McKenney &lt;paulmck@linux.vnet.ibm.com&gt;
</content>
</entry>
<entry>
<title>rcu: Make synchronize_rcu_expedited() use sequence-counter scheme</title>
<updated>2015-07-17T21:58:52Z</updated>
<author>
<name>Paul E. McKenney</name>
<email>paulmck@linux.vnet.ibm.com</email>
</author>
<published>2015-06-25T22:52:50Z</published>
<link rel='alternate' type='text/html' href='https://git.kobert.dev/pm24.git/commit/?id=543c6158f6dff20a741dfa492771f18ceaa1a109'/>
<id>urn:sha1:543c6158f6dff20a741dfa492771f18ceaa1a109</id>
<content type='text'>
Although synchronize_rcu_expedited() uses a sequence-counter scheme, it
is based on a single increment per grace period, which means that tasks
piggybacking off of concurrent grace periods may be forced to wait longer
than necessary.  This commit therefore applies the new sequence-count
functions developed for synchronize_sched_expedited() to speed things
up a bit and to consolidate the sequence-counter implementation.

Signed-off-by: Paul E. McKenney &lt;paulmck@linux.vnet.ibm.com&gt;
</content>
</entry>
<entry>
<title>rcu: Remove CONFIG_RCU_CPU_STALL_INFO</title>
<updated>2015-07-17T21:58:44Z</updated>
<author>
<name>Paul E. McKenney</name>
<email>paulmck@linux.vnet.ibm.com</email>
</author>
<published>2015-06-11T22:22:43Z</published>
<link rel='alternate' type='text/html' href='https://git.kobert.dev/pm24.git/commit/?id=75c27f119b6475d95374bdad872c6938b5c26196'/>
<id>urn:sha1:75c27f119b6475d95374bdad872c6938b5c26196</id>
<content type='text'>
The CONFIG_RCU_CPU_STALL_INFO has been default-y for a couple of
releases with no complaints, so it is time to eliminate this Kconfig
option entirely, so that the long-form RCU CPU stall warnings cannot
be disabled.  This commit does just that.

Signed-off-by: Paul E. McKenney &lt;paulmck@linux.vnet.ibm.com&gt;
</content>
</entry>
<entry>
<title>rcu: Stop disabling CPU hotplug in synchronize_rcu_expedited()</title>
<updated>2015-07-17T21:58:42Z</updated>
<author>
<name>Paul E. McKenney</name>
<email>paulmck@linux.vnet.ibm.com</email>
</author>
<published>2015-06-11T21:50:22Z</published>
<link rel='alternate' type='text/html' href='https://git.kobert.dev/pm24.git/commit/?id=9b683874504a57cfa97558d403c75e286e20c9ce'/>
<id>urn:sha1:9b683874504a57cfa97558d403c75e286e20c9ce</id>
<content type='text'>
The fact that tasks could be migrated from leaf to root rcu_node
structures meant that synchronize_rcu_expedited() had to disable
CPU hotplug.  However, tasks now stay put, so this commit removes the
CPU-hotplug disabling from synchronize_rcu_expedited().

Signed-off-by: Paul E. McKenney &lt;paulmck@linux.vnet.ibm.com&gt;
</content>
</entry>
<entry>
<title>rcu: Simplify arithmetic to calculate number of RCU nodes</title>
<updated>2015-07-15T21:45:21Z</updated>
<author>
<name>Alexander Gordeev</name>
<email>agordeev@redhat.com</email>
</author>
<published>2015-06-03T06:18:31Z</published>
<link rel='alternate' type='text/html' href='https://git.kobert.dev/pm24.git/commit/?id=426216970e0458c1f507860f4837cbde66a72263'/>
<id>urn:sha1:426216970e0458c1f507860f4837cbde66a72263</id>
<content type='text'>
This update makes arithmetic to calculate number of RCU nodes
more straight and easy to read.

Cc: "Paul E. McKenney" &lt;paulmck@linux.vnet.ibm.com&gt;
Cc: Steven Rostedt &lt;rostedt@goodmis.org&gt;
Signed-off-by: Alexander Gordeev &lt;agordeev@redhat.com&gt;
Signed-off-by: Paul E. McKenney &lt;paulmck@linux.vnet.ibm.com&gt;
</content>
</entry>
</feed>
