idle.2012.09.23a fixes architectures for which RCU no longer considered
the idle loop to be a quiescent state due to earlier
adaptive-dynticks changes. Affected architectures are alpha,
cris, frv, h8300, m32r, m68k, mn10300, parisc, score, xtensa,
and ia64.
Paul E. McKenney [Fri, 24 Aug 2012 20:22:13 +0000 (13:22 -0700)]
ia64: Add missing RCU idle APIs on idle loop
Traditionally, the entire idle task served as an RCU quiescent state.
But when RCU read side critical sections started appearing within the
idle loop, this traditional strategy became untenable. The fix was to
create new RCU APIs named rcu_idle_enter() and rcu_idle_exit(), which
must be called by each architecture's idle loop so that RCU can tell
when it is safe to ignore a given idle CPU.
Unfortunately, this fix was never applied to ia64, a shortcoming remedied
by this commit.
Reported by: Tony Luck <tony.luck@intel.com> Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org> Cc: <stable@vger.kernel.org> # 3.3+ Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Tested by: Tony Luck <tony.luck@intel.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
In the old times, the whole idle task was considered
as an RCU quiescent state. But as RCU became more and
more successful overtime, some RCU read side critical
section have been added even in the code of some
architectures idle tasks, for tracing for example.
So nowadays, rcu_idle_enter() and rcu_idle_exit() must
be called by the architecture to tell RCU about the part
in the idle loop that doesn't make use of rcu read side
critical sections, typically the part that puts the CPU
in low power mode.
This is necessary for RCU to find the quiescent states in
idle in order to complete grace periods.
Add this missing pair of calls in the xtensa's idle loop.
Reported-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Chris Zankel <chris@zankel.net> Cc: <stable@vger.kernel.org> # 3.3+ Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
In the old times, the whole idle task was considered
as an RCU quiescent state. But as RCU became more and
more successful overtime, some RCU read side critical
section have been added even in the code of some
architectures idle tasks, for tracing for example.
So nowadays, rcu_idle_enter() and rcu_idle_exit() must
be called by the architecture to tell RCU about the part
in the idle loop that doesn't make use of rcu read side
critical sections, typically the part that puts the CPU
in low power mode.
This is necessary for RCU to find the quiescent states in
idle in order to complete grace periods.
Add this missing pair of calls in scores's idle loop.
Reported-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Chen Liqin <liqin.chen@sunplusct.com> Cc: Lennox Wu <lennox.wu@gmail.com> Cc: <stable@vger.kernel.org> # 3.3+ Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
In the old times, the whole idle task was considered
as an RCU quiescent state. But as RCU became more and
more successful overtime, some RCU read side critical
section have been added even in the code of some
architectures idle tasks, for tracing for example.
So nowadays, rcu_idle_enter() and rcu_idle_exit() must
be called by the architecture to tell RCU about the part
in the idle loop that doesn't make use of rcu read side
critical sections, typically the part that puts the CPU
in low power mode.
This is necessary for RCU to find the quiescent states in
idle in order to complete grace periods.
Add this missing pair of calls in the parisc's idle loop.
Reported-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: James E.J. Bottomley <jejb@parisc-linux.org> Cc: Helge Deller <deller@gmx.de> Cc: Parisc <linux-parisc@vger.kernel.org> Cc: <stable@vger.kernel.org> # 3.3+ Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
In the old times, the whole idle task was considered
as an RCU quiescent state. But as RCU became more and
more successful overtime, some RCU read side critical
section have been added even in the code of some
architectures idle tasks, for tracing for example.
So nowadays, rcu_idle_enter() and rcu_idle_exit() must
be called by the architecture to tell RCU about the part
in the idle loop that doesn't make use of rcu read side
critical sections, typically the part that puts the CPU
in low power mode.
This is necessary for RCU to find the quiescent states in
idle in order to complete grace periods.
Add this missing pair of calls in the mn10300's idle loop.
Reported-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: David Howells <dhowells@redhat.com> Cc: Koichi Yasutake <yasutake.koichi@jp.panasonic.com> Cc: <stable@vger.kernel.org> # 3.3+ Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Acked-by: David Howells <dhowells@redhat.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
In the old times, the whole idle task was considered
as an RCU quiescent state. But as RCU became more and
more successful overtime, some RCU read side critical
section have been added even in the code of some
architectures idle tasks, for tracing for example.
So nowadays, rcu_idle_enter() and rcu_idle_exit() must
be called by the architecture to tell RCU about the part
in the idle loop that doesn't make use of rcu read side
critical sections, typically the part that puts the CPU
in low power mode.
This is necessary for RCU to find the quiescent states in
idle in order to complete grace periods.
Add this missing pair of calls in the m68k's idle loop.
Reported-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Geert Uytterhoeven <geert@linux-m68k.org> Cc: m68k <linux-m68k@lists.linux-m68k.org> Cc: <stable@vger.kernel.org> # 3.3+ Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
In the old times, the whole idle task was considered
as an RCU quiescent state. But as RCU became more and
more successful overtime, some RCU read side critical
section have been added even in the code of some
architectures idle tasks, for tracing for example.
So nowadays, rcu_idle_enter() and rcu_idle_exit() must
be called by the architecture to tell RCU about the part
in the idle loop that doesn't make use of rcu read side
critical sections, typically the part that puts the CPU
in low power mode.
This is necessary for RCU to find the quiescent states in
idle in order to complete grace periods.
Add this missing pair of calls in the m32r's idle loop.
Reported-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Hirokazu Takata <takata@linux-m32r.org> Cc: <stable@vger.kernel.org> # 3.3+ Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
In the old times, the whole idle task was considered
as an RCU quiescent state. But as RCU became more and
more successful overtime, some RCU read side critical
section have been added even in the code of some
architectures idle tasks, for tracing for example.
So nowadays, rcu_idle_enter() and rcu_idle_exit() must
be called by the architecture to tell RCU about the part
in the idle loop that doesn't make use of rcu read side
critical sections, typically the part that puts the CPU
in low power mode.
This is necessary for RCU to find the quiescent states in
idle in order to complete grace periods.
Add this missing pair of calls in the h8300's idle loop.
Reported-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Cc: <stable@vger.kernel.org> # 3.3+ Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
In the old times, the whole idle task was considered
as an RCU quiescent state. But as RCU became more and
more successful overtime, some RCU read side critical
section have been added even in the code of some
architectures idle tasks, for tracing for example.
So nowadays, rcu_idle_enter() and rcu_idle_exit() must
be called by the architecture to tell RCU about the part
in the idle loop that doesn't make use of rcu read side
critical sections, typically the part that puts the CPU
in low power mode.
This is necessary for RCU to find the quiescent states in
idle in order to complete grace periods.
Add this missing pair of calls in the Frv's idle loop.
Reported-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: David Howells <dhowells@redhat.com> Cc: <stable@vger.kernel.org> # 3.3+ Acked-by: David Howells <dhowells@redhat.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
In the old times, the whole idle task was considered
as an RCU quiescent state. But as RCU became more and
more successful overtime, some RCU read side critical
section have been added even in the code of some
architectures idle tasks, for tracing for example.
So nowadays, rcu_idle_enter() and rcu_idle_exit() must
be called by the architecture to tell RCU about the part
in the idle loop that doesn't make use of rcu read side
critical sections, typically the part that puts the CPU
in low power mode.
This is necessary for RCU to find the quiescent states in
idle in order to complete grace periods.
Add this missing pair of calls in the Cris's idle loop.
Reported-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mikael Starvik <starvik@axis.com> Cc: Jesper Nilsson <jesper.nilsson@axis.com> Cc: Cris <linux-cris-kernel@axis.com> Cc: <stable@vger.kernel.org> # 3.3+ Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
In the old times, the whole idle task was considered
as an RCU quiescent state. But as RCU became more and
more successful overtime, some RCU read side critical
section have been added even in the code of some
architectures idle tasks, for tracing for example.
So nowadays, rcu_idle_enter() and rcu_idle_exit() must
be called by the architecture to tell RCU about the part
in the idle loop that doesn't make use of rcu read side
critical sections, typically the part that puts the CPU
in low power mode.
This is necessary for RCU to find the quiescent states in
idle in order to complete grace periods.
Add this missing pair of calls in the Alpha's idle loop.
Reported-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Tested-by: Michael Cree <mcree@orcon.net.nz> Cc: Richard Henderson <rth@twiddle.net> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Matt Turner <mattst88@gmail.com> Cc: alpha <linux-alpha@vger.kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: <stable@vger.kernel.org> # 3.3+ Reviewed-by: Josh Triplett <josh@joshtriplett.org>
cpu_idle() is called on the boot CPU by the init code with
preemption disabled. But the cpu_idle() function in alpha
doesn't handle this when it calls schedule() directly.
Fix it by converting it into schedule_preempt_disabled().
Also disable preemption before calling cpu_idle() from
secondary CPU entry code to stay consistent with this
state.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Tested-by: Michael Cree <mcree@orcon.net.nz> Cc: Richard Henderson <rth@twiddle.net> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Matt Turner <mattst88@gmail.com> Cc: alpha <linux-alpha@vger.kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Use get_online_cpus to avoid races involving CPU hotplug
If arch/x86/kernel/cpuid.c is a module, a CPU might offline or online
between the for_each_online_cpu() loop and the call to
register_hotcpu_notifier in cpuid_init or the call to
unregister_hotcpu_notifier in cpuid_exit. The potential races can
lead to leaks/duplicates, attempts to destroy non-existant devices, or
random pointer dereferences.
Use get_online_cpus to avoid races involving CPU hotplug
If arch/x86/kernel/msr.c is a module, a CPU might offline or online
between the for_each_online_cpu(i) loop and the call to
register_hotcpu_notifier in msr_init or the call to
unregister_hotcpu_notifier in msr_exit. The potential races can lead
to leaks/duplicates, attempts to destroy non-existant devices, or
random pointer dereferences.
For example, in msr_init if:
for_each_online_cpu(i) {
err = msr_device_create(i);
if (err != 0)
goto out_class;
}
<----- CPU offlines
register_hotcpu_notifier(&msr_class_cpu_notifier);
and the CPU never onlines before msr_exit, then the module will never
call msr_device_destroy for the associated CPU.
This fix surrounds for_each_online_cpu and register_hotcpu_notifier or
unregister_hotcpu_notifier with get_online_cpus+put_online_cpus.
Tested on a VM.
Signed-off-by: Silas Boyd-Wickizer <sbw@mit.edu> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Peter Zijlstra [Mon, 20 Aug 2012 09:26:57 +0000 (11:26 +0200)]
sched: Fix load avg vs cpu-hotplug
Rabik and Paul reported two different issues related to the same few
lines of code.
Rabik's issue is that the nr_uninterruptible migration code is wrong in
that he sees artifacts due to this (Rabik please do expand in more
detail).
Paul's issue is that this code as it stands relies on us using
stop_machine() for unplug, we all would like to remove this assumption
so that eventually we can remove this stop_machine() usage altogether.
The only reason we'd have to migrate nr_uninterruptible is so that we
could use for_each_online_cpu() loops in favour of
for_each_possible_cpu() loops, however since nr_uninterruptible() is the
only such loop and its using possible lets not bother at all.
The problem Rabik sees is (probably) caused by the fact that by
migrating nr_uninterruptible we screw rq->calc_load_active for both rqs
involved.
So don't bother with fancy migration schemes (meaning we now have to
keep using for_each_possible_cpu()) and instead fold any nr_active delta
after we migrate all tasks away to make sure we don't have any skewed
nr_active accounting.
[ paulmck: Move call to calc_load_migration to CPU_DEAD to avoid
miscounting noted by Rakib. ]
Reported-by: Rakib Mullick <rakib.mullick@gmail.com> Reported-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org>
Posting a callback after the CPU_DEAD notifier effectively leaks
that callback unless/until that CPU comes back online. Silence is
unhelpful when attempting to track down such leaks, so this commit emits
a WARN_ON_ONCE() and unconditionally leaks the callback when an offline
CPU attempts to register a callback. The rdp->nxttail[RCU_NEXT_TAIL] is
set to NULL in the CPU_DEAD notifier and restored in the CPU_UP_PREPARE
notifier, allowing _call_rcu() to determine exactly when posting callbacks
is illegal.
Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
rcu: Remove _rcu_barrier() dependency on __stop_machine()
Currently, _rcu_barrier() relies on preempt_disable() to prevent
any CPU from going offline, which in turn depends on CPU hotplug's
use of __stop_machine().
This patch therefore makes _rcu_barrier() use get_online_cpus() to
block CPU-hotplug operations. This has the added benefit of removing
the need for _rcu_barrier() to adopt callbacks: Because CPU-hotplug
operations are excluded, there can be no callbacks to adopt. This
commit simplifies the code accordingly.
Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
The print_cpu_stall_fast_no_hz() function attempts to print -1 when
the ->idle_gp_timer is not pending, but unsigned arithmetic causes it
to instead print ULONG_MAX, which is 4294967295 on 32-bit systems and 18446744073709551615 on 64-bit systems. Neither of these are the most
reader-friendly values, so this commit instead causes "timer not pending"
to be printed when ->idle_gp_timer is not pending.
Reported-by: Paul Walmsley <paul@pwsan.com> Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Li Zhong [Wed, 19 Sep 2012 15:52:32 +0000 (08:52 -0700)]
rcu: Move TINY_RCU quiescent state out of extended quiescent state
TINY_RCU's rcu_idle_enter_common() invokes rcu_sched_qs() in order
to inform the RCU core of the quiescent state implied by idle entry.
Of course, idle is also an extended quiescent state, so that the call
to rcu_sched_qs() speeds up RCU's invoking of any callbacks that might
be queued. This speed-up is important when entering into dyntick-idle
mode -- if there are no further scheduling-clock interrupts, the callbacks
might never be invoked, which could result in a system hang.
However, processing callbacks does event tracing, which in turn
implies RCU read-side critical sections, which are illegal in extended
quiescent states. This patch therefore moves the call to rcu_sched_qs()
so that it precedes the point at which we inform lockdep that RCU has
entered an extended quiescent state.
Signed-off-by: Li Zhong <zhong@linux.vnet.ibm.com> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Michael Wang [Fri, 17 Aug 2012 04:33:34 +0000 (12:33 +0800)]
kmemleak: Replace list_for_each_continue_rcu with new interface
This patch replaces list_for_each_continue_rcu() with
list_for_each_entry_continue_rcu() to save a few lines
of code and allow removing list_for_each_continue_rcu().
Signed-off-by: Michael Wang <wangyun@linux.vnet.ibm.com> Acked-by: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Paul E. McKenney [Thu, 23 Aug 2012 15:34:07 +0000 (08:34 -0700)]
time: RCU permitted to stop idle entry via softirq
The can_stop_idle_tick() function complains if a softirq vector is
raised too late in the idle-entry process, presumably in order to
prevent dangling softirq invocations from being delayed across the
full idle period, which might be indefinitely long -- and if softirq
was asserted any later than the call to this function, such a delay
might well happen.
However, RCU needs to be able to use softirq to stop idle entry in
order to be able to drain RCU callbacks from the current CPU, which in
turn enables faster entry into dyntick-idle mode, which in turn reduces
power consumption. Because RCU takes this action at a well-defined
point in the idle-entry path, it is safe for RCU to take this approach.
This commit therefore silences the error message that is sometimes
produced when the going-idle CPU suddenly finds that it has an RCU_SOFTIRQ
to process. The error message will continue to be issued for other
softirq vectors.
Reported-by: Sedat Dilek <sedat.dilek@gmail.com> Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Tested-by: Sedat Dilek <sedat.dilek@gmail.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Paul E. McKenney [Tue, 21 Aug 2012 19:14:19 +0000 (12:14 -0700)]
rcu: Move TINY_PREEMPT_RCU away from raw_local_irq_save()
The use of raw_local_irq_save() is unnecessary, given that local_irq_save()
really does disable interrupts. Also, it appears to interfere with lockdep.
Therefore, this commit moves to local_irq_save().
Reported-by: Fengguang Wu <fengguang.wu@intel.com> Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Tested-by: Fengguang Wu <fengguang.wu@intel.com>
Paul E. McKenney [Mon, 13 Aug 2012 23:34:12 +0000 (16:34 -0700)]
rcu: Remove redundant memory barrier from __call_rcu()
The first memory barrier in __call_rcu() is supposed to order any
updates done beforehand by the caller against the actual queuing
of the callback. However, the second memory barrier (which is intended
to order incrementing the queue lengths before queuing the callback)
is also between the caller's updates and the queuing of the callback.
The second memory barrier can therefore serve both purposes.
This commit therefore removes the first memory barrier.
Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Paul E. McKenney [Mon, 13 Aug 2012 18:17:06 +0000 (11:17 -0700)]
rcu: Avoid spurious RCU CPU stall warnings
If a given CPU avoids the idle loop but also avoids starting a new
RCU grace period for a full minute, RCU can issue spurious RCU CPU
stall warnings. This commit fixes this issue by adding a check for
ongoing grace period to avoid these spurious stall warnings.
Reported-by: Becky Bruce <bgillbruce@gmail.com> Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Paul E. McKenney [Fri, 10 Aug 2012 23:55:59 +0000 (16:55 -0700)]
rcu: Protect rcu_node accesses during CPU stall warnings
The print_other_cpu_stall() function accesses a number of rcu_node
fields without protection from the ->lock. In theory, this is not
a problem because the fields accessed are all integers, but in
practice the compiler can get nasty. Therefore, the commit extends
the existing critical section to cover the entire loop body.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
The rcu_print_detail_task_stall_rnp() function invokes
rcu_preempt_blocked_readers_cgp() to verify that there are some preempted
RCU readers blocking the current grace period outside of the protection
of the rcu_node structure's ->lock. This means that the last blocked
reader might exit its RCU read-side critical section and remove itself
from the ->blkd_tasks list before the ->lock is acquired, resulting in
a segmentation fault when the subsequent code attempts to dereference
the now-NULL gp_tasks pointer.
This commit therefore moves the test under the lock. This will not
have measurable effect on lock contention because this code is invoked
only when printing RCU CPU stall warnings, in other words, in the common
case, never.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Paul E. McKenney [Fri, 10 Aug 2012 20:55:03 +0000 (13:55 -0700)]
rcu: Apply for_each_rcu_flavor() to increment_cpu_stall_ticks()
The increment_cpu_stall_ticks() function listed each RCU flavor
explicitly, with an ifdef to handle preemptible RCU. This commit
therefore applies for_each_rcu_flavor() to save a line of code.
Because this commit switches from a code-based enumeration of the
flavors of RCU to an rcu_state-list-based enumeration, it is no longer
possible to apply __get_cpu_var() to the per-CPU rcu_data structures.
We instead use __this_cpu_var() on the rcu_state structure's ->rda field
that references the corresponding rcu_data structures.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Commit 1217ed1b (rcu: permit rcu_read_unlock() to be called while holding
runqueue locks) made rcu_initiate_boost() restore irq state when releasing
the rcu_node structure's ->lock, but failed to update the header comment
accordingly. This commit therefore brings the header comment up to date.
Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
rcu: Make offline-CPU checking allow for indefinite delays
The rcu_implicit_offline_qs() function implicitly assumed that execution
would progress predictably when interrupts are disabled, which is of course
not guaranteed when running on a hypervisor. Furthermore, this function
is short, and is called from one place only in a short function.
This commit therefore ensures that the timing is checked before
checking the condition, which guarantees correct behavior even given
indefinite delays. It also inlines rcu_implicit_offline_qs() into
rcu_implicit_dynticks_qs().
Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Paul E. McKenney [Tue, 31 Jul 2012 21:09:49 +0000 (14:09 -0700)]
rcu: Improve boost selection when moving tasks to root rcu_node
The rcu_preempt_offline_tasks() moves all tasks queued on a given leaf
rcu_node structure to the root rcu_node, which is done when the last CPU
corresponding the the leaf rcu_node structure goes offline. Now that
RCU-preempt's synchronize_rcu_expedited() implementation blocks CPU-hotplug
operations during the initialization of each rcu_node structure's
->boost_tasks pointer, rcu_preempt_offline_tasks() can do a better job
of setting the root rcu_node's ->boost_tasks pointer.
The key point is that rcu_preempt_offline_tasks() runs as part of the
CPU-hotplug process, so that a concurrent synchronize_rcu_expedited()
is guaranteed to either have not started on the one hand (in which case
there is no boosting on behalf of the expedited grace period) or to be
completely initialized on the other (in which case, in the absence of
other priority boosting, all ->boost_tasks pointers will be initialized).
Therefore, if rcu_preempt_offline_tasks() finds that the ->boost_tasks
pointer is equal to the ->exp_tasks pointer, it can be sure that it is
correctly placed.
In the case where there was boosting ongoing at the time that the
synchronize_rcu_expedited() function started, different nodes might start
boosting the tasks blocking the expedited grace period at different times.
In this mixed case, the root node will either be boosting tasks for
the expedited grace period already, or it will start as soon as it gets
done boosting for the normal grace period -- but in this latter case,
the root node's tasks needed to be boosted in any case.
This commit therefore adds a check of the ->boost_tasks pointer against
the ->exp_tasks pointer to the list that prevents updating ->boost_tasks.
Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Paul E. McKenney [Tue, 31 Jul 2012 17:12:48 +0000 (10:12 -0700)]
rcu: Permit RCU_NONIDLE() to be used from interrupt context
There is a need to use RCU from interrupt context, but either before
rcu_irq_enter() is called or after rcu_irq_exit() is called. If the
interrupt occurs from idle, then lockdep-RCU will complain about such
uses, as they appear to be illegal uses of RCU from the idle loop.
In other environments, RCU_NONIDLE() could be used to properly protect
the use of RCU, but RCU_NONIDLE() currently cannot be invoked except
from process context.
This commit therefore modifies RCU_NONIDLE() to permit its use more
globally.
Reported-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Paul E. McKenney [Fri, 27 Jul 2012 20:41:47 +0000 (13:41 -0700)]
rcu: Properly initialize ->boost_tasks on CPU offline
When rcu_preempt_offline_tasks() clears tasks from a leaf rcu_node
structure, it does not NULL out the structure's ->boost_tasks field.
This commit therefore fixes this issue.
Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Paul E. McKenney [Wed, 11 Jul 2012 07:24:57 +0000 (00:24 -0700)]
rcu: Pull TINY_RCU dyntick-idle tracing into non-idle region
Because TINY_RCU's idle detection keys directly off of the nesting
level, rather than from a separate variable as in TREE_RCU, the
TINY_RCU dyntick-idle tracing on transition to idle must happen
before the change to the nesting level. This commit therefore makes
this change by passing the desired new value (rather than the old value)
of the nesting level in to rcu_idle_enter_common().
[ paulmck: Add fix for wrong-variable bug spotted by
Michael Wang <wangyun@linux.vnet.ibm.com>. ]
Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
rcu: Add PROVE_RCU_DELAY to provoke difficult races
There have been some recent bugs that were triggered only when
preemptible RCU's __rcu_read_unlock() was preempted just after setting
->rcu_read_lock_nesting to INT_MIN, which is a low-probability event.
Therefore, reproducing those bugs (to say nothing of gaining confidence
in alleged fixes) was quite difficult. This commit therefore creates
a new debug-only RCU kernel config option that forces a short delay
in __rcu_read_unlock() to increase the probability of those sorts of
bugs occurring.
Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Paul E. McKenney [Sat, 25 Aug 2012 22:27:40 +0000 (15:27 -0700)]
rcu: Prevent initialization race in rcutorture kthreads
When you do something like "t = kthread_run(...)", it is possible that
the kthread will start running before the assignment to "t" happens.
If the child kthread expects to find a pointer to its task_struct in "t",
it will then be fatally disappointed. This commit therefore switches
such cases to kthread_create() followed by wake_up_process(), guaranteeing
that the assignment happens before the child kthread starts running.
Reported-by: Fengguang Wu <fengguang.wu@intel.com> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
The current documentation did not help someone grepping for SRCU to
learn that disabling preemption is not a replacement for srcu_read_lock(),
so upgrade the documentation to bring this out, not just for SRCU,
but also for RCU-bh. Also document the fact that SRCU readers are
respected on CPUs executing in user mode, idle CPUs, and even on
offline CPUs.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org> Reviewed-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Paul E. McKenney [Mon, 23 Jul 2012 19:05:55 +0000 (12:05 -0700)]
rcu: Track CPU-hotplug duration statistics
Many rcutorture runs include CPU-hotplug operations in their stress
testing. This commit accumulates statistics on the durations of these
operations in deference to the recent concern about the overhead and
latency of these operations.
Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Paul E. McKenney [Mon, 23 Jul 2012 19:30:22 +0000 (12:30 -0700)]
rcu: Update rcutorture defaults
A number of new features have been added to rcutorture over the years, but
the defaults have not been updated to include them. This commit therefore
turns on a couple of them that have proven helpful and trustworthy, namely
periodic progress reports and testing of NO_HZ.
Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Currently, rcu_init_geometry() only reshapes RCU's combining trees
if the leaf fanout is changed at boot time. This means that by
default, kernels compiled with (say) NR_CPUS=4096 will keep oversized
data structures, even when running on systems with (say) four CPUs.
This commit therefore checks to see if the maximum number of CPUs on
the actual running system (nr_cpu_ids) differs from NR_CPUS, and if so
reshapes the combining trees accordingly.
Reported-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
rcu: Handle unbalanced rcu_node configurations with few CPUs
If CONFIG_RCU_FANOUT_EXACT=y, if there are not enough CPUs (according
to nr_cpu_ids) to require more than a single rcu_node structure, but if
NR_CPUS is larger than would fit into a single rcu_node structure, then
the current rcu_init_levelspread() code is subject to integer overflow
in the eight-bit ->levelspread[] array in the rcu_state structure.
In this case, the solution is -not- to increase the size of the
elements in this array because the values in that array should be
constrained to the number of bits in an unsigned long. Instead, this
commit replaces NR_CPUS with nr_cpu_ids in the rcu_init_levelspread()
function's initialization of the cprv local variable. This results in
all of the arithmetic being consistently based off of the nr_cpu_ids
value, thus avoiding the overflow, which was caused by the mixing of
nr_cpu_ids and NR_CPUS.
Reported-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Paul E. McKenney [Tue, 21 Aug 2012 22:00:05 +0000 (15:00 -0700)]
rcu: Simplify quiescent-state detection
The current quiescent-state detection algorithm is needlessly
complex. It records the grace-period number corresponding to
the quiescent state at the time of the quiescent state, which
works, but it seems better to simply erase any record of previous
quiescent states at the time that the CPU notices the new grace
period. This has the further advantage of removing another piece
of RCU for which lockless reasoning is required.
Therefore, this commit makes this change.
Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Paul E. McKenney [Tue, 31 Jul 2012 00:19:25 +0000 (17:19 -0700)]
rcu: Reduce synchronize_rcu_expedited() latency
The synchronize_rcu_expedited() function disables interrupts across a
scan of all leaf rcu_node structures, which is not good for real-time
scheduling latency on large systems (hundreds or especially thousands
of CPUs). This commit therefore holds off CPU-hotplug operations using
get_online_cpus(), and removes the prior acquisiion of the ->onofflock
(which required disabling interrupts).
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Paul E. McKenney [Mon, 23 Jul 2012 23:03:51 +0000 (16:03 -0700)]
rcu: Eliminate signed overflow in synchronize_rcu_expedited()
In the C language, signed overflow is undefined. It is true that
twos-complement arithmetic normally comes to the rescue, but if the
compiler can subvert this any time it has any information about the values
being compared. For example, given "if (a - b > 0)", if the compiler
has enough information to realize that (for example) the value of "a"
is positive and that of "b" is negative, the compiler is within its
rights to optimize to a simple "if (1)", which might not be what you want.
This commit therefore converts synchronize_rcu_expedited()'s work-done
detection counter from signed to unsigned.
Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Paul E. McKenney [Wed, 11 Jul 2012 12:23:18 +0000 (05:23 -0700)]
rcu: Adjust for unconditional ->completed assignment
Now that the rcu_node structures' ->completed fields are unconditionally
assigned at grace-period cleanup time, they should already have the
correct value for the new grace period at grace-period initialization
time. This commit therefore inserts a WARN_ON_ONCE() to verify this
invariant.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
rcu: Add random PROVE_RCU_DELAY to grace-period initialization
Preemption greatly raised the probability of certain types of race
conditions, so this commit adds an anti-heisenbug to greatly increase
the collision cross section, also known as the probability of occurrence.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
The current approach to grace-period initialization is vulnerable to
extremely low-probability races. These races stem from the fact that
the old grace period is marked completed on the same traversal through
the rcu_node structure that is marking the start of the new grace period.
This means that some rcu_node structures will believe that the old grace
period is still in effect at the same time that other rcu_node structures
believe that the new grace period has already started.
These sorts of disagreements can result in too-short grace periods,
as shown in the following scenario:
1. CPU 0 completes a grace period, but needs an additional
grace period, so starts initializing one, initializing all
the non-leaf rcu_node structures and the first leaf rcu_node
structure. Because CPU 0 is both completing the old grace
period and starting a new one, it marks the completion of
the old grace period and the start of the new grace period
in a single traversal of the rcu_node structures.
Therefore, CPUs corresponding to the first rcu_node structure
can become aware that the prior grace period has completed, but
CPUs corresponding to the other rcu_node structures will see
this same prior grace period as still being in progress.
2. CPU 1 passes through a quiescent state, and therefore informs
the RCU core. Because its leaf rcu_node structure has already
been initialized, this CPU's quiescent state is applied to the
new (and only partially initialized) grace period.
3. CPU 1 enters an RCU read-side critical section and acquires
a reference to data item A. Note that this CPU believes that
its critical section started after the beginning of the new
grace period, and therefore will not block this new grace period.
4. CPU 16 exits dyntick-idle mode. Because it was in dyntick-idle
mode, other CPUs informed the RCU core of its extended quiescent
state for the past several grace periods. This means that CPU 16
is not yet aware that these past grace periods have ended. Assume
that CPU 16 corresponds to the second leaf rcu_node structure --
which has not yet been made aware of the new grace period.
5. CPU 16 removes data item A from its enclosing data structure
and passes it to call_rcu(), which queues a callback in the
RCU_NEXT_TAIL segment of the callback queue.
6. CPU 16 enters the RCU core, possibly because it has taken a
scheduling-clock interrupt, or alternatively because it has
more than 10,000 callbacks queued. It notes that the second
most recent grace period has completed (recall that because it
corresponds to the second as-yet-uninitialized rcu_node structure,
it cannot yet become aware that the most recent grace period has
completed), and therefore advances its callbacks. The callback
for data item A is therefore in the RCU_NEXT_READY_TAIL segment
of the callback queue.
7. CPU 0 completes initialization of the remaining leaf rcu_node
structures for the new grace period, including the structure
corresponding to CPU 16.
8. CPU 16 again enters the RCU core, again, possibly because it has
taken a scheduling-clock interrupt, or alternatively because
it now has more than 10,000 callbacks queued. It notes that
the most recent grace period has ended, and therefore advances
its callbacks. The callback for data item A is therefore in
the RCU_DONE_TAIL segment of the callback queue.
9. All CPUs other than CPU 1 pass through quiescent states. Because
CPU 1 already passed through its quiescent state, the new grace
period completes. Note that CPU 1 is still in its RCU read-side
critical section, still referencing data item A.
10. Suppose that CPU 2 wais the last CPU to pass through a quiescent
state for the new grace period, and suppose further that CPU 2
did not have any callbacks queued, therefore not needing an
additional grace period. CPU 2 therefore traverses all of the
rcu_node structures, marking the new grace period as completed,
but does not initialize a new grace period.
11. CPU 16 yet again enters the RCU core, yet again possibly because
it has taken a scheduling-clock interrupt, or alternatively
because it now has more than 10,000 callbacks queued. It notes
that the new grace period has ended, and therefore advances
its callbacks. The callback for data item A is therefore in
the RCU_DONE_TAIL segment of the callback queue. This means
that this callback is now considered ready to be invoked.
12. CPU 16 invokes the callback, freeing data item A while CPU 1
is still referencing it.
This scenario represents a day-zero bug for TREE_RCU. This commit
therefore ensures that the old grace period is marked completed in
all leaf rcu_node structures before a new grace period is marked
started in any of them.
That said, it would have been insanely difficult to force this race to
happen before the grace-period initialization process was preemptible.
Therefore, this commit is not a candidate for -stable.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Conflicts:
rcu: Make rcutree module parameters visible in sysfs
The module parameters blimit, qhimark, and qlomark (and more
recently, rcu_fanout_leaf) have permission masks of zero, so
that their values are not visible from sysfs. This is unnecessary
and inconvenient to administrators who might like an easy way to
see what these values are on a running system. This commit therefore
sets their permission masks to 0444, allowing them to be read but
not written.
Reported-by: Rusty Russell <rusty@ozlabs.org> Reported-by: Josh Triplett <josh@joshtriplett.org> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Paul E. McKenney [Wed, 27 Jun 2012 03:45:57 +0000 (20:45 -0700)]
rcu: Control grace-period duration from sysfs
Although almost everyone is well-served by the defaults, some uses of RCU
benefit from shorter grace periods, while others benefit more from the
greater efficiency provided by longer grace periods. Situations requiring
a large number of grace periods to elapse (and wireshark startup has
been called out as an example of this) are helped by lower-latency
grace periods. Furthermore, in some embedded applications, people are
willing to accept a small degradation in update efficiency (due to there
being more of the shorter grace-period operations) in order to gain the
lower latency.
In contrast, those few systems with thousands of CPUs need longer grace
periods because the CPU overhead of a grace period rises roughly
linearly with the number of CPUs. Such systems normally do not make
much use of facilities that require large numbers of grace periods to
elapse, so this is a good tradeoff.
Therefore, this commit allows the durations to be controlled from sysfs.
There are two sysfs parameters, one named "jiffies_till_first_fqs" that
specifies the delay in jiffies from the end of grace-period initialization
until the first attempt to force quiescent states, and the other named
"jiffies_till_next_fqs" that specifies the delay (again in jiffies)
between subsequent attempts to force quiescent states. They both default
to three jiffies, which is compatible with the old hard-coded behavior.
At some future time, it may be possible to automatically increase the
grace-period length with the number of CPUs, but we do not yet have
sufficient data to do a good job. Preliminary data indicates that we
should add an addiitonal jiffy to each of the delays for every 200 CPUs
in the system, but more experimentation is needed. For now, the number
of systems with more than 1,000 CPUs is small enough that this can be
relegated to boot-time hand tuning.
Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Large systems running RCU_FAST_NO_HZ kernels see extreme memory
contention on the rcu_state structure's ->fqslock field. This
can be avoided by disabling RCU_FAST_NO_HZ, either at compile time
or at boot time (via the nohz kernel boot parameter), but large
systems will no doubt become sensitive to energy consumption.
This commit therefore uses a combining-tree approach to spread the
memory contention across new cache lines in the leaf rcu_node structures.
This can be thought of as a tournament lock that has only a try-lock
acquisition primitive.
The effect on small systems is minimal, because such systems have
an rcu_node "tree" consisting of a single node. In addition, this
functionality is not used on fastpaths.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Paul E. McKenney [Mon, 25 Jun 2012 15:41:11 +0000 (08:41 -0700)]
rcu: Allow RCU quiescent-state forcing to be preempted
RCU quiescent-state forcing is currently carried out without preemption
points, which can result in excessive latency spikes on large systems
(many hundreds or thousands of CPUs). This patch therefore inserts
a voluntary preemption point into force_qs_rnp(), which should greatly
reduce the magnitude of these spikes.
Reported-by: Mike Galbraith <mgalbraith@suse.de> Reported-by: Dimitri Sivanich <sivanich@sgi.com> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Paul E. McKenney [Sat, 23 Jun 2012 00:06:26 +0000 (17:06 -0700)]
rcu: Move quiescent-state forcing into kthread
As the first step towards allowing quiescent-state forcing to be
preemptible, this commit moves RCU quiescent-state forcing into the
same kthread that is now used to initialize and clean up after grace
periods. This is yet another step towards keeping scheduling
latency down to a dull roar.
Updated to change from raw_spin_lock_irqsave() to raw_spin_lock_irq()
and to remove the now-unused rcu_state structure fields as suggested by
Peter Zijlstra.
Reported-by: Mike Galbraith <mgalbraith@suse.de> Reported-by: Dimitri Sivanich <sivanich@sgi.com> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Dimitri Sivanich [Fri, 29 Jun 2012 21:17:29 +0000 (14:17 -0700)]
rcu: Segregate rcu_state fields to improve cache locality
The fields in the rcu_state structure that are protected by the
root rcu_node structure's ->lock can share a cache line with the
fields protected by ->onofflock. This can result in excessive
memory contention on large systems, so this commit applies
____cacheline_internodealigned_in_smp to the ->onofflock field in
order to segregate them.
Signed-off-by: Dimitri Sivanich <sivanich@sgi.com> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Tested-by: Dimitri Sivanich <sivanich@sgi.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Paul E. McKenney [Tue, 12 Jun 2012 00:39:43 +0000 (17:39 -0700)]
rcu: Provide OOM handler to motivate lazy RCU callbacks
In kernels built with CONFIG_RCU_FAST_NO_HZ=y, CPUs can accumulate a
large number of lazy callbacks, which as the name implies will be slow
to be invoked. This can be a problem on small-memory systems, where the
default 6-second sleep for CPUs having only lazy RCU callbacks could well
be fatal. This commit therefore installs an OOM hander that ensures that
every CPU with lazy callbacks has at least one non-lazy callback, in turn
ensuring timely advancement for these callbacks.
Updated to fix bug that disabled OOM killing, noted by Lai Jiangshan.
Updated to push the for_each_rcu_flavor() loop into rcu_oom_notify_cpu(),
thus reducing the number of IPIs, as suggested by Steven Rostedt. Also
to make the for_each_online_cpu() loop be preemptible. (Later, it might
be good to use smp_call_function(), as suggested by Peter Zijlstra.)
Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Tested-by: Sasha Levin <levinsasha928@gmail.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Paul E. McKenney [Thu, 21 Jun 2012 16:54:10 +0000 (09:54 -0700)]
rcu: Prevent offline CPUs from executing RCU core code
Earlier versions of RCU invoked the RCU core from the CPU_DYING notifier
in order to note a quiescent state for the outgoing CPU. Because the
CPU is marked "offline" during the execution of the CPU_DYING notifiers,
the RCU core had to tolerate being invoked from an offline CPU. However,
commit b1420f1c (Make rcu_barrier() less disruptive) left only tracing
code in the CPU_DYING notifier, so the RCU core need no longer execute
on offline CPUs. This commit therefore enforces this restriction.
Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Paul E. McKenney [Fri, 22 Jun 2012 18:08:41 +0000 (11:08 -0700)]
rcu: Break up rcu_gp_kthread() into subfunctions
Then rcu_gp_kthread() function is too large and furthermore needs to
have the force_quiescent_state() code pulled in. This commit therefore
breaks up rcu_gp_kthread() into rcu_gp_init() and rcu_gp_cleanup().
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Paul E. McKenney [Thu, 21 Jun 2012 15:19:05 +0000 (08:19 -0700)]
rcu: Allow RCU grace-period cleanup to be preempted
RCU grace-period cleanup is currently carried out with interrupts
disabled, which can result in excessive latency spikes on large systems
(many hundreds or thousands of CPUs). This patch therefore makes the
RCU grace-period cleanup be preemptible, including voluntary preemption
points, which should eliminate those latency spikes. Similar spikes from
forcing of quiescent states will be dealt with similarly by later patches.
Updated to replace uses of spin_lock_irqsave() with spin_lock_irq(), as
suggested by Peter Zijlstra.
Reported-by: Mike Galbraith <mgalbraith@suse.de> Reported-by: Dimitri Sivanich <sivanich@sgi.com> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Paul E. McKenney [Thu, 21 Jun 2012 00:07:14 +0000 (17:07 -0700)]
rcu: Move RCU grace-period cleanup into kthread
As a first step towards allowing grace-period cleanup to be preemptible,
this commit moves the RCU grace-period cleanup into the same kthread
that is now used to initialize grace periods. This is needed to keep
scheduling latency down to a dull roar.
[ paulmck: Get rid of stray spin_lock_irqsave() calls. ]
Reported-by: Mike Galbraith <mgalbraith@suse.de> Reported-by: Dimitri Sivanich <sivanich@sgi.com> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Paul E. McKenney [Wed, 20 Jun 2012 00:18:20 +0000 (17:18 -0700)]
rcu: Allow RCU grace-period initialization to be preempted
RCU grace-period initialization is currently carried out with interrupts
disabled, which can result in 200-microsecond latency spikes on systems
on which RCU has been configured for 4096 CPUs. This patch therefore
makes the RCU grace-period initialization be preemptible, which should
eliminate those latency spikes. Similar spikes from grace-period cleanup
and the forcing of quiescent states will be dealt with similarly by later
patches.
Reported-by: Mike Galbraith <mgalbraith@suse.de> Reported-by: Dimitri Sivanich <sivanich@sgi.com> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
The next step in reducing RCU's grace-period initialization latency on
large systems will make this initialization preemptible. Unfortunately,
making the grace-period initialization subject to interrupts (let alone
preemption) exposes the following race on systems whose rcu_node tree
contains more than one node:
1. CPU 31 starts initializing the grace period, including the
first leaf rcu_node structures, and is then preempted.
2. CPU 0 refers to the first leaf rcu_node structure, and notes
that a new grace period has started. It passes through a
quiescent state shortly thereafter, and informs the RCU core
of this rite of passage.
3. CPU 0 enters an RCU read-side critical section, acquiring
a pointer to an RCU-protected data item.
4. CPU 31 takes an interrupt whose handler removes the data item
referenced by CPU 0 from the data structure, and registers an
RCU callback in order to free it.
5. CPU 31 resumes initializing the grace period, including its
own rcu_node structure. In invokes rcu_start_gp_per_cpu(),
which advances all callbacks, including the one registered
in #4 above, to be handled by the current grace period.
6. The remaining CPUs pass through quiescent states and inform
the RCU core, but CPU 0 remains in its RCU read-side critical
section, still referencing the now-removed data item.
7. The grace period completes and all the callbacks are invoked,
including the one that frees the data item that CPU 0 is still
referencing. Oops!!!
One way to avoid this race is to remove grace-period acceleration from
rcu_start_gp_per_cpu(). Now, the only reason for this acceleration was
to allow CPUs bringing RCU out of idle state to have their callbacks
invoked after only one grace period, rather than the two grace periods
that would otherwise be required. But this acceleration does not
work when RCU grace-period initialization is moved to a kthread because
the CPU posting the callback is no longer necessarily the CPU that is
initializing the resulting grace period.
This commit therefore removes this now-pointless (and soon to be dangerous)
grace-period acceleration, thus avoiding the above race.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Paul E. McKenney [Tue, 19 Jun 2012 01:36:08 +0000 (18:36 -0700)]
rcu: Move RCU grace-period initialization into a kthread
As the first step towards allowing grace-period initialization to be
preemptible, this commit moves the RCU grace-period initialization
into its own kthread. This is needed to keep large-system scheduling
latency at reasonable levels.
Also change raw_spin_lock_irqsave() to raw_spin_lock_irq() as suggested
by Peter Zijlstra in review comments.
Reported-by: Mike Galbraith <mgalbraith@suse.de> Reported-by: Dimitri Sivanich <sivanich@sgi.com> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Paul E. McKenney [Sat, 22 Sep 2012 20:55:30 +0000 (13:55 -0700)]
rcu: Fix day-one dyntick-idle stall-warning bug
Each grace period is supposed to have at least one callback waiting
for that grace period to complete. However, if CONFIG_NO_HZ=n, an
extra callback-free grace period is no big problem -- it will chew up
a tiny bit of CPU time, but it will complete normally. In contrast,
CONFIG_NO_HZ=y kernels have the potential for all the CPUs to go to
sleep indefinitely, in turn indefinitely delaying completion of the
callback-free grace period. Given that nothing is waiting on this grace
period, this is also not a problem.
That is, unless RCU CPU stall warnings are also enabled, as they are
in recent kernels. In this case, if a CPU wakes up after at least one
minute of inactivity, an RCU CPU stall warning will result. The reason
that no one noticed until quite recently is that most systems have enough
OS noise that they will never remain absolutely idle for a full minute.
But there are some embedded systems with cut-down userspace configurations
that consistently get into this situation.
All this begs the question of exactly how a callback-free grace period
gets started in the first place. This can happen due to the fact that
CPUs do not necessarily agree on which grace period is in progress.
If a CPU still believes that the grace period that just completed is
still ongoing, it will believe that it has callbacks that need to wait for
another grace period, never mind the fact that the grace period that they
were waiting for just completed. This CPU can therefore erroneously
decide to start a new grace period. Note that this can happen in
TREE_RCU and TREE_PREEMPT_RCU even on a single-CPU system: Deadlock
considerations mean that the CPU that detected the end of the grace
period is not necessarily officially informed of this fact for some time.
Once this CPU notices that the earlier grace period completed, it will
invoke its callbacks. It then won't have any callbacks left. If no
other CPU has any callbacks, we now have a callback-free grace period.
This commit therefore makes CPUs check more carefully before starting a
new grace period. This new check relies on an array of tail pointers
into each CPU's list of callbacks. If the CPU is up to date on which
grace periods have completed, it checks to see if any callbacks follow
the RCU_DONE_TAIL segment, otherwise it checks to see if any callbacks
follow the RCU_WAIT_TAIL segment. The reason that this works is that
the RCU_WAIT_TAIL segment will be promoted to the RCU_DONE_TAIL segment
as soon as the CPU is officially notified that the old grace period
has ended.
This change is to cpu_needs_another_gp(), which is called in a number
of places. The only one that really matters is in rcu_start_gp(), where
the root rcu_node structure's ->lock is held, which prevents any
other CPU from starting or completing a grace period, so that the
comparison that determines whether the CPU is missing the completion
of a grace period is stable.
Reported-by: Becky Bruce <bgillbruce@gmail.com> Reported-by: Subodh Nijsure <snijsure@grid-net.com> Reported-by: Paul Walmsley <paul@pwsan.com> Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Tested-by: Paul Walmsley <paul@pwsan.com> # OMAP3730, OMAP4430 Cc: stable@vger.kernel.org
trace: Don't declare trace_*_rcuidle functions in modules
Tracepoints declare a static inline trace_*_rcuidle variant of the trace
function, to support safely generating trace events from the idle loop.
Module code never actually uses that variant of trace functions, because
modules don't run code that needs tracing with RCU idled. However, the
declaration of those otherwise unused functions causes the module to
reference rcu_idle_exit and rcu_idle_enter, which RCU does not export to
modules.
To avoid this, don't generate trace_*_rcuidle functions for tracepoints
declared in module code.
Link: http://lkml.kernel.org/r/20120905062306.GA14756@leaf Reported-by: Steven Rostedt <rostedt@goodmis.org> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Josh Triplett <josh@joshtriplett.org> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Merge branch 'fixes-for-3.6' of git://git.linaro.org/people/mszyprowski/linux-dma-mapping
Pull DMA-mapping fixes from Marek Szyprowski:
"Another set of fixes for ARM dma-mapping subsystem.
Commit e9da6e9905e6 replaced custom consistent buffer remapping code
with generic vmalloc areas. It however introduced some regressions
caused by limited support for allocations in atomic context. This
series contains fixes for those regressions.
For some subplatforms the default, pre-allocated pool for atomic
allocations turned out to be too small, so a function for setting its
size has been added.
Another set of patches adds support for atomic allocations to
IOMMU-aware DMA-mapping implementation.
The last part of this pull request contains two fixes for Contiguous
Memory Allocator, which relax too strict requirements."
* 'fixes-for-3.6' of git://git.linaro.org/people/mszyprowski/linux-dma-mapping:
ARM: dma-mapping: IOMMU allocates pages from atomic_pool with GFP_ATOMIC
ARM: dma-mapping: Introduce __atomic_get_pages() for __iommu_get_pages()
ARM: dma-mapping: Refactor out to introduce __in_atomic_pool
ARM: dma-mapping: atomic_pool with struct page **pages
ARM: Kirkwood: increase atomic coherent pool size
ARM: DMA-Mapping: print warning when atomic coherent allocation fails
ARM: DMA-Mapping: add function for setting coherent pool size from platform code
ARM: relax conditions required for enabling Contiguous Memory Allocator
mm: cma: fix alignment requirements for contiguous regions
Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dtor/input
Pull input subsystem updates from Dmitry Torokhov.
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dtor/input:
Input: wacom - add support for EMR on Cintiq 24HD touch
Input: i8042 - add Gigabyte T1005 series netbooks to noloop table
Input: imx_keypad - reset the hardware before enabling
Input: edt-ft5x06 - fix build error when compiling wthout CONFIG_DEBUG_FS
Merge branch 'upstream-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/jikos/hid
Pull HID updates from Jiri Kosina:
"It contains a fix for Eaton Ellipse MAX UPS from Alan Stern,
performance improvement (not processing debug data if noone is
interested), by Henrik Rydberg, and allowing tpkbd-driven devices to
work even with generic driver in a crippled mode, by Andres Freund."
* 'upstream-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/jikos/hid:
HID: tpkbd: work even if the new Lenovo Keyboard driver is not configured
HID: Only dump input if someone is listening
HID: add NOGET quirk for Eaton Ellipse MAX UPS
Andres Freund [Thu, 30 Aug 2012 12:37:14 +0000 (14:37 +0200)]
HID: tpkbd: work even if the new Lenovo Keyboard driver is not configured
c1dcad2d32d0252e8a3023d20311b52a187ecda3 added a new driver configured by
HID_LENOVO_TPKBD but made the hid_have_special_driver entry non-optional which
lead to a recognized but non-working device if the new driver wasn't
configured (which is the correct default).
Signed-off-by: Andres Freund <andres@anarazel.de> Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Merge tag 'stable/for-linus-3.6-rc4-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen
Pull Xen bug-fixes from Konrad Rzeszutek Wilk:
* Fix for TLB flushing introduced in v3.6
* Fix Xen-SWIOTLB not using proper DMA mask - device had 64bit but
in a 32-bit kernel we need to allocate for coherent pages from a
32-bit pool.
* When trying to re-use P2M nodes we had a one-off error and triggered
a BUG_ON check with specific CONFIG_ option.
* When doing FLR in Xen-PCI-backend we would first do FLR then save the
PCI configuration space. We needed to do it the other way around.
* tag 'stable/for-linus-3.6-rc4-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen:
xen/pciback: Fix proper FLR steps.
xen: Use correct masking in xen_swiotlb_alloc_coherent.
xen: fix logical error in tlb flushing
xen/p2m: Fix one-off error in checking the P2M tree directory.
Merge tag '3.6-pci-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci
Pull PCI updates from Bjorn Helgaas:
"Power management
- PCI/PM: Enable D3/D3cold by default for most devices
- PCI/PM: Keep parent bridge active when probing device
- PCI/PM: Fix config reg access for D3cold and bridge suspending
- PCI/PM: Add ABI document for sysfs file d3cold_allowed
Core
- PCI: Don't print anything while decoding is disabled"
* tag '3.6-pci-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci:
PCI: Don't print anything while decoding is disabled
PCI/PM: Add ABI document for sysfs file d3cold_allowed
PCI/PM: Fix config reg access for D3cold and bridge suspending
PCI/PM: Keep parent bridge active when probing device
PCI/PM: Enable D3/D3cold by default for most devices
Merge tag 'fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/arm/arm-soc
Pull ARM SoC bug fixes from Olof Johansson:
"Mostly Renesas and Atmel bugfixes this time, targeting boot and build
problems. A couple of patches for gemini and kirkwood as well. On a
whole nothing very controversial."
* tag 'fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/arm/arm-soc:
ARM: gemini: fix the gemini build
ARM: shmobile: armadillo800eva: enable rw rootfs mount
ARM: Kirkwood: Fix 'SZ_1M' undeclared here for db88f6281-bp-setup.c
ARM: shmobile: mackerel: fixup usb module order
ARM: shmobile: armadillo800eva: fixup: sound card detection order
ARM: shmobile: marzen: fixup smsc911x id for regulator
ARM: at91/feature-removal-schedule: delay at91_mci removal
ARM: mach-shmobile: armadillo800eva: Enable power button as wakeup source
ARM: mach-shmobile: armadillo800eva: Fix GPIO buttons descriptions
ARM: at91/dts: remove partial parameter in at91sam9g25ek.dts
ARM: at91/clock: fix PLLA overclock warning
ARM: at91: fix rtc-at91sam9 irq issue due to sparse irq support
ARM: at91: fix system timer irq issue due to sparse irq support
ARM: shmobile: sh73a0: fixup RELOC_BASE of intca_irq_pins_desc
Merge tag 'hwmon-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/groeck/linux-staging
Pull a hwmon fix from Guenter Roeck:
"One patch, fixing DIV_ROUND_CLOSEST to support negative dividends.
While the changes are not in the drivers/hwmon directory, the problem
primarily affects hwmon drivers, and it makes sense to push the patch
through the hwmon tree."
* tag 'hwmon-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/groeck/linux-staging:
linux/kernel.h: Fix DIV_ROUND_CLOSEST to support negative dividends
Merge branch 'rc-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/mmarek/kbuild
Pull kbuild fixes from Michal Marek:
"These are two fixes that should go into 3.6. The link-vmlinux.sh one
is obvious.
The other one fixes make firmware_install with certain configurations,
where a file in the toplevel firmware tree gets installed first, and
$(INSTALL_FW_PATH)/$$(dir <file>) results in /lib/firmware/./, which
confuses make 3.82 for some reason."
* 'rc-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/mmarek/kbuild:
firmware: fix directory creation rule matching with make 3.82
link-vmlinux.sh: Fix stray "echo" in error message
When we do FLR and save PCI config we did it in the wrong order.
The end result was that if a PCI device was unbind from
its driver, then binded to xen-pciback, and then back to its
driver we would get:
Merge tag 'mmc-fixes-for-3.6-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/cjb/mmc
Pull MMC fixes from Chris Ball:
- a firmware bug on several Samsung MoviNAND eMMC models causes
permanent corruption on the device when secure erase and secure trim
requests are made, so we disable those requests on these eMMC devices.
- atmel-mci: fix a hang with some SD cards by waiting for not-busy flag.
- dw_mmc: low-power mode breaks SDIO interrupts; fix PIO error handling;
fix handling of error interrupts.
- mxs-mmc: fix deadlocks; fix compile error due to dma.h arch change.
- omap: fix broken PIO mode causing memory corruption.
- sdhci-esdhc: fix card detection.
* tag 'mmc-fixes-for-3.6-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/cjb/mmc:
mmc: omap: fix broken PIO mode
mmc: card: Skip secure erase on MoviNAND; causes unrecoverable corruption.
mmc: dw_mmc: Disable low power mode if SDIO interrupts are used
mmc: dw_mmc: fix error handling in PIO mode
mmc: dw_mmc: correct mishandling error interrupt
mmc: dw_mmc: amend using error interrupt status
mmc: atmel-mci: not busy flag has also to be used for read operations
mmc: sdhci-esdhc: break out early if clock is 0
mmc: mxs-mmc: fix deadlock caused by recursion loop
mmc: mxs-mmc: fix deadlock in SDIO IRQ case
mmc: bfin_sdh: fix dma_desc_array build error
arch/um/os-Linux/time.c: In function 'deliver_alarm':
arch/um/os-Linux/time.c:117:3: error: too few arguments to function 'alarm_handler'
arch/um/os-Linux/internal.h:1:6: note: declared here
The error was introduced by commit d3c1cfcd ("um: pass siginfo to guest
process") in 3.6-rc1.
Merge branch 'merge' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc
Pull powerpc fixes from Benjamin Herrenschmidt:
"Here are a few fixes for 3.6 that were piling up while I was away or
busy (I was mostly MIA a week or two before San Diego).
Some fixes from Anton fixing up issues with our relatively new DSCR
control feature, and a few other fixes that are either regressions or
bugs nasty enough to warrant not waiting."
* 'merge' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc:
powerpc: Don't use __put_user() in patch_instruction
powerpc: Make sure IPI handlers see data written by IPI senders
powerpc: Restore correct DSCR in context switch
powerpc: Fix DSCR inheritance in copy_thread()
powerpc: Keep thread.dscr and thread.dscr_inherit in sync
powerpc: Update DSCR on all CPUs when writing sysfs dscr_default
powerpc/powernv: Always go into nap mode when CPU is offline
powerpc: Give hypervisor decrementer interrupts their own handler
powerpc/vphn: Fix arch_update_cpu_topology() return value
Merge tag 'gpio-fixes-for-v3.6' of git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-gpio
Pull GPIO fixes from Linus Walleij:
"These are some GPIO regression fixes for v3.6:
- Erroneous debug message from of_get_named_gpio_flags()
- Make sure the MC9S08DZ60 GPIO driver depend on I2C being compiled
in (not module) or allmodconfig breaks.
- Check return value from irq_alloc_descs() in the Emma Mobile GPIO
driver.
- Assign the owner field for the rdc321x driver so the module won't
be removed if it has active GPIOs."
* tag 'gpio-fixes-for-v3.6' of git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-gpio:
gpio: rdc321x: Prevent removal of modules exporting active GPIOs
gpio: em: Fix checking return value of irq_alloc_descs
gpio: mc9s08dz60: Fix build error if I2C=m
gpio: Fix debug message in of_get_named_gpio_flags()
Merge tag 'sound-3.6' of git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound
Pull sound fixes from Takashi Iwai:
"There are nothing scaring, contains only small fixes for HD-audio and
USB-audio:
- EPSS regression fix and GPIO fix for HD-audio IDT codecs
- A series of USB-audio regression fixes that are found since 3.5
kernel"
* tag 'sound-3.6' of git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound:
ALSA: snd-usb: fix cross-interface streaming devices
ALSA: snd-usb: fix calls to next_packet_size
ALSA: snd-usb: restore delay information
ALSA: snd-usb: use list_for_each_safe for endpoint resources
ALSA: snd-usb: Fix URB cancellation at stream start
ALSA: hda - Don't trust codec EPSS bit for IDT 92HD83xx & co
ALSA: hda - Avoid unnecessary parameter read for EPSS
ALSA: hda - Do not set GPIOs for speakers on IDT if there are no speakers
Merge tag 'fbdev-fixes-for-3.6-1' of git://github.com/schandinat/linux-2.6
Pull fbdev fixes from Florian Tobias Schandinat:
- a fix by Paul Cercueil to prevent a possible buffer overflow
- a fix by Bruno Prémont to prevent a rare sleep in invalid context
- a fix by Julia Lawall for a double free in auo_k190x
- a fix by Dan Carpenter to prevent a division by zero in mb862xxfb
- a regression fix by Tomi Valkeinen for the SDI output in OMAP
- a fix by Grazvydas Ignotas to fix the console colors in OMAP
* tag 'fbdev-fixes-for-3.6-1' of git://github.com/schandinat/linux-2.6:
OMAPFB: fix framebuffer console colors
OMAPDSS: Fix SDI PLL locking
video: mb862xxfb: prevent divide by zero bug
drivers/video/auo_k190x.c: drop kfree of devm_kzalloc's data
fbcon: Fix bit_putcs() call to kmalloc(s, GFP_KERNEL)
fbcon: prevent possible buffer overflow.
Merge tag 'upstream-3.6-rc5' of git://git.infradead.org/linux-ubi
Pull ubi fix from Artem Bityutskiy:
"A single small fix for memory deallocation: we allocated memory using
'kmem_cache_alloc()' but were freeing it using 'kfree()' in some
cases. Now we fix this by using 'kmem_cache_free()' instead."
* tag 'upstream-3.6-rc5' of git://git.infradead.org/linux-ubi:
UBI: fix a horrible memory deallocation bug
Fix order of arguments to compat_put_time[spec|val]
Commit 644595f89620 ("compat: Handle COMPAT_USE_64BIT_TIME in
net/socket.c") introduced a bug where the helper functions to take
either a 64-bit or compat time[spec|val] got the arguments in the wrong
order, passing the kernel stack pointer off as a user pointer (and vice
versa).
Because of the user address range check, that in turn then causes an
EFAULT due to the user pointer range checking failing for the kernel
address. Incorrectly resuling in a failed system call for 32-bit
processes with a 64-bit kernel.
On odder architectures like HP-PA (with separate user/kernel address
spaces), it can be used read kernel memory.
Ronny Hegewald [Fri, 31 Aug 2012 09:57:52 +0000 (09:57 +0000)]
xen: Use correct masking in xen_swiotlb_alloc_coherent.
When running 32-bit pvops-dom0 and a driver tries to allocate a coherent
DMA-memory the xen swiotlb-implementation returned memory beyond 4GB.
The underlaying reason is that if the supplied driver passes in a
DMA_BIT_MASK(64) ( hwdev->coherent_dma_mask is set to 0xffffffffffffffff)
our dma_mask will be u64 set to 0xffffffffffffffff even if we set it to
DMA_BIT_MASK(32) previously. Meaning we do not reset the upper bits.
By using the dma_alloc_coherent_mask function - it does the proper casting
and we get 0xfffffffff.
This caused not working sound on a system with 4 GB and a 64-bit
compatible sound-card with sets the DMA-mask to 64bit.
On bare-metal and the forward-ported xen-dom0 patches from OpenSuse a coherent
DMA-memory is always allocated inside the 32-bit address-range by calling
dma_alloc_coherent_mask.
This patch adds the same functionality to xen swiotlb and is a rebase of the
original patch from Ronny Hegewald which never got upstream b/c the
underlaying reason was not understood until now.
The original email with the original patch is in:
http://old-list-archives.xen.org/archives/html/xen-devel/2010-02/msg00038.html
the original thread from where the discussion started is in:
http://old-list-archives.xen.org/archives/html/xen-devel/2010-01/msg00928.html
Signed-off-by: Ronny Hegewald <ronny.hegewald@online.de> Signed-off-by: Stefano Panella <stefano.panella@citrix.com> Acked-By: David Vrabel <david.vrabel@citrix.com> Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> CC: stable@vger.kernel.org
Alex Shi [Fri, 24 Aug 2012 08:55:13 +0000 (08:55 +0000)]
xen: fix logical error in tlb flushing
While TLB_FLUSH_ALL gets passed as 'end' argument to
flush_tlb_others(), the Xen code was made to check its 'start'
parameter. That may give a incorrect op.cmd to MMUEXT_INVLPG_MULTI
instead of MMUEXT_TLB_FLUSH_MULTI. Then it causes some page can not
be flushed from TLB.
This patch fixed this issue.
Reported-by: Jan Beulich <jbeulich@suse.com> Signed-off-by: Alex Shi <alex.shi@intel.com> Acked-by: Jan Beulich <jbeulich@suse.com> Tested-by: Yongjie Ren <yongjie.ren@intel.com> Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
* commit '4cb38750d49010ae72e718d46605ac9ba5a851b4': (6849 commits)
bcma: fix invalid PMU chip control masks
[libata] pata_cmd64x: whitespace cleanup
libata-acpi: fix up for acpi_pm_device_sleep_state API
sata_dwc_460ex: device tree may specify dma_channel
ahci, trivial: fixed coding style issues related to braces
ahci_platform: add hibernation callbacks
libata-eh.c: local functions should not be exposed globally
libata-transport.c: local functions should not be exposed globally
sata_dwc_460ex: support hardreset
ata: use module_pci_driver
drivers/ata/pata_pcmcia.c: adjust suspicious bit operation
pata_imx: Convert to clk_prepare_enable/clk_disable_unprepare
ahci: Enable SB600 64bit DMA on MSI K9AGM2 (MS-7327) v2
[libata] Prevent interface errors with Seagate FreeAgent GoFlex
drivers/acpi/glue: revert accidental license-related 6b66d95895c bits
libata-acpi: add missing inlines in libata.h
i2c-omap: Add support for I2C_M_STOP message flag
i2c: Fall back to emulated SMBus if the operation isn't supported natively
i2c: Add SCCB support
i2c-tiny-usb: Add support for the Robofuzz OSIF USB/I2C converter
...
xen/p2m: Fix one-off error in checking the P2M tree directory.
We would traverse the full P2M top directory (from 0->MAX_DOMAIN_PAGES
inclusive) when trying to figure out whether we can re-use some of the
P2M middle leafs.
Which meant that if the kernel was compiled with MAX_DOMAIN_PAGES=512
we would try to use the 512th entry. Fortunately for us the p2m_top_index
has a check for this:
powerpc: Don't use __put_user() in patch_instruction
patch_instruction() can be called very early on ppc32, when the kernel
isn't yet running at it's linked address. That can cause the !
is_kernel_addr() test in __put_user() to trip and call might_sleep()
which is very bad at that point during boot.
Use a lower level function instead for now, at least until we get to
rework ppc32 boot process to do the code patching later, like ppc64
does.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Paul Mackerras [Tue, 4 Sep 2012 18:33:08 +0000 (18:33 +0000)]
powerpc: Make sure IPI handlers see data written by IPI senders
We have been observing hangs, both of KVM guest vcpu tasks and more
generally, where a process that is woken doesn't properly wake up and
continue to run, but instead sticks in TASK_WAKING state. This
happens because the update of rq->wake_list in ttwu_queue_remote()
is not ordered with the update of ipi_message in
smp_muxed_ipi_message_pass(), and the reading of rq->wake_list in
scheduler_ipi() is not ordered with the reading of ipi_message in
smp_ipi_demux(). Thus it is possible for the IPI receiver not to see
the updated rq->wake_list and therefore conclude that there is nothing
for it to do.
In order to make sure that anything done before smp_send_reschedule()
is ordered before anything done in the resulting call to scheduler_ipi(),
this adds barriers in smp_muxed_message_pass() and smp_ipi_demux().
The barrier in smp_muxed_message_pass() is a full barrier to ensure that
there is a full ordering between the smp_send_reschedule() caller and
scheduler_ipi(). In smp_ipi_demux(), we use xchg() rather than
xchg_local() because xchg() includes release and acquire barriers.
Using xchg() rather than xchg_local() makes sense given that
ipi_message is not just accessed locally.
This moves the barrier between setting the message and calling the
cause_ipi() function into the individual cause_ipi implementations.
Most of them -- those that used outb, out_8 or similar -- already had
a full barrier because out_8 etc. include a sync before the MMIO
store. This adds an explicit barrier in the two remaining cases.
These changes made no measurable difference to the speed of IPIs as
measured using a simple ping-pong latency test across two CPUs on
different cores of a POWER7 machine.
The analysis of the reason why processes were not waking up properly
is due to Milton Miller.
Cc: stable@vger.kernel.org # v3.0+ Reported-by: Milton Miller <miltonm@bga.com> Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Anton Blanchard [Mon, 3 Sep 2012 16:51:10 +0000 (16:51 +0000)]
powerpc: Restore correct DSCR in context switch
During a context switch we always restore the per thread DSCR value.
If we aren't doing explicit DSCR management
(ie thread.dscr_inherit == 0) and the default DSCR changed while
the process has been sleeping we end up with the wrong value.
Check thread.dscr_inherit and select the default DSCR or per thread
DSCR as required.
This was found with the following test case, when running with
more threads than CPUs (ie forcing context switching):
Anton Blanchard [Mon, 3 Sep 2012 16:49:47 +0000 (16:49 +0000)]
powerpc: Fix DSCR inheritance in copy_thread()
If the default DSCR is non zero we set thread.dscr_inherit in
copy_thread() meaning the new thread and all its children will ignore
future updates to the default DSCR. This is not intended and is
a change in behaviour that a number of our users have hit.
We just need to inherit thread.dscr and thread.dscr_inherit from
the parent which ends up being much simpler.
Anton Blanchard [Mon, 3 Sep 2012 16:48:46 +0000 (16:48 +0000)]
powerpc: Keep thread.dscr and thread.dscr_inherit in sync
When we update the DSCR either via emulation of mtspr(DSCR) or via
a change to dscr_default in sysfs we don't update thread.dscr.
We will eventually update it at context switch time but there is
a period where thread.dscr is incorrect.
If we fork at this point we will copy the old value of thread.dscr
into the child. To avoid this, always keep thread.dscr in sync with
reality.
Anton Blanchard [Mon, 3 Sep 2012 16:47:56 +0000 (16:47 +0000)]
powerpc: Update DSCR on all CPUs when writing sysfs dscr_default
Writing to dscr_default in sysfs doesn't actually change the DSCR -
we rely on a context switch on each CPU to do the work. There is no
guarantee we will get a context switch in a reasonable amount of time
so fire off an IPI to force an immediate change.
This issue was found with the following test case:
Paul Mackerras [Thu, 26 Jul 2012 18:51:09 +0000 (18:51 +0000)]
powerpc/powernv: Always go into nap mode when CPU is offline
The CPU hotplug code for the powernv platform currently only puts
offline CPUs into nap mode if the powersave_nap variable is set.
However, HV-style KVM on this platform requires secondary CPU threads
to be offline and in nap mode. Since we know nap mode works just
fine on all POWER7 machines, and the only machines that support the
powernv platform are POWER7 machines, this changes the code to
always put offline CPUs into nap mode, regardless of powersave_nap.
Powersave_nap still controls whether or not CPUs go into nap mode
when idle, as before.
Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Paul Mackerras [Thu, 26 Jul 2012 13:56:11 +0000 (13:56 +0000)]
powerpc: Give hypervisor decrementer interrupts their own handler
At the moment the handler for hypervisor decrementer interrupts is
the same as for decrementer interrupts, i.e. timer_interrupt().
This is bogus; if we ever do get a hypervisor decrementer interrupt
it won't have anything to do with the next timer event. In fact
the only time we get hypervisor decrementer interrupts is when one
is left pending on exit from a KVM guest.
When we get a hypervisor decrementer interrupt we don't need to do
anything special to clear it, since they are edge-triggered on the
transition of HDEC from 0 to -1. Thus this adds an empty handler
function for them. We don't need to have them masked when interrupts
are soft-disabled, so we use STD_EXCEPTION_HV instead of
MASKABLE_EXCEPTION_HV.
Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Linus Walleij [Thu, 30 Aug 2012 17:22:36 +0000 (19:22 +0200)]
ARM: gemini: fix the gemini build
Test-compiling obscure machines I notice that the gemini (which
by the way lacks a defconfig) is broken since some time back.
Adding a simple missing include makes it build again.
Signed-off-by: Linus Walleij <linus.walleij@linaro.org> Signed-off-by: Olof Johansson <olof@lixom.net>