Although NMI-based stack dumps are in principle more accurate, they are
also more likely to trigger deadlocks. This commit therefore replaces
all uses of trigger_all_cpu_backtrace() with rcu_dump_cpu_stacks(), so
that the CPU detecting an RCU CPU stall does the stack dumping.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Binding the grace-period kthreads to the timekeeping CPU resulted in
significant performance decreases for some workloads. For more detail,
see:
https://lkml.org/lkml/2014/6/3/395 for benchmark numbers
https://lkml.org/lkml/2014/6/4/218 for CPU statistics
It turns out that it is necessary to bind the grace-period kthreads
to the timekeeping CPU only when all but CPU 0 is a nohz_full CPU
on the one hand or if CONFIG_NO_HZ_FULL_SYSIDLE=y on the other.
In other cases, it suffices to bind the grace-period kthreads to the
set of non-nohz_full CPUs.
This commit therefore creates a tick_nohz_not_full_mask that is the
complement of tick_nohz_full_mask, and then binds the grace-period
kthread to the set of CPUs indicated by this new mask, which covers
the CONFIG_NO_HZ_FULL_SYSIDLE=n case. The CONFIG_NO_HZ_FULL_SYSIDLE=y
case still binds the grace-period kthreads to the timekeeping CPU.
This commit also includes the tick_nohz_full_enabled() check suggested
by Frederic Weisbecker.
Reported-by: Jet Chen <jet.chen@intel.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
[ paulmck: Created housekeeping_affine() and housekeeping_mask per
fweisbec feedback. ]
RCU priority boosting currently checks for boosting via a pointer in
task_struct. However, this is not needed: As Oleg noted, if the
rt_mutex is placed in the rcu_node instead of on the booster's stack,
the boostee can simply check it see if it owns the lock. This commit
makes this change, shrinking task_struct by one pointer and the kernel
by thirteen lines.
Suggested-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
The rcu_start_future_gp() function checks the current rcu_node's ->gpnum
and ->completed twice, once without ACCESS_ONCE() and once with it.
Which is pointless because we hold that rcu_node's ->lock at that point.
The intent was to check the current rcu_node structure and the root
rcu_node structure, the latter locklessly with ACCESS_ONCE(). This
commit therefore makes that change.
The reason that it is safe to locklessly check the root rcu_nodes's
->gpnum and ->completed fields is that we hold the current rcu_node's
->lock, which constrains the root rcu_node's ability to change its
->gpnum and ->completed fields. Of course, if there is a single rcu_node
structure, then rnp_root==rnp, and holding the lock prevents all changes.
If there is more than one rcu_node structure, then the code updates the
fields in the following order:
1. Increment rnp_root->gpnum to start new grace period.
2. Increment rnp->gpnum to initialize the current rcu_node,
continuing initialization for the new grace period.
3. Increment rnp_root->completed to end the current grace period.
4. Increment rnp->completed to continue cleaning up after the
old grace period.
So there are four possible combinations of relative values of these
four fields:
N N N N: RCU idle, new grace period must be initiated.
Although rnp_root->gpnum might be incremented immediately
after we check, that will just result in unnecessary work.
The grace period already started, and we try to start it.
N+1 N N N: RCU grace period just started. No further change is
possible because we hold rnp->lock, so the checks of
rnp_root->gpnum and rnp_root->completed are stable.
We know that our request for a future grace period will
be seen during grace-period cleanup.
N+1 N N+1 N: RCU grace period is ongoing. Because rnp->gpnum is
different than rnp->completed, we won't even look at
rnp_root->gpnum and rnp_root->completed, so the possible
concurrent change to rnp_root->completed does not matter.
We know that our request for a future grace period will
be seen during grace-period cleanup, which cannot pass
this rcu_node because we hold its ->lock.
N+1 N+1 N+1 N: RCU grace period has ended, but not yet been cleaned up.
Because rnp->gpnum is different than rnp->completed, we
won't look at rnp_root->gpnum and rnp_root->completed, so
the possible concurrent change to rnp_root->completed does
not matter. We know that our request for a future grace
period will be seen during grace-period cleanup, which
cannot pass this rcu_node because we hold its ->lock.
Therefore, despite initial appearances, the lockless check is safe.
Signed-off-by: Pranith Kumar <bobby.prani@gmail.com>
[ paulmck: Update comment to say why the lockless check is safe. ]
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
The current approach to RCU priority boosting uses an rt_mutex strictly
for its priority-boosting side effects. The rt_mutex_init_proxy_locked()
function is used by the booster to initialize the lock as held by the
boostee. The booster then uses rt_mutex_lock() to acquire this rt_mutex,
which priority-boosts the boostee. When the boostee reaches the end
of its outermost RCU read-side critical section, it checks a field in
its task structure to see whether it has been boosted, and, if so, uses
rt_mutex_unlock() to release the rt_mutex. The booster can then go on
to boost the next task that is blocking the current RCU grace period.
But reasonable implementations of rt_mutex_unlock() might result in the
boostee referencing the rt_mutex's data after releasing it. But the
booster might have re-initialized the rt_mutex between the time that the
boostee released it and the time that it later referenced it. This is
clearly asking for trouble, so this commit introduces a completion that
forces the booster to wait until the boostee has completely finished with
the rt_mutex, thus avoiding the case where the booster is re-initializing
the rt_mutex before the last boostee's last reference to that rt_mutex.
This of course does introduce some overhead, but the priority-boosting
code paths are miles from any possible fastpath, and the overhead of
executing the completion will normally be quite small compared to the
overhead of priority boosting and deboosting, so this should be OK.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
The m68k architecture aligns only to 16-bit boundaries, which can cause
the align-to-32-bits check in __call_rcu() to trigger. Because there is
currently no known potential need for more than one low-order bit, this
commit loosens the check to 16-bit boundaries.
Reported-by: Greg Ungerer <gerg@uclinux.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Lai Jiangshan <laijs@cn.fujitsu.com>
RCU contains code of the following forms:
ACCESS_ONCE(x)++;
ACCESS_ONCE(x) += y;
ACCESS_ONCE(x) -= y;
Now these constructs do operate correctly, but they really result in a
pair of volatile accesses, one to do the load and another to do the store.
This can be confusing, as the casual reader might well assume that (for
example) gcc might generate a memory-to-memory add instruction for each
of these three cases. In fact, gcc will do no such thing. Also, there
is a good chance that the kernel will move to separate load and store
variants of ACCESS_ONCE(), and constructs like the above could easily
confuse both people and scripts attempting to make that sort of change.
Finally, most of RCU's read-modify-write uses of ACCESS_ONCE() really
only need the store to be volatile, so that the read-modify-write form
might be misleading.
This commit therefore changes the above forms in RCU so that each instance
of ACCESS_ONCE() either does a load or a store, but not both. In a few
cases, ACCESS_ONCE() was not critical, for example, for maintaining
statisitics. In these cases, ACCESS_ONCE() has been dispensed with
entirely.
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
In kernels built with CONFIG_NO_HZ_FULL, tick_do_timer_cpu is constant
once boot completes. Thus, there is no need to wrap it in ACCESS_ONCE()
in code that is built only when CONFIG_NO_HZ_FULL. This commit therefore
removes the redundant ACCESS_ONCE().
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Reviewed-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Those two arrays are being passed to lockdep_init_map(), which expects
const char *, and are stored in lockdep_map the same way.
Cc: Dipankar Sarma <dipankar@in.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Fabian Frederick <fabf@skynet.be>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Enabling NO_HZ_FULL currently has the side effect of enabling callback
offloading on all CPUs. This results in lots of additional rcuo kthreads,
and can also increase context switching and wakeups, even in cases where
callback offloading is neither needed nor particularly desirable. This
commit therefore enables callback offloading on a given CPU only if
specifically requested at build time or boot time, or if that CPU has
been specifically designated (again, either at build time or boot time)
as a nohz_full CPU.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
An 80-CPU system with a context-switch-heavy workload can require so
many NOCB kthread wakeups that the RCU grace-period kthreads spend several
tens of percent of a CPU just awakening things. This clearly will not
scale well: If you add enough CPUs, the RCU grace-period kthreads would
get behind, increasing grace-period latency.
To avoid this problem, this commit divides the NOCB kthreads into leaders
and followers, where the grace-period kthreads awaken the leaders each of
whom in turn awakens its followers. By default, the number of groups of
kthreads is the square root of the number of CPUs, but this default may
be overridden using the rcutree.rcu_nocb_leader_stride boot parameter.
This reduces the number of wakeups done per grace period by the RCU
grace-period kthread by the square root of the number of CPUs, but of
course by shifting those wakeups to the leaders. In addition, because
the leaders do grace periods on behalf of their respective followers,
the number of wakeups of the followers decreases by up to a factor of two.
Instead of being awakened once when new callbacks arrive and again
at the end of the grace period, the followers are awakened only at
the end of the grace period.
For a numerical example, in a 4096-CPU system, the grace-period kthread
would awaken 64 leaders, each of which would awaken its 63 followers
at the end of the grace period. This compares favorably with the 79
wakeups for the grace-period kthread on an 80-CPU system.
Reported-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Commit ac1bea8578 (Make cond_resched() report RCU quiescent states)
fixed a problem where a CPU looping in the kernel with but one runnable
task would give RCU CPU stall warnings, even if the in-kernel loop
contained cond_resched() calls. Unfortunately, in so doing, it introduced
performance regressions in Anton Blanchard's will-it-scale "open1" test.
The problem appears to be not so much the increased cond_resched() path
length as an increase in the rate at which grace periods complete, which
increased per-update grace-period overhead.
This commit takes a different approach to fixing this bug, mainly by
moving the RCU-visible quiescent state from cond_resched() to
rcu_note_context_switch(), and by further reducing the check to a
simple non-zero test of a single per-CPU variable. However, this
approach requires that the force-quiescent-state processing send
resched IPIs to the offending CPUs. These will be sent only once
the grace period has reached an age specified by the boot/sysfs
parameter rcutree.jiffies_till_sched_qs, or once the grace period
reaches an age halfway to the point at which RCU CPU stall warnings
will be emitted, whichever comes first.
Reported-by: Dave Hansen <dave.hansen@intel.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Christoph Lameter <cl@gentwo.org>
Cc: Mike Galbraith <umgwanakikbuti@gmail.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
[ paulmck: Made rcu_momentary_dyntick_idle() as suggested by the
ktest build robot. Also fixed smp_mb() comment as noted by
Oleg Nesterov. ]
Merge with e552592e (Reduce overhead of cond_resched() checks for RCU)
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Currently, call_rcu() relies on implicit allocation and initialization
for the debug-objects handling of RCU callbacks. If you hammer the
kernel hard enough with Sasha's modified version of trinity, you can end
up with the sl*b allocators recursing into themselves via this implicit
call_rcu() allocation.
This commit therefore exports the debug_init_rcu_head() and
debug_rcu_head_free() functions, which permits the allocators to allocated
and pre-initialize the debug-objects information, so that there no longer
any need for call_rcu() to do that initialization, which in turn prevents
the recursion into the memory allocators.
Reported-by: Sasha Levin <sasha.levin@oracle.com>
Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Looks-good-to: Christoph Lameter <cl@linux.com>
Some sysrq handlers can run for a long time, because they dump a lot
of data onto a serial console. Having RCU stall warnings pop up in
the middle of them only makes the problem worse.
This commit provides rcu_sysrq_start() and rcu_sysrq_end() APIs to
temporarily suppress RCU CPU stall warnings while a sysrq request is
handled.
Signed-off-by: Rik van Riel <riel@redhat.com>
[ paulmck: Fix TINY_RCU build error. ]
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
The variable and struct both having the name "rcu_state" confuses
sparse in some situations, so this commit changes the variable to
"rcu_state_p" in order to avoid this confusion. This also makes
things easier for human readers.
Signed-off-by: Uma Sharma <uma.sharma523@gmail.com>
[ paulmck: Changed the declaration and several additional uses. ]
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
The torture tests are designed to run in isolation, but do not enforce
this isolation. This commit therefore checks for concurrent torture
tests, and refuses to start new tests while old tests are running.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
There are usually lots of readers and only one writer, so if there has
to be a choice, we would want rcu_torture_writer to win. This commit
therefore removes the set_user_nice() from rcu_torture_writer().
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
The rcu_torture_reader() function uses an on-stack timer_list structure
which it initializes with setup_timer_on_stack(). However, it fails to
use destroy_timer_on_stack() before exiting, which results in leaking a
tracking object if DEBUG_OBJECTS is enabled. This commit therefore
invokes destroy_timer_on_stack() to avoid this leakage.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
The original rcu_torture_writer() avoided testing the synchronous
grace-period primitives because they were simply wrappers around
call_rcu() invocations. The testing of these synchronous primitives
was delegated to the fake writers. However, there really is no excuse
not to test them, especially in the case of SRCU, where the wrappering
is somewhat more elaborate. This commit therefore makes the default
rcutorture parameters cause rcu_torture_writer() to include synchronous
grace-period primitives in its testing.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
This commit adds rcutorture testing for get_state_synchronize_rcu()
and cond_synchronize_rcu().
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
The return value from torture_create_kthread() is currently ignored
when creating the rcu_torture_fqs kthread. This commit therefore
captures the return value so that it can be tested for errors.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
The rcu_torture_reader() function currently uses schedule(). This commit
therefore speeds things up a bit by substituting cond_resched().
This change makes rcu_torture_reader() more CPU-bound, so this commit
also adjusts the number of readers (the "nreaders" module parameter,
which feeds into the "nrealreaders" variable) to allow one CPU to be
free of readers on SMP systems. The point of this is to increase the
probability that readers will be watching while an updater makes a change.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Given a CPU running a loop containing cond_resched(), with no
other tasks runnable on that CPU, RCU will eventually report RCU
CPU stall warnings due to lack of quiescent states. Fortunately,
every call to cond_resched() is a perfectly good quiescent state.
Unfortunately, invoking rcu_note_context_switch() is a bit heavyweight
for cond_resched(), especially given the need to disable preemption,
and, for RCU-preempt, interrupts as well.
This commit therefore maintains a per-CPU counter that causes
cond_resched(), cond_resched_lock(), and cond_resched_softirq() to call
rcu_note_context_switch(), but only about once per 256 invocations.
This ratio was chosen in keeping with the relative time constants of
RCU grace periods.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
This commit allows rcutorture to print additional state for the
RCU grace-period kthreads in cases where RCU seems reluctant to
start a new grace period.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
This commit adds a call to rcutorture_trace_dump() to dump the ftrace
buffer when the RCU grace period stalls in order to help debug the
stall. Note that this is different than the RCU CPU stall warning,
as it is rcutorture detecting the stall rather than the underlying RCU
implementation.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
The srcu_torture_stats() function prints SRCU's per-CPU c[] array with
an unsigned format, which means that the number one less than zero is
a very large number. This commit therefore prints this array with a
signed format in order to improve readability of the rcutorture output.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Mark functions as static in kernel/rcu/torture.c because they are not
used outside this file.
This eliminates the following warning in kernel/rcu/torture.c:
kernel/rcu/torture.c:902:6: warning: no previous prototype for ‘rcutorture_trace_dump’ [-Wmissing-prototypes]
kernel/rcu/torture.c:1572:6: warning: no previous prototype for ‘rcu_torture_barrier_cbf’ [-Wmissing-prototypes]
Signed-off-by: Rashika Kheria <rashika.kheria@gmail.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
The rcutorture output currently does not distinguish between stalls in
the RCU implementation and stalls in the rcu_torture_writer() kthreads.
This commit therefore adds some diagnostics to help distinguish between
these two conditions, at least for the non-SRCU implementations. (SRCU
does not provide evidence of update-side forward progress by design.)
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
__this_cpu_ptr is being phased out.
One special case is increment_cpu_stall_ticks().
A per cpu variable is incremented so use raw_cpu_inc().
Cc: Dipankar Sarma <dipankar@in.ibm.com>
Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Currently, small systems move back into RCU_SYSIDLE_NOT from
RCU_SYSIDLE_SHORT and large systems do not. This works because moving
aggressively to RCU_SYSIDLE_NOT affects only performance, not correctness,
and on small systems, the performance impact should be negligible. That
said, this difference does make RCU a bit more complex, and RCU does not
seem to be suffering from any lack of complexity. This commit therefore
adjusts small-system operation to match that of large systems, so that
the state never moves back to RCU_SYSIDLE_NOT from RCU_SYSIDLE_SHORT.
Reported-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Currently, RCU binds the grace-period kthreads to the timekeeping
CPU only if CONFIG_NO_HZ_FULL_SYSIDLE=y. This means that these
kthreads must be bound manually when CONFIG_NO_HZ_FULL_SYSIDLE=n and
CONFIG_NO_HZ_FULL=y: Otherwise, these kthreads will induce OS jitter on
random CPUs. Given that we are trying to reduce the amount of manual
tweaking required to make CONFIG_NO_HZ_FULL=y work nicely, this commit
makes this binding happen when CONFIG_NO_HZ_FULL=y, even in cases where
CONFIG_NO_HZ_FULL_SYSIDLE=n.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
This patch merges the function rcu_force_quiescent_state() with
rcu_sched_force_quiescent_state(), using the rcu_state pointer. Firstly,
the rcu_sched_force_quiescent_state() function is deleted from the file
kernel/rcu/tree.c. Also, the rcu_force_quiescent_state() function that was
calling force_quiescent_state with the argument rcu_preempt_state pointer
was deleted as well. The new function that combines the old ones uses
the rcu_state pointer and is located after rcu_batches_completed_bh()
in kernel/rcu/tree.c.
Signed-off-by: Andreea-Cristina Bernat <bernat.ada@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
kfree_call_rcu is defined two times. When defined under CONFIG_TREE_PREEMPT_RCU,
it uses rcu_preempt_state. Otherwise, it uses rcu_sched_state.
This patch uses the rcu_state_pointer to combine the two definitions into one.
The resulting function is placed after the closing of the preprocessor
conditional CONFIG_TREE_PREEMPT_RCU.
Signed-off-by: Andreea-Cristina Bernat <bernat.ada@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
This patch replaces NR_CPUS with nr_cpu_ids as NR_CPUS should
consider cpumask_var_t.
Signed-off-by: Himangi Saraogi <himangi774@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
This patch adds event tracing to dyntick_save_progress_counter() in the case
where it returns 1. I used the tracepoint string "dti" because this function
returns 1 in case the CPU is in dynticks idle mode.
Signed-off-by: Andreea-Cristina Bernat <bernat.ada@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Some of the accesses to the rcu_state structure's ->jiffies_stall
field are unprotected. This patch protects them with ACCESS_ONCE().
The following coccinelle script was used to acheive this:
/* coccinelle script to protect uses of ->jiffies_stall with ACCESS_ONCE() */
@@
identifier a;
@@
(
ACCESS_ONCE(a->jiffies_stall)
|
- a->jiffies_stall
+ ACCESS_ONCE(a->jiffies_stall)
)
Signed-off-by: Himangi Saraogi <himangi774@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
The rcu_start_gp_advanced() function currently uses irq_work_queue()
to defer wakeups of the RCU grace-period kthread. This deferring
is necessary to avoid RCU-scheduler deadlocks involving the rcu_node
structure's lock, meaning that RCU cannot call any of the scheduler's
wake-up functions while holding one of these locks.
Unfortunately, the second and subsequent calls to irq_work_queue() are
ignored, and the first call will be ignored (aside from queuing the work
item) if the scheduler-clock tick is turned off. This is OK for many
uses, especially those where irq_work_queue() is called from an interrupt
or softirq handler, because in those cases the scheduler-clock-tick state
will be re-evaluated, which will turn the scheduler-clock tick back on.
On the next tick, any deferred work will then be processed.
However, this strategy does not always work for RCU, which can be invoked
at process level from idle CPUs. In this case, the tick might never
be turned back on, indefinitely defering a grace-period start request.
Note that the RCU CPU stall detector cannot see this condition, because
there is no RCU grace period in progress. Therefore, we can (and do!)
see long tens-of-seconds stalls in grace-period handling. In theory,
we could see a full grace-period hang, but rcutorture testing to date
has seen only the tens-of-seconds stalls. Event tracing demonstrates
that irq_work_queue() is being called repeatedly to no effect during
these stalls: The "newreq" event appears repeatedly from a task that is
not one of the grace-period kthreads.
In theory, irq_work_queue() might be fixed to avoid this sort of issue,
but RCU's requirements are unusual and it is quite straightforward to pass
wake-up responsibility up through RCU's call chain, so that the wakeup
happens when the offending locks are released.
This commit therefore makes this change. The rcu_start_gp_advanced(),
rcu_start_future_gp(), rcu_accelerate_cbs(), rcu_advance_cbs(),
__note_gp_changes(), and rcu_start_gp() functions now return a boolean
which indicates when a wake-up is needed. A new rcu_gp_kthread_wake()
does the wakeup when it is necessary and safe to do so: No self-wakes,
no wake-ups if the ->gp_flags field indicates there is no need (as in
someone else did the wake-up before we got around to it), and no wake-ups
before the grace-period kthread has been created.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Some of the uses of the rcu_state structure's ->jiffies_stall field
do not use ACCESS_ONCE(), despite there being unprotected accesses.
This commit therefore uses the ACCESS_ONCE() macro to protect this field.
Signed-off-by: Iulia Manda <iulia.manda21@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
The ->preemptible field in rcu_data is only initialized in the function
rcu_init_percpu_data(), and never used. This commit therefore removes
this field.
Signed-off-by: Iulia Manda <iulia.manda21@gmail.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
In the old days, the only source of requests for future grace periods
was NOCB CPUs. This has changed: CPUs routinely post requests for
future grace periods in order to promote power efficiency and reduce
OS jitter with minimal impact on grace-period latency. This commit
therefore updates cpu_needs_another_gp() to invoke rcu_future_needs_gp()
instead of rcu_nocb_needs_gp(). The latter is no longer used, so is
now removed. This commit also adds tracing for the irq_work_queue()
wakeup case.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
The print_other_cpu_stall() and print_cpu_stall() functions print
grace-period numbers using an unsigned format, which means that the number
one less than zero is a very large number. This commit therefore causes
these numbers to be printed with a signed format in order to improve
readability of the RCU CPU stall-warning output.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Signed-off-by: Liu Ping Fan <kernelfans@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
A number of ->gp_flags accesses don't have ACCESS_ONCE(), but all of
the can race against other loads or stores. This commit therefore
applies ACCESS_ONCE() to the unprotected ->gp_flags accesses.
Reported-by: Alexey Roytman <alexey.roytman@oracle.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Pull scheduler changes from Ingo Molnar:
"Bigger changes:
- sched/idle restructuring: they are WIP preparation for deeper
integration between the scheduler and idle state selection, by
Nicolas Pitre.
- add NUMA scheduling pseudo-interleaving, by Rik van Riel.
- optimize cgroup context switches, by Peter Zijlstra.
- RT scheduling enhancements, by Thomas Gleixner.
The rest is smaller changes, non-urgnt fixes and cleanups"
* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (68 commits)
sched: Clean up the task_hot() function
sched: Remove double calculation in fix_small_imbalance()
sched: Fix broken setscheduler()
sparc64, sched: Remove unused sparc64_multi_core
sched: Remove unused mc_capable() and smt_capable()
sched/numa: Move task_numa_free() to __put_task_struct()
sched/fair: Fix endless loop in idle_balance()
sched/core: Fix endless loop in pick_next_task()
sched/fair: Push down check for high priority class task into idle_balance()
sched/rt: Fix picking RT and DL tasks from empty queue
trace: Replace hardcoding of 19 with MAX_NICE
sched: Guarantee task priority in pick_next_task()
sched/idle: Remove stale old file
sched: Put rq's sched_avg under CONFIG_FAIR_GROUP_SCHED
cpuidle/arm64: Remove redundant cpuidle_idle_call()
cpuidle/powernv: Remove redundant cpuidle_idle_call()
sched, nohz: Exclude isolated cores from load balancing
sched: Fix select_task_rq_fair() description comments
workqueue: Replace hardcoding of -20 and 19 with MIN_NICE and MAX_NICE
sys: Replace hardcoding of -20 and 19 with MIN_NICE and MAX_NICE
...
The following pattern is currently not well supported by RCU:
1. Make data element inaccessible to RCU readers.
2. Do work that probably lasts for more than one grace period.
3. Do something to make sure RCU readers in flight before #1 above
have completed.
Here are some things that could currently be done:
a. Do a synchronize_rcu() unconditionally at either #1 or #3 above.
This works, but imposes needless work and latency.
b. Post an RCU callback at #1 above that does a wakeup, then
wait for the wakeup at #3. This works well, but likely results
in an extra unneeded grace period. Open-coding this is also
a bit more semi-tricky code than would be good.
This commit therefore adds get_state_synchronize_rcu() and
cond_synchronize_rcu() APIs. Call get_state_synchronize_rcu() at #1
above and pass its return value to cond_synchronize_rcu() at #3 above.
This results in a call to synchronize_rcu() if no grace period has
elapsed between #1 and #3, but requires only a load, comparison, and
memory barrier if a full grace period did elapse.
Requested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
The kbuild test bot uncovered an implicit dependence on the
trace header being present before rcu.h in ia64 allmodconfig
that looks like this:
In file included from kernel/ksysfs.c:22:0:
kernel/rcu/rcu.h: In function '__rcu_reclaim':
kernel/rcu/rcu.h:107:3: error: implicit declaration of function 'trace_rcu_invoke_kfree_callback' [-Werror=implicit-function-declaration]
kernel/rcu/rcu.h:112:3: error: implicit declaration of function 'trace_rcu_invoke_callback' [-Werror=implicit-function-declaration]
cc1: some warnings being treated as errors
Looking at other rcu.h users, we can find that they all
were sourcing the trace header in advance of rcu.h itself,
as seen in the context of this diff. There were also some
inconsistencies as to whether it was or wasn't sourced based
on the parent tracing Kconfig.
Rather than "fix" it at each use site, and have inconsistent
use based on whether "#ifdef CONFIG_RCU_TRACE" was used or not,
lets just source the trace header just once, in the actual consumer
of it, which is rcu.h itself. We include it unconditionally, as
build testing shows us that is a hard requirement for some files.
Reported-by: kbuild test robot <fengguang.wu@intel.com>
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
This commit fixes the follwoing warning:
kernel/ksysfs.c:143:5: warning: symbol 'rcu_expedited' was not declared. Should it be static?
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
[ paulmck: Moved the declaration to include/linux/rcupdate.h to avoid
including the RCU-internal rcu.h file outside of RCU. ]
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
This commit adds a deliberately buggy RCU implementation into rcutorture
to allow easy checking that rcutorture correctly flags buggy RCU
implementations.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
The specific torture modules (like rcutorture) need to call
torture_cleanup() in any case, so this commit makes torture_cleanup()
deal with torture_shutdown_cleanup() and torture_stutter_cleanup() so
that the specific modules don't have to deal with these details.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Stopping of kthreads is not RCU-specific, so this commit abstracts
out torture_stop_kthread(), saving a few lines of code in the process.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Creation of kthreads is not RCU-specific, so this commit abstracts
out torture_create_kthread(), saving a few tens of lines of code in
the process.
This change requires modifying VERBOSE_TOROUT_ERRSTRING() to take a
non-const string, so that _torture_create_kthread() can avoid an
open-coded substitute.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
This commit adds a missing error return to the code path that creates
the rcu_torture_barrier() kthread.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Not all of the rcutorture kthreads waited for kthread_should_stop()
before returning from their top-level functions, and none of them
used torture_shutdown_absorb() properly. These problems can result in
segfaults and hangs at shutdown time, and some recent changes perturbed
timing sufficiently to make them much more probable. This commit
therefore creates a torture_kthread_stopping() function that does the
proper kthread shutdown dance in one centralized location.
Accommodate this grouping by making VERBOSE_TOROUT_STRING() capable of
taking a non-const string as its argument, which allows the new
torture_kthread_stopping() to pass its "title" argument directly to
the updated version of VERBOSE_TOROUT_STRING().
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
A few "stealth-start rcutorture kthreads" have accumulated over the years,
so this commit adds console-log announcements (but only if the torture
tests are running verbose).
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
This commit applies some simple cleanups to rcu_torture_init() error
checking.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Because auto-shutdown of torture testing is not specific to RCU,
this commit moves the auto-shutdown function to kernel/torture.c.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Because stuttering the test load (stopping and restarting it) is useful
for non-RCU testing, this commit moves the load-stuttering functionality
to kernel/torture.c.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
This commit introduces the torture_must_stop() function in order to
keep use of the fullstop variable local to kernel/torture.c. There
is also a torture_must_stop_irq() counterpart for use from RCU callbacks,
timeout handlers, and the like.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Because handling the race between rmmod and system shutdown is not
specific to RCU, this commit abstracts torture_shutdown_notify(),
placing this code into kernel/torture.c. This change also allows
fullstop_mutex to be private to kernel/torture.c.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
This commit creates a torture_cleanup() that handles the generic
cleanup actions local to kernel/torture.c.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
This commit creates torture_init_begin() and torture_init_end() functions
to abstract locking and allow the torture_type and verbose variables
in kernel/torture.o to become static. With a bit more abstraction,
fullstop_mutex will also become static.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Because online/offline torturing is not specific to RCU, this commit
abstracts it into the kernel/torture.c module to allow other torture
tests to use it.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
The torture_shuffle() function forces each CPU in turn to go idle
periodically in order to check for problems interacting with per-CPU
variables and with dyntick-idle mode. Because this sort of debugging
is not specific to RCU, this commit abstracts that functionality.
This in turn requires abstracting some additional infrastructure.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Because handling races between rmmod and normal shutdown is not specific
to rcutorture, this commit renames rcutorture_shutdown_absorb() to
torture_shutdown_absorb() and pulls it out into then kernel/torture.c
module. This implies pulling the fullstop mechanism into kernel/torture.c
as well.
The exporting of fullstop and fullstop_mutex is ugly and must die.
And it does in fact die in later commits that introduce higher-level
APIs that encapsulate both of these variables.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>`
These diagnostic macros are not confined to torturing RCU, so this commit
makes them available to other torture tests. Also removed the do-while
from TOROUT_STRING() in response to checkpatch complaints.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Since it doesn't do printk()s anymore anyway, this commit renames these
macros from PRINTK to TOROUT (short for torture output).
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Create a torture_param() macro and apply it to rcutorture in order to
save a few lines of code. This same macro may be applied to other
torture frameworks.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Because rcu_torture_random() will be used by the locking equivalent to
rcutorture, pull it out into its own module. This new module cannot
be separately configured, instead, use the Kconfig "select" statement
from the Kconfig options of tests depending on it.
Suggested-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
This commit does a code-style cleanup so that the first curly brace
of an initializer does not appear at the beginning of a line.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
If CONFIG_RCU_NOCB_CPU_ALL=y, then no CPU will ever have RCU callbacks
because these callbacks will instead be handled by the rcuo kthreads.
However, the current version of RCU_FAST_NO_HZ nevertheless checks for RCU
callbacks. This commit therefore creates static inline implementations
of rcu_prepare_for_idle() and rcu_cleanup_after_idle() that are no-ops
when CONFIG_RCU_NOCB_CPU_ALL=y.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
If CONFIG_RCU_NOCB_CPU_ALL=y, then rcu_needs_cpu() will always
return false, however, the current version nevertheless checks
for RCU callbacks. This commit therefore creates a static inline
implementation of rcu_needs_cpu() that unconditionally returns false
when CONFIG_RCU_NOCB_CPU_ALL=y.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
If CONFIG_RCU_NOCB_CPU_ALL=y, then rcu_is_nocb_cpu() will always
return true, however, the current version nevertheless checks
rcu_nocb_mask. This commit therefore creates a static inline
implementation of rcu_is_nocb_cpu() that unconditionally returns
true when CONFIG_RCU_NOCB_CPU_ALL=y.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
For better use of CPU idle time, allow the scheduler to select the CPU
on which the SRCU grace period work would be scheduled. This improves
idle residency time and conserves power.
This functionality is enabled when CONFIG_WQ_POWER_EFFICIENT is selected.
Cc: Lai Jiangshan <laijs@cn.fujitsu.com>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Dipankar Sarma <dipankar@in.ibm.com>
Signed-off-by: Shaibal Dutta <shaibal.dutta@broadcom.com>
[zoran.markovic@linaro.org: Rebased to latest kernel version. Added commit
message. Fixed code alignment.]
Signed-off-by: Zoran Markovic <zoran.markovic@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
This commit fixes a grammar issue in the rcu_nohz_full_cpu() comment
header, so that it is clear that the plural is CPUs not Kconfig options.
Signed-off-by: Paul Bolle <pebolle@tiscali.nl>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Because jiffies is one of a very few variables marked "volatile", there
is no need to use ACCESS_ONCE() when accessing it. This commit therefore
removes the redundant ACCESS_ONCE() wrappers.
Reported by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
All of the RCU source files have the usual GPL header, which contains a
long-obsolete postal address for FSF. To avoid the need to track the
FSF office's movements, this commit substitutes the URL where GPL may
be found.
Reported-by: Greg KH <gregkh@linuxfoundation.org>
Reported-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
The ->n_force_qs_lh field is accessed without the benefit of any
synchronization, so this commit adds the needed ACCESS_ONCE() wrappers.
Yes, increments to ->n_force_qs_lh can be lost, but contention should
be low and the field is strictly statistical in nature, so this is not
a problem.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Pull vfs updates from Al Viro:
"Assorted stuff; the biggest pile here is Christoph's ACL series. Plus
assorted cleanups and fixes all over the place...
There will be another pile later this week"
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (43 commits)
__dentry_path() fixes
vfs: Remove second variable named error in __dentry_path
vfs: Is mounted should be testing mnt_ns for NULL or error.
Fix race when checking i_size on direct i/o read
hfsplus: remove can_set_xattr
nfsd: use get_acl and ->set_acl
fs: remove generic_acl
nfs: use generic posix ACL infrastructure for v3 Posix ACLs
gfs2: use generic posix ACL infrastructure
jfs: use generic posix ACL infrastructure
xfs: use generic posix ACL infrastructure
reiserfs: use generic posix ACL infrastructure
ocfs2: use generic posix ACL infrastructure
jffs2: use generic posix ACL infrastructure
hfsplus: use generic posix ACL infrastructure
f2fs: use generic posix ACL infrastructure
ext2/3/4: use generic posix ACL infrastructure
btrfs: use generic posix ACL infrastructure
fs: make posix_acl_create more useful
fs: make posix_acl_chmod more useful
...
rcu_dereference_check_fdtable() looks very wrong,
1. rcu_my_thread_group_empty() was added by 844b9a8707 "vfs: fix
RCU-lockdep false positive due to /proc" but it doesn't really
fix the problem. A CLONE_THREAD (without CLONE_FILES) task can
hit the same race with get_files_struct().
And otoh rcu_my_thread_group_empty() can suppress the correct
warning if the caller is the CLONE_FILES (without CLONE_THREAD)
task.
2. files->count == 1 check is not really right too. Even if this
files_struct is not shared it is not safe to access it lockless
unless the caller is the owner.
Otoh, this check is sub-optimal. files->count == 0 always means
it is safe to use it lockless even if files != current->files,
but put_files_struct() has to take rcu_read_lock(). See the next
patch.
This patch removes the buggy checks and turns fcheck_files() into
__fcheck_files() which uses rcu_dereference_raw(), the "unshared"
callers, fget_light() and fget_raw_light(), can use it to avoid
the warning from RCU-lockdep.
fcheck_files() is trivially reimplemented as rcu_lockdep_assert()
plus __fcheck_files().
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Pull RCU updates from Ingo Molnar:
- add RCU torture scripts/tooling
- static analysis improvements
- update RCU documentation
- miscellaneous fixes
* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (52 commits)
rcu: Remove "extern" from function declarations in kernel/rcu/rcu.h
rcu: Remove "extern" from function declarations in include/linux/*rcu*.h
rcu/torture: Dynamically allocate SRCU output buffer to avoid overflow
rcu: Don't activate RCU core on NO_HZ_FULL CPUs
rcu: Warn on allegedly impossible rcu_read_unlock_special() from irq
rcu: Add an RCU_INITIALIZER for global RCU-protected pointers
rcu: Make rcu_assign_pointer's assignment volatile and type-safe
bonding: Use RCU_INIT_POINTER() for better overhead and for sparse
rcu: Add comment on evaluate-once properties of rcu_assign_pointer().
rcu: Provide better diagnostics for blocking in RCU callback functions
rcu: Improve SRCU's grace-period comments
rcu: Fix CONFIG_RCU_FANOUT_EXACT for odd fanout/leaf values
rcu: Fix coccinelle warnings
rcutorture: Stop tracking FSF's postal address
rcutorture: Move checkarg to functions.sh
rcutorture: Flag errors and warnings with color coding
rcutorture: Record results from repeated runs of the same test scenario
rcutorture: Test summary at end of run with less chattiness
rcutorture: Update comment in kvm.sh listing typical RCU trace events
rcutorture: Add tracing-enabled version of TREE08
...
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.15 (GNU/Linux)
iQEcBAABAgAGBQJSrhGrAAoJEHm+PkMAQRiGsNoH/jIK3CsQ2lbW7yRLXmfgtbzz
i2Kep6D4SDvmaLpLYOVC8xNYTiE8jtTbSXHomwP5wMZ63MQDhBfnEWsEWqeZ9+D9
3Q46p0QWuoBgYu2VGkoxTfygkT6hhSpwWIi3SeImbY4fg57OHiUil/+YGhORM4Qc
K4549OCTY3sIrgmWL77gzqjRUo+pQ4C73NKqZ3+5nlOmYBZC1yugk8mFwEpQkwhK
4NRNU760Fo+XIht/bINqRiPMddzC15p0mxvJy3cDW8bZa1tFSS9SB7AQUULBbcHL
+2dFlFOEb5SV1sNiNPrJ0W+h2qUh2e7kPB0F8epaBppgbwVdyQoC2u4uuLV2ZN0=
=lI2r
-----END PGP SIGNATURE-----
Merge tag 'v3.13-rc4' into core/locking
Merge Linux 3.13-rc4, to refresh this rather old tree with the latest fixes.
Signed-off-by: Ingo Molnar <mingo@kernel.org>
RCU must ensure that there is the equivalent of a full memory
barrier between any memory access preceding grace period and any
memory access following that same grace period, regardless of
which CPU(s) happen to execute the two memory accesses.
Therefore, downgrading UNLOCK+LOCK to no longer imply a full
memory barrier requires some adjustments to RCU.
This commit therefore adds smp_mb__after_unlock_lock()
invocations as needed after the RCU lock acquisitions that need
to be part of a full-memory-barrier UNLOCK+LOCK.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: <linux-arch@vger.kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/1386799151-2219-7-git-send-email-paulmck@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Function prototypes don't need to have the "extern" keyword since this
is the default behavior. Its explicit use is redundant. This commit
therefore removes them.
Signed-off-by: Teodora Baluta <teobaluta@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
If the rcutorture SRCU output exceeds 4096 bytes, for example, if you
have more than about 75 CPUs, it will overflow the current statically
allocated buffer. This commit therefore replaces this static buffer
with a dynamically buffer whose size is based on the number of CPUs.
Benefits:
- Avoids both buffer overflow and output truncation.
- Handles an arbitrarily large number of CPUs.
- Straightforward implementation.
Shortcomings:
- Some memory is wasted:
1 cpu now comsumes 50 - 60 bytes, and this patch provides 200 bytes.
Therefore, for 1K CPUs, roughly 100KB of memory will be wasted.
However, the memory is freed immediately after printing, so this
wastage should not be a problem in practice.
Testing (Fedora16 2 CPUs, 2GB RAM x86_64):
- as module, with/without "torture_type=srcu".
- build-in not boot runnable, with/without "torture_type=srcu".
- build-in let boot runnable, with/without "torture_type=srcu".
Signed-off-by: Chen Gang <gang.chen@asianux.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Whenever a CPU receives a scheduling-clock interrupt, RCU checks to see
if the RCU core needs anything from this CPU. If so, RCU raises
RCU_SOFTIRQ to carry out any needed processing.
This approach has worked well historically, but it is undesirable on
NO_HZ_FULL CPUs. Such CPUs are expected to spend almost all of their time
in userspace, so that scheduling-clock interrupts can be disabled while
there is only one runnable task on the CPU in question. Unfortunately,
raising any softirq has the potential to wake up ksoftirqd, which would
provide the second runnable task on that CPU, preventing disabling of
scheduling-clock interrupts.
What is needed instead is for RCU to leave NO_HZ_FULL CPUs alone,
relying on the grace-period kthreads' quiescent-state forcing to
do any needed RCU work on behalf of those CPUs.
This commit therefore refrains from raising RCU_SOFTIRQ on any
NO_HZ_FULL CPUs during any grace periods that have been in effect
for less than one second. The one-second limit handles the case
where an inappropriate workload is running on a NO_HZ_FULL CPU
that features lots of scheduling-clock interrupts, but no idle
or userspace time.
Reported-by: Mike Galbraith <bitbucket@online.de>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Tested-by: Mike Galbraith <bitbucket@online.de>
Toasted-by: Frederic Weisbecker <fweisbec@gmail.com>
After commit #10f39bb1b2c1 (rcu: protect __rcu_read_unlock() against
scheduler-using irq handlers), it is no longer possible to enter
the main body of rcu_read_lock_special() from an NMI, interrupt, or
softirq handler. In theory, this implies that the check for "in_irq()
|| in_serving_softirq()" must always fail, so that in theory this check
could be removed entirely.
In practice, this commit wraps this condition with a WARN_ON_ONCE().
If this warning never triggers, then the condition will be removed
entirely.
[ paulmck: And one way of triggering the WARN_ON() is if a scheduling
clock interrupt occurs in an RCU read-side critical section, setting
RCU_READ_UNLOCK_NEED_QS, which is handled by rcu_read_unlock_special().
Updated this commit to return if only that bit was set. ]
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Currently blocking in an RCU callback function will result in
"scheduling while atomic", which could be triggered for any number
of reasons. To aid debugging, this patch introduces a rcu_callback_map
that is used to tie the inappropriate voluntary context switch back
to the fact that the function is being invoked from within a callback.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
This commit documents the memory-barrier guarantees provided by
synchronize_srcu() and call_srcu().
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Each element of the rcu_state structure's ->levelspread[] array
is intended to contain the per-level fanout, where the zero-th
element corresponds to the root of the rcu_node tree, and the last
element corresponds to the leaves. In the CONFIG_RCU_FANOUT_EXACT
case, this means that the last element should be filled in
from CONFIG_RCU_FANOUT_LEAF (or from the rcu_fanout_leaf boot
parameter, if provided) and that the remaining elements should
be filled in from CONFIG_RCU_FANOUT. Unfortunately, the current
code in rcu_init_levelspread() takes the opposite approach, placing
CONFIG_RCU_FANOUT_LEAF in the zero-th element and CONFIG_RCU_FANOUT in
the remaining elements.
For typical power-of-two values, this generates odd but functional
rcu_node trees. However, other values, for example CONFIG_RCU_FANOUT=3
and CONFIG_RCU_FANOUT_LEAF=2, generate trees that can leave some CPUs
out of the grace-period computation, resulting in too-short grace periods
and therefore a broken RCU implementation.
This commit therefore fixes rcu_init_levelspread() to set the last
->levelspread[] array element from CONFIG_RCU_FANOUT_LEAF and the
remaining elements from CONFIG_RCU_FANOUT, thus generating the
intended rcu_node trees.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
This commit fixes the following coccinelle warning:
kernel/rcu/tree.c:712:9-10: WARNING: return of 0/1 in function
'rcu_lockdep_current_cpu_online' with return type bool
Return statements in functions returning bool should use
true/false instead of 1/0.
Generated by: coccinelle/misc/boolreturn.cocci
Signed-off-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Some RCU bugs have been specific to the layout of the rcu_node tree,
but RCU will silently adjust the tree at boot time if appropriate.
This obscures valuable debugging information, so print a message when
this happens.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
The srcu_barrier() docbook header left out the "sp" argument, so this
commit adds that argument's docbook text.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
The current task-level idle entry/exit code forces an entry/exit on
each call, regardless of the nesting level. This commit therefore
properly accounts for nesting.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Frederic Weisbecker <fweisbec@gmail.com>
Dave Jones got the following lockdep splat:
> ======================================================
> [ INFO: possible circular locking dependency detected ]
> 3.12.0-rc3+ #92 Not tainted
> -------------------------------------------------------
> trinity-child2/15191 is trying to acquire lock:
> (&rdp->nocb_wq){......}, at: [<ffffffff8108ff43>] __wake_up+0x23/0x50
>
> but task is already holding lock:
> (&ctx->lock){-.-...}, at: [<ffffffff81154c19>] perf_event_exit_task+0x109/0x230
>
> which lock already depends on the new lock.
>
>
> the existing dependency chain (in reverse order) is:
>
> -> #3 (&ctx->lock){-.-...}:
> [<ffffffff810cc243>] lock_acquire+0x93/0x200
> [<ffffffff81733f90>] _raw_spin_lock+0x40/0x80
> [<ffffffff811500ff>] __perf_event_task_sched_out+0x2df/0x5e0
> [<ffffffff81091b83>] perf_event_task_sched_out+0x93/0xa0
> [<ffffffff81732052>] __schedule+0x1d2/0xa20
> [<ffffffff81732f30>] preempt_schedule_irq+0x50/0xb0
> [<ffffffff817352b6>] retint_kernel+0x26/0x30
> [<ffffffff813eed04>] tty_flip_buffer_push+0x34/0x50
> [<ffffffff813f0504>] pty_write+0x54/0x60
> [<ffffffff813e900d>] n_tty_write+0x32d/0x4e0
> [<ffffffff813e5838>] tty_write+0x158/0x2d0
> [<ffffffff811c4850>] vfs_write+0xc0/0x1f0
> [<ffffffff811c52cc>] SyS_write+0x4c/0xa0
> [<ffffffff8173d4e4>] tracesys+0xdd/0xe2
>
> -> #2 (&rq->lock){-.-.-.}:
> [<ffffffff810cc243>] lock_acquire+0x93/0x200
> [<ffffffff81733f90>] _raw_spin_lock+0x40/0x80
> [<ffffffff810980b2>] wake_up_new_task+0xc2/0x2e0
> [<ffffffff81054336>] do_fork+0x126/0x460
> [<ffffffff81054696>] kernel_thread+0x26/0x30
> [<ffffffff8171ff93>] rest_init+0x23/0x140
> [<ffffffff81ee1e4b>] start_kernel+0x3f6/0x403
> [<ffffffff81ee1571>] x86_64_start_reservations+0x2a/0x2c
> [<ffffffff81ee1664>] x86_64_start_kernel+0xf1/0xf4
>
> -> #1 (&p->pi_lock){-.-.-.}:
> [<ffffffff810cc243>] lock_acquire+0x93/0x200
> [<ffffffff8173419b>] _raw_spin_lock_irqsave+0x4b/0x90
> [<ffffffff810979d1>] try_to_wake_up+0x31/0x350
> [<ffffffff81097d62>] default_wake_function+0x12/0x20
> [<ffffffff81084af8>] autoremove_wake_function+0x18/0x40
> [<ffffffff8108ea38>] __wake_up_common+0x58/0x90
> [<ffffffff8108ff59>] __wake_up+0x39/0x50
> [<ffffffff8110d4f8>] __call_rcu_nocb_enqueue+0xa8/0xc0
> [<ffffffff81111450>] __call_rcu+0x140/0x820
> [<ffffffff81111b8d>] call_rcu+0x1d/0x20
> [<ffffffff81093697>] cpu_attach_domain+0x287/0x360
> [<ffffffff81099d7e>] build_sched_domains+0xe5e/0x10a0
> [<ffffffff81efa7fc>] sched_init_smp+0x3b7/0x47a
> [<ffffffff81ee1f4e>] kernel_init_freeable+0xf6/0x202
> [<ffffffff817200be>] kernel_init+0xe/0x190
> [<ffffffff8173d22c>] ret_from_fork+0x7c/0xb0
>
> -> #0 (&rdp->nocb_wq){......}:
> [<ffffffff810cb7ca>] __lock_acquire+0x191a/0x1be0
> [<ffffffff810cc243>] lock_acquire+0x93/0x200
> [<ffffffff8173419b>] _raw_spin_lock_irqsave+0x4b/0x90
> [<ffffffff8108ff43>] __wake_up+0x23/0x50
> [<ffffffff8110d4f8>] __call_rcu_nocb_enqueue+0xa8/0xc0
> [<ffffffff81111450>] __call_rcu+0x140/0x820
> [<ffffffff81111bb0>] kfree_call_rcu+0x20/0x30
> [<ffffffff81149abf>] put_ctx+0x4f/0x70
> [<ffffffff81154c3e>] perf_event_exit_task+0x12e/0x230
> [<ffffffff81056b8d>] do_exit+0x30d/0xcc0
> [<ffffffff8105893c>] do_group_exit+0x4c/0xc0
> [<ffffffff810589c4>] SyS_exit_group+0x14/0x20
> [<ffffffff8173d4e4>] tracesys+0xdd/0xe2
>
> other info that might help us debug this:
>
> Chain exists of:
> &rdp->nocb_wq --> &rq->lock --> &ctx->lock
>
> Possible unsafe locking scenario:
>
> CPU0 CPU1
> ---- ----
> lock(&ctx->lock);
> lock(&rq->lock);
> lock(&ctx->lock);
> lock(&rdp->nocb_wq);
>
> *** DEADLOCK ***
>
> 1 lock held by trinity-child2/15191:
> #0: (&ctx->lock){-.-...}, at: [<ffffffff81154c19>] perf_event_exit_task+0x109/0x230
>
> stack backtrace:
> CPU: 2 PID: 15191 Comm: trinity-child2 Not tainted 3.12.0-rc3+ #92
> ffffffff82565b70 ffff880070c2dbf8 ffffffff8172a363 ffffffff824edf40
> ffff880070c2dc38 ffffffff81726741 ffff880070c2dc90 ffff88022383b1c0
> ffff88022383aac0 0000000000000000 ffff88022383b188 ffff88022383b1c0
> Call Trace:
> [<ffffffff8172a363>] dump_stack+0x4e/0x82
> [<ffffffff81726741>] print_circular_bug+0x200/0x20f
> [<ffffffff810cb7ca>] __lock_acquire+0x191a/0x1be0
> [<ffffffff810c6439>] ? get_lock_stats+0x19/0x60
> [<ffffffff8100b2f4>] ? native_sched_clock+0x24/0x80
> [<ffffffff810cc243>] lock_acquire+0x93/0x200
> [<ffffffff8108ff43>] ? __wake_up+0x23/0x50
> [<ffffffff8173419b>] _raw_spin_lock_irqsave+0x4b/0x90
> [<ffffffff8108ff43>] ? __wake_up+0x23/0x50
> [<ffffffff8108ff43>] __wake_up+0x23/0x50
> [<ffffffff8110d4f8>] __call_rcu_nocb_enqueue+0xa8/0xc0
> [<ffffffff81111450>] __call_rcu+0x140/0x820
> [<ffffffff8109bc8f>] ? local_clock+0x3f/0x50
> [<ffffffff81111bb0>] kfree_call_rcu+0x20/0x30
> [<ffffffff81149abf>] put_ctx+0x4f/0x70
> [<ffffffff81154c3e>] perf_event_exit_task+0x12e/0x230
> [<ffffffff81056b8d>] do_exit+0x30d/0xcc0
> [<ffffffff810c9af5>] ? trace_hardirqs_on_caller+0x115/0x1e0
> [<ffffffff810c9bcd>] ? trace_hardirqs_on+0xd/0x10
> [<ffffffff8105893c>] do_group_exit+0x4c/0xc0
> [<ffffffff810589c4>] SyS_exit_group+0x14/0x20
> [<ffffffff8173d4e4>] tracesys+0xdd/0xe2
The underlying problem is that perf is invoking call_rcu() with the
scheduler locks held, but in NOCB mode, call_rcu() will with high
probability invoke the scheduler -- which just might want to use its
locks. The reason that call_rcu() needs to invoke the scheduler is
to wake up the corresponding rcuo callback-offload kthread, which
does the job of starting up a grace period and invoking the callbacks
afterwards.
One solution (championed on a related problem by Lai Jiangshan) is to
simply defer the wakeup to some point where scheduler locks are no longer
held. Since we don't want to unnecessarily incur the cost of such
deferral, the task before us is threefold:
1. Determine when it is likely that a relevant scheduler lock is held.
2. Defer the wakeup in such cases.
3. Ensure that all deferred wakeups eventually happen, preferably
sooner rather than later.
We use irqs_disabled_flags() as a proxy for relevant scheduler locks
being held. This works because the relevant locks are always acquired
with interrupts disabled. We may defer more often than needed, but that
is at least safe.
The wakeup deferral is tracked via a new field in the per-CPU and
per-RCU-flavor rcu_data structure, namely ->nocb_defer_wakeup.
This flag is checked by the RCU core processing. The __rcu_pending()
function now checks this flag, which causes rcu_check_callbacks()
to initiate RCU core processing at each scheduling-clock interrupt
where this flag is set. Of course this is not sufficient because
scheduling-clock interrupts are often turned off (the things we used to
be able to count on!). So the flags are also checked on entry to any
state that RCU considers to be idle, which includes both NO_HZ_IDLE idle
state and NO_HZ_FULL user-mode-execution state.
This approach should allow call_rcu() to be invoked regardless of what
locks you might be holding, the key word being "should".
Reported-by: Dave Jones <davej@redhat.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
It is all too easy to forget that wait_event() does not necessarily
imply a full memory barrier. The case where it does not is where the
condition transitions to true just as wait_event() starts execution.
This is actually a feature: The standard use of wait_event() involves
locking, in which case the locks provide the needed ordering (you hold a
lock across the wake_up() and acquire that same lock after wait_event()
returns).
Given that I did forget that wait_event() does not necessarily imply a
full memory barrier in one case, this commit fixes that case. This commit
also adds comments calling out the placement of existing memory barriers
relied on by wait_event() calls.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
When an RCU CPU stall warning occurs, the CPU invokes resched_cpu() on
itself. This can help move the grace period forward in some situations,
but it would be even better to do this -before- the RCU CPU stall warning.
This commit therefore causes resched_cpu() to be called every five jiffies
once the system is halfway to an RCU CPU stall warning.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
RCU and the fine grained idle time accounting functions check
tick_nohz_enabled. But that variable is merily telling that NOHZ has
been enabled in the config and not been disabled on the command line.
But it does not tell anything about nohz being active. That's what all
this should check for.
Matthew reported, that the idle accounting on his old P1 machine
showed bogus values, when he enabled NOHZ in the config and did not
disable it on the kernel command line. The reason is that his machine
uses (refined) jiffies as a clocksource which explains why the "fine"
grained accounting went into lala land, because it depends on when the
system goes and leaves idle relative to the jiffies increment.
Provide a tick_nohz_active indicator and let RCU and the accounting
code use this instead of tick_nohz_enable.
Reported-and-tested-by: Matthew Whitehead <tedheadster@gmail.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Steven Rostedt <rostedt@goodmis.org>
Reviewed-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: john.stultz@linaro.org
Cc: mwhitehe@redhat.com
Link: http://lkml.kernel.org/r/alpine.DEB.2.02.1311132052240.30673@ionos.tec.linutronix.de
The only real feature that was added this release is from Namhyung Kim,
who introduced "set_graph_notrace" filter that lets you run the function
graph tracer and not trace particular functions and their call chain.
Tom Zanussi added some updates to the ftrace multibuffer tracing that
made it more consistent with the top level tracing.
One of the fixes for perf function tracing required an API change in
RCU; the addition of "rcu_is_watching()". As Paul McKenney is pushing
that change in this release too, he gave me a branch that included
all the changes to get that working, and I pulled that into my tree
in order to complete the perf function tracing fix.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.14 (GNU/Linux)
iQEcBAABAgAGBQJSgX5SAAoJEKQekfcNnQGulUAH/jORqJrKaNAulmZ314VsAqfa
zMtF5UAAPf7kqc3AN/jtFrhJUNEfxWOo7A4r0FsM/rKdWJF+98GA6aqYVD+XoWFt
+36fg1enxbXUjixQ96Uh+o1+BJUgYDqljuWzqSu/oiXWfWwl8+WL4kcbhb+V9WcF
SpdzLCWVZRfhyDiN3+0zvyQ8RSG2Pd7CWn9zroI0e4sxGo0Ki6JUnIcXtZGOBDOQ
IIZdjXvGSfpJ+3u3XvRPXJcltRCtOsVWxYzrmvRlmHDW5QMe1+WmmrlojTePrLaJ
xn8+3WINqetAR+ZQnazbpt1XzJzKa8QtFgpiN0kT6qL7cg3N1Owc4vLGohl7wok=
=Nesf
-----END PGP SIGNATURE-----
Merge tag 'trace-3.13' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace
Pull tracing update from Steven Rostedt:
"This batch of changes is mostly clean ups and small bug fixes. The
only real feature that was added this release is from Namhyung Kim,
who introduced "set_graph_notrace" filter that lets you run the
function graph tracer and not trace particular functions and their
call chain.
Tom Zanussi added some updates to the ftrace multibuffer tracing that
made it more consistent with the top level tracing.
One of the fixes for perf function tracing required an API change in
RCU; the addition of "rcu_is_watching()". As Paul McKenney is pushing
that change in this release too, he gave me a branch that included all
the changes to get that working, and I pulled that into my tree in
order to complete the perf function tracing fix"
* tag 'trace-3.13' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace:
tracing: Add rcu annotation for syscall trace descriptors
tracing: Do not use signed enums with unsigned long long in fgragh output
tracing: Remove unused function ftrace_off_permanent()
tracing: Do not assign filp->private_data to freed memory
tracing: Add helper function tracing_is_disabled()
tracing: Open tracer when ftrace_dump_on_oops is used
tracing: Add support for SOFT_DISABLE to syscall events
tracing: Make register/unregister_ftrace_command __init
tracing: Update event filters for multibuffer
recordmcount.pl: Add support for __fentry__
ftrace: Have control op function callback only trace when RCU is watching
rcu: Do not trace rcu_is_watching() functions
ftrace/x86: skip over the breakpoint for ftrace caller
trace/trace_stat: use rbtree postorder iteration helper instead of opencoding
ftrace: Add set_graph_notrace filter
ftrace: Narrow down the protected area of graph_lock
ftrace: Introduce struct ftrace_graph_data
ftrace: Get rid of ftrace_graph_filter_enabled
tracing: Fix potential out-of-bounds in trace_get_user()
tracing: Show more exact help information about snapshot
Conflicts:
kernel/Makefile
There are conflicts in kernel/Makefile due to file moving in the
scheduler tree - resolve them.
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Paul E. McKenney
Pranith Kumar
Fabian Frederick
Linus Torvalds
Rik van Riel
Uma Sharma
Thomas Gleixner
Rashika Kheria
Christoph Lameter
Pranith Kumar
Andreea-Cristina Bernat
Himangi Saraogi
Iulia Manda
Liu Ping Fan
Peter Zijlstra
Paul Gortmaker
Dongsheng Yang
Shaibal Dutta
Paul Bolle
Oleg Nesterov
Ingo Molnar
Teodora Baluta
Chen Gang
Lai Jiangshan
Fengguang Wu