summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--Documentation/RCU/checklist.txt6
-rw-r--r--Documentation/RCU/torture.txt6
-rw-r--r--Documentation/RCU/trace.txt100
-rw-r--r--Documentation/RCU/whatisRCU.txt22
-rw-r--r--Documentation/kernel-per-CPU-kthreads.txt47
-rw-r--r--Documentation/timers/NO_HZ.txt79
-rw-r--r--arch/powerpc/kvm/book3s_hv.c2
-rw-r--r--include/linux/hardirq.h2
-rw-r--r--include/linux/rcupdate.h5
-rw-r--r--include/linux/rcutiny.h41
-rw-r--r--include/linux/rcutree.h3
-rw-r--r--include/linux/srcu.h43
-rw-r--r--init/Kconfig46
-rw-r--r--kernel/rcupdate.c29
-rw-r--r--kernel/rcutiny.c21
-rw-r--r--kernel/rcutiny_plugin.h1009
-rw-r--r--kernel/rcutorture.c39
-rw-r--r--kernel/rcutree.c18
-rw-r--r--kernel/rcutree.h15
-rw-r--r--kernel/rcutree_plugin.h36
20 files changed, 266 insertions, 1303 deletions
diff --git a/Documentation/RCU/checklist.txt b/Documentation/RCU/checklist.txt
index 79e789b8b8ea..7703ec73a9bb 100644
--- a/Documentation/RCU/checklist.txt
+++ b/Documentation/RCU/checklist.txt
@@ -354,12 +354,6 @@ over a rather long period of time, but improvements are always welcome!
using RCU rather than SRCU, because RCU is almost always faster
and easier to use than is SRCU.
- If you need to enter your read-side critical section in a
- hardirq or exception handler, and then exit that same read-side
- critical section in the task that was interrupted, then you need
- to srcu_read_lock_raw() and srcu_read_unlock_raw(), which avoid
- the lockdep checking that would otherwise this practice illegal.
-
Also unlike other forms of RCU, explicit initialization
and cleanup is required via init_srcu_struct() and
cleanup_srcu_struct(). These are passed a "struct srcu_struct"
diff --git a/Documentation/RCU/torture.txt b/Documentation/RCU/torture.txt
index 7dce8a17eac2..d8a502387397 100644
--- a/Documentation/RCU/torture.txt
+++ b/Documentation/RCU/torture.txt
@@ -182,12 +182,6 @@ torture_type The type of RCU to test, with string values as follows:
"srcu_expedited": srcu_read_lock(), srcu_read_unlock() and
synchronize_srcu_expedited().
- "srcu_raw": srcu_read_lock_raw(), srcu_read_unlock_raw(),
- and call_srcu().
-
- "srcu_raw_sync": srcu_read_lock_raw(), srcu_read_unlock_raw(),
- and synchronize_srcu().
-
"sched": preempt_disable(), preempt_enable(), and
call_rcu_sched().
diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt
index c776968f4463..f3778f8952da 100644
--- a/Documentation/RCU/trace.txt
+++ b/Documentation/RCU/trace.txt
@@ -530,113 +530,21 @@ o "nos" counts the number of times we balked for other
reasons, e.g., the grace period ended first.
-CONFIG_TINY_RCU and CONFIG_TINY_PREEMPT_RCU debugfs Files and Formats
+CONFIG_TINY_RCU debugfs Files and Formats
These implementations of RCU provides a single debugfs file under the
top-level directory RCU, namely rcu/rcudata, which displays fields in
-rcu_bh_ctrlblk, rcu_sched_ctrlblk and, for CONFIG_TINY_PREEMPT_RCU,
-rcu_preempt_ctrlblk.
+rcu_bh_ctrlblk and rcu_sched_ctrlblk.
The output of "cat rcu/rcudata" is as follows:
-rcu_preempt: qlen=24 gp=1097669 g197/p197/c197 tasks=...
- ttb=. btg=no ntb=184 neb=0 nnb=183 j=01f7 bt=0274
- normal balk: nt=1097669 gt=0 bt=371 b=0 ny=25073378 nos=0
- exp balk: bt=0 nos=0
rcu_sched: qlen: 0
rcu_bh: qlen: 0
-This is split into rcu_preempt, rcu_sched, and rcu_bh sections, with the
-rcu_preempt section appearing only in CONFIG_TINY_PREEMPT_RCU builds.
-The last three lines of the rcu_preempt section appear only in
-CONFIG_RCU_BOOST kernel builds. The fields are as follows:
+This is split into rcu_sched and rcu_bh sections. The field is as
+follows:
o "qlen" is the number of RCU callbacks currently waiting either
for an RCU grace period or waiting to be invoked. This is the
only field present for rcu_sched and rcu_bh, due to the
short-circuiting of grace period in those two cases.
-
-o "gp" is the number of grace periods that have completed.
-
-o "g197/p197/c197" displays the grace-period state, with the
- "g" number being the number of grace periods that have started
- (mod 256), the "p" number being the number of grace periods
- that the CPU has responded to (also mod 256), and the "c"
- number being the number of grace periods that have completed
- (once again mode 256).
-
- Why have both "gp" and "g"? Because the data flowing into
- "gp" is only present in a CONFIG_RCU_TRACE kernel.
-
-o "tasks" is a set of bits. The first bit is "T" if there are
- currently tasks that have recently blocked within an RCU
- read-side critical section, the second bit is "N" if any of the
- aforementioned tasks are blocking the current RCU grace period,
- and the third bit is "E" if any of the aforementioned tasks are
- blocking the current expedited grace period. Each bit is "."
- if the corresponding condition does not hold.
-
-o "ttb" is a single bit. It is "B" if any of the blocked tasks
- need to be priority boosted and "." otherwise.
-
-o "btg" indicates whether boosting has been carried out during
- the current grace period, with "exp" indicating that boosting
- is in progress for an expedited grace period, "no" indicating
- that boosting has not yet started for a normal grace period,
- "begun" indicating that boosting has bebug for a normal grace
- period, and "done" indicating that boosting has completed for
- a normal grace period.
-
-o "ntb" is the total number of tasks subjected to RCU priority boosting
- periods since boot.
-
-o "neb" is the number of expedited grace periods that have had
- to resort to RCU priority boosting since boot.
-
-o "nnb" is the number of normal grace periods that have had
- to resort to RCU priority boosting since boot.
-
-o "j" is the low-order 16 bits of the jiffies counter in hexadecimal.
-
-o "bt" is the low-order 16 bits of the value that the jiffies counter
- will have at the next time that boosting is scheduled to begin.
-
-o In the line beginning with "normal balk", the fields are as follows:
-
- o "nt" is the number of times that the system balked from
- boosting because there were no blocked tasks to boost.
- Note that the system will balk from boosting even if the
- grace period is overdue when the currently running task
- is looping within an RCU read-side critical section.
- There is no point in boosting in this case, because
- boosting a running task won't make it run any faster.
-
- o "gt" is the number of times that the system balked
- from boosting because, although there were blocked tasks,
- none of them were preventing the current grace period
- from completing.
-
- o "bt" is the number of times that the system balked
- from boosting because boosting was already in progress.
-
- o "b" is the number of times that the system balked from
- boosting because boosting had already completed for
- the grace period in question.
-
- o "ny" is the number of times that the system balked from
- boosting because it was not yet time to start boosting
- the grace period in question.
-
- o "nos" is the number of times that the system balked from
- boosting for inexplicable ("not otherwise specified")
- reasons. This can actually happen due to races involving
- increments of the jiffies counter.
-
-o In the line beginning with "exp balk", the fields are as follows:
-
- o "bt" is the number of times that the system balked from
- boosting because there were no blocked tasks to boost.
-
- o "nos" is the number of times that the system balked from
- boosting for inexplicable ("not otherwise specified")
- reasons.
diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt
index 10df0b82f459..0f0fb7c432c2 100644
--- a/Documentation/RCU/whatisRCU.txt
+++ b/Documentation/RCU/whatisRCU.txt
@@ -842,9 +842,7 @@ SRCU: Critical sections Grace period Barrier
srcu_read_lock synchronize_srcu srcu_barrier
srcu_read_unlock call_srcu
- srcu_read_lock_raw synchronize_srcu_expedited
- srcu_read_unlock_raw
- srcu_dereference
+ srcu_dereference synchronize_srcu_expedited
SRCU: Initialization/cleanup
init_srcu_struct
@@ -865,38 +863,32 @@ list can be helpful:
a. Will readers need to block? If so, you need SRCU.
-b. Is it necessary to start a read-side critical section in a
- hardirq handler or exception handler, and then to complete
- this read-side critical section in the task that was
- interrupted? If so, you need SRCU's srcu_read_lock_raw() and
- srcu_read_unlock_raw() primitives.
-
-c. What about the -rt patchset? If readers would need to block
+b. What about the -rt patchset? If readers would need to block
in an non-rt kernel, you need SRCU. If readers would block
in a -rt kernel, but not in a non-rt kernel, SRCU is not
necessary.
-d. Do you need to treat NMI handlers, hardirq handlers,
+c. Do you need to treat NMI handlers, hardirq handlers,
and code segments with preemption disabled (whether
via preempt_disable(), local_irq_save(), local_bh_disable(),
or some other mechanism) as if they were explicit RCU readers?
If so, RCU-sched is the only choice that will work for you.
-e. Do you need RCU grace periods to complete even in the face
+d. Do you need RCU grace periods to complete even in the face
of softirq monopolization of one or more of the CPUs? For
example, is your code subject to network-based denial-of-service
attacks? If so, you need RCU-bh.
-f. Is your workload too update-intensive for normal use of
+e. Is your workload too update-intensive for normal use of
RCU, but inappropriate for other synchronization mechanisms?
If so, consider SLAB_DESTROY_BY_RCU. But please be careful!
-g. Do you need read-side critical sections that are respected
+f. Do you need read-side critical sections that are respected
even though they are in the middle of the idle loop, during
user-mode execution, or on an offlined CPU? If so, SRCU is the
only choice that will work for you.
-h. Otherwise, use RCU.
+g. Otherwise, use RCU.
Of course, this all assumes that you have determined that RCU is in fact
the right tool for your job.
diff --git a/Documentation/kernel-per-CPU-kthreads.txt b/Documentation/kernel-per-CPU-kthreads.txt
index cbf7ae412da4..5f39ef55c6f6 100644
--- a/Documentation/kernel-per-CPU-kthreads.txt
+++ b/Documentation/kernel-per-CPU-kthreads.txt
@@ -157,6 +157,53 @@ RCU_SOFTIRQ: Do at least one of the following:
calls and by forcing both kernel threads and interrupts
to execute elsewhere.
+Name: kworker/%u:%d%s (cpu, id, priority)
+Purpose: Execute workqueue requests
+To reduce its OS jitter, do any of the following:
+1. Run your workload at a real-time priority, which will allow
+ preempting the kworker daemons.
+2. Do any of the following needed to avoid jitter that your
+ application cannot tolerate:
+ a. Build your kernel with CONFIG_SLUB=y rather than
+ CONFIG_SLAB=y, thus avoiding the slab allocator's periodic
+ use of each CPU's workqueues to run its cache_reap()
+ function.
+ b. Avoid using oprofile, thus avoiding OS jitter from
+ wq_sync_buffer().
+ c. Limit your CPU frequency so that a CPU-frequency
+ governor is not required, possibly enlisting the aid of
+ special heatsinks or other cooling technologies. If done
+ correctly, and if you CPU architecture permits, you should
+ be able to build your kernel with CONFIG_CPU_FREQ=n to
+ avoid the CPU-frequency governor periodically running
+ on each CPU, including cs_dbs_timer() and od_dbs_timer().
+ WARNING: Please check your CPU specifications to
+ make sure that this is safe on your particular system.
+ d. It is not possible to entirely get rid of OS jitter
+ from vmstat_update() on CONFIG_SMP=y systems, but you
+ can decrease its frequency by writing a large value to
+ /proc/sys/vm/stat_interval. The default value is HZ,
+ for an interval of one second. Of course, larger values
+ will make your virtual-memory statistics update more
+ slowly. Of course, you can also run your workload at
+ a real-time priority, thus preempting vmstat_update().
+ e. If running on high-end powerpc servers, build with
+ CONFIG_PPC_RTAS_DAEMON=n. This prevents the RTAS
+ daemon from running on each CPU every second or so.
+ (This will require editing Kconfig files and will defeat
+ this platform's RAS functionality.) This avoids jitter
+ due to the rtas_event_scan() function.
+ WARNING: Please check your CPU specifications to
+ make sure that this is safe on your particular system.
+ f. If running on Cell Processor, build your kernel with
+ CBE_CPUFREQ_SPU_GOVERNOR=n to avoid OS jitter from
+ spu_gov_work().
+ WARNING: Please check your CPU specifications to
+ make sure that this is safe on your particular system.
+ g. If running on PowerMAC, build your kernel with
+ CONFIG_PMAC_RACKMETER=n to disable the CPU-meter,
+ avoiding OS jitter from rackmeter_do_timer().
+
Name: rcuc/%u
Purpose: Execute RCU callbacks in CONFIG_RCU_BOOST=y kernels.
To reduce its OS jitter, do at least one of the following:
diff --git a/Documentation/timers/NO_HZ.txt b/Documentation/timers/NO_HZ.txt
index 5b5322024067..88697584242b 100644
--- a/Documentation/timers/NO_HZ.txt
+++ b/Documentation/timers/NO_HZ.txt
@@ -7,21 +7,59 @@ efficiency and reducing OS jitter. Reducing OS jitter is important for
some types of computationally intensive high-performance computing (HPC)
applications and for real-time applications.
-There are two main contexts in which the number of scheduling-clock
-interrupts can be reduced compared to the old-school approach of sending
-a scheduling-clock interrupt to all CPUs every jiffy whether they need
-it or not (CONFIG_HZ_PERIODIC=y or CONFIG_NO_HZ=n for older kernels):
+There are three main ways of managing scheduling-clock interrupts
+(also known as "scheduling-clock ticks" or simply "ticks"):
-1. Idle CPUs (CONFIG_NO_HZ_IDLE=y or CONFIG_NO_HZ=y for older kernels).
+1. Never omit scheduling-clock ticks (CONFIG_HZ_PERIODIC=y or
+ CONFIG_NO_HZ=n for older kernels). You normally will -not-
+ want to choose this option.
-2. CPUs having only one runnable task (CONFIG_NO_HZ_FULL=y).
+2. Omit scheduling-clock ticks on idle CPUs (CONFIG_NO_HZ_IDLE=y or
+ CONFIG_NO_HZ=y for older kernels). This is the most common
+ approach, and should be the default.
-These two cases are described in the following two sections, followed
+3. Omit scheduling-clock ticks on CPUs that are either idle or that
+ have only one runnable task (CONFIG_NO_HZ_FULL=y). Unless you
+ are running realtime applications or certain types of HPC
+ workloads, you will normally -not- want this option.
+
+These three cases are described in the following three sections, followed
by a third section on RCU-specific considerations and a fourth and final
section listing known issues.
-IDLE CPUs
+NEVER OMIT SCHEDULING-CLOCK TICKS
+
+Very old versions of Linux from the 1990s and the very early 2000s
+are incapable of omitting scheduling-clock ticks. It turns out that
+there are some situations where this old-school approach is still the
+right approach, for example, in heavy workloads with lots of tasks
+that use short bursts of CPU, where there are very frequent idle
+periods, but where these idle periods are also quite short (tens or
+hundreds of microseconds). For these types of workloads, scheduling
+clock interrupts will normally be delivered any way because there
+will frequently be multiple runnable tasks per CPU. In these cases,
+attempting to turn off the scheduling clock interrupt will have no effect
+other than increasing the overhead of switching to and from idle and
+transitioning between user and kernel execution.
+
+This mode of operation can be selected using CONFIG_HZ_PERIODIC=y (or
+CONFIG_NO_HZ=n for older kernels).
+
+However, if you are instead running a light workload with long idle
+periods, failing to omit scheduling-clock interrupts will result in
+excessive power consumption. This is especially bad on battery-powered
+devices, where it results in extremely short battery lifetimes. If you
+are running light workloads, you should therefore read the following
+section.
+
+In addition, if you are running either a real-time workload or an HPC
+workload with short iterations, the scheduling-clock interrupts can
+degrade your applications performance. If this describes your workload,
+you should read the following two sections.
+
+
+OMIT SCHEDULING-CLOCK TICKS FOR IDLE CPUs
If a CPU is idle, there is little point in sending it a scheduling-clock
interrupt. After all, the primary purpose of a scheduling-clock interrupt
@@ -59,10 +97,12 @@ By default, CONFIG_NO_HZ_IDLE=y kernels boot with "nohz=on", enabling
dyntick-idle mode.
-CPUs WITH ONLY ONE RUNNABLE TASK
+OMIT SCHEDULING-CLOCK TICKS FOR CPUs WITH ONLY ONE RUNNABLE TASK
If a CPU has only one runnable task, there is little point in sending it
a scheduling-clock interrupt because there is no other task to switch to.
+Note that omitting scheduling-clock ticks for CPUs with only one runnable
+task implies also omitting them for idle CPUs.
The CONFIG_NO_HZ_FULL=y Kconfig option causes the kernel to avoid
sending scheduling-clock interrupts to CPUs with a single runnable task,
@@ -238,6 +278,11 @@ o Adaptive-ticks does not do anything unless there is only one
single runnable SCHED_FIFO task and multiple runnable SCHED_OTHER
tasks, even though these interrupts are unnecessary.
+ And even when there are multiple runnable tasks on a given CPU,
+ there is little point in interrupting that CPU until the current
+ running task's timeslice expires, which is almost always way
+ longer than the time of the next scheduling-clock interrupt.
+
Better handling of these sorts of situations is future work.
o A reboot is required to reconfigure both adaptive idle and RCU
@@ -268,6 +313,16 @@ o Unless all CPUs are idle, at least one CPU must keep the
scheduling-clock interrupt going in order to support accurate
timekeeping.
-o If there are adaptive-ticks CPUs, there will be at least one
- CPU keeping the scheduling-clock interrupt going, even if all
- CPUs are otherwise idle.
+o If there might potentially be some adaptive-ticks CPUs, there
+ will be at least one CPU keeping the scheduling-clock interrupt
+ going, even if all CPUs are otherwise idle.
+
+ Better handling of this situation is ongoing work.
+
+o Some process-handling operations still require the occasional
+ scheduling-clock tick. These operations include calculating CPU
+ load, maintaining sched average, computing CFS entity vruntime,
+ computing avenrun, and carrying out load balancing. They are
+ currently accommodated by scheduling-clock tick every second
+ or so. On-going work will eliminate the need even for these
+ infrequent scheduling-clock ticks.
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 550f5928b394..2efa9dde741a 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1864,7 +1864,7 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
up_out:
up_read(&current->mm->mmap_sem);
- goto out;
+ goto out_srcu;
}
int kvmppc_core_init_vm(struct kvm *kvm)
diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h
index c1d6555d2567..05bcc0903766 100644
--- a/include/linux/hardirq.h
+++ b/include/linux/hardirq.h
@@ -128,7 +128,7 @@ extern void synchronize_irq(unsigned int irq);
# define synchronize_irq(irq) barrier()
#endif
-#if defined(CONFIG_TINY_RCU) || defined(CONFIG_TINY_PREEMPT_RCU)
+#if defined(CONFIG_TINY_RCU)
static inline void rcu_nmi_enter(void)
{
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index ddcc7826d907..4b14bdc911d7 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -216,6 +216,7 @@ static inline int rcu_preempt_depth(void)
#endif /* #else #ifdef CONFIG_PREEMPT_RCU */
/* Internal to kernel */
+extern void rcu_init(void);
extern void rcu_sched_qs(int cpu);
extern void rcu_bh_qs(int cpu);
extern void rcu_check_callbacks(int cpu, int user);
@@ -239,8 +240,6 @@ static inline void rcu_user_hooks_switch(struct task_struct *prev,
struct task_struct *next) { }
#endif /* CONFIG_RCU_USER_QS */
-extern void exit_rcu(void);
-
/**
* RCU_NONIDLE - Indicate idle-loop code that needs RCU readers
* @a: Code that RCU needs to pay attention to.
@@ -277,7 +276,7 @@ void wait_rcu_gp(call_rcu_func_t crf);
#if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU)
#include <linux/rcutree.h>
-#elif defined(CONFIG_TINY_RCU) || defined(CONFIG_TINY_PREEMPT_RCU)
+#elif defined(CONFIG_TINY_RCU)
#include <linux/rcutiny.h>
#else
#error "Unknown RCU implementation specified to kernel configuration"
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 4e56a9c69a35..e31005ee339e 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -27,10 +27,6 @@
#include <linux/cache.h>
-static inline void rcu_init(void)
-{
-}
-
static inline void rcu_barrier_bh(void)
{
wait_rcu_gp(call_rcu_bh);
@@ -41,8 +37,6 @@ static inline void rcu_barrier_sched(void)
wait_rcu_gp(call_rcu_sched);
}
-#ifdef CONFIG_TINY_RCU
-
static inline void synchronize_rcu_expedited(void)
{
synchronize_sched(); /* Only one CPU, so pretty fast anyway!!! */
@@ -53,17 +47,6 @@ static inline void rcu_barrier(void)
rcu_barrier_sched(); /* Only one CPU, so only one list of callbacks! */
}
-#else /* #ifdef CONFIG_TINY_RCU */
-
-void synchronize_rcu_expedited(void);
-
-static inline void rcu_barrier(void)
-{
- wait_rcu_gp(call_rcu);
-}
-
-#endif /* #else #ifdef CONFIG_TINY_RCU */
-
static inline void synchronize_rcu_bh(void)
{
synchronize_sched();
@@ -85,35 +68,15 @@ static inline void kfree_call_rcu(struct rcu_head *head,
call_rcu(head, func);
}
-#ifdef CONFIG_TINY_RCU
-
-static inline void rcu_preempt_note_context_switch(void)
-{
-}
-
static inline int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies)
{
*delta_jiffies = ULONG_MAX;
return 0;
}
-#else /* #ifdef CONFIG_TINY_RCU */
-
-void rcu_preempt_note_context_switch(void);
-int rcu_preempt_needs_cpu(void);
-
-static inline int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies)
-{
- *delta_jiffies = ULONG_MAX;
- return rcu_preempt_needs_cpu();
-}
-
-#endif /* #else #ifdef CONFIG_TINY_RCU */
-
static inline void rcu_note_context_switch(int cpu)
{
rcu_sched_qs(cpu);
- rcu_preempt_note_context_switch();
}
/*
@@ -156,6 +119,10 @@ static inline void rcu_cpu_stall_reset(void)
{
}
+static inline void exit_rcu(void)
+{
+}
+
#ifdef CONFIG_DEBUG_LOCK_ALLOC
extern int rcu_scheduler_active __read_mostly;
extern void rcu_scheduler_starting(void);
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index 952b79339304..226169d1bd2b 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -30,7 +30,6 @@
#ifndef __LINUX_RCUTREE_H
#define __LINUX_RCUTREE_H
-extern void rcu_init(void);
extern void rcu_note_context_switch(int cpu);
extern int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies);
extern void rcu_cpu_stall_reset(void);
@@ -86,6 +85,8 @@ extern void rcu_force_quiescent_state(void);
extern void rcu_bh_force_quiescent_state(void);
extern void rcu_sched_force_quiescent_state(void);
+extern void exit_rcu(void);
+
extern void rcu_scheduler_starting(void);
extern int rcu_scheduler_active __read_mostly;
diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index 04f4121a23ae..c114614ed172 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -237,47 +237,4 @@ static inline void srcu_read_unlock(struct srcu_struct *sp, int idx)
__srcu_read_unlock(sp, idx);
}
-/**
- * srcu_read_lock_raw - register a new reader for an SRCU-protected structure.
- * @sp: srcu_struct in which to register the new reader.
- *
- * Enter an SRCU read-side critical section. Similar to srcu_read_lock(),
- * but avoids the RCU-lockdep checking. This means that it is legal to
- * use srcu_read_lock_raw() in one context, for example, in an exception
- * handler, and then have the matching srcu_read_unlock_raw() in another
- * context, for example in the task that took the exception.
- *
- * However, the entire SRCU read-side critical section must reside within a
- * single task. For example, beware of using srcu_read_lock_raw() in
- * a device interrupt handler and srcu_read_unlock() in the interrupted
- * task: This will not work if interrupts are threaded.
- */
-static inline int srcu_read_lock_raw(struct srcu_struct *sp)
-{
- unsigned long flags;
- int ret;
-
- local_irq_save(flags);
- ret = __srcu_read_lock(sp);
- local_irq_restore(flags);
- return ret;
-}
-
-/**
- * srcu_read_unlock_raw - unregister reader from an SRCU-protected structure.
- * @sp: srcu_struct in which to unregister the old reader.
- * @idx: return value from corresponding srcu_read_lock_raw().
- *
- * Exit an SRCU read-side critical section without lockdep-RCU checking.
- * See srcu_read_lock_raw() for more details.
- */
-static inline void srcu_read_unlock_raw(struct srcu_struct *sp, int idx)
-{
- unsigned long flags;
-
- local_irq_save(flags);
- __srcu_read_unlock(sp, idx);
- local_irq_restore(flags);
-}
-
#endif
diff --git a/init/Kconfig b/init/Kconfig
index 2d9b83104dcf..be52daf4bc3b 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -459,18 +459,10 @@ config TINY_RCU
is not required. This option greatly reduces the
memory footprint of RCU.
-config TINY_PREEMPT_RCU
- bool "Preemptible UP-only small-memory-footprint RCU"
- depends on PREEMPT && !SMP
- help
- This option selects the RCU implementation that is designed
- for real-time UP systems. This option greatly reduces the
- memory footprint of RCU.
-
endchoice
config PREEMPT_RCU
- def_bool ( TREE_PREEMPT_RCU || TINY_PREEMPT_RCU )
+ def_bool TREE_PREEMPT_RCU
help
This option enables preemptible-RCU code that is common between
the TREE_PREEMPT_RCU and TINY_PREEMPT_RCU implementations.
@@ -656,7 +648,7 @@ config RCU_BOOST_DELAY
Accept the default if unsure.
config RCU_NOCB_CPU
- bool "Offload RCU callback processing from boot-selected CPUs (EXPERIMENTAL"
+ bool "Offload RCU callback processing from boot-selected CPUs"
depends on TREE_RCU || TREE_PREEMPT_RCU
default n
help
@@ -682,9 +674,10 @@ choice
prompt "Build-forced no-CBs CPUs"
default RCU_NOCB_CPU_NONE
help
- This option allows no-CBs CPUs to be specified at build time.
- Additional no-CBs CPUs may be specified by the rcu_nocbs=
- boot parameter.
+ This option allows no-CBs CPUs (whose RCU callbacks are invoked
+ from kthreads rather than from softirq context) to be specified
+ at build time. Additional no-CBs CPUs may be specified by
+ the rcu_nocbs= boot parameter.
config RCU_NOCB_CPU_NONE
bool "No build_forced no-CBs CPUs"
@@ -692,25 +685,40 @@ config RCU_NOCB_CPU_NONE
help
This option does not force any of the CPUs to be no-CBs CPUs.
Only CPUs designated by the rcu_nocbs= boot parameter will be
- no-CBs CPUs.
+ no-CBs CPUs, whose RCU callbacks will be invoked by per-CPU
+ kthreads whose names begin with "rcuo". All other CPUs will
+ invoke their own RCU callbacks in softirq context.
+
+ Select this option if you want to choose no-CBs CPUs at
+ boot time, for example, to allow testing of different no-CBs
+ configurations without having to rebuild the kernel each time.
config RCU_NOCB_CPU_ZERO
bool "CPU 0 is a build_forced no-CBs CPU"
depends on RCU_NOCB_CPU && !NO_HZ_FULL
help
- This option forces CPU 0 to be a no-CBs CPU. Additional CPUs
- may be designated as no-CBs CPUs using the rcu_nocbs= boot
- parameter will be no-CBs CPUs.
+ This option forces CPU 0 to be a no-CBs CPU, so that its RCU
+ callbacks are invoked by a per-CPU kthread whose name begins
+ with "rcuo". Additional CPUs may be designated as no-CBs
+ CPUs using the rcu_nocbs= boot parameter will be no-CBs CPUs.
+ All other CPUs will invoke their own RCU callbacks in softirq
+ context.
Select this if CPU 0 needs to be a no-CBs CPU for real-time
- or energy-efficiency reasons.
+ or energy-efficiency reasons, but the real reason it exists
+ is to ensure that randconfig testing covers mixed systems.
config RCU_NOCB_CPU_ALL
bool "All CPUs are build_forced no-CBs CPUs"
depends on RCU_NOCB_CPU
help
This option forces all CPUs to be no-CBs CPUs. The rcu_nocbs=
- boot parameter will be ignored.
+ boot parameter will be ignored. All CPUs' RCU callbacks will
+ be executed in the context of per-CPU rcuo kthreads created for
+ this purpose. Assuming that the kthreads whose names start with
+ "rcuo" are bound to "housekeeping" CPUs, this reduces OS jitter
+ on the remaining CPUs, but might decrease memory locality during
+ RCU-callback invocation, thus potentially degrading throughput.
Select this if all CPUs need to be no-CBs CPUs for real-time
or energy-efficiency reasons.
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index 48ab70384a4c..cce6ba8bbace 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -104,31 +104,7 @@ void __rcu_read_unlock(void)
}
EXPORT_SYMBOL_GPL(__rcu_read_unlock);
-/*
- * Check for a task exiting while in a preemptible-RCU read-side
- * critical section, clean up if so. No need to issue warnings,
- * as debug_check_no_locks_held() already does this if lockdep
- * is enabled.
- */
-void exit_rcu(void)
-{
- struct task_struct *t = current;
-
- if (likely(list_empty(&current->rcu_node_entry)))
- return;
- t->rcu_read_lock_nesting = 1;
- barrier();
- t->rcu_read_unlock_special = RCU_READ_UNLOCK_BLOCKED;
- __rcu_read_unlock();
-}
-
-#else /* #ifdef CONFIG_PREEMPT_RCU */
-
-void exit_rcu(void)
-{
-}
-
-#endif /* #else #ifdef CONFIG_PREEMPT_RCU */
+#endif /* #ifdef CONFIG_PREEMPT_RCU */
#ifdef CONFIG_DEBUG_LOCK_ALLOC
static struct lock_class_key rcu_lock_key;
@@ -145,9 +121,6 @@ static struct lock_class_key rcu_sched_lock_key;
struct lockdep_map rcu_sched_lock_map =
STATIC_LOCKDEP_MAP_INIT("rcu_read_lock_sched", &rcu_sched_lock_key);
EXPORT_SYMBOL_GPL(rcu_sched_lock_map);
-#endif
-
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
int debug_lockdep_rcu_enabled(void)
{
diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c
index a0714a51b6d7..aa344111de3e 100644
--- a/kernel/rcutiny.c
+++ b/kernel/rcutiny.c
@@ -44,7 +44,6 @@
/* Forward declarations for rcutiny_plugin.h. */
struct rcu_ctrlblk;
-static void invoke_rcu_callbacks(void);
static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp);
static void rcu_process_callbacks(struct softirq_action *unused);
static void __call_rcu(struct rcu_head *head,
@@ -205,7 +204,7 @@ static int rcu_is_cpu_rrupt_from_idle(void)
*/
static int rcu_qsctr_help(struct rcu_ctrlblk *rcp)
{
- reset_cpu_stall_ticks(rcp);
+ RCU_TRACE(reset_cpu_stall_ticks(rcp));
if (rcp->rcucblist != NULL &&
rcp->donetail != rcp->curtail) {
rcp->donetail = rcp->curtail;
@@ -227,7 +226,7 @@ void rcu_sched_qs(int cpu)
local_irq_save(flags);
if (rcu_qsctr_help(&rcu_sched_ctrlblk) +
rcu_qsctr_help(&rcu_bh_ctrlblk))
- invoke_rcu_callbacks();
+ raise_softirq(RCU_SOFTIRQ);
local_irq_restore(flags);
}
@@ -240,7 +239,7 @@ void rcu_bh_qs(int cpu)
local_irq_save(flags);
if (rcu_qsctr_help(&rcu_bh_ctrlblk))
- invoke_rcu_callbacks();
+ raise_softirq(RCU_SOFTIRQ);
local_irq_restore(flags);
}
@@ -252,12 +251,11 @@ void rcu_bh_qs(int cpu)
*/
void rcu_check_callbacks(int cpu, int user)
{
- check_cpu_stalls();
+ RCU_TRACE(check_cpu_stalls());
if (user || rcu_is_cpu_rrupt_from_idle())
rcu_sched_qs(cpu);
else if (!in_softirq())
rcu_bh_qs(cpu);
- rcu_preempt_check_callbacks();
}
/*
@@ -278,7 +276,7 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
ACCESS_ONCE(rcp->rcucblist),
need_resched(),
is_idle_task(current),
- rcu_is_callbacks_kthread()));
+ false));
return;
}
@@ -290,7 +288,6 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
*rcp->donetail = NULL;
if (rcp->curtail == rcp->donetail)
rcp->curtail = &rcp->rcucblist;
- rcu_preempt_remove_callbacks(rcp);
rcp->donetail = &rcp->rcucblist;
local_irq_restore(flags);
@@ -309,14 +306,13 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
RCU_TRACE(rcu_trace_sub_qlen(rcp, cb_count));
RCU_TRACE(trace_rcu_batch_end(rcp->name, cb_count, 0, need_resched(),
is_idle_task(current),
- rcu_is_callbacks_kthread()));
+ false));
}
static void rcu_process_callbacks(struct softirq_action *unused)
{
__rcu_process_callbacks(&rcu_sched_ctrlblk);
__rcu_process_callbacks(&rcu_bh_ctrlblk);
- rcu_preempt_process_callbacks();
}
/*
@@ -382,3 +378,8 @@ void call_rcu_bh(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
__call_rcu(head, func, &rcu_bh_ctrlblk);
}
EXPORT_SYMBOL_GPL(call_rcu_bh);
+
+void rcu_init(void)
+{
+ open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
+}
diff --git a/kernel/rcutiny_plugin.h b/kernel/rcutiny_plugin.h
index 8a233002faeb..0cd385acccfa 100644
--- a/kernel/rcutiny_plugin.h
+++ b/kernel/rcutiny_plugin.h
@@ -53,958 +53,10 @@ static struct rcu_ctrlblk rcu_bh_ctrlblk = {
};
#ifdef CONFIG_DEBUG_LOCK_ALLOC
+#include <linux/kernel_stat.h>
+
int rcu_scheduler_active __read_mostly;
EXPORT_SYMBOL_GPL(rcu_scheduler_active);
-#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
-
-#ifdef CONFIG_RCU_TRACE
-
-static void check_cpu_stall(struct rcu_ctrlblk *rcp)
-{
- unsigned long j;
- unsigned long js;
-
- if (rcu_cpu_stall_suppress)
- return;
- rcp->ticks_this_gp++;
- j = jiffies;
- js = rcp->jiffies_stall;
- if (*rcp->curtail && ULONG_CMP_GE(j, js)) {
- pr_err("INFO: %s stall on CPU (%lu ticks this GP) idle=%llx (t=%lu jiffies q=%ld)\n",
- rcp->name, rcp->ticks_this_gp, rcu_dynticks_nesting,
- jiffies - rcp->gp_start, rcp->qlen);
- dump_stack();
- }
- if (*rcp->curtail && ULONG_CMP_GE(j, js))
- rcp->jiffies_stall = jiffies +
- 3 * rcu_jiffies_till_stall_check() + 3;
- else if (ULONG_CMP_GE(j, js))
- rcp->jiffies_stall = jiffies + rcu_jiffies_till_stall_check();
-}
-
-static void check_cpu_stall_preempt(void);
-
-#endif /* #ifdef CONFIG_RCU_TRACE */
-
-static void reset_cpu_stall_ticks(struct rcu_ctrlblk *rcp)
-{
-#ifdef CONFIG_RCU_TRACE
- rcp->ticks_this_gp = 0;
- rcp->gp_start = jiffies;
- rcp->jiffies_stall = jiffies + rcu_jiffies_till_stall_check();
-#endif /* #ifdef CONFIG_RCU_TRACE */
-}
-
-static void check_cpu_stalls(void)
-{
- RCU_TRACE(check_cpu_stall(&rcu_bh_ctrlblk));
- RCU_TRACE(check_cpu_stall(&rcu_sched_ctrlblk));
- RCU_TRACE(check_cpu_stall_preempt());
-}
-
-#ifdef CONFIG_TINY_PREEMPT_RCU
-
-#include <linux/delay.h>
-
-/* Global control variables for preemptible RCU. */
-struct rcu_preempt_ctrlblk {
- struct rcu_ctrlblk rcb; /* curtail: ->next ptr of last CB for GP. */
- struct rcu_head **nexttail;
- /* Tasks blocked in a preemptible RCU */
- /* read-side critical section while an */
- /* preemptible-RCU grace period is in */
- /* progress must wait for a later grace */
- /* period. This pointer points to the */
- /* ->next pointer of the last task that */
- /* must wait for a later grace period, or */
- /* to &->rcb.rcucblist if there is no */
- /* such task. */
- struct list_head blkd_tasks;
- /* Tasks blocked in RCU read-side critical */
- /* section. Tasks are placed at the head */
- /* of this list and age towards the tail. */
- struct list_head *gp_tasks;
- /* Pointer to the first task blocking the */
- /* current grace period, or NULL if there */
- /* is no such task. */
- struct list_head *exp_tasks;
- /* Pointer to first task blocking the */
- /* current expedited grace period, or NULL */
- /* if there is no such task. If there */
- /* is no current expedited grace period, */
- /* then there cannot be any such task. */
-#ifdef CONFIG_RCU_BOOST
- struct list_head *boost_tasks;
- /* Pointer to first task that needs to be */
- /* priority-boosted, or NULL if no priority */
- /* boosting is needed. If there is no */
- /* current or expedited grace period, there */
- /* can be no such task. */
-#endif /* #ifdef CONFIG_RCU_BOOST */
- u8 gpnum; /* Current grace period. */
- u8 gpcpu; /* Last grace period blocked by the CPU. */
- u8 completed; /* Last grace period completed. */
- /* If all three are equal, RCU is idle. */
-#ifdef CONFIG_RCU_BOOST
- unsigned long boost_time; /* When to start boosting (jiffies) */
-#endif /* #ifdef CONFIG_RCU_BOOST */
-#ifdef CONFIG_RCU_TRACE
- unsigned long n_grace_periods;
-#ifdef CONFIG_RCU_BOOST
- unsigned long n_tasks_boosted;
- /* Total number of tasks boosted. */
- unsigned long n_exp_boosts;
- /* Number of tasks boosted for expedited GP. */
- unsigned long n_normal_boosts;
- /* Number of tasks boosted for normal GP. */
- unsigned long n_balk_blkd_tasks;
- /* Refused to boost: no blocked tasks. */
- unsigned long n_balk_exp_gp_tasks;
- /* Refused to boost: nothing blocking GP. */
- unsigned long n_balk_boost_tasks;
- /* Refused to boost: already boosting. */
- unsigned long n_balk_notyet;
- /* Refused to boost: not yet time. */
- unsigned long n_balk_nos;
- /* Refused to boost: not sure why, though. */
- /* This can happen due to race conditions. */
-#endif /* #ifdef CONFIG_RCU_BOOST */
-#endif /* #ifdef CONFIG_RCU_TRACE */
-};
-
-static struct rcu_preempt_ctrlblk rcu_preempt_ctrlblk = {
- .rcb.donetail = &rcu_preempt_ctrlblk.rcb.rcucblist,
- .rcb.curtail = &rcu_preempt_ctrlblk.rcb.rcucblist,
- .nexttail = &rcu_preempt_ctrlblk.rcb.rcucblist,
- .blkd_tasks = LIST_HEAD_INIT(rcu_preempt_ctrlblk.blkd_tasks),
- RCU_TRACE(.rcb.name = "rcu_preempt")
-};
-
-static int rcu_preempted_readers_exp(void);
-static void rcu_report_exp_done(void);
-
-/*
- * Return true if the CPU has not yet responded to the current grace period.
- */
-static int rcu_cpu_blocking_cur_gp(void)
-{
- return rcu_preempt_ctrlblk.gpcpu != rcu_preempt_ctrlblk.gpnum;
-}
-
-/*
- * Check for a running RCU reader. Because there is only one CPU,
- * there can be but one running RCU reader at a time. ;-)
- *
- * Returns zero if there are no running readers. Returns a positive
- * number if there is at least one reader within its RCU read-side
- * critical section. Returns a negative number if an outermost reader
- * is in the midst of exiting from its RCU read-side critical section
- *
- * Returns zero if there are no running readers. Returns a positive
- * number if there is at least one reader within its RCU read-side
- * critical section. Returns a negative number if an outermost reader
- * is in the midst of exiting from its RCU read-side critical section.
- */
-static int rcu_preempt_running_reader(void)
-{
- return current->rcu_read_lock_nesting;
-}
-
-/*
- * Check for preempted RCU readers blocking any grace period.
- * If the caller needs a reliable answer, it must disable hard irqs.
- */
-static int rcu_preempt_blocked_readers_any(void)
-{
- return !list_empty(&rcu_preempt_ctrlblk.blkd_tasks);
-}
-
-/*
- * Check for preempted RCU readers blocking the current grace period.
- * If the caller needs a reliable answer, it must disable hard irqs.
- */
-static int rcu_preempt_blocked_readers_cgp(void)
-{
- return rcu_preempt_ctrlblk.gp_tasks != NULL;
-}
-
-/*
- * Return true if another preemptible-RCU grace period is needed.
- */
-static int rcu_preempt_needs_another_gp(void)
-{
- return *rcu_preempt_ctrlblk.rcb.curtail != NULL;
-}
-
-/*
- * Return true if a preemptible-RCU grace period is in progress.
- * The caller must disable hardirqs.
- */
-static int rcu_preempt_gp_in_progress(void)
-{
- return rcu_preempt_ctrlblk.completed != rcu_preempt_ctrlblk.gpnum;
-}
-
-/*
- * Advance a ->blkd_tasks-list pointer to the next entry, instead
- * returning NULL if at the end of the list.
- */
-static struct list_head *rcu_next_node_entry(struct task_struct *t)
-{
- struct list_head *np;
-
- np = t->rcu_node_entry.next;
- if (np == &rcu_preempt_ctrlblk.blkd_tasks)
- np = NULL;
- return np;
-}
-
-#ifdef CONFIG_RCU_TRACE
-
-#ifdef CONFIG_RCU_BOOST
-static void rcu_initiate_boost_trace(void);
-#endif /* #ifdef CONFIG_RCU_BOOST */
-
-/*
- * Dump additional statistice for TINY_PREEMPT_RCU.
- */
-static void show_tiny_preempt_stats(struct seq_file *m)
-{
- seq_printf(m, "rcu_preempt: qlen=%ld gp=%lu g%u/p%u/c%u tasks=%c%c%c\n",
- rcu_preempt_ctrlblk.rcb.qlen,
- rcu_preempt_ctrlblk.n_grace_periods,
- rcu_preempt_ctrlblk.gpnum,
- rcu_preempt_ctrlblk.gpcpu,
- rcu_preempt_ctrlblk.completed,
- "T."[list_empty(&rcu_preempt_ctrlblk.blkd_tasks)],
- "N."[!rcu_preempt_ctrlblk.gp_tasks],
- "E."[!rcu_preempt_ctrlblk.exp_tasks]);
-#ifdef CONFIG_RCU_BOOST
- seq_printf(m, "%sttb=%c ntb=%lu neb=%lu nnb=%lu j=%04x bt=%04x\n",
- " ",
- "B."[!rcu_preempt_ctrlblk.boost_tasks],
- rcu_preempt_ctrlblk.n_tasks_boosted,
- rcu_preempt_ctrlblk.n_exp_boosts,
- rcu_preempt_ctrlblk.n_normal_boosts,
- (int)(jiffies & 0xffff),
- (int)(rcu_preempt_ctrlblk.boost_time & 0xffff));
- seq_printf(m, "%s: nt=%lu egt=%lu bt=%lu ny=%lu nos=%lu\n",
- " balk",
- rcu_preempt_ctrlblk.n_balk_blkd_tasks,
- rcu_preempt_ctrlblk.n_balk_exp_gp_tasks,
- rcu_preempt_ctrlblk.n_balk_boost_tasks,
- rcu_preempt_ctrlblk.n_balk_notyet,
- rcu_preempt_ctrlblk.n_balk_nos);
-#endif /* #ifdef CONFIG_RCU_BOOST */
-}
-
-#endif /* #ifdef CONFIG_RCU_TRACE */
-
-#ifdef CONFIG_RCU_BOOST
-
-#include "rtmutex_common.h"
-
-#define RCU_BOOST_PRIO CONFIG_RCU_BOOST_PRIO
-
-/* Controls for rcu_kthread() kthread. */
-static struct task_struct *rcu_kthread_task;
-static DECLARE_WAIT_QUEUE_HEAD(rcu_kthread_wq);
-static unsigned long have_rcu_kthread_work;
-
-/*
- * Carry out RCU priority boosting on the task indicated by ->boost_tasks,
- * and advance ->boost_tasks to the next task in the ->blkd_tasks list.
- */
-static int rcu_boost(void)
-{
- unsigned long flags;
- struct rt_mutex mtx;
- struct task_struct *t;
- struct list_head *tb;
-
- if (rcu_preempt_ctrlblk.boost_tasks == NULL &&
- rcu_preempt_ctrlblk.exp_tasks == NULL)
- return 0; /* Nothing to boost. */
-
- local_irq_save(flags);
-
- /*
- * Recheck with irqs disabled: all tasks in need of boosting
- * might exit their RCU read-side critical sections on their own
- * if we are preempted just before disabling irqs.
- */
- if (rcu_preempt_ctrlblk.boost_tasks == NULL &&
- rcu_preempt_ctrlblk.exp_tasks == NULL) {
- local_irq_restore(flags);
- return 0;
- }
-
- /*
- * Preferentially boost tasks blocking expedited grace periods.
- * This cannot starve the normal grace periods because a second
- * expedited grace period must boost all blocked tasks, including
- * those blocking the pre-existing normal grace period.
- */
- if (rcu_preempt_ctrlblk.exp_tasks != NULL) {
- tb = rcu_preempt_ctrlblk.exp_tasks;
- RCU_TRACE(rcu_preempt_ctrlblk.n_exp_boosts++);
- } else {
- tb = rcu_preempt_ctrlblk.boost_tasks;
- RCU_TRACE(rcu_preempt_ctrlblk.n_normal_boosts++);
- }
- RCU_TRACE(rcu_preempt_ctrlblk.n_tasks_boosted++);
-
- /*
- * We boost task t by manufacturing an rt_mutex that appears to
- * be held by task t. We leave a pointer to that rt_mutex where
- * task t can find it, and task t will release the mutex when it
- * exits its outermost RCU read-side critical section. Then
- * simply acquiring this artificial rt_mutex will boost task
- * t's priority. (Thanks to tglx for suggesting this approach!)
- */
- t = container_of(tb, struct task_struct, rcu_node_entry);
- rt_mutex_init_proxy_locked(&mtx, t);
- t->rcu_boost_mutex = &mtx;
- local_irq_restore(flags);
- rt_mutex_lock(&mtx);
- rt_mutex_unlock(&mtx); /* Keep lockdep happy. */
-
- return ACCESS_ONCE(rcu_preempt_ctrlblk.boost_tasks) != NULL ||
- ACCESS_ONCE(rcu_preempt_ctrlblk.exp_tasks) != NULL;
-}
-
-/*
- * Check to see if it is now time to start boosting RCU readers blocking
- * the current grace period, and, if so, tell the rcu_kthread_task to
- * start boosting them. If there is an expedited boost in progress,
- * we wait for it to complete.
- *
- * If there are no blocked readers blocking the current grace period,
- * return 0 to let the caller know, otherwise return 1. Note that this
- * return value is independent of whether or not boosting was done.
- */
-static int rcu_initiate_boost(void)
-{
- if (!rcu_preempt_blocked_readers_cgp() &&
- rcu_preempt_ctrlblk.exp_tasks == NULL) {
- RCU_TRACE(rcu_preempt_ctrlblk.n_balk_exp_gp_tasks++);
- return 0;
- }
- if (rcu_preempt_ctrlblk.exp_tasks != NULL ||
- (rcu_preempt_ctrlblk.gp_tasks != NULL &&
- rcu_preempt_ctrlblk.boost_tasks == NULL &&
- ULONG_CMP_GE(jiffies, rcu_preempt_ctrlblk.boost_time))) {
- if (rcu_preempt_ctrlblk.exp_tasks == NULL)
- rcu_preempt_ctrlblk.boost_tasks =
- rcu_preempt_ctrlblk.gp_tasks;
- invoke_rcu_callbacks();
- } else {
- RCU_TRACE(rcu_initiate_boost_trace());
- }
- return 1;
-}
-
-#define RCU_BOOST_DELAY_JIFFIES DIV_ROUND_UP(CONFIG_RCU_BOOST_DELAY * HZ, 1000)
-
-/*
- * Do priority-boost accounting for the start of a new grace period.
- */
-static void rcu_preempt_boost_start_gp(void)
-{
- rcu_preempt_ctrlblk.boost_time = jiffies + RCU_BOOST_DELAY_JIFFIES;
-}
-
-#else /* #ifdef CONFIG_RCU_BOOST */
-
-/*
- * If there is no RCU priority boosting, we don't initiate boosting,
- * but we do indicate whether there are blocked readers blocking the
- * current grace period.
- */
-static int rcu_initiate_boost(void)
-{
- return rcu_preempt_blocked_readers_cgp();
-}
-
-/*
- * If there is no RCU priority boosting, nothing to do at grace-period start.
- */
-static void rcu_preempt_boost_start_gp(void)
-{
-}
-
-#endif /* else #ifdef CONFIG_RCU_BOOST */
-
-/*
- * Record a preemptible-RCU quiescent state for the specified CPU. Note
- * that this just means that the task currently running on the CPU is
- * in a quiescent state. There might be any number of tasks blocked
- * while in an RCU read-side critical section.
- *
- * Unlike the other rcu_*_qs() functions, callers to this function
- * must disable irqs in order to protect the assignment to
- * ->rcu_read_unlock_special.
- *
- * Because this is a single-CPU implementation, the only way a grace
- * period can end is if the CPU is in a quiescent state. The reason is
- * that a blocked preemptible-RCU reader can exit its critical section
- * only if the CPU is running it at the time. Therefore, when the
- * last task blocking the current grace period exits its RCU read-side
- * critical section, neither the CPU nor blocked tasks will be stopping
- * the current grace period. (In contrast, SMP implementations
- * might have CPUs running in RCU read-side critical sections that
- * block later grace periods -- but this is not possible given only
- * one CPU.)
- */
-static void rcu_preempt_cpu_qs(void)
-{
- /* Record both CPU and task as having responded to current GP. */
- rcu_preempt_ctrlblk.gpcpu = rcu_preempt_ctrlblk.gpnum;
- current->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS;
-
- /* If there is no GP then there is nothing more to do. */
- if (!rcu_preempt_gp_in_progress())
- return;
- /*
- * Check up on boosting. If there are readers blocking the
- * current grace period, leave.
- */
- if (rcu_initiate_boost())
- return;
-
- /* Advance callbacks. */
- rcu_preempt_ctrlblk.completed = rcu_preempt_ctrlblk.gpnum;
- rcu_preempt_ctrlblk.rcb.donetail = rcu_preempt_ctrlblk.rcb.curtail;
- rcu_preempt_ctrlblk.rcb.curtail = rcu_preempt_ctrlblk.nexttail;
-
- /* If there are no blocked readers, next GP is done instantly. */
- if (!rcu_preempt_blocked_readers_any())
- rcu_preempt_ctrlblk.rcb.donetail = rcu_preempt_ctrlblk.nexttail;
-
- /* If there are done callbacks, cause them to be invoked. */
- if (*rcu_preempt_ctrlblk.rcb.donetail != NULL)
- invoke_rcu_callbacks();
-}
-
-/*
- * Start a new RCU grace period if warranted. Hard irqs must be disabled.
- */
-static void rcu_preempt_start_gp(void)
-{
- if (!rcu_preempt_gp_in_progress() && rcu_preempt_needs_another_gp()) {
-
- /* Official start of GP. */
- rcu_preempt_ctrlblk.gpnum++;
- RCU_TRACE(rcu_preempt_ctrlblk.n_grace_periods++);
- reset_cpu_stall_ticks(&rcu_preempt_ctrlblk.rcb);
-
- /* Any blocked RCU readers block new GP. */
- if (rcu_preempt_blocked_readers_any())
- rcu_preempt_ctrlblk.gp_tasks =
- rcu_preempt_ctrlblk.blkd_tasks.next;
-
- /* Set up for RCU priority boosting. */
- rcu_preempt_boost_start_gp();
-
- /* If there is no running reader, CPU is done with GP. */
- if (!rcu_preempt_running_reader())
- rcu_preempt_cpu_qs();
- }
-}
-
-/*
- * We have entered the scheduler, and the current task might soon be
- * context-switched away from. If this task is in an RCU read-side
- * critical section, we will no longer be able to rely on the CPU to
- * record that fact, so we enqueue the task on the blkd_tasks list.
- * If the task started after the current grace period began, as recorded
- * by ->gpcpu, we enqueue at the beginning of the list. Otherwise
- * before the element referenced by ->gp_tasks (or at the tail if
- * ->gp_tasks is NULL) and point ->gp_tasks at the newly added element.
- * The task will dequeue itself when it exits the outermost enclosing
- * RCU read-side critical section. Therefore, the current grace period
- * cannot be permitted to complete until the ->gp_tasks pointer becomes
- * NULL.
- *
- * Caller must disable preemption.
- */
-void rcu_preempt_note_context_switch(void)
-{
- struct task_struct *t = current;
- unsigned long flags;
-
- local_irq_save(flags); /* must exclude scheduler_tick(). */
- if (rcu_preempt_running_reader() > 0 &&
- (t->rcu_read_unlock_special & RCU_READ_UNLOCK_BLOCKED) == 0) {
-
- /* Possibly blocking in an RCU read-side critical section. */
- t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BLOCKED;
-
- /*
- * If this CPU has already checked in, then this task
- * will hold up the next grace period rather than the
- * current grace period. Queue the task accordingly.
- * If the task is queued for the current grace period
- * (i.e., this CPU has not yet passed through a quiescent
- * state for the current grace period), then as long
- * as that task remains queued, the current grace period
- * cannot end.
- */
- list_add(&t->rcu_node_entry, &rcu_preempt_ctrlblk.blkd_tasks);
- if (rcu_cpu_blocking_cur_gp())
- rcu_preempt_ctrlblk.gp_tasks = &t->rcu_node_entry;
- } else if (rcu_preempt_running_reader() < 0 &&
- t->rcu_read_unlock_special) {
- /*
- * Complete exit from RCU read-side critical section on
- * behalf of preempted instance of __rcu_read_unlock().
- */
- rcu_read_unlock_special(t);
- }
-
- /*
- * Either we were not in an RCU read-side critical section to
- * begin with, or we have now recorded that critical section
- * globally. Either way, we can now note a quiescent state
- * for this CPU. Again, if we were in an RCU read-side critical
- * section, and if that critical section was blocking the current
- * grace period, then the fact that the task has been enqueued
- * means that current grace period continues to be blocked.
- */
- rcu_preempt_cpu_qs();
- local_irq_restore(flags);
-}
-
-/*
- * Handle special cases during rcu_read_unlock(), such as needing to
- * notify RCU core processing or task having blocked during the RCU
- * read-side critical section.
- */
-void rcu_read_unlock_special(struct task_struct *t)
-{
- int empty;
- int empty_exp;
- unsigned long flags;
- struct list_head *np;
-#ifdef CONFIG_RCU_BOOST
- struct rt_mutex *rbmp = NULL;
-#endif /* #ifdef CONFIG_RCU_BOOST */
- int special;
-
- /*
- * NMI handlers cannot block and cannot safely manipulate state.
- * They therefore cannot possibly be special, so just leave.
- */
- if (in_nmi())
- return;
-
- local_irq_save(flags);
-
- /*
- * If RCU core is waiting for this CPU to exit critical section,
- * let it know that we have done so.
- */
- special = t->rcu_read_unlock_special;
- if (special & RCU_READ_UNLOCK_NEED_QS)
- rcu_preempt_cpu_qs();
-
- /* Hardware IRQ handlers cannot block. */
- if (in_irq() || in_serving_softirq()) {
- local_irq_restore(flags);
- return;
- }
-
- /* Clean up if blocked during RCU read-side critical section. */
- if (special & RCU_READ_UNLOCK_BLOCKED) {
- t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_BLOCKED;
-
- /*
- * Remove this task from the ->blkd_tasks list and adjust
- * any pointers that might have been referencing it.
- */
- empty = !rcu_preempt_blocked_readers_cgp();
- empty_exp = rcu_preempt_ctrlblk.exp_tasks == NULL;
- np = rcu_next_node_entry(t);
- list_del_init(&t->rcu_node_entry);
- if (&t->rcu_node_entry == rcu_preempt_ctrlblk.gp_tasks)
- rcu_preempt_ctrlblk.gp_tasks = np;
- if (&t->rcu_node_entry == rcu_preempt_ctrlblk.exp_tasks)
- rcu_preempt_ctrlblk.exp_tasks = np;
-#ifdef CONFIG_RCU_BOOST
- if (&t->rcu_node_entry == rcu_preempt_ctrlblk.boost_tasks)
- rcu_preempt_ctrlblk.boost_tasks = np;
-#endif /* #ifdef CONFIG_RCU_BOOST */
-
- /*
- * If this was the last task on the current list, and if
- * we aren't waiting on the CPU, report the quiescent state
- * and start a new grace period if needed.
- */
- if (!empty && !rcu_preempt_blocked_readers_cgp()) {
- rcu_preempt_cpu_qs();
- rcu_preempt_start_gp();
- }
-
- /*
- * If this was the last task on the expedited lists,
- * then we need wake up the waiting task.
- */
- if (!empty_exp && rcu_preempt_ctrlblk.exp_tasks == NULL)
- rcu_report_exp_done();
- }
-#ifdef CONFIG_RCU_BOOST
- /* Unboost self if was boosted. */
- if (t->rcu_boost_mutex != NULL) {
- rbmp = t->rcu_boost_mutex;
- t->rcu_boost_mutex = NULL;
- rt_mutex_unlock(rbmp);
- }
-#endif /* #ifdef CONFIG_RCU_BOOST */
- local_irq_restore(flags);
-}
-
-/*
- * Check for a quiescent state from the current CPU. When a task blocks,
- * the task is recorded in the rcu_preempt_ctrlblk structure, which is
- * checked elsewhere. This is called from the scheduling-clock interrupt.
- *
- * Caller must disable hard irqs.
- */
-static void rcu_preempt_check_callbacks(void)
-{
- struct task_struct *t = current;
-
- if (rcu_preempt_gp_in_progress() &&
- (!rcu_preempt_running_reader() ||
- !rcu_cpu_blocking_cur_gp()))
- rcu_preempt_cpu_qs();
- if (&rcu_preempt_ctrlblk.rcb.rcucblist !=
- rcu_preempt_ctrlblk.rcb.donetail)
- invoke_rcu_callbacks();
- if (rcu_preempt_gp_in_progress() &&
- rcu_cpu_blocking_cur_gp() &&
- rcu_preempt_running_reader() > 0)
- t->rcu_read_unlock_special |= RCU_READ_UNLOCK_NEED_QS;
-}
-
-/*
- * TINY_PREEMPT_RCU has an extra callback-list tail pointer to
- * update, so this is invoked from rcu_process_callbacks() to
- * handle that case. Of course, it is invoked for all flavors of
- * RCU, but RCU callbacks can appear only on one of the lists, and
- * neither ->nexttail nor ->donetail can possibly be NULL, so there
- * is no need for an explicit check.
- */
-static void rcu_preempt_remove_callbacks(struct rcu_ctrlblk *rcp)
-{
- if (rcu_preempt_ctrlblk.nexttail == rcp->donetail)
- rcu_preempt_ctrlblk.nexttail = &rcp->rcucblist;
-}
-
-/*
- * Process callbacks for preemptible RCU.
- */
-static void rcu_preempt_process_callbacks(void)
-{
- __rcu_process_callbacks(&rcu_preempt_ctrlblk.rcb);
-}
-
-/*
- * Queue a preemptible -RCU callback for invocation after a grace period.
- */
-void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
-{
- unsigned long flags;
-
- debug_rcu_head_queue(head);
- head->func = func;
- head->next = NULL;
-
- local_irq_save(flags);
- *rcu_preempt_ctrlblk.nexttail = head;
- rcu_preempt_ctrlblk.nexttail = &head->next;
- RCU_TRACE(rcu_preempt_ctrlblk.rcb.qlen++);
- rcu_preempt_start_gp(); /* checks to see if GP needed. */
- local_irq_restore(flags);
-}
-EXPORT_SYMBOL_GPL(call_rcu);
-
-/*
- * synchronize_rcu - wait until a grace period has elapsed.
- *
- * Control will return to the caller some time after a full grace
- * period has elapsed, in other words after all currently executing RCU
- * read-side critical sections have completed. RCU read-side critical
- * sections are delimited by rcu_read_lock() and rcu_read_unlock(),
- * and may be nested.
- */
-void synchronize_rcu(void)
-{
- rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map) &&
- !lock_is_held(&rcu_lock_map) &&
- !lock_is_held(&rcu_sched_lock_map),
- "Illegal synchronize_rcu() in RCU read-side critical section");
-
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
- if (!rcu_scheduler_active)
- return;
-#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
-
- WARN_ON_ONCE(rcu_preempt_running_reader());
- if (!rcu_preempt_blocked_readers_any())
- return;
-
- /* Once we get past the fastpath checks, same code as rcu_barrier(). */
- if (rcu_expedited)
- synchronize_rcu_expedited();
- else
- rcu_barrier();
-}
-EXPORT_SYMBOL_GPL(synchronize_rcu);
-
-static DECLARE_WAIT_QUEUE_HEAD(sync_rcu_preempt_exp_wq);
-static unsigned long sync_rcu_preempt_exp_count;
-static DEFINE_MUTEX(sync_rcu_preempt_exp_mutex);
-
-/*
- * Return non-zero if there are any tasks in RCU read-side critical
- * sections blocking the current preemptible-RCU expedited grace period.
- * If there is no preemptible-RCU expedited grace period currently in
- * progress, returns zero unconditionally.
- */
-static int rcu_preempted_readers_exp(void)
-{
- return rcu_preempt_ctrlblk.exp_tasks != NULL;
-}
-
-/*
- * Report the exit from RCU read-side critical section for the last task
- * that queued itself during or before the current expedited preemptible-RCU
- * grace period.
- */
-static void rcu_report_exp_done(void)
-{
- wake_up(&sync_rcu_preempt_exp_wq);
-}
-
-/*
- * Wait for an rcu-preempt grace period, but expedite it. The basic idea
- * is to rely in the fact that there is but one CPU, and that it is
- * illegal for a task to invoke synchronize_rcu_expedited() while in a
- * preemptible-RCU read-side critical section. Therefore, any such
- * critical sections must correspond to blocked tasks, which must therefore
- * be on the ->blkd_tasks list. So just record the current head of the
- * list in the ->exp_tasks pointer, and wait for all tasks including and
- * after the task pointed to by ->exp_tasks to drain.
- */
-void synchronize_rcu_expedited(void)
-{
- unsigned long flags;
- struct rcu_preempt_ctrlblk *rpcp = &rcu_preempt_ctrlblk;
- unsigned long snap;
-
- barrier(); /* ensure prior action seen before grace period. */
-
- WARN_ON_ONCE(rcu_preempt_running_reader());
-
- /*
- * Acquire lock so that there is only one preemptible RCU grace
- * period in flight. Of course, if someone does the expedited
- * grace period for us while we are acquiring the lock, just leave.
- */
- snap = sync_rcu_preempt_exp_count + 1;
- mutex_lock(&sync_rcu_preempt_exp_mutex);
- if (ULONG_CMP_LT(snap, sync_rcu_preempt_exp_count))
- goto unlock_mb_ret; /* Others did our work for us. */
-
- local_irq_save(flags);
-
- /*
- * All RCU readers have to already be on blkd_tasks because
- * we cannot legally be executing in an RCU read-side critical
- * section.
- */
-
- /* Snapshot current head of ->blkd_tasks list. */
- rpcp->exp_tasks = rpcp->blkd_tasks.next;
- if (rpcp->exp_tasks == &rpcp->blkd_tasks)
- rpcp->exp_tasks = NULL;
-
- /* Wait for tail of ->blkd_tasks list to drain. */
- if (!rcu_preempted_readers_exp()) {
- local_irq_restore(flags);
- } else {
- rcu_initiate_boost();
- local_irq_restore(flags);
- wait_event(sync_rcu_preempt_exp_wq,
- !rcu_preempted_readers_exp());
- }
-
- /* Clean up and exit. */
- barrier(); /* ensure expedited GP seen before counter increment. */
- sync_rcu_preempt_exp_count++;
-unlock_mb_ret:
- mutex_unlock(&sync_rcu_preempt_exp_mutex);
- barrier(); /* ensure subsequent action seen after grace period. */
-}
-EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
-
-/*
- * Does preemptible RCU need the CPU to stay out of dynticks mode?
- */
-int rcu_preempt_needs_cpu(void)
-{
- return rcu_preempt_ctrlblk.rcb.rcucblist != NULL;
-}
-
-#else /* #ifdef CONFIG_TINY_PREEMPT_RCU */
-
-#ifdef CONFIG_RCU_TRACE
-
-/*
- * Because preemptible RCU does not exist, it is not necessary to
- * dump out its statistics.
- */
-static void show_tiny_preempt_stats(struct seq_file *m)
-{
-}
-
-#endif /* #ifdef CONFIG_RCU_TRACE */
-
-/*
- * Because preemptible RCU does not exist, it never has any callbacks
- * to check.
- */
-static void rcu_preempt_check_callbacks(void)
-{
-}
-
-/*
- * Because preemptible RCU does not exist, it never has any callbacks
- * to remove.
- */
-static void rcu_preempt_remove_callbacks(struct rcu_ctrlblk *rcp)
-{
-}
-
-/*
- * Because preemptible RCU does not exist, it never has any callbacks
- * to process.
- */
-static void rcu_preempt_process_callbacks(void)
-{
-}
-
-#endif /* #else #ifdef CONFIG_TINY_PREEMPT_RCU */
-
-#ifdef CONFIG_RCU_BOOST
-
-/*
- * Wake up rcu_kthread() to process callbacks now eligible for invocation
- * or to boost readers.
- */
-static void invoke_rcu_callbacks(void)
-{
- have_rcu_kthread_work = 1;
- if (rcu_kthread_task != NULL)
- wake_up(&rcu_kthread_wq);
-}
-
-#ifdef CONFIG_RCU_TRACE
-
-/*
- * Is the current CPU running the RCU-callbacks kthread?
- * Caller must have preemption disabled.
- */
-static bool rcu_is_callbacks_kthread(void)
-{
- return rcu_kthread_task == current;
-}
-
-#endif /* #ifdef CONFIG_RCU_TRACE */
-
-/*
- * This kthread invokes RCU callbacks whose grace periods have
- * elapsed. It is awakened as needed, and takes the place of the
- * RCU_SOFTIRQ that is used for this purpose when boosting is disabled.
- * This is a kthread, but it is never stopped, at least not until
- * the system goes down.
- */
-static int rcu_kthread(void *arg)
-{
- unsigned long work;
- unsigned long morework;
- unsigned long flags;
-
- for (;;) {
- wait_event_interruptible(rcu_kthread_wq,
- have_rcu_kthread_work != 0);
- morework = rcu_boost();
- local_irq_save(flags);
- work = have_rcu_kthread_work;
- have_rcu_kthread_work = morework;
- local_irq_restore(flags);
- if (work)
- rcu_process_callbacks(NULL);
- schedule_timeout_interruptible(1); /* Leave CPU for others. */
- }
-
- return 0; /* Not reached, but needed to shut gcc up. */
-}
-
-/*
- * Spawn the kthread that invokes RCU callbacks.
- */
-static int __init rcu_spawn_kthreads(void)
-{
- struct sched_param sp;
-
- rcu_kthread_task = kthread_run(rcu_kthread, NULL, "rcu_kthread");
- sp.sched_priority = RCU_BOOST_PRIO;
- sched_setscheduler_nocheck(rcu_kthread_task, SCHED_FIFO, &sp);
- return 0;
-}
-early_initcall(rcu_spawn_kthreads);
-
-#else /* #ifdef CONFIG_RCU_BOOST */
-
-/* Hold off callback invocation until early_initcall() time. */
-static int rcu_scheduler_fully_active __read_mostly;
-
-/*
- * Start up softirq processing of callbacks.
- */
-void invoke_rcu_callbacks(void)
-{
- if (rcu_scheduler_fully_active)
- raise_softirq(RCU_SOFTIRQ);
-}
-
-#ifdef CONFIG_RCU_TRACE
-
-/*
- * There is no callback kthread, so this thread is never it.
- */
-static bool rcu_is_callbacks_kthread(void)
-{
- return false;
-}
-
-#endif /* #ifdef CONFIG_RCU_TRACE */
-
-static int __init rcu_scheduler_really_started(void)
-{
- rcu_scheduler_fully_active = 1;
- open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
- raise_softirq(RCU_SOFTIRQ); /* Invoke any callbacks from early boot. */
- return 0;
-}
-early_initcall(rcu_scheduler_really_started);
-
-#endif /* #else #ifdef CONFIG_RCU_BOOST */
-
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-#include <linux/kernel_stat.h>
/*
* During boot, we forgive RCU lockdep issues. After this function is
@@ -1020,25 +72,6 @@ void __init rcu_scheduler_starting(void)
#ifdef CONFIG_RCU_TRACE
-#ifdef CONFIG_RCU_BOOST
-
-static void rcu_initiate_boost_trace(void)
-{
- if (list_empty(&rcu_preempt_ctrlblk.blkd_tasks))
- rcu_preempt_ctrlblk.n_balk_blkd_tasks++;
- else if (rcu_preempt_ctrlblk.gp_tasks == NULL &&
- rcu_preempt_ctrlblk.exp_tasks == NULL)
- rcu_preempt_ctrlblk.n_balk_exp_gp_tasks++;
- else if (rcu_preempt_ctrlblk.boost_tasks != NULL)
- rcu_preempt_ctrlblk.n_balk_boost_tasks++;
- else if (!ULONG_CMP_GE(jiffies, rcu_preempt_ctrlblk.boost_time))
- rcu_preempt_ctrlblk.n_balk_notyet++;
- else
- rcu_preempt_ctrlblk.n_balk_nos++;
-}
-
-#endif /* #ifdef CONFIG_RCU_BOOST */
-
static void rcu_trace_sub_qlen(struct rcu_ctrlblk *rcp, int n)
{
unsigned long flags;
@@ -1053,7 +86,6 @@ static void rcu_trace_sub_qlen(struct rcu_ctrlblk *rcp, int n)
*/
static int show_tiny_stats(struct seq_file *m, void *unused)
{
- show_tiny_preempt_stats(m);
seq_printf(m, "rcu_sched: qlen: %ld\n", rcu_sched_ctrlblk.qlen);
seq_printf(m, "rcu_bh: qlen: %ld\n", rcu_bh_ctrlblk.qlen);
return 0;
@@ -1103,11 +135,40 @@ MODULE_AUTHOR("Paul E. McKenney");
MODULE_DESCRIPTION("Read-Copy Update tracing for tiny implementation");
MODULE_LICENSE("GPL");
-static void check_cpu_stall_preempt(void)
+static void check_cpu_stall(struct rcu_ctrlblk *rcp)
{
-#ifdef CONFIG_TINY_PREEMPT_RCU
- check_cpu_stall(&rcu_preempt_ctrlblk.rcb);
-#endif /* #ifdef CONFIG_TINY_PREEMPT_RCU */
+ unsigned long j;
+ unsigned long js;
+
+ if (rcu_cpu_stall_suppress)
+ return;
+ rcp->ticks_this_gp++;
+ j = jiffies;
+ js = rcp->jiffies_stall;
+ if (*rcp->curtail && ULONG_CMP_GE(j, js)) {
+ pr_err("INFO: %s stall on CPU (%lu ticks this GP) idle=%llx (t=%lu jiffies q=%ld)\n",
+ rcp->name, rcp->ticks_this_gp, rcu_dynticks_nesting,
+ jiffies - rcp->gp_start, rcp->qlen);
+ dump_stack();
+ }
+ if (*rcp->curtail && ULONG_CMP_GE(j, js))
+ rcp->jiffies_stall = jiffies +
+ 3 * rcu_jiffies_till_stall_check() + 3;
+ else if (ULONG_CMP_GE(j, js))
+ rcp->jiffies_stall = jiffies + rcu_jiffies_till_stall_check();
+}
+
+static void reset_cpu_stall_ticks(struct rcu_ctrlblk *rcp)
+{
+ rcp->ticks_this_gp = 0;
+ rcp->gp_start = jiffies;
+ rcp->jiffies_stall = jiffies + rcu_jiffies_till_stall_check();
+}
+
+static void check_cpu_stalls(void)
+{
+ RCU_TRACE(check_cpu_stall(&rcu_bh_ctrlblk));
+ RCU_TRACE(check_cpu_stall(&rcu_sched_ctrlblk));
}
#endif /* #ifdef CONFIG_RCU_TRACE */
diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c
index e1f3a8c96724..b1fa5510388d 100644
--- a/kernel/rcutorture.c
+++ b/kernel/rcutorture.c
@@ -695,44 +695,6 @@ static struct rcu_torture_ops srcu_sync_ops = {
.name = "srcu_sync"
};
-static int srcu_torture_read_lock_raw(void) __acquires(&srcu_ctl)
-{
- return srcu_read_lock_raw(&srcu_ctl);
-}
-
-static void srcu_torture_read_unlock_raw(int idx) __releases(&srcu_ctl)
-{
- srcu_read_unlock_raw(&srcu_ctl, idx);
-}
-
-static struct rcu_torture_ops srcu_raw_ops = {
- .init = rcu_sync_torture_init,
- .readlock = srcu_torture_read_lock_raw,
- .read_delay = srcu_read_delay,
- .readunlock = srcu_torture_read_unlock_raw,
- .completed = srcu_torture_completed,
- .deferred_free = srcu_torture_deferred_free,
- .sync = srcu_torture_synchronize,
- .call = NULL,
- .cb_barrier = NULL,
- .stats = srcu_torture_stats,
- .name = "srcu_raw"
-};
-
-static struct rcu_torture_ops srcu_raw_sync_ops = {
- .init = rcu_sync_torture_init,
- .readlock = srcu_torture_read_lock_raw,
- .read_delay = srcu_read_delay,
- .readunlock = srcu_torture_read_unlock_raw,
- .completed = srcu_torture_completed,
- .deferred_free = rcu_sync_torture_deferred_free,
- .sync = srcu_torture_synchronize,
- .call = NULL,
- .cb_barrier = NULL,
- .stats = srcu_torture_stats,
- .name = "srcu_raw_sync"
-};
-
static void srcu_torture_synchronize_expedited(void)
{
synchronize_srcu_expedited(&srcu_ctl);
@@ -1983,7 +1945,6 @@ rcu_torture_init(void)
{ &rcu_ops, &rcu_sync_ops, &rcu_expedited_ops,
&rcu_bh_ops, &rcu_bh_sync_ops, &rcu_bh_expedited_ops,
&srcu_ops, &srcu_sync_ops, &srcu_expedited_ops,
- &srcu_raw_ops, &srcu_raw_sync_ops,
&sched_ops, &sched_sync_ops, &sched_expedited_ops, };
mutex_lock(&fullstop_mutex);
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 7a5194ef90da..cf3adc6fe001 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -218,8 +218,8 @@ module_param(blimit, long, 0444);
module_param(qhimark, long, 0444);
module_param(qlowmark, long, 0444);
-static ulong jiffies_till_first_fqs = RCU_JIFFIES_TILL_FORCE_QS;
-static ulong jiffies_till_next_fqs = RCU_JIFFIES_TILL_FORCE_QS;
+static ulong jiffies_till_first_fqs = ULONG_MAX;
+static ulong jiffies_till_next_fqs = ULONG_MAX;
module_param(jiffies_till_first_fqs, ulong, 0644);
module_param(jiffies_till_next_fqs, ulong, 0644);
@@ -3171,11 +3171,25 @@ static void __init rcu_init_one(struct rcu_state *rsp,
*/
static void __init rcu_init_geometry(void)
{
+ ulong d;
int i;
int j;
int n = nr_cpu_ids;
int rcu_capacity[MAX_RCU_LVLS + 1];
+ /*
+ * Initialize any unspecified boot parameters.
+ * The default values of jiffies_till_first_fqs and
+ * jiffies_till_next_fqs are set to the RCU_JIFFIES_TILL_FORCE_QS
+ * value, which is a function of HZ, then adding one for each
+ * RCU_JIFFIES_FQS_DIV CPUs that might be on the system.
+ */
+ d = RCU_JIFFIES_TILL_FORCE_QS + nr_cpu_ids / RCU_JIFFIES_FQS_DIV;
+ if (jiffies_till_first_fqs == ULONG_MAX)
+ jiffies_till_first_fqs = d;
+ if (jiffies_till_next_fqs == ULONG_MAX)
+ jiffies_till_next_fqs = d;
+
/* If the compile-time values are accurate, just leave. */
if (rcu_fanout_leaf == CONFIG_RCU_FANOUT_LEAF &&
nr_cpu_ids == NR_CPUS)
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index 4df503470e42..4a39d364493c 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -343,12 +343,17 @@ struct rcu_data {
#define RCU_FORCE_QS 3 /* Need to force quiescent state. */
#define RCU_SIGNAL_INIT RCU_SAVE_DYNTICK
-#define RCU_JIFFIES_TILL_FORCE_QS 3 /* for rsp->jiffies_force_qs */
+#define RCU_JIFFIES_TILL_FORCE_QS (1 + (HZ > 250) + (HZ > 500))
+ /* For jiffies_till_first_fqs and */
+ /* and jiffies_till_next_fqs. */
-#define RCU_STALL_RAT_DELAY 2 /* Allow other CPUs time */
- /* to take at least one */
- /* scheduling clock irq */
- /* before ratting on them. */
+#define RCU_JIFFIES_FQS_DIV 256 /* Very large systems need more */
+ /* delay between bouts of */
+ /* quiescent-state forcing. */
+
+#define RCU_STALL_RAT_DELAY 2 /* Allow other CPUs time to take */
+ /* at least one scheduling clock */
+ /* irq before ratting on them. */
#define rcu_wait(cond) \
do { \
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index f279148a0168..63098a59216e 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -81,7 +81,7 @@ static void __init rcu_bootup_announce_oddness(void)
pr_info("\tFour-level hierarchy is enabled.\n");
#endif
if (rcu_fanout_leaf != CONFIG_RCU_FANOUT_LEAF)
- pr_info("\tExperimental boot-time adjustment of leaf fanout to %d.\n", rcu_fanout_leaf);
+ pr_info("\tBoot-time adjustment of leaf fanout to %d.\n", rcu_fanout_leaf);
if (nr_cpu_ids != NR_CPUS)
pr_info("\tRCU restricting CPUs from NR_CPUS=%d to nr_cpu_ids=%d.\n", NR_CPUS, nr_cpu_ids);
#ifdef CONFIG_RCU_NOCB_CPU
@@ -91,19 +91,19 @@ static void __init rcu_bootup_announce_oddness(void)
have_rcu_nocb_mask = true;
}
#ifdef CONFIG_RCU_NOCB_CPU_ZERO
- pr_info("\tExperimental no-CBs CPU 0\n");
+ pr_info("\tOffload RCU callbacks from CPU 0\n");
cpumask_set_cpu(0, rcu_nocb_mask);
#endif /* #ifdef CONFIG_RCU_NOCB_CPU_ZERO */
#ifdef CONFIG_RCU_NOCB_CPU_ALL
- pr_info("\tExperimental no-CBs for all CPUs\n");
+ pr_info("\tOffload RCU callbacks from all CPUs\n");
cpumask_setall(rcu_nocb_mask);
#endif /* #ifdef CONFIG_RCU_NOCB_CPU_ALL */
#endif /* #ifndef CONFIG_RCU_NOCB_CPU_NONE */
if (have_rcu_nocb_mask) {
cpulist_scnprintf(nocb_buf, sizeof(nocb_buf), rcu_nocb_mask);
- pr_info("\tExperimental no-CBs CPUs: %s.\n", nocb_buf);
+ pr_info("\tOffload RCU callbacks from CPUs: %s.\n", nocb_buf);
if (rcu_nocb_poll)
- pr_info("\tExperimental polled no-CBs CPUs.\n");
+ pr_info("\tPoll for callbacks from no-CBs CPUs.\n");
}
#endif /* #ifdef CONFIG_RCU_NOCB_CPU */
}
@@ -932,6 +932,24 @@ static void __init __rcu_init_preempt(void)
rcu_init_one(&rcu_preempt_state, &rcu_preempt_data);
}
+/*
+ * Check for a task exiting while in a preemptible-RCU read-side
+ * critical section, clean up if so. No need to issue warnings,
+ * as debug_check_no_locks_held() already does this if lockdep
+ * is enabled.
+ */
+void exit_rcu(void)
+{
+ struct task_struct *t = current;
+
+ if (likely(list_empty(&current->rcu_node_entry)))
+ return;
+ t->rcu_read_lock_nesting = 1;
+ barrier();
+ t->rcu_read_unlock_special = RCU_READ_UNLOCK_BLOCKED;
+ __rcu_read_unlock();
+}
+
#else /* #ifdef CONFIG_TREE_PREEMPT_RCU */
static struct rcu_state *rcu_state = &rcu_sched_state;
@@ -1100,6 +1118,14 @@ static void __init __rcu_init_preempt(void)
{
}
+/*
+ * Because preemptible RCU does not exist, tasks cannot possibly exit
+ * while in preemptible RCU read-side critical sections.
+ */
+void exit_rcu(void)
+{
+}
+
#endif /* #else #ifdef CONFIG_TREE_PREEMPT_RCU */
#ifdef CONFIG_RCU_BOOST