summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--Documentation/RCU/checklist.txt6
-rw-r--r--Documentation/RCU/torture.txt6
-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/srcu.h43
-rw-r--r--init/Kconfig36
-rw-r--r--kernel/rcupdate.c3
-rw-r--r--kernel/rcutorture.c39
-rw-r--r--kernel/rcutree.c162
-rw-r--r--kernel/rcutree.h15
-rw-r--r--kernel/rcutree_plugin.h12
13 files changed, 205 insertions, 267 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/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/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 e7fb255413d2..be52daf4bc3b 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -648,7 +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
@@ -674,9 +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"
@@ -684,25 +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 0be1fa2ea521..cce6ba8bbace 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -121,9 +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/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 1009c0ccd4b1..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);
@@ -985,65 +985,6 @@ void rcu_cpu_stall_reset(void)
}
/*
- * Update CPU-local rcu_data state to record the newly noticed grace period.
- * This is used both when we started the grace period and when we notice
- * that someone else started the grace period. The caller must hold the
- * ->lock of the leaf rcu_node structure corresponding to the current CPU,
- * and must have irqs disabled.
- */
-static void __note_new_gpnum(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp)
-{
- if (rdp->gpnum != rnp->gpnum) {
- /*
- * If the current grace period is waiting for this CPU,
- * set up to detect a quiescent state, otherwise don't
- * go looking for one.
- */
- rdp->gpnum = rnp->gpnum;
- trace_rcu_grace_period(rsp->name, rdp->gpnum, "cpustart");
- rdp->passed_quiesce = 0;
- rdp->qs_pending = !!(rnp->qsmask & rdp->grpmask);
- zero_cpu_stall_ticks(rdp);
- }
-}
-
-static void note_new_gpnum(struct rcu_state *rsp, struct rcu_data *rdp)
-{
- unsigned long flags;
- struct rcu_node *rnp;
-
- local_irq_save(flags);
- rnp = rdp->mynode;
- if (rdp->gpnum == ACCESS_ONCE(rnp->gpnum) || /* outside lock. */
- !raw_spin_trylock(&rnp->lock)) { /* irqs already off, so later. */
- local_irq_restore(flags);
- return;
- }
- __note_new_gpnum(rsp, rnp, rdp);
- raw_spin_unlock_irqrestore(&rnp->lock, flags);
-}
-
-/*
- * Did someone else start a new RCU grace period start since we last
- * checked? Update local state appropriately if so. Must be called
- * on the CPU corresponding to rdp.
- */
-static int
-check_for_new_grace_period(struct rcu_state *rsp, struct rcu_data *rdp)
-{
- unsigned long flags;
- int ret = 0;
-
- local_irq_save(flags);
- if (rdp->gpnum != rsp->gpnum) {
- note_new_gpnum(rsp, rdp);
- ret = 1;
- }
- local_irq_restore(flags);
- return ret;
-}
-
-/*
* Initialize the specified rcu_data structure's callback list to empty.
*/
static void init_callback_list(struct rcu_data *rdp)
@@ -1313,18 +1254,16 @@ static void rcu_advance_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
}
/*
- * Advance this CPU's callbacks, but only if the current grace period
- * has ended. This may be called only from the CPU to whom the rdp
- * belongs. In addition, the corresponding leaf rcu_node structure's
- * ->lock must be held by the caller, with irqs disabled.
+ * Update CPU-local rcu_data state to record the beginnings and ends of
+ * grace periods. The caller must hold the ->lock of the leaf rcu_node
+ * structure corresponding to the current CPU, and must have irqs disabled.
*/
-static void
-__rcu_process_gp_end(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp)
+static void __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp)
{
- /* Did another grace period end? */
+ /* Handle the ends of any preceding grace periods first. */
if (rdp->completed == rnp->completed) {
- /* No, so just accelerate recent callbacks. */
+ /* No grace period end, so just accelerate recent callbacks. */
rcu_accelerate_cbs(rsp, rnp, rdp);
} else {
@@ -1335,68 +1274,40 @@ __rcu_process_gp_end(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_dat
/* Remember that we saw this grace-period completion. */
rdp->completed = rnp->completed;
trace_rcu_grace_period(rsp->name, rdp->gpnum, "cpuend");
+ }
+ if (rdp->gpnum != rnp->gpnum) {
/*
- * If we were in an extended quiescent state, we may have
- * missed some grace periods that others CPUs handled on
- * our behalf. Catch up with this state to avoid noting
- * spurious new grace periods. If another grace period
- * has started, then rnp->gpnum will have advanced, so
- * we will detect this later on. Of course, any quiescent
- * states we found for the old GP are now invalid.
- */
- if (ULONG_CMP_LT(rdp->gpnum, rdp->completed)) {
- rdp->gpnum = rdp->completed;
- rdp->passed_quiesce = 0;
- }
-
- /*
- * If RCU does not need a quiescent state from this CPU,
- * then make sure that this CPU doesn't go looking for one.
+ * If the current grace period is waiting for this CPU,
+ * set up to detect a quiescent state, otherwise don't
+ * go looking for one.
*/
- if ((rnp->qsmask & rdp->grpmask) == 0)
- rdp->qs_pending = 0;
+ rdp->gpnum = rnp->gpnum;
+ trace_rcu_grace_period(rsp->name, rdp->gpnum, "cpustart");
+ rdp->passed_quiesce = 0;
+ rdp->qs_pending = !!(rnp->qsmask & rdp->grpmask);
+ zero_cpu_stall_ticks(rdp);
}
}
-/*
- * Advance this CPU's callbacks, but only if the current grace period
- * has ended. This may be called only from the CPU to whom the rdp
- * belongs.
- */
-static void
-rcu_process_gp_end(struct rcu_state *rsp, struct rcu_data *rdp)
+static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp)
{
unsigned long flags;
struct rcu_node *rnp;
local_irq_save(flags);
rnp = rdp->mynode;
- if (rdp->completed == ACCESS_ONCE(rnp->completed) || /* outside lock. */
+ if ((rdp->gpnum == ACCESS_ONCE(rnp->gpnum) &&
+ rdp->completed == ACCESS_ONCE(rnp->completed)) || /* w/out lock. */
!raw_spin_trylock(&rnp->lock)) { /* irqs already off, so later. */
local_irq_restore(flags);
return;
}
- __rcu_process_gp_end(rsp, rnp, rdp);
+ __note_gp_changes(rsp, rnp, rdp);
raw_spin_unlock_irqrestore(&rnp->lock, flags);
}
/*
- * Do per-CPU grace-period initialization for running CPU. The caller
- * must hold the lock of the leaf rcu_node structure corresponding to
- * this CPU.
- */
-static void
-rcu_start_gp_per_cpu(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp)
-{
- /* Prior grace period ended, so advance callbacks for current CPU. */
- __rcu_process_gp_end(rsp, rnp, rdp);
-
- /* Set state so that this CPU will detect the next quiescent state. */
- __note_new_gpnum(rsp, rnp, rdp);
-}
-
-/*
* Initialize a new grace period.
*/
static int rcu_gp_init(struct rcu_state *rsp)
@@ -1444,7 +1355,7 @@ static int rcu_gp_init(struct rcu_state *rsp)
WARN_ON_ONCE(rnp->completed != rsp->completed);
ACCESS_ONCE(rnp->completed) = rsp->completed;
if (rnp == rdp->mynode)
- rcu_start_gp_per_cpu(rsp, rnp, rdp);
+ __note_gp_changes(rsp, rnp, rdp);
rcu_preempt_boost_start_gp(rnp);
trace_rcu_grace_period_init(rsp->name, rnp->gpnum,
rnp->level, rnp->grplo,
@@ -1527,7 +1438,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
ACCESS_ONCE(rnp->completed) = rsp->gpnum;
rdp = this_cpu_ptr(rsp->rda);
if (rnp == rdp->mynode)
- __rcu_process_gp_end(rsp, rnp, rdp);
+ __note_gp_changes(rsp, rnp, rdp);
nocb += rcu_future_gp_cleanup(rsp, rnp);
raw_spin_unlock_irq(&rnp->lock);
cond_resched();
@@ -1805,9 +1716,8 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp)
static void
rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp)
{
- /* If there is now a new grace period, record and return. */
- if (check_for_new_grace_period(rsp, rdp))
- return;
+ /* Check for grace-period ends and beginnings. */
+ note_gp_changes(rsp, rdp);
/*
* Does this CPU still need to do its part for current grace period?
@@ -2271,9 +2181,6 @@ __rcu_process_callbacks(struct rcu_state *rsp)
WARN_ON_ONCE(rdp->beenonline == 0);
- /* Handle the end of a grace period that some other CPU ended. */
- rcu_process_gp_end(rsp, rdp);
-
/* Update RCU state based on any recent quiescent states. */
rcu_check_quiescent_state(rsp, rdp);
@@ -2358,8 +2265,7 @@ static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp,
if (unlikely(rdp->qlen > rdp->qlen_last_fqs_check + qhimark)) {
/* Are we ignoring a completed grace period? */
- rcu_process_gp_end(rsp, rdp);
- check_for_new_grace_period(rsp, rdp);
+ note_gp_changes(rsp, rdp);
/* Start a new grace period if one not already started. */
if (!rcu_gp_in_progress(rsp)) {
@@ -3265,11 +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 de701bbdb624..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 */
}
@@ -1654,7 +1654,7 @@ static bool rcu_try_advance_all_cbs(void)
*/
if (rdp->completed != rnp->completed &&
rdp->nxttail[RCU_DONE_TAIL] != rdp->nxttail[RCU_NEXT_TAIL])
- rcu_process_gp_end(rsp, rdp);
+ note_gp_changes(rsp, rdp);
if (cpu_has_callbacks_ready_to_invoke(rdp))
cbs_ready = true;
generated by cgit v1.2.3 (git 2.0.4) at 2024-11-17 05:00:55 +0000