#include <linux/nmi.h>
#include <linux/atomic.h>
#include <linux/bitops.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/completion.h>
#include <linux/moduleparam.h>
#include <linux/percpu.h>
static void invoke_rcu_core(void);
static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp);
-#define RCU_KTHREAD_PRIO 1 /* RT priority for per-CPU kthreads. */
-
/*
* Track the rcutorture test sequence number and the update version
* number within a given test. The rcutorture_testseq is incremented
};
#endif /* #ifdef CONFIG_NO_HZ */
-static int blimit = 10; /* Maximum callbacks per rcu_do_batch. */
-static int qhimark = 10000; /* If this many pending, ignore blimit. */
-static int qlowmark = 100; /* Once only this many pending, use blimit. */
+static long blimit = 10; /* Maximum callbacks per rcu_do_batch. */
+static long qhimark = 10000; /* If this many pending, ignore blimit. */
+static long qlowmark = 100; /* Once only this many pending, use blimit. */
-module_param(blimit, int, 0);
-module_param(qhimark, int, 0);
-module_param(qlowmark, int, 0);
+module_param(blimit, long, 0);
+module_param(qhimark, long, 0);
+module_param(qlowmark, long, 0);
int rcu_cpu_stall_suppress __read_mostly;
module_param(rcu_cpu_stall_suppress, int, 0644);
static int
cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp)
{
- return *rdp->nxttail[RCU_DONE_TAIL] && !rcu_gp_in_progress(rsp);
+ return *rdp->nxttail[RCU_DONE_TAIL +
+ ACCESS_ONCE(rsp->completed) != rdp->completed] &&
+ !rcu_gp_in_progress(rsp);
}
/*
smp_mb__after_atomic_inc(); /* Force ordering with next sojourn. */
WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1);
local_irq_restore(flags);
-
- /* If the interrupt queued a callback, get out of dyntick mode. */
- if (in_irq() &&
- (__get_cpu_var(rcu_sched_data).nxtlist ||
- __get_cpu_var(rcu_bh_data).nxtlist ||
- rcu_preempt_needs_cpu(smp_processor_id())))
- set_need_resched();
}
/*
*/
static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
{
- unsigned long curr;
- unsigned long snap;
+ unsigned int curr;
+ unsigned int snap;
- curr = (unsigned long)atomic_add_return(0, &rdp->dynticks->dynticks);
- snap = (unsigned long)rdp->dynticks_snap;
+ curr = (unsigned int)atomic_add_return(0, &rdp->dynticks->dynticks);
+ snap = (unsigned int)rdp->dynticks_snap;
/*
* If the CPU passed through or entered a dynticks idle phase with
* read-side critical section that started before the beginning
* of the current RCU grace period.
*/
- if ((curr & 0x1) == 0 || ULONG_CMP_GE(curr, snap + 2)) {
+ if ((curr & 0x1) == 0 || UINT_CMP_GE(curr, snap + 2)) {
trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, "dti");
rdp->dynticks_fqs++;
return 1;
int cpu;
long delta;
unsigned long flags;
+ int ndetected;
struct rcu_node *rnp = rcu_get_root(rsp);
/* Only let one CPU complain about others per time interval. */
* Now rat on any tasks that got kicked up to the root rcu_node
* due to CPU offlining.
*/
- rcu_print_task_stall(rnp);
+ ndetected = rcu_print_task_stall(rnp);
raw_spin_unlock_irqrestore(&rnp->lock, flags);
/*
rsp->name);
rcu_for_each_leaf_node(rsp, rnp) {
raw_spin_lock_irqsave(&rnp->lock, flags);
- rcu_print_task_stall(rnp);
+ ndetected += rcu_print_task_stall(rnp);
raw_spin_unlock_irqrestore(&rnp->lock, flags);
if (rnp->qsmask == 0)
continue;
for (cpu = 0; cpu <= rnp->grphi - rnp->grplo; cpu++)
- if (rnp->qsmask & (1UL << cpu))
+ if (rnp->qsmask & (1UL << cpu)) {
printk(" %d", rnp->grplo + cpu);
+ ndetected++;
+ }
}
printk("} (detected by %d, t=%ld jiffies)\n",
smp_processor_id(), (long)(jiffies - rsp->gp_start));
- trigger_all_cpu_backtrace();
+ if (ndetected == 0)
+ printk(KERN_ERR "INFO: Stall ended before state dump start\n");
+ else if (!trigger_all_cpu_backtrace())
+ dump_stack();
/* If so configured, complain about tasks blocking the grace period. */
*/
printk(KERN_ERR "INFO: %s detected stall on CPU %d (t=%lu jiffies)\n",
rsp->name, smp_processor_id(), jiffies - rsp->gp_start);
- trigger_all_cpu_backtrace();
+ if (!trigger_all_cpu_backtrace())
+ dump_stack();
raw_spin_lock_irqsave(&rnp->lock, flags);
if (ULONG_CMP_GE(jiffies, rsp->jiffies_stall))
struct rcu_data *rdp = this_cpu_ptr(rsp->rda);
struct rcu_node *rnp = rcu_get_root(rsp);
- if (!cpu_needs_another_gp(rsp, rdp) || rsp->fqs_active) {
- if (cpu_needs_another_gp(rsp, rdp))
- rsp->fqs_need_gp = 1;
- if (rnp->completed == rsp->completed) {
- raw_spin_unlock_irqrestore(&rnp->lock, flags);
- return;
- }
- raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
+ if (!rcu_scheduler_fully_active ||
+ !cpu_needs_another_gp(rsp, rdp)) {
+ /*
+ * Either the scheduler hasn't yet spawned the first
+ * non-idle task or this CPU does not need another
+ * grace period. Either way, don't start a new grace
+ * period.
+ */
+ raw_spin_unlock_irqrestore(&rnp->lock, flags);
+ return;
+ }
+ if (rsp->fqs_active) {
/*
- * Propagate new ->completed value to rcu_node structures
- * so that other CPUs don't have to wait until the start
- * of the next grace period to process their callbacks.
+ * This CPU needs a grace period, but force_quiescent_state()
+ * is running. Tell it to start one on this CPU's behalf.
*/
- rcu_for_each_node_breadth_first(rsp, rnp) {
- raw_spin_lock(&rnp->lock); /* irqs already disabled. */
- rnp->completed = rsp->completed;
- raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
- }
- local_irq_restore(flags);
+ rsp->fqs_need_gp = 1;
+ raw_spin_unlock_irqrestore(&rnp->lock, flags);
return;
}
__releases(rcu_get_root(rsp)->lock)
{
unsigned long gp_duration;
+ struct rcu_node *rnp = rcu_get_root(rsp);
+ struct rcu_data *rdp = this_cpu_ptr(rsp->rda);
WARN_ON_ONCE(!rcu_gp_in_progress(rsp));
gp_duration = jiffies - rsp->gp_start;
if (gp_duration > rsp->gp_max)
rsp->gp_max = gp_duration;
- rsp->completed = rsp->gpnum;
+
+ /*
+ * We know the grace period is complete, but to everyone else
+ * it appears to still be ongoing. But it is also the case
+ * that to everyone else it looks like there is nothing that
+ * they can do to advance the grace period. It is therefore
+ * safe for us to drop the lock in order to mark the grace
+ * period as completed in all of the rcu_node structures.
+ *
+ * But if this CPU needs another grace period, it will take
+ * care of this while initializing the next grace period.
+ * We use RCU_WAIT_TAIL instead of the usual RCU_DONE_TAIL
+ * because the callbacks have not yet been advanced: Those
+ * callbacks are waiting on the grace period that just now
+ * completed.
+ */
+ if (*rdp->nxttail[RCU_WAIT_TAIL] == NULL) {
+ raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
+
+ /*
+ * Propagate new ->completed value to rcu_node structures
+ * so that other CPUs don't have to wait until the start
+ * of the next grace period to process their callbacks.
+ */
+ rcu_for_each_node_breadth_first(rsp, rnp) {
+ raw_spin_lock(&rnp->lock); /* irqs already disabled. */
+ rnp->completed = rsp->gpnum;
+ raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
+ }
+ rnp = rcu_get_root(rsp);
+ raw_spin_lock(&rnp->lock); /* irqs already disabled. */
+ }
+
+ rsp->completed = rsp->gpnum; /* Declare the grace period complete. */
trace_rcu_grace_period(rsp->name, rsp->completed, "end");
rsp->signaled = RCU_GP_IDLE;
rcu_start_gp(rsp, flags); /* releases root node's rnp->lock. */
{
unsigned long flags;
struct rcu_head *next, *list, **tail;
- int bl, count;
+ long bl, count;
/* If no callbacks are ready, just return.*/
if (!cpu_has_callbacks_ready_to_invoke(rdp)) {
&__get_cpu_var(rcu_sched_data));
__rcu_process_callbacks(&rcu_bh_state, &__get_cpu_var(rcu_bh_data));
rcu_preempt_process_callbacks();
-
- /* If we are last CPU on way to dyntick-idle mode, accelerate it. */
- rcu_needs_cpu_flush();
trace_rcu_utilization("End RCU core");
}
check_cpu_stall(rsp, rdp);
/* Is the RCU core waiting for a quiescent state from this CPU? */
- if (rdp->qs_pending && !rdp->passed_quiesce) {
+ if (rcu_scheduler_fully_active &&
+ rdp->qs_pending && !rdp->passed_quiesce) {
/*
* If force_quiescent_state() coming soon and this CPU
/* Set up local state, ensuring consistent view of global state. */
raw_spin_lock_irqsave(&rnp->lock, flags);
- rdp->passed_quiesce = 0; /* We could be racing with new GP, */
- rdp->qs_pending = 1; /* so set up to respond to current GP. */
rdp->beenonline = 1; /* We have now been online. */
rdp->preemptible = preemptible;
rdp->qlen_last_fqs_check = 0;
rnp->qsmaskinit |= mask;
mask = rnp->grpmask;
if (rnp == rdp->mynode) {
- rdp->gpnum = rnp->completed; /* if GP in progress... */
+ /*
+ * If there is a grace period in progress, we will
+ * set up to wait for it next time we run the
+ * RCU core code.
+ */
+ rdp->gpnum = rnp->completed;
rdp->completed = rnp->completed;
+ rdp->passed_quiesce = 0;
+ rdp->qs_pending = 0;
rdp->passed_quiesce_gpnum = rnp->gpnum - 1;
trace_rcu_grace_period(rsp->name, rdp->gpnum, "cpuonl");
}