UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity

rcu: Improve diagnostics for spurious RCU CPU stall warnings 

The current RCU CPU stall warning code will print "Stall ended before
state dump start" any time that the stall-warning code is triggered on
a CPU that has already reported a quiescent state for the current grace
period and if all quiescent states have been reported for the current
grace period.  However, a true stall can result in these symptoms, for
example, by preventing RCU's grace-period kthreads from ever running

This commit therefore checks for this condition, reporting the end of
the stall only if one of the grace-period counters has actually advanced.
Otherwise, it reports the last time that the grace-period kthread made
meaningful progress.  (In normal situations, the grace-period kthread
should make meaningful progress at least every jiffies_till_next_fqs
jiffies.)

Reported-by: Miroslav Benes <mbenes@suse.cz>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Tested-by: Miroslav Benes <mbenes@suse.cz>
This commit is contained in:
Paul E. McKenney 2014-12-11 10:20:59 -08:00
parent fc908ed33e
commit 6ccd2ecd42
3 changed files with 34 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
Documentation/RCU/stallwarn.txt
View File

@ -187,6 +187,11 @@ o For !CONFIG_PREEMPT kernels, a CPU looping anywhere in the
behavior, you might need to replace some of the cond_resched()
calls with calls to cond_resched_rcu_qs().
o Anything that prevents RCU's grace-period kthreads from running.
This can result in the "All QSes seen" console-log message.
This message will include information on when the kthread last
ran and how often it should be expected to run.
o A CPU-bound real-time task in a CONFIG_PREEMPT kernel, which might
happen to preempt a low-priority task in the middle of an RCU
read-side critical section. This is especially damaging if

32
kernel/rcu/tree.c
View File

@ -1066,11 +1066,13 @@ static void rcu_dump_cpu_stacks(struct rcu_state *rsp)
}
}
static void print_other_cpu_stall(struct rcu_state *rsp)
static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum)
{
int cpu;
long delta;
unsigned long flags;
unsigned long gpa;
unsigned long j;
int ndetected = 0;
struct rcu_node *rnp = rcu_get_root(rsp);
long totqlen = 0;
@ -1123,10 +1125,22 @@ static void print_other_cpu_stall(struct rcu_state *rsp)
pr_cont("(detected by %d, t=%ld jiffies, g=%ld, c=%ld, q=%lu)\n",
smp_processor_id(), (long)(jiffies - rsp->gp_start),
(long)rsp->gpnum, (long)rsp->completed, totqlen);
if (ndetected == 0)
pr_err("INFO: Stall ended before state dump start\n");
else
if (ndetected) {
rcu_dump_cpu_stacks(rsp);
} else {
if (ACCESS_ONCE(rsp->gpnum) != gpnum ||
ACCESS_ONCE(rsp->completed) == gpnum) {
pr_err("INFO: Stall ended before state dump start\n");
} else {
j = jiffies;
gpa = ACCESS_ONCE(rsp->gp_activity);
pr_err("All QSes seen, last %s kthread activity %ld (%ld-%ld), jiffies_till_next_fqs=%ld\n",
rsp->name, j - gpa, j, gpa,
jiffies_till_next_fqs);
/* In this case, the current CPU might be at fault. */
sched_show_task(current);
}
}
/* Complain about tasks blocking the grace period. */
@ -1226,7 +1240,7 @@ static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY)) {
/* They had a few time units to dump stack, so complain. */
print_other_cpu_stall(rsp);
print_other_cpu_stall(rsp, gpnum);
}
}
@ -1622,6 +1636,7 @@ static int rcu_gp_init(struct rcu_state *rsp)
struct rcu_data *rdp;
struct rcu_node *rnp = rcu_get_root(rsp);
ACCESS_ONCE(rsp->gp_activity) = jiffies;
rcu_bind_gp_kthread();
raw_spin_lock_irq(&rnp->lock);
smp_mb__after_unlock_lock();
@ -1682,6 +1697,7 @@ static int rcu_gp_init(struct rcu_state *rsp)
rnp->grphi, rnp->qsmask);
raw_spin_unlock_irq(&rnp->lock);
cond_resched_rcu_qs();
ACCESS_ONCE(rsp->gp_activity) = jiffies;
}
mutex_unlock(&rsp->onoff_mutex);
@ -1698,6 +1714,7 @@ static int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in)
unsigned long maxj;
struct rcu_node *rnp = rcu_get_root(rsp);
ACCESS_ONCE(rsp->gp_activity) = jiffies;
rsp->n_force_qs++;
if (fqs_state == RCU_SAVE_DYNTICK) {
/* Collect dyntick-idle snapshots. */
@ -1736,6 +1753,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
struct rcu_data *rdp;
struct rcu_node *rnp = rcu_get_root(rsp);
ACCESS_ONCE(rsp->gp_activity) = jiffies;
raw_spin_lock_irq(&rnp->lock);
smp_mb__after_unlock_lock();
gp_duration = jiffies - rsp->gp_start;
@ -1772,6 +1790,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
nocb += rcu_future_gp_cleanup(rsp, rnp);
raw_spin_unlock_irq(&rnp->lock);
cond_resched_rcu_qs();
ACCESS_ONCE(rsp->gp_activity) = jiffies;
}
rnp = rcu_get_root(rsp);
raw_spin_lock_irq(&rnp->lock);
@ -1821,6 +1840,7 @@ static int __noreturn rcu_gp_kthread(void *arg)
if (rcu_gp_init(rsp))
break;
cond_resched_rcu_qs();
ACCESS_ONCE(rsp->gp_activity) = jiffies;
WARN_ON(signal_pending(current));
trace_rcu_grace_period(rsp->name,
ACCESS_ONCE(rsp->gpnum),
@ -1864,9 +1884,11 @@ static int __noreturn rcu_gp_kthread(void *arg)
ACCESS_ONCE(rsp->gpnum),
TPS("fqsend"));
cond_resched_rcu_qs();
ACCESS_ONCE(rsp->gp_activity) = jiffies;
} else {
/* Deal with stray signal. */
cond_resched_rcu_qs();
ACCESS_ONCE(rsp->gp_activity) = jiffies;
WARN_ON(signal_pending(current));
trace_rcu_grace_period(rsp->name,
ACCESS_ONCE(rsp->gpnum),

2
kernel/rcu/tree.h
View File

@ -488,6 +488,8 @@ struct rcu_state {
/* due to no GP active. */
unsigned long gp_start; /* Time at which GP started, */
/* but in jiffies. */
unsigned long gp_activity; /* Time of last GP kthread */
/* activity in jiffies. */
unsigned long jiffies_stall; /* Time at which to check */
/* for CPU stalls. */
unsigned long jiffies_resched; /* Time at which to resched */