summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--Documentation/RCU/stallwarn.rst23
-rw-r--r--kernel/rcu/tree.c25
-rw-r--r--kernel/rcu/tree_stall.h32
3 files changed, 69 insertions, 11 deletions
diff --git a/Documentation/RCU/stallwarn.rst b/Documentation/RCU/stallwarn.rst
index c9ab6af4d3be..d53856cc6390 100644
--- a/Documentation/RCU/stallwarn.rst
+++ b/Documentation/RCU/stallwarn.rst
@@ -92,7 +92,9 @@ warnings:
buggy timer hardware through bugs in the interrupt or exception
path (whether hardware, firmware, or software) through bugs
in Linux's timer subsystem through bugs in the scheduler, and,
- yes, even including bugs in RCU itself.
+ yes, even including bugs in RCU itself. It can also result in
+ the ``rcu_.*timer wakeup didn't happen for`` console-log message,
+ which will include additional debugging information.
- A bug in the RCU implementation.
@@ -292,6 +294,25 @@ kthread is waiting for a short timeout, the "state" precedes value of the
task_struct ->state field, and the "cpu" indicates that the grace-period
kthread last ran on CPU 5.
+If the relevant grace-period kthread does not wake from FQS wait in a
+reasonable time, then the following additional line is printed::
+
+ kthread timer wakeup didn't happen for 23804 jiffies! g7076 f0x0 RCU_GP_WAIT_FQS(5) ->state=0x402
+
+The "23804" indicates that kthread's timer expired more than 23 thousand
+jiffies ago. The rest of the line has meaning similar to the kthread
+starvation case.
+
+Additionally, the following line is printed::
+
+ Possible timer handling issue on cpu=4 timer-softirq=11142
+
+Here "cpu" indicates that the grace-period kthread last ran on CPU 4,
+where it queued the fqs timer. The number following the "timer-softirq"
+is the current ``TIMER_SOFTIRQ`` count on cpu 4. If this value does not
+change on successive RCU CPU stall warnings, there is further reason to
+suspect a timer problem.
+
Multiple Warnings From One Stall
================================
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 40e5e3dd253e..e918f100cc34 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1765,7 +1765,7 @@ static bool rcu_gp_init(void)
* go offline later. Please also refer to "Hotplug CPU" section
* of RCU's Requirements documentation.
*/
- rcu_state.gp_state = RCU_GP_ONOFF;
+ WRITE_ONCE(rcu_state.gp_state, RCU_GP_ONOFF);
rcu_for_each_leaf_node(rnp) {
smp_mb(); // Pair with barriers used when updating ->ofl_seq to odd values.
firstseq = READ_ONCE(rnp->ofl_seq);
@@ -1831,7 +1831,7 @@ static bool rcu_gp_init(void)
* The grace period cannot complete until the initialization
* process finishes, because this kthread handles both.
*/
- rcu_state.gp_state = RCU_GP_INIT;
+ WRITE_ONCE(rcu_state.gp_state, RCU_GP_INIT);
rcu_for_each_node_breadth_first(rnp) {
rcu_gp_slow(gp_init_delay);
raw_spin_lock_irqsave_rcu_node(rnp, flags);
@@ -1930,17 +1930,22 @@ static void rcu_gp_fqs_loop(void)
ret = 0;
for (;;) {
if (!ret) {
- rcu_state.jiffies_force_qs = jiffies + j;
+ WRITE_ONCE(rcu_state.jiffies_force_qs, jiffies + j);
+ /*
+ * jiffies_force_qs before RCU_GP_WAIT_FQS state
+ * update; required for stall checks.
+ */
+ smp_wmb();
WRITE_ONCE(rcu_state.jiffies_kick_kthreads,
jiffies + (j ? 3 * j : 2));
}
trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq,
TPS("fqswait"));
- rcu_state.gp_state = RCU_GP_WAIT_FQS;
+ WRITE_ONCE(rcu_state.gp_state, RCU_GP_WAIT_FQS);
ret = swait_event_idle_timeout_exclusive(
rcu_state.gp_wq, rcu_gp_fqs_check_wake(&gf), j);
rcu_gp_torture_wait();
- rcu_state.gp_state = RCU_GP_DOING_FQS;
+ WRITE_ONCE(rcu_state.gp_state, RCU_GP_DOING_FQS);
/* Locking provides needed memory barriers. */
/* If grace period done, leave loop. */
if (!READ_ONCE(rnp->qsmask) &&
@@ -2054,7 +2059,7 @@ static void rcu_gp_cleanup(void)
trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq, TPS("end"));
rcu_seq_end(&rcu_state.gp_seq);
ASSERT_EXCLUSIVE_WRITER(rcu_state.gp_seq);
- rcu_state.gp_state = RCU_GP_IDLE;
+ WRITE_ONCE(rcu_state.gp_state, RCU_GP_IDLE);
/* Check for GP requests since above loop. */
rdp = this_cpu_ptr(&rcu_data);
if (!needgp && ULONG_CMP_LT(rnp->gp_seq, rnp->gp_seq_needed)) {
@@ -2093,12 +2098,12 @@ static int __noreturn rcu_gp_kthread(void *unused)
for (;;) {
trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq,
TPS("reqwait"));
- rcu_state.gp_state = RCU_GP_WAIT_GPS;
+ WRITE_ONCE(rcu_state.gp_state, RCU_GP_WAIT_GPS);
swait_event_idle_exclusive(rcu_state.gp_wq,
READ_ONCE(rcu_state.gp_flags) &
RCU_GP_FLAG_INIT);
rcu_gp_torture_wait();
- rcu_state.gp_state = RCU_GP_DONE_GPS;
+ WRITE_ONCE(rcu_state.gp_state, RCU_GP_DONE_GPS);
/* Locking provides needed memory barrier. */
if (rcu_gp_init())
break;
@@ -2113,9 +2118,9 @@ static int __noreturn rcu_gp_kthread(void *unused)
rcu_gp_fqs_loop();
/* Handle grace-period end. */
- rcu_state.gp_state = RCU_GP_CLEANUP;
+ WRITE_ONCE(rcu_state.gp_state, RCU_GP_CLEANUP);
rcu_gp_cleanup();
- rcu_state.gp_state = RCU_GP_CLEANED;
+ WRITE_ONCE(rcu_state.gp_state, RCU_GP_CLEANED);
}
}
diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h
index 29cf096b5d20..353da30bd558 100644
--- a/kernel/rcu/tree_stall.h
+++ b/kernel/rcu/tree_stall.h
@@ -482,6 +482,36 @@ static void rcu_check_gp_kthread_starvation(void)
}
}
+/* Complain about missing wakeups from expired fqs wait timer */
+static void rcu_check_gp_kthread_expired_fqs_timer(void)
+{
+ struct task_struct *gpk = rcu_state.gp_kthread;
+ short gp_state;
+ unsigned long jiffies_fqs;
+ int cpu;
+
+ /*
+ * Order reads of .gp_state and .jiffies_force_qs.
+ * Matching smp_wmb() is present in rcu_gp_fqs_loop().
+ */
+ gp_state = smp_load_acquire(&rcu_state.gp_state);
+ jiffies_fqs = READ_ONCE(rcu_state.jiffies_force_qs);
+
+ if (gp_state == RCU_GP_WAIT_FQS &&
+ time_after(jiffies, jiffies_fqs + RCU_STALL_MIGHT_MIN) &&
+ gpk && !READ_ONCE(gpk->on_rq)) {
+ cpu = task_cpu(gpk);
+ pr_err("%s kthread timer wakeup didn't happen for %ld jiffies! g%ld f%#x %s(%d) ->state=%#lx\n",
+ rcu_state.name, (jiffies - jiffies_fqs),
+ (long)rcu_seq_current(&rcu_state.gp_seq),
+ data_race(rcu_state.gp_flags),
+ gp_state_getname(RCU_GP_WAIT_FQS), RCU_GP_WAIT_FQS,
+ gpk->state);
+ pr_err("\tPossible timer handling issue on cpu=%d timer-softirq=%u\n",
+ cpu, kstat_softirqs_cpu(TIMER_SOFTIRQ, cpu));
+ }
+}
+
static void print_other_cpu_stall(unsigned long gp_seq, unsigned long gps)
{
int cpu;
@@ -543,6 +573,7 @@ static void print_other_cpu_stall(unsigned long gp_seq, unsigned long gps)
WRITE_ONCE(rcu_state.jiffies_stall,
jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
+ rcu_check_gp_kthread_expired_fqs_timer();
rcu_check_gp_kthread_starvation();
panic_on_rcu_stall();
@@ -578,6 +609,7 @@ static void print_cpu_stall(unsigned long gps)
jiffies - gps,
(long)rcu_seq_current(&rcu_state.gp_seq), totqlen);
+ rcu_check_gp_kthread_expired_fqs_timer();
rcu_check_gp_kthread_starvation();
rcu_dump_cpu_stacks();
generated by cgit v1.2.3 (git 2.39.0) at 2024-12-04 16:07:20 +0300