lkml.org 
[lkml]   [2019]   [Jan]   [9]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH tip/core/rcu 08/12] rcu: Improve diagnostics for failed RCU grace-period start
Date
If a grace period fails to start (for example, because you commented
out the last two lines of rcu_accelerate_cbs_unlocked()), rcu_core()
will invoke rcu_check_gp_start_stall(), which will notice and complain.
However, this complaint is lacking crucial debugging information such
as when the last wakeup executed and what the value of ->gp_seq was at
that time. This commit therefore removes the current pr_alert() from
rcu_check_gp_start_stall(), instead invoking show_rcu_gp_kthreads(),
which has been updated to print the needed information, which is collected
by rcu_gp_kthread_wake().

Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
---
kernel/rcu/tree.c | 55 +++++++++++++++++++++++++++--------------------
kernel/rcu/tree.h | 2 ++
2 files changed, 34 insertions(+), 23 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index b003a3cfe192..8543a90d53f2 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -512,6 +512,14 @@ void rcu_force_quiescent_state(void)
}
EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);

+/*
+ * Return the root node of the rcu_state structure.
+ */
+static struct rcu_node *rcu_get_root(void)
+{
+ return &rcu_state.node[0];
+}
+
/*
* Convert a ->gp_state value to a character string.
*/
@@ -529,19 +537,30 @@ void show_rcu_gp_kthreads(void)
{
int cpu;
unsigned long j;
+ unsigned long ja;
+ unsigned long jr;
+ unsigned long jw;
struct rcu_data *rdp;
struct rcu_node *rnp;

- j = jiffies - READ_ONCE(rcu_state.gp_activity);
- pr_info("%s: wait state: %s(%d) ->state: %#lx delta ->gp_activity %ld\n",
+ j = jiffies;
+ ja = j - READ_ONCE(rcu_state.gp_activity);
+ jr = j - READ_ONCE(rcu_state.gp_req_activity);
+ jw = j - READ_ONCE(rcu_state.gp_wake_time);
+ pr_info("%s: wait state: %s(%d) ->state: %#lx delta ->gp_activity %lu ->gp_req_activity %lu ->gp_wake_time %lu ->gp_wake_seq %ld ->gp_seq %ld ->gp_seq_needed %ld ->gp_flags %#x\n",
rcu_state.name, gp_state_getname(rcu_state.gp_state),
- rcu_state.gp_state, rcu_state.gp_kthread->state, j);
+ rcu_state.gp_state,
+ rcu_state.gp_kthread ? rcu_state.gp_kthread->state : 0x1ffffL,
+ ja, jr, jw, (long)READ_ONCE(rcu_state.gp_wake_seq),
+ (long)READ_ONCE(rcu_state.gp_seq),
+ (long)READ_ONCE(rcu_get_root()->gp_seq_needed),
+ READ_ONCE(rcu_state.gp_flags));
rcu_for_each_node_breadth_first(rnp) {
if (ULONG_CMP_GE(rcu_state.gp_seq, rnp->gp_seq_needed))
continue;
- pr_info("\trcu_node %d:%d ->gp_seq %lu ->gp_seq_needed %lu\n",
- rnp->grplo, rnp->grphi, rnp->gp_seq,
- rnp->gp_seq_needed);
+ pr_info("\trcu_node %d:%d ->gp_seq %ld ->gp_seq_needed %ld\n",
+ rnp->grplo, rnp->grphi, (long)rnp->gp_seq,
+ (long)rnp->gp_seq_needed);
if (!rcu_is_leaf_node(rnp))
continue;
for_each_leaf_node_possible_cpu(rnp, cpu) {
@@ -550,8 +569,8 @@ void show_rcu_gp_kthreads(void)
ULONG_CMP_GE(rcu_state.gp_seq,
rdp->gp_seq_needed))
continue;
- pr_info("\tcpu %d ->gp_seq_needed %lu\n",
- cpu, rdp->gp_seq_needed);
+ pr_info("\tcpu %d ->gp_seq_needed %ld\n",
+ cpu, (long)rdp->gp_seq_needed);
}
}
/* sched_show_task(rcu_state.gp_kthread); */
@@ -577,14 +596,6 @@ void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
}
EXPORT_SYMBOL_GPL(rcutorture_get_gp_data);

-/*
- * Return the root node of the rcu_state structure.
- */
-static struct rcu_node *rcu_get_root(void)
-{
- return &rcu_state.node[0];
-}
-
/*
* Enter an RCU extended quiescent state, which can be either the
* idle loop or adaptive-tickless usermode execution.
@@ -1560,7 +1571,8 @@ static bool rcu_future_gp_cleanup(struct rcu_node *rnp)
* Awaken the grace-period kthread. Don't do a self-awaken, and don't
* bother awakening when there is nothing for the grace-period kthread
* to do (as in several CPUs raced to awaken, and we lost), and finally
- * don't try to awaken a kthread that has not yet been created.
+ * don't try to awaken a kthread that has not yet been created. If
+ * all those checks are passed, track some debug information and awaken.
*/
static void rcu_gp_kthread_wake(void)
{
@@ -1568,6 +1580,8 @@ static void rcu_gp_kthread_wake(void)
!READ_ONCE(rcu_state.gp_flags) ||
!rcu_state.gp_kthread)
return;
+ WRITE_ONCE(rcu_state.gp_wake_time, jiffies);
+ WRITE_ONCE(rcu_state.gp_wake_seq, READ_ONCE(rcu_state.gp_seq));
swake_up_one(&rcu_state.gp_wq);
}

@@ -2657,16 +2671,11 @@ rcu_check_gp_start_stall(struct rcu_node *rnp, struct rcu_data *rdp,
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
return;
}
- pr_alert("%s: g%ld->%ld gar:%lu ga:%lu f%#x gs:%d %s->state:%#lx\n",
- __func__, (long)READ_ONCE(rcu_state.gp_seq),
- (long)READ_ONCE(rnp_root->gp_seq_needed),
- j - rcu_state.gp_req_activity, j - rcu_state.gp_activity,
- rcu_state.gp_flags, rcu_state.gp_state, rcu_state.name,
- rcu_state.gp_kthread ? rcu_state.gp_kthread->state : 0x1ffffL);
WARN_ON(1);
if (rnp_root != rnp)
raw_spin_unlock_rcu_node(rnp_root);
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+ show_rcu_gp_kthreads();
}

/*
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 008c356c7033..1f2ada7ef7d7 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -309,6 +309,8 @@ struct rcu_state {
struct swait_queue_head gp_wq; /* Where GP task waits. */
short gp_flags; /* Commands for GP task. */
short gp_state; /* GP kthread sleep state. */
+ unsigned long gp_wake_time; /* Last GP kthread wake. */
+ unsigned long gp_wake_seq; /* ->gp_seq at ^^^. */

/* End of fields guarded by root rcu_node's lock. */

--
2.17.1
\
 
 \ /
  Last update: 2019-01-09 22:29    [W:0.141 / U:0.012 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site