From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
To: linux-kernel@vger.kernel.org
Cc: mingo@kernel.org, jiangshanlai@gmail.com, dipankar@in.ibm.com,
akpm@linux-foundation.org, mathieu.desnoyers@efficios.com,
josh@joshtriplett.org, tglx@linutronix.de, peterz@infradead.org,
rostedt@goodmis.org, dhowells@redhat.com, edumazet@google.com,
fweisbec@gmail.com, oleg@redhat.com, joel@joelfernandes.org,
"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Subject: [PATCH tip/core/rcu 20/22] rcu: Add CPU online/offline state to dump_blkd_tasks()
Date: Tue, 26 Jun 2018 10:10:46 -0700 [thread overview]
Message-ID: <20180626171048.2181-20-paulmck@linux.vnet.ibm.com> (raw)
In-Reply-To: <20180626002052.GA24146@linux.vnet.ibm.com>
Interactions between CPU-hotplug operations and grace-period
initialization can result in dump_blkd_tasks(). One of the first
debugging actions in this case is to search back in dmesg to work
out which of the affected rcu_node structure's CPUs are online and to
determine the last CPU-hotplug operation affecting any of those CPUs.
This can be laborious and error-prone, especially when console output
is lost.
This commit therefore causes dump_blkd_tasks() to dump the state of
the affected rcu_node structure's CPUs and the last grace period during
which the last offline and online operation affected each of these CPUs.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
kernel/rcu/tree.c | 12 ++++++++++--
kernel/rcu/tree.h | 12 +++++++++---
kernel/rcu/tree_plugin.h | 25 ++++++++++++++++++++-----
3 files changed, 39 insertions(+), 10 deletions(-)
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index c698a595b932..1e87ff1154a5 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1954,7 +1954,7 @@ static bool rcu_gp_init(struct rcu_state *rsp)
rcu_gp_slow(rsp, gp_init_delay);
raw_spin_lock_irqsave_rcu_node(rnp, flags);
rdp = this_cpu_ptr(rsp->rda);
- rcu_preempt_check_blocked_tasks(rnp);
+ rcu_preempt_check_blocked_tasks(rsp, rnp);
rnp->qsmask = rnp->qsmaskinit;
WRITE_ONCE(rnp->gp_seq, rsp->gp_seq);
if (rnp == rdp->mynode)
@@ -2063,7 +2063,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
rcu_for_each_node_breadth_first(rsp, rnp) {
raw_spin_lock_irq_rcu_node(rnp);
if (WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)))
- dump_blkd_tasks(rnp, 10);
+ dump_blkd_tasks(rsp, rnp, 10);
WARN_ON_ONCE(rnp->qsmask);
WRITE_ONCE(rnp->gp_seq, new_gp_seq);
rdp = this_cpu_ptr(rsp->rda);
@@ -3514,6 +3514,10 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp)
rdp->dynticks = &per_cpu(rcu_dynticks, cpu);
WARN_ON_ONCE(rdp->dynticks->dynticks_nesting != 1);
WARN_ON_ONCE(rcu_dynticks_in_eqs(rcu_dynticks_snap(rdp->dynticks)));
+ rdp->rcu_ofl_gp_seq = rsp->gp_seq;
+ rdp->rcu_ofl_gp_flags = RCU_GP_CLEANED;
+ rdp->rcu_onl_gp_seq = rsp->gp_seq;
+ rdp->rcu_onl_gp_flags = RCU_GP_CLEANED;
rdp->cpu = cpu;
rdp->rsp = rsp;
rcu_boot_init_nocb_percpu_data(rdp);
@@ -3709,6 +3713,8 @@ void rcu_cpu_starting(unsigned int cpu)
/* Allow lockless access for expedited grace periods. */
smp_store_release(&rsp->ncpus, rsp->ncpus + nbits); /* ^^^ */
rcu_gpnum_ovf(rnp, rdp); /* Offline-induced counter wrap? */
+ rdp->rcu_onl_gp_seq = READ_ONCE(rsp->gp_seq);
+ rdp->rcu_onl_gp_flags = READ_ONCE(rsp->gp_flags);
if (rnp->qsmask & mask) { /* RCU waiting on incoming CPU? */
/* Report QS -after- changing ->qsmaskinitnext! */
rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags);
@@ -3736,6 +3742,8 @@ static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp)
mask = rdp->grpmask;
spin_lock(&rsp->ofl_lock);
raw_spin_lock_irqsave_rcu_node(rnp, flags); /* Enforce GP memory-order guarantee. */
+ rdp->rcu_ofl_gp_seq = READ_ONCE(rsp->gp_seq);
+ rdp->rcu_ofl_gp_flags = READ_ONCE(rsp->gp_flags);
if (rnp->qsmask & mask) { /* RCU waiting on outgoing CPU? */
/* Report quiescent state -before- changing ->qsmaskinitnext! */
rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags);
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 795d469c6f67..f52bc059bfec 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -255,12 +255,16 @@ struct rcu_data {
/* Leader CPU takes GP-end wakeups. */
#endif /* #ifdef CONFIG_RCU_NOCB_CPU */
- /* 7) RCU CPU stall data. */
+ /* 7) Diagnostic data, including RCU CPU stall warnings. */
unsigned int softirq_snap; /* Snapshot of softirq activity. */
/* ->rcu_iw* fields protected by leaf rcu_node ->lock. */
struct irq_work rcu_iw; /* Check for non-irq activity. */
bool rcu_iw_pending; /* Is ->rcu_iw pending? */
unsigned long rcu_iw_gp_seq; /* ->gp_seq associated with ->rcu_iw. */
+ unsigned long rcu_ofl_gp_seq; /* ->gp_seq at last offline. */
+ short rcu_ofl_gp_flags; /* ->gp_flags at last offline. */
+ unsigned long rcu_onl_gp_seq; /* ->gp_seq at last online. */
+ short rcu_onl_gp_flags; /* ->gp_flags at last online. */
int cpu;
struct rcu_state *rsp;
@@ -431,11 +435,13 @@ static bool rcu_preempt_has_tasks(struct rcu_node *rnp);
static void rcu_print_detail_task_stall(struct rcu_state *rsp);
static int rcu_print_task_stall(struct rcu_node *rnp);
static int rcu_print_task_exp_stall(struct rcu_node *rnp);
-static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp);
+static void rcu_preempt_check_blocked_tasks(struct rcu_state *rsp,
+ struct rcu_node *rnp);
static void rcu_preempt_check_callbacks(void);
void call_rcu(struct rcu_head *head, rcu_callback_t func);
static void __init __rcu_init_preempt(void);
-static void dump_blkd_tasks(struct rcu_node *rnp, int ncheck);
+static void dump_blkd_tasks(struct rcu_state *rsp, struct rcu_node *rnp,
+ int ncheck);
static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags);
static void rcu_preempt_boost_start_gp(struct rcu_node *rnp);
static void invoke_rcu_callbacks_kthread(void);
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index f45ff97b0d51..613372246a07 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -699,13 +699,14 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp)
* Also, if there are blocked tasks on the list, they automatically
* block the newly created grace period, so set up ->gp_tasks accordingly.
*/
-static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
+static void
+rcu_preempt_check_blocked_tasks(struct rcu_state *rsp, struct rcu_node *rnp)
{
struct task_struct *t;
RCU_LOCKDEP_WARN(preemptible(), "rcu_preempt_check_blocked_tasks() invoked with preemption enabled!!!\n");
if (WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)))
- dump_blkd_tasks(rnp, 10);
+ dump_blkd_tasks(rsp, rnp, 10);
if (rcu_preempt_has_tasks(rnp) &&
(rnp->qsmaskinit || rnp->wait_blkd_tasks)) {
rnp->gp_tasks = rnp->blkd_tasks.next;
@@ -854,10 +855,14 @@ void exit_rcu(void)
* Dump the blocked-tasks state, but limit the list dump to the
* specified number of elements.
*/
-static void dump_blkd_tasks(struct rcu_node *rnp, int ncheck)
+static void
+dump_blkd_tasks(struct rcu_state *rsp, struct rcu_node *rnp, int ncheck)
{
+ int cpu;
int i;
struct list_head *lhp;
+ bool onl;
+ struct rcu_data *rdp;
struct rcu_node *rnp1;
raw_lockdep_assert_held_rcu_node(rnp);
@@ -877,6 +882,14 @@ static void dump_blkd_tasks(struct rcu_node *rnp, int ncheck)
break;
}
pr_cont("\n");
+ for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++) {
+ rdp = per_cpu_ptr(rsp->rda, cpu);
+ onl = !!(rdp->grpmask & rcu_rnp_online_cpus(rnp));
+ pr_info("\t%d: %c online: %ld(%d) offline: %ld(%d)\n",
+ cpu, ".o"[onl],
+ (long)rdp->rcu_onl_gp_seq, rdp->rcu_onl_gp_flags,
+ (long)rdp->rcu_ofl_gp_seq, rdp->rcu_ofl_gp_flags);
+ }
}
#else /* #ifdef CONFIG_PREEMPT_RCU */
@@ -949,7 +962,8 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp)
* so there is no need to check for blocked tasks. So check only for
* bogus qsmask values.
*/
-static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
+static void
+rcu_preempt_check_blocked_tasks(struct rcu_state *rsp, struct rcu_node *rnp)
{
WARN_ON_ONCE(rnp->qsmask);
}
@@ -990,7 +1004,8 @@ void exit_rcu(void)
/*
* Dump the guaranteed-empty blocked-tasks state. Trust but verify.
*/
-static void dump_blkd_tasks(struct rcu_node *rnp, int ncheck)
+static void
+dump_blkd_tasks(struct rcu_state *rsp, struct rcu_node *rnp, int ncheck)
{
WARN_ON_ONCE(!list_empty(&rnp->blkd_tasks));
}
--
2.17.1
next prev parent reply other threads:[~2018-06-26 17:12 UTC|newest]
Thread overview: 45+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-06-26 0:20 [PATCH tip/core/rcu 0/22] Grace-period fixes for v4.19 Paul E. McKenney
2018-06-26 17:10 ` [PATCH tip/core/rcu 01/22] rcu: Clean up handling of tasks blocked across full-rcu_node offline Paul E. McKenney
2018-06-26 17:10 ` [PATCH tip/core/rcu 02/22] rcu: Fix an obsolete ->qsmaskinit comment Paul E. McKenney
2018-06-26 17:10 ` [PATCH tip/core/rcu 03/22] rcu: Make rcu_init_new_rnp() stop upon already-set bit Paul E. McKenney
2018-06-26 17:10 ` [PATCH tip/core/rcu 04/22] rcu: Make rcu_report_unblock_qs_rnp() warn on violated preconditions Paul E. McKenney
2018-06-26 17:10 ` [PATCH tip/core/rcu 05/22] rcu: Fix typo and add additional debug Paul E. McKenney
2018-06-26 17:10 ` [PATCH tip/core/rcu 06/22] rcu: Replace smp_wmb() with smp_store_release() for stall check Paul E. McKenney
2018-06-26 17:10 ` [PATCH tip/core/rcu 07/22] rcu: Prevent useless FQS scan after all CPUs have checked in Paul E. McKenney
2018-06-26 17:10 ` [PATCH tip/core/rcu 08/22] rcu: Suppress false-positive offline-CPU lockdep-RCU splat Paul E. McKenney
2018-06-26 17:10 ` [PATCH tip/core/rcu 09/22] rcu: Suppress false-positive preempted-task splats Paul E. McKenney
2018-06-26 17:10 ` [PATCH tip/core/rcu 10/22] rcu: Suppress more involved " Paul E. McKenney
2018-06-26 17:10 ` [PATCH tip/core/rcu 11/22] rcu: Suppress false-positive splats from mid-init task resume Paul E. McKenney
2018-06-26 17:10 ` [PATCH tip/core/rcu 12/22] rcu: Fix grace-period hangs " Paul E. McKenney
2018-06-26 17:10 ` [PATCH tip/core/rcu 13/22] rcu: Fix grace-period hangs due to race with CPU offline Paul E. McKenney
2018-06-26 17:44 ` Peter Zijlstra
2018-06-26 18:19 ` Paul E. McKenney
2018-06-26 19:48 ` Peter Zijlstra
2018-06-26 20:40 ` Paul E. McKenney
2018-06-26 17:51 ` Peter Zijlstra
2018-06-26 18:29 ` Paul E. McKenney
2018-06-26 20:07 ` Peter Zijlstra
2018-06-26 20:26 ` Paul E. McKenney
2018-06-26 20:32 ` Peter Zijlstra
2018-06-26 23:40 ` Paul E. McKenney
2018-06-27 8:33 ` Peter Zijlstra
2018-06-27 15:43 ` Paul E. McKenney
2018-06-27 9:11 ` Peter Zijlstra
2018-06-27 9:46 ` Peter Zijlstra
2018-06-27 15:57 ` Paul E. McKenney
2018-06-27 17:51 ` Peter Zijlstra
2018-06-28 5:13 ` Paul E. McKenney
2018-06-28 8:26 ` Peter Zijlstra
2018-06-28 12:38 ` Paul E. McKenney
2018-06-28 13:06 ` Peter Zijlstra
2018-06-29 4:30 ` Paul E. McKenney
2018-06-27 15:53 ` Paul E. McKenney
2018-06-26 17:10 ` [PATCH tip/core/rcu 14/22] rcu: Add RCU-preempt check for waiting on newly onlined CPU Paul E. McKenney
2018-06-26 17:10 ` [PATCH tip/core/rcu 15/22] rcu: Move grace-period pre-init delay after pre-init Paul E. McKenney
2018-06-26 17:10 ` [PATCH tip/core/rcu 16/22] rcu: Remove failsafe check for lost quiescent state Paul E. McKenney
2018-06-26 17:10 ` [PATCH tip/core/rcu 17/22] rcutorture: Change units of onoff_interval to jiffies Paul E. McKenney
2018-06-26 17:10 ` [PATCH tip/core/rcu 18/22] rcu: Remove CPU-hotplug failsafe from force-quiescent-state code path Paul E. McKenney
2018-06-26 17:10 ` [PATCH tip/core/rcu 19/22] rcu: Add up-tree information to dump_blkd_tasks() diagnostics Paul E. McKenney
2018-06-26 17:10 ` Paul E. McKenney [this message]
2018-06-26 17:10 ` [PATCH tip/core/rcu 21/22] rcu: Record ->gp_state for both phases of grace-period initialization Paul E. McKenney
2018-06-26 17:10 ` [PATCH tip/core/rcu 22/22] rcu: Add diagnostics for offline CPUs failing to report QS Paul E. McKenney
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20180626171048.2181-20-paulmck@linux.vnet.ibm.com \
--to=paulmck@linux.vnet.ibm.com \
--cc=akpm@linux-foundation.org \
--cc=dhowells@redhat.com \
--cc=dipankar@in.ibm.com \
--cc=edumazet@google.com \
--cc=fweisbec@gmail.com \
--cc=jiangshanlai@gmail.com \
--cc=joel@joelfernandes.org \
--cc=josh@joshtriplett.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mathieu.desnoyers@efficios.com \
--cc=mingo@kernel.org \
--cc=oleg@redhat.com \
--cc=peterz@infradead.org \
--cc=rostedt@goodmis.org \
--cc=tglx@linutronix.de \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®