Merge tag 'rcu-next-v6.7' of git://git.kernel.org/pub/scm/linux/kernel/git/frederic/linux-dynticks

Pull RCU updates from Frederic Weisbecker:

 - RCU torture, locktorture and generic torture infrastructure updates
   that include various fixes, cleanups and consolidations.

   Among the user visible things, ftrace dumps can now be found into
   their own file, and module parameters get better documented and
   reported on dumps.

 - Generic and misc fixes all over the place. Some highlights:

     * Hotplug handling has seen some light cleanups and comments

     * An RCU barrier can now be triggered through sysfs to serialize
       memory stress testing and avoid OOM

     * Object information is now dumped in case of invalid callback
       invocation

     * Also various SRCU issues, too hard to trigger to deserve urgent
       pull requests, have been fixed

 - RCU documentation updates

 - RCU reference scalability test minor fixes and doc improvements.

 - RCU tasks minor fixes

 - Stall detection updates. Introduce RCU CPU Stall notifiers that
   allows a subsystem to provide informations to help debugging. Also
   cure some false positive stalls.

* tag 'rcu-next-v6.7' of git://git.kernel.org/pub/scm/linux/kernel/git/frederic/linux-dynticks: (56 commits)
  srcu: Only accelerate on enqueue time
  locktorture: Check the correct variable for allocation failure
  srcu: Fix callbacks acceleration mishandling
  rcu: Comment why callbacks migration can't wait for CPUHP_RCUTREE_PREP
  rcu: Standardize explicit CPU-hotplug calls
  rcu: Conditionally build CPU-hotplug teardown callbacks
  rcu: Remove references to rcu_migrate_callbacks() from diagrams
  rcu: Assume rcu_report_dead() is always called locally
  rcu: Assume IRQS disabled from rcu_report_dead()
  rcu: Use rcu_segcblist_segempty() instead of open coding it
  rcu: kmemleak: Ignore kmemleak false positives when RCU-freeing objects
  srcu: Fix srcu_struct node grpmask overflow on 64-bit systems
  torture: Convert parse-console.sh to mktemp
  rcutorture: Traverse possible cpu to set maxcpu in rcu_nocb_toggle()
  rcutorture: Replace schedule_timeout*() 1-jiffy waits with HZ/20
  torture: Add kvm.sh --debug-info argument
  locktorture: Rename readers_bind/writers_bind to bind_readers/bind_writers
  doc: Catch-up update for locktorture module parameters
  locktorture: Add call_rcu_chains module parameter
  locktorture: Add new module parameters to lock_torture_print_module_parms()
  ...

1 files changed, 170 insertions, 72 deletions

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index cb1caefa8bd0..700524726079 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -31,6 +31,7 @@
 #include <linux/bitops.h>
 #include <linux/export.h>
 #include <linux/completion.h>
+#include <linux/kmemleak.h>
 #include <linux/moduleparam.h>
 #include <linux/panic.h>
 #include <linux/panic_notifier.h>
@@ -1260,7 +1261,7 @@ EXPORT_SYMBOL_GPL(rcu_gp_slow_register);
 /* Unregister a counter, with NULL for not caring which. */
 void rcu_gp_slow_unregister(atomic_t *rgssp)
 {
-	WARN_ON_ONCE(rgssp && rgssp != rcu_gp_slow_suppress);
+	WARN_ON_ONCE(rgssp && rgssp != rcu_gp_slow_suppress && rcu_gp_slow_suppress != NULL);
 
 	WRITE_ONCE(rcu_gp_slow_suppress, NULL);
 }
@@ -1556,10 +1557,22 @@ static bool rcu_gp_fqs_check_wake(int *gfp)
  */
 static void rcu_gp_fqs(bool first_time)
 {
+	int nr_fqs = READ_ONCE(rcu_state.nr_fqs_jiffies_stall);
 	struct rcu_node *rnp = rcu_get_root();
 
 	WRITE_ONCE(rcu_state.gp_activity, jiffies);
 	WRITE_ONCE(rcu_state.n_force_qs, rcu_state.n_force_qs + 1);
+
+	WARN_ON_ONCE(nr_fqs > 3);
+	/* Only countdown nr_fqs for stall purposes if jiffies moves. */
+	if (nr_fqs) {
+		if (nr_fqs == 1) {
+			WRITE_ONCE(rcu_state.jiffies_stall,
+				   jiffies + rcu_jiffies_till_stall_check());
+		}
+		WRITE_ONCE(rcu_state.nr_fqs_jiffies_stall, --nr_fqs);
+	}
+
 	if (first_time) {
 		/* Collect dyntick-idle snapshots. */
 		force_qs_rnp(dyntick_save_progress_counter);
@@ -2135,6 +2148,7 @@ static void rcu_do_batch(struct rcu_data *rdp)
 		trace_rcu_invoke_callback(rcu_state.name, rhp);
 
 		f = rhp->func;
+		debug_rcu_head_callback(rhp);
 		WRITE_ONCE(rhp->func, (rcu_callback_t)0L);
 		f(rhp);
 
@@ -2713,7 +2727,7 @@ __call_rcu_common(struct rcu_head *head, rcu_callback_t func, bool lazy_in)
  */
 void call_rcu_hurry(struct rcu_head *head, rcu_callback_t func)
 {
-	return __call_rcu_common(head, func, false);
+	__call_rcu_common(head, func, false);
 }
 EXPORT_SYMBOL_GPL(call_rcu_hurry);
 #endif
@@ -2764,7 +2778,7 @@ EXPORT_SYMBOL_GPL(call_rcu_hurry);
  */
 void call_rcu(struct rcu_head *head, rcu_callback_t func)
 {
-	return __call_rcu_common(head, func, IS_ENABLED(CONFIG_RCU_LAZY));
+	__call_rcu_common(head, func, IS_ENABLED(CONFIG_RCU_LAZY));
 }
 EXPORT_SYMBOL_GPL(call_rcu);
 
@@ -3388,6 +3402,14 @@ void kvfree_call_rcu(struct rcu_head *head, void *ptr)
 		success = true;
 	}
 
+	/*
+	 * The kvfree_rcu() caller considers the pointer freed at this point
+	 * and likely removes any references to it. Since the actual slab
+	 * freeing (and kmemleak_free()) is deferred, tell kmemleak to ignore
+	 * this object (no scanning or false positives reporting).
+	 */
+	kmemleak_ignore(ptr);
+
 	// Set timer to drain after KFREE_DRAIN_JIFFIES.
 	if (rcu_scheduler_active == RCU_SCHEDULER_RUNNING)
 		schedule_delayed_monitor_work(krcp);
@@ -4083,6 +4105,82 @@ retry:
 }
 EXPORT_SYMBOL_GPL(rcu_barrier);
 
+static unsigned long rcu_barrier_last_throttle;
+
+/**
+ * rcu_barrier_throttled - Do rcu_barrier(), but limit to one per second
+ *
+ * This can be thought of as guard rails around rcu_barrier() that
+ * permits unrestricted userspace use, at least assuming the hardware's
+ * try_cmpxchg() is robust.  There will be at most one call per second to
+ * rcu_barrier() system-wide from use of this function, which means that
+ * callers might needlessly wait a second or three.
+ *
+ * This is intended for use by test suites to avoid OOM by flushing RCU
+ * callbacks from the previous test before starting the next.  See the
+ * rcutree.do_rcu_barrier module parameter for more information.
+ *
+ * Why not simply make rcu_barrier() more scalable?  That might be
+ * the eventual endpoint, but let's keep it simple for the time being.
+ * Note that the module parameter infrastructure serializes calls to a
+ * given .set() function, but should concurrent .set() invocation ever be
+ * possible, we are ready!
+ */
+static void rcu_barrier_throttled(void)
+{
+	unsigned long j = jiffies;
+	unsigned long old = READ_ONCE(rcu_barrier_last_throttle);
+	unsigned long s = rcu_seq_snap(&rcu_state.barrier_sequence);
+
+	while (time_in_range(j, old, old + HZ / 16) ||
+	       !try_cmpxchg(&rcu_barrier_last_throttle, &old, j)) {
+		schedule_timeout_idle(HZ / 16);
+		if (rcu_seq_done(&rcu_state.barrier_sequence, s)) {
+			smp_mb(); /* caller's subsequent code after above check. */
+			return;
+		}
+		j = jiffies;
+		old = READ_ONCE(rcu_barrier_last_throttle);
+	}
+	rcu_barrier();
+}
+
+/*
+ * Invoke rcu_barrier_throttled() when a rcutree.do_rcu_barrier
+ * request arrives.  We insist on a true value to allow for possible
+ * future expansion.
+ */
+static int param_set_do_rcu_barrier(const char *val, const struct kernel_param *kp)
+{
+	bool b;
+	int ret;
+
+	if (rcu_scheduler_active != RCU_SCHEDULER_RUNNING)
+		return -EAGAIN;
+	ret = kstrtobool(val, &b);
+	if (!ret && b) {
+		atomic_inc((atomic_t *)kp->arg);
+		rcu_barrier_throttled();
+		atomic_dec((atomic_t *)kp->arg);
+	}
+	return ret;
+}
+
+/*
+ * Output the number of outstanding rcutree.do_rcu_barrier requests.
+ */
+static int param_get_do_rcu_barrier(char *buffer, const struct kernel_param *kp)
+{
+	return sprintf(buffer, "%d\n", atomic_read((atomic_t *)kp->arg));
+}
+
+static const struct kernel_param_ops do_rcu_barrier_ops = {
+	.set = param_set_do_rcu_barrier,
+	.get = param_get_do_rcu_barrier,
+};
+static atomic_t do_rcu_barrier;
+module_param_cb(do_rcu_barrier, &do_rcu_barrier_ops, &do_rcu_barrier, 0644);
+
 /*
  * Compute the mask of online CPUs for the specified rcu_node structure.
  * This will not be stable unless the rcu_node structure's ->lock is
@@ -4130,7 +4228,7 @@ bool rcu_lockdep_current_cpu_online(void)
 	rdp = this_cpu_ptr(&rcu_data);
 	/*
 	 * Strictly, we care here about the case where the current CPU is
-	 * in rcu_cpu_starting() and thus has an excuse for rdp->grpmask
+	 * in rcutree_report_cpu_starting() and thus has an excuse for rdp->grpmask
 	 * not being up to date. So arch_spin_is_locked() might have a
 	 * false positive if it's held by some *other* CPU, but that's
 	 * OK because that just means a false *negative* on the warning.
@@ -4152,25 +4250,6 @@ static bool rcu_init_invoked(void)
 }
 
 /*
- * Near the end of the offline process.  Trace the fact that this CPU
- * is going offline.
- */
-int rcutree_dying_cpu(unsigned int cpu)
-{
-	bool blkd;
-	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
-	struct rcu_node *rnp = rdp->mynode;
-
-	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
-		return 0;
-
-	blkd = !!(READ_ONCE(rnp->qsmask) & rdp->grpmask);
-	trace_rcu_grace_period(rcu_state.name, READ_ONCE(rnp->gp_seq),
-			       blkd ? TPS("cpuofl-bgp") : TPS("cpuofl"));
-	return 0;
-}
-
-/*
  * All CPUs for the specified rcu_node structure have gone offline,
  * and all tasks that were preempted within an RCU read-side critical
  * section while running on one of those CPUs have since exited their RCU
@@ -4216,23 +4295,6 @@ static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf)
 }
 
 /*
- * The CPU has been completely removed, and some other CPU is reporting
- * this fact from process context.  Do the remainder of the cleanup.
- * There can only be one CPU hotplug operation at a time, so no need for
- * explicit locking.
- */
-int rcutree_dead_cpu(unsigned int cpu)
-{
-	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
-		return 0;
-
-	WRITE_ONCE(rcu_state.n_online_cpus, rcu_state.n_online_cpus - 1);
-	// Stop-machine done, so allow nohz_full to disable tick.
-	tick_dep_clear(TICK_DEP_BIT_RCU);
-	return 0;
-}
-
-/*
  * Propagate ->qsinitmask bits up the rcu_node tree to account for the
  * first CPU in a given leaf rcu_node structure coming online.  The caller
  * must hold the corresponding leaf rcu_node ->lock with interrupts
@@ -4385,29 +4447,6 @@ int rcutree_online_cpu(unsigned int cpu)
 }
 
 /*
- * Near the beginning of the process.  The CPU is still very much alive
- * with pretty much all services enabled.
- */
-int rcutree_offline_cpu(unsigned int cpu)
-{
-	unsigned long flags;
-	struct rcu_data *rdp;
-	struct rcu_node *rnp;
-
-	rdp = per_cpu_ptr(&rcu_data, cpu);
-	rnp = rdp->mynode;
-	raw_spin_lock_irqsave_rcu_node(rnp, flags);
-	rnp->ffmask &= ~rdp->grpmask;
-	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-
-	rcutree_affinity_setting(cpu, cpu);
-
-	// nohz_full CPUs need the tick for stop-machine to work quickly
-	tick_dep_set(TICK_DEP_BIT_RCU);
-	return 0;
-}
-
-/*
  * Mark the specified CPU as being online so that subsequent grace periods
  * (both expedited and normal) will wait on it.  Note that this means that
  * incoming CPUs are not allowed to use RCU read-side critical sections
@@ -4418,8 +4457,10 @@ int rcutree_offline_cpu(unsigned int cpu)
  * from the incoming CPU rather than from the cpuhp_step mechanism.
  * This is because this function must be invoked at a precise location.
  * This incoming CPU must not have enabled interrupts yet.
+ *
+ * This mirrors the effects of rcutree_report_cpu_dead().
  */
-void rcu_cpu_starting(unsigned int cpu)
+void rcutree_report_cpu_starting(unsigned int cpu)
 {
 	unsigned long mask;
 	struct rcu_data *rdp;
@@ -4473,14 +4514,21 @@ void rcu_cpu_starting(unsigned int cpu)
  * Note that this function is special in that it is invoked directly
  * from the outgoing CPU rather than from the cpuhp_step mechanism.
  * This is because this function must be invoked at a precise location.
+ *
+ * This mirrors the effect of rcutree_report_cpu_starting().
  */
-void rcu_report_dead(unsigned int cpu)
+void rcutree_report_cpu_dead(void)
 {
-	unsigned long flags, seq_flags;
+	unsigned long flags;
 	unsigned long mask;
-	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
+	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
 	struct rcu_node *rnp = rdp->mynode;  /* Outgoing CPU's rdp & rnp. */
 
+	/*
+	 * IRQS must be disabled from now on and until the CPU dies, or an interrupt
+	 * may introduce a new READ-side while it is actually off the QS masks.
+	 */
+	lockdep_assert_irqs_disabled();
 	// Do any dangling deferred wakeups.
 	do_nocb_deferred_wakeup(rdp);
 
@@ -4488,7 +4536,6 @@ void rcu_report_dead(unsigned int cpu)
 
 	/* Remove outgoing CPU from mask in the leaf rcu_node structure. */
 	mask = rdp->grpmask;
-	local_irq_save(seq_flags);
 	arch_spin_lock(&rcu_state.ofl_lock);
 	raw_spin_lock_irqsave_rcu_node(rnp, flags); /* Enforce GP memory-order guarantee. */
 	rdp->rcu_ofl_gp_seq = READ_ONCE(rcu_state.gp_seq);
@@ -4502,8 +4549,6 @@ void rcu_report_dead(unsigned int cpu)
 	WRITE_ONCE(rnp->qsmaskinitnext, rnp->qsmaskinitnext & ~mask);
 	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	arch_spin_unlock(&rcu_state.ofl_lock);
-	local_irq_restore(seq_flags);
-
 	rdp->cpu_started = false;
 }
 
@@ -4558,7 +4603,60 @@ void rcutree_migrate_callbacks(int cpu)
 		  cpu, rcu_segcblist_n_cbs(&rdp->cblist),
 		  rcu_segcblist_first_cb(&rdp->cblist));
 }
-#endif
+
+/*
+ * The CPU has been completely removed, and some other CPU is reporting
+ * this fact from process context.  Do the remainder of the cleanup.
+ * There can only be one CPU hotplug operation at a time, so no need for
+ * explicit locking.
+ */
+int rcutree_dead_cpu(unsigned int cpu)
+{
+	WRITE_ONCE(rcu_state.n_online_cpus, rcu_state.n_online_cpus - 1);
+	// Stop-machine done, so allow nohz_full to disable tick.
+	tick_dep_clear(TICK_DEP_BIT_RCU);
+	return 0;
+}
+
+/*
+ * Near the end of the offline process.  Trace the fact that this CPU
+ * is going offline.
+ */
+int rcutree_dying_cpu(unsigned int cpu)
+{
+	bool blkd;
+	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
+	struct rcu_node *rnp = rdp->mynode;
+
+	blkd = !!(READ_ONCE(rnp->qsmask) & rdp->grpmask);
+	trace_rcu_grace_period(rcu_state.name, READ_ONCE(rnp->gp_seq),
+			       blkd ? TPS("cpuofl-bgp") : TPS("cpuofl"));
+	return 0;
+}
+
+/*
+ * Near the beginning of the process.  The CPU is still very much alive
+ * with pretty much all services enabled.
+ */
+int rcutree_offline_cpu(unsigned int cpu)
+{
+	unsigned long flags;
+	struct rcu_data *rdp;
+	struct rcu_node *rnp;
+
+	rdp = per_cpu_ptr(&rcu_data, cpu);
+	rnp = rdp->mynode;
+	raw_spin_lock_irqsave_rcu_node(rnp, flags);
+	rnp->ffmask &= ~rdp->grpmask;
+	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+
+	rcutree_affinity_setting(cpu, cpu);
+
+	// nohz_full CPUs need the tick for stop-machine to work quickly
+	tick_dep_set(TICK_DEP_BIT_RCU);
+	return 0;
+}
+#endif /* #ifdef CONFIG_HOTPLUG_CPU */
 
 /*
  * On non-huge systems, use expedited RCU grace periods to make suspend
@@ -4990,7 +5088,7 @@ void __init rcu_init(void)
 	pm_notifier(rcu_pm_notify, 0);
 	WARN_ON(num_online_cpus() > 1); // Only one CPU this early in boot.
 	rcutree_prepare_cpu(cpu);
-	rcu_cpu_starting(cpu);
+	rcutree_report_cpu_starting(cpu);
 	rcutree_online_cpu(cpu);
 
 	/* Create workqueue for Tree SRCU and for expedited GPs. */