RCU stall detection updates for v6.7

index 6f06dc12904a..b5ce0580074e 100644
@@ -537,13 +537,11 @@ static void rcu_check_gp_kthread_starvation(void)
 			pr_err("\tUnless %s kthread gets sufficient CPU time, OOM is now expected behavior.\n", rcu_state.name);
 			pr_err("RCU grace-period kthread stack dump:\n");
 			sched_show_task(gpk);
-			if (cpu >= 0) {
-				if (cpu_is_offline(cpu)) {
-					pr_err("RCU GP kthread last ran on offline CPU %d.\n", cpu);
-				} else  {
-					pr_err("Stack dump where RCU GP kthread last ran:\n");
-					dump_cpu_task(cpu);
-				}
+			if (cpu_is_offline(cpu)) {
+				pr_err("RCU GP kthread last ran on offline CPU %d.\n", cpu);
+			} else  {
+				pr_err("Stack dump where RCU GP kthread last ran:\n");
+				dump_cpu_task(cpu);
 			}
 			wake_up_process(gpk);
 		}

index b5ce0580074e..fc04a8d7ce96 100644
@@ -534,12 +534,14 @@ static void rcu_check_gp_kthread_starvation(void)
 		       data_race(READ_ONCE(rcu_state.gp_state)),
 		       gpk ? data_race(READ_ONCE(gpk->__state)) : ~0, cpu);
 		if (gpk) {
+			struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
+
 			pr_err("\tUnless %s kthread gets sufficient CPU time, OOM is now expected behavior.\n", rcu_state.name);
 			pr_err("RCU grace-period kthread stack dump:\n");
 			sched_show_task(gpk);
 			if (cpu_is_offline(cpu)) {
 				pr_err("RCU GP kthread last ran on offline CPU %d.\n", cpu);
-			} else  {
+			} else if (!(data_race(READ_ONCE(rdp->mynode->qsmask)) & rdp->grpmask)) {
 				pr_err("Stack dump where RCU GP kthread last ran:\n");
 				dump_cpu_task(cpu);
 			}

index fc04a8d7ce96..2443d1d4a6dc 100644
@@ -711,7 +711,7 @@ static void print_cpu_stall(unsigned long gps)
 
 static void check_cpu_stall(struct rcu_data *rdp)
 {
-	bool didstall = false;
+	bool self_detected;
 	unsigned long gs1;
 	unsigned long gs2;
 	unsigned long gps;

@@ -758,10 +758,10 @@ static void check_cpu_stall(struct rcu_data *rdp)
 		return; /* No stall or GP completed since entering function. */
 	rnp = rdp->mynode;
 	jn = jiffies + ULONG_MAX / 2;
+	self_detected = READ_ONCE(rnp->qsmask) & rdp->grpmask;
 	if (rcu_gp_in_progress() &&
-	    (READ_ONCE(rnp->qsmask) & rdp->grpmask) &&
+	    (self_detected || ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY)) &&
 	    cmpxchg(&rcu_state.jiffies_stall, js, jn) == js) {
-
 		/*
 		 * If a virtual machine is stopped by the host it can look to
 		 * the watchdog like an RCU stall. Check to see if the host

@@ -770,33 +770,21 @@ static void check_cpu_stall(struct rcu_data *rdp)
 		if (kvm_check_and_clear_guest_paused())
 			return;
 
-		/* We haven't checked in, so go dump stack. */
-		print_cpu_stall(gps);
-		if (READ_ONCE(rcu_cpu_stall_ftrace_dump))
-			rcu_ftrace_dump(DUMP_ALL);
-		didstall = true;
-
-	} else if (rcu_gp_in_progress() &&
-		   ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY) &&
-		   cmpxchg(&rcu_state.jiffies_stall, js, jn) == js) {
+		if (self_detected) {
+			/* We haven't checked in, so go dump stack. */
+			print_cpu_stall(gps);
+		} else {
+			/* They had a few time units to dump stack, so complain. */
+			print_other_cpu_stall(gs2, gps);
+		}
 
-		/*
-		 * If a virtual machine is stopped by the host it can look to
-		 * the watchdog like an RCU stall. Check to see if the host
-		 * stopped the vm.
-		 */
-		if (kvm_check_and_clear_guest_paused())
-			return;
-
-		/* They had a few time units to dump stack, so complain. */
-		print_other_cpu_stall(gs2, gps);
 		if (READ_ONCE(rcu_cpu_stall_ftrace_dump))
 			rcu_ftrace_dump(DUMP_ALL);
-		didstall = true;
-	}
-	if (didstall && READ_ONCE(rcu_state.jiffies_stall) == jn) {
-		jn = jiffies + 3 * rcu_jiffies_till_stall_check() + 3;
-		WRITE_ONCE(rcu_state.jiffies_stall, jn);
+
+		if (READ_ONCE(rcu_state.jiffies_stall) == jn) {
+			jn = jiffies + 3 * rcu_jiffies_till_stall_check() + 3;
+			WRITE_ONCE(rcu_state.jiffies_stall, jn);
+		}
 	}
 }
 

new file mode 100644
index 000000000000..ebf371364581
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * Read-Copy Update notifiers, initially RCU CPU stall notifier.
+ * Separate from rcupdate.h to avoid #include loops.
+ *
+ * Copyright (C) 2023 Paul E. McKenney.
+ */
+
+#ifndef __LINUX_RCU_NOTIFIER_H
+#define __LINUX_RCU_NOTIFIER_H
+
+// Actions for RCU CPU stall notifier calls.
+#define RCU_STALL_NOTIFY_NORM	1
+#define RCU_STALL_NOTIFY_EXP	2
+
+#ifdef CONFIG_RCU_STALL_COMMON
+
+#include <linux/notifier.h>
+#include <linux/types.h>
+
+int rcu_stall_chain_notifier_register(struct notifier_block *n);
+int rcu_stall_chain_notifier_unregister(struct notifier_block *n);
+
+#else // #ifdef CONFIG_RCU_STALL_COMMON
+
+// No RCU CPU stall warnings in Tiny RCU.
+static inline int rcu_stall_chain_notifier_register(struct notifier_block *n) { return -EEXIST; }
+static inline int rcu_stall_chain_notifier_unregister(struct notifier_block *n) { return -ENOENT; }
+
+#endif // #else // #ifdef CONFIG_RCU_STALL_COMMON
+
+#endif /* __LINUX_RCU_NOTIFIER_H */

index 98e13be411af..ef3bab977407 100644
@@ -654,4 +654,10 @@ static inline bool rcu_cpu_beenfullyonline(int cpu) { return true; }
 bool rcu_cpu_beenfullyonline(int cpu);
 #endif
 
+#ifdef CONFIG_RCU_STALL_COMMON
+int rcu_stall_notifier_call_chain(unsigned long val, void *v);
+#else // #ifdef CONFIG_RCU_STALL_COMMON
+static inline int rcu_stall_notifier_call_chain(unsigned long val, void *v) { return NOTIFY_DONE; }
+#endif // #else // #ifdef CONFIG_RCU_STALL_COMMON
+
 #endif /* __LINUX_RCU_H */

index 8239b39d945b..6d7cea5d591f 100644
@@ -621,10 +621,14 @@ static void synchronize_rcu_expedited_wait(void)
 	}
 
 	for (;;) {
+		unsigned long j;
+
 		if (synchronize_rcu_expedited_wait_once(jiffies_stall))
 			return;
 		if (rcu_stall_is_suppressed())
 			continue;
+		j = jiffies;
+		rcu_stall_notifier_call_chain(RCU_STALL_NOTIFY_EXP, (void *)(j - jiffies_start));
 		trace_rcu_stall_warning(rcu_state.name, TPS("ExpeditedStall"));
 		pr_err("INFO: %s detected expedited stalls on CPUs/tasks: {",
 		       rcu_state.name);

@@ -647,7 +651,7 @@ static void synchronize_rcu_expedited_wait(void)
 			}
 		}
 		pr_cont(" } %lu jiffies s: %lu root: %#lx/%c\n",
-			jiffies - jiffies_start, rcu_state.expedited_sequence,
+			j - jiffies_start, rcu_state.expedited_sequence,
 			data_race(rnp_root->expmask),
 			".T"[!!data_race(rnp_root->exp_tasks)]);
 		if (ndetected) {

80 lines not on this page · raw message

index ade42d6a9d9b..1830cacac01d 100644
@@ -21,6 +21,7 @@
 #include <linux/spinlock.h>
 #include <linux/smp.h>
 #include <linux/rcupdate_wait.h>
+#include <linux/rcu_notifier.h>
 #include <linux/interrupt.h>
 #include <linux/sched/signal.h>
 #include <uapi/linux/sched/types.h>

@@ -2428,6 +2429,16 @@ static int rcutorture_booster_init(unsigned int cpu)
 	return 0;
 }
 
+static int rcu_torture_stall_nf(struct notifier_block *nb, unsigned long v, void *ptr)
+{
+	pr_info("%s: v=%lu, duration=%lu.\n", __func__, v, (unsigned long)ptr);
+	return NOTIFY_OK;
+}
+
+static struct notifier_block rcu_torture_stall_block = {
+	.notifier_call = rcu_torture_stall_nf,
+};
+
 /*
  * CPU-stall kthread.  It waits as specified by stall_cpu_holdoff, then
  * induces a CPU stall for the time specified by stall_cpu.

@@ -2435,9 +2446,14 @@ static int rcutorture_booster_init(unsigned int cpu)
 static int rcu_torture_stall(void *args)
 {
 	int idx;
+	int ret;
 	unsigned long stop_at;
 
 	VERBOSE_TOROUT_STRING("rcu_torture_stall task started");
+	ret = rcu_stall_chain_notifier_register(&rcu_torture_stall_block);
+	if (ret)
+		pr_info("%s: rcu_stall_chain_notifier_register() returned %d, %sexpected.\n",
+			__func__, ret, !IS_ENABLED(CONFIG_RCU_STALL_COMMON) ? "un" : "");
 	if (stall_cpu_holdoff > 0) {
 		VERBOSE_TOROUT_STRING("rcu_torture_stall begin holdoff");
 		schedule_timeout_interruptible(stall_cpu_holdoff * HZ);

@@ -2481,6 +2497,11 @@ static int rcu_torture_stall(void *args)
 		cur_ops->readunlock(idx);
 	}
 	pr_alert("%s end.\n", __func__);
+	if (!ret) {
+		ret = rcu_stall_chain_notifier_unregister(&rcu_torture_stall_block);
+		if (ret)
+			pr_info("%s: rcu_stall_chain_notifier_unregister() returned %d.\n", __func__, ret);
+	}
 	torture_shutdown_absorb("rcu_torture_stall");
 	while (!kthread_should_stop())
 		schedule_timeout_interruptible(10 * HZ);

index cb1caefa8bd0..d85779f67aea 100644
@@ -1556,10 +1556,22 @@ 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);

index 192536916f9a..e9821a8422db 100644
@@ -386,6 +386,10 @@ struct rcu_state {
 						/*  in jiffies. */
 	unsigned long jiffies_stall;		/* Time at which to check */
 						/*  for CPU stalls. */
+	int nr_fqs_jiffies_stall;		/* Number of fqs loops after
+						 * which read jiffies and set
+						 * jiffies_stall. Stall
+						 * warnings disabled if !0. */
 	unsigned long jiffies_resched;		/* Time at which to resched */
 						/*  a reluctant CPU. */
 	unsigned long n_force_qs_gpstart;	/* Snapshot of n_force_qs at */

index 49544f932279..ac8e86babe44 100644
@@ -150,12 +150,17 @@ static void panic_on_rcu_stall(void)
 /**
  * rcu_cpu_stall_reset - restart stall-warning timeout for current grace period
  *
+ * To perform the reset request from the caller, disable stall detection until
+ * 3 fqs loops have passed. This is required to ensure a fresh jiffies is
+ * loaded.  It should be safe to do from the fqs loop as enough timer
+ * interrupts and context switches should have passed.
+ *
  * The caller must disable hard irqs.
  */
 void rcu_cpu_stall_reset(void)
 {
-	WRITE_ONCE(rcu_state.jiffies_stall,
-		   jiffies + rcu_jiffies_till_stall_check());
+	WRITE_ONCE(rcu_state.nr_fqs_jiffies_stall, 3);
+	WRITE_ONCE(rcu_state.jiffies_stall, ULONG_MAX);
 }
 
 //////////////////////////////////////////////////////////////////////////////

@@ -171,6 +176,7 @@ static void record_gp_stall_check_time(void)
 	WRITE_ONCE(rcu_state.gp_start, j);
 	j1 = rcu_jiffies_till_stall_check();
 	smp_mb(); // ->gp_start before ->jiffies_stall and caller's ->gp_seq.
+	WRITE_ONCE(rcu_state.nr_fqs_jiffies_stall, 0);
 	WRITE_ONCE(rcu_state.jiffies_stall, j + j1);
 	rcu_state.jiffies_resched = j + j1 / 2;
 	rcu_state.n_force_qs_gpstart = READ_ONCE(rcu_state.n_force_qs);

@@ -726,6 +732,16 @@ static void check_cpu_stall(struct rcu_data *rdp)
 	    !rcu_gp_in_progress())
 		return;
 	rcu_stall_kick_kthreads();
+
+	/*
+	 * Check if it was requested (via rcu_cpu_stall_reset()) that the FQS
+	 * loop has to set jiffies to ensure a non-stale jiffies value. This
+	 * is required to have good jiffies value after coming out of long
+	 * breaks of jiffies updates. Not doing so can cause false positives.
+	 */
+	if (READ_ONCE(rcu_state.nr_fqs_jiffies_stall) > 0)
+		return;
+
 	j = jiffies;
 
 	/*