Merge branches 'rcu/fixes', 'rcu/nocb', 'rcu/torture', 'rcu/stall' and 'rcu/srcu' into rcu/dev

Documentation/admin-guide/kernel-parameters.txt

@@ -5421,6 +5421,14 @@
 			The delay, in seconds, between successive
 			read-then-exit testing episodes.
 
+	rcutorture.reader_flavor= [KNL]
+			A bit mask indicating which readers to use.
+			If there is more than one bit set, the readers
+			are entered from low-order bit up, and are
+			exited in the opposite order.  For SRCU, the
+			0x1 bit is normal readers, 0x2 NMI-safe readers,
+			and 0x4 light-weight readers.
+
 	rcutorture.shuffle_interval= [KNL]
 			Set task-shuffle interval (s).  Shuffling tasks
 			allows some CPUs to go into dyntick-idle mode

include/linux/rcutiny.h

@@ -165,7 +165,6 @@ static inline bool rcu_inkernel_boot_has_ended(void) { return true; }
 static inline bool rcu_is_watching(void) { return true; }
 static inline void rcu_momentary_eqs(void) { }
 static inline void kfree_rcu_scheduler_running(void) { }
-static inline bool rcu_gp_might_be_stalled(void) { return false; }
 
 /* Avoid RCU read-side critical sections leaking across. */
 static inline void rcu_all_qs(void) { barrier(); }

include/linux/rcutree.h

@@ -40,7 +40,6 @@ void kvfree_rcu_barrier(void);
 void rcu_barrier(void);
 void rcu_momentary_eqs(void);
 void kfree_rcu_scheduler_running(void);
-bool rcu_gp_might_be_stalled(void);
 
 struct rcu_gp_oldstate {
 	unsigned long rgos_norm;

include/linux/srcu.h

@@ -56,6 +56,13 @@ void call_srcu(struct srcu_struct *ssp, struct rcu_head *head,
 void cleanup_srcu_struct(struct srcu_struct *ssp);
 int __srcu_read_lock(struct srcu_struct *ssp) __acquires(ssp);
 void __srcu_read_unlock(struct srcu_struct *ssp, int idx) __releases(ssp);
+#ifdef CONFIG_TINY_SRCU
+#define __srcu_read_lock_lite __srcu_read_lock
+#define __srcu_read_unlock_lite __srcu_read_unlock
+#else // #ifdef CONFIG_TINY_SRCU
+int __srcu_read_lock_lite(struct srcu_struct *ssp) __acquires(ssp);
+void __srcu_read_unlock_lite(struct srcu_struct *ssp, int idx) __releases(ssp);
+#endif // #else // #ifdef CONFIG_TINY_SRCU
 void synchronize_srcu(struct srcu_struct *ssp);
 
 #define SRCU_GET_STATE_COMPLETED 0x1
@@ -176,17 +183,6 @@ static inline int srcu_read_lock_held(const struct srcu_struct *ssp)
 
 #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 
-#define SRCU_NMI_UNKNOWN	0x0
-#define SRCU_NMI_UNSAFE		0x1
-#define SRCU_NMI_SAFE		0x2
-
-#if defined(CONFIG_PROVE_RCU) && defined(CONFIG_TREE_SRCU)
-void srcu_check_nmi_safety(struct srcu_struct *ssp, bool nmi_safe);
-#else
-static inline void srcu_check_nmi_safety(struct srcu_struct *ssp,
-					 bool nmi_safe) { }
-#endif
-
 
 /**
  * srcu_dereference_check - fetch SRCU-protected pointer for later dereferencing
@@ -236,33 +232,67 @@ static inline void srcu_check_nmi_safety(struct srcu_struct *ssp,
  * a mutex that is held elsewhere while calling synchronize_srcu() or
  * synchronize_srcu_expedited().
  *
- * Note that srcu_read_lock() and the matching srcu_read_unlock() must
+ * The return value from srcu_read_lock() must be passed unaltered
- * occur in the same context, for example, it is illegal to invoke
+ * to the matching srcu_read_unlock().  Note that srcu_read_lock() and
- * srcu_read_unlock() in an irq handler if the matching srcu_read_lock()
+ * the matching srcu_read_unlock() must occur in the same context, for
- * was invoked in process context.
+ * example, it is illegal to invoke srcu_read_unlock() in an irq handler
+ * if the matching srcu_read_lock() was invoked in process context.  Or,
+ * for that matter to invoke srcu_read_unlock() from one task and the
+ * matching srcu_read_lock() from another.
  */
 static inline int srcu_read_lock(struct srcu_struct *ssp) __acquires(ssp)
 {
 	int retval;
 
-	srcu_check_nmi_safety(ssp, false);
+	srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL);
 	retval = __srcu_read_lock(ssp);
 	srcu_lock_acquire(&ssp->dep_map);
 	return retval;
 }
 
+/**
+ * srcu_read_lock_lite - register a new reader for an SRCU-protected structure.
+ * @ssp: srcu_struct in which to register the new reader.
+ *
+ * Enter an SRCU read-side critical section, but for a light-weight
+ * smp_mb()-free reader.  See srcu_read_lock() for more information.
+ *
+ * If srcu_read_lock_lite() is ever used on an srcu_struct structure,
+ * then none of the other flavors may be used, whether before, during,
+ * or after.  Note that grace-period auto-expediting is disabled for _lite
+ * srcu_struct structures because auto-expedited grace periods invoke
+ * synchronize_rcu_expedited(), IPIs and all.
+ *
+ * Note that srcu_read_lock_lite() can be invoked only from those contexts
+ * where RCU is watching, that is, from contexts where it would be legal
+ * to invoke rcu_read_lock().  Otherwise, lockdep will complain.
+ */
+static inline int srcu_read_lock_lite(struct srcu_struct *ssp) __acquires(ssp)
+{
+	int retval;
+
+	srcu_check_read_flavor_lite(ssp);
+	retval = __srcu_read_lock_lite(ssp);
+	rcu_try_lock_acquire(&ssp->dep_map);
+	return retval;
+}
+
 /**
  * srcu_read_lock_nmisafe - register a new reader for an SRCU-protected structure.
  * @ssp: srcu_struct in which to register the new reader.
  *
  * Enter an SRCU read-side critical section, but in an NMI-safe manner.
  * See srcu_read_lock() for more information.
+ *
+ * If srcu_read_lock_nmisafe() is ever used on an srcu_struct structure,
+ * then none of the other flavors may be used, whether before, during,
+ * or after.
  */
 static inline int srcu_read_lock_nmisafe(struct srcu_struct *ssp) __acquires(ssp)
 {
 	int retval;
 
-	srcu_check_nmi_safety(ssp, true);
+	srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NMI);
 	retval = __srcu_read_lock_nmisafe(ssp);
 	rcu_try_lock_acquire(&ssp->dep_map);
 	return retval;
@@ -274,7 +304,7 @@ srcu_read_lock_notrace(struct srcu_struct *ssp) __acquires(ssp)
 {
 	int retval;
 
-	srcu_check_nmi_safety(ssp, false);
+	srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL);
 	retval = __srcu_read_lock(ssp);
 	return retval;
 }
@@ -303,7 +333,7 @@ srcu_read_lock_notrace(struct srcu_struct *ssp) __acquires(ssp)
 static inline int srcu_down_read(struct srcu_struct *ssp) __acquires(ssp)
 {
 	WARN_ON_ONCE(in_nmi());
-	srcu_check_nmi_safety(ssp, false);
+	srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL);
 	return __srcu_read_lock(ssp);
 }
 
@@ -318,11 +348,27 @@ static inline void srcu_read_unlock(struct srcu_struct *ssp, int idx)
 	__releases(ssp)
 {
 	WARN_ON_ONCE(idx & ~0x1);
-	srcu_check_nmi_safety(ssp, false);
+	srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL);
 	srcu_lock_release(&ssp->dep_map);
 	__srcu_read_unlock(ssp, idx);
 }
 
+/**
+ * srcu_read_unlock_lite - unregister a old reader from an SRCU-protected structure.
+ * @ssp: srcu_struct in which to unregister the old reader.
+ * @idx: return value from corresponding srcu_read_lock().
+ *
+ * Exit a light-weight SRCU read-side critical section.
+ */
+static inline void srcu_read_unlock_lite(struct srcu_struct *ssp, int idx)
+	__releases(ssp)
+{
+	WARN_ON_ONCE(idx & ~0x1);
+	srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_LITE);
+	srcu_lock_release(&ssp->dep_map);
+	__srcu_read_unlock_lite(ssp, idx);
+}
+
 /**
  * srcu_read_unlock_nmisafe - unregister a old reader from an SRCU-protected structure.
  * @ssp: srcu_struct in which to unregister the old reader.
@@ -334,7 +380,7 @@ static inline void srcu_read_unlock_nmisafe(struct srcu_struct *ssp, int idx)
 	__releases(ssp)
 {
 	WARN_ON_ONCE(idx & ~0x1);
-	srcu_check_nmi_safety(ssp, true);
+	srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NMI);
 	rcu_lock_release(&ssp->dep_map);
 	__srcu_read_unlock_nmisafe(ssp, idx);
 }
@@ -343,7 +389,7 @@ static inline void srcu_read_unlock_nmisafe(struct srcu_struct *ssp, int idx)
 static inline notrace void
 srcu_read_unlock_notrace(struct srcu_struct *ssp, int idx) __releases(ssp)
 {
-	srcu_check_nmi_safety(ssp, false);
+	srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL);
 	__srcu_read_unlock(ssp, idx);
 }
 
@@ -360,7 +406,7 @@ static inline void srcu_up_read(struct srcu_struct *ssp, int idx)
 {
 	WARN_ON_ONCE(idx & ~0x1);
 	WARN_ON_ONCE(in_nmi());
-	srcu_check_nmi_safety(ssp, false);
+	srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL);
 	__srcu_read_unlock(ssp, idx);
 }
 

include/linux/srcutiny.h

@@ -81,6 +81,9 @@ static inline void srcu_barrier(struct srcu_struct *ssp)
 	synchronize_srcu(ssp);
 }
 
+#define srcu_check_read_flavor(ssp, read_flavor) do { } while (0)
+#define srcu_check_read_flavor_lite(ssp) do { } while (0)
+
 /* Defined here to avoid size increase for non-torture kernels. */
 static inline void srcu_torture_stats_print(struct srcu_struct *ssp,
 					    char *tt, char *tf)

include/linux/srcutree.h

@@ -25,7 +25,7 @@ struct srcu_data {
 	/* Read-side state. */
 	atomic_long_t srcu_lock_count[2];	/* Locks per CPU. */
 	atomic_long_t srcu_unlock_count[2];	/* Unlocks per CPU. */
-	int srcu_nmi_safety;			/* NMI-safe srcu_struct structure? */
+	int srcu_reader_flavor;			/* Reader flavor for srcu_struct structure? */
 
 	/* Update-side state. */
 	spinlock_t __private lock ____cacheline_internodealigned_in_smp;
@@ -43,6 +43,11 @@ struct srcu_data {
 	struct srcu_struct *ssp;
 };
 
+/* Values for ->srcu_reader_flavor. */
+#define SRCU_READ_FLAVOR_NORMAL	0x1		// srcu_read_lock().
+#define SRCU_READ_FLAVOR_NMI	0x2		// srcu_read_lock_nmisafe().
+#define SRCU_READ_FLAVOR_LITE	0x4		// srcu_read_lock_lite().
+
 /*
  * Node in SRCU combining tree, similar in function to rcu_data.
  */
@@ -204,4 +209,64 @@ void synchronize_srcu_expedited(struct srcu_struct *ssp);
 void srcu_barrier(struct srcu_struct *ssp);
 void srcu_torture_stats_print(struct srcu_struct *ssp, char *tt, char *tf);
 
+/*
+ * Counts the new reader in the appropriate per-CPU element of the
+ * srcu_struct.  Returns an index that must be passed to the matching
+ * srcu_read_unlock_lite().
+ *
+ * Note that this_cpu_inc() is an RCU read-side critical section either
+ * because it disables interrupts, because it is a single instruction,
+ * or because it is a read-modify-write atomic operation, depending on
+ * the whims of the architecture.
+ */
+static inline int __srcu_read_lock_lite(struct srcu_struct *ssp)
+{
+	int idx;
+
+	RCU_LOCKDEP_WARN(!rcu_is_watching(), "RCU must be watching srcu_read_lock_lite().");
+	idx = READ_ONCE(ssp->srcu_idx) & 0x1;
+	this_cpu_inc(ssp->sda->srcu_lock_count[idx].counter); /* Y */
+	barrier(); /* Avoid leaking the critical section. */
+	return idx;
+}
+
+/*
+ * Removes the count for the old reader from the appropriate
+ * per-CPU element of the srcu_struct.  Note that this may well be a
+ * different CPU than that which was incremented by the corresponding
+ * srcu_read_lock_lite(), but it must be within the same task.
+ *
+ * Note that this_cpu_inc() is an RCU read-side critical section either
+ * because it disables interrupts, because it is a single instruction,
+ * or because it is a read-modify-write atomic operation, depending on
+ * the whims of the architecture.
+ */
+static inline void __srcu_read_unlock_lite(struct srcu_struct *ssp, int idx)
+{
+	barrier();  /* Avoid leaking the critical section. */
+	this_cpu_inc(ssp->sda->srcu_unlock_count[idx].counter);  /* Z */
+	RCU_LOCKDEP_WARN(!rcu_is_watching(), "RCU must be watching srcu_read_unlock_lite().");
+}
+
+void __srcu_check_read_flavor(struct srcu_struct *ssp, int read_flavor);
+
+// Record _lite() usage even for CONFIG_PROVE_RCU=n kernels.
+static inline void srcu_check_read_flavor_lite(struct srcu_struct *ssp)
+{
+	struct srcu_data *sdp = raw_cpu_ptr(ssp->sda);
+
+	if (likely(READ_ONCE(sdp->srcu_reader_flavor) & SRCU_READ_FLAVOR_LITE))
+		return;
+
+	// Note that the cmpxchg() in srcu_check_read_flavor() is fully ordered.
+	__srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_LITE);
+}
+
+// Record non-_lite() usage only for CONFIG_PROVE_RCU=y kernels.
+static inline void srcu_check_read_flavor(struct srcu_struct *ssp, int read_flavor)
+{
+	if (IS_ENABLED(CONFIG_PROVE_RCU))
+		__srcu_check_read_flavor(ssp, read_flavor);
+}
+
 #endif

kernel/rcu/rcu_segcblist.h

@@ -120,7 +120,6 @@ void rcu_segcblist_inc_len(struct rcu_segcblist *rsclp);
 void rcu_segcblist_add_len(struct rcu_segcblist *rsclp, long v);
 void rcu_segcblist_init(struct rcu_segcblist *rsclp);
 void rcu_segcblist_disable(struct rcu_segcblist *rsclp);
-void rcu_segcblist_offload(struct rcu_segcblist *rsclp, bool offload);
 bool rcu_segcblist_ready_cbs(struct rcu_segcblist *rsclp);
 bool rcu_segcblist_pend_cbs(struct rcu_segcblist *rsclp);
 struct rcu_head *rcu_segcblist_first_cb(struct rcu_segcblist *rsclp);

kernel/rcu/rcuscale.c

@@ -889,14 +889,14 @@ kfree_scale_init(void)
 
 		if (WARN_ON_ONCE(jiffies_at_lazy_cb - jif_start < 2 * HZ)) {
 			pr_alert("ERROR: call_rcu() CBs are not being lazy as expected!\n");
-			WARN_ON_ONCE(1);
+			firsterr = -1;
-			return -1;
+			goto unwind;
 		}
 
 		if (WARN_ON_ONCE(jiffies_at_lazy_cb - jif_start > 3 * HZ)) {
 			pr_alert("ERROR: call_rcu() CBs are being too lazy!\n");
-			WARN_ON_ONCE(1);
+			firsterr = -1;
-			return -1;
+			goto unwind;
 		}
 	}
 

kernel/rcu/rcutorture.c

@@ -57,9 +57,9 @@ MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.ibm.com> and Josh Triplett <josh@
 
 /* Bits for ->extendables field, extendables param, and related definitions. */
 #define RCUTORTURE_RDR_SHIFT_1	 8	/* Put SRCU index in upper bits. */
-#define RCUTORTURE_RDR_MASK_1	 (1 << RCUTORTURE_RDR_SHIFT_1)
+#define RCUTORTURE_RDR_MASK_1	 (0xff << RCUTORTURE_RDR_SHIFT_1)
-#define RCUTORTURE_RDR_SHIFT_2	 9	/* Put SRCU index in upper bits. */
+#define RCUTORTURE_RDR_SHIFT_2	 16	/* Put SRCU index in upper bits. */
-#define RCUTORTURE_RDR_MASK_2	 (1 << RCUTORTURE_RDR_SHIFT_2)
+#define RCUTORTURE_RDR_MASK_2	 (0xff << RCUTORTURE_RDR_SHIFT_2)
 #define RCUTORTURE_RDR_BH	 0x01	/* Extend readers by disabling bh. */
 #define RCUTORTURE_RDR_IRQ	 0x02	/*  ... disabling interrupts. */
 #define RCUTORTURE_RDR_PREEMPT	 0x04	/*  ... disabling preemption. */
@@ -71,6 +71,9 @@ MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.ibm.com> and Josh Triplett <josh@
 #define RCUTORTURE_MAX_EXTEND	 \
 	(RCUTORTURE_RDR_BH | RCUTORTURE_RDR_IRQ | RCUTORTURE_RDR_PREEMPT | \
 	 RCUTORTURE_RDR_RBH | RCUTORTURE_RDR_SCHED)
+#define RCUTORTURE_RDR_ALLBITS	\
+	(RCUTORTURE_MAX_EXTEND | RCUTORTURE_RDR_RCU_1 | RCUTORTURE_RDR_RCU_2 | \
+	 RCUTORTURE_RDR_MASK_1 | RCUTORTURE_RDR_MASK_2)
 #define RCUTORTURE_RDR_MAX_LOOPS 0x7	/* Maximum reader extensions. */
 					/* Must be power of two minus one. */
 #define RCUTORTURE_RDR_MAX_SEGS (RCUTORTURE_RDR_MAX_LOOPS + 3)
@@ -108,6 +111,7 @@ torture_param(int, nocbs_nthreads, 0, "Number of NOCB toggle threads, 0 to disab
 torture_param(int, nocbs_toggle, 1000, "Time between toggling nocb state (ms)");
 torture_param(int, read_exit_delay, 13, "Delay between read-then-exit episodes (s)");
 torture_param(int, read_exit_burst, 16, "# of read-then-exit bursts per episode, zero to disable");
+torture_param(int, reader_flavor, 0x1, "Reader flavors to use, one per bit.");
 torture_param(int, shuffle_interval, 3, "Number of seconds between shuffles");
 torture_param(int, shutdown_secs, 0, "Shutdown time (s), <= zero to disable.");
 torture_param(int, stall_cpu, 0, "Stall duration (s), zero to disable.");
@@ -643,10 +647,25 @@ static void srcu_get_gp_data(int *flags, unsigned long *gp_seq)
 
 static int srcu_torture_read_lock(void)
 {
-	if (cur_ops == &srcud_ops)
+	int idx;
-		return srcu_read_lock_nmisafe(srcu_ctlp);
+	int ret = 0;
-	else
+
-		return srcu_read_lock(srcu_ctlp);
+	if ((reader_flavor & 0x1) || !(reader_flavor & 0x7)) {
+		idx = srcu_read_lock(srcu_ctlp);
+		WARN_ON_ONCE(idx & ~0x1);
+		ret += idx;
+	}
+	if (reader_flavor & 0x2) {
+		idx = srcu_read_lock_nmisafe(srcu_ctlp);
+		WARN_ON_ONCE(idx & ~0x1);
+		ret += idx << 1;
+	}
+	if (reader_flavor & 0x4) {
+		idx = srcu_read_lock_lite(srcu_ctlp);
+		WARN_ON_ONCE(idx & ~0x1);
+		ret += idx << 2;
+	}
+	return ret;
 }
 
 static void
@@ -670,10 +689,13 @@ srcu_read_delay(struct torture_random_state *rrsp, struct rt_read_seg *rtrsp)
 
 static void srcu_torture_read_unlock(int idx)
 {
-	if (cur_ops == &srcud_ops)
+	WARN_ON_ONCE((reader_flavor && (idx & ~reader_flavor)) || (!reader_flavor && (idx & ~0x1)));
-		srcu_read_unlock_nmisafe(srcu_ctlp, idx);
+	if (reader_flavor & 0x4)
-	else
+		srcu_read_unlock_lite(srcu_ctlp, (idx & 0x4) >> 2);
-		srcu_read_unlock(srcu_ctlp, idx);
+	if (reader_flavor & 0x2)
+		srcu_read_unlock_nmisafe(srcu_ctlp, (idx & 0x2) >> 1);
+	if ((reader_flavor & 0x1) || !(reader_flavor & 0x7))
+		srcu_read_unlock(srcu_ctlp, idx & 0x1);
 }
 
 static int torture_srcu_read_lock_held(void)
@@ -1061,8 +1083,13 @@ static bool rcu_torture_boost_failed(unsigned long gp_state, unsigned long *star
 			// At most one persisted message per boost test.
 			j = jiffies;
 			lp = READ_ONCE(last_persist);
-			if (time_after(j, lp + mininterval) && cmpxchg(&last_persist, lp, j) == lp)
+			if (time_after(j, lp + mininterval) &&
-				pr_info("Boost inversion persisted: No QS from CPU %d\n", cpu);
+			    cmpxchg(&last_persist, lp, j) == lp) {
+				if (cpu < 0)
+					pr_info("Boost inversion persisted: QS from all CPUs\n");
+				else
+					pr_info("Boost inversion persisted: No QS from CPU %d\n", cpu);
+			}
 			return false; // passed on a technicality
 		}
 		VERBOSE_TOROUT_STRING("rcu_torture_boost boosting failed");
@@ -1830,7 +1857,7 @@ static void rcutorture_one_extend(int *readstate, int newstate,
 	int statesold = *readstate & ~newstate;
 
 	WARN_ON_ONCE(idxold2 < 0);
-	WARN_ON_ONCE((idxold2 >> RCUTORTURE_RDR_SHIFT_2) > 1);
+	WARN_ON_ONCE(idxold2 & ~RCUTORTURE_RDR_ALLBITS);
 	rtrsp->rt_readstate = newstate;
 
 	/* First, put new protection in place to avoid critical-section gap. */
@@ -1845,9 +1872,9 @@ static void rcutorture_one_extend(int *readstate, int newstate,
 	if (statesnew & RCUTORTURE_RDR_SCHED)
 		rcu_read_lock_sched();
 	if (statesnew & RCUTORTURE_RDR_RCU_1)
-		idxnew1 = (cur_ops->readlock() & 0x1) << RCUTORTURE_RDR_SHIFT_1;
+		idxnew1 = (cur_ops->readlock() << RCUTORTURE_RDR_SHIFT_1) & RCUTORTURE_RDR_MASK_1;
 	if (statesnew & RCUTORTURE_RDR_RCU_2)
-		idxnew2 = (cur_ops->readlock() & 0x1) << RCUTORTURE_RDR_SHIFT_2;
+		idxnew2 = (cur_ops->readlock() << RCUTORTURE_RDR_SHIFT_2) & RCUTORTURE_RDR_MASK_2;
 
 	/*
 	 * Next, remove old protection, in decreasing order of strength
@@ -1867,7 +1894,7 @@ static void rcutorture_one_extend(int *readstate, int newstate,
 	if (statesold & RCUTORTURE_RDR_RBH)
 		rcu_read_unlock_bh();
 	if (statesold & RCUTORTURE_RDR_RCU_2) {
-		cur_ops->readunlock((idxold2 >> RCUTORTURE_RDR_SHIFT_2) & 0x1);
+		cur_ops->readunlock((idxold2 & RCUTORTURE_RDR_MASK_2) >> RCUTORTURE_RDR_SHIFT_2);
 		WARN_ON_ONCE(idxnew2 != -1);
 		idxold2 = 0;
 	}
@@ -1877,7 +1904,7 @@ static void rcutorture_one_extend(int *readstate, int newstate,
 		lockit = !cur_ops->no_pi_lock && !statesnew && !(torture_random(trsp) & 0xffff);
 		if (lockit)
 			raw_spin_lock_irqsave(&current->pi_lock, flags);
-		cur_ops->readunlock((idxold1 >> RCUTORTURE_RDR_SHIFT_1) & 0x1);
+		cur_ops->readunlock((idxold1 & RCUTORTURE_RDR_MASK_1) >> RCUTORTURE_RDR_SHIFT_1);
 		WARN_ON_ONCE(idxnew1 != -1);
 		idxold1 = 0;
 		if (lockit)
@@ -1892,16 +1919,13 @@ static void rcutorture_one_extend(int *readstate, int newstate,
 	if (idxnew1 == -1)
 		idxnew1 = idxold1 & RCUTORTURE_RDR_MASK_1;
 	WARN_ON_ONCE(idxnew1 < 0);
-	if (WARN_ON_ONCE((idxnew1 >> RCUTORTURE_RDR_SHIFT_1) > 1))
-		pr_info("Unexpected idxnew1 value of %#x\n", idxnew1);
 	if (idxnew2 == -1)
 		idxnew2 = idxold2 & RCUTORTURE_RDR_MASK_2;
 	WARN_ON_ONCE(idxnew2 < 0);
-	WARN_ON_ONCE((idxnew2 >> RCUTORTURE_RDR_SHIFT_2) > 1);
 	*readstate = idxnew1 | idxnew2 | newstate;
 	WARN_ON_ONCE(*readstate < 0);
-	if (WARN_ON_ONCE((*readstate >> RCUTORTURE_RDR_SHIFT_2) > 1))
+	if (WARN_ON_ONCE(*readstate & ~RCUTORTURE_RDR_ALLBITS))
-		pr_info("Unexpected idxnew2 value of %#x\n", idxnew2);
+		pr_info("Unexpected readstate value of %#x\n", *readstate);
 }
 
 /* Return the biggest extendables mask given current RCU and boot parameters. */
@@ -1926,7 +1950,7 @@ rcutorture_extend_mask(int oldmask, struct torture_random_state *trsp)
 	unsigned long preempts_irq = preempts | RCUTORTURE_RDR_IRQ;
 	unsigned long bhs = RCUTORTURE_RDR_BH | RCUTORTURE_RDR_RBH;
 
-	WARN_ON_ONCE(mask >> RCUTORTURE_RDR_SHIFT_1);
+	WARN_ON_ONCE(mask >> RCUTORTURE_RDR_SHIFT_1);  // Can't have reader idx bits.
 	/* Mostly only one bit (need preemption!), sometimes lots of bits. */
 	if (!(randmask1 & 0x7))
 		mask = mask & randmask2;
@@ -2399,6 +2423,7 @@ rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, const char *tag)
 		 "n_barrier_cbs=%d "
 		 "onoff_interval=%d onoff_holdoff=%d "
 		 "read_exit_delay=%d read_exit_burst=%d "
+		 "reader_flavor=%x "
 		 "nocbs_nthreads=%d nocbs_toggle=%d "
 		 "test_nmis=%d\n",
 		 torture_type, tag, nrealreaders, nfakewriters,
@@ -2411,6 +2436,7 @@ rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, const char *tag)
 		 n_barrier_cbs,
 		 onoff_interval, onoff_holdoff,
 		 read_exit_delay, read_exit_burst,
+		 reader_flavor,
 		 nocbs_nthreads, nocbs_toggle,
 		 test_nmis);
 }

kernel/rcu/refscale.c

@@ -75,6 +75,9 @@ MODULE_PARM_DESC(scale_type, "Type of test (rcu, srcu, refcnt, rwsem, rwlock.");
 torture_param(int, verbose, 0, "Enable verbose debugging printk()s");
 torture_param(int, verbose_batched, 0, "Batch verbose debugging printk()s");
 
+// Number of seconds to extend warm-up and cool-down for multiple guest OSes
+torture_param(long, guest_os_delay, 0,
+	      "Number of seconds to extend warm-up/cool-down for multiple guest OSes.");
 // Wait until there are multiple CPUs before starting test.
 torture_param(int, holdoff, IS_BUILTIN(CONFIG_RCU_REF_SCALE_TEST) ? 10 : 0,
 	      "Holdoff time before test start (s)");
@@ -212,6 +215,36 @@ static const struct ref_scale_ops srcu_ops = {
 	.name		= "srcu"
 };
 
+static void srcu_lite_ref_scale_read_section(const int nloops)
+{
+	int i;
+	int idx;
+
+	for (i = nloops; i >= 0; i--) {
+		idx = srcu_read_lock_lite(srcu_ctlp);
+		srcu_read_unlock_lite(srcu_ctlp, idx);
+	}
+}
+
+static void srcu_lite_ref_scale_delay_section(const int nloops, const int udl, const int ndl)
+{
+	int i;
+	int idx;
+
+	for (i = nloops; i >= 0; i--) {
+		idx = srcu_read_lock_lite(srcu_ctlp);
+		un_delay(udl, ndl);
+		srcu_read_unlock_lite(srcu_ctlp, idx);
+	}
+}
+
+static const struct ref_scale_ops srcu_lite_ops = {
+	.init		= rcu_sync_scale_init,
+	.readsection	= srcu_lite_ref_scale_read_section,
+	.delaysection	= srcu_lite_ref_scale_delay_section,
+	.name		= "srcu-lite"
+};
+
 #ifdef CONFIG_TASKS_RCU
 
 // Definitions for RCU Tasks ref scale testing: Empty read markers.
@@ -801,6 +834,18 @@ static void rcu_scale_one_reader(void)
 		cur_ops->delaysection(loops, readdelay / 1000, readdelay % 1000);
 }
 
+// Warm up cache, or, if needed run a series of rcu_scale_one_reader()
+// to allow multiple rcuscale guest OSes to collect mutually valid data.
+static void rcu_scale_warm_cool(void)
+{
+	unsigned long jdone = jiffies + (guest_os_delay > 0 ? guest_os_delay * HZ : -1);
+
+	do {
+		rcu_scale_one_reader();
+		cond_resched();
+	} while (time_before(jiffies, jdone));
+}
+
 // Reader kthread.  Repeatedly does empty RCU read-side
 // critical section, minimizing update-side interference.
 static int
@@ -829,7 +874,7 @@ ref_scale_reader(void *arg)
 		goto end;
 
 	// Make sure that the CPU is affinitized appropriately during testing.
-	WARN_ON_ONCE(raw_smp_processor_id() != me);
+	WARN_ON_ONCE(raw_smp_processor_id() != me % nr_cpu_ids);
 
 	WRITE_ONCE(rt->start_reader, 0);
 	if (!atomic_dec_return(&n_started))
@@ -957,6 +1002,7 @@ static int main_func(void *arg)
 		schedule_timeout_uninterruptible(1);
 
 	// Start exp readers up per experiment
+	rcu_scale_warm_cool();
 	for (exp = 0; exp < nruns && !torture_must_stop(); exp++) {
 		if (torture_must_stop())
 			goto end;
@@ -987,6 +1033,7 @@ static int main_func(void *arg)
 
 		result_avg[exp] = div_u64(1000 * process_durations(nreaders), nreaders * loops);
 	}
+	rcu_scale_warm_cool();
 
 	// Print the average of all experiments
 	SCALEOUT("END OF TEST. Calculating average duration per loop (nanoseconds)...\n");
@@ -1082,9 +1129,10 @@ ref_scale_init(void)
 	long i;
 	int firsterr = 0;
 	static const struct ref_scale_ops *scale_ops[] = {
-		&rcu_ops, &srcu_ops, RCU_TRACE_OPS RCU_TASKS_OPS &refcnt_ops, &rwlock_ops,
+		&rcu_ops, &srcu_ops, &srcu_lite_ops, RCU_TRACE_OPS RCU_TASKS_OPS
-		&rwsem_ops, &lock_ops, &lock_irq_ops, &acqrel_ops, &clock_ops, &jiffies_ops,
+		&refcnt_ops, &rwlock_ops, &rwsem_ops, &lock_ops, &lock_irq_ops, &acqrel_ops,
-		&typesafe_ref_ops, &typesafe_lock_ops, &typesafe_seqlock_ops,
+		&clock_ops, &jiffies_ops, &typesafe_ref_ops, &typesafe_lock_ops,
+		&typesafe_seqlock_ops,
 	};
 
 	if (!torture_init_begin(scale_type, verbose))

kernel/rcu/srcutree.c

@@ -128,7 +128,7 @@ static void init_srcu_struct_data(struct srcu_struct *ssp)
 	 * Initialize the per-CPU srcu_data array, which feeds into the
 	 * leaves of the srcu_node tree.
 	 */
-	WARN_ON_ONCE(ARRAY_SIZE(sdp->srcu_lock_count) !=
+	BUILD_BUG_ON(ARRAY_SIZE(sdp->srcu_lock_count) !=
 		     ARRAY_SIZE(sdp->srcu_unlock_count));
 	for_each_possible_cpu(cpu) {
 		sdp = per_cpu_ptr(ssp->sda, cpu);
@@ -187,7 +187,7 @@ static bool init_srcu_struct_nodes(struct srcu_struct *ssp, gfp_t gfp_flags)
 	/* Each pass through this loop initializes one srcu_node structure. */
 	srcu_for_each_node_breadth_first(ssp, snp) {
 		spin_lock_init(&ACCESS_PRIVATE(snp, lock));
-		WARN_ON_ONCE(ARRAY_SIZE(snp->srcu_have_cbs) !=
+		BUILD_BUG_ON(ARRAY_SIZE(snp->srcu_have_cbs) !=
 			     ARRAY_SIZE(snp->srcu_data_have_cbs));
 		for (i = 0; i < ARRAY_SIZE(snp->srcu_have_cbs); i++) {
 			snp->srcu_have_cbs[i] = SRCU_SNP_INIT_SEQ;
@@ -419,41 +419,60 @@ static void check_init_srcu_struct(struct srcu_struct *ssp)
 }
 
 /*
- * Returns approximate total of the readers' ->srcu_lock_count[] values
+ * Is the current or any upcoming grace period to be expedited?
- * for the rank of per-CPU counters specified by idx.
  */
-static unsigned long srcu_readers_lock_idx(struct srcu_struct *ssp, int idx)
+static bool srcu_gp_is_expedited(struct srcu_struct *ssp)
 {
-	int cpu;
+	struct srcu_usage *sup = ssp->srcu_sup;
-	unsigned long sum = 0;
 
-	for_each_possible_cpu(cpu) {
+	return ULONG_CMP_LT(READ_ONCE(sup->srcu_gp_seq), READ_ONCE(sup->srcu_gp_seq_needed_exp));
-		struct srcu_data *cpuc = per_cpu_ptr(ssp->sda, cpu);
-
-		sum += atomic_long_read(&cpuc->srcu_lock_count[idx]);
-	}
-	return sum;
 }
 
 /*
- * Returns approximate total of the readers' ->srcu_unlock_count[] values
+ * Computes approximate total of the readers' ->srcu_lock_count[] values
- * for the rank of per-CPU counters specified by idx.
+ * for the rank of per-CPU counters specified by idx, and returns true if
+ * the caller did the proper barrier (gp), and if the count of the locks
+ * matches that of the unlocks passed in.
  */
-static unsigned long srcu_readers_unlock_idx(struct srcu_struct *ssp, int idx)
+static bool srcu_readers_lock_idx(struct srcu_struct *ssp, int idx, bool gp, unsigned long unlocks)
 {
 	int cpu;
 	unsigned long mask = 0;
 	unsigned long sum = 0;
 
 	for_each_possible_cpu(cpu) {
-		struct srcu_data *cpuc = per_cpu_ptr(ssp->sda, cpu);
+		struct srcu_data *sdp = per_cpu_ptr(ssp->sda, cpu);
 
-		sum += atomic_long_read(&cpuc->srcu_unlock_count[idx]);
+		sum += atomic_long_read(&sdp->srcu_lock_count[idx]);
 		if (IS_ENABLED(CONFIG_PROVE_RCU))
-			mask = mask | READ_ONCE(cpuc->srcu_nmi_safety);
+			mask = mask | READ_ONCE(sdp->srcu_reader_flavor);
 	}
-	WARN_ONCE(IS_ENABLED(CONFIG_PROVE_RCU) && (mask & (mask >> 1)),
+	WARN_ONCE(IS_ENABLED(CONFIG_PROVE_RCU) && (mask & (mask - 1)),
-		  "Mixed NMI-safe readers for srcu_struct at %ps.\n", ssp);
+		  "Mixed reader flavors for srcu_struct at %ps.\n", ssp);
+	if (mask & SRCU_READ_FLAVOR_LITE && !gp)
+		return false;
+	return sum == unlocks;
+}
+
+/*
+ * Returns approximate total of the readers' ->srcu_unlock_count[] values
+ * for the rank of per-CPU counters specified by idx.
+ */
+static unsigned long srcu_readers_unlock_idx(struct srcu_struct *ssp, int idx, unsigned long *rdm)
+{
+	int cpu;
+	unsigned long mask = 0;
+	unsigned long sum = 0;
+
+	for_each_possible_cpu(cpu) {
+		struct srcu_data *sdp = per_cpu_ptr(ssp->sda, cpu);
+
+		sum += atomic_long_read(&sdp->srcu_unlock_count[idx]);
+		mask = mask | READ_ONCE(sdp->srcu_reader_flavor);
+	}
+	WARN_ONCE(IS_ENABLED(CONFIG_PROVE_RCU) && (mask & (mask - 1)),
+		  "Mixed reader flavors for srcu_struct at %ps.\n", ssp);
+	*rdm = mask;
 	return sum;
 }
 
@@ -463,22 +482,28 @@ static unsigned long srcu_readers_unlock_idx(struct srcu_struct *ssp, int idx)
  */
 static bool srcu_readers_active_idx_check(struct srcu_struct *ssp, int idx)
 {
+	bool did_gp;
+	unsigned long rdm;
 	unsigned long unlocks;
 
-	unlocks = srcu_readers_unlock_idx(ssp, idx);
+	unlocks = srcu_readers_unlock_idx(ssp, idx, &rdm);
+	did_gp = !!(rdm & SRCU_READ_FLAVOR_LITE);
 
 	/*
 	 * Make sure that a lock is always counted if the corresponding
 	 * unlock is counted. Needs to be a smp_mb() as the read side may
 	 * contain a read from a variable that is written to before the
 	 * synchronize_srcu() in the write side. In this case smp_mb()s
-	 * A and B act like the store buffering pattern.
+	 * A and B (or X and Y) act like the store buffering pattern.
 	 *
-	 * This smp_mb() also pairs with smp_mb() C to prevent accesses
+	 * This smp_mb() also pairs with smp_mb() C (or, in the case of X,
-	 * after the synchronize_srcu() from being executed before the
+	 * Z) to prevent accesses after the synchronize_srcu() from being
-	 * grace period ends.
+	 * executed before the grace period ends.
 	 */
-	smp_mb(); /* A */
+	if (!did_gp)
+		smp_mb(); /* A */
+	else
+		synchronize_rcu(); /* X */
 
 	/*
 	 * If the locks are the same as the unlocks, then there must have
@@ -536,7 +561,7 @@ static bool srcu_readers_active_idx_check(struct srcu_struct *ssp, int idx)
 	 * which are unlikely to be configured with an address space fully
 	 * populated with memory, at least not anytime soon.
 	 */
-	return srcu_readers_lock_idx(ssp, idx) == unlocks;
+	return srcu_readers_lock_idx(ssp, idx, did_gp, unlocks);
 }
 
 /**
@@ -554,12 +579,12 @@ static bool srcu_readers_active(struct srcu_struct *ssp)
 	unsigned long sum = 0;
 
 	for_each_possible_cpu(cpu) {
-		struct srcu_data *cpuc = per_cpu_ptr(ssp->sda, cpu);
+		struct srcu_data *sdp = per_cpu_ptr(ssp->sda, cpu);
 
-		sum += atomic_long_read(&cpuc->srcu_lock_count[0]);
+		sum += atomic_long_read(&sdp->srcu_lock_count[0]);
-		sum += atomic_long_read(&cpuc->srcu_lock_count[1]);
+		sum += atomic_long_read(&sdp->srcu_lock_count[1]);
-		sum -= atomic_long_read(&cpuc->srcu_unlock_count[0]);
+		sum -= atomic_long_read(&sdp->srcu_unlock_count[0]);
-		sum -= atomic_long_read(&cpuc->srcu_unlock_count[1]);
+		sum -= atomic_long_read(&sdp->srcu_unlock_count[1]);
 	}
 	return sum;
 }
@@ -622,7 +647,7 @@ static unsigned long srcu_get_delay(struct srcu_struct *ssp)
 	unsigned long jbase = SRCU_INTERVAL;
 	struct srcu_usage *sup = ssp->srcu_sup;
 
-	if (ULONG_CMP_LT(READ_ONCE(sup->srcu_gp_seq), READ_ONCE(sup->srcu_gp_seq_needed_exp)))
+	if (srcu_gp_is_expedited(ssp))
 		jbase = 0;
 	if (rcu_seq_state(READ_ONCE(sup->srcu_gp_seq))) {
 		j = jiffies - 1;
@@ -687,28 +712,28 @@ void cleanup_srcu_struct(struct srcu_struct *ssp)
 }
 EXPORT_SYMBOL_GPL(cleanup_srcu_struct);
 
-#ifdef CONFIG_PROVE_RCU
 /*
- * Check for consistent NMI safety.
+ * Check for consistent reader flavor.
  */
-void srcu_check_nmi_safety(struct srcu_struct *ssp, bool nmi_safe)
+void __srcu_check_read_flavor(struct srcu_struct *ssp, int read_flavor)
 {
-	int nmi_safe_mask = 1 << nmi_safe;
+	int old_read_flavor;
-	int old_nmi_safe_mask;
 	struct srcu_data *sdp;
 
-	/* NMI-unsafe use in NMI is a bad sign */
+	/* NMI-unsafe use in NMI is a bad sign, as is multi-bit read_flavor values. */
-	WARN_ON_ONCE(!nmi_safe && in_nmi());
+	WARN_ON_ONCE((read_flavor != SRCU_READ_FLAVOR_NMI) && in_nmi());
+	WARN_ON_ONCE(read_flavor & (read_flavor - 1));
+
 	sdp = raw_cpu_ptr(ssp->sda);
-	old_nmi_safe_mask = READ_ONCE(sdp->srcu_nmi_safety);
+	old_read_flavor = READ_ONCE(sdp->srcu_reader_flavor);
-	if (!old_nmi_safe_mask) {
+	if (!old_read_flavor) {
-		WRITE_ONCE(sdp->srcu_nmi_safety, nmi_safe_mask);
+		old_read_flavor = cmpxchg(&sdp->srcu_reader_flavor, 0, read_flavor);
-		return;
+		if (!old_read_flavor)
+			return;
 	}
-	WARN_ONCE(old_nmi_safe_mask != nmi_safe_mask, "CPU %d old state %d new state %d\n", sdp->cpu, old_nmi_safe_mask, nmi_safe_mask);
+	WARN_ONCE(old_read_flavor != read_flavor, "CPU %d old state %d new state %d\n", sdp->cpu, old_read_flavor, read_flavor);
 }
-EXPORT_SYMBOL_GPL(srcu_check_nmi_safety);
+EXPORT_SYMBOL_GPL(__srcu_check_read_flavor);
-#endif /* CONFIG_PROVE_RCU */
 
 /*
  * Counts the new reader in the appropriate per-CPU element of the
@@ -867,7 +892,7 @@ static void srcu_gp_end(struct srcu_struct *ssp)
 	spin_lock_irq_rcu_node(sup);
 	idx = rcu_seq_state(sup->srcu_gp_seq);
 	WARN_ON_ONCE(idx != SRCU_STATE_SCAN2);
-	if (ULONG_CMP_LT(READ_ONCE(sup->srcu_gp_seq), READ_ONCE(sup->srcu_gp_seq_needed_exp)))
+	if (srcu_gp_is_expedited(ssp))
 		cbdelay = 0;
 
 	WRITE_ONCE(sup->srcu_last_gp_end, ktime_get_mono_fast_ns());
@@ -1122,6 +1147,8 @@ static void srcu_flip(struct srcu_struct *ssp)
 	 * it stays until either (1) Compilers learn about this sort of
 	 * control dependency or (2) Some production workload running on
 	 * a production system is unduly delayed by this slowpath smp_mb().
+	 * Except for _lite() readers, where it is inoperative, which
+	 * means that it is a good thing that it is redundant.
 	 */
 	smp_mb(); /* E */  /* Pairs with B and C. */
 
@@ -1139,7 +1166,9 @@ static void srcu_flip(struct srcu_struct *ssp)
 }
 
 /*
- * If SRCU is likely idle, return true, otherwise return false.
+ * If SRCU is likely idle, in other words, the next SRCU grace period
+ * should be expedited, return true, otherwise return false.  Except that
+ * in the presence of _lite() readers, always return false.
  *
  * Note that it is OK for several current from-idle requests for a new
  * grace period from idle to specify expediting because they will all end
@@ -1159,7 +1188,7 @@ static void srcu_flip(struct srcu_struct *ssp)
  * negligible when amortized over that time period, and the extra latency
  * of a needlessly non-expedited grace period is similarly negligible.
  */
-static bool srcu_might_be_idle(struct srcu_struct *ssp)
+static bool srcu_should_expedite(struct srcu_struct *ssp)
 {
 	unsigned long curseq;
 	unsigned long flags;
@@ -1168,6 +1197,9 @@ static bool srcu_might_be_idle(struct srcu_struct *ssp)
 	unsigned long tlast;
 
 	check_init_srcu_struct(ssp);
+	/* If _lite() readers, don't do unsolicited expediting. */
+	if (this_cpu_read(ssp->sda->srcu_reader_flavor) & SRCU_READ_FLAVOR_LITE)
+		return false;
 	/* If the local srcu_data structure has callbacks, not idle.  */
 	sdp = raw_cpu_ptr(ssp->sda);
 	spin_lock_irqsave_rcu_node(sdp, flags);
@@ -1469,14 +1501,15 @@ EXPORT_SYMBOL_GPL(synchronize_srcu_expedited);
  * Implementation of these memory-ordering guarantees is similar to
  * that of synchronize_rcu().
  *
- * If SRCU is likely idle, expedite the first request.  This semantic
+ * If SRCU is likely idle as determined by srcu_should_expedite(),
- * was provided by Classic SRCU, and is relied upon by its users, so TREE
+ * expedite the first request.  This semantic was provided by Classic SRCU,
- * SRCU must also provide it.  Note that detecting idleness is heuristic
+ * and is relied upon by its users, so TREE SRCU must also provide it.
- * and subject to both false positives and negatives.
+ * Note that detecting idleness is heuristic and subject to both false
+ * positives and negatives.
  */
 void synchronize_srcu(struct srcu_struct *ssp)
 {
-	if (srcu_might_be_idle(ssp) || rcu_gp_is_expedited())
+	if (srcu_should_expedite(ssp) || rcu_gp_is_expedited())
 		synchronize_srcu_expedited(ssp);
 	else
 		__synchronize_srcu(ssp, true);

kernel/rcu/tree_nocb.h

@@ -891,7 +891,18 @@ static void nocb_cb_wait(struct rcu_data *rdp)
 	swait_event_interruptible_exclusive(rdp->nocb_cb_wq,
 					    nocb_cb_wait_cond(rdp));
 	if (kthread_should_park()) {
-		kthread_parkme();
+		/*
+		 * kthread_park() must be preceded by an rcu_barrier().
+		 * But yet another rcu_barrier() might have sneaked in between
+		 * the barrier callback execution and the callbacks counter
+		 * decrement.
+		 */
+		if (rdp->nocb_cb_sleep) {
+			rcu_nocb_lock_irqsave(rdp, flags);
+			WARN_ON_ONCE(rcu_segcblist_n_cbs(&rdp->cblist));
+			rcu_nocb_unlock_irqrestore(rdp, flags);
+			kthread_parkme();
+		}
 	} else if (READ_ONCE(rdp->nocb_cb_sleep)) {
 		WARN_ON(signal_pending(current));
 		trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("WokeEmpty"));

kernel/rcu/tree_stall.h

@@ -76,36 +76,6 @@ int rcu_jiffies_till_stall_check(void)
 }
 EXPORT_SYMBOL_GPL(rcu_jiffies_till_stall_check);
 
-/**
- * rcu_gp_might_be_stalled - Is it likely that the grace period is stalled?
- *
- * Returns @true if the current grace period is sufficiently old that
- * it is reasonable to assume that it might be stalled.  This can be
- * useful when deciding whether to allocate memory to enable RCU-mediated
- * freeing on the one hand or just invoking synchronize_rcu() on the other.
- * The latter is preferable when the grace period is stalled.
- *
- * Note that sampling of the .gp_start and .gp_seq fields must be done
- * carefully to avoid false positives at the beginnings and ends of
- * grace periods.
- */
-bool rcu_gp_might_be_stalled(void)
-{
-	unsigned long d = rcu_jiffies_till_stall_check() / RCU_STALL_MIGHT_DIV;
-	unsigned long j = jiffies;
-
-	if (d < RCU_STALL_MIGHT_MIN)
-		d = RCU_STALL_MIGHT_MIN;
-	smp_mb(); // jiffies before .gp_seq to avoid false positives.
-	if (!rcu_gp_in_progress())
-		return false;
-	// Long delays at this point avoids false positive, but a delay
-	// of ULONG_MAX/4 jiffies voids your no-false-positive warranty.
-	smp_mb(); // .gp_seq before second .gp_start
-	// And ditto here.
-	return !time_before(j, READ_ONCE(rcu_state.gp_start) + d);
-}
-
 /* Don't do RCU CPU stall warnings during long sysrq printouts. */
 void rcu_sysrq_start(void)
 {
@@ -365,7 +335,7 @@ static int rcu_print_task_stall(struct rcu_node *rnp, unsigned long flags)
  * that don't support NMI-based stack dumps.  The NMI-triggered stack
  * traces are more accurate because they are printed by the target CPU.
  */
-static void rcu_dump_cpu_stacks(void)
+static void rcu_dump_cpu_stacks(unsigned long gp_seq)
 {
 	int cpu;
 	unsigned long flags;
@@ -373,15 +343,23 @@ static void rcu_dump_cpu_stacks(void)
 
 	rcu_for_each_leaf_node(rnp) {
 		printk_deferred_enter();
-		raw_spin_lock_irqsave_rcu_node(rnp, flags);
+		for_each_leaf_node_possible_cpu(rnp, cpu) {
-		for_each_leaf_node_possible_cpu(rnp, cpu)
+			if (gp_seq != data_race(rcu_state.gp_seq)) {
+				printk_deferred_exit();
+				pr_err("INFO: Stall ended during stack backtracing.\n");
+				return;
+			}
+			if (!(data_race(rnp->qsmask) & leaf_node_cpu_bit(rnp, cpu)))
+				continue;
+			raw_spin_lock_irqsave_rcu_node(rnp, flags);
 			if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu)) {
 				if (cpu_is_offline(cpu))
 					pr_err("Offline CPU %d blocking current GP.\n", cpu);
 				else
 					dump_cpu_task(cpu);
 			}
-		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+		}
 		printk_deferred_exit();
 	}
 }
@@ -638,7 +616,7 @@ static void print_other_cpu_stall(unsigned long gp_seq, unsigned long gps)
 	       (long)rcu_seq_current(&rcu_state.gp_seq), totqlen,
 	       data_race(rcu_state.n_online_cpus)); // Diagnostic read
 	if (ndetected) {
-		rcu_dump_cpu_stacks();
+		rcu_dump_cpu_stacks(gp_seq);
 
 		/* Complain about tasks blocking the grace period. */
 		rcu_for_each_leaf_node(rnp)
@@ -670,7 +648,7 @@ static void print_other_cpu_stall(unsigned long gp_seq, unsigned long gps)
 	rcu_force_quiescent_state();  /* Kick them all. */
 }
 
-static void print_cpu_stall(unsigned long gps)
+static void print_cpu_stall(unsigned long gp_seq, unsigned long gps)
 {
 	int cpu;
 	unsigned long flags;
@@ -707,7 +685,7 @@ static void print_cpu_stall(unsigned long gps)
 	rcu_check_gp_kthread_expired_fqs_timer();
 	rcu_check_gp_kthread_starvation();
 
-	rcu_dump_cpu_stacks();
+	rcu_dump_cpu_stacks(gp_seq);
 
 	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	/* Rewrite if needed in case of slow consoles. */
@@ -789,7 +767,8 @@ static void check_cpu_stall(struct rcu_data *rdp)
 	gs2 = READ_ONCE(rcu_state.gp_seq);
 	if (gs1 != gs2 ||
 	    ULONG_CMP_LT(j, js) ||
-	    ULONG_CMP_GE(gps, js))
+	    ULONG_CMP_GE(gps, js) ||
+	    !rcu_seq_state(gs2))
 		return; /* No stall or GP completed since entering function. */
 	rnp = rdp->mynode;
 	jn = jiffies + ULONG_MAX / 2;
@@ -810,7 +789,7 @@ static void check_cpu_stall(struct rcu_data *rdp)
 			pr_err("INFO: %s detected stall, but suppressed full report due to a stuck CSD-lock.\n", rcu_state.name);
 		} else if (self_detected) {
 			/* We haven't checked in, so go dump stack. */
-			print_cpu_stall(gps);
+			print_cpu_stall(gs2, gps);
 		} else {
 			/* They had a few time units to dump stack, so complain. */
 			print_other_cpu_stall(gs2, gps);

tools/testing/selftests/rcutorture/bin/kvm-test-1-run-batch.sh

@@ -56,27 +56,30 @@ do
 	echo > $i/kvm-test-1-run-qemu.sh.out
 	export TORTURE_AFFINITY=
 	kvm-get-cpus-script.sh $T/cpuarray.awk $T/cpubatches.awk $T/cpustate
-	cat << '	___EOF___' >> $T/cpubatches.awk
+	if test -z "${TORTURE_NO_AFFINITY}"
-	END {
+	then
-		affinitylist = "";
+		cat << '		___EOF___' >> $T/cpubatches.awk
-		if (!gotcpus()) {
+		END {
-			print "echo No CPU-affinity information, so no taskset command.";
+			affinitylist = "";
-		} else if (cpu_count !~ /^[0-9][0-9]*$/) {
+			if (!gotcpus()) {
-			print "echo " scenario ": Bogus number of CPUs (old qemu-cmd?), so no taskset command.";
+				print "echo No CPU-affinity information, so no taskset command.";
-		} else {
+			} else if (cpu_count !~ /^[0-9][0-9]*$/) {
-			affinitylist = nextcpus(cpu_count);
+				print "echo " scenario ": Bogus number of CPUs (old qemu-cmd?), so no taskset command.";
-			if (!(affinitylist ~ /^[0-9,-][0-9,-]*$/))
+			} else {
-				print "echo " scenario ": Bogus CPU-affinity information, so no taskset command.";
+				affinitylist = nextcpus(cpu_count);
-			else if (!dumpcpustate())
+				if (!(affinitylist ~ /^[0-9,-][0-9,-]*$/))
-				print "echo " scenario ": Could not dump state, so no taskset command.";
+					print "echo " scenario ": Bogus CPU-affinity information, so no taskset command.";
-			else
+				else if (!dumpcpustate())
-				print "export TORTURE_AFFINITY=" affinitylist;
+					print "echo " scenario ": Could not dump state, so no taskset command.";
+				else
+					print "export TORTURE_AFFINITY=" affinitylist;
+			}
 		}
-	}
+		___EOF___
-	___EOF___
+		cpu_count="`grep '# TORTURE_CPU_COUNT=' $i/qemu-cmd | sed -e 's/^.*=//'`"
-	cpu_count="`grep '# TORTURE_CPU_COUNT=' $i/qemu-cmd | sed -e 's/^.*=//'`"
+		affinity_export="`awk -f $T/cpubatches.awk -v cpu_count="$cpu_count" -v scenario=$i < /dev/null`"
-	affinity_export="`awk -f $T/cpubatches.awk -v cpu_count="$cpu_count" -v scenario=$i < /dev/null`"
+		$affinity_export
-	$affinity_export
+	fi
 	kvm-test-1-run-qemu.sh $i >> $i/kvm-test-1-run-qemu.sh.out 2>&1 &
 done
 for i in $runfiles

tools/testing/selftests/rcutorture/bin/kvm.sh

@@ -42,6 +42,7 @@ TORTURE_JITTER_STOP=""
 TORTURE_KCONFIG_KASAN_ARG=""
 TORTURE_KCONFIG_KCSAN_ARG=""
 TORTURE_KMAKE_ARG=""
+TORTURE_NO_AFFINITY=""
 TORTURE_QEMU_MEM=512
 torture_qemu_mem_default=1
 TORTURE_REMOTE=
@@ -82,6 +83,7 @@ usage () {
 	echo "       --kmake-arg kernel-make-arguments"
 	echo "       --mac nn:nn:nn:nn:nn:nn"
 	echo "       --memory megabytes|nnnG"
+	echo "       --no-affinity"
 	echo "       --no-initrd"
 	echo "       --qemu-args qemu-arguments"
 	echo "       --qemu-cmd qemu-system-..."
@@ -220,6 +222,9 @@ do
 		torture_qemu_mem_default=
 		shift
 		;;
+	--no-affinity)
+		TORTURE_NO_AFFINITY="no-affinity"
+		;;
 	--no-initrd)
 		TORTURE_INITRD=""; export TORTURE_INITRD
 		;;
@@ -417,6 +422,7 @@ TORTURE_KCONFIG_KASAN_ARG="$TORTURE_KCONFIG_KASAN_ARG"; export TORTURE_KCONFIG_K
 TORTURE_KCONFIG_KCSAN_ARG="$TORTURE_KCONFIG_KCSAN_ARG"; export TORTURE_KCONFIG_KCSAN_ARG
 TORTURE_KMAKE_ARG="$TORTURE_KMAKE_ARG"; export TORTURE_KMAKE_ARG
 TORTURE_MOD="$TORTURE_MOD"; export TORTURE_MOD
+TORTURE_NO_AFFINITY="$TORTURE_NO_AFFINITY"; export TORTURE_NO_AFFINITY
 TORTURE_QEMU_CMD="$TORTURE_QEMU_CMD"; export TORTURE_QEMU_CMD
 TORTURE_QEMU_INTERACTIVE="$TORTURE_QEMU_INTERACTIVE"; export TORTURE_QEMU_INTERACTIVE
 TORTURE_QEMU_MAC="$TORTURE_QEMU_MAC"; export TORTURE_QEMU_MAC

tools/testing/selftests/rcutorture/configs/rcu/CFLIST

@@ -5,6 +5,7 @@ TREE04
 TREE05
 TREE07
 TREE09
+SRCU-L
 SRCU-N
 SRCU-P
 SRCU-T

tools/testing/selftests/rcutorture/configs/rcu/SRCU-L

@@ -0,0 +1,10 @@
+CONFIG_RCU_TRACE=n
+CONFIG_SMP=y
+CONFIG_NR_CPUS=6
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_RCU_EXPERT=n
+CONFIG_KPROBES=n
+CONFIG_FTRACE=n

tools/testing/selftests/rcutorture/configs/rcu/SRCU-L.boot

@@ -0,0 +1,3 @@
+rcutorture.torture_type=srcu
+rcutorture.reader_flavor=0x4
+rcutorture.fwd_progress=3

tools/testing/selftests/rcutorture/configs/rcu/SRCU-N.boot

@@ -1,2 +1,3 @@
 rcutorture.torture_type=srcu
+rcutorture.reader_flavor=0x2
 rcutorture.fwd_progress=3

tools/testing/selftests/rcutorture/configs/rcu/TREE10

@@ -1,5 +1,5 @@
 CONFIG_SMP=y
-CONFIG_NR_CPUS=56
+CONFIG_NR_CPUS=74
 CONFIG_PREEMPT_NONE=y
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=n