Merge branch 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull RCU updates from Ingo Molnar:
 "The biggest change in this cycle is the conclusion of the big
  'simplify RCU to two primary flavors' consolidation work - i.e.
  there's a single RCU flavor for any kernel variant (PREEMPT and
  !PREEMPT):

    - Consolidate the RCU-bh, RCU-preempt, and RCU-sched flavors into a
      single flavor similar to RCU-sched in !PREEMPT kernels and into a
      single flavor similar to RCU-preempt (but also waiting on
      preempt-disabled sequences of code) in PREEMPT kernels.

      This branch also includes a refactoring of
      rcu_{nmi,irq}_{enter,exit}() from Byungchul Park.

    - Now that there is only one RCU flavor in any given running kernel,
      the many "rsp" pointers are no longer required, and this cleanup
      series removes them.

    - This branch carries out additional cleanups made possible by the
      RCU flavor consolidation, including inlining now-trivial
      functions, updating comments and definitions, and removing
      now-unneeded rcutorture scenarios.

    - Now that there is only one flavor of RCU in any running kernel,
      there is also only on rcu_data structure per CPU. This means that
      the rcu_dynticks structure can be merged into the rcu_data
      structure, a task taken on by this branch. This branch also
      contains a -rt-related fix from Mike Galbraith.

  There were also other updates:

    - Documentation updates, including some good-eye catches from Joel
      Fernandes.

    - SRCU updates, most notably changes enabling call_srcu() to be
      invoked very early in the boot sequence.

    - Torture-test updates, including some preliminary work towards
      making rcutorture better able to find problems that result in
      insufficient grace-period forward progress.

    - Initial changes to RCU to better promote forward progress of grace
      periods, including fixing a bug found by Marius Hillenbrand and
      David Woodhouse, with the fix suggested by Peter Zijlstra"

* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (140 commits)
  srcu: Make early-boot call_srcu() reuse workqueue lists
  rcutorture: Test early boot call_srcu()
  srcu: Make call_srcu() available during very early boot
  rcu: Convert rcu_state.ofl_lock to raw_spinlock_t
  rcu: Remove obsolete ->dynticks_fqs and ->cond_resched_completed
  rcu: Switch ->dynticks to rcu_data structure, remove rcu_dynticks
  rcu: Switch dyntick nesting counters to rcu_data structure
  rcu: Switch urgent quiescent-state requests to rcu_data structure
  rcu: Switch lazy counts to rcu_data structure
  rcu: Switch last accelerate/advance to rcu_data structure
  rcu: Switch ->tick_nohz_enabled_snap to rcu_data structure
  rcu: Merge rcu_dynticks structure into rcu_data structure
  rcu: Remove unused rcu_dynticks_snap() from Tiny RCU
  rcu: Convert "1UL << x" to "BIT(x)"
  rcu: Avoid resched_cpu() when rescheduling the current CPU
  rcu: More aggressively enlist scheduler aid for nohz_full CPUs
  rcu: Compute jiffies_till_sched_qs from other kernel parameters
  rcu: Provide functions for determining if call_rcu() has been invoked
  rcu: Eliminate ->rcu_qs_ctr from the rcu_dynticks structure
  rcu: Motivate Tiny RCU forward progress
  ...

14 files changed, 2008 insertions, 2387 deletions

diff --git a/kernel/rcu/Kconfig b/kernel/rcu/Kconfig
index 9210379c0353..939a2056c87a 100644
--- a/kernel/rcu/Kconfig
+++ b/kernel/rcu/Kconfig
@@ -196,7 +196,7 @@ config RCU_BOOST
 	  This option boosts the priority of preempted RCU readers that
 	  block the current preemptible RCU grace period for too long.
 	  This option also prevents heavy loads from blocking RCU
-	  callback invocation for all flavors of RCU.
+	  callback invocation.
 
 	  Say Y here if you are working with real-time apps or heavy loads
 	  Say N here if you are unsure.
@@ -225,12 +225,12 @@ config RCU_NOCB_CPU
 	  callback invocation to energy-efficient CPUs in battery-powered
 	  asymmetric multiprocessors.
 
-	  This option offloads callback invocation from the set of
-	  CPUs specified at boot time by the rcu_nocbs parameter.
-	  For each such CPU, a kthread ("rcuox/N") will be created to
-	  invoke callbacks, where the "N" is the CPU being offloaded,
-	  and where the "x" is "b" for RCU-bh, "p" for RCU-preempt, and
-	  "s" for RCU-sched.  Nothing prevents this kthread from running
+	  This option offloads callback invocation from the set of CPUs
+	  specified at boot time by the rcu_nocbs parameter.  For each
+	  such CPU, a kthread ("rcuox/N") will be created to invoke
+	  callbacks, where the "N" is the CPU being offloaded, and where
+	  the "p" for RCU-preempt (PREEMPT kernels) and "s" for RCU-sched
+	  (!PREEMPT kernels).  Nothing prevents this kthread from running
 	  on the specified CPUs, but (1) the kthreads may be preempted
 	  between each callback, and (2) affinity or cgroups can be used
 	  to force the kthreads to run on whatever set of CPUs is desired.
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 4d04683c31b2..2866166863f0 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -176,8 +176,9 @@ static inline unsigned long rcu_seq_diff(unsigned long new, unsigned long old)
 
 /*
  * debug_rcu_head_queue()/debug_rcu_head_unqueue() are used internally
- * by call_rcu() and rcu callback execution, and are therefore not part of the
- * RCU API. Leaving in rcupdate.h because they are used by all RCU flavors.
+ * by call_rcu() and rcu callback execution, and are therefore not part
+ * of the RCU API. These are in rcupdate.h because they are used by all
+ * RCU implementations.
  */
 
 #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
@@ -223,6 +224,7 @@ void kfree(const void *);
  */
 static inline bool __rcu_reclaim(const char *rn, struct rcu_head *head)
 {
+	rcu_callback_t f;
 	unsigned long offset = (unsigned long)head->func;
 
 	rcu_lock_acquire(&rcu_callback_map);
@@ -233,7 +235,9 @@ static inline bool __rcu_reclaim(const char *rn, struct rcu_head *head)
 		return true;
 	} else {
 		RCU_TRACE(trace_rcu_invoke_callback(rn, head);)
-		head->func(head);
+		f = head->func;
+		WRITE_ONCE(head->func, (rcu_callback_t)0L);
+		f(head);
 		rcu_lock_release(&rcu_callback_map);
 		return false;
 	}
@@ -328,40 +332,35 @@ static inline void rcu_init_levelspread(int *levelspread, const int *levelcnt)
 	}
 }
 
-/* Returns first leaf rcu_node of the specified RCU flavor. */
-#define rcu_first_leaf_node(rsp) ((rsp)->level[rcu_num_lvls - 1])
+/* Returns a pointer to the first leaf rcu_node structure. */
+#define rcu_first_leaf_node() (rcu_state.level[rcu_num_lvls - 1])
 
 /* Is this rcu_node a leaf? */
 #define rcu_is_leaf_node(rnp) ((rnp)->level == rcu_num_lvls - 1)
 
 /* Is this rcu_node the last leaf? */
-#define rcu_is_last_leaf_node(rsp, rnp) ((rnp) == &(rsp)->node[rcu_num_nodes - 1])
+#define rcu_is_last_leaf_node(rnp) ((rnp) == &rcu_state.node[rcu_num_nodes - 1])
 
 /*
- * Do a full breadth-first scan of the rcu_node structures for the
- * specified rcu_state structure.
+ * Do a full breadth-first scan of the {s,}rcu_node structures for the
+ * specified state structure (for SRCU) or the only rcu_state structure
+ * (for RCU).
  */
-#define rcu_for_each_node_breadth_first(rsp, rnp) \
-	for ((rnp) = &(rsp)->node[0]; \
-	     (rnp) < &(rsp)->node[rcu_num_nodes]; (rnp)++)
+#define srcu_for_each_node_breadth_first(sp, rnp) \
+	for ((rnp) = &(sp)->node[0]; \
+	     (rnp) < &(sp)->node[rcu_num_nodes]; (rnp)++)
+#define rcu_for_each_node_breadth_first(rnp) \
+	srcu_for_each_node_breadth_first(&rcu_state, rnp)
 
 /*
- * Do a breadth-first scan of the non-leaf rcu_node structures for the
- * specified rcu_state structure.  Note that if there is a singleton
- * rcu_node tree with but one rcu_node structure, this loop is a no-op.
+ * Scan the leaves of the rcu_node hierarchy for the rcu_state structure.
+ * Note that if there is a singleton rcu_node tree with but one rcu_node
+ * structure, this loop -will- visit the rcu_node structure.  It is still
+ * a leaf node, even if it is also the root node.
  */
-#define rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) \
-	for ((rnp) = &(rsp)->node[0]; !rcu_is_leaf_node(rsp, rnp); (rnp)++)
-
-/*
- * Scan the leaves of the rcu_node hierarchy for the specified rcu_state
- * structure.  Note that if there is a singleton rcu_node tree with but
- * one rcu_node structure, this loop -will- visit the rcu_node structure.
- * It is still a leaf node, even if it is also the root node.
- */
-#define rcu_for_each_leaf_node(rsp, rnp) \
-	for ((rnp) = rcu_first_leaf_node(rsp); \
-	     (rnp) < &(rsp)->node[rcu_num_nodes]; (rnp)++)
+#define rcu_for_each_leaf_node(rnp) \
+	for ((rnp) = rcu_first_leaf_node(); \
+	     (rnp) < &rcu_state.node[rcu_num_nodes]; (rnp)++)
 
 /*
  * Iterate over all possible CPUs in a leaf RCU node.
@@ -435,6 +434,12 @@ do {									\
 
 #endif /* #if defined(SRCU) || !defined(TINY_RCU) */
 
+#ifdef CONFIG_SRCU
+void srcu_init(void);
+#else /* #ifdef CONFIG_SRCU */
+static inline void srcu_init(void) { }
+#endif /* #else #ifdef CONFIG_SRCU */
+
 #ifdef CONFIG_TINY_RCU
 /* Tiny RCU doesn't expedite, as its purpose in life is instead to be tiny. */
 static inline bool rcu_gp_is_normal(void) { return true; }
@@ -515,29 +520,19 @@ void srcutorture_get_gp_data(enum rcutorture_type test_type,
 
 #ifdef CONFIG_TINY_RCU
 static inline unsigned long rcu_get_gp_seq(void) { return 0; }
-static inline unsigned long rcu_bh_get_gp_seq(void) { return 0; }
-static inline unsigned long rcu_sched_get_gp_seq(void) { return 0; }
 static inline unsigned long rcu_exp_batches_completed(void) { return 0; }
-static inline unsigned long rcu_exp_batches_completed_sched(void) { return 0; }
 static inline unsigned long
 srcu_batches_completed(struct srcu_struct *sp) { return 0; }
 static inline void rcu_force_quiescent_state(void) { }
-static inline void rcu_bh_force_quiescent_state(void) { }
-static inline void rcu_sched_force_quiescent_state(void) { }
 static inline void show_rcu_gp_kthreads(void) { }
 static inline int rcu_get_gp_kthreads_prio(void) { return 0; }
 #else /* #ifdef CONFIG_TINY_RCU */
 unsigned long rcu_get_gp_seq(void);
-unsigned long rcu_bh_get_gp_seq(void);
-unsigned long rcu_sched_get_gp_seq(void);
 unsigned long rcu_exp_batches_completed(void);
-unsigned long rcu_exp_batches_completed_sched(void);
 unsigned long srcu_batches_completed(struct srcu_struct *sp);
 void show_rcu_gp_kthreads(void);
 int rcu_get_gp_kthreads_prio(void);
 void rcu_force_quiescent_state(void);
-void rcu_bh_force_quiescent_state(void);
-void rcu_sched_force_quiescent_state(void);
 extern struct workqueue_struct *rcu_gp_wq;
 extern struct workqueue_struct *rcu_par_gp_wq;
 #endif /* #else #ifdef CONFIG_TINY_RCU */
diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c
index 34244523550e..b459da70b4fc 100644
--- a/kernel/rcu/rcuperf.c
+++ b/kernel/rcu/rcuperf.c
@@ -190,36 +190,6 @@ static struct rcu_perf_ops rcu_ops = {
 };
 
 /*
- * Definitions for rcu_bh perf testing.
- */
-
-static int rcu_bh_perf_read_lock(void) __acquires(RCU_BH)
-{
-	rcu_read_lock_bh();
-	return 0;
-}
-
-static void rcu_bh_perf_read_unlock(int idx) __releases(RCU_BH)
-{
-	rcu_read_unlock_bh();
-}
-
-static struct rcu_perf_ops rcu_bh_ops = {
-	.ptype		= RCU_BH_FLAVOR,
-	.init		= rcu_sync_perf_init,
-	.readlock	= rcu_bh_perf_read_lock,
-	.readunlock	= rcu_bh_perf_read_unlock,
-	.get_gp_seq	= rcu_bh_get_gp_seq,
-	.gp_diff	= rcu_seq_diff,
-	.exp_completed	= rcu_exp_batches_completed_sched,
-	.async		= call_rcu_bh,
-	.gp_barrier	= rcu_barrier_bh,
-	.sync		= synchronize_rcu_bh,
-	.exp_sync	= synchronize_rcu_bh_expedited,
-	.name		= "rcu_bh"
-};
-
-/*
  * Definitions for srcu perf testing.
  */
 
@@ -306,36 +276,6 @@ static struct rcu_perf_ops srcud_ops = {
 };
 
 /*
- * Definitions for sched perf testing.
- */
-
-static int sched_perf_read_lock(void)
-{
-	preempt_disable();
-	return 0;
-}
-
-static void sched_perf_read_unlock(int idx)
-{
-	preempt_enable();
-}
-
-static struct rcu_perf_ops sched_ops = {
-	.ptype		= RCU_SCHED_FLAVOR,
-	.init		= rcu_sync_perf_init,
-	.readlock	= sched_perf_read_lock,
-	.readunlock	= sched_perf_read_unlock,
-	.get_gp_seq	= rcu_sched_get_gp_seq,
-	.gp_diff	= rcu_seq_diff,
-	.exp_completed	= rcu_exp_batches_completed_sched,
-	.async		= call_rcu_sched,
-	.gp_barrier	= rcu_barrier_sched,
-	.sync		= synchronize_sched,
-	.exp_sync	= synchronize_sched_expedited,
-	.name		= "sched"
-};
-
-/*
  * Definitions for RCU-tasks perf testing.
  */
 
@@ -611,7 +551,7 @@ rcu_perf_cleanup(void)
 		kfree(writer_n_durations);
 	}
 
-	/* Do flavor-specific cleanup operations.  */
+	/* Do torture-type-specific cleanup operations.  */
 	if (cur_ops->cleanup != NULL)
 		cur_ops->cleanup();
 
@@ -661,8 +601,7 @@ rcu_perf_init(void)
 	long i;
 	int firsterr = 0;
 	static struct rcu_perf_ops *perf_ops[] = {
-		&rcu_ops, &rcu_bh_ops, &srcu_ops, &srcud_ops, &sched_ops,
-		&tasks_ops,
+		&rcu_ops, &srcu_ops, &srcud_ops, &tasks_ops,
 	};
 
 	if (!torture_init_begin(perf_type, verbose))
@@ -680,6 +619,7 @@ rcu_perf_init(void)
 		for (i = 0; i < ARRAY_SIZE(perf_ops); i++)
 			pr_cont(" %s", perf_ops[i]->name);
 		pr_cont("\n");
+		WARN_ON(!IS_MODULE(CONFIG_RCU_PERF_TEST));
 		firsterr = -EINVAL;
 		goto unwind;
 	}
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index c596c6f1e457..210c77460365 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -66,15 +66,19 @@ MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and Josh Triplett <josh@jos
 /* Bits for ->extendables field, extendables param, and related definitions. */
 #define RCUTORTURE_RDR_SHIFT	 8	/* Put SRCU index in upper bits. */
 #define RCUTORTURE_RDR_MASK	 ((1 << RCUTORTURE_RDR_SHIFT) - 1)
-#define RCUTORTURE_RDR_BH	 0x1	/* Extend readers by disabling bh. */
-#define RCUTORTURE_RDR_IRQ	 0x2	/*  ... disabling interrupts. */
-#define RCUTORTURE_RDR_PREEMPT	 0x4	/*  ... disabling preemption. */
-#define RCUTORTURE_RDR_RCU	 0x8	/*  ... entering another RCU reader. */
-#define RCUTORTURE_RDR_NBITS	 4	/* Number of bits defined above. */
-#define RCUTORTURE_MAX_EXTEND	 (RCUTORTURE_RDR_BH | RCUTORTURE_RDR_IRQ | \
-				  RCUTORTURE_RDR_PREEMPT)
+#define RCUTORTURE_RDR_BH	 0x01	/* Extend readers by disabling bh. */
+#define RCUTORTURE_RDR_IRQ	 0x02	/*  ... disabling interrupts. */
+#define RCUTORTURE_RDR_PREEMPT	 0x04	/*  ... disabling preemption. */
+#define RCUTORTURE_RDR_RBH	 0x08	/*  ... rcu_read_lock_bh(). */
+#define RCUTORTURE_RDR_SCHED	 0x10	/*  ... rcu_read_lock_sched(). */
+#define RCUTORTURE_RDR_RCU	 0x20	/*  ... entering another RCU reader. */
+#define RCUTORTURE_RDR_NBITS	 6	/* Number of bits defined above. */
+#define RCUTORTURE_MAX_EXTEND	 \
+	(RCUTORTURE_RDR_BH | RCUTORTURE_RDR_IRQ | RCUTORTURE_RDR_PREEMPT | \
+	 RCUTORTURE_RDR_RBH | RCUTORTURE_RDR_SCHED)
 #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)
 
 torture_param(int, cbflood_inter_holdoff, HZ,
 	      "Holdoff between floods (jiffies)");
@@ -89,6 +93,12 @@ torture_param(int, fqs_duration, 0,
 	      "Duration of fqs bursts (us), 0 to disable");
 torture_param(int, fqs_holdoff, 0, "Holdoff time within fqs bursts (us)");
 torture_param(int, fqs_stutter, 3, "Wait time between fqs bursts (s)");
+torture_param(bool, fwd_progress, 1, "Test grace-period forward progress");
+torture_param(int, fwd_progress_div, 4, "Fraction of CPU stall to wait");
+torture_param(int, fwd_progress_holdoff, 60,
+	      "Time between forward-progress tests (s)");
+torture_param(bool, fwd_progress_need_resched, 1,
+	      "Hide cond_resched() behind need_resched()");
 torture_param(bool, gp_cond, false, "Use conditional/async GP wait primitives");
 torture_param(bool, gp_exp, false, "Use expedited GP wait primitives");
 torture_param(bool, gp_normal, false,
@@ -125,7 +135,7 @@ torture_param(int, verbose, 1,
 
 static char *torture_type = "rcu";
 module_param(torture_type, charp, 0444);
-MODULE_PARM_DESC(torture_type, "Type of RCU to torture (rcu, rcu_bh, ...)");
+MODULE_PARM_DESC(torture_type, "Type of RCU to torture (rcu, srcu, ...)");
 
 static int nrealreaders;
 static int ncbflooders;
@@ -137,6 +147,7 @@ static struct task_struct **cbflood_task;
 static struct task_struct *fqs_task;
 static struct task_struct *boost_tasks[NR_CPUS];
 static struct task_struct *stall_task;
+static struct task_struct *fwd_prog_task;
 static struct task_struct **barrier_cbs_tasks;
 static struct task_struct *barrier_task;
 
@@ -197,6 +208,18 @@ static const char * const rcu_torture_writer_state_names[] = {
 	"RTWS_STOPPING",
 };
 
+/* Record reader segment types and duration for first failing read. */
+struct rt_read_seg {
+	int rt_readstate;
+	unsigned long rt_delay_jiffies;
+	unsigned long rt_delay_ms;
+	unsigned long rt_delay_us;
+	bool rt_preempted;
+};
+static int err_segs_recorded;
+static struct rt_read_seg err_segs[RCUTORTURE_RDR_MAX_SEGS];
+static int rt_read_nsegs;
+
 static const char *rcu_torture_writer_state_getname(void)
 {
 	unsigned int i = READ_ONCE(rcu_torture_writer_state);
@@ -278,7 +301,8 @@ struct rcu_torture_ops {
 	void (*init)(void);
 	void (*cleanup)(void);
 	int (*readlock)(void);
-	void (*read_delay)(struct torture_random_state *rrsp);
+	void (*read_delay)(struct torture_random_state *rrsp,
+			   struct rt_read_seg *rtrsp);
 	void (*readunlock)(int idx);
 	unsigned long (*get_gp_seq)(void);
 	unsigned long (*gp_diff)(unsigned long new, unsigned long old);
@@ -291,6 +315,7 @@ struct rcu_torture_ops {
 	void (*cb_barrier)(void);
 	void (*fqs)(void);
 	void (*stats)(void);
+	int (*stall_dur)(void);
 	int irq_capable;
 	int can_boost;
 	int extendables;
@@ -310,12 +335,13 @@ static int rcu_torture_read_lock(void) __acquires(RCU)
 	return 0;
 }
 
-static void rcu_read_delay(struct torture_random_state *rrsp)
+static void
+rcu_read_delay(struct torture_random_state *rrsp, struct rt_read_seg *rtrsp)
 {
 	unsigned long started;
 	unsigned long completed;
 	const unsigned long shortdelay_us = 200;
-	const unsigned long longdelay_ms = 50;
+	unsigned long longdelay_ms = 300;
 	unsigned long long ts;
 
 	/* We want a short delay sometimes to make a reader delay the grace
@@ -325,16 +351,23 @@ static void rcu_read_delay(struct torture_random_state *rrsp)
 	if (!(torture_random(rrsp) % (nrealreaders * 2000 * longdelay_ms))) {
 		started = cur_ops->get_gp_seq();
 		ts = rcu_trace_clock_local();
+		if (preempt_count() & (SOFTIRQ_MASK | HARDIRQ_MASK))
+			longdelay_ms = 5; /* Avoid triggering BH limits. */
 		mdelay(longdelay_ms);
+		rtrsp->rt_delay_ms = longdelay_ms;
 		completed = cur_ops->get_gp_seq();
 		do_trace_rcu_torture_read(cur_ops->name, NULL, ts,
 					  started, completed);
 	}
-	if (!(torture_random(rrsp) % (nrealreaders * 2 * shortdelay_us)))
+	if (!(torture_random(rrsp) % (nrealreaders * 2 * shortdelay_us))) {
 		udelay(shortdelay_us);
+		rtrsp->rt_delay_us = shortdelay_us;
+	}
 	if (!preempt_count() &&
-	    !(torture_random(rrsp) % (nrealreaders * 500)))
+	    !(torture_random(rrsp) % (nrealreaders * 500))) {
 		torture_preempt_schedule();  /* QS only if preemptible. */
+		rtrsp->rt_preempted = true;
+	}
 }
 
 static void rcu_torture_read_unlock(int idx) __releases(RCU)
@@ -429,53 +462,14 @@ static struct rcu_torture_ops rcu_ops = {
 	.cb_barrier	= rcu_barrier,
 	.fqs		= rcu_force_quiescent_state,
 	.stats		= NULL,
+	.stall_dur	= rcu_jiffies_till_stall_check,
 	.irq_capable	= 1,
 	.can_boost	= rcu_can_boost(),
+	.extendables	= RCUTORTURE_MAX_EXTEND,
 	.name		= "rcu"
 };
 
 /*
- * Definitions for rcu_bh torture testing.
- */
-
-static int rcu_bh_torture_read_lock(void) __acquires(RCU_BH)
-{
-	rcu_read_lock_bh();
-	return 0;
-}
-
-static void rcu_bh_torture_read_unlock(int idx) __releases(RCU_BH)
-{
-	rcu_read_unlock_bh();
-}
-
-static void rcu_bh_torture_deferred_free(struct rcu_torture *p)
-{
-	call_rcu_bh(&p->rtort_rcu, rcu_torture_cb);
-}
-
-static struct rcu_torture_ops rcu_bh_ops = {
-	.ttype		= RCU_BH_FLAVOR,
-	.init		= rcu_sync_torture_init,
-	.readlock	= rcu_bh_torture_read_lock,
-	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
-	.readunlock	= rcu_bh_torture_read_unlock,
-	.get_gp_seq	= rcu_bh_get_gp_seq,
-	.gp_diff	= rcu_seq_diff,
-	.deferred_free	= rcu_bh_torture_deferred_free,
-	.sync		= synchronize_rcu_bh,
-	.exp_sync	= synchronize_rcu_bh_expedited,
-	.call		= call_rcu_bh,
-	.cb_barrier	= rcu_barrier_bh,
-	.fqs		= rcu_bh_force_quiescent_state,
-	.stats		= NULL,
-	.irq_capable	= 1,
-	.extendables	= (RCUTORTURE_RDR_BH | RCUTORTURE_RDR_IRQ),
-	.ext_irq_conflict = RCUTORTURE_RDR_RCU,
-	.name		= "rcu_bh"
-};
-
-/*
  * Don't even think about trying any of these in real life!!!
  * The names includes "busted", and they really means it!
  * The only purpose of these functions is to provide a buggy RCU
@@ -531,7 +525,8 @@ static int srcu_torture_read_lock(void) __acquires(srcu_ctlp)
 	return srcu_read_lock(srcu_ctlp);
 }
 
-static void srcu_read_delay(struct torture_random_state *rrsp)
+static void
+srcu_read_delay(struct torture_random_state *rrsp, struct rt_read_seg *rtrsp)
 {
 	long delay;
 	const long uspertick = 1000000 / HZ;
@@ -541,10 +536,12 @@ static void srcu_read_delay(struct torture_random_state *rrsp)
 
 	delay = torture_random(rrsp) %
 		(nrealreaders * 2 * longdelay * uspertick);
-	if (!delay && in_task())
+	if (!delay && in_task()) {
 		schedule_timeout_interruptible(longdelay);
-	else
-		rcu_read_delay(rrsp);
+		rtrsp->rt_delay_jiffies = longdelay;
+	} else {
+		rcu_read_delay(rrsp, rtrsp);
+	}
 }
 
 static void srcu_torture_read_unlock(int idx) __releases(srcu_ctlp)
@@ -663,48 +660,6 @@ static struct rcu_torture_ops busted_srcud_ops = {
 };
 
 /*
- * Definitions for sched torture testing.
- */
-
-static int sched_torture_read_lock(void)
-{
-	preempt_disable();
-	return 0;
-}
-
-static void sched_torture_read_unlock(int idx)
-{
-	preempt_enable();
-}
-
-static void rcu_sched_torture_deferred_free(struct rcu_torture *p)
-{
-	call_rcu_sched(&p->rtort_rcu, rcu_torture_cb);
-}
-
-static struct rcu_torture_ops sched_ops = {
-	.ttype		= RCU_SCHED_FLAVOR,
-	.init		= rcu_sync_torture_init,
-	.readlock	= sched_torture_read_lock,
-	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
-	.readunlock	= sched_torture_read_unlock,
-	.get_gp_seq	= rcu_sched_get_gp_seq,
-	.gp_diff	= rcu_seq_diff,
-	.deferred_free	= rcu_sched_torture_deferred_free,
-	.sync		= synchronize_sched,
-	.exp_sync	= synchronize_sched_expedited,
-	.get_state	= get_state_synchronize_sched,
-	.cond_sync	= cond_synchronize_sched,
-	.call		= call_rcu_sched,
-	.cb_barrier	= rcu_barrier_sched,
-	.fqs		= rcu_sched_force_quiescent_state,
-	.stats		= NULL,
-	.irq_capable	= 1,
-	.extendables	= RCUTORTURE_MAX_EXTEND,
-	.name		= "sched"
-};
-
-/*
  * Definitions for RCU-tasks torture testing.
  */
 
@@ -1116,7 +1071,8 @@ rcu_torture_writer(void *arg)
 				break;
 			}
 		}
-		rcu_torture_current_version++;
+		WRITE_ONCE(rcu_torture_current_version,
+			   rcu_torture_current_version + 1);
 		/* Cycle through nesting levels of rcu_expedite_gp() calls. */
 		if (can_expedite &&
 		    !(torture_random(&rand) & 0xff & (!!expediting - 1))) {
@@ -1132,7 +1088,10 @@ rcu_torture_writer(void *arg)
 				       !rcu_gp_is_normal();
 		}
 		rcu_torture_writer_state = RTWS_STUTTER;
-		stutter_wait("rcu_torture_writer");
+		if (stutter_wait("rcu_torture_writer"))
+			for (i = 0; i < ARRAY_SIZE(rcu_tortures); i++)
+				if (list_empty(&rcu_tortures[i].rtort_free))
+					WARN_ON_ONCE(1);
 	} while (!torture_must_stop());
 	/* Reset expediting back to unexpedited. */
 	if (expediting > 0)
@@ -1199,7 +1158,8 @@ static void rcu_torture_timer_cb(struct rcu_head *rhp)
  * change, do a ->read_delay().
  */
 static void rcutorture_one_extend(int *readstate, int newstate,
-				  struct torture_random_state *trsp)
+				  struct torture_random_state *trsp,
+				  struct rt_read_seg *rtrsp)
 {
 	int idxnew = -1;
 	int idxold = *readstate;
@@ -1208,6 +1168,7 @@ static void rcutorture_one_extend(int *readstate, int newstate,
 
 	WARN_ON_ONCE(idxold < 0);
 	WARN_ON_ONCE((idxold >> RCUTORTURE_RDR_SHIFT) > 1);
+	rtrsp->rt_readstate = newstate;
 
 	/* First, put new protection in place to avoid critical-section gap. */
 	if (statesnew & RCUTORTURE_RDR_BH)
@@ -1216,6 +1177,10 @@ static void rcutorture_one_extend(int *readstate, int newstate,
 		local_irq_disable();
 	if (statesnew & RCUTORTURE_RDR_PREEMPT)
 		preempt_disable();
+	if (statesnew & RCUTORTURE_RDR_RBH)
+		rcu_read_lock_bh();
+	if (statesnew & RCUTORTURE_RDR_SCHED)
+		rcu_read_lock_sched();
 	if (statesnew & RCUTORTURE_RDR_RCU)
 		idxnew = cur_ops->readlock() << RCUTORTURE_RDR_SHIFT;
 
@@ -1226,12 +1191,16 @@ static void rcutorture_one_extend(int *readstate, int newstate,
 		local_bh_enable();
 	if (statesold & RCUTORTURE_RDR_PREEMPT)
 		preempt_enable();
+	if (statesold & RCUTORTURE_RDR_RBH)
+		rcu_read_unlock_bh();
+	if (statesold & RCUTORTURE_RDR_SCHED)
+		rcu_read_unlock_sched();
 	if (statesold & RCUTORTURE_RDR_RCU)
 		cur_ops->readunlock(idxold >> RCUTORTURE_RDR_SHIFT);
 
 	/* Delay if neither beginning nor end and there was a change. */
 	if ((statesnew || statesold) && *readstate && newstate)
-		cur_ops->read_delay(trsp);
+		cur_ops->read_delay(trsp, rtrsp);
 
 	/* Update the reader state. */
 	if (idxnew == -1)
@@ -1260,18 +1229,19 @@ rcutorture_extend_mask(int oldmask, struct torture_random_state *trsp)
 {
 	int mask = rcutorture_extend_mask_max();
 	unsigned long randmask1 = torture_random(trsp) >> 8;
-	unsigned long randmask2 = randmask1 >> 1;
+	unsigned long randmask2 = randmask1 >> 3;
 
 	WARN_ON_ONCE(mask >> RCUTORTURE_RDR_SHIFT);
-	/* Half the time lots of bits, half the time only one bit. */
-	if (randmask1 & 0x1)
+	/* Most of the time lots of bits, half the time only one bit. */
+	if (!(randmask1 & 0x7))
 		mask = mask & randmask2;
 	else
 		mask = mask & (1 << (randmask2 % RCUTORTURE_RDR_NBITS));
+	/* Can't enable bh w/irq disabled. */
 	if ((mask & RCUTORTURE_RDR_IRQ) &&
-	    !(mask & RCUTORTURE_RDR_BH) &&
-	    (oldmask & RCUTORTURE_RDR_BH))
-		mask |= RCUTORTURE_RDR_BH; /* Can't enable bh w/irq disabled. */
+	    ((!(mask & RCUTORTURE_RDR_BH) && (oldmask & RCUTORTURE_RDR_BH)) ||
+	     (!(mask & RCUTORTURE_RDR_RBH) && (oldmask & RCUTORTURE_RDR_RBH))))
+		mask |= RCUTORTURE_RDR_BH | RCUTORTURE_RDR_RBH;
 	if ((mask & RCUTORTURE_RDR_IRQ) &&
 	    !(mask & cur_ops->ext_irq_conflict) &&
 	    (oldmask & cur_ops->ext_irq_conflict))
@@ -1283,20 +1253,25 @@ rcutorture_extend_mask(int oldmask, struct torture_random_state *trsp)
  * Do a randomly selected number of extensions of an existing RCU read-side
  * critical section.
  */
-static void rcutorture_loop_extend(int *readstate,
-				   struct torture_random_state *trsp)
+static struct rt_read_seg *
+rcutorture_loop_extend(int *readstate, struct torture_random_state *trsp,
+		       struct rt_read_seg *rtrsp)
 {
 	int i;
+	int j;
 	int mask = rcutorture_extend_mask_max();
 
 	WARN_ON_ONCE(!*readstate); /* -Existing- RCU read-side critsect! */
 	if (!((mask - 1) & mask))
-		return;  /* Current RCU flavor not extendable. */
-	i = (torture_random(trsp) >> 3) & RCUTORTURE_RDR_MAX_LOOPS;
-	while (i--) {
+		return rtrsp;  /* Current RCU reader not extendable. */
+	/* Bias towards larger numbers of loops. */
+	i = (torture_random(trsp) >> 3);
+	i = ((i | (i >> 3)) & RCUTORTURE_RDR_MAX_LOOPS) + 1;
+	for (j = 0; j < i; j++) {
 		mask = rcutorture_extend_mask(*readstate, trsp);
-		rcutorture_one_extend(readstate, mask, trsp);
+		rcutorture_one_extend(readstate, mask, trsp, &rtrsp[j]);
 	}
+	return &rtrsp[j];
 }
 
 /*
@@ -1306,16 +1281,20 @@ static void rcutorture_loop_extend(int *readstate,
  */
 static bool rcu_torture_one_read(struct torture_random_state *trsp)
 {
+	int i;
 	unsigned long started;
 	unsigned long completed;
 	int newstate;
 	struct rcu_torture *p;
 	int pipe_count;
 	int readstate = 0;
+	struct rt_read_seg rtseg[RCUTORTURE_RDR_MAX_SEGS] = { { 0 } };
+	struct rt_read_seg *rtrsp = &rtseg[0];
+	struct rt_read_seg *rtrsp1;
 	unsigned long long ts;
 
 	newstate = rcutorture_extend_mask(readstate, trsp);
-	rcutorture_one_extend(&readstate, newstate, trsp);
+	rcutorture_one_extend(&readstate, newstate, trsp, rtrsp++);
 	started = cur_ops->get_gp_seq();
 	ts = rcu_trace_clock_local();
 	p = rcu_dereference_check(rcu_torture_current,
@@ -1325,12 +1304,12 @@ static bool rcu_torture_one_read(struct torture_random_state *trsp)
 				  torturing_tasks());
 	if (p == NULL) {
 		/* Wait for rcu_torture_writer to get underway */
-		rcutorture_one_extend(&readstate, 0, trsp);
+		rcutorture_one_extend(&readstate, 0, trsp, rtrsp);
 		return false;
 	}
 	if (p->rtort_mbtest == 0)
 		atomic_inc(&n_rcu_torture_mberror);
-	rcutorture_loop_extend(&readstate, trsp);
+	rtrsp = rcutorture_loop_extend(&readstate, trsp, rtrsp);
 	preempt_disable();
 	pipe_count = p->rtort_pipe_count;
 	if (pipe_count > RCU_TORTURE_PIPE_LEN) {
@@ -1351,8 +1330,17 @@ static bool rcu_torture_one_read(struct torture_random_state *trsp)
 	}
 	__this_cpu_inc(rcu_torture_batch[completed]);
 	preempt_enable();
-	rcutorture_one_extend(&readstate, 0, trsp);
+	rcutorture_one_extend(&readstate, 0, trsp, rtrsp);
 	WARN_ON_ONCE(readstate & RCUTORTURE_RDR_MASK);
+
+	/* If error or close call, record the sequence of reader protections. */
+	if ((pipe_count > 1 || completed > 1) && !xchg(&err_segs_recorded, 1)) {
+		i = 0;
+		for (rtrsp1 = &rtseg[0]; rtrsp1 < rtrsp; rtrsp1++)
+			err_segs[i++] = *rtrsp1;
+		rt_read_nsegs = i;
+	}
+
 	return true;
 }
 
@@ -1387,6 +1375,9 @@ static void rcu_torture_timer(struct timer_list *unused)
 static int
 rcu_torture_reader(void *arg)
 {
+	unsigned long lastsleep = jiffies;
+	long myid = (long)arg;
+	int mynumonline = myid;
 	DEFINE_TORTURE_RANDOM(rand);
 	struct timer_list t;
 
@@ -1402,6 +1393,12 @@ rcu_torture_reader(void *arg)
 		}
 		if (!rcu_torture_one_read(&rand))
 			schedule_timeout_interruptible(HZ);
+		if (time_after(jiffies, lastsleep)) {
+			schedule_timeout_interruptible(1);
+			lastsleep = jiffies + 10;
+		}
+		while (num_online_cpus() < mynumonline && !torture_must_stop())
+			schedule_timeout_interruptible(HZ / 5);
 		stutter_wait("rcu_torture_reader");
 	} while (!torture_must_stop());
 	if (irqreader && cur_ops->irq_capable) {
@@ -1655,6 +1652,121 @@ static int __init rcu_torture_stall_init(void)
 	return torture_create_kthread(rcu_torture_stall, NULL, stall_task);
 }
 
+/* State structure for forward-progress self-propagating RCU callback. */
+struct fwd_cb_state {
+	struct rcu_head rh;
+	int stop;
+};
+
+/*
+ * Forward-progress self-propagating RCU callback function.  Because
+ * callbacks run from softirq, this function is an implicit RCU read-side
+ * critical section.
+ */
+static void rcu_torture_fwd_prog_cb(struct rcu_head *rhp)
+{
+	struct fwd_cb_state *fcsp = container_of(rhp, struct fwd_cb_state, rh);
+
+	if (READ_ONCE(fcsp->stop)) {
+		WRITE_ONCE(fcsp->stop, 2);
+		return;
+	}
+	cur_ops->call(&fcsp->rh, rcu_torture_fwd_prog_cb);
+}
+
+/* Carry out grace-period forward-progress testing. */
+static int rcu_torture_fwd_prog(void *args)
+{
+	unsigned long cver;
+	unsigned long dur;
+	struct fwd_cb_state fcs;
+	unsigned long gps;
+	int idx;
+	int sd;
+	int sd4;
+	bool selfpropcb = false;
+	unsigned long stopat;
+	int tested = 0;
+	int tested_tries = 0;
+	static DEFINE_TORTURE_RANDOM(trs);
+
+	VERBOSE_TOROUT_STRING("rcu_torture_fwd_progress task started");
+	if (!IS_ENABLED(CONFIG_SMP) || !IS_ENABLED(CONFIG_RCU_BOOST))
+		set_user_nice(current, MAX_NICE);
+	if  (cur_ops->call && cur_ops->sync && cur_ops->cb_barrier) {
+		init_rcu_head_on_stack(&fcs.rh);
+		selfpropcb = true;
+	}
+	do {
+		schedule_timeout_interruptible(fwd_progress_holdoff * HZ);
+		if  (selfpropcb) {
+			WRITE_ONCE(fcs.stop, 0);
+			cur_ops->call(&fcs.rh, rcu_torture_fwd_prog_cb);
+		}
+		cver = READ_ONCE(rcu_torture_current_version);
+		gps = cur_ops->get_gp_seq();
+		sd = cur_ops->stall_dur() + 1;
+		sd4 = (sd + fwd_progress_div - 1) / fwd_progress_div;
+		dur = sd4 + torture_random(&trs) % (sd - sd4);
+		stopat = jiffies + dur;
+		while (time_before(jiffies, stopat) && !torture_must_stop()) {
+			idx = cur_ops->readlock();
+			udelay(10);
+			cur_ops->readunlock(idx);
+			if (!fwd_progress_need_resched || need_resched())
+				cond_resched();
+		}
+		tested_tries++;
+		if (!time_before(jiffies, stopat) && !torture_must_stop()) {
+			tested++;
+			cver = READ_ONCE(rcu_torture_current_version) - cver;
+			gps = rcutorture_seq_diff(cur_ops->get_gp_seq(), gps);
+			WARN_ON(!cver && gps < 2);
+			pr_alert("%s: Duration %ld cver %ld gps %ld\n", __func__, dur, cver, gps);
+		}
+		if (selfpropcb) {
+			WRITE_ONCE(fcs.stop, 1);
+			cur_ops->sync(); /* Wait for running CB to complete. */
+			cur_ops->cb_barrier(); /* Wait for queued callbacks. */
+		}
+		/* Avoid slow periods, better to test when busy. */
+		stutter_wait("rcu_torture_fwd_prog");
+	} while (!torture_must_stop());
+	if (selfpropcb) {
+		WARN_ON(READ_ONCE(fcs.stop) != 2);
+		destroy_rcu_head_on_stack(&fcs.rh);
+	}
+	/* Short runs might not contain a valid forward-progress attempt. */
+	WARN_ON(!tested && tested_tries >= 5);
+	pr_alert("%s: tested %d tested_tries %d\n", __func__, tested, tested_tries);
+	torture_kthread_stopping("rcu_torture_fwd_prog");
+	return 0;
+}
+
+/* If forward-progress checking is requested and feasible, spawn the thread. */
+static int __init rcu_torture_fwd_prog_init(void)
+{
+	if (!fwd_progress)
+		return 0; /* Not requested, so don't do it. */
+	if (!cur_ops->stall_dur || cur_ops->stall_dur() <= 0) {
+		VERBOSE_TOROUT_STRING("rcu_torture_fwd_prog_init: Disabled, unsupported by RCU flavor under test");
+		return 0;
+	}