Merge tag 'core-rcu-2021-04-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull RCU updates from Ingo Molnar:

 - Support for "N" as alias for last bit in bitmap parsing library (eg
   using syntax like "nohz_full=2-N")

 - kvfree_rcu updates

 - mm_dump_obj() updates. (One of these is to mm, but was suggested by
   Andrew Morton.)

 - RCU callback offloading update

 - Polling RCU grace-period interfaces

 - Realtime-related RCU updates

 - Tasks-RCU updates

 - Torture-test updates

 - Torture-test scripting updates

 - Miscellaneous fixes

* tag 'core-rcu-2021-04-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (77 commits)
  rcutorture: Test start_poll_synchronize_rcu() and poll_state_synchronize_rcu()
  rcu: Provide polling interfaces for Tiny RCU grace periods
  torture: Fix kvm.sh --datestamp regex check
  torture: Consolidate qemu-cmd duration editing into kvm-transform.sh
  torture: Print proper vmlinux path for kvm-again.sh runs
  torture: Make TORTURE_TRUST_MAKE available in kvm-again.sh environment
  torture: Make kvm-transform.sh update jitter commands
  torture: Add --duration argument to kvm-again.sh
  torture: Add kvm-again.sh to rerun a previous torture-test
  torture: Create a "batches" file for build reuse
  torture: De-capitalize TORTURE_SUITE
  torture: Make upper-case-only no-dot no-slash scenario names official
  torture: Rename SRCU-t and SRCU-u to avoid lowercase characters
  torture: Remove no-mpstat error message
  torture: Record kvm-test-1-run.sh and kvm-test-1-run-qemu.sh PIDs
  torture: Record jitter start/stop commands
  torture: Extract kvm-test-1-run-qemu.sh from kvm-test-1-run.sh
  torture: Record TORTURE_KCONFIG_GDB_ARG in qemu-cmd
  torture: Abstract jitter.sh start/stop into scripts
  rcu: Provide polling interfaces for Tree RCU grace periods
  ...

Documentation/RCU/RTFP.txt

@@ -847,7 +847,7 @@ Symposium on Distributed Computing}
 	'It's entirely possible that the current user could be replaced
 	by RCU and/or seqlocks, and we could get rid of brlocks entirely.'
 	.
-	Steve Hemminger responds by replacing them with RCU.
+	Stephen Hemminger responds by replacing them with RCU.
 }
 }
 

Documentation/admin-guide/kernel-parameters.rst

@@ -68,6 +68,13 @@ For example one can add to the command line following parameter:
 
 where the final item represents CPUs 100,101,125,126,150,151,...
 
+The value "N" can be used to represent the numerically last CPU on the system,
+i.e "foo_cpus=16-N" would be equivalent to "16-31" on a 32 core system.
+
+Keep in mind that "N" is dynamic, so if system changes cause the bitmap width
+to change, such as less cores in the CPU list, then N and any ranges using N
+will also change.  Use the same on a small 4 core system, and "16-N" becomes
+"16-3" and now the same boot input will be flagged as invalid (start > end).
 
 
 This document may not be entirely up to date and comprehensive. The command

Documentation/admin-guide/kernel-parameters.txt

@@ -4077,9 +4077,7 @@
 				see CONFIG_RAS_CEC help text.
 
 	rcu_nocbs=	[KNL]
-			The argument is a cpu list, as described above,
+			The argument is a cpu list, as described above.
-			except that the string "all" can be used to
-			specify every CPU on the system.
 
 			In kernels built with CONFIG_RCU_NOCB_CPU=y, set
 			the specified list of CPUs to be no-callback CPUs.
@@ -4268,6 +4266,18 @@
 	rcuscale.kfree_rcu_test= [KNL]
 			Set to measure performance of kfree_rcu() flooding.
 
+	rcuscale.kfree_rcu_test_double= [KNL]
+			Test the double-argument variant of kfree_rcu().
+			If this parameter has the same value as
+			rcuscale.kfree_rcu_test_single, both the single-
+			and double-argument variants are tested.
+
+	rcuscale.kfree_rcu_test_single= [KNL]
+			Test the single-argument variant of kfree_rcu().
+			If this parameter has the same value as
+			rcuscale.kfree_rcu_test_double, both the single-
+			and double-argument variants are tested.
+
 	rcuscale.kfree_nthreads= [KNL]
 			The number of threads running loops of kfree_rcu().
 

include/linux/mm.h

@@ -3180,7 +3180,11 @@ unsigned long wp_shared_mapping_range(struct address_space *mapping,
 
 extern int sysctl_nr_trim_pages;
 
+#ifdef CONFIG_PRINTK
 void mem_dump_obj(void *object);
+#else
+static inline void mem_dump_obj(void *object) {}
+#endif
 
 #endif /* __KERNEL__ */
 #endif /* _LINUX_MM_H */

include/linux/rcu_segcblist.h

@@ -109,7 +109,7 @@ struct rcu_cblist {
  *  |                           SEGCBLIST_KTHREAD_GP                           |
  *  |                                                                          |
  *  |   Kthreads handle callbacks holding nocb_lock, local rcu_core() stops    |
- *  |   handling callbacks.                                                    |
+ *  |   handling callbacks. Enable bypass queueing.                            |
  *  ----------------------------------------------------------------------------
  */
 
@@ -125,7 +125,7 @@ struct rcu_cblist {
  *  |                           SEGCBLIST_KTHREAD_GP                           |
  *  |                                                                          |
  *  |   CB/GP kthreads handle callbacks holding nocb_lock, local rcu_core()    |
- *  |   ignores callbacks.                                                     |
+ *  |   ignores callbacks. Bypass enqueue is enabled.                          |
  *  ----------------------------------------------------------------------------
  *                                      |
  *                                      v
@@ -134,7 +134,8 @@ struct rcu_cblist {
  *  |                           SEGCBLIST_KTHREAD_GP                           |
  *  |                                                                          |
  *  |   CB/GP kthreads and local rcu_core() handle callbacks concurrently      |
- *  |   holding nocb_lock. Wake up CB and GP kthreads if necessary.            |
+ *  |   holding nocb_lock. Wake up CB and GP kthreads if necessary. Disable    |
+ *  |   bypass enqueue.                                                        |
  *  ----------------------------------------------------------------------------
  *                                      |
  *                                      v

include/linux/rculist_nulls.h

@@ -161,7 +161,7 @@ static inline void hlist_nulls_add_fake(struct hlist_nulls_node *n)
  *
  * The barrier() is needed to make sure compiler doesn't cache first element [1],
  * as this loop can be restarted [2]
- * [1] Documentation/core-api/atomic_ops.rst around line 114
+ * [1] Documentation/memory-barriers.txt around line 1533
  * [2] Documentation/RCU/rculist_nulls.rst around line 146
  */
 #define hlist_nulls_for_each_entry_rcu(tpos, pos, head, member)			\

include/linux/rcupdate.h

@@ -882,7 +882,7 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
  * The BUILD_BUG_ON check must not involve any function calls, hence the
  * checks are done in macros here.
  */
-#define kfree_rcu kvfree_rcu
+#define kfree_rcu(ptr, rhf...) kvfree_rcu(ptr, ## rhf)
 
 /**
  * kvfree_rcu() - kvfree an object after a grace period.

include/linux/rcutiny.h

@@ -17,10 +17,9 @@
 /* Never flag non-existent other CPUs! */
 static inline bool rcu_eqs_special_set(int cpu) { return false; }
 
-static inline unsigned long get_state_synchronize_rcu(void)
+unsigned long get_state_synchronize_rcu(void);
-{
+unsigned long start_poll_synchronize_rcu(void);
-	return 0;
+bool poll_state_synchronize_rcu(unsigned long oldstate);
-}
 
 static inline void cond_synchronize_rcu(unsigned long oldstate)
 {

include/linux/rcutree.h

@@ -41,6 +41,8 @@ void rcu_momentary_dyntick_idle(void);
 void kfree_rcu_scheduler_running(void);
 bool rcu_gp_might_be_stalled(void);
 unsigned long get_state_synchronize_rcu(void);
+unsigned long start_poll_synchronize_rcu(void);
+bool poll_state_synchronize_rcu(unsigned long oldstate);
 void cond_synchronize_rcu(unsigned long oldstate);
 
 void rcu_idle_enter(void);

include/linux/slab.h

@@ -186,8 +186,10 @@ void kfree(const void *);
 void kfree_sensitive(const void *);
 size_t __ksize(const void *);
 size_t ksize(const void *);
+#ifdef CONFIG_PRINTK
 bool kmem_valid_obj(void *object);
 void kmem_dump_obj(void *object);
+#endif
 
 #ifdef CONFIG_HAVE_HARDENED_USERCOPY_ALLOCATOR
 void __check_heap_object(const void *ptr, unsigned long n, struct page *page,

include/linux/vmalloc.h

@@ -241,7 +241,7 @@ pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms)
 int register_vmap_purge_notifier(struct notifier_block *nb);
 int unregister_vmap_purge_notifier(struct notifier_block *nb);
 
-#ifdef CONFIG_MMU
+#if defined(CONFIG_MMU) && defined(CONFIG_PRINTK)
 bool vmalloc_dump_obj(void *object);
 #else
 static inline bool vmalloc_dump_obj(void *object) { return false; }

include/trace/events/rcu.h

@@ -432,6 +432,34 @@ TRACE_EVENT_RCU(rcu_fqs,
 		  __entry->cpu, __entry->qsevent)
 );
 
+/*
+ * Tracepoint for RCU stall events. Takes a string identifying the RCU flavor
+ * and a string identifying which function detected the RCU stall as follows:
+ *
+ *	"StallDetected": Scheduler-tick detects other CPU's stalls.
+ *	"SelfDetected": Scheduler-tick detects a current CPU's stall.
+ *	"ExpeditedStall": Expedited grace period detects stalls.
+ */
+TRACE_EVENT(rcu_stall_warning,
+
+	TP_PROTO(const char *rcuname, const char *msg),
+
+	TP_ARGS(rcuname, msg),
+
+	TP_STRUCT__entry(
+		__field(const char *, rcuname)
+		__field(const char *, msg)
+	),
+
+	TP_fast_assign(
+		__entry->rcuname = rcuname;
+		__entry->msg = msg;
+	),
+
+	TP_printk("%s %s",
+		  __entry->rcuname, __entry->msg)
+);
+
 #endif /* #if defined(CONFIG_TREE_RCU) */
 
 /*

kernel/rcu/rcu_segcblist.c

@@ -261,8 +261,7 @@ void rcu_segcblist_disable(struct rcu_segcblist *rsclp)
 }
 
 /*
- * Mark the specified rcu_segcblist structure as offloaded.  This
+ * Mark the specified rcu_segcblist structure as offloaded.
- * structure must be empty.
  */
 void rcu_segcblist_offload(struct rcu_segcblist *rsclp, bool offload)
 {

kernel/rcu/rcuscale.c

@@ -625,6 +625,8 @@ rcu_scale_shutdown(void *arg)
 torture_param(int, kfree_nthreads, -1, "Number of threads running loops of kfree_rcu().");
 torture_param(int, kfree_alloc_num, 8000, "Number of allocations and frees done in an iteration.");
 torture_param(int, kfree_loops, 10, "Number of loops doing kfree_alloc_num allocations and frees.");
+torture_param(bool, kfree_rcu_test_double, false, "Do we run a kfree_rcu() double-argument scale test?");
+torture_param(bool, kfree_rcu_test_single, false, "Do we run a kfree_rcu() single-argument scale test?");
 
 static struct task_struct **kfree_reader_tasks;
 static int kfree_nrealthreads;
@@ -644,10 +646,13 @@ kfree_scale_thread(void *arg)
 	struct kfree_obj *alloc_ptr;
 	u64 start_time, end_time;
 	long long mem_begin, mem_during = 0;
+	bool kfree_rcu_test_both;
+	DEFINE_TORTURE_RANDOM(tr);
 
 	VERBOSE_SCALEOUT_STRING("kfree_scale_thread task started");
 	set_cpus_allowed_ptr(current, cpumask_of(me % nr_cpu_ids));
 	set_user_nice(current, MAX_NICE);
+	kfree_rcu_test_both = (kfree_rcu_test_single == kfree_rcu_test_double);
 
 	start_time = ktime_get_mono_fast_ns();
 
@@ -670,7 +675,15 @@ kfree_scale_thread(void *arg)
 			if (!alloc_ptr)
 				return -ENOMEM;
 
-			kfree_rcu(alloc_ptr, rh);
+			// By default kfree_rcu_test_single and kfree_rcu_test_double are
+			// initialized to false. If both have the same value (false or true)
+			// both are randomly tested, otherwise only the one with value true
+			// is tested.
+			if ((kfree_rcu_test_single && !kfree_rcu_test_double) ||
+					(kfree_rcu_test_both && torture_random(&tr) & 0x800))
+				kfree_rcu(alloc_ptr);
+			else
+				kfree_rcu(alloc_ptr, rh);
 		}
 
 		cond_resched();

kernel/rcu/rcutorture.c

@@ -245,11 +245,11 @@ static const char *rcu_torture_writer_state_getname(void)
 	return rcu_torture_writer_state_names[i];
 }
 
-#if defined(CONFIG_RCU_BOOST) && !defined(CONFIG_HOTPLUG_CPU)
+#if defined(CONFIG_RCU_BOOST) && defined(CONFIG_PREEMPT_RT)
-#define rcu_can_boost() 1
+# define rcu_can_boost() 1
-#else /* #if defined(CONFIG_RCU_BOOST) && !defined(CONFIG_HOTPLUG_CPU) */
+#else
-#define rcu_can_boost() 0
+# define rcu_can_boost() 0
-#endif /* #else #if defined(CONFIG_RCU_BOOST) && !defined(CONFIG_HOTPLUG_CPU) */
+#endif
 
 #ifdef CONFIG_RCU_TRACE
 static u64 notrace rcu_trace_clock_local(void)
@@ -494,6 +494,8 @@ static struct rcu_torture_ops rcu_ops = {
 	.sync		= synchronize_rcu,
 	.exp_sync	= synchronize_rcu_expedited,
 	.get_gp_state	= get_state_synchronize_rcu,
+	.start_gp_poll	= start_poll_synchronize_rcu,
+	.poll_gp_state	= poll_state_synchronize_rcu,
 	.cond_sync	= cond_synchronize_rcu,
 	.call		= call_rcu,
 	.cb_barrier	= rcu_barrier,
@@ -923,9 +925,13 @@ static void rcu_torture_enable_rt_throttle(void)
 
 static bool rcu_torture_boost_failed(unsigned long start, unsigned long end)
 {
+	static int dbg_done;
+
 	if (end - start > test_boost_duration * HZ - HZ / 2) {
 		VERBOSE_TOROUT_STRING("rcu_torture_boost boosting failed");
 		n_rcu_torture_boost_failure++;
+		if (!xchg(&dbg_done, 1) && cur_ops->gp_kthread_dbg)
+			cur_ops->gp_kthread_dbg();
 
 		return true; /* failed */
 	}
@@ -948,8 +954,8 @@ static int rcu_torture_boost(void *arg)
 	init_rcu_head_on_stack(&rbi.rcu);
 	/* Each pass through the following loop does one boost-test cycle. */
 	do {
-		/* Track if the test failed already in this test interval? */
+		bool failed = false; // Test failed already in this test interval
-		bool failed = false;
+		bool firsttime = true;
 
 		/* Increment n_rcu_torture_boosts once per boost-test */
 		while (!kthread_should_stop()) {
@@ -975,18 +981,17 @@ static int rcu_torture_boost(void *arg)
 
 		/* Do one boost-test interval. */
 		endtime = oldstarttime + test_boost_duration * HZ;
-		call_rcu_time = jiffies;
 		while (time_before(jiffies, endtime)) {
 			/* If we don't have a callback in flight, post one. */
 			if (!smp_load_acquire(&rbi.inflight)) {
 				/* RCU core before ->inflight = 1. */
 				smp_store_release(&rbi.inflight, 1);
-				call_rcu(&rbi.rcu, rcu_torture_boost_cb);
+				cur_ops->call(&rbi.rcu, rcu_torture_boost_cb);
 				/* Check if the boost test failed */
-				failed = failed ||
+				if (!firsttime && !failed)
-					 rcu_torture_boost_failed(call_rcu_time,
+					failed = rcu_torture_boost_failed(call_rcu_time, jiffies);
-								 jiffies);
 				call_rcu_time = jiffies;
+				firsttime = false;
 			}
 			if (stutter_wait("rcu_torture_boost"))
 				sched_set_fifo_low(current);
@@ -999,7 +1004,7 @@ static int rcu_torture_boost(void *arg)
 		 * this case the boost check would never happen in the above
 		 * loop so do another one here.
 		 */
-		if (!failed && smp_load_acquire(&rbi.inflight))
+		if (!firsttime && !failed && smp_load_acquire(&rbi.inflight))
 			rcu_torture_boost_failed(call_rcu_time, jiffies);
 
 		/*
@@ -1025,6 +1030,9 @@ checkwait:	if (stutter_wait("rcu_torture_boost"))
 			sched_set_fifo_low(current);
 	} while (!torture_must_stop());
 
+	while (smp_load_acquire(&rbi.inflight))
+		schedule_timeout_uninterruptible(1); // rcu_barrier() deadlocks.
+
 	/* Clean up and exit. */
 	while (!kthread_should_stop() || smp_load_acquire(&rbi.inflight)) {
 		torture_shutdown_absorb("rcu_torture_boost");
@@ -1223,14 +1231,6 @@ rcu_torture_writer(void *arg)
 				WARN_ON_ONCE(1);
 				break;
 			}
-			if (cur_ops->get_gp_state && cur_ops->poll_gp_state)
-				WARN_ONCE(rcu_torture_writer_state != RTWS_DEF_FREE &&
-					  !cur_ops->poll_gp_state(cookie),
-					  "%s: Cookie check 2 failed %s(%d) %lu->%lu\n",
-					  __func__,
-					  rcu_torture_writer_state_getname(),
-					  rcu_torture_writer_state,
-					  cookie, cur_ops->get_gp_state());
 		}
 		WRITE_ONCE(rcu_torture_current_version,
 			   rcu_torture_current_version + 1);
@@ -1589,7 +1589,7 @@ static bool rcu_torture_one_read(struct torture_random_state *trsp, long myid)
 	preempt_enable();
 	if (cur_ops->get_gp_state && cur_ops->poll_gp_state)
 		WARN_ONCE(cur_ops->poll_gp_state(cookie),
-			  "%s: Cookie check 3 failed %s(%d) %lu->%lu\n",
+			  "%s: Cookie check 2 failed %s(%d) %lu->%lu\n",
 			  __func__,
 			  rcu_torture_writer_state_getname(),
 			  rcu_torture_writer_state,
@@ -1797,7 +1797,7 @@ rcu_torture_stats_print(void)
 		WARN_ON_ONCE(n_rcu_torture_barrier_error);  // rcu_barrier()
 		WARN_ON_ONCE(n_rcu_torture_boost_ktrerror); // no boost kthread
 		WARN_ON_ONCE(n_rcu_torture_boost_rterror); // can't set RT prio
-		WARN_ON_ONCE(n_rcu_torture_boost_failure); // RCU boost failed
+		WARN_ON_ONCE(n_rcu_torture_boost_failure); // boost failed (TIMER_SOFTIRQ RT prio?)
 		WARN_ON_ONCE(i > 1); // Too-short grace period
 	}
 	pr_cont("Reader Pipe: ");
@@ -1861,6 +1861,45 @@ rcu_torture_stats(void *arg)
 		torture_shutdown_absorb("rcu_torture_stats");
 	} while (!torture_must_stop());
 	torture_kthread_stopping("rcu_torture_stats");
+
+	{
+		struct rcu_head *rhp;
+		struct kmem_cache *kcp;
+		static int z;
+
+		kcp = kmem_cache_create("rcuscale", 136, 8, SLAB_STORE_USER, NULL);
+		rhp = kmem_cache_alloc(kcp, GFP_KERNEL);
+		pr_alert("mem_dump_obj() slab test: rcu_torture_stats = %px, &rhp = %px, rhp = %px, &z = %px\n", stats_task, &rhp, rhp, &z);
+		pr_alert("mem_dump_obj(ZERO_SIZE_PTR):");
+		mem_dump_obj(ZERO_SIZE_PTR);
+		pr_alert("mem_dump_obj(NULL):");
+		mem_dump_obj(NULL);
+		pr_alert("mem_dump_obj(%px):", &rhp);
+		mem_dump_obj(&rhp);
+		pr_alert("mem_dump_obj(%px):", rhp);
+		mem_dump_obj(rhp);
+		pr_alert("mem_dump_obj(%px):", &rhp->func);
+		mem_dump_obj(&rhp->func);
+		pr_alert("mem_dump_obj(%px):", &z);
+		mem_dump_obj(&z);
+		kmem_cache_free(kcp, rhp);
+		kmem_cache_destroy(kcp);
+		rhp = kmalloc(sizeof(*rhp), GFP_KERNEL);
+		pr_alert("mem_dump_obj() kmalloc test: rcu_torture_stats = %px, &rhp = %px, rhp = %px\n", stats_task, &rhp, rhp);
+		pr_alert("mem_dump_obj(kmalloc %px):", rhp);
+		mem_dump_obj(rhp);
+		pr_alert("mem_dump_obj(kmalloc %px):", &rhp->func);
+		mem_dump_obj(&rhp->func);
+		kfree(rhp);
+		rhp = vmalloc(4096);
+		pr_alert("mem_dump_obj() vmalloc test: rcu_torture_stats = %px, &rhp = %px, rhp = %px\n", stats_task, &rhp, rhp);
+		pr_alert("mem_dump_obj(vmalloc %px):", rhp);
+		mem_dump_obj(rhp);
+		pr_alert("mem_dump_obj(vmalloc %px):", &rhp->func);
+		mem_dump_obj(&rhp->func);
+		vfree(rhp);
+	}
+
 	return 0;
 }
 
@@ -1971,8 +2010,8 @@ static int rcu_torture_stall(void *args)
 			local_irq_disable();
 		else if (!stall_cpu_block)
 			preempt_disable();
-		pr_alert("rcu_torture_stall start on CPU %d.\n",
+		pr_alert("%s start on CPU %d.\n",
-			 raw_smp_processor_id());
+			  __func__, raw_smp_processor_id());
 		while (ULONG_CMP_LT((unsigned long)ktime_get_seconds(),
 				    stop_at))
 			if (stall_cpu_block)
@@ -1983,7 +2022,7 @@ static int rcu_torture_stall(void *args)
 			preempt_enable();
 		cur_ops->readunlock(idx);
 	}
-	pr_alert("rcu_torture_stall end.\n");
+	pr_alert("%s end.\n", __func__);
 	torture_shutdown_absorb("rcu_torture_stall");
 	while (!kthread_should_stop())
 		schedule_timeout_interruptible(10 * HZ);
@@ -2595,6 +2634,8 @@ static bool rcu_torture_can_boost(void)
 
 	if (!(test_boost == 1 && cur_ops->can_boost) && test_boost != 2)
 		return false;
+	if (!cur_ops->call)
+		return false;
 
 	prio = rcu_get_gp_kthreads_prio();
 	if (!prio)

kernel/rcu/tasks.h

@@ -20,7 +20,7 @@ typedef void (*holdouts_func_t)(struct list_head *hop, bool ndrpt, bool *frptp);
 typedef void (*postgp_func_t)(struct rcu_tasks *rtp);
 
 /**
- * Definition for a Tasks-RCU-like mechanism.
+ * struct rcu_tasks - Definition for a Tasks-RCU-like mechanism.
  * @cbs_head: Head of callback list.
  * @cbs_tail: Tail pointer for callback list.
  * @cbs_wq: Wait queue allowning new callback to get kthread's attention.
@@ -38,7 +38,7 @@ typedef void (*postgp_func_t)(struct rcu_tasks *rtp);
  * @pregp_func: This flavor's pre-grace-period function (optional).
  * @pertask_func: This flavor's per-task scan function (optional).
  * @postscan_func: This flavor's post-task scan function (optional).
- * @holdout_func: This flavor's holdout-list scan function (optional).
+ * @holdouts_func: This flavor's holdout-list scan function (optional).
  * @postgp_func: This flavor's post-grace-period function (optional).
  * @call_func: This flavor's call_rcu()-equivalent function.
  * @name: This flavor's textual name.
@@ -726,6 +726,42 @@ EXPORT_SYMBOL_GPL(show_rcu_tasks_rude_gp_kthread);
 // flavors, rcu_preempt and rcu_sched.  The fact that RCU Tasks Trace
 // readers can operate from idle, offline, and exception entry/exit in no
 // way allows rcu_preempt and rcu_sched readers to also do so.
+//
+// The implementation uses rcu_tasks_wait_gp(), which relies on function
+// pointers in the rcu_tasks structure.  The rcu_spawn_tasks_trace_kthread()
+// function sets these function pointers up so that rcu_tasks_wait_gp()
+// invokes these functions in this order:
+//
+// rcu_tasks_trace_pregp_step():
+//	Initialize the count of readers and block CPU-hotplug operations.
+// rcu_tasks_trace_pertask(), invoked on every non-idle task:
+//	Initialize per-task state and attempt to identify an immediate
+//	quiescent state for that task, or, failing that, attempt to
+//	set that task's .need_qs flag so that task's next outermost
+//	rcu_read_unlock_trace() will report the quiescent state (in which
+//	case the count of readers is incremented).  If both attempts fail,
+//	the task is added to a "holdout" list.
+// rcu_tasks_trace_postscan():
+//	Initialize state and attempt to identify an immediate quiescent
+//	state as above (but only for idle tasks), unblock CPU-hotplug
+//	operations, and wait for an RCU grace period to avoid races with
+//	tasks that are in the process of exiting.
+// check_all_holdout_tasks_trace(), repeatedly until holdout list is empty:
+//	Scans the holdout list, attempting to identify a quiescent state
+//	for each task on the list.  If there is a quiescent state, the
+//	corresponding task is removed from the holdout list.
+// rcu_tasks_trace_postgp():
+//	Wait for the count of readers do drop to zero, reporting any stalls.
+//	Also execute full memory barriers to maintain ordering with code
+//	executing after the grace period.
+//
+// The exit_tasks_rcu_finish_trace() synchronizes with exiting tasks.
+//
+// Pre-grace-period update-side code is ordered before the grace
+// period via the ->cbs_lock and barriers in rcu_tasks_kthread().
+// Pre-grace-period read-side code is ordered before the grace period by
+// atomic_dec_and_test() of the count of readers (for IPIed readers) and by
+// scheduler context-switch ordering (for locked-down non-running readers).
 
 // The lockdep state must be outside of #ifdef to be useful.
 #ifdef CONFIG_DEBUG_LOCK_ALLOC

kernel/rcu/tiny.c

@@ -32,12 +32,14 @@ struct rcu_ctrlblk {
 	struct rcu_head *rcucblist;	/* List of pending callbacks (CBs). */
 	struct rcu_head **donetail;	/* ->next pointer of last "done" CB. */
 	struct rcu_head **curtail;	/* ->next pointer of last CB. */
+	unsigned long gp_seq;		/* Grace-period counter. */
 };
 
 /* Definition for rcupdate control block. */
 static struct rcu_ctrlblk rcu_ctrlblk = {
 	.donetail	= &rcu_ctrlblk.rcucblist,
 	.curtail	= &rcu_ctrlblk.rcucblist,
+	.gp_seq		= 0 - 300UL,
 };
 
 void rcu_barrier(void)
@@ -56,6 +58,7 @@ void rcu_qs(void)
 		rcu_ctrlblk.donetail = rcu_ctrlblk.curtail;
 		raise_softirq_irqoff(RCU_SOFTIRQ);
 	}
+	WRITE_ONCE(rcu_ctrlblk.gp_seq, rcu_ctrlblk.gp_seq + 1);
 	local_irq_restore(flags);
 }
 
@@ -177,6 +180,43 @@ void call_rcu(struct rcu_head *head, rcu_callback_t func)
 }
 EXPORT_SYMBOL_GPL(call_rcu);
 
+/*
+ * Return a grace-period-counter "cookie".  For more information,
+ * see the Tree RCU header comment.
+ */
+unsigned long get_state_synchronize_rcu(void)
+{
+	return READ_ONCE(rcu_ctrlblk.gp_seq);
+}
+EXPORT_SYMBOL_GPL(get_state_synchronize_rcu);
+
+/*
+ * Return a grace-period-counter "cookie" and ensure that a future grace
+ * period completes.  For more information, see the Tree RCU header comment.
+ */
+unsigned long start_poll_synchronize_rcu(void)
+{
+	unsigned long gp_seq = get_state_synchronize_rcu();
+
+	if (unlikely(is_idle_task(current))) {
+		/* force scheduling for rcu_qs() */
+		resched_cpu(0);
+	}
+	return gp_seq;
+}
+EXPORT_SYMBOL_GPL(start_poll_synchronize_rcu);
+
+/*
+ * Return true if the grace period corresponding to oldstate has completed
+ * and false otherwise.  For more information, see the Tree RCU header
+ * comment.
+ */
+bool poll_state_synchronize_rcu(unsigned long oldstate)
+{
+	return READ_ONCE(rcu_ctrlblk.gp_seq) != oldstate;
+}
+EXPORT_SYMBOL_GPL(poll_state_synchronize_rcu);
+
 void __init rcu_init(void)
 {
 	open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);

kernel/rcu/tree.c

@@ -156,6 +156,7 @@ static void invoke_rcu_core(void);
 static void rcu_report_exp_rdp(struct rcu_data *rdp);
 static void sync_sched_exp_online_cleanup(int cpu);
 static void check_cb_ovld_locked(struct rcu_data *rdp, struct rcu_node *rnp);
+static bool rcu_rdp_is_offloaded(struct rcu_data *rdp);
 
 /* rcuc/rcub kthread realtime priority */
 static int kthread_prio = IS_ENABLED(CONFIG_RCU_BOOST) ? 1 : 0;
@@ -648,7 +649,6 @@ static noinstr void rcu_eqs_enter(bool user)
 	instrumentation_begin();
 	trace_rcu_dyntick(TPS("Start"), rdp->dynticks_nesting, 0, atomic_read(&rdp->dynticks));
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current));
-	rdp = this_cpu_ptr(&rcu_data);
 	rcu_prepare_for_idle();
 	rcu_preempt_deferred_qs(current);
 
@@ -1077,7 +1077,6 @@ noinstr void rcu_nmi_enter(void)
 	} else if (!in_nmi()) {
 		instrumentation_begin();
 		rcu_irq_enter_check_tick();
-		instrumentation_end();
 	} else  {
 		instrumentation_begin();
 	}
@@ -1672,7 +1671,7 @@ static bool __note_gp_changes(struct rcu_node *rnp, struct rcu_data *rdp)
 {
 	bool ret = false;
 	bool need_qs;
-	const bool offloaded = rcu_segcblist_is_offloaded(&rdp->cblist);
+	const bool offloaded = rcu_rdp_is_offloaded(rdp);
 
 	raw_lockdep_assert_held_rcu_node(rnp);
 
@@ -2128,7 +2127,7 @@ static void rcu_gp_cleanup(void)
 		needgp = true;
 	}
 	/* Advance CBs to reduce false positives below. */
-	offloaded = rcu_segcblist_is_offloaded(&rdp->cblist);
+	offloaded = rcu_rdp_is_offloaded(rdp);
 	if ((offloaded || !rcu_accelerate_cbs(rnp, rdp)) && needgp) {
 		WRITE_ONCE(rcu_state.gp_flags, RCU_GP_FLAG_INIT);
 		WRITE_ONCE(rcu_state.gp_req_activity, jiffies);
@@ -2327,7 +2326,7 @@ rcu_report_qs_rdp(struct rcu_data *rdp)
 	unsigned long flags;
 	unsigned long mask;
 	bool needwake = false;
-	const bool offloaded = rcu_segcblist_is_offloaded(&rdp->cblist);
+	const bool offloaded = rcu_rdp_is_offloaded(rdp);
 	struct rcu_node *rnp;
 
 	WARN_ON_ONCE(rdp->cpu != smp_processor_id());
@@ -2414,7 +2413,7 @@ int rcutree_dying_cpu(unsigned int cpu)
 
 	blkd = !!(rnp->qsmask & rdp->grpmask);
 	trace_rcu_grace_period(rcu_state.name, READ_ONCE(rnp->gp_seq),
-			       blkd ? TPS("cpuofl") : TPS("cpuofl-bgp"));
+			       blkd ? TPS("cpuofl-bgp") : TPS("cpuofl"));
 	return 0;
 }
 
@@ -2497,7 +2496,7 @@ static void rcu_do_batch(struct rcu_data *rdp)
 	int div;
 	bool __maybe_unused empty;
 	unsigned long flags;
-	const bool offloaded = rcu_segcblist_is_offloaded(&rdp->cblist);
+	const bool offloaded = rcu_rdp_is_offloaded(rdp);
 	struct rcu_head *rhp;
 	struct rcu_cblist rcl = RCU_CBLIST_INITIALIZER(rcl);
 	long bl, count = 0;
@@ -3066,7 +3065,7 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func)
 	trace_rcu_segcb_stats(&rdp->cblist, TPS("SegCBQueued"));
 
 	/* Go handle any RCU core processing required. */
-	if (unlikely(rcu_segcblist_is_offloaded(&rdp->cblist))) {
+	if (unlikely(rcu_rdp_is_offloaded(rdp))) {
 		__call_rcu_nocb_wake(rdp, was_alldone, flags); /* unlocks */
 	} else {
 		__call_rcu_core(rdp, head, flags);
@@ -3229,8 +3228,7 @@ krc_this_cpu_lock(unsigned long *flags)
 static inline void
 krc_this_cpu_unlock(struct kfree_rcu_cpu *krcp, unsigned long flags)
 {
-	raw_spin_unlock(&krcp->lock);
+	raw_spin_unlock_irqrestore(&krcp->lock, flags);
-	local_irq_restore(flags);
 }
 
 static inline struct kvfree_rcu_bulk_data *
@@ -3464,7 +3462,7 @@ static void fill_page_cache_func(struct work_struct *work)
 
 	for (i = 0; i < rcu_min_cached_objs; i++) {
 		bnode = (struct kvfree_rcu_bulk_data *)
-			__get_free_page(GFP_KERNEL | __GFP_NOWARN);
+			__get_free_page(GFP_KERNEL | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN);
 
 		if (bnode) {
 			raw_spin_lock_irqsave(&krcp->lock, flags);
@@ -3493,37 +3491,62 @@ run_page_cache_worker(struct kfree_rcu_cpu *krcp)
 	}
 }
 
+// Record ptr in a page managed by krcp, with the pre-krc_this_cpu_lock()
+// state specified by flags.  If can_alloc is true, the caller must
+// be schedulable and not be holding any locks or mutexes that might be
+// acquired by the memory allocator or anything that it might invoke.
+// Returns true if ptr was successfully recorded, else the caller must
+// use a fallback.
 static inline bool
-kvfree_call_rcu_add_ptr_to_bulk(struct kfree_rcu_cpu *krcp, void *ptr)
+add_ptr_to_bulk_krc_lock(struct kfree_rcu_cpu **krcp,
+	unsigned long *flags, void *ptr, bool can_alloc)
 {
 	struct kvfree_rcu_bulk_data *bnode;
 	int idx;
 
-	if (unlikely(!krcp->initialized))
+	*krcp = krc_this_cpu_lock(flags);
+	if (unlikely(!(*krcp)->initialized))
 		return false;
 
-	lockdep_assert_held(&krcp->lock);
 	idx = !!is_vmalloc_addr(ptr);
 
 	/* Check if a new block is required. */
-	if (!krcp->bkvhead[idx] ||
+	if (!(*krcp)->bkvhead[idx] ||
-			krcp->bkvhead[idx]->nr_records == KVFREE_BULK_MAX_ENTR) {
+			(*krcp)->bkvhead[idx]->nr_records == KVFREE_BULK_MAX_ENTR) {
-		bnode = get_cached_bnode(krcp);
+		bnode = get_cached_bnode(*krcp);
-		/* Switch to emergency path. */
+		if (!bnode && can_alloc) {
+			krc_this_cpu_unlock(*krcp, *flags);
+
+			// __GFP_NORETRY - allows a light-weight direct reclaim
+			// what is OK from minimizing of fallback hitting point of
+			// view. Apart of that it forbids any OOM invoking what is
+			// also beneficial since we are about to release memory soon.
+			//
+			// __GFP_NOMEMALLOC - prevents from consuming of all the
+			// memory reserves. Please note we have a fallback path.
+			//
+			// __GFP_NOWARN - it is supposed that an allocation can
+			// be failed under low memory or high memory pressure
+			// scenarios.
+			bnode = (struct kvfree_rcu_bulk_data *)
+				__get_free_page(GFP_KERNEL | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN);
+			*krcp = krc_this_cpu_lock(flags);
+		}
+
 		if (!bnode)
 			return false;
 
 		/* Initialize the new block. */
 		bnode->nr_records = 0;
-		bnode->next = krcp->bkvhead[idx];
+		bnode->next = (*krcp)->bkvhead[idx];
 
 		/* Attach it to the head. */
-		krcp->bkvhead[idx] = bnode;
+		(*krcp)->bkvhead[idx] = bnode;
 	}
 
 	/* Finally insert. */
-	krcp->bkvhead[idx]->records
+	(*krcp)->bkvhead[idx]->records
-		[krcp->bkvhead[idx]->nr_records++] = ptr;
+		[(*krcp)->bkvhead[idx]->nr_records++] = ptr;
 
 	return true;
 }
@@ -3561,8 +3584,6 @@ void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 		ptr = (unsigned long *) func;
 	}
 
-	krcp = krc_this_cpu_lock(&flags);
-
 	// Queue the object but don't yet schedule the batch.
 	if (debug_rcu_head_queue(ptr)) {
 		// Probable double kfree_rcu(), just leak.
@@ -3570,12 +3591,11 @@ void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 			  __func__, head);
 
 		// Mark as success and leave.
-		success = true;
+		return;
-		goto unlock_return;
 	}
 
 	kasan_record_aux_stack(ptr);
-	success = kvfree_call_rcu_add_ptr_to_bulk(krcp, ptr);
+	success = add_ptr_to_bulk_krc_lock(&krcp, &flags, ptr, !head);
 	if (!success) {
 		run_page_cache_worker(krcp);
 
@@ -3774,8 +3794,8 @@ EXPORT_SYMBOL_GPL(synchronize_rcu);
  * get_state_synchronize_rcu - Snapshot current RCU state
  *
  * Returns a cookie that is used by a later call to cond_synchronize_rcu()
- * to determine whether or not a full grace period has elapsed in the
+ * or poll_state_synchronize_rcu() to determine whether or not a full
- * meantime.
+ * grace period has elapsed in the meantime.
  */
 unsigned long get_state_synchronize_rcu(void)
 {
@@ -3788,14 +3808,77 @@ unsigned long get_state_synchronize_rcu(void)
 }
 EXPORT_SYMBOL_GPL(get_state_synchronize_rcu);
 
+/**
+ * start_poll_synchronize_rcu - Snapshot and start RCU grace period
+ *
+ * Returns a cookie that is used by a later call to cond_synchronize_rcu()
+ * or poll_state_synchronize_rcu() to determine whether or not a full
+ * grace period has elapsed in the meantime.  If the needed grace period
+ * is not already slated to start, notifies RCU core of the need for that
+ * grace period.
+ *
+ * Interrupts must be enabled for the case where it is necessary to awaken
+ * the grace-period kthread.
+ */
+unsigned long start_poll_synchronize_rcu(void)
+{
+	unsigned long flags;
+	unsigned long gp_seq = get_state_synchronize_rcu();
+	bool needwake;
+	struct rcu_data *rdp;
+	struct rcu_node *rnp;
+
+	lockdep_assert_irqs_enabled();
+	local_irq_save(flags);
+	rdp = this_cpu_ptr(&rcu_data);
+	rnp = rdp->mynode;
+	raw_spin_lock_rcu_node(rnp); // irqs already disabled.
+	needwake = rcu_start_this_gp(rnp, rdp, gp_seq);
+	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+	if (needwake)
+		rcu_gp_kthread_wake();
+	return gp_seq;
+}
+EXPORT_SYMBOL_GPL(start_poll_synchronize_rcu);
+
+/**
+ * poll_state_synchronize_rcu - Conditionally wait for an RCU grace period
+ *
+ * @oldstate: return from call to get_state_synchronize_rcu() or start_poll_synchronize_rcu()
+ *
+ * If a full RCU grace period has elapsed since the earlier call from
+ * which oldstate was obtained, return @true, otherwise return @false.
+ * If @false is returned, it is the caller's responsibilty to invoke this
+ * function later on until it does return @true.  Alternatively, the caller
+ * can explicitly wait for a grace period, for example, by passing @oldstate
+ * to cond_synchronize_rcu() or by directly invoking synchronize_rcu().
+ *
+ * Yes, this function does not take counter wrap into account.
+ * But counter wrap is harmless.  If the counter wraps, we have waited for
+ * more than 2 billion grace periods (and way more on a 64-bit system!).
+ * Those needing to keep oldstate values for very long time periods
+ * (many hours even on 32-bit systems) should check them occasionally
+ * and either refresh them or set a flag indicating that the grace period
+ * has completed.
+ */
+bool poll_state_synchronize_rcu(unsigned long oldstate)
+{
+	if (rcu_seq_done(&rcu_state.gp_seq, oldstate)) {
+		smp_mb(); /* Ensure GP ends before subsequent accesses. */
+		return true;
+	}
+	return false;
+}
+EXPORT_SYMBOL_GPL(poll_state_synchronize_rcu);
+
 /**
  * cond_synchronize_rcu - Conditionally wait for an RCU grace period
  *
  * @oldstate: return value from earlier call to get_state_synchronize_rcu()
  *
  * If a full RCU grace period has elapsed since the earlier call to
- * get_state_synchronize_rcu(), just return.  Otherwise, invoke
+ * get_state_synchronize_rcu() or start_poll_synchronize_rcu(), just return.
- * synchronize_rcu() to wait for a full grace period.
+ * Otherwise, invoke synchronize_rcu() to wait for a full grace period.
  *
  * Yes, this function does not take counter wrap into account.  But
  * counter wrap is harmless.  If the counter wraps, we have waited for
@@ -3804,10 +3887,8 @@ EXPORT_SYMBOL_GPL(get_state_synchronize_rcu);
  */
 void cond_synchronize_rcu(unsigned long oldstate)
 {
-	if (!rcu_seq_done(&rcu_state.gp_seq, oldstate))
+	if (!poll_state_synchronize_rcu(oldstate))
 		synchronize_rcu();
-	else
-		smp_mb(); /* Ensure GP ends before subsequent accesses. */
 }
 EXPORT_SYMBOL_GPL(cond_synchronize_rcu);
 
@@ -3843,13 +3924,13 @@ static int rcu_pending(int user)
 		return 1;
 
 	/* Does this CPU have callbacks ready to invoke? */
-	if (!rcu_segcblist_is_offloaded(&rdp->cblist) &&
+	if (!rcu_rdp_is_offloaded(rdp) &&
 	    rcu_segcblist_ready_cbs(&rdp->cblist))
 		return 1;
 
 	/* Has RCU gone idle with this CPU needing another grace period? */
 	if (!gp_in_progress && rcu_segcblist_is_enabled(&rdp->cblist) &&
-	    !rcu_segcblist_is_offloaded(&rdp->cblist) &&
+	    !rcu_rdp_is_offloaded(rdp) &&
 	    !rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL))
 		return 1;
 
@@ -3968,7 +4049,7 @@ void rcu_barrier(void)
 	for_each_possible_cpu(cpu) {
 		rdp = per_cpu_ptr(&rcu_data, cpu);
 		if (cpu_is_offline(cpu) &&
-		    !rcu_segcblist_is_offloaded(&rdp->cblist))
+		    !rcu_rdp_is_offloaded(rdp))
 			continue;
 		if (rcu_segcblist_n_cbs(&rdp->cblist) && cpu_online(cpu)) {
 			rcu_barrier_trace(TPS("OnlineQ"), cpu,
@@ -4083,15 +4164,13 @@ int rcutree_prepare_cpu(unsigned int cpu)
 	rdp->dynticks_nesting = 1;	/* CPU not up, no tearing. */
 	rcu_dynticks_eqs_online();
 	raw_spin_unlock_rcu_node(rnp);		/* irqs remain disabled. */
+
 	/*
-	 * Lock in case the CB/GP kthreads are still around handling
+	 * Only non-NOCB CPUs that didn't have early-boot callbacks need to be
-	 * old callbacks (longer term we should flush all callbacks
+	 * (re-)initialized.
-	 * before completing CPU offline)
 	 */
-	rcu_nocb_lock(rdp);
+	if (!rcu_segcblist_is_enabled(&rdp->cblist))
-	if (rcu_segcblist_empty(&rdp->cblist)) /* No early-boot CBs? */
 		rcu_segcblist_init(&rdp->cblist);  /* Re-enable callbacks. */
-	rcu_nocb_unlock(rdp);
 
 	/*
 	 * Add CPU to leaf rcu_node pending-online bitmask.  Any needed
@@ -4291,7 +4370,7 @@ void rcutree_migrate_callbacks(int cpu)
 	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
 	bool needwake;
 
-	if (rcu_segcblist_is_offloaded(&rdp->cblist) ||
+	if (rcu_rdp_is_offloaded(rdp) ||
 	    rcu_segcblist_empty(&rdp->cblist))
 		return;  /* No callbacks to migrate. */
 
@@ -4309,7 +4388,7 @@ void rcutree_migrate_callbacks(int cpu)
 	rcu_segcblist_disable(&rdp->cblist);
 	WARN_ON_ONCE(rcu_segcblist_empty(&my_rdp->cblist) !=
 		     !rcu_segcblist_n_cbs(&my_rdp->cblist));
-	if (rcu_segcblist_is_offloaded(&my_rdp->cblist)) {
+	if (rcu_rdp_is_offloaded(my_rdp)) {
 		raw_spin_unlock_rcu_node(my_rnp); /* irqs remain disabled. */
 		__call_rcu_nocb_wake(my_rdp, true, flags);
 	} else {

kernel/rcu/tree_exp.h

@@ -521,6 +521,7 @@ static void synchronize_rcu_expedited_wait(void)
 		if (rcu_stall_is_suppressed())
 			continue;
 		panic_on_rcu_stall();
+		trace_rcu_stall_warning(rcu_state.name, TPS("ExpeditedStall"));
 		pr_err("INFO: %s detected expedited stalls on CPUs/tasks: {",
 		       rcu_state.name);
 		ndetected = 0;

kernel/rcu/tree_plugin.h

@@ -16,8 +16,70 @@
 #ifdef CONFIG_RCU_NOCB_CPU
 static cpumask_var_t rcu_nocb_mask; /* CPUs to have callbacks offloaded. */
 static bool __read_mostly rcu_nocb_poll;    /* Offload kthread are to poll. */
+static inline int rcu_lockdep_is_held_nocb(struct rcu_data *rdp)
+{
+	return lockdep_is_held(&rdp->nocb_lock);
+}
+
+static inline bool rcu_current_is_nocb_kthread(struct rcu_data *rdp)
+{
+	/* Race on early boot between thread creation and assignment */
+	if (!rdp->nocb_cb_kthread || !rdp->nocb_gp_kthread)
+		return true;
+
+	if (current == rdp->nocb_cb_kthread || current == rdp->nocb_gp_kthread)
+		if (in_task())
+			return true;
+	return false;
+}
+
+static inline bool rcu_running_nocb_timer(struct rcu_data *rdp)
+{
+	return (timer_curr_running(&rdp->nocb_timer) && !in_irq());
+}
+#else
+static inline int rcu_lockdep_is_held_nocb(struct rcu_data *rdp)
+{
+	return 0;
+}
+
+static inline bool rcu_current_is_nocb_kthread(struct rcu_data *rdp)
+{
+	return false;
+}
+
+static inline bool rcu_running_nocb_timer(struct rcu_data *rdp)
+{
+	return false;
+}
+
 #endif /* #ifdef CONFIG_RCU_NOCB_CPU */
 
+static bool rcu_rdp_is_offloaded(struct rcu_data *rdp)
+{
+	/*
+	 * In order to read the offloaded state of an rdp is a safe
+	 * and stable way and prevent from its value to be changed
+	 * under us, we must either hold the barrier mutex, the cpu
+	 * hotplug lock (read or write) or the nocb lock. Local
+	 * non-preemptible reads are also safe. NOCB kthreads and
+	 * timers have their own means of synchronization against the
+	 * offloaded state updaters.
+	 */
+	RCU_LOCKDEP_WARN(
+		!(lockdep_is_held(&rcu_state.barrier_mutex) ||
+		  (IS_ENABLED(CONFIG_HOTPLUG_CPU) && lockdep_is_cpus_held()) ||
+		  rcu_lockdep_is_held_nocb(rdp) ||
+		  (rdp == this_cpu_ptr(&rcu_data) &&
+		   !(IS_ENABLED(CONFIG_PREEMPT_COUNT) && preemptible())) ||
+		  rcu_current_is_nocb_kthread(rdp) ||
+		  rcu_running_nocb_timer(rdp)),
+		"Unsafe read of RCU_NOCB offloaded state"
+	);
+
+	return rcu_segcblist_is_offloaded(&rdp->cblist);
+}
+
 /*
  * Check the RCU kernel configuration parameters and print informative
  * messages about anything out of the ordinary.
@@ -393,8 +455,9 @@ void __rcu_read_unlock(void)
 {
 	struct task_struct *t = current;
 
+	barrier();  // critical section before exit code.
 	if (rcu_preempt_read_exit() == 0) {
-		barrier();  /* critical section before exit code. */
+		barrier();  // critical-section exit before .s check.
 		if (unlikely(READ_ONCE(t->rcu_read_unlock_special.s)))
 			rcu_read_unlock_special(t);
 	}
@@ -598,9 +661,9 @@ static void rcu_preempt_deferred_qs_handler(struct irq_work *iwp)
 static void rcu_read_unlock_special(struct task_struct *t)
 {
 	unsigned long flags;
+	bool irqs_were_disabled;
 	bool preempt_bh_were_disabled =
 			!!(preempt_count() & (PREEMPT_MASK | SOFTIRQ_MASK));
-	bool irqs_were_disabled;
 
 	/* NMI handlers cannot block and cannot safely manipulate state. */
 	if (in_nmi())
@@ -609,30 +672,33 @@ static void rcu_read_unlock_special(struct task_struct *t)
 	local_irq_save(flags);
 	irqs_were_disabled = irqs_disabled_flags(flags);
 	if (preempt_bh_were_disabled || irqs_were_disabled) {
-		bool exp;
+		bool expboost; // Expedited GP in flight or possible boosting.
 		struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
 		struct rcu_node *rnp = rdp->mynode;
 
-		exp = (t->rcu_blocked_node &&
+		expboost = (t->rcu_blocked_node && READ_ONCE(t->rcu_blocked_node->exp_tasks)) ||
-		       READ_ONCE(t->rcu_blocked_node->exp_tasks)) ||
+			   (rdp->grpmask & READ_ONCE(rnp->expmask)) ||
-		      (rdp->grpmask & READ_ONCE(rnp->expmask));
+			   IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD) ||
+			   (IS_ENABLED(CONFIG_RCU_BOOST) && irqs_were_disabled &&
+			    t->rcu_blocked_node);
 		// Need to defer quiescent state until everything is enabled.
-		if (use_softirq && (in_irq() || (exp && !irqs_were_disabled))) {
+		if (use_softirq && (in_irq() || (expboost && !irqs_were_disabled))) {
 			// Using softirq, safe to awaken, and either the
-			// wakeup is free or there is an expedited GP.
+			// wakeup is free or there is either an expedited
+			// GP in flight or a potential need to deboost.
 			raise_softirq_irqoff(RCU_SOFTIRQ);
 		} else {
 			// Enabling BH or preempt does reschedule, so...
-			// Also if no expediting, slow is OK.
+			// Also if no expediting and no possible deboosting,
-			// Plus nohz_full CPUs eventually get tick enabled.
+			// slow is OK.  Plus nohz_full CPUs eventually get
+			// tick enabled.
 			set_tsk_need_resched(current);
 			set_preempt_need_resched();
 			if (IS_ENABLED(CONFIG_IRQ_WORK) && irqs_were_disabled &&
-			    !rdp->defer_qs_iw_pending && exp && cpu_online(rdp->cpu)) {
+			    expboost && !rdp->defer_qs_iw_pending && cpu_online(rdp->cpu)) {
 				// Get scheduler to re-evaluate and call hooks.
 				// If !IRQ_WORK, FQS scan will eventually IPI.
-				init_irq_work(&rdp->defer_qs_iw,
+				init_irq_work(&rdp->defer_qs_iw, rcu_preempt_deferred_qs_handler);
-					      rcu_preempt_deferred_qs_handler);
 				rdp->defer_qs_iw_pending = true;
 				irq_work_queue_on(&rdp->defer_qs_iw, rdp->cpu);
 			}
@@ -1257,7 +1323,7 @@ int rcu_needs_cpu(u64 basemono, u64 *nextevt)
 {
 	*nextevt = KTIME_MAX;
 	return !rcu_segcblist_empty(&this_cpu_ptr(&rcu_data)->cblist) &&
-	       !rcu_segcblist_is_offloaded(&this_cpu_ptr(&rcu_data)->cblist);
+		!rcu_rdp_is_offloaded(this_cpu_ptr(&rcu_data));
 }
 
 /*
@@ -1352,7 +1418,7 @@ int rcu_needs_cpu(u64 basemono, u64 *nextevt)
 
 	/* If no non-offloaded callbacks, RCU doesn't need the CPU. */
 	if (rcu_segcblist_empty(&rdp->cblist) ||
-	    rcu_segcblist_is_offloaded(&this_cpu_ptr(&rcu_data)->cblist)) {
+	    rcu_rdp_is_offloaded(rdp)) {
 		*nextevt = KTIME_MAX;
 		return 0;
 	}
@@ -1388,7 +1454,7 @@ static void rcu_prepare_for_idle(void)
 	int tne;
 
 	lockdep_assert_irqs_disabled();
-	if (rcu_segcblist_is_offloaded(&rdp->cblist))
+	if (rcu_rdp_is_offloaded(rdp))
 		return;
 
 	/* Handle nohz enablement switches conservatively. */
@@ -1429,7 +1495,7 @@ static void rcu_cleanup_after_idle(void)
 	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
 
 	lockdep_assert_irqs_disabled();
-	if (rcu_segcblist_is_offloaded(&rdp->cblist))
+	if (rcu_rdp_is_offloaded(rdp))
 		return;
 	if (rcu_try_advance_all_cbs())
 		invoke_rcu_core();
@@ -1464,14 +1530,12 @@ static void rcu_cleanup_after_idle(void)
 
 /*
  * Parse the boot-time rcu_nocb_mask CPU list from the kernel parameters.
- * The string after the "rcu_nocbs=" is either "all" for all CPUs, or a
+ * If the list is invalid, a warning is emitted and all CPUs are offloaded.
- * comma-separated list of CPUs and/or CPU ranges.  If an invalid list is
- * given, a warning is emitted and all CPUs are offloaded.
  */
 static int __init rcu_nocb_setup(char *str)
 {
 	alloc_bootmem_cpumask_var(&rcu_nocb_mask);
-	if (!strcasecmp(str, "all"))
+	if (!strcasecmp(str, "all"))		/* legacy: use "0-N" instead */
 		cpumask_setall(rcu_nocb_mask);
 	else
 		if (cpulist_parse(str, rcu_nocb_mask)) {
@@ -1494,7 +1558,7 @@ early_param("rcu_nocb_poll", parse_rcu_nocb_poll);
  * After all, the main point of bypassing is to avoid lock contention
  * on ->nocb_lock, which only can happen at high call_rcu() rates.
  */
-int nocb_nobypass_lim_per_jiffy = 16 * 1000 / HZ;
+static int nocb_nobypass_lim_per_jiffy = 16 * 1000 / HZ;
 module_param(nocb_nobypass_lim_per_jiffy, int, 0);
 
 /*
@@ -1560,7 +1624,7 @@ static void rcu_nocb_bypass_unlock(struct rcu_data *rdp)
 static void rcu_nocb_lock(struct rcu_data *rdp)
 {
 	lockdep_assert_irqs_disabled();
-	if (!rcu_segcblist_is_offloaded(&rdp->cblist))
+	if (!rcu_rdp_is_offloaded(rdp))
 		return;
 	raw_spin_lock(&rdp->nocb_lock);
 }
@@ -1571,7 +1635,7 @@ static void rcu_nocb_lock(struct rcu_data *rdp)
  */
 static void rcu_nocb_unlock(struct rcu_data *rdp)
 {
-	if (rcu_segcblist_is_offloaded(&rdp->cblist)) {
+	if (rcu_rdp_is_offloaded(rdp)) {
 		lockdep_assert_irqs_disabled();
 		raw_spin_unlock(&rdp->nocb_lock);
 	}
@@ -1584,7 +1648,7 @@ static void rcu_nocb_unlock(struct rcu_data *rdp)
 static void rcu_nocb_unlock_irqrestore(struct rcu_data *rdp,
 				       unsigned long flags)
 {
-	if (rcu_segcblist_is_offloaded(&rdp->cblist)) {
+	if (rcu_rdp_is_offloaded(rdp)) {
 		lockdep_assert_irqs_disabled();
 		raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags);
 	} else {
@@ -1596,7 +1660,7 @@ static void rcu_nocb_unlock_irqrestore(struct rcu_data *rdp,
 static void rcu_lockdep_assert_cblist_protected(struct rcu_data *rdp)
 {
 	lockdep_assert_irqs_disabled();
-	if (rcu_segcblist_is_offloaded(&rdp->cblist))
+	if (rcu_rdp_is_offloaded(rdp))
 		lockdep_assert_held(&rdp->nocb_lock);
 }
 
@@ -1641,12 +1705,16 @@ static bool wake_nocb_gp(struct rcu_data *rdp, bool force,
 
 	lockdep_assert_held(&rdp->nocb_lock);
 	if (!READ_ONCE(rdp_gp->nocb_gp_kthread)) {
+		rcu_nocb_unlock_irqrestore(rdp, flags);
 		trace_rcu_nocb_wake(rcu_state.name, rdp->cpu,
 				    TPS("AlreadyAwake"));
-		rcu_nocb_unlock_irqrestore(rdp, flags);
 		return false;
 	}
-	del_timer(&rdp->nocb_timer);
+
+	if (READ_ONCE(rdp->nocb_defer_wakeup) > RCU_NOCB_WAKE_NOT) {
+		WRITE_ONCE(rdp->nocb_defer_wakeup, RCU_NOCB_WAKE_NOT);
+		del_timer(&rdp->nocb_timer);
+	}
 	rcu_nocb_unlock_irqrestore(rdp, flags);
 	raw_spin_lock_irqsave(&rdp_gp->nocb_gp_lock, flags);
 	if (force || READ_ONCE(rdp_gp->nocb_gp_sleep)) {
@@ -1690,7 +1758,7 @@ static bool rcu_nocb_do_flush_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
 {
 	struct rcu_cblist rcl;
 
-	WARN_ON_ONCE(!rcu_segcblist_is_offloaded(&rdp->cblist));
+	WARN_ON_ONCE(!rcu_rdp_is_offloaded(rdp));
 	rcu_lockdep_assert_cblist_protected(rdp);
 	lockdep_assert_held(&rdp->nocb_bypass_lock);
 	if (rhp && !rcu_cblist_n_cbs(&rdp->nocb_bypass)) {
@@ -1718,7 +1786,7 @@ static bool rcu_nocb_do_flush_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
 static bool rcu_nocb_flush_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
 				  unsigned long j)
 {
-	if (!rcu_segcblist_is_offloaded(&rdp->cblist))
+	if (!rcu_rdp_is_offloaded(rdp))
 		return true;
 	rcu_lockdep_assert_cblist_protected(rdp);
 	rcu_nocb_bypass_lock(rdp);
@@ -1732,7 +1800,7 @@ static bool rcu_nocb_flush_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
 static void rcu_nocb_try_flush_bypass(struct rcu_data *rdp, unsigned long j)
 {
 	rcu_lockdep_assert_cblist_protected(rdp);
-	if (!rcu_segcblist_is_offloaded(&rdp->cblist) ||
+	if (!rcu_rdp_is_offloaded(rdp) ||
 	    !rcu_nocb_bypass_trylock(rdp))
 		return;
 	WARN_ON_ONCE(!rcu_nocb_do_flush_bypass(rdp, NULL, j));
@@ -1764,11 +1832,22 @@ static bool rcu_nocb_try_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
 	unsigned long j = jiffies;
 	long ncbs = rcu_cblist_n_cbs(&rdp->nocb_bypass);
 
-	if (!rcu_segcblist_is_offloaded(&rdp->cblist)) {
+	lockdep_assert_irqs_disabled();
+
+	// Pure softirq/rcuc based processing: no bypassing, no
+	// locking.
+	if (!rcu_rdp_is_offloaded(rdp)) {
+		*was_alldone = !rcu_segcblist_pend_cbs(&rdp->cblist);
+		return false;
+	}
+
+	// In the process of (de-)offloading: no bypassing, but
+	// locking.
+	if (!rcu_segcblist_completely_offloaded(&rdp->cblist)) {
+		rcu_nocb_lock(rdp);
 		*was_alldone = !rcu_segcblist_pend_cbs(&rdp->cblist);
 		return false; /* Not offloaded, no bypassing. */
 	}
-	lockdep_assert_irqs_disabled();
 
 	// Don't use ->nocb_bypass during early boot.
 	if (rcu_scheduler_active != RCU_SCHEDULER_RUNNING) {
@@ -1878,9 +1957,9 @@ static void __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_alldone,
 	// If we are being polled or there is no kthread, just leave.
 	t = READ_ONCE(rdp->nocb_gp_kthread);
 	if (rcu_nocb_poll || !t) {
+		rcu_nocb_unlock_irqrestore(rdp, flags);
 		trace_rcu_nocb_wake(rcu_state.name, rdp->cpu,
 				    TPS("WakeNotPoll"));
-		rcu_nocb_unlock_irqrestore(rdp, flags);
 		return;
 	}
 	// Need to actually to a wakeup.
@@ -1915,8 +1994,8 @@ static void __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_alldone,
 					   TPS("WakeOvfIsDeferred"));
 		rcu_nocb_unlock_irqrestore(rdp, flags);
 	} else {
-		trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("WakeNot"));
 		rcu_nocb_unlock_irqrestore(rdp, flags);
+		trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("WakeNot"));
 	}
 	return;
 }
@@ -1954,7 +2033,8 @@ static inline bool nocb_gp_enabled_cb(struct rcu_data *rdp)
 	return rcu_segcblist_test_flags(&rdp->cblist, flags);
 }
 
-static inline bool nocb_gp_update_state(struct rcu_data *rdp, bool *needwake_state)
+static inline bool nocb_gp_update_state_deoffloading(struct rcu_data *rdp,
+						     bool *needwake_state)
 {
 	struct rcu_segcblist *cblist = &rdp->cblist;
 
@@ -1964,7 +2044,7 @@ static inline bool nocb_gp_update_state(struct rcu_data *rdp, bool *needwake_sta
 			if (rcu_segcblist_test_flags(cblist, SEGCBLIST_KTHREAD_CB))
 				*needwake_state = true;
 		}
-		return true;
+		return false;
 	}
 
 	/*
@@ -1975,7 +2055,7 @@ static inline bool nocb_gp_update_state(struct rcu_data *rdp, bool *needwake_sta
 	rcu_segcblist_clear_flags(cblist, SEGCBLIST_KTHREAD_GP);
 	if (!rcu_segcblist_test_flags(cblist, SEGCBLIST_KTHREAD_CB))
 		*needwake_state = true;
-	return false;
+	return true;
 }
 
 
@@ -2013,7 +2093,7 @@ static void nocb_gp_wait(struct rcu_data *my_rdp)
 			continue;
 		trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("Check"));
 		rcu_nocb_lock_irqsave(rdp, flags);
-		if (!nocb_gp_update_state(rdp, &needwake_state)) {
+		if (nocb_gp_update_state_deoffloading(rdp, &needwake_state)) {
 			rcu_nocb_unlock_irqrestore(rdp, flags);
 			if (needwake_state)
 				swake_up_one(&rdp->nocb_state_wq);
@@ -2168,11 +2248,18 @@ static void nocb_cb_wait(struct rcu_data *rdp)
 	unsigned long flags;
 	bool needwake_state = false;
 	bool needwake_gp = false;
+	bool can_sleep = true;
 	struct rcu_node *rnp = rdp->mynode;
 
 	local_irq_save(flags);
 	rcu_momentary_dyntick_idle();
 	local_irq_restore(flags);
+	/*
+	 * Disable BH to provide the expected environment.  Also, when
+	 * transitioning to/from NOCB mode, a self-requeuing callback might
+	 * be invoked from softirq.  A short grace period could cause both
+	 * instances of this callback would execute concurrently.
+	 */
 	local_bh_disable();
 	rcu_do_batch(rdp);
 	local_bh_enable();
@@ -2185,8 +2272,6 @@ static void nocb_cb_wait(struct rcu_data *rdp)
 		raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */
 	}
 
-	WRITE_ONCE(rdp->nocb_cb_sleep, true);
-
 	if (rcu_segcblist_test_flags(cblist, SEGCBLIST_OFFLOADED)) {
 		if (!rcu_segcblist_test_flags(cblist, SEGCBLIST_KTHREAD_CB)) {
 			rcu_segcblist_set_flags(cblist, SEGCBLIST_KTHREAD_CB);
@@ -2194,7 +2279,7 @@ static void nocb_cb_wait(struct rcu_data *rdp)
 				needwake_state = true;
 		}
 		if (rcu_segcblist_ready_cbs(cblist))
-			WRITE_ONCE(rdp->nocb_cb_sleep, false);
+			can_sleep = false;
 	} else {
 		/*
 		 * De-offloading. Clear our flag and notify the de-offload worker.
@@ -2207,6 +2292,8 @@ static void nocb_cb_wait(struct rcu_data *rdp)
 			needwake_state = true;
 	}
 
+	WRITE_ONCE(rdp->nocb_cb_sleep, can_sleep);
+
 	if (rdp->nocb_cb_sleep)
 		trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("CBSleep"));
 
@@ -2265,7 +2352,6 @@ static bool do_nocb_deferred_wakeup_common(struct rcu_data *rdp)
 		return false;
 	}
 	ndw = READ_ONCE(rdp->nocb_defer_wakeup);
-	WRITE_ONCE(rdp->nocb_defer_wakeup, RCU_NOCB_WAKE_NOT);
 	ret = wake_nocb_gp(rdp, ndw == RCU_NOCB_WAKE_FORCE, flags);
 	trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("DeferredWake"));
 
@@ -2331,24 +2417,28 @@ static int rdp_offload_toggle(struct rcu_data *rdp,
 	return 0;
 }
 
-static int __rcu_nocb_rdp_deoffload(struct rcu_data *rdp)
+static long rcu_nocb_rdp_deoffload(void *arg)
 {
+	struct rcu_data *rdp = arg;
 	struct rcu_segcblist *cblist = &rdp->cblist;
 	unsigned long flags;
 	int ret;
 
+	WARN_ON_ONCE(rdp->cpu != raw_smp_processor_id());
+
 	pr_info("De-offloading %d\n", rdp->cpu);
 
 	rcu_nocb_lock_irqsave(rdp, flags);
 	/*
-	 * If there are still pending work offloaded, the offline
+	 * Flush once and for all now. This suffices because we are
-	 * CPU won't help much handling them.
+	 * running on the target CPU holding ->nocb_lock (thus having
+	 * interrupts disabled), and because rdp_offload_toggle()
+	 * invokes rcu_segcblist_offload(), which clears SEGCBLIST_OFFLOADED.
+	 * Thus future calls to rcu_segcblist_completely_offloaded() will
+	 * return false, which means that future calls to rcu_nocb_try_bypass()
+	 * will refuse to put anything into the bypass.
 	 */
-	if (cpu_is_offline(rdp->cpu) && !rcu_segcblist_empty(&rdp->cblist)) {
+	WARN_ON_ONCE(!rcu_nocb_flush_bypass(rdp, NULL, jiffies));
-		rcu_nocb_unlock_irqrestore(rdp, flags);
-		return -EBUSY;
-	}
-
 	ret = rdp_offload_toggle(rdp, false, flags);
 	swait_event_exclusive(rdp->nocb_state_wq,
 			      !rcu_segcblist_test_flags(cblist, SEGCBLIST_KTHREAD_CB |
@@ -2360,32 +2450,24 @@ static int __rcu_nocb_rdp_deoffload(struct rcu_data *rdp)
 	del_timer_sync(&rdp->nocb_timer);
 
 	/*
-	 * Flush bypass. While IRQs are disabled and once we set
+	 * Theoretically we could set SEGCBLIST_SOFTIRQ_ONLY with CB unlocked
-	 * SEGCBLIST_SOFTIRQ_ONLY, no callback is supposed to be
+	 * and IRQs disabled but let's be paranoid.
-	 * enqueued on bypass.
 	 */
 	rcu_nocb_lock_irqsave(rdp, flags);
-	rcu_nocb_flush_bypass(rdp, NULL, jiffies);
 	rcu_segcblist_set_flags(cblist, SEGCBLIST_SOFTIRQ_ONLY);
 	/*
 	 * With SEGCBLIST_SOFTIRQ_ONLY, we can't use
-	 * rcu_nocb_unlock_irqrestore() anymore. Theoretically we
+	 * rcu_nocb_unlock_irqrestore() anymore.
-	 * could set SEGCBLIST_SOFTIRQ_ONLY with cb unlocked and IRQs
-	 * disabled now, but let's be paranoid.
 	 */
 	raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags);
 
+	/* Sanity check */
+	WARN_ON_ONCE(rcu_cblist_n_cbs(&rdp->nocb_bypass));
+
+
 	return ret;
 }
 
-static long rcu_nocb_rdp_deoffload(void *arg)
-{
-	struct rcu_data *rdp = arg;
-
-	WARN_ON_ONCE(rdp->cpu != raw_smp_processor_id());
-	return __rcu_nocb_rdp_deoffload(rdp);
-}
-
 int rcu_nocb_cpu_deoffload(int cpu)
 {
 	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
@@ -2397,13 +2479,15 @@ int rcu_nocb_cpu_deoffload(int cpu)
 	}
 	mutex_lock(&rcu_state.barrier_mutex);
 	cpus_read_lock();
-	if (rcu_segcblist_is_offloaded(&rdp->cblist)) {
+	if (rcu_rdp_is_offloaded(rdp)) {
-		if (cpu_online(cpu))
+		if (cpu_online(cpu)) {
 			ret = work_on_cpu(cpu, rcu_nocb_rdp_deoffload, rdp);
-		else
+			if (!ret)
-			ret = __rcu_nocb_rdp_deoffload(rdp);
+				cpumask_clear_cpu(cpu, rcu_nocb_mask);
-		if (!ret)
+		} else {
-			cpumask_clear_cpu(cpu, rcu_nocb_mask);
+			pr_info("NOCB: Can't CB-deoffload an offline CPU\n");
+			ret = -EINVAL;
+		}
 	}
 	cpus_read_unlock();
 	mutex_unlock(&rcu_state.barrier_mutex);
@@ -2412,12 +2496,14 @@ int rcu_nocb_cpu_deoffload(int cpu)
 }
 EXPORT_SYMBOL_GPL(rcu_nocb_cpu_deoffload);
 
-static int __rcu_nocb_rdp_offload(struct rcu_data *rdp)
+static long rcu_nocb_rdp_offload(void *arg)
 {
+	struct rcu_data *rdp = arg;
 	struct rcu_segcblist *cblist = &rdp->cblist;
 	unsigned long flags;
 	int ret;
 
+	WARN_ON_ONCE(rdp->cpu != raw_smp_processor_id());
 	/*
 	 * For now we only support re-offload, ie: the rdp must have been
 	 * offloaded on boot first.
@@ -2457,14 +2543,6 @@ static int __rcu_nocb_rdp_offload(struct rcu_data *rdp)
 	return ret;
 }
 
-static long rcu_nocb_rdp_offload(void *arg)
-{
-	struct rcu_data *rdp = arg;
-
-	WARN_ON_ONCE(rdp->cpu != raw_smp_processor_id());
-	return __rcu_nocb_rdp_offload(rdp);
-}
-
 int rcu_nocb_cpu_offload(int cpu)
 {
 	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
@@ -2472,13 +2550,15 @@ int rcu_nocb_cpu_offload(int cpu)
 
 	mutex_lock(&rcu_state.barrier_mutex);
 	cpus_read_lock();
-	if (!rcu_segcblist_is_offloaded(&rdp->cblist)) {
+	if (!rcu_rdp_is_offloaded(rdp)) {
-		if (cpu_online(cpu))
+		if (cpu_online(cpu)) {
 			ret = work_on_cpu(cpu, rcu_nocb_rdp_offload, rdp);
-		else
+			if (!ret)
-			ret = __rcu_nocb_rdp_offload(rdp);
+				cpumask_set_cpu(cpu, rcu_nocb_mask);
-		if (!ret)
+		} else {
-			cpumask_set_cpu(cpu, rcu_nocb_mask);
+			pr_info("NOCB: Can't CB-offload an offline CPU\n");
+			ret = -EINVAL;
+		}
 	}
 	cpus_read_unlock();
 	mutex_unlock(&rcu_state.barrier_mutex);

kernel/rcu/tree_stall.h

@@ -536,6 +536,7 @@ static void print_other_cpu_stall(unsigned long gp_seq, unsigned long gps)
 	 * See Documentation/RCU/stallwarn.rst for info on how to debug
 	 * RCU CPU stall warnings.
 	 */
+	trace_rcu_stall_warning(rcu_state.name, TPS("StallDetected"));
 	pr_err("INFO: %s detected stalls on CPUs/tasks:\n", rcu_state.name);
 	rcu_for_each_leaf_node(rnp) {
 		raw_spin_lock_irqsave_rcu_node(rnp, flags);
@@ -606,6 +607,7 @@ static void print_cpu_stall(unsigned long gps)
 	 * See Documentation/RCU/stallwarn.rst for info on how to debug
 	 * RCU CPU stall warnings.
 	 */
+	trace_rcu_stall_warning(rcu_state.name, TPS("SelfDetected"));
 	pr_err("INFO: %s self-detected stall on CPU\n", rcu_state.name);
 	raw_spin_lock_irqsave_rcu_node(rdp->mynode, flags);
 	print_cpu_stall_info(smp_processor_id());

kernel/softirq.c

@@ -423,7 +423,7 @@ static inline void invoke_softirq(void)
 	if (ksoftirqd_running(local_softirq_pending()))
 		return;
 
-	if (!force_irqthreads) {
+	if (!force_irqthreads || !__this_cpu_read(ksoftirqd)) {
 #ifdef CONFIG_HAVE_IRQ_EXIT_ON_IRQ_STACK
 		/*
 		 * We can safely execute softirq on the current stack if

kernel/torture.c

@@ -816,9 +816,9 @@ bool torture_init_begin(char *ttype, int v)
 {
 	mutex_lock(&fullstop_mutex);
 	if (torture_type != NULL) {
-		pr_alert("torture_init_begin: Refusing %s init: %s running.\n",
+		pr_alert("%s: Refusing %s init: %s running.\n",
-			 ttype, torture_type);
+			  __func__, ttype, torture_type);
-		pr_alert("torture_init_begin: One torture test at a time!\n");
+		pr_alert("%s: One torture test at a time!\n", __func__);
 		mutex_unlock(&fullstop_mutex);
 		return false;
 	}

lib/bitmap.c

@@ -487,30 +487,25 @@ EXPORT_SYMBOL(bitmap_print_to_pagebuf);
 
 /*
  * Region 9-38:4/10 describes the following bitmap structure:
- * 0	   9  12    18			38
+ * 0	   9  12    18			38	     N
- * .........****......****......****......
+ * .........****......****......****..................
- *	    ^  ^     ^			 ^
+ *	    ^  ^     ^			 ^	     ^
- *      start  off   group_len	       end
+ *      start  off   group_len	       end	 nbits
  */
 struct region {
 	unsigned int start;
 	unsigned int off;
 	unsigned int group_len;
 	unsigned int end;
+	unsigned int nbits;
 };
 
-static int bitmap_set_region(const struct region *r,
+static void bitmap_set_region(const struct region *r, unsigned long *bitmap)
-				unsigned long *bitmap, int nbits)
 {
 	unsigned int start;
 
-	if (r->end >= nbits)
-		return -ERANGE;
-
 	for (start = r->start; start <= r->end; start += r->group_len)
 		bitmap_set(bitmap, start, min(r->end - start + 1, r->off));
-
-	return 0;
 }
 
 static int bitmap_check_region(const struct region *r)
@@ -518,14 +513,23 @@ static int bitmap_check_region(const struct region *r)
 	if (r->start > r->end || r->group_len == 0 || r->off > r->group_len)
 		return -EINVAL;
 
+	if (r->end >= r->nbits)
+		return -ERANGE;
+
 	return 0;
 }
 
-static const char *bitmap_getnum(const char *str, unsigned int *num)
+static const char *bitmap_getnum(const char *str, unsigned int *num,
+				 unsigned int lastbit)
 {
 	unsigned long long n;
 	unsigned int len;
 
+	if (str[0] == 'N') {
+		*num = lastbit;
+		return str + 1;
+	}
+
 	len = _parse_integer(str, 10, &n);
 	if (!len)
 		return ERR_PTR(-EINVAL);
@@ -573,7 +577,9 @@ static const char *bitmap_find_region_reverse(const char *start, const char *end
 
 static const char *bitmap_parse_region(const char *str, struct region *r)
 {
-	str = bitmap_getnum(str, &r->start);
+	unsigned int lastbit = r->nbits - 1;
+
+	str = bitmap_getnum(str, &r->start, lastbit);
 	if (IS_ERR(str))
 		return str;
 
@@ -583,7 +589,7 @@ static const char *bitmap_parse_region(const char *str, struct region *r)
 	if (*str != '-')
 		return ERR_PTR(-EINVAL);
 
-	str = bitmap_getnum(str + 1, &r->end);
+	str = bitmap_getnum(str + 1, &r->end, lastbit);
 	if (IS_ERR(str))
 		return str;
 
@@ -593,14 +599,14 @@ static const char *bitmap_parse_region(const char *str, struct region *r)
 	if (*str != ':')
 		return ERR_PTR(-EINVAL);
 
-	str = bitmap_getnum(str + 1, &r->off);
+	str = bitmap_getnum(str + 1, &r->off, lastbit);
 	if (IS_ERR(str))
 		return str;
 
 	if (*str != '/')
 		return ERR_PTR(-EINVAL);
 
-	return bitmap_getnum(str + 1, &r->group_len);
+	return bitmap_getnum(str + 1, &r->group_len, lastbit);
 
 no_end:
 	r->end = r->start;
@@ -627,6 +633,10 @@ no_pattern:
  * From each group will be used only defined amount of bits.
  * Syntax: range:used_size/group_size
  * Example: 0-1023:2/256 ==> 0,1,256,257,512,513,768,769
+ * The value 'N' can be used as a dynamically substituted token for the
+ * maximum allowed value; i.e (nmaskbits - 1).  Keep in mind that it is
+ * dynamic, so if system changes cause the bitmap width to change, such
+ * as more cores in a CPU list, then any ranges using N will also change.
  *
  * Returns: 0 on success, -errno on invalid input strings. Error values:
  *
@@ -640,7 +650,8 @@ int bitmap_parselist(const char *buf, unsigned long *maskp, int nmaskbits)
 	struct region r;
 	long ret;
 
-	bitmap_zero(maskp, nmaskbits);
+	r.nbits = nmaskbits;
+	bitmap_zero(maskp, r.nbits);
 
 	while (buf) {
 		buf = bitmap_find_region(buf);
@@ -655,9 +666,7 @@ int bitmap_parselist(const char *buf, unsigned long *maskp, int nmaskbits)
 		if (ret)
 			return ret;
 
-		ret = bitmap_set_region(&r, maskp, nmaskbits);
+		bitmap_set_region(&r, maskp);
-		if (ret)
-			return ret;
 	}
 
 	return 0;

lib/test_bitmap.c

@@ -34,6 +34,8 @@ static const unsigned long exp1[] __initconst = {
 	BITMAP_FROM_U64(0x3333333311111111ULL),
 	BITMAP_FROM_U64(0xffffffff77777777ULL),
 	BITMAP_FROM_U64(0),
+	BITMAP_FROM_U64(0x00008000),
+	BITMAP_FROM_U64(0x80000000),
 };
 
 static const unsigned long exp2[] __initconst = {
@@ -334,15 +336,47 @@ static const struct test_bitmap_parselist parselist_tests[] __initconst = {
 	{0, " ,  ,,  , ,   ",		&exp1[12 * step], 8, 0},
 	{0, " ,  ,,  , ,   \n",		&exp1[12 * step], 8, 0},
 
+	{0, "0-0",			&exp1[0], 32, 0},
+	{0, "1-1",			&exp1[1 * step], 32, 0},
+	{0, "15-15",			&exp1[13 * step], 32, 0},
+	{0, "31-31",			&exp1[14 * step], 32, 0},
+
+	{0, "0-0:0/1",			&exp1[12 * step], 32, 0},
+	{0, "0-0:1/1",			&exp1[0], 32, 0},
+	{0, "0-0:1/31",			&exp1[0], 32, 0},
+	{0, "0-0:31/31",		&exp1[0], 32, 0},
+	{0, "1-1:1/1",			&exp1[1 * step], 32, 0},
+	{0, "0-15:16/31",		&exp1[2 * step], 32, 0},
+	{0, "15-15:1/2",		&exp1[13 * step], 32, 0},
+	{0, "15-15:31/31",		&exp1[13 * step], 32, 0},
+	{0, "15-31:1/31",		&exp1[13 * step], 32, 0},
+	{0, "16-31:16/31",		&exp1[3 * step], 32, 0},
+	{0, "31-31:31/31",		&exp1[14 * step], 32, 0},
+
+	{0, "N-N",			&exp1[14 * step], 32, 0},
+	{0, "0-0:1/N",			&exp1[0], 32, 0},
+	{0, "0-0:N/N",			&exp1[0], 32, 0},
+	{0, "0-15:16/N",		&exp1[2 * step], 32, 0},
+	{0, "15-15:N/N",		&exp1[13 * step], 32, 0},
+	{0, "15-N:1/N",			&exp1[13 * step], 32, 0},
+	{0, "16-N:16/N",		&exp1[3 * step], 32, 0},
+	{0, "N-N:N/N",			&exp1[14 * step], 32, 0},
+
+	{0, "0-N:1/3,1-N:1/3,2-N:1/3",		&exp1[8 * step], 32, 0},
+	{0, "0-31:1/3,1-31:1/3,2-31:1/3",	&exp1[8 * step], 32, 0},
+	{0, "1-10:8/12,8-31:24/29,0-31:0/3",	&exp1[9 * step], 32, 0},
+
 	{-EINVAL, "-1",	NULL, 8, 0},
 	{-EINVAL, "-0",	NULL, 8, 0},
 	{-EINVAL, "10-1", NULL, 8, 0},
-	{-EINVAL, "0-31:", NULL, 8, 0},
+	{-ERANGE, "8-8", NULL, 8, 0},
-	{-EINVAL, "0-31:0", NULL, 8, 0},
+	{-ERANGE, "0-31", NULL, 8, 0},
-	{-EINVAL, "0-31:0/", NULL, 8, 0},
+	{-EINVAL, "0-31:", NULL, 32, 0},
-	{-EINVAL, "0-31:0/0", NULL, 8, 0},
+	{-EINVAL, "0-31:0", NULL, 32, 0},
-	{-EINVAL, "0-31:1/0", NULL, 8, 0},
+	{-EINVAL, "0-31:0/", NULL, 32, 0},
-	{-EINVAL, "0-31:10/1", NULL, 8, 0},
+	{-EINVAL, "0-31:0/0", NULL, 32, 0},
+	{-EINVAL, "0-31:1/0", NULL, 32, 0},
+	{-EINVAL, "0-31:10/1", NULL, 32, 0},
 	{-EOVERFLOW, "0-98765432123456789:10/1", NULL, 8, 0},
 
 	{-EINVAL, "a-31", NULL, 8, 0},

mm/slab.c

@@ -3651,6 +3651,7 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t flags,
 EXPORT_SYMBOL(__kmalloc_node_track_caller);
 #endif /* CONFIG_NUMA */
 
+#ifdef CONFIG_PRINTK
 void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct page *page)
 {
 	struct kmem_cache *cachep;
@@ -3670,6 +3671,7 @@ void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct page *page)
 	if (DEBUG && cachep->flags & SLAB_STORE_USER)
 		kpp->kp_ret = *dbg_userword(cachep, objp);
 }
+#endif
 
 /**
  * __do_kmalloc - allocate memory

mm/slab.h

@@ -621,6 +621,7 @@ static inline bool slab_want_init_on_free(struct kmem_cache *c)
 	return false;
 }
 
+#ifdef CONFIG_PRINTK
 #define KS_ADDRS_COUNT 16
 struct kmem_obj_info {
 	void *kp_ptr;
@@ -632,5 +633,6 @@ struct kmem_obj_info {
 	void *kp_stack[KS_ADDRS_COUNT];
 };
 void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct page *page);
+#endif
 
 #endif /* MM_SLAB_H */

mm/slab_common.c

@@ -526,6 +526,7 @@ bool slab_is_available(void)
 	return slab_state >= UP;
 }
 
+#ifdef CONFIG_PRINTK
 /**
  * kmem_valid_obj - does the pointer reference a valid slab object?
  * @object: pointer to query.
@@ -544,6 +545,7 @@ bool kmem_valid_obj(void *object)
 	page = virt_to_head_page(object);
 	return PageSlab(page);
 }
+EXPORT_SYMBOL_GPL(kmem_valid_obj);
 
 /**
  * kmem_dump_obj - Print available slab provenance information
@@ -600,6 +602,8 @@ void kmem_dump_obj(void *object)
 		pr_info("    %pS\n", kp.kp_stack[i]);
 	}
 }
+EXPORT_SYMBOL_GPL(kmem_dump_obj);
+#endif
 
 #ifndef CONFIG_SLOB
 /* Create a cache during boot when no slab services are available yet */

mm/slob.c

@@ -461,11 +461,13 @@ out:
 	spin_unlock_irqrestore(&slob_lock, flags);
 }
 
+#ifdef CONFIG_PRINTK
 void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct page *page)
 {
 	kpp->kp_ptr = object;
 	kpp->kp_page = page;
 }
+#endif
 
 /*
  * End of slob allocator proper. Begin kmem_cache_alloc and kmalloc frontend.

mm/slub.c

@@ -3964,6 +3964,7 @@ int __kmem_cache_shutdown(struct kmem_cache *s)
 	return 0;
 }
 
+#ifdef CONFIG_PRINTK
 void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct page *page)
 {
 	void *base;
@@ -4003,6 +4004,7 @@ void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct page *page)
 #endif
 #endif
 }
+#endif
 
 /********************************************************************
  *		Kmalloc subsystem

mm/util.c

@@ -983,6 +983,7 @@ int __weak memcmp_pages(struct page *page1, struct page *page2)
 	return ret;
 }
 
+#ifdef CONFIG_PRINTK
 /**
  * mem_dump_obj - Print available provenance information
  * @object: object for which to find provenance information.
@@ -1013,3 +1014,5 @@ void mem_dump_obj(void *object)
 	}
 	pr_cont(" non-slab/vmalloc memory.\n");
 }
+EXPORT_SYMBOL_GPL(mem_dump_obj);
+#endif

mm/vmalloc.c

@@ -3450,6 +3450,7 @@ void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms)
 }
 #endif	/* CONFIG_SMP */
 
+#ifdef CONFIG_PRINTK
 bool vmalloc_dump_obj(void *object)
 {
 	struct vm_struct *vm;
@@ -3462,6 +3463,7 @@ bool vmalloc_dump_obj(void *object)
 		vm->nr_pages, (unsigned long)vm->addr, vm->caller);
 	return true;
 }
+#endif
 
 #ifdef CONFIG_PROC_FS
 static void *s_start(struct seq_file *m, loff_t *pos)

tools/testing/selftests/rcutorture/bin/cpus2use.sh

@@ -21,7 +21,6 @@ then
 		awk -v ncpus=$ncpus '{ print ncpus * ($7 + $NF) / 100 }'`
 else
 	# No mpstat command, so use all available CPUs.
-	echo The mpstat command is not available, so greedily using all CPUs.
 	idlecpus=$ncpus
 fi
 awk -v ncpus=$ncpus -v idlecpus=$idlecpus < /dev/null '

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

@@ -5,10 +5,11 @@
 # of this script is to inflict random OS jitter on a concurrently running
 # test.
 #
-# Usage: jitter.sh me duration [ sleepmax [ spinmax ] ]
+# Usage: jitter.sh me jittering-path duration [ sleepmax [ spinmax ] ]
 #
 # me: Random-number-generator seed salt.
 # duration: Time to run in seconds.
+# jittering-path: Path to file whose removal will stop this script.
 # sleepmax: Maximum microseconds to sleep, defaults to one second.
 # spinmax: Maximum microseconds to spin, defaults to one millisecond.
 #
@@ -17,9 +18,10 @@
 # Authors: Paul E. McKenney <paulmck@linux.ibm.com>
 
 me=$(($1 * 1000))
-duration=$2
+jittering=$2
-sleepmax=${3-1000000}
+duration=$3
-spinmax=${4-1000}
+sleepmax=${4-1000000}
+spinmax=${5-1000}
 
 n=1
 
@@ -47,7 +49,7 @@ do
 	fi
 
 	# Check for stop request.
-	if test -f "$TORTURE_STOPFILE"
+	if ! test -f "$jittering"
 	then
 		exit 1;
 	fi
@@ -67,10 +69,10 @@ do
 		srand(n + me + systime());
 		ncpus = split(cpus, ca);
 		curcpu = ca[int(rand() * ncpus + 1)];
-		mask = lshift(1, curcpu);
+		z = "";
-		if (mask + 0 <= 0)
+		for (i = 1; 4 * i <= curcpu; i++)
-			mask = 1;
+			z = z "0";
-		printf("%#x\n", mask);
+		print "0x" 2 ^ (curcpu % 4) z;
 	}' < /dev/null`
 	n=$(($n+1))
 	if ! taskset -p $cpumask $$ > /dev/null 2>&1

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

@@ -0,0 +1,37 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
+#
+# Start up the specified number of jitter.sh scripts in the background.
+#
+# Usage: . jitterstart.sh n jittering-dir duration [ sleepmax [ spinmax ] ]
+#
+# n: Number of jitter.sh scripts to start up.
+# jittering-dir: Directory in which to put "jittering" file.
+# duration: Time to run in seconds.
+# sleepmax: Maximum microseconds to sleep, defaults to one second.
+# spinmax: Maximum microseconds to spin, defaults to one millisecond.
+#
+# Copyright (C) 2021 Facebook, Inc.
+#
+# Authors: Paul E. McKenney <paulmck@kernel.org>
+
+jitter_n=$1
+if test -z "$jitter_n"
+then
+	echo jitterstart.sh: Missing count of jitter.sh scripts to start.
+	exit 33
+fi
+jittering_dir=$2
+if test -z "$jittering_dir"
+then
+	echo jitterstart.sh: Missing directory in which to place jittering file.
+	exit 34
+fi
+shift
+shift
+
+touch ${jittering_dir}/jittering
+for ((jitter_i = 1; jitter_i <= $jitter_n; jitter_i++))
+do
+	jitter.sh $jitter_i "${jittering_dir}/jittering" "$@" &
+done

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

@@ -0,0 +1,23 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
+#
+# Remove the "jittering" file, signaling the jitter.sh scripts to stop,
+# then wait for them to terminate.
+#
+# Usage: . jitterstop.sh jittering-dir
+#
+# jittering-dir: Directory containing "jittering" file.
+#
+# Copyright (C) 2021 Facebook, Inc.
+#
+# Authors: Paul E. McKenney <paulmck@kernel.org>
+
+jittering_dir=$1
+if test -z "$jittering_dir"
+then
+	echo jitterstop.sh: Missing directory in which to place jittering file.
+	exit 34
+fi
+
+rm -f ${jittering_dir}/jittering
+wait

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

@@ -0,0 +1,199 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
+#
+# Rerun a series of tests under KVM.
+#
+# Usage: kvm-again.sh /path/to/old/run [ options ]
+#
+# Copyright (C) 2021 Facebook, Inc.
+#
+# Authors: Paul E. McKenney <paulmck@kernel.org>
+
+scriptname=$0
+args="$*"
+
+T=${TMPDIR-/tmp}/kvm-again.sh.$$
+trap 'rm -rf $T' 0
+mkdir $T
+
+if ! test -d tools/testing/selftests/rcutorture/bin
+then
+	echo $scriptname must be run from top-level directory of kernel source tree.
+	exit 1
+fi
+
+oldrun=$1
+shift
+if ! test -d "$oldrun"
+then
+	echo "Usage: $scriptname /path/to/old/run [ options ]"
+	exit 1
+fi
+if ! cp "$oldrun/batches" $T/batches.oldrun
+then
+	# Later on, can reconstitute this from console.log files.
+	echo Prior run batches file does not exist: $oldrun/batches
+	exit 1
+fi
+
+if test -f "$oldrun/torture_suite"
+then
+	torture_suite="`cat $oldrun/torture_suite`"
+elif test -f "$oldrun/TORTURE_SUITE"
+then
+	torture_suite="`cat $oldrun/TORTURE_SUITE`"
+else
+	echo "Prior run torture_suite file does not exist: $oldrun/{torture_suite,TORTURE_SUITE}"
+	exit 1
+fi
+
+KVM="`pwd`/tools/testing/selftests/rcutorture"; export KVM
+PATH=${KVM}/bin:$PATH; export PATH
+. functions.sh
+
+dryrun=
+dur=
+default_link="cp -R"
+rundir="`pwd`/tools/testing/selftests/rcutorture/res/`date +%Y.%m.%d-%H.%M.%S-again`"
+
+startdate="`date`"
+starttime="`get_starttime`"
+
+usage () {
+	echo "Usage: $scriptname $oldrun [ arguments ]:"
+	echo "       --dryrun"
+	echo "       --duration minutes | <seconds>s | <hours>h | <days>d"
+	echo "       --link hard|soft|copy"
+	echo "       --remote"
+	echo "       --rundir /new/res/path"
+	exit 1
+}
+
+while test $# -gt 0
+do
+	case "$1" in
+	--dryrun)
+		dryrun=1
+		;;
+	--duration)
+		checkarg --duration "(minutes)" $# "$2" '^[0-9][0-9]*\(s\|m\|h\|d\|\)$' '^error'
+		mult=60
+		if echo "$2" | grep -q 's$'
+		then
+			mult=1
+		elif echo "$2" | grep -q 'h$'
+		then
+			mult=3600
+		elif echo "$2" | grep -q 'd$'
+		then
+			mult=86400
+		fi
+		ts=`echo $2 | sed -e 's/[smhd]$//'`
+		dur=$(($ts*mult))
+		shift
+		;;
+	--link)
+		checkarg --link "hard|soft|copy" "$#" "$2" 'hard\|soft\|copy' '^--'
+		case "$2" in
+		copy)
+			arg_link="cp -R"
+			;;
+		hard)
+			arg_link="cp -Rl"
+			;;
+		soft)
+			arg_link="cp -Rs"
+			;;
+		esac
+		shift
+		;;
+	--remote)
+		arg_remote=1
+		default_link="cp -as"
+		;;
+	--rundir)
+		checkarg --rundir "(absolute pathname)" "$#" "$2" '^/' '^error'
+		rundir=$2
+		if test -e "$rundir"
+		then
+			echo "--rundir $2: Already exists."
+			usage
+		fi
+		shift
+		;;
+	*)
+		echo Unknown argument $1
+		usage
+		;;
+	esac
+	shift
+done
+if test -z "$arg_link"
+then
+	arg_link="$default_link"
+fi
+
+echo ---- Re-run results directory: $rundir
+
+# Copy old run directory tree over and adjust.
+mkdir -p "`dirname "$rundir"`"
+if ! $arg_link "$oldrun" "$rundir"
+then
+	echo "Cannot copy from $oldrun to $rundir."
+	usage
+fi
+rm -f "$rundir"/*/{console.log,console.log.diags,qemu_pid,qemu-retval,Warnings,kvm-test-1-run.sh.out,kvm-test-1-run-qemu.sh.out,vmlinux} "$rundir"/log
+echo $oldrun > "$rundir/re-run"
+if ! test -d "$rundir/../../bin"
+then
+	$arg_link "$oldrun/../../bin" "$rundir/../.."
+fi
+for i in $rundir/*/qemu-cmd
+do
+	cp "$i" $T
+	qemu_cmd_dir="`dirname "$i"`"
+	kernel_dir="`echo $qemu_cmd_dir | sed -e 's/\.[0-9]\+$//'`"
+	jitter_dir="`dirname "$kernel_dir"`"
+	kvm-transform.sh "$kernel_dir/bzImage" "$qemu_cmd_dir/console.log" "$jitter_dir" $dur < $T/qemu-cmd > $i
+	if test -n "$arg_remote"
+	then
+		echo "# TORTURE_KCONFIG_GDB_ARG=''" >> $i
+	fi
+done
+
+# Extract settings from the last qemu-cmd file transformed above.
+grep '^#' $i | sed -e 's/^# //' > $T/qemu-cmd-settings
+. $T/qemu-cmd-settings
+
+grep -v '^#' $T/batches.oldrun | awk '
+BEGIN {
+	oldbatch = 1;
+}
+
+{
+	if (oldbatch != $1) {
+		print "kvm-test-1-run-batch.sh" curbatch;
+		curbatch = "";
+		oldbatch = $1;
+	}
+	curbatch = curbatch " " $2;
+}
+
+END {
+	print "kvm-test-1-run-batch.sh" curbatch
+}' > $T/runbatches.sh
+
+if test -n "$dryrun"
+then
+	echo ---- Dryrun complete, directory: $rundir | tee -a "$rundir/log"
+else
+	( cd "$rundir"; sh $T/runbatches.sh )
+	kcsan-collapse.sh "$rundir" | tee -a "$rundir/log"
+	echo | tee -a "$rundir/log"
+	echo ---- Results directory: $rundir | tee -a "$rundir/log"
+	kvm-recheck.sh "$rundir" > $T/kvm-recheck.sh.out 2>&1
+	ret=$?
+	cat $T/kvm-recheck.sh.out | tee -a "$rundir/log"
+	echo " --- Done at `date` (`get_starttime_duration $starttime`) exitcode $ret" | tee -a "$rundir/log"
+	exit $ret
+fi

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

@@ -30,7 +30,7 @@ do
 			resdir=`echo $i | sed -e 's,/$,,' -e 's,/[^/]*$,,'`
 			head -1 $resdir/log
 		fi
-		TORTURE_SUITE="`cat $i/../TORTURE_SUITE`"
+		TORTURE_SUITE="`cat $i/../torture_suite`"
 		configfile=`echo $i | sed -e 's,^.*/,,'`
 		rm -f $i/console.log.*.diags
 		kvm-recheck-${TORTURE_SUITE}.sh $i

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

@@ -0,0 +1,67 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
+#
+# Carry out a kvm-based run for the specified batch of scenarios, which
+# might have been built by --build-only kvm.sh run.
+#
+# Usage: kvm-test-1-run-batch.sh SCENARIO [ SCENARIO ... ]
+#
+# Each SCENARIO is the name of a directory in the current directory
+#	containing a ready-to-run qemu-cmd file.
+#
+# Copyright (C) 2021 Facebook, Inc.
+#
+# Authors: Paul E. McKenney <paulmck@kernel.org>
+
+T=${TMPDIR-/tmp}/kvm-test-1-run-batch.sh.$$
+trap 'rm -rf $T' 0
+mkdir $T
+
+echo ---- Running batch $*
+# Check arguments
+runfiles=
+for i in "$@"
+do
+	if ! echo $i | grep -q '^[^/.a-z]\+\(\.[0-9]\+\)\?$'
+	then
+		echo Bad scenario name: \"$i\" 1>&2
+		exit 1
+	fi
+	if ! test -d "$i"
+	then
+		echo Scenario name not a directory: \"$i\" 1>&2
+		exit 2
+	fi
+	if ! test -f "$i/qemu-cmd"
+	then
+		echo Scenario lacks a command file: \"$i/qemu-cmd\" 1>&2
+		exit 3
+	fi
+	rm -f $i/build.*
+	touch $i/build.run
+	runfiles="$runfiles $i/build.run"
+done
+
+# Extract settings from the qemu-cmd file.
+grep '^#' $1/qemu-cmd | sed -e 's/^# //' > $T/qemu-cmd-settings
+. $T/qemu-cmd-settings
+
+# Start up jitter, start each scenario, wait, end jitter.
+echo ---- System running test: `uname -a`
+echo ---- Starting kernels. `date` | tee -a log
+$TORTURE_JITTER_START
+for i in "$@"
+do
+	echo ---- System running test: `uname -a` > $i/kvm-test-1-run-qemu.sh.out
+	echo > $i/kvm-test-1-run-qemu.sh.out
+	kvm-test-1-run-qemu.sh $i >> $i/kvm-test-1-run-qemu.sh.out 2>&1 &
+done
+for i in $runfiles
+do
+	while ls $i > /dev/null 2>&1
+	do
+		:
+	done
+done
+echo ---- All kernel runs complete. `date` | tee -a log
+$TORTURE_JITTER_STOP

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

@@ -0,0 +1,176 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
+#
+# Carry out a kvm-based run for the specified qemu-cmd file, which might
+# have been generated by --build-only kvm.sh run.
+#
+# Usage: kvm-test-1-run-qemu.sh qemu-cmd-dir
+#
+# qemu-cmd-dir provides the directory containing qemu-cmd file.
+#	This is assumed to be of the form prefix/ds/scenario, where
+#	"ds" is the top-level date-stamped directory and "scenario"
+#	is the scenario name.  Any required adjustments to this file
+#	must have been made by the caller.  The shell-command comments
+#	at the end of the qemu-cmd file are not optional.
+#
+# Copyright (C) 2021 Facebook, Inc.
+#
+# Authors: Paul E. McKenney <paulmck@kernel.org>
+
+T=${TMPDIR-/tmp}/kvm-test-1-run-qemu.sh.$$
+trap 'rm -rf $T' 0
+mkdir $T
+
+resdir="$1"
+if ! test -d "$resdir"
+then
+	echo $0: Nonexistent directory: $resdir
+	exit 1
+fi
+if ! test -f "$resdir/qemu-cmd"
+then
+	echo $0: Nonexistent qemu-cmd file: $resdir/qemu-cmd
+	exit 1
+fi
+
+echo ' ---' `date`: Starting kernel, PID $$
+
+# Obtain settings from the qemu-cmd file.
+grep '^#' $resdir/qemu-cmd | sed -e 's/^# //' > $T/qemu-cmd-settings
+. $T/qemu-cmd-settings
+
+# Decorate qemu-cmd with redirection, backgrounding, and PID capture
+sed -e 's/$/ 2>\&1 \&/' < $resdir/qemu-cmd > $T/qemu-cmd
+echo 'echo $! > $resdir/qemu_pid' >> $T/qemu-cmd
+
+# In case qemu refuses to run...
+echo "NOTE: $QEMU either did not run or was interactive" > $resdir/console.log
+
+# Attempt to run qemu
+kstarttime=`gawk 'BEGIN { print systime() }' < /dev/null`
+( . $T/qemu-cmd; wait `cat  $resdir/qemu_pid`; echo $? > $resdir/qemu-retval ) &
+commandcompleted=0
+if test -z "$TORTURE_KCONFIG_GDB_ARG"
+then
+	sleep 10 # Give qemu's pid a chance to reach the file
+	if test -s "$resdir/qemu_pid"
+	then
+		qemu_pid=`cat "$resdir/qemu_pid"`
+		echo Monitoring qemu job at pid $qemu_pid
+	else
+		qemu_pid=""
+		echo Monitoring qemu job at yet-as-unknown pid
+	fi
+fi
+if test -n "$TORTURE_KCONFIG_GDB_ARG"
+then
+	base_resdir=`echo $resdir | sed -e 's/\.[0-9]\+$//'`
+	if ! test -f $base_resdir/vmlinux
+	then
+		base_resdir="`cat re-run`/$resdir"
+		if ! test -f $base_resdir/vmlinux
+		then
+			base_resdir=/path/to
+		fi
+	fi
+	echo Waiting for you to attach a debug session, for example: > /dev/tty
+	echo "    gdb $base_resdir/vmlinux" > /dev/tty
+	echo 'After symbols load and the "(gdb)" prompt appears:' > /dev/tty
+	echo "    target remote :1234" > /dev/tty
+	echo "    continue" > /dev/tty
+	kstarttime=`gawk 'BEGIN { print systime() }' < /dev/null`
+fi
+while :
+do
+	if test -z "$qemu_pid" -a -s "$resdir/qemu_pid"
+	then
+		qemu_pid=`cat "$resdir/qemu_pid"`
+	fi
+	kruntime=`gawk 'BEGIN { print systime() - '"$kstarttime"' }' < /dev/null`
+	if test -z "$qemu_pid" || kill -0 "$qemu_pid" > /dev/null 2>&1
+	then
+		if test -n "$TORTURE_KCONFIG_GDB_ARG"
+		then
+			:
+		elif test $kruntime -ge $seconds || test -f "$resdir/../STOP.1"
+		then
+			break;
+		fi
+		sleep 1
+	else
+		commandcompleted=1
+		if test $kruntime -lt $seconds
+		then
+			echo Completed in $kruntime vs. $seconds >> $resdir/Warnings 2>&1
+			grep "^(qemu) qemu:" $resdir/kvm-test-1-run.sh.out >> $resdir/Warnings 2>&1
+			killpid="`sed -n "s/^(qemu) qemu: terminating on signal [0-9]* from pid \([0-9]*\).*$/\1/p" $resdir/Warnings`"
+			if test -n "$killpid"
+			then
+				echo "ps -fp $killpid" >> $resdir/Warnings 2>&1
+				ps -fp $killpid >> $resdir/Warnings 2>&1
+			fi
+		else
+			echo ' ---' `date`: "Kernel done"
+		fi
+		break
+	fi
+done
+if test -z "$qemu_pid" -a -s "$resdir/qemu_pid"
+then
+	qemu_pid=`cat "$resdir/qemu_pid"`
+fi
+if test $commandcompleted -eq 0 -a -n "$qemu_pid"
+then
+	if ! test -f "$resdir/../STOP.1"
+	then
+		echo Grace period for qemu job at pid $qemu_pid
+	fi
+	oldline="`tail $resdir/console.log`"
+	while :
+	do
+		if test -f "$resdir/../STOP.1"
+		then
+			echo "PID $qemu_pid killed due to run STOP.1 request" >> $resdir/Warnings 2>&1
+			kill -KILL $qemu_pid
+			break
+		fi
+		kruntime=`gawk 'BEGIN { print systime() - '"$kstarttime"' }' < /dev/null`
+		if kill -0 $qemu_pid > /dev/null 2>&1
+		then
+			:
+		else
+			break
+		fi
+		must_continue=no
+		newline="`tail $resdir/console.log`"
+		if test "$newline" != "$oldline" && echo $newline | grep -q ' [0-9]\+us : '
+		then
+			must_continue=yes
+		fi
+		last_ts="`tail $resdir/console.log | grep '^\[ *[0-9]\+\.[0-9]\+]' | tail -1 | sed -e 's/^\[ *//' -e 's/\..*$//'`"
+		if test -z "$last_ts"
+		then
+			last_ts=0
+		fi
+		if test "$newline" != "$oldline" -a "$last_ts" -lt $((seconds + $TORTURE_SHUTDOWN_GRACE))
+		then
+			must_continue=yes
+		fi
+		if test $must_continue = no -a $kruntime -ge $((seconds + $TORTURE_SHUTDOWN_GRACE))
+		then
+			echo "!!! PID $qemu_pid hung at $kruntime vs. $seconds seconds" >> $resdir/Warnings 2>&1
+			kill -KILL $qemu_pid
+			break
+		fi
+		oldline=$newline
+		sleep 10
+	done
+elif test -z "$qemu_pid"
+then
+	echo Unknown PID, cannot kill qemu command
+fi
+
+# Tell the script that this run is done.
+rm -f $resdir/build.run
+
+parse-console.sh $resdir/console.log $title

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

@@ -7,15 +7,15 @@
 # Execute this in the source tree.  Do not run it as a background task
 # because qemu does not seem to like that much.
 #
-# Usage: kvm-test-1-run.sh config builddir resdir seconds qemu-args boot_args
+# Usage: kvm-test-1-run.sh config resdir seconds qemu-args boot_args_in
 #
 # qemu-args defaults to "-enable-kvm -nographic", along with arguments
 #			specifying the number of CPUs and other options
 #			generated from the underlying CPU architecture.
-# boot_args defaults to value returned by the per_version_boot_params
+# boot_args_in defaults to value returned by the per_version_boot_params
 #			shell function.
 #
-# Anything you specify for either qemu-args or boot_args is appended to
+# Anything you specify for either qemu-args or boot_args_in is appended to
 # the default values.  The "-smp" value is deduced from the contents of
 # the config fragment.
 #
@@ -35,14 +35,13 @@ mkdir $T
 config_template=${1}
 config_dir=`echo $config_template | sed -e 's,/[^/]*$,,'`
 title=`echo $config_template | sed -e 's/^.*\///'`
-builddir=${2}
+resdir=${2}
-resdir=${3}
 if test -z "$resdir" -o ! -d "$resdir" -o ! -w "$resdir"
 then
 	echo "kvm-test-1-run.sh :$resdir: Not a writable directory, cannot store results into it"
 	exit 1
 fi
-echo ' ---' `date`: Starting build
+echo ' ---' `date`: Starting build, PID $$
 echo ' ---' Kconfig fragment at: $config_template >> $resdir/log
 touch $resdir/ConfigFragment.input
 
@@ -73,7 +72,7 @@ config_override_param "--kconfig argument" KcList "$TORTURE_KCONFIG_ARG"
 cp $T/KcList $resdir/ConfigFragment
 
 base_resdir=`echo $resdir | sed -e 's/\.[0-9]\+$//'`
-if test "$base_resdir" != "$resdir" -a -f $base_resdir/bzImage -a -f $base_resdir/vmlinux
+if test "$base_resdir" != "$resdir" && test -f $base_resdir/bzImage && test -f $base_resdir/vmlinux
 then
 	# Rerunning previous test, so use that test's kernel.
 	QEMU="`identify_qemu $base_resdir/vmlinux`"
@@ -83,6 +82,17 @@ then
 	ln -s $base_resdir/.config $resdir  # for kvm-recheck.sh
 	# Arch-independent indicator
 	touch $resdir/builtkernel
+elif test "$base_resdir" != "$resdir"
+then
+	# Rerunning previous test for which build failed
+	ln -s $base_resdir/Make*.out $resdir  # for kvm-recheck.sh
+	ln -s $base_resdir/.config $resdir  # for kvm-recheck.sh
+	echo Initial build failed, not running KVM, see $resdir.
+	if test -f $resdir/build.wait
+	then
+		mv $resdir/build.wait $resdir/build.ready
+	fi
+	exit 1
 elif kvm-build.sh $T/KcList $resdir
 then
 	# Had to build a kernel for this test.
@@ -107,23 +117,23 @@ else
 	# Build failed.
 	cp .config $resdir || :
 	echo Build failed, not running KVM, see $resdir.
-	if test -f $builddir.wait
+	if test -f $resdir/build.wait
 	then
-		mv $builddir.wait $builddir.ready
+		mv $resdir/build.wait $resdir/build.ready
 	fi
 	exit 1
 fi
-if test -f $builddir.wait
+if test -f $resdir/build.wait
 then
-	mv $builddir.wait $builddir.ready
+	mv $resdir/build.wait $resdir/build.ready
 fi
-while test -f $builddir.ready
+while test -f $resdir/build.ready
 do
 	sleep 1
 done
-seconds=$4
+seconds=$3
-qemu_args=$5
+qemu_args=$4
-boot_args=$6
+boot_args_in=$5
 
 if test -z "$TORTURE_BUILDONLY"
 then
@@ -133,7 +143,7 @@ fi
 # Generate -smp qemu argument.
 qemu_args="-enable-kvm -nographic $qemu_args"
 cpu_count=`configNR_CPUS.sh $resdir/ConfigFragment`
-cpu_count=`configfrag_boot_cpus "$boot_args" "$config_template" "$cpu_count"`
+cpu_count=`configfrag_boot_cpus "$boot_args_in" "$config_template" "$cpu_count"`
 if test "$cpu_count" -gt "$TORTURE_ALLOTED_CPUS"
 then
 	echo CPU count limited from $cpu_count to $TORTURE_ALLOTED_CPUS | tee -a $resdir/Warnings
@@ -149,16 +159,52 @@ qemu_args="$qemu_args `identify_qemu_args "$QEMU" "$resdir/console.log"`"
 qemu_append="`identify_qemu_append "$QEMU"`"
 
 # Pull in Kconfig-fragment boot parameters
-boot_args="`configfrag_boot_params "$boot_args" "$config_template"`"
+boot_args="`configfrag_boot_params "$boot_args_in" "$config_template"`"
 # Generate kernel-version-specific boot parameters
 boot_args="`per_version_boot_params "$boot_args" $resdir/.config $seconds`"
 if test -n "$TORTURE_BOOT_GDB_ARG"
 then
 	boot_args="$boot_args $TORTURE_BOOT_GDB_ARG"
 fi
+
+# Give bare-metal advice
+modprobe_args="`echo $boot_args | tr -s ' ' '\012' | grep "^$TORTURE_MOD\." | sed -e "s/$TORTURE_MOD\.//g"`"
+kboot_args="`echo $boot_args | tr -s ' ' '\012' | grep -v "^$TORTURE_MOD\."`"
+testid_txt="`dirname $resdir`/testid.txt"
+touch $resdir/bare-metal
+echo To run this scenario on bare metal: >> $resdir/bare-metal
+echo >> $resdir/bare-metal
+echo " 1." Set your bare-metal build tree to the state shown in this file: >> $resdir/bare-metal
+echo "   " $testid_txt >> $resdir/bare-metal
+echo " 2." Update your bare-metal build tree"'"s .config based on this file: >> $resdir/bare-metal
+echo "   " $resdir/ConfigFragment >> $resdir/bare-metal
+echo " 3." Make the bare-metal kernel"'"s build system aware of your .config updates: >> $resdir/bare-metal
+echo "   " $ 'yes "" | make oldconfig' >> $resdir/bare-metal
+echo " 4." Build your bare-metal kernel. >> $resdir/bare-metal
+echo " 5." Boot your bare-metal kernel with the following parameters: >> $resdir/bare-metal
+echo "   " $kboot_args >> $resdir/bare-metal
+echo " 6." Start the test with the following command: >> $resdir/bare-metal
+echo "   " $ modprobe $TORTURE_MOD $modprobe_args >> $resdir/bare-metal
+echo " 7." After some time, end the test with the following command: >> $resdir/bare-metal
+echo "   " $ rmmod $TORTURE_MOD >> $resdir/bare-metal
+echo " 8." Copy your bare-metal kernel"'"s .config file, overwriting this file: >> $resdir/bare-metal
+echo "   " $resdir/.config >> $resdir/bare-metal
+echo " 9." Copy the console output from just before the modprobe to just after >> $resdir/bare-metal
+echo "   " the rmmod into this file: >> $resdir/bare-metal
+echo "   " $resdir/console.log >> $resdir/bare-metal
+echo "10." Check for runtime errors using the following command: >> $resdir/bare-metal
+echo "   " $ tools/testing/selftests/rcutorture/bin/kvm-recheck.sh `dirname $resdir` >> $resdir/bare-metal
+echo >> $resdir/bare-metal
+echo Some of the above steps may be skipped if you build your bare-metal >> $resdir/bare-metal
+echo kernel here: `head -n 1 $testid_txt | sed -e 's/^Build directory: //'`  >> $resdir/bare-metal
+
 echo $QEMU $qemu_args -m $TORTURE_QEMU_MEM -kernel $KERNEL -append \"$qemu_append $boot_args\" $TORTURE_QEMU_GDB_ARG > $resdir/qemu-cmd
 echo "# TORTURE_SHUTDOWN_GRACE=$TORTURE_SHUTDOWN_GRACE" >> $resdir/qemu-cmd
 echo "# seconds=$seconds" >> $resdir/qemu-cmd
+echo "# TORTURE_KCONFIG_GDB_ARG=\"$TORTURE_KCONFIG_GDB_ARG\"" >> $resdir/qemu-cmd
+echo "# TORTURE_JITTER_START=\"$TORTURE_JITTER_START\"" >> $resdir/qemu-cmd
+echo "# TORTURE_JITTER_STOP=\"$TORTURE_JITTER_STOP\"" >> $resdir/qemu-cmd
+echo "# TORTURE_TRUST_MAKE=\"$TORTURE_TRUST_MAKE\"; export TORTURE_TRUST_MAKE" >> $resdir/qemu-cmd
 
 if test -n "$TORTURE_BUILDONLY"
 then
@@ -167,140 +213,4 @@ then
 	exit 0
 fi
 
-# Decorate qemu-cmd with redirection, backgrounding, and PID capture
+kvm-test-1-run-qemu.sh $resdir
-sed -e 's/$/ 2>\&1 \&/' < $resdir/qemu-cmd > $T/qemu-cmd
-echo 'echo $! > $resdir/qemu_pid' >> $T/qemu-cmd
-
-# In case qemu refuses to run...
-echo "NOTE: $QEMU either did not run or was interactive" > $resdir/console.log
-
-# Attempt to run qemu
-kstarttime=`gawk 'BEGIN { print systime() }' < /dev/null`
-( . $T/qemu-cmd; wait `cat  $resdir/qemu_pid`; echo $? > $resdir/qemu-retval ) &
-commandcompleted=0
-if test -z "$TORTURE_KCONFIG_GDB_ARG"
-then
-	sleep 10 # Give qemu's pid a chance to reach the file
-	if test -s "$resdir/qemu_pid"
-	then
-		qemu_pid=`cat "$resdir/qemu_pid"`
-		echo Monitoring qemu job at pid $qemu_pid
-	else
-		qemu_pid=""
-		echo Monitoring qemu job at yet-as-unknown pid
-	fi
-fi
-if test -n "$TORTURE_KCONFIG_GDB_ARG"
-then
-	echo Waiting for you to attach a debug session, for example: > /dev/tty
-	echo "    gdb $base_resdir/vmlinux" > /dev/tty
-	echo 'After symbols load and the "(gdb)" prompt appears:' > /dev/tty
-	echo "    target remote :1234" > /dev/tty
-	echo "    continue" > /dev/tty
-	kstarttime=`gawk 'BEGIN { print systime() }' < /dev/null`
-fi
-while :
-do
-	if test -z "$qemu_pid" -a -s "$resdir/qemu_pid"
-	then
-		qemu_pid=`cat "$resdir/qemu_pid"`
-	fi
-	kruntime=`gawk 'BEGIN { print systime() - '"$kstarttime"' }' < /dev/null`
-	if test -z "$qemu_pid" || kill -0 "$qemu_pid" > /dev/null 2>&1
-	then
-		if test -n "$TORTURE_KCONFIG_GDB_ARG"
-		then
-			:
-		elif test $kruntime -ge $seconds || test -f "$resdir/../STOP.1"
-		then
-			break;
-		fi
-		sleep 1
-	else
-		commandcompleted=1
-		if test $kruntime -lt $seconds
-		then
-			echo Completed in $kruntime vs. $seconds >> $resdir/Warnings 2>&1
-			grep "^(qemu) qemu:" $resdir/kvm-test-1-run.sh.out >> $resdir/Warnings 2>&1
-			killpid="`sed -n "s/^(qemu) qemu: terminating on signal [0-9]* from pid \([0-9]*\).*$/\1/p" $resdir/Warnings`"
-			if test -n "$killpid"
-			then
-				echo "ps -fp $killpid" >> $resdir/Warnings 2>&1
-				ps -fp $killpid >> $resdir/Warnings 2>&1
-			fi
-			# Reduce probability of PID reuse by allowing a one-minute buffer
-			if test $((kruntime + 60)) -lt $seconds && test -s "$resdir/../jitter_pids"
-			then
-				awk < "$resdir/../jitter_pids" '
-				NF > 0 {
-					pidlist = pidlist " " $1;
-					n++;
-				}
-				END {
-					if (n > 0) {
-						print "kill " pidlist;
-					}
-				}' | sh
-			fi
-		else
-			echo ' ---' `date`: "Kernel done"
-		fi
-		break
-	fi
-done
-if test -z "$qemu_pid" -a -s "$resdir/qemu_pid"
-then
-	qemu_pid=`cat "$resdir/qemu_pid"`
-fi
-if test $commandcompleted -eq 0 -a -n "$qemu_pid"
-then
-	if ! test -f "$resdir/../STOP.1"
-	then
-		echo Grace period for qemu job at pid $qemu_pid
-	fi
-	oldline="`tail $resdir/console.log`"
-	while :
-	do
-		if test -f "$resdir/../STOP.1"
-		then
-			echo "PID $qemu_pid killed due to run STOP.1 request" >> $resdir/Warnings 2>&1
-			kill -KILL $qemu_pid
-			break
-		fi
-		kruntime=`gawk 'BEGIN { print systime() - '"$kstarttime"' }' < /dev/null`
-		if kill -0 $qemu_pid > /dev/null 2>&1
-		then
-			:
-		else
-			break
-		fi
-		must_continue=no
-		newline="`tail $resdir/console.log`"
-		if test "$newline" != "$oldline" && echo $newline | grep -q ' [0-9]\+us : '
-		then
-			must_continue=yes
-		fi
-		last_ts="`tail $resdir/console.log | grep '^\[ *[0-9]\+\.[0-9]\+]' | tail -1 | sed -e 's/^\[ *//' -e 's/\..*$//'`"
-		if test -z "$last_ts"
-		then
-			last_ts=0
-		fi
-		if test "$newline" != "$oldline" -a "$last_ts" -lt $((seconds + $TORTURE_SHUTDOWN_GRACE))
-		then
-			must_continue=yes
-		fi
-		if test $must_continue = no -a $kruntime -ge $((seconds + $TORTURE_SHUTDOWN_GRACE))
-		then
-			echo "!!! PID $qemu_pid hung at $kruntime vs. $seconds seconds" >> $resdir/Warnings 2>&1
-			kill -KILL $qemu_pid
-			break
-		fi
-		oldline=$newline
-		sleep 10
-	done
-elif test -z "$qemu_pid"
-then
-	echo Unknown PID, cannot kill qemu command
-fi
-
-parse-console.sh $resdir/console.log $title

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

@@ -3,7 +3,7 @@
 #
 # Transform a qemu-cmd file to allow reuse.
 #
-# Usage: kvm-transform.sh bzImage console.log < qemu-cmd-in > qemu-cmd-out
+# Usage: kvm-transform.sh bzImage console.log jitter_dir [ seconds ] < qemu-cmd-in > qemu-cmd-out
 #
 #	bzImage: Kernel and initrd from the same prior kvm.sh run.
 #	console.log: File into which to place console output.
@@ -29,20 +29,62 @@ then
 	echo "Need console log file name."
 	exit 1
 fi
+jitter_dir="$3"
+if test -z "$jitter_dir" || ! test -d "$jitter_dir"
+then
+	echo "Need valid jitter directory: '$jitter_dir'"
+	exit 1
+fi
+seconds="$4"
+if test -n "$seconds" && echo $seconds | grep -q '[^0-9]'
+then
+	echo "Invalid duration, should be numeric in seconds: '$seconds'"
+	exit 1
+fi
+
+awk -v image="$image" -v consolelog="$consolelog" -v jitter_dir="$jitter_dir" \
+    -v seconds="$seconds" '
+/^# seconds=/ {
+	if (seconds == "")
+		print $0;
+	else
+		print "# seconds=" seconds;
+	next;
+}
+
+/^# TORTURE_JITTER_START=/ {
+	print "# TORTURE_JITTER_START=\". jitterstart.sh " $4 " " jitter_dir " " $6 " " $7;
+	next;
+}
+
+/^# TORTURE_JITTER_STOP=/ {
+	print "# TORTURE_JITTER_STOP=\". jitterstop.sh " " " jitter_dir " " $5;
+	next;
+}
+
+/^#/ {
+	print $0;
+	next;
+}
 
-awk -v image="$image" -v consolelog="$consolelog" '
 {
 	line = "";
 	for (i = 1; i <= NF; i++) {
-		if (line == "")
+		if ("" seconds != "" && $i ~ /\.shutdown_secs=[0-9]*$/) {
+			sub(/[0-9]*$/, seconds, $i);
+			if (line == "")
+				line = $i;
+			else
+				line = line " " $i;
+		} else if (line == "") {
 			line = $i;
-		else
+		} else {
 			line = line " " $i;
+		}
 		if ($i == "-serial") {
 			i++;
 			line = line " file:" consolelog;
-		}
+		} else if ($i == "-kernel") {
-		if ($i == "-kernel") {
 			i++;
 			line = line " " image;
 		}

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

@@ -29,17 +29,21 @@ PATH=${KVM}/bin:$PATH; export PATH
 TORTURE_ALLOTED_CPUS="`identify_qemu_vcpus`"
 TORTURE_DEFCONFIG=defconfig
 TORTURE_BOOT_IMAGE=""
+TORTURE_BUILDONLY=
 TORTURE_INITRD="$KVM/initrd"; export TORTURE_INITRD
 TORTURE_KCONFIG_ARG=""
 TORTURE_KCONFIG_GDB_ARG=""
 TORTURE_BOOT_GDB_ARG=""
 TORTURE_QEMU_GDB_ARG=""
+TORTURE_JITTER_START=""
+TORTURE_JITTER_STOP=""
 TORTURE_KCONFIG_KASAN_ARG=""
 TORTURE_KCONFIG_KCSAN_ARG=""
 TORTURE_KMAKE_ARG=""
 TORTURE_QEMU_MEM=512
 TORTURE_SHUTDOWN_GRACE=180
 TORTURE_SUITE=rcu
+TORTURE_MOD=rcutorture
 TORTURE_TRUST_MAKE=""
 resdir=""
 configs=""
@@ -100,7 +104,7 @@ do
 		TORTURE_BUILDONLY=1
 		;;
 	--configs|--config)
-		checkarg --configs "(list of config files)" "$#" "$2" '^[^/]\+$' '^--'
+		checkarg --configs "(list of config files)" "$#" "$2" '^[^/.a-z]\+$' '^--'
 		configs="$configs $2"
 		shift
 		;;
@@ -116,7 +120,7 @@ do
 		shift
 		;;
 	--datestamp)
-		checkarg --datestamp "(relative pathname)" "$#" "$2" '^[a-zA-Z0-9._-/]*$' '^--'
+		checkarg --datestamp "(relative pathname)" "$#" "$2" '^[a-zA-Z0-9._/-]*$' '^--'
 		ds=$2
 		shift
 		;;
@@ -215,6 +219,7 @@ do
 	--torture)
 		checkarg --torture "(suite name)" "$#" "$2" '^\(lock\|rcu\|rcuscale\|refscale\|scf\)$' '^--'
 		TORTURE_SUITE=$2
+		TORTURE_MOD="`echo $TORTURE_SUITE | sed -e 's/^\(lock\|rcu\|scf\)$/\1torture/'`"
 		shift
 		if test "$TORTURE_SUITE" = rcuscale || test "$TORTURE_SUITE" = refscale
 		then
@@ -381,6 +386,7 @@ TORTURE_QEMU_GDB_ARG="$TORTURE_QEMU_GDB_ARG"; export TORTURE_QEMU_GDB_ARG
 TORTURE_KCONFIG_KASAN_ARG="$TORTURE_KCONFIG_KASAN_ARG"; export TORTURE_KCONFIG_KASAN_ARG
 TORTURE_KCONFIG_KCSAN_ARG="$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_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
@@ -399,12 +405,17 @@ echo Results directory: $resdir/$ds
 echo $scriptname $args
 touch $resdir/$ds/log
 echo $scriptname $args >> $resdir/$ds/log
-echo ${TORTURE_SUITE} > $resdir/$ds/TORTURE_SUITE
+echo ${TORTURE_SUITE} > $resdir/$ds/torture_suite
-pwd > $resdir/$ds/testid.txt
+echo Build directory: `pwd` > $resdir/$ds/testid.txt
 if test -d .git
 then
+	echo Current commit: `git rev-parse HEAD` >> $resdir/$ds/testid.txt
+	echo >> $resdir/$ds/testid.txt
+	echo ' ---' Output of "'"git status"'": >> $resdir/$ds/testid.txt
 	git status >> $resdir/$ds/testid.txt
-	git rev-parse HEAD >> $resdir/$ds/testid.txt
+	echo >> $resdir/$ds/testid.txt
+	echo >> $resdir/$ds/testid.txt
+	echo ' ---' Output of "'"git diff HEAD"'": >> $resdir/$ds/testid.txt
 	git diff HEAD >> $resdir/$ds/testid.txt
 fi
 ___EOF___
@@ -434,42 +445,6 @@ function dump(first, pastlast, batchnum)
 	print "echo ----Start batch " batchnum ": `date` | tee -a " rd "log";
 	print "needqemurun="
 	jn=1
-	for (j = first; j < pastlast; j++) {
-		builddir=KVM "/b" j - first + 1
-		cpusr[jn] = cpus[j];
-		if (cfrep[cf[j]] == "") {
-			cfr[jn] = cf[j];
-			cfrep[cf[j]] = 1;
-		} else {
-			cfrep[cf[j]]++;
-			cfr[jn] = cf[j] "." cfrep[cf[j]];
-		}
-		if (cpusr[jn] > ncpus && ncpus != 0)
-			ovf = "-ovf";
-		else
-			ovf = "";
-		print "echo ", cfr[jn], cpusr[jn] ovf ": Starting build. `date` | tee -a " rd "log";
-		print "rm -f " builddir ".*";
-		print "touch " builddir ".wait";
-		print "mkdir " rd cfr[jn] " || :";
-		print "kvm-test-1-run.sh " CONFIGDIR cf[j], builddir, rd cfr[jn], dur " \"" TORTURE_QEMU_ARG "\" \"" TORTURE_BOOTARGS "\" > " rd cfr[jn]  "/kvm-test-1-run.sh.out 2>&1 &"
-		print "echo ", cfr[jn], cpusr[jn] ovf ": Waiting for build to complete. `date` | tee -a " rd "log";
-		print "while test -f " builddir ".wait"
-		print "do"
-		print "\tsleep 1"
-		print "done"
-		print "echo ", cfr[jn], cpusr[jn] ovf ": Build complete. `date` | tee -a " rd "log";
-		jn++;
-	}
-	for (j = 1; j < jn; j++) {
-		builddir=KVM "/b" j
-		print "rm -f " builddir ".ready"
-		print "if test -f \"" rd cfr[j] "/builtkernel\""
-		print "then"
-		print "\techo ----", cfr[j], cpusr[j] ovf ": Kernel present. `date` | tee -a " rd "log";
-		print "\tneedqemurun=1"
-		print "fi"
-	}
 	njitter = 0;
 	split(jitter, ja);
 	if (ja[1] == -1 && ncpus == 0)
@@ -478,6 +453,49 @@ function dump(first, pastlast, batchnum)
 		njitter = ncpus;
 	else
 		njitter = ja[1];
+	print "TORTURE_JITTER_START=\". jitterstart.sh " njitter " " rd " " dur " " ja[2] " " ja[3] "\"; export TORTURE_JITTER_START";
+	print "TORTURE_JITTER_STOP=\". jitterstop.sh " rd " \"; export TORTURE_JITTER_STOP"
+	for (j = first; j < pastlast; j++) {
+		cpusr[jn] = cpus[j];
+		if (cfrep[cf[j]] == "") {
+			cfr[jn] = cf[j];
+			cfrep[cf[j]] = 1;
+		} else {
+			cfrep[cf[j]]++;
+			cfr[jn] = cf[j] "." cfrep[cf[j]];
+		}
+		builddir=rd cfr[jn] "/build";
+		if (cpusr[jn] > ncpus && ncpus != 0)
+			ovf = "-ovf";
+		else
+			ovf = "";
+		print "echo ", cfr[jn], cpusr[jn] ovf ": Starting build. `date` | tee -a " rd "log";
+		print "mkdir " rd cfr[jn] " || :";
+		print "touch " builddir ".wait";
+		print "kvm-test-1-run.sh " CONFIGDIR cf[j], rd cfr[jn], dur " \"" TORTURE_QEMU_ARG "\" \"" TORTURE_BOOTARGS "\" > " rd cfr[jn]  "/kvm-test-1-run.sh.out 2>&1 &"
+		print "echo ", cfr[jn], cpusr[jn] ovf ": Waiting for build to complete. `date` | tee -a " rd "log";
+		print "while test -f " builddir ".wait"
+		print "do"
+		print "\tsleep 1"
+		print "done"
+		print "echo ", cfr[jn], cpusr[jn] ovf ": Build complete. `date` | tee -a " rd "log";
+		jn++;
+	}
+	print "runfiles="
+	for (j = 1; j < jn; j++) {
+		builddir=rd cfr[j] "/build";
+		if (TORTURE_BUILDONLY)
+			print "rm -f " builddir ".ready"
+		else
+			print "mv " builddir ".ready " builddir ".run"
+			print "runfiles=\"$runfiles " builddir ".run\""
+		fi
+		print "if test -f \"" rd cfr[j] "/builtkernel\""
+		print "then"
+		print "\techo ----", cfr[j], cpusr[j] ovf ": Kernel present. `date` | tee -a " rd "log";
+		print "\tneedqemurun=1"
+		print "fi"
+	}
 	if (TORTURE_BUILDONLY && njitter != 0) {
 		njitter = 0;
 		print "echo Build-only run, so suppressing jitter | tee -a " rd "log"
@@ -488,19 +506,18 @@ function dump(first, pastlast, batchnum)
 	print "if test -n \"$needqemurun\""
 	print "then"
 	print "\techo ---- Starting kernels. `date` | tee -a " rd "log";
-	print "\techo > " rd "jitter_pids"
+	print "\t$TORTURE_JITTER_START";
-	for (j = 0; j < njitter; j++) {
+	print "\twhile ls $runfiles > /dev/null 2>&1"
-		print "\tjitter.sh " j " " dur " " ja[2] " " ja[3] "&"
+	print "\tdo"
-		print "\techo $! >> " rd "jitter_pids"
+	print "\t\t:"
-	}
+	print "\tdone"
-	print "\twait"
+	print "\t$TORTURE_JITTER_STOP";
 	print "\techo ---- All kernel runs complete. `date` | tee -a " rd "log";
 	print "else"
 	print "\twait"
 	print "\techo ---- No kernel runs. `date` | tee -a " rd "log";
 	print "fi"
 	for (j = 1; j < jn; j++) {
-		builddir=KVM "/b" j
 		print "echo ----", cfr[j], cpusr[j] ovf ": Build/run results: | tee -a " rd "log";
 		print "cat " rd cfr[j]  "/kvm-test-1-run.sh.out | tee -a " rd "log";
 	}
@@ -548,6 +565,18 @@ echo 'ret=$?' >> $T/script
 echo "cat $T/kvm-recheck.sh.out | tee -a $resdir/$ds/log" >> $T/script
 echo 'exit $ret' >> $T/script
 
+# Extract the tests and their batches from the script.
+egrep 'Start batch|Starting build\.' $T/script | grep -v ">>" |
+	sed -e 's/:.*$//' -e 's/^echo //' -e 's/-ovf//' |
+	awk '
+	/^----Start/ {
+		batchno = $3;
+		next;
+	}
+	{
+		print batchno, $1, $2
+	}' > $T/batches
+
 if test "$dryrun" = script
 then
 	cat $T/script
@@ -566,21 +595,14 @@ then
 	exit 0
 elif test "$dryrun" = batches
 then
-	# Extract the tests and their batches from the script.
+	cat $T/batches
-	egrep 'Start batch|Starting build\.' $T/script | grep -v ">>" |
+	exit 0
-		sed -e 's/:.*$//' -e 's/^echo //' -e 's/-ovf//' |
-		awk '
-		/^----Start/ {
-			batchno = $3;
-			next;
-		}
-		{
-			print batchno, $1, $2
-		}'
 else
-	# Not a dryrun, so run the script.
+	# Not a dryrun.  Record the batches and the number of CPUs, then run the script.
 	bash $T/script
 	ret=$?
+	cp $T/batches $resdir/$ds/batches
+	echo '#' cpus=$cpus >> $resdir/$ds/batches
 	echo " --- Done at `date` (`get_starttime_duration $starttime`) exitcode $ret" | tee -a $resdir/$ds/log
 	exit $ret
 fi

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

@@ -374,7 +374,7 @@ done
 if test "$do_kvfree" = "yes"
 then
 	torture_bootargs="rcuscale.kfree_rcu_test=1 rcuscale.kfree_nthreads=16 rcuscale.holdoff=20 rcuscale.kfree_loops=10000 torture.disable_onoff_at_boot"
-	torture_set "rcuscale-kvfree" tools/testing/selftests/rcutorture/bin/kvm.sh --torture rcuscale --allcpus --duration 10 --kconfig "CONFIG_NR_CPUS=$HALF_ALLOTED_CPUS" --trust-make
+	torture_set "rcuscale-kvfree" tools/testing/selftests/rcutorture/bin/kvm.sh --torture rcuscale --allcpus --duration 10 --kconfig "CONFIG_NR_CPUS=$HALF_ALLOTED_CPUS" --memory 1G --trust-make
 fi
 
 echo " --- " $scriptname $args

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

@@ -7,8 +7,8 @@ TREE07
 TREE09
 SRCU-N
 SRCU-P
-SRCU-t
+SRCU-T
-SRCU-u
+SRCU-U
 TINY01
 TINY02
 TASKS01

tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot

@@ -4,3 +4,4 @@ rcutree.gp_init_delay=3
 rcutree.gp_cleanup_delay=3
 rcutree.kthread_prio=2
 threadirqs
+tree.use_softirq=0

tools/testing/selftests/rcutorture/configs/rcu/TREE04.boot

@@ -1 +1 @@
-rcutree.rcu_fanout_leaf=4 nohz_full=1-7
+rcutree.rcu_fanout_leaf=4 nohz_full=1-N

tools/testing/selftests/rcutorture/configs/rcu/TREE08.boot

@@ -1,3 +1,3 @@
 rcupdate.rcu_self_test=1
 rcutree.rcu_fanout_exact=1
-rcu_nocbs=0-7
+rcu_nocbs=all

tools/testing/selftests/rcutorture/configs/rcuscale/ver_functions.sh

@@ -12,5 +12,5 @@
 # Adds per-version torture-module parameters to kernels supporting them.
 per_version_boot_params () {
 	echo $1 rcuscale.shutdown=1 \
-		rcuscale.verbose=1
+		rcuscale.verbose=0
 }

tools/testing/selftests/rcutorture/configs/refscale/ver_functions.sh

@@ -12,5 +12,5 @@
 # Adds per-version torture-module parameters to kernels supporting them.
 per_version_boot_params () {
 	echo $1 refscale.shutdown=1 \
-		refscale.verbose=1
+		refscale.verbose=0
 }