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
  ...

54 files changed, 1304 insertions, 422 deletions

diff --git a/Documentation/RCU/RTFP.txt b/Documentation/RCU/RTFP.txt
index 3b0876c77355..588d97366a46 100644
--- a/Documentation/RCU/RTFP.txt
+++ b/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.
 }
 }
 
diff --git a/Documentation/admin-guide/kernel-parameters.rst b/Documentation/admin-guide/kernel-parameters.rst
index 24302cad174a..3996b54158bf 100644
--- a/Documentation/admin-guide/kernel-parameters.rst
+++ b/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
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 70a30f65bfca..fa08ec0dfbe7 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/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,
-			except that the string "all" can be used to
-			specify every CPU on the system.
+			The argument is a cpu list, as described above.
 
 			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().
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 06094627f1c1..21115933b9b8 100644
--- a/include/linux/mm.h
+++ b/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 */
diff --git a/include/linux/rcu_segcblist.h b/include/linux/rcu_segcblist.h
index 8afe886e85f1..3db96c4f45fd 100644
--- a/include/linux/rcu_segcblist.h
+++ b/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
diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h
index ff3e94779e73..d8afdb8784c1 100644
--- a/include/linux/rculist_nulls.h
+++ b/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)			\
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 6d855ef091ba..9455476c5ba2 100644
--- a/include/linux/rcupdate.h
+++ b/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.
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 2a97334eb786..35e0be326ffc 100644
--- a/include/linux/rcutiny.h
+++ b/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)
-{
-	return 0;
-}
+unsigned long get_state_synchronize_rcu(void);
+unsigned long start_poll_synchronize_rcu(void);
+bool poll_state_synchronize_rcu(unsigned long oldstate);
 
 static inline void cond_synchronize_rcu(unsigned long oldstate)
 {
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index df578b73960f..b89b54130f49 100644
--- a/include/linux/rcutree.h
+++ b/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);
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 7ae604076767..0c97d788762c 100644
--- a/include/linux/slab.h
+++ b/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,
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index df92211cf771..3de7be6dd17c 100644
--- a/include/linux/vmalloc.h
+++ b/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; }
diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index 5fc29400e1a2..c7711e9b6900 100644
--- a/include/trace/events/rcu.h
+++ b/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) */
 
 /*
diff --git a/kernel/rcu/rcu_segcblist.c b/kernel/rcu/rcu_segcblist.c
index 7f181c9675f7..aaa111237b60 100644
--- a/kernel/rcu/rcu_segcblist.c
+++ b/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
- * structure must be empty.
+ * Mark the specified rcu_segcblist structure as offloaded.
  */
 void rcu_segcblist_offload(struct rcu_segcblist *rsclp, bool offload)
 {
diff --git a/kernel/rcu/rcuscale.c b/kernel/rcu/rcuscale.c
index 06491d5530db..dca51fe9c73f 100644
--- a/kernel/rcu/rcuscale.c
+++ b/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();
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 99657ffa6688..29d2f4c647d3 100644
--- a/kernel/rcu/rcutorture.c
+++ b/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)
-#define rcu_can_boost() 1
-#else /* #if defined(CONFIG_RCU_BOOST) && !defined(CONFIG_HOTPLUG_CPU) */
-#define rcu_can_boost() 0
-#endif /* #else #if defined(CONFIG_RCU_BOOST) && !defined(CONFIG_HOTPLUG_CPU) */
+#if defined(CONFIG_RCU_BOOST) && defined(CONFIG_PREEMPT_RT)
+# define rcu_can_boost() 1
+#else
+# define rcu_can_boost() 0
+#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;
+		bool failed = false; // Test failed already in this test interval
+		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 ||
-					 rcu_torture_boost_failed(call_rcu_time,
-								 jiffies);
+				if (!firsttime && !failed)
+					failed = rcu_torture_boost_failed(call_rcu_time, 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