Merge branches 'doc.2020.06.29a', 'fixes.2020.06.29a', 'kfree_rcu.2020.06.29a', 'rcu-tasks.2020.06.29a', 'scale.2020.06.29a', 'srcu.2020.06.29a' and 'torture.2020.06.29a' into HEAD

doc.2020.06.29a:  Documentation updates.
fixes.2020.06.29a:  Miscellaneous fixes.
kfree_rcu.2020.06.29a:  kfree_rcu() updates.
rcu-tasks.2020.06.29a:  RCU Tasks updates.
scale.2020.06.29a:  Read-side scalability tests.
srcu.2020.06.29a:  SRCU updates.
torture.2020.06.29a:  Torture-test updates.

Author: paulmckrcu

Documentation/admin-guide/kernel-parameters.txt

@@ -4038,6 +4038,14 @@
 			latencies, which will choose a value aligned
 			with the appropriate hardware boundaries.
 
+	rcutree.rcu_min_cached_objs= [KNL]
+			Minimum number of objects which are cached and
+			maintained per one CPU. Object size is equal
+			to PAGE_SIZE. The cache allows to reduce the
+			pressure to page allocator, also it makes the
+			whole algorithm to behave better in low memory
+			condition.
+
 	rcutree.jiffies_till_first_fqs= [KNL]
 			Set delay from grace-period initialization to
 			first attempt to force quiescent states.
@@ -4258,6 +4266,20 @@
 			Set time (jiffies) between CPU-hotplug operations,
 			or zero to disable CPU-hotplug testing.
 
+	rcutorture.read_exit= [KNL]
+			Set the number of read-then-exit kthreads used
+			to test the interaction of RCU updaters and
+			task-exit processing.
+
+	rcutorture.read_exit_burst= [KNL]
+			The number of times in a given read-then-exit
+			episode that a set of read-then-exit kthreads
+			is spawned.
+
+	rcutorture.read_exit_delay= [KNL]
+			The delay, in seconds, between successive
+			read-then-exit testing episodes.
+
 	rcutorture.shuffle_interval= [KNL]
 			Set task-shuffle interval (s).  Shuffling tasks
 			allows some CPUs to go into dyntick-idle mode
@@ -4407,6 +4429,45 @@
 			      reboot_cpu is s[mp]#### with #### being the processor
 					to be used for rebooting.
 
+	refscale.holdoff= [KNL]
+			Set test-start holdoff period.  The purpose of
+			this parameter is to delay the start of the
+			test until boot completes in order to avoid
+			interference.
+
+	refscale.loops= [KNL]
+			Set the number of loops over the synchronization
+			primitive under test.  Increasing this number
+			reduces noise due to loop start/end overhead,
+			but the default has already reduced the per-pass
+			noise to a handful of picoseconds on ca. 2020
+			x86 laptops.
+
+	refscale.nreaders= [KNL]
+			Set number of readers.  The default value of -1
+			selects N, where N is roughly 75% of the number
+			of CPUs.  A value of zero is an interesting choice.
+
+	refscale.nruns= [KNL]
+			Set number of runs, each of which is dumped onto
+			the console log.
+
+	refscale.readdelay= [KNL]
+			Set the read-side critical-section duration,
+			measured in microseconds.
+
+	refscale.scale_type= [KNL]
+			Specify the read-protection implementation to test.
+
+	refscale.shutdown= [KNL]
+			Shut down the system at the end of the performance
+			test.  This defaults to 1 (shut it down) when
+			rcuperf is built into the kernel and to 0 (leave
+			it running) when rcuperf is built as a module.
+
+	refscale.verbose= [KNL]
+			Enable additional printk() statements.
+
 	relax_domain_level=
 			[KNL, SMP] Set scheduler's default relax_domain_level.
 			See Documentation/admin-guide/cgroup-v1/cpusets.rst.
@@ -5082,6 +5143,13 @@
 			Prevent the CPU-hotplug component of torturing
 			until after init has spawned.
 
+	torture.ftrace_dump_at_shutdown= [KNL]
+			Dump the ftrace buffer at torture-test shutdown,
+			even if there were no errors.  This can be a
+			very costly operation when many torture tests
+			are running concurrently, especially on systems
+			with rotating-rust storage.
+
 	tp720=		[HW,PS2]
 
 	tpm_suspend_pcr=[HW,TPM]

fs/btrfs/extent_io.c

@@ -4515,6 +4515,8 @@ int try_release_extent_mapping(struct page *page, gfp_t mask)
 
 			/* once for us */
 			free_extent_map(em);
+
+			cond_resched(); /* Allow large-extent preemption. */
 		}
 	}
 	return try_release_extent_state(tree, page, mask);

include/linux/rculist.h

@@ -512,7 +512,7 @@ static inline void hlist_replace_rcu(struct hlist_node *old,
  * @right: The hlist head on the right
  *
  * The lists start out as [@left  ][node1 ... ] and
-                          [@right ][node2 ... ]
+ *                        [@right ][node2 ... ]
  * The lists end up as    [@left  ][node2 ... ]
  *                        [@right ][node1 ... ]
  */

include/linux/rcupdate.h

@@ -828,17 +828,17 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
 
 /*
  * Does the specified offset indicate that the corresponding rcu_head
- * structure can be handled by kfree_rcu()?
+ * structure can be handled by kvfree_rcu()?
  */
-#define __is_kfree_rcu_offset(offset) ((offset) < 4096)
+#define __is_kvfree_rcu_offset(offset) ((offset) < 4096)
 
 /*
  * Helper macro for kfree_rcu() to prevent argument-expansion eyestrain.
  */
-#define __kfree_rcu(head, offset) \
+#define __kvfree_rcu(head, offset) \
 	do { \
-		BUILD_BUG_ON(!__is_kfree_rcu_offset(offset)); \
-		kfree_call_rcu(head, (rcu_callback_t)(unsigned long)(offset)); \
+		BUILD_BUG_ON(!__is_kvfree_rcu_offset(offset)); \
+		kvfree_call_rcu(head, (rcu_callback_t)(unsigned long)(offset)); \
 	} while (0)
 
 /**
@@ -857,7 +857,7 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
  * Because the functions are not allowed in the low-order 4096 bytes of
  * kernel virtual memory, offsets up to 4095 bytes can be accommodated.
  * If the offset is larger than 4095 bytes, a compile-time error will
- * be generated in __kfree_rcu().  If this error is triggered, you can
+ * be generated in __kvfree_rcu(). If this error is triggered, you can
  * either fall back to use of call_rcu() or rearrange the structure to
  * position the rcu_head structure into the first 4096 bytes.
  *
@@ -872,7 +872,46 @@ do {									\
 	typeof (ptr) ___p = (ptr);					\
 									\
 	if (___p)							\
-		__kfree_rcu(&((___p)->rhf), offsetof(typeof(*(ptr)), rhf)); \
+		__kvfree_rcu(&((___p)->rhf), offsetof(typeof(*(ptr)), rhf)); \
+} while (0)
+
+/**
+ * kvfree_rcu() - kvfree an object after a grace period.
+ *
+ * This macro consists of one or two arguments and it is
+ * based on whether an object is head-less or not. If it
+ * has a head then a semantic stays the same as it used
+ * to be before:
+ *
+ *     kvfree_rcu(ptr, rhf);
+ *
+ * where @ptr is a pointer to kvfree(), @rhf is the name
+ * of the rcu_head structure within the type of @ptr.
+ *
+ * When it comes to head-less variant, only one argument
+ * is passed and that is just a pointer which has to be
+ * freed after a grace period. Therefore the semantic is
+ *
+ *     kvfree_rcu(ptr);
+ *
+ * where @ptr is a pointer to kvfree().
+ *
+ * Please note, head-less way of freeing is permitted to
+ * use from a context that has to follow might_sleep()
+ * annotation. Otherwise, please switch and embed the
+ * rcu_head structure within the type of @ptr.
+ */
+#define kvfree_rcu(...) KVFREE_GET_MACRO(__VA_ARGS__,		\
+	kvfree_rcu_arg_2, kvfree_rcu_arg_1)(__VA_ARGS__)
+
+#define KVFREE_GET_MACRO(_1, _2, NAME, ...) NAME
+#define kvfree_rcu_arg_2(ptr, rhf) kfree_rcu(ptr, rhf)
+#define kvfree_rcu_arg_1(ptr)					\
+do {								\
+	typeof(ptr) ___p = (ptr);				\
+								\
+	if (___p)						\
+		kvfree_call_rcu(NULL, (rcu_callback_t) (___p));	\
 } while (0)
 
 /*

include/linux/rcupdate_trace.h

@@ -36,8 +36,8 @@ void rcu_read_unlock_trace_special(struct task_struct *t, int nesting);
 /**
  * rcu_read_lock_trace - mark beginning of RCU-trace read-side critical section
  *
- * When synchronize_rcu_trace() is invoked by one task, then that task
- * is guaranteed to block until all other tasks exit their read-side
+ * When synchronize_rcu_tasks_trace() is invoked by one task, then that
+ * task is guaranteed to block until all other tasks exit their read-side
  * critical sections.  Similarly, if call_rcu_trace() is invoked on one
  * task while other tasks are within RCU read-side critical sections,
  * invocation of the corresponding RCU callback is deferred until after

include/linux/rcutiny.h

@@ -34,9 +34,25 @@ static inline void synchronize_rcu_expedited(void)
 	synchronize_rcu();
 }
 
-static inline void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
+/*
+ * Add one more declaration of kvfree() here. It is
+ * not so straight forward to just include <linux/mm.h>
+ * where it is defined due to getting many compile
+ * errors caused by that include.
+ */
+extern void kvfree(const void *addr);
+
+static inline void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 {
-	call_rcu(head, func);
+	if (head) {
+		call_rcu(head, func);
+		return;
+	}
+
+	// kvfree_rcu(one_arg) call.
+	might_sleep();
+	synchronize_rcu();
+	kvfree((void *) func);
 }
 
 void rcu_qs(void);

include/linux/rcutree.h

@@ -33,7 +33,7 @@ static inline void rcu_virt_note_context_switch(int cpu)
 }
 
 void synchronize_rcu_expedited(void);
-void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func);
+void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func);
 
 void rcu_barrier(void);
 bool rcu_eqs_special_set(int cpu);

include/linux/torture.h

@@ -55,6 +55,11 @@ struct torture_random_state {
 #define DEFINE_TORTURE_RANDOM_PERCPU(name) \
 	DEFINE_PER_CPU(struct torture_random_state, name)
 unsigned long torture_random(struct torture_random_state *trsp);
+static inline void torture_random_init(struct torture_random_state *trsp)
+{
+	trsp->trs_state = 0;
+	trsp->trs_count = 0;
+}
 
 /* Task shuffler, which causes CPUs to occasionally go idle. */
 void torture_shuffle_task_register(struct task_struct *tp);

include/trace/events/rcu.h

@@ -435,11 +435,12 @@ TRACE_EVENT_RCU(rcu_fqs,
 #endif /* #if defined(CONFIG_TREE_RCU) */
 
 /*
- * Tracepoint for dyntick-idle entry/exit events.  These take a string
- * as argument: "Start" for entering dyntick-idle mode, "Startirq" for
- * entering it from irq/NMI, "End" for leaving it, "Endirq" for leaving it
- * to irq/NMI, "--=" for events moving towards idle, and "++=" for events
- * moving away from idle.
+ * Tracepoint for dyntick-idle entry/exit events.  These take 2 strings
+ * as argument:
+ * polarity: "Start", "End", "StillNonIdle" for entering, exiting or still not
+ *            being in dyntick-idle mode.
+ * context: "USER" or "IDLE" or "IRQ".
+ * NMIs nested in IRQs are inferred with dynticks_nesting > 1 in IRQ context.
  *
  * These events also take a pair of numbers, which indicate the nesting
  * depth before and after the event of interest, and a third number that is
@@ -506,13 +507,13 @@ TRACE_EVENT_RCU(rcu_callback,
 
 /*
  * Tracepoint for the registration of a single RCU callback of the special
- * kfree() form.  The first argument is the RCU type, the second argument
+ * kvfree() form.  The first argument is the RCU type, the second argument
  * is a pointer to the RCU callback, the third argument is the offset
  * of the callback within the enclosing RCU-protected data structure,
  * the fourth argument is the number of lazy callbacks queued, and the
  * fifth argument is the total number of callbacks queued.
  */
-TRACE_EVENT_RCU(rcu_kfree_callback,
+TRACE_EVENT_RCU(rcu_kvfree_callback,
 
 	TP_PROTO(const char *rcuname, struct rcu_head *rhp, unsigned long offset,
 		 long qlen),
@@ -596,12 +597,12 @@ TRACE_EVENT_RCU(rcu_invoke_callback,
 
 /*
  * Tracepoint for the invocation of a single RCU callback of the special
- * kfree() form.  The first argument is the RCU flavor, the second
+ * kvfree() form.  The first argument is the RCU flavor, the second
  * argument is a pointer to the RCU callback, and the third argument
  * is the offset of the callback within the enclosing RCU-protected
  * data structure.
  */
-TRACE_EVENT_RCU(rcu_invoke_kfree_callback,
+TRACE_EVENT_RCU(rcu_invoke_kvfree_callback,
 
 	TP_PROTO(const char *rcuname, struct rcu_head *rhp, unsigned long offset),
 

kernel/locking/lockdep.c

@@ -5851,9 +5851,7 @@ void lockdep_rcu_suspicious(const char *file, const int line, const char *s)
 	pr_warn("\n%srcu_scheduler_active = %d, debug_locks = %d\n",
 	       !rcu_lockdep_current_cpu_online()
 			? "RCU used illegally from offline CPU!\n"
-			: !rcu_is_watching()
-				? "RCU used illegally from idle CPU!\n"
-				: "",
+			: "",
 	       rcu_scheduler_active, debug_locks);
 
 	/*