Merge branches 'doc.2020.02.27a', 'fixes.2020.03.21a', 'kfree_rcu.202…

…0.02.20a', 'locktorture.2020.02.20a', 'ovld.2020.02.20a', 'rcu-tasks.2020.02.20a', 'srcu.2020.02.20a' and 'torture.2020.02.20a' into HEAD

doc.2020.02.27a: Documentation updates.
fixes.2020.03.21a: Miscellaneous fixes.
kfree_rcu.2020.02.20a: Updates to kfree_rcu().
locktorture.2020.02.20a: Lock torture-test updates.
ovld.2020.02.20a: Updates to callback-overload handling.
rcu-tasks.2020.02.20a: RCU-tasks updates.
srcu.2020.02.20a: SRCU updates.
torture.2020.02.20a: Torture-test updates.

Documentation/admin-guide/kernel-parameters.txt

@@ -3980,6 +3980,15 @@
 			Set threshold of queued RCU callbacks below which
 			batch limiting is re-enabled.
 
+	rcutree.qovld= [KNL]
+			Set threshold of queued RCU callbacks beyond which
+			RCU's force-quiescent-state scan will aggressively
+			enlist help from cond_resched() and sched IPIs to
+			help CPUs more quickly reach quiescent states.
+			Set to less than zero to make this be set based
+			on rcutree.qhimark at boot time and to zero to
+			disable more aggressive help enlistment.
+
 	rcutree.rcu_idle_gp_delay= [KNL]
 			Set wakeup interval for idle CPUs that have
 			RCU callbacks (RCU_FAST_NO_HZ=y).
@@ -4195,6 +4204,12 @@
 	rcupdate.rcu_cpu_stall_suppress= [KNL]
 			Suppress RCU CPU stall warning messages.
 
+	rcupdate.rcu_cpu_stall_suppress_at_boot= [KNL]
+			Suppress RCU CPU stall warning messages and
+			rcutorture writer stall warnings that occur
+			during early boot, that is, during the time
+			before the init task is spawned.
+
 	rcupdate.rcu_cpu_stall_timeout= [KNL]
 			Set timeout for RCU CPU stall warning messages.
 
@@ -4867,6 +4882,10 @@
 			topology updates sent by the hypervisor to this
 			LPAR.
 
+	torture.disable_onoff_at_boot= [KNL]
+			Prevent the CPU-hotplug component of torturing
+			until after init has spawned.
+
 	tp720=		[HW,PS2]
 
 	tpm_suspend_pcr=[HW,TPM]

fs/nfs/dir.c

@@ -2383,7 +2383,7 @@ static int nfs_access_get_cached_rcu(struct inode *inode, const struct cred *cre
 	rcu_read_lock();
 	if (nfsi->cache_validity & NFS_INO_INVALID_ACCESS)
 		goto out;
-	lh = rcu_dereference(nfsi->access_cache_entry_lru.prev);
+	lh = rcu_dereference(list_tail_rcu(&nfsi->access_cache_entry_lru));
 	cache = list_entry(lh, struct nfs_access_entry, lru);
 	if (lh == &nfsi->access_cache_entry_lru ||
 	    cred_fscmp(cred, cache->cred) != 0)

include/linux/rculist.h

@@ -60,9 +60,9 @@ static inline void INIT_LIST_HEAD_RCU(struct list_head *list)
 #define __list_check_rcu(dummy, cond, extra...)				\
 	({								\
 	check_arg_count_one(extra);					\
-	RCU_LOCKDEP_WARN(!cond && !rcu_read_lock_any_held(),		\
+	RCU_LOCKDEP_WARN(!(cond) && !rcu_read_lock_any_held(),		\
 			 "RCU-list traversed in non-reader section!");	\
-	 })
+	})
 #else
 #define __list_check_rcu(dummy, cond, extra...)				\
 	({ check_arg_count_one(extra); })

include/linux/rcutiny.h

@@ -83,6 +83,7 @@ void rcu_scheduler_starting(void);
 static inline void rcu_scheduler_starting(void) { }
 #endif /* #else #ifndef CONFIG_SRCU */
 static inline void rcu_end_inkernel_boot(void) { }
+static inline bool rcu_inkernel_boot_has_ended(void) { return true; }
 static inline bool rcu_is_watching(void) { return true; }
 static inline void rcu_momentary_dyntick_idle(void) { }
 static inline void kfree_rcu_scheduler_running(void) { }

include/linux/rcutree.h

@@ -54,6 +54,7 @@ void exit_rcu(void);
 void rcu_scheduler_starting(void);
 extern int rcu_scheduler_active __read_mostly;
 void rcu_end_inkernel_boot(void);
+bool rcu_inkernel_boot_has_ended(void);
 bool rcu_is_watching(void);
 #ifndef CONFIG_PREEMPTION
 void rcu_all_qs(void);

include/linux/timer.h

@@ -164,7 +164,7 @@ static inline void destroy_timer_on_stack(struct timer_list *timer) { }
  */
 static inline int timer_pending(const struct timer_list * timer)
 {
-	return timer->entry.pprev != NULL;
+	return !hlist_unhashed_lockless(&timer->entry);
 }
 
 extern void add_timer_on(struct timer_list *timer, int cpu);

include/trace/events/rcu.h

@@ -623,6 +623,34 @@ TRACE_EVENT_RCU(rcu_invoke_kfree_callback,
 		  __entry->rcuname, __entry->rhp, __entry->offset)
 );
 
+/*
+ * Tracepoint for the invocation of a single RCU callback of the special
+ * kfree_bulk() form. The first argument is the RCU flavor, the second
+ * argument is a number of elements in array to free, the third is an
+ * address of the array holding nr_records entries.
+ */
+TRACE_EVENT_RCU(rcu_invoke_kfree_bulk_callback,
+
+	TP_PROTO(const char *rcuname, unsigned long nr_records, void **p),
+
+	TP_ARGS(rcuname, nr_records, p),
+
+	TP_STRUCT__entry(
+		__field(const char *, rcuname)
+		__field(unsigned long, nr_records)
+		__field(void **, p)
+	),
+
+	TP_fast_assign(
+		__entry->rcuname = rcuname;
+		__entry->nr_records = nr_records;
+		__entry->p = p;
+	),
+
+	TP_printk("%s bulk=0x%p nr_records=%lu",
+		__entry->rcuname, __entry->p, __entry->nr_records)
+);
+
 /*
  * Tracepoint for exiting rcu_do_batch after RCU callbacks have been
  * invoked.  The first argument is the name of the RCU flavor,
@@ -712,6 +740,7 @@ TRACE_EVENT_RCU(rcu_torture_read,
  *	"Begin": rcu_barrier() started.
  *	"EarlyExit": rcu_barrier() piggybacked, thus early exit.
  *	"Inc1": rcu_barrier() piggyback check counter incremented.
+ *	"OfflineNoCBQ": rcu_barrier() found offline no-CBs CPU with callbacks.
  *	"OnlineQ": rcu_barrier() found online CPU with callbacks.
  *	"OnlineNQ": rcu_barrier() found online CPU, no callbacks.
  *	"IRQ": An rcu_barrier_callback() callback posted on remote CPU.

kernel/locking/locktorture.c

@@ -618,7 +618,7 @@ static struct lock_torture_ops percpu_rwsem_lock_ops = {
 static int lock_torture_writer(void *arg)
 {
 	struct lock_stress_stats *lwsp = arg;
-	static DEFINE_TORTURE_RANDOM(rand);
+	DEFINE_TORTURE_RANDOM(rand);
 
 	VERBOSE_TOROUT_STRING("lock_torture_writer task started");
 	set_user_nice(current, MAX_NICE);
@@ -655,7 +655,7 @@ static int lock_torture_writer(void *arg)
 static int lock_torture_reader(void *arg)
 {
 	struct lock_stress_stats *lrsp = arg;
-	static DEFINE_TORTURE_RANDOM(rand);
+	DEFINE_TORTURE_RANDOM(rand);
 
 	VERBOSE_TOROUT_STRING("lock_torture_reader task started");
 	set_user_nice(current, MAX_NICE);
@@ -696,15 +696,16 @@ static void __torture_print_stats(char *page,
 		if (statp[i].n_lock_fail)
 			fail = true;
 		sum += statp[i].n_lock_acquired;
-		if (max < statp[i].n_lock_fail)
-			max = statp[i].n_lock_fail;
-		if (min > statp[i].n_lock_fail)
-			min = statp[i].n_lock_fail;
+		if (max < statp[i].n_lock_acquired)
+			max = statp[i].n_lock_acquired;
+		if (min > statp[i].n_lock_acquired)
+			min = statp[i].n_lock_acquired;
 	}
 	page += sprintf(page,
 			"%s:  Total: %lld  Max/Min: %ld/%ld %s  Fail: %d %s\n",
 			write ? "Writes" : "Reads ",
-			sum, max, min, max / 2 > min ? "???" : "",
+			sum, max, min,
+			!onoff_interval && max / 2 > min ? "???" : "",
 			fail, fail ? "!!!" : "");
 	if (fail)
 		atomic_inc(&cxt.n_lock_torture_errors);

kernel/locking/rtmutex.c

@@ -57,7 +57,7 @@ rt_mutex_set_owner(struct rt_mutex *lock, struct task_struct *owner)
 	if (rt_mutex_has_waiters(lock))
 		val |= RT_MUTEX_HAS_WAITERS;
 
-	lock->owner = (struct task_struct *)val;
+	WRITE_ONCE(lock->owner, (struct task_struct *)val);
 }
 
 static inline void clear_rt_mutex_waiters(struct rt_mutex *lock)

kernel/rcu/Makefile

@@ -3,6 +3,10 @@
 # and is generally not a function of system call inputs.
 KCOV_INSTRUMENT := n
 
+ifeq ($(CONFIG_KCSAN),y)
+KBUILD_CFLAGS += -g -fno-omit-frame-pointer
+endif
+
 obj-y += update.o sync.o
 obj-$(CONFIG_TREE_SRCU) += srcutree.o
 obj-$(CONFIG_TINY_SRCU) += srcutiny.o

kernel/rcu/rcu.h

@@ -198,13 +198,25 @@ static inline void debug_rcu_head_unqueue(struct rcu_head *head)
 }
 #endif	/* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
 
+extern int rcu_cpu_stall_suppress_at_boot;
+
+static inline bool rcu_stall_is_suppressed_at_boot(void)
+{
+	return rcu_cpu_stall_suppress_at_boot && !rcu_inkernel_boot_has_ended();
+}
+
 #ifdef CONFIG_RCU_STALL_COMMON
 
 extern int rcu_cpu_stall_ftrace_dump;
 extern int rcu_cpu_stall_suppress;
 extern int rcu_cpu_stall_timeout;
 int rcu_jiffies_till_stall_check(void);
 
+static inline bool rcu_stall_is_suppressed(void)
+{
+	return rcu_stall_is_suppressed_at_boot() || rcu_cpu_stall_suppress;
+}
+
 #define rcu_ftrace_dump_stall_suppress() \
 do { \
 	if (!rcu_cpu_stall_suppress) \
@@ -218,6 +230,11 @@ do { \
 } while (0)
 
 #else /* #endif #ifdef CONFIG_RCU_STALL_COMMON */
+
+static inline bool rcu_stall_is_suppressed(void)
+{
+	return rcu_stall_is_suppressed_at_boot();
+}
 #define rcu_ftrace_dump_stall_suppress()
 #define rcu_ftrace_dump_stall_unsuppress()
 #endif /* #ifdef CONFIG_RCU_STALL_COMMON */
@@ -325,7 +342,8 @@ static inline void rcu_init_levelspread(int *levelspread, const int *levelcnt)
  * Iterate over all possible CPUs in a leaf RCU node.
  */
 #define for_each_leaf_node_possible_cpu(rnp, cpu) \
-	for ((cpu) = cpumask_next((rnp)->grplo - 1, cpu_possible_mask); \
+	for (WARN_ON_ONCE(!rcu_is_leaf_node(rnp)), \
+	     (cpu) = cpumask_next((rnp)->grplo - 1, cpu_possible_mask); \
 	     (cpu) <= rnp->grphi; \
 	     (cpu) = cpumask_next((cpu), cpu_possible_mask))
 
@@ -335,7 +353,8 @@ static inline void rcu_init_levelspread(int *levelspread, const int *levelcnt)
 #define rcu_find_next_bit(rnp, cpu, mask) \
 	((rnp)->grplo + find_next_bit(&(mask), BITS_PER_LONG, (cpu)))
 #define for_each_leaf_node_cpu_mask(rnp, cpu, mask) \
-	for ((cpu) = rcu_find_next_bit((rnp), 0, (mask)); \
+	for (WARN_ON_ONCE(!rcu_is_leaf_node(rnp)), \
+	     (cpu) = rcu_find_next_bit((rnp), 0, (mask)); \
 	     (cpu) <= rnp->grphi; \
 	     (cpu) = rcu_find_next_bit((rnp), (cpu) + 1 - (rnp->grplo), (mask)))
 

kernel/rcu/rcu_segcblist.c

@@ -182,7 +182,7 @@ void rcu_segcblist_offload(struct rcu_segcblist *rsclp)
 bool rcu_segcblist_ready_cbs(struct rcu_segcblist *rsclp)
 {
 	return rcu_segcblist_is_enabled(rsclp) &&
-	       &rsclp->head != rsclp->tails[RCU_DONE_TAIL];
+	       &rsclp->head != READ_ONCE(rsclp->tails[RCU_DONE_TAIL]);
 }
 
 /*
@@ -381,8 +381,6 @@ void rcu_segcblist_insert_pend_cbs(struct rcu_segcblist *rsclp,
 		return; /* Nothing to do. */
 	WRITE_ONCE(*rsclp->tails[RCU_NEXT_TAIL], rclp->head);
 	WRITE_ONCE(rsclp->tails[RCU_NEXT_TAIL], rclp->tail);
-	rclp->head = NULL;
-	rclp->tail = &rclp->head;
 }
 
 /*

kernel/rcu/rcuperf.c

@@ -12,6 +12,7 @@
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
+#include <linux/mm.h>
 #include <linux/module.h>
 #include <linux/kthread.h>
 #include <linux/err.h>
@@ -611,6 +612,7 @@ kfree_perf_thread(void *arg)
 	long me = (long)arg;
 	struct kfree_obj *alloc_ptr;
 	u64 start_time, end_time;
+	long long mem_begin, mem_during = 0;
 
 	VERBOSE_PERFOUT_STRING("kfree_perf_thread task started");
 	set_cpus_allowed_ptr(current, cpumask_of(me % nr_cpu_ids));
@@ -626,6 +628,12 @@ kfree_perf_thread(void *arg)
 	}
 
 	do {
+		if (!mem_during) {
+			mem_during = mem_begin = si_mem_available();
+		} else if (loop % (kfree_loops / 4) == 0) {
+			mem_during = (mem_during + si_mem_available()) / 2;
+		}
+
 		for (i = 0; i < kfree_alloc_num; i++) {
 			alloc_ptr = kmalloc(sizeof(struct kfree_obj), GFP_KERNEL);
 			if (!alloc_ptr)
@@ -645,9 +653,11 @@ kfree_perf_thread(void *arg)
 		else
 			b_rcu_gp_test_finished = cur_ops->get_gp_seq();
 
-		pr_alert("Total time taken by all kfree'ers: %llu ns, loops: %d, batches: %ld\n",
+		pr_alert("Total time taken by all kfree'ers: %llu ns, loops: %d, batches: %ld, memory footprint: %lldMB\n",
 		       (unsigned long long)(end_time - start_time), kfree_loops,
-		       rcuperf_seq_diff(b_rcu_gp_test_finished, b_rcu_gp_test_started));
+		       rcuperf_seq_diff(b_rcu_gp_test_finished, b_rcu_gp_test_started),
+		       (mem_begin - mem_during) >> (20 - PAGE_SHIFT));
+
 		if (shutdown) {
 			smp_mb(); /* Assign before wake. */
 			wake_up(&shutdown_wq);