Merge branches 'rcu/torture', 'rcu/fixes', 'rcu/docs', 'rcu/refscale', 'rcu/tasks' and 'rcu/stall' into rcu/next

rcu/torture: RCU torture, locktorture and generic torture infrastructure
rcu/fixes: Generic and misc fixes
rcu/docs: RCU documentation updates
rcu/refscale: RCU reference scalability test updates
rcu/tasks: RCU tasks updates
rcu/stall: Stall detection updates

Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.rst

@@ -181,7 +181,7 @@ operations is carried out at several levels:
    of this wait (or series of waits, as the case may be) is to permit a
    concurrent CPU-hotplug operation to complete.
 #. In the case of RCU-sched, one of the last acts of an outgoing CPU is
-   to invoke ``rcu_report_dead()``, which reports a quiescent state for
+   to invoke ``rcutree_report_cpu_dead()``, which reports a quiescent state for
    that CPU. However, this is likely paranoia-induced redundancy.
 
 +-----------------------------------------------------------------------+

Documentation/RCU/Design/Memory-Ordering/TreeRCU-callback-registry.svg

@@ -564,15 +564,6 @@
        font-size="192"
        id="text202-7-9-6"
        style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rcutree_migrate_callbacks()</text>
-    <text
-       xml:space="preserve"
-       x="8335.4873"
-       y="5357.1006"
-       font-style="normal"
-       font-weight="bold"
-       font-size="192"
-       id="text202-7-9-6-0"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rcu_migrate_callbacks()</text>
     <text
        xml:space="preserve"
        x="8768.4678"

Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-fqs.svg

@@ -1135,7 +1135,7 @@
        font-weight="bold"
        font-size="192"
        id="text202-7-5-3-27-6-5"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rcu_report_dead()</text>
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rcutree_report_cpu_dead()</text>
     <text
        xml:space="preserve"
        x="3745.7725"
@@ -1256,7 +1256,7 @@
        font-style="normal"
        y="3679.27"
        x="-3804.9949"
-       xml:space="preserve">rcu_cpu_starting()</text>
+       xml:space="preserve">rcutree_report_cpu_starting()</text>
     <g
        style="fill:none;stroke-width:0.025in"
        id="g3107-7-5-0"

Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp.svg

@@ -1446,15 +1446,6 @@
        font-size="192"
        id="text202-7-9-6"
        style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rcutree_migrate_callbacks()</text>
-    <text
-       xml:space="preserve"
-       x="8335.4873"
-       y="5357.1006"
-       font-style="normal"
-       font-weight="bold"
-       font-size="192"
-       id="text202-7-9-6-0"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rcu_migrate_callbacks()</text>
     <text
        xml:space="preserve"
        x="8768.4678"
@@ -3274,7 +3265,7 @@
          font-weight="bold"
          font-size="192"
          id="text202-7-5-3-27-6-5"
-         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rcu_report_dead()</text>
+         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rcutree_report_cpu_dead()</text>
       <text
          xml:space="preserve"
          x="3745.7725"
@@ -3395,7 +3386,7 @@
          font-style="normal"
          y="3679.27"
          x="-3804.9949"
-         xml:space="preserve">rcu_cpu_starting()</text>
+         xml:space="preserve">rcutree_report_cpu_starting()</text>
       <g
          style="fill:none;stroke-width:0.025in"
          id="g3107-7-5-0"

Documentation/RCU/Design/Memory-Ordering/TreeRCU-hotplug.svg

@@ -607,7 +607,7 @@
        font-weight="bold"
        font-size="192"
        id="text202-7-5-3-27-6"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rcu_report_dead()</text>
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rcutree_report_cpu_dead()</text>
     <text
        xml:space="preserve"
        x="3745.7725"
@@ -728,7 +728,7 @@
        font-style="normal"
        y="3679.27"
        x="-3804.9949"
-       xml:space="preserve">rcu_cpu_starting()</text>
+       xml:space="preserve">rcutree_report_cpu_starting()</text>
     <g
        style="fill:none;stroke-width:0.025in"
        id="g3107-7-5-0"

Documentation/RCU/Design/Requirements/Requirements.rst

@@ -1955,12 +1955,12 @@ if offline CPUs block an RCU grace period for too long.
 
 An offline CPU's quiescent state will be reported either:
 
-1.  As the CPU goes offline using RCU's hotplug notifier (rcu_report_dead()).
+1.  As the CPU goes offline using RCU's hotplug notifier (rcutree_report_cpu_dead()).
 2.  When grace period initialization (rcu_gp_init()) detects a
     race either with CPU offlining or with a task unblocking on a leaf
     ``rcu_node`` structure whose CPUs are all offline.
 
-The CPU-online path (rcu_cpu_starting()) should never need to report
+The CPU-online path (rcutree_report_cpu_starting()) should never need to report
 a quiescent state for an offline CPU.  However, as a debugging measure,
 it does emit a warning if a quiescent state was not already reported
 for that CPU.

Documentation/RCU/listRCU.rst

@@ -8,6 +8,15 @@ One of the most common uses of RCU is protecting read-mostly linked lists
 that all of the required memory ordering is provided by the list macros.
 This document describes several list-based RCU use cases.
 
+When iterating a list while holding the rcu_read_lock(), writers may
+modify the list.  The reader is guaranteed to see all of the elements
+which were added to the list before they acquired the rcu_read_lock()
+and are still on the list when they drop the rcu_read_unlock().
+Elements which are added to, or removed from the list may or may not
+be seen.  If the writer calls list_replace_rcu(), the reader may see
+either the old element or the new element; they will not see both,
+nor will they see neither.
+
 
 Example 1: Read-mostly list: Deferred Destruction
 -------------------------------------------------

Documentation/RCU/whatisRCU.rst

@@ -59,8 +59,8 @@ experiment with should focus on Section 2.  People who prefer to start
 with example uses should focus on Sections 3 and 4.  People who need to
 understand the RCU implementation should focus on Section 5, then dive
 into the kernel source code.  People who reason best by analogy should
-focus on Section 6.  Section 7 serves as an index to the docbook API
+focus on Section 6 and 7.  Section 8 serves as an index to the docbook
-documentation, and Section 8 is the traditional answer key.
+API documentation, and Section 9 is the traditional answer key.
 
 So, start with the section that makes the most sense to you and your
 preferred method of learning.  If you need to know everything about

Documentation/admin-guide/kernel-parameters.txt

@@ -4820,6 +4820,13 @@
 			Set maximum number of finished RCU callbacks to
 			process in one batch.
 
+	rcutree.do_rcu_barrier=	[KNL]
+			Request a call to rcu_barrier().  This is
+			throttled so that userspace tests can safely
+			hammer on the sysfs variable if they so choose.
+			If triggered before the RCU grace-period machinery
+			is fully active, this will error out with EAGAIN.
+
 	rcutree.dump_tree=	[KNL]
 			Dump the structure of the rcu_node combining tree
 			out at early boot.  This is used for diagnostic
@@ -5473,6 +5480,12 @@
 			test until boot completes in order to avoid
 			interference.
 
+	refscale.lookup_instances= [KNL]
+			Number of data elements to use for the forms of
+			SLAB_TYPESAFE_BY_RCU testing.  A negative number
+			is negated and multiplied by nr_cpu_ids, while
+			zero specifies nr_cpu_ids.
+
 	refscale.loops= [KNL]
 			Set the number of loops over the synchronization
 			primitive under test.  Increasing this number

arch/arm64/kernel/smp.c

@@ -215,7 +215,7 @@ asmlinkage notrace void secondary_start_kernel(void)
 	if (system_uses_irq_prio_masking())
 		init_gic_priority_masking();
 
-	rcu_cpu_starting(cpu);
+	rcutree_report_cpu_starting(cpu);
 	trace_hardirqs_off();
 
 	/*
@@ -401,7 +401,7 @@ void __noreturn cpu_die_early(void)
 
 	/* Mark this CPU absent */
 	set_cpu_present(cpu, 0);
-	rcu_report_dead(cpu);
+	rcutree_report_cpu_dead();
 
 	if (IS_ENABLED(CONFIG_HOTPLUG_CPU)) {
 		update_cpu_boot_status(CPU_KILL_ME);

arch/powerpc/kernel/smp.c

@@ -1629,7 +1629,7 @@ void start_secondary(void *unused)
 
 	smp_store_cpu_info(cpu);
 	set_dec(tb_ticks_per_jiffy);
-	rcu_cpu_starting(cpu);
+	rcutree_report_cpu_starting(cpu);
 	cpu_callin_map[cpu] = 1;
 
 	if (smp_ops->setup_cpu)

arch/s390/kernel/smp.c

@@ -898,7 +898,7 @@ static void smp_start_secondary(void *cpuvoid)
 	S390_lowcore.restart_flags = 0;
 	restore_access_regs(S390_lowcore.access_regs_save_area);
 	cpu_init();
-	rcu_cpu_starting(cpu);
+	rcutree_report_cpu_starting(cpu);
 	init_cpu_timer();
 	vtime_init();
 	vdso_getcpu_init();

arch/x86/kernel/smpboot.c

@@ -288,7 +288,7 @@ static void notrace start_secondary(void *unused)
 
 	cpu_init();
 	fpu__init_cpu();
-	rcu_cpu_starting(raw_smp_processor_id());
+	rcutree_report_cpu_starting(raw_smp_processor_id());
 	x86_cpuinit.early_percpu_clock_init();
 
 	ap_starting();

include/linux/interrupt.h

@@ -566,7 +566,7 @@ enum
  *
  * _ RCU:
  * 	1) rcutree_migrate_callbacks() migrates the queue.
- * 	2) rcu_report_dead() reports the final quiescent states.
+ * 	2) rcutree_report_cpu_dead() reports the final quiescent states.
  *
  * _ IRQ_POLL: irq_poll_cpu_dead() migrates the queue
  */

include/linux/rcu_notifier.h

@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * Read-Copy Update notifiers, initially RCU CPU stall notifier.
+ * Separate from rcupdate.h to avoid #include loops.
+ *
+ * Copyright (C) 2023 Paul E. McKenney.
+ */
+
+#ifndef __LINUX_RCU_NOTIFIER_H
+#define __LINUX_RCU_NOTIFIER_H
+
+// Actions for RCU CPU stall notifier calls.
+#define RCU_STALL_NOTIFY_NORM	1
+#define RCU_STALL_NOTIFY_EXP	2
+
+#ifdef CONFIG_RCU_STALL_COMMON
+
+#include <linux/notifier.h>
+#include <linux/types.h>
+
+int rcu_stall_chain_notifier_register(struct notifier_block *n);
+int rcu_stall_chain_notifier_unregister(struct notifier_block *n);
+
+#else // #ifdef CONFIG_RCU_STALL_COMMON
+
+// No RCU CPU stall warnings in Tiny RCU.
+static inline int rcu_stall_chain_notifier_register(struct notifier_block *n) { return -EEXIST; }
+static inline int rcu_stall_chain_notifier_unregister(struct notifier_block *n) { return -ENOENT; }
+
+#endif // #else // #ifdef CONFIG_RCU_STALL_COMMON
+
+#endif /* __LINUX_RCU_NOTIFIER_H */

include/linux/rcupdate.h

@@ -122,8 +122,6 @@ static inline void call_rcu_hurry(struct rcu_head *head, rcu_callback_t func)
 void rcu_init(void);
 extern int rcu_scheduler_active;
 void rcu_sched_clock_irq(int user);
-void rcu_report_dead(unsigned int cpu);
-void rcutree_migrate_callbacks(int cpu);
 
 #ifdef CONFIG_TASKS_RCU_GENERIC
 void rcu_init_tasks_generic(void);

include/linux/rcutiny.h

@@ -171,6 +171,6 @@ static inline void rcu_all_qs(void) { barrier(); }
 #define rcutree_offline_cpu      NULL
 #define rcutree_dead_cpu         NULL
 #define rcutree_dying_cpu        NULL
-static inline void rcu_cpu_starting(unsigned int cpu) { }
+static inline void rcutree_report_cpu_starting(unsigned int cpu) { }
 
 #endif /* __LINUX_RCUTINY_H */

include/linux/rcutree.h

@@ -37,7 +37,6 @@ void synchronize_rcu_expedited(void);
 void kvfree_call_rcu(struct rcu_head *head, void *ptr);
 
 void rcu_barrier(void);
-bool rcu_eqs_special_set(int cpu);
 void rcu_momentary_dyntick_idle(void);
 void kfree_rcu_scheduler_running(void);
 bool rcu_gp_might_be_stalled(void);
@@ -111,9 +110,21 @@ void rcu_all_qs(void);
 /* RCUtree hotplug events */
 int rcutree_prepare_cpu(unsigned int cpu);
 int rcutree_online_cpu(unsigned int cpu);
-int rcutree_offline_cpu(unsigned int cpu);
+void rcutree_report_cpu_starting(unsigned int cpu);
+
+#ifdef CONFIG_HOTPLUG_CPU
 int rcutree_dead_cpu(unsigned int cpu);
 int rcutree_dying_cpu(unsigned int cpu);
-void rcu_cpu_starting(unsigned int cpu);
+int rcutree_offline_cpu(unsigned int cpu);
+#else
+#define rcutree_dead_cpu NULL
+#define rcutree_dying_cpu NULL
+#define rcutree_offline_cpu NULL
+#endif
+
+void rcutree_migrate_callbacks(int cpu);
+
+/* Called from hotplug and also arm64 early secondary boot failure */
+void rcutree_report_cpu_dead(void);
 
 #endif /* __LINUX_RCUTREE_H */

include/linux/slab.h

@@ -245,8 +245,9 @@ DEFINE_FREE(kfree, void *, if (_T) kfree(_T))
 size_t ksize(const void *objp);
 
 #ifdef CONFIG_PRINTK
-bool kmem_valid_obj(void *object);
+bool kmem_dump_obj(void *object);
-void kmem_dump_obj(void *object);
+#else
+static inline bool kmem_dump_obj(void *object) { return false; }
 #endif
 
 /*

kernel/cpu.c

@@ -1372,7 +1372,14 @@ static int takedown_cpu(unsigned int cpu)
 	cpuhp_bp_sync_dead(cpu);
 
 	tick_cleanup_dead_cpu(cpu);
+
+	/*
+	 * Callbacks must be re-integrated right away to the RCU state machine.
+	 * Otherwise an RCU callback could block a further teardown function
+	 * waiting for its completion.
+	 */
 	rcutree_migrate_callbacks(cpu);
+
 	return 0;
 }
 
@@ -1388,10 +1395,10 @@ void cpuhp_report_idle_dead(void)
 	struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state);
 
 	BUG_ON(st->state != CPUHP_AP_OFFLINE);
-	rcu_report_dead(smp_processor_id());
+	rcutree_report_cpu_dead();
 	st->state = CPUHP_AP_IDLE_DEAD;
 	/*
-	 * We cannot call complete after rcu_report_dead() so we delegate it
+	 * We cannot call complete after rcutree_report_cpu_dead() so we delegate it
 	 * to an online cpu.
 	 */
 	smp_call_function_single(cpumask_first(cpu_online_mask),
@@ -1617,7 +1624,7 @@ void notify_cpu_starting(unsigned int cpu)
 	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
 	enum cpuhp_state target = min((int)st->target, CPUHP_AP_ONLINE);
 
-	rcu_cpu_starting(cpu);	/* Enables RCU usage on this CPU. */
+	rcutree_report_cpu_starting(cpu);	/* Enables RCU usage on this CPU. */
 	cpumask_set_cpu(cpu, &cpus_booted_once_mask);
 
 	/*

kernel/rcu/rcu.h

@@ -10,6 +10,7 @@
 #ifndef __LINUX_RCU_H
 #define __LINUX_RCU_H
 
+#include <linux/slab.h>
 #include <trace/events/rcu.h>
 
 /*
@@ -248,6 +249,12 @@ static inline void debug_rcu_head_unqueue(struct rcu_head *head)
 }
 #endif	/* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
 
+static inline void debug_rcu_head_callback(struct rcu_head *rhp)
+{
+	if (unlikely(!rhp->func))
+		kmem_dump_obj(rhp);
+}
+
 extern int rcu_cpu_stall_suppress_at_boot;
 
 static inline bool rcu_stall_is_suppressed_at_boot(void)
@@ -650,4 +657,10 @@ static inline bool rcu_cpu_beenfullyonline(int cpu) { return true; }
 bool rcu_cpu_beenfullyonline(int cpu);
 #endif
 
+#ifdef CONFIG_RCU_STALL_COMMON
+int rcu_stall_notifier_call_chain(unsigned long val, void *v);
+#else // #ifdef CONFIG_RCU_STALL_COMMON
+static inline int rcu_stall_notifier_call_chain(unsigned long val, void *v) { return NOTIFY_DONE; }
+#endif // #else // #ifdef CONFIG_RCU_STALL_COMMON
+
 #endif /* __LINUX_RCU_H */

kernel/rcu/rcu_segcblist.c

@@ -368,7 +368,7 @@ bool rcu_segcblist_entrain(struct rcu_segcblist *rsclp,
 	smp_mb(); /* Ensure counts are updated before callback is entrained. */
 	rhp->next = NULL;
 	for (i = RCU_NEXT_TAIL; i > RCU_DONE_TAIL; i--)
-		if (rsclp->tails[i] != rsclp->tails[i - 1])
+		if (!rcu_segcblist_segempty(rsclp, i))
 			break;
 	rcu_segcblist_inc_seglen(rsclp, i);
 	WRITE_ONCE(*rsclp->tails[i], rhp);
@@ -551,7 +551,7 @@ bool rcu_segcblist_accelerate(struct rcu_segcblist *rsclp, unsigned long seq)
 	 * as their ->gp_seq[] grace-period completion sequence number.
 	 */
 	for (i = RCU_NEXT_READY_TAIL; i > RCU_DONE_TAIL; i--)
-		if (rsclp->tails[i] != rsclp->tails[i - 1] &&
+		if (!rcu_segcblist_segempty(rsclp, i) &&
 		    ULONG_CMP_LT(rsclp->gp_seq[i], seq))
 			break;
 

kernel/rcu/rcutorture.c

@@ -21,6 +21,7 @@
 #include <linux/spinlock.h>
 #include <linux/smp.h>
 #include <linux/rcupdate_wait.h>
+#include <linux/rcu_notifier.h>
 #include <linux/interrupt.h>
 #include <linux/sched/signal.h>
 #include <uapi/linux/sched/types.h>
@@ -2428,6 +2429,16 @@ static int rcutorture_booster_init(unsigned int cpu)
 	return 0;
 }
 
+static int rcu_torture_stall_nf(struct notifier_block *nb, unsigned long v, void *ptr)
+{
+	pr_info("%s: v=%lu, duration=%lu.\n", __func__, v, (unsigned long)ptr);
+	return NOTIFY_OK;
+}
+
+static struct notifier_block rcu_torture_stall_block = {
+	.notifier_call = rcu_torture_stall_nf,
+};
+
 /*
  * CPU-stall kthread.  It waits as specified by stall_cpu_holdoff, then
  * induces a CPU stall for the time specified by stall_cpu.
@@ -2435,9 +2446,14 @@ static int rcutorture_booster_init(unsigned int cpu)
 static int rcu_torture_stall(void *args)
 {
 	int idx;
+	int ret;
 	unsigned long stop_at;
 
 	VERBOSE_TOROUT_STRING("rcu_torture_stall task started");
+	ret = rcu_stall_chain_notifier_register(&rcu_torture_stall_block);
+	if (ret)
+		pr_info("%s: rcu_stall_chain_notifier_register() returned %d, %sexpected.\n",
+			__func__, ret, !IS_ENABLED(CONFIG_RCU_STALL_COMMON) ? "un" : "");
 	if (stall_cpu_holdoff > 0) {
 		VERBOSE_TOROUT_STRING("rcu_torture_stall begin holdoff");
 		schedule_timeout_interruptible(stall_cpu_holdoff * HZ);
@@ -2481,6 +2497,11 @@ static int rcu_torture_stall(void *args)
 		cur_ops->readunlock(idx);
 	}
 	pr_alert("%s end.\n", __func__);
+	if (!ret) {
+		ret = rcu_stall_chain_notifier_unregister(&rcu_torture_stall_block);
+		if (ret)
+			pr_info("%s: rcu_stall_chain_notifier_unregister() returned %d.\n", __func__, ret);
+	}
 	torture_shutdown_absorb("rcu_torture_stall");
 	while (!kthread_should_stop())
 		schedule_timeout_interruptible(10 * HZ);

kernel/rcu/refscale.c

@@ -655,12 +655,12 @@ retry:
 			goto retry;
 		}
 		un_delay(udl, ndl);
+		b = READ_ONCE(rtsp->a);
 		// Remember, seqlock read-side release can fail.
 		if (!rts_release(rtsp, start)) {
 			rcu_read_unlock();
 			goto retry;
 		}
-		b = READ_ONCE(rtsp->a);
 		WARN_ONCE(a != b, "Re-read of ->a changed from %u to %u.\n", a, b);
 		b = rtsp->b;
 		rcu_read_unlock();
@@ -1025,8 +1025,8 @@ static void
 ref_scale_print_module_parms(struct ref_scale_ops *cur_ops, const char *tag)
 {
 	pr_alert("%s" SCALE_FLAG
-		 "--- %s:  verbose=%d shutdown=%d holdoff=%d loops=%ld nreaders=%d nruns=%d readdelay=%d\n", scale_type, tag,
+		 "--- %s:  verbose=%d verbose_batched=%d shutdown=%d holdoff=%d lookup_instances=%ld loops=%ld nreaders=%d nruns=%d readdelay=%d\n", scale_type, tag,
-		 verbose, shutdown, holdoff, loops, nreaders, nruns, readdelay);
+		 verbose, verbose_batched, shutdown, holdoff, lookup_instances, loops, nreaders, nruns, readdelay);
 }
 
 static void

kernel/rcu/srcutiny.c

@@ -138,6 +138,7 @@ void srcu_drive_gp(struct work_struct *wp)
 	while (lh) {
 		rhp = lh;
 		lh = lh->next;
+		debug_rcu_head_callback(rhp);
 		local_bh_disable();
 		rhp->func(rhp);
 		local_bh_enable();

kernel/rcu/srcutree.c

@@ -223,7 +223,7 @@ static bool init_srcu_struct_nodes(struct srcu_struct *ssp, gfp_t gfp_flags)
 				snp->grplo = cpu;
 			snp->grphi = cpu;
 		}
-		sdp->grpmask = 1 << (cpu - sdp->mynode->grplo);
+		sdp->grpmask = 1UL << (cpu - sdp->mynode->grplo);
 	}
 	smp_store_release(&ssp->srcu_sup->srcu_size_state, SRCU_SIZE_WAIT_BARRIER);
 	return true;
@@ -255,29 +255,31 @@ static int init_srcu_struct_fields(struct srcu_struct *ssp, bool is_static)
 	ssp->srcu_sup->sda_is_static = is_static;
 	if (!is_static)
 		ssp->sda = alloc_percpu(struct srcu_data);
-	if (!ssp->sda) {
+	if (!ssp->sda)
-		if (!is_static)
+		goto err_free_sup;
-			kfree(ssp->srcu_sup);
-		return -ENOMEM;
-	}
 	init_srcu_struct_data(ssp);
 	ssp->srcu_sup->srcu_gp_seq_needed_exp = 0;
 	ssp->srcu_sup->srcu_last_gp_end = ktime_get_mono_fast_ns();
 	if (READ_ONCE(ssp->srcu_sup->srcu_size_state) == SRCU_SIZE_SMALL && SRCU_SIZING_IS_INIT()) {
-		if (!init_srcu_struct_nodes(ssp, GFP_ATOMIC)) {
+		if (!init_srcu_struct_nodes(ssp, GFP_ATOMIC))
-			if (!ssp->srcu_sup->sda_is_static) {
+			goto err_free_sda;
-				free_percpu(ssp->sda);
+		WRITE_ONCE(ssp->srcu_sup->srcu_size_state, SRCU_SIZE_BIG);
-				ssp->sda = NULL;
-				kfree(ssp->srcu_sup);
-				return -ENOMEM;
-			}
-		} else {
-			WRITE_ONCE(ssp->srcu_sup->srcu_size_state, SRCU_SIZE_BIG);
-		}
 	}
 	ssp->srcu_sup->srcu_ssp = ssp;
 	smp_store_release(&ssp->srcu_sup->srcu_gp_seq_needed, 0); /* Init done. */
 	return 0;
+
+err_free_sda:
+	if (!is_static) {
+		free_percpu(ssp->sda);
+		ssp->sda = NULL;
+	}
+err_free_sup:
+	if (!is_static) {
+		kfree(ssp->srcu_sup);
+		ssp->srcu_sup = NULL;
+	}
+	return -ENOMEM;
 }
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
@@ -782,8 +784,7 @@ static void srcu_gp_start(struct srcu_struct *ssp)
 	spin_lock_rcu_node(sdp);  /* Interrupts already disabled. */
 	rcu_segcblist_advance(&sdp->srcu_cblist,
 			      rcu_seq_current(&ssp->srcu_sup->srcu_gp_seq));
-	(void)rcu_segcblist_accelerate(&sdp->srcu_cblist,
+	WARN_ON_ONCE(!rcu_segcblist_segempty(&sdp->srcu_cblist, RCU_NEXT_TAIL));
-				       rcu_seq_snap(&ssp->srcu_sup->srcu_gp_seq));
 	spin_unlock_rcu_node(sdp);  /* Interrupts remain disabled. */
 	WRITE_ONCE(ssp->srcu_sup->srcu_gp_start, jiffies);
 	WRITE_ONCE(ssp->srcu_sup->srcu_n_exp_nodelay, 0);
@@ -833,7 +834,7 @@ static void srcu_schedule_cbs_snp(struct srcu_struct *ssp, struct srcu_node *snp
 	int cpu;
 
 	for (cpu = snp->grplo; cpu <= snp->grphi; cpu++) {
-		if (!(mask & (1 << (cpu - snp->grplo))))
+		if (!(mask & (1UL << (cpu - snp->grplo))))
 			continue;
 		srcu_schedule_cbs_sdp(per_cpu_ptr(ssp->sda, cpu), delay);
 	}
@@ -1242,10 +1243,37 @@ static unsigned long srcu_gp_start_if_needed(struct srcu_struct *ssp,
 	spin_lock_irqsave_sdp_contention(sdp, &flags);
 	if (rhp)
 		rcu_segcblist_enqueue(&sdp->srcu_cblist, rhp);
+	/*
+	 * The snapshot for acceleration must be taken _before_ the read of the
+	 * current gp sequence used for advancing, otherwise advancing may fail
+	 * and acceleration may then fail too.
+	 *
+	 * This could happen if:
+	 *
+	 *  1) The RCU_WAIT_TAIL segment has callbacks (gp_num = X + 4) and the
+	 *     RCU_NEXT_READY_TAIL also has callbacks (gp_num = X + 8).
+	 *
+	 *  2) The grace period for RCU_WAIT_TAIL is seen as started but not
+	 *     completed so rcu_seq_current() returns X + SRCU_STATE_SCAN1.
+	 *
+	 *  3) This value is passed to rcu_segcblist_advance() which can't move
+	 *     any segment forward and fails.
+	 *
+	 *  4) srcu_gp_start_if_needed() still proceeds with callback acceleration.
+	 *     But then the call to rcu_seq_snap() observes the grace period for the
+	 *     RCU_WAIT_TAIL segment as completed and the subsequent one for the
+	 *     RCU_NEXT_READY_TAIL segment as started (ie: X + 4 + SRCU_STATE_SCAN1)
+	 *     so it returns a snapshot of the next grace period, which is X + 12.
+	 *
+	 *  5) The value of X + 12 is passed to rcu_segcblist_accelerate() but the
+	 *     freshly enqueued callback in RCU_NEXT_TAIL can't move to
+	 *     RCU_NEXT_READY_TAIL which already has callbacks for a previous grace
+	 *     period (gp_num = X + 8). So acceleration fails.
+	 */
+	s = rcu_seq_snap(&ssp->srcu_sup->srcu_gp_seq);
 	rcu_segcblist_advance(&sdp->srcu_cblist,
 			      rcu_seq_current(&ssp->srcu_sup->srcu_gp_seq));
-	s = rcu_seq_snap(&ssp->srcu_sup->srcu_gp_seq);
+	WARN_ON_ONCE(!rcu_segcblist_accelerate(&sdp->srcu_cblist, s) && rhp);
-	(void)rcu_segcblist_accelerate(&sdp->srcu_cblist, s);
 	if (ULONG_CMP_LT(sdp->srcu_gp_seq_needed, s)) {
 		sdp->srcu_gp_seq_needed = s;
 		needgp = true;
@@ -1692,6 +1720,7 @@ static void srcu_invoke_callbacks(struct work_struct *work)
 	ssp = sdp->ssp;
 	rcu_cblist_init(&ready_cbs);
 	spin_lock_irq_rcu_node(sdp);
+	WARN_ON_ONCE(!rcu_segcblist_segempty(&sdp->srcu_cblist, RCU_NEXT_TAIL));
 	rcu_segcblist_advance(&sdp->srcu_cblist,
 			      rcu_seq_current(&ssp->srcu_sup->srcu_gp_seq));
 	if (sdp->srcu_cblist_invoking ||
@@ -1708,6 +1737,7 @@ static void srcu_invoke_callbacks(struct work_struct *work)
 	rhp = rcu_cblist_dequeue(&ready_cbs);
 	for (; rhp != NULL; rhp = rcu_cblist_dequeue(&ready_cbs)) {
 		debug_rcu_head_unqueue(rhp);
+		debug_rcu_head_callback(rhp);
 		local_bh_disable();
 		rhp->func(rhp);
 		local_bh_enable();
@@ -1720,8 +1750,6 @@ static void srcu_invoke_callbacks(struct work_struct *work)
 	 */
 	spin_lock_irq_rcu_node(sdp);
 	rcu_segcblist_add_len(&sdp->srcu_cblist, -len);
-	(void)rcu_segcblist_accelerate(&sdp->srcu_cblist,
-				       rcu_seq_snap(&ssp->srcu_sup->srcu_gp_seq));
 	sdp->srcu_cblist_invoking = false;
 	more = rcu_segcblist_ready_cbs(&sdp->srcu_cblist);
 	spin_unlock_irq_rcu_node(sdp);

kernel/rcu/tasks.h

@@ -432,6 +432,7 @@ static void rcu_barrier_tasks_generic(struct rcu_tasks *rtp)
 static int rcu_tasks_need_gpcb(struct rcu_tasks *rtp)
 {
 	int cpu;
+	int dequeue_limit;
 	unsigned long flags;
 	bool gpdone = poll_state_synchronize_rcu(rtp->percpu_dequeue_gpseq);
 	long n;
@@ -439,7 +440,8 @@ static int rcu_tasks_need_gpcb(struct rcu_tasks *rtp)
 	long ncbsnz = 0;
 	int needgpcb = 0;
 
-	for (cpu = 0; cpu < smp_load_acquire(&rtp->percpu_dequeue_lim); cpu++) {
+	dequeue_limit = smp_load_acquire(&rtp->percpu_dequeue_lim);
+	for (cpu = 0; cpu < dequeue_limit; cpu++) {
 		struct rcu_tasks_percpu *rtpcp = per_cpu_ptr(rtp->rtpcpu, cpu);
 
 		/* Advance and accelerate any new callbacks. */
@@ -538,6 +540,7 @@ static void rcu_tasks_invoke_cbs(struct rcu_tasks *rtp, struct rcu_tasks_percpu
 	raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags);
 	len = rcl.len;
 	for (rhp = rcu_cblist_dequeue(&rcl); rhp; rhp = rcu_cblist_dequeue(&rcl)) {
+		debug_rcu_head_callback(rhp);
 		local_bh_disable();
 		rhp->func(rhp);
 		local_bh_enable();
@@ -1084,7 +1087,7 @@ void rcu_barrier_tasks(void)
 }
 EXPORT_SYMBOL_GPL(rcu_barrier_tasks);
 
-int rcu_tasks_lazy_ms = -1;
+static int rcu_tasks_lazy_ms = -1;
 module_param(rcu_tasks_lazy_ms, int, 0444);
 
 static int __init rcu_spawn_tasks_kthread(void)
@@ -1979,20 +1982,22 @@ static void test_rcu_tasks_callback(struct rcu_head *rhp)
 
 static void rcu_tasks_initiate_self_tests(void)
 {
-	pr_info("Running RCU-tasks wait API self tests\n");
 #ifdef CONFIG_TASKS_RCU
+	pr_info("Running RCU Tasks wait API self tests\n");
 	tests[0].runstart = jiffies;
 	synchronize_rcu_tasks();
 	call_rcu_tasks(&tests[0].rh, test_rcu_tasks_callback);
 #endif
 
 #ifdef CONFIG_TASKS_RUDE_RCU
+	pr_info("Running RCU Tasks Rude wait API self tests\n");
 	tests[1].runstart = jiffies;
 	synchronize_rcu_tasks_rude();
 	call_rcu_tasks_rude(&tests[1].rh, test_rcu_tasks_callback);
 #endif
 
 #ifdef CONFIG_TASKS_TRACE_RCU
+	pr_info("Running RCU Tasks Trace wait API self tests\n");
 	tests[2].runstart = jiffies;
 	synchronize_rcu_tasks_trace();
 	call_rcu_tasks_trace(&tests[2].rh, test_rcu_tasks_callback);

kernel/rcu/tiny.c

@@ -97,6 +97,7 @@ static inline bool rcu_reclaim_tiny(struct rcu_head *head)
 
 	trace_rcu_invoke_callback("", head);
 	f = head->func;
+	debug_rcu_head_callback(head);
 	WRITE_ONCE(head->func, (rcu_callback_t)0L);
 	f(head);
 	rcu_lock_release(&rcu_callback_map);

kernel/rcu/tree.c

@@ -31,6 +31,7 @@
 #include <linux/bitops.h>
 #include <linux/export.h>
 #include <linux/completion.h>
+#include <linux/kmemleak.h>
 #include <linux/moduleparam.h>
 #include <linux/panic.h>
 #include <linux/panic_notifier.h>
@@ -1260,7 +1261,7 @@ EXPORT_SYMBOL_GPL(rcu_gp_slow_register);
 /* Unregister a counter, with NULL for not caring which. */
 void rcu_gp_slow_unregister(atomic_t *rgssp)
 {
-	WARN_ON_ONCE(rgssp && rgssp != rcu_gp_slow_suppress);
+	WARN_ON_ONCE(rgssp && rgssp != rcu_gp_slow_suppress && rcu_gp_slow_suppress != NULL);
 
 	WRITE_ONCE(rcu_gp_slow_suppress, NULL);
 }
@@ -1556,10 +1557,22 @@ static bool rcu_gp_fqs_check_wake(int *gfp)
  */
 static void rcu_gp_fqs(bool first_time)
 {
+	int nr_fqs = READ_ONCE(rcu_state.nr_fqs_jiffies_stall);
 	struct rcu_node *rnp = rcu_get_root();
 
 	WRITE_ONCE(rcu_state.gp_activity, jiffies);
 	WRITE_ONCE(rcu_state.n_force_qs, rcu_state.n_force_qs + 1);
+
+	WARN_ON_ONCE(nr_fqs > 3);
+	/* Only countdown nr_fqs for stall purposes if jiffies moves. */
+	if (nr_fqs) {
+		if (nr_fqs == 1) {
+			WRITE_ONCE(rcu_state.jiffies_stall,
+				   jiffies + rcu_jiffies_till_stall_check());
+		}
+		WRITE_ONCE(rcu_state.nr_fqs_jiffies_stall, --nr_fqs);
+	}
+
 	if (first_time) {
 		/* Collect dyntick-idle snapshots. */
 		force_qs_rnp(dyntick_save_progress_counter);
@@ -2135,6 +2148,7 @@ static void rcu_do_batch(struct rcu_data *rdp)
 		trace_rcu_invoke_callback(rcu_state.name, rhp);
 
 		f = rhp->func;
+		debug_rcu_head_callback(rhp);
 		WRITE_ONCE(rhp->func, (rcu_callback_t)0L);
 		f(rhp);
 
@@ -2713,7 +2727,7 @@ __call_rcu_common(struct rcu_head *head, rcu_callback_t func, bool lazy_in)
  */
 void call_rcu_hurry(struct rcu_head *head, rcu_callback_t func)
 {
-	return __call_rcu_common(head, func, false);
+	__call_rcu_common(head, func, false);
 }
 EXPORT_SYMBOL_GPL(call_rcu_hurry);
 #endif
@@ -2764,7 +2778,7 @@ EXPORT_SYMBOL_GPL(call_rcu_hurry);
  */
 void call_rcu(struct rcu_head *head, rcu_callback_t func)
 {
-	return __call_rcu_common(head, func, IS_ENABLED(CONFIG_RCU_LAZY));
+	__call_rcu_common(head, func, IS_ENABLED(CONFIG_RCU_LAZY));
 }
 EXPORT_SYMBOL_GPL(call_rcu);
 
@@ -3388,6 +3402,14 @@ void kvfree_call_rcu(struct rcu_head *head, void *ptr)
 		success = true;
 	}
 
+	/*
+	 * The kvfree_rcu() caller considers the pointer freed at this point
+	 * and likely removes any references to it. Since the actual slab
+	 * freeing (and kmemleak_free()) is deferred, tell kmemleak to ignore
+	 * this object (no scanning or false positives reporting).
+	 */
+	kmemleak_ignore(ptr);
+
 	// Set timer to drain after KFREE_DRAIN_JIFFIES.
 	if (rcu_scheduler_active == RCU_SCHEDULER_RUNNING)
 		schedule_delayed_monitor_work(krcp);
@@ -4083,6 +4105,82 @@ retry:
 }
 EXPORT_SYMBOL_GPL(rcu_barrier);
 
+static unsigned long rcu_barrier_last_throttle;
+
+/**
+ * rcu_barrier_throttled - Do rcu_barrier(), but limit to one per second
+ *
+ * This can be thought of as guard rails around rcu_barrier() that
+ * permits unrestricted userspace use, at least assuming the hardware's
+ * try_cmpxchg() is robust.  There will be at most one call per second to
+ * rcu_barrier() system-wide from use of this function, which means that
+ * callers might needlessly wait a second or three.
+ *
+ * This is intended for use by test suites to avoid OOM by flushing RCU
+ * callbacks from the previous test before starting the next.  See the
+ * rcutree.do_rcu_barrier module parameter for more information.
+ *
+ * Why not simply make rcu_barrier() more scalable?  That might be
+ * the eventual endpoint, but let's keep it simple for the time being.
+ * Note that the module parameter infrastructure serializes calls to a
+ * given .set() function, but should concurrent .set() invocation ever be
+ * possible, we are ready!
+ */
+static void rcu_barrier_throttled(void)
+{
+	unsigned long j = jiffies;
+	unsigned long old = READ_ONCE(rcu_barrier_last_throttle);
+	unsigned long s = rcu_seq_snap(&rcu_state.barrier_sequence);
+
+	while (time_in_range(j, old, old + HZ / 16) ||
+	       !try_cmpxchg(&rcu_barrier_last_throttle, &old, j)) {
+		schedule_timeout_idle(HZ / 16);
+		if (rcu_seq_done(&rcu_state.barrier_sequence, s)) {
+			smp_mb(); /* caller's subsequent code after above check. */
+			return;
+		}
+		j = jiffies;
+		old = READ_ONCE(rcu_barrier_last_throttle);
+	}
+	rcu_barrier();
+}
+
+/*
+ * Invoke rcu_barrier_throttled() when a rcutree.do_rcu_barrier
+ * request arrives.  We insist on a true value to allow for possible
+ * future expansion.
+ */
+static int param_set_do_rcu_barrier(const char *val, const struct kernel_param *kp)
+{
+	bool b;
+	int ret;
+
+	if (rcu_scheduler_active != RCU_SCHEDULER_RUNNING)
+		return -EAGAIN;
+	ret = kstrtobool(val, &b);
+	if (!ret && b) {
+		atomic_inc((atomic_t *)kp->arg);
+		rcu_barrier_throttled();
+		atomic_dec((atomic_t *)kp->arg);
+	}
+	return ret;
+}
+
+/*
+ * Output the number of outstanding rcutree.do_rcu_barrier requests.
+ */
+static int param_get_do_rcu_barrier(char *buffer, const struct kernel_param *kp)
+{
+	return sprintf(buffer, "%d\n", atomic_read((atomic_t *)kp->arg));
+}
+
+static const struct kernel_param_ops do_rcu_barrier_ops = {
+	.set = param_set_do_rcu_barrier,
+	.get = param_get_do_rcu_barrier,
+};
+static atomic_t do_rcu_barrier;
+module_param_cb(do_rcu_barrier, &do_rcu_barrier_ops, &do_rcu_barrier, 0644);
+
 /*
  * Compute the mask of online CPUs for the specified rcu_node structure.
  * This will not be stable unless the rcu_node structure's ->lock is
@@ -4130,7 +4228,7 @@ bool rcu_lockdep_current_cpu_online(void)
 	rdp = this_cpu_ptr(&rcu_data);
 	/*
 	 * Strictly, we care here about the case where the current CPU is
-	 * in rcu_cpu_starting() and thus has an excuse for rdp->grpmask
+	 * in rcutree_report_cpu_starting() and thus has an excuse for rdp->grpmask
 	 * not being up to date. So arch_spin_is_locked() might have a
 	 * false positive if it's held by some *other* CPU, but that's
 	 * OK because that just means a false *negative* on the warning.
@@ -4151,25 +4249,6 @@ static bool rcu_init_invoked(void)
 	return !!rcu_state.n_online_cpus;
 }
 
-/*
- * Near the end of the offline process.  Trace the fact that this CPU
- * is going offline.
- */
-int rcutree_dying_cpu(unsigned int cpu)
-{
-	bool blkd;
-	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
-	struct rcu_node *rnp = rdp->mynode;
-
-	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
-		return 0;
-
-	blkd = !!(READ_ONCE(rnp->qsmask) & rdp->grpmask);
-	trace_rcu_grace_period(rcu_state.name, READ_ONCE(rnp->gp_seq),
-			       blkd ? TPS("cpuofl-bgp") : TPS("cpuofl"));
-	return 0;
-}
-
 /*
  * All CPUs for the specified rcu_node structure have gone offline,
  * and all tasks that were preempted within an RCU read-side critical
@@ -4215,23 +4294,6 @@ static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf)
 	}
 }
 
-/*
- * The CPU has been completely removed, and some other CPU is reporting
- * this fact from process context.  Do the remainder of the cleanup.
- * There can only be one CPU hotplug operation at a time, so no need for
- * explicit locking.
- */
-int rcutree_dead_cpu(unsigned int cpu)
-{
-	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
-		return 0;
-
-	WRITE_ONCE(rcu_state.n_online_cpus, rcu_state.n_online_cpus - 1);
-	// Stop-machine done, so allow nohz_full to disable tick.
-	tick_dep_clear(TICK_DEP_BIT_RCU);
-	return 0;
-}
-
 /*
  * Propagate ->qsinitmask bits up the rcu_node tree to account for the
  * first CPU in a given leaf rcu_node structure coming online.  The caller
@@ -4384,29 +4446,6 @@ int rcutree_online_cpu(unsigned int cpu)
 	return 0;
 }
 
-/*
- * Near the beginning of the process.  The CPU is still very much alive
- * with pretty much all services enabled.
- */
-int rcutree_offline_cpu(unsigned int cpu)
-{
-	unsigned long flags;
-	struct rcu_data *rdp;
-	struct rcu_node *rnp;
-
-	rdp = per_cpu_ptr(&rcu_data, cpu);
-	rnp = rdp->mynode;
-	raw_spin_lock_irqsave_rcu_node(rnp, flags);
-	rnp->ffmask &= ~rdp->grpmask;
-	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-
-	rcutree_affinity_setting(cpu, cpu);
-
-	// nohz_full CPUs need the tick for stop-machine to work quickly
-	tick_dep_set(TICK_DEP_BIT_RCU);
-	return 0;
-}
-
 /*
  * Mark the specified CPU as being online so that subsequent grace periods
  * (both expedited and normal) will wait on it.  Note that this means that
@@ -4418,8 +4457,10 @@ int rcutree_offline_cpu(unsigned int cpu)
  * from the incoming CPU rather than from the cpuhp_step mechanism.
  * This is because this function must be invoked at a precise location.
  * This incoming CPU must not have enabled interrupts yet.
+ *
+ * This mirrors the effects of rcutree_report_cpu_dead().
  */
-void rcu_cpu_starting(unsigned int cpu)
+void rcutree_report_cpu_starting(unsigned int cpu)
 {
 	unsigned long mask;
 	struct rcu_data *rdp;
@@ -4473,14 +4514,21 @@ void rcu_cpu_starting(unsigned int cpu)
  * Note that this function is special in that it is invoked directly
  * from the outgoing CPU rather than from the cpuhp_step mechanism.
  * This is because this function must be invoked at a precise location.
+ *
+ * This mirrors the effect of rcutree_report_cpu_starting().
  */
-void rcu_report_dead(unsigned int cpu)
+void rcutree_report_cpu_dead(void)
 {
-	unsigned long flags, seq_flags;
+	unsigned long flags;
 	unsigned long mask;
-	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
+	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
 	struct rcu_node *rnp = rdp->mynode;  /* Outgoing CPU's rdp & rnp. */
 
+	/*
+	 * IRQS must be disabled from now on and until the CPU dies, or an interrupt
+	 * may introduce a new READ-side while it is actually off the QS masks.
+	 */
+	lockdep_assert_irqs_disabled();
 	// Do any dangling deferred wakeups.
 	do_nocb_deferred_wakeup(rdp);
 
@@ -4488,7 +4536,6 @@ void rcu_report_dead(unsigned int cpu)
 
 	/* Remove outgoing CPU from mask in the leaf rcu_node structure. */
 	mask = rdp->grpmask;
-	local_irq_save(seq_flags);
 	arch_spin_lock(&rcu_state.ofl_lock);
 	raw_spin_lock_irqsave_rcu_node(rnp, flags); /* Enforce GP memory-order guarantee. */
 	rdp->rcu_ofl_gp_seq = READ_ONCE(rcu_state.gp_seq);
@@ -4502,8 +4549,6 @@ void rcu_report_dead(unsigned int cpu)
 	WRITE_ONCE(rnp->qsmaskinitnext, rnp->qsmaskinitnext & ~mask);
 	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	arch_spin_unlock(&rcu_state.ofl_lock);
-	local_irq_restore(seq_flags);
-
 	rdp->cpu_started = false;
 }
 
@@ -4558,7 +4603,60 @@ void rcutree_migrate_callbacks(int cpu)
 		  cpu, rcu_segcblist_n_cbs(&rdp->cblist),
 		  rcu_segcblist_first_cb(&rdp->cblist));
 }
-#endif
+
+/*
+ * The CPU has been completely removed, and some other CPU is reporting
+ * this fact from process context.  Do the remainder of the cleanup.
+ * There can only be one CPU hotplug operation at a time, so no need for
+ * explicit locking.
+ */
+int rcutree_dead_cpu(unsigned int cpu)
+{
+	WRITE_ONCE(rcu_state.n_online_cpus, rcu_state.n_online_cpus - 1);
+	// Stop-machine done, so allow nohz_full to disable tick.
+	tick_dep_clear(TICK_DEP_BIT_RCU);
+	return 0;
+}
+
+/*
+ * Near the end of the offline process.  Trace the fact that this CPU
+ * is going offline.
+ */
+int rcutree_dying_cpu(unsigned int cpu)
+{
+	bool blkd;
+	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
+	struct rcu_node *rnp = rdp->mynode;
+
+	blkd = !!(READ_ONCE(rnp->qsmask) & rdp->grpmask);
+	trace_rcu_grace_period(rcu_state.name, READ_ONCE(rnp->gp_seq),
+			       blkd ? TPS("cpuofl-bgp") : TPS("cpuofl"));
+	return 0;
+}
+
+/*
+ * Near the beginning of the process.  The CPU is still very much alive
+ * with pretty much all services enabled.
+ */
+int rcutree_offline_cpu(unsigned int cpu)
+{
+	unsigned long flags;
+	struct rcu_data *rdp;
+	struct rcu_node *rnp;
+
+	rdp = per_cpu_ptr(&rcu_data, cpu);
+	rnp = rdp->mynode;
+	raw_spin_lock_irqsave_rcu_node(rnp, flags);
+	rnp->ffmask &= ~rdp->grpmask;
+	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+
+	rcutree_affinity_setting(cpu, cpu);
+
+	// nohz_full CPUs need the tick for stop-machine to work quickly
+	tick_dep_set(TICK_DEP_BIT_RCU);
+	return 0;
+}
+#endif /* #ifdef CONFIG_HOTPLUG_CPU */
 
 /*
  * On non-huge systems, use expedited RCU grace periods to make suspend
@@ -4990,7 +5088,7 @@ void __init rcu_init(void)
 	pm_notifier(rcu_pm_notify, 0);
 	WARN_ON(num_online_cpus() > 1); // Only one CPU this early in boot.
 	rcutree_prepare_cpu(cpu);
-	rcu_cpu_starting(cpu);
+	rcutree_report_cpu_starting(cpu);
 	rcutree_online_cpu(cpu);
 
 	/* Create workqueue for Tree SRCU and for expedited GPs. */

kernel/rcu/tree.h

@@ -386,6 +386,10 @@ struct rcu_state {
 						/*  in jiffies. */
 	unsigned long jiffies_stall;		/* Time at which to check */
 						/*  for CPU stalls. */
+	int nr_fqs_jiffies_stall;		/* Number of fqs loops after
+						 * which read jiffies and set
+						 * jiffies_stall. Stall
+						 * warnings disabled if !0. */
 	unsigned long jiffies_resched;		/* Time at which to resched */
 						/*  a reluctant CPU. */
 	unsigned long n_force_qs_gpstart;	/* Snapshot of n_force_qs at */

kernel/rcu/tree_exp.h

@@ -621,10 +621,14 @@ static void synchronize_rcu_expedited_wait(void)
 	}
 
 	for (;;) {
+		unsigned long j;
+
 		if (synchronize_rcu_expedited_wait_once(jiffies_stall))
 			return;
 		if (rcu_stall_is_suppressed())
 			continue;
+		j = jiffies;
+		rcu_stall_notifier_call_chain(RCU_STALL_NOTIFY_EXP, (void *)(j - jiffies_start));
 		trace_rcu_stall_warning(rcu_state.name, TPS("ExpeditedStall"));
 		pr_err("INFO: %s detected expedited stalls on CPUs/tasks: {",
 		       rcu_state.name);
@@ -647,7 +651,7 @@ static void synchronize_rcu_expedited_wait(void)
 			}
 		}
 		pr_cont(" } %lu jiffies s: %lu root: %#lx/%c\n",
-			jiffies - jiffies_start, rcu_state.expedited_sequence,
+			j - jiffies_start, rcu_state.expedited_sequence,
 			data_race(rnp_root->expmask),
 			".T"[!!data_race(rnp_root->exp_tasks)]);
 		if (ndetected) {

kernel/rcu/tree_stall.h

@@ -8,6 +8,7 @@
  */
 
 #include <linux/kvm_para.h>
+#include <linux/rcu_notifier.h>
 
 //////////////////////////////////////////////////////////////////////////////
 //
@@ -149,12 +150,17 @@ static void panic_on_rcu_stall(void)
 /**
  * rcu_cpu_stall_reset - restart stall-warning timeout for current grace period
  *
+ * To perform the reset request from the caller, disable stall detection until
+ * 3 fqs loops have passed. This is required to ensure a fresh jiffies is
+ * loaded.  It should be safe to do from the fqs loop as enough timer
+ * interrupts and context switches should have passed.
+ *
  * The caller must disable hard irqs.
  */
 void rcu_cpu_stall_reset(void)
 {
-	WRITE_ONCE(rcu_state.jiffies_stall,
+	WRITE_ONCE(rcu_state.nr_fqs_jiffies_stall, 3);
-		   jiffies + rcu_jiffies_till_stall_check());
+	WRITE_ONCE(rcu_state.jiffies_stall, ULONG_MAX);
 }
 
 //////////////////////////////////////////////////////////////////////////////
@@ -170,6 +176,7 @@ static void record_gp_stall_check_time(void)
 	WRITE_ONCE(rcu_state.gp_start, j);
 	j1 = rcu_jiffies_till_stall_check();
 	smp_mb(); // ->gp_start before ->jiffies_stall and caller's ->gp_seq.
+	WRITE_ONCE(rcu_state.nr_fqs_jiffies_stall, 0);
 	WRITE_ONCE(rcu_state.jiffies_stall, j + j1);
 	rcu_state.jiffies_resched = j + j1 / 2;
 	rcu_state.n_force_qs_gpstart = READ_ONCE(rcu_state.n_force_qs);
@@ -534,16 +541,16 @@ static void rcu_check_gp_kthread_starvation(void)
 		       data_race(READ_ONCE(rcu_state.gp_state)),
 		       gpk ? data_race(READ_ONCE(gpk->__state)) : ~0, cpu);
 		if (gpk) {
+			struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
+
 			pr_err("\tUnless %s kthread gets sufficient CPU time, OOM is now expected behavior.\n", rcu_state.name);
 			pr_err("RCU grace-period kthread stack dump:\n");
 			sched_show_task(gpk);
-			if (cpu >= 0) {
+			if (cpu_is_offline(cpu)) {
-				if (cpu_is_offline(cpu)) {
+				pr_err("RCU GP kthread last ran on offline CPU %d.\n", cpu);
-					pr_err("RCU GP kthread last ran on offline CPU %d.\n", cpu);
+			} else if (!(data_race(READ_ONCE(rdp->mynode->qsmask)) & rdp->grpmask)) {
-				} else  {
+				pr_err("Stack dump where RCU GP kthread last ran:\n");
-					pr_err("Stack dump where RCU GP kthread last ran:\n");
+				dump_cpu_task(cpu);
-					dump_cpu_task(cpu);
-				}
 			}
 			wake_up_process(gpk);
 		}
@@ -711,7 +718,7 @@ static void print_cpu_stall(unsigned long gps)
 
 static void check_cpu_stall(struct rcu_data *rdp)
 {
-	bool didstall = false;
+	bool self_detected;
 	unsigned long gs1;
 	unsigned long gs2;
 	unsigned long gps;
@@ -725,6 +732,16 @@ static void check_cpu_stall(struct rcu_data *rdp)
 	    !rcu_gp_in_progress())
 		return;
 	rcu_stall_kick_kthreads();
+
+	/*
+	 * Check if it was requested (via rcu_cpu_stall_reset()) that the FQS
+	 * loop has to set jiffies to ensure a non-stale jiffies value. This
+	 * is required to have good jiffies value after coming out of long
+	 * breaks of jiffies updates. Not doing so can cause false positives.
+	 */
+	if (READ_ONCE(rcu_state.nr_fqs_jiffies_stall) > 0)
+		return;
+
 	j = jiffies;
 
 	/*
@@ -758,10 +775,10 @@ static void check_cpu_stall(struct rcu_data *rdp)
 		return; /* No stall or GP completed since entering function. */
 	rnp = rdp->mynode;
 	jn = jiffies + ULONG_MAX / 2;
+	self_detected = READ_ONCE(rnp->qsmask) & rdp->grpmask;
 	if (rcu_gp_in_progress() &&
-	    (READ_ONCE(rnp->qsmask) & rdp->grpmask) &&
+	    (self_detected || ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY)) &&
 	    cmpxchg(&rcu_state.jiffies_stall, js, jn) == js) {
-
 		/*
 		 * If a virtual machine is stopped by the host it can look to
 		 * the watchdog like an RCU stall. Check to see if the host
@@ -770,39 +787,28 @@ static void check_cpu_stall(struct rcu_data *rdp)
 		if (kvm_check_and_clear_guest_paused())
 			return;
 
-		/* We haven't checked in, so go dump stack. */
+		rcu_stall_notifier_call_chain(RCU_STALL_NOTIFY_NORM, (void *)j - gps);
-		print_cpu_stall(gps);
+		if (self_detected) {
+			/* We haven't checked in, so go dump stack. */
+			print_cpu_stall(gps);
+		} else {
+			/* They had a few time units to dump stack, so complain. */
+			print_other_cpu_stall(gs2, gps);
+		}
+
 		if (READ_ONCE(rcu_cpu_stall_ftrace_dump))
 			rcu_ftrace_dump(DUMP_ALL);
-		didstall = true;
 
-	} else if (rcu_gp_in_progress() &&
+		if (READ_ONCE(rcu_state.jiffies_stall) == jn) {
-		   ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY) &&
+			jn = jiffies + 3 * rcu_jiffies_till_stall_check() + 3;
-		   cmpxchg(&rcu_state.jiffies_stall, js, jn) == js) {
+			WRITE_ONCE(rcu_state.jiffies_stall, jn);
-
+		}
-		/*
-		 * If a virtual machine is stopped by the host it can look to
-		 * the watchdog like an RCU stall. Check to see if the host
-		 * stopped the vm.
-		 */
-		if (kvm_check_and_clear_guest_paused())
-			return;
-
-		/* They had a few time units to dump stack, so complain. */
-		print_other_cpu_stall(gs2, gps);
-		if (READ_ONCE(rcu_cpu_stall_ftrace_dump))
-			rcu_ftrace_dump(DUMP_ALL);
-		didstall = true;
-	}
-	if (didstall && READ_ONCE(rcu_state.jiffies_stall) == jn) {
-		jn = jiffies + 3 * rcu_jiffies_till_stall_check() + 3;
-		WRITE_ONCE(rcu_state.jiffies_stall, jn);
 	}
 }
 
 //////////////////////////////////////////////////////////////////////////////
 //
-// RCU forward-progress mechanisms, including of callback invocation.
+// RCU forward-progress mechanisms, including for callback invocation.
 
 
 /*
@@ -1054,3 +1060,58 @@ static int __init rcu_sysrq_init(void)
 	return 0;
 }
 early_initcall(rcu_sysrq_init);
+
+
+//////////////////////////////////////////////////////////////////////////////
+//
+// RCU CPU stall-warning notifiers
+
+static ATOMIC_NOTIFIER_HEAD(rcu_cpu_stall_notifier_list);
+
+/**
+ * rcu_stall_chain_notifier_register - Add an RCU CPU stall notifier
+ * @n: Entry to add.
+ *
+ * Adds an RCU CPU stall notifier to an atomic notifier chain.
+ * The @action passed to a notifier will be @RCU_STALL_NOTIFY_NORM or
+ * friends.  The @data will be the duration of the stalled grace period,
+ * in jiffies, coerced to a void* pointer.
+ *
+ * Returns 0 on success, %-EEXIST on error.
+ */
+int rcu_stall_chain_notifier_register(struct notifier_block *n)
+{
+	return atomic_notifier_chain_register(&rcu_cpu_stall_notifier_list, n);
+}
+EXPORT_SYMBOL_GPL(rcu_stall_chain_notifier_register);
+
+/**
+ * rcu_stall_chain_notifier_unregister - Remove an RCU CPU stall notifier
+ * @n: Entry to add.
+ *
+ * Removes an RCU CPU stall notifier from an atomic notifier chain.
+ *
+ * Returns zero on success, %-ENOENT on failure.
+ */
+int rcu_stall_chain_notifier_unregister(struct notifier_block *n)
+{
+	return atomic_notifier_chain_unregister(&rcu_cpu_stall_notifier_list, n);
+}
+EXPORT_SYMBOL_GPL(rcu_stall_chain_notifier_unregister);
+
+/*
+ * rcu_stall_notifier_call_chain - Call functions in an RCU CPU stall notifier chain
+ * @val: Value passed unmodified to notifier function
+ * @v: Pointer passed unmodified to notifier function
+ *
+ * Calls each function in the RCU CPU stall notifier chain in turn, which
+ * is an atomic call chain.  See atomic_notifier_call_chain() for more
+ * information.
+ *
+ * This is for use within RCU, hence the omission of the extra asterisk
+ * to indicate a non-kerneldoc format header comment.
+ */
+int rcu_stall_notifier_call_chain(unsigned long val, void *v)
+{
+	return atomic_notifier_call_chain(&rcu_cpu_stall_notifier_list, val, v);
+}

mm/slab_common.c

@@ -528,26 +528,6 @@ bool slab_is_available(void)
 }
 
 #ifdef CONFIG_PRINTK
-/**
- * kmem_valid_obj - does the pointer reference a valid slab object?
- * @object: pointer to query.
- *
- * Return: %true if the pointer is to a not-yet-freed object from
- * kmalloc() or kmem_cache_alloc(), either %true or %false if the pointer
- * is to an already-freed object, and %false otherwise.
- */
-bool kmem_valid_obj(void *object)
-{
-	struct folio *folio;
-
-	/* Some arches consider ZERO_SIZE_PTR to be a valid address. */
-	if (object < (void *)PAGE_SIZE || !virt_addr_valid(object))
-		return false;
-	folio = virt_to_folio(object);
-	return folio_test_slab(folio);
-}
-EXPORT_SYMBOL_GPL(kmem_valid_obj);
-
 static void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab)
 {
 	if (__kfence_obj_info(kpp, object, slab))
@@ -566,11 +546,11 @@ static void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *
  * and, if available, the slab name, return address, and stack trace from
  * the allocation and last free path of that object.
  *
- * This function will splat if passed a pointer to a non-slab object.
+ * Return: %true if the pointer is to a not-yet-freed object from
- * If you are not sure what type of object you have, you should instead
+ * kmalloc() or kmem_cache_alloc(), either %true or %false if the pointer
- * use mem_dump_obj().
+ * is to an already-freed object, and %false otherwise.
  */
-void kmem_dump_obj(void *object)
+bool kmem_dump_obj(void *object)
 {
 	char *cp = IS_ENABLED(CONFIG_MMU) ? "" : "/vmalloc";
 	int i;
@@ -578,13 +558,13 @@ void kmem_dump_obj(void *object)
 	unsigned long ptroffset;
 	struct kmem_obj_info kp = { };
 
-	if (WARN_ON_ONCE(!virt_addr_valid(object)))
+	/* Some arches consider ZERO_SIZE_PTR to be a valid address. */
-		return;
+	if (object < (void *)PAGE_SIZE || !virt_addr_valid(object))
+		return false;
 	slab = virt_to_slab(object);
-	if (WARN_ON_ONCE(!slab)) {
+	if (!slab)
-		pr_cont(" non-slab memory.\n");
+		return false;
-		return;
+
-	}
 	kmem_obj_info(&kp, object, slab);
 	if (kp.kp_slab_cache)
 		pr_cont(" slab%s %s", cp, kp.kp_slab_cache->name);
@@ -621,6 +601,7 @@ void kmem_dump_obj(void *object)
 		pr_info("    %pS\n", kp.kp_free_stack[i]);
 	}
 
+	return true;
 }
 EXPORT_SYMBOL_GPL(kmem_dump_obj);
 #endif

mm/util.c

@@ -1060,10 +1060,8 @@ void mem_dump_obj(void *object)
 {
 	const char *type;
 
-	if (kmem_valid_obj(object)) {
+	if (kmem_dump_obj(object))
-		kmem_dump_obj(object);
 		return;
-	}
 
 	if (vmalloc_dump_obj(object))
 		return;

scripts/checkpatch.pl

@@ -6427,15 +6427,6 @@ sub process {
 			}
 		}
 
-# check for soon-to-be-deprecated single-argument k[v]free_rcu() API
-		if ($line =~ /\bk[v]?free_rcu\s*\([^(]+\)/) {
-			if ($line =~ /\bk[v]?free_rcu\s*\([^,]+\)/) {
-				ERROR("DEPRECATED_API",
-				      "Single-argument k[v]free_rcu() API is deprecated, please pass rcu_head object or call k[v]free_rcu_mightsleep()." . $herecurr);
-			}
-		}
-
-
 # check for unnecessary "Out of Memory" messages
 		if ($line =~ /^\+.*\b$logFunctions\s*\(/ &&
 		    $prevline =~ /^[ \+]\s*if\s*\(\s*(\!\s*|NULL\s*==\s*)?($Lval)(\s*==\s*NULL\s*)?\s*\)/ &&