Merge tag 'rcu.2023.02.10a' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu

Pull RCU updates from Paul McKenney:

 - Documentation updates

 - Miscellaneous fixes, perhaps most notably:

      - Throttling callback invocation based on the number of callbacks
        that are now ready to invoke instead of on the total number of
        callbacks

      - Several patches that suppress false-positive boot-time
        diagnostics, for example, due to lockdep not yet being
        initialized

      - Make expedited RCU CPU stall warnings dump stacks of any tasks
        that are blocking the stalled grace period. (Normal RCU CPU
        stall warnings have done this for many years)

      - Lazy-callback fixes to avoid delays during boot, suspend, and
        resume. (Note that lazy callbacks must be explicitly enabled, so
        this should not (yet) affect production use cases)

 - Make kfree_rcu() and friends take advantage of polled grace periods,
   thus reducing memory footprint by almost two orders of magnitude,
   admittedly on a microbenchmark

   This also begins the transition from kfree_rcu(p) to
   kfree_rcu_mightsleep(p). This transition was motivated by bugs where
   kfree_rcu(p), which can block, was typed instead of the intended
   kfree_rcu(p, rh)

 - SRCU updates, perhaps most notably fixing a bug that causes SRCU to
   fail when booted on a system with a non-zero boot CPU. This
   surprising situation actually happens for kdump kernels on the
   powerpc architecture

   This also adds an srcu_down_read() and srcu_up_read(), which act like
   srcu_read_lock() and srcu_read_unlock(), but allow an SRCU read-side
   critical section to be handed off from one task to another

 - Clean up the now-useless SRCU Kconfig option

   There are a few more commits that are not yet acked or pulled into
   maintainer trees, and these will be in a pull request for a later
   merge window

 - RCU-tasks updates, perhaps most notably these fixes:

      - A strange interaction between PID-namespace unshare and the
        RCU-tasks grace period that results in a low-probability but
        very real hang

      - A race between an RCU tasks rude grace period on a single-CPU
        system and CPU-hotplug addition of the second CPU that can
        result in a too-short grace period

      - A race between shrinking RCU tasks down to a single callback
        list and queuing a new callback to some other CPU, but where
        that queuing is delayed for more than an RCU grace period. This
        can result in that callback being stranded on the non-boot CPU

 - Torture-test updates and fixes

 - Torture-test scripting updates and fixes

 - Provide additional RCU CPU stall-warning information in kernels built
   with CONFIG_RCU_CPU_STALL_CPUTIME=y, and restore the full five-minute
   timeout limit for expedited RCU CPU stall warnings

* tag 'rcu.2023.02.10a' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu: (80 commits)
  rcu/kvfree: Add kvfree_rcu_mightsleep() and kfree_rcu_mightsleep()
  kernel/notifier: Remove CONFIG_SRCU
  init: Remove "select SRCU"
  fs/quota: Remove "select SRCU"
  fs/notify: Remove "select SRCU"
  fs/btrfs: Remove "select SRCU"
  fs: Remove CONFIG_SRCU
  drivers/pci/controller: Remove "select SRCU"
  drivers/net: Remove "select SRCU"
  drivers/md: Remove "select SRCU"
  drivers/hwtracing/stm: Remove "select SRCU"
  drivers/dax: Remove "select SRCU"
  drivers/base: Remove CONFIG_SRCU
  rcu: Disable laziness if lazy-tracking says so
  rcu: Track laziness during boot and suspend
  rcu: Remove redundant call to rcu_boost_kthread_setaffinity()
  rcu: Allow up to five minutes expedited RCU CPU stall-warning timeouts
  rcu: Align the output of RCU CPU stall warning messages
  rcu: Add RCU stall diagnosis information
  sched: Add helper nr_context_switches_cpu()
  ...

7 files changed, 82 insertions, 14 deletions

diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h
index ddb5a358fd82..9935f7ecbfb9 100644
--- a/include/linux/kernel_stat.h
+++ b/include/linux/kernel_stat.h
@@ -52,6 +52,7 @@ DECLARE_PER_CPU(struct kernel_cpustat, kernel_cpustat);
 #define kstat_cpu(cpu) per_cpu(kstat, cpu)
 #define kcpustat_cpu(cpu) per_cpu(kernel_cpustat, cpu)
 
+extern unsigned long long nr_context_switches_cpu(int cpu);
 extern unsigned long long nr_context_switches(void);
 
 extern unsigned int kstat_irqs_cpu(unsigned int irq, int cpu);
@@ -67,6 +68,17 @@ static inline unsigned int kstat_softirqs_cpu(unsigned int irq, int cpu)
        return kstat_cpu(cpu).softirqs[irq];
 }
 
+static inline unsigned int kstat_cpu_softirqs_sum(int cpu)
+{
+	int i;
+	unsigned int sum = 0;
+
+	for (i = 0; i < NR_SOFTIRQS; i++)
+		sum += kstat_softirqs_cpu(i, cpu);
+
+	return sum;
+}
+
 /*
  * Number of interrupts per specific IRQ source, since bootup
  */
@@ -75,7 +87,7 @@ extern unsigned int kstat_irqs_usr(unsigned int irq);
 /*
  * Number of interrupts per cpu, since bootup
  */
-static inline unsigned int kstat_cpu_irqs_sum(unsigned int cpu)
+static inline unsigned long kstat_cpu_irqs_sum(unsigned int cpu)
 {
 	return kstat_cpu(cpu).irqs_sum;
 }
diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h
index d8afdb8784c1..ba4c00dd8005 100644
--- a/include/linux/rculist_nulls.h
+++ b/include/linux/rculist_nulls.h
@@ -139,7 +139,7 @@ static inline void hlist_nulls_add_tail_rcu(struct hlist_nulls_node *n,
 	if (last) {
 		n->next = last->next;
 		n->pprev = &last->next;
-		rcu_assign_pointer(hlist_next_rcu(last), n);
+		rcu_assign_pointer(hlist_nulls_next_rcu(last), n);
 	} else {
 		hlist_nulls_add_head_rcu(n, h);
 	}
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 03abf883a281..094321c17e48 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -238,6 +238,7 @@ void synchronize_rcu_tasks_rude(void);
 
 #define rcu_note_voluntary_context_switch(t) rcu_tasks_qs(t, false)
 void exit_tasks_rcu_start(void);
+void exit_tasks_rcu_stop(void);
 void exit_tasks_rcu_finish(void);
 #else /* #ifdef CONFIG_TASKS_RCU_GENERIC */
 #define rcu_tasks_classic_qs(t, preempt) do { } while (0)
@@ -246,6 +247,7 @@ void exit_tasks_rcu_finish(void);
 #define call_rcu_tasks call_rcu
 #define synchronize_rcu_tasks synchronize_rcu
 static inline void exit_tasks_rcu_start(void) { }
+static inline void exit_tasks_rcu_stop(void) { }
 static inline void exit_tasks_rcu_finish(void) { }
 #endif /* #else #ifdef CONFIG_TASKS_RCU_GENERIC */
 
@@ -374,11 +376,18 @@ static inline int debug_lockdep_rcu_enabled(void)
  * RCU_LOCKDEP_WARN - emit lockdep splat if specified condition is met
  * @c: condition to check
  * @s: informative message
+ *
+ * This checks debug_lockdep_rcu_enabled() before checking (c) to
+ * prevent early boot splats due to lockdep not yet being initialized,
+ * and rechecks it after checking (c) to prevent false-positive splats
+ * due to races with lockdep being disabled.  See commit 3066820034b5dd
+ * ("rcu: Reject RCU_LOCKDEP_WARN() false positives") for more detail.
  */
 #define RCU_LOCKDEP_WARN(c, s)						\
 	do {								\
 		static bool __section(".data.unlikely") __warned;	\
-		if ((c) && debug_lockdep_rcu_enabled() && !__warned) {	\
+		if (debug_lockdep_rcu_enabled() && (c) &&		\
+		    debug_lockdep_rcu_enabled() && !__warned) {		\
 			__warned = true;				\
 			lockdep_rcu_suspicious(__FILE__, __LINE__, s);	\
 		}							\
@@ -1004,6 +1013,9 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
 #define kvfree_rcu(...) KVFREE_GET_MACRO(__VA_ARGS__,		\
 	kvfree_rcu_arg_2, kvfree_rcu_arg_1)(__VA_ARGS__)
 
+#define kvfree_rcu_mightsleep(ptr) kvfree_rcu_arg_1(ptr)
+#define kfree_rcu_mightsleep(ptr) kvfree_rcu_mightsleep(ptr)
+
 #define KVFREE_GET_MACRO(_1, _2, NAME, ...) NAME
 #define kvfree_rcu_arg_2(ptr, rhf)					\
 do {									\
@@ -1011,8 +1023,7 @@ do {									\
 									\
 	if (___p) {									\
 		BUILD_BUG_ON(!__is_kvfree_rcu_offset(offsetof(typeof(*(ptr)), rhf)));	\
-		kvfree_call_rcu(&((___p)->rhf), (rcu_callback_t)(unsigned long)		\
-			(offsetof(typeof(*(ptr)), rhf)));				\
+		kvfree_call_rcu(&((___p)->rhf), (void *) (___p));			\
 	}										\
 } while (0)
 
@@ -1021,7 +1032,7 @@ do {								\
 	typeof(ptr) ___p = (ptr);				\
 								\
 	if (___p)						\
-		kvfree_call_rcu(NULL, (rcu_callback_t) (___p));	\
+		kvfree_call_rcu(NULL, (void *) (___p));		\
 } while (0)
 
 /*
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 68f9070aa111..7f17acf29dda 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -98,25 +98,25 @@ static inline void synchronize_rcu_expedited(void)
  */
 extern void kvfree(const void *addr);
 
-static inline void __kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
+static inline void __kvfree_call_rcu(struct rcu_head *head, void *ptr)
 {
 	if (head) {
-		call_rcu(head, func);
+		call_rcu(head, (rcu_callback_t) ((void *) head - ptr));
 		return;
 	}
 
 	// kvfree_rcu(one_arg) call.
 	might_sleep();
 	synchronize_rcu();
-	kvfree((void *) func);
+	kvfree(ptr);
 }
 
 #ifdef CONFIG_KASAN_GENERIC
-void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func);
+void kvfree_call_rcu(struct rcu_head *head, void *ptr);
 #else
-static inline void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
+static inline void kvfree_call_rcu(struct rcu_head *head, void *ptr)
 {
-	__kvfree_call_rcu(head, func);
+	__kvfree_call_rcu(head, ptr);
 }
 #endif
 
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index 4003bf6cfa1c..56bccb5a8fde 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -33,7 +33,7 @@ static inline void rcu_virt_note_context_switch(void)
 }
 
 void synchronize_rcu_expedited(void);
-void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func);
+void kvfree_call_rcu(struct rcu_head *head, void *ptr);
 
 void rcu_barrier(void);
 bool rcu_eqs_special_set(int cpu);
diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index 9b9d0bbf1d3c..74796cd7e7a9 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -215,6 +215,34 @@ srcu_read_lock_notrace(struct srcu_struct *ssp) __acquires(ssp)
 }
 
 /**
+ * srcu_down_read - register a new reader for an SRCU-protected structure.
+ * @ssp: srcu_struct in which to register the new reader.
+ *
+ * Enter a semaphore-like SRCU read-side critical section.  Note that
+ * SRCU read-side critical sections may be nested.  However, it is
+ * illegal to call anything that waits on an SRCU grace period for the
+ * same srcu_struct, whether directly or indirectly.  Please note that
+ * one way to indirectly wait on an SRCU grace period is to acquire
+ * a mutex that is held elsewhere while calling synchronize_srcu() or
+ * synchronize_srcu_expedited().  But if you want lockdep to help you
+ * keep this stuff straight, you should instead use srcu_read_lock().
+ *
+ * The semaphore-like nature of srcu_down_read() means that the matching
+ * srcu_up_read() can be invoked from some other context, for example,
+ * from some other task or from an irq handler.  However, neither
+ * srcu_down_read() nor srcu_up_read() may be invoked from an NMI handler.
+ *
+ * Calls to srcu_down_read() may be nested, similar to the manner in
+ * which calls to down_read() may be nested.
+ */
+static inline int srcu_down_read(struct srcu_struct *ssp) __acquires(ssp)
+{
+	WARN_ON_ONCE(in_nmi());
+	srcu_check_nmi_safety(ssp, false);
+	return __srcu_read_lock(ssp);
+}
+
+/**
  * srcu_read_unlock - unregister a old reader from an SRCU-protected structure.
  * @ssp: srcu_struct in which to unregister the old reader.
  * @idx: return value from corresponding srcu_read_lock().
@@ -255,6 +283,23 @@ srcu_read_unlock_notrace(struct srcu_struct *ssp, int idx) __releases(ssp)
 }
 
 /**
+ * srcu_up_read - unregister a old reader from an SRCU-protected structure.
+ * @ssp: srcu_struct in which to unregister the old reader.
+ * @idx: return value from corresponding srcu_read_lock().
+ *
+ * Exit an SRCU read-side critical section, but not necessarily from
+ * the same context as the maching srcu_down_read().
+ */
+static inline void srcu_up_read(struct srcu_struct *ssp, int idx)
+	__releases(ssp)
+{
+	WARN_ON_ONCE(idx & ~0x1);
+	WARN_ON_ONCE(in_nmi());
+	srcu_check_nmi_safety(ssp, false);
+	__srcu_read_unlock(ssp, idx);
+}
+
+/**
  * smp_mb__after_srcu_read_unlock - ensure full ordering after srcu_read_unlock
  *
  * Converts the preceding srcu_read_unlock into a two-way memory barrier.
diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h
index c689a81752c9..558057b517b7 100644
--- a/include/linux/srcutree.h
+++ b/include/linux/srcutree.h
@@ -49,7 +49,7 @@ struct srcu_data {
 struct srcu_node {
 	spinlock_t __private lock;
 	unsigned long srcu_have_cbs[4];		/* GP seq for children having CBs, but only */
-						/*  if greater than ->srcu_gq_seq. */
+						/*  if greater than ->srcu_gp_seq. */
 	unsigned long srcu_data_have_cbs[4];	/* Which srcu_data structs have CBs for given GP? */
 	unsigned long srcu_gp_seq_needed_exp;	/* Furthest future exp GP. */
 	struct srcu_node *srcu_parent;		/* Next up in tree. */