Merge branch 'core-rcu.2021.08.28a' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu

Pull RCU updates from Paul McKenney:
 "RCU changes for this cycle were:

   - Documentation updates

   - Miscellaneous fixes

   - Offloaded-callbacks updates

   - Updates to the nolibc library

   - Tasks-RCU updates

   - In-kernel torture-test updates

   - Torture-test scripting, perhaps most notably the pinning of
     torture-test guest OSes so as to force differences in memory
     latency. For example, in a two-socket system, a four-CPU guest OS
     will have one pair of its CPUs pinned to threads in a single core
     on one socket and the other pair pinned to threads in a single core
     on the other socket. This approach proved able to force race
     conditions that earlier testing missed. Some of these race
     conditions are still being tracked down"

* 'core-rcu.2021.08.28a' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu: (61 commits)
  torture: Replace deprecated CPU-hotplug functions.
  rcu: Replace deprecated CPU-hotplug functions
  rcu: Print human-readable message for schedule() in RCU reader
  rcu: Explain why rcu_all_qs() is a stub in preemptible TREE RCU
  rcu: Use per_cpu_ptr to get the pointer of per_cpu variable
  rcu: Remove useless "ret" update in rcu_gp_fqs_loop()
  rcu: Mark accesses in tree_stall.h
  rcu: Make rcu_gp_init() and rcu_gp_fqs_loop noinline to conserve stack
  rcu: Mark lockless ->qsmask read in rcu_check_boost_fail()
  srcutiny: Mark read-side data races
  rcu: Start timing stall repetitions after warning complete
  rcu: Do not disable GP stall detection in rcu_cpu_stall_reset()
  rcu/tree: Handle VM stoppage in stall detection
  rculist: Unify documentation about missing list_empty_rcu()
  rcu: Mark accesses to ->rcu_read_lock_nesting
  rcu: Weaken ->dynticks accesses and updates
  rcu: Remove special bit at the bottom of the ->dynticks counter
  rcu: Fix stall-warning deadlock due to non-release of rcu_node ->lock
  rcu: Fix to include first blocked task in stall warning
  torture: Make kvm-test-1-run-qemu.sh check for reboot loops
  ...

4 files changed, 23 insertions, 27 deletions

diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index f8633d37e358..d29740be4833 100644
--- a/include/linux/rculist.h
+++ b/include/linux/rculist.h
@@ -11,15 +11,6 @@
 #include <linux/rcupdate.h>
 
 /*
- * Why is there no list_empty_rcu()?  Because list_empty() serves this
- * purpose.  The list_empty() function fetches the RCU-protected pointer
- * and compares it to the address of the list head, but neither dereferences
- * this pointer itself nor provides this pointer to the caller.  Therefore,
- * it is not necessary to use rcu_dereference(), so that list_empty() can
- * be used anywhere you would want to use a list_empty_rcu().
- */
-
-/*
  * INIT_LIST_HEAD_RCU - Initialize a list_head visible to RCU readers
  * @list: list to be initialized
  *
@@ -318,21 +309,29 @@ static inline void list_splice_tail_init_rcu(struct list_head *list,
 /*
  * Where are list_empty_rcu() and list_first_entry_rcu()?
  *
- * Implementing those functions following their counterparts list_empty() and
- * list_first_entry() is not advisable because they lead to subtle race
- * conditions as the following snippet shows:
+ * They do not exist because they would lead to subtle race conditions:
  *
  * if (!list_empty_rcu(mylist)) {
  *	struct foo *bar = list_first_entry_rcu(mylist, struct foo, list_member);
  *	do_something(bar);
  * }
  *
- * The list may not be empty when list_empty_rcu checks it, but it may be when
- * list_first_entry_rcu rereads the ->next pointer.
- *
- * Rereading the ->next pointer is not a problem for list_empty() and
- * list_first_entry() because they would be protected by a lock that blocks
- * writers.
+ * The list might be non-empty when list_empty_rcu() checks it, but it
+ * might have become empty by the time that list_first_entry_rcu() rereads
+ * the ->next pointer, which would result in a SEGV.
+ *
+ * When not using RCU, it is OK for list_first_entry() to re-read that
+ * pointer because both functions should be protected by some lock that
+ * blocks writers.
+ *
+ * When using RCU, list_empty() uses READ_ONCE() to fetch the
+ * RCU-protected ->next pointer and then compares it to the address of the
+ * list head.  However, it neither dereferences this pointer nor provides
+ * this pointer to its caller.  Thus, READ_ONCE() suffices (that is,
+ * rcu_dereference() is not needed), which means that list_empty() can be
+ * used anywhere you would want to use list_empty_rcu().  Just don't
+ * expect anything useful to happen if you do a subsequent lockless
+ * call to list_first_entry_rcu()!!!
  *
  * See list_first_or_null_rcu for an alternative.
  */
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index d9680b798b21..434d12fe2d4f 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -53,7 +53,7 @@ void __rcu_read_unlock(void);
  * nesting depth, but makes sense only if CONFIG_PREEMPT_RCU -- in other
  * types of kernel builds, the rcu_read_lock() nesting depth is unknowable.
  */
-#define rcu_preempt_depth() (current->rcu_read_lock_nesting)
+#define rcu_preempt_depth() READ_ONCE(current->rcu_read_lock_nesting)
 
 #else /* #ifdef CONFIG_PREEMPT_RCU */
 
@@ -167,7 +167,7 @@ void synchronize_rcu_tasks(void);
 # define synchronize_rcu_tasks synchronize_rcu
 # endif
 
-# ifdef CONFIG_TASKS_RCU_TRACE
+# ifdef CONFIG_TASKS_TRACE_RCU
 # define rcu_tasks_trace_qs(t)						\
 	do {								\
 		if (!likely(READ_ONCE((t)->trc_reader_checked)) &&	\
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 953e70fafe38..9be015305f9f 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -14,9 +14,6 @@
 
 #include <asm/param.h> /* for HZ */
 
-/* Never flag non-existent other CPUs! */
-static inline bool rcu_eqs_special_set(int cpu) { return false; }
-
 unsigned long get_state_synchronize_rcu(void);
 unsigned long start_poll_synchronize_rcu(void);
 bool poll_state_synchronize_rcu(unsigned long oldstate);
diff --git a/include/linux/srcutiny.h b/include/linux/srcutiny.h
index 0e0cf4d6a72a..6cfaa0a9a9b9 100644
--- a/include/linux/srcutiny.h
+++ b/include/linux/srcutiny.h
@@ -61,7 +61,7 @@ static inline int __srcu_read_lock(struct srcu_struct *ssp)
 	int idx;
 
 	idx = ((READ_ONCE(ssp->srcu_idx) + 1) & 0x2) >> 1;
-	WRITE_ONCE(ssp->srcu_lock_nesting[idx], ssp->srcu_lock_nesting[idx] + 1);
+	WRITE_ONCE(ssp->srcu_lock_nesting[idx], READ_ONCE(ssp->srcu_lock_nesting[idx]) + 1);
 	return idx;
 }
 
@@ -81,11 +81,11 @@ static inline void srcu_torture_stats_print(struct srcu_struct *ssp,
 {
 	int idx;
 
-	idx = ((READ_ONCE(ssp->srcu_idx) + 1) & 0x2) >> 1;
+	idx = ((data_race(READ_ONCE(ssp->srcu_idx)) + 1) & 0x2) >> 1;
 	pr_alert("%s%s Tiny SRCU per-CPU(idx=%d): (%hd,%hd)\n",
 		 tt, tf, idx,
-		 READ_ONCE(ssp->srcu_lock_nesting[!idx]),
-		 READ_ONCE(ssp->srcu_lock_nesting[idx]));
+		 data_race(READ_ONCE(ssp->srcu_lock_nesting[!idx])),
+		 data_race(READ_ONCE(ssp->srcu_lock_nesting[idx])));
 }
 
 #endif