Merge branch 'rcu-v28-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'rcu-v28-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (21 commits)
  rcu: RCU-based detection of stalled CPUs for Classic RCU, fix
  rcu: RCU-based detection of stalled CPUs for Classic RCU
  rcu: add rcu_read_lock_sched() / rcu_read_unlock_sched()
  rcu: fix sparse shadowed variable warning
  doc/RCU: fix pseudocode in rcuref.txt
  rcuclassic: fix compiler warning
  rcu: use irq-safe locks
  rcuclassic: fix compilation NG
  rcu: fix locking cleanup fallout
  rcu: remove redundant ACCESS_ONCE definition from rcupreempt.c
  rcu: fix classic RCU locking cleanup lockdep problem
  rcu: trace fix possible mem-leak
  rcu: just rename call_rcu_bh instead of making it a macro
  rcu: remove list_for_each_rcu()
  rcu: fixes to include/linux/rcupreempt.h
  rcu: classic RCU locking and memory-barrier cleanups
  rcu: prevent console flood when one CPU sees another AWOL via RCU
  rcu, debug: detect stalled grace periods, cleanups
  rcu, debug: detect stalled grace periods
  rcu classic: new algorithm for callbacks-processing(v2)
  ...

Documentation/RCU/checklist.txt

@@ -210,7 +210,7 @@ over a rather long period of time, but improvements are always welcome!
 		number of updates per grace period.
 
 9.	All RCU list-traversal primitives, which include
-	rcu_dereference(), list_for_each_rcu(), list_for_each_entry_rcu(),
+	rcu_dereference(), list_for_each_entry_rcu(),
 	list_for_each_continue_rcu(), and list_for_each_safe_rcu(),
 	must be either within an RCU read-side critical section or
 	must be protected by appropriate update-side locks.  RCU

Documentation/RCU/rcuref.txt

@@ -29,9 +29,9 @@ release_referenced()			delete()
 					}
 
 If this list/array is made lock free using RCU as in changing the
-write_lock() in add() and delete() to spin_lock and changing read_lock
-in search_and_reference to rcu_read_lock(), the atomic_get in
-search_and_reference could potentially hold reference to an element which
+write_lock() in add() and delete() to spin_lock() and changing read_lock()
+in search_and_reference() to rcu_read_lock(), the atomic_inc() in
+search_and_reference() could potentially hold reference to an element which
 has already been deleted from the list/array.  Use atomic_inc_not_zero()
 in this scenario as follows:
 
@@ -40,20 +40,20 @@ add()					search_and_reference()
 {					{
     alloc_object			    rcu_read_lock();
     ...					    search_for_element
-    atomic_set(&el->rc, 1);		    if (atomic_inc_not_zero(&el->rc)) {
-    write_lock(&list_lock);		        rcu_read_unlock();
+    atomic_set(&el->rc, 1);		    if (!atomic_inc_not_zero(&el->rc)) {
+    spin_lock(&list_lock);		        rcu_read_unlock();
 					        return FAIL;
     add_element				    }
     ...					    ...
-    write_unlock(&list_lock);		    rcu_read_unlock();
+    spin_unlock(&list_lock);		    rcu_read_unlock();
 }					}
 3.					4.
 release_referenced()			delete()
 {					{
-    ...					    write_lock(&list_lock);
+    ...					    spin_lock(&list_lock);
     if (atomic_dec_and_test(&el->rc))       ...
         call_rcu(&el->head, el_free);       delete_element
-    ...                                     write_unlock(&list_lock);
+    ...                                     spin_unlock(&list_lock);
 } 					    ...
 					    if (atomic_dec_and_test(&el->rc))
 					        call_rcu(&el->head, el_free);

Documentation/RCU/whatisRCU.txt

@@ -786,8 +786,6 @@ RCU pointer/list traversal:
 	list_for_each_entry_rcu
 	hlist_for_each_entry_rcu
 
-	list_for_each_rcu		(to be deprecated in favor of
-					 list_for_each_entry_rcu)
 	list_for_each_continue_rcu	(to be deprecated in favor of new
 					 list_for_each_entry_continue_rcu)
 

include/linux/compiler.h

@@ -190,7 +190,9 @@ extern void __chk_io_ptr(const volatile void __iomem *);
  * ACCESS_ONCE() in different C statements.
  *
  * This macro does absolutely -nothing- to prevent the CPU from reordering,
- * merging, or refetching absolutely anything at any time.
+ * merging, or refetching absolutely anything at any time.  Its main intended
+ * use is to mediate communication between process-level code and irq/NMI
+ * handlers, all running on the same CPU.
  */
 #define ACCESS_ONCE(x) (*(volatile typeof(x) *)&(x))
 

include/linux/rcuclassic.h

@@ -40,12 +40,21 @@
 #include <linux/cpumask.h>
 #include <linux/seqlock.h>
 
+#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
+#define RCU_SECONDS_TILL_STALL_CHECK	( 3 * HZ) /* for rcp->jiffies_stall */
+#define RCU_SECONDS_TILL_STALL_RECHECK	(30 * HZ) /* for rcp->jiffies_stall */
+#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
 
 /* Global control variables for rcupdate callback mechanism. */
 struct rcu_ctrlblk {
 	long	cur;		/* Current batch number.                      */
 	long	completed;	/* Number of the last completed batch         */
-	int	next_pending;	/* Is the next batch already waiting?         */
+	long	pending;	/* Number of the last pending batch           */
+#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
+	unsigned long gp_start;	/* Time at which GP started in jiffies. */
+	unsigned long jiffies_stall;
+				/* Time at which to check for CPU stalls. */
+#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
 
 	int	signaled;
 
@@ -66,11 +75,7 @@ static inline int rcu_batch_after(long a, long b)
 	return (a - b) > 0;
 }
 
-/*
- * Per-CPU data for Read-Copy UPdate.
- * nxtlist - new callbacks are added here
- * curlist - current batch for which quiescent cycle started if any
- */
+/* Per-CPU data for Read-Copy UPdate. */
 struct rcu_data {
 	/* 1) quiescent state handling : */
 	long		quiescbatch;     /* Batch # for grace period */
@@ -78,12 +83,24 @@ struct rcu_data {
 	int		qs_pending;	 /* core waits for quiesc state */
 
 	/* 2) batch handling */
-	long  	       	batch;           /* Batch # for current RCU batch */
+	/*
+	 * if nxtlist is not NULL, then:
+	 * batch:
+	 *	The batch # for the last entry of nxtlist
+	 * [*nxttail[1], NULL = *nxttail[2]):
+	 *	Entries that batch # <= batch
+	 * [*nxttail[0], *nxttail[1]):
+	 *	Entries that batch # <= batch - 1
+	 * [nxtlist, *nxttail[0]):
+	 *	Entries that batch # <= batch - 2
+	 *	The grace period for these entries has completed, and
+	 *	the other grace-period-completed entries may be moved
+	 *	here temporarily in rcu_process_callbacks().
+	 */
+	long  	       	batch;
 	struct rcu_head *nxtlist;
-	struct rcu_head **nxttail;
+	struct rcu_head **nxttail[3];
 	long            qlen; 	 	 /* # of queued callbacks */
-	struct rcu_head *curlist;
-	struct rcu_head **curtail;
 	struct rcu_head *donelist;
 	struct rcu_head **donetail;
 	long		blimit;		 /* Upper limit on a processed batch */

include/linux/rculist.h

@@ -198,20 +198,6 @@ static inline void list_splice_init_rcu(struct list_head *list,
 	at->prev = last;
 }
 
-/**
- * list_for_each_rcu	-	iterate over an rcu-protected list
- * @pos:	the &struct list_head to use as a loop cursor.
- * @head:	the head for your list.
- *
- * This list-traversal primitive may safely run concurrently with
- * the _rcu list-mutation primitives such as list_add_rcu()
- * as long as the traversal is guarded by rcu_read_lock().
- */
-#define list_for_each_rcu(pos, head) \
-	for (pos = rcu_dereference((head)->next); \
-		prefetch(pos->next), pos != (head); \
-		pos = rcu_dereference(pos->next))
-
 #define __list_for_each_rcu(pos, head) \
 	for (pos = rcu_dereference((head)->next); \
 		pos != (head); \

include/linux/rcupdate.h

@@ -132,6 +132,26 @@ struct rcu_head {
  */
 #define rcu_read_unlock_bh() __rcu_read_unlock_bh()
 
+/**
+ * rcu_read_lock_sched - mark the beginning of a RCU-classic critical section
+ *
+ * Should be used with either
+ * - synchronize_sched()
+ * or
+ * - call_rcu_sched() and rcu_barrier_sched()
+ * on the write-side to insure proper synchronization.
+ */
+#define rcu_read_lock_sched() preempt_disable()
+
+/*
+ * rcu_read_unlock_sched - marks the end of a RCU-classic critical section
+ *
+ * See rcu_read_lock_sched for more information.
+ */
+#define rcu_read_unlock_sched() preempt_enable()
+
+
+
 /**
  * rcu_dereference - fetch an RCU-protected pointer in an
  * RCU read-side critical section.  This pointer may later

include/linux/rcupreempt.h

@@ -57,7 +57,13 @@ static inline void rcu_qsctr_inc(int cpu)
 	rdssp->sched_qs++;
 }
 #define rcu_bh_qsctr_inc(cpu)
-#define call_rcu_bh(head, rcu) call_rcu(head, rcu)
+
+/*
+ * Someone might want to pass call_rcu_bh as a function pointer.
+ * So this needs to just be a rename and not a macro function.
+ *  (no parentheses)
+ */
+#define call_rcu_bh	 	call_rcu
 
 /**
  * call_rcu_sched - Queue RCU callback for invocation after sched grace period.
@@ -111,7 +117,6 @@ extern struct rcupreempt_trace *rcupreempt_trace_cpu(int cpu);
 struct softirq_action;
 
 #ifdef CONFIG_NO_HZ
-DECLARE_PER_CPU(struct rcu_dyntick_sched, rcu_dyntick_sched);
 
 static inline void rcu_enter_nohz(void)
 {
@@ -126,8 +131,8 @@ static inline void rcu_exit_nohz(void)
 {
 	static DEFINE_RATELIMIT_STATE(rs, 10 * HZ, 1);
 
-	smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */
 	__get_cpu_var(rcu_dyntick_sched).dynticks++;
+	smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */
 	WARN_ON_RATELIMIT(!(__get_cpu_var(rcu_dyntick_sched).dynticks & 0x1),
 				&rs);
 }

kernel/rcupreempt.c

@@ -58,14 +58,6 @@
 #include <linux/cpumask.h>
 #include <linux/rcupreempt_trace.h>
 
-/*
- * Macro that prevents the compiler from reordering accesses, but does
- * absolutely -nothing- to prevent CPUs from reordering.  This is used
- * only to mediate communication between mainline code and hardware
- * interrupt and NMI handlers.
- */
-#define ACCESS_ONCE(x) (*(volatile typeof(x) *)&(x))
-
 /*
  * PREEMPT_RCU data structures.
  */

kernel/rcupreempt_trace.c

@@ -308,11 +308,16 @@ out:
 
 static int __init rcupreempt_trace_init(void)
 {
+	int ret;
+
 	mutex_init(&rcupreempt_trace_mutex);
 	rcupreempt_trace_buf = kmalloc(RCUPREEMPT_TRACE_BUF_SIZE, GFP_KERNEL);
 	if (!rcupreempt_trace_buf)
 		return 1;
-	return rcupreempt_debugfs_init();
+	ret = rcupreempt_debugfs_init();
+	if (ret)
+		kfree(rcupreempt_trace_buf);
+	return ret;
 }
 
 static void __exit rcupreempt_trace_cleanup(void)

lib/Kconfig.debug

@@ -597,6 +597,19 @@ config RCU_TORTURE_TEST_RUNNABLE
 	  Say N here if you want the RCU torture tests to start only
 	  after being manually enabled via /proc.
 
+config RCU_CPU_STALL_DETECTOR
+	bool "Check for stalled CPUs delaying RCU grace periods"
+	depends on CLASSIC_RCU
+	default n
+	help
+	  This option causes RCU to printk information on which
+	  CPUs are delaying the current grace period, but only when
+	  the grace period extends for excessive time periods.
+
+	  Say Y if you want RCU to perform such checks.
+
+	  Say N if you are unsure.
+
 config KPROBES_SANITY_TEST
 	bool "Kprobes sanity tests"
 	depends on DEBUG_KERNEL