RCU changes for v3.5

index 43b39d6..88e466b 100644
@@ -705,6 +705,7 @@ static void stack_proc(void *arg)
 	struct task_struct *from = current, *to = arg;
 
 	to->thread.saved_task = from;
+	rcu_switch_from(from);
 	switch_to(from, to, from);
 }
 

index d079290..e0f0fab 100644
@@ -30,6 +30,7 @@
  * This is only for internal list manipulation where we know
  * the prev/next entries already!
  */
+#ifndef CONFIG_DEBUG_LIST
 static inline void __list_add_rcu(struct list_head *new,
 		struct list_head *prev, struct list_head *next)
 {

@@ -38,6 +39,10 @@ static inline void __list_add_rcu(struct list_head *new,
 	rcu_assign_pointer(list_next_rcu(prev), new);
 	next->prev = new;
 }
+#else
+extern void __list_add_rcu(struct list_head *new,
+		struct list_head *prev, struct list_head *next);
+#endif
 
 /**
  * list_add_rcu - add a new entry to rcu-protected list

@@ -108,7 +113,7 @@ static inline void list_add_tail_rcu(struct list_head *new,
  */
 static inline void list_del_rcu(struct list_head *entry)
 {
-	__list_del(entry->prev, entry->next);
+	__list_del_entry(entry);
 	entry->prev = LIST_POISON2;
 }
 

@@ -228,18 +233,43 @@ static inline void list_splice_init_rcu(struct list_head *list,
 	})
 
 /**
- * list_first_entry_rcu - get the first element from a 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:
+ *
+ * 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.
+ *
+ * See list_first_or_null_rcu for an alternative.
+ */
+
+/**
+ * list_first_or_null_rcu - get the first element from a list
  * @ptr:        the list head to take the element from.
  * @type:       the type of the struct this is embedded in.
  * @member:     the name of the list_struct within the struct.
  *
- * Note, that list is expected to be not empty.
+ * Note that if the list is empty, it returns NULL.
  *
  * This primitive may safely run concurrently with the _rcu list-mutation
  * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock().
  */
-#define list_first_entry_rcu(ptr, type, member) \
-	list_entry_rcu((ptr)->next, type, member)
+#define list_first_or_null_rcu(ptr, type, member) \
+	({struct list_head *__ptr = (ptr); \
+	  struct list_head __rcu *__next = list_next_rcu(__ptr); \
+	  likely(__ptr != __next) ? container_of(__next, type, member) : NULL; \
+	})
 
 /**
  * list_for_each_entry_rcu	-	iterate over rcu list of given type

index 20fb776..26d1a47 100644
@@ -184,12 +184,14 @@ static inline int rcu_preempt_depth(void)
 /* Internal to kernel */
 extern void rcu_sched_qs(int cpu);
 extern void rcu_bh_qs(int cpu);
+extern void rcu_preempt_note_context_switch(void);
 extern void rcu_check_callbacks(int cpu, int user);
 struct notifier_block;
 extern void rcu_idle_enter(void);
 extern void rcu_idle_exit(void);
 extern void rcu_irq_enter(void);
 extern void rcu_irq_exit(void);
+extern void exit_rcu(void);
 
 /**
  * RCU_NONIDLE - Indicate idle-loop code that needs RCU readers

@@ -922,6 +924,21 @@ void __kfree_rcu(struct rcu_head *head, unsigned long offset)
 	kfree_call_rcu(head, (rcu_callback)offset);
 }
 
+/*
+ * Does the specified offset indicate that the corresponding rcu_head
+ * structure can be handled by kfree_rcu()?
+ */
+#define __is_kfree_rcu_offset(offset) ((offset) < 4096)
+
+/*
+ * Helper macro for kfree_rcu() to prevent argument-expansion eyestrain.
+ */
+#define __kfree_rcu(head, offset) \
+	do { \
+		BUILD_BUG_ON(!__is_kfree_rcu_offset(offset)); \
+		call_rcu(head, (void (*)(struct rcu_head *))(unsigned long)(offset)); \
+	} while (0)
+
 /**
  * kfree_rcu() - kfree an object after a grace period.
  * @ptr:	pointer to kfree

@@ -944,6 +961,9 @@ void __kfree_rcu(struct rcu_head *head, unsigned long offset)
  *
  * Note that the allowable offset might decrease in the future, for example,
  * to allow something like kmem_cache_free_rcu().
+ *
+ * The BUILD_BUG_ON check must not involve any function calls, hence the
+ * checks are done in macros here.
  */
 #define kfree_rcu(ptr, rcu_head)					\
 	__kfree_rcu(&((ptr)->rcu_head), offsetof(typeof(*(ptr)), rcu_head))

index e93df77..adb5e5a 100644
@@ -87,14 +87,6 @@ static inline void kfree_call_rcu(struct rcu_head *head,
 
 #ifdef CONFIG_TINY_RCU
 
-static inline void rcu_preempt_note_context_switch(void)
-{
-}
-
-static inline void exit_rcu(void)
-{
-}
-
 static inline int rcu_needs_cpu(int cpu)
 {
 	return 0;

@@ -102,8 +94,6 @@ static inline int rcu_needs_cpu(int cpu)
 
 #else /* #ifdef CONFIG_TINY_RCU */
 
-void rcu_preempt_note_context_switch(void);
-extern void exit_rcu(void);
 int rcu_preempt_needs_cpu(void);
 
 static inline int rcu_needs_cpu(int cpu)

@@ -116,7 +106,6 @@ static inline int rcu_needs_cpu(int cpu)
 static inline void rcu_note_context_switch(int cpu)
 {
 	rcu_sched_qs(cpu);
-	rcu_preempt_note_context_switch();
 }
 
 /*

index e8ee5dd..3c6083c 100644
@@ -45,18 +45,6 @@ static inline void rcu_virt_note_context_switch(int cpu)
 	rcu_note_context_switch(cpu);
 }
 
-#ifdef CONFIG_TREE_PREEMPT_RCU
-
-extern void exit_rcu(void);
-
-#else /* #ifdef CONFIG_TREE_PREEMPT_RCU */
-
-static inline void exit_rcu(void)
-{
-}
-
-#endif /* #else #ifdef CONFIG_TREE_PREEMPT_RCU */
-
 extern void synchronize_rcu_bh(void);
 extern void synchronize_sched_expedited(void);
 extern void synchronize_rcu_expedited(void);

@@ -98,13 +86,6 @@ extern void rcu_force_quiescent_state(void);
 extern void rcu_bh_force_quiescent_state(void);
 extern void rcu_sched_force_quiescent_state(void);
 
-/* A context switch is a grace period for RCU-sched and RCU-bh. */
-static inline int rcu_blocking_is_gp(void)
-{
-	might_sleep();  /* Check for RCU read-side critical section. */
-	return num_online_cpus() == 1;
-}
-
 extern void rcu_scheduler_starting(void);
 extern int rcu_scheduler_active __read_mostly;
 

index 81a173c..8f3fd94 100644
@@ -1905,12 +1905,22 @@ static inline void rcu_copy_process(struct task_struct *p)
 	INIT_LIST_HEAD(&p->rcu_node_entry);
 }
 
+static inline void rcu_switch_from(struct task_struct *prev)
+{
+	if (prev->rcu_read_lock_nesting != 0)
+		rcu_preempt_note_context_switch();
+}
+
 #else
 
 static inline void rcu_copy_process(struct task_struct *p)
 {
 }
 
+static inline void rcu_switch_from(struct task_struct *prev)
+{
+}
+
 #endif
 
 #ifdef CONFIG_SMP

77 lines not on this page · raw message

index 3370997..1480900 100644
@@ -292,6 +292,8 @@ TRACE_EVENT(rcu_dyntick,
  *	"More callbacks": Still more callbacks, try again to clear them out.
  *	"Callbacks drained": All callbacks processed, off to dyntick idle!
  *	"Timer": Timer fired to cause CPU to continue processing callbacks.
+ *	"Demigrate": Timer fired on wrong CPU, woke up correct CPU.
+ *	"Cleanup after idle": Idle exited, timer canceled.
  */
 TRACE_EVENT(rcu_prep_idle,
 

index a86f174..95cba41 100644
@@ -51,6 +51,34 @@
 
 #include "rcu.h"
 
+#ifdef CONFIG_PREEMPT_RCU
+
+/*
+ * Check for a task exiting while in a preemptible-RCU read-side
+ * critical section, clean up if so.  No need to issue warnings,
+ * as debug_check_no_locks_held() already does this if lockdep
+ * is enabled.
+ */
+void exit_rcu(void)
+{
+	struct task_struct *t = current;
+
+	if (likely(list_empty(&current->rcu_node_entry)))
+		return;
+	t->rcu_read_lock_nesting = 1;
+	barrier();
+	t->rcu_read_unlock_special = RCU_READ_UNLOCK_BLOCKED;
+	__rcu_read_unlock();
+}
+
+#else /* #ifdef CONFIG_PREEMPT_RCU */
+
+void exit_rcu(void)
+{
+}
+
+#endif /* #else #ifdef CONFIG_PREEMPT_RCU */
+
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 static struct lock_class_key rcu_lock_key;
 struct lockdep_map rcu_lock_map =

index 22ecea0..fc31a2d 100644
@@ -851,22 +851,6 @@ int rcu_preempt_needs_cpu(void)
 	return rcu_preempt_ctrlblk.rcb.rcucblist != NULL;
 }
 
-/*
- * Check for a task exiting while in a preemptible -RCU read-side
- * critical section, clean up if so.  No need to issue warnings,
- * as debug_check_no_locks_held() already does this if lockdep
- * is enabled.
- */
-void exit_rcu(void)
-{
-	struct task_struct *t = current;
-
-	if (t->rcu_read_lock_nesting == 0)
-		return;
-	t->rcu_read_lock_nesting = 1;
-	__rcu_read_unlock();
-}
-
 #else /* #ifdef CONFIG_TINY_PREEMPT_RCU */
 
 #ifdef CONFIG_RCU_TRACE

462 lines not on this page · raw message

458 lines not on this page · raw message

index cdd1be0..7f5d138 100644
@@ -29,18 +29,14 @@
 #include <linux/seqlock.h>
 
 /*
- * Define shape of hierarchy based on NR_CPUS and CONFIG_RCU_FANOUT.
+ * Define shape of hierarchy based on NR_CPUS, CONFIG_RCU_FANOUT, and
+ * CONFIG_RCU_FANOUT_LEAF.
  * In theory, it should be possible to add more levels straightforwardly.
  * In practice, this did work well going from three levels to four.
  * Of course, your mileage may vary.
  */
 #define MAX_RCU_LVLS 4
-#if CONFIG_RCU_FANOUT > 16
-#define RCU_FANOUT_LEAF       16
-#else /* #if CONFIG_RCU_FANOUT > 16 */
-#define RCU_FANOUT_LEAF       (CONFIG_RCU_FANOUT)
-#endif /* #else #if CONFIG_RCU_FANOUT > 16 */
-#define RCU_FANOUT_1	      (RCU_FANOUT_LEAF)
+#define RCU_FANOUT_1	      (CONFIG_RCU_FANOUT_LEAF)
 #define RCU_FANOUT_2	      (RCU_FANOUT_1 * CONFIG_RCU_FANOUT)
 #define RCU_FANOUT_3	      (RCU_FANOUT_2 * CONFIG_RCU_FANOUT)
 #define RCU_FANOUT_4	      (RCU_FANOUT_3 * CONFIG_RCU_FANOUT)

@@ -371,6 +367,17 @@ struct rcu_state {
 
 	raw_spinlock_t onofflock;		/* exclude on/offline and */
 						/*  starting new GP. */
+	struct rcu_head *orphan_nxtlist;	/* Orphaned callbacks that */
+						/*  need a grace period. */
+	struct rcu_head **orphan_nxttail;	/* Tail of above. */
+	struct rcu_head *orphan_donelist;	/* Orphaned callbacks that */
+						/*  are ready to invoke. */
+	struct rcu_head **orphan_donetail;	/* Tail of above. */
+	long qlen_lazy;				/* Number of lazy callbacks. */
+	long qlen;				/* Total number of callbacks. */
+	struct task_struct *rcu_barrier_in_progress;
+						/* Task doing rcu_barrier(), */
+						/*  or NULL if no barrier. */
 	raw_spinlock_t fqslock;			/* Only one task forcing */
 						/*  quiescent states. */
 	unsigned long jiffies_force_qs;		/* Time at which to invoke */

@@ -423,7 +430,6 @@ DECLARE_PER_CPU(char, rcu_cpu_has_work);
 /* Forward declarations for rcutree_plugin.h */
 static void rcu_bootup_announce(void);
 long rcu_batches_completed(void);
-static void rcu_preempt_note_context_switch(int cpu);
 static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp);
 #ifdef CONFIG_HOTPLUG_CPU
 static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp,

@@ -471,6 +477,7 @@ static void __cpuinit rcu_prepare_kthreads(int cpu);
 static void rcu_prepare_for_idle_init(int cpu);
 static void rcu_cleanup_after_idle(int cpu);
 static void rcu_prepare_for_idle(int cpu);
+static void rcu_idle_count_callbacks_posted(void);
 static void print_cpu_stall_info_begin(void);
 static void print_cpu_stall_info(struct rcu_state *rsp, int cpu);
 static void print_cpu_stall_info_end(void);

258 lines not on this page · raw message

index ed459ed..d4bc16d 100644
@@ -271,13 +271,13 @@ static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp)
 
 	gpnum = rsp->gpnum;
 	seq_printf(m, "c=%lu g=%lu s=%d jfq=%ld j=%x "
-		      "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu\n",
+		      "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu oqlen=%ld/%ld\n",
 		   rsp->completed, gpnum, rsp->fqs_state,
 		   (long)(rsp->jiffies_force_qs - jiffies),
 		   (int)(jiffies & 0xffff),
 		   rsp->n_force_qs, rsp->n_force_qs_ngp,
 		   rsp->n_force_qs - rsp->n_force_qs_ngp,
-		   rsp->n_force_qs_lh);
+		   rsp->n_force_qs_lh, rsp->qlen_lazy, rsp->qlen);
 	for (rnp = &rsp->node[0]; rnp - &rsp->node[0] < NUM_RCU_NODES; rnp++) {
 		if (rnp->level != level) {
 			seq_puts(m, "\n");

index 0533a68..8bedcc4 100644
@@ -2083,6 +2083,7 @@ context_switch(struct rq *rq, struct task_struct *prev,
 #endif
 
 	/* Here we just switch the register state and the stack. */
+	rcu_switch_from(prev);
 	switch_to(prev, next, prev);
 
 	barrier();

642 lines not on this page · raw message

index a297ffc..837c552 100644
@@ -861,7 +861,13 @@ EXPORT_SYMBOL(mod_timer);
  *
  * mod_timer_pinned() is a way to update the expire field of an
  * active timer (if the timer is inactive it will be activated)
- * and not allow the timer to be migrated to a different CPU.
+ * and to ensure that the timer is scheduled on the current CPU.
+ *
+ * Note that this does not prevent the timer from being migrated
+ * when the current CPU goes offline.  If this is a problem for
+ * you, use CPU-hotplug notifiers to handle it correctly, for
+ * example, cancelling the timer when the corresponding CPU goes
+ * offline.
  *
  * mod_timer_pinned(timer, expires) is equivalent to:
  *

index 982b850..3810b48 100644
@@ -10,6 +10,7 @@
 #include <linux/list.h>
 #include <linux/bug.h>
 #include <linux/kernel.h>
+#include <linux/rculist.h>
 
 /*
  * Insert a new entry between two known consecutive entries.

@@ -75,3 +76,24 @@ void list_del(struct list_head *entry)
 	entry->prev = LIST_POISON2;
 }
 EXPORT_SYMBOL(list_del);
+
+/*
+ * RCU variants.
+ */
+void __list_add_rcu(struct list_head *new,
+		    struct list_head *prev, struct list_head *next)
+{
+	WARN(next->prev != prev,
+		"list_add_rcu corruption. next->prev should be "
+		"prev (%p), but was %p. (next=%p).\n",
+		prev, next->prev, next);
+	WARN(prev->next != next,
+		"list_add_rcu corruption. prev->next should be "
+		"next (%p), but was %p. (prev=%p).\n",
+		next, prev->next, prev);
+	new->next = next;
+	new->prev = prev;
+	rcu_assign_pointer(list_next_rcu(prev), new);
+	next->prev = new;
+}
+EXPORT_SYMBOL(__list_add_rcu);