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

Pull RCU changes from Ingo Molnar:
 "This is the v3.5 RCU tree from Paul E.  McKenney:

 1) A set of improvements and fixes to the RCU_FAST_NO_HZ feature (with
    more on the way for 3.6).  Posted to LKML:
       https://lkml.org/lkml/2012/4/23/324 (commits 1-3 and 5),
       https://lkml.org/lkml/2012/4/16/611 (commit 4),
       https://lkml.org/lkml/2012/4/30/390 (commit 6), and
       https://lkml.org/lkml/2012/5/4/410 (commit 7, combined with
       the other commits for the convenience of the tester).

 2) Changes to make rcu_barrier() avoid disrupting execution of CPUs
    that have no RCU callbacks.  Posted to LKML:
       https://lkml.org/lkml/2012/4/23/322.

 3) A couple of commits that improve the efficiency of the interaction
    between preemptible RCU and the scheduler, these two being all that
    survived an abortive attempt to allow preemptible RCU's
    __rcu_read_lock() to be inlined.  The full set was posted to LKML at
    https://lkml.org/lkml/2012/4/14/143, and the first and third patches
    of that set remain.

 4) Lai Jiangshan's algorithmic implementation of SRCU, which includes
    call_srcu() and srcu_barrier().  A major feature of this new
    implementation is that synchronize_srcu() no longer disturbs the
    execution of other CPUs.  This work is based on earlier
    implementations by Peter Zijlstra and Paul E.  McKenney.  Posted to
    LKML: https://lkml.org/lkml/2012/2/22/82.

 5) A number of miscellaneous bug fixes and improvements which were
    posted to LKML at: https://lkml.org/lkml/2012/4/23/353 with
    subsequent updates posted to LKML."

* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (32 commits)
  rcu: Make rcu_barrier() less disruptive
  rcu: Explicitly initialize RCU_FAST_NO_HZ per-CPU variables
  rcu: Make RCU_FAST_NO_HZ handle timer migration
  rcu: Update RCU maintainership
  rcu: Make exit_rcu() more precise and consolidate
  rcu: Move PREEMPT_RCU preemption to switch_to() invocation
  rcu: Ensure that RCU_FAST_NO_HZ timers expire on correct CPU
  rcu: Add rcutorture test for call_srcu()
  rcu: Implement per-domain single-threaded call_srcu() state machine
  rcu: Use single value to handle expedited SRCU grace periods
  rcu: Improve srcu_readers_active_idx()'s cache locality
  rcu: Remove unused srcu_barrier()
  rcu: Implement a variant of Peter's SRCU algorithm
  rcu: Improve SRCU's wait_idx() comments
  rcu: Flip ->completed only once per SRCU grace period
  rcu: Increment upper bit only for srcu_read_lock()
  rcu: Remove fast check path from __synchronize_srcu()
  rcu: Direct algorithmic SRCU implementation
  rcu: Introduce rcutorture testing for rcu_barrier()
  timer: Fix mod_timer_pinned() header comment
  ...

1 files changed, 99 insertions, 55 deletions

diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index c023464816b..2411000d986 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -153,7 +153,7 @@ static void rcu_preempt_qs(int cpu)
  *
  * Caller must disable preemption.
  */
-static void rcu_preempt_note_context_switch(int cpu)
+void rcu_preempt_note_context_switch(void)
 {
 	struct task_struct *t = current;
 	unsigned long flags;
@@ -164,7 +164,7 @@ static void rcu_preempt_note_context_switch(int cpu)
 	    (t->rcu_read_unlock_special & RCU_READ_UNLOCK_BLOCKED) == 0) {
 
 		/* Possibly blocking in an RCU read-side critical section. */
-		rdp = per_cpu_ptr(rcu_preempt_state.rda, cpu);
+		rdp = __this_cpu_ptr(rcu_preempt_state.rda);
 		rnp = rdp->mynode;
 		raw_spin_lock_irqsave(&rnp->lock, flags);
 		t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BLOCKED;
@@ -228,7 +228,7 @@ static void rcu_preempt_note_context_switch(int cpu)
 	 * means that we continue to block the current grace period.
 	 */
 	local_irq_save(flags);
-	rcu_preempt_qs(cpu);
+	rcu_preempt_qs(smp_processor_id());
 	local_irq_restore(flags);
 }
 
@@ -969,22 +969,6 @@ static void __init __rcu_init_preempt(void)
 	rcu_init_one(&rcu_preempt_state, &rcu_preempt_data);
 }
 
-/*
- * 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_TREE_PREEMPT_RCU */
 
 static struct rcu_state *rcu_state = &rcu_sched_state;
@@ -1018,14 +1002,6 @@ void rcu_force_quiescent_state(void)
 EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
 
 /*
- * Because preemptible RCU does not exist, we never have to check for
- * CPUs being in quiescent states.
- */
-static void rcu_preempt_note_context_switch(int cpu)
-{
-}
-
-/*
  * Because preemptible RCU does not exist, there are never any preempted
  * RCU readers.
  */
@@ -1938,6 +1914,14 @@ static void rcu_prepare_for_idle(int cpu)
 {
 }
 
+/*
+ * Don't bother keeping a running count of the number of RCU callbacks
+ * posted because CONFIG_RCU_FAST_NO_HZ=n.
+ */
+static void rcu_idle_count_callbacks_posted(void)
+{
+}
+
 #else /* #if !defined(CONFIG_RCU_FAST_NO_HZ) */
 
 /*
@@ -1978,11 +1962,20 @@ static void rcu_prepare_for_idle(int cpu)
 #define RCU_IDLE_GP_DELAY 6		/* Roughly one grace period. */
 #define RCU_IDLE_LAZY_GP_DELAY (6 * HZ)	/* Roughly six seconds. */
 
+/* Loop counter for rcu_prepare_for_idle(). */
 static DEFINE_PER_CPU(int, rcu_dyntick_drain);
+/* If rcu_dyntick_holdoff==jiffies, don't try to enter dyntick-idle mode. */
 static DEFINE_PER_CPU(unsigned long, rcu_dyntick_holdoff);
-static DEFINE_PER_CPU(struct hrtimer, rcu_idle_gp_timer);
-static ktime_t rcu_idle_gp_wait;	/* If some non-lazy callbacks. */
-static ktime_t rcu_idle_lazy_gp_wait;	/* If only lazy callbacks. */
+/* Timer to awaken the CPU if it enters dyntick-idle mode with callbacks. */
+static DEFINE_PER_CPU(struct timer_list, rcu_idle_gp_timer);
+/* Scheduled expiry time for rcu_idle_gp_timer to allow reposting. */
+static DEFINE_PER_CPU(unsigned long, rcu_idle_gp_timer_expires);
+/* Enable special processing on first attempt to enter dyntick-idle mode. */
+static DEFINE_PER_CPU(bool, rcu_idle_first_pass);
+/* Running count of non-lazy callbacks posted, never decremented. */
+static DEFINE_PER_CPU(unsigned long, rcu_nonlazy_posted);
+/* Snapshot of rcu_nonlazy_posted to detect meaningful exits from idle. */
+static DEFINE_PER_CPU(unsigned long, rcu_nonlazy_posted_snap);
 
 /*
  * Allow the CPU to enter dyntick-idle mode if either: (1) There are no
@@ -1995,6 +1988,8 @@ static ktime_t rcu_idle_lazy_gp_wait;	/* If only lazy callbacks. */
  */
 int rcu_needs_cpu(int cpu)
 {
+	/* Flag a new idle sojourn to the idle-entry state machine. */
+	per_cpu(rcu_idle_first_pass, cpu) = 1;
 	/* If no callbacks, RCU doesn't need the CPU. */
 	if (!rcu_cpu_has_callbacks(cpu))
 		return 0;
@@ -2045,16 +2040,34 @@ static bool rcu_cpu_has_nonlazy_callbacks(int cpu)
 }
 
 /*
+ * Handler for smp_call_function_single().  The only point of this
+ * handler is to wake the CPU up, so the handler does only tracing.
+ */
+void rcu_idle_demigrate(void *unused)
+{
+	trace_rcu_prep_idle("Demigrate");
+}
+
+/*
  * Timer handler used to force CPU to start pushing its remaining RCU
  * callbacks in the case where it entered dyntick-idle mode with callbacks
  * pending.  The hander doesn't really need to do anything because the
  * real work is done upon re-entry to idle, or by the next scheduling-clock
  * interrupt should idle not be re-entered.
+ *
+ * One special case: the timer gets migrated without awakening the CPU
+ * on which the timer was scheduled on.  In this case, we must wake up
+ * that CPU.  We do so with smp_call_function_single().
  */
-static enum hrtimer_restart rcu_idle_gp_timer_func(struct hrtimer *hrtp)
+static void rcu_idle_gp_timer_func(unsigned long cpu_in)
 {
+	int cpu = (int)cpu_in;
+
 	trace_rcu_prep_idle("Timer");
-	return HRTIMER_NORESTART;
+	if (cpu != smp_processor_id())
+		smp_call_function_single(cpu, rcu_idle_demigrate, NULL, 0);
+	else
+		WARN_ON_ONCE(1); /* Getting here can hang the system... */
 }
 
 /*
@@ -2062,19 +2075,11 @@ static enum hrtimer_restart rcu_idle_gp_timer_func(struct hrtimer *hrtp)
  */
 static void rcu_prepare_for_idle_init(int cpu)
 {
-	static int firsttime = 1;
-	struct hrtimer *hrtp = &per_cpu(rcu_idle_gp_timer, cpu);
-
-	hrtimer_init(hrtp, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	hrtp->function = rcu_idle_gp_timer_func;
-	if (firsttime) {
-		unsigned int upj = jiffies_to_usecs(RCU_IDLE_GP_DELAY);
-
-		rcu_idle_gp_wait = ns_to_ktime(upj * (u64)1000);
-		upj = jiffies_to_usecs(RCU_IDLE_LAZY_GP_DELAY);
-		rcu_idle_lazy_gp_wait = ns_to_ktime(upj * (u64)1000);
-		firsttime = 0;
-	}
+	per_cpu(rcu_dyntick_holdoff, cpu) = jiffies - 1;
+	setup_timer(&per_cpu(rcu_idle_gp_timer, cpu),
+		    rcu_idle_gp_timer_func, cpu);
+	per_cpu(rcu_idle_gp_timer_expires, cpu) = jiffies - 1;
+	per_cpu(rcu_idle_first_pass, cpu) = 1;
 }
 
 /*
@@ -2084,7 +2089,8 @@ static void rcu_prepare_for_idle_init(int cpu)
  */
 static void rcu_cleanup_after_idle(int cpu)
 {
-	hrtimer_cancel(&per_cpu(rcu_idle_gp_timer, cpu));
+	del_timer(&per_cpu(rcu_idle_gp_timer, cpu));
+	trace_rcu_prep_idle("Cleanup after idle");
 }
 
 /*
@@ -2108,6 +2114,29 @@ static void rcu_cleanup_after_idle(int cpu)
  */
 static void rcu_prepare_for_idle(int cpu)
 {
+	struct timer_list *tp;
+
+	/*
+	 * If this is an idle re-entry, for example, due to use of
+	 * RCU_NONIDLE() or the new idle-loop tracing API within the idle
+	 * loop, then don't take any state-machine actions, unless the
+	 * momentary exit from idle queued additional non-lazy callbacks.
+	 * Instead, repost the rcu_idle_gp_timer if this CPU has callbacks
+	 * pending.
+	 */
+	if (!per_cpu(rcu_idle_first_pass, cpu) &&
+	    (per_cpu(rcu_nonlazy_posted, cpu) ==
+	     per_cpu(rcu_nonlazy_posted_snap, cpu))) {
+		if (rcu_cpu_has_callbacks(cpu)) {
+			tp = &per_cpu(rcu_idle_gp_timer, cpu);
+			mod_timer_pinned(tp, per_cpu(rcu_idle_gp_timer_expires, cpu));
+		}
+		return;
+	}
+	per_cpu(rcu_idle_first_pass, cpu) = 0;
+	per_cpu(rcu_nonlazy_posted_snap, cpu) =
+		per_cpu(rcu_nonlazy_posted, cpu) - 1;
+
 	/*
 	 * If there are no callbacks on this CPU, enter dyntick-idle mode.
 	 * Also reset state to avoid prejudicing later attempts.
@@ -2140,11 +2169,15 @@ static void rcu_prepare_for_idle(int cpu)
 		per_cpu(rcu_dyntick_drain, cpu) = 0;
 		per_cpu(rcu_dyntick_holdoff, cpu) = jiffies;
 		if (rcu_cpu_has_nonlazy_callbacks(cpu))
-			hrtimer_start(&per_cpu(rcu_idle_gp_timer, cpu),
-				      rcu_idle_gp_wait, HRTIMER_MODE_REL);
+			per_cpu(rcu_idle_gp_timer_expires, cpu) =
+					   jiffies + RCU_IDLE_GP_DELAY;
 		else
-			hrtimer_start(&per_cpu(rcu_idle_gp_timer, cpu),
-				      rcu_idle_lazy_gp_wait, HRTIMER_MODE_REL);
+			per_cpu(rcu_idle_gp_timer_expires, cpu) =
+					   jiffies + RCU_IDLE_LAZY_GP_DELAY;
+		tp = &per_cpu(rcu_idle_gp_timer, cpu);
+		mod_timer_pinned(tp, per_cpu(rcu_idle_gp_timer_expires, cpu));
+		per_cpu(rcu_nonlazy_posted_snap, cpu) =
+			per_cpu(rcu_nonlazy_posted, cpu);
 		return; /* Nothing more to do immediately. */
 	} else if (--per_cpu(rcu_dyntick_drain, cpu) <= 0) {
 		/* We have hit the limit, so time to give up. */
@@ -2184,6 +2217,19 @@ static void rcu_prepare_for_idle(int cpu)
 		trace_rcu_prep_idle("Callbacks drained");
 }
 
+/*
+ * Keep a running count of the number of non-lazy callbacks posted
+ * on this CPU.  This running counter (which is never decremented) allows
+ * rcu_prepare_for_idle() to detect when something out of the idle loop
+ * posts a callback, even if an equal number of callbacks are invoked.
+ * Of course, callbacks should only be posted from within a trace event
+ * designed to be called from idle or from within RCU_NONIDLE().
+ */
+static void rcu_idle_count_callbacks_posted(void)
+{
+	__this_cpu_add(rcu_nonlazy_posted, 1);
+}
+
 #endif /* #else #if !defined(CONFIG_RCU_FAST_NO_HZ) */
 
 #ifdef CONFIG_RCU_CPU_STALL_INFO
@@ -2192,14 +2238,12 @@ static void rcu_prepare_for_idle(int cpu)
 
 static void print_cpu_stall_fast_no_hz(char *cp, int cpu)
 {
-	struct hrtimer *hrtp = &per_cpu(rcu_idle_gp_timer, cpu);
+	struct timer_list *tltp = &per_cpu(rcu_idle_gp_timer, cpu);
 
-	sprintf(cp, "drain=%d %c timer=%lld",
+	sprintf(cp, "drain=%d %c timer=%lu",
 		per_cpu(rcu_dyntick_drain, cpu),
 		per_cpu(rcu_dyntick_holdoff, cpu) == jiffies ? 'H' : '.',
-		hrtimer_active(hrtp)
-			? ktime_to_us(hrtimer_get_remaining(hrtp))
-			: -1);
+		timer_pending(tltp) ? tltp->expires - jiffies : -1);
 }
 
 #else /* #ifdef CONFIG_RCU_FAST_NO_HZ */