[PATCH tip/core/rcu 12/12] rcu: Discard separate per-CPU callback counts

["Paul E. McKenney" <paulmck@linux.ibm.com>]

Back when there were multiple flavors of RCU, it was necessary to
separately count lazy and non-lazy callbacks for each CPU.  These counts
were used in CONFIG_RCU_FAST_NO_HZ kernels to determine how long a newly
idle CPU should be allowed to sleep before handling its RCU callbacks.
But now that there is only one flavor, the callback counts for a given
CPU's sole rcu_data structure are the counts for that CPU.

This commit therefore removes the rcu_data structure's ->nonlazy_posted
and ->nonlazy_posted_snap fields, the rcu_idle_count_callbacks_posted()
and rcu_cpu_has_callbacks() functions, repurposes the rcu_data structure's
->all_lazy field to record the laziness state at the beginning of the
latest idle sojourn, and modifies CONFIG_RCU_FAST_NO_HZ RCU CPU stall
warnings accordingly.

Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
---
 Documentation/RCU/stallwarn.txt | 15 +++++-----
 kernel/rcu/tree.c               | 25 -----------------
 kernel/rcu/tree.h               |  6 +---
 kernel/rcu/tree_plugin.h        | 50 ++++++++-------------------------
 4 files changed, 21 insertions(+), 75 deletions(-)

diff --git a/Documentation/RCU/stallwarn.txt b/Documentation/RCU/stallwarn.txt
index 073dbc12d1ea..1ab70c37921f 100644
--- a/Documentation/RCU/stallwarn.txt
+++ b/Documentation/RCU/stallwarn.txt
@@ -219,17 +219,18 @@ an estimate of the total number of RCU callbacks queued across all CPUs
 In kernels with CONFIG_RCU_FAST_NO_HZ, more information is printed
 for each CPU:
 
-	0: (64628 ticks this GP) idle=dd5/3fffffffffffffff/0 softirq=82/543 last_accelerate: a345/d342 nonlazy_posted: 25 .D
+	0: (64628 ticks this GP) idle=dd5/3fffffffffffffff/0 softirq=82/543 last_accelerate: a345/d342 Nonlazy posted: ..D
 
 The "last_accelerate:" prints the low-order 16 bits (in hex) of the
 jiffies counter when this CPU last invoked rcu_try_advance_all_cbs()
 from rcu_needs_cpu() or last invoked rcu_accelerate_cbs() from
-rcu_prepare_for_idle().  The "nonlazy_posted:" prints the number
-of non-lazy callbacks posted since the last call to rcu_needs_cpu().
-Finally, an "L" indicates that there are currently no non-lazy callbacks
-("." is printed otherwise, as shown above) and "D" indicates that
-dyntick-idle processing is enabled ("." is printed otherwise, for example,
-if disabled via the "nohz=" kernel boot parameter).
+rcu_prepare_for_idle().  The "Nonlazy posted:" indicates lazy-callback
+status, so that an "l" indicates that all callbacks were lazy at the start
+of the last idle period and an "L" indicates that there are currently
+no non-lazy callbacks (in both cases, "." is printed otherwise, as
+shown above) and "D" indicates that dyntick-idle processing is enabled
+("." is printed otherwise, for example, if disabled via the "nohz="
+kernel boot parameter).
 
 If the grace period ends just as the stall warning starts printing,
 there will be a spurious stall-warning message, which will include
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index e2bd42b2b563..e53a586b397b 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2878,9 +2878,6 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func, int cpu, bool lazy)
 			rcu_segcblist_init(&rdp->cblist);
 	}
 	rcu_segcblist_enqueue(&rdp->cblist, head, lazy);
-	if (!lazy)
-		rcu_idle_count_callbacks_posted();
-
 	if (__is_kfree_rcu_offset((unsigned long)func))
 		trace_rcu_kfree_callback(rcu_state.name, head,
 					 (unsigned long)func,
@@ -3110,28 +3107,6 @@ static int rcu_pending(void)
 	return 0;
 }
 
-/*
- * Return true if the specified CPU has any callback.  If all_lazy is
- * non-NULL, store an indication of whether all callbacks are lazy.
- * (If there are no callbacks, all of them are deemed to be lazy.)
- */
-static bool rcu_cpu_has_callbacks(bool *all_lazy)
-{
-	bool al = true;
-	bool hc = false;
-	struct rcu_data *rdp;
-
-	rdp = this_cpu_ptr(&rcu_data);
-	if (!rcu_segcblist_empty(&rdp->cblist)) {
-		hc = true;
-		if (rcu_segcblist_n_nonlazy_cbs(&rdp->cblist))
-			al = false;
-	}
-	if (all_lazy)
-		*all_lazy = al;
-	return hc;
-}
-
 /*
  * Helper function for rcu_barrier() tracing.  If tracing is disabled,
  * the compiler is expected to optimize this away.
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 50bb41cdc5fb..20feecbb0ab6 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -193,10 +193,7 @@ struct rcu_data {
 	bool rcu_need_heavy_qs;		/* GP old, so heavy quiescent state! */
 	bool rcu_urgent_qs;		/* GP old need light quiescent state. */
 #ifdef CONFIG_RCU_FAST_NO_HZ
-	bool all_lazy;			/* Are all CPU's CBs lazy? */
-	unsigned long nonlazy_posted;	/* # times non-lazy CB posted to CPU. */
-	unsigned long nonlazy_posted_snap;
-					/* Nonlazy_posted snapshot. */
+	bool all_lazy;			/* All CPU's CBs lazy at idle start? */
 	unsigned long last_accelerate;	/* Last jiffy CBs were accelerated. */
 	unsigned long last_advance_all;	/* Last jiffy CBs were all advanced. */
 	int tick_nohz_enabled_snap;	/* Previously seen value from sysfs. */
@@ -430,7 +427,6 @@ static void __init rcu_spawn_boost_kthreads(void);
 static void rcu_prepare_kthreads(int cpu);
 static void rcu_cleanup_after_idle(void);
 static void rcu_prepare_for_idle(void);
-static void rcu_idle_count_callbacks_posted(void);
 static bool rcu_preempt_has_tasks(struct rcu_node *rnp);
 static bool rcu_preempt_need_deferred_qs(struct task_struct *t);
 static void rcu_preempt_deferred_qs(struct task_struct *t);
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 43f3f2ee9d63..abd238c70900 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -1474,7 +1474,7 @@ static void rcu_prepare_kthreads(int cpu)
 int rcu_needs_cpu(u64 basemono, u64 *nextevt)
 {
 	*nextevt = KTIME_MAX;
-	return rcu_cpu_has_callbacks(NULL);
+	return !rcu_segcblist_empty(&this_cpu_ptr(&rcu_data)->cblist);
 }
 
 /*
@@ -1493,14 +1493,6 @@ static void rcu_prepare_for_idle(void)
 {
 }
 
-/*
- * 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) */
 
 /*
@@ -1583,11 +1575,8 @@ int rcu_needs_cpu(u64 basemono, u64 *nextevt)
 
 	lockdep_assert_irqs_disabled();
 
-	/* Snapshot to detect later posting of non-lazy callback. */
-	rdp->nonlazy_posted_snap = rdp->nonlazy_posted;
-
 	/* If no callbacks, RCU doesn't need the CPU. */
-	if (!rcu_cpu_has_callbacks(&rdp->all_lazy)) {
+	if (rcu_segcblist_empty(&rdp->cblist)) {
 		*nextevt = KTIME_MAX;
 		return 0;
 	}
@@ -1601,11 +1590,12 @@ int rcu_needs_cpu(u64 basemono, u64 *nextevt)
 	rdp->last_accelerate = jiffies;
 
 	/* Request timer delay depending on laziness, and round. */
-	if (!rdp->all_lazy) {
+	rdp->all_lazy = !rcu_segcblist_n_nonlazy_cbs(&rdp->cblist);
+	if (rdp->all_lazy) {
+		dj = round_jiffies(rcu_idle_lazy_gp_delay + jiffies) - jiffies;
+	} else {
 		dj = round_up(rcu_idle_gp_delay + jiffies,
 			       rcu_idle_gp_delay) - jiffies;
-	} else {
-		dj = round_jiffies(rcu_idle_lazy_gp_delay + jiffies) - jiffies;
 	}
 	*nextevt = basemono + dj * TICK_NSEC;
 	return 0;
@@ -1635,7 +1625,7 @@ static void rcu_prepare_for_idle(void)
 	/* Handle nohz enablement switches conservatively. */
 	tne = READ_ONCE(tick_nohz_active);
 	if (tne != rdp->tick_nohz_enabled_snap) {
-		if (rcu_cpu_has_callbacks(NULL))
+		if (!rcu_segcblist_empty(&rdp->cblist))
 			invoke_rcu_core(); /* force nohz to see update. */
 		rdp->tick_nohz_enabled_snap = tne;
 		return;
@@ -1648,10 +1638,8 @@ static void rcu_prepare_for_idle(void)
 	 * callbacks, invoke RCU core for the side-effect of recalculating
 	 * idle duration on re-entry to idle.
 	 */
-	if (rdp->all_lazy &&
-	    rdp->nonlazy_posted != rdp->nonlazy_posted_snap) {
+	if (rdp->all_lazy && rcu_segcblist_n_nonlazy_cbs(&rdp->cblist)) {
 		rdp->all_lazy = false;
-		rdp->nonlazy_posted_snap = rdp->nonlazy_posted;
 		invoke_rcu_core();
 		return;
 	}
@@ -1687,19 +1675,6 @@ static void rcu_cleanup_after_idle(void)
 		invoke_rcu_core();
 }
 
-/*
- * 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_data.nonlazy_posted, 1);
-}
-
 #endif /* #else #if !defined(CONFIG_RCU_FAST_NO_HZ) */
 
 #ifdef CONFIG_RCU_FAST_NO_HZ
@@ -1707,13 +1682,12 @@ static void rcu_idle_count_callbacks_posted(void)
 static void print_cpu_stall_fast_no_hz(char *cp, int cpu)
 {
 	struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
-	unsigned long nlpd = rdp->nonlazy_posted - rdp->nonlazy_posted_snap;
 
-	sprintf(cp, "last_accelerate: %04lx/%04lx, nonlazy_posted: %ld, %c%c",
+	sprintf(cp, "last_accelerate: %04lx/%04lx, Nonlazy posted: %c%c%c",
 		rdp->last_accelerate & 0xffff, jiffies & 0xffff,
-		ulong2long(nlpd),
-		rdp->all_lazy ? 'L' : '.',
-		rdp->tick_nohz_enabled_snap ? '.' : 'D');
+		".l"[rdp->all_lazy],
+		".L"[!rcu_segcblist_n_nonlazy_cbs(&rdp->cblist)],
+		".D"[!rdp->tick_nohz_enabled_snap]);
 }
 
 #else /* #ifdef CONFIG_RCU_FAST_NO_HZ */
-- 
2.17.1