Merge branch 'rcu/urgent' of...

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

Pull RCU updates from Paul E. McKenney:

 "This series greatly reduces the performance degradation of Tree SRCU
  on a CPU-hotplug stress test.  The effect was not subtle:  Mike Galbraith
  measured Classic SRCU at 55 seconds and Tree SRCU at more than 16 -minutes-
  for this test.  Mike collected ftrace data that showed that Classic SRCU
  was auto-expediting invocations of synchronize_srcu() that found SRCU
  completely idle.  This series therefore adds this auto-expedite capability
  to Tree SRCU, bringing the performance shortfall to less than ten seconds,
  which is a great improvement over the initial shortfall of 15 minutes."
Signed-off-by: Ingo Molnar <mingo@kernel.org>

Documentation/admin-guide/kernel-parameters.txt

@@ -3779,6 +3779,14 @@
 	spia_pedr=
 	spia_peddr=
 
+	srcutree.exp_holdoff [KNL]
+			Specifies how many nanoseconds must elapse
+			since the end of the last SRCU grace period for
+			a given srcu_struct until the next normal SRCU
+			grace period will be considered for automatic
+			expediting.  Set to zero to disable automatic
+			expediting.
+
 	stacktrace	[FTRACE]
 			Enabled the stack tracer on boot up.
 

include/linux/srcuclassic.h

@@ -98,4 +98,18 @@ void synchronize_srcu_expedited(struct srcu_struct *sp);
 void srcu_barrier(struct srcu_struct *sp);
 unsigned long srcu_batches_completed(struct srcu_struct *sp);
 
+static inline void srcutorture_get_gp_data(enum rcutorture_type test_type,
+					   struct srcu_struct *sp, int *flags,
+					   unsigned long *gpnum,
+					   unsigned long *completed)
+{
+	if (test_type != SRCU_FLAVOR)
+		return;
+	*flags = 0;
+	*completed = sp->completed;
+	*gpnum = *completed;
+	if (sp->batch_queue.head || sp->batch_check0.head || sp->batch_check0.head)
+		(*gpnum)++;
+}
+
 #endif

include/linux/srcutiny.h

@@ -78,4 +78,16 @@ static inline unsigned long srcu_batches_completed(struct srcu_struct *sp)
 	return 0;
 }
 
+static inline void srcutorture_get_gp_data(enum rcutorture_type test_type,
+					   struct srcu_struct *sp, int *flags,
+					   unsigned long *gpnum,
+					   unsigned long *completed)
+{
+	if (test_type != SRCU_FLAVOR)
+		return;
+	*flags = 0;
+	*completed = sp->srcu_gp_seq;
+	*gpnum = *completed;
+}
+
 #endif

include/linux/srcutree.h

@@ -43,10 +43,13 @@ struct srcu_data {
 	spinlock_t lock ____cacheline_internodealigned_in_smp;
 	struct rcu_segcblist srcu_cblist;	/* List of callbacks.*/
 	unsigned long srcu_gp_seq_needed;	/* Furthest future GP needed. */
+	unsigned long srcu_gp_seq_needed_exp;	/* Furthest future exp GP. */
 	bool srcu_cblist_invoking;		/* Invoking these CBs? */
 	struct delayed_work work;		/* Context for CB invoking. */
 	struct rcu_head srcu_barrier_head;	/* For srcu_barrier() use. */
 	struct srcu_node *mynode;		/* Leaf srcu_node. */
+	unsigned long grpmask;			/* Mask for leaf srcu_node */
+						/*  ->srcu_data_have_cbs[]. */
 	int cpu;
 	struct srcu_struct *sp;
 };
@@ -59,6 +62,9 @@ struct srcu_node {
 	unsigned long srcu_have_cbs[4];		/* GP seq for children */
 						/*  having CBs, but only */
 						/*  is > ->srcu_gq_seq. */
+	unsigned long srcu_data_have_cbs[4];	/* Which srcu_data structs */
+						/*  have CBs for given GP? */
+	unsigned long srcu_gp_seq_needed_exp;	/* Furthest future exp GP. */
 	struct srcu_node *srcu_parent;		/* Next up in tree. */
 	int grplo;				/* Least CPU for node. */
 	int grphi;				/* Biggest CPU for node. */
@@ -77,7 +83,8 @@ struct srcu_struct {
 	unsigned int srcu_idx;			/* Current rdr array element. */
 	unsigned long srcu_gp_seq;		/* Grace-period seq #. */
 	unsigned long srcu_gp_seq_needed;	/* Latest gp_seq needed. */
-	atomic_t srcu_exp_cnt;			/* # ongoing expedited GPs. */
+	unsigned long srcu_gp_seq_needed_exp;	/* Furthest future exp GP. */
+	unsigned long srcu_last_gp_end;		/* Last GP end timestamp (ns) */
 	struct srcu_data __percpu *sda;		/* Per-CPU srcu_data array. */
 	unsigned long srcu_barrier_seq;		/* srcu_barrier seq #. */
 	struct mutex srcu_barrier_mutex;	/* Serialize barrier ops. */
@@ -136,4 +143,8 @@ void synchronize_srcu_expedited(struct srcu_struct *sp);
 void srcu_barrier(struct srcu_struct *sp);
 unsigned long srcu_batches_completed(struct srcu_struct *sp);
 
+void srcutorture_get_gp_data(enum rcutorture_type test_type,
+			     struct srcu_struct *sp, int *flags,
+			     unsigned long *gpnum, unsigned long *completed);
+
 #endif

kernel/rcu/rcutorture.c

@@ -1360,12 +1360,14 @@ rcu_torture_stats_print(void)
 		cur_ops->stats();
 	if (rtcv_snap == rcu_torture_current_version &&
 	    rcu_torture_current != NULL) {
-		int __maybe_unused flags;
-		unsigned long __maybe_unused gpnum;
-		unsigned long __maybe_unused completed;
+		int __maybe_unused flags = 0;
+		unsigned long __maybe_unused gpnum = 0;
+		unsigned long __maybe_unused completed = 0;
 
 		rcutorture_get_gp_data(cur_ops->ttype,
 				       &flags, &gpnum, &completed);
+		srcutorture_get_gp_data(cur_ops->ttype, srcu_ctlp,
+					&flags, &gpnum, &completed);
 		wtp = READ_ONCE(writer_task);
 		pr_alert("??? Writer stall state %s(%d) g%lu c%lu f%#x ->state %#lx\n",
 			 rcu_torture_writer_state_getname(),

kernel/rcu/tree.c

@@ -704,15 +704,11 @@ void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
 	default:
 		break;
 	}
-	if (rsp != NULL) {
-		*flags = READ_ONCE(rsp->gp_flags);
-		*gpnum = READ_ONCE(rsp->gpnum);
-		*completed = READ_ONCE(rsp->completed);
+	if (rsp == NULL)
 		return;
-	}
-	*flags = 0;
-	*gpnum = 0;
-	*completed = 0;
+	*flags = READ_ONCE(rsp->gp_flags);
+	*gpnum = READ_ONCE(rsp->gpnum);
+	*completed = READ_ONCE(rsp->completed);
 }
 EXPORT_SYMBOL_GPL(rcutorture_get_gp_data);