torture: Maintain torture-specific set of CPUs-online books

The TREE01 rcutorture scenario intentionally creates confusion as to the
number of available CPUs by specifying the "maxcpus=8 nr_cpus=43" kernel
boot parameters.  This can disable rcutorture's load shedding, which
currently uses num_online_cpus(), which would count the extra 35 CPUs.
However, the rcutorture guest OS will be provisioned with only 8 CPUs,
which means that rcutorture will present full load even when all but one
of the original 8 CPUs are offline.  This can result in spurious errors
due to extreme overloading of that single remaining CPU.

This commit therefore keeps a separate set of books on the number of
usable online CPUs, so that torture_num_online_cpus() is used for load
shedding instead of num_online_cpus().  Note that initial sizing must
use num_online_cpus() because torture_num_online_cpus() will return
NR_CPUS until shortly after torture_onoff_init() is invoked.

Reported-by: Frederic Weisbecker <frederic@kernel.org>
[ paulmck: Apply feedback from kernel test robot. ]
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

3 files changed, 23 insertions, 2 deletions

diff --git a/include/linux/torture.h b/include/linux/torture.h
index d62d13c8c69a..0910c5803f35 100644
--- a/include/linux/torture.h
+++ b/include/linux/torture.h
@@ -48,6 +48,11 @@ do {										\
 void verbose_torout_sleep(void);
 
 /* Definitions for online/offline exerciser. */
+#ifdef CONFIG_HOTPLUG_CPU
+int torture_num_online_cpus(void);
+#else /* #ifdef CONFIG_HOTPLUG_CPU */
+static inline int torture_num_online_cpus(void) { return 1; }
+#endif /* #else #ifdef CONFIG_HOTPLUG_CPU */
 typedef void torture_ofl_func(void);
 bool torture_offline(int cpu, long *n_onl_attempts, long *n_onl_successes,
 		     unsigned long *sum_offl, int *min_onl, int *max_onl);
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 76c838696366..a816df4e86e0 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -1338,7 +1338,7 @@ static void rcu_torture_reader_do_mbchk(long myid, struct rcu_torture *rtp,
 					struct torture_random_state *trsp)
 {
 	unsigned long loops;
-	int noc = num_online_cpus();
+	int noc = torture_num_online_cpus();
 	int rdrchked;
 	int rdrchker;
 	struct rcu_torture_reader_check *rtrcp; // Me.
@@ -1658,7 +1658,7 @@ rcu_torture_reader(void *arg)
 			torture_hrtimeout_us(500, 1000, &rand);
 			lastsleep = jiffies + 10;
 		}
-		while (num_online_cpus() < mynumonline && !torture_must_stop())
+		while (torture_num_online_cpus() < mynumonline && !torture_must_stop())
 			schedule_timeout_interruptible(HZ / 5);
 		stutter_wait("rcu_torture_reader");
 	} while (!torture_must_stop());
diff --git a/kernel/torture.c b/kernel/torture.c
index 507a20be6950..01e336f1e5b2 100644
--- a/kernel/torture.c
+++ b/kernel/torture.c
@@ -175,6 +175,19 @@ static unsigned long sum_online;
 static int min_online = -1;
 static int max_online;
 
+static int torture_online_cpus = NR_CPUS;
+
+/*
+ * Some torture testing leverages confusion as to the number of online
+ * CPUs.  This function returns the torture-testing view of this number,
+ * which allows torture tests to load-balance appropriately.
+ */
+int torture_num_online_cpus(void)
+{
+	return READ_ONCE(torture_online_cpus);
+}
+EXPORT_SYMBOL_GPL(torture_num_online_cpus);
+
 /*
  * Attempt to take a CPU offline.  Return false if the CPU is already
  * offline or if it is not subject to CPU-hotplug operations.  The
@@ -229,6 +242,8 @@ bool torture_offline(int cpu, long *n_offl_attempts, long *n_offl_successes,
 			*min_offl = delta;
 		if (*max_offl < delta)
 			*max_offl = delta;
+		WRITE_ONCE(torture_online_cpus, torture_online_cpus - 1);
+		WARN_ON_ONCE(torture_online_cpus <= 0);
 	}
 
 	return true;
@@ -285,6 +300,7 @@ bool torture_online(int cpu, long *n_onl_attempts, long *n_onl_successes,
 			*min_onl = delta;
 		if (*max_onl < delta)
 			*max_onl = delta;
+		WRITE_ONCE(torture_online_cpus, torture_online_cpus + 1);
 	}
 
 	return true;