scftorture: Count single_rpc offline failures in statistics outputgrafted

scf_torture_stats_print() aggregates each invoker thread's counters
into a local scf_statistics structure before printing, but the
n_single_rpc_ofl field is missing from the aggregation loop.  As a
result, the "single_rpc_ofl" value printed in the statistics line is
always zero, even when smp_call_function_single() invocations for the
RPC test have failed due to offline CPUs and been counted by the
invoker threads.

Add the missing accumulation so that the printed value reflects the
actual counts.

Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

1 files changed, 67 insertions, 0 deletions

diff --git a/arch/powerpc/boot/util.S b/arch/powerpc/boot/util.S
new file mode 100644
index 000000000..6a92376da
--- /dev/null
+++ b/arch/powerpc/boot/util.S
@@ -0,0 +1,67 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copied from <file:arch/powerpc/kernel/misc_32.S>
+ *
+ * This file contains miscellaneous low-level functions.
+ *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ *
+ * Largely rewritten by Cort Dougan (cort@cs.nmt.edu)
+ * and Paul Mackerras.
+ *
+ * kexec bits:
+ * Copyright (C) 2002-2003 Eric Biederman  <ebiederm@xmission.com>
+ * GameCube/ppc32 port Copyright (C) 2004 Albert Herranz
+ */
+#include "ppc_asm.h"
+
+#define SPRN_PVR        0x11F   /* Processor Version Register */
+
+	.text
+
+/* udelay needs to know the period of the
+ * timebase in nanoseconds.  This used to be hardcoded to be 60ns
+ * (period of 66MHz/4).  Now a variable is used that is initialized to
+ * 60 for backward compatibility, but it can be overridden as necessary
+ * with code something like this:
+ *    extern unsigned long timebase_period_ns;
+ *    timebase_period_ns = 1000000000 / bd->bi_tbfreq;
+ */
+	.data
+	.globl timebase_period_ns
+timebase_period_ns:
+	.long	60
+
+	.text
+/*
+ * Delay for a number of microseconds
+ */
+	.globl	udelay
+udelay:
+	mulli	r4,r3,1000	/* nanoseconds */
+	/*  Change r4 to be the number of ticks using:
+	 *	(nanoseconds + (timebase_period_ns - 1 )) / timebase_period_ns
+	 *  timebase_period_ns defaults to 60 (16.6MHz) */
+	mflr	r5
+	bcl	20,31,0f
+0:	mflr	r6
+	mtlr	r5
+	addis	r5,r6,(timebase_period_ns-0b)@ha
+	lwz	r5,(timebase_period_ns-0b)@l(r5)
+	add	r4,r4,r5
+	addi	r4,r4,-1
+	divw	r4,r4,r5	/* BUS ticks */
+1:	MFTBU(r5)
+	MFTBL(r6)
+	MFTBU(r7)
+	cmpw	0,r5,r7
+	bne	1b		/* Get [synced] base time */
+	addc	r9,r6,r4	/* Compute end time */
+	addze	r8,r5
+2:	MFTBU(r5)
+	cmpw	0,r5,r8
+	blt	2b
+	bgt	3f
+	MFTBL(r6)
+	cmpw	0,r6,r9
+	blt	2b
+3:	blr