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, 148 insertions, 0 deletions

diff --git a/arch/arm/lib/memset.S b/arch/arm/lib/memset.S
new file mode 100644
index 000000000..de75ae4d5
--- /dev/null
+++ b/arch/arm/lib/memset.S
@@ -0,0 +1,148 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ *  linux/arch/arm/lib/memset.S
+ *
+ *  Copyright (C) 1995-2000 Russell King
+ *
+ *  ASM optimised string functions
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+#include <asm/unwind.h>
+
+	.text
+	.align	5
+
+ENTRY(__memset)
+ENTRY(mmioset)
+WEAK(memset)
+UNWIND( .fnstart         )
+	and	r1, r1, #255		@ cast to unsigned char
+	ands	r3, r0, #3		@ 1 unaligned?
+	mov	ip, r0			@ preserve r0 as return value
+	bne	6f			@ 1
+/*
+ * we know that the pointer in ip is aligned to a word boundary.
+ */
+1:	orr	r1, r1, r1, lsl #8
+	orr	r1, r1, r1, lsl #16
+	mov	r3, r1
+7:	cmp	r2, #16
+	blt	4f
+UNWIND( .fnend              )
+
+#if ! CALGN(1)+0
+
+/*
+ * We need 2 extra registers for this loop - use r8 and the LR
+ */
+UNWIND( .fnstart            )
+UNWIND( .save {r8, lr}      )
+	stmfd	sp!, {r8, lr}
+	mov	r8, r1
+	mov	lr, r3
+
+2:	subs	r2, r2, #64
+	stmiage	ip!, {r1, r3, r8, lr}	@ 64 bytes at a time.
+	stmiage	ip!, {r1, r3, r8, lr}
+	stmiage	ip!, {r1, r3, r8, lr}
+	stmiage	ip!, {r1, r3, r8, lr}
+	bgt	2b
+	ldmfdeq	sp!, {r8, pc}		@ Now <64 bytes to go.
+/*
+ * No need to correct the count; we're only testing bits from now on
+ */
+	tst	r2, #32
+	stmiane	ip!, {r1, r3, r8, lr}
+	stmiane	ip!, {r1, r3, r8, lr}
+	tst	r2, #16
+	stmiane	ip!, {r1, r3, r8, lr}
+	ldmfd	sp!, {r8, lr}
+UNWIND( .fnend              )
+
+#else
+
+/*
+ * This version aligns the destination pointer in order to write
+ * whole cache lines at once.
+ */
+
+UNWIND( .fnstart               )
+UNWIND( .save {r4-r8, lr}      )
+	stmfd	sp!, {r4-r8, lr}
+	mov	r4, r1
+	mov	r5, r3
+	mov	r6, r1
+	mov	r7, r3
+	mov	r8, r1
+	mov	lr, r3
+
+	cmp	r2, #96
+	tstgt	ip, #31
+	ble	3f
+
+	and	r8, ip, #31
+	rsb	r8, r8, #32
+	sub	r2, r2, r8
+	movs	r8, r8, lsl #(32 - 4)
+	stmiacs	ip!, {r4, r5, r6, r7}
+	stmiami	ip!, {r4, r5}
+	tst	r8, #(1 << 30)
+	mov	r8, r1
+	strne	r1, [ip], #4
+
+3:	subs	r2, r2, #64
+	stmiage	ip!, {r1, r3-r8, lr}
+	stmiage	ip!, {r1, r3-r8, lr}
+	bgt	3b
+	ldmfdeq	sp!, {r4-r8, pc}
+
+	tst	r2, #32
+	stmiane	ip!, {r1, r3-r8, lr}
+	tst	r2, #16
+	stmiane	ip!, {r4-r7}
+	ldmfd	sp!, {r4-r8, lr}
+UNWIND( .fnend                 )
+
+#endif
+
+UNWIND( .fnstart            )
+4:	tst	r2, #8
+	stmiane	ip!, {r1, r3}
+	tst	r2, #4
+	strne	r1, [ip], #4
+/*
+ * When we get here, we've got less than 4 bytes to set.  We
+ * may have an unaligned pointer as well.
+ */
+5:	tst	r2, #2
+	strbne	r1, [ip], #1
+	strbne	r1, [ip], #1
+	tst	r2, #1
+	strbne	r1, [ip], #1
+	ret	lr
+
+6:	subs	r2, r2, #4		@ 1 do we have enough
+	blt	5b			@ 1 bytes to align with?
+	cmp	r3, #2			@ 1
+	strblt	r1, [ip], #1		@ 1
+	strble	r1, [ip], #1		@ 1
+	strb	r1, [ip], #1		@ 1
+	add	r2, r2, r3		@ 1 (r2 = r2 - (4 - r3))
+	b	1b
+UNWIND( .fnend   )
+ENDPROC(memset)
+ENDPROC(mmioset)
+ENDPROC(__memset)
+
+ENTRY(__memset32)
+UNWIND( .fnstart         )
+	mov	r3, r1			@ copy r1 to r3 and fall into memset64
+UNWIND( .fnend   )
+ENDPROC(__memset32)
+ENTRY(__memset64)
+UNWIND( .fnstart         )
+	mov	ip, r0			@ preserve r0 as return value
+	b	7b			@ jump into the middle of memset
+UNWIND( .fnend   )
+ENDPROC(__memset64)