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, 183 insertions, 0 deletions

diff --git a/arch/alpha/lib/memmove.S b/arch/alpha/lib/memmove.S
new file mode 100644
index 000000000..3a27689e3
--- /dev/null
+++ b/arch/alpha/lib/memmove.S
@@ -0,0 +1,183 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * arch/alpha/lib/memmove.S
+ *
+ * Barely optimized memmove routine for Alpha EV5.
+ *
+ * This is hand-massaged output from the original memcpy.c.  We defer to
+ * memcpy whenever possible; the backwards copy loops are not unrolled.
+ */
+#include <linux/export.h>
+	.set noat
+	.set noreorder
+	.text
+
+	.align 4
+	.globl memmove
+	.ent memmove
+memmove:
+	ldgp $29, 0($27)
+	unop
+	nop
+	.prologue 1
+
+	addq $16,$18,$4
+	addq $17,$18,$5
+	cmpule $4,$17,$1		/*  dest + n <= src  */
+	cmpule $5,$16,$2		/*  dest >= src + n  */
+
+	bis $1,$2,$1
+	mov $16,$0
+	xor $16,$17,$2
+	bne $1,memcpy			!samegp
+
+	and $2,7,$2			/* Test for src/dest co-alignment.  */
+	and $16,7,$1
+	cmpule $16,$17,$3
+	bne $3,$memmove_up		/* dest < src */
+
+	and $4,7,$1
+	bne $2,$misaligned_dn
+	unop
+	beq $1,$skip_aligned_byte_loop_head_dn
+
+$aligned_byte_loop_head_dn:
+	lda $4,-1($4)
+	lda $5,-1($5)
+	unop
+	ble $18,$egress
+
+	ldq_u $3,0($5)
+	ldq_u $2,0($4)
+	lda $18,-1($18)
+	extbl $3,$5,$1
+
+	insbl $1,$4,$1
+	mskbl $2,$4,$2
+	bis $1,$2,$1
+	and $4,7,$6
+
+	stq_u $1,0($4)
+	bne $6,$aligned_byte_loop_head_dn
+
+$skip_aligned_byte_loop_head_dn:
+	lda $18,-8($18)
+	blt $18,$skip_aligned_word_loop_dn
+
+$aligned_word_loop_dn:
+	ldq $1,-8($5)
+	nop
+	lda $5,-8($5)
+	lda $18,-8($18)
+
+	stq $1,-8($4)
+	nop
+	lda $4,-8($4)
+	bge $18,$aligned_word_loop_dn
+
+$skip_aligned_word_loop_dn:
+	lda $18,8($18)
+	bgt $18,$byte_loop_tail_dn
+	unop
+	ret $31,($26),1
+
+	.align 4
+$misaligned_dn:
+	nop
+	fnop
+	unop
+	beq $18,$egress
+
+$byte_loop_tail_dn:
+	ldq_u $3,-1($5)
+	ldq_u $2,-1($4)
+	lda $5,-1($5)
+	lda $4,-1($4)
+
+	lda $18,-1($18)
+	extbl $3,$5,$1
+	insbl $1,$4,$1
+	mskbl $2,$4,$2
+
+	bis $1,$2,$1
+	stq_u $1,0($4)
+	bgt $18,$byte_loop_tail_dn
+	br $egress
+
+$memmove_up:
+	mov $16,$4
+	mov $17,$5
+	bne $2,$misaligned_up
+	beq $1,$skip_aligned_byte_loop_head_up
+
+$aligned_byte_loop_head_up:
+	unop
+	ble $18,$egress
+	ldq_u $3,0($5)
+	ldq_u $2,0($4)
+
+	lda $18,-1($18)
+	extbl $3,$5,$1
+	insbl $1,$4,$1
+	mskbl $2,$4,$2
+
+	bis $1,$2,$1
+	lda $5,1($5)
+	stq_u $1,0($4)
+	lda $4,1($4)
+
+	and $4,7,$6
+	bne $6,$aligned_byte_loop_head_up
+
+$skip_aligned_byte_loop_head_up:
+	lda $18,-8($18)
+	blt $18,$skip_aligned_word_loop_up
+
+$aligned_word_loop_up:
+	ldq $1,0($5)
+	nop
+	lda $5,8($5)
+	lda $18,-8($18)
+
+	stq $1,0($4)
+	nop
+	lda $4,8($4)
+	bge $18,$aligned_word_loop_up
+
+$skip_aligned_word_loop_up:
+	lda $18,8($18)
+	bgt $18,$byte_loop_tail_up
+	unop
+	ret $31,($26),1
+
+	.align 4
+$misaligned_up:
+	nop
+	fnop
+	unop
+	beq $18,$egress
+
+$byte_loop_tail_up:
+	ldq_u $3,0($5)
+	ldq_u $2,0($4)
+	lda $18,-1($18)
+	extbl $3,$5,$1
+
+	insbl $1,$4,$1
+	mskbl $2,$4,$2
+	bis $1,$2,$1
+	stq_u $1,0($4)
+
+	lda $5,1($5)
+	lda $4,1($4)
+	nop
+	bgt $18,$byte_loop_tail_up
+
+$egress:
+	ret $31,($26),1
+	nop
+	nop
+	nop
+
+	.end memmove
+	EXPORT_SYMBOL(memmove)