@@ -5,5 +5,6 @@ rdvl-sve
sve-probe-vls
sve-ptrace
sve-test
+ssve-test
vec-syscfg
vlset
@@ -5,6 +5,7 @@ TEST_GEN_PROGS := sve-ptrace sve-probe-vls vec-syscfg
TEST_PROGS_EXTENDED := fp-pidbench fpsimd-test fpsimd-stress \
rdvl-sme rdvl-sve \
sve-test sve-stress \
+ ssve-test ssve-stress \
vlset
all: $(TEST_GEN_PROGS) $(TEST_PROGS_EXTENDED)
@@ -19,6 +20,8 @@ sve-ptrace: sve-ptrace.o
sve-probe-vls: sve-probe-vls.o rdvl.o
sve-test: sve-test.o asm-utils.o
$(CC) -nostdlib $^ -o $@
+ssve-test: sve-test.S asm-utils.o
+ $(CC) -DSSVE -nostdlib $^ -o $@
vec-syscfg: vec-syscfg.o rdvl.o
vlset: vlset.o
new file mode 100644
@@ -0,0 +1,59 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0-only
+# Copyright (C) 2015-2019 ARM Limited.
+# Original author: Dave Martin <Dave.Martin@arm.com>
+
+set -ue
+
+NR_CPUS=`nproc`
+
+pids=
+logs=
+
+cleanup () {
+ trap - INT TERM CHLD
+ set +e
+
+ if [ -n "$pids" ]; then
+ kill $pids
+ wait $pids
+ pids=
+ fi
+
+ if [ -n "$logs" ]; then
+ cat $logs
+ rm $logs
+ logs=
+ fi
+}
+
+interrupt () {
+ cleanup
+ exit 0
+}
+
+child_died () {
+ cleanup
+ exit 1
+}
+
+trap interrupt INT TERM EXIT
+
+for x in `seq 0 $((NR_CPUS * 4))`; do
+ log=`mktemp`
+ logs=$logs\ $log
+ ./ssve-test >$log &
+ pids=$pids\ $!
+done
+
+# Wait for all child processes to be created:
+sleep 10
+
+while :; do
+ kill -USR1 $pids
+done &
+pids=$pids\ $!
+
+wait
+
+exit 1
@@ -156,6 +156,7 @@ endfunction
// We fill the upper lanes of FFR with zeros.
// Beware: corrupts P0.
function setup_ffr
+#ifndef SSVE
mov x4, x30
and w0, w0, #0x3
@@ -178,6 +179,9 @@ function setup_ffr
wrffr p0.b
ret x4
+#else
+ ret
+#endif
endfunction
// Trivial memory compare: compare x2 bytes starting at address x0 with
@@ -260,6 +264,7 @@ endfunction
// Beware -- corrupts P0.
// Clobbers x0-x5.
function check_ffr
+#ifndef SSVE
mov x3, x30
ldr x4, =scratch
@@ -280,6 +285,9 @@ function check_ffr
mov x2, x5
mov x30, x3
b memcmp
+#else
+ ret
+#endif
endfunction
// Any SVE register modified here can cause corruption in the main
@@ -295,13 +303,26 @@ function irritator_handler
movi v0.8b, #1
movi v9.16b, #2
movi v31.8b, #3
+#ifndef SSVE
// And P0
rdffr p0.b
// And FFR
wrffr p15.b
+#endif
+
+ ret
+endfunction
+
+#ifdef SSVE
+function enable_sm
+ // Set SVCR.SM to 1, equivalent to SMSTART SM but doesn't need a
+ // SME capable toolchain.
+ mov x0, #1
+ msr S3_3_C4_C2_2, x0
ret
endfunction
+#endif
function terminate_handler
mov w21, w0
@@ -359,6 +380,11 @@ endfunction
.globl _start
function _start
_start:
+#ifdef SSVE
+ puts "Streaming mode "
+ bl enable_sm
+#endif
+
// Sanity-check and report the vector length
rdvl x19, #8
@@ -407,6 +433,10 @@ _start:
orr w2, w2, #SA_NODEFER
bl setsignal
+#ifdef SSVE
+ bl enable_sm // syscalls will have exited streaming mode
+#endif
+
mov x22, #0 // generation number, increments per iteration
.Ltest_loop:
rdvl x0, #8
One of the features of SME is the addition of streaming mode, in which we have access to a set of streaming mode SVE registers at the SME vector length. Since these are accessed using the SVE instructions let's reuse the existing SVE stress test for testing with a compile time option for controlling the few small differences needed: - Enter streaming mode immediately on starting the program. - In streaming mode FFR is removed so skip reading and writing FFR. In order to avoid requiring a cutting edge toolchain with SME support use the op/CR form for specifying SVCR. Signed-off-by: Mark Brown <broonie@kernel.org> --- tools/testing/selftests/arm64/fp/.gitignore | 1 + tools/testing/selftests/arm64/fp/Makefile | 3 + tools/testing/selftests/arm64/fp/ssve-stress | 59 ++++++++++++++++++++ tools/testing/selftests/arm64/fp/sve-test.S | 30 ++++++++++ 4 files changed, 93 insertions(+) create mode 100644 tools/testing/selftests/arm64/fp/ssve-stress