diff mbox series

[v3,14/21] kselftest/arm64: Add a stress test program for ZT0

Message ID 20221111215026.813348-15-broonie@kernel.org
State Accepted
Commit 1c07425e902cd3137961c3d45b4271bf8a9b8eb9
Headers show
Series arm64/sme: Support SME 2 and SME 2.1 | expand

Commit Message

Mark Brown Nov. 11, 2022, 9:50 p.m. UTC
Following the pattern for the other register sets add a stress test program
for ZT0 which continually loads and verifies patterns in the register in
an effort to discover context switching problems.

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/sme-inst.h |  20 ++
 tools/testing/selftests/arm64/fp/zt-test.S  | 324 ++++++++++++++++++++
 4 files changed, 348 insertions(+)
 create mode 100644 tools/testing/selftests/arm64/fp/zt-test.S

Comments

Zenghui Yu Dec. 17, 2022, 9:15 a.m. UTC | #1
On 2022/11/12 5:50, Mark Brown wrote:
> +// Trivial memory copy: copy x2 bytes, starting at address x1, to address x0.
> +// Clobbers x0-x3
> +function memcpy
> +	cmp	x2, #0
> +	b.eq	1f
> +0:	ldrb	w3, [x1], #1
> +	strb	w3, [x0], #1
> +	subs	x2, x2, #1
> +	b.ne	0b
> +1:	ret
> +endfunction

There is an exact same implementation of memcpy in fp/asm-utils.S.

> +
> +// Generate a test pattern for storage in ZT
> +// x0: pid
> +// x1: generation
> +
> +// These values are used to constuct a 32-bit pattern that is repeated in the

s/constuct/construct/ ?

> +// scratch buffer as many times as will fit:
> +// bits 31:24	generation number (increments once per test_loop)
> +// bits 23: 8	pid
> +// bits  7: 0	32-bit lane index
> +
> +function pattern
> +	mov	w3, wzr
> +	bfi	w3, w0, #8, #16		// PID
> +	bfi	w3, w1, #24, #8		// Generation
> +
> +	ldr	x0, =scratch
> +	mov	w1, #ZT_B / 4
> +
> +0:	str	w3, [x0], #4
> +	add	w3, w3, #1		// Lane
> +	subs	w1, w1, #1
> +	b.ne	0b
> +
> +	ret
> +endfunction
> +
> +// Set up test pattern in a ZT horizontal vector
> +// x0: pid
> +// x1: generation
> +function setup_zt
> +	mov	x4, x30
> +
> +	bl	pattern			// Get pattern in scratch buffer
> +	ldr	x0, =ztref
> +	ldr	x1, =scratch
> +	mov	x2, #ZT_B
> +	bl	memcpy
> +
> +	_ldr_zt 0			// load zt0 from pointer x0

Isn't x0 already clobbered by memcpy (and is now pointing to the
end of ztref)?

> +
> +	ret	x4
> +endfunction
> +
> +// Trivial memory compare: compare x2 bytes starting at address x0 with
> +// bytes starting at address x1.
> +// Returns only if all bytes match; otherwise, the program is aborted.
> +// Clobbers x0-x5.
> +function memcmp
> +	cbz	x2, 2f
> +
> +	stp	x0, x1, [sp, #-0x20]!
> +	str	x2, [sp, #0x10]
> +
> +	mov	x5, #0
> +0:	ldrb	w3, [x0, x5]
> +	ldrb	w4, [x1, x5]
> +	add	x5, x5, #1
> +	cmp	w3, w4
> +	b.ne	1f
> +	subs	x2, x2, #1
> +	b.ne	0b
> +
> +1:	ldr	x2, [sp, #0x10]
> +	ldp	x0, x1, [sp], #0x20
> +	b.ne	barf
> +
> +2:	ret
> +endfunction
> +
> +// Verify that a ZT vector matches its shadow in memory, else abort
> +// Clobbers x0-x7 and x12.

It looks like check_zt doesn't clobber as many registers as "x0-x7
and x12".

> +function check_zt
> +	mov	x3, x30
> +
> +	ldr	x0, =scratch		// Poison scratch
> +	mov	x1, #ZT_B
> +	bl	memfill_ae
> +
> +	ldr	x0, =scratch
> +	_str_zt 0
> +
> +	ldr	x0, =ztref
> +	ldr	x1, =scratch
> +	mov	x2, #ZT_B
> +	mov	x30, x3
> +	b	memcmp
> +endfunction

[...]
> +.Ltest_loop:
> +	mov	x0, x20
> +	mov	x1, x22
> +	bl	setup_zt
> +
> +	mov	x8, #__NR_sched_yield	// Encourage preemption
> +	svc	#0
> +
> +	mov	x0, x20
> +	mov	x1, x22

check_zt receives no parameter so there is no need to initialize
x0 and x1.

> +	bl	check_zt
> +
> +	add	x22, x22, #1	// Everything still working
> +	b	.Ltest_loop
> +
> +.Labort:
> +	mov	x0, #0
> +	mov	x1, #SIGABRT
> +	mov	x8, #__NR_kill
> +	svc	#0
> +endfunction

[...]
> +function svcr_barf

And svcr_barf is unused in zt-test.

Zenghui
diff mbox series

Patch

diff --git a/tools/testing/selftests/arm64/fp/.gitignore b/tools/testing/selftests/arm64/fp/.gitignore
index df79d29664a1..41bde4c97d47 100644
--- a/tools/testing/selftests/arm64/fp/.gitignore
+++ b/tools/testing/selftests/arm64/fp/.gitignore
@@ -12,3 +12,4 @@  vlset
 za-fork
 za-ptrace
 za-test
+zt-test
diff --git a/tools/testing/selftests/arm64/fp/Makefile b/tools/testing/selftests/arm64/fp/Makefile
index 36db61358ed5..aff3026d3dff 100644
--- a/tools/testing/selftests/arm64/fp/Makefile
+++ b/tools/testing/selftests/arm64/fp/Makefile
@@ -14,6 +14,7 @@  TEST_GEN_PROGS_EXTENDED := fp-pidbench fpsimd-test \
 	sve-test \
 	ssve-test \
 	za-test \
+	zt-test \
 	vlset
 TEST_PROGS_EXTENDED := fpsimd-stress sve-stress ssve-stress za-stress
 
@@ -41,5 +42,7 @@  $(OUTPUT)/za-fork: za-fork.c $(OUTPUT)/za-fork-asm.o
 $(OUTPUT)/za-ptrace: za-ptrace.c
 $(OUTPUT)/za-test: za-test.S $(OUTPUT)/asm-utils.o
 	$(CC) -nostdlib $^ -o $@
+$(OUTPUT)/zt-test: zt-test.S $(OUTPUT)/asm-utils.o
+	$(CC) -nostdlib $^ -o $@
 
 include ../../lib.mk
diff --git a/tools/testing/selftests/arm64/fp/sme-inst.h b/tools/testing/selftests/arm64/fp/sme-inst.h
index 7191e53ca1c0..9292bba5400b 100644
--- a/tools/testing/selftests/arm64/fp/sme-inst.h
+++ b/tools/testing/selftests/arm64/fp/sme-inst.h
@@ -48,4 +48,24 @@ 
 		| ((\offset) & 7)
 .endm
 
+/*
+ * LDR (ZT0)
+ *
+ *	LDR ZT0, nx
+ */
+.macro _ldr_zt nx
+	.inst	0xe11f8000			\
+		| (((\nx) & 0x1f) << 5)
+.endm
+
+/*
+ * STR (ZT0)
+ *
+ *	STR ZT0, nx
+ */
+.macro _str_zt nx
+	.inst	0xe13f8000			\
+		| (((\nx) & 0x1f) << 5)
+.endm
+
 #endif
diff --git a/tools/testing/selftests/arm64/fp/zt-test.S b/tools/testing/selftests/arm64/fp/zt-test.S
new file mode 100644
index 000000000000..6f04a8bf60f6
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/zt-test.S
@@ -0,0 +1,324 @@ 
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (C) 2021-2 ARM Limited.
+// Original author: Mark Brown <broonie@kernel.org>
+//
+// Scalable Matrix Extension ZT context switch test
+// Repeatedly writes unique test patterns into ZT0
+// and reads them back to verify integrity.
+
+#include <asm/unistd.h>
+#include "assembler.h"
+#include "asm-offsets.h"
+#include "sme-inst.h"
+
+.arch_extension sve
+
+#define ZT_SZ	512
+#define ZT_B	(ZT_SZ / 8)
+
+// Declare some storage space to shadow ZT register contents and a
+// scratch buffer.
+.pushsection .text
+.data
+.align 4
+ztref:
+	.space	ZT_B
+scratch:
+	.space	ZT_B
+.popsection
+
+// Trivial memory copy: copy x2 bytes, starting at address x1, to address x0.
+// Clobbers x0-x3
+function memcpy
+	cmp	x2, #0
+	b.eq	1f
+0:	ldrb	w3, [x1], #1
+	strb	w3, [x0], #1
+	subs	x2, x2, #1
+	b.ne	0b
+1:	ret
+endfunction
+
+// Generate a test pattern for storage in ZT
+// x0: pid
+// x1: generation
+
+// These values are used to constuct a 32-bit pattern that is repeated in the
+// scratch buffer as many times as will fit:
+// bits 31:24	generation number (increments once per test_loop)
+// bits 23: 8	pid
+// bits  7: 0	32-bit lane index
+
+function pattern
+	mov	w3, wzr
+	bfi	w3, w0, #8, #16		// PID
+	bfi	w3, w1, #24, #8		// Generation
+
+	ldr	x0, =scratch
+	mov	w1, #ZT_B / 4
+
+0:	str	w3, [x0], #4
+	add	w3, w3, #1		// Lane
+	subs	w1, w1, #1
+	b.ne	0b
+
+	ret
+endfunction
+
+// Set up test pattern in a ZT horizontal vector
+// x0: pid
+// x1: generation
+function setup_zt
+	mov	x4, x30
+
+	bl	pattern			// Get pattern in scratch buffer
+	ldr	x0, =ztref
+	ldr	x1, =scratch
+	mov	x2, #ZT_B
+	bl	memcpy
+
+	_ldr_zt 0			// load zt0 from pointer x0
+
+	ret	x4
+endfunction
+
+// Trivial memory compare: compare x2 bytes starting at address x0 with
+// bytes starting at address x1.
+// Returns only if all bytes match; otherwise, the program is aborted.
+// Clobbers x0-x5.
+function memcmp
+	cbz	x2, 2f
+
+	stp	x0, x1, [sp, #-0x20]!
+	str	x2, [sp, #0x10]
+
+	mov	x5, #0
+0:	ldrb	w3, [x0, x5]
+	ldrb	w4, [x1, x5]
+	add	x5, x5, #1
+	cmp	w3, w4
+	b.ne	1f
+	subs	x2, x2, #1
+	b.ne	0b
+
+1:	ldr	x2, [sp, #0x10]
+	ldp	x0, x1, [sp], #0x20
+	b.ne	barf
+
+2:	ret
+endfunction
+
+// Verify that a ZT vector matches its shadow in memory, else abort
+// Clobbers x0-x7 and x12.
+function check_zt
+	mov	x3, x30
+
+	ldr	x0, =scratch		// Poison scratch
+	mov	x1, #ZT_B
+	bl	memfill_ae
+
+	ldr	x0, =scratch
+	_str_zt 0
+
+	ldr	x0, =ztref
+	ldr	x1, =scratch
+	mov	x2, #ZT_B
+	mov	x30, x3
+	b	memcmp
+endfunction
+
+// Any SME register modified here can cause corruption in the main
+// thread -- but *only* the locations modified here.
+function irritator_handler
+	// Increment the irritation signal count (x23):
+	ldr	x0, [x2, #ucontext_regs + 8 * 23]
+	add	x0, x0, #1
+	str	x0, [x2, #ucontext_regs + 8 * 23]
+
+	// Corrupt some random ZT data
+#if 0
+	adr	x0, .text + (irritator_handler - .text) / 16 * 16
+	movi	v0.8b, #1
+	movi	v9.16b, #2
+	movi	v31.8b, #3
+#endif
+
+	ret
+endfunction
+
+function tickle_handler
+	// Increment the signal count (x23):
+	ldr	x0, [x2, #ucontext_regs + 8 * 23]
+	add	x0, x0, #1
+	str	x0, [x2, #ucontext_regs + 8 * 23]
+
+	ret
+endfunction
+
+function terminate_handler
+	mov	w21, w0
+	mov	x20, x2
+
+	puts	"Terminated by signal "
+	mov	w0, w21
+	bl	putdec
+	puts	", no error, iterations="
+	ldr	x0, [x20, #ucontext_regs + 8 * 22]
+	bl	putdec
+	puts	", signals="
+	ldr	x0, [x20, #ucontext_regs + 8 * 23]
+	bl	putdecn
+
+	mov	x0, #0
+	mov	x8, #__NR_exit
+	svc	#0
+endfunction
+
+// w0: signal number
+// x1: sa_action
+// w2: sa_flags
+// Clobbers x0-x6,x8
+function setsignal
+	str	x30, [sp, #-((sa_sz + 15) / 16 * 16 + 16)]!
+
+	mov	w4, w0
+	mov	x5, x1
+	mov	w6, w2
+
+	add	x0, sp, #16
+	mov	x1, #sa_sz
+	bl	memclr
+
+	mov	w0, w4
+	add	x1, sp, #16
+	str	w6, [x1, #sa_flags]
+	str	x5, [x1, #sa_handler]
+	mov	x2, #0
+	mov	x3, #sa_mask_sz
+	mov	x8, #__NR_rt_sigaction
+	svc	#0
+
+	cbz	w0, 1f
+
+	puts	"sigaction failure\n"
+	b	.Labort
+
+1:	ldr	x30, [sp], #((sa_sz + 15) / 16 * 16 + 16)
+	ret
+endfunction
+
+// Main program entry point
+.globl _start
+function _start
+_start:
+	mov	x23, #0		// signal count
+
+	mov	w0, #SIGINT
+	adr	x1, terminate_handler
+	mov	w2, #SA_SIGINFO
+	bl	setsignal
+
+	mov	w0, #SIGTERM
+	adr	x1, terminate_handler
+	mov	w2, #SA_SIGINFO
+	bl	setsignal
+
+	mov	w0, #SIGUSR1
+	adr	x1, irritator_handler
+	mov	w2, #SA_SIGINFO
+	orr	w2, w2, #SA_NODEFER
+	bl	setsignal
+
+	mov	w0, #SIGUSR2
+	adr	x1, tickle_handler
+	mov	w2, #SA_SIGINFO
+	orr	w2, w2, #SA_NODEFER
+	bl	setsignal
+
+	smstart_za
+
+	// Obtain our PID, to ensure test pattern uniqueness between processes
+	mov	x8, #__NR_getpid
+	svc	#0
+	mov	x20, x0
+
+	puts	"PID:\t"
+	mov	x0, x20
+	bl	putdecn
+
+	mov	x22, #0		// generation number, increments per iteration
+.Ltest_loop:
+	mov	x0, x20
+	mov	x1, x22
+	bl	setup_zt
+
+	mov	x8, #__NR_sched_yield	// Encourage preemption
+	svc	#0
+
+	mov	x0, x20
+	mov	x1, x22
+	bl	check_zt
+
+	add	x22, x22, #1	// Everything still working
+	b	.Ltest_loop
+
+.Labort:
+	mov	x0, #0
+	mov	x1, #SIGABRT
+	mov	x8, #__NR_kill
+	svc	#0
+endfunction
+
+function barf
+// fpsimd.c acitivty log dump hack
+//	ldr	w0, =0xdeadc0de
+//	mov	w8, #__NR_exit
+//	svc	#0
+// end hack
+	smstop
+	mov	x10, x0	// expected data
+	mov	x11, x1	// actual data
+	mov	x12, x2	// data size
+
+	puts	"Mismatch: PID="
+	mov	x0, x20
+	bl	putdec
+	puts	", iteration="
+	mov	x0, x22
+	bl	putdec
+	puts	"\tExpected ["
+	mov	x0, x10
+	mov	x1, x12
+	bl	dumphex
+	puts	"]\n\tGot      ["
+	mov	x0, x11
+	mov	x1, x12
+	bl	dumphex
+	puts	"]\n"
+
+	mov	x8, #__NR_getpid
+	svc	#0
+// fpsimd.c acitivty log dump hack
+//	ldr	w0, =0xdeadc0de
+//	mov	w8, #__NR_exit
+//	svc	#0
+// ^ end of hack
+	mov	x1, #SIGABRT
+	mov	x8, #__NR_kill
+	svc	#0
+//	mov	x8, #__NR_exit
+//	mov	x1, #1
+//	svc	#0
+endfunction
+
+function svcr_barf
+	mov	x10, x0
+
+	puts	"Bad SVCR: "
+	mov	x0, x10
+	bl	putdecn
+
+	mov	x8, #__NR_exit
+	mov	x1, #1
+	svc	#0
+endfunction