1 files changed, 99 insertions, 187 deletions

diff --git a/tools/testing/selftests/arm64/fp/sve-test.S b/tools/testing/selftests/arm64/fp/sve-test.S
index f95074c9b48b..fff60e2a25ad 100644
--- a/tools/testing/selftests/arm64/fp/sve-test.S
+++ b/tools/testing/selftests/arm64/fp/sve-test.S
@@ -13,6 +13,7 @@
 #include <asm/unistd.h>
 #include "assembler.h"
 #include "asm-offsets.h"
+#include "sme-inst.h"
 
 #define NZR	32
 #define NPR	16
@@ -46,130 +47,6 @@ define_accessor getz, NZR, _sve_str_v
 define_accessor setp, NPR, _sve_ldr_p
 define_accessor getp, NPR, _sve_str_p
 
-// Print a single character x0 to stdout
-// Clobbers x0-x2,x8
-function putc
-	str	x0, [sp, #-16]!
-
-	mov	x0, #1			// STDOUT_FILENO
-	mov	x1, sp
-	mov	x2, #1
-	mov	x8, #__NR_write
-	svc	#0
-
-	add	sp, sp, #16
-	ret
-endfunction
-
-// Print a NUL-terminated string starting at address x0 to stdout
-// Clobbers x0-x3,x8
-function puts
-	mov	x1, x0
-
-	mov	x2, #0
-0:	ldrb	w3, [x0], #1
-	cbz	w3, 1f
-	add	x2, x2, #1
-	b	0b
-
-1:	mov	w0, #1			// STDOUT_FILENO
-	mov	x8, #__NR_write
-	svc	#0
-
-	ret
-endfunction
-
-// Utility macro to print a literal string
-// Clobbers x0-x4,x8
-.macro puts string
-	.pushsection .rodata.str1.1, "aMS", 1
-.L__puts_literal\@: .string "\string"
-	.popsection
-
-	ldr	x0, =.L__puts_literal\@
-	bl	puts
-.endm
-
-// Print an unsigned decimal number x0 to stdout
-// Clobbers x0-x4,x8
-function putdec
-	mov	x1, sp
-	str	x30, [sp, #-32]!	// Result can't be > 20 digits
-
-	mov	x2, #0
-	strb	w2, [x1, #-1]!		// Write the NUL terminator
-
-	mov	x2, #10
-0:	udiv	x3, x0, x2		// div-mod loop to generate the digits
-	msub	x0, x3, x2, x0
-	add	w0, w0, #'0'
-	strb	w0, [x1, #-1]!
-	mov	x0, x3
-	cbnz	x3, 0b
-
-	ldrb	w0, [x1]
-	cbnz	w0, 1f
-	mov	w0, #'0'		// Print "0" for 0, not ""
-	strb	w0, [x1, #-1]!
-
-1:	mov	x0, x1
-	bl	puts
-
-	ldr	x30, [sp], #32
-	ret
-endfunction
-
-// Print an unsigned decimal number x0 to stdout, followed by a newline
-// Clobbers x0-x5,x8
-function putdecn
-	mov	x5, x30
-
-	bl	putdec
-	mov	x0, #'\n'
-	bl	putc
-
-	ret	x5
-endfunction
-
-// Clobbers x0-x3,x8
-function puthexb
-	str	x30, [sp, #-0x10]!
-
-	mov	w3, w0
-	lsr	w0, w0, #4
-	bl	puthexnibble
-	mov	w0, w3
-
-	ldr	x30, [sp], #0x10
-	// fall through to puthexnibble
-endfunction
-// Clobbers x0-x2,x8
-function puthexnibble
-	and	w0, w0, #0xf
-	cmp	w0, #10
-	blo	1f
-	add	w0, w0, #'a' - ('9' + 1)
-1:	add	w0, w0, #'0'
-	b	putc
-endfunction
-
-// x0=data in, x1=size in, clobbers x0-x5,x8
-function dumphex
-	str	x30, [sp, #-0x10]!
-
-	mov	x4, x0
-	mov	x5, x1
-
-0:	subs	x5, x5, #1
-	b.lo	1f
-	ldrb	w0, [x4], #1
-	bl	puthexb
-	b	0b
-
-1:	ldr	x30, [sp], #0x10
-	ret
-endfunction
-
 // Declare some storate space to shadow the SVE register contents:
 .pushsection .text
 .data
@@ -184,18 +61,6 @@ scratch:
 	.space	MAXVL_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 SVE registers
 // x0: pid	(16 bits)
 // x1: register number (6 bits)
@@ -284,16 +149,29 @@ endfunction
 // Set up test pattern in the FFR
 // x0: pid
 // x2: generation
+//
+// We need to generate a canonical FFR value, which consists of a number of
+// low "1" bits, followed by a number of zeros. This gives us 17 unique values
+// per 16 bits of FFR, so we create a 4 bit signature out of the PID and
+// generation, and use that as the initial number of ones in the pattern.
+// We fill the upper lanes of FFR with zeros.
 // Beware: corrupts P0.
 function setup_ffr
+#ifndef SSVE
 	mov	x4, x30
 
-	bl	pattern
+	and	w0, w0, #0x3
+	bfi	w0, w2, #2, #2
+	mov	w1, #1
+	lsl	w1, w1, w0
+	sub	w1, w1, #1
+
 	ldr	x0, =ffrref
-	ldr	x1, =scratch
-	rdvl	x2, #1
-	lsr	x2, x2, #3
-	bl	memcpy
+	strh	w1, [x0], 2
+	rdvl	x1, #1
+	lsr	x1, x1, #3
+	sub	x1, x1, #2
+	bl	memclr
 
 	mov	x0, #0
 	ldr	x1, =ffrref
@@ -302,33 +180,9 @@ function setup_ffr
 	wrffr	p0.b
 
 	ret	x4
-endfunction
-
-// Fill x1 bytes starting at x0 with 0xae (for canary purposes)
-// Clobbers x1, x2.
-function memfill_ae
-	mov	w2, #0xae
-	b	memfill
-endfunction
-
-// Fill x1 bytes starting at x0 with 0.
-// Clobbers x1, x2.
-function memclr
-	mov	w2, #0
-endfunction
-	// fall through to memfill
-
-// Trivial memory fill: fill x1 bytes starting at address x0 with byte w2
-// Clobbers x1
-function memfill
-	cmp	x1, #0
-	b.eq	1f
-
-0:	strb	w2, [x0], #1
-	subs	x1, x1, #1
-	b.ne	0b
-
-1:	ret
+#else
+	ret
+#endif
 endfunction
 
 // Trivial memory compare: compare x2 bytes starting at address x0 with
@@ -411,6 +265,7 @@ endfunction
 // Beware -- corrupts P0.
 // Clobbers x0-x5.
 function check_ffr
+#ifndef SSVE
 	mov	x3, x30
 
 	ldr	x4, =scratch
@@ -431,6 +286,9 @@ 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
@@ -446,10 +304,21 @@ 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
+
+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
@@ -509,7 +378,35 @@ endfunction
 // Main program entry point
 .globl _start
 function _start
-_start:
+	mov	x23, #0		// Irritation 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
+
+#ifdef SSVE
+	puts	"Streaming mode "
+	smstart_sm
+#endif
+
 	// Sanity-check and report the vector length
 
 	rdvl	x19, #8
@@ -540,23 +437,9 @@ _start:
 	mov	x0, x20
 	bl	putdecn
 
-	mov	x23, #0		// Irritation 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
+#ifdef SSVE
+	smstart_sm		// syscalls will have exited streaming mode
+#endif
 
 	mov	x22, #0		// generation number, increments per iteration
 .Ltest_loop:
@@ -590,6 +473,13 @@ _start:
 //	mov	x8, #__NR_sched_yield	// Encourage preemption
 //	svc	#0
 
+#ifdef SSVE
+	mrs	x0, S3_3_C4_C2_2	// SVCR should have ZA=0,SM=1
+	and	x1, x0, #3
+	cmp	x1, #1
+	b.ne	svcr_barf
+#endif
+
 	mov	x21, #0
 0:	mov	x0, x21
 	bl	check_zreg
@@ -625,7 +515,11 @@ function barf
 	mov	x11, x1	// actual data
 	mov	x12, x2	// data size
 
-	puts	"Mistatch: PID="
+#ifdef SSVE
+	mrs	x13, S3_3_C4_C2_2
+#endif
+
+	puts	"Mismatch: PID="
 	mov	x0, x20
 	bl	putdec
 	puts	", iteration="
@@ -644,6 +538,12 @@ function barf
 	bl	dumphex
 	puts	"]\n"
 
+#ifdef SSVE
+	puts	"\tSVCR: "
+	mov	x0, x13
+	bl	putdecn
+#endif
+
 	mov	x8, #__NR_getpid
 	svc	#0
 // fpsimd.c acitivty log dump hack
@@ -670,3 +570,15 @@ function vl_barf
 	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