kselftets/arm64: Use flag bits for features in fp-ptrace assembler code

The assembler portions of fp-ptrace are passed feature flags by the C code
indicating which architectural features are supported. Currently these use
an entire register for each flag which is wasteful and gets cumbersome as
new flags are added. Switch to using flag bits in a single register to make
things easier to maintain.

No functional change.

Signed-off-by: Mark Brown <broonie@kernel.org>
Link: https://lore.kernel.org/r/20241112-arm64-fp-ptrace-fpmr-v2-1-250b57c61254@kernel.org
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

Author: broonie

tools/testing/selftests/arm64/fp/fp-ptrace-asm.S

@@ -15,10 +15,7 @@
 
 // Load and save register values with pauses for ptrace
 //
-// x0 - SVE in use
-// x1 - SME in use
-// x2 - SME2 in use
-// x3 - FA64 supported
+// x0 - HAVE_ flags indicating which features are in use
 
 .globl load_and_save
 load_and_save:
@@ -44,7 +41,7 @@ load_and_save:
 	ldp	q30, q31, [x7, #16 * 30]
 
 	// SME?
-	cbz	x1, check_sve_in
+	tbz	x0, #HAVE_SME_SHIFT, check_sve_in
 
 	adrp	x7, svcr_in
 	ldr	x7, [x7, :lo12:svcr_in]
@@ -64,20 +61,24 @@ load_and_save:
 	bne	1b
 
 	// ZT?
-	cbz	x2, check_sm_in
+	tbz	x0, #HAVE_SME2_SHIFT, check_sm_in
 	adrp	x6, zt_in
 	add	x6, x6, :lo12:zt_in
 	_ldr_zt 6
 
 	// In streaming mode?
 check_sm_in:
 	tbz	x7, #SVCR_SM_SHIFT, check_sve_in
-	mov	x4, x3		// Load FFR if we have FA64
+
+	// Load FFR if we have FA64
+	mov	x4, #0
+	tbz	x0, #HAVE_FA64_SHIFT, load_sve
+	mov	x4, #1
 	b	load_sve
 
 	// SVE?
 check_sve_in:
-	cbz	x0, wait_for_writes
+	tbz	x0, #HAVE_SVE_SHIFT, wait_for_writes
 	mov	x4, #1
 
 load_sve:
@@ -165,8 +166,7 @@ wait_for_writes:
 	stp	q28, q29, [x7, #16 * 28]
 	stp	q30, q31, [x7, #16 * 30]
 
-	// SME?
-	cbz	x1, check_sve_out
+	tbz	x0, #HAVE_SME_SHIFT, check_sve_out
 
 	rdsvl	11, 1
 	adrp	x6, sme_vl_out
@@ -187,20 +187,24 @@ wait_for_writes:
 	bne	1b
 
 	// ZT?
-	cbz	x2, check_sm_out
+	tbz	x0, #HAVE_SME2_SHIFT, check_sm_out
 	adrp	x6, zt_out
 	add	x6, x6, :lo12:zt_out
 	_str_zt 6
 
 	// In streaming mode?
 check_sm_out:
 	tbz	x7, #SVCR_SM_SHIFT, check_sve_out
-	mov	x4, x3				// FFR?
+
+	// Do we have FA64 and FFR?
+	mov	x4, #0
+	tbz	x0, #HAVE_FA64_SHIFT, read_sve
+	mov	x4, #1
 	b	read_sve
 
 	// SVE?
 check_sve_out:
-	cbz	x0, wait_for_reads
+	tbz	x0, #HAVE_SVE_SHIFT, wait_for_reads
 	mov	x4, #1
 
 	rdvl	x7, #1
@@ -271,7 +275,7 @@ wait_for_reads:
 	brk #0
 
 	// Ensure we don't leave ourselves in streaming mode
-	cbz	x1, out
+	tbz	x0, #HAVE_SME_SHIFT, out
 	msr	S3_3_C4_C2_2, xzr
 
 out:

tools/testing/selftests/arm64/fp/fp-ptrace.c

@@ -82,7 +82,7 @@ uint64_t sve_vl_out;
 uint64_t sme_vl_out;
 uint64_t svcr_in, svcr_expected, svcr_out;
 
-void load_and_save(int sve, int sme, int sme2, int fa64);
+void load_and_save(int flags);
 
 static bool got_alarm;
 
@@ -198,7 +198,7 @@ static int vl_expected(struct test_config *config)
 
 static void run_child(struct test_config *config)
 {
-	int ret;
+	int ret, flags;
 
 	/* Let the parent attach to us */
 	ret = ptrace(PTRACE_TRACEME, 0, 0, 0);
@@ -224,8 +224,17 @@ static void run_child(struct test_config *config)
 	}
 
 	/* Load values and wait for the parent */
-	load_and_save(sve_supported(), sme_supported(),
-		      sme2_supported(), fa64_supported());
+	flags = 0;
+	if (sve_supported())
+		flags |= HAVE_SVE;
+	if (sme_supported())
+		flags |= HAVE_SME;
+	if (sme2_supported())
+		flags |= HAVE_SME2;
+	if (fa64_supported())
+		flags |= HAVE_FA64;
+
+	load_and_save(flags);
 
 	exit(0);
 }

tools/testing/selftests/arm64/fp/fp-ptrace.h

@@ -10,4 +10,14 @@
 #define SVCR_SM (1 << SVCR_SM_SHIFT)
 #define SVCR_ZA (1 << SVCR_ZA_SHIFT)
 
+#define HAVE_SVE_SHIFT		0
+#define HAVE_SME_SHIFT		1
+#define HAVE_SME2_SHIFT		2
+#define HAVE_FA64_SHIFT		3
+
+#define HAVE_SVE	(1 << HAVE_SVE_SHIFT)
+#define HAVE_SME	(1 << HAVE_SME_SHIFT)
+#define HAVE_SME2	(1 << HAVE_SME2_SHIFT)
+#define HAVE_FA64	(1 << HAVE_FA64_SHIFT)
+
 #endif