ARM64: Convert all labels to local labels

While debugging/profiling applications using perf or other tools, the
kernels appear scattered in the profile reports. This is because the labels
within the kernels are not local and each label is shown as a separate
function.

To avoid this, all the labels within the kernels are changed to local
labels.

kernel/arm64/daxpy_thunderx2t99.S

@@ -122,53 +122,53 @@ USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 	PROLOGUE
 
 	cmp	N, xzr
-	ble	axpy_kernel_L999
+	ble	.Ldaxpy_kernel_L999
 
 	fcmp	DA, #0.0
-	beq	axpy_kernel_L999
+	beq	.Ldaxpy_kernel_L999
 
 	cmp	INC_X, #1
-	bne	axpy_kernel_S_BEGIN
+	bne	.Ldaxpy_kernel_S_BEGIN
 	cmp	INC_Y, #1
-	bne	axpy_kernel_S_BEGIN
+	bne	.Ldaxpy_kernel_S_BEGIN
 
-axpy_kernel_F_BEGIN:
+.Ldaxpy_kernel_F_BEGIN:
 
 	asr	I, N, #5
 	cmp	I, xzr
-	beq	axpy_kernel_F1
+	beq	.Ldaxpy_kernel_F1
 
 	.align 5
-axpy_kernel_F32:
+.Ldaxpy_kernel_F32:
 
 	KERNEL_F32
 
 	subs	I, I, #1
-	bne	axpy_kernel_F32
+	bne	.Ldaxpy_kernel_F32
 
-axpy_kernel_F1:
+.Ldaxpy_kernel_F1:
 
 	ands	I, N, #31
-	ble	axpy_kernel_L999
+	ble	.Ldaxpy_kernel_L999
 
-axpy_kernel_F10:
+.Ldaxpy_kernel_F10:
 
 	KERNEL_F1
 
 	subs    I, I, #1
-        bne     axpy_kernel_F10
+        bne     .Ldaxpy_kernel_F10
 
-	b	axpy_kernel_L999
+	b	.Ldaxpy_kernel_L999
 
-axpy_kernel_S_BEGIN:
+.Ldaxpy_kernel_S_BEGIN:
 
 	INIT_S
 
 	asr	I, N, #2
 	cmp	I, xzr
-	ble	axpy_kernel_S1
+	ble	.Ldaxpy_kernel_S1
 
-axpy_kernel_S4:
+.Ldaxpy_kernel_S4:
 
 	KERNEL_S1
 	KERNEL_S1
@@ -176,21 +176,21 @@ axpy_kernel_S4:
 	KERNEL_S1
 
 	subs	I, I, #1
-	bne	axpy_kernel_S4
+	bne	.Ldaxpy_kernel_S4
 
-axpy_kernel_S1:
+.Ldaxpy_kernel_S1:
 
 	ands	I, N, #3
-	ble	axpy_kernel_L999
+	ble	.Ldaxpy_kernel_L999
 
-axpy_kernel_S10:
+.Ldaxpy_kernel_S10:
 
 	KERNEL_S1
 
 	subs    I, I, #1
-        bne     axpy_kernel_S10
+        bne     .Ldaxpy_kernel_S10
 
-axpy_kernel_L999:
+.Ldaxpy_kernel_L999:
 
 	mov	w0, wzr
 	ret