[ARM] Enable VFP to be built when non-VFP capable CPUs are selected

Since we pass flags to the compiler to control code generation based
on the least capable selected CPU, if we want to include VFP support,
we must tweak the assembler flags to allow the VFP instructions.
Moreover, we must not use the mrrc/mcrr versions since these will not
be recognised by the assembler.

We do not convert all instructions to the VFP-equivalent (yet) since
binutils appears to barf on "fmrx rn, fpinst" and doesn't provide any
other way (other than using the mrc equivalent) to encode this
instruction - which is rather a problem when you have a VFP
implementation which requires these instructions.
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

arch/arm/vfp/Makefile

@@ -7,6 +7,9 @@
 # EXTRA_CFLAGS := -DDEBUG
 # EXTRA_AFLAGS := -DDEBUG
 
+AFLAGS		:=$(AFLAGS:-msoft-float=-Wa,-mfpu=softvfp+vfp)
+LDFLAGS		+=--no-warn-mismatch
+
 obj-y			+= vfp.o
 
-vfp-$(CONFIG_VFP)	+= entry.o vfpmodule.o vfphw.o vfpsingle.o vfpdouble.o
+vfp-$(CONFIG_VFP)	+= vfpmodule.o entry.o vfphw.o vfpsingle.o vfpdouble.o

arch/arm/vfp/vfphw.S

@@ -192,7 +192,7 @@ vfp_get_double:
 	add	pc, pc, r0, lsl #3
 	mov	r0, r0
 	.irp	dr,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15
-	mrrc	p11, 1, r0, r1, c\dr	@ fmrrd	r0, r1, d\dr
+	fmrrd	r0, r1, d\dr
 	mov	pc, lr
 	.endr
 
@@ -206,6 +206,6 @@ vfp_put_double:
 	add	pc, pc, r0, lsl #3
 	mov	r0, r0
 	.irp	dr,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15
-	mcrr	p11, 1, r1, r2, c\dr	@ fmdrr	r1, r2, d\dr
+	fmdrr	d\dr, r1, r2
 	mov	pc, lr
 	.endr