sh: Optimized cache handling for SH-4/SH-4A caches.

This reworks some of the SH-4 cache handling code to more easily
accomodate newer-style caches (particularly for the > direct-mapped
case), as well as optimizing some of the old code.

Signed-off-by: Richard Curnow <richard.curnow@st.com>
Signed-off-by: Paul Mundt <lethal@linux-sh.org>

arch/sh/mm/clear_page.S

@@ -193,102 +193,5 @@ ENTRY(__clear_user_page)
 	 nop
 .L4096:	.word	4096
 
-ENTRY(__flush_cache_4096)
-	mov.l	1f,r3
-	add	r6,r3
-	mov	r4,r0
-	mov	#64,r2
-	shll	r2
-	mov	#64,r6
-	jmp	@r3
-	 mov	#96,r7
-	.align	2
-1:	.long	2f
-2:
-	.rept	32
-	mov.l	r5,@r0
-	mov.l	r5,@(32,r0)
-	mov.l	r5,@(r0,r6)
-	mov.l	r5,@(r0,r7)
-	add	r2,r5
-	add	r2,r0
-	.endr
-	nop
-	nop
-	nop
-	nop
-	nop
-	nop
-	nop
-	rts
-	 nop
-
-ENTRY(__flush_dcache_all)
-	mov.l	2f,r0
-	mov.l	3f,r4
-	and	r0,r4		! r4 = (unsigned long)&empty_zero_page[0] & ~0xffffc000
-	stc	sr,r1		! save SR
-	mov.l	4f,r2
-	or	r1,r2
-	mov	#32,r3
-	shll2	r3
-1:
-	ldc	r2,sr		! set BL bit
-	movca.l	r0,@r4
-	ocbi	@r4
-	add	#32,r4
-	movca.l	r0,@r4
-	ocbi	@r4
-	add	#32,r4
-	movca.l	r0,@r4
-	ocbi	@r4
-	add	#32,r4
-	movca.l	r0,@r4
-	ocbi	@r4
-	ldc	r1,sr		! restore SR
-	dt	r3
-	bf/s	1b
-	 add	#32,r4
-
-	rts
-	 nop
-	.align	2
-2:	.long	0xffffc000
-3:	.long	empty_zero_page
-4:	.long	0x10000000	! BL bit
-
-/* __flush_cache_4096_all(unsigned long addr) */
-ENTRY(__flush_cache_4096_all)
-	mov.l	2f,r0
-	mov.l	3f,r2
-	and	r0,r2
-	or	r2,r4		! r4 = addr | (unsigned long)&empty_zero_page[0] & ~0x3fff
-	stc	sr,r1		! save SR
-	mov.l	4f,r2
-	or	r1,r2
-	mov	#32,r3
-1:
-	ldc	r2,sr		! set BL bit
-	movca.l	r0,@r4
-	ocbi	@r4
-	add	#32,r4
-	movca.l	r0,@r4
-	ocbi	@r4
-	add	#32,r4
-	movca.l	r0,@r4
-	ocbi	@r4
-	add	#32,r4
-	movca.l	r0,@r4
-	ocbi	@r4
-	ldc	r1,sr		! restore SR
-	dt	r3
-	bf/s	1b
-	 add	#32,r4
-
-	rts
-	 nop
-	.align	2
-2:	.long	0xffffc000
-3:	.long	empty_zero_page
-4:	.long	0x10000000	! BL bit
 #endif
+