m68k: add cache support for V4e ColdFire cores running with MMU enabled

Add code to deal with instruction, data and branch caches of the V4e
ColdFire cores when they are running with the MMU enabled.

This code is loosely based on Freescales changes for the caches of the
V4e ColdFire in the 2.6.25 kernel BSP. That code was originally by
Kurt Mahan <kmahan@freescale.com> (now <kmahan@xmission.com>).

Signed-off-by: Greg Ungerer <gerg@uclinux.org>
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>
Acked-by: Matt Waddel <mwaddel@yahoo.com>
Acked-by: Kurt Mahan <kmahan@xmission.com>
diff --git a/arch/m68k/include/asm/cacheflush_mm.h b/arch/m68k/include/asm/cacheflush_mm.h
index 73de7c8..8104bd8 100644
--- a/arch/m68k/include/asm/cacheflush_mm.h
+++ b/arch/m68k/include/asm/cacheflush_mm.h
@@ -2,23 +2,89 @@
 #define _M68K_CACHEFLUSH_H
 
 #include <linux/mm.h>
+#ifdef CONFIG_COLDFIRE
+#include <asm/mcfsim.h>
+#endif
 
 /* cache code */
 #define FLUSH_I_AND_D	(0x00000808)
 #define FLUSH_I		(0x00000008)
 
+#ifndef ICACHE_MAX_ADDR
+#define ICACHE_MAX_ADDR	0
+#define ICACHE_SET_MASK	0
+#define DCACHE_MAX_ADDR	0
+#define DCACHE_SETMASK	0
+#endif
+
+static inline void flush_cf_icache(unsigned long start, unsigned long end)
+{
+	unsigned long set;
+
+	for (set = start; set <= end; set += (0x10 - 3)) {
+		__asm__ __volatile__ (
+			"cpushl %%ic,(%0)\n\t"
+			"addq%.l #1,%0\n\t"
+			"cpushl %%ic,(%0)\n\t"
+			"addq%.l #1,%0\n\t"
+			"cpushl %%ic,(%0)\n\t"
+			"addq%.l #1,%0\n\t"
+			"cpushl %%ic,(%0)"
+			: "=a" (set)
+			: "a" (set));
+	}
+}
+
+static inline void flush_cf_dcache(unsigned long start, unsigned long end)
+{
+	unsigned long set;
+
+	for (set = start; set <= end; set += (0x10 - 3)) {
+		__asm__ __volatile__ (
+			"cpushl %%dc,(%0)\n\t"
+			"addq%.l #1,%0\n\t"
+			"cpushl %%dc,(%0)\n\t"
+			"addq%.l #1,%0\n\t"
+			"cpushl %%dc,(%0)\n\t"
+			"addq%.l #1,%0\n\t"
+			"cpushl %%dc,(%0)"
+			: "=a" (set)
+			: "a" (set));
+	}
+}
+
+static inline void flush_cf_bcache(unsigned long start, unsigned long end)
+{
+	unsigned long set;
+
+	for (set = start; set <= end; set += (0x10 - 3)) {
+		__asm__ __volatile__ (
+			"cpushl %%bc,(%0)\n\t"
+			"addq%.l #1,%0\n\t"
+			"cpushl %%bc,(%0)\n\t"
+			"addq%.l #1,%0\n\t"
+			"cpushl %%bc,(%0)\n\t"
+			"addq%.l #1,%0\n\t"
+			"cpushl %%bc,(%0)"
+			: "=a" (set)
+			: "a" (set));
+	}
+}
+
 /*
  * Cache handling functions
  */
 
 static inline void flush_icache(void)
 {
-	if (CPU_IS_040_OR_060)
+	if (CPU_IS_COLDFIRE) {
+		flush_cf_icache(0, ICACHE_MAX_ADDR);
+	} else if (CPU_IS_040_OR_060) {
 		asm volatile (	"nop\n"
 			"	.chip	68040\n"
 			"	cpusha	%bc\n"
 			"	.chip	68k");
-	else {
+	} else {
 		unsigned long tmp;
 		asm volatile (	"movec	%%cacr,%0\n"
 			"	or.w	%1,%0\n"
@@ -51,12 +117,14 @@
    process changes.  */
 #define __flush_cache_all()					\
 ({								\
-	if (CPU_IS_040_OR_060)					\
+	if (CPU_IS_COLDFIRE) {					\
+		flush_cf_dcache(0, DCACHE_MAX_ADDR);		\
+	} else if (CPU_IS_040_OR_060) {				\
 		__asm__ __volatile__("nop\n\t"			\
 				     ".chip 68040\n\t"		\
 				     "cpusha %dc\n\t"		\
 				     ".chip 68k");		\
-	else {							\
+	} else {						\
 		unsigned long _tmp;				\
 		__asm__ __volatile__("movec %%cacr,%0\n\t"	\
 				     "orw %1,%0\n\t"		\
@@ -112,7 +180,17 @@
 /* RZ: use cpush %bc instead of cpush %dc, cinv %ic */
 static inline void __flush_page_to_ram(void *vaddr)
 {
-	if (CPU_IS_040_OR_060) {
+	if (CPU_IS_COLDFIRE) {
+		unsigned long addr, start, end;
+		addr = ((unsigned long) vaddr) & ~(PAGE_SIZE - 1);
+		start = addr & ICACHE_SET_MASK;
+		end = (addr + PAGE_SIZE - 1) & ICACHE_SET_MASK;
+		if (start > end) {
+			flush_cf_bcache(0, end);
+			end = ICACHE_MAX_ADDR;
+		}
+		flush_cf_bcache(start, end);
+	} else if (CPU_IS_040_OR_060) {
 		__asm__ __volatile__("nop\n\t"
 				     ".chip 68040\n\t"
 				     "cpushp %%bc,(%0)\n\t"
diff --git a/arch/m68k/mm/cache.c b/arch/m68k/mm/cache.c
index 5437fff..95d0bf6 100644
--- a/arch/m68k/mm/cache.c
+++ b/arch/m68k/mm/cache.c
@@ -74,8 +74,16 @@
 /* RZ: use cpush %bc instead of cpush %dc, cinv %ic */
 void flush_icache_range(unsigned long address, unsigned long endaddr)
 {
-
-	if (CPU_IS_040_OR_060) {
+	if (CPU_IS_COLDFIRE) {
+		unsigned long start, end;
+		start = address & ICACHE_SET_MASK;
+		end = endaddr & ICACHE_SET_MASK;
+		if (start > end) {
+			flush_cf_icache(0, end);
+			end = ICACHE_MAX_ADDR;
+		}
+		flush_cf_icache(start, end);
+	} else if (CPU_IS_040_OR_060) {
 		address &= PAGE_MASK;
 
 		do {
@@ -100,7 +108,17 @@
 void flush_icache_user_range(struct vm_area_struct *vma, struct page *page,
 			     unsigned long addr, int len)
 {
-	if (CPU_IS_040_OR_060) {
+	if (CPU_IS_COLDFIRE) {
+		unsigned long start, end;
+		start = addr & ICACHE_SET_MASK;
+		end = (addr + len) & ICACHE_SET_MASK;
+		if (start > end) {
+			flush_cf_icache(0, end);
+			end = ICACHE_MAX_ADDR;
+		}
+		flush_cf_icache(start, end);
+
+	} else if (CPU_IS_040_OR_060) {
 		asm volatile ("nop\n\t"
 			      ".chip 68040\n\t"
 			      "cpushp %%bc,(%0)\n\t"