diff --git a/board/dbau1x00/dbau1x00.c b/board/dbau1x00/dbau1x00.c
index a13eeeb1232306ed84b219493d4367a50d071f4c..1be72a2dd3e7731795c583688a7ccc58a38ec679 100644
--- a/board/dbau1x00/dbau1x00.c
+++ b/board/dbau1x00/dbau1x00.c
@@ -52,7 +52,7 @@ int checkboard (void)
 
 	*sys_counter = 0x100; /* Enable 32 kHz oscillator for RTC/TOY */
 
-	proc_id = read_32bit_cp0_register(CP0_PRID);
+	proc_id = read_c0_prid();
 
 	switch (proc_id >> 24) {
 	case 0:
diff --git a/board/gth2/gth2.c b/board/gth2/gth2.c
index 6da80dc758dc851e6cd13497a11b0ef266ae6688..9bc4d3fe5e84b630e70a7a65888fc72e827e1665 100644
--- a/board/gth2/gth2.c
+++ b/board/gth2/gth2.c
@@ -135,7 +135,7 @@ int checkboard (void)
 
 	*sys_counter = 0x100; /* Enable 32 kHz oscillator for RTC/TOY */
 
-	proc_id = read_32bit_cp0_register(CP0_PRID);
+	proc_id = read_c0_prid();
 
 	switch (proc_id >> 24) {
 	case 0:
diff --git a/board/pb1x00/pb1x00.c b/board/pb1x00/pb1x00.c
index 536c9544f53e407e9682c6a19ceb824d30ac8e0c..82b7235209ddea479714f5add85f29e8d597765e 100644
--- a/board/pb1x00/pb1x00.c
+++ b/board/pb1x00/pb1x00.c
@@ -51,7 +51,7 @@ int checkboard (void)
 
 	*sys_counter = 0x100; /* Enable 32 kHz oscillator for RTC/TOY */
 
-	proc_id = read_32bit_cp0_register(CP0_PRID);
+	proc_id = read_c0_prid();
 
 	switch (proc_id >> 24) {
 	case 0:
diff --git a/board/qemu-mips/qemu-mips.c b/board/qemu-mips/qemu-mips.c
index 68690743d686434c7702819aa0bb43a62a04f5b5..6e6eab27779b9018fc77edb732c008bcd6712b8a 100644
--- a/board/qemu-mips/qemu-mips.c
+++ b/board/qemu-mips/qemu-mips.c
@@ -38,7 +38,7 @@ int checkboard(void)
 	u32 proc_id;
 	u32 config1;
 
-	proc_id = read_32bit_cp0_register(CP0_PRID);
+	proc_id = read_c0_prid();
 	printf("Board: Qemu -M mips CPU: ");
 	switch (proc_id) {
 	case 0x00018000:
@@ -51,7 +51,7 @@ int checkboard(void)
 		printf("4KEc");
 		break;
 	case 0x00019300:
-		config1 = read_mips32_cp0_config1();
+		config1 = read_c0_config1();
 		if (config1 & 1)
 			printf("24Kf");
 		else
@@ -64,7 +64,7 @@ int checkboard(void)
 		printf("R4000");
 		break;
 	case 0x00018100:
-		config1 = read_mips32_cp0_config1();
+		config1 = read_c0_config1();
 		if (config1 & 1)
 			printf("5Kf");
 		else
diff --git a/cpu/mips/cpu.c b/cpu/mips/cpu.c
index e267bba4691e281faf45e307594149c97a4ae05b..0f58d25b892bbcc77ee3436c232d7ecdbadcc89a 100644
--- a/cpu/mips/cpu.c
+++ b/cpu/mips/cpu.c
@@ -66,10 +66,10 @@ void flush_cache(ulong start_addr, ulong size)
 
 void write_one_tlb(int index, u32 pagemask, u32 hi, u32 low0, u32 low1)
 {
-	write_32bit_cp0_register(CP0_ENTRYLO0, low0);
-	write_32bit_cp0_register(CP0_PAGEMASK, pagemask);
-	write_32bit_cp0_register(CP0_ENTRYLO1, low1);
-	write_32bit_cp0_register(CP0_ENTRYHI, hi);
-	write_32bit_cp0_register(CP0_INDEX, index);
+	write_c0_entrylo0(low0);
+	write_c0_pagemask(pagemask);
+	write_c0_entrylo1(low1);
+	write_c0_entryhi(hi);
+	write_c0_index(index);
 	tlb_write_indexed();
 }
diff --git a/include/asm-mips/errno.h b/include/asm-mips/errno.h
new file mode 100644
index 0000000000000000000000000000000000000000..1665a63a8120bba59b888d871b0c8b5fb2bfa61b
--- /dev/null
+++ b/include/asm-mips/errno.h
@@ -0,0 +1,143 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 1995, 1999, 2001, 2002 by Ralf Baechle
+ */
+#ifndef _ASM_MIPS_ERRNO_H
+#define _ASM_MIPS_ERRNO_H
+
+/*
+ * These first 34 error codes are from Linux 2.6, <asm-generic/errno-base.h>
+ */
+#define	EPERM		 1	/* Operation not permitted */
+#define	ENOENT		 2	/* No such file or directory */
+#define	ESRCH		 3	/* No such process */
+#define	EINTR		 4	/* Interrupted system call */
+#define	EIO		 5	/* I/O error */
+#define	ENXIO		 6	/* No such device or address */
+#define	E2BIG		 7	/* Argument list too long */
+#define	ENOEXEC		 8	/* Exec format error */
+#define	EBADF		 9	/* Bad file number */
+#define	ECHILD		10	/* No child processes */
+#define	EAGAIN		11	/* Try again */
+#define	ENOMEM		12	/* Out of memory */
+#define	EACCES		13	/* Permission denied */
+#define	EFAULT		14	/* Bad address */
+#define	ENOTBLK		15	/* Block device required */
+#define	EBUSY		16	/* Device or resource busy */
+#define	EEXIST		17	/* File exists */
+#define	EXDEV		18	/* Cross-device link */
+#define	ENODEV		19	/* No such device */
+#define	ENOTDIR		20	/* Not a directory */
+#define	EISDIR		21	/* Is a directory */
+#define	EINVAL		22	/* Invalid argument */
+#define	ENFILE		23	/* File table overflow */
+#define	EMFILE		24	/* Too many open files */
+#define	ENOTTY		25	/* Not a typewriter */
+#define	ETXTBSY		26	/* Text file busy */
+#define	EFBIG		27	/* File too large */
+#define	ENOSPC		28	/* No space left on device */
+#define	ESPIPE		29	/* Illegal seek */
+#define	EROFS		30	/* Read-only file system */
+#define	EMLINK		31	/* Too many links */
+#define	EPIPE		32	/* Broken pipe */
+#define	EDOM		33	/* Math argument out of domain of func */
+#define	ERANGE		34	/* Math result not representable */
+
+/*
+ * These error numbers are intended to be MIPS ABI compatible
+ */
+#define	ENOMSG		35	/* No message of desired type */
+#define	EIDRM		36	/* Identifier removed */
+#define	ECHRNG		37	/* Channel number out of range */
+#define	EL2NSYNC	38	/* Level 2 not synchronized */
+#define	EL3HLT		39	/* Level 3 halted */
+#define	EL3RST		40	/* Level 3 reset */
+#define	ELNRNG		41	/* Link number out of range */
+#define	EUNATCH		42	/* Protocol driver not attached */
+#define	ENOCSI		43	/* No CSI structure available */
+#define	EL2HLT		44	/* Level 2 halted */
+#define	EDEADLK		45	/* Resource deadlock would occur */
+#define	ENOLCK		46	/* No record locks available */
+#define	EBADE		50	/* Invalid exchange */
+#define	EBADR		51	/* Invalid request descriptor */
+#define	EXFULL		52	/* Exchange full */
+#define	ENOANO		53	/* No anode */
+#define	EBADRQC		54	/* Invalid request code */
+#define	EBADSLT		55	/* Invalid slot */
+#define	EDEADLOCK	56	/* File locking deadlock error */
+#define	EBFONT		59	/* Bad font file format */
+#define	ENOSTR		60	/* Device not a stream */
+#define	ENODATA		61	/* No data available */
+#define	ETIME		62	/* Timer expired */
+#define	ENOSR		63	/* Out of streams resources */
+#define	ENONET		64	/* Machine is not on the network */
+#define	ENOPKG		65	/* Package not installed */
+#define	EREMOTE		66	/* Object is remote */
+#define	ENOLINK		67	/* Link has been severed */
+#define	EADV		68	/* Advertise error */
+#define	ESRMNT		69	/* Srmount error */
+#define	ECOMM		70	/* Communication error on send */
+#define	EPROTO		71	/* Protocol error */
+#define	EDOTDOT		73	/* RFS specific error */
+#define	EMULTIHOP	74	/* Multihop attempted */
+#define	EBADMSG		77	/* Not a data message */
+#define	ENAMETOOLONG	78	/* File name too long */
+#define	EOVERFLOW	79	/* Value too large for defined data type */
+#define	ENOTUNIQ	80	/* Name not unique on network */
+#define	EBADFD		81	/* File descriptor in bad state */
+#define	EREMCHG		82	/* Remote address changed */
+#define	ELIBACC		83	/* Can not access a needed shared library */
+#define	ELIBBAD		84	/* Accessing a corrupted shared library */
+#define	ELIBSCN		85	/* .lib section in a.out corrupted */
+#define	ELIBMAX		86	/* Attempting to link in too many shared libraries */
+#define	ELIBEXEC	87	/* Cannot exec a shared library directly */
+#define	EILSEQ		88	/* Illegal byte sequence */
+#define	ENOSYS		89	/* Function not implemented */
+#define	ELOOP		90	/* Too many symbolic links encountered */
+#define	ERESTART	91	/* Interrupted system call should be restarted */
+#define	ESTRPIPE	92	/* Streams pipe error */
+#define	ENOTEMPTY	93	/* Directory not empty */
+#define	EUSERS		94	/* Too many users */
+#define	ENOTSOCK	95	/* Socket operation on non-socket */
+#define	EDESTADDRREQ	96	/* Destination address required */
+#define	EMSGSIZE	97	/* Message too long */
+#define	EPROTOTYPE	98	/* Protocol wrong type for socket */
+#define	ENOPROTOOPT	99	/* Protocol not available */
+#define	EPROTONOSUPPORT	120	/* Protocol not supported */
+#define	ESOCKTNOSUPPORT	121	/* Socket type not supported */
+#define	EOPNOTSUPP	122	/* Operation not supported on transport endpoint */
+#define	EPFNOSUPPORT	123	/* Protocol family not supported */
+#define	EAFNOSUPPORT	124	/* Address family not supported by protocol */
+#define	EADDRINUSE	125	/* Address already in use */
+#define	EADDRNOTAVAIL	126	/* Cannot assign requested address */
+#define	ENETDOWN	127	/* Network is down */
+#define	ENETUNREACH	128	/* Network is unreachable */
+#define	ENETRESET	129	/* Network dropped connection because of reset */
+#define	ECONNABORTED	130	/* Software caused connection abort */
+#define	ECONNRESET	131	/* Connection reset by peer */
+#define	ENOBUFS		132	/* No buffer space available */
+#define	EISCONN		133	/* Transport endpoint is already connected */
+#define	ENOTCONN	134	/* Transport endpoint is not connected */
+#define	EUCLEAN		135	/* Structure needs cleaning */
+#define	ENOTNAM		137	/* Not a XENIX named type file */
+#define	ENAVAIL		138	/* No XENIX semaphores available */
+#define	EISNAM		139	/* Is a named type file */
+#define	EREMOTEIO	140	/* Remote I/O error */
+#define EINIT		141	/* Reserved */
+#define EREMDEV		142	/* Error 142 */
+#define	ESHUTDOWN	143	/* Cannot send after transport endpoint shutdown */
+#define	ETOOMANYREFS	144	/* Too many references: cannot splice */
+#define	ETIMEDOUT	145	/* Connection timed out */
+#define	ECONNREFUSED	146	/* Connection refused */
+#define	EHOSTDOWN	147	/* Host is down */
+#define	EHOSTUNREACH	148	/* No route to host */
+#define	EWOULDBLOCK	EAGAIN	/* Operation would block */
+#define	EALREADY	149	/* Operation already in progress */
+#define	EINPROGRESS	150	/* Operation now in progress */
+#define	ESTALE		151	/* Stale NFS file handle */
+#define ECANCELED	158	/* AIO operation canceled */
+
+#endif /* _ASM_MIPS_ERRNO_H */
diff --git a/include/asm-mips/mipsregs.h b/include/asm-mips/mipsregs.h
index 61a0dac1cee54d90a3e568b5e1b8a62ffbbc2d7d..be7e5c65ec1f38e91435844192af5a9637c2b337 100644
--- a/include/asm-mips/mipsregs.h
+++ b/include/asm-mips/mipsregs.h
@@ -7,8 +7,8 @@
  * Copyright (C) 2000 Silicon Graphics, Inc.
  * Modified for further R[236]000 support by Paul M. Antoine, 1996.
  * Kevin D. Kissell, kevink@mips.com and Carsten Langgaard, carstenl@mips.com
- * Copyright (C) 2000 MIPS Technologies, Inc.  All rights reserved.
- * Copyright (C) 2003  Maciej W. Rozycki
+ * Copyright (C) 2000, 07 MIPS Technologies, Inc.
+ * Copyright (C) 2003, 2004  Maciej W. Rozycki
  */
 #ifndef _ASM_MIPSREGS_H
 #define _ASM_MIPSREGS_H
@@ -28,6 +28,15 @@
 #define STR(x) __STR(x)
 #endif
 
+/*
+ *  Configure language
+ */
+#ifdef __ASSEMBLY__
+#define _ULCAST_
+#else
+#define _ULCAST_ (unsigned long)
+#endif
+
 /*
  * Coprocessor 0 register names
  */
@@ -55,12 +64,15 @@
 #define CP0_XCONTEXT $20
 #define CP0_FRAMEMASK $21
 #define CP0_DIAGNOSTIC $22
+#define CP0_DEBUG $23
+#define CP0_DEPC $24
 #define CP0_PERFORMANCE $25
 #define CP0_ECC $26
 #define CP0_CACHEERR $27
 #define CP0_TAGLO $28
 #define CP0_TAGHI $29
 #define CP0_ERROREPC $30
+#define CP0_DESAVE $31
 
 /*
  * R4640/R4650 cp0 register names.  These registers are listed
@@ -82,11 +94,27 @@
 #define CP0_S1_DERRADDR0  $26
 #define CP0_S1_DERRADDR1  $27
 #define CP0_S1_INTCONTROL $20
+
+/*
+ * Coprocessor 0 Set 2 register names
+ */
+#define CP0_S2_SRSCTL	$12	/* MIPSR2 */
+
+/*
+ * Coprocessor 0 Set 3 register names
+ */
+#define CP0_S3_SRSMAP	$12	/* MIPSR2 */
+
+/*
+ *  TX39 Series
+ */
+#define CP0_TX39_CACHE	$7
+
 /*
  * Coprocessor 1 (FPU) register names
  */
-#define CP1_REVISION   $0
-#define CP1_STATUS     $31
+#define CP1_REVISION	$0
+#define CP1_STATUS	$31
 
 /*
  * FPU Status Register Values
@@ -95,230 +123,113 @@
  * Status Register Values
  */
 
-#define FPU_CSR_FLUSH   0x01000000      /* flush denormalised results to 0 */
-#define FPU_CSR_COND    0x00800000      /* $fcc0 */
-#define FPU_CSR_COND0   0x00800000      /* $fcc0 */
-#define FPU_CSR_COND1   0x02000000      /* $fcc1 */
-#define FPU_CSR_COND2   0x04000000      /* $fcc2 */
-#define FPU_CSR_COND3   0x08000000      /* $fcc3 */
-#define FPU_CSR_COND4   0x10000000      /* $fcc4 */
-#define FPU_CSR_COND5   0x20000000      /* $fcc5 */
-#define FPU_CSR_COND6   0x40000000      /* $fcc6 */
-#define FPU_CSR_COND7   0x80000000      /* $fcc7 */
+#define FPU_CSR_FLUSH	0x01000000	/* flush denormalised results to 0 */
+#define FPU_CSR_COND	0x00800000	/* $fcc0 */
+#define FPU_CSR_COND0	0x00800000	/* $fcc0 */
+#define FPU_CSR_COND1	0x02000000	/* $fcc1 */
+#define FPU_CSR_COND2	0x04000000	/* $fcc2 */
+#define FPU_CSR_COND3	0x08000000	/* $fcc3 */
+#define FPU_CSR_COND4	0x10000000	/* $fcc4 */
+#define FPU_CSR_COND5	0x20000000	/* $fcc5 */
+#define FPU_CSR_COND6	0x40000000	/* $fcc6 */
+#define FPU_CSR_COND7	0x80000000	/* $fcc7 */
 
 /*
  * X the exception cause indicator
  * E the exception enable
  * S the sticky/flag bit
-*/
-#define FPU_CSR_ALL_X 0x0003f000
-#define FPU_CSR_UNI_X   0x00020000
-#define FPU_CSR_INV_X   0x00010000
-#define FPU_CSR_DIV_X   0x00008000
-#define FPU_CSR_OVF_X   0x00004000
-#define FPU_CSR_UDF_X   0x00002000
-#define FPU_CSR_INE_X   0x00001000
-
-#define FPU_CSR_ALL_E   0x00000f80
-#define FPU_CSR_INV_E   0x00000800
-#define FPU_CSR_DIV_E   0x00000400
-#define FPU_CSR_OVF_E   0x00000200
-#define FPU_CSR_UDF_E   0x00000100
-#define FPU_CSR_INE_E   0x00000080
-
-#define FPU_CSR_ALL_S   0x0000007c
-#define FPU_CSR_INV_S   0x00000040
-#define FPU_CSR_DIV_S   0x00000020
-#define FPU_CSR_OVF_S   0x00000010
-#define FPU_CSR_UDF_S   0x00000008
-#define FPU_CSR_INE_S   0x00000004
+ */
+#define FPU_CSR_ALL_X	0x0003f000
+#define FPU_CSR_UNI_X	0x00020000
+#define FPU_CSR_INV_X	0x00010000
+#define FPU_CSR_DIV_X	0x00008000
+#define FPU_CSR_OVF_X	0x00004000
+#define FPU_CSR_UDF_X	0x00002000
+#define FPU_CSR_INE_X	0x00001000
 
-/* rounding mode */
-#define FPU_CSR_RN      0x0     /* nearest */
-#define FPU_CSR_RZ      0x1     /* towards zero */
-#define FPU_CSR_RU      0x2     /* towards +Infinity */
-#define FPU_CSR_RD      0x3     /* towards -Infinity */
+#define FPU_CSR_ALL_E	0x00000f80
+#define FPU_CSR_INV_E	0x00000800
+#define FPU_CSR_DIV_E	0x00000400
+#define FPU_CSR_OVF_E	0x00000200
+#define FPU_CSR_UDF_E	0x00000100
+#define FPU_CSR_INE_E	0x00000080
 
+#define FPU_CSR_ALL_S	0x0000007c
+#define FPU_CSR_INV_S	0x00000040
+#define FPU_CSR_DIV_S	0x00000020
+#define FPU_CSR_OVF_S	0x00000010
+#define FPU_CSR_UDF_S	0x00000008
+#define FPU_CSR_INE_S	0x00000004
+
+/* rounding mode */
+#define FPU_CSR_RN	0x0	/* nearest */
+#define FPU_CSR_RZ	0x1	/* towards zero */
+#define FPU_CSR_RU	0x2	/* towards +Infinity */
+#define FPU_CSR_RD	0x3	/* towards -Infinity */
 
 /*
  * Values for PageMask register
  */
-#include <linux/config.h>
 #ifdef CONFIG_CPU_VR41XX
-#define PM_1K   0x00000000
-#define PM_4K   0x00001800
-#define PM_16K  0x00007800
-#define PM_64K  0x0001f800
-#define PM_256K 0x0007f800
-#else
-#define PM_4K   0x00000000
-#define PM_16K  0x00006000
-#define PM_64K  0x0001e000
-#define PM_256K 0x0007e000
-#define PM_1M   0x001fe000
-#define PM_4M   0x007fe000
-#define PM_16M  0x01ffe000
-#endif
 
-/*
- * Values used for computation of new tlb entries
- */
-#define PL_4K   12
-#define PL_16K  14
-#define PL_64K  16
-#define PL_256K 18
-#define PL_1M   20
-#define PL_4M   22
-#define PL_16M  24
+/* Why doesn't stupidity hurt ... */
 
-/*
- * Macros to access the system control coprocessor
- */
-#define read_32bit_cp0_register(source)                         \
-({ int __res;                                                   \
-	__asm__ __volatile__(                                   \
-	".set\tpush\n\t"					\
-	".set\treorder\n\t"					\
-	"mfc0\t%0,"STR(source)"\n\t"                            \
-	".set\tpop"						\
-	: "=r" (__res));                                        \
-	__res;})
+#define PM_1K		0x00000000
+#define PM_4K		0x00001800
+#define PM_16K		0x00007800
+#define PM_64K		0x0001f800
+#define PM_256K		0x0007f800
 
-#define read_32bit_cp0_set1_register(source)                    \
-({ int __res;                                                   \
-	__asm__ __volatile__(                                   \
-	".set\tpush\n\t"					\
-	".set\treorder\n\t"					\
-	"cfc0\t%0,"STR(source)"\n\t"                            \
-	".set\tpop"						\
-	: "=r" (__res));                                        \
-	__res;})
+#else
 
-/*
- * For now use this only with interrupts disabled!
- */
-#define read_64bit_cp0_register(source)                         \
-({ int __res;                                                   \
-	__asm__ __volatile__(                                   \
-	".set\tmips3\n\t"                                       \
-	"dmfc0\t%0,"STR(source)"\n\t"                           \
-	".set\tmips0"                                           \
-	: "=r" (__res));                                        \
-	__res;})
+#define PM_4K		0x00000000
+#define PM_16K		0x00006000
+#define PM_64K		0x0001e000
+#define PM_256K		0x0007e000
+#define PM_1M		0x001fe000
+#define PM_4M		0x007fe000
+#define PM_16M		0x01ffe000
+#define PM_64M		0x07ffe000
+#define PM_256M		0x1fffe000
 
-#define write_32bit_cp0_register(register,value)                \
-	__asm__ __volatile__(                                   \
-	"mtc0\t%0,"STR(register)"\n\t"				\
-	"nop"							\
-	: : "r" (value));
-
-#define write_32bit_cp0_set1_register(register,value)           \
-	__asm__ __volatile__(                                   \
-	"ctc0\t%0,"STR(register)"\n\t"				\
-	"nop"							\
-	: : "r" (value));
-
-#define write_64bit_cp0_register(register,value)                \
-	__asm__ __volatile__(                                   \
-	".set\tmips3\n\t"                                       \
-	"dmtc0\t%0,"STR(register)"\n\t"                         \
-	".set\tmips0"                                           \
-	: : "r" (value))
-
-/*
- * This should be changed when we get a compiler that support the MIPS32 ISA.
- */
-#define read_mips32_cp0_config1()                               \
-({ int __res;                                                   \
-	__asm__ __volatile__(                                   \
-	".set\tnoreorder\n\t"                                   \
-	".set\tnoat\n\t"                                        \
-	".word\t0x40018001\n\t"                                 \
-	"move\t%0,$1\n\t"                                       \
-	".set\tat\n\t"                                          \
-	".set\treorder"                                         \
-	:"=r" (__res));                                         \
-	__res;})
+#endif
 
-#define tlb_write_indexed()                                     \
-	__asm__ __volatile__(                                   \
-		".set noreorder\n\t"                            \
-		"tlbwi\n\t"                                     \
-".set reorder")
+/*
+ * Values used for computation of new tlb entries
+ */
+#define PL_4K		12
+#define PL_16K		14
+#define PL_64K		16
+#define PL_256K		18
+#define PL_1M		20
+#define PL_4M		22
+#define PL_16M		24
+#define PL_64M		26
+#define PL_256M		28
 
 /*
  * R4x00 interrupt enable / cause bits
  */
-#define IE_SW0          (1<< 8)
-#define IE_SW1          (1<< 9)
-#define IE_IRQ0         (1<<10)
-#define IE_IRQ1         (1<<11)
-#define IE_IRQ2         (1<<12)
-#define IE_IRQ3         (1<<13)
-#define IE_IRQ4         (1<<14)
-#define IE_IRQ5         (1<<15)
+#define IE_SW0		(_ULCAST_(1) <<  8)
+#define IE_SW1		(_ULCAST_(1) <<  9)
+#define IE_IRQ0		(_ULCAST_(1) << 10)
+#define IE_IRQ1		(_ULCAST_(1) << 11)
+#define IE_IRQ2		(_ULCAST_(1) << 12)
+#define IE_IRQ3		(_ULCAST_(1) << 13)
+#define IE_IRQ4		(_ULCAST_(1) << 14)
+#define IE_IRQ5		(_ULCAST_(1) << 15)
 
 /*
  * R4x00 interrupt cause bits
  */
-#define C_SW0           (1<< 8)
-#define C_SW1           (1<< 9)
-#define C_IRQ0          (1<<10)
-#define C_IRQ1          (1<<11)
-#define C_IRQ2          (1<<12)
-#define C_IRQ3          (1<<13)
-#define C_IRQ4          (1<<14)
-#define C_IRQ5          (1<<15)
-
-#ifndef _LANGUAGE_ASSEMBLY
-/*
- * Manipulate the status register.
- * Mostly used to access the interrupt bits.
- */
-#define __BUILD_SET_CP0(name,register)                          \
-extern __inline__ unsigned int                                  \
-set_cp0_##name(unsigned int set)				\
-{                                                               \
-	unsigned int res;                                       \
-								\
-	res = read_32bit_cp0_register(register);                \
-	res |= set;						\
-	write_32bit_cp0_register(register, res);		\
-								\
-	return res;                                             \
-}								\
-								\
-extern __inline__ unsigned int                                  \
-clear_cp0_##name(unsigned int clear)				\
-{                                                               \
-	unsigned int res;                                       \
-								\
-	res = read_32bit_cp0_register(register);                \
-	res &= ~clear;						\
-	write_32bit_cp0_register(register, res);		\
-								\
-	return res;                                             \
-}								\
-								\
-extern __inline__ unsigned int                                  \
-change_cp0_##name(unsigned int change, unsigned int new)	\
-{                                                               \
-	unsigned int res;                                       \
-								\
-	res = read_32bit_cp0_register(register);                \
-	res &= ~change;                                         \
-	res |= (new & change);                                  \
-	if(change)                                              \
-		write_32bit_cp0_register(register, res);        \
-								\
-	return res;                                             \
-}
-
-__BUILD_SET_CP0(status,CP0_STATUS)
-__BUILD_SET_CP0(cause,CP0_CAUSE)
-__BUILD_SET_CP0(config,CP0_CONFIG)
-
-#endif /* defined (_LANGUAGE_ASSEMBLY) */
+#define C_SW0		(_ULCAST_(1) <<  8)
+#define C_SW1		(_ULCAST_(1) <<  9)
+#define C_IRQ0		(_ULCAST_(1) << 10)
+#define C_IRQ1		(_ULCAST_(1) << 11)
+#define C_IRQ2		(_ULCAST_(1) << 12)
+#define C_IRQ3		(_ULCAST_(1) << 13)
+#define C_IRQ4		(_ULCAST_(1) << 14)
+#define C_IRQ5		(_ULCAST_(1) << 15)
 
 /*
  * Bitfields in the R4xx0 cp0 status register
@@ -336,10 +247,17 @@ __BUILD_SET_CP0(config,CP0_CONFIG)
 #define ST0_DE			0x00010000
 #define ST0_CE			0x00020000
 
+/*
+ * Setting c0_status.co enables Hit_Writeback and Hit_Writeback_Invalidate
+ * cacheops in userspace.  This bit exists only on RM7000 and RM9000
+ * processors.
+ */
+#define ST0_CO			0x08000000
+
 /*
  * Bitfields in the R[23]000 cp0 status register.
  */
-#define ST0_IEC                 0x00000001
+#define ST0_IEC			0x00000001
 #define ST0_KUC			0x00000002
 #define ST0_IEP			0x00000004
 #define ST0_KUP			0x00000008
@@ -353,9 +271,14 @@ __BUILD_SET_CP0(config,CP0_CONFIG)
 /*
  * Bits specific to the R4640/R4650
  */
-#define ST0_UM                 (1   <<  4)
-#define ST0_IL                 (1   << 23)
-#define ST0_DL                 (1   << 24)
+#define ST0_UM			(_ULCAST_(1) <<  4)
+#define ST0_IL			(_ULCAST_(1) << 23)
+#define ST0_DL			(_ULCAST_(1) << 24)
+
+/*
+ * Enable the MIPS MDMX and DSP ASEs
+ */
+#define ST0_MX			0x01000000
 
 /*
  * Bitfields in the TX39 family CP0 Configuration Register 3
@@ -395,39 +318,40 @@ __BUILD_SET_CP0(config,CP0_CONFIG)
  */
 #define ST0_IM			0x0000ff00
 #define  STATUSB_IP0		8
-#define  STATUSF_IP0		(1   <<  8)
+#define  STATUSF_IP0		(_ULCAST_(1) <<  8)
 #define  STATUSB_IP1		9
-#define  STATUSF_IP1		(1   <<  9)
+#define  STATUSF_IP1		(_ULCAST_(1) <<  9)
 #define  STATUSB_IP2		10
-#define  STATUSF_IP2		(1   << 10)
+#define  STATUSF_IP2		(_ULCAST_(1) << 10)
 #define  STATUSB_IP3		11
-#define  STATUSF_IP3		(1   << 11)
+#define  STATUSF_IP3		(_ULCAST_(1) << 11)
 #define  STATUSB_IP4		12
-#define  STATUSF_IP4		(1   << 12)
+#define  STATUSF_IP4		(_ULCAST_(1) << 12)
 #define  STATUSB_IP5		13
-#define  STATUSF_IP5		(1   << 13)
+#define  STATUSF_IP5		(_ULCAST_(1) << 13)
 #define  STATUSB_IP6		14
-#define  STATUSF_IP6		(1   << 14)
+#define  STATUSF_IP6		(_ULCAST_(1) << 14)
 #define  STATUSB_IP7		15
-#define  STATUSF_IP7		(1   << 15)
+#define  STATUSF_IP7		(_ULCAST_(1) << 15)
 #define  STATUSB_IP8		0
-#define  STATUSF_IP8		(1   << 0)
+#define  STATUSF_IP8		(_ULCAST_(1) <<  0)
 #define  STATUSB_IP9		1
-#define  STATUSF_IP9		(1   << 1)
+#define  STATUSF_IP9		(_ULCAST_(1) <<  1)
 #define  STATUSB_IP10		2
-#define  STATUSF_IP10		(1   << 2)
+#define  STATUSF_IP10		(_ULCAST_(1) <<  2)
 #define  STATUSB_IP11		3
-#define  STATUSF_IP11		(1   << 3)
+#define  STATUSF_IP11		(_ULCAST_(1) <<  3)
 #define  STATUSB_IP12		4
-#define  STATUSF_IP12		(1   << 4)
+#define  STATUSF_IP12		(_ULCAST_(1) <<  4)
 #define  STATUSB_IP13		5
-#define  STATUSF_IP13		(1   << 5)
+#define  STATUSF_IP13		(_ULCAST_(1) <<  5)
 #define  STATUSB_IP14		6
-#define  STATUSF_IP14		(1   << 6)
+#define  STATUSF_IP14		(_ULCAST_(1) <<  6)
 #define  STATUSB_IP15		7
-#define  STATUSF_IP15		(1   << 7)
+#define  STATUSF_IP15		(_ULCAST_(1) <<  7)
 #define ST0_CH			0x00040000
 #define ST0_SR			0x00100000
+#define ST0_TS			0x00200000
 #define ST0_BEV			0x00400000
 #define ST0_RE			0x02000000
 #define ST0_FR			0x04000000
@@ -444,35 +368,36 @@ __BUILD_SET_CP0(config,CP0_CONFIG)
  * Refer to your MIPS R4xx0 manual, chapter 5 for explanation.
  */
 #define  CAUSEB_EXCCODE		2
-#define  CAUSEF_EXCCODE		(31  <<  2)
+#define  CAUSEF_EXCCODE		(_ULCAST_(31)  <<  2)
 #define  CAUSEB_IP		8
-#define  CAUSEF_IP		(255 <<  8)
+#define  CAUSEF_IP		(_ULCAST_(255) <<  8)
 #define  CAUSEB_IP0		8
-#define  CAUSEF_IP0		(1   <<  8)
+#define  CAUSEF_IP0		(_ULCAST_(1)   <<  8)
 #define  CAUSEB_IP1		9
-#define  CAUSEF_IP1		(1   <<  9)
+#define  CAUSEF_IP1		(_ULCAST_(1)   <<  9)
 #define  CAUSEB_IP2		10
-#define  CAUSEF_IP2		(1   << 10)
+#define  CAUSEF_IP2		(_ULCAST_(1)   << 10)
 #define  CAUSEB_IP3		11
-#define  CAUSEF_IP3		(1   << 11)
+#define  CAUSEF_IP3		(_ULCAST_(1)   << 11)
 #define  CAUSEB_IP4		12
-#define  CAUSEF_IP4		(1   << 12)
+#define  CAUSEF_IP4		(_ULCAST_(1)   << 12)
 #define  CAUSEB_IP5		13
-#define  CAUSEF_IP5		(1   << 13)
+#define  CAUSEF_IP5		(_ULCAST_(1)   << 13)
 #define  CAUSEB_IP6		14
-#define  CAUSEF_IP6		(1   << 14)
+#define  CAUSEF_IP6		(_ULCAST_(1)   << 14)
 #define  CAUSEB_IP7		15
-#define  CAUSEF_IP7		(1   << 15)
+#define  CAUSEF_IP7		(_ULCAST_(1)   << 15)
 #define  CAUSEB_IV		23
-#define  CAUSEF_IV		(1   << 23)
+#define  CAUSEF_IV		(_ULCAST_(1)   << 23)
 #define  CAUSEB_CE		28
-#define  CAUSEF_CE		(3   << 28)
+#define  CAUSEF_CE		(_ULCAST_(3)   << 28)
 #define  CAUSEB_BD		31
-#define  CAUSEF_BD		(1   << 31)
+#define  CAUSEF_BD		(_ULCAST_(1)   << 31)
 
 /*
- * Bits in the coprozessor 0 config register.
+ * Bits in the coprocessor 0 config register.
  */
+/* Generic bits.  */
 #define CONF_CM_CACHABLE_NO_WA		0
 #define CONF_CM_CACHABLE_WA		1
 #define CONF_CM_UNCACHED		2
@@ -482,66 +407,958 @@ __BUILD_SET_CP0(config,CP0_CONFIG)
 #define CONF_CM_CACHABLE_CUW		6
 #define CONF_CM_CACHABLE_ACCELERATED	7
 #define CONF_CM_CMASK			7
-#define CONF_DB				(1 <<  4)
-#define CONF_IB				(1 <<  5)
-#define CONF_SC				(1 << 17)
-#define CONF_AC                         (1 << 23)
-#define CONF_HALT                       (1 << 25)
+#define CONF_BE			(_ULCAST_(1) << 15)
+
+/* Bits common to various processors.  */
+#define CONF_CU			(_ULCAST_(1) <<  3)
+#define CONF_DB			(_ULCAST_(1) <<  4)
+#define CONF_IB			(_ULCAST_(1) <<  5)
+#define CONF_DC			(_ULCAST_(7) <<  6)
+#define CONF_IC			(_ULCAST_(7) <<  9)
+#define CONF_EB			(_ULCAST_(1) << 13)
+#define CONF_EM			(_ULCAST_(1) << 14)
+#define CONF_SM			(_ULCAST_(1) << 16)
+#define CONF_SC			(_ULCAST_(1) << 17)
+#define CONF_EW			(_ULCAST_(3) << 18)
+#define CONF_EP			(_ULCAST_(15)<< 24)
+#define CONF_EC			(_ULCAST_(7) << 28)
+#define CONF_CM			(_ULCAST_(1) << 31)
+
+/* Bits specific to the R4xx0.  */
+#define R4K_CONF_SW		(_ULCAST_(1) << 20)
+#define R4K_CONF_SS		(_ULCAST_(1) << 21)
+#define R4K_CONF_SB		(_ULCAST_(3) << 22)
+
+/* Bits specific to the R5000.  */
+#define R5K_CONF_SE		(_ULCAST_(1) << 12)
+#define R5K_CONF_SS		(_ULCAST_(3) << 20)
+
+/* Bits specific to the RM7000.  */
+#define RM7K_CONF_SE		(_ULCAST_(1) <<  3)
+#define RM7K_CONF_TE		(_ULCAST_(1) << 12)
+#define RM7K_CONF_CLK		(_ULCAST_(1) << 16)
+#define RM7K_CONF_TC		(_ULCAST_(1) << 17)
+#define RM7K_CONF_SI		(_ULCAST_(3) << 20)
+#define RM7K_CONF_SC		(_ULCAST_(1) << 31)
+
+/* Bits specific to the R10000.  */
+#define R10K_CONF_DN		(_ULCAST_(3) <<  3)
+#define R10K_CONF_CT		(_ULCAST_(1) <<  5)
+#define R10K_CONF_PE		(_ULCAST_(1) <<  6)
+#define R10K_CONF_PM		(_ULCAST_(3) <<  7)
+#define R10K_CONF_EC		(_ULCAST_(15)<<  9)
+#define R10K_CONF_SB		(_ULCAST_(1) << 13)
+#define R10K_CONF_SK		(_ULCAST_(1) << 14)
+#define R10K_CONF_SS		(_ULCAST_(7) << 16)
+#define R10K_CONF_SC		(_ULCAST_(7) << 19)
+#define R10K_CONF_DC		(_ULCAST_(7) << 26)
+#define R10K_CONF_IC		(_ULCAST_(7) << 29)
+
+/* Bits specific to the VR41xx.  */
+#define VR41_CONF_CS		(_ULCAST_(1) << 12)
+#define VR41_CONF_P4K		(_ULCAST_(1) << 13)
+#define VR41_CONF_BP		(_ULCAST_(1) << 16)
+#define VR41_CONF_M16		(_ULCAST_(1) << 20)
+#define VR41_CONF_AD		(_ULCAST_(1) << 23)
+
+/* Bits specific to the R30xx.  */
+#define R30XX_CONF_FDM		(_ULCAST_(1) << 19)
+#define R30XX_CONF_REV		(_ULCAST_(1) << 22)
+#define R30XX_CONF_AC		(_ULCAST_(1) << 23)
+#define R30XX_CONF_RF		(_ULCAST_(1) << 24)
+#define R30XX_CONF_HALT		(_ULCAST_(1) << 25)
+#define R30XX_CONF_FPINT	(_ULCAST_(7) << 26)
+#define R30XX_CONF_DBR		(_ULCAST_(1) << 29)
+#define R30XX_CONF_SB		(_ULCAST_(1) << 30)
+#define R30XX_CONF_LOCK		(_ULCAST_(1) << 31)
+
+/* Bits specific to the TX49.  */
+#define TX49_CONF_DC		(_ULCAST_(1) << 16)
+#define TX49_CONF_IC		(_ULCAST_(1) << 17)  /* conflict with CONF_SC */
+#define TX49_CONF_HALT		(_ULCAST_(1) << 18)
+#define TX49_CONF_CWFON		(_ULCAST_(1) << 27)
+
+/* Bits specific to the MIPS32/64 PRA.  */
+#define MIPS_CONF_MT		(_ULCAST_(7) <<  7)
+#define MIPS_CONF_AR		(_ULCAST_(7) << 10)
+#define MIPS_CONF_AT		(_ULCAST_(3) << 13)
+#define MIPS_CONF_M		(_ULCAST_(1) << 31)
+
+/*
+ * Bits in the MIPS32/64 PRA coprocessor 0 config registers 1 and above.
+ */
+#define MIPS_CONF1_FP		(_ULCAST_(1) <<  0)
+#define MIPS_CONF1_EP		(_ULCAST_(1) <<  1)
+#define MIPS_CONF1_CA		(_ULCAST_(1) <<  2)
+#define MIPS_CONF1_WR		(_ULCAST_(1) <<  3)
+#define MIPS_CONF1_PC		(_ULCAST_(1) <<  4)
+#define MIPS_CONF1_MD		(_ULCAST_(1) <<  5)
+#define MIPS_CONF1_C2		(_ULCAST_(1) <<  6)
+#define MIPS_CONF1_DA		(_ULCAST_(7) <<  7)
+#define MIPS_CONF1_DL		(_ULCAST_(7) << 10)
+#define MIPS_CONF1_DS		(_ULCAST_(7) << 13)
+#define MIPS_CONF1_IA		(_ULCAST_(7) << 16)
+#define MIPS_CONF1_IL		(_ULCAST_(7) << 19)
+#define MIPS_CONF1_IS		(_ULCAST_(7) << 22)
+#define MIPS_CONF1_TLBS		(_ULCAST_(63)<< 25)
+
+#define MIPS_CONF2_SA		(_ULCAST_(15)<<  0)
+#define MIPS_CONF2_SL		(_ULCAST_(15)<<  4)
+#define MIPS_CONF2_SS		(_ULCAST_(15)<<  8)
+#define MIPS_CONF2_SU		(_ULCAST_(15)<< 12)
+#define MIPS_CONF2_TA		(_ULCAST_(15)<< 16)
+#define MIPS_CONF2_TL		(_ULCAST_(15)<< 20)
+#define MIPS_CONF2_TS		(_ULCAST_(15)<< 24)
+#define MIPS_CONF2_TU		(_ULCAST_(7) << 28)
+
+#define MIPS_CONF3_TL		(_ULCAST_(1) <<  0)
+#define MIPS_CONF3_SM		(_ULCAST_(1) <<  1)
+#define MIPS_CONF3_MT		(_ULCAST_(1) <<  2)
+#define MIPS_CONF3_SP		(_ULCAST_(1) <<  4)
+#define MIPS_CONF3_VINT		(_ULCAST_(1) <<  5)
+#define MIPS_CONF3_VEIC		(_ULCAST_(1) <<  6)
+#define MIPS_CONF3_LPA		(_ULCAST_(1) <<  7)
+#define MIPS_CONF3_DSP		(_ULCAST_(1) << 10)
+#define MIPS_CONF3_ULRI		(_ULCAST_(1) << 13)
+
+#define MIPS_CONF7_WII		(_ULCAST_(1) << 31)
+
+#define MIPS_CONF7_RPS		(_ULCAST_(1) << 2)
+
+/*
+ * Bits in the MIPS32/64 coprocessor 1 (FPU) revision register.
+ */
+#define MIPS_FPIR_S		(_ULCAST_(1) << 16)
+#define MIPS_FPIR_D		(_ULCAST_(1) << 17)
+#define MIPS_FPIR_PS		(_ULCAST_(1) << 18)
+#define MIPS_FPIR_3D		(_ULCAST_(1) << 19)
+#define MIPS_FPIR_W		(_ULCAST_(1) << 20)
+#define MIPS_FPIR_L		(_ULCAST_(1) << 21)
+#define MIPS_FPIR_F64		(_ULCAST_(1) << 22)
+
+#ifndef __ASSEMBLY__
+
+/*
+ * Functions to access the R10000 performance counters.  These are basically
+ * mfc0 and mtc0 instructions from and to coprocessor register with a 5-bit
+ * performance counter number encoded into bits 1 ... 5 of the instruction.
+ * Only performance counters 0 to 1 actually exist, so for a non-R10000 aware
+ * disassembler these will look like an access to sel 0 or 1.
+ */
+#define read_r10k_perf_cntr(counter)				\
+({								\
+	unsigned int __res;					\
+	__asm__ __volatile__(					\
+	"mfpc\t%0, %1"						\
+	: "=r" (__res)						\
+	: "i" (counter));					\
+								\
+	__res;							\
+})
+
+#define write_r10k_perf_cntr(counter,val)			\
+do {								\
+	__asm__ __volatile__(					\
+	"mtpc\t%0, %1"						\
+	:							\
+	: "r" (val), "i" (counter));				\
+} while (0)
+
+#define read_r10k_perf_event(counter)				\
+({								\
+	unsigned int __res;					\
+	__asm__ __volatile__(					\
+	"mfps\t%0, %1"						\
+	: "=r" (__res)						\
+	: "i" (counter));					\
+								\
+	__res;							\
+})
+
+#define write_r10k_perf_cntl(counter,val)			\
+do {								\
+	__asm__ __volatile__(					\
+	"mtps\t%0, %1"						\
+	:							\
+	: "r" (val), "i" (counter));				\
+} while (0)
+
+/*
+ * Macros to access the system control coprocessor
+ */
+
+#define __read_32bit_c0_register(source, sel)				\
+({ int __res;								\
+	if (sel == 0)							\
+		__asm__ __volatile__(					\
+			"mfc0\t%0, " #source "\n\t"			\
+			: "=r" (__res));				\
+	else								\
+		__asm__ __volatile__(					\
+			".set\tmips32\n\t"				\
+			"mfc0\t%0, " #source ", " #sel "\n\t"		\
+			".set\tmips0\n\t"				\
+			: "=r" (__res));				\
+	__res;								\
+})
+
+#define __read_64bit_c0_register(source, sel)				\
+({ unsigned long long __res;						\
+	if (sizeof(unsigned long) == 4)					\
+		__res = __read_64bit_c0_split(source, sel);		\
+	else if (sel == 0)						\
+		__asm__ __volatile__(					\
+			".set\tmips3\n\t"				\
+			"dmfc0\t%0, " #source "\n\t"			\
+			".set\tmips0"					\
+			: "=r" (__res));				\
+	else								\
+		__asm__ __volatile__(					\
+			".set\tmips64\n\t"				\
+			"dmfc0\t%0, " #source ", " #sel "\n\t"		\
+			".set\tmips0"					\
+			: "=r" (__res));				\
+	__res;								\
+})
+
+#define __write_32bit_c0_register(register, sel, value)			\
+do {									\
+	if (sel == 0)							\
+		__asm__ __volatile__(					\
+			"mtc0\t%z0, " #register "\n\t"			\
+			: : "Jr" ((unsigned int)(value)));		\
+	else								\
+		__asm__ __volatile__(					\
+			".set\tmips32\n\t"				\
+			"mtc0\t%z0, " #register ", " #sel "\n\t"	\
+			".set\tmips0"					\
+			: : "Jr" ((unsigned int)(value)));		\
+} while (0)
+
+#define __write_64bit_c0_register(register, sel, value)			\
+do {									\
+	if (sizeof(unsigned long) == 4)					\
+		__write_64bit_c0_split(register, sel, value);		\
+	else if (sel == 0)						\
+		__asm__ __volatile__(					\
+			".set\tmips3\n\t"				\
+			"dmtc0\t%z0, " #register "\n\t"			\
+			".set\tmips0"					\
+			: : "Jr" (value));				\
+	else								\
+		__asm__ __volatile__(					\
+			".set\tmips64\n\t"				\
+			"dmtc0\t%z0, " #register ", " #sel "\n\t"	\
+			".set\tmips0"					\
+			: : "Jr" (value));				\
+} while (0)
+
+#define __read_ulong_c0_register(reg, sel)				\
+	((sizeof(unsigned long) == 4) ?					\
+	(unsigned long) __read_32bit_c0_register(reg, sel) :		\
+	(unsigned long) __read_64bit_c0_register(reg, sel))
+
+#define __write_ulong_c0_register(reg, sel, val)			\
+do {									\
+	if (sizeof(unsigned long) == 4)					\
+		__write_32bit_c0_register(reg, sel, val);		\
+	else								\
+		__write_64bit_c0_register(reg, sel, val);		\
+} while (0)
+
+/*
+ * On RM7000/RM9000 these are uses to access cop0 set 1 registers
+ */
+#define __read_32bit_c0_ctrl_register(source)				\
+({ int __res;								\
+	__asm__ __volatile__(						\
+		"cfc0\t%0, " #source "\n\t"				\
+		: "=r" (__res));					\
+	__res;								\
+})
+
+#define __write_32bit_c0_ctrl_register(register, value)			\
+do {									\
+	__asm__ __volatile__(						\
+		"ctc0\t%z0, " #register "\n\t"				\
+		: : "Jr" ((unsigned int)(value)));			\
+} while (0)
+
+/*
+ * These versions are only needed for systems with more than 38 bits of
+ * physical address space running the 32-bit kernel.  That's none atm :-)
+ */
+#define __read_64bit_c0_split(source, sel)				\
+({									\
+	unsigned long long __val;					\
+	unsigned long __flags;						\
+									\
+	local_irq_save(__flags);					\
+	if (sel == 0)							\
+		__asm__ __volatile__(					\
+			".set\tmips64\n\t"				\
+			"dmfc0\t%M0, " #source "\n\t"			\
+			"dsll\t%L0, %M0, 32\n\t"			\
+			"dsrl\t%M0, %M0, 32\n\t"			\
+			"dsrl\t%L0, %L0, 32\n\t"			\
+			".set\tmips0"					\
+			: "=r" (__val));				\
+	else								\
+		__asm__ __volatile__(					\
+			".set\tmips64\n\t"				\
+			"dmfc0\t%M0, " #source ", " #sel "\n\t"		\
+			"dsll\t%L0, %M0, 32\n\t"			\
+			"dsrl\t%M0, %M0, 32\n\t"			\
+			"dsrl\t%L0, %L0, 32\n\t"			\
+			".set\tmips0"					\
+			: "=r" (__val));				\
+	local_irq_restore(__flags);					\
+									\
+	__val;								\
+})
+
+#define __write_64bit_c0_split(source, sel, val)			\
+do {									\
+	unsigned long __flags;						\
+									\
+	local_irq_save(__flags);					\
+	if (sel == 0)							\
+		__asm__ __volatile__(					\
+			".set\tmips64\n\t"				\
+			"dsll\t%L0, %L0, 32\n\t"			\
+			"dsrl\t%L0, %L0, 32\n\t"			\
+			"dsll\t%M0, %M0, 32\n\t"			\
+			"or\t%L0, %L0, %M0\n\t"				\
+			"dmtc0\t%L0, " #source "\n\t"			\
+			".set\tmips0"					\
+			: : "r" (val));					\
+	else								\
+		__asm__ __volatile__(					\
+			".set\tmips64\n\t"				\
+			"dsll\t%L0, %L0, 32\n\t"			\
+			"dsrl\t%L0, %L0, 32\n\t"			\
+			"dsll\t%M0, %M0, 32\n\t"			\
+			"or\t%L0, %L0, %M0\n\t"				\
+			"dmtc0\t%L0, " #source ", " #sel "\n\t"		\
+			".set\tmips0"					\
+			: : "r" (val));					\
+	local_irq_restore(__flags);					\
+} while (0)
+
+#define read_c0_index()		__read_32bit_c0_register($0, 0)
+#define write_c0_index(val)	__write_32bit_c0_register($0, 0, val)
+
+#define read_c0_entrylo0()	__read_ulong_c0_register($2, 0)
+#define write_c0_entrylo0(val)	__write_ulong_c0_register($2, 0, val)
+
+#define read_c0_entrylo1()	__read_ulong_c0_register($3, 0)
+#define write_c0_entrylo1(val)	__write_ulong_c0_register($3, 0, val)
+
+#define read_c0_conf()		__read_32bit_c0_register($3, 0)
+#define write_c0_conf(val)	__write_32bit_c0_register($3, 0, val)
+
+#define read_c0_context()	__read_ulong_c0_register($4, 0)
+#define write_c0_context(val)	__write_ulong_c0_register($4, 0, val)
+
+#define read_c0_userlocal()	__read_ulong_c0_register($4, 2)
+#define write_c0_userlocal(val)	__write_ulong_c0_register($4, 2, val)
+
+#define read_c0_pagemask()	__read_32bit_c0_register($5, 0)
+#define write_c0_pagemask(val)	__write_32bit_c0_register($5, 0, val)
+
+#define read_c0_wired()		__read_32bit_c0_register($6, 0)
+#define write_c0_wired(val)	__write_32bit_c0_register($6, 0, val)
+
+#define read_c0_info()		__read_32bit_c0_register($7, 0)
+
+#define read_c0_cache()		__read_32bit_c0_register($7, 0)	/* TX39xx */
+#define write_c0_cache(val)	__write_32bit_c0_register($7, 0, val)
+
+#define read_c0_badvaddr()	__read_ulong_c0_register($8, 0)
+#define write_c0_badvaddr(val)	__write_ulong_c0_register($8, 0, val)
+
+#define read_c0_count()		__read_32bit_c0_register($9, 0)
+#define write_c0_count(val)	__write_32bit_c0_register($9, 0, val)
+
+#define read_c0_count2()	__read_32bit_c0_register($9, 6) /* pnx8550 */
+#define write_c0_count2(val)	__write_32bit_c0_register($9, 6, val)
+
+#define read_c0_count3()	__read_32bit_c0_register($9, 7) /* pnx8550 */
+#define write_c0_count3(val)	__write_32bit_c0_register($9, 7, val)
+
+#define read_c0_entryhi()	__read_ulong_c0_register($10, 0)
+#define write_c0_entryhi(val)	__write_ulong_c0_register($10, 0, val)
+
+#define read_c0_compare()	__read_32bit_c0_register($11, 0)
+#define write_c0_compare(val)	__write_32bit_c0_register($11, 0, val)
+
+#define read_c0_compare2()	__read_32bit_c0_register($11, 6) /* pnx8550 */
+#define write_c0_compare2(val)	__write_32bit_c0_register($11, 6, val)
+
+#define read_c0_compare3()	__read_32bit_c0_register($11, 7) /* pnx8550 */
+#define write_c0_compare3(val)	__write_32bit_c0_register($11, 7, val)
+
+#define read_c0_status()	__read_32bit_c0_register($12, 0)
+#ifdef CONFIG_MIPS_MT_SMTC
+#define write_c0_status(val)						\
+do {									\
+	__write_32bit_c0_register($12, 0, val);				\
+	__ehb();							\
+} while (0)
+#else
+/*
+ * Legacy non-SMTC code, which may be hazardous
+ * but which might not support EHB
+ */
+#define write_c0_status(val)	__write_32bit_c0_register($12, 0, val)
+#endif /* CONFIG_MIPS_MT_SMTC */
+
+#define read_c0_cause()		__read_32bit_c0_register($13, 0)
+#define write_c0_cause(val)	__write_32bit_c0_register($13, 0, val)
+
+#define read_c0_epc()		__read_ulong_c0_register($14, 0)
+#define write_c0_epc(val)	__write_ulong_c0_register($14, 0, val)
+
+#define read_c0_prid()		__read_32bit_c0_register($15, 0)
+
+#define read_c0_config()	__read_32bit_c0_register($16, 0)
+#define read_c0_config1()	__read_32bit_c0_register($16, 1)
+#define read_c0_config2()	__read_32bit_c0_register($16, 2)
+#define read_c0_config3()	__read_32bit_c0_register($16, 3)
+#define read_c0_config4()	__read_32bit_c0_register($16, 4)
+#define read_c0_config5()	__read_32bit_c0_register($16, 5)
+#define read_c0_config6()	__read_32bit_c0_register($16, 6)
+#define read_c0_config7()	__read_32bit_c0_register($16, 7)
+#define write_c0_config(val)	__write_32bit_c0_register($16, 0, val)
+#define write_c0_config1(val)	__write_32bit_c0_register($16, 1, val)
+#define write_c0_config2(val)	__write_32bit_c0_register($16, 2, val)
+#define write_c0_config3(val)	__write_32bit_c0_register($16, 3, val)
+#define write_c0_config4(val)	__write_32bit_c0_register($16, 4, val)
+#define write_c0_config5(val)	__write_32bit_c0_register($16, 5, val)
+#define write_c0_config6(val)	__write_32bit_c0_register($16, 6, val)
+#define write_c0_config7(val)	__write_32bit_c0_register($16, 7, val)
+
+/*
+ * The WatchLo register.  There may be upto 8 of them.
+ */
+#define read_c0_watchlo0()	__read_ulong_c0_register($18, 0)
+#define read_c0_watchlo1()	__read_ulong_c0_register($18, 1)
+#define read_c0_watchlo2()	__read_ulong_c0_register($18, 2)
+#define read_c0_watchlo3()	__read_ulong_c0_register($18, 3)
+#define read_c0_watchlo4()	__read_ulong_c0_register($18, 4)
+#define read_c0_watchlo5()	__read_ulong_c0_register($18, 5)
+#define read_c0_watchlo6()	__read_ulong_c0_register($18, 6)
+#define read_c0_watchlo7()	__read_ulong_c0_register($18, 7)
+#define write_c0_watchlo0(val)	__write_ulong_c0_register($18, 0, val)
+#define write_c0_watchlo1(val)	__write_ulong_c0_register($18, 1, val)
+#define write_c0_watchlo2(val)	__write_ulong_c0_register($18, 2, val)
+#define write_c0_watchlo3(val)	__write_ulong_c0_register($18, 3, val)
+#define write_c0_watchlo4(val)	__write_ulong_c0_register($18, 4, val)
+#define write_c0_watchlo5(val)	__write_ulong_c0_register($18, 5, val)
+#define write_c0_watchlo6(val)	__write_ulong_c0_register($18, 6, val)
+#define write_c0_watchlo7(val)	__write_ulong_c0_register($18, 7, val)
+
+/*
+ * The WatchHi register.  There may be upto 8 of them.
+ */
+#define read_c0_watchhi0()	__read_32bit_c0_register($19, 0)
+#define read_c0_watchhi1()	__read_32bit_c0_register($19, 1)
+#define read_c0_watchhi2()	__read_32bit_c0_register($19, 2)
+#define read_c0_watchhi3()	__read_32bit_c0_register($19, 3)
+#define read_c0_watchhi4()	__read_32bit_c0_register($19, 4)
+#define read_c0_watchhi5()	__read_32bit_c0_register($19, 5)
+#define read_c0_watchhi6()	__read_32bit_c0_register($19, 6)
+#define read_c0_watchhi7()	__read_32bit_c0_register($19, 7)
+
+#define write_c0_watchhi0(val)	__write_32bit_c0_register($19, 0, val)
+#define write_c0_watchhi1(val)	__write_32bit_c0_register($19, 1, val)
+#define write_c0_watchhi2(val)	__write_32bit_c0_register($19, 2, val)
+#define write_c0_watchhi3(val)	__write_32bit_c0_register($19, 3, val)
+#define write_c0_watchhi4(val)	__write_32bit_c0_register($19, 4, val)
+#define write_c0_watchhi5(val)	__write_32bit_c0_register($19, 5, val)
+#define write_c0_watchhi6(val)	__write_32bit_c0_register($19, 6, val)
+#define write_c0_watchhi7(val)	__write_32bit_c0_register($19, 7, val)
+
+#define read_c0_xcontext()	__read_ulong_c0_register($20, 0)
+#define write_c0_xcontext(val)	__write_ulong_c0_register($20, 0, val)
+
+#define read_c0_intcontrol()	__read_32bit_c0_ctrl_register($20)
+#define write_c0_intcontrol(val) __write_32bit_c0_ctrl_register($20, val)
+
+#define read_c0_framemask()	__read_32bit_c0_register($21, 0)
+#define write_c0_framemask(val)	__write_32bit_c0_register($21, 0, val)
+
+/* RM9000 PerfControl performance counter control register */
+#define read_c0_perfcontrol()	__read_32bit_c0_register($22, 0)
+#define write_c0_perfcontrol(val) __write_32bit_c0_register($22, 0, val)
+
+#define read_c0_diag()		__read_32bit_c0_register($22, 0)
+#define write_c0_diag(val)	__write_32bit_c0_register($22, 0, val)
+
+#define read_c0_diag1()		__read_32bit_c0_register($22, 1)
+#define write_c0_diag1(val)	__write_32bit_c0_register($22, 1, val)
+
+#define read_c0_diag2()		__read_32bit_c0_register($22, 2)
+#define write_c0_diag2(val)	__write_32bit_c0_register($22, 2, val)
+
+#define read_c0_diag3()		__read_32bit_c0_register($22, 3)
+#define write_c0_diag3(val)	__write_32bit_c0_register($22, 3, val)
+
+#define read_c0_diag4()		__read_32bit_c0_register($22, 4)
+#define write_c0_diag4(val)	__write_32bit_c0_register($22, 4, val)
+
+#define read_c0_diag5()		__read_32bit_c0_register($22, 5)
+#define write_c0_diag5(val)	__write_32bit_c0_register($22, 5, val)
+
+#define read_c0_debug()		__read_32bit_c0_register($23, 0)
+#define write_c0_debug(val)	__write_32bit_c0_register($23, 0, val)
+
+#define read_c0_depc()		__read_ulong_c0_register($24, 0)
+#define write_c0_depc(val)	__write_ulong_c0_register($24, 0, val)
+
+/*
+ * MIPS32 / MIPS64 performance counters
+ */
+#define read_c0_perfctrl0()	__read_32bit_c0_register($25, 0)
+#define write_c0_perfctrl0(val)	__write_32bit_c0_register($25, 0, val)
+#define read_c0_perfcntr0()	__read_32bit_c0_register($25, 1)
+#define write_c0_perfcntr0(val)	__write_32bit_c0_register($25, 1, val)
+#define read_c0_perfctrl1()	__read_32bit_c0_register($25, 2)
+#define write_c0_perfctrl1(val)	__write_32bit_c0_register($25, 2, val)
+#define read_c0_perfcntr1()	__read_32bit_c0_register($25, 3)
+#define write_c0_perfcntr1(val)	__write_32bit_c0_register($25, 3, val)
+#define read_c0_perfctrl2()	__read_32bit_c0_register($25, 4)
+#define write_c0_perfctrl2(val)	__write_32bit_c0_register($25, 4, val)
+#define read_c0_perfcntr2()	__read_32bit_c0_register($25, 5)
+#define write_c0_perfcntr2(val)	__write_32bit_c0_register($25, 5, val)
+#define read_c0_perfctrl3()	__read_32bit_c0_register($25, 6)
+#define write_c0_perfctrl3(val)	__write_32bit_c0_register($25, 6, val)
+#define read_c0_perfcntr3()	__read_32bit_c0_register($25, 7)
+#define write_c0_perfcntr3(val)	__write_32bit_c0_register($25, 7, val)
+
+/* RM9000 PerfCount performance counter register */
+#define read_c0_perfcount()	__read_64bit_c0_register($25, 0)
+#define write_c0_perfcount(val)	__write_64bit_c0_register($25, 0, val)
+
+#define read_c0_ecc()		__read_32bit_c0_register($26, 0)
+#define write_c0_ecc(val)	__write_32bit_c0_register($26, 0, val)
+
+#define read_c0_derraddr0()	__read_ulong_c0_register($26, 1)
+#define write_c0_derraddr0(val)	__write_ulong_c0_register($26, 1, val)
+
+#define read_c0_cacheerr()	__read_32bit_c0_register($27, 0)
+
+#define read_c0_derraddr1()	__read_ulong_c0_register($27, 1)
+#define write_c0_derraddr1(val)	__write_ulong_c0_register($27, 1, val)
+
+#define read_c0_taglo()		__read_32bit_c0_register($28, 0)
+#define write_c0_taglo(val)	__write_32bit_c0_register($28, 0, val)
+
+#define read_c0_dtaglo()	__read_32bit_c0_register($28, 2)
+#define write_c0_dtaglo(val)	__write_32bit_c0_register($28, 2, val)
+
+#define read_c0_taghi()		__read_32bit_c0_register($29, 0)
+#define write_c0_taghi(val)	__write_32bit_c0_register($29, 0, val)
+
+#define read_c0_errorepc()	__read_ulong_c0_register($30, 0)
+#define write_c0_errorepc(val)	__write_ulong_c0_register($30, 0, val)
+
+/* MIPSR2 */
+#define read_c0_hwrena()	__read_32bit_c0_register($7, 0)
+#define write_c0_hwrena(val)	__write_32bit_c0_register($7, 0, val)
+
+#define read_c0_intctl()	__read_32bit_c0_register($12, 1)
+#define write_c0_intctl(val)	__write_32bit_c0_register($12, 1, val)
+
+#define read_c0_srsctl()	__read_32bit_c0_register($12, 2)
+#define write_c0_srsctl(val)	__write_32bit_c0_register($12, 2, val)
+
+#define read_c0_srsmap()	__read_32bit_c0_register($12, 3)
+#define write_c0_srsmap(val)	__write_32bit_c0_register($12, 3, val)
+
+#define read_c0_ebase()		__read_32bit_c0_register($15, 1)
+#define write_c0_ebase(val)	__write_32bit_c0_register($15, 1, val)
 
 /*
- * R10000 performance counter definitions.
+ * Macros to access the floating point coprocessor control registers
+ */
+#define read_32bit_cp1_register(source)				\
+({ int __res;							\
+	__asm__ __volatile__(					\
+	".set\tpush\n\t"					\
+	".set\treorder\n\t"					\
+	"cfc1\t%0,"STR(source)"\n\t"				\
+	".set\tpop"						\
+	: "=r" (__res));					\
+	__res;})
+
+#define rddsp(mask)							\
+({									\
+	unsigned int __res;						\
+									\
+	__asm__ __volatile__(						\
+	"	.set	push				\n"		\
+	"	.set	noat				\n"		\
+	"	# rddsp $1, %x1				\n"		\
+	"	.word	0x7c000cb8 | (%x1 << 16)	\n"		\
+	"	move	%0, $1				\n"		\
+	"	.set	pop				\n"		\
+	: "=r" (__res)							\
+	: "i" (mask));							\
+	__res;								\
+})
+
+#define wrdsp(val, mask)						\
+do {									\
+	__asm__ __volatile__(						\
+	"	.set	push					\n"	\
+	"	.set	noat					\n"	\
+	"	move	$1, %0					\n"	\
+	"	# wrdsp $1, %x1					\n"	\
+	"	.word	0x7c2004f8 | (%x1 << 11)		\n"	\
+	"	.set	pop					\n"	\
+	:								\
+	: "r" (val), "i" (mask));					\
+} while (0)
+
+#define mfhi0()								\
+({									\
+	unsigned long __treg;						\
+									\
+	__asm__ __volatile__(						\
+	"	.set	push			\n"			\
+	"	.set	noat			\n"			\
+	"	# mfhi	%0, $ac0		\n"			\
+	"	.word	0x00000810		\n"			\
+	"	move	%0, $1			\n"			\
+	"	.set	pop			\n"			\
+	: "=r" (__treg));						\
+	__treg;								\
+})
+
+#define mfhi1()								\
+({									\
+	unsigned long __treg;						\
+									\
+	__asm__ __volatile__(						\
+	"	.set	push			\n"			\
+	"	.set	noat			\n"			\
+	"	# mfhi	%0, $ac1		\n"			\
+	"	.word	0x00200810		\n"			\
+	"	move	%0, $1			\n"			\
+	"	.set	pop			\n"			\
+	: "=r" (__treg));						\
+	__treg;								\
+})
+
+#define mfhi2()								\
+({									\
+	unsigned long __treg;						\
+									\
+	__asm__ __volatile__(						\
+	"	.set	push			\n"			\
+	"	.set	noat			\n"			\
+	"	# mfhi	%0, $ac2		\n"			\
+	"	.word	0x00400810		\n"			\
+	"	move	%0, $1			\n"			\
+	"	.set	pop			\n"			\
+	: "=r" (__treg));						\
+	__treg;								\
+})
+
+#define mfhi3()								\
+({									\
+	unsigned long __treg;						\
+									\
+	__asm__ __volatile__(						\
+	"	.set	push			\n"			\
+	"	.set	noat			\n"			\
+	"	# mfhi	%0, $ac3		\n"			\
+	"	.word	0x00600810		\n"			\
+	"	move	%0, $1			\n"			\
+	"	.set	pop			\n"			\
+	: "=r" (__treg));						\
+	__treg;								\
+})
+
+#define mflo0()								\
+({									\
+	unsigned long __treg;						\
+									\
+	__asm__ __volatile__(						\
+	"	.set	push			\n"			\
+	"	.set	noat			\n"			\
+	"	# mflo	%0, $ac0		\n"			\
+	"	.word	0x00000812		\n"			\
+	"	move	%0, $1			\n"			\
+	"	.set	pop			\n"			\
+	: "=r" (__treg));						\
+	__treg;								\
+})
+
+#define mflo1()								\
+({									\
+	unsigned long __treg;						\
+									\
+	__asm__ __volatile__(						\
+	"	.set	push			\n"			\
+	"	.set	noat			\n"			\
+	"	# mflo	%0, $ac1		\n"			\
+	"	.word	0x00200812		\n"			\
+	"	move	%0, $1			\n"			\
+	"	.set	pop			\n"			\
+	: "=r" (__treg));						\
+	__treg;								\
+})
+
+#define mflo2()								\
+({									\
+	unsigned long __treg;						\
+									\
+	__asm__ __volatile__(						\
+	"	.set	push			\n"			\
+	"	.set	noat			\n"			\
+	"	# mflo	%0, $ac2		\n"			\
+	"	.word	0x00400812		\n"			\
+	"	move	%0, $1			\n"			\
+	"	.set	pop			\n"			\
+	: "=r" (__treg));						\
+	__treg;								\
+})
+
+#define mflo3()								\
+({									\
+	unsigned long __treg;						\
+									\
+	__asm__ __volatile__(						\
+	"	.set	push			\n"			\
+	"	.set	noat			\n"			\
+	"	# mflo	%0, $ac3		\n"			\
+	"	.word	0x00600812		\n"			\
+	"	move	%0, $1			\n"			\
+	"	.set	pop			\n"			\
+	: "=r" (__treg));						\
+	__treg;								\
+})
+
+#define mthi0(x)							\
+do {									\
+	__asm__ __volatile__(						\
+	"	.set	push					\n"	\
+	"	.set	noat					\n"	\
+	"	move	$1, %0					\n"	\
+	"	# mthi	$1, $ac0				\n"	\
+	"	.word	0x00200011				\n"	\
+	"	.set	pop					\n"	\
+	:								\
+	: "r" (x));							\
+} while (0)
+
+#define mthi1(x)							\
+do {									\
+	__asm__ __volatile__(						\
+	"	.set	push					\n"	\
+	"	.set	noat					\n"	\
+	"	move	$1, %0					\n"	\
+	"	# mthi	$1, $ac1				\n"	\
+	"	.word	0x00200811				\n"	\
+	"	.set	pop					\n"	\
+	:								\
+	: "r" (x));							\
+} while (0)
+
+#define mthi2(x)							\
+do {									\
+	__asm__ __volatile__(						\
+	"	.set	push					\n"	\
+	"	.set	noat					\n"	\
+	"	move	$1, %0					\n"	\
+	"	# mthi	$1, $ac2				\n"	\
+	"	.word	0x00201011				\n"	\
+	"	.set	pop					\n"	\
+	:								\
+	: "r" (x));							\
+} while (0)
+
+#define mthi3(x)							\
+do {									\
+	__asm__ __volatile__(						\
+	"	.set	push					\n"	\
+	"	.set	noat					\n"	\
+	"	move	$1, %0					\n"	\
+	"	# mthi	$1, $ac3				\n"	\
+	"	.word	0x00201811				\n"	\
+	"	.set	pop					\n"	\
+	:								\
+	: "r" (x));							\
+} while (0)
+
+#define mtlo0(x)							\
+do {									\
+	__asm__ __volatile__(						\
+	"	.set	push					\n"	\
+	"	.set	noat					\n"	\
+	"	move	$1, %0					\n"	\
+	"	# mtlo	$1, $ac0				\n"	\
+	"	.word	0x00200013				\n"	\
+	"	.set	pop					\n"	\
+	:								\
+	: "r" (x));							\
+} while (0)
+
+#define mtlo1(x)							\
+do {									\
+	__asm__ __volatile__(						\
+	"	.set	push					\n"	\
+	"	.set	noat					\n"	\
+	"	move	$1, %0					\n"	\
+	"	# mtlo	$1, $ac1				\n"	\
+	"	.word	0x00200813				\n"	\
+	"	.set	pop					\n"	\
+	:								\
+	: "r" (x));							\
+} while (0)
+
+#define mtlo2(x)							\
+do {									\
+	__asm__ __volatile__(						\
+	"	.set	push					\n"	\
+	"	.set	noat					\n"	\
+	"	move	$1, %0					\n"	\
+	"	# mtlo	$1, $ac2				\n"	\
+	"	.word	0x00201013				\n"	\
+	"	.set	pop					\n"	\
+	:								\
+	: "r" (x));							\
+} while (0)
+
+#define mtlo3(x)							\
+do {									\
+	__asm__ __volatile__(						\
+	"	.set	push					\n"	\
+	"	.set	noat					\n"	\
+	"	move	$1, %0					\n"	\
+	"	# mtlo	$1, $ac3				\n"	\
+	"	.word	0x00201813				\n"	\
+	"	.set	pop					\n"	\
+	:								\
+	: "r" (x));							\
+} while (0)
+
+/*
+ * TLB operations.
  *
- * FIXME: The R10000 performance counter opens a nice way to implement CPU
- *        time accounting with a precission of one cycle.  I don't have
- *        R10000 silicon but just a manual, so ...
- */
-
-/*
- * Events counted by counter #0
- */
-#define CE0_CYCLES			0
-#define CE0_INSN_ISSUED			1
-#define CE0_LPSC_ISSUED			2
-#define CE0_S_ISSUED			3
-#define CE0_SC_ISSUED			4
-#define CE0_SC_FAILED			5
-#define CE0_BRANCH_DECODED		6
-#define CE0_QW_WB_SECONDARY		7
-#define CE0_CORRECTED_ECC_ERRORS	8
-#define CE0_ICACHE_MISSES		9
-#define CE0_SCACHE_I_MISSES		10
-#define CE0_SCACHE_I_WAY_MISSPREDICTED	11
-#define CE0_EXT_INTERVENTIONS_REQ	12
-#define CE0_EXT_INVALIDATE_REQ		13
-#define CE0_VIRTUAL_COHERENCY_COND	14
-#define CE0_INSN_GRADUATED		15
-
-/*
- * Events counted by counter #1
- */
-#define CE1_CYCLES			0
-#define CE1_INSN_GRADUATED		1
-#define CE1_LPSC_GRADUATED		2
-#define CE1_S_GRADUATED			3
-#define CE1_SC_GRADUATED		4
-#define CE1_FP_INSN_GRADUATED		5
-#define CE1_QW_WB_PRIMARY		6
-#define CE1_TLB_REFILL			7
-#define CE1_BRANCH_MISSPREDICTED	8
-#define CE1_DCACHE_MISS			9
-#define CE1_SCACHE_D_MISSES		10
-#define CE1_SCACHE_D_WAY_MISSPREDICTED	11
-#define CE1_EXT_INTERVENTION_HITS	12
-#define CE1_EXT_INVALIDATE_REQ		13
-#define CE1_SP_HINT_TO_CEXCL_SC_BLOCKS	14
-#define CE1_SP_HINT_TO_SHARED_SC_BLOCKS	15
-
-/*
- * These flags define in which priviledge mode the counters count events
- */
-#define CEB_USER	8	/* Count events in user mode, EXL = ERL = 0 */
-#define CEB_SUPERVISOR	4	/* Count events in supvervisor mode EXL = ERL = 0 */
-#define CEB_KERNEL	2	/* Count events in kernel mode EXL = ERL = 0 */
-#define CEB_EXL		1	/* Count events with EXL = 1, ERL = 0 */
+ * It is responsibility of the caller to take care of any TLB hazards.
+ */
+static inline void tlb_probe(void)
+{
+	__asm__ __volatile__(
+		".set noreorder\n\t"
+		"tlbp\n\t"
+		".set reorder");
+}
+
+static inline void tlb_read(void)
+{
+#if MIPS34K_MISSED_ITLB_WAR
+	int res = 0;
+
+	__asm__ __volatile__(
+	"	.set	push					\n"
+	"	.set	noreorder				\n"
+	"	.set	noat					\n"
+	"	.set	mips32r2				\n"
+	"	.word	0x41610001		# dvpe $1	\n"
+	"	move	%0, $1					\n"
+	"	ehb						\n"
+	"	.set	pop					\n"
+	: "=r" (res));
+
+	instruction_hazard();
+#endif
+
+	__asm__ __volatile__(
+		".set noreorder\n\t"
+		"tlbr\n\t"
+		".set reorder");
+
+#if MIPS34K_MISSED_ITLB_WAR
+	if ((res & _ULCAST_(1)))
+		__asm__ __volatile__(
+		"	.set	push				\n"
+		"	.set	noreorder			\n"
+		"	.set	noat				\n"
+		"	.set	mips32r2			\n"
+		"	.word	0x41600021	# evpe		\n"
+		"	ehb					\n"
+		"	.set	pop				\n");
+#endif
+}
+
+static inline void tlb_write_indexed(void)
+{
+	__asm__ __volatile__(
+		".set noreorder\n\t"
+		"tlbwi\n\t"
+		".set reorder");
+}
+
+static inline void tlb_write_random(void)
+{
+	__asm__ __volatile__(
+		".set noreorder\n\t"
+		"tlbwr\n\t"
+		".set reorder");
+}
+
+/*
+ * Manipulate bits in a c0 register.
+ */
+#define __BUILD_SET_C0(name)					\
+static inline unsigned int					\
+set_c0_##name(unsigned int set)					\
+{								\
+	unsigned int res;					\
+								\
+	res = read_c0_##name();					\
+	res |= set;						\
+	write_c0_##name(res);					\
+								\
+	return res;						\
+}								\
+								\
+static inline unsigned int					\
+clear_c0_##name(unsigned int clear)				\
+{								\
+	unsigned int res;					\
+								\
+	res = read_c0_##name();					\
+	res &= ~clear;						\
+	write_c0_##name(res);					\
+								\
+	return res;						\
+}								\
+								\
+static inline unsigned int					\
+change_c0_##name(unsigned int change, unsigned int new)		\
+{								\
+	unsigned int res;					\
+								\
+	res = read_c0_##name();					\
+	res &= ~change;						\
+	res |= (new & change);					\
+	write_c0_##name(res);					\
+								\
+	return res;						\
+}
+
+__BUILD_SET_C0(status)
+__BUILD_SET_C0(cause)
+__BUILD_SET_C0(config)
+__BUILD_SET_C0(intcontrol)
+__BUILD_SET_C0(intctl)
+__BUILD_SET_C0(srsmap)
+
+#endif /* !__ASSEMBLY__ */
 
 #endif /* _ASM_MIPSREGS_H */
diff --git a/lib_mips/board.c b/lib_mips/board.c
index 1645f2c7e0c5cb55eed90d7d418ec72139a39ab3..532550b603b1d1a8c99be23934c006f2681c83d6 100644
--- a/lib_mips/board.c
+++ b/lib_mips/board.c
@@ -28,6 +28,8 @@
 #include <version.h>
 #include <net.h>
 #include <environment.h>
+#include <nand.h>
+#include <spi.h>
 
 DECLARE_GLOBAL_DATA_PTR;
 
@@ -416,6 +418,17 @@ void board_init_r (gd_t *id, ulong dest_addr)
 	}
 #endif
 
+#ifdef CONFIG_CMD_NAND
+	puts ("NAND:  ");
+	nand_init ();		/* go init the NAND */
+#endif
+
+#ifdef CONFIG_CMD_SPI
+	puts ("SPI:   ");
+	spi_init ();		/* go init the SPI */
+	puts ("ready\n");
+#endif
+
 #if defined(CONFIG_MISC_INIT_R)
 	/* miscellaneous platform dependent initialisations */
 	misc_init_r ();