Merge branch 'upstream' of git://ftp.linux-mips.org/pub/scm/upstream-linus

* 'upstream' of git://ftp.linux-mips.org/pub/scm/upstream-linus: (22 commits)
  MIPS: Return after handling coprocessor 2 exception
  MIPS: BCM47xx: Add NVRAM support devices
  MIPS: Loongson: Define rtc device on MC146818-equipped systems
  MIPS: MT: Fix FPU affinity.
  MIPS: Oprofile: Fixup of loongson2_exit()
  MIPS: Alchemy: sleepcode without compile-time cputype dependencies
  MIPS: Tracing: Cleanup of address space checking
  MIPS: Tracing: Cleanup of function graph tracer
  MIPS: Tracing: Reduce the overhead of dynamic Function Tracer
  MIPS: Tracing: Cleanup of instructions used
  MIPS: Tracing: Fix 32-bit support with -mmcount-ra-address
  MIPS: Tracing: Fix argument passing of the 32bit support with gcc 4.5
  MIPS: Tracing: Cleanup comments
  MIPS: Tracing: Cleanup the arguments passing of prepare_ftrace_return
  MIPS: Tracing: Merge adjacent #ifdefs with same condition.
  MIPS: AR7, BCM63xx: fix gpio_to_irq() return value
  MIPS: Restore signalling NaN behaviour for abs.[sd]
  MIPS: Loongson: CS5536: Fix ISA support
  MIPS: Loongson: Add a missing break statement in CS5536 IDE code
  MIPS: Loongson: CS5536: Add missing RDMSRs for IDE and USB
  ...

25 files changed, 515 insertions, 175 deletions

diff --git a/arch/mips/alchemy/common/power.c b/arch/mips/alchemy/common/power.c
index 14eb8c492da..5ef06a164a8 100644
--- a/arch/mips/alchemy/common/power.c
+++ b/arch/mips/alchemy/common/power.c
@@ -193,9 +193,15 @@ static void restore_core_regs(void)
 
 void au_sleep(void)
 {
-	save_core_regs();
-	au1xxx_save_and_sleep();
-	restore_core_regs();
+	int cpuid = alchemy_get_cputype();
+	if (cpuid != ALCHEMY_CPU_UNKNOWN) {
+		save_core_regs();
+		if (cpuid <= ALCHEMY_CPU_AU1500)
+			alchemy_sleep_au1000();
+		else if (cpuid <= ALCHEMY_CPU_AU1200)
+			alchemy_sleep_au1550();
+		restore_core_regs();
+	}
 }
 
 #endif	/* CONFIG_PM */
diff --git a/arch/mips/alchemy/common/sleeper.S b/arch/mips/alchemy/common/sleeper.S
index 4f4b16741d1..77f3c743b71 100644
--- a/arch/mips/alchemy/common/sleeper.S
+++ b/arch/mips/alchemy/common/sleeper.S
@@ -22,10 +22,9 @@
 	.set noat
 	.align	5
 
-/* Save all of the processor general registers and go to sleep.
- * A wakeup condition will get us back here to restore the registers.
- */
-LEAF(au1xxx_save_and_sleep)
+
+/* preparatory stuff */
+.macro	SETUP_SLEEP
 	subu	sp, PT_SIZE
 	sw	$1, PT_R1(sp)
 	sw	$2, PT_R2(sp)
@@ -69,12 +68,32 @@ LEAF(au1xxx_save_and_sleep)
 	 */
 	lui	t3, 0xb190		/* sys_xxx */
 	sw	sp, 0x0018(t3)
-	la	k0, 3f			/* resume path */
+	la	k0, alchemy_sleep_wakeup	/* resume path */
 	sw	k0, 0x001c(t3)
+.endm
 
-	/* Put SDRAM into self refresh:  Preload instructions into cache,
-	 * issue a precharge, auto/self refresh, then sleep commands to it.
-	 */
+.macro	DO_SLEEP
+	/* put power supply and processor to sleep */
+	sw	zero, 0x0078(t3)	/* sys_slppwr */
+	sync
+	sw	zero, 0x007c(t3)	/* sys_sleep */
+	sync
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+.endm
+
+/* sleep code for Au1000/Au1100/Au1500 memory controller type */
+LEAF(alchemy_sleep_au1000)
+
+	SETUP_SLEEP
+
+	/* cache following instructions, as memory gets put to sleep */
 	la	t0, 1f
 	.set	mips3
 	cache	0x14, 0(t0)
@@ -84,17 +103,32 @@ LEAF(au1xxx_save_and_sleep)
 	.set	mips0
 
 1:	lui 	a0, 0xb400		/* mem_xxx */
-#if defined(CONFIG_SOC_AU1000) || defined(CONFIG_SOC_AU1100) ||	\
-    defined(CONFIG_SOC_AU1500)
 	sw	zero, 0x001c(a0) 	/* Precharge */
 	sync
 	sw	zero, 0x0020(a0)	/* Auto Refresh */
 	sync
 	sw	zero, 0x0030(a0)  	/* Sleep */
 	sync
-#endif
 
-#if defined(CONFIG_SOC_AU1550) || defined(CONFIG_SOC_AU1200)
+	DO_SLEEP
+
+END(alchemy_sleep_au1000)
+
+/* sleep code for Au1550/Au1200 memory controller type */
+LEAF(alchemy_sleep_au1550)
+
+	SETUP_SLEEP
+
+	/* cache following instructions, as memory gets put to sleep */
+	la	t0, 1f
+	.set	mips3
+	cache	0x14, 0(t0)
+	cache	0x14, 32(t0)
+	cache	0x14, 64(t0)
+	cache	0x14, 96(t0)
+	.set	mips0
+
+1:	lui 	a0, 0xb400		/* mem_xxx */
 	sw	zero, 0x08c0(a0) 	/* Precharge */
 	sync
 	sw	zero, 0x08d0(a0)	/* Self Refresh */
@@ -114,26 +148,17 @@ LEAF(au1xxx_save_and_sleep)
 	and 	t1, t0, t1		/* clear CE[1:0] */
 	sw 	t1, 0x0840(a0)		/* mem_sdconfiga */
 	sync
-#endif
 
-	/* put power supply and processor to sleep */
-	sw	zero, 0x0078(t3)	/* sys_slppwr */
-	sync
-	sw	zero, 0x007c(t3)	/* sys_sleep */
-	sync
-	nop
-	nop
-	nop
-	nop
-	nop
-	nop
-	nop
-	nop
+	DO_SLEEP
+
+END(alchemy_sleep_au1550)
+
 
 	/* This is where we return upon wakeup.
 	 * Reload all of the registers and return.
 	 */
-3:	lw	k0, 0x20(sp)
+LEAF(alchemy_sleep_wakeup)
+	lw	k0, 0x20(sp)
 	mtc0	k0, CP0_STATUS
 	lw	k0, 0x1c(sp)
 	mtc0	k0, CP0_CONTEXT
@@ -169,4 +194,4 @@ LEAF(au1xxx_save_and_sleep)
 	lw	$31, PT_R31(sp)
 	jr	ra
 	 addiu	sp, PT_SIZE
-END(au1xxx_save_and_sleep)
+END(alchemy_sleep_wakeup)
diff --git a/arch/mips/ar7/platform.c b/arch/mips/ar7/platform.c
index 566f2d7f2ea..8f31d1d5968 100644
--- a/arch/mips/ar7/platform.c
+++ b/arch/mips/ar7/platform.c
@@ -542,7 +542,7 @@ static int __init ar7_register_uarts(void)
 	if (IS_ERR(bus_clk))
 		panic("unable to get bus clk\n");
 
-	uart_port.type		= PORT_16550A;
+	uart_port.type		= PORT_AR7;
 	uart_port.uartclk	= clk_get_rate(bus_clk) / 2;
 	uart_port.iotype	= UPIO_MEM32;
 	uart_port.regshift	= 2;
diff --git a/arch/mips/bcm47xx/Makefile b/arch/mips/bcm47xx/Makefile
index 35294b12d63..7465e8a72d9 100644
--- a/arch/mips/bcm47xx/Makefile
+++ b/arch/mips/bcm47xx/Makefile
@@ -3,4 +3,4 @@
 # under Linux.
 #
 
-obj-y := gpio.o irq.o prom.o serial.o setup.o time.o wgt634u.o
+obj-y := gpio.o irq.o nvram.o prom.o serial.o setup.o time.o wgt634u.o
diff --git a/arch/mips/bcm47xx/nvram.c b/arch/mips/bcm47xx/nvram.c
new file mode 100644
index 00000000000..06e03b222f6
--- /dev/null
+++ b/arch/mips/bcm47xx/nvram.c
@@ -0,0 +1,94 @@
+/*
+ * BCM947xx nvram variable access
+ *
+ * Copyright (C) 2005 Broadcom Corporation
+ * Copyright (C) 2006 Felix Fietkau <nbd@openwrt.org>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/module.h>
+#include <linux/ssb/ssb.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <asm/addrspace.h>
+#include <asm/mach-bcm47xx/nvram.h>
+#include <asm/mach-bcm47xx/bcm47xx.h>
+
+static char nvram_buf[NVRAM_SPACE];
+
+/* Probe for NVRAM header */
+static void __init early_nvram_init(void)
+{
+	struct ssb_mipscore *mcore = &ssb_bcm47xx.mipscore;
+	struct nvram_header *header;
+	int i;
+	u32 base, lim, off;
+	u32 *src, *dst;
+
+	base = mcore->flash_window;
+	lim = mcore->flash_window_size;
+
+	off = FLASH_MIN;
+	while (off <= lim) {
+		/* Windowed flash access */
+		header = (struct nvram_header *)
+			KSEG1ADDR(base + off - NVRAM_SPACE);
+		if (header->magic == NVRAM_HEADER)
+			goto found;
+		off <<= 1;
+	}
+
+	/* Try embedded NVRAM at 4 KB and 1 KB as last resorts */
+	header = (struct nvram_header *) KSEG1ADDR(base + 4096);
+	if (header->magic == NVRAM_HEADER)
+		goto found;
+
+	header = (struct nvram_header *) KSEG1ADDR(base + 1024);
+	if (header->magic == NVRAM_HEADER)
+		goto found;
+
+	return;
+
+found:
+	src = (u32 *) header;
+	dst = (u32 *) nvram_buf;
+	for (i = 0; i < sizeof(struct nvram_header); i += 4)
+		*dst++ = *src++;
+	for (; i < header->len && i < NVRAM_SPACE; i += 4)
+		*dst++ = le32_to_cpu(*src++);
+}
+
+int nvram_getenv(char *name, char *val, size_t val_len)
+{
+	char *var, *value, *end, *eq;
+
+	if (!name)
+		return 1;
+
+	if (!nvram_buf[0])
+		early_nvram_init();
+
+	/* Look for name=value and return value */
+	var = &nvram_buf[sizeof(struct nvram_header)];
+	end = nvram_buf + sizeof(nvram_buf) - 2;
+	end[0] = end[1] = '\0';
+	for (; *var; var = value + strlen(value) + 1) {
+		eq = strchr(var, '=');
+		if (!eq)
+			break;
+		value = eq + 1;
+		if ((eq - var) == strlen(name) &&
+			strncmp(var, name, (eq - var)) == 0) {
+			snprintf(val, val_len, "%s", value);
+			return 0;
+		}
+	}
+	return 1;
+}
+EXPORT_SYMBOL(nvram_getenv);
diff --git a/arch/mips/bcm47xx/setup.c b/arch/mips/bcm47xx/setup.c
index d442e11625f..b1aee33efd1 100644
--- a/arch/mips/bcm47xx/setup.c
+++ b/arch/mips/bcm47xx/setup.c
@@ -1,8 +1,8 @@
 /*
  *  Copyright (C) 2004 Florian Schirmer <jolt@tuxbox.org>
- *  Copyright (C) 2005 Waldemar Brodkorb <wbx@openwrt.org>
  *  Copyright (C) 2006 Felix Fietkau <nbd@openwrt.org>
  *  Copyright (C) 2006 Michael Buesch <mb@bu3sch.de>
+ *  Copyright (C) 2010 Waldemar Brodkorb <wbx@openadk.org>
  *
  *  This program is free software; you can redistribute  it and/or modify it
  *  under  the terms of  the GNU General  Public License as published by the
@@ -33,6 +33,7 @@
 #include <asm/time.h>
 #include <bcm47xx.h>
 #include <asm/fw/cfe/cfe_api.h>
+#include <asm/mach-bcm47xx/nvram.h>
 
 struct ssb_bus ssb_bcm47xx;
 EXPORT_SYMBOL(ssb_bcm47xx);
@@ -81,28 +82,42 @@ static int bcm47xx_get_invariants(struct ssb_bus *bus,
 	/* Fill boardinfo structure */
 	memset(&(iv->boardinfo), 0 , sizeof(struct ssb_boardinfo));
 
-	if (cfe_getenv("boardvendor", buf, sizeof(buf)) >= 0)
+	if (cfe_getenv("boardvendor", buf, sizeof(buf)) >= 0 ||
+	    nvram_getenv("boardvendor", buf, sizeof(buf)) >= 0)
 		iv->boardinfo.type = (u16)simple_strtoul(buf, NULL, 0);
-	if (cfe_getenv("boardtype", buf, sizeof(buf)) >= 0)
+	if (cfe_getenv("boardtype", buf, sizeof(buf)) >= 0 ||
+	    nvram_getenv("boardtype", buf, sizeof(buf)) >= 0)
 		iv->boardinfo.type = (u16)simple_strtoul(buf, NULL, 0);
-	if (cfe_getenv("boardrev", buf, sizeof(buf)) >= 0)
+	if (cfe_getenv("boardrev", buf, sizeof(buf)) >= 0 ||
+	    nvram_getenv("boardrev", buf, sizeof(buf)) >= 0)
 		iv->boardinfo.rev = (u16)simple_strtoul(buf, NULL, 0);
 
 	/* Fill sprom structure */
 	memset(&(iv->sprom), 0, sizeof(struct ssb_sprom));
 	iv->sprom.revision = 3;
 
-	if (cfe_getenv("et0macaddr", buf, sizeof(buf)) >= 0)
+	if (cfe_getenv("et0macaddr", buf, sizeof(buf)) >= 0 ||
+	    nvram_getenv("et0macaddr", buf, sizeof(buf)) >= 0)
 		str2eaddr(buf, iv->sprom.et0mac);
-	if (cfe_getenv("et1macaddr", buf, sizeof(buf)) >= 0)
+
+	if (cfe_getenv("et1macaddr", buf, sizeof(buf)) >= 0 ||
+	    nvram_getenv("et1macaddr", buf, sizeof(buf)) >= 0)
 		str2eaddr(buf, iv->sprom.et1mac);
-	if (cfe_getenv("et0phyaddr", buf, sizeof(buf)) >= 0)
-		iv->sprom.et0phyaddr = simple_strtoul(buf, NULL, 10);
-	if (cfe_getenv("et1phyaddr", buf, sizeof(buf)) >= 0)
-		iv->sprom.et1phyaddr = simple_strtoul(buf, NULL, 10);
-	if (cfe_getenv("et0mdcport", buf, sizeof(buf)) >= 0)
+
+	if (cfe_getenv("et0phyaddr", buf, sizeof(buf)) >= 0 ||
+	    nvram_getenv("et0phyaddr", buf, sizeof(buf)) >= 0)
+		iv->sprom.et0phyaddr = simple_strtoul(buf, NULL, 0);
+
+	if (cfe_getenv("et1phyaddr", buf, sizeof(buf)) >= 0 ||
+	    nvram_getenv("et1phyaddr", buf, sizeof(buf)) >= 0)
+		iv->sprom.et1phyaddr = simple_strtoul(buf, NULL, 0);
+
+	if (cfe_getenv("et0mdcport", buf, sizeof(buf)) >= 0 ||
+	    nvram_getenv("et0mdcport", buf, sizeof(buf)) >= 0)
 		iv->sprom.et0mdcport = simple_strtoul(buf, NULL, 10);
-	if (cfe_getenv("et1mdcport", buf, sizeof(buf)) >= 0)
+
+	if (cfe_getenv("et1mdcport", buf, sizeof(buf)) >= 0 ||
+	    nvram_getenv("et1mdcport", buf, sizeof(buf)) >= 0)
 		iv->sprom.et1mdcport = simple_strtoul(buf, NULL, 10);
 
 	return 0;
diff --git a/arch/mips/include/asm/mach-ar7/ar7.h b/arch/mips/include/asm/mach-ar7/ar7.h
index f1cf3894349..483ffea9ecb 100644
--- a/arch/mips/include/asm/mach-ar7/ar7.h
+++ b/arch/mips/include/asm/mach-ar7/ar7.h
@@ -50,7 +50,7 @@
 #define UR8_REGS_WDT	(AR7_REGS_BASE + 0x0b00)
 #define UR8_REGS_UART1	(AR7_REGS_BASE + 0x0f00)
 
-#define AR7_RESET_PEREPHERIAL	0x0
+#define AR7_RESET_PERIPHERAL	0x0
 #define AR7_RESET_SOFTWARE	0x4
 #define AR7_RESET_STATUS	0x8
 
@@ -128,7 +128,7 @@ static inline int ar7_has_high_cpmac(void)
 static inline void ar7_device_enable(u32 bit)
 {
 	void *reset_reg =
-		(void *)KSEG1ADDR(AR7_REGS_RESET + AR7_RESET_PEREPHERIAL);
+		(void *)KSEG1ADDR(AR7_REGS_RESET + AR7_RESET_PERIPHERAL);
 	writel(readl(reset_reg) | (1 << bit), reset_reg);
 	msleep(20);
 }
@@ -136,7 +136,7 @@ static inline void ar7_device_enable(u32 bit)
 static inline void ar7_device_disable(u32 bit)
 {
 	void *reset_reg =
-		(void *)KSEG1ADDR(AR7_REGS_RESET + AR7_RESET_PEREPHERIAL);
+		(void *)KSEG1ADDR(AR7_REGS_RESET + AR7_RESET_PERIPHERAL);
 	writel(readl(reset_reg) & ~(1 << bit), reset_reg);
 	msleep(20);
 }
diff --git a/arch/mips/include/asm/mach-ar7/gpio.h b/arch/mips/include/asm/mach-ar7/gpio.h
index 73f9b162c97..abc317c0372 100644
--- a/arch/mips/include/asm/mach-ar7/gpio.h
+++ b/arch/mips/include/asm/mach-ar7/gpio.h
@@ -24,7 +24,7 @@
 #define AR7_GPIO_MAX 32
 #define NR_BUILTIN_GPIO AR7_GPIO_MAX
 
-#define gpio_to_irq(gpio)	NULL
+#define gpio_to_irq(gpio)	-1
 
 #define gpio_get_value __gpio_get_value
 #define gpio_set_value __gpio_set_value
diff --git a/arch/mips/include/asm/mach-au1x00/au1000.h b/arch/mips/include/asm/mach-au1x00/au1000.h
index e76941db231..a6976619160 100644
--- a/arch/mips/include/asm/mach-au1x00/au1000.h
+++ b/arch/mips/include/asm/mach-au1x00/au1000.h
@@ -188,7 +188,8 @@ extern unsigned long get_au1x00_uart_baud_base(void);
 extern unsigned long au1xxx_calc_clock(void);
 
 /* PM: arch/mips/alchemy/common/sleeper.S, power.c, irq.c */
-void au1xxx_save_and_sleep(void);
+void alchemy_sleep_au1000(void);
+void alchemy_sleep_au1550(void);
 void au_sleep(void);
 
 
diff --git a/arch/mips/include/asm/mach-bcm47xx/nvram.h b/arch/mips/include/asm/mach-bcm47xx/nvram.h
new file mode 100644
index 00000000000..0d8cc146f7a
--- /dev/null
+++ b/arch/mips/include/asm/mach-bcm47xx/nvram.h
@@ -0,0 +1,36 @@
+/*
+ *  Copyright (C) 2005, Broadcom Corporation
+ *  Copyright (C) 2006, Felix Fietkau <nbd@openwrt.org>
+ *
+ *  This program is free software; you can redistribute  it and/or modify it
+ *  under  the terms of  the GNU General  Public License as published by the
+ *  Free Software Foundation;  either version 2 of the  License, or (at your
+ *  option) any later version.
+ */
+
+#ifndef __NVRAM_H
+#define __NVRAM_H
+
+#include <linux/types.h>
+
+struct nvram_header {
+	u32 magic;
+	u32 len;
+	u32 crc_ver_init;	/* 0:7 crc, 8:15 ver, 16:31 sdram_init */
+	u32 config_refresh;	/* 0:15 sdram_config, 16:31 sdram_refresh */
+	u32 config_ncdl;	/* ncdl values for memc */
+};
+
+#define NVRAM_HEADER		0x48534C46	/* 'FLSH' */
+#define NVRAM_VERSION		1
+#define NVRAM_HEADER_SIZE	20
+#define NVRAM_SPACE		0x8000
+
+#define FLASH_MIN		0x00020000	/* Minimum flash size */
+
+#define NVRAM_MAX_VALUE_LEN 255
+#define NVRAM_MAX_PARAM_LEN 64
+
+extern int nvram_getenv(char *name, char *val, size_t val_len);
+
+#endif
diff --git a/arch/mips/include/asm/mach-bcm63xx/gpio.h b/arch/mips/include/asm/mach-bcm63xx/gpio.h
index 7cda8c0a397..1eb534de8e3 100644
--- a/arch/mips/include/asm/mach-bcm63xx/gpio.h
+++ b/arch/mips/include/asm/mach-bcm63xx/gpio.h
@@ -3,7 +3,7 @@
 
 #include <bcm63xx_gpio.h>
 
-#define gpio_to_irq(gpio)	NULL
+#define gpio_to_irq(gpio)	-1
 
 #define gpio_get_value __gpio_get_value
 #define gpio_set_value __gpio_set_value
diff --git a/arch/mips/kernel/ftrace.c b/arch/mips/kernel/ftrace.c
index e9e64e0ff7a..5a84a1f1123 100644
--- a/arch/mips/kernel/ftrace.c
+++ b/arch/mips/kernel/ftrace.c
@@ -2,7 +2,7 @@
  * Code for replacing ftrace calls with jumps.
  *
  * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com>
- * Copyright (C) 2009 DSLab, Lanzhou University, China
+ * Copyright (C) 2009, 2010 DSLab, Lanzhou University, China
  * Author: Wu Zhangjin <wuzhangjin@gmail.com>
  *
  * Thanks goes to Steven Rostedt for writing the original x86 version.
@@ -12,18 +12,62 @@
 #include <linux/init.h>
 #include <linux/ftrace.h>
 
-#include <asm/cacheflush.h>
 #include <asm/asm.h>
 #include <asm/asm-offsets.h>
+#include <asm/cacheflush.h>
+#include <asm/uasm.h>
+
+/*
+ * If the Instruction Pointer is in module space (0xc0000000), return true;
+ * otherwise, it is in kernel space (0x80000000), return false.
+ *
+ * FIXME: This will not work when the kernel space and module space are the
+ * same. If they are the same, we need to modify scripts/recordmcount.pl,
+ * ftrace_make_nop/call() and the other related parts to ensure the
+ * enabling/disabling of the calling site to _mcount is right for both kernel
+ * and module.
+ */
+
+static inline int in_module(unsigned long ip)
+{
+	return ip & 0x40000000;
+}
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 
 #define JAL 0x0c000000		/* jump & link: ip --> ra, jump to target */
 #define ADDR_MASK 0x03ffffff	/*  op_code|addr : 31...26|25 ....0 */
-#define jump_insn_encode(op_code, addr) \
-	((unsigned int)((op_code) | (((addr) >> 2) & ADDR_MASK)))
 
-static unsigned int ftrace_nop = 0x00000000;
+#define INSN_B_1F_4 0x10000004	/* b 1f; offset = 4 */
+#define INSN_B_1F_5 0x10000005	/* b 1f; offset = 5 */
+#define INSN_NOP 0x00000000	/* nop */
+#define INSN_JAL(addr)	\
+	((unsigned int)(JAL | (((addr) >> 2) & ADDR_MASK)))
+
+static unsigned int insn_jal_ftrace_caller __read_mostly;
+static unsigned int insn_lui_v1_hi16_mcount __read_mostly;
+static unsigned int insn_j_ftrace_graph_caller __maybe_unused __read_mostly;
+
+static inline void ftrace_dyn_arch_init_insns(void)
+{
+	u32 *buf;
+	unsigned int v1;
+
+	/* lui v1, hi16_mcount */
+	v1 = 3;
+	buf = (u32 *)&insn_lui_v1_hi16_mcount;
+	UASM_i_LA_mostly(&buf, v1, MCOUNT_ADDR);
+
+	/* jal (ftrace_caller + 8), jump over the first two instruction */
+	buf = (u32 *)&insn_jal_ftrace_caller;
+	uasm_i_jal(&buf, (FTRACE_ADDR + 8));
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	/* j ftrace_graph_caller */
+	buf = (u32 *)&insn_j_ftrace_graph_caller;
+	uasm_i_j(&buf, (unsigned long)ftrace_graph_caller);
+#endif
+}
 
 static int ftrace_modify_code(unsigned long ip, unsigned int new_code)
 {
@@ -40,67 +84,56 @@ static int ftrace_modify_code(unsigned long ip, unsigned int new_code)
 	return 0;
 }
 
-static int lui_v1;
-static int jal_mcount;
-
 int ftrace_make_nop(struct module *mod,
 		    struct dyn_ftrace *rec, unsigned long addr)
 {
 	unsigned int new;
-	int faulted;
 	unsigned long ip = rec->ip;
 
-	/* We have compiled module with -mlong-calls, but compiled the kernel
-	 * without it, we need to cope with them respectively. */
-	if (ip & 0x40000000) {
-		/* record it for ftrace_make_call */
-		if (lui_v1 == 0) {
-			/* lui_v1 = *(unsigned int *)ip; */
-			safe_load_code(lui_v1, ip, faulted);
-
-			if (unlikely(faulted))
-				return -EFAULT;
-		}
-
-		/* lui v1, hi_16bit_of_mcount        --> b 1f (0x10000004)
+	/*
+	 * We have compiled module with -mlong-calls, but compiled the kernel
+	 * without it, we need to cope with them respectively.
+	 */
+	if (in_module(ip)) {
+#if defined(KBUILD_MCOUNT_RA_ADDRESS) && defined(CONFIG_32BIT)
+		/*
+		 * lui v1, hi_16bit_of_mcount        --> b 1f (0x10000005)
+		 * addiu v1, v1, low_16bit_of_mcount
+		 * move at, ra
+		 * move $12, ra_address
+		 * jalr v1
+		 *  sub sp, sp, 8
+		 *                                  1: offset = 5 instructions
+		 */
+		new = INSN_B_1F_5;
+#else
+		/*
+		 * lui v1, hi_16bit_of_mcount        --> b 1f (0x10000004)
 		 * addiu v1, v1, low_16bit_of_mcount
 		 * move at, ra
 		 * jalr v1
-		 * nop
-		 * 				     1f: (ip + 12)
+		 *  nop | move $12, ra_address | sub sp, sp, 8
+		 *                                  1: offset = 4 instructions
 		 */
-		new = 0x10000004;
+		new = INSN_B_1F_4;
+#endif
 	} else {
-		/* record/calculate it for ftrace_make_call */
-		if (jal_mcount == 0) {
-			/* We can record it directly like this:
-			 *     jal_mcount = *(unsigned int *)ip;
-			 * Herein, jump over the first two nop instructions */
-			jal_mcount = jump_insn_encode(JAL, (MCOUNT_ADDR + 8));
-		}
-
-		/* move at, ra
-		 * jalr v1		--> nop
+		/*
+		 * move at, ra
+		 * jal _mcount		--> nop
 		 */
-		new = ftrace_nop;
+		new = INSN_NOP;
 	}
 	return ftrace_modify_code(ip, new);
 }
 
-static int modified;	/* initialized as 0 by default */
-
 int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 {
 	unsigned int new;
 	unsigned long ip = rec->ip;
 
-	/* We just need to remove the "b ftrace_stub" at the fist time! */
-	if (modified == 0) {
-		modified = 1;
-		ftrace_modify_code(addr, ftrace_nop);
-	}
 	/* ip, module: 0xc0000000, kernel: 0x80000000 */
-	new = (ip & 0x40000000) ? lui_v1 : jal_mcount;
+	new = in_module(ip) ? insn_lui_v1_hi16_mcount : insn_jal_ftrace_caller;
 
 	return ftrace_modify_code(ip, new);
 }
@@ -111,44 +144,48 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 {
 	unsigned int new;
 
-	new = jump_insn_encode(JAL, (unsigned long)func);
+	new = INSN_JAL((unsigned long)func);
 
 	return ftrace_modify_code(FTRACE_CALL_IP, new);
 }
 
 int __init ftrace_dyn_arch_init(void *data)
 {
+	/* Encode the instructions when booting */
+	ftrace_dyn_arch_init_insns();
+
+	/* Remove "b ftrace_stub" to ensure ftrace_caller() is executed */
+	ftrace_modify_code(MCOUNT_ADDR, INSN_NOP);
+
 	/* The return code is retured via data */
 	*(unsigned long *)data = 0;
 
 	return 0;
 }
-#endif				/* CONFIG_DYNAMIC_FTRACE */
+#endif	/* CONFIG_DYNAMIC_FTRACE */
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 
 extern void ftrace_graph_call(void);
-#define JMP	0x08000000	/* jump to target directly */
-#define CALL_FTRACE_GRAPH_CALLER \
-	jump_insn_encode(JMP, (unsigned long)(&ftrace_graph_caller))
 #define FTRACE_GRAPH_CALL_IP	((unsigned long)(&ftrace_graph_call))
 
 int ftrace_enable_ftrace_graph_caller(void)
 {
 	return ftrace_modify_code(FTRACE_GRAPH_CALL_IP,
-				  CALL_FTRACE_GRAPH_CALLER);
+			insn_j_ftrace_graph_caller);
 }
 
 int ftrace_disable_ftrace_graph_caller(void)
 {
-	return ftrace_modify_code(FTRACE_GRAPH_CALL_IP, ftrace_nop);
+	return ftrace_modify_code(FTRACE_GRAPH_CALL_IP, INSN_NOP);
 }
 
-#endif				/* !CONFIG_DYNAMIC_FTRACE */
+#endif	/* CONFIG_DYNAMIC_FTRACE */
 
 #ifndef KBUILD_MCOUNT_RA_ADDRESS
+
 #define S_RA_SP	(0xafbf << 16)	/* s{d,w} ra, offset(sp) */
 #define S_R_SP	(0xafb0 << 16)  /* s{d,w} R, offset(sp) */
 #define OFFSET_MASK	0xffff	/* stack offset range: 0 ~ PT_SIZE */
@@ -162,17 +199,17 @@ unsigned long ftrace_get_parent_addr(unsigned long self_addr,
 	unsigned int code;
 	int faulted;
 
-	/* in module or kernel? */
-	if (self_addr & 0x40000000) {
-		/* module: move to the instruction "lui v1, HI_16BIT_OF_MCOUNT" */
-		ip = self_addr - 20;
-	} else {
-		/* kernel: move to the instruction "move ra, at" */
-		ip = self_addr - 12;
-	}
+	/*
+	 * For module, move the ip from calling site of mcount to the
+	 * instruction "lui v1, hi_16bit_of_mcount"(offset is 20), but for
+	 * kernel, move to the instruction "move ra, at"(offset is 12)
+	 */
+	ip = self_addr - (in_module(self_addr) ? 20 : 12);
 
-	/* search the text until finding the non-store instruction or "s{d,w}
-	 * ra, offset(sp)" instruction */
+	/*
+	 * search the text until finding the non-store instruction or "s{d,w}
+	 * ra, offset(sp)" instruction
+	 */
 	do {
 		ip -= 4;
 
@@ -181,10 +218,11 @@ unsigned long ftrace_get_parent_addr(unsigned long self_addr,
 
 		if (unlikely(faulted))
 			return 0;
-
-		/* If we hit the non-store instruction before finding where the
+		/*
+		 * If we hit the non-store instruction before finding where the
 		 * ra is stored, then this is a leaf function and it does not
-		 * store the ra on the stack. */
+		 * store the ra on the stack
+		 */
 		if ((code & S_R_SP) != S_R_SP)
 			return parent_addr;
 
@@ -202,7 +240,7 @@ unsigned long ftrace_get_parent_addr(unsigned long self_addr,
 	return 0;
 }
 
-#endif
+#endif	/* !KBUILD_MCOUNT_RA_ADDRESS */
 
 /*
  * Hook the return address and push it in the stack of return addrs
@@ -220,7 +258,8 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
 	if (unlikely(atomic_read(&current->tracing_graph_pause)))
 		return;
 
-	/* "parent" is the stack address saved the return address of the caller
+	/*
+	 * "parent" is the stack address saved the return address of the caller
 	 * of _mcount.
 	 *
 	 * if the gcc < 4.5, a leaf function does not save the return address
@@ -242,10 +281,11 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
 		goto out;
 #ifndef KBUILD_MCOUNT_RA_ADDRESS
 	parent = (unsigned long *)ftrace_get_parent_addr(self_addr, old,
-							 (unsigned long)parent,
-							 fp);
-	/* If fails when getting the stack address of the non-leaf function's
-	 * ra, stop function graph tracer and return */
+			(unsigned long)parent, fp);
+	/*
+	 * If fails when getting the stack address of the non-leaf function's
+	 * ra, stop function graph tracer and return
+	 */
 	if (parent == 0)
 		goto out;
 #endif
@@ -272,4 +312,4 @@ out:
 	ftrace_graph_stop();
 	WARN_ON(1);
 }
-#endif				/* CONFIG_FUNCTION_GRAPH_TRACER */
+#endif	/* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/mips/kernel/mcount.S b/arch/mips/kernel/mcount.S
index 6851fc97a51..6bfcb7a00ec 100644
--- a/arch/mips/kernel/mcount.S
+++ b/arch/mips/kernel/mcount.S
@@ -6,6 +6,7 @@
  * more details.
  *
  * Copyright (C) 2009 Lemote Inc. & DSLab, Lanzhou University, China
+ * Copyright (C) 2010 DSLab, Lanzhou University, China
  * Author: Wu Zhangjin <wuzhangjin@gmail.com>
  */
 
@@ -45,8 +46,6 @@
 	PTR_L	a5, PT_R9(sp)
 	PTR_L	a6, PT_R10(sp)
 	PTR_L	a7, PT_R11(sp)
-#endif
-#ifdef CONFIG_64BIT
 	PTR_ADDIU	sp, PT_SIZE
 #else
 	PTR_ADDIU	sp, (PT_SIZE + 8)
@@ -58,6 +57,12 @@
 	 move ra, AT
 	.endm
 
+/*
+ * The -mmcount-ra-address option of gcc 4.5 uses register $12 to pass
+ * the location of the parent's return address.
+ */
+#define MCOUNT_RA_ADDRESS_REG	$12
+
 #ifdef CONFIG_DYNAMIC_FTRACE
 
 NESTED(ftrace_caller, PT_SIZE, ra)
@@ -71,14 +76,14 @@ _mcount:
 
 	MCOUNT_SAVE_REGS
 #ifdef KBUILD_MCOUNT_RA_ADDRESS
-	PTR_S	t0, PT_R12(sp)	/* t0 saved the location of the return address(at) by -mmcount-ra-address */
+	PTR_S	MCOUNT_RA_ADDRESS_REG, PT_R12(sp)
 #endif
 
-	move	a0, ra		/* arg1: next ip, selfaddr */
+	move	a0, ra		/* arg1: self return address */
 	.globl ftrace_call
 ftrace_call:
 	nop	/* a placeholder for the call to a real tracing function */
-	 move	a1, AT		/* arg2: the caller's next ip, parent */
+	 move	a1, AT		/* arg2: parent's return address */
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	.globl ftrace_graph_call
@@ -119,9 +124,9 @@ NESTED(_mcount, PT_SIZE, ra)
 static_trace:
 	MCOUNT_SAVE_REGS
 
-	move	a0, ra		/* arg1: next ip, selfaddr */
+	move	a0, ra		/* arg1: self return address */
 	jalr	t2		/* (1) call *ftrace_trace_function */
-	 move	a1, AT		/* arg2: the caller's next ip, parent */
+	 move	a1, AT		/* arg2: parent's return address */
 
 	MCOUNT_RESTORE_REGS
 	.globl ftrace_stub
@@ -134,28 +139,34 @@ ftrace_stub:
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 
 NESTED(ftrace_graph_caller, PT_SIZE, ra)
-#ifdef CONFIG_DYNAMIC_FTRACE
-	PTR_L	a1, PT_R31(sp)	/* load the original ra from the stack */
-#ifdef KBUILD_MCOUNT_RA_ADDRESS
-	PTR_L	t0, PT_R12(sp)	/* load the original t0 from the stack */
-#endif
-#else
+#ifndef CONFIG_DYNAMIC_FTRACE