tracing: MIPS: add misc fixups and cleanups

index e9e64e0..37aa767 100644
@@ -62,14 +62,26 @@ int ftrace_make_nop(struct module *mod,
 				return -EFAULT;
 		}
 
+#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 = 0x10000005;
+#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;
+#endif
 	} else {
 		/* record/calculate it for ftrace_make_call */
 		if (jal_mcount == 0) {

index 37aa767..b1b8fec 100644
@@ -23,7 +23,10 @@
 #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)	jump_insn_encode(JAL, addr)
 
 static int ftrace_modify_code(unsigned long ip, unsigned int new_code)
 {

@@ -71,7 +74,7 @@ int ftrace_make_nop(struct module *mod,
 		 *  sub sp, sp, 8
 		 *                                  1: offset = 5 instructions
 		 */
-		new = 0x10000005;
+		new = INSN_B_1F_5;
 #else
 		/* lui v1, hi_16bit_of_mcount        --> b 1f (0x10000004)
 		 * addiu v1, v1, low_16bit_of_mcount

@@ -80,7 +83,7 @@ int ftrace_make_nop(struct module *mod,
 		 *  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 */

@@ -88,13 +91,13 @@ int ftrace_make_nop(struct module *mod,
 			/* 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));
+			jal_mcount = INSN_JAL(MCOUNT_ADDR + 8);
 		}
 
 		/* move at, ra
 		 * jalr v1		--> nop
 		 */
-		new = ftrace_nop;
+		new = INSN_NOP;
 	}
 	return ftrace_modify_code(ip, new);
 }

@@ -109,7 +112,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 	/* We just need to remove the "b ftrace_stub" at the fist time! */
 	if (modified == 0) {
 		modified = 1;
-		ftrace_modify_code(addr, ftrace_nop);
+		ftrace_modify_code(addr, INSN_NOP);
 	}
 	/* ip, module: 0xc0000000, kernel: 0x80000000 */
 	new = (ip & 0x40000000) ? lui_v1 : jal_mcount;

@@ -123,7 +126,7 @@ 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);
 }

@@ -155,7 +158,7 @@ int ftrace_enable_ftrace_graph_caller(void)
 
 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 */

index b1b8fec..c4042ca 100644
@@ -2,7 +2,7 @@
  * Code for replacing ftrace calls with jumps.
  *
  * Copyright (C) 2007-2008 Steven Rostedt <[email protected]>
- * Copyright (C) 2009 DSLab, Lanzhou University, China
+ * Copyright (C) 2009, 2010 DSLab, Lanzhou University, China
  * Author: Wu Zhangjin <[email protected]>
  *
  * Thanks goes to Steven Rostedt for writing the original x86 version.

@@ -12,21 +12,46 @@
 #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>
 
 #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)))
 
 #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)	jump_insn_encode(JAL, addr)
+#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)
 {

@@ -43,30 +68,20 @@ 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. */
+	/*
+	 * 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;
-		}
-
 #if defined(KBUILD_MCOUNT_RA_ADDRESS) && defined(CONFIG_32BIT)
-		/* lui v1, hi_16bit_of_mcount        --> b 1f (0x10000005)
+		/*
+		 * lui v1, hi_16bit_of_mcount        --> b 1f (0x10000005)
 		 * addiu v1, v1, low_16bit_of_mcount
 		 * move at, ra
 		 * move $12, ra_address

@@ -76,7 +91,8 @@ int ftrace_make_nop(struct module *mod,
 		 */
 		new = INSN_B_1F_5;
 #else
-		/* lui v1, hi_16bit_of_mcount        --> b 1f (0x10000004)
+		/*
+		 * lui v1, hi_16bit_of_mcount        --> b 1f (0x10000004)
 		 * addiu v1, v1, low_16bit_of_mcount
 		 * move at, ra
 		 * jalr v1

@@ -86,36 +102,22 @@ int ftrace_make_nop(struct module *mod,
 		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 = INSN_JAL(MCOUNT_ADDR + 8);
-		}
-
-		/* move at, ra
-		 * jalr v1		--> nop
+		/*
+		 * move at, ra
+		 * jal _mcount		--> 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, INSN_NOP);
-	}
 	/* ip, module: 0xc0000000, kernel: 0x80000000 */
-	new = (ip & 0x40000000) ? lui_v1 : jal_mcount;
+	new = (ip & 0x40000000) ? insn_lui_v1_hi16_mcount : insn_jal_ftrace_caller;
 
 	return ftrace_modify_code(ip, new);
 }

@@ -133,6 +135,12 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 
 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;
 

@@ -145,15 +153,12 @@ int __init ftrace_dyn_arch_init(void *data)
 #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)

index c4042ca..628e90b 100644
@@ -146,7 +146,7 @@ int __init ftrace_dyn_arch_init(void *data)
 
 	return 0;
 }
-#endif				/* CONFIG_DYNAMIC_FTRACE */
+#endif	/* CONFIG_DYNAMIC_FTRACE */
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 

@@ -166,9 +166,10 @@ int ftrace_disable_ftrace_graph_caller(void)
 	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 */

@@ -182,17 +183,17 @@ 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 - ((self_addr & 0x40000000) ? 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;
 

@@ -201,10 +202,11 @@ 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;
 

@@ -222,7 +224,7 @@ 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

@@ -240,7 +242,8 @@ 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

@@ -262,10 +265,11 @@ 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

@@ -292,4 +296,4 @@ out:
 	ftrace_graph_stop();
 	WARN_ON(1);
 }
-#endif				/* CONFIG_FUNCTION_GRAPH_TRACER */
+#endif	/* CONFIG_FUNCTION_GRAPH_TRACER */

index 628e90b..37f15b6 100644
@@ -17,6 +17,17 @@
 #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 may not work when the kernel is compiled with -msym32.
+ */
+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 */

@@ -78,7 +89,7 @@ int ftrace_make_nop(struct module *mod,
 	 * We have compiled module with -mlong-calls, but compiled the kernel
 	 * without it, we need to cope with them respectively.
 	 */
-	if (ip & 0x40000000) {
+	if (in_module(ip)) {
 #if defined(KBUILD_MCOUNT_RA_ADDRESS) && defined(CONFIG_32BIT)
 		/*
 		 * lui v1, hi_16bit_of_mcount        --> b 1f (0x10000005)

@@ -117,7 +128,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 	unsigned long ip = rec->ip;
 
 	/* ip, module: 0xc0000000, kernel: 0x80000000 */
-	new = (ip & 0x40000000) ? insn_lui_v1_hi16_mcount : insn_jal_ftrace_caller;
+	new = in_module(ip) ? insn_lui_v1_hi16_mcount : insn_jal_ftrace_caller;
 
 	return ftrace_modify_code(ip, new);
 }

@@ -188,7 +199,7 @@ unsigned long ftrace_get_parent_addr(unsigned long self_addr,
 	 * 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 - ((self_addr & 0x40000000) ? 20 : 12);
+	ip = self_addr - (in_module(self_addr) ? 20 : 12);
 
 	/*
 	 * search the text until finding the non-store instruction or "s{d,w}