diff --git a/Documentation/ftrace.txt b/Documentation/ftrace.txt
index 753f4de4b175..35a78bc6651d 100644
--- a/Documentation/ftrace.txt
+++ b/Documentation/ftrace.txt
@@ -324,7 +324,7 @@ output. To see what is available, simply cat the file:
 
   cat /debug/tracing/trace_options
   print-parent nosym-offset nosym-addr noverbose noraw nohex nobin \
- noblock nostacktrace nosched-tree
+ noblock nostacktrace nosched-tree nouserstacktrace nosym-userobj
 
 To disable one of the options, echo in the option prepended with "no".
 
@@ -378,6 +378,20 @@ Here are the available options:
 		When a trace is recorded, so is the stack of functions.
 		This allows for back traces of trace sites.
 
+  userstacktrace - This option changes the trace.
+		   It records a stacktrace of the current userspace thread.
+
+  sym-userobj - when user stacktrace are enabled, look up which object the
+		address belongs to, and print a relative address
+		This is especially useful when ASLR is on, otherwise you don't
+		get a chance to resolve the address to object/file/line after the app is no
+		longer running
+
+		The lookup is performed when you read trace,trace_pipe,latency_trace. Example:
+
+		a.out-1623  [000] 40874.465068: /root/a.out[+0x480] <-/root/a.out[+0
+x494] <- /root/a.out[+0x4a8] <- /lib/libc-2.7.so[+0x1e1a6]
+
   sched-tree - TBD (any users??)
 
 
diff --git a/Documentation/tracers/mmiotrace.txt b/Documentation/tracers/mmiotrace.txt
index 5bbbe2096223..cde23b4a12a1 100644
--- a/Documentation/tracers/mmiotrace.txt
+++ b/Documentation/tracers/mmiotrace.txt
@@ -37,7 +37,7 @@ $ echo mmiotrace > /debug/tracing/current_tracer
 $ cat /debug/tracing/trace_pipe > mydump.txt &
 Start X or whatever.
 $ echo "X is up" > /debug/tracing/trace_marker
-$ echo none > /debug/tracing/current_tracer
+$ echo nop > /debug/tracing/current_tracer
 Check for lost events.
 
 
@@ -66,7 +66,7 @@ which action. It is recommended to place descriptive markers about what you
 do.
 
 Shut down mmiotrace (requires root privileges):
-$ echo none > /debug/tracing/current_tracer
+$ echo nop > /debug/tracing/current_tracer
 The 'cat' process exits. If it does not, kill it by issuing 'fg' command and
 pressing ctrl+c.
 
@@ -81,7 +81,9 @@ are:
 $ cat /debug/tracing/trace_entries
 gives you a number. Approximately double this number and write it back, for
 instance:
+$ echo 0 > /debug/tracing/tracing_enabled
 $ echo 128000 > /debug/tracing/trace_entries
+$ echo 1 > /debug/tracing/tracing_enabled
 Then start again from the top.
 
 If you are doing a trace for a driver project, e.g. Nouveau, you should also
diff --git a/arch/powerpc/include/asm/ftrace.h b/arch/powerpc/include/asm/ftrace.h
index b298f7a631e6..e5f2ae8362f7 100644
--- a/arch/powerpc/include/asm/ftrace.h
+++ b/arch/powerpc/include/asm/ftrace.h
@@ -7,7 +7,19 @@
 
 #ifndef __ASSEMBLY__
 extern void _mcount(void);
-#endif
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+static inline unsigned long ftrace_call_adjust(unsigned long addr)
+{
+       /* reloction of mcount call site is the same as the address */
+       return addr;
+}
+
+struct dyn_arch_ftrace {
+	struct module *mod;
+};
+#endif /*  CONFIG_DYNAMIC_FTRACE */
+#endif /* __ASSEMBLY__ */
 
 #endif
 
diff --git a/arch/powerpc/include/asm/module.h b/arch/powerpc/include/asm/module.h
index e5f14b13ccf0..08454880a2c0 100644
--- a/arch/powerpc/include/asm/module.h
+++ b/arch/powerpc/include/asm/module.h
@@ -34,11 +34,19 @@ struct mod_arch_specific {
 #ifdef __powerpc64__
 	unsigned int stubs_section;	/* Index of stubs section in module */
 	unsigned int toc_section;	/* What section is the TOC? */
-#else
+#ifdef CONFIG_DYNAMIC_FTRACE
+	unsigned long toc;
+	unsigned long tramp;
+#endif
+
+#else /* powerpc64 */
 	/* Indices of PLT sections within module. */
 	unsigned int core_plt_section;
 	unsigned int init_plt_section;
+#ifdef CONFIG_DYNAMIC_FTRACE
+	unsigned long tramp;
 #endif
+#endif /* powerpc64 */
 
 	/* List of BUG addresses, source line numbers and filenames */
 	struct list_head bug_list;
@@ -68,6 +76,12 @@ struct mod_arch_specific {
 #    endif	/* MODULE */
 #endif
 
+#ifdef CONFIG_DYNAMIC_FTRACE
+#    ifdef MODULE
+	asm(".section .ftrace.tramp,\"ax\",@nobits; .align 3; .previous");
+#    endif	/* MODULE */
+#endif
+
 
 struct exception_table_entry;
 void sort_ex_table(struct exception_table_entry *start,
diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c
index f4b006ed0ab1..3271cd698e4c 100644
--- a/arch/powerpc/kernel/ftrace.c
+++ b/arch/powerpc/kernel/ftrace.c
@@ -9,22 +9,30 @@
 
 #include <linux/spinlock.h>
 #include <linux/hardirq.h>
+#include <linux/uaccess.h>
+#include <linux/module.h>
 #include <linux/ftrace.h>
 #include <linux/percpu.h>
 #include <linux/init.h>
 #include <linux/list.h>
 
 #include <asm/cacheflush.h>
+#include <asm/code-patching.h>
 #include <asm/ftrace.h>
 
+#if 0
+#define DEBUGP printk
+#else
+#define DEBUGP(fmt , ...)	do { } while (0)
+#endif
 
-static unsigned int ftrace_nop = 0x60000000;
+static unsigned int ftrace_nop = PPC_NOP_INSTR;
 
 #ifdef CONFIG_PPC32
 # define GET_ADDR(addr) addr
 #else
 /* PowerPC64's functions are data that points to the functions */
-# define GET_ADDR(addr) *(unsigned long *)addr
+# define GET_ADDR(addr) (*(unsigned long *)addr)
 #endif
 
 
@@ -33,12 +41,12 @@ static unsigned int ftrace_calc_offset(long ip, long addr)
 	return (int)(addr - ip);
 }
 
-unsigned char *ftrace_nop_replace(void)
+static unsigned char *ftrace_nop_replace(void)
 {
 	return (char *)&ftrace_nop;
 }
 
-unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
+static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
 {
 	static unsigned int op;
 
@@ -68,49 +76,434 @@ unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
 # define _ASM_PTR	" .long "
 #endif
 
-int
+static int
 ftrace_modify_code(unsigned long ip, unsigned char *old_code,
 		   unsigned char *new_code)
 {
-	unsigned replaced;
-	unsigned old = *(unsigned *)old_code;
-	unsigned new = *(unsigned *)new_code;
-	int faulted = 0;
+	unsigned char replaced[MCOUNT_INSN_SIZE];
 
 	/*
 	 * Note: Due to modules and __init, code can
 	 *  disappear and change, we need to protect against faulting
-	 *  as well as code changing.
+	 *  as well as code changing. We do this by using the
+	 *  probe_kernel_* functions.
 	 *
 	 * No real locking needed, this code is run through
-	 * kstop_machine.
+	 * kstop_machine, or before SMP starts.
 	 */
-	asm volatile (
-		"1: lwz		%1, 0(%2)\n"
-		"   cmpw	%1, %5\n"
-		"   bne		2f\n"
-		"   stwu	%3, 0(%2)\n"
-		"2:\n"
-		".section .fixup, \"ax\"\n"
-		"3:	li %0, 1\n"
-		"	b 2b\n"
-		".previous\n"
-		".section __ex_table,\"a\"\n"
-		_ASM_ALIGN "\n"
-		_ASM_PTR "1b, 3b\n"
-		".previous"
-		: "=r"(faulted), "=r"(replaced)
-		: "r"(ip), "r"(new),
-		  "0"(faulted), "r"(old)
-		: "memory");
 
-	if (replaced != old && replaced != new)
-		faulted = 2;
+	/* read the text we want to modify */
+	if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE))
+		return -EFAULT;
 
-	if (!faulted)
-		flush_icache_range(ip, ip + 8);
+	/* Make sure it is what we expect it to be */
+	if (memcmp(replaced, old_code, MCOUNT_INSN_SIZE) != 0)
+		return -EINVAL;
 
-	return faulted;
+	/* replace the text with the new text */
+	if (probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE))
+		return -EPERM;
+
+	flush_icache_range(ip, ip + 8);
+
+	return 0;
+}
+
+/*
+ * Helper functions that are the same for both PPC64 and PPC32.
+ */
+static int test_24bit_addr(unsigned long ip, unsigned long addr)
+{
+	long diff;
+
+	/*
+	 * Can we get to addr from ip in 24 bits?
+	 *  (26 really, since we mulitply by 4 for 4 byte alignment)
+	 */
+	diff = addr - ip;
+
+	/*
+	 * Return true if diff is less than 1 << 25
+	 *  and greater than -1 << 26.
+	 */
+	return (diff < (1 << 25)) && (diff > (-1 << 26));
+}
+
+static int is_bl_op(unsigned int op)
+{
+	return (op & 0xfc000003) == 0x48000001;
+}
+
+static int test_offset(unsigned long offset)
+{
+	return (offset + 0x2000000 > 0x3ffffff) || ((offset & 3) != 0);
+}
+
+static unsigned long find_bl_target(unsigned long ip, unsigned int op)
+{
+	static int offset;
+
+	offset = (op & 0x03fffffc);
+	/* make it signed */
+	if (offset & 0x02000000)
+		offset |= 0xfe000000;
+
+	return ip + (long)offset;
+}
+
+static unsigned int branch_offset(unsigned long offset)
+{
+	/* return "bl ip+offset" */
+	return 0x48000001 | (offset & 0x03fffffc);
+}
+
+#ifdef CONFIG_PPC64
+static int
+__ftrace_make_nop(struct module *mod,
+		  struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned char replaced[MCOUNT_INSN_SIZE * 2];
+	unsigned int *op = (unsigned *)&replaced;
+	unsigned char jmp[8];
+	unsigned long *ptr = (unsigned long *)&jmp;
+	unsigned long ip = rec->ip;
+	unsigned long tramp;
+	int offset;
+
+	/* read where this goes */
+	if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE))
+		return -EFAULT;
+
+	/* Make sure that that this is still a 24bit jump */
+	if (!is_bl_op(*op)) {
+		printk(KERN_ERR "Not expected bl: opcode is %x\n", *op);
+		return -EINVAL;
+	}
+
+	/* lets find where the pointer goes */
+	tramp = find_bl_target(ip, *op);
+
+	/*
+	 * On PPC64 the trampoline looks like:
+	 * 0x3d, 0x82, 0x00, 0x00,    addis   r12,r2, <high>
+	 * 0x39, 0x8c, 0x00, 0x00,    addi    r12,r12, <low>
+	 *   Where the bytes 2,3,6 and 7 make up the 32bit offset
+	 *   to the TOC that holds the pointer.
+	 *   to jump to.
+	 * 0xf8, 0x41, 0x00, 0x28,    std     r2,40(r1)
+	 * 0xe9, 0x6c, 0x00, 0x20,    ld      r11,32(r12)
+	 *   The actually address is 32 bytes from the offset
+	 *   into the TOC.
+	 * 0xe8, 0x4c, 0x00, 0x28,    ld      r2,40(r12)
+	 */
+
+	DEBUGP("ip:%lx jumps to %lx r2: %lx", ip, tramp, mod->arch.toc);
+
+	/* Find where the trampoline jumps to */
+	if (probe_kernel_read(jmp, (void *)tramp, 8)) {
+		printk(KERN_ERR "Failed to read %lx\n", tramp);
+		return -EFAULT;
+	}
+
+	DEBUGP(" %08x %08x",
+	       (unsigned)(*ptr >> 32),
+	       (unsigned)*ptr);
+
+	offset = (unsigned)jmp[2] << 24 |
+		(unsigned)jmp[3] << 16 |
+		(unsigned)jmp[6] << 8 |
+		(unsigned)jmp[7];
+
+	DEBUGP(" %x ", offset);
+
+	/* get the address this jumps too */
+	tramp = mod->arch.toc + offset + 32;
+	DEBUGP("toc: %lx", tramp);
+
+	if (probe_kernel_read(jmp, (void *)tramp, 8)) {
+		printk(KERN_ERR "Failed to read %lx\n", tramp);
+		return -EFAULT;
+	}
+
+	DEBUGP(" %08x %08x\n",
+	       (unsigned)(*ptr >> 32),
+	       (unsigned)*ptr);
+
+	/* This should match what was called */
+	if (*ptr != GET_ADDR(addr)) {
+		printk(KERN_ERR "addr does not match %lx\n", *ptr);
+		return -EINVAL;
+	}
+
+	/*
+	 * We want to nop the line, but the next line is
+	 *  0xe8, 0x41, 0x00, 0x28   ld r2,40(r1)
+	 * This needs to be turned to a nop too.
+	 */
+	if (probe_kernel_read(replaced, (void *)(ip+4), MCOUNT_INSN_SIZE))
+		return -EFAULT;
+
+	if (*op != 0xe8410028) {
+		printk(KERN_ERR "Next line is not ld! (%08x)\n", *op);
+		return -EINVAL;
+	}
+
+	/*
+	 * Milton Miller pointed out that we can not blindly do nops.
+	 * If a task was preempted when calling a trace function,
+	 * the nops will remove the way to restore the TOC in r2
+	 * and the r2 TOC will get corrupted.
+	 */
+
+	/*
+	 * Replace:
+	 *   bl <tramp>  <==== will be replaced with "b 1f"
+	 *   ld r2,40(r1)
+	 *  1:
+	 */
+	op[0] = 0x48000008;	/* b +8 */
+
+	if (probe_kernel_write((void *)ip, replaced, MCOUNT_INSN_SIZE))
+		return -EPERM;
+
+	return 0;
+}
+
+#else /* !PPC64 */
+static int
+__ftrace_make_nop(struct module *mod,
+		  struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned char replaced[MCOUNT_INSN_SIZE];
+	unsigned int *op = (unsigned *)&replaced;
+	unsigned char jmp[8];
+	unsigned int *ptr = (unsigned int *)&jmp;
+	unsigned long ip = rec->ip;
+	unsigned long tramp;
+	int offset;
+
+	if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE))
+		return -EFAULT;
+
+	/* Make sure that that this is still a 24bit jump */
+	if (!is_bl_op(*op)) {
+		printk(KERN_ERR "Not expected bl: opcode is %x\n", *op);
+		return -EINVAL;
+	}
+
+	/* lets find where the pointer goes */
+	tramp = find_bl_target(ip, *op);
+
+	/*
+	 * On PPC32 the trampoline looks like:
+	 * lis r11,sym@ha
+	 * addi r11,r11,sym@l
+	 * mtctr r11
+	 * bctr
+	 */
+
+	DEBUGP("ip:%lx jumps to %lx", ip, tramp);
+
+	/* Find where the trampoline jumps to */
+	if (probe_kernel_read(jmp, (void *)tramp, 8)) {
+		printk(KERN_ERR "Failed to read %lx\n", tramp);
+		return -EFAULT;
+	}
+
+	DEBUGP(" %08x %08x ", ptr[0], ptr[1]);
+
+	tramp = (ptr[1] & 0xffff) |
+		((ptr[0] & 0xffff) << 16);
+	if (tramp & 0x8000)
+		tramp -= 0x10000;
+
+	DEBUGP(" %x ", tramp);
+
+	if (tramp != addr) {
+		printk(KERN_ERR
+		       "Trampoline location %08lx does not match addr\n",
+		       tramp);
+		return -EINVAL;
+	}
+
+	op[0] = PPC_NOP_INSTR;
+
+	if (probe_kernel_write((void *)ip, replaced, MCOUNT_INSN_SIZE))
+		return -EPERM;
+
+	return 0;
+}
+#endif /* PPC64 */
+
+int ftrace_make_nop(struct module *mod,
+		    struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned char *old, *new;
+	unsigned long ip = rec->ip;
+
+	/*
+	 * If the calling address is more that 24 bits away,
+	 * then we had to use a trampoline to make the call.
+	 * Otherwise just update the call site.
+	 */
+	if (test_24bit_addr(ip, addr)) {
+		/* within range */
+		old = ftrace_call_replace(ip, addr);
+		new = ftrace_nop_replace();
+		return ftrace_modify_code(ip, old, new);
+	}
+
+	/*
+	 * Out of range jumps are called from modules.
+	 * We should either already have a pointer to the module
+	 * or it has been passed in.
+	 */
+	if (!rec->arch.mod) {
+		if (!mod) {
+			printk(KERN_ERR "No module loaded addr=%lx\n",
+			       addr);
+			return -EFAULT;
+		}
+		rec->arch.mod = mod;
+	} else if (mod) {
+		if (mod != rec->arch.mod) {
+			printk(KERN_ERR
+			       "Record mod %p not equal to passed in mod %p\n",
+			       rec->arch.mod, mod);
+			return -EINVAL;
+		}
+		/* nothing to do if mod == rec->arch.mod */
+	} else
+		mod = rec->arch.mod;
+
+	return __ftrace_make_nop(mod, rec, addr);
+
+}
+
+#ifdef CONFIG_PPC64
+static int
+__ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned char replaced[MCOUNT_INSN_SIZE * 2];
+	unsigned int *op = (unsigned *)&replaced;
+	unsigned long ip = rec->ip;
+	unsigned long offset;
+
+	/* read where this goes */
+	if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE * 2))
+		return -EFAULT;
+
+	/*
+	 * It should be pointing to two nops or
+	 *  b +8; ld r2,40(r1)
+	 */
+	if (((op[0] != 0x48000008) || (op[1] != 0xe8410028)) &&
+	    ((op[0] != PPC_NOP_INSTR) || (op[1] != PPC_NOP_INSTR))) {
+		printk(KERN_ERR "Expected NOPs but have %x %x\n", op[0], op[1]);
+		return -EINVAL;
+	}
+
+	/* If we never set up a trampoline to ftrace_caller, then bail */
+	if (!rec->arch.mod->arch.tramp) {
+		printk(KERN_ERR "No ftrace trampoline\n");
+		return -EINVAL;
+	}
+
+	/* now calculate a jump to the ftrace caller trampoline */
+	offset = rec->arch.mod->arch.tramp - ip;
+
+	if (test_offset(offset)) {
+		printk(KERN_ERR "REL24 %li out of range!\n",
+		       (long int)offset);
+		return -EINVAL;
+	}
+
+	/* Set to "bl addr" */
+	op[0] = branch_offset(offset);
+	/* ld r2,40(r1) */
+	op[1] = 0xe8410028;
+
+	DEBUGP("write to %lx\n", rec->ip);
+
+	if (probe_kernel_write((void *)ip, replaced, MCOUNT_INSN_SIZE * 2))
+		return -EPERM;
+
+	return 0;
+}
+#else
+static int
+__ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned char replaced[MCOUNT_INSN_SIZE];
+	unsigned int *op = (unsigned *)&replaced;
+	unsigned long ip = rec->ip;
+	unsigned long offset;
+
+	/* read where this goes */
+	if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE))
+		return -EFAULT;
+
+	/* It should be pointing to a nop */
+	if (op[0] != PPC_NOP_INSTR) {
+		printk(KERN_ERR "Expected NOP but have %x\n", op[0]);
+		return -EINVAL;
+	}
+
+	/* If we never set up a trampoline to ftrace_caller, then bail */
+	if (!rec->arch.mod->arch.tramp) {
+		printk(KERN_ERR "No ftrace trampoline\n");
+		return -EINVAL;
+	}
+
+	/* now calculate a jump to the ftrace caller trampoline */
+	offset = rec->arch.mod->arch.tramp - ip;
+
+	if (test_offset(offset)) {
+		printk(KERN_ERR "REL24 %li out of range!\n",
+		       (long int)offset);
+		return -EINVAL;
+	}
+
+	/* Set to "bl addr" */
+	op[0] = branch_offset(offset);
+
+	DEBUGP("write to %lx\n", rec->ip);
+
+	if (probe_kernel_write((void *)ip, replaced, MCOUNT_INSN_SIZE))
+		return -EPERM;
+
+	return 0;
+}
+#endif /* CONFIG_PPC64 */
+
+int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned char *old, *new;
+	unsigned long ip = rec->ip;
+
+	/*
+	 * If the calling address is more that 24 bits away,
+	 * then we had to use a trampoline to make the call.
+	 * Otherwise just update the call site.
+	 */
+	if (test_24bit_addr(ip, addr)) {
+		/* within range */
+		old = ftrace_nop_replace();
+		new = ftrace_call_replace(ip, addr);
+		return ftrace_modify_code(ip, old, new);
+	}
+
+	/*
+	 * Out of range jumps are called from modules.
+	 * Being that we are converting from nop, it had better
+	 * already have a module defined.
+	 */
+	if (!rec->arch.mod) {
+		printk(KERN_ERR "No module loaded\n");
+		return -EINVAL;
+	}
+
+	return __ftrace_make_call(rec, addr);
 }
 
 int ftrace_update_ftrace_func(ftrace_func_t func)
@@ -128,10 +521,10 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 
 int __init ftrace_dyn_arch_init(void *data)
 {
-	/* This is running in kstop_machine */
+	/* caller expects data to be zero */
+	unsigned long *p = data;
 
-	ftrace_mcount_set(data);
+	*p = 0;
 
 	return 0;
 }
-
diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c
index 31982d05d81a..88d9c1d5e5fb 100644
--- a/arch/powerpc/kernel/idle.c
+++ b/arch/powerpc/kernel/idle.c
@@ -69,10 +69,15 @@ void cpu_idle(void)
 				smp_mb();
 				local_irq_disable();
 
+				/* Don't trace irqs off for idle */
+				stop_critical_timings();
+
 				/* check again after disabling irqs */
 				if (!need_resched() && !cpu_should_die())
 					ppc_md.power_save();
 
+				start_critical_timings();
+
 				local_irq_enable();
 				set_thread_flag(TIF_POLLING_NRFLAG);
 
diff --git a/arch/powerpc/kernel/module_32.c b/arch/powerpc/kernel/module_32.c
index 2df91a03462a..f832773fc28e 100644
--- a/arch/powerpc/kernel/module_32.c
+++ b/arch/powerpc/kernel/module_32.c
@@ -22,6 +22,7 @@
 #include <linux/fs.h>
 #include <linux/string.h>
 #include <linux/kernel.h>
+#include <linux/ftrace.h>
 #include <linux/cache.h>
 #include <linux/bug.h>
 #include <linux/sort.h>
@@ -53,6 +54,9 @@ static unsigned int count_relocs(const Elf32_Rela *rela, unsigned int num)
 			r_addend = rela[i].r_addend;
 		}
 
+#ifdef CONFIG_DYNAMIC_FTRACE
+	_count_relocs++;	/* add one for ftrace_caller */
+#endif
 	return _count_relocs;
 }
 
@@ -306,5 +310,11 @@ int apply_relocate_add(Elf32_Shdr *sechdrs,
 			return -ENOEXEC;
 		}
 	}
+#ifdef CONFIG_DYNAMIC_FTRACE
+	module->arch.tramp =
+		do_plt_call(module->module_core,
+			    (unsigned long)ftrace_caller,
+			    sechdrs, module);
+#endif
 	return 0;
 }
diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c
index 1af2377e4992..8992b031a7b6 100644
--- a/arch/powerpc/kernel/module_64.c
+++ b/arch/powerpc/kernel/module_64.c
@@ -20,6 +20,7 @@
 #include <linux/moduleloader.h>
 #include <linux/err.h>
 #include <linux/vmalloc.h>
+#include <linux/ftrace.h>
 #include <linux/bug.h>
 #include <asm/module.h>
 #include <asm/firmware.h>
@@ -163,6 +164,11 @@ static unsigned long get_stubs_size(const Elf64_Ehdr *hdr,
 		}
 	}
 
+#ifdef CONFIG_DYNAMIC_FTRACE
+	/* make the trampoline to the ftrace_caller */
+	relocs++;
+#endif
+
 	DEBUGP("Looks like a total of %lu stubs, max\n", relocs);
 	return relocs * sizeof(struct ppc64_stub_entry);
 }
@@ -441,5 +447,12 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 		}
 	}
 
+#ifdef CONFIG_DYNAMIC_FTRACE
+	me->arch.toc = my_r2(sechdrs, me);
+	me->arch.tramp = stub_for_addr(sechdrs,
+				       (unsigned long)ftrace_caller,
+				       me);
+#endif
+
 	return 0;
 }
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 7a146baaa990..e49a4fd718fe 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -36,6 +36,7 @@ config X86
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_GENERIC_DMA_COHERENT if X86_32
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
+	select USER_STACKTRACE_SUPPORT
 
 config ARCH_DEFCONFIG
 	string
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index 2bb43b433e07..754a3e082f94 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -29,7 +29,6 @@ struct dyn_arch_ftrace {
 #endif /* CONFIG_FUNCTION_TRACER */
 
 #ifdef CONFIG_FUNCTION_RET_TRACER
-#define FTRACE_RET_STACK_SIZE 20
 
 #ifndef __ASSEMBLY__
 
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index e90e81ef6ab9..0921b4018c11 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -40,36 +40,8 @@ struct thread_info {
 						*/
 	__u8			supervisor_stack[0];
 #endif
-
-#ifdef CONFIG_FUNCTION_RET_TRACER
-	/* Index of current stored adress in ret_stack */
-	int		curr_ret_stack;
-	/* Stack of return addresses for return function tracing */
-	struct ftrace_ret_stack	ret_stack[FTRACE_RET_STACK_SIZE];
-	/*
-	 * Number of functions that haven't been traced
-	 * because of depth overrun.
-	 */
-	atomic_t	trace_overrun;
-#endif
 };
 
-#ifdef CONFIG_FUNCTION_RET_TRACER
-#define INIT_THREAD_INFO(tsk)			\
-{						\
-	.task		= &tsk,			\
-	.exec_domain	= &default_exec_domain,	\
-	.flags		= 0,			\
-	.cpu		= 0,			\
-	.preempt_count	= 1,			\
-	.addr_limit	= KERNEL_DS,		\
-	.restart_block = {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
-	.curr_ret_stack = -1,\
-	.trace_overrun	= ATOMIC_INIT(0)	\
-}
-#else
 #define INIT_THREAD_INFO(tsk)			\
 {						\
 	.task		= &tsk,			\
@@ -82,7 +54,6 @@ struct thread_info {
 		.fn = do_no_restart_syscall,	\
 	},					\
 }
-#endif
 
 #define init_thread_info	(init_thread_union.thread_info)
 #define init_stack		(init_thread_union.stack)
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 356bb1eb6e9a..bb137f7297ed 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -350,19 +350,21 @@ static int push_return_trace(unsigned long ret, unsigned long long time,
 				unsigned long func)
 {
 	int index;
-	struct thread_info *ti = current_thread_info();
+
+	if (!current->ret_stack)
+		return -EBUSY;
 
 	/* The return trace stack is full */
-	if (ti->curr_ret_stack == FTRACE_RET_STACK_SIZE - 1) {
-		atomic_inc(&ti->trace_overrun);
+	if (current->curr_ret_stack == FTRACE_RETFUNC_DEPTH - 1) {
+		atomic_inc(&current->trace_overrun);
 		return -EBUSY;
 	}
 
-	index = ++ti->curr_ret_stack;
+	index = ++current->curr_ret_stack;
 	barrier();
-	ti->ret_stack[index].ret = ret;
-	ti->ret_stack[index].func = func;
-	ti->ret_stack[index].calltime = time;
+	current->ret_stack[index].ret = ret;
+	current->ret_stack[index].func = func;
+	current->ret_stack[index].calltime = time;
 
 	return 0;
 }
@@ -373,13 +375,12 @@ static void pop_return_trace(unsigned long *ret, unsigned long long *time,
 {
 	int index;
 
-	struct thread_info *ti = current_thread_info();
-	index = ti->curr_ret_stack;
-	*ret = ti->ret_stack[index].ret;
-	*func = ti->ret_stack[index].func;
-	*time = ti->ret_stack[index].calltime;
-	*overrun = atomic_read(&ti->trace_overrun);
-	ti->curr_ret_stack--;
+	index = current->curr_ret_stack;
+	*ret = current->ret_stack[index].ret;
+	*func = current->ret_stack[index].func;
+	*time = current->ret_stack[index].calltime;
+	*overrun = atomic_read(&current->trace_overrun);
+	current->curr_ret_stack--;
 }
 
 /*
diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index a03e7f6d90c3..10786af95545 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -6,6 +6,7 @@
 #include <linux/sched.h>
 #include <linux/stacktrace.h>
 #include <linux/module.h>
+#include <linux/uaccess.h>
 #include <asm/stacktrace.h>
 
 static void save_stack_warning(void *data, char *msg)
@@ -83,3 +84,66 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 		trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
 EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
+
+/* Userspace stacktrace - based on kernel/trace/trace_sysprof.c */
+
+struct stack_frame {
+	const void __user	*next_fp;
+	unsigned long		ret_addr;
+};
+
+static int copy_stack_frame(const void __user *fp, struct stack_frame *frame)
+{
+	int ret;
+
+	if (!access_ok(VERIFY_READ, fp, sizeof(*frame)))
+		return 0;
+
+	ret = 1;
+	pagefault_disable();
+	if (__copy_from_user_inatomic(frame, fp, sizeof(*frame)))
+		ret = 0;
+	pagefault_enable();
+
+	return ret;
+}
+
+static inline void __save_stack_trace_user(struct stack_trace *trace)
+{
+	const struct pt_regs *regs = task_pt_regs(current);
+	const void __user *fp = (const void __user *)regs->bp;
+
+	if (trace->nr_entries < trace->max_entries)
+		trace->entries[trace->nr_entries++] = regs->ip;
+
+	while (trace->nr_entries < trace->max_entries) {
+		struct stack_frame frame;
+
+		frame.next_fp = NULL;
+		frame.ret_addr = 0;
+		if (!copy_stack_frame(fp, &frame))
+			break;
+		if ((unsigned long)fp < regs->sp)
+			break;
+		if (frame.ret_addr) {
+			trace->entries[trace->nr_entries++] =
+				frame.ret_addr;
+		}
+		if (fp == frame.next_fp)
+			break;
+		fp = frame.next_fp;
+	}
+}
+
+void save_stack_trace_user(struct stack_trace *trace)
+{
+	/*
+	 * Trace user stack if we are not a kernel thread
+	 */
+	if (current->mm) {
+		__save_stack_trace_user(trace);
+	}
+	if (trace->nr_entries < trace->max_entries)
+		trace->entries[trace->nr_entries++] = ULONG_MAX;
+}
+
diff --git a/fs/seq_file.c b/fs/seq_file.c
index eba2eabcd2b8..f03220d7891b 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -357,7 +357,18 @@ int seq_printf(struct seq_file *m, const char *f, ...)
 }
 EXPORT_SYMBOL(seq_printf);
 
-static char *mangle_path(char *s, char *p, char *esc)
+/**
+ *	mangle_path -	mangle and copy path to buffer beginning
+ *	@s: buffer start
+ *	@p: beginning of path in above buffer
+ *	@esc: set of characters that need escaping
+ *
+ *      Copy the path from @p to @s, replacing each occurrence of character from
+ *      @esc with usual octal escape.
+ *      Returns pointer past last written character in @s, or NULL in case of
+ *      failure.
+ */
+char *mangle_path(char *s, char *p, char *esc)
 {
 	while (s <= p) {
 		char c = *p++;
@@ -376,6 +387,7 @@ static char *mangle_path(char *s, char *p, char *esc)
 	}
 	return NULL;
 }
+EXPORT_SYMBOL_GPL(mangle_path);
 
 /*
  * return the absolute path of 'dentry' residing in mount 'mnt'.
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index f7ba4ea5e128..7854d87b97b2 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -257,6 +257,7 @@ extern int ftrace_dump_on_oops;
 
 extern void tracing_start(void);
 extern void tracing_stop(void);
+extern void ftrace_off_permanent(void);
 
 extern void
 ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3);
@@ -290,6 +291,7 @@ ftrace_printk(const char *fmt, ...) __attribute__ ((format (printf, 1, 0)));
 
 static inline void tracing_start(void) { }
 static inline void tracing_stop(void) { }
+static inline void ftrace_off_permanent(void) { }
 static inline int
 ftrace_printk(const char *fmt, ...)
 {
@@ -323,6 +325,8 @@ struct ftrace_retfunc {
 };
 
 #ifdef CONFIG_FUNCTION_RET_TRACER
+#define FTRACE_RETFUNC_DEPTH 50
+#define FTRACE_RETSTACK_ALLOC_SIZE 32
 /* Type of a callback handler of tracing return function */
 typedef void (*trace_function_return_t)(struct ftrace_retfunc *);
 
@@ -330,6 +334,12 @@ extern int register_ftrace_return(trace_function_return_t func);
 /* The current handler in use */
 extern trace_function_return_t ftrace_function_return;
 extern void unregister_ftrace_return(void);
+
+extern void ftrace_retfunc_init_task(struct task_struct *t);
+extern void ftrace_retfunc_exit_task(struct task_struct *t);
+#else
+static inline void ftrace_retfunc_init_task(struct task_struct *t) { }
+static inline void ftrace_retfunc_exit_task(struct task_struct *t) { }
 #endif
 
 #endif /* _LINUX_FTRACE_H */
diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index e097c2e6b6dc..3bb87a753fa3 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -122,6 +122,7 @@ void ring_buffer_normalize_time_stamp(int cpu, u64 *ts);
 
 void tracing_on(void);
 void tracing_off(void);
+void tracing_off_permanent(void);
 
 enum ring_buffer_flags {
 	RB_FL_OVERWRITE		= 1 << 0,
diff --git a/include/linux/sched.h b/include/linux/sched.h
index c8e0db464206..bee1e93c95ad 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1352,6 +1352,17 @@ struct task_struct {
 	unsigned long default_timer_slack_ns;
 
 	struct list_head	*scm_work_list;
+#ifdef CONFIG_FUNCTION_RET_TRACER
+	/* Index of current stored adress in ret_stack */
+	int curr_ret_stack;
+	/* Stack of return addresses for return function tracing */
+	struct ftrace_ret_stack	*ret_stack;
+	/*
+	 * Number of functions that haven't been traced
+	 * because of depth overrun.
+	 */
+	atomic_t trace_overrun;
+#endif
 };
 
 /*
@@ -2006,18 +2017,6 @@ static inline void setup_thread_stack(struct task_struct *p, struct task_struct
 {
 	*task_thread_info(p) = *task_thread_info(org);
 	task_thread_info(p)->task = p;
-
-#ifdef CONFIG_FUNCTION_RET_TRACER
-	/*
-	 * When fork() creates a child process, this function is called.
-	 * But the child task may not inherit the return adresses traced
-	 * by the return function tracer because it will directly execute
-	 * in userspace and will not return to kernel functions its parent
-	 * used.
-	 */
-	task_thread_info(p)->curr_ret_stack = -1;
-	atomic_set(&task_thread_info(p)->trace_overrun, 0);
-#endif
 }
 
 static inline unsigned long *end_of_stack(struct task_struct *p)
diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h
index dc50bcc282a8..b3dfa72f13b9 100644
--- a/include/linux/seq_file.h
+++ b/include/linux/seq_file.h
@@ -34,6 +34,7 @@ struct seq_operations {
 
 #define SEQ_SKIP 1
 
+char *mangle_path(char *s, char *p, char *esc);
 int seq_open(struct file *, const struct seq_operations *);
 ssize_t seq_read(struct file *, char __user *, size_t, loff_t *);
 loff_t seq_lseek(struct file *, loff_t, int);
diff --git a/include/linux/stacktrace.h b/include/linux/stacktrace.h
index b106fd8e0d5c..1a8cecc4f38c 100644
--- a/include/linux/stacktrace.h
+++ b/include/linux/stacktrace.h
@@ -15,9 +15,17 @@ extern void save_stack_trace_tsk(struct task_struct *tsk,
 				struct stack_trace *trace);
 
 extern void print_stack_trace(struct stack_trace *trace, int spaces);
+
+#ifdef CONFIG_USER_STACKTRACE_SUPPORT
+extern void save_stack_trace_user(struct stack_trace *trace);
+#else
+# define save_stack_trace_user(trace)              do { } while (0)
+#endif
+
 #else
 # define save_stack_trace(trace)			do { } while (0)
 # define save_stack_trace_tsk(tsk, trace)		do { } while (0)
+# define save_stack_trace_user(trace)			do { } while (0)
 # define print_stack_trace(trace, spaces)		do { } while (0)
 #endif
 
diff --git a/init/main.c b/init/main.c
index e810196bf2f2..79213c0785d2 100644
--- a/init/main.c
+++ b/init/main.c
@@ -723,7 +723,7 @@ int do_one_initcall(initcall_t fn)
 		disable_boot_trace();
 		rettime = ktime_get();
 		delta = ktime_sub(rettime, calltime);
-		ret.duration = (unsigned long long) delta.tv64 >> 10;
+		ret.duration = (unsigned long long) ktime_to_ns(delta) >> 10;
 		trace_boot_ret(&ret, fn);
 		printk("initcall %pF returned %d after %Ld usecs\n", fn,
 			ret.result, ret.duration);
diff --git a/kernel/exit.c b/kernel/exit.c
index 35c8ec2ba03a..e5ae36ebe8af 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1127,7 +1127,6 @@ NORET_TYPE void do_exit(long code)
 	preempt_disable();
 	/* causes final put_task_struct in finish_task_switch(). */
 	tsk->state = TASK_DEAD;
-
 	schedule();
 	BUG();
 	/* Avoid "noreturn function does return".  */
diff --git a/kernel/fork.c b/kernel/fork.c
index ac62f43ee430..d6e1a3205f62 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -47,6 +47,7 @@
 #include <linux/mount.h>
 #include <linux/audit.h>
 #include <linux/memcontrol.h>
+#include <linux/ftrace.h>
 #include <linux/profile.h>
 #include <linux/rmap.h>
 #include <linux/acct.h>
@@ -139,6 +140,7 @@ void free_task(struct task_struct *tsk)
 	prop_local_destroy_single(&tsk->dirties);
 	free_thread_info(tsk->stack);
 	rt_mutex_debug_task_free(tsk);
+	ftrace_retfunc_exit_task(tsk);
 	free_task_struct(tsk);
 }
 EXPORT_SYMBOL(free_task);
@@ -1269,6 +1271,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	total_forks++;
 	spin_unlock(&current->sighand->siglock);
 	write_unlock_irq(&tasklist_lock);
+	ftrace_retfunc_init_task(p);
 	proc_fork_connector(p);
 	cgroup_post_fork(p);
 	return p;
diff --git a/kernel/power/disk.c b/kernel/power/disk.c
index c9d74083746f..f77d3819ef57 100644
--- a/kernel/power/disk.c
+++ b/kernel/power/disk.c
@@ -22,7 +22,6 @@
 #include <linux/console.h>
 #include <linux/cpu.h>
 #include <linux/freezer.h>
-#include <linux/ftrace.h>
 
 #include "power.h"
 
@@ -257,7 +256,7 @@ static int create_image(int platform_mode)
 
 int hibernation_snapshot(int platform_mode)
 {
-	int error, ftrace_save;
+	int error;
 
 	/* Free memory before shutting down devices. */
 	error = swsusp_shrink_memory();
@@ -269,7 +268,6 @@ int hibernation_snapshot(int platform_mode)
 		goto Close;
 
 	suspend_console();
-	ftrace_save = __ftrace_enabled_save();
 	error = device_suspend(PMSG_FREEZE);
 	if (error)
 		goto Recover_platform;
@@ -299,7 +297,6 @@ int hibernation_snapshot(int platform_mode)
  Resume_devices:
 	device_resume(in_suspend ?
 		(error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE);
-	__ftrace_enabled_restore(ftrace_save);
 	resume_console();
  Close:
 	platform_end(platform_mode);
@@ -370,11 +367,10 @@ static int resume_target_kernel(void)
 
 int hibernation_restore(int platform_mode)
 {
-	int error, ftrace_save;
+	int error;
 
 	pm_prepare_console();
 	suspend_console();
-	ftrace_save = __ftrace_enabled_save();
 	error = device_suspend(PMSG_QUIESCE);
 	if (error)
 		goto Finish;
@@ -389,7 +385,6 @@ int hibernation_restore(int platform_mode)
 	platform_restore_cleanup(platform_mode);
 	device_resume(PMSG_RECOVER);
  Finish:
-	__ftrace_enabled_restore(ftrace_save);
 	resume_console();
 	pm_restore_console();
 	return error;
@@ -402,7 +397,7 @@ int hibernation_restore(int platform_mode)
 
 int hibernation_platform_enter(void)
 {
-	int error, ftrace_save;
+	int error;
 
 	if (!hibernation_ops)
 		return -ENOSYS;
@@ -417,7 +412,6 @@ int hibernation_platform_enter(void)
 		goto Close;
 
 	suspend_console();
-	ftrace_save = __ftrace_enabled_save();
 	error = device_suspend(PMSG_HIBERNATE);
 	if (error) {
 		if (hibernation_ops->recover)
@@ -452,7 +446,6 @@ int hibernation_platform_enter(void)
 	hibernation_ops->finish();
  Resume_devices:
 	device_resume(PMSG_RESTORE);
-	__ftrace_enabled_restore(ftrace_save);
 	resume_console();
  Close:
 	hibernation_ops->end();
diff --git a/kernel/power/main.c b/kernel/power/main.c
index b8f7ce9473e8..613f16941b85 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -22,7 +22,6 @@
 #include <linux/freezer.h>
 #include <linux/vmstat.h>
 #include <linux/syscalls.h>
-#include <linux/ftrace.h>
 
 #include "power.h"
 
@@ -317,7 +316,7 @@ static int suspend_enter(suspend_state_t state)
  */
 int suspend_devices_and_enter(suspend_state_t state)
 {
-	int error, ftrace_save;
+	int error;
 
 	if (!suspend_ops)
 		return -ENOSYS;
@@ -328,7 +327,6 @@ int suspend_devices_and_enter(suspend_state_t state)
 			goto Close;
 	}
 	suspend_console();
-	ftrace_save = __ftrace_enabled_save();
 	suspend_test_start();
 	error = device_suspend(PMSG_SUSPEND);
 	if (error) {
@@ -360,7 +358,6 @@ int suspend_devices_and_enter(suspend_state_t state)
 	suspend_test_start();
 	device_resume(PMSG_RESUME);
 	suspend_test_finish("resume devices");
-	__ftrace_enabled_restore(ftrace_save);
 	resume_console();
  Close:
 	if (suspend_ops->end)
diff --git a/kernel/sched.c b/kernel/sched.c
index 4de56108c86f..388d9db044ab 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -5901,6 +5901,7 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu)
 	 * The idle tasks have their own, simple scheduling class:
 	 */
 	idle->sched_class = &idle_sched_class;
+	ftrace_retfunc_init_task(idle);
 }
 
 /*
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 61e8cca6ff45..9cbf7761f498 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -3,6 +3,9 @@
 #  select HAVE_FUNCTION_TRACER:
 #
 
+config USER_STACKTRACE_SUPPORT
+	bool
+
 config NOP_TRACER
 	bool
 
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index f212da486689..53042f118f23 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1498,10 +1498,77 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
 
 #ifdef CONFIG_FUNCTION_RET_TRACER
 
+static atomic_t ftrace_retfunc_active;
+
 /* The callback that hooks the return of a function */
 trace_function_return_t ftrace_function_return =
 			(trace_function_return_t)ftrace_stub;
 
+
+/* Try to assign a return stack array on FTRACE_RETSTACK_ALLOC_SIZE tasks. */
+static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list)
+{
+	int i;
+	int ret = 0;
+	unsigned long flags;
+	int start = 0, end = FTRACE_RETSTACK_ALLOC_SIZE;
+	struct task_struct *g, *t;
+
+	for (i = 0; i < FTRACE_RETSTACK_ALLOC_SIZE; i++) {
+		ret_stack_list[i] = kmalloc(FTRACE_RETFUNC_DEPTH
+					* sizeof(struct ftrace_ret_stack),
+					GFP_KERNEL);
+		if (!ret_stack_list[i]) {
+			start = 0;
+			end = i;
+			ret = -ENOMEM;
+			goto free;
+		}
+	}
+
+	read_lock_irqsave(&tasklist_lock, flags);
+	do_each_thread(g, t) {
+		if (start == end) {
+			ret = -EAGAIN;
+			goto unlock;
+		}
+
+		if (t->ret_stack == NULL) {
+			t->ret_stack = ret_stack_list[start++];
+			t->curr_ret_stack = -1;
+			atomic_set(&t->trace_overrun, 0);
+		}
+	} while_each_thread(g, t);
+
+unlock:
+	read_unlock_irqrestore(&tasklist_lock, flags);
+free:
+	for (i = start; i < end; i++)
+		kfree(ret_stack_list[i]);
+	return ret;
+}
+
+/* Allocate a return stack for each task */
+static int start_return_tracing(void)
+{
+	struct ftrace_ret_stack **ret_stack_list;
+	int ret;
+
+	ret_stack_list = kmalloc(FTRACE_RETSTACK_ALLOC_SIZE *
+				sizeof(struct ftrace_ret_stack *),
+				GFP_KERNEL);
+
+	if (!ret_stack_list)
+		return -ENOMEM;
+
+	do {
+		ret = alloc_retstack_tasklist(ret_stack_list);
+	} while (ret == -EAGAIN);
+
+	kfree(ret_stack_list);
+	return ret;
+}
+
 int register_ftrace_return(trace_function_return_t func)
 {
 	int ret = 0;
@@ -1516,7 +1583,12 @@ int register_ftrace_return(trace_function_return_t func)
 		ret = -EBUSY;
 		goto out;
 	}
-
+	atomic_inc(&ftrace_retfunc_active);
+	ret = start_return_tracing();
+	if (ret) {
+		atomic_dec(&ftrace_retfunc_active);
+		goto out;
+	}
 	ftrace_tracing_type = FTRACE_TYPE_RETURN;
 	ftrace_function_return = func;
 	ftrace_startup();
@@ -1530,6 +1602,7 @@ void unregister_ftrace_return(void)
 {
 	mutex_lock(&ftrace_sysctl_lock);
 
+	atomic_dec(&ftrace_retfunc_active);
 	ftrace_function_return = (trace_function_return_t)ftrace_stub;
 	ftrace_shutdown();
 	/* Restore normal tracing type */
@@ -1537,6 +1610,32 @@ void unregister_ftrace_return(void)
 
 	mutex_unlock(&ftrace_sysctl_lock);
 }
+
+/* Allocate a return stack for newly created task */
+void ftrace_retfunc_init_task(struct task_struct *t)
+{
+	if (atomic_read(&ftrace_retfunc_active)) {
+		t->ret_stack = kmalloc(FTRACE_RETFUNC_DEPTH
+				* sizeof(struct ftrace_ret_stack),
+				GFP_KERNEL);
+		if (!t->ret_stack)
+			return;
+		t->curr_ret_stack = -1;
+		atomic_set(&t->trace_overrun, 0);
+	} else
+		t->ret_stack = NULL;
+}
+
+void ftrace_retfunc_exit_task(struct task_struct *t)
+{
+	struct ftrace_ret_stack	*ret_stack = t->ret_stack;
+
+	t->ret_stack = NULL;
+	/* NULL must become visible to IRQs before we free it: */
+	barrier();
+
+	kfree(ret_stack);
+}
 #endif
 
 
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 85ced143c2c4..e206951603c1 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -18,8 +18,46 @@
 
 #include "trace.h"
 
-/* Global flag to disable all recording to ring buffers */
-static int ring_buffers_off __read_mostly;
+/*
+ * A fast way to enable or disable all ring buffers is to
+ * call tracing_on or tracing_off. Turning off the ring buffers
+ * prevents all ring buffers from being recorded to.
+ * Turning this switch on, makes it OK to write to the
+ * ring buffer, if the ring buffer is enabled itself.
+ *
+ * There's three layers that must be on in order to write
+ * to the ring buffer.
+ *
+ * 1) This global flag must be set.
+ * 2) The ring buffer must be enabled for recording.
+ * 3) The per cpu buffer must be enabled for recording.
+ *
+ * In case of an anomaly, this global flag has a bit set that
+ * will permantly disable all ring buffers.
+ */
+
+/*
+ * Global flag to disable all recording to ring buffers
+ *  This has two bits: ON, DISABLED
+ *
+ *  ON   DISABLED
+ * ---- ----------
+ *   0      0        : ring buffers are off
+ *   1      0        : ring buffers are on
+ *   X      1        : ring buffers are permanently disabled
+ */
+
+enum {
+	RB_BUFFERS_ON_BIT	= 0,
+	RB_BUFFERS_DISABLED_BIT	= 1,
+};
+
+enum {
+	RB_BUFFERS_ON		= 1 << RB_BUFFERS_ON_BIT,
+	RB_BUFFERS_DISABLED	= 1 << RB_BUFFERS_DISABLED_BIT,
+};
+
+static long ring_buffer_flags __read_mostly = RB_BUFFERS_ON;
 
 /**
  * tracing_on - enable all tracing buffers
@@ -29,7 +67,7 @@ static int ring_buffers_off __read_mostly;
  */
 void tracing_on(void)
 {
-	ring_buffers_off = 0;
+	set_bit(RB_BUFFERS_ON_BIT, &ring_buffer_flags);
 }
 
 /**
@@ -42,7 +80,18 @@ void tracing_on(void)
  */
 void tracing_off(void)
 {
-	ring_buffers_off = 1;
+	clear_bit(RB_BUFFERS_ON_BIT, &ring_buffer_flags);
+}
+
+/**
+ * tracing_off_permanent - permanently disable ring buffers
+ *
+ * This function, once called, will disable all ring buffers
+ * permanenty.
+ */
+void tracing_off_permanent(void)
+{
+	set_bit(RB_BUFFERS_DISABLED_BIT, &ring_buffer_flags);
 }
 
 #include "trace.h"
@@ -1185,7 +1234,7 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer,
 	struct ring_buffer_event *event;
 	int cpu, resched;
 
-	if (ring_buffers_off)
+	if (ring_buffer_flags != RB_BUFFERS_ON)
 		return NULL;
 
 	if (atomic_read(&buffer->record_disabled))
@@ -1297,7 +1346,7 @@ int ring_buffer_write(struct ring_buffer *buffer,
 	int ret = -EBUSY;
 	int cpu, resched;
 
-	if (ring_buffers_off)
+	if (ring_buffer_flags != RB_BUFFERS_ON)
 		return -EBUSY;
 
 	if (atomic_read(&buffer->record_disabled))
@@ -2178,12 +2227,14 @@ static ssize_t
 rb_simple_read(struct file *filp, char __user *ubuf,
 	       size_t cnt, loff_t *ppos)
 {
-	int *p = filp->private_data;
+	long *p = filp->private_data;
 	char buf[64];
 	int r;
 
-	/* !ring_buffers_off == tracing_on */
-	r = sprintf(buf, "%d\n", !*p);
+	if (test_bit(RB_BUFFERS_DISABLED_BIT, p))
+		r = sprintf(buf, "permanently disabled\n");
+	else
+		r = sprintf(buf, "%d\n", test_bit(RB_BUFFERS_ON_BIT, p));
 
 	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
 }
@@ -2192,7 +2243,7 @@ static ssize_t
 rb_simple_write(struct file *filp, const char __user *ubuf,
 		size_t cnt, loff_t *ppos)
 {
-	int *p = filp->private_data;
+	long *p = filp->private_data;
 	char buf[64];
 	long val;
 	int ret;
@@ -2209,8 +2260,10 @@ rb_simple_write(struct file *filp, const char __user *ubuf,
 	if (ret < 0)
 		return ret;
 
-	/* !ring_buffers_off == tracing_on */
-	*p = !val;
+	if (val)
+		set_bit(RB_BUFFERS_ON_BIT, p);
+	else
+		clear_bit(RB_BUFFERS_ON_BIT, p);
 
 	(*ppos)++;
 
@@ -2232,7 +2285,7 @@ static __init int rb_init_debugfs(void)
 	d_tracer = tracing_init_dentry();
 
 	entry = debugfs_create_file("tracing_on", 0644, d_tracer,
-				    &ring_buffers_off, &rb_simple_fops);
+				    &ring_buffer_flags, &rb_simple_fops);
 	if (!entry)
 		pr_warning("Could not create debugfs 'tracing_on' entry\n");
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 4ee6f0375222..a45b59e53fbc 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -30,6 +30,7 @@
 #include <linux/gfp.h>
 #include <linux/fs.h>
 #include <linux/kprobes.h>
+#include <linux/seq_file.h>
 #include <linux/writeback.h>
 
 #include <linux/stacktrace.h>
@@ -275,6 +276,8 @@ static const char *trace_options[] = {
 	"ftrace_preempt",
 	"branch",
 	"annotate",
+	"userstacktrace",
+	"sym-userobj",
 	NULL
 };
 
@@ -421,6 +424,28 @@ trace_seq_putmem_hex(struct trace_seq *s, void *mem, size_t len)
 	return trace_seq_putmem(s, hex, j);
 }
 
+static int
+trace_seq_path(struct trace_seq *s, struct path *path)
+{
+	unsigned char *p;
+
+	if (s->len >= (PAGE_SIZE - 1))
+		return 0;
+	p = d_path(path, s->buffer + s->len, PAGE_SIZE - s->len);
+	if (!IS_ERR(p)) {
+		p = mangle_path(s->buffer + s->len, p, "\n");
+		if (p) {
+			s->len = p - s->buffer;
+			return 1;
+		}
+	} else {
+		s->buffer[s->len++] = '?';
+		return 1;
+	}
+
+	return 0;
+}
+
 static void
 trace_seq_reset(struct trace_seq *s)
 {
@@ -660,6 +685,21 @@ static void trace_init_cmdlines(void)
 static int trace_stop_count;
 static DEFINE_SPINLOCK(tracing_start_lock);
 
+/**
+ * ftrace_off_permanent - disable all ftrace code permanently
+ *
+ * This should only be called when a serious anomally has
+ * been detected.  This will turn off the function tracing,
+ * ring buffers, and other tracing utilites. It takes no
+ * locks and can be called from any context.
+ */
+void ftrace_off_permanent(void)
+{
+	tracing_disabled = 1;
+	ftrace_stop();
+	tracing_off_permanent();
+}
+
 /**
  * tracing_start - quick start of the tracer
  *
@@ -801,6 +841,7 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags,
 
 	entry->preempt_count		= pc & 0xff;
 	entry->pid			= (tsk) ? tsk->pid : 0;
+	entry->tgid               	= (tsk) ? tsk->tgid : 0;
 	entry->flags =
 #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT
 		(irqs_disabled_flags(flags) ? TRACE_FLAG_IRQS_OFF : 0) |
@@ -918,6 +959,44 @@ void __trace_stack(struct trace_array *tr,
 	ftrace_trace_stack(tr, data, flags, skip, preempt_count());
 }
 
+static void ftrace_trace_userstack(struct trace_array *tr,
+		   struct trace_array_cpu *data,
+		   unsigned long flags, int pc)
+{
+	struct ring_buffer_event *event;
+	struct userstack_entry *entry;
+	struct stack_trace trace;
+	unsigned long irq_flags;
+
+	if (!(trace_flags & TRACE_ITER_USERSTACKTRACE))
+		return;
+
+	event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
+					 &irq_flags);
+	if (!event)
+		return;
+	entry	= ring_buffer_event_data(event);
+	tracing_generic_entry_update(&entry->ent, flags, pc);
+	entry->ent.type		= TRACE_USER_STACK;
+
+	memset(&entry->caller, 0, sizeof(entry->caller));
+
+	trace.nr_entries	= 0;
+	trace.max_entries	= FTRACE_STACK_ENTRIES;
+	trace.skip		= 0;
+	trace.entries		= entry->caller;
+
+	save_stack_trace_user(&trace);
+	ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
+}
+
+void __trace_userstack(struct trace_array *tr,
+		   struct trace_array_cpu *data,
+		   unsigned long flags)
+{
+	ftrace_trace_userstack(tr, data, flags, preempt_count());
+}
+
 static void
 ftrace_trace_special(void *__tr, void *__data,
 		     unsigned long arg1, unsigned long arg2, unsigned long arg3,
@@ -941,6 +1020,7 @@ ftrace_trace_special(void *__tr, void *__data,
 	entry->arg3			= arg3;
 	ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
 	ftrace_trace_stack(tr, data, irq_flags, 4, pc);
+	ftrace_trace_userstack(tr, data, irq_flags, pc);
 
 	trace_wake_up();
 }
@@ -979,6 +1059,7 @@ tracing_sched_switch_trace(struct trace_array *tr,
 	entry->next_cpu	= task_cpu(next);
 	ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
 	ftrace_trace_stack(tr, data, flags, 5, pc);
+	ftrace_trace_userstack(tr, data, flags, pc);
 }
 
 void
@@ -1008,6 +1089,7 @@ tracing_sched_wakeup_trace(struct trace_array *tr,
 	entry->next_cpu			= task_cpu(wakee);
 	ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
 	ftrace_trace_stack(tr, data, flags, 6, pc);
+	ftrace_trace_userstack(tr, data, flags, pc);
 
 	trace_wake_up();
 }
@@ -1387,6 +1469,78 @@ seq_print_ip_sym(struct trace_seq *s, unsigned long ip, unsigned long sym_flags)
 	return ret;
 }
 
+static inline int seq_print_user_ip(struct trace_seq *s, struct mm_struct *mm,
+				    unsigned long ip, unsigned long sym_flags)
+{
+	struct file *file = NULL;
+	unsigned long vmstart = 0;
+	int ret = 1;
+
+	if (mm) {
+		const struct vm_area_struct *vma;
+
+		down_read(&mm->mmap_sem);
+		vma = find_vma(mm, ip);
+		if (vma) {
+			file = vma->vm_file;
+			vmstart = vma->vm_start;
+		}
+		if (file) {
+			ret = trace_seq_path(s, &file->f_path);
+			if (ret)
+				ret = trace_seq_printf(s, "[+0x%lx]", ip - vmstart);
+		}
+		up_read(&mm->mmap_sem);
+	}
+	if (ret && ((sym_flags & TRACE_ITER_SYM_ADDR) || !file))
+		ret = trace_seq_printf(s, " <" IP_FMT ">", ip);
+	return ret;
+}
+
+static int
+seq_print_userip_objs(const struct userstack_entry *entry, struct trace_seq *s,
+		      unsigned long sym_flags)
+{
+	struct mm_struct *mm = NULL;
+	int ret = 1;
+	unsigned int i;
+
+	if (trace_flags & TRACE_ITER_SYM_USEROBJ) {
+		struct task_struct *task;
+		/*
+		 * we do the lookup on the thread group leader,
+		 * since individual threads might have already quit!
+		 */
+		rcu_read_lock();
+		task = find_task_by_vpid(entry->ent.tgid);
+		if (task)
+			mm = get_task_mm(task);
+		rcu_read_unlock();
+	}
+
+	for (i = 0; i < FTRACE_STACK_ENTRIES; i++) {
+		unsigned long ip = entry->caller[i];
+
+		if (ip == ULONG_MAX || !ret)
+			break;
+		if (i && ret)
+			ret = trace_seq_puts(s, " <- ");
+		if (!ip) {
+			if (ret)
+				ret = trace_seq_puts(s, "??");
+			continue;
+		}
+		if (!ret)
+			break;
+		if (ret)
+			ret = seq_print_user_ip(s, mm, ip, sym_flags);
+	}
+
+	if (mm)
+		mmput(mm);
+	return ret;
+}
+
 static void print_lat_help_header(struct seq_file *m)
 {
 	seq_puts(m, "#                  _------=> CPU#            \n");
@@ -1702,6 +1856,15 @@ print_lat_fmt(struct trace_iterator *iter, unsigned int trace_idx, int cpu)
 				 field->line);
 		break;
 	}
+	case TRACE_USER_STACK: {
+		struct userstack_entry *field;
+
+		trace_assign_type(field, entry);
+
+		seq_print_userip_objs(field, s, sym_flags);
+		trace_seq_putc(s, '\n');
+		break;
+	}
 	default:
 		trace_seq_printf(s, "Unknown type %d\n", entry->type);
 	}
@@ -1853,6 +2016,19 @@ static enum print_line_t print_trace_fmt(struct trace_iterator *iter)
 				 field->line);
 		break;
 	}
+	case TRACE_USER_STACK: {
+		struct userstack_entry *field;
+
+		trace_assign_type(field, entry);
+
+		ret = seq_print_userip_objs(field, s, sym_flags);
+		if (!ret)
+			return TRACE_TYPE_PARTIAL_LINE;
+		ret = trace_seq_putc(s, '\n');
+		if (!ret)
+			return TRACE_TYPE_PARTIAL_LINE;
+		break;
+	}
 	}
 	return TRACE_TYPE_HANDLED;
 }
@@ -1912,6 +2088,7 @@ static enum print_line_t print_raw_fmt(struct trace_iterator *iter)
 		break;
 	}
 	case TRACE_SPECIAL:
+	case TRACE_USER_STACK:
 	case TRACE_STACK: {
 		struct special_entry *field;
 
@@ -2000,6 +2177,7 @@ static enum print_line_t print_hex_fmt(struct trace_iterator *iter)
 		break;
 	}
 	case TRACE_SPECIAL:
+	case TRACE_USER_STACK:
 	case TRACE_STACK: {
 		struct special_entry *field;
 
@@ -2054,6 +2232,7 @@ static enum print_line_t print_bin_fmt(struct trace_iterator *iter)
 		break;
 	}
 	case TRACE_SPECIAL:
+	case TRACE_USER_STACK:
 	case TRACE_STACK: {
 		struct special_entry *field;
 
@@ -3488,6 +3667,9 @@ void ftrace_dump(void)
 		atomic_inc(&global_trace.data[cpu]->disabled);
 	}
 
+	/* don't look at user memory in panic mode */
+	trace_flags &= ~TRACE_ITER_SYM_USEROBJ;
+
 	printk(KERN_TRACE "Dumping ftrace buffer:\n");
 
 	iter.tr = &global_trace;
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 2cb12fd98f6b..28c15c2ebc22 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -26,6 +26,7 @@ enum trace_type {
 	TRACE_BOOT_CALL,
 	TRACE_BOOT_RET,
 	TRACE_FN_RET,
+	TRACE_USER_STACK,
 
 	__TRACE_LAST_TYPE
 };
@@ -42,6 +43,7 @@ struct trace_entry {
 	unsigned char		flags;
 	unsigned char		preempt_count;
 	int			pid;
+	int			tgid;
 };
 
 /*
@@ -99,6 +101,11 @@ struct stack_entry {
 	unsigned long		caller[FTRACE_STACK_ENTRIES];
 };
 
+struct userstack_entry {
+	struct trace_entry	ent;
+	unsigned long		caller[FTRACE_STACK_ENTRIES];
+};
+
 /*
  * ftrace_printk entry:
  */
@@ -240,6 +247,7 @@ extern void __ftrace_bad_type(void);
 		IF_ASSIGN(var, ent, struct ctx_switch_entry, 0);	\
 		IF_ASSIGN(var, ent, struct trace_field_cont, TRACE_CONT); \
 		IF_ASSIGN(var, ent, struct stack_entry, TRACE_STACK);	\
+		IF_ASSIGN(var, ent, struct userstack_entry, TRACE_USER_STACK);\
 		IF_ASSIGN(var, ent, struct print_entry, TRACE_PRINT);	\
 		IF_ASSIGN(var, ent, struct special_entry, 0);		\
 		IF_ASSIGN(var, ent, struct trace_mmiotrace_rw,		\
@@ -500,6 +508,8 @@ enum trace_iterator_flags {
 	TRACE_ITER_PREEMPTONLY		= 0x800,
 	TRACE_ITER_BRANCH		= 0x1000,
 	TRACE_ITER_ANNOTATE		= 0x2000,
+	TRACE_ITER_USERSTACKTRACE       = 0x4000,
+	TRACE_ITER_SYM_USEROBJ          = 0x8000
 };
 
 /*
diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c
index 433d650eda9f..2a98a206acc2 100644
--- a/kernel/trace/trace_mmiotrace.c
+++ b/kernel/trace/trace_mmiotrace.c
@@ -18,12 +18,14 @@ struct header_iter {
 
 static struct trace_array *mmio_trace_array;
 static bool overrun_detected;
+static unsigned long prev_overruns;
 
 static void mmio_reset_data(struct trace_array *tr)
 {
 	int cpu;
 
 	overrun_detected = false;
+	prev_overruns = 0;
 	tr->time_start = ftrace_now(tr->cpu);
 
 	for_each_online_cpu(cpu)
@@ -123,16 +125,12 @@ static void mmio_close(struct trace_iterator *iter)
 
 static unsigned long count_overruns(struct trace_iterator *iter)
 {
-	int cpu;
 	unsigned long cnt = 0;
-/* FIXME: */
-#if 0
-	for_each_online_cpu(cpu) {
-		cnt += iter->overrun[cpu];
-		iter->overrun[cpu] = 0;
-	}
-#endif
-	(void)cpu;
+	unsigned long over = ring_buffer_overruns(iter->tr->buffer);
+
+	if (over > prev_overruns)
+		cnt = over - prev_overruns;
+	prev_overruns = over;
 	return cnt;
 }
 
diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl
index eeac71c87c66..0197e2f6b544 100755
--- a/scripts/recordmcount.pl
+++ b/scripts/recordmcount.pl
@@ -130,11 +130,13 @@ my %weak;		# List of weak functions
 my %convert;		# List of local functions used that needs conversion
 
 my $type;
+my $nm_regex;		# Find the local functions (return function)
 my $section_regex;	# Find the start of a section
 my $function_regex;	# Find the name of a function
 			#    (return offset and func name)
 my $mcount_regex;	# Find the call site to mcount (return offset)
-my $alignment;         # The .align value to use for $mcount_section
+my $alignment;		# The .align value to use for $mcount_section
+my $section_type;	# Section header plus possible alignment command
 
 if ($arch eq "x86") {
     if ($bits == 64) {
@@ -144,9 +146,18 @@ if ($arch eq "x86") {
     }
 }
 
+#
+# We base the defaults off of i386, the other archs may
+# feel free to change them in the below if statements.
+#
+$nm_regex = "^[0-9a-fA-F]+\\s+t\\s+(\\S+)";
+$section_regex = "Disassembly of section\\s+(\\S+):";
+$function_regex = "^([0-9a-fA-F]+)\\s+<(.*?)>:";
+$mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\smcount\$";
+$section_type = '@progbits';
+$type = ".long";
+
 if ($arch eq "x86_64") {
-    $section_regex = "Disassembly of section\\s+(\\S+):";
-    $function_regex = "^([0-9a-fA-F]+)\\s+<(.*?)>:";
     $mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\smcount([+-]0x[0-9a-zA-Z]+)?\$";
     $type = ".quad";
     $alignment = 8;
@@ -158,10 +169,6 @@ if ($arch eq "x86_64") {
     $cc .= " -m64";
 
 } elsif ($arch eq "i386") {
-    $section_regex = "Disassembly of section\\s+(\\S+):";
-    $function_regex = "^([0-9a-fA-F]+)\\s+<(.*?)>:";
-    $mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\smcount\$";
-    $type = ".long";
     $alignment = 4;
 
     # force flags for this arch
@@ -170,6 +177,27 @@ if ($arch eq "x86_64") {
     $objcopy .= " -O elf32-i386";
     $cc .= " -m32";
 
+} elsif ($arch eq "sh") {
+    $alignment = 2;
+
+    # force flags for this arch
+    $ld .= " -m shlelf_linux";
+    $objcopy .= " -O elf32-sh-linux";
+    $cc .= " -m32";
+
+} elsif ($arch eq "powerpc") {
+    $nm_regex = "^[0-9a-fA-F]+\\s+t\\s+(\\.?\\S+)";
+    $function_regex = "^([0-9a-fA-F]+)\\s+<(\\.?.*?)>:";
+    $mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\s\\.?_mcount\$";
+
+    if ($bits == 64) {
+	$type = ".quad";
+    }
+
+} elsif ($arch eq "arm") {
+    $alignment = 2;
+    $section_type = '%progbits';
+
 } else {
     die "Arch $arch is not supported with CONFIG_FTRACE_MCOUNT_RECORD";
 }
@@ -239,7 +267,7 @@ if (!$found_version) {
 #
 open (IN, "$nm $inputfile|") || die "error running $nm";
 while (<IN>) {
-    if (/^[0-9a-fA-F]+\s+t\s+(\S+)/) {
+    if (/$nm_regex/) {
 	$locals{$1} = 1;
     } elsif (/^[0-9a-fA-F]+\s+([wW])\s+(\S+)/) {
 	$weak{$2} = $1;
@@ -290,8 +318,8 @@ sub update_funcs
 	if (!$opened) {
 	    open(FILE, ">$mcount_s") || die "can't create $mcount_s\n";
 	    $opened = 1;
-	    print FILE "\t.section $mcount_section,\"a\",\@progbits\n";
-	    print FILE "\t.align $alignment\n";
+	    print FILE "\t.section $mcount_section,\"a\",$section_type\n";
+	    print FILE "\t.align $alignment\n" if (defined($alignment));
 	}
 	printf FILE "\t%s %s + %d\n", $type, $ref_func, $offsets[$i] - $offset;
     }