powerpc: Split ftrace bits into a separate file

entry_*.S now includes a lot more than just kernel entry/exit code. As a
first step at cleaning this up, let's split out the ftrace bits into
separate files. Also move all related tracing code into a new trace/
subdirectory.

No functional changes.

Suggested-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

5 files changed, 1166 insertions, 0 deletions

diff --git a/arch/powerpc/kernel/trace/Makefile b/arch/powerpc/kernel/trace/Makefile
new file mode 100644
index 000000000000..5f5a35254a9b
--- /dev/null
+++ b/arch/powerpc/kernel/trace/Makefile
@@ -0,0 +1,24 @@
+#
+# Makefile for the powerpc trace subsystem
+#
+
+subdir-ccflags-$(CONFIG_PPC_WERROR)	:= -Werror
+
+ifdef CONFIG_FUNCTION_TRACER
+# do not trace tracer code
+CFLAGS_REMOVE_ftrace.o = -mno-sched-epilog $(CC_FLAGS_FTRACE)
+endif
+
+obj32-$(CONFIG_FUNCTION_TRACER)		+= ftrace_32.o
+obj64-$(CONFIG_FUNCTION_TRACER)		+= ftrace_64.o
+obj-$(CONFIG_DYNAMIC_FTRACE)		+= ftrace.o
+obj-$(CONFIG_FUNCTION_GRAPH_TRACER)	+= ftrace.o
+obj-$(CONFIG_FTRACE_SYSCALLS)		+= ftrace.o
+obj-$(CONFIG_TRACING)			+= trace_clock.o
+
+obj-$(CONFIG_PPC64)			+= $(obj64-y)
+obj-$(CONFIG_PPC32)			+= $(obj32-y)
+
+# Disable GCOV & sanitizers in odd or sensitive code
+GCOV_PROFILE_ftrace.o := n
+UBSAN_SANITIZE_ftrace.o := n
diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c
new file mode 100644
index 000000000000..32509de6ce4c
--- /dev/null
+++ b/arch/powerpc/kernel/trace/ftrace.c
@@ -0,0 +1,620 @@
+/*
+ * Code for replacing ftrace calls with jumps.
+ *
+ * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com>
+ *
+ * Thanks goes out to P.A. Semi, Inc for supplying me with a PPC64 box.
+ *
+ * Added function graph tracer code, taken from x86 that was written
+ * by Frederic Weisbecker, and ported to PPC by Steven Rostedt.
+ *
+ */
+
+#define pr_fmt(fmt) "ftrace-powerpc: " fmt
+
+#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/asm-prototypes.h>
+#include <asm/cacheflush.h>
+#include <asm/code-patching.h>
+#include <asm/ftrace.h>
+#include <asm/syscall.h>
+
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+static unsigned int
+ftrace_call_replace(unsigned long ip, unsigned long addr, int link)
+{
+	unsigned int op;
+
+	addr = ppc_function_entry((void *)addr);
+
+	/* if (link) set op to 'bl' else 'b' */
+	op = create_branch((unsigned int *)ip, addr, link ? 1 : 0);
+
+	return op;
+}
+
+static int
+ftrace_modify_code(unsigned long ip, unsigned int old, unsigned int new)
+{
+	unsigned int replaced;
+
+	/*
+	 * Note:
+	 * We are paranoid about modifying text, as if a bug was to happen, it
+	 * could cause us to read or write to someplace that could cause harm.
+	 * Carefully read and modify the code with probe_kernel_*(), and make
+	 * sure what we read is what we expected it to be before modifying it.
+	 */
+
+	/* read the text we want to modify */
+	if (probe_kernel_read(&replaced, (void *)ip, MCOUNT_INSN_SIZE))
+		return -EFAULT;
+
+	/* Make sure it is what we expect it to be */
+	if (replaced != old) {
+		pr_err("%p: replaced (%#x) != old (%#x)",
+		(void *)ip, replaced, old);
+		return -EINVAL;
+	}
+
+	/* replace the text with the new text */
+	if (patch_instruction((unsigned int *)ip, new))
+		return -EPERM;
+
+	return 0;
+}
+
+/*
+ * Helper functions that are the same for both PPC64 and PPC32.
+ */
+static int test_24bit_addr(unsigned long ip, unsigned long addr)
+{
+	addr = ppc_function_entry((void *)addr);
+
+	/* use the create_branch to verify that this offset can be branched */
+	return create_branch((unsigned int *)ip, addr, 0);
+}
+
+#ifdef CONFIG_MODULES
+
+static int is_bl_op(unsigned int op)
+{
+	return (op & 0xfc000003) == 0x48000001;
+}
+
+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;
+}
+
+#ifdef CONFIG_PPC64
+static int
+__ftrace_make_nop(struct module *mod,
+		  struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned long entry, ptr, tramp;
+	unsigned long ip = rec->ip;
+	unsigned int op, pop;
+
+	/* read where this goes */
+	if (probe_kernel_read(&op, (void *)ip, sizeof(int))) {
+		pr_err("Fetching opcode failed.\n");
+		return -EFAULT;
+	}
+
+	/* Make sure that that this is still a 24bit jump */
+	if (!is_bl_op(op)) {
+		pr_err("Not expected bl: opcode is %x\n", op);
+		return -EINVAL;
+	}
+
+	/* lets find where the pointer goes */
+	tramp = find_bl_target(ip, op);
+
+	pr_devel("ip:%lx jumps to %lx", ip, tramp);
+
+	if (module_trampoline_target(mod, tramp, &ptr)) {
+		pr_err("Failed to get trampoline target\n");
+		return -EFAULT;
+	}
+
+	pr_devel("trampoline target %lx", ptr);
+
+	entry = ppc_global_function_entry((void *)addr);
+	/* This should match what was called */
+	if (ptr != entry) {
+		pr_err("addr %lx does not match expected %lx\n", ptr, entry);
+		return -EINVAL;
+	}
+
+#ifdef CC_USING_MPROFILE_KERNEL
+	/* When using -mkernel_profile there is no load to jump over */
+	pop = PPC_INST_NOP;
+
+	if (probe_kernel_read(&op, (void *)(ip - 4), 4)) {
+		pr_err("Fetching instruction at %lx failed.\n", ip - 4);
+		return -EFAULT;
+	}
+
+	/* We expect either a mflr r0, or a std r0, LRSAVE(r1) */
+	if (op != PPC_INST_MFLR && op != PPC_INST_STD_LR) {
+		pr_err("Unexpected instruction %08x around bl _mcount\n", op);
+		return -EINVAL;
+	}
+#else
+	/*
+	 * Our original call site looks like:
+	 *
+	 * bl <tramp>
+	 * ld r2,XX(r1)
+	 *
+	 * Milton Miller pointed out that we can not simply nop the branch.
+	 * 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.
+	 *
+	 * Use a b +8 to jump over the load.
+	 */
+
+	pop = PPC_INST_BRANCH | 8;	/* b +8 */
+
+	/*
+	 * Check what is in the next instruction. We can see ld r2,40(r1), but
+	 * on first pass after boot we will see mflr r0.
+	 */
+	if (probe_kernel_read(&op, (void *)(ip+4), MCOUNT_INSN_SIZE)) {
+		pr_err("Fetching op failed.\n");
+		return -EFAULT;
+	}
+
+	if (op != PPC_INST_LD_TOC) {
+		pr_err("Expected %08x found %08x\n", PPC_INST_LD_TOC, op);
+		return -EINVAL;
+	}
+#endif /* CC_USING_MPROFILE_KERNEL */
+
+	if (patch_instruction((unsigned int *)ip, pop)) {
+		pr_err("Patching NOP failed.\n");
+		return -EPERM;
+	}
+
+	return 0;
+}
+
+#else /* !PPC64 */
+static int
+__ftrace_make_nop(struct module *mod,
+		  struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned int op;
+	unsigned int jmp[4];
+	unsigned long ip = rec->ip;
+	unsigned long tramp;
+
+	if (probe_kernel_read(&op, (void *)ip, MCOUNT_INSN_SIZE))
+		return -EFAULT;
+
+	/* Make sure that that this is still a 24bit jump */
+	if (!is_bl_op(op)) {
+		pr_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:
+	 *  0x3d, 0x80, 0x00, 0x00  lis r12,sym@ha
+	 *  0x39, 0x8c, 0x00, 0x00  addi r12,r12,sym@l
+	 *  0x7d, 0x89, 0x03, 0xa6  mtctr r12
+	 *  0x4e, 0x80, 0x04, 0x20  bctr
+	 */
+
+	pr_devel("ip:%lx jumps to %lx", ip, tramp);
+
+	/* Find where the trampoline jumps to */
+	if (probe_kernel_read(jmp, (void *)tramp, sizeof(jmp))) {
+		pr_err("Failed to read %lx\n", tramp);
+		return -EFAULT;
+	}
+
+	pr_devel(" %08x %08x ", jmp[0], jmp[1]);
+
+	/* verify that this is what we expect it to be */
+	if (((jmp[0] & 0xffff0000) != 0x3d800000) ||
+	    ((jmp[1] & 0xffff0000) != 0x398c0000) ||
+	    (jmp[2] != 0x7d8903a6) ||
+	    (jmp[3] != 0x4e800420)) {
+		pr_err("Not a trampoline\n");
+		return -EINVAL;
+	}
+
+	tramp = (jmp[1] & 0xffff) |
+		((jmp[0] & 0xffff) << 16);
+	if (tramp & 0x8000)
+		tramp -= 0x10000;
+
+	pr_devel(" %lx ", tramp);
+
+	if (tramp != addr) {
+		pr_err("Trampoline location %08lx does not match addr\n",
+		       tramp);
+		return -EINVAL;
+	}
+
+	op = PPC_INST_NOP;
+
+	if (patch_instruction((unsigned int *)ip, op))
+		return -EPERM;
+
+	return 0;
+}
+#endif /* PPC64 */
+#endif /* CONFIG_MODULES */
+
+int ftrace_make_nop(struct module *mod,
+		    struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned long ip = rec->ip;
+	unsigned int old, new;
+
+	/*
+	 * 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, 1);
+		new = PPC_INST_NOP;
+		return ftrace_modify_code(ip, old, new);
+	}
+
+#ifdef CONFIG_MODULES
+	/*
+	 * 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) {
+			pr_err("No module loaded addr=%lx\n", addr);
+			return -EFAULT;
+		}
+		rec->arch.mod = mod;
+	} else if (mod) {
+		if (mod != rec->arch.mod) {
+			pr_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);
+#else
+	/* We should not get here without modules */
+	return -EINVAL;
+#endif /* CONFIG_MODULES */
+}
+
+#ifdef CONFIG_MODULES
+#ifdef CONFIG_PPC64
+/*
+ * Examine the existing instructions for __ftrace_make_call.
+ * They should effectively be a NOP, and follow formal constraints,
+ * depending on the ABI. Return false if they don't.
+ */
+#ifndef CC_USING_MPROFILE_KERNEL
+static int
+expected_nop_sequence(void *ip, unsigned int op0, unsigned int op1)
+{
+	/*
+	 * We expect to see:
+	 *
+	 * b +8
+	 * ld r2,XX(r1)
+	 *
+	 * The load offset is different depending on the ABI. For simplicity
+	 * just mask it out when doing the compare.
+	 */
+	if ((op0 != 0x48000008) || ((op1 & 0xffff0000) != 0xe8410000))
+		return 0;
+	return 1;
+}
+#else
+static int
+expected_nop_sequence(void *ip, unsigned int op0, unsigned int op1)
+{
+	/* look for patched "NOP" on ppc64 with -mprofile-kernel */
+	if (op0 != PPC_INST_NOP)
+		return 0;
+	return 1;
+}
+#endif
+
+static int
+__ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned int op[2];
+	void *ip = (void *)rec->ip;
+
+	/* read where this goes */
+	if (probe_kernel_read(op, ip, sizeof(op)))
+		return -EFAULT;
+
+	if (!expected_nop_sequence(ip, op[0], op[1])) {
+		pr_err("Unexpected call sequence at %p: %x %x\n",
+		ip, op[0], op[1]);
+		return -EINVAL;
+	}
+
+	/* If we never set up a trampoline to ftrace_caller, then bail */
+	if (!rec->arch.mod->arch.tramp) {
+		pr_err("No ftrace trampoline\n");
+		return -EINVAL;
+	}
+
+	/* Ensure branch is within 24 bits */
+	if (!create_branch(ip, rec->arch.mod->arch.tramp, BRANCH_SET_LINK)) {
+		pr_err("Branch out of range\n");
+		return -EINVAL;
+	}
+
+	if (patch_branch(ip, rec->arch.mod->arch.tramp, BRANCH_SET_LINK)) {
+		pr_err("REL24 out of range!\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
+			unsigned long addr)
+{
+	return ftrace_make_call(rec, addr);
+}
+#endif
+
+#else  /* !CONFIG_PPC64: */
+static int
+__ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned int op;
+	unsigned long ip = rec->ip;
+
+	/* read where this goes */
+	if (probe_kernel_read(&op, (void *)ip, MCOUNT_INSN_SIZE))
+		return -EFAULT;
+
+	/* It should be pointing to a nop */
+	if (op != PPC_INST_NOP) {
+		pr_err("Expected NOP but have %x\n", op);
+		return -EINVAL;
+	}
+
+	/* If we never set up a trampoline to ftrace_caller, then bail */
+	if (!rec->arch.mod->arch.tramp) {
+		pr_err("No ftrace trampoline\n");
+		return -EINVAL;
+	}
+
+	/* create the branch to the trampoline */
+	op = create_branch((unsigned int *)ip,
+			   rec->arch.mod->arch.tramp, BRANCH_SET_LINK);
+	if (!op) {
+		pr_err("REL24 out of range!\n");
+		return -EINVAL;
+	}
+
+	pr_devel("write to %lx\n", rec->ip);
+
+	if (patch_instruction((unsigned int *)ip, op))
+		return -EPERM;
+
+	return 0;
+}
+#endif /* CONFIG_PPC64 */
+#endif /* CONFIG_MODULES */
+
+int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned long ip = rec->ip;
+	unsigned int old, new;
+
+	/*
+	 * 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 = PPC_INST_NOP;
+		new = ftrace_call_replace(ip, addr, 1);
+		return ftrace_modify_code(ip, old, new);
+	}
+
+#ifdef CONFIG_MODULES
+	/*
+	 * 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) {
+		pr_err("No module loaded\n");
+		return -EINVAL;
+	}
+
+	return __ftrace_make_call(rec, addr);
+#else
+	/* We should not get here without modules */
+	return -EINVAL;
+#endif /* CONFIG_MODULES */
+}
+
+int ftrace_update_ftrace_func(ftrace_func_t func)
+{
+	unsigned long ip = (unsigned long)(&ftrace_call);
+	unsigned int old, new;
+	int ret;
+
+	old = *(unsigned int *)&ftrace_call;
+	new = ftrace_call_replace(ip, (unsigned long)func, 1);
+	ret = ftrace_modify_code(ip, old, new);
+
+	return ret;
+}
+
+static int __ftrace_replace_code(struct dyn_ftrace *rec, int enable)
+{
+	unsigned long ftrace_addr = (unsigned long)FTRACE_ADDR;
+	int ret;
+
+	ret = ftrace_update_record(rec, enable);
+
+	switch (ret) {
+	case FTRACE_UPDATE_IGNORE:
+		return 0;
+	case FTRACE_UPDATE_MAKE_CALL:
+		return ftrace_make_call(rec, ftrace_addr);
+	case FTRACE_UPDATE_MAKE_NOP:
+		return ftrace_make_nop(NULL, rec, ftrace_addr);
+	}
+
+	return 0;
+}
+
+void ftrace_replace_code(int enable)
+{
+	struct ftrace_rec_iter *iter;
+	struct dyn_ftrace *rec;
+	int ret;
+
+	for (iter = ftrace_rec_iter_start(); iter;
+	     iter = ftrace_rec_iter_next(iter)) {
+		rec = ftrace_rec_iter_record(iter);
+		ret = __ftrace_replace_code(rec, enable);
+		if (ret) {
+			ftrace_bug(ret, rec);
+			return;
+		}
+	}
+}
+
+/*
+ * Use the default ftrace_modify_all_code, but without
+ * stop_machine().
+ */
+void arch_ftrace_update_code(int command)
+{
+	ftrace_modify_all_code(command);
+}
+
+int __init ftrace_dyn_arch_init(void)
+{
+	return 0;
+}
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+extern void ftrace_graph_call(void);
+extern void ftrace_graph_stub(void);
+
+int ftrace_enable_ftrace_graph_caller(void)
+{
+	unsigned long ip = (unsigned long)(&ftrace_graph_call);
+	unsigned long addr = (unsigned long)(&ftrace_graph_caller);
+	unsigned long stub = (unsigned long)(&ftrace_graph_stub);
+	unsigned int old, new;
+
+	old = ftrace_call_replace(ip, stub, 0);
+	new = ftrace_call_replace(ip, addr, 0);
+
+	return ftrace_modify_code(ip, old, new);
+}
+
+int ftrace_disable_ftrace_graph_caller(void)
+{
+	unsigned long ip = (unsigned long)(&ftrace_graph_call);
+	unsigned long addr = (unsigned long)(&ftrace_graph_caller);
+	unsigned long stub = (unsigned long)(&ftrace_graph_stub);
+	unsigned int old, new;
+
+	old = ftrace_call_replace(ip, addr, 0);
+	new = ftrace_call_replace(ip, stub, 0);
+
+	return ftrace_modify_code(ip, old, new);
+}
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+/*
+ * Hook the return address and push it in the stack of return addrs
+ * in current thread info. Return the address we want to divert to.
+ */
+unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip)
+{
+	struct ftrace_graph_ent trace;
+	unsigned long return_hooker;
+
+	if (unlikely(ftrace_graph_is_dead()))
+		goto out;
+
+	if (unlikely(atomic_read(&current->tracing_graph_pause)))
+		goto out;
+
+	return_hooker = ppc_function_entry(return_to_handler);
+
+	trace.func = ip;
+	trace.depth = current->curr_ret_stack + 1;
+
+	/* Only trace if the calling function expects to */
+	if (!ftrace_graph_entry(&trace))
+		goto out;
+
+	if (ftrace_push_return_trace(parent, ip, &trace.depth, 0,
+				     NULL) == -EBUSY)
+		goto out;
+
+	parent = return_hooker;
+out:
+	return parent;
+}
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
+#if defined(CONFIG_FTRACE_SYSCALLS) && defined(CONFIG_PPC64)
+unsigned long __init arch_syscall_addr(int nr)
+{
+	return sys_call_table[nr*2];
+}
+#endif /* CONFIG_FTRACE_SYSCALLS && CONFIG_PPC64 */
+
+#ifdef PPC64_ELF_ABI_v1
+char *arch_ftrace_match_adjust(char *str, const char *search)
+{
+	if (str[0] == '.' && search[0] != '.')
+		return str + 1;
+	else
+		return str;
+}
+#endif /* PPC64_ELF_ABI_v1 */
diff --git a/arch/powerpc/kernel/trace/ftrace_32.S b/arch/powerpc/kernel/trace/ftrace_32.S
new file mode 100644
index 000000000000..afef2c076282
--- /dev/null
+++ b/arch/powerpc/kernel/trace/ftrace_32.S
@@ -0,0 +1,118 @@
+/*
+ * Split from entry_32.S
+ *
+ * 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/magic.h>
+#include <asm/reg.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/ftrace.h>
+#include <asm/export.h>
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+_GLOBAL(mcount)
+_GLOBAL(_mcount)
+	/*
+	 * It is required that _mcount on PPC32 must preserve the
+	 * link register. But we have r0 to play with. We use r0
+	 * to push the return address back to the caller of mcount
+	 * into the ctr register, restore the link register and
+	 * then jump back using the ctr register.
+	 */
+	mflr	r0
+	mtctr	r0
+	lwz	r0, 4(r1)
+	mtlr	r0
+	bctr
+
+_GLOBAL(ftrace_caller)
+	MCOUNT_SAVE_FRAME
+	/* r3 ends up with link register */
+	subi	r3, r3, MCOUNT_INSN_SIZE
+.globl ftrace_call
+ftrace_call:
+	bl	ftrace_stub
+	nop
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+.globl ftrace_graph_call
+ftrace_graph_call:
+	b	ftrace_graph_stub
+_GLOBAL(ftrace_graph_stub)
+#endif
+	MCOUNT_RESTORE_FRAME
+	/* old link register ends up in ctr reg */
+	bctr
+#else
+_GLOBAL(mcount)
+_GLOBAL(_mcount)
+
+	MCOUNT_SAVE_FRAME
+
+	subi	r3, r3, MCOUNT_INSN_SIZE
+	LOAD_REG_ADDR(r5, ftrace_trace_function)
+	lwz	r5,0(r5)
+
+	mtctr	r5
+	bctrl
+	nop
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	b	ftrace_graph_caller
+#endif
+	MCOUNT_RESTORE_FRAME
+	bctr
+#endif
+EXPORT_SYMBOL(_mcount)
+
+_GLOBAL(ftrace_stub)
+	blr
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+_GLOBAL(ftrace_graph_caller)
+	/* load r4 with local address */
+	lwz	r4, 44(r1)
+	subi	r4, r4, MCOUNT_INSN_SIZE
+
+	/* Grab the LR out of the caller stack frame */
+	lwz	r3,52(r1)
+
+	bl	prepare_ftrace_return
+	nop
+
+        /*
+         * prepare_ftrace_return gives us the address we divert to.
+         * Change the LR in the callers stack frame to this.
+         */
+	stw	r3,52(r1)
+
+	MCOUNT_RESTORE_FRAME
+	/* old link register ends up in ctr reg */
+	bctr
+
+_GLOBAL(return_to_handler)
+	/* need to save return values */
+	stwu	r1, -32(r1)
+	stw	r3, 20(r1)
+	stw	r4, 16(r1)
+	stw	r31, 12(r1)
+	mr	r31, r1
+
+	bl	ftrace_return_to_handler
+	nop
+
+	/* return value has real return address */
+	mtlr	r3
+
+	lwz	r3, 20(r1)
+	lwz	r4, 16(r1)
+	lwz	r31,12(r1)
+	lwz	r1, 0(r1)
+
+	/* Jump back to real return address */
+	blr
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/powerpc/kernel/trace/ftrace_64.S b/arch/powerpc/kernel/trace/ftrace_64.S
new file mode 100644
index 000000000000..587e7b5c0aff
--- /dev/null
+++ b/arch/powerpc/kernel/trace/ftrace_64.S
@@ -0,0 +1,389 @@
+/*
+ * Split from entry_64.S
+ *
+ * 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/magic.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/ftrace.h>
+#include <asm/ppc-opcode.h>
+#include <asm/export.h>
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+_GLOBAL(mcount)
+_GLOBAL(_mcount)
+EXPORT_SYMBOL(_mcount)
+	mflr	r12
+	mtctr	r12
+	mtlr	r0
+	bctr
+
+#ifndef CC_USING_MPROFILE_KERNEL
+_GLOBAL_TOC(ftrace_caller)
+	/* Taken from output of objdump from lib64/glibc */
+	mflr	r3
+	ld	r11, 0(r1)
+	stdu	r1, -112(r1)
+	std	r3, 128(r1)
+	ld	r4, 16(r11)
+	subi	r3, r3, MCOUNT_INSN_SIZE
+.globl ftrace_call
+ftrace_call:
+	bl	ftrace_stub
+	nop
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+.globl ftrace_graph_call
+ftrace_graph_call:
+	b	ftrace_graph_stub
+_GLOBAL(ftrace_graph_stub)
+#endif
+	ld	r0, 128(r1)
+	mtlr	r0
+	addi	r1, r1, 112
+
+#else /* CC_USING_MPROFILE_KERNEL */
+/*
+ *
+ * ftrace_caller() is the function that replaces _mcount() when ftrace is
+ * active.
+ *
+ * We arrive here after a function A calls function B, and we are the trace
+ * function for B. When we enter r1 points to A's stack frame, B has not yet
+ * had a chance to allocate one yet.
+ *
+ * Additionally r2 may point either to the TOC for A, or B, depending on
+ * whether B did a TOC setup sequence before calling us.
+ *
+ * On entry the LR points back to the _mcount() call site, and r0 holds the
+ * saved LR as it was on entry to B, ie. the original return address at the
+ * call site in A.
+ *
+ * Our job is to save the register state into a struct pt_regs (on the stack)
+ * and then arrange for the ftrace function to be called.
+ */
+_GLOBAL(ftrace_caller)
+	/* Save the original return address in A's stack frame */
+	std	r0,LRSAVE(r1)
+
+	/* Create our stack frame + pt_regs */
+	stdu	r1,-SWITCH_FRAME_SIZE(r1)
+
+	/* Save all gprs to pt_regs */
+	SAVE_8GPRS(0,r1)
+	SAVE_8GPRS(8,r1)
+	SAVE_8GPRS(16,r1)
+	SAVE_8GPRS(24,r1)
+
+	/* Load special regs for save below */
+	mfmsr   r8
+	mfctr   r9
+	mfxer   r10
+	mfcr	r11
+
+	/* Get the _mcount() call site out of LR */
+	mflr	r7
+	/* Save it as pt_regs->nip */
+	std     r7, _NIP(r1)
+	/* Save the read LR in pt_regs->link */
+	std     r0, _LINK(r1)
+
+	/* Save callee's TOC in the ABI compliant location */
+	std	r2, 24(r1)
+	ld	r2,PACATOC(r13)	/* get kernel TOC in r2 */
+
+	addis	r3,r2,function_trace_op@toc@ha
+	addi	r3,r3,function_trace_op@toc@l
+	ld	r5,0(r3)
+
+#ifdef CONFIG_LIVEPATCH
+	mr	r14,r7		/* remember old NIP */
+#endif
+	/* Calculate ip from nip-4 into r3 for call below */
+	subi    r3, r7, MCOUNT_INSN_SIZE
+
+	/* Put the original return address in r4 as parent_ip */
+	mr	r4, r0
+
+	/* Save special regs */
+	std     r8, _MSR(r1)
+	std     r9, _CTR(r1)
+	std     r10, _XER(r1)
+	std     r11, _CCR(r1)
+
+	/* Load &pt_regs in r6 for call below */
+	addi    r6, r1 ,STACK_FRAME_OVERHEAD
+
+	/* ftrace_call(r3, r4, r5, r6) */
+.globl ftrace_call
+ftrace_call:
+	bl	ftrace_stub
+	nop
+
+	/* Load ctr with the possibly modified NIP */
+	ld	r3, _NIP(r1)
+	mtctr	r3
+#ifdef CONFIG_LIVEPATCH
+	cmpd	r14,r3		/* has NIP been altered? */
+#endif
+
+	/* Restore gprs */
+	REST_8GPRS(0,r1)
+	REST_8GPRS(8,r1)
+	REST_8GPRS(16,r1)
+	REST_8GPRS(24,r1)
+
+	/* Restore possibly modified LR */
+	ld	r0, _LINK(r1)
+	mtlr	r0
+
+	/* Restore callee's TOC */
+	ld	r2, 24(r1)
+
+	/* Pop our stack frame */
+	addi r1, r1, SWITCH_FRAME_SIZE
+
+#ifdef CONFIG_LIVEPATCH
+        /* Based on the cmpd above, if the NIP was altered handle livepatch */
+	bne-	livepatch_handler
+#endif
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+.globl ftrace_graph_call
+ftrace_graph_call:
+	b	ftrace_graph_stub
+_GLOBAL(ftrace_graph_stub)
+#endif
+
+	bctr			/* jump after _mcount site */
+#endif /* CC_USING_MPROFILE_KERNEL */
+
+_GLOBAL(ftrace_stub)
+	blr
+
+#ifdef CONFIG_LIVEPATCH
+	/*
+	 * This function runs in the mcount context, between two functions. As
+	 * such it can only clobber registers which are volatile and used in
+	 * function linkage.
+	 *
+	 * We get here when a function A, calls another function B, but B has
+	 * been live patched with a new function C.
+	 *
+	 * On entry:
+	 *  - we have no stack frame and can not allocate one
+	 *  - LR points back to the original caller (in A)
+	 *  - CTR holds the new NIP in C
+	 *  - r0 & r12 are free
+	 *
+	 * r0 can't be used as the base register for a DS-form load or store, so
+	 * we temporarily shuffle r1 (stack pointer) into r0 and then put it back.
+	 */
+livepatch_handler:
+	CURRENT_THREAD_INFO(r12, r1)
+
+	/* Save stack pointer into r0 */
+	mr	r0, r1
+
+	/* Allocate 3 x 8 bytes */
+	ld	r1, TI_livepatch_sp(r12)
+	addi	r1, r1, 24
+	std	r1, TI_livepatch_sp(r12)
+
+	/* Save toc & real LR on livepatch stack */
+	std	r2,  -24(r1)
+	mflr	r12
+	std	r12, -16(r1)
+
+	/* Store stack end marker */
+	lis     r12, STACK_END_MAGIC@h
+	ori     r12, r12, STACK_END_MAGIC@l
+	std	r12, -8(r1)
+
+	/* Restore real stack pointer */
+	mr	r1, r0
+
+	/* Put ctr in r12 for global entry and branch there */
+	mfctr	r12
+	bctrl
+
+	/*
+	 * Now we are returning from the patched function to the original
+	 * caller A. We are free to use r0 and r12, and we can use r2 until we
+	 * restore it.
+	 */
+
+	CURRENT_THREAD_INFO(r12, r1)
+
+	/* Save stack pointer into r0 */
+	mr	r0, r1
+
+	ld	r1, TI_livepatch_sp(r12)
+
+	/* Check stack marker hasn't been trashed */
+	lis     r2,  STACK_END_MAGIC@h
+	ori     r2,  r2, STACK_END_MAGIC@l
+	ld	r12, -8(r1)
+1:	tdne	r12, r2
+	EMIT_BUG_ENTRY 1b, __FILE__, __LINE__ - 1, 0
+
+	/* Restore LR & toc from livepatch stack */
+	ld	r12, -16(r1)
+	mtlr	r12
+	ld	r2,  -24(r1)
+
+	/* Pop livepatch stack frame */
+	CURRENT_THREAD_INFO(r12, r0)
+	subi	r1, r1, 24
+	std	r1, TI_livepatch_sp(r12)
+
+	/* Restore real stack pointer */
+	mr	r1, r0
+
+	/* Return to original caller of live patched function */
+	blr
+#endif
+
+
+#else
+_GLOBAL_TOC(_mcount)
+EXPORT_SYMBOL(_mcount)
+	/* Taken from output of objdump from lib64/glibc */
+	mflr	r3
+	ld	r11, 0(r1)
+	stdu	r1, -112(r1)
+	std	r3, 128(r1)
+	ld	r4, 16(r11)
+
+	subi	r3, r3, MCOUNT_INSN_SIZE
+	LOAD_REG_ADDR(r5,ftrace_trace_function)
+	ld	r5,0(r5)
+	ld	r5,0(r5)
+	mtctr	r5
+	bctrl
+	nop
+
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	b	ftrace_graph_caller
+#endif
+	ld	r0, 128(r1)
+	mtlr	r0
+	addi	r1, r1, 112
+_GLOBAL(ftrace_stub)
+	blr
+
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+#ifndef CC_USING_MPROFILE_KERNEL
+_GLOBAL(ftrace_graph_caller)
+	/* load r4 with local address */
+	ld	r4, 128(r1)
+	subi	r4, r4, MCOUNT_INSN_SIZE
+
+	/* Grab the LR out of the caller stack frame */
+	ld	r11, 112(r1)
+	ld	r3, 16(r11)
+
+	bl	prepare_ftrace_return
+	nop
+
+	/*
+	 * prepare_ftrace_return gives us the address we divert to.
+	 * Change the LR in the callers stack frame to this.
+	 */
+	ld	r11, 112(r1)
+	std	r3, 16(r11)
+
+	ld	r0, 128(r1)
+	mtlr	r0
+	addi	r1, r1, 112
+	blr
+
+#else /* CC_USING_MPROFILE_KERNEL */
+_GLOBAL(ftrace_graph_caller)
+	stdu	r1, -112(r1)
+	/* with -mprofile-kernel, parameter regs are still alive at _mcount */
+	std	r10, 104(r1)
+	std	r9, 96(r1)
+	std	r8, 88(r1)
+	std	r7, 80(r1)
+	std	r6, 72(r1)
+	std	r5, 64(r1)
+	std	r4, 56(r1)
+	std	r3, 48(r1)
+
+	/* Save callee's TOC in the ABI compliant location */
+	std	r2, 24(r1)
+	ld	r2, PACATOC(r13)	/* get kernel TOC in r2 */
+
+	mfctr	r4		/* ftrace_caller has moved local addr here */
+	std	r4, 40(r1)
+	mflr	r3		/* ftrace_caller has restored LR from stack */
+	subi	r4, r4, MCOUNT_INSN_SIZE
+
+	bl	prepare_ftrace_return
+	nop
+
+	/*
+	 * prepare_ftrace_return gives us the address we divert to.
+	 * Change the LR to this.
+	 */
+	mtlr	r3
+
+	ld	r0, 40(r1)
+	mtctr	r0
+	ld	r10, 104(r1)
+	ld	r9, 96(r1)
+	ld	r8, 88(r1)
+	ld	r7, 80(r1)
+	ld	r6, 72(r1)
+	ld	r5, 64(r1)
+	ld	r4, 56(r1)
+	ld	r3, 48(r1)
+
+	/* Restore callee's TOC */
+	ld	r2, 24(r1)
+
+	addi	r1, r1, 112
+	mflr	r0
+	std	r0, LRSAVE(r1)
+	bctr
+#endif /* CC_USING_MPROFILE_KERNEL */
+
+_GLOBAL(return_to_handler)
+	/* need to save return values */
+	std	r4,  -32(r1)
+	std	r3,  -24(r1)
+	/* save TOC */
+	std	r2,  -16(r1)
+	std	r31, -8(r1)
+	mr	r31, r1
+	stdu	r1, -112(r1)
+
+	/*
+	 * We might be called from a module.
+	 * Switch to our TOC to run inside the core kernel.
+	 */
+	ld	r2, PACATOC(r13)
+
+	bl	ftrace_return_to_handler
+	nop
+
+	/* return value has real return address */
+	mtlr	r3
+
+	ld	r1, 0(r1)
+	ld	r4,  -32(r1)
+	ld	r3,  -24(r1)
+	ld	r2,  -16(r1)
+	ld	r31, -8(r1)
+
+	/* Jump back to real return address */
+	blr
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/powerpc/kernel/trace/trace_clock.c b/arch/powerpc/kernel/trace/trace_clock.c
new file mode 100644
index 000000000000..49170690946d
--- /dev/null
+++ b/arch/powerpc/kernel/trace/trace_clock.c
@@ -0,0 +1,15 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * Copyright (C) 2015 Naveen N. Rao, IBM Corporation
+ */
+
+#include <asm/trace_clock.h>
+#include <asm/time.h>
+
+u64 notrace trace_clock_ppc_tb(void)
+{
+	return get_tb();
+}