Merge tag 'trace-3.19' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace

1dd7dcb6 · Linus Torvalds <[email protected]> · 2014-12-10 19:58:13 -08:00

Pull tracing updates from Steven Rostedt:
 "There was a lot of clean ups and minor fixes.  One of those clean ups
  was to the trace_seq code.  It also removed the return values to the
  trace_seq_*() functions and use trace_seq_has_overflowed() to see if
  the buffer filled up or not.  This is similar to work being done to
  the seq_file code as well in another tree.

  Some of the other goodies include:

   - Added some "!" (NOT) logic to the tracing filter.

   - Fixed the frame pointer logic to the x86_64 mcount trampolines

   - Added the logic for dynamic trampolines on !CONFIG_PREEMPT systems.
     That is, the ftrace trampoline can be dynamically allocated and be
     called directly by functions that only have a single hook to them"

* tag 'trace-3.19' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace: (55 commits)
  tracing: Truncated output is better than nothing
  tracing: Add additional marks to signal very large time deltas
  Documentation: describe trace_buf_size parameter more accurately
  tracing: Allow NOT to filter AND and OR clauses
  tracing: Add NOT to filtering logic
  ftrace/fgraph/x86: Have prepare_ftrace_return() take ip as first parameter
  ftrace/x86: Get rid of ftrace_caller_setup
  ftrace/x86: Have save_mcount_regs macro also save stack frames if needed
  ftrace/x86: Add macro MCOUNT_REG_SIZE for amount of stack used to save mcount regs
  ftrace/x86: Simplify save_mcount_regs on getting RIP
  ftrace/x86: Have save_mcount_regs store RIP in %rdi for first parameter
  ftrace/x86: Rename MCOUNT_SAVE_FRAME and add more detailed comments
  ftrace/x86: Move MCOUNT_SAVE_FRAME out of header file
  ftrace/x86: Have static tracing also use ftrace_caller_setup
  ftrace/x86: Have static function tracing always test for function graph
  kprobes: Add IPMODIFY flag to kprobe_ftrace_ops
  ftrace, kprobes: Support IPMODIFY flag to find IP modify conflict
  kprobes/ftrace: Recover original IP if pre_handler doesn't change it
  tracing/trivial: Fix typos and make an int into a bool
  tracing: Deletion of an unnecessary check before iput()
  ...

Commit: 1dd7dcb6eaa677b034e7ef63df8320277507ae70
Parents: b6da0076 · 3558a5ac

Merge commit. Changes below are compared with the first parent: b6da0076.

Changes

38 files changed · +1680 −1312

File	Status	Add	Del	Content
Documentation/kernel-parameters.txt	modified	+1	−1	View file
Documentation/trace/ftrace.txt	modified	+12	−3	View file
arch/powerpc/kernel/ftrace.c	modified	+1	−1	View file
arch/x86/include/asm/ftrace.h	modified	+0	−33	View file
arch/x86/kernel/ftrace.c	modified	+279	−9	View file
arch/x86/kernel/kprobes/ftrace.c	modified	+6	−3	View file
arch/x86/kernel/mcount_64.S	modified	+172	−52	View file
arch/x86/kvm/mmutrace.h	modified	+2	−2	View file
drivers/firmware/efi/cper.c	modified	+1	−1	View file
include/linux/ftrace.h	modified	+33	−3	View file
include/linux/ftrace_event.h	modified	+11	−0	View file
include/linux/trace_seq.h	modified	+27	−22	View file
include/trace/ftrace.h	modified	+3	−5	View file
kernel/extable.c	modified	+6	−1	View file
kernel/kprobes.c	modified	+1	−1	View file
kernel/trace/blktrace.c	modified	+66	−82	View file
kernel/trace/ftrace.c	modified	+298	−32	View file
kernel/trace/ring_buffer.c	modified	+36	−39	View file
kernel/trace/trace.c	modified	+79	−80	View file
kernel/trace/trace.h	modified	+4	−13	View file
kernel/trace/trace_branch.c	modified	+23	−24	View file
kernel/trace/trace_events.c	modified	+2	−2	View file
kernel/trace/trace_events_filter.c	modified	+23	−6	View file
kernel/trace/trace_events_trigger.c	modified	+3	−3	View file
kernel/trace/trace_functions.c	modified	+97	−22	View file
kernel/trace/trace_functions_graph.c	modified	+128	−284	View file
kernel/trace/trace_kdb.c	modified	+13	−8	View file
kernel/trace/trace_kprobe.c	modified	+18	−28	View file
kernel/trace/trace_mmiotrace.c	modified	+21	−31	View file
kernel/trace/trace_output.c	modified	+191	−255	View file
kernel/trace/trace_output.h	modified	+5	−11	View file
kernel/trace/trace_printk.c	modified	+1	−1	View file
kernel/trace/trace_probe.c	modified	+6	−4	View file
kernel/trace/trace_sched_switch.c	modified	+0	−144	View file
kernel/trace/trace_sched_wakeup.c	modified	+56	−0	View file
kernel/trace/trace_seq.c	modified	+24	−62	View file
kernel/trace/trace_syscalls.c	modified	+19	−28	View file
kernel/trace/trace_uprobe.c	modified	+12	−16	View file

Only the first 600 diff lines are shown. Download the complete patch.

Documentation/kernel-parameters.txt

View file

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index d6eb363..32ba9ea 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -3520,7 +3520,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			are saved.
 
 	trace_buf_size=nn[KMG]
-			[FTRACE] will set tracing buffer size.
+			[FTRACE] will set tracing buffer size on each cpu.
 
 	trace_event=[event-list]
 			[FTRACE] Set and start specified trace events in order

Documentation/trace/ftrace.txt

View file

diff --git a/Documentation/trace/ftrace.txt b/Documentation/trace/ftrace.txt
index 4da4261..8408e04 100644
--- a/Documentation/trace/ftrace.txt
+++ b/Documentation/trace/ftrace.txt
@@ -234,6 +234,11 @@ of ftrace. Here is a list of some of the key files:
 	will be displayed on the same line as the function that
 	is returning registers.
 
+	If the callback registered to be traced by a function with
+	the "ip modify" attribute (thus the regs->ip can be changed),
+	an 'I' will be displayed on the same line as the function that
+	can be overridden.
+
   function_profile_enabled:
 
 	When set it will enable all functions with either the function
@@ -680,9 +685,11 @@ The above is mostly meaningful for kernel developers.
 	 needs to be fixed to be only relative to the same CPU.
 	 The marks are determined by the difference between this
 	 current trace and the next trace.
-	  '!' - greater than preempt_mark_thresh (default 100)
-	  '+' - greater than 1 microsecond
-	  ' ' - less than or equal to 1 microsecond.
+	  '$' - greater than 1 second
+	  '#' - greater than 1000 microsecond
+	  '!' - greater than 100 microsecond
+	  '+' - greater than 10 microsecond
+	  ' ' - less than or equal to 10 microsecond.
 
   The rest is the same as the 'trace' file.
 
@@ -1951,6 +1958,8 @@ want, depending on your needs.
 
   + means that the function exceeded 10 usecs.
   ! means that the function exceeded 100 usecs.
+  # means that the function exceeded 1000 usecs.
+  $ means that the function exceeded 1 sec.
 
 
 - The task/pid field displays the thread cmdline and pid which

arch/powerpc/kernel/ftrace.c

View file

diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c
index 390311c..e66af6d 100644
--- a/arch/powerpc/kernel/ftrace.c
+++ b/arch/powerpc/kernel/ftrace.c
@@ -449,7 +449,7 @@ void ftrace_replace_code(int enable)
 		rec = ftrace_rec_iter_record(iter);
 		ret = __ftrace_replace_code(rec, enable);
 		if (ret) {
-			ftrace_bug(ret, rec->ip);
+			ftrace_bug(ret, rec);
 			return;
 		}
 	}

arch/x86/include/asm/ftrace.h

View file

diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index e1f7fec..f45acad 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -1,39 +1,6 @@
 #ifndef _ASM_X86_FTRACE_H
 #define _ASM_X86_FTRACE_H
 
-#ifdef __ASSEMBLY__
-
-	/* skip is set if the stack was already partially adjusted */
-	.macro MCOUNT_SAVE_FRAME skip=0
-	 /*
-	  * We add enough stack to save all regs.
-	  */
-	subq $(SS+8-\skip), %rsp
-	movq %rax, RAX(%rsp)
-	movq %rcx, RCX(%rsp)
-	movq %rdx, RDX(%rsp)
-	movq %rsi, RSI(%rsp)
-	movq %rdi, RDI(%rsp)
-	movq %r8, R8(%rsp)
-	movq %r9, R9(%rsp)
-	 /* Move RIP to its proper location */
-	movq SS+8(%rsp), %rdx
-	movq %rdx, RIP(%rsp)
-	.endm
-
-	.macro MCOUNT_RESTORE_FRAME skip=0
-	movq R9(%rsp), %r9
-	movq R8(%rsp), %r8
-	movq RDI(%rsp), %rdi
-	movq RSI(%rsp), %rsi
-	movq RDX(%rsp), %rdx
-	movq RCX(%rsp), %rcx
-	movq RAX(%rsp), %rax
-	addq $(SS+8-\skip), %rsp
-	.endm
-
-#endif
-
 #ifdef CONFIG_FUNCTION_TRACER
 #ifdef CC_USING_FENTRY
 # define MCOUNT_ADDR		((long)(__fentry__))

arch/x86/kernel/ftrace.c

View file

diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 3386dc9..2142376 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -17,6 +17,7 @@
 #include <linux/ftrace.h>
 #include <linux/percpu.h>
 #include <linux/sched.h>
+#include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/list.h>
 #include <linux/module.h>
@@ -47,7 +48,7 @@ int ftrace_arch_code_modify_post_process(void)
 union ftrace_code_union {
 	char code[MCOUNT_INSN_SIZE];
 	struct {
-		char e8;
+		unsigned char e8;
 		int offset;
 	} __attribute__((packed));
 };
@@ -582,7 +583,7 @@ void ftrace_replace_code(int enable)
 
  remove_breakpoints:
 	pr_warn("Failed on %s (%d):\n", report, count);
-	ftrace_bug(ret, rec ? rec->ip : 0);
+	ftrace_bug(ret, rec);
 	for_ftrace_rec_iter(iter) {
 		rec = ftrace_rec_iter_record(iter);
 		/*
@@ -644,13 +645,8 @@ int __init ftrace_dyn_arch_init(void)
 {
 	return 0;
 }
-#endif
-
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-
-#ifdef CONFIG_DYNAMIC_FTRACE
-extern void ftrace_graph_call(void);
 
+#if defined(CONFIG_X86_64) || defined(CONFIG_FUNCTION_GRAPH_TRACER)
 static unsigned char *ftrace_jmp_replace(unsigned long ip, unsigned long addr)
 {
 	static union ftrace_code_union calc;
@@ -664,6 +660,280 @@ static unsigned char *ftrace_jmp_replace(unsigned long ip, unsigned long addr)
 	 */
 	return calc.code;
 }
+#endif
+
+/* Currently only x86_64 supports dynamic trampolines */
+#ifdef CONFIG_X86_64
+
+#ifdef CONFIG_MODULES
+#include <linux/moduleloader.h>
+/* Module allocation simplifies allocating memory for code */
+static inline void *alloc_tramp(unsigned long size)
+{
+	return module_alloc(size);
+}
+static inline void tramp_free(void *tramp)
+{
+	module_free(NULL, tramp);
+}
+#else
+/* Trampolines can only be created if modules are supported */
+static inline void *alloc_tramp(unsigned long size)
+{
+	return NULL;
+}
+static inline void tramp_free(void *tramp) { }
+#endif
+
+/* Defined as markers to the end of the ftrace default trampolines */
+extern void ftrace_caller_end(void);
+extern void ftrace_regs_caller_end(void);
+extern void ftrace_return(void);
+extern void ftrace_caller_op_ptr(void);
+extern void ftrace_regs_caller_op_ptr(void);
+
+/* movq function_trace_op(%rip), %rdx */
+/* 0x48 0x8b 0x15 <offset-to-ftrace_trace_op (4 bytes)> */
+#define OP_REF_SIZE	7
+
+/*
+ * The ftrace_ops is passed to the function callback. Since the
+ * trampoline only services a single ftrace_ops, we can pass in
+ * that ops directly.
+ *
+ * The ftrace_op_code_union is used to create a pointer to the
+ * ftrace_ops that will be passed to the callback function.
+ */
+union ftrace_op_code_union {
+	char code[OP_REF_SIZE];
+	struct {
+		char op[3];
+		int offset;
+	} __attribute__((packed));
+};
+
+static unsigned long
+create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
+{
+	unsigned const char *jmp;
+	unsigned long start_offset;
+	unsigned long end_offset;
+	unsigned long op_offset;
+	unsigned long offset;
+	unsigned long size;
+	unsigned long ip;
+	unsigned long *ptr;
+	void *trampoline;
+	/* 48 8b 15 <offset> is movq <offset>(%rip), %rdx */
+	unsigned const char op_ref[] = { 0x48, 0x8b, 0x15 };
+	union ftrace_op_code_union op_ptr;
+	int ret;
+
+	if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) {
+		start_offset = (unsigned long)ftrace_regs_caller;
+		end_offset = (unsigned long)ftrace_regs_caller_end;
+		op_offset = (unsigned long)ftrace_regs_caller_op_ptr;
+	} else {
+		start_offset = (unsigned long)ftrace_caller;
+		end_offset = (unsigned long)ftrace_caller_end;
+		op_offset = (unsigned long)ftrace_caller_op_ptr;
+	}
+
+	size = end_offset - start_offset;
+
+	/*
+	 * Allocate enough size to store the ftrace_caller code,
+	 * the jmp to ftrace_return, as well as the address of
+	 * the ftrace_ops this trampoline is used for.
+	 */
+	trampoline = alloc_tramp(size + MCOUNT_INSN_SIZE + sizeof(void *));
+	if (!trampoline)
+		return 0;
+
+	*tramp_size = size + MCOUNT_INSN_SIZE + sizeof(void *);
+
+	/* Copy ftrace_caller onto the trampoline memory */
+	ret = probe_kernel_read(trampoline, (void *)start_offset, size);
+	if (WARN_ON(ret < 0)) {
+		tramp_free(trampoline);
+		return 0;
+	}
+
+	ip = (unsigned long)trampoline + size;
+
+	/* The trampoline ends with a jmp to ftrace_return */
+	jmp = ftrace_jmp_replace(ip, (unsigned long)ftrace_return);
+	memcpy(trampoline + size, jmp, MCOUNT_INSN_SIZE);
+
+	/*
+	 * The address of the ftrace_ops that is used for this trampoline
+	 * is stored at the end of the trampoline. This will be used to
+	 * load the third parameter for the callback. Basically, that
+	 * location at the end of the trampoline takes the place of
+	 * the global function_trace_op variable.
+	 */
+
+	ptr = (unsigned long *)(trampoline + size + MCOUNT_INSN_SIZE);
+	*ptr = (unsigned long)ops;
+
+	op_offset -= start_offset;
+	memcpy(&op_ptr, trampoline + op_offset, OP_REF_SIZE);
+
+	/* Are we pointing to the reference? */
+	if (WARN_ON(memcmp(op_ptr.op, op_ref, 3) != 0)) {
+		tramp_free(trampoline);
+		return 0;
+	}
+
+	/* Load the contents of ptr into the callback parameter */
+	offset = (unsigned long)ptr;
+	offset -= (unsigned long)trampoline + op_offset + OP_REF_SIZE;
+
+	op_ptr.offset = offset;
+
+	/* put in the new offset to the ftrace_ops */
+	memcpy(trampoline + op_offset, &op_ptr, OP_REF_SIZE);
+
+	/* ALLOC_TRAMP flags lets us know we created it */
+	ops->flags |= FTRACE_OPS_FL_ALLOC_TRAMP;
+
+	return (unsigned long)trampoline;
+}
+
+static unsigned long calc_trampoline_call_offset(bool save_regs)
+{
+	unsigned long start_offset;
+	unsigned long call_offset;
+
+	if (save_regs) {
+		start_offset = (unsigned long)ftrace_regs_caller;
+		call_offset = (unsigned long)ftrace_regs_call;
+	} else {
+		start_offset = (unsigned long)ftrace_caller;
+		call_offset = (unsigned long)ftrace_call;
+	}
+
+	return call_offset - start_offset;
+}
+
+void arch_ftrace_update_trampoline(struct ftrace_ops *ops)
+{
+	ftrace_func_t func;
+	unsigned char *new;
+	unsigned long offset;
+	unsigned long ip;
+	unsigned int size;
+	int ret;
+
+	if (ops->trampoline) {
+		/*
+		 * The ftrace_ops caller may set up its own trampoline.
+		 * In such a case, this code must not modify it.
+		 */
+		if (!(ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP))
+			return;
+	} else {
+		ops->trampoline = create_trampoline(ops, &size);
+		if (!ops->trampoline)
+			return;
+		ops->trampoline_size = size;
+	}
+
+	offset = calc_trampoline_call_offset(ops->flags & FTRACE_OPS_FL_SAVE_REGS);
+	ip = ops->trampoline + offset;
+
+	func = ftrace_ops_get_func(ops);
+
+	/* Do a safe modify in case the trampoline is executing */
+	new = ftrace_call_replace(ip, (unsigned long)func);
+	ret = update_ftrace_func(ip, new);
+
+	/* The update should never fail */
+	WARN_ON(ret);
+}
+
+/* Return the address of the function the trampoline calls */
+static void *addr_from_call(void *ptr)
+{
+	union ftrace_code_union calc;
+	int ret;
+
+	ret = probe_kernel_read(&calc, ptr, MCOUNT_INSN_SIZE);
+	if (WARN_ON_ONCE(ret < 0))
+		return NULL;
+
+	/* Make sure this is a call */
+	if (WARN_ON_ONCE(calc.e8 != 0xe8)) {
+		pr_warn("Expected e8, got %x\n", calc.e8);
+		return NULL;
+	}
+
+	return ptr + MCOUNT_INSN_SIZE + calc.offset;
+}
+
+void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent,
+			   unsigned long frame_pointer);
+
+/*
+ * If the ops->trampoline was not allocated, then it probably
+ * has a static trampoline func, or is the ftrace caller itself.
+ */
+static void *static_tramp_func(struct ftrace_ops *ops, struct dyn_ftrace *rec)
+{
+	unsigned long offset;
+	bool save_regs = rec->flags & FTRACE_FL_REGS_EN;
+	void *ptr;
+
+	if (ops && ops->trampoline) {
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+		/*
+		 * We only know about function graph tracer setting as static
+		 * trampoline.
+		 */
+		if (ops->trampoline == FTRACE_GRAPH_ADDR)
+			return (void *)prepare_ftrace_return;
+#endif
+		return NULL;
+	}
+
+	offset = calc_trampoline_call_offset(save_regs);
+
+	if (save_regs)
+		ptr = (void *)FTRACE_REGS_ADDR + offset;
+	else
+		ptr = (void *)FTRACE_ADDR + offset;
+
+	return addr_from_call(ptr);
+}
+
+void *arch_ftrace_trampoline_func(struct ftrace_ops *ops, struct dyn_ftrace *rec)
+{
+	unsigned long offset;
+
+	/* If we didn't allocate this trampoline, consider it static */
+	if (!ops || !(ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP))
+		return static_tramp_func(ops, rec);
+
+	offset = calc_trampoline_call_offset(ops->flags & FTRACE_OPS_FL_SAVE_REGS);
+	return addr_from_call((void *)ops->trampoline + offset);
+}
+
+void arch_ftrace_trampoline_free(struct ftrace_ops *ops)
+{
+	if (!ops || !(ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP))
+		return;
+
+	tramp_free((void *)ops->trampoline);
+	ops->trampoline = 0;
+}
+
+#endif /* CONFIG_X86_64 */
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+extern void ftrace_graph_call(void);
 
 static int ftrace_mod_jmp(unsigned long ip, void *func)
 {
@@ -694,7 +964,7 @@ int ftrace_disable_ftrace_graph_caller(void)
  * Hook the return address and push it in the stack of return addrs
  * in current thread info.
  */
-void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
+void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent,
 			   unsigned long frame_pointer)
 {
 	unsigned long old;

arch/x86/kernel/kprobes/ftrace.c

View file

diff --git a/arch/x86/kernel/kprobes/ftrace.c b/arch/x86/kernel/kprobes/ftrace.c
index 717b02a..5f8f0b3 100644
--- a/arch/x86/kernel/kprobes/ftrace.c
+++ b/arch/x86/kernel/kprobes/ftrace.c
@@ -27,7 +27,7 @@
 
 static nokprobe_inline
 int __skip_singlestep(struct kprobe *p, struct pt_regs *regs,
-		      struct kprobe_ctlblk *kcb)
+		      struct kprobe_ctlblk *kcb, unsigned long orig_ip)
 {
 	/*
 	 * Emulate singlestep (and also recover regs->ip)
@@ -39,6 +39,8 @@ int __skip_singlestep(struct kprobe *p, struct pt_regs *regs,
 		p->post_handler(p, regs, 0);
 	}
 	__this_cpu_write(current_kprobe, NULL);
+	if (orig_ip)
+		regs->ip = orig_ip;
 	return 1;
 }
 
@@ -46,7 +48,7 @@ int skip_singlestep(struct kprobe *p, struct pt_regs *regs,
 		    struct kprobe_ctlblk *kcb)
 {
 	if (kprobe_ftrace(p))
-		return __skip_singlestep(p, regs, kcb);
+		return __skip_singlestep(p, regs, kcb, 0);
 	else
 		return 0;
 }
@@ -71,13 +73,14 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
 	if (kprobe_running()) {
 		kprobes_inc_nmissed_count(p);
 	} else {
+		unsigned long orig_ip = regs->ip;
 		/* Kprobe handler expects regs->ip = ip + 1 as breakpoint hit */
 		regs->ip = ip + sizeof(kprobe_opcode_t);
 
 		__this_cpu_write(current_kprobe, p);
 		kcb->kprobe_status = KPROBE_HIT_ACTIVE;
 		if (!p->pre_handler || !p->pre_handler(p, regs))
-			__skip_singlestep(p, regs, kcb);
+			__skip_singlestep(p, regs, kcb, orig_ip);
 		/*
 		 * If pre_handler returns !0, it sets regs->ip and
 		 * resets current kprobe.

arch/x86/kernel/mcount_64.S

View file

diff --git a/arch/x86/kernel/mcount_64.S b/arch/x86/kernel/mcount_64.S
index c73aecf..94ea120 100644
--- a/arch/x86/kernel/mcount_64.S
+++ b/arch/x86/kernel/mcount_64.S
@@ -21,40 +21,159 @@
 # define function_hook	mcount
 #endif
 
+/* All cases save the original rbp (8 bytes) */
+#ifdef CONFIG_FRAME_POINTER
+# ifdef CC_USING_FENTRY
+/* Save parent and function stack frames (rip and rbp) */
+#  define MCOUNT_FRAME_SIZE	(8+16*2)
+# else
+/* Save just function stack frame (rip and rbp) */
+#  define MCOUNT_FRAME_SIZE	(8+16)
+# endif
+#else
+/* No need to save a stack frame */
+# define MCOUNT_FRAME_SIZE	8
+#endif /* CONFIG_FRAME_POINTER */
+
+/* Size of stack used to save mcount regs in save_mcount_regs */
+#define MCOUNT_REG_SIZE		(SS+8 + MCOUNT_FRAME_SIZE)
+
+/*
+ * gcc -pg option adds a call to 'mcount' in most functions.
+ * When -mfentry is used, the call is to 'fentry' and not 'mcount'
+ * and is done before the function's stack frame is set up.
+ * They both require a set of regs to be saved before calling
+ * any C code and restored before returning back to the function.
+ *
+ * On boot up, all these calls are converted into nops. When tracing
+ * is enabled, the call can jump to either ftrace_caller or
+ * ftrace_regs_caller. Callbacks (tracing functions) that require
+ * ftrace_regs_caller (like kprobes) need to have pt_regs passed to
+ * it. For this reason, the size of the pt_regs structure will be
+ * allocated on the stack and the required mcount registers will
+ * be saved in the locations that pt_regs has them in.
+ */
+
+/*
+ * @added: the amount of stack added before calling this
+ *
+ * After this is called, the following registers contain:
+ *
+ *  %rdi - holds the address that called the trampoline
+ *  %rsi - holds the parent function (traced function's return address)
+ *  %rdx - holds the original %rbp
+ */
+.macro save_mcount_regs added=0
+
+	/* Always save the original rbp */
+	pushq %rbp
+
+#ifdef CONFIG_FRAME_POINTER
+	/*
+	 * Stack traces will stop at the ftrace trampoline if the frame pointer
+	 * is not set up properly. If fentry is used, we need to save a frame
+	 * pointer for the parent as well as the function traced, because the
+	 * fentry is called before the stack frame is set up, where as mcount
+	 * is called afterward.
+	 */
+#ifdef CC_USING_FENTRY
+	/* Save the parent pointer (skip orig rbp and our return address) */
+	pushq \added+8*2(%rsp)
+	pushq %rbp
+	movq %rsp, %rbp
+	/* Save the return address (now skip orig rbp, rbp and parent) */
+	pushq \added+8*3(%rsp)
+#else
+	/* Can't assume that rip is before this (unless added was zero) */
+	pushq \added+8(%rsp)
+#endif
+	pushq %rbp
+	movq %rsp, %rbp
+#endif /* CONFIG_FRAME_POINTER */
+
+	/*
+	 * We add enough stack to save all regs.
+	 */
+	subq $(MCOUNT_REG_SIZE - MCOUNT_FRAME_SIZE), %rsp
+	movq %rax, RAX(%rsp)
+	movq %rcx, RCX(%rsp)
+	movq %rdx, RDX(%rsp)
+	movq %rsi, RSI(%rsp)
+	movq %rdi, RDI(%rsp)
+	movq %r8, R8(%rsp)
+	movq %r9, R9(%rsp)
+	/*
+	 * Save the original RBP. Even though the mcount ABI does not
+	 * require this, it helps out callers.
+	 */
+	movq MCOUNT_REG_SIZE-8(%rsp), %rdx
+	movq %rdx, RBP(%rsp)
+
+	/* Copy the parent address into %rsi (second parameter) */
+#ifdef CC_USING_FENTRY
+	movq MCOUNT_REG_SIZE+8+\added(%rsp), %rsi
+#else
+	/* %rdx contains original %rbp */
+	movq 8(%rdx), %rsi
+#endif
+
+	 /* Move RIP to its proper location */
+	movq MCOUNT_REG_SIZE+\added(%rsp), %rdi
+	movq %rdi, RIP(%rsp)
+