[RFC PATCH 4/4] ftrace/x86: Add support for -mfentry to x86_64

From: Steven Rostedt
Date: Tue Aug 07 2012 - 15:41:28 EST


From: Steven Rostedt <srostedt@xxxxxxxxxx>

If the kernel is compiled with gcc 4.6.0 which supports -mfentry,
then use that instead of mcount.

With mcount, frame pointers are forced with the -pg option and we
get something like:

<can_vma_merge_before>:
55 push %rbp
48 89 e5 mov %rsp,%rbp
53 push %rbx
41 51 push %r9
e8 fe 6a 39 00 callq ffffffff81483d00 <mcount>
31 c0 xor %eax,%eax
48 89 fb mov %rdi,%rbx
48 89 d7 mov %rdx,%rdi
48 33 73 30 xor 0x30(%rbx),%rsi
48 f7 c6 ff ff ff f7 test $0xfffffffff7ffffff,%rsi

With -mfentry, frame pointers are no longer forced and the call looks
like this:

<can_vma_merge_before>:
e8 33 af 37 00 callq ffffffff81461b40 <__fentry__>
53 push %rbx
48 89 fb mov %rdi,%rbx
31 c0 xor %eax,%eax
48 89 d7 mov %rdx,%rdi
41 51 push %r9
48 33 73 30 xor 0x30(%rbx),%rsi
48 f7 c6 ff ff ff f7 test $0xfffffffff7ffffff,%rsi

This adds the ftrace hook at the beginning of the function before a
frame is set up, and allows the function callbacks to be able to access
parameters. As kprobes now can use function tracing (at least on x86)
this speeds up the kprobe hooks that are at the beginning of the
function.

Cc: Masami Hiramatsu <masami.hiramatsu.pt@xxxxxxxxxxx>
Cc: Andi Kleen <andi@xxxxxxxxxxxxxx>
Signed-off-by: Steven Rostedt <rostedt@xxxxxxxxxxx>
---
arch/x86/Kconfig | 1 +
arch/x86/include/asm/ftrace.h | 7 ++++++-
arch/x86/kernel/entry_64.S | 18 +++++++++++++++++-
arch/x86/kernel/x8664_ksyms_64.c | 6 +++++-
4 files changed, 29 insertions(+), 3 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index c70684f..bbbf5d8 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -36,6 +36,7 @@ config X86
select HAVE_KRETPROBES
select HAVE_OPTPROBES
select HAVE_FTRACE_MCOUNT_RECORD
+ select HAVE_FENTRY if X86_64
select HAVE_C_RECORDMCOUNT
select HAVE_DYNAMIC_FTRACE
select HAVE_FUNCTION_TRACER
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index a6cae0c..9a25b52 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -35,7 +35,11 @@
#endif

#ifdef CONFIG_FUNCTION_TRACER
-#define MCOUNT_ADDR ((long)(mcount))
+#ifdef CC_USING_FENTRY
+# define MCOUNT_ADDR ((long)(__fentry__))
+#else
+# define MCOUNT_ADDR ((long)(mcount))
+#endif
#define MCOUNT_INSN_SIZE 5 /* sizeof mcount call */

#ifdef CONFIG_DYNAMIC_FTRACE
@@ -46,6 +50,7 @@
#ifndef __ASSEMBLY__
extern void mcount(void);
extern atomic_t modifying_ftrace_code;
+extern void __fentry__(void);

static inline unsigned long ftrace_call_adjust(unsigned long addr)
{
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 38308fa..2add3bb 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -69,9 +69,16 @@

#ifdef CONFIG_FUNCTION_TRACER
#ifdef CONFIG_DYNAMIC_FTRACE
+
+#ifdef CC_USING_FENTRY
+ENTRY(__fentry__)
+ retq
+END(__fentry__)
+#else
ENTRY(mcount)
retq
END(mcount)
+#endif

/* skip is set if stack has been adjusted */
.macro ftrace_caller_setup skip=0
@@ -84,7 +91,11 @@ END(mcount)
movq RIP(%rsp), %rdi
subq $MCOUNT_INSN_SIZE, %rdi
/* Load the parent_ip into the second parameter */
+#ifdef CC_USING_FENTRY
+ movq SS+16(%rsp), %rsi
+#else
movq 8(%rbp), %rsi
+#endif
.endm

ENTRY(ftrace_caller)
@@ -215,9 +226,14 @@ END(mcount)
ENTRY(ftrace_graph_caller)
MCOUNT_SAVE_FRAME

+#ifdef CC_USING_FENTRY
+ leaq SS+16(%rsp), %rdi
+ movq $0, %rdx /* No framepointers needed */
+#else
leaq 8(%rbp), %rdi
- movq RIP(%rsp), %rsi
movq (%rbp), %rdx
+#endif
+ movq RIP(%rsp), %rsi
subq $MCOUNT_INSN_SIZE, %rsi

call prepare_ftrace_return
diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c
index 9796c2f..643b236 100644
--- a/arch/x86/kernel/x8664_ksyms_64.c
+++ b/arch/x86/kernel/x8664_ksyms_64.c
@@ -13,9 +13,13 @@
#include <asm/ftrace.h>

#ifdef CONFIG_FUNCTION_TRACER
-/* mcount is defined in assembly */
+/* mcount and __fentry__ are defined in assembly */
+#ifdef CC_USING_FENTRY
+EXPORT_SYMBOL(__fentry__);
+#else
EXPORT_SYMBOL(mcount);
#endif
+#endif

EXPORT_SYMBOL(__get_user_1);
EXPORT_SYMBOL(__get_user_2);
--
1.7.10.4


Attachment: signature.asc
Description: This is a digitally signed message part