ftrace/x86: Add support for -mfentry to x86_64

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.

Link: http://lkml.kernel.org/r/20120807194100.130477900@goodmis.org

Acked-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Andi Kleen <andi@firstfloor.org>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

4 files changed, 39 insertions, 7 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index a2d19ee750ca..28dd891a0a16 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 a6cae0c1720c..9a25b522d377 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 b7a81dcb7366..ed767b747fe5 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -68,10 +68,18 @@
         .section .entry.text, "ax"
 
 #ifdef CONFIG_FUNCTION_TRACER
+
+#ifdef CC_USING_FENTRY
+# define function_hook  __fentry__
+#else
+# define function_hook  mcount
+#endif
+
 #ifdef CONFIG_DYNAMIC_FTRACE
-ENTRY(mcount)
+
+ENTRY(function_hook)
         retq
-END(mcount)
+END(function_hook)
 
 /* skip is set if stack has been adjusted */
 .macro ftrace_caller_setup skip=0
@@ -84,7 +92,11 @@ 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)
@@ -177,7 +189,8 @@ END(ftrace_regs_caller)
 
 
 #else /* ! CONFIG_DYNAMIC_FTRACE */
-ENTRY(mcount)
+
+ENTRY(function_hook)
         cmpl $0, function_trace_stop
         jne  ftrace_stub
 
@@ -199,7 +212,11 @@ trace:
         MCOUNT_SAVE_FRAME
 
         movq RIP(%rsp), %rdi
+#ifdef CC_USING_FENTRY
+        movq SS+16(%rsp), %rsi
+#else
         movq 8(%rbp), %rsi
+#endif
         subq $MCOUNT_INSN_SIZE, %rdi
 
         call   *ftrace_trace_function
@@ -207,7 +224,7 @@ trace:
         MCOUNT_RESTORE_FRAME
 
         jmp ftrace_stub
-END(mcount)
+END(function_hook)
 #endif /* CONFIG_DYNAMIC_FTRACE */
 #endif /* CONFIG_FUNCTION_TRACER */
 
@@ -215,9 +232,14 @@ 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 6020f6f5927c..1330dd102950 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);