ftrace: Use of __fentry__

Ingo,

Please pull the latest tip/perf/core tree, which can be found at:

git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace.git
tip/perf/core

Head SHA1: d57c5d51a30152f3175d2344cb6395f08bf8ee0c

Steven Rostedt (4):
ftrace: Make recordmcount.c handle __fentry__
ftrace: Add -mfentry to Makefile on function tracer
ftrace: Do not test frame pointers if -mfentry is used ftrace/x86: Add support for -mfentry to x86_64

----

 Makefile                             |    6 +++++-
 arch/x86/Kconfig                     |    1 +
 arch/x86/include/asm/ftrace.h        |    7 ++++++-
 arch/x86/kernel/entry_64.S           |   32 +++++++++++++++++++++++++++-----
 arch/x86/kernel/x8664_ksyms_64.c     |    6 +++++-
 kernel/trace/Kconfig                 |    5 +++++
 kernel/trace/trace_functions_graph.c |    5 ++++-
 scripts/recordmcount.h               |    4 +++-
 8 files changed, 56 insertions(+), 10 deletions(-)

With gcc 4.6.0 the -mfentry feature places the function profiling call at the start of the function. When this is used, the call is to __fentry__ and not mcount.

Change recordmcount.c to record both callers to __fentry__ and mcount.

---
 scripts/recordmcount.h |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

index 54e35c1..9d1421e 100644
@@ -261,11 +261,13 @@ static unsigned get_mcountsym(Elf_Sym const *const sym0,
 		&sym0[Elf_r_sym(relp)];
 	char const *symname = &str0[w(symp->st_name)];
 	char const *mcount = gpfx == '_' ? "_mcount" : "mcount";
+	char const *fentry = "__fentry__";
 
 	if (symname[0] == '.')
 		++symname;  /* ppc64 hack */
 	if (strcmp(mcount, symname) == 0 ||
-	    (altmcount && strcmp(altmcount, symname) == 0))
+	    (altmcount && strcmp(altmcount, symname) == 0) ||
+	    (strcmp(fentry, symname) == 0))
 		mcountsym = Elf_r_sym(relp);
 
 	return mcountsym;

1.7.10.4

I did a quick read of the patches and they all look good to me.

-Andi

[email protected] -- Speaking for myself only.

Thanks to Andi Kleen, gcc 4.6.0 now supports -mfentry for x86 (and hopefully soon for other archs). What this does is to have the function profiler start at the beginning of the function instead of after the stack is set up. As plain -pg (mcount) is called after the stack is set up, and in some cases can have issues with the function graph tracer. It also requires frame pointers to be enabled.

The -mfentry now calls __fentry__ at the beginning of the function. This allows for compiling without frame pointers and even has the ability to access parameters if needed.

If the architecture and the compiler both support -mfentry then use that instead.

---
 Makefile             |    6 +++++-
 kernel/trace/Kconfig |    5 +++++
 2 files changed, 10 insertions(+), 1 deletion(-)

index ddf5be9..e7ca93f 100644
@@ -609,7 +609,11 @@ KBUILD_CFLAGS 	+= $(call cc-option, -femit-struct-debug-baseonly)
 endif
 
 ifdef CONFIG_FUNCTION_TRACER
-KBUILD_CFLAGS	+= -pg
+ifdef CONFIG_HAVE_FENTRY
+CC_USING_FENTRY	:= $(call cc-option, -mfentry -DCC_USING_FENTRY)
+endif
+KBUILD_CFLAGS	+= -pg $(CC_USING_FENTRY)
+KBUILD_AFLAGS	+= $(CC_USING_FENTRY)
 ifdef CONFIG_DYNAMIC_FTRACE
 	ifdef CONFIG_HAVE_C_RECORDMCOUNT
 		BUILD_C_RECORDMCOUNT := y

index 8c4c070..9301a0e 100644
@@ -49,6 +49,11 @@ config HAVE_SYSCALL_TRACEPOINTS
 	help
 	  See Documentation/trace/ftrace-design.txt
 
+config HAVE_FENTRY
+	bool
+	help
+	  Arch supports the gcc options -pg with -mfentry
+
 config HAVE_C_RECORDMCOUNT
 	bool
 	help

1.7.10.4

The function graph has a test to check if the frame pointer is corrupted, which can happen with various options of gcc with mcount. But this is not an issue with -mfentry as -mfentry does not need nor use frame pointers for function graph tracing.

---
 kernel/trace/trace_functions_graph.c |    5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

index ce27c8b..99b4378 100644
@@ -143,7 +143,7 @@ ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret,
 		return;
 	}
 
-#ifdef CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST
+#if defined(CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST) && !defined(CC_USING_FENTRY)
 	/*
 	 * The arch may choose to record the frame pointer used
 	 * and check it here to make sure that it is what we expect it

@@ -154,6 +154,9 @@ ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret,
 	 *
 	 * Currently, x86_32 with optimize for size (-Os) makes the latest
 	 * gcc do the above.
+	 *
+	 * Note, -mfentry does not use frame pointers, and this test
+	 *  is not needed if CC_USING_FENTRY is set.
 	 */
 	if (unlikely(current->ret_stack[index].fp != frame_pointer)) {
 		ftrace_graph_stop();

1.7.10.4

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.

---
 arch/x86/Kconfig                 |    1 +
 arch/x86/include/asm/ftrace.h    |    7 ++++++-
 arch/x86/kernel/entry_64.S       |   32 +++++++++++++++++++++++++++-----
 arch/x86/kernel/x8664_ksyms_64.c |    6 +++++-
 4 files changed, 39 insertions(+), 7 deletions(-)

index a2d19ee..28dd891 100644
@@ -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

index a6cae0c..9a25b52 100644
@@ -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)
 {

index b7a81dc..ed767b7 100644
@@ -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

index 6020f6f..1330dd1 100644
@@ -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