ftrace/recordmcount: Make ignored mcount calls into nops at compile time

There are sections that are ignored by ftrace for the function tracing because
the text is in a section that can be removed without notice. The mcount calls
in these sections are ignored and ftrace never sees them. The downside of this
is that the functions in these sections still call mcount. Although the mcount
function is defined in assembly simply as a return, this added overhead is
unnecessary.

The solution is to convert these callers into nops at compile time.
A better solution is to add 'notrace' to the section markers, but as new sections
come up all the time, it would be nice that they are delt with when they
are created.

Later patches will deal with finding these sections and doing the proper solution.

Thanks to H. Peter Anvin for giving me the right nops to use for x86.

Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: John Reiser <jreiser@bitwagon.com>
Link: http://lkml.kernel.org/r/20110421023738.237101176@goodmis.org
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

1 files changed, 38 insertions, 2 deletions

diff --git a/scripts/recordmcount.c b/scripts/recordmcount.c
index 37c59654c13..78054a41d13 100644
--- a/scripts/recordmcount.c
+++ b/scripts/recordmcount.c
@@ -118,6 +118,34 @@ umalloc(size_t size)
 	return addr;
 }
 
+static unsigned char ideal_nop5_x86_64[5] = { 0x0f, 0x1f, 0x44, 0x00, 0x00 };
+static unsigned char ideal_nop5_x86_32[5] = { 0x3e, 0x8d, 0x74, 0x26, 0x00 };
+static unsigned char *ideal_nop;
+
+static char rel_type_nop;
+
+static int (*make_nop)(void *map, size_t const offset);
+
+static int make_nop_x86(void *map, size_t const offset)
+{
+	uint32_t *ptr;
+	unsigned char *op;
+
+	/* Confirm we have 0xe8 0x0 0x0 0x0 0x0 */
+	ptr = map + offset;
+	if (*ptr != 0)
+		return -1;
+
+	op = map + offset - 1;
+	if (*op != 0xe8)
+		return -1;
+
+	/* convert to nop */
+	ulseek(fd_map, offset - 1, SEEK_SET);
+	uwrite(fd_map, ideal_nop, 5);
+	return 0;
+}
+
 /*
  * Get the whole file as a programming convenience in order to avoid
  * malloc+lseek+read+free of many pieces.  If successful, then mmap
@@ -301,7 +329,11 @@ do_file(char const *const fname)
 			w2(ehdr->e_machine), fname);
 		fail_file();
 		break;
-	case EM_386:	 reltype = R_386_32;                   break;
+	case EM_386:
+		reltype = R_386_32;
+		make_nop = make_nop_x86;
+		ideal_nop = ideal_nop5_x86_32;
+		break;
 	case EM_ARM:	 reltype = R_ARM_ABS32;
 			 altmcount = "__gnu_mcount_nc";
 			 break;
@@ -312,7 +344,11 @@ do_file(char const *const fname)
 	case EM_S390:    /* reltype: e_class    */ gpfx = '_'; break;
 	case EM_SH:	 reltype = R_SH_DIR32;                 break;
 	case EM_SPARCV9: reltype = R_SPARC_64;     gpfx = '_'; break;
-	case EM_X86_64:	 reltype = R_X86_64_64;                break;
+	case EM_X86_64:
+		make_nop = make_nop_x86;
+		ideal_nop = ideal_nop5_x86_64;
+		reltype = R_X86_64_64;
+		break;
 	}  /* end switch */
 
 	switch (ehdr->e_ident[EI_CLASS]) {