parisc: add dynamic ftrace

This patch implements dynamic ftrace for PA-RISC. The required mcount
call sequences can get pretty long, so instead of patching the
whole call sequence out of the functions, we are using
-fpatchable-function-entry from gcc. This puts a configurable amount of
NOPS before/at the start of the function. Taking do_sys_open() as example,
which would look like this when the call is patched out:

1036b248:       08 00 02 40     nop
1036b24c:       08 00 02 40     nop
1036b250:       08 00 02 40     nop
1036b254:       08 00 02 40     nop

1036b258 <do_sys_open>:
1036b258:       08 00 02 40     nop
1036b25c:       08 03 02 41     copy r3,r1
1036b260:       6b c2 3f d9     stw rp,-14(sp)
1036b264:       08 1e 02 43     copy sp,r3
1036b268:       6f c1 01 00     stw,ma r1,80(sp)

When ftrace gets enabled for this function the kernel will patch these
NOPs to:

1036b248:       10 19 57 20     <address of ftrace>
1036b24c:       6f c1 00 80     stw,ma r1,40(sp)
1036b250:       48 21 3f d1     ldw -18(r1),r1
1036b254:       e8 20 c0 02     bv,n r0(r1)

1036b258 <do_sys_open>:
1036b258:       e8 3f 1f df     b,l,n .-c,r1
1036b25c:       08 03 02 41     copy r3,r1
1036b260:       6b c2 3f d9     stw rp,-14(sp)
1036b264:       08 1e 02 43     copy sp,r3
1036b268:       6f c1 01 00     stw,ma r1,80(sp)

So the first NOP in do_sys_open() will be patched to jump backwards into
some minimal trampoline code which pushes a stackframe, saves r1 which
holds the return address, loads the address of the real ftrace function,
and branches to that location. For 64 Bit things are getting a bit more
complicated (and longer) because we must make sure that the address of
ftrace location is 8 byte aligned, and the offset passed to ldd for
fetching the address is 8 byte aligned as well.

Note that gcc has a bug which misplaces the function label, and needs a
patch to make dynamic ftrace work. See
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=90751 for details.

Signed-off-by: Sven Schnelle <svens@stackframe.org>
Signed-off-by: Helge Deller <deller@gmx.de>

1 files changed, 19 insertions, 1 deletions

diff --git a/arch/parisc/kernel/module.c b/arch/parisc/kernel/module.c
index df5d1a493197..eab964a8bf4b 100644
--- a/arch/parisc/kernel/module.c
+++ b/arch/parisc/kernel/module.c
@@ -858,6 +858,7 @@ int module_finalize(const Elf_Ehdr *hdr,
 	const char *strtab = NULL;
 	const Elf_Shdr *s;
 	char *secstrings;
+	int err, symindex = -1;
 	Elf_Sym *newptr, *oldptr;
 	Elf_Shdr *symhdr = NULL;
 #ifdef DEBUG
@@ -884,6 +885,7 @@ int module_finalize(const Elf_Ehdr *hdr,
 		if(sechdrs[i].sh_type == SHT_SYMTAB
 		   && (sechdrs[i].sh_flags & SHF_ALLOC)) {
 			int strindex = sechdrs[i].sh_link;
+			symindex = i;
 			/* FIXME: AWFUL HACK
 			 * The cast is to drop the const from
 			 * the sechdrs pointer */
@@ -939,8 +941,24 @@ int module_finalize(const Elf_Ehdr *hdr,
 		if (!strcmp(".altinstructions", secname))
 			/* patch .altinstructions */
 			apply_alternatives(aseg, aseg + s->sh_size, me->name);
-	}
 
+		/* For 32 bit kernels we're compiling modules with
+		 * -ffunction-sections so we must relocate the addresses in the
+		 *__mcount_loc section.
+		 */
+		if (symindex != -1 && !strcmp(secname, "__mcount_loc")) {
+			if (s->sh_type == SHT_REL)
+				err = apply_relocate((Elf_Shdr *)sechdrs,
+							strtab, symindex,
+							s - sechdrs, me);
+			else if (s->sh_type == SHT_RELA)
+				err = apply_relocate_add((Elf_Shdr *)sechdrs,
+							strtab, symindex,
+							s - sechdrs, me);
+			if (err)
+				return err;
+		}
+	}
 	return 0;
 }