[RFC PATCH v4 04/17] powerpc32/ftrace: Unify 32-bit and 64-bit ftrace entry code

[Naveen N Rao]

On 32-bit powerpc, gcc generates a three instruction sequence for
function profiling:
	mflr	r0
	stw	r0, 4(r1)
	bl	_mcount

On kernel boot, the call to _mcount() is nop-ed out, to be patched back
in when ftrace is actually enabled. The 'stw' instruction therefore is
not necessary unless ftrace is enabled. Nop it out during ftrace init.

When ftrace is enabled, we want the 'stw' so that stack unwinding works
properly. Perform the same within the ftrace handler, similar to 64-bit
powerpc.

Reviewed-by: Nicholas Piggin <npiggin@xxxxxxxxx>
Signed-off-by: Naveen N Rao <naveen@xxxxxxxxxx>
---
 arch/powerpc/kernel/trace/ftrace.c       | 6 ++++--
 arch/powerpc/kernel/trace/ftrace_entry.S | 4 ++--
 2 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c
index 2ef504700e8d..8c3e523e4f96 100644
--- a/arch/powerpc/kernel/trace/ftrace.c
+++ b/arch/powerpc/kernel/trace/ftrace.c
@@ -240,8 +240,10 @@ int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec)
 	} else if (IS_ENABLED(CONFIG_PPC32)) {
 		/* Expected sequence: 'mflr r0', 'stw r0,4(r1)', 'bl _mcount' */
 		ret = ftrace_validate_inst(ip - 8, ppc_inst(PPC_RAW_MFLR(_R0)));
-		if (!ret)
-			ret = ftrace_validate_inst(ip - 4, ppc_inst(PPC_RAW_STW(_R0, _R1, 4)));
+		if (ret)
+			return ret;
+		ret = ftrace_modify_code(ip - 4, ppc_inst(PPC_RAW_STW(_R0, _R1, 4)),
+					 ppc_inst(PPC_RAW_NOP()));
 	} else if (IS_ENABLED(CONFIG_MPROFILE_KERNEL)) {
 		/* Expected sequence: 'mflr r0', ['std r0,16(r1)'], 'bl _mcount' */
 		ret = ftrace_read_inst(ip - 4, &old);
diff --git a/arch/powerpc/kernel/trace/ftrace_entry.S b/arch/powerpc/kernel/trace/ftrace_entry.S
index 76dbe9fd2c0f..244a1c7bb1e8 100644
--- a/arch/powerpc/kernel/trace/ftrace_entry.S
+++ b/arch/powerpc/kernel/trace/ftrace_entry.S
@@ -33,6 +33,8 @@
  * and then arrange for the ftrace function to be called.
  */
 .macro	ftrace_regs_entry allregs
+	/* Save the original return address in A's stack frame */
+	PPC_STL		r0, LRSAVE(r1)
 	/* Create a minimal stack frame for representing B */
 	PPC_STLU	r1, -STACK_FRAME_MIN_SIZE(r1)
 
@@ -44,8 +46,6 @@
 	SAVE_GPRS(3, 10, r1)
 
 #ifdef CONFIG_PPC64
-	/* Save the original return address in A's stack frame */
-	std	r0, LRSAVE+SWITCH_FRAME_SIZE+STACK_FRAME_MIN_SIZE(r1)
 	/* Ok to continue? */
 	lbz	r3, PACA_FTRACE_ENABLED(r13)
 	cmpdi	r3, 0
-- 
2.45.2