The gcc switch -mprofile-kernel, available for ppc64 on gcc > 4.8.5,
allows to call _mcount very early in the function, which low-level
ASM code and code patching functions need to consider.
Especially the link register and the parameter registers are still
alive and not yet saved into a new stack frame.

Signed-off-by: Torsten Duwe <redacted>
---
 arch/powerpc/kernel/entry_64.S  | 45 +++++++++++++++++++++++++++++++++++++++--
 arch/powerpc/kernel/ftrace.c    | 12 +++++++++--
 arch/powerpc/kernel/module_64.c | 14 +++++++++++++
 3 files changed, 67 insertions(+), 4 deletions(-)

diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index a94f155..e7cd043 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S

@@ -1206,7 +1206,12 @@ _GLOBAL(enter_prom)
 #ifdef CONFIG_DYNAMIC_FTRACE
 _GLOBAL(mcount)
 _GLOBAL(_mcount)
-	blr
+	std	r0,LRSAVE(r1) /* gcc6 does this _after_ this call _only_ */
+	mflr	r0
+	mtctr	r0
+	ld	r0,LRSAVE(r1)
+	mtlr	r0
+	bctr

@@ -1262,13 +1267,28 @@ _GLOBAL(ftrace_stub)
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 _GLOBAL(ftrace_graph_caller)
+#ifdef CC_USING_MPROFILE_KERNEL
+	/* with -mprofile-kernel, parameter regs are still alive at _mcount */
+	std	r10, 104(r1)
+	std	r9, 96(r1)
+	std	r8, 88(r1)
+	std	r7, 80(r1)
+	std	r6, 72(r1)
+	std	r5, 64(r1)
+	std	r4, 56(r1)
+	std	r3, 48(r1)
+	mfctr	r4		/* ftrace_caller has moved local addr here */
+	std	r4, 40(r1)
+	mflr	r3		/* ftrace_caller has restored LR from stack */
+#else
 	/* load r4 with local address */
 	ld	r4, 128(r1)
-	subi	r4, r4, MCOUNT_INSN_SIZE
 
 	/* Grab the LR out of the caller stack frame */
 	ld	r11, 112(r1)
 	ld	r3, 16(r11)
+#endif
+	subi	r4, r4, MCOUNT_INSN_SIZE
 
 	bl	prepare_ftrace_return
 	nop

@@ -1277,6 +1297,26 @@ _GLOBAL(ftrace_graph_caller)
 	 * prepare_ftrace_return gives us the address we divert to.
 	 * Change the LR in the callers stack frame to this.
 	 */
+
+#ifdef CC_USING_MPROFILE_KERNEL
+	mtlr	r3
+
+	ld	r0, 40(r1)
+	mtctr	r0
+	ld	r10, 104(r1)
+	ld	r9, 96(r1)
+	ld	r8, 88(r1)
+	ld	r7, 80(r1)
+	ld	r6, 72(r1)
+	ld	r5, 64(r1)
+	ld	r4, 56(r1)
+	ld	r3, 48(r1)
+
+	addi	r1, r1, 112
+	mflr	r0
+	std	r0, LRSAVE(r1)
+	bctr
+#else
 	ld	r11, 112(r1)
 	std	r3, 16(r11)
 

@@ -1284,6 +1324,7 @@ _GLOBAL(ftrace_graph_caller)
 	mtlr	r0
 	addi	r1, r1, 112
 	blr
+#endif
 
 _GLOBAL(return_to_handler)
 	/* need to save return values */

diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c
index 44d4d8e..080c525 100644
--- a/arch/powerpc/kernel/ftrace.c
+++ b/arch/powerpc/kernel/ftrace.c

@@ -306,11 +306,19 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 	 * The load offset is different depending on the ABI. For simplicity
 	 * just mask it out when doing the compare.
 	 */
+#ifndef CC_USING_MPROFILE_KERNEL
 	if ((op[0] != 0x48000008) || ((op[1] & 0xffff0000) != 0xe8410000)) {
-		pr_err("Unexpected call sequence: %x %x\n", op[0], op[1]);
+		pr_err("Unexpected call sequence at %p: %x %x\n",
+		ip, op[0], op[1]);
 		return -EINVAL;
 	}
-
+#else
+	/* look for patched "NOP" on ppc64 with -mprofile-kernel */
+	if (op[0] != 0x60000000) {

diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c
index 6838451..30f6be1 100644
--- a/arch/powerpc/kernel/module_64.c
+++ b/arch/powerpc/kernel/module_64.c

@@ -475,6 +475,20 @@ static unsigned long stub_for_addr(Elf64_Shdr *sechdrs,
 static int restore_r2(u32 *instruction, struct module *me)
 {
 	if (*instruction != PPC_INST_NOP) {
+#ifdef CC_USING_MPROFILE_KERNEL
+		/* -mprofile_kernel sequence starting with
+		 * mflr r0 and maybe std r0, LRSAVE(r1)
+		 */
+		if ((instruction[-3] == 0x7c0802a6 &&
+		    instruction[-2] == 0xf8010010) ||
+		    instruction[-2] == 0x7c0802a6) {
+			/* Nothing to be done here, it's an _mcount
+			 * call location and r2 will have to be
+			 * restored in the _mcount function.
+			 */
+			return 1;
+		};
+#endif