powerpc: ftrace, do nothing in mcount call for dyn ftrace

Impact: quicken mcount calls that are not replaced by dyn ftrace

Dynamic ftrace no longer does on the fly recording of mcount locations.
The mcount locations are now found at compile time. The mcount
function no longer needs to store registers and call a stub function.
It can now just simply return.

Since there are some functions that do not get converted to a nop
(.init sections and other code that may disappear), this patch should
help speed up that code.

Also, the stub for mcount on PowerPC 32 can not be a simple branch
link register like it is on PowerPC 64. According to the ABI specification:

"The _mcount routine is required to restore the link register from
 the stack so that the profiling code can be inserted transparently,
 whether or not the profiled function saves the link register itself."

This means that we must restore the link register that was used
to make the call to mcount.  The minimal mcount function for PPC32
ends up being:

 mcount:
        mflr    r0
        mtctr   r0
        lwz     r0, 4(r1)
        mtlr    r0
        bctr

Where we move the link register used to call mcount into the
ctr register, and then restore the link register from the stack.
Then we use the ctr register to jump back to the mcount caller.
The r0 register is free for us to use.
Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

arch/powerpc/kernel/entry_32.S

@@ -1162,39 +1162,17 @@ machine_check_in_rtas:
 #ifdef CONFIG_DYNAMIC_FTRACE
 _GLOBAL(mcount)
 _GLOBAL(_mcount)
-	stwu	r1,-48(r1)
-	stw	r3, 12(r1)
-	stw	r4, 16(r1)
-	stw	r5, 20(r1)
-	stw	r6, 24(r1)
-	mflr	r3
-	stw	r7, 28(r1)
-	mfcr	r5
-	stw	r8, 32(r1)
-	stw	r9, 36(r1)
-	stw	r10,40(r1)
-	stw	r3, 44(r1)
-	stw	r5, 8(r1)
-	subi	r3, r3, MCOUNT_INSN_SIZE
-	.globl mcount_call
-mcount_call:
-	bl	ftrace_stub
-	nop
-	lwz	r6, 8(r1)
-	lwz	r0, 44(r1)
-	lwz	r3, 12(r1)
+	/*
+	 * It is required that _mcount on PPC32 must preserve the
+	 * link register. But we have r0 to play with. We use r0
+	 * to push the return address back to the caller of mcount
+	 * into the ctr register, restore the link register and
+	 * then jump back using the ctr register.
+	 */
+	mflr	r0
 	mtctr	r0
-	lwz	r4, 16(r1)
-	mtcr	r6
-	lwz	r5, 20(r1)
-	lwz	r6, 24(r1)
-	lwz	r0, 52(r1)
-	lwz	r7, 28(r1)
-	lwz	r8, 32(r1)
+	lwz	r0, 4(r1)
 	mtlr	r0
-	lwz	r9, 36(r1)
-	lwz	r10,40(r1)
-	addi	r1, r1, 48
 	bctr
 
 _GLOBAL(ftrace_caller)

arch/powerpc/kernel/entry_64.S

@@ -888,18 +888,6 @@ _GLOBAL(enter_prom)
 #ifdef CONFIG_DYNAMIC_FTRACE
 _GLOBAL(mcount)
 _GLOBAL(_mcount)
-	/* Taken from output of objdump from lib64/glibc */
-	mflr	r3
-	stdu	r1, -112(r1)
-	std	r3, 128(r1)
-	subi	r3, r3, MCOUNT_INSN_SIZE
-	.globl mcount_call
-mcount_call:
-	bl	ftrace_stub
-	nop
-	ld	r0, 128(r1)
-	mtlr	r0
-	addi	r1, r1, 112
 	blr
 
 _GLOBAL(ftrace_caller)