[PATCH 0/1] powerpc: make mcount a stub for dynamic ftrace

[PATCH 0/1] powerpc: make mcount a stub for dynamic ftrace

[Steven Rostedt]

Paul,

I have one more patch. I added it to the end of the ppc/ftrace branch.
The new way of handling the finding of mcounts means we do not need
to do anything in the mcount call itself. It should just be a stub
and when ftrace is enabled, it will change the caller sites to call
something other than mcount.

The following patches are in:

  git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace.git

    branch: ppc/ftrace


Steven Rostedt (1):
      powerpc: ftrace, do nothing in mcount call for dyn ftrace

----
 arch/powerpc/kernel/entry_32.S |   35 +----------------------------------
 arch/powerpc/kernel/entry_64.S |   12 ------------
 2 files changed, 1 insertions(+), 46 deletions(-)

[PATCH 1/1] powerpc: ftrace, do nothing in mcount call for dyn ftrace

[Steven Rostedt]

From: Steven Rostedt <srostedt@redhat.com>

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.

Signed-off-by: Steven Rostedt <srostedt@redhat.com>
---
 arch/powerpc/kernel/entry_32.S |   35 +----------------------------------
 arch/powerpc/kernel/entry_64.S |   12 ------------
 2 files changed, 1 insertions(+), 46 deletions(-)

diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 7ecc0d1..d2c4035 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -1162,40 +1162,7 @@ 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)
-	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)
-	mtlr	r0
-	lwz	r9, 36(r1)
-	lwz	r10,40(r1)
-	addi	r1, r1, 48
-	bctr
+	blr
 
 _GLOBAL(ftrace_caller)
 	/* Based off of objdump optput from glibc */
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index e6d5284..b00982e 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/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)
-- 
1.5.6.5

-- 

Re: [PATCH 0/1] powerpc: make mcount a stub for dynamic ftrace

[Ingo Molnar]

* Steven Rostedt <rostedt@goodmis.org> wrote:

> Paul,
> 
> I have one more patch. I added it to the end of the ppc/ftrace 
> branch. The new way of handling the finding of mcounts means we do 
> not need to do anything in the mcount call itself. It should just be 
> a stub and when ftrace is enabled, it will change the caller sites 
> to call something other than mcount.
> 
> The following patches are in:
> 
>   git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace.git
> 
>     branch: ppc/ftrace

i've also pulled the ppc/ftrace branch into tip/tracing/powerpc, and 
added it to ftrace-next's linux-next integration rules.

So if Paul gives the green light that the commits have the right 
structure, we can freeze down the branch and the SHA1's and integrate 
it into ftrace-next. (which is integrated in linux-next after the 
powerpc tree so should be all fine in terms of merge ordering)

	Ingo