Once gcc is enhanced to optionally generate NOPs at the beginning
of each function, like the concept proven in
https://gcc.gnu.org/ml/gcc-patches/2016-04/msg01671.html
(sans the "fprintf (... pad_size);", which spoils the data structure
for kernel use), the generated pads can nicely be used to reroute
function calls for tracing/profiling, or live patching.

The pads look like
fffffc00081335f0 <hrtimer_init>:
fffffc00081335f0:       d503201f        nop
fffffc00081335f4:       d503201f        nop
fffffc00081335f8:       a9bd7bfd        stp     x29, x30, [sp,#-48]!
fffffc00081335fc:       910003fd        mov     x29, sp
[...]

This patch gets the pad locations from the compiler-generated
__prolog_pads_loc into the _mcount_loc array, and provides the
code patching functions to turn the pads at runtime into

fffffc00081335f0     mov     x9, x30
fffffc00081335f4     bl      0xfffffc00080a08c0 <ftrace_caller>
fffffc00081335f8     stp     x29, x30, [sp,#-48]!
fffffc00081335fc     mov     x29, sp

as well as an ftrace_caller that can handle these call sites.
Now ARCH_SUPPORTS_FTRACE_OPS as a benefit, and the graph caller
still works, too.

Signed-off-by: Li Bin <redacted>
Signed-off-by: Torsten Duwe <redacted>
---
 arch/arm64/Kconfig                |  1 +
 arch/arm64/Makefile               |  4 ++
 arch/arm64/include/asm/ftrace.h   |  8 ++++
 arch/arm64/kernel/Makefile        |  6 +--
 arch/arm64/kernel/entry-ftrace.S  | 89 +++++++++++++++++++++++++++++++++++++++
 arch/arm64/kernel/ftrace.c        | 43 +++++++++++++++++--
 include/asm-generic/vmlinux.lds.h |  2 +-
 include/linux/compiler.h          |  4 ++
 8 files changed, 150 insertions(+), 7 deletions(-)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 5a0a691..36a0e26 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig

@@ -72,6 +72,7 @@ config ARM64
 	select HAVE_DMA_API_DEBUG
 	select HAVE_DMA_CONTIGUOUS
 	select HAVE_DYNAMIC_FTRACE
+	select HAVE_DYNAMIC_FTRACE_WITH_REGS
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_FUNCTION_TRACER

diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 648a32c..e5e335c 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile

@@ -35,6 +35,10 @@ KBUILD_CFLAGS	+= -fno-asynchronous-unwind-tables
 KBUILD_CFLAGS	+= $(call cc-option, -mpc-relative-literal-loads)
 KBUILD_AFLAGS	+= $(lseinstr)
 
+ifeq ($(CONFIG_DYNAMIC_FTRACE_WITH_REGS), y)
+CC_FLAGS_FTRACE := -fprolog-pad=2 -DCC_USING_PROLOG_PAD
+endif
+