[PATCH v3 0/2] arm64: Enable OPTPROBE for arm64

From: Qi Liu
Date: Tue Aug 10 2021 - 05:18:02 EST


This patch introduce optprobe for ARM64, using a branch instruction
to replace probed instruction.

The test result on Hip08 platform is shown here, and optprobe could
reduce the latency to 1/4 of normal kprobe

kprobe before optimized:
[280709.846380] do_empty returned 0 and took 1530 ns to execute
[280709.852057] do_empty returned 0 and took 550 ns to execute
[280709.857631] do_empty returned 0 and took 440 ns to execute
[280709.863215] do_empty returned 0 and took 380 ns to execute
[280709.868787] do_empty returned 0 and took 360 ns to execute
[280709.874362] do_empty returned 0 and took 340 ns to execute
[280709.879936] do_empty returned 0 and took 320 ns to execute
[280709.885505] do_empty returned 0 and took 300 ns to execute
[280709.891075] do_empty returned 0 and took 280 ns to execute
[280709.896646] do_empty returned 0 and took 290 ns to execute
[280709.902220] do_empty returned 0 and took 290 ns to execute
[280709.907807] do_empty returned 0 and took 290 ns to execute

optprobe:
[ 2965.964572] do_empty returned 0 and took 90 ns to execute
[ 2965.969952] do_empty returned 0 and took 80 ns to execute
[ 2965.975332] do_empty returned 0 and took 70 ns to execute
[ 2965.980714] do_empty returned 0 and took 60 ns to execute
[ 2965.986128] do_empty returned 0 and took 80 ns to execute
[ 2965.991507] do_empty returned 0 and took 70 ns to execute
[ 2965.996884] do_empty returned 0 and took 70 ns to execute
[ 2966.002262] do_empty returned 0 and took 80 ns to execute
[ 2966.007642] do_empty returned 0 and took 70 ns to execute
[ 2966.013020] do_empty returned 0 and took 70 ns to execute
[ 2966.018400] do_empty returned 0 and took 70 ns to execute
[ 2966.023779] do_empty returned 0 and took 70 ns to execute
[ 2966.029158] do_empty returned 0 and took 70 ns to execute

Changes since V2:
- Address the comments from Masami, prepare another writable buffer in
arch_prepare_optimized_kprobe()and build the trampoline code on it.
- Address the comments from Amit, move save_all_base_regs and
restore_all_base_regs to <asm/assembler.h>, as these two macros are reused
in optprobe.
- Link: https://lore.kernel.org/lkml/20210804060209.95817-1-liuqi115@xxxxxxxxxx/

Changes since V1:
- Address the comments from Masami, checks for all branch instructions, and
use aarch64_insn_patch_text_nosync() instead of aarch64_insn_patch_text()
in each probe.
- Link: https://lore.kernel.org/lkml/20210719122417.10355-1-liuqi115@xxxxxxxxxx/

Qi Liu (2):
arm64: assembler: Make save_all_base_regs and restore_all_base_regs common macros
arm64: kprobe: Enable OPTPROBE for arm64

arch/arm64/Kconfig | 1 +
arch/arm64/include/asm/assembler.h | 52 ++++
arch/arm64/include/asm/kprobes.h | 24 ++
arch/arm64/kernel/probes/Makefile | 2 +
arch/arm64/kernel/probes/kprobes.c | 19 +-
arch/arm64/kernel/probes/kprobes_trampoline.S | 52 ----
arch/arm64/kernel/probes/opt_arm64.c | 239 ++++++++++++++++++
.../arm64/kernel/probes/optprobe_trampoline.S | 37 +++
8 files changed, 371 insertions(+), 55 deletions(-)
create mode 100644 arch/arm64/kernel/probes/opt_arm64.c
create mode 100644 arch/arm64/kernel/probes/optprobe_trampoline.S

--
2.17.1