Re: [PATCH v5] arm64: implement KPROBES_ON_FTRACE

[Masami Hiramatsu]

Hi Jisheng,

On Thu, 22 Aug 2019 11:25:00 +0000
Jisheng Zhang <Jisheng.Zhang@xxxxxxxxxxxxx> wrote:

> KPROBES_ON_FTRACE avoids much of the overhead with regular kprobes as it
> eliminates the need for a trap, as well as the need to emulate or
> single-step instructions.
> 
> Tested on berlin arm64 platform.
> 
> ~ # mount -t debugfs debugfs /sys/kernel/debug/
> ~ # cd /sys/kernel/debug/
> /sys/kernel/debug # echo 'p _do_fork' > tracing/kprobe_events
> 
> before the patch:
> 
> /sys/kernel/debug # cat kprobes/list
> ffffff801009fe28  k  _do_fork+0x0    [DISABLED]
> 
> after the patch:
> 
> /sys/kernel/debug # cat kprobes/list
> ffffff801009ff54  k  _do_fork+0x4    [DISABLED][FTRACE]
> 
> Signed-off-by: Jisheng Zhang <Jisheng.Zhang@xxxxxxxxxxxxx>

Looks good to me.

Acked-by: Masami Hiramatsu <mhiramat@xxxxxxxxxx>

Thank you,

> ---
> 
> KPROBES_ON_FTRACE avoids much of the overhead with regular kprobes as it
> eliminates the need for a trap, as well as the need to emulate or
> single-step instructions.
> 
> Applied after arm64 FTRACE_WITH_REGS:
> http://lists.infradead.org/pipermail/linux-arm-kernel/2019-August/674404.html
> 
> Changes since v4:
>   - correct reg->pc: probed on foo, then pre_handler see foo+0x4, while
>     post_handler see foo+0x8
> 
> Changes since v3:
>   - move kprobe_lookup_name() and arch_kprobe_on_func_entry to ftrace.c since
>     we only want to choose the ftrace entry for KPROBES_ON_FTRACE.
>   - only choose ftrace entry if (addr && !offset)
> 
> Changes since v2:
>   - remove patch1, make it a single cleanup patch
>   - remove "This patch" in the change log
>   - implement arm64's kprobe_lookup_name() and arch_kprobe_on_func_entry instead
>     of patching the common kprobes code
> 
> Changes since v1:
>   - make the kprobes/x86: use instruction_pointer and instruction_pointer_set
>     as patch1
>   - add Masami's ACK to patch1
>   - add some description about KPROBES_ON_FTRACE and why we need it on
>     arm64
>   - correct the log before the patch
>   - remove the consolidation patch, make it as TODO
>   - only adjust kprobe's addr when KPROBE_FLAG_FTRACE is set
>   - if KPROBES_ON_FTRACE, ftrace_call_adjust() the kprobe's addr before
>     calling ftrace_location()
>   - update the kprobes-on-ftrace/arch-support.txt in doc
> 
>  .../debug/kprobes-on-ftrace/arch-support.txt  |  2 +-
>  arch/arm64/Kconfig                            |  1 +
>  arch/arm64/kernel/probes/Makefile             |  1 +
>  arch/arm64/kernel/probes/ftrace.c             | 83 +++++++++++++++++++
>  4 files changed, 86 insertions(+), 1 deletion(-)
>  create mode 100644 arch/arm64/kernel/probes/ftrace.c
> 
> diff --git a/Documentation/features/debug/kprobes-on-ftrace/arch-support.txt b/Documentation/features/debug/kprobes-on-ftrace/arch-support.txt
> index 68f266944d5f..e8358a38981c 100644
> --- a/Documentation/features/debug/kprobes-on-ftrace/arch-support.txt
> +++ b/Documentation/features/debug/kprobes-on-ftrace/arch-support.txt
> @@ -9,7 +9,7 @@
>      |       alpha: | TODO |
>      |         arc: | TODO |
>      |         arm: | TODO |
> -    |       arm64: | TODO |
> +    |       arm64: |  ok  |
>      |         c6x: | TODO |
>      |        csky: | TODO |
>      |       h8300: | TODO |
> diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
> index 663392d1eae2..928700f15e23 100644
> --- a/arch/arm64/Kconfig
> +++ b/arch/arm64/Kconfig
> @@ -167,6 +167,7 @@ config ARM64
>  	select HAVE_STACKPROTECTOR
>  	select HAVE_SYSCALL_TRACEPOINTS
>  	select HAVE_KPROBES
> +	select HAVE_KPROBES_ON_FTRACE
>  	select HAVE_KRETPROBES
>  	select HAVE_GENERIC_VDSO
>  	select IOMMU_DMA if IOMMU_SUPPORT
> diff --git a/arch/arm64/kernel/probes/Makefile b/arch/arm64/kernel/probes/Makefile
> index 8e4be92e25b1..4020cfc66564 100644
> --- a/arch/arm64/kernel/probes/Makefile
> +++ b/arch/arm64/kernel/probes/Makefile
> @@ -4,3 +4,4 @@ obj-$(CONFIG_KPROBES)		+= kprobes.o decode-insn.o	\
>  				   simulate-insn.o
>  obj-$(CONFIG_UPROBES)		+= uprobes.o decode-insn.o	\
>  				   simulate-insn.o
> +obj-$(CONFIG_KPROBES_ON_FTRACE)	+= ftrace.o
> diff --git a/arch/arm64/kernel/probes/ftrace.c b/arch/arm64/kernel/probes/ftrace.c
> new file mode 100644
> index 000000000000..9f80905f02fa
> --- /dev/null
> +++ b/arch/arm64/kernel/probes/ftrace.c
> @@ -0,0 +1,83 @@
> +// SPDX-License-Identifier: GPL-2.0-or-later
> +/*
> + * Dynamic Ftrace based Kprobes Optimization
> + *
> + * Copyright (C) Hitachi Ltd., 2012
> + * Copyright (C) 2019 Jisheng Zhang <jszhang@xxxxxxxxxx>
> + *		      Synaptics Incorporated
> + */
> +
> +#include <linux/kprobes.h>
> +
> +/* Ftrace callback handler for kprobes -- called under preepmt disabed */
> +void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
> +			   struct ftrace_ops *ops, struct pt_regs *regs)
> +{
> +	struct kprobe *p;
> +	struct kprobe_ctlblk *kcb;
> +
> +	/* Preempt is disabled by ftrace */
> +	p = get_kprobe((kprobe_opcode_t *)ip);
> +	if (unlikely(!p) || kprobe_disabled(p))
> +		return;
> +
> +	kcb = get_kprobe_ctlblk();
> +	if (kprobe_running()) {
> +		kprobes_inc_nmissed_count(p);
> +	} else {
> +		unsigned long orig_ip = instruction_pointer(regs);
> +
> +		instruction_pointer_set(regs, ip);
> +		__this_cpu_write(current_kprobe, p);
> +		kcb->kprobe_status = KPROBE_HIT_ACTIVE;
> +		if (!p->pre_handler || !p->pre_handler(p, regs)) {
> +			/*
> +			 * Emulate singlestep (and also recover regs->pc)
> +			 * as if there is a nop
> +			 */
> +			instruction_pointer_set(regs,
> +				(unsigned long)p->addr + MCOUNT_INSN_SIZE);
> +			if (unlikely(p->post_handler)) {
> +				kcb->kprobe_status = KPROBE_HIT_SSDONE;
> +				p->post_handler(p, regs, 0);
> +			}
> +			instruction_pointer_set(regs, orig_ip);
> +		}
> +		/*
> +		 * If pre_handler returns !0, it changes regs->pc. We have to
> +		 * skip emulating post_handler.
> +		 */
> +		__this_cpu_write(current_kprobe, NULL);
> +	}
> +}
> +NOKPROBE_SYMBOL(kprobe_ftrace_handler);
> +
> +kprobe_opcode_t *kprobe_lookup_name(const char *name, unsigned int offset)
> +{
> +	unsigned long addr = kallsyms_lookup_name(name);
> +
> +	if (addr && !offset) {
> +		unsigned long faddr;
> +		/*
> +		 * with -fpatchable-function-entry=2, the first 4 bytes is the
> +		 * LR saver, then the actual call insn. So ftrace location is
> +		 * always on the first 4 bytes offset.
> +		 */
> +		faddr = ftrace_location_range(addr,
> +					      addr + AARCH64_INSN_SIZE);
> +		if (faddr)
> +			return (kprobe_opcode_t *)faddr;
> +	}
> +	return (kprobe_opcode_t *)addr;
> +}
> +
> +bool arch_kprobe_on_func_entry(unsigned long offset)
> +{
> +	return offset <= AARCH64_INSN_SIZE;
> +}
> +
> +int arch_prepare_kprobe_ftrace(struct kprobe *p)
> +{
> +	p->ainsn.api.insn = NULL;
> +	return 0;
> +}
> -- 
> 2.23.0.rc1
> 


-- 
Masami Hiramatsu <mhiramat@xxxxxxxxxx>