[PATCH] kprobe/ftrace: bail out if ftrace was killed

Masami Hiramatsu (Google) mhiramat at kernel.org
Mon Apr 29 06:48:03 PDT 2024


Hi Stephen,

On Fri, 26 Apr 2024 15:58:34 -0700
Stephen Brennan <stephen.s.brennan at oracle.com> wrote:

> If an error happens in ftrace, ftrace_kill() will prevent disarming
> kprobes. Eventually, the ftrace_ops associated with the kprobes will be
> freed, yet the kprobes will still be active, and when triggered, they
> will use the freed memory, likely resulting in a page fault and panic.

Hmm, indeed.

> 
> This behavior can be reproduced quite easily, by creating a kprobe and
> then triggering a ftrace_kill(). For simplicity, we can simulate an
> ftrace error with a kernel module like [1]:
> 
> [1]: https://github.com/brenns10/kernel_stuff/tree/master/ftrace_killer
> 
>   sudo perf probe --add commit_creds
>   sudo perf trace -e probe:commit_creds
>   # In another terminal
>   make
>   sudo insmod ftrace_killer.ko  # calls ftrace_kill(), simulating bug
>   # Back to perf terminal
>   # ctrl-c
>   sudo perf probe --del commit_creds
> 
> After a short period, a page fault and panic would occur as the kprobe
> continues to execute and uses the freed ftrace_ops. While ftrace_kill()
> is supposed to be used only in extreme circumstances, it is invoked in
> FTRACE_WARN_ON() and so there are many places where an unexpected bug
> could be triggered, yet the system may continue operating, possibly
> without the administrator noticing. If ftrace_kill() does not panic the
> system, then we should do everything we can to continue operating,
> rather than leave a ticking time bomb.

OK, the patch looks good to me.

Acked-by: Masami Hiramatsu (Google) <mhiramat at kernel.org>

Thanks!

> 
> Signed-off-by: Stephen Brennan <stephen.s.brennan at oracle.com>
> ---
> 
> Apologies for the wide net cast here. I recognize that a change like this
> may need to be split up and go through arch-specific trees. I hoped to get
> feedback on the patch itself. If it's satisfactory and the architecture
> maintainers prefer it split out, I'm glad to do it. Thanks!
> 
>  arch/csky/kernel/probes/ftrace.c     | 3 +++
>  arch/loongarch/kernel/ftrace_dyn.c   | 3 +++
>  arch/parisc/kernel/ftrace.c          | 3 +++
>  arch/powerpc/kernel/kprobes-ftrace.c | 3 +++
>  arch/riscv/kernel/probes/ftrace.c    | 3 +++
>  arch/s390/kernel/ftrace.c            | 3 +++
>  arch/x86/kernel/kprobes/ftrace.c     | 3 +++
>  include/linux/ftrace.h               | 2 ++
>  8 files changed, 23 insertions(+)
> 
> diff --git a/arch/csky/kernel/probes/ftrace.c b/arch/csky/kernel/probes/ftrace.c
> index 834cffcfbce3..3931bf9f707b 100644
> --- a/arch/csky/kernel/probes/ftrace.c
> +++ b/arch/csky/kernel/probes/ftrace.c
> @@ -12,6 +12,9 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
>  	struct kprobe_ctlblk *kcb;
>  	struct pt_regs *regs;
>  
> +	if (unlikely(ftrace_is_dead()))
> +		return;
> +
>  	bit = ftrace_test_recursion_trylock(ip, parent_ip);
>  	if (bit < 0)
>  		return;
> diff --git a/arch/loongarch/kernel/ftrace_dyn.c b/arch/loongarch/kernel/ftrace_dyn.c
> index 73858c9029cc..82c952cb5be0 100644
> --- a/arch/loongarch/kernel/ftrace_dyn.c
> +++ b/arch/loongarch/kernel/ftrace_dyn.c
> @@ -287,6 +287,9 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
>  	struct kprobe *p;
>  	struct kprobe_ctlblk *kcb;
>  
> +	if (unlikely(ftrace_is_dead()))
> +		return;
> +
>  	bit = ftrace_test_recursion_trylock(ip, parent_ip);
>  	if (bit < 0)
>  		return;
> diff --git a/arch/parisc/kernel/ftrace.c b/arch/parisc/kernel/ftrace.c
> index 621a4b386ae4..3660834f54c3 100644
> --- a/arch/parisc/kernel/ftrace.c
> +++ b/arch/parisc/kernel/ftrace.c
> @@ -206,6 +206,9 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
>  	struct kprobe *p;
>  	int bit;
>  
> +	if (unlikely(ftrace_is_dead()))
> +		return;
> +
>  	bit = ftrace_test_recursion_trylock(ip, parent_ip);
>  	if (bit < 0)
>  		return;
> diff --git a/arch/powerpc/kernel/kprobes-ftrace.c b/arch/powerpc/kernel/kprobes-ftrace.c
> index 072ebe7f290b..85eb55aa1457 100644
> --- a/arch/powerpc/kernel/kprobes-ftrace.c
> +++ b/arch/powerpc/kernel/kprobes-ftrace.c
> @@ -21,6 +21,9 @@ void kprobe_ftrace_handler(unsigned long nip, unsigned long parent_nip,
>  	struct pt_regs *regs;
>  	int bit;
>  
> +	if (unlikely(ftrace_is_dead()))
> +		return;
> +
>  	bit = ftrace_test_recursion_trylock(nip, parent_nip);
>  	if (bit < 0)
>  		return;
> diff --git a/arch/riscv/kernel/probes/ftrace.c b/arch/riscv/kernel/probes/ftrace.c
> index 7142ec42e889..8814fbe4c888 100644
> --- a/arch/riscv/kernel/probes/ftrace.c
> +++ b/arch/riscv/kernel/probes/ftrace.c
> @@ -11,6 +11,9 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
>  	struct kprobe_ctlblk *kcb;
>  	int bit;
>  
> +	if (unlikely(ftrace_is_dead()))
> +		return;
> +
>  	bit = ftrace_test_recursion_trylock(ip, parent_ip);
>  	if (bit < 0)
>  		return;
> diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c
> index c46381ea04ec..ccbe8ccf945b 100644
> --- a/arch/s390/kernel/ftrace.c
> +++ b/arch/s390/kernel/ftrace.c
> @@ -296,6 +296,9 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
>  	struct kprobe *p;
>  	int bit;
>  
> +	if (unlikely(ftrace_is_dead()))
> +		return;
> +
>  	bit = ftrace_test_recursion_trylock(ip, parent_ip);
>  	if (bit < 0)
>  		return;
> diff --git a/arch/x86/kernel/kprobes/ftrace.c b/arch/x86/kernel/kprobes/ftrace.c
> index dd2ec14adb77..c73f9ab7ff50 100644
> --- a/arch/x86/kernel/kprobes/ftrace.c
> +++ b/arch/x86/kernel/kprobes/ftrace.c
> @@ -21,6 +21,9 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
>  	struct kprobe_ctlblk *kcb;
>  	int bit;
>  
> +	if (unlikely(ftrace_is_dead()))
> +		return;
> +
>  	bit = ftrace_test_recursion_trylock(ip, parent_ip);
>  	if (bit < 0)
>  		return;
> diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
> index 54d53f345d14..ba83e99c1fbe 100644
> --- a/include/linux/ftrace.h
> +++ b/include/linux/ftrace.h
> @@ -399,6 +399,7 @@ int ftrace_lookup_symbols(const char **sorted_syms, size_t cnt, unsigned long *a
>  #define register_ftrace_function(ops) ({ 0; })
>  #define unregister_ftrace_function(ops) ({ 0; })
>  static inline void ftrace_kill(void) { }
> +static inline int ftrace_is_dead(void) { return 0; }
>  static inline void ftrace_free_init_mem(void) { }
>  static inline void ftrace_free_mem(struct module *mod, void *start, void *end) { }
>  static inline int ftrace_lookup_symbols(const char **sorted_syms, size_t cnt, unsigned long *addrs)
> @@ -914,6 +915,7 @@ static inline bool is_ftrace_trampoline(unsigned long addr)
>  
>  /* totally disable ftrace - can not re-enable after this */
>  void ftrace_kill(void);
> +int ftrace_is_dead(void);
>  
>  static inline void tracer_disable(void)
>  {
> -- 
> 2.39.3
> 


-- 
Masami Hiramatsu (Google) <mhiramat at kernel.org>



More information about the linux-riscv mailing list