[2/4] fprobe: make fprobe_kprobe_handler recursion free

Message ID 6c428b9f74090b2780b67ca498c45aa5e8c38c44.1684120990.git.zegao@tencent.com
State New
Headers
Series Make fpobe + rethook immune to recursion |

Commit Message

Ze Gao May 15, 2023, 3:26 a.m. UTC
  Current implementation calls kprobe related functions before doing
ftrace recursion check in fprobe_kprobe_handler, which opens door
to kernel crash due to stack recursion if preempt_count_{add, sub}
is traceable.

Refactor the common part out of fprobe_kprobe_handler and fprobe_
handler and call ftrace recursion detection at the very beginning,
and also mark these functions notrace so that the whole fprobe_k-
probe_handler is free from recusion. And

Signed-off-by: Ze Gao <zegao@tencent.com>
---
 kernel/trace/fprobe.c | 61 +++++++++++++++++++++++++++++++------------
 1 file changed, 45 insertions(+), 16 deletions(-)
  

Comments

Steven Rostedt May 16, 2023, 1:25 a.m. UTC | #1
On Mon, 15 May 2023 11:26:39 +0800
Ze Gao <zegao2021@gmail.com> wrote:

> Current implementation calls kprobe related functions before doing
> ftrace recursion check in fprobe_kprobe_handler, which opens door
> to kernel crash due to stack recursion if preempt_count_{add, sub}
> is traceable.
> 
> Refactor the common part out of fprobe_kprobe_handler and fprobe_
> handler and call ftrace recursion detection at the very beginning,
> and also mark these functions notrace so that the whole fprobe_k-
> probe_handler is free from recusion. And
> 
> Signed-off-by: Ze Gao <zegao@tencent.com>
> ---
>  kernel/trace/fprobe.c | 61 +++++++++++++++++++++++++++++++------------
>  1 file changed, 45 insertions(+), 16 deletions(-)
> 
> diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c
> index 9abb3905bc8e..ad9a36c87ad9 100644
> --- a/kernel/trace/fprobe.c
> +++ b/kernel/trace/fprobe.c
> @@ -20,30 +20,22 @@ struct fprobe_rethook_node {
>  	char data[];
>  };
>  
> -static void fprobe_handler(unsigned long ip, unsigned long parent_ip,
> -			   struct ftrace_ops *ops, struct ftrace_regs *fregs)
> +static inline notrace void __fprobe_handler(unsigned long ip, unsigned long


FYI, if you look in kernel/trace/Makefile you'll see:

ccflags-remove-$(CONFIG_FUNCTION_TRACER) += $(CC_FLAGS_FTRACE)

Which removes the flags to add tracing. So there's no reason to add
"notrace" here, as all functions in this directory are by default "notrace".

-- Steve


> +		parent_ip, struct ftrace_ops *ops, struct ftrace_regs *fregs)
>  {
>  	struct fprobe_rethook_node *fpr;
>  	struct rethook_node *rh = NULL;
>  	struct fprobe *fp;
>  	void *entry_data = NULL;
> -	int bit, ret;
> +	int ret;
>  
>  	fp = container_of(ops, struct fprobe, ops);
> -	if (fprobe_disabled(fp))
> -		return;
> -
> -	bit = ftrace_test_recursion_trylock(ip, parent_ip);
> -	if (bit < 0) {
> -		fp->nmissed++;
> -		return;
> -	}
>  
>  	if (fp->exit_handler) {
>  		rh = rethook_try_get(fp->rethook);
>  		if (!rh) {
>  			fp->nmissed++;
> -			goto out;
> +			return;
>  		}
>  		fpr = container_of(rh, struct fprobe_rethook_node, node);
>  		fpr->entry_ip = ip;
> @@ -61,23 +53,60 @@ static void fprobe_handler(unsigned long ip, unsigned long parent_ip,
>  		else
>  			rethook_hook(rh, ftrace_get_regs(fregs), true);
>  	}
>
  
Ze Gao May 16, 2023, 3:02 a.m. UTC | #2
Hi Steven,

On Tue, May 16, 2023 at 9:25 AM Steven Rostedt <rostedt@goodmis.org> wrote:
>
> On Mon, 15 May 2023 11:26:39 +0800
> Ze Gao <zegao2021@gmail.com> wrote:
>
> > Current implementation calls kprobe related functions before doing
> > ftrace recursion check in fprobe_kprobe_handler, which opens door
> > to kernel crash due to stack recursion if preempt_count_{add, sub}
> > is traceable.
> >
> > Refactor the common part out of fprobe_kprobe_handler and fprobe_
> > handler and call ftrace recursion detection at the very beginning,
> > and also mark these functions notrace so that the whole fprobe_k-
> > probe_handler is free from recusion. And
> >
> > Signed-off-by: Ze Gao <zegao@tencent.com>
> > ---
> >  kernel/trace/fprobe.c | 61 +++++++++++++++++++++++++++++++------------
> >  1 file changed, 45 insertions(+), 16 deletions(-)
> >
> > diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c
> > index 9abb3905bc8e..ad9a36c87ad9 100644
> > --- a/kernel/trace/fprobe.c
> > +++ b/kernel/trace/fprobe.c
> > @@ -20,30 +20,22 @@ struct fprobe_rethook_node {
> >       char data[];
> >  };
> >
> > -static void fprobe_handler(unsigned long ip, unsigned long parent_ip,
> > -                        struct ftrace_ops *ops, struct ftrace_regs *fregs)
> > +static inline notrace void __fprobe_handler(unsigned long ip, unsigned long
>
>
> FYI, if you look in kernel/trace/Makefile you'll see:
>
> ccflags-remove-$(CONFIG_FUNCTION_TRACER) += $(CC_FLAGS_FTRACE)
>
> Which removes the flags to add tracing. So there's no reason to add
> "notrace" here, as all functions in this directory are by default "notrace".

Thanks for your valuable info, which I missed before. I'll send v2 to
remove those
unnecessary notrace annotations, and use the same trick for rethook too.

BTW,  I think we can mark rethook routines decls notrace in
include/linux/rethook.h,
which helps to remind developers of other arch(s) this important info.
What do you think of it?

Regards,
Ze
  

Patch

diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c
index 9abb3905bc8e..ad9a36c87ad9 100644
--- a/kernel/trace/fprobe.c
+++ b/kernel/trace/fprobe.c
@@ -20,30 +20,22 @@  struct fprobe_rethook_node {
 	char data[];
 };
 
-static void fprobe_handler(unsigned long ip, unsigned long parent_ip,
-			   struct ftrace_ops *ops, struct ftrace_regs *fregs)
+static inline notrace void __fprobe_handler(unsigned long ip, unsigned long
+		parent_ip, struct ftrace_ops *ops, struct ftrace_regs *fregs)
 {
 	struct fprobe_rethook_node *fpr;
 	struct rethook_node *rh = NULL;
 	struct fprobe *fp;
 	void *entry_data = NULL;
-	int bit, ret;
+	int ret;
 
 	fp = container_of(ops, struct fprobe, ops);
-	if (fprobe_disabled(fp))
-		return;
-
-	bit = ftrace_test_recursion_trylock(ip, parent_ip);
-	if (bit < 0) {
-		fp->nmissed++;
-		return;
-	}
 
 	if (fp->exit_handler) {
 		rh = rethook_try_get(fp->rethook);
 		if (!rh) {
 			fp->nmissed++;
-			goto out;
+			return;
 		}
 		fpr = container_of(rh, struct fprobe_rethook_node, node);
 		fpr->entry_ip = ip;
@@ -61,23 +53,60 @@  static void fprobe_handler(unsigned long ip, unsigned long parent_ip,
 		else
 			rethook_hook(rh, ftrace_get_regs(fregs), true);
 	}
-out:
+}
+
+static void notrace fprobe_handler(unsigned long ip, unsigned long parent_ip,
+			   struct ftrace_ops *ops, struct ftrace_regs *fregs)
+{
+	struct fprobe *fp;
+	int bit;
+
+	fp = container_of(ops, struct fprobe, ops);
+	if (fprobe_disabled(fp))
+		return;
+
+	/* recursion detection has to go before any traceable function and
+	 * all functions before this point should be marked as notrace
+	 */
+	bit = ftrace_test_recursion_trylock(ip, parent_ip);
+	if (bit < 0) {
+		fp->nmissed++;
+		return;
+	}
+	__fprobe_handler(ip, parent_ip, ops, fregs);
 	ftrace_test_recursion_unlock(bit);
+
 }
 NOKPROBE_SYMBOL(fprobe_handler);
 
-static void fprobe_kprobe_handler(unsigned long ip, unsigned long parent_ip,
+static void notrace fprobe_kprobe_handler(unsigned long ip, unsigned long parent_ip,
 				  struct ftrace_ops *ops, struct ftrace_regs *fregs)
 {
-	struct fprobe *fp = container_of(ops, struct fprobe, ops);
+	struct fprobe *fp;
+	int bit;
+
+	fp = container_of(ops, struct fprobe, ops);
+	if (fprobe_disabled(fp))
+		return;
+
+	/* recursion detection has to go before any traceable function and
+	 * all functions called before this point should be marked as notrace
+	 */
+	bit = ftrace_test_recursion_trylock(ip, parent_ip);
+	if (bit < 0) {
+		fp->nmissed++;
+		return;
+	}
 
 	if (unlikely(kprobe_running())) {
 		fp->nmissed++;
 		return;
 	}
+
 	kprobe_busy_begin();
-	fprobe_handler(ip, parent_ip, ops, fregs);
+	__fprobe_handler(ip, parent_ip, ops, fregs);
 	kprobe_busy_end();
+	ftrace_test_recursion_unlock(bit);
 }
 
 static void fprobe_exit_handler(struct rethook_node *rh, void *data,