[for-next][PATCH 11/13] fprobe: Introduce FPROBE_FL_KPROBE_SHARED flag for fprobe

[Steven Rostedt <rostedt@goodmis.org>]

From: Masami Hiramatsu <mhiramat@kernel.org>

Introduce FPROBE_FL_KPROBE_SHARED flag for sharing fprobe callback with
kprobes safely from the viewpoint of recursion.

Since the recursion safety of the fprobe (and ftrace) is a bit different
from the kprobes, this may cause an issue if user wants to run the same
code from the fprobe and the kprobes.

The kprobes has per-cpu 'current_kprobe' variable which protects the
kprobe handler from recursion in any case. On the other hand, the fprobe
uses only ftrace_test_recursion_trylock(), which will allow interrupt
context calls another (or same) fprobe during the fprobe user handler is
running.

This is not a matter in cases if the common callback shared among the
kprobes and the fprobe has its own recursion detection, or it can handle
the recursion in the different contexts (normal/interrupt/NMI.)
But if it relies on the 'current_kprobe' recursion lock, it has to check
kprobe_running() and use kprobe_busy_*() APIs.

Fprobe has FPROBE_FL_KPROBE_SHARED flag to do this. If your common callback
code will be shared with kprobes, please set FPROBE_FL_KPROBE_SHARED
*before* registering the fprobe, like;

 fprobe.flags = FPROBE_FL_KPROBE_SHARED;

 register_fprobe(&fprobe, "func*", NULL);

This will protect your common callback from the nested call.

Link: https://lkml.kernel.org/r/164735293127.1084943.15687374237275817599.stgit@devnote2

Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Andrii Nakryiko <andrii.nakryiko@gmail.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Martin KaFai Lau <kafai@fb.com>
Cc: Song Liu <songliubraving@fb.com>
Cc: Yonghong Song <yhs@fb.com>
Cc: John Fastabend <john.fastabend@gmail.com>
Cc: KP Singh <kpsingh@chromium.org>
Cc: "Naveen N . Rao" <naveen.n.rao@linux.ibm.com>
Cc: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
Cc: "David S . Miller" <davem@davemloft.net>
Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/linux/fprobe.h  | 12 ++++++++++++
 include/linux/kprobes.h |  3 +++
 kernel/trace/fprobe.c   | 19 ++++++++++++++++++-
 3 files changed, 33 insertions(+), 1 deletion(-)

diff --git a/include/linux/fprobe.h b/include/linux/fprobe.h
index 8eefec2b485e..1c2bde0ead73 100644
--- a/include/linux/fprobe.h
+++ b/include/linux/fprobe.h
@@ -34,13 +34,25 @@ struct fprobe {
 	void (*exit_handler)(struct fprobe *fp, unsigned long entry_ip, struct pt_regs *regs);
 };
 
+/* This fprobe is soft-disabled. */
 #define FPROBE_FL_DISABLED	1
 
+/*
+ * This fprobe handler will be shared with kprobes.
+ * This flag must be set before registering.
+ */
+#define FPROBE_FL_KPROBE_SHARED	2
+
 static inline bool fprobe_disabled(struct fprobe *fp)
 {
 	return (fp) ? fp->flags & FPROBE_FL_DISABLED : false;
 }
 
+static inline bool fprobe_shared_with_kprobes(struct fprobe *fp)
+{
+	return (fp) ? fp->flags & FPROBE_FL_KPROBE_SHARED : false;
+}
+
 #ifdef CONFIG_FPROBE
 int register_fprobe(struct fprobe *fp, const char *filter, const char *notfilter);
 int register_fprobe_ips(struct fprobe *fp, unsigned long *addrs, int num);
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 19b884353b15..5f1859836deb 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -427,6 +427,9 @@ static inline struct kprobe *kprobe_running(void)
 {
 	return NULL;
 }
+#define kprobe_busy_begin()	do {} while (0)
+#define kprobe_busy_end()	do {} while (0)
+
 static inline int register_kprobe(struct kprobe *p)
 {
 	return -EOPNOTSUPP;
diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c
index 38073632bfe4..8b2dd5b9dcd1 100644
--- a/kernel/trace/fprobe.c
+++ b/kernel/trace/fprobe.c
@@ -56,6 +56,20 @@ static void fprobe_handler(unsigned long ip, unsigned long parent_ip,
 }
 NOKPROBE_SYMBOL(fprobe_handler);
 
+static void 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);
+
+	if (unlikely(kprobe_running())) {
+		fp->nmissed++;
+		return;
+	}
+	kprobe_busy_begin();
+	fprobe_handler(ip, parent_ip, ops, fregs);
+	kprobe_busy_end();
+}
+
 static void fprobe_exit_handler(struct rethook_node *rh, void *data,
 				struct pt_regs *regs)
 {
@@ -110,7 +124,10 @@ static unsigned long *get_ftrace_locations(const char **syms, int num)
 static void fprobe_init(struct fprobe *fp)
 {
 	fp->nmissed = 0;
-	fp->ops.func = fprobe_handler;
+	if (fprobe_shared_with_kprobes(fp))
+		fp->ops.func = fprobe_kprobe_handler;
+	else
+		fp->ops.func = fprobe_handler;
 	fp->ops.flags |= FTRACE_OPS_FL_SAVE_REGS;
 }
 
-- 
2.35.1